[2021-03-25 22:12:18 swin_base_patch4_window7_224] INFO: number of params: 87768224 [2021-03-25 22:12:18 swin_base_patch4_window7_224] INFO: number of GFLOPs: 15.418000384 [2021-03-25 22:12:19 swin_base_patch4_window7_224] INFO: no checkpoint found in , ignoring auto resume [2021-03-25 22:12:19 swin_base_patch4_window7_224] INFO: Start training [2021-03-25 22:12:26 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 0/1251] eta: 2:16:45 lr: 0.000001 loss: 7.0331 (7.0331) grad_norm: 1.9603 (1.9603) time: 6.5591 [2021-03-25 22:12:33 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 10/1251] eta: 0:26:37 lr: 0.000001 loss: 7.0550 (7.0548) grad_norm: 1.9603 (1.9758) time: 1.2872 [2021-03-25 22:12:40 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 20/1251] eta: 0:20:10 lr: 0.000002 loss: 7.0376 (7.0405) grad_norm: 1.9508 (1.9654) time: 0.7047 [2021-03-25 22:12:46 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 30/1251] eta: 0:17:48 lr: 0.000002 loss: 7.0101 (7.0270) grad_norm: 1.9320 (1.9585) time: 0.6482 [2021-03-25 22:12:53 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 40/1251] eta: 0:16:27 lr: 0.000003 loss: 6.9997 (7.0194) grad_norm: 1.9254 (1.9515) time: 0.6394 [2021-03-25 22:12:59 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 50/1251] eta: 0:15:36 lr: 0.000003 loss: 6.9997 (7.0178) grad_norm: 1.9169 (1.9388) time: 0.6314 [2021-03-25 22:13:05 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 60/1251] eta: 0:15:00 lr: 0.000003 loss: 6.9938 (7.0163) grad_norm: 1.8641 (1.9216) time: 0.6345 [2021-03-25 22:13:12 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 70/1251] eta: 0:14:33 lr: 0.000004 loss: 6.9846 (7.0130) grad_norm: 1.8448 (1.9090) time: 0.6388 [2021-03-25 22:13:18 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 80/1251] eta: 0:14:10 lr: 0.000004 loss: 6.9699 (7.0087) grad_norm: 1.7909 (1.8932) time: 0.6348 [2021-03-25 22:13:24 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 90/1251] eta: 0:13:51 lr: 0.000005 loss: 6.9646 (7.0057) grad_norm: 1.7555 (1.8745) time: 0.6305 [2021-03-25 22:13:31 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 100/1251] eta: 0:13:34 lr: 0.000005 loss: 6.9678 (7.0024) grad_norm: 1.6875 (1.8539) time: 0.6332 [2021-03-25 22:13:37 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 110/1251] eta: 0:13:20 lr: 0.000005 loss: 6.9697 (7.0000) grad_norm: 1.6255 (1.8308) time: 0.6388 [2021-03-25 22:13:44 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 120/1251] eta: 0:13:08 lr: 0.000006 loss: 6.9642 (6.9972) grad_norm: 1.5636 (1.8086) time: 0.6415 [2021-03-25 22:13:50 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 130/1251] eta: 0:12:55 lr: 0.000006 loss: 6.9566 (6.9941) grad_norm: 1.5170 (1.7848) time: 0.6327 [2021-03-25 22:13:56 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 140/1251] eta: 0:12:43 lr: 0.000007 loss: 6.9554 (6.9929) grad_norm: 1.4641 (1.7616) time: 0.6287 [2021-03-25 22:14:03 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 150/1251] eta: 0:12:32 lr: 0.000007 loss: 6.9554 (6.9902) grad_norm: 1.4464 (1.7386) time: 0.6300 [2021-03-25 22:14:09 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 160/1251] eta: 0:12:21 lr: 0.000007 loss: 6.9593 (6.9881) grad_norm: 1.3840 (1.7149) time: 0.6294 [2021-03-25 22:14:15 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 170/1251] eta: 0:12:12 lr: 0.000008 loss: 6.9557 (6.9858) grad_norm: 1.3341 (1.6916) time: 0.6316 [2021-03-25 22:14:21 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 180/1251] eta: 0:12:02 lr: 0.000008 loss: 6.9443 (6.9837) grad_norm: 1.2793 (1.6685) time: 0.6316 [2021-03-25 22:14:28 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 190/1251] eta: 0:11:53 lr: 0.000009 loss: 6.9362 (6.9811) grad_norm: 1.2398 (1.6450) time: 0.6315 [2021-03-25 22:14:34 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 200/1251] eta: 0:11:44 lr: 0.000009 loss: 6.9347 (6.9787) grad_norm: 1.2024 (1.6220) time: 0.6335 [2021-03-25 22:14:41 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 210/1251] eta: 0:11:36 lr: 0.000009 loss: 6.9331 (6.9763) grad_norm: 1.1526 (1.5995) time: 0.6398 [2021-03-25 22:14:47 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 220/1251] eta: 0:11:28 lr: 0.000010 loss: 6.9262 (6.9743) grad_norm: 1.1261 (1.5774) time: 0.6396 [2021-03-25 22:14:53 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 230/1251] eta: 0:11:20 lr: 0.000010 loss: 6.9296 (6.9723) grad_norm: 1.0913 (1.5559) time: 0.6339 [2021-03-25 22:15:00 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 240/1251] eta: 0:11:12 lr: 0.000011 loss: 6.9214 (6.9693) grad_norm: 1.0634 (1.5353) time: 0.6334 [2021-03-25 22:15:06 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 250/1251] eta: 0:11:04 lr: 0.000011 loss: 6.9086 (6.9669) grad_norm: 1.0464 (1.5157) time: 0.6330 [2021-03-25 22:15:12 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 260/1251] eta: 0:10:56 lr: 0.000011 loss: 6.9033 (6.9648) grad_norm: 1.0379 (1.4972) time: 0.6290 [2021-03-25 22:15:18 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 270/1251] eta: 0:10:48 lr: 0.000012 loss: 6.9018 (6.9626) grad_norm: 1.0259 (1.4795) time: 0.6259 [2021-03-25 22:15:25 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 280/1251] eta: 0:10:40 lr: 0.000012 loss: 6.9119 (6.9608) grad_norm: 0.9895 (1.4617) time: 0.6257 [2021-03-25 22:15:31 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 290/1251] eta: 0:10:32 lr: 0.000013 loss: 6.9176 (6.9591) grad_norm: 0.9800 (1.4449) time: 0.6212 [2021-03-25 22:15:37 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 300/1251] eta: 0:10:24 lr: 0.000013 loss: 6.9119 (6.9578) grad_norm: 0.9554 (1.4286) time: 0.6155 [2021-03-25 22:15:43 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 310/1251] eta: 0:10:16 lr: 0.000013 loss: 6.9021 (6.9560) grad_norm: 0.9453 (1.4127) time: 0.6134 [2021-03-25 22:15:49 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 320/1251] eta: 0:10:08 lr: 0.000014 loss: 6.8885 (6.9538) grad_norm: 0.9322 (1.3976) time: 0.6142 [2021-03-25 22:15:55 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 330/1251] eta: 0:10:01 lr: 0.000014 loss: 6.8762 (6.9516) grad_norm: 0.9178 (1.3835) time: 0.6133 [2021-03-25 22:16:02 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 340/1251] eta: 0:09:53 lr: 0.000015 loss: 6.8813 (6.9495) grad_norm: 0.9282 (1.3699) time: 0.6118 [2021-03-25 22:16:08 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 350/1251] eta: 0:09:46 lr: 0.000015 loss: 6.8832 (6.9477) grad_norm: 0.9280 (1.3573) time: 0.6173 [2021-03-25 22:16:14 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 360/1251] eta: 0:09:38 lr: 0.000015 loss: 6.8889 (6.9463) grad_norm: 0.9169 (1.3449) time: 0.6158 [2021-03-25 22:16:20 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 370/1251] eta: 0:09:31 lr: 0.000016 loss: 6.8792 (6.9444) grad_norm: 0.9059 (1.3329) time: 0.6096 [2021-03-25 22:16:26 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 380/1251] eta: 0:09:24 lr: 0.000016 loss: 6.8720 (6.9428) grad_norm: 0.8917 (1.3217) time: 0.6150 [2021-03-25 22:16:32 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 390/1251] eta: 0:09:17 lr: 0.000017 loss: 6.8866 (6.9411) grad_norm: 0.9064 (1.3112) time: 0.6199 [2021-03-25 22:16:38 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 400/1251] eta: 0:09:09 lr: 0.000017 loss: 6.8791 (6.9393) grad_norm: 0.9024 (1.3007) time: 0.6137 [2021-03-25 22:16:45 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 410/1251] eta: 0:09:02 lr: 0.000017 loss: 6.8762 (6.9380) grad_norm: 0.8900 (1.2908) time: 0.6109 [2021-03-25 22:16:51 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 420/1251] eta: 0:08:55 lr: 0.000018 loss: 6.8786 (6.9368) grad_norm: 0.8916 (1.2814) time: 0.6159 [2021-03-25 22:16:57 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 430/1251] eta: 0:08:48 lr: 0.000018 loss: 6.8812 (6.9354) grad_norm: 0.8887 (1.2724) time: 0.6170 [2021-03-25 22:17:03 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 440/1251] eta: 0:08:41 lr: 0.000019 loss: 6.8825 (6.9340) grad_norm: 0.8713 (1.2633) time: 0.6157 [2021-03-25 22:17:09 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 450/1251] eta: 0:08:34 lr: 0.000019 loss: 6.8846 (6.9329) grad_norm: 0.8679 (1.2548) time: 0.6144 [2021-03-25 22:17:15 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 460/1251] eta: 0:08:27 lr: 0.000019 loss: 6.8739 (6.9314) grad_norm: 0.8725 (1.2464) time: 0.6177 [2021-03-25 22:17:22 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 470/1251] eta: 0:08:21 lr: 0.000020 loss: 6.8609 (6.9299) grad_norm: 0.8605 (1.2384) time: 0.6178 [2021-03-25 22:17:28 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 480/1251] eta: 0:08:14 lr: 0.000020 loss: 6.8546 (6.9285) grad_norm: 0.8587 (1.2303) time: 0.6133 [2021-03-25 22:17:34 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 490/1251] eta: 0:08:07 lr: 0.000021 loss: 6.8639 (6.9274) grad_norm: 0.8490 (1.2226) time: 0.6153 [2021-03-25 22:17:40 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 500/1251] eta: 0:08:00 lr: 0.000021 loss: 6.8676 (6.9257) grad_norm: 0.8411 (1.2149) time: 0.6164 [2021-03-25 22:17:46 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 510/1251] eta: 0:07:53 lr: 0.000021 loss: 6.8661 (6.9245) grad_norm: 0.8411 (1.2074) time: 0.6167 [2021-03-25 22:17:52 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 520/1251] eta: 0:07:47 lr: 0.000022 loss: 6.8661 (6.9232) grad_norm: 0.8468 (1.2012) time: 0.6156 [2021-03-25 22:17:59 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 530/1251] eta: 0:07:40 lr: 0.000022 loss: 6.8556 (6.9214) grad_norm: 0.8769 (1.1948) time: 0.6151 [2021-03-25 22:18:05 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 540/1251] eta: 0:07:33 lr: 0.000023 loss: 6.8442 (6.9200) grad_norm: 0.8586 (1.1885) time: 0.6243 [2021-03-25 22:18:11 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 550/1251] eta: 0:07:27 lr: 0.000023 loss: 6.8552 (6.9189) grad_norm: 0.8589 (1.1825) time: 0.6192 [2021-03-25 22:18:17 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 560/1251] eta: 0:07:20 lr: 0.000023 loss: 6.8552 (6.9177) grad_norm: 0.8433 (1.1763) time: 0.6126 [2021-03-25 22:18:23 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 570/1251] eta: 0:07:14 lr: 0.000024 loss: 6.8358 (6.9161) grad_norm: 0.8351 (1.1707) time: 0.6224 [2021-03-25 22:18:30 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 580/1251] eta: 0:07:07 lr: 0.000024 loss: 6.8378 (6.9151) grad_norm: 0.8501 (1.1658) time: 0.6255 [2021-03-25 22:18:36 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 590/1251] eta: 0:07:00 lr: 0.000025 loss: 6.8551 (6.9140) grad_norm: 0.8921 (1.1614) time: 0.6225 [2021-03-25 22:18:42 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 600/1251] eta: 0:06:54 lr: 0.000025 loss: 6.8283 (6.9123) grad_norm: 0.8615 (1.1564) time: 0.6221 [2021-03-25 22:18:48 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 610/1251] eta: 0:06:47 lr: 0.000025 loss: 6.8282 (6.9111) grad_norm: 0.8724 (1.1525) time: 0.6196 [2021-03-25 22:18:55 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 620/1251] eta: 0:06:41 lr: 0.000026 loss: 6.8391 (6.9101) grad_norm: 0.8850 (1.1492) time: 0.6238 [2021-03-25 22:19:01 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 630/1251] eta: 0:06:34 lr: 0.000026 loss: 6.8600 (6.9096) grad_norm: 0.8660 (1.1446) time: 0.6253 [2021-03-25 22:19:07 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 640/1251] eta: 0:06:28 lr: 0.000027 loss: 6.8600 (6.9087) grad_norm: 0.8775 (1.1412) time: 0.6189 [2021-03-25 22:19:13 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 650/1251] eta: 0:06:21 lr: 0.000027 loss: 6.8266 (6.9075) grad_norm: 0.9179 (1.1397) time: 0.6186 [2021-03-25 22:19:19 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 660/1251] eta: 0:06:15 lr: 0.000027 loss: 6.8152 (6.9061) grad_norm: 0.9036 (1.1359) time: 0.6208 [2021-03-25 22:19:26 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 670/1251] eta: 0:06:08 lr: 0.000028 loss: 6.8169 (6.9049) grad_norm: 0.8967 (1.1347) time: 0.6205 [2021-03-25 22:19:32 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 680/1251] eta: 0:06:02 lr: 0.000028 loss: 6.8339 (6.9041) grad_norm: 0.9455 (1.1317) time: 0.6257 [2021-03-25 22:19:38 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 690/1251] eta: 0:05:56 lr: 0.000029 loss: 6.8372 (6.9029) grad_norm: 0.9184 (1.1288) time: 0.6252 [2021-03-25 22:19:44 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 700/1251] eta: 0:05:49 lr: 0.000029 loss: 6.8341 (6.9020) grad_norm: 0.9583 (1.1274) time: 0.6202 [2021-03-25 22:19:51 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 710/1251] eta: 0:05:43 lr: 0.000029 loss: 6.8288 (6.9008) grad_norm: 0.9998 (1.1269) time: 0.6265 [2021-03-25 22:19:57 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 720/1251] eta: 0:05:36 lr: 0.000030 loss: 6.8288 (6.9000) grad_norm: 1.0444 (1.1261) time: 0.6279 [2021-03-25 22:20:03 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 730/1251] eta: 0:05:30 lr: 0.000030 loss: 6.8457 (6.8992) grad_norm: 1.0153 (1.1257) time: 0.6245 [2021-03-25 22:20:09 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 740/1251] eta: 0:05:24 lr: 0.000031 loss: 6.8257 (6.8983) grad_norm: 1.0438 (1.1259) time: 0.6228 [2021-03-25 22:20:16 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 750/1251] eta: 0:05:17 lr: 0.000031 loss: 6.8245 (6.8974) grad_norm: 1.0957 (1.1255) time: 0.6249 [2021-03-25 22:20:22 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 760/1251] eta: 0:05:11 lr: 0.000031 loss: 6.8410 (6.8966) grad_norm: 1.1064 (1.1257) time: 0.6317 [2021-03-25 22:20:29 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 770/1251] eta: 0:05:05 lr: 0.000032 loss: 6.8410 (6.8957) grad_norm: 1.1485 (1.1266) time: 0.6485 [2021-03-25 22:20:35 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 780/1251] eta: 0:04:58 lr: 0.000032 loss: 6.8472 (6.8949) grad_norm: 1.1617 (1.1267) time: 0.6515 [2021-03-25 22:20:41 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 790/1251] eta: 0:04:52 lr: 0.000033 loss: 6.8137 (6.8935) grad_norm: 1.1714 (1.1281) time: 0.6348 [2021-03-25 22:20:48 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 800/1251] eta: 0:04:46 lr: 0.000033 loss: 6.8019 (6.8926) grad_norm: 1.2642 (1.1304) time: 0.6277 [2021-03-25 22:20:54 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 810/1251] eta: 0:04:39 lr: 0.000033 loss: 6.7766 (6.8908) grad_norm: 1.2545 (1.1315) time: 0.6303 [2021-03-25 22:21:00 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 820/1251] eta: 0:04:33 lr: 0.000034 loss: 6.7652 (6.8899) grad_norm: 1.2648 (1.1357) time: 0.6349 [2021-03-25 22:21:07 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 830/1251] eta: 0:04:27 lr: 0.000034 loss: 6.7846 (6.8885) grad_norm: 1.3183 (1.1361) time: 0.6386 [2021-03-25 22:21:13 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 840/1251] eta: 0:04:20 lr: 0.000035 loss: 6.7826 (6.8874) grad_norm: 1.2419 (1.1386) time: 0.6341 [2021-03-25 22:21:19 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 850/1251] eta: 0:04:14 lr: 0.000035 loss: 6.7880 (6.8862) grad_norm: 1.3313 (1.1445) time: 0.6336 [2021-03-25 22:21:26 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 860/1251] eta: 0:04:08 lr: 0.000035 loss: 6.7831 (6.8849) grad_norm: 1.2477 (1.1455) time: 0.6348 [2021-03-25 22:21:32 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 870/1251] eta: 0:04:01 lr: 0.000036 loss: 6.7798 (6.8839) grad_norm: 1.2436 (1.1478) time: 0.6326 [2021-03-25 22:21:38 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 880/1251] eta: 0:03:55 lr: 0.000036 loss: 6.7612 (6.8824) grad_norm: 1.3232 (1.1501) time: 0.6345 [2021-03-25 22:21:45 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 890/1251] eta: 0:03:48 lr: 0.000037 loss: 6.7392 (6.8806) grad_norm: 1.2137 (1.1512) time: 0.6350 [2021-03-25 22:21:51 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 900/1251] eta: 0:03:42 lr: 0.000037 loss: 6.7658 (6.8795) grad_norm: 1.2094 (1.1529) time: 0.6351 [2021-03-25 22:21:57 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 910/1251] eta: 0:03:36 lr: 0.000037 loss: 6.7835 (6.8784) grad_norm: 1.2454 (1.1553) time: 0.6363 [2021-03-25 22:22:04 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 920/1251] eta: 0:03:29 lr: 0.000038 loss: 6.7765 (6.8774) grad_norm: 1.2931 (1.1560) time: 0.6327 [2021-03-25 22:22:10 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 930/1251] eta: 0:03:23 lr: 0.000038 loss: 6.7883 (6.8765) grad_norm: 1.2542 (1.1582) time: 0.6337 [2021-03-25 22:22:16 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 940/1251] eta: 0:03:17 lr: 0.000039 loss: 6.7782 (6.8749) grad_norm: 1.3059 (1.1598) time: 0.6332 [2021-03-25 22:22:23 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 950/1251] eta: 0:03:10 lr: 0.000039 loss: 6.6734 (6.8727) grad_norm: 1.3455 (1.1624) time: 0.6313 [2021-03-25 22:22:29 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 960/1251] eta: 0:03:04 lr: 0.000039 loss: 6.6907 (6.8714) grad_norm: 1.4695 (1.1680) time: 0.6363 [2021-03-25 22:22:35 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 970/1251] eta: 0:02:58 lr: 0.000040 loss: 6.7459 (6.8702) grad_norm: 1.4531 (1.1703) time: 0.6361 [2021-03-25 22:22:42 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 980/1251] eta: 0:02:51 lr: 0.000040 loss: 6.7849 (6.8695) grad_norm: 1.3931 (1.1757) time: 0.6342 [2021-03-25 22:22:48 swin_base_patch4_window7_224] INFO: Epoch: [0] [ 990/1251] eta: 0:02:45 lr: 0.000041 loss: 6.7846 (6.8683) grad_norm: 1.3931 (1.1782) time: 0.6327 [2021-03-25 22:22:54 swin_base_patch4_window7_224] INFO: Epoch: [0] [1000/1251] eta: 0:02:39 lr: 0.000041 loss: 6.7604 (6.8670) grad_norm: 1.4034 (1.1813) time: 0.6329 [2021-03-25 22:23:01 swin_base_patch4_window7_224] INFO: Epoch: [0] [1010/1251] eta: 0:02:32 lr: 0.000041 loss: 6.7712 (6.8662) grad_norm: 1.4839 (1.1860) time: 0.6371 [2021-03-25 22:23:07 swin_base_patch4_window7_224] INFO: Epoch: [0] [1020/1251] eta: 0:02:26 lr: 0.000042 loss: 6.7490 (6.8649) grad_norm: 1.4288 (1.1887) time: 0.6371 [2021-03-25 22:23:14 swin_base_patch4_window7_224] INFO: Epoch: [0] [1030/1251] eta: 0:02:20 lr: 0.000042 loss: 6.7446 (6.8637) grad_norm: 1.5370 (1.1978) time: 0.6329 [2021-03-25 22:23:20 swin_base_patch4_window7_224] INFO: Epoch: [0] [1040/1251] eta: 0:02:13 lr: 0.000043 loss: 6.7512 (6.8627) grad_norm: 2.0053 (1.2038) time: 0.6323 [2021-03-25 22:23:26 swin_base_patch4_window7_224] INFO: Epoch: [0] [1050/1251] eta: 0:02:07 lr: 0.000043 loss: 6.7570 (6.8613) grad_norm: 1.6247 (1.2096) time: 0.6338 [2021-03-25 22:23:32 swin_base_patch4_window7_224] INFO: Epoch: [0] [1060/1251] eta: 0:02:01 lr: 0.000043 loss: 6.7487 (6.8603) grad_norm: 1.7320 (1.2149) time: 0.6326 [2021-03-25 22:23:39 swin_base_patch4_window7_224] INFO: Epoch: [0] [1070/1251] eta: 0:01:54 lr: 0.000044 loss: 6.7253 (6.8589) grad_norm: 1.5832 (1.2191) time: 0.6344 [2021-03-25 22:23:45 swin_base_patch4_window7_224] INFO: Epoch: [0] [1080/1251] eta: 0:01:48 lr: 0.000044 loss: 6.7220 (6.8576) grad_norm: 1.5661 (1.2232) time: 0.6356 [2021-03-25 22:23:52 swin_base_patch4_window7_224] INFO: Epoch: [0] [1090/1251] eta: 0:01:42 lr: 0.000045 loss: 6.6878 (6.8558) grad_norm: 1.7225 (1.2332) time: 0.6339 [2021-03-25 22:23:58 swin_base_patch4_window7_224] INFO: Epoch: [0] [1100/1251] eta: 0:01:35 lr: 0.000045 loss: 6.6878 (6.8542) grad_norm: 1.8518 (1.2380) time: 0.6308 [2021-03-25 22:24:04 swin_base_patch4_window7_224] INFO: Epoch: [0] [1110/1251] eta: 0:01:29 lr: 0.000045 loss: 6.7049 (6.8528) grad_norm: 1.7850 (1.2439) time: 0.6306 [2021-03-25 22:24:10 swin_base_patch4_window7_224] INFO: Epoch: [0] [1120/1251] eta: 0:01:23 lr: 0.000046 loss: 6.7153 (6.8516) grad_norm: 1.7456 (1.2479) time: 0.6318 [2021-03-25 22:24:17 swin_base_patch4_window7_224] INFO: Epoch: [0] [1130/1251] eta: 0:01:16 lr: 0.000046 loss: 6.7165 (6.8505) grad_norm: 1.7041 (1.2521) time: 0.6299 [2021-03-25 22:24:23 swin_base_patch4_window7_224] INFO: Epoch: [0] [1140/1251] eta: 0:01:10 lr: 0.000047 loss: 6.7038 (6.8488) grad_norm: 1.5242 (1.2542) time: 0.6287 [2021-03-25 22:24:29 swin_base_patch4_window7_224] INFO: Epoch: [0] [1150/1251] eta: 0:01:04 lr: 0.000047 loss: 6.6648 (6.8477) grad_norm: 1.4869 (1.2572) time: 0.6310 [2021-03-25 22:24:36 swin_base_patch4_window7_224] INFO: Epoch: [0] [1160/1251] eta: 0:00:57 lr: 0.000047 loss: 6.7123 (6.8463) grad_norm: 1.5806 (1.2640) time: 0.6359 [2021-03-25 22:24:42 swin_base_patch4_window7_224] INFO: Epoch: [0] [1170/1251] eta: 0:00:51 lr: 0.000048 loss: 6.7005 (6.8449) grad_norm: 1.9803 (1.2712) time: 0.6367 [2021-03-25 22:24:48 swin_base_patch4_window7_224] INFO: Epoch: [0] [1180/1251] eta: 0:00:45 lr: 0.000048 loss: 6.6834 (6.8437) grad_norm: 1.9378 (1.2761) time: 0.6309 [2021-03-25 22:24:55 swin_base_patch4_window7_224] INFO: Epoch: [0] [1190/1251] eta: 0:00:38 lr: 0.000049 loss: 6.6847 (6.8424) grad_norm: 1.8403 (1.2796) time: 0.6280 [2021-03-25 22:25:01 swin_base_patch4_window7_224] INFO: Epoch: [0] [1200/1251] eta: 0:00:32 lr: 0.000049 loss: 6.7179 (6.8411) grad_norm: 1.8403 (1.2855) time: 0.6351 [2021-03-25 22:25:07 swin_base_patch4_window7_224] INFO: Epoch: [0] [1210/1251] eta: 0:00:25 lr: 0.000049 loss: 6.7179 (6.8401) grad_norm: 2.0070 (1.2929) time: 0.6328 [2021-03-25 22:25:14 swin_base_patch4_window7_224] INFO: Epoch: [0] [1220/1251] eta: 0:00:19 lr: 0.000050 loss: 6.6361 (6.8387) grad_norm: 1.9431 (1.2970) time: 0.6290 [2021-03-25 22:25:20 swin_base_patch4_window7_224] INFO: Epoch: [0] [1230/1251] eta: 0:00:13 lr: 0.000050 loss: 6.6600 (6.8374) grad_norm: 1.9971 (1.3041) time: 0.6346 [2021-03-25 22:25:26 swin_base_patch4_window7_224] INFO: Epoch: [0] [1240/1251] eta: 0:00:06 lr: 0.000051 loss: 6.6765 (6.8362) grad_norm: 2.2686 (1.3128) time: 0.6353 [2021-03-25 22:25:33 swin_base_patch4_window7_224] INFO: Epoch: [0] [1250/1251] eta: 0:00:00 lr: 0.000051 loss: 6.6640 (6.8347) grad_norm: 1.8658 (1.3172) time: 0.6301 [2021-03-25 22:26:29 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:05 loss: 6.0962 (6.0962) acc1: 1.5625 (1.5625) acc5: 7.8125 (7.8125) [2021-03-25 22:26:31 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 6.2507 (6.2398) acc1: 1.5625 (2.2727) acc5: 6.2500 (6.5341) [2021-03-25 22:26:32 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 6.1985 (6.2242) acc1: 1.5625 (2.3065) acc5: 6.2500 (8.1101) [2021-03-25 22:26:34 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 6.1953 (6.2232) acc1: 1.5625 (2.1673) acc5: 9.3750 (8.1149) [2021-03-25 22:26:35 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 6.2157 (6.2262) acc1: 1.5625 (2.0960) acc5: 6.2500 (7.6982) [2021-03-25 22:26:36 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 6.2114 (6.2248) acc1: 1.5625 (2.2400) acc5: 6.2500 (7.6480) [2021-03-25 22:26:37 swin_base_patch4_window7_224] INFO: * Acc@1 2.122 Acc@5 7.268 loss 6.227 [2021-03-25 22:26:37 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 2.1% [2021-03-25 22:26:37 swin_base_patch4_window7_224] INFO: Max accuracy: 2.12% [2021-03-25 22:26:42 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 0/1251] eta: 1:39:10 lr: 0.000051 loss: 6.5338 (6.5338) grad_norm: 1.7390 (1.7390) time: 4.7565 [2021-03-25 22:26:48 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 10/1251] eta: 0:20:50 lr: 0.000051 loss: 6.6745 (6.6603) grad_norm: 1.7668 (1.8822) time: 1.0078 [2021-03-25 22:26:55 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 20/1251] eta: 0:17:01 lr: 0.000052 loss: 6.6745 (6.6649) grad_norm: 1.9056 (1.9342) time: 0.6335 [2021-03-25 22:27:01 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 30/1251] eta: 0:15:37 lr: 0.000052 loss: 6.6783 (6.6797) grad_norm: 2.0055 (1.9952) time: 0.6363 [2021-03-25 22:27:07 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 40/1251] eta: 0:14:50 lr: 0.000053 loss: 6.6664 (6.6777) grad_norm: 1.8306 (1.9360) time: 0.6365 [2021-03-25 22:27:14 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 50/1251] eta: 0:14:17 lr: 0.000053 loss: 6.6469 (6.6769) grad_norm: 1.8306 (1.9486) time: 0.6304 [2021-03-25 22:27:20 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 60/1251] eta: 0:13:56 lr: 0.000053 loss: 6.6209 (6.6672) grad_norm: 1.8677 (1.9352) time: 0.6330 [2021-03-25 22:27:26 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 70/1251] eta: 0:13:36 lr: 0.000054 loss: 6.5874 (6.6555) grad_norm: 1.8677 (1.9379) time: 0.6325 [2021-03-25 22:27:33 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 80/1251] eta: 0:13:21 lr: 0.000054 loss: 6.6210 (6.6567) grad_norm: 2.0254 (1.9857) time: 0.6310 [2021-03-25 22:27:39 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 90/1251] eta: 0:13:07 lr: 0.000055 loss: 6.6689 (6.6557) grad_norm: 2.1772 (2.0015) time: 0.6323 [2021-03-25 22:27:45 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 100/1251] eta: 0:12:57 lr: 0.000055 loss: 6.6693 (6.6591) grad_norm: 2.0399 (2.0366) time: 0.6389 [2021-03-25 22:27:52 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 110/1251] eta: 0:12:46 lr: 0.000055 loss: 6.6702 (6.6594) grad_norm: 2.1775 (2.0652) time: 0.6403 [2021-03-25 22:27:58 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 120/1251] eta: 0:12:36 lr: 0.000056 loss: 6.6702 (6.6599) grad_norm: 2.0552 (2.0561) time: 0.6360 [2021-03-25 22:28:04 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 130/1251] eta: 0:12:26 lr: 0.000056 loss: 6.6147 (6.6574) grad_norm: 2.0108 (2.0575) time: 0.6335 [2021-03-25 22:28:11 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 140/1251] eta: 0:12:17 lr: 0.000057 loss: 6.6059 (6.6513) grad_norm: 2.0670 (2.0594) time: 0.6300 [2021-03-25 22:28:17 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 150/1251] eta: 0:12:08 lr: 0.000057 loss: 6.6150 (6.6504) grad_norm: 2.0947 (2.0829) time: 0.6334 [2021-03-25 22:28:23 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 160/1251] eta: 0:11:59 lr: 0.000057 loss: 6.6489 (6.6523) grad_norm: 2.2373 (2.0962) time: 0.6298 [2021-03-25 22:28:30 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 170/1251] eta: 0:11:51 lr: 0.000058 loss: 6.6757 (6.6516) grad_norm: 1.9907 (2.0834) time: 0.6347 [2021-03-25 22:28:36 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 180/1251] eta: 0:11:43 lr: 0.000058 loss: 6.6339 (6.6497) grad_norm: 1.9907 (2.0850) time: 0.6339 [2021-03-25 22:28:42 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 190/1251] eta: 0:11:35 lr: 0.000059 loss: 6.6308 (6.6468) grad_norm: 1.9992 (2.0799) time: 0.6293 [2021-03-25 22:28:49 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 200/1251] eta: 0:11:27 lr: 0.000059 loss: 6.6394 (6.6450) grad_norm: 1.8901 (2.0675) time: 0.6358 [2021-03-25 22:28:55 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 210/1251] eta: 0:11:19 lr: 0.000059 loss: 6.6394 (6.6442) grad_norm: 1.7942 (2.0574) time: 0.6338 [2021-03-25 22:29:01 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 220/1251] eta: 0:11:12 lr: 0.000060 loss: 6.6293 (6.6434) grad_norm: 1.8839 (2.0556) time: 0.6275 [2021-03-25 22:29:08 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 230/1251] eta: 0:11:04 lr: 0.000060 loss: 6.6074 (6.6419) grad_norm: 1.8336 (2.0466) time: 0.6306 [2021-03-25 22:29:14 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 240/1251] eta: 0:10:57 lr: 0.000061 loss: 6.5679 (6.6390) grad_norm: 1.8336 (2.0546) time: 0.6346 [2021-03-25 22:29:20 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 250/1251] eta: 0:10:50 lr: 0.000061 loss: 6.5749 (6.6374) grad_norm: 1.9443 (2.0525) time: 0.6358 [2021-03-25 22:29:27 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 260/1251] eta: 0:10:43 lr: 0.000061 loss: 6.6568 (6.6384) grad_norm: 1.9295 (2.0532) time: 0.6316 [2021-03-25 22:29:33 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 270/1251] eta: 0:10:36 lr: 0.000062 loss: 6.6393 (6.6378) grad_norm: 1.9295 (2.0478) time: 0.6361 [2021-03-25 22:29:39 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 280/1251] eta: 0:10:29 lr: 0.000062 loss: 6.5915 (6.6369) grad_norm: 1.7716 (2.0370) time: 0.6449 [2021-03-25 22:29:46 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 290/1251] eta: 0:10:22 lr: 0.000063 loss: 6.5947 (6.6353) grad_norm: 1.9006 (2.0368) time: 0.6377 [2021-03-25 22:29:52 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 300/1251] eta: 0:10:15 lr: 0.000063 loss: 6.5869 (6.6332) grad_norm: 2.0587 (2.0368) time: 0.6327 [2021-03-25 22:29:58 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 310/1251] eta: 0:10:09 lr: 0.000063 loss: 6.5869 (6.6320) grad_norm: 1.8662 (2.0325) time: 0.6342 [2021-03-25 22:30:05 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 320/1251] eta: 0:10:02 lr: 0.000064 loss: 6.5513 (6.6297) grad_norm: 1.9032 (2.0365) time: 0.6329 [2021-03-25 22:30:11 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 330/1251] eta: 0:09:55 lr: 0.000064 loss: 6.5513 (6.6286) grad_norm: 1.7222 (2.0264) time: 0.6299 [2021-03-25 22:30:17 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 340/1251] eta: 0:09:48 lr: 0.000065 loss: 6.6028 (6.6290) grad_norm: 1.7512 (2.0254) time: 0.6307 [2021-03-25 22:30:24 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 350/1251] eta: 0:09:41 lr: 0.000065 loss: 6.6293 (6.6296) grad_norm: 1.7712 (2.0212) time: 0.6313 [2021-03-25 22:30:30 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 360/1251] eta: 0:09:34 lr: 0.000065 loss: 6.6356 (6.6296) grad_norm: 1.7712 (2.0199) time: 0.6264 [2021-03-25 22:30:36 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 370/1251] eta: 0:09:27 lr: 0.000066 loss: 6.6243 (6.6286) grad_norm: 2.1113 (2.0315) time: 0.6281 [2021-03-25 22:30:43 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 380/1251] eta: 0:09:20 lr: 0.000066 loss: 6.6254 (6.6288) grad_norm: 2.1113 (2.0301) time: 0.6319 [2021-03-25 22:30:49 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 390/1251] eta: 0:09:14 lr: 0.000067 loss: 6.6263 (6.6279) grad_norm: 1.7386 (2.0235) time: 0.6318 [2021-03-25 22:30:55 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 400/1251] eta: 0:09:07 lr: 0.000067 loss: 6.5479 (6.6234) grad_norm: 1.8184 (2.0246) time: 0.6276 [2021-03-25 22:31:01 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 410/1251] eta: 0:09:00 lr: 0.000067 loss: 6.4502 (6.6201) grad_norm: 1.8602 (2.0223) time: 0.6270 [2021-03-25 22:31:08 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 420/1251] eta: 0:08:54 lr: 0.000068 loss: 6.4816 (6.6191) grad_norm: 1.8669 (2.0284) time: 0.6366 [2021-03-25 22:31:14 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 430/1251] eta: 0:08:47 lr: 0.000068 loss: 6.6372 (6.6189) grad_norm: 1.9980 (2.0277) time: 0.6385 [2021-03-25 22:31:20 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 440/1251] eta: 0:08:41 lr: 0.000069 loss: 6.6305 (6.6185) grad_norm: 1.9518 (2.0270) time: 0.6322 [2021-03-25 22:31:27 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 450/1251] eta: 0:08:34 lr: 0.000069 loss: 6.6235 (6.6185) grad_norm: 2.0386 (2.0313) time: 0.6337 [2021-03-25 22:31:33 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 460/1251] eta: 0:08:27 lr: 0.000069 loss: 6.5858 (6.6177) grad_norm: 2.0373 (2.0301) time: 0.6359 [2021-03-25 22:31:40 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 470/1251] eta: 0:08:21 lr: 0.000070 loss: 6.5158 (6.6153) grad_norm: 1.8914 (2.0271) time: 0.6342 [2021-03-25 22:31:46 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 480/1251] eta: 0:08:14 lr: 0.000070 loss: 6.5873 (6.6160) grad_norm: 1.7887 (2.0263) time: 0.6386 [2021-03-25 22:31:52 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 490/1251] eta: 0:08:08 lr: 0.000071 loss: 6.5873 (6.6145) grad_norm: 1.9029 (2.0261) time: 0.6349 [2021-03-25 22:31:59 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 500/1251] eta: 0:08:01 lr: 0.000071 loss: 6.5337 (6.6132) grad_norm: 1.9193 (2.0290) time: 0.6297 [2021-03-25 22:32:05 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 510/1251] eta: 0:07:55 lr: 0.000071 loss: 6.5186 (6.6123) grad_norm: 2.0845 (2.0315) time: 0.6310 [2021-03-25 22:32:11 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 520/1251] eta: 0:07:48 lr: 0.000072 loss: 6.5496 (6.6122) grad_norm: 2.2344 (2.0347) time: 0.6313 [2021-03-25 22:32:18 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 530/1251] eta: 0:07:42 lr: 0.000072 loss: 6.6259 (6.6117) grad_norm: 2.1483 (2.0350) time: 0.6354 [2021-03-25 22:32:24 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 540/1251] eta: 0:07:35 lr: 0.000073 loss: 6.6256 (6.6107) grad_norm: 1.9828 (2.0339) time: 0.6336 [2021-03-25 22:32:30 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 550/1251] eta: 0:07:29 lr: 0.000073 loss: 6.5965 (6.6100) grad_norm: 1.9312 (2.0328) time: 0.6388 [2021-03-25 22:32:37 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 560/1251] eta: 0:07:22 lr: 0.000073 loss: 6.5965 (6.6092) grad_norm: 1.8892 (2.0337) time: 0.6401 [2021-03-25 22:32:43 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 570/1251] eta: 0:07:16 lr: 0.000074 loss: 6.5561 (6.6083) grad_norm: 1.8952 (2.0350) time: 0.6365 [2021-03-25 22:32:49 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 580/1251] eta: 0:07:09 lr: 0.000074 loss: 6.5561 (6.6079) grad_norm: 2.0419 (2.0362) time: 0.6377 [2021-03-25 22:32:56 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 590/1251] eta: 0:07:03 lr: 0.000075 loss: 6.5774 (6.6067) grad_norm: 2.0868 (2.0391) time: 0.6351 [2021-03-25 22:33:02 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 600/1251] eta: 0:06:56 lr: 0.000075 loss: 6.4903 (6.6046) grad_norm: 2.1899 (2.0422) time: 0.6357 [2021-03-25 22:33:09 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 610/1251] eta: 0:06:50 lr: 0.000075 loss: 6.5491 (6.6043) grad_norm: 2.1882 (2.0441) time: 0.6365 [2021-03-25 22:33:15 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 620/1251] eta: 0:06:44 lr: 0.000076 loss: 6.5740 (6.6022) grad_norm: 2.0849 (2.0447) time: 0.6387 [2021-03-25 22:33:21 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 630/1251] eta: 0:06:37 lr: 0.000076 loss: 6.5709 (6.6019) grad_norm: 2.0174 (2.0458) time: 0.6365 [2021-03-25 22:33:28 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 640/1251] eta: 0:06:31 lr: 0.000077 loss: 6.5675 (6.5994) grad_norm: 2.0571 (2.0486) time: 0.6369 [2021-03-25 22:33:34 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 650/1251] eta: 0:06:24 lr: 0.000077 loss: 6.4733 (6.5991) grad_norm: 2.0340 (2.0493) time: 0.6390 [2021-03-25 22:33:40 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 660/1251] eta: 0:06:18 lr: 0.000077 loss: 6.5917 (6.5992) grad_norm: 1.8656 (2.0454) time: 0.6403 [2021-03-25 22:33:47 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 670/1251] eta: 0:06:11 lr: 0.000078 loss: 6.5462 (6.5970) grad_norm: 1.7495 (2.0430) time: 0.6348 [2021-03-25 22:33:53 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 680/1251] eta: 0:06:05 lr: 0.000078 loss: 6.5217 (6.5955) grad_norm: 1.8824 (2.0438) time: 0.6323 [2021-03-25 22:34:00 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 690/1251] eta: 0:05:59 lr: 0.000079 loss: 6.4792 (6.5943) grad_norm: 1.9363 (2.0429) time: 0.6366 [2021-03-25 22:34:06 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 700/1251] eta: 0:05:52 lr: 0.000079 loss: 6.5035 (6.5928) grad_norm: 1.9325 (2.0423) time: 0.6381 [2021-03-25 22:34:12 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 710/1251] eta: 0:05:46 lr: 0.000079 loss: 6.5340 (6.5915) grad_norm: 2.0889 (2.0445) time: 0.6374 [2021-03-25 22:34:19 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 720/1251] eta: 0:05:39 lr: 0.000080 loss: 6.4694 (6.5892) grad_norm: 1.9476 (2.0427) time: 0.6367 [2021-03-25 22:34:25 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 730/1251] eta: 0:05:33 lr: 0.000080 loss: 6.4886 (6.5885) grad_norm: 1.8696 (2.0429) time: 0.6344 [2021-03-25 22:34:31 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 740/1251] eta: 0:05:26 lr: 0.000080 loss: 6.5081 (6.5876) grad_norm: 2.0346 (2.0452) time: 0.6343 [2021-03-25 22:34:38 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 750/1251] eta: 0:05:20 lr: 0.000081 loss: 6.4629 (6.5852) grad_norm: 2.0346 (2.0425) time: 0.6420 [2021-03-25 22:34:44 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 760/1251] eta: 0:05:14 lr: 0.000081 loss: 6.5097 (6.5856) grad_norm: 1.7609 (2.0422) time: 0.6420 [2021-03-25 22:34:51 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 770/1251] eta: 0:05:07 lr: 0.000082 loss: 6.5746 (6.5849) grad_norm: 2.1402 (2.0498) time: 0.6360 [2021-03-25 22:34:57 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 780/1251] eta: 0:05:01 lr: 0.000082 loss: 6.5940 (6.5850) grad_norm: 2.2901 (2.0512) time: 0.6352 [2021-03-25 22:35:03 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 790/1251] eta: 0:04:54 lr: 0.000082 loss: 6.5940 (6.5843) grad_norm: 2.0298 (2.0509) time: 0.6381 [2021-03-25 22:35:10 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 800/1251] eta: 0:04:48 lr: 0.000083 loss: 6.5129 (6.5832) grad_norm: 1.8797 (2.0498) time: 0.6355 [2021-03-25 22:35:16 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 810/1251] eta: 0:04:42 lr: 0.000083 loss: 6.5129 (6.5822) grad_norm: 1.8919 (2.0489) time: 0.6370 [2021-03-25 22:35:22 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 820/1251] eta: 0:04:35 lr: 0.000084 loss: 6.5120 (6.5813) grad_norm: 1.8717 (2.0470) time: 0.6379 [2021-03-25 22:35:29 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 830/1251] eta: 0:04:29 lr: 0.000084 loss: 6.4866 (6.5798) grad_norm: 1.8437 (2.0460) time: 0.6303 [2021-03-25 22:35:35 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 840/1251] eta: 0:04:22 lr: 0.000084 loss: 6.4838 (6.5792) grad_norm: 2.0855 (2.0515) time: 0.6286 [2021-03-25 22:35:41 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 850/1251] eta: 0:04:16 lr: 0.000085 loss: 6.4783 (6.5775) grad_norm: 2.0765 (2.0504) time: 0.6316 [2021-03-25 22:35:48 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 860/1251] eta: 0:04:09 lr: 0.000085 loss: 6.4569 (6.5767) grad_norm: 1.8092 (2.0488) time: 0.6322 [2021-03-25 22:35:54 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 870/1251] eta: 0:04:03 lr: 0.000086 loss: 6.4720 (6.5757) grad_norm: 2.0451 (2.0507) time: 0.6361 [2021-03-25 22:36:00 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 880/1251] eta: 0:03:57 lr: 0.000086 loss: 6.5034 (6.5754) grad_norm: 1.9861 (2.0490) time: 0.6324 [2021-03-25 22:36:07 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 890/1251] eta: 0:03:50 lr: 0.000086 loss: 6.5652 (6.5752) grad_norm: 1.8126 (2.0462) time: 0.6306 [2021-03-25 22:36:13 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 900/1251] eta: 0:03:44 lr: 0.000087 loss: 6.5364 (6.5741) grad_norm: 1.8069 (2.0447) time: 0.6356 [2021-03-25 22:36:19 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 910/1251] eta: 0:03:37 lr: 0.000087 loss: 6.5134 (6.5731) grad_norm: 1.8936 (2.0437) time: 0.6395 [2021-03-25 22:36:26 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 920/1251] eta: 0:03:31 lr: 0.000088 loss: 6.5207 (6.5725) grad_norm: 1.8142 (2.0413) time: 0.6418 [2021-03-25 22:36:32 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 930/1251] eta: 0:03:25 lr: 0.000088 loss: 6.5450 (6.5718) grad_norm: 1.9528 (2.0423) time: 0.6338 [2021-03-25 22:36:38 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 940/1251] eta: 0:03:18 lr: 0.000088 loss: 6.5961 (6.5718) grad_norm: 2.0947 (2.0453) time: 0.6309 [2021-03-25 22:36:45 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 950/1251] eta: 0:03:12 lr: 0.000089 loss: 6.5103 (6.5707) grad_norm: 2.1891 (2.0461) time: 0.6374 [2021-03-25 22:36:51 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 960/1251] eta: 0:03:05 lr: 0.000089 loss: 6.3910 (6.5695) grad_norm: 2.1891 (2.0493) time: 0.6350 [2021-03-25 22:36:57 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 970/1251] eta: 0:02:59 lr: 0.000090 loss: 6.4540 (6.5688) grad_norm: 2.2436 (2.0521) time: 0.6325 [2021-03-25 22:37:04 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 980/1251] eta: 0:02:53 lr: 0.000090 loss: 6.4522 (6.5673) grad_norm: 2.0269 (2.0511) time: 0.6335 [2021-03-25 22:37:10 swin_base_patch4_window7_224] INFO: Epoch: [1] [ 990/1251] eta: 0:02:46 lr: 0.000090 loss: 6.4522 (6.5660) grad_norm: 1.9598 (2.0529) time: 0.6363 [2021-03-25 22:37:17 swin_base_patch4_window7_224] INFO: Epoch: [1] [1000/1251] eta: 0:02:40 lr: 0.000091 loss: 6.4009 (6.5642) grad_norm: 2.0094 (2.0514) time: 0.6374 [2021-03-25 22:37:23 swin_base_patch4_window7_224] INFO: Epoch: [1] [1010/1251] eta: 0:02:33 lr: 0.000091 loss: 6.3858 (6.5629) grad_norm: 1.8618 (2.0493) time: 0.6345 [2021-03-25 22:37:29 swin_base_patch4_window7_224] INFO: Epoch: [1] [1020/1251] eta: 0:02:27 lr: 0.000092 loss: 6.4569 (6.5625) grad_norm: 1.8275 (2.0472) time: 0.6387 [2021-03-25 22:37:36 swin_base_patch4_window7_224] INFO: Epoch: [1] [1030/1251] eta: 0:02:21 lr: 0.000092 loss: 6.5116 (6.5623) grad_norm: 1.9026 (2.0480) time: 0.6353 [2021-03-25 22:37:42 swin_base_patch4_window7_224] INFO: Epoch: [1] [1040/1251] eta: 0:02:14 lr: 0.000092 loss: 6.5116 (6.5616) grad_norm: 1.9718 (2.0470) time: 0.6327 [2021-03-25 22:37:48 swin_base_patch4_window7_224] INFO: Epoch: [1] [1050/1251] eta: 0:02:08 lr: 0.000093 loss: 6.4046 (6.5600) grad_norm: 1.9263 (2.0461) time: 0.6369 [2021-03-25 22:37:55 swin_base_patch4_window7_224] INFO: Epoch: [1] [1060/1251] eta: 0:02:01 lr: 0.000093 loss: 6.4498 (6.5590) grad_norm: 1.9263 (2.0445) time: 0.6361 [2021-03-25 22:38:01 swin_base_patch4_window7_224] INFO: Epoch: [1] [1070/1251] eta: 0:01:55 lr: 0.000094 loss: 6.5440 (6.5593) grad_norm: 1.8134 (2.0421) time: 0.6321 [2021-03-25 22:38:07 swin_base_patch4_window7_224] INFO: Epoch: [1] [1080/1251] eta: 0:01:49 lr: 0.000094 loss: 6.5825 (6.5591) grad_norm: 1.7386 (2.0397) time: 0.6343 [2021-03-25 22:38:14 swin_base_patch4_window7_224] INFO: Epoch: [1] [1090/1251] eta: 0:01:42 lr: 0.000094 loss: 6.5602 (6.5584) grad_norm: 1.7338 (2.0375) time: 0.6317 [2021-03-25 22:38:20 swin_base_patch4_window7_224] INFO: Epoch: [1] [1100/1251] eta: 0:01:36 lr: 0.000095 loss: 6.4783 (6.5573) grad_norm: 1.7595 (2.0370) time: 0.6295 [2021-03-25 22:38:26 swin_base_patch4_window7_224] INFO: Epoch: [1] [1110/1251] eta: 0:01:29 lr: 0.000095 loss: 6.4192 (6.5567) grad_norm: 2.1834 (2.0386) time: 0.6340 [2021-03-25 22:38:33 swin_base_patch4_window7_224] INFO: Epoch: [1] [1120/1251] eta: 0:01:23 lr: 0.000096 loss: 6.4413 (6.5561) grad_norm: 1.9708 (2.0381) time: 0.6320 [2021-03-25 22:38:39 swin_base_patch4_window7_224] INFO: Epoch: [1] [1130/1251] eta: 0:01:17 lr: 0.000096 loss: 6.4757 (6.5557) grad_norm: 1.9012 (2.0367) time: 0.6351 [2021-03-25 22:38:45 swin_base_patch4_window7_224] INFO: Epoch: [1] [1140/1251] eta: 0:01:10 lr: 0.000096 loss: 6.4757 (6.5541) grad_norm: 1.8241 (2.0364) time: 0.6334 [2021-03-25 22:38:52 swin_base_patch4_window7_224] INFO: Epoch: [1] [1150/1251] eta: 0:01:04 lr: 0.000097 loss: 6.4248 (6.5531) grad_norm: 1.9467 (2.0367) time: 0.6289 [2021-03-25 22:38:58 swin_base_patch4_window7_224] INFO: Epoch: [1] [1160/1251] eta: 0:00:58 lr: 0.000097 loss: 6.5224 (6.5525) grad_norm: 2.1569 (2.0399) time: 0.6294 [2021-03-25 22:39:04 swin_base_patch4_window7_224] INFO: Epoch: [1] [1170/1251] eta: 0:00:51 lr: 0.000098 loss: 6.4184 (6.5511) grad_norm: 2.1530 (2.0400) time: 0.6304 [2021-03-25 22:39:11 swin_base_patch4_window7_224] INFO: Epoch: [1] [1180/1251] eta: 0:00:45 lr: 0.000098 loss: 6.4046 (6.5504) grad_norm: 2.0713 (2.0403) time: 0.6325 [2021-03-25 22:39:17 swin_base_patch4_window7_224] INFO: Epoch: [1] [1190/1251] eta: 0:00:38 lr: 0.000098 loss: 6.4784 (6.5496) grad_norm: 1.8801 (2.0386) time: 0.6304 [2021-03-25 22:39:23 swin_base_patch4_window7_224] INFO: Epoch: [1] [1200/1251] eta: 0:00:32 lr: 0.000099 loss: 6.4784 (6.5489) grad_norm: 1.6389 (2.0349) time: 0.6310 [2021-03-25 22:39:29 swin_base_patch4_window7_224] INFO: Epoch: [1] [1210/1251] eta: 0:00:26 lr: 0.000099 loss: 6.4201 (6.5482) grad_norm: 1.6562 (2.0334) time: 0.6291 [2021-03-25 22:39:36 swin_base_patch4_window7_224] INFO: Epoch: [1] [1220/1251] eta: 0:00:19 lr: 0.000100 loss: 6.3900 (6.5474) grad_norm: 1.9939 (2.0360) time: 0.6320 [2021-03-25 22:39:42 swin_base_patch4_window7_224] INFO: Epoch: [1] [1230/1251] eta: 0:00:13 lr: 0.000100 loss: 6.4281 (6.5464) grad_norm: 2.1542 (2.0374) time: 0.6346 [2021-03-25 22:39:48 swin_base_patch4_window7_224] INFO: Epoch: [1] [1240/1251] eta: 0:00:07 lr: 0.000100 loss: 6.4286 (6.5460) grad_norm: 2.0178 (2.0365) time: 0.6237 [2021-03-25 22:39:55 swin_base_patch4_window7_224] INFO: Epoch: [1] [1250/1251] eta: 0:00:00 lr: 0.000101 loss: 6.4193 (6.5449) grad_norm: 1.8404 (2.0339) time: 0.6277 [2021-03-25 22:39:59 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:39 loss: 5.3807 (5.3807) acc1: 9.3750 (9.3750) acc5: 26.5625 (26.5625) [2021-03-25 22:40:01 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 5.5610 (5.5488) acc1: 6.2500 (6.1080) acc5: 17.1875 (18.0398) [2021-03-25 22:40:04 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 5.6078 (5.6107) acc1: 4.6875 (5.8036) acc5: 17.1875 (16.9643) [2021-03-25 22:40:06 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 5.6194 (5.6133) acc1: 4.6875 (5.2923) acc5: 15.6250 (16.1794) [2021-03-25 22:40:07 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 5.6178 (5.6089) acc1: 4.6875 (5.3354) acc5: 15.6250 (16.1585) [2021-03-25 22:40:08 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 5.6315 (5.6088) acc1: 6.2500 (5.3440) acc5: 15.6250 (15.8720) [2021-03-25 22:40:10 swin_base_patch4_window7_224] INFO: * Acc@1 4.902 Acc@5 15.226 loss 5.613 [2021-03-25 22:40:10 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 4.9% [2021-03-25 22:40:10 swin_base_patch4_window7_224] INFO: Max accuracy: 4.90% [2021-03-25 22:40:15 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 0/1251] eta: 1:29:01 lr: 0.000101 loss: 6.2205 (6.2205) grad_norm: 1.9576 (1.9576) time: 4.2700 [2021-03-25 22:40:21 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 10/1251] eta: 0:20:14 lr: 0.000101 loss: 6.4306 (6.4144) grad_norm: 1.9730 (1.9800) time: 0.9786 [2021-03-25 22:40:27 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 20/1251] eta: 0:16:39 lr: 0.000102 loss: 6.5160 (6.4537) grad_norm: 1.9698 (1.9822) time: 0.6392 [2021-03-25 22:40:34 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 30/1251] eta: 0:15:20 lr: 0.000102 loss: 6.5160 (6.4545) grad_norm: 1.8551 (1.9482) time: 0.6305 [2021-03-25 22:40:40 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 40/1251] eta: 0:14:37 lr: 0.000102 loss: 6.4152 (6.4387) grad_norm: 1.6727 (1.8707) time: 0.6322 [2021-03-25 22:40:46 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 50/1251] eta: 0:14:07 lr: 0.000103 loss: 6.5091 (6.4538) grad_norm: 1.6693 (1.8587) time: 0.6314 [2021-03-25 22:40:53 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 60/1251] eta: 0:13:47 lr: 0.000103 loss: 6.5673 (6.4735) grad_norm: 1.9204 (1.8951) time: 0.6333 [2021-03-25 22:40:59 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 70/1251] eta: 0:13:30 lr: 0.000104 loss: 6.5225 (6.4796) grad_norm: 1.9358 (1.8942) time: 0.6367 [2021-03-25 22:41:05 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 80/1251] eta: 0:13:17 lr: 0.000104 loss: 6.4796 (6.4843) grad_norm: 1.9075 (1.8994) time: 0.6383 [2021-03-25 22:41:12 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 90/1251] eta: 0:13:04 lr: 0.000104 loss: 6.4244 (6.4729) grad_norm: 1.9360 (1.8998) time: 0.6387 [2021-03-25 22:41:18 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 100/1251] eta: 0:12:54 lr: 0.000105 loss: 6.4244 (6.4674) grad_norm: 1.7803 (1.8869) time: 0.6418 [2021-03-25 22:41:25 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 110/1251] eta: 0:12:44 lr: 0.000105 loss: 6.3817 (6.4556) grad_norm: 1.8792 (1.8959) time: 0.6418 [2021-03-25 22:41:31 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 120/1251] eta: 0:12:35 lr: 0.000106 loss: 6.3817 (6.4577) grad_norm: 1.7863 (1.8871) time: 0.6409 [2021-03-25 22:41:37 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 130/1251] eta: 0:12:25 lr: 0.000106 loss: 6.4781 (6.4579) grad_norm: 1.9296 (1.9104) time: 0.6405 [2021-03-25 22:41:44 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 140/1251] eta: 0:12:16 lr: 0.000106 loss: 6.5031 (6.4592) grad_norm: 1.9265 (1.8966) time: 0.6325 [2021-03-25 22:41:50 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 150/1251] eta: 0:12:07 lr: 0.000107 loss: 6.4875 (6.4489) grad_norm: 1.7442 (1.8903) time: 0.6287 [2021-03-25 22:41:56 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 160/1251] eta: 0:11:59 lr: 0.000107 loss: 6.4875 (6.4521) grad_norm: 1.7442 (1.8812) time: 0.6342 [2021-03-25 22:42:03 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 170/1251] eta: 0:11:50 lr: 0.000108 loss: 6.5057 (6.4534) grad_norm: 1.7768 (1.8792) time: 0.6346 [2021-03-25 22:42:09 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 180/1251] eta: 0:11:42 lr: 0.000108 loss: 6.5091 (6.4563) grad_norm: 1.7814 (1.8790) time: 0.6306 [2021-03-25 22:42:15 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 190/1251] eta: 0:11:34 lr: 0.000108 loss: 6.4637 (6.4536) grad_norm: 1.9189 (1.8843) time: 0.6334 [2021-03-25 22:42:22 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 200/1251] eta: 0:11:28 lr: 0.000109 loss: 6.4421 (6.4577) grad_norm: 1.9825 (1.8853) time: 0.6466 [2021-03-25 22:42:28 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 210/1251] eta: 0:11:20 lr: 0.000109 loss: 6.4759 (6.4581) grad_norm: 1.8913 (1.8876) time: 0.6453 [2021-03-25 22:42:35 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 220/1251] eta: 0:11:13 lr: 0.000110 loss: 6.4774 (6.4572) grad_norm: 1.8300 (1.8855) time: 0.6358 [2021-03-25 22:42:41 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 230/1251] eta: 0:11:06 lr: 0.000110 loss: 6.4951 (6.4569) grad_norm: 1.8300 (1.8865) time: 0.6386 [2021-03-25 22:42:47 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 240/1251] eta: 0:10:59 lr: 0.000110 loss: 6.3177 (6.4498) grad_norm: 1.8009 (1.8792) time: 0.6379 [2021-03-25 22:42:54 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 250/1251] eta: 0:10:52 lr: 0.000111 loss: 6.2978 (6.4461) grad_norm: 1.9436 (1.8867) time: 0.6400 [2021-03-25 22:43:00 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 260/1251] eta: 0:10:44 lr: 0.000111 loss: 6.3746 (6.4439) grad_norm: 2.0217 (1.8856) time: 0.6353 [2021-03-25 22:43:06 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 270/1251] eta: 0:10:37 lr: 0.000112 loss: 6.4299 (6.4445) grad_norm: 1.8851 (1.8836) time: 0.6284 [2021-03-25 22:43:13 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 280/1251] eta: 0:10:31 lr: 0.000112 loss: 6.4217 (6.4401) grad_norm: 1.9478 (1.8870) time: 0.6387 [2021-03-25 22:43:19 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 290/1251] eta: 0:10:24 lr: 0.000112 loss: 6.2740 (6.4351) grad_norm: 1.8423 (1.8821) time: 0.6426 [2021-03-25 22:43:26 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 300/1251] eta: 0:10:17 lr: 0.000113 loss: 6.3162 (6.4330) grad_norm: 1.7508 (1.8809) time: 0.6379 [2021-03-25 22:43:32 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 310/1251] eta: 0:10:10 lr: 0.000113 loss: 6.4482 (6.4341) grad_norm: 1.7878 (1.8814) time: 0.6378 [2021-03-25 22:43:38 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 320/1251] eta: 0:10:03 lr: 0.000114 loss: 6.4482 (6.4315) grad_norm: 1.8321 (1.8793) time: 0.6374 [2021-03-25 22:43:45 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 330/1251] eta: 0:09:56 lr: 0.000114 loss: 6.3575 (6.4299) grad_norm: 1.8321 (1.8787) time: 0.6365 [2021-03-25 22:43:51 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 340/1251] eta: 0:09:49 lr: 0.000114 loss: 6.3467 (6.4294) grad_norm: 1.9936 (1.8838) time: 0.6344 [2021-03-25 22:43:58 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 350/1251] eta: 0:09:43 lr: 0.000115 loss: 6.3555 (6.4293) grad_norm: 2.0723 (1.8910) time: 0.6392 [2021-03-25 22:44:04 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 360/1251] eta: 0:09:36 lr: 0.000115 loss: 6.2818 (6.4233) grad_norm: 1.9736 (1.8922) time: 0.6394 [2021-03-25 22:44:10 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 370/1251] eta: 0:09:29 lr: 0.000116 loss: 6.2558 (6.4219) grad_norm: 1.8513 (1.8897) time: 0.6355 [2021-03-25 22:44:17 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 380/1251] eta: 0:09:23 lr: 0.000116 loss: 6.4320 (6.4216) grad_norm: 1.8109 (1.8886) time: 0.6354 [2021-03-25 22:44:23 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 390/1251] eta: 0:09:16 lr: 0.000116 loss: 6.4169 (6.4202) grad_norm: 1.8109 (1.8884) time: 0.6300 [2021-03-25 22:44:29 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 400/1251] eta: 0:09:09 lr: 0.000117 loss: 6.3962 (6.4211) grad_norm: 1.9057 (1.8923) time: 0.6269 [2021-03-25 22:44:36 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 410/1251] eta: 0:09:02 lr: 0.000117 loss: 6.3956 (6.4203) grad_norm: 1.9540 (1.8938) time: 0.6319 [2021-03-25 22:44:42 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 420/1251] eta: 0:08:56 lr: 0.000118 loss: 6.3588 (6.4192) grad_norm: 1.7649 (1.8916) time: 0.6380 [2021-03-25 22:44:48 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 430/1251] eta: 0:08:49 lr: 0.000118 loss: 6.4421 (6.4199) grad_norm: 1.7680 (1.8944) time: 0.6374 [2021-03-25 22:44:55 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 440/1251] eta: 0:08:42 lr: 0.000118 loss: 6.5099 (6.4199) grad_norm: 1.8647 (1.8951) time: 0.6324 [2021-03-25 22:45:01 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 450/1251] eta: 0:08:36 lr: 0.000119 loss: 6.3943 (6.4174) grad_norm: 1.8476 (1.8942) time: 0.6304 [2021-03-25 22:45:07 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 460/1251] eta: 0:08:29 lr: 0.000119 loss: 6.3239 (6.4152) grad_norm: 1.8823 (1.8971) time: 0.6310 [2021-03-25 22:45:14 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 470/1251] eta: 0:08:22 lr: 0.000120 loss: 6.3746 (6.4155) grad_norm: 1.8820 (1.8961) time: 0.6310 [2021-03-25 22:45:20 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 480/1251] eta: 0:08:16 lr: 0.000120 loss: 6.4628 (6.4143) grad_norm: 1.7829 (1.8950) time: 0.6360 [2021-03-25 22:45:26 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 490/1251] eta: 0:08:09 lr: 0.000120 loss: 6.4335 (6.4150) grad_norm: 1.9144 (1.8971) time: 0.6373 [2021-03-25 22:45:33 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 500/1251] eta: 0:08:03 lr: 0.000121 loss: 6.4335 (6.4140) grad_norm: 2.0666 (1.9004) time: 0.6357 [2021-03-25 22:45:39 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 510/1251] eta: 0:07:56 lr: 0.000121 loss: 6.3896 (6.4121) grad_norm: 2.0666 (1.9024) time: 0.6353 [2021-03-25 22:45:45 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 520/1251] eta: 0:07:50 lr: 0.000122 loss: 6.3896 (6.4109) grad_norm: 1.9373 (1.9030) time: 0.6398 [2021-03-25 22:45:52 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 530/1251] eta: 0:07:43 lr: 0.000122 loss: 6.2773 (6.4087) grad_norm: 1.8767 (1.9030) time: 0.6385 [2021-03-25 22:45:58 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 540/1251] eta: 0:07:37 lr: 0.000122 loss: 6.3636 (6.4080) grad_norm: 1.8329 (1.9009) time: 0.6318 [2021-03-25 22:46:04 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 550/1251] eta: 0:07:30 lr: 0.000123 loss: 6.4434 (6.4083) grad_norm: 1.7560 (1.8999) time: 0.6342 [2021-03-25 22:46:11 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 560/1251] eta: 0:07:24 lr: 0.000123 loss: 6.3735 (6.4075) grad_norm: 1.7258 (1.8956) time: 0.6367 [2021-03-25 22:46:17 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 570/1251] eta: 0:07:17 lr: 0.000124 loss: 6.3735 (6.4061) grad_norm: 1.7354 (1.8964) time: 0.6404 [2021-03-25 22:46:24 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 580/1251] eta: 0:07:11 lr: 0.000124 loss: 6.3679 (6.4046) grad_norm: 1.8603 (1.8949) time: 0.6406 [2021-03-25 22:46:30 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 590/1251] eta: 0:07:04 lr: 0.000124 loss: 6.4228 (6.4055) grad_norm: 1.8557 (1.8952) time: 0.6351 [2021-03-25 22:46:36 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 600/1251] eta: 0:06:57 lr: 0.000125 loss: 6.4527 (6.4056) grad_norm: 1.5786 (1.8886) time: 0.6262 [2021-03-25 22:46:43 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 610/1251] eta: 0:06:51 lr: 0.000125 loss: 6.4055 (6.4052) grad_norm: 1.5524 (1.8875) time: 0.6302 [2021-03-25 22:46:49 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 620/1251] eta: 0:06:44 lr: 0.000126 loss: 6.4055 (6.4051) grad_norm: 1.8249 (1.8876) time: 0.6359 [2021-03-25 22:46:55 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 630/1251] eta: 0:06:38 lr: 0.000126 loss: 6.4094 (6.4045) grad_norm: 1.8335 (1.8877) time: 0.6335 [2021-03-25 22:47:02 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 640/1251] eta: 0:06:31 lr: 0.000126 loss: 6.2668 (6.4015) grad_norm: 1.9687 (1.8895) time: 0.6352 [2021-03-25 22:47:08 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 650/1251] eta: 0:06:25 lr: 0.000127 loss: 6.3284 (6.4008) grad_norm: 1.8316 (1.8882) time: 0.6322 [2021-03-25 22:47:14 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 660/1251] eta: 0:06:19 lr: 0.000127 loss: 6.3284 (6.3996) grad_norm: 1.8316 (1.8899) time: 0.6349 [2021-03-25 22:47:21 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 670/1251] eta: 0:06:12 lr: 0.000128 loss: 6.3600 (6.3998) grad_norm: 1.9773 (1.8916) time: 0.6373 [2021-03-25 22:47:27 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 680/1251] eta: 0:06:06 lr: 0.000128 loss: 6.3649 (6.3995) grad_norm: 1.8264 (1.8925) time: 0.6296 [2021-03-25 22:47:33 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 690/1251] eta: 0:05:59 lr: 0.000128 loss: 6.3421 (6.3976) grad_norm: 1.9251 (1.8952) time: 0.6259 [2021-03-25 22:47:39 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 700/1251] eta: 0:05:52 lr: 0.000129 loss: 6.3893 (6.3977) grad_norm: 1.9726 (1.8945) time: 0.6238 [2021-03-25 22:47:46 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 710/1251] eta: 0:05:46 lr: 0.000129 loss: 6.4492 (6.3975) grad_norm: 1.7078 (1.8918) time: 0.6299 [2021-03-25 22:47:52 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 720/1251] eta: 0:05:40 lr: 0.000130 loss: 6.3952 (6.3959) grad_norm: 1.7973 (1.8923) time: 0.6394 [2021-03-25 22:47:59 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 730/1251] eta: 0:05:33 lr: 0.000130 loss: 6.3875 (6.3966) grad_norm: 1.8507 (1.8922) time: 0.6426 [2021-03-25 22:48:05 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 740/1251] eta: 0:05:27 lr: 0.000130 loss: 6.4007 (6.3970) grad_norm: 1.7977 (1.8912) time: 0.6410 [2021-03-25 22:48:11 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 750/1251] eta: 0:05:20 lr: 0.000131 loss: 6.3938 (6.3956) grad_norm: 1.7268 (1.8891) time: 0.6398 [2021-03-25 22:48:18 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 760/1251] eta: 0:05:14 lr: 0.000131 loss: 6.3250 (6.3943) grad_norm: 1.6664 (1.8881) time: 0.6398 [2021-03-25 22:48:24 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 770/1251] eta: 0:05:08 lr: 0.000132 loss: 6.3209 (6.3927) grad_norm: 1.6892 (1.8859) time: 0.6358 [2021-03-25 22:48:31 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 780/1251] eta: 0:05:01 lr: 0.000132 loss: 6.2543 (6.3913) grad_norm: 1.7173 (1.8849) time: 0.6375 [2021-03-25 22:48:37 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 790/1251] eta: 0:04:55 lr: 0.000132 loss: 6.3390 (6.3908) grad_norm: 1.8633 (1.8861) time: 0.6384 [2021-03-25 22:48:43 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 800/1251] eta: 0:04:48 lr: 0.000133 loss: 6.3823 (6.3901) grad_norm: 1.8628 (1.8860) time: 0.6331 [2021-03-25 22:48:50 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 810/1251] eta: 0:04:42 lr: 0.000133 loss: 6.4104 (6.3897) grad_norm: 1.8628 (1.8877) time: 0.6303 [2021-03-25 22:48:56 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 820/1251] eta: 0:04:35 lr: 0.000134 loss: 6.4049 (6.3888) grad_norm: 2.0716 (1.8896) time: 0.6306 [2021-03-25 22:49:02 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 830/1251] eta: 0:04:29 lr: 0.000134 loss: 6.2304 (6.3869) grad_norm: 1.9935 (1.8895) time: 0.6307 [2021-03-25 22:49:09 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 840/1251] eta: 0:04:23 lr: 0.000134 loss: 6.2955 (6.3859) grad_norm: 1.8649 (1.8888) time: 0.6379 [2021-03-25 22:49:15 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 850/1251] eta: 0:04:16 lr: 0.000135 loss: 6.3518 (6.3863) grad_norm: 1.7532 (1.8871) time: 0.6343 [2021-03-25 22:49:21 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 860/1251] eta: 0:04:10 lr: 0.000135 loss: 6.3324 (6.3846) grad_norm: 1.6235 (1.8848) time: 0.6319 [2021-03-25 22:49:28 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 870/1251] eta: 0:04:03 lr: 0.000136 loss: 6.2601 (6.3832) grad_norm: 1.6531 (1.8846) time: 0.6383 [2021-03-25 22:49:34 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 880/1251] eta: 0:03:57 lr: 0.000136 loss: 6.3667 (6.3834) grad_norm: 1.7343 (1.8833) time: 0.6390 [2021-03-25 22:49:40 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 890/1251] eta: 0:03:50 lr: 0.000136 loss: 6.4608 (6.3839) grad_norm: 1.8739 (1.8847) time: 0.6383 [2021-03-25 22:49:47 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 900/1251] eta: 0:03:44 lr: 0.000137 loss: 6.4392 (6.3825) grad_norm: 1.8290 (1.8840) time: 0.6377 [2021-03-25 22:49:53 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 910/1251] eta: 0:03:38 lr: 0.000137 loss: 6.3553 (6.3820) grad_norm: 1.7525 (1.8829) time: 0.6403 [2021-03-25 22:50:00 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 920/1251] eta: 0:03:31 lr: 0.000138 loss: 6.4235 (6.3827) grad_norm: 1.6813 (1.8807) time: 0.6353 [2021-03-25 22:50:06 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 930/1251] eta: 0:03:25 lr: 0.000138 loss: 6.3594 (6.3808) grad_norm: 1.7421 (1.8802) time: 0.6400 [2021-03-25 22:50:12 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 940/1251] eta: 0:03:18 lr: 0.000138 loss: 6.2248 (6.3800) grad_norm: 1.7258 (1.8780) time: 0.6418 [2021-03-25 22:50:19 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 950/1251] eta: 0:03:12 lr: 0.000139 loss: 6.2319 (6.3793) grad_norm: 1.7466 (1.8809) time: 0.6411 [2021-03-25 22:50:25 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 960/1251] eta: 0:03:06 lr: 0.000139 loss: 6.3339 (6.3787) grad_norm: 1.9022 (1.8800) time: 0.6433 [2021-03-25 22:50:32 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 970/1251] eta: 0:02:59 lr: 0.000140 loss: 6.2265 (6.3765) grad_norm: 1.8442 (1.8818) time: 0.6349 [2021-03-25 22:50:38 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 980/1251] eta: 0:02:53 lr: 0.000140 loss: 6.2702 (6.3758) grad_norm: 1.8718 (1.8829) time: 0.6343 [2021-03-25 22:50:44 swin_base_patch4_window7_224] INFO: Epoch: [2] [ 990/1251] eta: 0:02:46 lr: 0.000140 loss: 6.3234 (6.3757) grad_norm: 1.7629 (1.8806) time: 0.6350 [2021-03-25 22:50:51 swin_base_patch4_window7_224] INFO: Epoch: [2] [1000/1251] eta: 0:02:40 lr: 0.000141 loss: 6.2781 (6.3746) grad_norm: 1.6914 (1.8791) time: 0.6336 [2021-03-25 22:50:57 swin_base_patch4_window7_224] INFO: Epoch: [2] [1010/1251] eta: 0:02:34 lr: 0.000141 loss: 6.3239 (6.3736) grad_norm: 1.7276 (1.8780) time: 0.6344 [2021-03-25 22:51:03 swin_base_patch4_window7_224] INFO: Epoch: [2] [1020/1251] eta: 0:02:27 lr: 0.000142 loss: 6.1835 (6.3719) grad_norm: 1.6937 (1.8761) time: 0.6319 [2021-03-25 22:51:10 swin_base_patch4_window7_224] INFO: Epoch: [2] [1030/1251] eta: 0:02:21 lr: 0.000142 loss: 6.1835 (6.3714) grad_norm: 1.6484 (1.8747) time: 0.6331 [2021-03-25 22:51:16 swin_base_patch4_window7_224] INFO: Epoch: [2] [1040/1251] eta: 0:02:14 lr: 0.000142 loss: 6.3034 (6.3705) grad_norm: 1.7282 (1.8751) time: 0.6364 [2021-03-25 22:51:22 swin_base_patch4_window7_224] INFO: Epoch: [2] [1050/1251] eta: 0:02:08 lr: 0.000143 loss: 6.2525 (6.3690) grad_norm: 1.8932 (1.8768) time: 0.6374 [2021-03-25 22:51:29 swin_base_patch4_window7_224] INFO: Epoch: [2] [1060/1251] eta: 0:02:02 lr: 0.000143 loss: 6.3098 (6.3684) grad_norm: 1.8778 (1.8759) time: 0.6388 [2021-03-25 22:51:35 swin_base_patch4_window7_224] INFO: Epoch: [2] [1070/1251] eta: 0:01:55 lr: 0.000144 loss: 6.3756 (6.3680) grad_norm: 1.7798 (1.8767) time: 0.6414 [2021-03-25 22:51:41 swin_base_patch4_window7_224] INFO: Epoch: [2] [1080/1251] eta: 0:01:49 lr: 0.000144 loss: 6.3703 (6.3676) grad_norm: 1.8444 (1.8768) time: 0.6363 [2021-03-25 22:51:48 swin_base_patch4_window7_224] INFO: Epoch: [2] [1090/1251] eta: 0:01:42 lr: 0.000144 loss: 6.3703 (6.3674) grad_norm: 1.8444 (1.8770) time: 0.6317 [2021-03-25 22:51:54 swin_base_patch4_window7_224] INFO: Epoch: [2] [1100/1251] eta: 0:01:36 lr: 0.000145 loss: 6.3661 (6.3656) grad_norm: 1.7712 (1.8766) time: 0.6350 [2021-03-25 22:52:00 swin_base_patch4_window7_224] INFO: Epoch: [2] [1110/1251] eta: 0:01:30 lr: 0.000145 loss: 6.3572 (6.3659) grad_norm: 1.7468 (1.8772) time: 0.6313 [2021-03-25 22:52:07 swin_base_patch4_window7_224] INFO: Epoch: [2] [1120/1251] eta: 0:01:23 lr: 0.000146 loss: 6.2914 (6.3653) grad_norm: 1.8288 (1.8768) time: 0.6295 [2021-03-25 22:52:13 swin_base_patch4_window7_224] INFO: Epoch: [2] [1130/1251] eta: 0:01:17 lr: 0.000146 loss: 6.2847 (6.3652) grad_norm: 1.8318 (1.8765) time: 0.6317 [2021-03-25 22:52:19 swin_base_patch4_window7_224] INFO: Epoch: [2] [1140/1251] eta: 0:01:10 lr: 0.000146 loss: 6.2631 (6.3638) grad_norm: 1.8331 (1.8765) time: 0.6284 [2021-03-25 22:52:26 swin_base_patch4_window7_224] INFO: Epoch: [2] [1150/1251] eta: 0:01:04 lr: 0.000147 loss: 6.2543 (6.3634) grad_norm: 1.8223 (1.8756) time: 0.6314 [2021-03-25 22:52:32 swin_base_patch4_window7_224] INFO: Epoch: [2] [1160/1251] eta: 0:00:58 lr: 0.000147 loss: 6.2599 (6.3630) grad_norm: 1.8049 (1.8753) time: 0.6382 [2021-03-25 22:52:38 swin_base_patch4_window7_224] INFO: Epoch: [2] [1170/1251] eta: 0:00:51 lr: 0.000148 loss: 6.3760 (6.3626) grad_norm: 1.7558 (1.8743) time: 0.6380 [2021-03-25 22:52:45 swin_base_patch4_window7_224] INFO: Epoch: [2] [1180/1251] eta: 0:00:45 lr: 0.000148 loss: 6.3267 (6.3615) grad_norm: 1.8432 (1.8769) time: 0.6344 [2021-03-25 22:52:51 swin_base_patch4_window7_224] INFO: Epoch: [2] [1190/1251] eta: 0:00:38 lr: 0.000148 loss: 6.2710 (6.3605) grad_norm: 1.9451 (1.8774) time: 0.6361 [2021-03-25 22:52:57 swin_base_patch4_window7_224] INFO: Epoch: [2] [1200/1251] eta: 0:00:32 lr: 0.000149 loss: 6.2710 (6.3595) grad_norm: 1.9263 (1.8782) time: 0.6353 [2021-03-25 22:53:04 swin_base_patch4_window7_224] INFO: Epoch: [2] [1210/1251] eta: 0:00:26 lr: 0.000149 loss: 6.2819 (6.3585) grad_norm: 1.8895 (1.8781) time: 0.6348 [2021-03-25 22:53:10 swin_base_patch4_window7_224] INFO: Epoch: [2] [1220/1251] eta: 0:00:19 lr: 0.000150 loss: 6.2539 (6.3581) grad_norm: 1.8537 (1.8780) time: 0.6372 [2021-03-25 22:53:17 swin_base_patch4_window7_224] INFO: Epoch: [2] [1230/1251] eta: 0:00:13 lr: 0.000150 loss: 6.3225 (6.3579) grad_norm: 1.9286 (1.8827) time: 0.6317 [2021-03-25 22:53:23 swin_base_patch4_window7_224] INFO: Epoch: [2] [1240/1251] eta: 0:00:07 lr: 0.000150 loss: 6.3088 (6.3569) grad_norm: 2.1563 (1.8840) time: 0.6289 [2021-03-25 22:53:29 swin_base_patch4_window7_224] INFO: Epoch: [2] [1250/1251] eta: 0:00:00 lr: 0.000151 loss: 6.1904 (6.3553) grad_norm: 1.8958 (1.8838) time: 0.6279 [2021-03-25 22:53:32 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:09 loss: 4.8332 (4.8332) acc1: 12.5000 (12.5000) acc5: 34.3750 (34.3750) [2021-03-25 22:53:36 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 5.0902 (5.0790) acc1: 9.3750 (9.5170) acc5: 25.0000 (25.5682) [2021-03-25 22:53:38 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 5.0698 (5.0615) acc1: 9.3750 (9.4494) acc5: 23.4375 (25.0744) [2021-03-25 22:53:40 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 5.0463 (5.0304) acc1: 10.9375 (10.0302) acc5: 25.0000 (25.2016) [2021-03-25 22:53:42 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 4.9732 (5.0195) acc1: 10.9375 (10.2134) acc5: 25.0000 (25.5335) [2021-03-25 22:53:43 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 4.9901 (5.0398) acc1: 10.9375 (10.2080) acc5: 25.0000 (25.2480) [2021-03-25 22:53:45 swin_base_patch4_window7_224] INFO: * Acc@1 9.362 Acc@5 24.920 loss 5.045 [2021-03-25 22:53:45 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 9.4% [2021-03-25 22:53:45 swin_base_patch4_window7_224] INFO: Max accuracy: 9.36% [2021-03-25 22:53:49 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 0/1251] eta: 1:26:43 lr: 0.000151 loss: 6.0867 (6.0867) grad_norm: 1.8715 (1.8715) time: 4.1595 [2021-03-25 22:53:55 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 10/1251] eta: 0:20:12 lr: 0.000151 loss: 6.1957 (6.2154) grad_norm: 2.1398 (2.0476) time: 0.9767 [2021-03-25 22:54:02 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 20/1251] eta: 0:16:42 lr: 0.000152 loss: 6.1957 (6.2062) grad_norm: 1.9354 (1.9985) time: 0.6468 [2021-03-25 22:54:08 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 30/1251] eta: 0:15:22 lr: 0.000152 loss: 6.1926 (6.2186) grad_norm: 1.9354 (1.9912) time: 0.6332 [2021-03-25 22:54:14 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 40/1251] eta: 0:14:38 lr: 0.000152 loss: 6.1981 (6.2284) grad_norm: 1.6503 (1.9181) time: 0.6332 [2021-03-25 22:54:21 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 50/1251] eta: 0:14:11 lr: 0.000153 loss: 6.3247 (6.2524) grad_norm: 1.7036 (1.9083) time: 0.6377 [2021-03-25 22:54:27 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 60/1251] eta: 0:13:50 lr: 0.000153 loss: 6.2731 (6.2242) grad_norm: 1.8835 (1.9265) time: 0.6388 [2021-03-25 22:54:33 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 70/1251] eta: 0:13:32 lr: 0.000154 loss: 6.2731 (6.2411) grad_norm: 1.8319 (1.9135) time: 0.6337 [2021-03-25 22:54:40 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 80/1251] eta: 0:13:17 lr: 0.000154 loss: 6.3113 (6.2429) grad_norm: 1.7983 (1.9030) time: 0.6315 [2021-03-25 22:54:46 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 90/1251] eta: 0:13:03 lr: 0.000154 loss: 6.2792 (6.2309) grad_norm: 1.8918 (1.9178) time: 0.6306 [2021-03-25 22:54:52 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 100/1251] eta: 0:12:52 lr: 0.000155 loss: 6.3135 (6.2398) grad_norm: 2.0616 (1.9439) time: 0.6309 [2021-03-25 22:54:59 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 110/1251] eta: 0:12:42 lr: 0.000155 loss: 6.2865 (6.2307) grad_norm: 2.0133 (1.9611) time: 0.6379 [2021-03-25 22:55:05 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 120/1251] eta: 0:12:33 lr: 0.000156 loss: 6.1144 (6.2284) grad_norm: 2.0119 (1.9669) time: 0.6425 [2021-03-25 22:55:12 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 130/1251] eta: 0:12:24 lr: 0.000156 loss: 6.1307 (6.2174) grad_norm: 1.7384 (1.9439) time: 0.6418 [2021-03-25 22:55:18 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 140/1251] eta: 0:12:15 lr: 0.000156 loss: 6.1307 (6.2149) grad_norm: 1.6577 (1.9359) time: 0.6362 [2021-03-25 22:55:24 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 150/1251] eta: 0:12:07 lr: 0.000157 loss: 6.1935 (6.2100) grad_norm: 1.8983 (1.9371) time: 0.6356 [2021-03-25 22:55:31 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 160/1251] eta: 0:11:58 lr: 0.000157 loss: 6.2388 (6.2107) grad_norm: 1.8626 (1.9354) time: 0.6370 [2021-03-25 22:55:37 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 170/1251] eta: 0:11:51 lr: 0.000158 loss: 6.2452 (6.2115) grad_norm: 1.8012 (1.9262) time: 0.6386 [2021-03-25 22:55:43 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 180/1251] eta: 0:11:43 lr: 0.000158 loss: 6.3077 (6.2154) grad_norm: 1.6976 (1.9200) time: 0.6386 [2021-03-25 22:55:50 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 190/1251] eta: 0:11:35 lr: 0.000158 loss: 6.1959 (6.2089) grad_norm: 1.7631 (1.9130) time: 0.6340 [2021-03-25 22:55:56 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 200/1251] eta: 0:11:28 lr: 0.000159 loss: 6.0061 (6.2046) grad_norm: 1.8023 (1.9156) time: 0.6365 [2021-03-25 22:56:02 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 210/1251] eta: 0:11:20 lr: 0.000159 loss: 6.2160 (6.2067) grad_norm: 1.8246 (1.9108) time: 0.6347 [2021-03-25 22:56:09 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 220/1251] eta: 0:11:13 lr: 0.000160 loss: 6.3062 (6.2110) grad_norm: 1.9089 (1.9160) time: 0.6342 [2021-03-25 22:56:15 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 230/1251] eta: 0:11:05 lr: 0.000160 loss: 6.3040 (6.2117) grad_norm: 1.9328 (1.9211) time: 0.6357 [2021-03-25 22:56:22 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 240/1251] eta: 0:10:58 lr: 0.000160 loss: 6.2862 (6.2130) grad_norm: 1.9328 (1.9222) time: 0.6372 [2021-03-25 22:56:28 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 250/1251] eta: 0:10:51 lr: 0.000161 loss: 6.2862 (6.2114) grad_norm: 1.9371 (inf) time: 0.6346 [2021-03-25 22:56:34 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 260/1251] eta: 0:10:44 lr: 0.000161 loss: 6.0227 (6.2095) grad_norm: 1.8740 (inf) time: 0.6336 [2021-03-25 22:56:41 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 270/1251] eta: 0:10:37 lr: 0.000162 loss: 6.2830 (6.2111) grad_norm: 1.8379 (inf) time: 0.6377 [2021-03-25 22:56:47 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 280/1251] eta: 0:10:30 lr: 0.000162 loss: 6.1819 (6.2077) grad_norm: 1.8520 (inf) time: 0.6339 [2021-03-25 22:56:53 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 290/1251] eta: 0:10:22 lr: 0.000162 loss: 6.2457 (6.2137) grad_norm: 1.7742 (inf) time: 0.6291 [2021-03-25 22:57:00 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 300/1251] eta: 0:10:15 lr: 0.000163 loss: 6.3907 (6.2185) grad_norm: 1.8706 (inf) time: 0.6277 [2021-03-25 22:57:06 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 310/1251] eta: 0:10:09 lr: 0.000163 loss: 6.3727 (6.2193) grad_norm: 1.8941 (inf) time: 0.6357 [2021-03-25 22:57:12 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 320/1251] eta: 0:10:02 lr: 0.000164 loss: 6.0568 (6.2134) grad_norm: 1.8038 (inf) time: 0.6411 [2021-03-25 22:57:19 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 330/1251] eta: 0:09:55 lr: 0.000164 loss: 6.0291 (6.2100) grad_norm: 1.8635 (inf) time: 0.6375 [2021-03-25 22:57:25 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 340/1251] eta: 0:09:49 lr: 0.000164 loss: 6.1470 (6.2095) grad_norm: 1.8849 (inf) time: 0.6366 [2021-03-25 22:57:31 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 350/1251] eta: 0:09:42 lr: 0.000165 loss: 6.1750 (6.2066) grad_norm: 1.8829 (inf) time: 0.6341 [2021-03-25 22:57:38 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 360/1251] eta: 0:09:35 lr: 0.000165 loss: 6.2243 (6.2093) grad_norm: 1.7966 (inf) time: 0.6306 [2021-03-25 22:57:44 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 370/1251] eta: 0:09:28 lr: 0.000166 loss: 6.2152 (6.2082) grad_norm: 1.8786 (inf) time: 0.6315 [2021-03-25 22:57:50 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 380/1251] eta: 0:09:21 lr: 0.000166 loss: 6.1464 (6.2048) grad_norm: 1.8668 (inf) time: 0.6357 [2021-03-25 22:57:57 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 390/1251] eta: 0:09:15 lr: 0.000166 loss: 6.1688 (6.2050) grad_norm: 1.8360 (inf) time: 0.6357 [2021-03-25 22:58:03 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 400/1251] eta: 0:09:08 lr: 0.000167 loss: 6.1988 (6.2018) grad_norm: 1.9180 (inf) time: 0.6319 [2021-03-25 22:58:09 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 410/1251] eta: 0:09:01 lr: 0.000167 loss: 6.2303 (6.2026) grad_norm: 1.8290 (inf) time: 0.6348 [2021-03-25 22:58:16 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 420/1251] eta: 0:08:55 lr: 0.000168 loss: 6.3015 (6.2033) grad_norm: 1.8312 (inf) time: 0.6380 [2021-03-25 22:58:22 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 430/1251] eta: 0:08:48 lr: 0.000168 loss: 6.2928 (6.2032) grad_norm: 1.9390 (inf) time: 0.6326 [2021-03-25 22:58:28 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 440/1251] eta: 0:08:41 lr: 0.000168 loss: 6.0419 (6.1993) grad_norm: 1.9390 (inf) time: 0.6280 [2021-03-25 22:58:35 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 450/1251] eta: 0:08:35 lr: 0.000169 loss: 6.0419 (6.1992) grad_norm: 1.8535 (inf) time: 0.6288 [2021-03-25 22:58:41 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 460/1251] eta: 0:08:28 lr: 0.000169 loss: 6.2301 (6.1996) grad_norm: 1.7906 (inf) time: 0.6280 [2021-03-25 22:58:47 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 470/1251] eta: 0:08:21 lr: 0.000170 loss: 6.2352 (6.1995) grad_norm: 1.8917 (inf) time: 0.6296 [2021-03-25 22:58:54 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 480/1251] eta: 0:08:15 lr: 0.000170 loss: 6.2352 (6.1969) grad_norm: 1.9192 (inf) time: 0.6359 [2021-03-25 22:59:00 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 490/1251] eta: 0:08:08 lr: 0.000170 loss: 6.1371 (6.1969) grad_norm: 1.9199 (inf) time: 0.6362 [2021-03-25 22:59:06 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 500/1251] eta: 0:08:02 lr: 0.000171 loss: 6.2354 (6.1959) grad_norm: 1.9080 (inf) time: 0.6345 [2021-03-25 22:59:13 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 510/1251] eta: 0:07:55 lr: 0.000171 loss: 6.2354 (6.1949) grad_norm: 1.8695 (inf) time: 0.6365 [2021-03-25 22:59:19 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 520/1251] eta: 0:07:49 lr: 0.000172 loss: 6.2212 (6.1948) grad_norm: 1.7604 (inf) time: 0.6351 [2021-03-25 22:59:26 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 530/1251] eta: 0:07:42 lr: 0.000172 loss: 6.1505 (6.1929) grad_norm: 1.7677 (inf) time: 0.6390 [2021-03-25 22:59:32 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 540/1251] eta: 0:07:36 lr: 0.000172 loss: 6.1505 (6.1941) grad_norm: 1.9426 (inf) time: 0.6421 [2021-03-25 22:59:38 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 550/1251] eta: 0:07:30 lr: 0.000173 loss: 6.1557 (6.1908) grad_norm: 2.0358 (inf) time: 0.6418 [2021-03-25 22:59:45 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 560/1251] eta: 0:07:23 lr: 0.000173 loss: 6.1656 (6.1910) grad_norm: 2.0726 (inf) time: 0.6388 [2021-03-25 22:59:51 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 570/1251] eta: 0:07:16 lr: 0.000174 loss: 6.3003 (6.1920) grad_norm: 1.7967 (inf) time: 0.6345 [2021-03-25 22:59:57 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 580/1251] eta: 0:07:10 lr: 0.000174 loss: 6.1975 (6.1894) grad_norm: 1.7532 (inf) time: 0.6343 [2021-03-25 23:00:04 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 590/1251] eta: 0:07:04 lr: 0.000174 loss: 6.0133 (6.1872) grad_norm: 2.0474 (inf) time: 0.6384 [2021-03-25 23:00:10 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 600/1251] eta: 0:06:57 lr: 0.000175 loss: 6.1666 (6.1880) grad_norm: 2.0778 (inf) time: 0.6371 [2021-03-25 23:00:17 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 610/1251] eta: 0:06:51 lr: 0.000175 loss: 6.1666 (6.1863) grad_norm: 2.0165 (inf) time: 0.6367 [2021-03-25 23:00:23 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 620/1251] eta: 0:06:44 lr: 0.000176 loss: 6.2215 (6.1873) grad_norm: 1.7524 (inf) time: 0.6371 [2021-03-25 23:00:29 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 630/1251] eta: 0:06:38 lr: 0.000176 loss: 6.1744 (6.1850) grad_norm: 1.7949 (inf) time: 0.6327 [2021-03-25 23:00:36 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 640/1251] eta: 0:06:31 lr: 0.000176 loss: 6.0626 (6.1851) grad_norm: 1.8101 (inf) time: 0.6339 [2021-03-25 23:00:42 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 650/1251] eta: 0:06:25 lr: 0.000177 loss: 6.2145 (6.1864) grad_norm: 1.8058 (inf) time: 0.6330 [2021-03-25 23:00:48 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 660/1251] eta: 0:06:18 lr: 0.000177 loss: 6.2145 (6.1856) grad_norm: 1.8097 (inf) time: 0.6291 [2021-03-25 23:00:54 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 670/1251] eta: 0:06:12 lr: 0.000178 loss: 6.2034 (6.1850) grad_norm: 1.8476 (inf) time: 0.6285 [2021-03-25 23:01:01 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 680/1251] eta: 0:06:05 lr: 0.000178 loss: 6.2296 (6.1826) grad_norm: 1.7799 (inf) time: 0.6306 [2021-03-25 23:01:07 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 690/1251] eta: 0:05:59 lr: 0.000178 loss: 6.2425 (6.1832) grad_norm: 1.8699 (inf) time: 0.6344 [2021-03-25 23:01:14 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 700/1251] eta: 0:05:52 lr: 0.000179 loss: 6.2345 (6.1826) grad_norm: 1.9211 (inf) time: 0.6409 [2021-03-25 23:01:20 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 710/1251] eta: 0:05:46 lr: 0.000179 loss: 6.1079 (6.1808) grad_norm: 1.8879 (inf) time: 0.6410 [2021-03-25 23:01:26 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 720/1251] eta: 0:05:40 lr: 0.000180 loss: 6.2284 (6.1828) grad_norm: 1.8239 (inf) time: 0.6414 [2021-03-25 23:01:33 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 730/1251] eta: 0:05:33 lr: 0.000180 loss: 6.2749 (6.1822) grad_norm: 1.8174 (inf) time: 0.6422 [2021-03-25 23:01:39 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 740/1251] eta: 0:05:27 lr: 0.000180 loss: 6.0535 (6.1794) grad_norm: 1.8227 (inf) time: 0.6403 [2021-03-25 23:01:46 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 750/1251] eta: 0:05:20 lr: 0.000181 loss: 6.0922 (6.1777) grad_norm: 1.8877 (inf) time: 0.6408 [2021-03-25 23:01:52 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 760/1251] eta: 0:05:14 lr: 0.000181 loss: 6.2618 (6.1784) grad_norm: 1.9373 (inf) time: 0.6394 [2021-03-25 23:01:58 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 770/1251] eta: 0:05:07 lr: 0.000182 loss: 6.2342 (6.1787) grad_norm: 1.9296 (inf) time: 0.6318 [2021-03-25 23:02:05 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 780/1251] eta: 0:05:01 lr: 0.000182 loss: 6.1695 (6.1784) grad_norm: 1.7495 (inf) time: 0.6381 [2021-03-25 23:02:11 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 790/1251] eta: 0:04:55 lr: 0.000182 loss: 6.1676 (6.1774) grad_norm: 1.7437 (inf) time: 0.6425 [2021-03-25 23:02:18 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 800/1251] eta: 0:04:48 lr: 0.000183 loss: 6.2152 (6.1774) grad_norm: 1.7805 (inf) time: 0.6418 [2021-03-25 23:02:24 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 810/1251] eta: 0:04:42 lr: 0.000183 loss: 6.2909 (6.1785) grad_norm: 1.8890 (inf) time: 0.6409 [2021-03-25 23:02:30 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 820/1251] eta: 0:04:35 lr: 0.000184 loss: 6.2305 (6.1779) grad_norm: 1.9341 (inf) time: 0.6330 [2021-03-25 23:02:37 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 830/1251] eta: 0:04:29 lr: 0.000184 loss: 6.2043 (6.1779) grad_norm: 1.9175 (inf) time: 0.6348 [2021-03-25 23:02:43 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 840/1251] eta: 0:04:23 lr: 0.000184 loss: 6.2043 (6.1771) grad_norm: 1.8765 (inf) time: 0.6343 [2021-03-25 23:02:49 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 850/1251] eta: 0:04:16 lr: 0.000185 loss: 6.1302 (6.1764) grad_norm: 1.8887 (inf) time: 0.6323 [2021-03-25 23:02:56 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 860/1251] eta: 0:04:10 lr: 0.000185 loss: 6.0215 (6.1747) grad_norm: 1.9032 (inf) time: 0.6412 [2021-03-25 23:03:02 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 870/1251] eta: 0:04:03 lr: 0.000186 loss: 5.9945 (6.1745) grad_norm: 1.8736 (inf) time: 0.6471 [2021-03-25 23:03:09 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 880/1251] eta: 0:03:57 lr: 0.000186 loss: 6.2477 (6.1736) grad_norm: 2.0213 (inf) time: 0.6424 [2021-03-25 23:03:15 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 890/1251] eta: 0:03:51 lr: 0.000186 loss: 6.1443 (6.1736) grad_norm: 2.3222 (inf) time: 0.6333 [2021-03-25 23:03:21 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 900/1251] eta: 0:03:44 lr: 0.000187 loss: 6.0751 (6.1734) grad_norm: 2.1541 (inf) time: 0.6335 [2021-03-25 23:03:28 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 910/1251] eta: 0:03:38 lr: 0.000187 loss: 6.2338 (6.1738) grad_norm: 1.8939 (inf) time: 0.6409 [2021-03-25 23:03:34 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 920/1251] eta: 0:03:31 lr: 0.000188 loss: 6.2338 (6.1738) grad_norm: 1.9236 (inf) time: 0.6349 [2021-03-25 23:03:40 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 930/1251] eta: 0:03:25 lr: 0.000188 loss: 6.2333 (6.1737) grad_norm: 2.1326 (inf) time: 0.6285 [2021-03-25 23:03:47 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 940/1251] eta: 0:03:18 lr: 0.000188 loss: 6.2114 (6.1740) grad_norm: 2.0447 (inf) time: 0.6315 [2021-03-25 23:03:53 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 950/1251] eta: 0:03:12 lr: 0.000189 loss: 6.1956 (6.1750) grad_norm: 1.9513 (inf) time: 0.6346 [2021-03-25 23:03:59 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 960/1251] eta: 0:03:06 lr: 0.000189 loss: 6.1389 (6.1743) grad_norm: 1.9496 (inf) time: 0.6332 [2021-03-25 23:04:06 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 970/1251] eta: 0:02:59 lr: 0.000190 loss: 6.1124 (6.1741) grad_norm: 1.8995 (inf) time: 0.6365 [2021-03-25 23:04:12 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 980/1251] eta: 0:02:53 lr: 0.000190 loss: 6.1054 (6.1722) grad_norm: 1.9395 (inf) time: 0.6370 [2021-03-25 23:04:18 swin_base_patch4_window7_224] INFO: Epoch: [3] [ 990/1251] eta: 0:02:46 lr: 0.000190 loss: 6.1735 (6.1719) grad_norm: 1.9333 (inf) time: 0.6326 [2021-03-25 23:04:25 swin_base_patch4_window7_224] INFO: Epoch: [3] [1000/1251] eta: 0:02:40 lr: 0.000191 loss: 6.1740 (6.1705) grad_norm: 1.9091 (inf) time: 0.6343 [2021-03-25 23:04:31 swin_base_patch4_window7_224] INFO: Epoch: [3] [1010/1251] eta: 0:02:34 lr: 0.000191 loss: 6.2425 (6.1701) grad_norm: 1.9536 (inf) time: 0.6329 [2021-03-25 23:04:37 swin_base_patch4_window7_224] INFO: Epoch: [3] [1020/1251] eta: 0:02:27 lr: 0.000192 loss: 6.2032 (6.1683) grad_norm: 1.8269 (inf) time: 0.6322 [2021-03-25 23:04:44 swin_base_patch4_window7_224] INFO: Epoch: [3] [1030/1251] eta: 0:02:21 lr: 0.000192 loss: 5.9941 (6.1677) grad_norm: 1.7345 (inf) time: 0.6349 [2021-03-25 23:04:50 swin_base_patch4_window7_224] INFO: Epoch: [3] [1040/1251] eta: 0:02:14 lr: 0.000192 loss: 6.1789 (6.1676) grad_norm: 1.7345 (inf) time: 0.6369 [2021-03-25 23:04:56 swin_base_patch4_window7_224] INFO: Epoch: [3] [1050/1251] eta: 0:02:08 lr: 0.000193 loss: 6.1789 (6.1675) grad_norm: 1.8638 (inf) time: 0.6346 [2021-03-25 23:05:03 swin_base_patch4_window7_224] INFO: Epoch: [3] [1060/1251] eta: 0:02:02 lr: 0.000193 loss: 6.0702 (6.1663) grad_norm: 2.0016 (inf) time: 0.6355 [2021-03-25 23:05:09 swin_base_patch4_window7_224] INFO: Epoch: [3] [1070/1251] eta: 0:01:55 lr: 0.000194 loss: 6.0702 (6.1637) grad_norm: 1.8413 (inf) time: 0.6404 [2021-03-25 23:05:16 swin_base_patch4_window7_224] INFO: Epoch: [3] [1080/1251] eta: 0:01:49 lr: 0.000194 loss: 6.0746 (6.1631) grad_norm: 1.8413 (inf) time: 0.6372 [2021-03-25 23:05:22 swin_base_patch4_window7_224] INFO: Epoch: [3] [1090/1251] eta: 0:01:42 lr: 0.000194 loss: 6.1408 (6.1623) grad_norm: 1.8585 (inf) time: 0.6381 [2021-03-25 23:05:28 swin_base_patch4_window7_224] INFO: Epoch: [3] [1100/1251] eta: 0:01:36 lr: 0.000195 loss: 6.1463 (6.1605) grad_norm: 1.8585 (inf) time: 0.6399 [2021-03-25 23:05:35 swin_base_patch4_window7_224] INFO: Epoch: [3] [1110/1251] eta: 0:01:30 lr: 0.000195 loss: 5.9213 (6.1578) grad_norm: 1.9288 (inf) time: 0.6350 [2021-03-25 23:05:41 swin_base_patch4_window7_224] INFO: Epoch: [3] [1120/1251] eta: 0:01:23 lr: 0.000196 loss: 5.7470 (6.1561) grad_norm: 1.8983 (inf) time: 0.6341 [2021-03-25 23:05:47 swin_base_patch4_window7_224] INFO: Epoch: [3] [1130/1251] eta: 0:01:17 lr: 0.000196 loss: 5.9866 (6.1554) grad_norm: 1.8778 (inf) time: 0.6354 [2021-03-25 23:05:54 swin_base_patch4_window7_224] INFO: Epoch: [3] [1140/1251] eta: 0:01:10 lr: 0.000196 loss: 6.0562 (6.1549) grad_norm: 1.8113 (inf) time: 0.6324 [2021-03-25 23:06:00 swin_base_patch4_window7_224] INFO: Epoch: [3] [1150/1251] eta: 0:01:04 lr: 0.000197 loss: 5.9721 (6.1524) grad_norm: 1.8146 (inf) time: 0.6329 [2021-03-25 23:06:06 swin_base_patch4_window7_224] INFO: Epoch: [3] [1160/1251] eta: 0:00:58 lr: 0.000197 loss: 5.9678 (6.1511) grad_norm: 1.8192 (inf) time: 0.6329 [2021-03-25 23:06:13 swin_base_patch4_window7_224] INFO: Epoch: [3] [1170/1251] eta: 0:00:51 lr: 0.000198 loss: 6.0838 (6.1513) grad_norm: 1.6954 (inf) time: 0.6329 [2021-03-25 23:06:19 swin_base_patch4_window7_224] INFO: Epoch: [3] [1180/1251] eta: 0:00:45 lr: 0.000198 loss: 6.1712 (6.1510) grad_norm: 1.8040 (inf) time: 0.6360 [2021-03-25 23:06:25 swin_base_patch4_window7_224] INFO: Epoch: [3] [1190/1251] eta: 0:00:38 lr: 0.000198 loss: 6.2239 (6.1516) grad_norm: 1.8857 (inf) time: 0.6324 [2021-03-25 23:06:32 swin_base_patch4_window7_224] INFO: Epoch: [3] [1200/1251] eta: 0:00:32 lr: 0.000199 loss: 6.2398 (6.1513) grad_norm: 1.8171 (inf) time: 0.6293 [2021-03-25 23:06:38 swin_base_patch4_window7_224] INFO: Epoch: [3] [1210/1251] eta: 0:00:26 lr: 0.000199 loss: 6.0071 (6.1496) grad_norm: 1.9423 (inf) time: 0.6361 [2021-03-25 23:06:44 swin_base_patch4_window7_224] INFO: Epoch: [3] [1220/1251] eta: 0:00:19 lr: 0.000200 loss: 6.0071 (6.1488) grad_norm: 1.9061 (inf) time: 0.6350 [2021-03-25 23:06:51 swin_base_patch4_window7_224] INFO: Epoch: [3] [1230/1251] eta: 0:00:13 lr: 0.000200 loss: 6.2109 (6.1496) grad_norm: 1.7263 (inf) time: 0.6271 [2021-03-25 23:06:57 swin_base_patch4_window7_224] INFO: Epoch: [3] [1240/1251] eta: 0:00:07 lr: 0.000200 loss: 6.0763 (6.1477) grad_norm: 1.7809 (inf) time: 0.6265 [2021-03-25 23:07:03 swin_base_patch4_window7_224] INFO: Epoch: [3] [1250/1251] eta: 0:00:00 lr: 0.000201 loss: 6.0313 (6.1489) grad_norm: 1.9119 (inf) time: 0.6190 [2021-03-25 23:07:07 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:37 loss: 4.4690 (4.4690) acc1: 18.7500 (18.7500) acc5: 39.0625 (39.0625) [2021-03-25 23:07:10 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 4.4180 (4.4144) acc1: 15.6250 (16.4773) acc5: 37.5000 (37.2159) [2021-03-25 23:07:12 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 4.4180 (4.4602) acc1: 15.6250 (16.8155) acc5: 37.5000 (37.6488) [2021-03-25 23:07:14 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 4.5141 (4.4863) acc1: 15.6250 (15.8266) acc5: 34.3750 (36.0383) [2021-03-25 23:07:16 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 4.4829 (4.4673) acc1: 15.6250 (16.3110) acc5: 34.3750 (36.6997) [2021-03-25 23:07:17 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 4.4205 (4.4911) acc1: 15.6250 (15.9040) acc5: 35.9375 (36.1600) [2021-03-25 23:07:18 swin_base_patch4_window7_224] INFO: * Acc@1 15.402 Acc@5 35.280 loss 4.498 [2021-03-25 23:07:18 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 15.4% [2021-03-25 23:07:18 swin_base_patch4_window7_224] INFO: Max accuracy: 15.40% [2021-03-25 23:07:23 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 0/1251] eta: 1:31:19 lr: 0.000201 loss: 6.3804 (6.3804) grad_norm: 2.3020 (2.3020) time: 4.3799 [2021-03-25 23:07:29 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 10/1251] eta: 0:20:11 lr: 0.000201 loss: 6.0552 (6.0637) grad_norm: 1.9578 (2.0585) time: 0.9761 [2021-03-25 23:07:36 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 20/1251] eta: 0:16:41 lr: 0.000202 loss: 6.0552 (6.0475) grad_norm: 1.9349 (2.0482) time: 0.6349 [2021-03-25 23:07:42 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 30/1251] eta: 0:15:22 lr: 0.000202 loss: 5.9459 (5.9903) grad_norm: 1.8640 (2.0022) time: 0.6349 [2021-03-25 23:07:48 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 40/1251] eta: 0:14:39 lr: 0.000202 loss: 5.9739 (6.0149) grad_norm: 1.8336 (1.9690) time: 0.6355 [2021-03-25 23:07:55 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 50/1251] eta: 0:14:11 lr: 0.000203 loss: 6.0448 (6.0082) grad_norm: 1.8223 (1.9493) time: 0.6353 [2021-03-25 23:08:01 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 60/1251] eta: 0:13:48 lr: 0.000203 loss: 6.1036 (6.0321) grad_norm: 1.8878 (1.9684) time: 0.6325 [2021-03-25 23:08:07 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 70/1251] eta: 0:13:31 lr: 0.000204 loss: 6.1036 (6.0092) grad_norm: 1.8528 (1.9515) time: 0.6311 [2021-03-25 23:08:14 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 80/1251] eta: 0:13:16 lr: 0.000204 loss: 5.9212 (5.9980) grad_norm: 1.8456 (1.9787) time: 0.6334 [2021-03-25 23:08:20 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 90/1251] eta: 0:13:04 lr: 0.000204 loss: 5.9427 (5.9948) grad_norm: 1.8730 (1.9753) time: 0.6372 [2021-03-25 23:08:26 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 100/1251] eta: 0:12:54 lr: 0.000205 loss: 6.1432 (6.0127) grad_norm: 1.8380 (1.9799) time: 0.6450 [2021-03-25 23:08:33 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 110/1251] eta: 0:12:43 lr: 0.000205 loss: 6.1432 (6.0046) grad_norm: 1.8830 (2.0070) time: 0.6400 [2021-03-25 23:08:39 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 120/1251] eta: 0:12:33 lr: 0.000206 loss: 5.9203 (6.0010) grad_norm: 2.0207 (2.0231) time: 0.6318 [2021-03-25 23:08:45 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 130/1251] eta: 0:12:23 lr: 0.000206 loss: 6.1171 (6.0097) grad_norm: 1.9089 (2.0223) time: 0.6281 [2021-03-25 23:08:52 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 140/1251] eta: 0:12:14 lr: 0.000206 loss: 6.1238 (6.0133) grad_norm: 1.8483 (2.0176) time: 0.6315 [2021-03-25 23:08:58 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 150/1251] eta: 0:12:06 lr: 0.000207 loss: 5.9868 (6.0032) grad_norm: 1.9338 (2.0227) time: 0.6370 [2021-03-25 23:09:04 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 160/1251] eta: 0:11:58 lr: 0.000207 loss: 6.0026 (6.0103) grad_norm: 1.9987 (2.0170) time: 0.6371 [2021-03-25 23:09:11 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 170/1251] eta: 0:11:50 lr: 0.000208 loss: 6.0026 (5.9988) grad_norm: 1.7204 (2.0029) time: 0.6361 [2021-03-25 23:09:17 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 180/1251] eta: 0:11:42 lr: 0.000208 loss: 6.0680 (6.0053) grad_norm: 1.7670 (2.0028) time: 0.6351 [2021-03-25 23:09:24 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 190/1251] eta: 0:11:34 lr: 0.000208 loss: 6.0680 (5.9994) grad_norm: 1.8751 (1.9987) time: 0.6368 [2021-03-25 23:09:30 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 200/1251] eta: 0:11:28 lr: 0.000209 loss: 6.1283 (6.0048) grad_norm: 1.9789 (1.9982) time: 0.6444 [2021-03-25 23:09:36 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 210/1251] eta: 0:11:20 lr: 0.000209 loss: 6.2465 (6.0111) grad_norm: 1.9000 (1.9861) time: 0.6453 [2021-03-25 23:09:43 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 220/1251] eta: 0:11:13 lr: 0.000210 loss: 6.1930 (6.0146) grad_norm: 1.7963 (1.9830) time: 0.6400 [2021-03-25 23:09:49 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 230/1251] eta: 0:11:06 lr: 0.000210 loss: 6.1272 (6.0141) grad_norm: 1.8250 (1.9822) time: 0.6377 [2021-03-25 23:09:56 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 240/1251] eta: 0:10:59 lr: 0.000210 loss: 6.1812 (6.0219) grad_norm: 1.8250 (1.9810) time: 0.6395 [2021-03-25 23:10:02 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 250/1251] eta: 0:10:52 lr: 0.000211 loss: 6.1863 (6.0217) grad_norm: 1.8952 (1.9810) time: 0.6450 [2021-03-25 23:10:08 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 260/1251] eta: 0:10:45 lr: 0.000211 loss: 6.0856 (6.0216) grad_norm: 1.9437 (inf) time: 0.6368 [2021-03-25 23:10:15 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 270/1251] eta: 0:10:38 lr: 0.000212 loss: 5.9342 (6.0186) grad_norm: 1.8785 (inf) time: 0.6337 [2021-03-25 23:10:21 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 280/1251] eta: 0:10:31 lr: 0.000212 loss: 6.1548 (6.0223) grad_norm: 1.8717 (inf) time: 0.6416 [2021-03-25 23:10:28 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 290/1251] eta: 0:10:24 lr: 0.000212 loss: 6.1655 (6.0228) grad_norm: 1.9456 (inf) time: 0.6375 [2021-03-25 23:10:34 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 300/1251] eta: 0:10:17 lr: 0.000213 loss: 6.1408 (6.0268) grad_norm: 2.0030 (inf) time: 0.6335 [2021-03-25 23:10:40 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 310/1251] eta: 0:10:10 lr: 0.000213 loss: 6.0800 (6.0224) grad_norm: 2.0616 (inf) time: 0.6379 [2021-03-25 23:10:47 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 320/1251] eta: 0:10:03 lr: 0.000214 loss: 6.0002 (6.0202) grad_norm: 1.9786 (inf) time: 0.6344 [2021-03-25 23:10:53 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 330/1251] eta: 0:09:57 lr: 0.000214 loss: 5.8554 (6.0160) grad_norm: 1.8779 (inf) time: 0.6381 [2021-03-25 23:10:59 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 340/1251] eta: 0:09:50 lr: 0.000214 loss: 6.1094 (6.0208) grad_norm: 1.9389 (inf) time: 0.6423 [2021-03-25 23:11:06 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 350/1251] eta: 0:09:43 lr: 0.000215 loss: 6.2632 (6.0234) grad_norm: 2.0222 (inf) time: 0.6358 [2021-03-25 23:11:12 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 360/1251] eta: 0:09:36 lr: 0.000215 loss: 5.9954 (6.0205) grad_norm: 2.0147 (inf) time: 0.6306 [2021-03-25 23:11:18 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 370/1251] eta: 0:09:29 lr: 0.000216 loss: 5.8885 (6.0169) grad_norm: 1.8233 (inf) time: 0.6300 [2021-03-25 23:11:25 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 380/1251] eta: 0:09:22 lr: 0.000216 loss: 5.8464 (6.0125) grad_norm: 1.8233 (inf) time: 0.6328 [2021-03-25 23:11:31 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 390/1251] eta: 0:09:16 lr: 0.000216 loss: 6.0549 (6.0121) grad_norm: 1.9401 (inf) time: 0.6318 [2021-03-25 23:11:37 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 400/1251] eta: 0:09:09 lr: 0.000217 loss: 6.1350 (6.0152) grad_norm: 1.8143 (inf) time: 0.6280 [2021-03-25 23:11:44 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 410/1251] eta: 0:09:02 lr: 0.000217 loss: 6.0929 (6.0151) grad_norm: 1.8095 (inf) time: 0.6317 [2021-03-25 23:11:50 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 420/1251] eta: 0:08:55 lr: 0.000218 loss: 5.9896 (6.0127) grad_norm: 1.8629 (inf) time: 0.6345 [2021-03-25 23:11:56 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 430/1251] eta: 0:08:49 lr: 0.000218 loss: 6.0491 (6.0124) grad_norm: 1.8748 (inf) time: 0.6383 [2021-03-25 23:12:03 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 440/1251] eta: 0:08:42 lr: 0.000218 loss: 6.0875 (6.0132) grad_norm: 1.9446 (inf) time: 0.6433 [2021-03-25 23:12:09 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 450/1251] eta: 0:08:36 lr: 0.000219 loss: 6.0456 (6.0129) grad_norm: 1.9482 (inf) time: 0.6404 [2021-03-25 23:12:16 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 460/1251] eta: 0:08:29 lr: 0.000219 loss: 6.0456 (6.0133) grad_norm: 1.9217 (inf) time: 0.6411 [2021-03-25 23:12:22 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 470/1251] eta: 0:08:23 lr: 0.000220 loss: 6.0961 (6.0140) grad_norm: 1.7831 (inf) time: 0.6388 [2021-03-25 23:12:28 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 480/1251] eta: 0:08:16 lr: 0.000220 loss: 5.9401 (6.0117) grad_norm: 1.7903 (inf) time: 0.6357 [2021-03-25 23:12:35 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 490/1251] eta: 0:08:10 lr: 0.000220 loss: 6.0505 (6.0123) grad_norm: 1.9460 (inf) time: 0.6366 [2021-03-25 23:12:41 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 500/1251] eta: 0:08:03 lr: 0.000221 loss: 6.0759 (6.0108) grad_norm: 2.0072 (inf) time: 0.6357 [2021-03-25 23:12:47 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 510/1251] eta: 0:07:56 lr: 0.000221 loss: 5.8163 (6.0070) grad_norm: 1.9544 (inf) time: 0.6299 [2021-03-25 23:12:54 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 520/1251] eta: 0:07:50 lr: 0.000222 loss: 6.0015 (6.0090) grad_norm: 1.8291 (inf) time: 0.6312 [2021-03-25 23:13:00 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 530/1251] eta: 0:07:43 lr: 0.000222 loss: 6.0840 (6.0046) grad_norm: 1.8219 (inf) time: 0.6369 [2021-03-25 23:13:06 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 540/1251] eta: 0:07:37 lr: 0.000222 loss: 5.9553 (6.0044) grad_norm: 1.8294 (inf) time: 0.6347 [2021-03-25 23:13:13 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 550/1251] eta: 0:07:30 lr: 0.000223 loss: 6.0531 (6.0026) grad_norm: 1.8294 (inf) time: 0.6400 [2021-03-25 23:13:19 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 560/1251] eta: 0:07:24 lr: 0.000223 loss: 6.0730 (6.0032) grad_norm: 1.9868 (inf) time: 0.6399 [2021-03-25 23:13:26 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 570/1251] eta: 0:07:17 lr: 0.000224 loss: 6.0145 (6.0000) grad_norm: 1.9868 (inf) time: 0.6335 [2021-03-25 23:13:32 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 580/1251] eta: 0:07:11 lr: 0.000224 loss: 6.0650 (5.9995) grad_norm: 1.9167 (inf) time: 0.6335 [2021-03-25 23:13:38 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 590/1251] eta: 0:07:04 lr: 0.000224 loss: 6.1370 (5.9998) grad_norm: 1.9167 (inf) time: 0.6344 [2021-03-25 23:13:45 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 600/1251] eta: 0:06:58 lr: 0.000225 loss: 6.0083 (5.9977) grad_norm: 1.9387 (inf) time: 0.6325 [2021-03-25 23:13:51 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 610/1251] eta: 0:06:51 lr: 0.000225 loss: 5.9796 (5.9976) grad_norm: 1.9387 (inf) time: 0.6304 [2021-03-25 23:13:57 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 620/1251] eta: 0:06:45 lr: 0.000226 loss: 6.0433 (5.9969) grad_norm: 1.8201 (inf) time: 0.6347 [2021-03-25 23:14:04 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 630/1251] eta: 0:06:38 lr: 0.000226 loss: 6.0488 (5.9987) grad_norm: 1.8199 (inf) time: 0.6395 [2021-03-25 23:14:10 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 640/1251] eta: 0:06:32 lr: 0.000226 loss: 6.0655 (5.9977) grad_norm: 1.9297 (inf) time: 0.6399 [2021-03-25 23:14:16 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 650/1251] eta: 0:06:25 lr: 0.000227 loss: 5.9867 (5.9959) grad_norm: 2.0802 (inf) time: 0.6400 [2021-03-25 23:14:23 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 660/1251] eta: 0:06:19 lr: 0.000227 loss: 5.8668 (5.9938) grad_norm: 2.0802 (inf) time: 0.6359 [2021-03-25 23:14:29 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 670/1251] eta: 0:06:12 lr: 0.000228 loss: 5.8668 (5.9936) grad_norm: 1.9035 (inf) time: 0.6327 [2021-03-25 23:14:35 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 680/1251] eta: 0:06:06 lr: 0.000228 loss: 6.0541 (5.9936) grad_norm: 1.9269 (inf) time: 0.6329 [2021-03-25 23:14:42 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 690/1251] eta: 0:05:59 lr: 0.000228 loss: 5.9741 (5.9927) grad_norm: 1.9856 (inf) time: 0.6329 [2021-03-25 23:14:48 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 700/1251] eta: 0:05:53 lr: 0.000229 loss: 6.0536 (5.9926) grad_norm: 1.9441 (inf) time: 0.6338 [2021-03-25 23:14:54 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 710/1251] eta: 0:05:46 lr: 0.000229 loss: 6.0536 (5.9906) grad_norm: 1.8795 (inf) time: 0.6332 [2021-03-25 23:15:01 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 720/1251] eta: 0:05:40 lr: 0.000230 loss: 5.6855 (5.9878) grad_norm: 2.0070 (inf) time: 0.6304 [2021-03-25 23:15:07 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 730/1251] eta: 0:05:33 lr: 0.000230 loss: 5.7028 (5.9854) grad_norm: 1.9148 (inf) time: 0.6272 [2021-03-25 23:15:13 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 740/1251] eta: 0:05:27 lr: 0.000230 loss: 5.9148 (5.9850) grad_norm: 1.7715 (inf) time: 0.6315 [2021-03-25 23:15:20 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 750/1251] eta: 0:05:21 lr: 0.000231 loss: 5.9600 (5.9854) grad_norm: 1.7715 (inf) time: 0.6408 [2021-03-25 23:15:26 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 760/1251] eta: 0:05:14 lr: 0.000231 loss: 5.9612 (5.9863) grad_norm: 1.8400 (inf) time: 0.6444 [2021-03-25 23:15:33 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 770/1251] eta: 0:05:08 lr: 0.000232 loss: 5.9538 (5.9852) grad_norm: 1.8400 (inf) time: 0.6372 [2021-03-25 23:15:39 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 780/1251] eta: 0:05:01 lr: 0.000232 loss: 5.9682 (5.9849) grad_norm: 1.9310 (inf) time: 0.6342 [2021-03-25 23:15:45 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 790/1251] eta: 0:04:55 lr: 0.000232 loss: 6.0144 (5.9840) grad_norm: 1.8027 (inf) time: 0.6378 [2021-03-25 23:15:52 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 800/1251] eta: 0:04:48 lr: 0.000233 loss: 5.9154 (5.9827) grad_norm: 1.7172 (inf) time: 0.6330 [2021-03-25 23:15:58 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 810/1251] eta: 0:04:42 lr: 0.000233 loss: 5.9205 (5.9816) grad_norm: 1.6364 (inf) time: 0.6291 [2021-03-25 23:16:04 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 820/1251] eta: 0:04:35 lr: 0.000234 loss: 6.0388 (5.9826) grad_norm: 1.7013 (inf) time: 0.6316 [2021-03-25 23:16:11 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 830/1251] eta: 0:04:29 lr: 0.000234 loss: 6.0522 (5.9818) grad_norm: 1.9121 (inf) time: 0.6281 [2021-03-25 23:16:17 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 840/1251] eta: 0:04:23 lr: 0.000234 loss: 5.9900 (5.9816) grad_norm: 1.9158 (inf) time: 0.6342 [2021-03-25 23:16:23 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 850/1251] eta: 0:04:16 lr: 0.000235 loss: 5.9815 (5.9805) grad_norm: 1.8069 (inf) time: 0.6471 [2021-03-25 23:16:30 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 860/1251] eta: 0:04:10 lr: 0.000235 loss: 6.0963 (5.9836) grad_norm: 1.9182 (inf) time: 0.6389 [2021-03-25 23:16:36 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 870/1251] eta: 0:04:03 lr: 0.000236 loss: 6.1686 (5.9855) grad_norm: 1.9581 (inf) time: 0.6344 [2021-03-25 23:16:42 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 880/1251] eta: 0:03:57 lr: 0.000236 loss: 6.1450 (5.9860) grad_norm: 2.0006 (inf) time: 0.6377 [2021-03-25 23:16:49 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 890/1251] eta: 0:03:51 lr: 0.000236 loss: 6.0688 (5.9842) grad_norm: 1.7231 (inf) time: 0.6319 [2021-03-25 23:16:55 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 900/1251] eta: 0:03:44 lr: 0.000237 loss: 5.7063 (5.9830) grad_norm: 1.7795 (inf) time: 0.6307 [2021-03-25 23:17:01 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 910/1251] eta: 0:03:38 lr: 0.000237 loss: 5.9975 (5.9836) grad_norm: 2.1402 (inf) time: 0.6303 [2021-03-25 23:17:08 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 920/1251] eta: 0:03:31 lr: 0.000238 loss: 6.0511 (5.9836) grad_norm: 2.1404 (inf) time: 0.6308 [2021-03-25 23:17:14 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 930/1251] eta: 0:03:25 lr: 0.000238 loss: 6.0828 (5.9838) grad_norm: 2.0327 (inf) time: 0.6298 [2021-03-25 23:17:20 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 940/1251] eta: 0:03:18 lr: 0.000238 loss: 6.1198 (5.9852) grad_norm: 2.1425 (inf) time: 0.6313 [2021-03-25 23:17:27 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 950/1251] eta: 0:03:12 lr: 0.000239 loss: 6.0513 (5.9836) grad_norm: 1.7971 (inf) time: 0.6359 [2021-03-25 23:17:33 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 960/1251] eta: 0:03:06 lr: 0.000239 loss: 5.9304 (5.9820) grad_norm: 1.7971 (inf) time: 0.6379 [2021-03-25 23:17:39 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 970/1251] eta: 0:02:59 lr: 0.000240 loss: 6.0094 (5.9824) grad_norm: 1.8436 (inf) time: 0.6390 [2021-03-25 23:17:46 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 980/1251] eta: 0:02:53 lr: 0.000240 loss: 6.0317 (5.9813) grad_norm: 1.8513 (inf) time: 0.6341 [2021-03-25 23:17:52 swin_base_patch4_window7_224] INFO: Epoch: [4] [ 990/1251] eta: 0:02:46 lr: 0.000240 loss: 5.7991 (5.9801) grad_norm: 1.8338 (inf) time: 0.6418 [2021-03-25 23:17:59 swin_base_patch4_window7_224] INFO: Epoch: [4] [1000/1251] eta: 0:02:40 lr: 0.000241 loss: 5.7744 (5.9796) grad_norm: 1.9037 (inf) time: 0.6397 [2021-03-25 23:18:05 swin_base_patch4_window7_224] INFO: Epoch: [4] [1010/1251] eta: 0:02:34 lr: 0.000241 loss: 6.1094 (5.9798) grad_norm: 1.9037 (inf) time: 0.6336 [2021-03-25 23:18:11 swin_base_patch4_window7_224] INFO: Epoch: [4] [1020/1251] eta: 0:02:27 lr: 0.000242 loss: 6.0112 (5.9783) grad_norm: 1.8770 (inf) time: 0.6342 [2021-03-25 23:18:18 swin_base_patch4_window7_224] INFO: Epoch: [4] [1030/1251] eta: 0:02:21 lr: 0.000242 loss: 5.5854 (5.9750) grad_norm: 2.0830 (inf) time: 0.6335 [2021-03-25 23:18:24 swin_base_patch4_window7_224] INFO: Epoch: [4] [1040/1251] eta: 0:02:14 lr: 0.000242 loss: 5.7851 (5.9740) grad_norm: 1.8808 (inf) time: 0.6391 [2021-03-25 23:18:30 swin_base_patch4_window7_224] INFO: Epoch: [4] [1050/1251] eta: 0:02:08 lr: 0.000243 loss: 5.9051 (5.9718) grad_norm: 1.8674 (inf) time: 0.6391 [2021-03-25 23:18:37 swin_base_patch4_window7_224] INFO: Epoch: [4] [1060/1251] eta: 0:02:02 lr: 0.000243 loss: 5.7481 (5.9710) grad_norm: 1.9280 (inf) time: 0.6407 [2021-03-25 23:18:43 swin_base_patch4_window7_224] INFO: Epoch: [4] [1070/1251] eta: 0:01:55 lr: 0.000244 loss: 5.9487 (5.9708) grad_norm: 1.8903 (inf) time: 0.6379 [2021-03-25 23:18:50 swin_base_patch4_window7_224] INFO: Epoch: [4] [1080/1251] eta: 0:01:49 lr: 0.000244 loss: 5.9664 (5.9704) grad_norm: 1.9249 (inf) time: 0.6398 [2021-03-25 23:18:56 swin_base_patch4_window7_224] INFO: Epoch: [4] [1090/1251] eta: 0:01:42 lr: 0.000244 loss: 6.0377 (5.9699) grad_norm: 1.9554 (inf) time: 0.6462 [2021-03-25 23:19:03 swin_base_patch4_window7_224] INFO: Epoch: [4] [1100/1251] eta: 0:01:36 lr: 0.000245 loss: 5.8423 (5.9679) grad_norm: 1.8579 (inf) time: 0.6469 [2021-03-25 23:19:09 swin_base_patch4_window7_224] INFO: Epoch: [4] [1110/1251] eta: 0:01:30 lr: 0.000245 loss: 5.6518 (5.9644) grad_norm: 1.8466 (inf) time: 0.6386 [2021-03-25 23:19:15 swin_base_patch4_window7_224] INFO: Epoch: [4] [1120/1251] eta: 0:01:23 lr: 0.000246 loss: 5.7790 (5.9639) grad_norm: 1.9852 (inf) time: 0.6329 [2021-03-25 23:19:22 swin_base_patch4_window7_224] INFO: Epoch: [4] [1130/1251] eta: 0:01:17 lr: 0.000246 loss: 5.9755 (5.9634) grad_norm: 2.0415 (inf) time: 0.6381 [2021-03-25 23:19:28 swin_base_patch4_window7_224] INFO: Epoch: [4] [1140/1251] eta: 0:01:10 lr: 0.000246 loss: 5.7704 (5.9616) grad_norm: 1.7874 (inf) time: 0.6387 [2021-03-25 23:19:34 swin_base_patch4_window7_224] INFO: Epoch: [4] [1150/1251] eta: 0:01:04 lr: 0.000247 loss: 5.7785 (5.9617) grad_norm: 1.7507 (inf) time: 0.6385 [2021-03-25 23:19:41 swin_base_patch4_window7_224] INFO: Epoch: [4] [1160/1251] eta: 0:00:58 lr: 0.000247 loss: 5.9778 (5.9613) grad_norm: 1.7049 (inf) time: 0.6383 [2021-03-25 23:19:47 swin_base_patch4_window7_224] INFO: Epoch: [4] [1170/1251] eta: 0:00:51 lr: 0.000248 loss: 6.0225 (5.9623) grad_norm: 1.8713 (inf) time: 0.6364 [2021-03-25 23:19:54 swin_base_patch4_window7_224] INFO: Epoch: [4] [1180/1251] eta: 0:00:45 lr: 0.000248 loss: 5.9419 (5.9611) grad_norm: 1.9604 (inf) time: 0.6437 [2021-03-25 23:20:00 swin_base_patch4_window7_224] INFO: Epoch: [4] [1190/1251] eta: 0:00:39 lr: 0.000248 loss: 5.8807 (5.9608) grad_norm: 1.8809 (inf) time: 0.6465 [2021-03-25 23:20:06 swin_base_patch4_window7_224] INFO: Epoch: [4] [1200/1251] eta: 0:00:32 lr: 0.000249 loss: 6.0566 (5.9613) grad_norm: 1.8685 (inf) time: 0.6363 [2021-03-25 23:20:13 swin_base_patch4_window7_224] INFO: Epoch: [4] [1210/1251] eta: 0:00:26 lr: 0.000249 loss: 5.7733 (5.9578) grad_norm: 1.9345 (inf) time: 0.6327 [2021-03-25 23:20:19 swin_base_patch4_window7_224] INFO: Epoch: [4] [1220/1251] eta: 0:00:19 lr: 0.000250 loss: 5.7733 (5.9577) grad_norm: 1.8267 (inf) time: 0.6350 [2021-03-25 23:20:26 swin_base_patch4_window7_224] INFO: Epoch: [4] [1230/1251] eta: 0:00:13 lr: 0.000250 loss: 5.9135 (5.9565) grad_norm: 1.8267 (inf) time: 0.6386 [2021-03-25 23:20:32 swin_base_patch4_window7_224] INFO: Epoch: [4] [1240/1251] eta: 0:00:07 lr: 0.000250 loss: 5.9687 (5.9568) grad_norm: 1.9089 (inf) time: 0.6384 [2021-03-25 23:20:38 swin_base_patch4_window7_224] INFO: Epoch: [4] [1250/1251] eta: 0:00:00 lr: 0.000251 loss: 6.0083 (5.9572) grad_norm: 1.9311 (inf) time: 0.6354 [2021-03-25 23:20:42 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:30 loss: 3.7517 (3.7517) acc1: 25.0000 (25.0000) acc5: 51.5625 (51.5625) [2021-03-25 23:20:44 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 4.0245 (4.0699) acc1: 20.3125 (19.8864) acc5: 42.1875 (42.4716) [2021-03-25 23:20:47 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 4.0245 (4.0300) acc1: 20.3125 (21.0565) acc5: 42.1875 (44.0476) [2021-03-25 23:20:49 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 4.0671 (4.0493) acc1: 21.8750 (21.6230) acc5: 45.3125 (44.1028) [2021-03-25 23:20:51 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 4.0546 (4.0439) acc1: 21.8750 (21.6082) acc5: 43.7500 (43.5595) [2021-03-25 23:20:52 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 4.0461 (4.0396) acc1: 21.8750 (21.6640) acc5: 43.7500 (43.5840) [2021-03-25 23:20:54 swin_base_patch4_window7_224] INFO: * Acc@1 21.236 Acc@5 43.938 loss 4.034 [2021-03-25 23:20:54 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 21.2% [2021-03-25 23:20:54 swin_base_patch4_window7_224] INFO: Max accuracy: 21.24% [2021-03-25 23:20:58 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 0/1251] eta: 1:29:24 lr: 0.000251 loss: 5.9603 (5.9603) grad_norm: 1.4974 (1.4974) time: 4.2883 [2021-03-25 23:21:04 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 10/1251] eta: 0:20:13 lr: 0.000251 loss: 6.0036 (5.8836) grad_norm: 1.8744 (2.1066) time: 0.9774 [2021-03-25 23:21:11 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 20/1251] eta: 0:16:45 lr: 0.000252 loss: 6.0036 (5.8639) grad_norm: 1.9686 (2.1699) time: 0.6433 [2021-03-25 23:21:17 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 30/1251] eta: 0:15:23 lr: 0.000252 loss: 5.9190 (5.8603) grad_norm: 1.8886 (2.0747) time: 0.6348 [2021-03-25 23:21:24 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 40/1251] eta: 0:14:43 lr: 0.000252 loss: 6.1247 (5.9326) grad_norm: 1.7041 (1.9685) time: 0.6373 [2021-03-25 23:21:30 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 50/1251] eta: 0:14:16 lr: 0.000253 loss: 6.0498 (5.9460) grad_norm: 1.6684 (1.9223) time: 0.6462 [2021-03-25 23:21:36 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 60/1251] eta: 0:13:54 lr: 0.000253 loss: 5.9853 (5.9462) grad_norm: 1.8133 (1.9181) time: 0.6426 [2021-03-25 23:21:43 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 70/1251] eta: 0:13:34 lr: 0.000254 loss: 5.9457 (5.9426) grad_norm: 1.8133 (1.9011) time: 0.6312 [2021-03-25 23:21:49 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 80/1251] eta: 0:13:21 lr: 0.000254 loss: 5.9457 (5.9259) grad_norm: 1.7373 (1.9132) time: 0.6342 [2021-03-25 23:21:55 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 90/1251] eta: 0:13:08 lr: 0.000254 loss: 6.0158 (5.9145) grad_norm: 1.7373 (1.9050) time: 0.6418 [2021-03-25 23:22:02 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 100/1251] eta: 0:12:57 lr: 0.000255 loss: 5.9324 (5.8977) grad_norm: 1.8276 (1.9125) time: 0.6376 [2021-03-25 23:22:08 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 110/1251] eta: 0:12:45 lr: 0.000255 loss: 5.9786 (5.9046) grad_norm: 1.8736 (1.9066) time: 0.6322 [2021-03-25 23:22:15 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 120/1251] eta: 0:12:35 lr: 0.000256 loss: 6.0888 (5.9109) grad_norm: 2.0206 (1.9394) time: 0.6342 [2021-03-25 23:22:21 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 130/1251] eta: 0:12:26 lr: 0.000256 loss: 5.9363 (5.9053) grad_norm: 2.0994 (1.9570) time: 0.6392 [2021-03-25 23:22:27 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 140/1251] eta: 0:12:17 lr: 0.000256 loss: 5.9191 (5.9048) grad_norm: 1.9457 (1.9639) time: 0.6346 [2021-03-25 23:22:34 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 150/1251] eta: 0:12:08 lr: 0.000257 loss: 5.9191 (5.9035) grad_norm: 2.0006 (1.9736) time: 0.6321 [2021-03-25 23:22:40 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 160/1251] eta: 0:12:00 lr: 0.000257 loss: 5.8171 (5.8966) grad_norm: 1.9822 (1.9772) time: 0.6346 [2021-03-25 23:22:46 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 170/1251] eta: 0:11:51 lr: 0.000258 loss: 5.8838 (5.8973) grad_norm: 1.9822 (1.9769) time: 0.6351 [2021-03-25 23:22:53 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 180/1251] eta: 0:11:44 lr: 0.000258 loss: 5.8086 (5.8876) grad_norm: 1.9265 (1.9829) time: 0.6368 [2021-03-25 23:22:59 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 190/1251] eta: 0:11:35 lr: 0.000258 loss: 5.7932 (5.8788) grad_norm: 1.7629 (1.9745) time: 0.6345 [2021-03-25 23:23:05 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 200/1251] eta: 0:11:28 lr: 0.000259 loss: 5.8569 (5.8668) grad_norm: 1.8651 (1.9817) time: 0.6316 [2021-03-25 23:23:12 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 210/1251] eta: 0:11:20 lr: 0.000259 loss: 5.9301 (5.8649) grad_norm: 1.8361 (1.9742) time: 0.6317 [2021-03-25 23:23:18 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 220/1251] eta: 0:11:13 lr: 0.000260 loss: 5.8118 (5.8561) grad_norm: 1.8242 (1.9794) time: 0.6335 [2021-03-25 23:23:24 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 230/1251] eta: 0:11:06 lr: 0.000260 loss: 5.5802 (5.8517) grad_norm: 1.9028 (1.9748) time: 0.6407 [2021-03-25 23:23:31 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 240/1251] eta: 0:10:58 lr: 0.000260 loss: 5.9513 (5.8517) grad_norm: 1.8675 (1.9698) time: 0.6351 [2021-03-25 23:23:37 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 250/1251] eta: 0:10:51 lr: 0.000261 loss: 5.9513 (5.8460) grad_norm: 1.7940 (1.9671) time: 0.6344 [2021-03-25 23:23:43 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 260/1251] eta: 0:10:44 lr: 0.000261 loss: 5.9004 (5.8513) grad_norm: 1.7919 (1.9621) time: 0.6389 [2021-03-25 23:23:50 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 270/1251] eta: 0:10:37 lr: 0.000262 loss: 5.8628 (5.8498) grad_norm: 1.8788 (1.9644) time: 0.6340 [2021-03-25 23:23:56 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 280/1251] eta: 0:10:30 lr: 0.000262 loss: 5.8366 (5.8496) grad_norm: 1.9084 (1.9638) time: 0.6333 [2021-03-25 23:24:02 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 290/1251] eta: 0:10:23 lr: 0.000262 loss: 5.9177 (5.8526) grad_norm: 1.7596 (1.9575) time: 0.6328 [2021-03-25 23:24:09 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 300/1251] eta: 0:10:16 lr: 0.000263 loss: 5.9448 (5.8563) grad_norm: 1.7925 (1.9566) time: 0.6343 [2021-03-25 23:24:15 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 310/1251] eta: 0:10:09 lr: 0.000263 loss: 5.7615 (5.8543) grad_norm: 2.0927 (1.9677) time: 0.6342 [2021-03-25 23:24:22 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 320/1251] eta: 0:10:02 lr: 0.000264 loss: 5.8526 (5.8550) grad_norm: 2.1384 (1.9652) time: 0.6344 [2021-03-25 23:24:28 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 330/1251] eta: 0:09:55 lr: 0.000264 loss: 5.9298 (5.8527) grad_norm: 2.0082 (1.9732) time: 0.6364 [2021-03-25 23:24:34 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 340/1251] eta: 0:09:49 lr: 0.000264 loss: 5.9466 (5.8527) grad_norm: 2.0082 (1.9707) time: 0.6373 [2021-03-25 23:24:41 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 350/1251] eta: 0:09:42 lr: 0.000265 loss: 5.6470 (5.8468) grad_norm: 1.9915 (1.9742) time: 0.6379 [2021-03-25 23:24:47 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 360/1251] eta: 0:09:35 lr: 0.000265 loss: 5.9091 (5.8474) grad_norm: 1.8479 (1.9715) time: 0.6280 [2021-03-25 23:24:53 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 370/1251] eta: 0:09:28 lr: 0.000266 loss: 6.0093 (5.8524) grad_norm: 1.8109 (1.9692) time: 0.6287 [2021-03-25 23:25:00 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 380/1251] eta: 0:09:21 lr: 0.000266 loss: 6.0160 (5.8505) grad_norm: 1.8811 (inf) time: 0.6341 [2021-03-25 23:25:06 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 390/1251] eta: 0:09:15 lr: 0.000266 loss: 5.9917 (5.8502) grad_norm: 2.1913 (inf) time: 0.6297 [2021-03-25 23:25:12 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 400/1251] eta: 0:09:08 lr: 0.000267 loss: 5.8355 (5.8456) grad_norm: 1.8712 (inf) time: 0.6282 [2021-03-25 23:25:18 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 410/1251] eta: 0:09:01 lr: 0.000267 loss: 5.8367 (5.8450) grad_norm: 1.7930 (inf) time: 0.6260 [2021-03-25 23:25:25 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 420/1251] eta: 0:08:54 lr: 0.000268 loss: 5.8206 (5.8400) grad_norm: 1.8017 (inf) time: 0.6332 [2021-03-25 23:25:31 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 430/1251] eta: 0:08:48 lr: 0.000268 loss: 5.5817 (5.8352) grad_norm: 1.8508 (inf) time: 0.6389 [2021-03-25 23:25:37 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 440/1251] eta: 0:08:41 lr: 0.000268 loss: 5.7168 (5.8324) grad_norm: 1.9898 (inf) time: 0.6369 [2021-03-25 23:25:44 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 450/1251] eta: 0:08:35 lr: 0.000269 loss: 5.9257 (5.8339) grad_norm: 1.8662 (inf) time: 0.6382 [2021-03-25 23:25:50 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 460/1251] eta: 0:08:28 lr: 0.000269 loss: 5.9316 (5.8353) grad_norm: 1.8204 (inf) time: 0.6391 [2021-03-25 23:25:57 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 470/1251] eta: 0:08:22 lr: 0.000270 loss: 5.9316 (5.8375) grad_norm: 1.7119 (inf) time: 0.6328 [2021-03-25 23:26:03 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 480/1251] eta: 0:08:15 lr: 0.000270 loss: 5.9827 (5.8370) grad_norm: 1.7897 (inf) time: 0.6297 [2021-03-25 23:26:09 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 490/1251] eta: 0:08:09 lr: 0.000270 loss: 5.6766 (5.8317) grad_norm: 1.9056 (inf) time: 0.6344 [2021-03-25 23:26:16 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 500/1251] eta: 0:08:02 lr: 0.000271 loss: 5.6791 (5.8318) grad_norm: 1.8139 (inf) time: 0.6346 [2021-03-25 23:26:22 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 510/1251] eta: 0:07:55 lr: 0.000271 loss: 5.6610 (5.8282) grad_norm: 1.8981 (inf) time: 0.6357 [2021-03-25 23:26:28 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 520/1251] eta: 0:07:49 lr: 0.000272 loss: 5.6610 (5.8298) grad_norm: 2.1730 (inf) time: 0.6349 [2021-03-25 23:26:35 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 530/1251] eta: 0:07:42 lr: 0.000272 loss: 6.0178 (5.8293) grad_norm: 1.8306 (inf) time: 0.6347 [2021-03-25 23:26:41 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 540/1251] eta: 0:07:36 lr: 0.000272 loss: 6.1169 (5.8347) grad_norm: 1.7401 (inf) time: 0.6365 [2021-03-25 23:26:47 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 550/1251] eta: 0:07:29 lr: 0.000273 loss: 6.0380 (5.8298) grad_norm: 1.7976 (inf) time: 0.6362 [2021-03-25 23:26:54 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 560/1251] eta: 0:07:23 lr: 0.000273 loss: 5.7649 (5.8304) grad_norm: 2.0465 (inf) time: 0.6387 [2021-03-25 23:27:00 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 570/1251] eta: 0:07:16 lr: 0.000274 loss: 5.8706 (5.8302) grad_norm: 2.0665 (inf) time: 0.6347 [2021-03-25 23:27:06 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 580/1251] eta: 0:07:10 lr: 0.000274 loss: 5.6924 (5.8296) grad_norm: 2.0711 (inf) time: 0.6310 [2021-03-25 23:27:13 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 590/1251] eta: 0:07:03 lr: 0.000274 loss: 5.9976 (5.8304) grad_norm: 1.7935 (inf) time: 0.6307 [2021-03-25 23:27:19 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 600/1251] eta: 0:06:57 lr: 0.000275 loss: 5.5365 (5.8232) grad_norm: 1.8054 (inf) time: 0.6309 [2021-03-25 23:27:25 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 610/1251] eta: 0:06:50 lr: 0.000275 loss: 5.3465 (5.8202) grad_norm: 1.8836 (inf) time: 0.6341 [2021-03-25 23:27:32 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 620/1251] eta: 0:06:44 lr: 0.000276 loss: 5.7467 (5.8210) grad_norm: 1.9577 (inf) time: 0.6358 [2021-03-25 23:27:38 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 630/1251] eta: 0:06:37 lr: 0.000276 loss: 5.7898 (5.8205) grad_norm: 2.1220 (inf) time: 0.6347 [2021-03-25 23:27:44 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 640/1251] eta: 0:06:31 lr: 0.000276 loss: 5.7898 (5.8220) grad_norm: 1.9522 (inf) time: 0.6320 [2021-03-25 23:27:51 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 650/1251] eta: 0:06:24 lr: 0.000277 loss: 5.7823 (5.8180) grad_norm: 1.9894 (inf) time: 0.6324 [2021-03-25 23:27:57 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 660/1251] eta: 0:06:18 lr: 0.000277 loss: 5.7262 (5.8180) grad_norm: 1.9241 (inf) time: 0.6368 [2021-03-25 23:28:04 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 670/1251] eta: 0:06:12 lr: 0.000278 loss: 5.7269 (5.8166) grad_norm: 1.8762 (inf) time: 0.6417 [2021-03-25 23:28:10 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 680/1251] eta: 0:06:05 lr: 0.000278 loss: 5.8469 (5.8177) grad_norm: 1.9843 (inf) time: 0.6404 [2021-03-25 23:28:16 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 690/1251] eta: 0:05:59 lr: 0.000278 loss: 5.8488 (5.8146) grad_norm: 2.1415 (inf) time: 0.6318 [2021-03-25 23:28:23 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 700/1251] eta: 0:05:52 lr: 0.000279 loss: 5.7623 (5.8109) grad_norm: 2.1415 (nan) time: 0.6310 [2021-03-25 23:28:29 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 710/1251] eta: 0:05:46 lr: 0.000279 loss: 5.7224 (5.8107) grad_norm: 1.9853 (nan) time: 0.6367 [2021-03-25 23:28:35 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 720/1251] eta: 0:05:39 lr: 0.000279 loss: 5.6646 (5.8084) grad_norm: 1.8732 (nan) time: 0.6408 [2021-03-25 23:28:42 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 730/1251] eta: 0:05:33 lr: 0.000280 loss: 5.6606 (5.8069) grad_norm: 1.9001 (nan) time: 0.6359 [2021-03-25 23:28:48 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 740/1251] eta: 0:05:27 lr: 0.000280 loss: 5.6543 (5.8048) grad_norm: 1.9061 (nan) time: 0.6356 [2021-03-25 23:28:54 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 750/1251] eta: 0:05:20 lr: 0.000281 loss: 5.4558 (5.7999) grad_norm: 1.8505 (nan) time: 0.6390 [2021-03-25 23:29:01 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 760/1251] eta: 0:05:14 lr: 0.000281 loss: 5.6333 (5.8015) grad_norm: 1.7735 (nan) time: 0.6311 [2021-03-25 23:29:07 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 770/1251] eta: 0:05:07 lr: 0.000281 loss: 5.8465 (5.8000) grad_norm: 1.7388 (nan) time: 0.6293 [2021-03-25 23:29:13 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 780/1251] eta: 0:05:01 lr: 0.000282 loss: 5.8247 (5.8007) grad_norm: 1.7388 (nan) time: 0.6386 [2021-03-25 23:29:20 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 790/1251] eta: 0:04:54 lr: 0.000282 loss: 5.8277 (5.7988) grad_norm: 1.8594 (nan) time: 0.6371 [2021-03-25 23:29:26 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 800/1251] eta: 0:04:48 lr: 0.000283 loss: 5.7740 (5.7967) grad_norm: 1.8626 (nan) time: 0.6359 [2021-03-25 23:29:33 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 810/1251] eta: 0:04:42 lr: 0.000283 loss: 5.9481 (5.7981) grad_norm: 1.8867 (nan) time: 0.6436 [2021-03-25 23:29:39 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 820/1251] eta: 0:04:35 lr: 0.000283 loss: 5.8865 (5.7973) grad_norm: 1.8867 (nan) time: 0.6396 [2021-03-25 23:29:45 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 830/1251] eta: 0:04:29 lr: 0.000284 loss: 5.7157 (5.7948) grad_norm: 1.9861 (nan) time: 0.6360 [2021-03-25 23:29:52 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 840/1251] eta: 0:04:22 lr: 0.000284 loss: 5.7588 (5.7959) grad_norm: 1.9287 (nan) time: 0.6364 [2021-03-25 23:29:58 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 850/1251] eta: 0:04:16 lr: 0.000285 loss: 5.8926 (5.7968) grad_norm: 1.8564 (nan) time: 0.6398 [2021-03-25 23:30:05 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 860/1251] eta: 0:04:10 lr: 0.000285 loss: 5.7160 (5.7957) grad_norm: 1.8815 (nan) time: 0.6404 [2021-03-25 23:30:11 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 870/1251] eta: 0:04:03 lr: 0.000285 loss: 5.7281 (5.7955) grad_norm: 1.9391 (nan) time: 0.6391 [2021-03-25 23:30:17 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 880/1251] eta: 0:03:57 lr: 0.000286 loss: 5.8629 (5.7959) grad_norm: 1.9391 (nan) time: 0.6424 [2021-03-25 23:30:24 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 890/1251] eta: 0:03:50 lr: 0.000286 loss: 5.7976 (5.7953) grad_norm: 1.8796 (nan) time: 0.6412 [2021-03-25 23:30:30 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 900/1251] eta: 0:03:44 lr: 0.000287 loss: 6.0586 (5.7983) grad_norm: 1.9466 (nan) time: 0.6339 [2021-03-25 23:30:36 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 910/1251] eta: 0:03:38 lr: 0.000287 loss: 6.0562 (5.7989) grad_norm: 1.9466 (nan) time: 0.6332 [2021-03-25 23:30:43 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 920/1251] eta: 0:03:31 lr: 0.000287 loss: 5.9722 (5.8001) grad_norm: 1.9078 (nan) time: 0.6349 [2021-03-25 23:30:49 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 930/1251] eta: 0:03:25 lr: 0.000288 loss: 5.8092 (5.7968) grad_norm: 1.9078 (nan) time: 0.6354 [2021-03-25 23:30:55 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 940/1251] eta: 0:03:18 lr: 0.000288 loss: 5.6955 (5.7960) grad_norm: 1.9016 (nan) time: 0.6337 [2021-03-25 23:31:02 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 950/1251] eta: 0:03:12 lr: 0.000289 loss: 5.7762 (5.7945) grad_norm: 1.9922 (nan) time: 0.6361 [2021-03-25 23:31:08 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 960/1251] eta: 0:03:06 lr: 0.000289 loss: 5.8121 (5.7938) grad_norm: 2.0060 (nan) time: 0.6421 [2021-03-25 23:31:15 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 970/1251] eta: 0:02:59 lr: 0.000289 loss: 5.8753 (5.7947) grad_norm: 1.8881 (nan) time: 0.6430 [2021-03-25 23:31:21 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 980/1251] eta: 0:02:53 lr: 0.000290 loss: 5.8910 (5.7933) grad_norm: 1.8045 (nan) time: 0.6397 [2021-03-25 23:31:27 swin_base_patch4_window7_224] INFO: Epoch: [5] [ 990/1251] eta: 0:02:46 lr: 0.000290 loss: 5.8223 (5.7937) grad_norm: 1.7508 (nan) time: 0.6325 [2021-03-25 23:31:34 swin_base_patch4_window7_224] INFO: Epoch: [5] [1000/1251] eta: 0:02:40 lr: 0.000291 loss: 5.8353 (5.7930) grad_norm: 1.6642 (nan) time: 0.6319 [2021-03-25 23:31:40 swin_base_patch4_window7_224] INFO: Epoch: [5] [1010/1251] eta: 0:02:34 lr: 0.000291 loss: 5.8683 (5.7942) grad_norm: 1.6599 (nan) time: 0.6317 [2021-03-25 23:31:46 swin_base_patch4_window7_224] INFO: Epoch: [5] [1020/1251] eta: 0:02:27 lr: 0.000291 loss: 5.9899 (5.7951) grad_norm: 1.8176 (nan) time: 0.6328 [2021-03-25 23:31:53 swin_base_patch4_window7_224] INFO: Epoch: [5] [1030/1251] eta: 0:02:21 lr: 0.000292 loss: 5.6723 (5.7911) grad_norm: 2.1284 (nan) time: 0.6332 [2021-03-25 23:31:59 swin_base_patch4_window7_224] INFO: Epoch: [5] [1040/1251] eta: 0:02:14 lr: 0.000292 loss: 5.6266 (5.7910) grad_norm: 1.9756 (nan) time: 0.6327 [2021-03-25 23:32:05 swin_base_patch4_window7_224] INFO: Epoch: [5] [1050/1251] eta: 0:02:08 lr: 0.000293 loss: 5.7774 (5.7912) grad_norm: 1.9198 (nan) time: 0.6333 [2021-03-25 23:32:12 swin_base_patch4_window7_224] INFO: Epoch: [5] [1060/1251] eta: 0:02:02 lr: 0.000293 loss: 5.7774 (5.7917) grad_norm: 1.9986 (nan) time: 0.6308 [2021-03-25 23:32:18 swin_base_patch4_window7_224] INFO: Epoch: [5] [1070/1251] eta: 0:01:55 lr: 0.000293 loss: 5.8930 (5.7906) grad_norm: 1.9986 (nan) time: 0.6281 [2021-03-25 23:32:24 swin_base_patch4_window7_224] INFO: Epoch: [5] [1080/1251] eta: 0:01:49 lr: 0.000294 loss: 5.7025 (5.7883) grad_norm: 1.8850 (nan) time: 0.6292 [2021-03-25 23:32:31 swin_base_patch4_window7_224] INFO: Epoch: [5] [1090/1251] eta: 0:01:42 lr: 0.000294 loss: 5.8217 (5.7891) grad_norm: 1.8850 (nan) time: 0.6322 [2021-03-25 23:32:37 swin_base_patch4_window7_224] INFO: Epoch: [5] [1100/1251] eta: 0:01:36 lr: 0.000295 loss: 5.8529 (5.7893) grad_norm: 1.8240 (nan) time: 0.6312 [2021-03-25 23:32:43 swin_base_patch4_window7_224] INFO: Epoch: [5] [1110/1251] eta: 0:01:30 lr: 0.000295 loss: 5.7729 (5.7893) grad_norm: 1.8991 (nan) time: 0.6329 [2021-03-25 23:32:50 swin_base_patch4_window7_224] INFO: Epoch: [5] [1120/1251] eta: 0:01:23 lr: 0.000295 loss: 5.8910 (5.7884) grad_norm: 2.2288 (nan) time: 0.6412 [2021-03-25 23:32:56 swin_base_patch4_window7_224] INFO: Epoch: [5] [1130/1251] eta: 0:01:17 lr: 0.000296 loss: 5.8910 (5.7880) grad_norm: 1.9622 (nan) time: 0.6390 [2021-03-25 23:33:02 swin_base_patch4_window7_224] INFO: Epoch: [5] [1140/1251] eta: 0:01:10 lr: 0.000296 loss: 5.7261 (5.7873) grad_norm: 1.7874 (nan) time: 0.6342 [2021-03-25 23:33:09 swin_base_patch4_window7_224] INFO: Epoch: [5] [1150/1251] eta: 0:01:04 lr: 0.000297 loss: 5.5413 (5.7850) grad_norm: 1.7874 (nan) time: 0.6369 [2021-03-25 23:33:15 swin_base_patch4_window7_224] INFO: Epoch: [5] [1160/1251] eta: 0:00:58 lr: 0.000297 loss: 5.6675 (5.7847) grad_norm: 1.8823 (nan) time: 0.6331 [2021-03-25 23:33:21 swin_base_patch4_window7_224] INFO: Epoch: [5] [1170/1251] eta: 0:00:51 lr: 0.000297 loss: 5.8061 (5.7853) grad_norm: 1.9270 (nan) time: 0.6297 [2021-03-25 23:33:28 swin_base_patch4_window7_224] INFO: Epoch: [5] [1180/1251] eta: 0:00:45 lr: 0.000298 loss: 5.8061 (5.7849) grad_norm: 1.8158 (nan) time: 0.6288 [2021-03-25 23:33:34 swin_base_patch4_window7_224] INFO: Epoch: [5] [1190/1251] eta: 0:00:38 lr: 0.000298 loss: 5.7758 (5.7830) grad_norm: 1.8588 (nan) time: 0.6293 [2021-03-25 23:33:40 swin_base_patch4_window7_224] INFO: Epoch: [5] [1200/1251] eta: 0:00:32 lr: 0.000299 loss: 5.7308 (5.7832) grad_norm: 1.8614 (nan) time: 0.6321 [2021-03-25 23:33:47 swin_base_patch4_window7_224] INFO: Epoch: [5] [1210/1251] eta: 0:00:26 lr: 0.000299 loss: 5.8153 (5.7834) grad_norm: 1.8246 (nan) time: 0.6362 [2021-03-25 23:33:53 swin_base_patch4_window7_224] INFO: Epoch: [5] [1220/1251] eta: 0:00:19 lr: 0.000299 loss: 5.8153 (5.7829) grad_norm: 1.9962 (nan) time: 0.6392 [2021-03-25 23:33:59 swin_base_patch4_window7_224] INFO: Epoch: [5] [1230/1251] eta: 0:00:13 lr: 0.000300 loss: 5.6956 (5.7823) grad_norm: 1.8865 (nan) time: 0.6410 [2021-03-25 23:34:06 swin_base_patch4_window7_224] INFO: Epoch: [5] [1240/1251] eta: 0:00:07 lr: 0.000300 loss: 5.6956 (5.7808) grad_norm: 1.8765 (nan) time: 0.6380 [2021-03-25 23:34:12 swin_base_patch4_window7_224] INFO: Epoch: [5] [1250/1251] eta: 0:00:00 lr: 0.000301 loss: 5.7619 (5.7802) grad_norm: 1.9301 (nan) time: 0.6285 [2021-03-25 23:35:10 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 4.1019 (4.1019) acc1: 15.6250 (15.6250) acc5: 40.6250 (40.6250) [2021-03-25 23:35:12 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 3.7661 (3.7576) acc1: 25.0000 (25.5682) acc5: 48.4375 (48.1534) [2021-03-25 23:35:13 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 3.6649 (3.6889) acc1: 26.5625 (26.3393) acc5: 48.4375 (49.7024) [2021-03-25 23:35:15 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 3.6649 (3.6970) acc1: 25.0000 (25.8569) acc5: 50.0000 (49.2440) [2021-03-25 23:35:16 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 3.6926 (3.6974) acc1: 23.4375 (26.3338) acc5: 50.0000 (50.0000) [2021-03-25 23:35:17 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 3.6467 (3.6832) acc1: 25.0000 (26.4960) acc5: 51.5625 (50.0160) [2021-03-25 23:35:18 swin_base_patch4_window7_224] INFO: * Acc@1 25.714 Acc@5 50.370 loss 3.687 [2021-03-25 23:35:18 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 25.7% [2021-03-25 23:35:18 swin_base_patch4_window7_224] INFO: Max accuracy: 25.71% [2021-03-25 23:35:23 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 0/1251] eta: 1:31:47 lr: 0.000301 loss: 5.0908 (5.0908) grad_norm: 1.5902 (1.5902) time: 4.4023 [2021-03-25 23:35:29 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 10/1251] eta: 0:20:14 lr: 0.000301 loss: 5.6779 (5.6326) grad_norm: 1.8301 (1.9384) time: 0.9790 [2021-03-25 23:35:36 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 20/1251] eta: 0:16:54 lr: 0.000301 loss: 5.6779 (5.6568) grad_norm: 1.8830 (2.0445) time: 0.6451 [2021-03-25 23:35:42 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 30/1251] eta: 0:15:31 lr: 0.000302 loss: 5.6260 (5.6422) grad_norm: 1.9392 (2.0161) time: 0.6446 [2021-03-25 23:35:48 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 40/1251] eta: 0:14:47 lr: 0.000302 loss: 5.7222 (5.6830) grad_norm: 1.9036 (2.0828) time: 0.6369 [2021-03-25 23:35:55 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 50/1251] eta: 0:14:17 lr: 0.000303 loss: 5.6994 (5.6520) grad_norm: 1.9536 (2.0942) time: 0.6377 [2021-03-25 23:36:01 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 60/1251] eta: 0:13:56 lr: 0.000303 loss: 5.4278 (5.6025) grad_norm: 1.9092 (2.0604) time: 0.6389 [2021-03-25 23:36:08 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 70/1251] eta: 0:13:40 lr: 0.000303 loss: 5.7791 (5.6425) grad_norm: 1.9409 (2.0648) time: 0.6445 [2021-03-25 23:36:14 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 80/1251] eta: 0:13:24 lr: 0.000304 loss: 5.8896 (5.6648) grad_norm: 2.0405 (2.0596) time: 0.6398 [2021-03-25 23:36:20 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 90/1251] eta: 0:13:09 lr: 0.000304 loss: 5.7679 (5.6635) grad_norm: 2.0209 (2.0764) time: 0.6294 [2021-03-25 23:36:27 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 100/1251] eta: 0:12:57 lr: 0.000305 loss: 5.8637 (5.6750) grad_norm: 1.8961 (2.0585) time: 0.6326 [2021-03-25 23:36:33 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 110/1251] eta: 0:12:46 lr: 0.000305 loss: 5.7424 (5.6650) grad_norm: 1.8865 (2.0735) time: 0.6350 [2021-03-25 23:36:39 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 120/1251] eta: 0:12:37 lr: 0.000305 loss: 5.8043 (5.6696) grad_norm: 1.8729 (2.0660) time: 0.6374 [2021-03-25 23:36:46 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 130/1251] eta: 0:12:27 lr: 0.000306 loss: 5.8618 (5.6754) grad_norm: 1.7343 (2.0497) time: 0.6376 [2021-03-25 23:36:52 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 140/1251] eta: 0:12:19 lr: 0.000306 loss: 5.8247 (5.6726) grad_norm: 1.9112 (2.0554) time: 0.6395 [2021-03-25 23:36:58 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 150/1251] eta: 0:12:10 lr: 0.000307 loss: 5.7473 (5.6782) grad_norm: 1.9476 (2.0458) time: 0.6421 [2021-03-25 23:37:05 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 160/1251] eta: 0:12:01 lr: 0.000307 loss: 5.8350 (5.6930) grad_norm: 1.9280 (2.0386) time: 0.6355 [2021-03-25 23:37:11 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 170/1251] eta: 0:11:53 lr: 0.000307 loss: 5.7618 (5.6817) grad_norm: 1.8982 (2.0302) time: 0.6357 [2021-03-25 23:37:18 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 180/1251] eta: 0:11:45 lr: 0.000308 loss: 5.6526 (5.6792) grad_norm: 1.9985 (2.0324) time: 0.6354 [2021-03-25 23:37:24 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 190/1251] eta: 0:11:38 lr: 0.000308 loss: 5.7594 (5.6864) grad_norm: 1.9508 (2.0246) time: 0.6390 [2021-03-25 23:37:30 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 200/1251] eta: 0:11:30 lr: 0.000309 loss: 5.7693 (5.6937) grad_norm: 1.8843 (2.0236) time: 0.6440 [2021-03-25 23:37:37 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 210/1251] eta: 0:11:22 lr: 0.000309 loss: 5.7129 (5.6942) grad_norm: 1.8927 (2.0167) time: 0.6358 [2021-03-25 23:37:43 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 220/1251] eta: 0:11:15 lr: 0.000309 loss: 5.5930 (5.6761) grad_norm: 1.8303 (2.0123) time: 0.6303 [2021-03-25 23:37:49 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 230/1251] eta: 0:11:07 lr: 0.000310 loss: 5.5930 (5.6789) grad_norm: 1.7940 (2.0135) time: 0.6359 [2021-03-25 23:37:56 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 240/1251] eta: 0:11:00 lr: 0.000310 loss: 5.6784 (5.6780) grad_norm: 1.8265 (2.0257) time: 0.6361 [2021-03-25 23:38:02 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 250/1251] eta: 0:10:52 lr: 0.000311 loss: 5.6650 (5.6756) grad_norm: 1.6125 (2.0086) time: 0.6276 [2021-03-25 23:38:08 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 260/1251] eta: 0:10:45 lr: 0.000311 loss: 5.6650 (5.6769) grad_norm: 1.9060 (2.0228) time: 0.6311 [2021-03-25 23:38:15 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 270/1251] eta: 0:10:38 lr: 0.000311 loss: 5.7408 (5.6728) grad_norm: 2.2109 (2.0299) time: 0.6364 [2021-03-25 23:38:21 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 280/1251] eta: 0:10:31 lr: 0.000312 loss: 5.4951 (5.6694) grad_norm: 1.8786 (2.0234) time: 0.6325 [2021-03-25 23:38:27 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 290/1251] eta: 0:10:24 lr: 0.000312 loss: 5.5930 (5.6746) grad_norm: 1.6903 (2.0145) time: 0.6346 [2021-03-25 23:38:34 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 300/1251] eta: 0:10:17 lr: 0.000313 loss: 5.8108 (5.6737) grad_norm: 1.8343 (2.0136) time: 0.6363 [2021-03-25 23:38:40 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 310/1251] eta: 0:10:10 lr: 0.000313 loss: 5.8108 (5.6728) grad_norm: 1.8671 (2.0098) time: 0.6297 [2021-03-25 23:38:46 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 320/1251] eta: 0:10:03 lr: 0.000313 loss: 5.6354 (5.6698) grad_norm: 1.8772 (2.0237) time: 0.6291 [2021-03-25 23:38:53 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 330/1251] eta: 0:09:56 lr: 0.000314 loss: 5.8274 (5.6738) grad_norm: 2.2305 (2.0235) time: 0.6312 [2021-03-25 23:38:59 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 340/1251] eta: 0:09:49 lr: 0.000314 loss: 5.9884 (5.6728) grad_norm: 1.9118 (2.0249) time: 0.6319 [2021-03-25 23:39:05 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 350/1251] eta: 0:09:42 lr: 0.000315 loss: 5.5501 (5.6649) grad_norm: 1.7900 (2.0184) time: 0.6399 [2021-03-25 23:39:12 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 360/1251] eta: 0:09:36 lr: 0.000315 loss: 5.6449 (5.6676) grad_norm: 1.8496 (2.0201) time: 0.6412 [2021-03-25 23:39:18 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 370/1251] eta: 0:09:29 lr: 0.000315 loss: 5.7977 (5.6701) grad_norm: 1.7967 (2.0165) time: 0.6384 [2021-03-25 23:39:25 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 380/1251] eta: 0:09:22 lr: 0.000316 loss: 5.7793 (5.6666) grad_norm: 1.7891 (2.0152) time: 0.6373 [2021-03-25 23:39:31 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 390/1251] eta: 0:09:16 lr: 0.000316 loss: 5.7986 (5.6699) grad_norm: 1.9238 (2.0208) time: 0.6350 [2021-03-25 23:39:37 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 400/1251] eta: 0:09:09 lr: 0.000317 loss: 5.9172 (5.6762) grad_norm: 1.7754 (2.0176) time: 0.6412 [2021-03-25 23:39:44 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 410/1251] eta: 0:09:02 lr: 0.000317 loss: 5.6931 (5.6730) grad_norm: 1.8289 (2.0251) time: 0.6378 [2021-03-25 23:39:50 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 420/1251] eta: 0:08:56 lr: 0.000317 loss: 5.5685 (5.6720) grad_norm: 1.9970 (2.0411) time: 0.6322 [2021-03-25 23:39:56 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 430/1251] eta: 0:08:49 lr: 0.000318 loss: 5.6237 (5.6695) grad_norm: 1.9970 (2.0430) time: 0.6362 [2021-03-25 23:40:03 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 440/1251] eta: 0:08:43 lr: 0.000318 loss: 5.7208 (5.6732) grad_norm: 1.8790 (2.0375) time: 0.6359 [2021-03-25 23:40:09 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 450/1251] eta: 0:08:36 lr: 0.000319 loss: 5.7208 (5.6711) grad_norm: 1.7774 (2.0358) time: 0.6345 [2021-03-25 23:40:15 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 460/1251] eta: 0:08:29 lr: 0.000319 loss: 5.5718 (5.6682) grad_norm: 1.8076 (2.0359) time: 0.6320 [2021-03-25 23:40:22 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 470/1251] eta: 0:08:23 lr: 0.000319 loss: 5.6989 (5.6672) grad_norm: 1.8929 (2.0350) time: 0.6342 [2021-03-25 23:40:28 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 480/1251] eta: 0:08:16 lr: 0.000320 loss: 5.5850 (5.6657) grad_norm: 1.6896 (2.0268) time: 0.6337 [2021-03-25 23:40:34 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 490/1251] eta: 0:08:09 lr: 0.000320 loss: 5.5850 (5.6647) grad_norm: 1.7014 (2.0297) time: 0.6337 [2021-03-25 23:40:41 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 500/1251] eta: 0:08:03 lr: 0.000321 loss: 5.8148 (5.6653) grad_norm: 1.9741 (2.0318) time: 0.6371 [2021-03-25 23:40:47 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 510/1251] eta: 0:07:56 lr: 0.000321 loss: 5.6174 (5.6637) grad_norm: 1.9741 (2.0373) time: 0.6345 [2021-03-25 23:40:53 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 520/1251] eta: 0:07:50 lr: 0.000321 loss: 5.5793 (5.6581) grad_norm: 1.9260 (2.0334) time: 0.6280 [2021-03-25 23:41:00 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 530/1251] eta: 0:07:43 lr: 0.000322 loss: 5.5793 (5.6584) grad_norm: 1.8334 (2.0340) time: 0.6291 [2021-03-25 23:41:06 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 540/1251] eta: 0:07:37 lr: 0.000322 loss: 5.6397 (5.6560) grad_norm: 2.0552 (2.0366) time: 0.6380 [2021-03-25 23:41:13 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 550/1251] eta: 0:07:30 lr: 0.000323 loss: 5.3691 (5.6508) grad_norm: 2.0509 (2.0347) time: 0.6387 [2021-03-25 23:41:19 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 560/1251] eta: 0:07:24 lr: 0.000323 loss: 5.6487 (5.6503) grad_norm: 1.7156 (2.0312) time: 0.6423 [2021-03-25 23:41:25 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 570/1251] eta: 0:07:17 lr: 0.000323 loss: 5.8038 (5.6545) grad_norm: 1.9394 (2.0373) time: 0.6460 [2021-03-25 23:41:32 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 580/1251] eta: 0:07:11 lr: 0.000324 loss: 5.8038 (5.6546) grad_norm: 1.9394 (2.0345) time: 0.6460 [2021-03-25 23:41:38 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 590/1251] eta: 0:07:04 lr: 0.000324 loss: 5.7112 (5.6598) grad_norm: 1.7746 (2.0338) time: 0.6458 [2021-03-25 23:41:45 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 600/1251] eta: 0:06:58 lr: 0.000325 loss: 5.6261 (5.6564) grad_norm: 1.8143 (2.0353) time: 0.6449 [2021-03-25 23:41:51 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 610/1251] eta: 0:06:52 lr: 0.000325 loss: 5.2798 (5.6522) grad_norm: 1.9862 (2.0374) time: 0.6424 [2021-03-25 23:41:58 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 620/1251] eta: 0:06:45 lr: 0.000325 loss: 5.6739 (5.6534) grad_norm: 1.7797 (2.0327) time: 0.6397 [2021-03-25 23:42:04 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 630/1251] eta: 0:06:39 lr: 0.000326 loss: 5.6739 (5.6507) grad_norm: 1.7657 (2.0363) time: 0.6354 [2021-03-25 23:42:10 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 640/1251] eta: 0:06:32 lr: 0.000326 loss: 5.6205 (5.6521) grad_norm: 1.8475 (2.0329) time: 0.6317 [2021-03-25 23:42:17 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 650/1251] eta: 0:06:26 lr: 0.000327 loss: 5.8207 (5.6518) grad_norm: 1.8456 (2.0319) time: 0.6298 [2021-03-25 23:42:23 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 660/1251] eta: 0:06:19 lr: 0.000327 loss: 5.5586 (5.6479) grad_norm: 1.9673 (2.0328) time: 0.6265 [2021-03-25 23:42:29 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 670/1251] eta: 0:06:12 lr: 0.000327 loss: 5.5701 (5.6474) grad_norm: 1.8453 (2.0296) time: 0.6249 [2021-03-25 23:42:35 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 680/1251] eta: 0:06:06 lr: 0.000328 loss: 5.8019 (5.6496) grad_norm: 2.0514 (2.0360) time: 0.6266 [2021-03-25 23:42:42 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 690/1251] eta: 0:05:59 lr: 0.000328 loss: 5.7199 (5.6483) grad_norm: 1.7230 (2.0320) time: 0.6329 [2021-03-25 23:42:48 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 700/1251] eta: 0:05:53 lr: 0.000329 loss: 5.6893 (5.6492) grad_norm: 1.6310 (2.0293) time: 0.6395 [2021-03-25 23:42:55 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 710/1251] eta: 0:05:47 lr: 0.000329 loss: 5.6501 (5.6476) grad_norm: 1.8629 (2.0303) time: 0.6414 [2021-03-25 23:43:01 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 720/1251] eta: 0:05:40 lr: 0.000329 loss: 5.4595 (5.6447) grad_norm: 1.8453 (2.0280) time: 0.6348 [2021-03-25 23:43:07 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 730/1251] eta: 0:05:34 lr: 0.000330 loss: 5.3789 (5.6419) grad_norm: 1.7584 (2.0246) time: 0.6346 [2021-03-25 23:43:14 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 740/1251] eta: 0:05:27 lr: 0.000330 loss: 5.7553 (5.6435) grad_norm: 1.7972 (2.0224) time: 0.6445 [2021-03-25 23:43:20 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 750/1251] eta: 0:05:21 lr: 0.000331 loss: 5.8429 (5.6436) grad_norm: 1.8131 (2.0202) time: 0.6454 [2021-03-25 23:43:27 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 760/1251] eta: 0:05:14 lr: 0.000331 loss: 5.8869 (5.6462) grad_norm: 1.7759 (2.0181) time: 0.6434 [2021-03-25 23:43:33 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 770/1251] eta: 0:05:08 lr: 0.000331 loss: 5.8351 (5.6469) grad_norm: 1.8133 (2.0215) time: 0.6398 [2021-03-25 23:43:39 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 780/1251] eta: 0:05:02 lr: 0.000332 loss: 5.6623 (5.6462) grad_norm: 2.0538 (2.0219) time: 0.6376 [2021-03-25 23:43:46 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 790/1251] eta: 0:04:55 lr: 0.000332 loss: 5.5764 (5.6454) grad_norm: 1.8825 (2.0208) time: 0.6375 [2021-03-25 23:43:52 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 800/1251] eta: 0:04:49 lr: 0.000333 loss: 5.4655 (5.6426) grad_norm: 1.8825 (2.0211) time: 0.6379 [2021-03-25 23:43:58 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 810/1251] eta: 0:04:42 lr: 0.000333 loss: 5.4655 (5.6416) grad_norm: 1.8066 (2.0191) time: 0.6389 [2021-03-25 23:44:05 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 820/1251] eta: 0:04:36 lr: 0.000333 loss: 5.7138 (5.6423) grad_norm: 1.7296 (2.0165) time: 0.6414 [2021-03-25 23:44:11 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 830/1251] eta: 0:04:29 lr: 0.000334 loss: 5.8292 (5.6424) grad_norm: 1.7663 (2.0150) time: 0.6438 [2021-03-25 23:44:18 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 840/1251] eta: 0:04:23 lr: 0.000334 loss: 5.4496 (5.6388) grad_norm: 1.8171 (2.0139) time: 0.6393 [2021-03-25 23:44:24 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 850/1251] eta: 0:04:17 lr: 0.000335 loss: 5.5077 (5.6392) grad_norm: 1.8273 (2.0124) time: 0.6373 [2021-03-25 23:44:30 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 860/1251] eta: 0:04:10 lr: 0.000335 loss: 5.7964 (5.6390) grad_norm: 1.7376 (2.0123) time: 0.6360 [2021-03-25 23:44:37 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 870/1251] eta: 0:04:04 lr: 0.000335 loss: 5.7457 (5.6394) grad_norm: 1.8378 (2.0165) time: 0.6384 [2021-03-25 23:44:43 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 880/1251] eta: 0:03:57 lr: 0.000336 loss: 5.8025 (5.6412) grad_norm: 2.2235 (2.0227) time: 0.6365 [2021-03-25 23:44:50 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 890/1251] eta: 0:03:51 lr: 0.000336 loss: 5.6541 (5.6407) grad_norm: 2.0115 (2.0210) time: 0.6357 [2021-03-25 23:44:56 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 900/1251] eta: 0:03:44 lr: 0.000337 loss: 5.6519 (5.6404) grad_norm: 1.9846 (2.0218) time: 0.6393 [2021-03-25 23:45:02 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 910/1251] eta: 0:03:38 lr: 0.000337 loss: 5.6519 (5.6379) grad_norm: 1.8644 (2.0184) time: 0.6371 [2021-03-25 23:45:09 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 920/1251] eta: 0:03:32 lr: 0.000337 loss: 5.6160 (5.6377) grad_norm: 1.6940 (2.0162) time: 0.6359 [2021-03-25 23:45:15 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 930/1251] eta: 0:03:25 lr: 0.000338 loss: 5.6160 (5.6368) grad_norm: 1.8168 (2.0144) time: 0.6393 [2021-03-25 23:45:22 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 940/1251] eta: 0:03:19 lr: 0.000338 loss: 5.8828 (5.6385) grad_norm: 1.8591 (2.0138) time: 0.6407 [2021-03-25 23:45:28 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 950/1251] eta: 0:03:12 lr: 0.000339 loss: 5.8779 (5.6400) grad_norm: 1.9149 (2.0127) time: 0.6415 [2021-03-25 23:45:34 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 960/1251] eta: 0:03:06 lr: 0.000339 loss: 5.6584 (5.6395) grad_norm: 1.7690 (2.0108) time: 0.6392 [2021-03-25 23:45:41 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 970/1251] eta: 0:03:00 lr: 0.000339 loss: 5.4603 (5.6382) grad_norm: 1.7220 (2.0082) time: 0.6371 [2021-03-25 23:45:47 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 980/1251] eta: 0:02:53 lr: 0.000340 loss: 5.4816 (5.6370) grad_norm: 1.8144 (2.0074) time: 0.6390 [2021-03-25 23:45:54 swin_base_patch4_window7_224] INFO: Epoch: [6] [ 990/1251] eta: 0:02:47 lr: 0.000340 loss: 5.7283 (5.6397) grad_norm: 1.7094 (2.0043) time: 0.6400 [2021-03-25 23:46:00 swin_base_patch4_window7_224] INFO: Epoch: [6] [1000/1251] eta: 0:02:40 lr: 0.000341 loss: 5.9492 (5.6408) grad_norm: 1.7094 (2.0026) time: 0.6363 [2021-03-25 23:46:06 swin_base_patch4_window7_224] INFO: Epoch: [6] [1010/1251] eta: 0:02:34 lr: 0.000341 loss: 5.6493 (5.6393) grad_norm: 1.7632 (2.0004) time: 0.6452 [2021-03-25 23:46:13 swin_base_patch4_window7_224] INFO: Epoch: [6] [1020/1251] eta: 0:02:28 lr: 0.000341 loss: 5.6493 (5.6393) grad_norm: 1.7576 (2.0007) time: 0.6446 [2021-03-25 23:46:19 swin_base_patch4_window7_224] INFO: Epoch: [6] [1030/1251] eta: 0:02:21 lr: 0.000342 loss: 5.6767 (5.6397) grad_norm: 1.8654 (2.0003) time: 0.6353 [2021-03-25 23:46:25 swin_base_patch4_window7_224] INFO: Epoch: [6] [1040/1251] eta: 0:02:15 lr: 0.000342 loss: 5.6422 (5.6410) grad_norm: 1.8791 (2.0023) time: 0.6363 [2021-03-25 23:46:32 swin_base_patch4_window7_224] INFO: Epoch: [6] [1050/1251] eta: 0:02:08 lr: 0.000343 loss: 5.6612 (5.6419) grad_norm: 2.0871 (2.0067) time: 0.6319 [2021-03-25 23:46:38 swin_base_patch4_window7_224] INFO: Epoch: [6] [1060/1251] eta: 0:02:02 lr: 0.000343 loss: 5.6046 (5.6420) grad_norm: 1.9615 (2.0068) time: 0.6338 [2021-03-25 23:46:44 swin_base_patch4_window7_224] INFO: Epoch: [6] [1070/1251] eta: 0:01:55 lr: 0.000343 loss: 5.5665 (5.6405) grad_norm: 1.7455 (2.0065) time: 0.6346 [2021-03-25 23:46:51 swin_base_patch4_window7_224] INFO: Epoch: [6] [1080/1251] eta: 0:01:49 lr: 0.000344 loss: 5.6557 (5.6399) grad_norm: 2.1327 (2.0080) time: 0.6341 [2021-03-25 23:46:57 swin_base_patch4_window7_224] INFO: Epoch: [6] [1090/1251] eta: 0:01:43 lr: 0.000344 loss: 5.8425 (5.6420) grad_norm: 2.0567 (2.0084) time: 0.6333 [2021-03-25 23:47:04 swin_base_patch4_window7_224] INFO: Epoch: [6] [1100/1251] eta: 0:01:36 lr: 0.000345 loss: 5.8717 (5.6420) grad_norm: 1.9817 (2.0112) time: 0.6363 [2021-03-25 23:47:10 swin_base_patch4_window7_224] INFO: Epoch: [6] [1110/1251] eta: 0:01:30 lr: 0.000345 loss: 5.7202 (5.6421) grad_norm: 1.7480 (2.0091) time: 0.6397 [2021-03-25 23:47:16 swin_base_patch4_window7_224] INFO: Epoch: [6] [1120/1251] eta: 0:01:23 lr: 0.000345 loss: 5.6646 (5.6422) grad_norm: 1.7480 (2.0080) time: 0.6358 [2021-03-25 23:47:23 swin_base_patch4_window7_224] INFO: Epoch: [6] [1130/1251] eta: 0:01:17 lr: 0.000346 loss: 5.6131 (5.6403) grad_norm: 1.7649 (2.0056) time: 0.6305 [2021-03-25 23:47:29 swin_base_patch4_window7_224] INFO: Epoch: [6] [1140/1251] eta: 0:01:11 lr: 0.000346 loss: 5.6287 (5.6410) grad_norm: 1.7155 (2.0046) time: 0.6296 [2021-03-25 23:47:35 swin_base_patch4_window7_224] INFO: Epoch: [6] [1150/1251] eta: 0:01:04 lr: 0.000347 loss: 5.6165 (5.6396) grad_norm: 1.9872 (2.0072) time: 0.6341 [2021-03-25 23:47:42 swin_base_patch4_window7_224] INFO: Epoch: [6] [1160/1251] eta: 0:00:58 lr: 0.000347 loss: 5.5826 (5.6383) grad_norm: 2.0915 (2.0077) time: 0.6354 [2021-03-25 23:47:48 swin_base_patch4_window7_224] INFO: Epoch: [6] [1170/1251] eta: 0:00:51 lr: 0.000347 loss: 5.6146 (5.6380) grad_norm: 1.8430 (2.0063) time: 0.6330 [2021-03-25 23:47:54 swin_base_patch4_window7_224] INFO: Epoch: [6] [1180/1251] eta: 0:00:45 lr: 0.000348 loss: 5.6146 (5.6369) grad_norm: 1.7252 (2.0052) time: 0.6352 [2021-03-25 23:48:01 swin_base_patch4_window7_224] INFO: Epoch: [6] [1190/1251] eta: 0:00:39 lr: 0.000348 loss: 5.5290 (5.6353) grad_norm: 1.8964 (2.0048) time: 0.6420 [2021-03-25 23:48:07 swin_base_patch4_window7_224] INFO: Epoch: [6] [1200/1251] eta: 0:00:32 lr: 0.000349 loss: 5.6228 (5.6354) grad_norm: 1.8455 (2.0032) time: 0.6403 [2021-03-25 23:48:13 swin_base_patch4_window7_224] INFO: Epoch: [6] [1210/1251] eta: 0:00:26 lr: 0.000349 loss: 5.5492 (5.6349) grad_norm: 1.8029 (2.0033) time: 0.6356 [2021-03-25 23:48:20 swin_base_patch4_window7_224] INFO: Epoch: [6] [1220/1251] eta: 0:00:19 lr: 0.000349 loss: 5.5431 (5.6350) grad_norm: 2.1059 (2.0052) time: 0.6341 [2021-03-25 23:48:26 swin_base_patch4_window7_224] INFO: Epoch: [6] [1230/1251] eta: 0:00:13 lr: 0.000350 loss: 5.6837 (5.6352) grad_norm: 2.0572 (2.0042) time: 0.6360 [2021-03-25 23:48:33 swin_base_patch4_window7_224] INFO: Epoch: [6] [1240/1251] eta: 0:00:07 lr: 0.000350 loss: 5.6837 (5.6355) grad_norm: 1.9303 (2.0058) time: 0.6385 [2021-03-25 23:48:39 swin_base_patch4_window7_224] INFO: Epoch: [6] [1250/1251] eta: 0:00:00 lr: 0.000351 loss: 5.7147 (5.6364) grad_norm: 1.9289 (2.0058) time: 0.6293 [2021-03-25 23:48:44 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:59 loss: 3.3662 (3.3662) acc1: 31.2500 (31.2500) acc5: 48.4375 (48.4375) [2021-03-25 23:48:46 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:21 loss: 3.3662 (3.3823) acc1: 29.6875 (30.8239) acc5: 56.2500 (54.2614) [2021-03-25 23:48:50 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:13 loss: 3.3418 (3.3975) acc1: 29.6875 (30.5804) acc5: 54.6875 (54.0179) [2021-03-25 23:48:52 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 3.4388 (3.4199) acc1: 29.6875 (30.6452) acc5: 51.5625 (53.8810) [2021-03-25 23:48:53 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 3.3661 (3.3993) acc1: 29.6875 (30.7927) acc5: 53.1250 (54.4588) [2021-03-25 23:48:54 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 3.3661 (3.4071) acc1: 29.6875 (30.5600) acc5: 54.6875 (54.3680) [2021-03-25 23:48:55 swin_base_patch4_window7_224] INFO: * Acc@1 29.728 Acc@5 55.088 loss 3.414 [2021-03-25 23:48:55 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 29.7% [2021-03-25 23:48:55 swin_base_patch4_window7_224] INFO: Max accuracy: 29.73% [2021-03-25 23:48:59 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 0/1251] eta: 1:32:19 lr: 0.000351 loss: 5.8662 (5.8662) grad_norm: 1.7647 (1.7647) time: 4.4278 [2021-03-25 23:49:06 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 10/1251] eta: 0:20:22 lr: 0.000351 loss: 5.7429 (5.6797) grad_norm: 1.7647 (1.8997) time: 0.9850 [2021-03-25 23:49:12 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 20/1251] eta: 0:16:44 lr: 0.000351 loss: 5.6994 (5.6105) grad_norm: 1.7441 (1.9705) time: 0.6354 [2021-03-25 23:49:18 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 30/1251] eta: 0:15:22 lr: 0.000352 loss: 5.5645 (5.5938) grad_norm: 1.7985 (1.9433) time: 0.6297 [2021-03-25 23:49:25 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 40/1251] eta: 0:14:38 lr: 0.000352 loss: 5.6781 (5.6171) grad_norm: 1.9032 (2.0054) time: 0.6310 [2021-03-25 23:49:31 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 50/1251] eta: 0:14:11 lr: 0.000353 loss: 5.6504 (5.5849) grad_norm: 1.8726 (1.9885) time: 0.6370 [2021-03-25 23:49:38 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 60/1251] eta: 0:13:50 lr: 0.000353 loss: 5.5182 (5.5821) grad_norm: 1.7430 (1.9511) time: 0.6379 [2021-03-25 23:49:44 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 70/1251] eta: 0:13:31 lr: 0.000353 loss: 5.5637 (5.5806) grad_norm: 1.7462 (1.9678) time: 0.6296 [2021-03-25 23:49:50 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 80/1251] eta: 0:13:16 lr: 0.000354 loss: 5.5637 (5.5780) grad_norm: 2.0078 (2.0020) time: 0.6299 [2021-03-25 23:49:57 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 90/1251] eta: 0:13:04 lr: 0.000354 loss: 5.5837 (5.5809) grad_norm: 2.0611 (1.9974) time: 0.6367 [2021-03-25 23:50:03 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 100/1251] eta: 0:12:54 lr: 0.000355 loss: 5.5923 (5.5809) grad_norm: 1.8148 (1.9876) time: 0.6406 [2021-03-25 23:50:09 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 110/1251] eta: 0:12:43 lr: 0.000355 loss: 5.5923 (5.5775) grad_norm: 1.8391 (2.0050) time: 0.6387 [2021-03-25 23:50:16 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 120/1251] eta: 0:12:34 lr: 0.000355 loss: 5.6991 (5.5759) grad_norm: 1.8620 (2.0063) time: 0.6386 [2021-03-25 23:50:22 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 130/1251] eta: 0:12:25 lr: 0.000356 loss: 5.6877 (5.5797) grad_norm: 1.8427 (2.0022) time: 0.6426 [2021-03-25 23:50:29 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 140/1251] eta: 0:12:16 lr: 0.000356 loss: 5.5842 (5.5699) grad_norm: 1.8427 (1.9993) time: 0.6391 [2021-03-25 23:50:35 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 150/1251] eta: 0:12:08 lr: 0.000357 loss: 5.4478 (5.5564) grad_norm: 1.8687 (1.9954) time: 0.6364 [2021-03-25 23:50:41 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 160/1251] eta: 0:11:59 lr: 0.000357 loss: 5.5410 (5.5607) grad_norm: 1.8139 (1.9955) time: 0.6334 [2021-03-25 23:50:48 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 170/1251] eta: 0:11:50 lr: 0.000357 loss: 5.6577 (5.5647) grad_norm: 1.6596 (1.9772) time: 0.6310 [2021-03-25 23:50:54 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 180/1251] eta: 0:11:43 lr: 0.000358 loss: 5.7554 (5.5786) grad_norm: 1.5897 (1.9611) time: 0.6391 [2021-03-25 23:51:00 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 190/1251] eta: 0:11:35 lr: 0.000358 loss: 5.6258 (5.5733) grad_norm: 1.6330 (1.9502) time: 0.6401 [2021-03-25 23:51:07 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 200/1251] eta: 0:11:29 lr: 0.000359 loss: 5.4822 (5.5726) grad_norm: 1.7203 (1.9454) time: 0.6430 [2021-03-25 23:51:13 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 210/1251] eta: 0:11:20 lr: 0.000359 loss: 5.7285 (5.5920) grad_norm: 1.7817 (1.9448) time: 0.6378 [2021-03-25 23:51:19 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 220/1251] eta: 0:11:13 lr: 0.000359 loss: 5.7179 (5.5843) grad_norm: 1.7692 (1.9490) time: 0.6301 [2021-03-25 23:51:26 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 230/1251] eta: 0:11:05 lr: 0.000360 loss: 5.5590 (5.5895) grad_norm: 1.7692 (1.9511) time: 0.6298 [2021-03-25 23:51:32 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 240/1251] eta: 0:10:58 lr: 0.000360 loss: 5.5360 (5.5814) grad_norm: 1.7909 (1.9529) time: 0.6293 [2021-03-25 23:51:38 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 250/1251] eta: 0:10:51 lr: 0.000361 loss: 5.3243 (5.5674) grad_norm: 1.9963 (1.9643) time: 0.6322 [2021-03-25 23:51:45 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 260/1251] eta: 0:10:43 lr: 0.000361 loss: 5.4718 (5.5679) grad_norm: 1.9538 (1.9620) time: 0.6313 [2021-03-25 23:51:51 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 270/1251] eta: 0:10:36 lr: 0.000361 loss: 5.7828 (5.5723) grad_norm: 1.8205 (1.9671) time: 0.6331 [2021-03-25 23:51:57 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 280/1251] eta: 0:10:29 lr: 0.000362 loss: 5.6574 (5.5688) grad_norm: 1.9129 (1.9746) time: 0.6347 [2021-03-25 23:52:04 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 290/1251] eta: 0:10:23 lr: 0.000362 loss: 5.4097 (5.5593) grad_norm: 1.9129 (1.9718) time: 0.6385 [2021-03-25 23:52:10 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 300/1251] eta: 0:10:16 lr: 0.000363 loss: 5.3955 (5.5591) grad_norm: 1.8996 (1.9733) time: 0.6403 [2021-03-25 23:52:17 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 310/1251] eta: 0:10:09 lr: 0.000363 loss: 5.5305 (5.5560) grad_norm: 1.8115 (1.9676) time: 0.6371 [2021-03-25 23:52:23 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 320/1251] eta: 0:10:02 lr: 0.000363 loss: 5.5911 (5.5572) grad_norm: 1.7526 (1.9659) time: 0.6330 [2021-03-25 23:52:29 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 330/1251] eta: 0:09:55 lr: 0.000364 loss: 5.5911 (5.5544) grad_norm: 1.8208 (1.9748) time: 0.6365 [2021-03-25 23:52:36 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 340/1251] eta: 0:09:49 lr: 0.000364 loss: 5.5511 (5.5527) grad_norm: 2.0472 (2.0015) time: 0.6399 [2021-03-25 23:52:42 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 350/1251] eta: 0:09:42 lr: 0.000365 loss: 5.7827 (5.5596) grad_norm: 2.3076 (2.0071) time: 0.6338 [2021-03-25 23:52:48 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 360/1251] eta: 0:09:35 lr: 0.000365 loss: 5.7142 (5.5541) grad_norm: 1.9927 (2.0120) time: 0.6293 [2021-03-25 23:52:55 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 370/1251] eta: 0:09:28 lr: 0.000365 loss: 5.4127 (5.5507) grad_norm: 1.7897 (2.0127) time: 0.6360 [2021-03-25 23:53:01 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 380/1251] eta: 0:09:22 lr: 0.000366 loss: 5.4127 (5.5480) grad_norm: 1.8861 (2.0241) time: 0.6382 [2021-03-25 23:53:07 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 390/1251] eta: 0:09:15 lr: 0.000366 loss: 5.6686 (5.5493) grad_norm: 2.0015 (2.0353) time: 0.6358 [2021-03-25 23:53:14 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 400/1251] eta: 0:09:08 lr: 0.000367 loss: 5.4740 (5.5436) grad_norm: 1.9496 (2.0305) time: 0.6367 [2021-03-25 23:53:20 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 410/1251] eta: 0:09:02 lr: 0.000367 loss: 5.4740 (5.5467) grad_norm: 1.8031 (2.0242) time: 0.6319 [2021-03-25 23:53:26 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 420/1251] eta: 0:08:55 lr: 0.000367 loss: 5.5498 (5.5386) grad_norm: 1.7325 (2.0187) time: 0.6337 [2021-03-25 23:53:33 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 430/1251] eta: 0:08:48 lr: 0.000368 loss: 5.2139 (5.5349) grad_norm: 1.6878 (2.0114) time: 0.6361 [2021-03-25 23:53:39 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 440/1251] eta: 0:08:42 lr: 0.000368 loss: 5.5226 (5.5371) grad_norm: 1.7457 (2.0167) time: 0.6303 [2021-03-25 23:53:45 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 450/1251] eta: 0:08:35 lr: 0.000369 loss: 5.5604 (5.5366) grad_norm: 2.0088 (2.0173) time: 0.6320 [2021-03-25 23:53:52 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 460/1251] eta: 0:08:28 lr: 0.000369 loss: 5.7624 (5.5400) grad_norm: 1.8721 (2.0143) time: 0.6341 [2021-03-25 23:53:58 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 470/1251] eta: 0:08:22 lr: 0.000369 loss: 5.7624 (5.5405) grad_norm: 1.8006 (2.0107) time: 0.6332 [2021-03-25 23:54:04 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 480/1251] eta: 0:08:15 lr: 0.000370 loss: 5.4092 (5.5350) grad_norm: 1.8611 (2.0092) time: 0.6348 [2021-03-25 23:54:11 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 490/1251] eta: 0:08:09 lr: 0.000370 loss: 5.3060 (5.5320) grad_norm: 2.0234 (2.0110) time: 0.6353 [2021-03-25 23:54:17 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 500/1251] eta: 0:08:02 lr: 0.000371 loss: 5.3686 (5.5314) grad_norm: 2.0234 (2.0132) time: 0.6349 [2021-03-25 23:54:23 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 510/1251] eta: 0:07:56 lr: 0.000371 loss: 5.6367 (5.5329) grad_norm: 1.9577 (2.0108) time: 0.6316 [2021-03-25 23:54:30 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 520/1251] eta: 0:07:49 lr: 0.000371 loss: 5.6335 (5.5334) grad_norm: 1.8204 (2.0079) time: 0.6359 [2021-03-25 23:54:36 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 530/1251] eta: 0:07:42 lr: 0.000372 loss: 5.6332 (5.5342) grad_norm: 1.8526 (inf) time: 0.6344 [2021-03-25 23:54:42 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 540/1251] eta: 0:07:36 lr: 0.000372 loss: 5.6110 (5.5307) grad_norm: 2.0968 (inf) time: 0.6300 [2021-03-25 23:54:49 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 550/1251] eta: 0:07:30 lr: 0.000373 loss: 5.5969 (5.5316) grad_norm: 1.8140 (inf) time: 0.6451 [2021-03-25 23:54:55 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 560/1251] eta: 0:07:23 lr: 0.000373 loss: 5.5969 (5.5280) grad_norm: 1.7977 (inf) time: 0.6521 [2021-03-25 23:55:02 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 570/1251] eta: 0:07:17 lr: 0.000373 loss: 5.1497 (5.5252) grad_norm: 1.8422 (inf) time: 0.6459 [2021-03-25 23:55:08 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 580/1251] eta: 0:07:10 lr: 0.000374 loss: 5.3712 (5.5230) grad_norm: 1.7543 (inf) time: 0.6396 [2021-03-25 23:55:15 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 590/1251] eta: 0:07:04 lr: 0.000374 loss: 5.4603 (5.5218) grad_norm: 1.7608 (inf) time: 0.6343 [2021-03-25 23:55:21 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 600/1251] eta: 0:06:58 lr: 0.000375 loss: 5.4860 (5.5218) grad_norm: 1.7617 (inf) time: 0.6412 [2021-03-25 23:55:27 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 610/1251] eta: 0:06:51 lr: 0.000375 loss: 5.7724 (5.5279) grad_norm: 1.8216 (inf) time: 0.6410 [2021-03-25 23:55:34 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 620/1251] eta: 0:06:44 lr: 0.000375 loss: 5.6904 (5.5256) grad_norm: 1.8904 (inf) time: 0.6280 [2021-03-25 23:55:40 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 630/1251] eta: 0:06:38 lr: 0.000376 loss: 5.6575 (5.5252) grad_norm: 1.8085 (inf) time: 0.6249 [2021-03-25 23:55:46 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 640/1251] eta: 0:06:31 lr: 0.000376 loss: 5.7685 (5.5274) grad_norm: 1.8085 (inf) time: 0.6312 [2021-03-25 23:55:53 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 650/1251] eta: 0:06:25 lr: 0.000377 loss: 5.7414 (5.5281) grad_norm: 1.8794 (inf) time: 0.6418 [2021-03-25 23:55:59 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 660/1251] eta: 0:06:19 lr: 0.000377 loss: 5.7893 (5.5315) grad_norm: 1.8851 (inf) time: 0.6392 [2021-03-25 23:56:05 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 670/1251] eta: 0:06:12 lr: 0.000377 loss: 5.8717 (5.5347) grad_norm: 1.7671 (inf) time: 0.6330 [2021-03-25 23:56:12 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 680/1251] eta: 0:06:06 lr: 0.000378 loss: 5.7580 (5.5349) grad_norm: 1.7896 (inf) time: 0.6363 [2021-03-25 23:56:18 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 690/1251] eta: 0:05:59 lr: 0.000378 loss: 5.5681 (5.5350) grad_norm: 1.7896 (inf) time: 0.6338 [2021-03-25 23:56:25 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 700/1251] eta: 0:05:53 lr: 0.000379 loss: 5.4290 (5.5329) grad_norm: 1.8114 (inf) time: 0.6346 [2021-03-25 23:56:31 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 710/1251] eta: 0:05:46 lr: 0.000379 loss: 5.5913 (5.5349) grad_norm: 1.8114 (inf) time: 0.6367 [2021-03-25 23:56:37 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 720/1251] eta: 0:05:40 lr: 0.000379 loss: 5.7777 (5.5367) grad_norm: 1.7045 (inf) time: 0.6303 [2021-03-25 23:56:44 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 730/1251] eta: 0:05:33 lr: 0.000380 loss: 5.7558 (5.5402) grad_norm: 1.7268 (inf) time: 0.6322 [2021-03-25 23:56:50 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 740/1251] eta: 0:05:27 lr: 0.000380 loss: 5.7974 (5.5390) grad_norm: 1.9447 (inf) time: 0.6388 [2021-03-25 23:56:56 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 750/1251] eta: 0:05:21 lr: 0.000381 loss: 5.2085 (5.5333) grad_norm: 2.5656 (inf) time: 0.6434 [2021-03-25 23:57:03 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 760/1251] eta: 0:05:14 lr: 0.000381 loss: 5.2676 (5.5301) grad_norm: 2.2536 (inf) time: 0.6388 [2021-03-25 23:57:09 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 770/1251] eta: 0:05:08 lr: 0.000381 loss: 5.5305 (5.5316) grad_norm: 1.9131 (inf) time: 0.6305 [2021-03-25 23:57:15 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 780/1251] eta: 0:05:01 lr: 0.000382 loss: 5.6450 (5.5339) grad_norm: 1.7442 (inf) time: 0.6339 [2021-03-25 23:57:22 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 790/1251] eta: 0:04:55 lr: 0.000382 loss: 5.6450 (5.5341) grad_norm: 1.7442 (inf) time: 0.6389 [2021-03-25 23:57:28 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 800/1251] eta: 0:04:48 lr: 0.000383 loss: 5.6621 (5.5343) grad_norm: 1.9564 (inf) time: 0.6428 [2021-03-25 23:57:35 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 810/1251] eta: 0:04:42 lr: 0.000383 loss: 5.6137 (5.5325) grad_norm: 1.8179 (inf) time: 0.6401 [2021-03-25 23:57:41 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 820/1251] eta: 0:04:35 lr: 0.000383 loss: 5.6137 (5.5332) grad_norm: 1.6990 (inf) time: 0.6345 [2021-03-25 23:57:47 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 830/1251] eta: 0:04:29 lr: 0.000384 loss: 5.6973 (5.5335) grad_norm: 1.5877 (inf) time: 0.6330 [2021-03-25 23:57:54 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 840/1251] eta: 0:04:23 lr: 0.000384 loss: 5.4114 (5.5297) grad_norm: 1.5733 (inf) time: 0.6371 [2021-03-25 23:58:00 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 850/1251] eta: 0:04:16 lr: 0.000385 loss: 5.4692 (5.5305) grad_norm: 1.7198 (inf) time: 0.6362 [2021-03-25 23:58:06 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 860/1251] eta: 0:04:10 lr: 0.000385 loss: 5.4692 (5.5288) grad_norm: 1.8362 (inf) time: 0.6341 [2021-03-25 23:58:13 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 870/1251] eta: 0:04:03 lr: 0.000385 loss: 5.6472 (5.5304) grad_norm: 1.7631 (inf) time: 0.6402 [2021-03-25 23:58:19 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 880/1251] eta: 0:03:57 lr: 0.000386 loss: 5.5364 (5.5287) grad_norm: 1.7874 (inf) time: 0.6407 [2021-03-25 23:58:26 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 890/1251] eta: 0:03:51 lr: 0.000386 loss: 5.2977 (5.5263) grad_norm: 1.9173 (inf) time: 0.6374 [2021-03-25 23:58:32 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 900/1251] eta: 0:03:44 lr: 0.000387 loss: 5.4034 (5.5267) grad_norm: 2.0509 (inf) time: 0.6354 [2021-03-25 23:58:38 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 910/1251] eta: 0:03:38 lr: 0.000387 loss: 5.6464 (5.5283) grad_norm: 2.0145 (inf) time: 0.6287 [2021-03-25 23:58:44 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 920/1251] eta: 0:03:31 lr: 0.000387 loss: 5.6430 (5.5300) grad_norm: 1.9629 (inf) time: 0.6276 [2021-03-25 23:58:51 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 930/1251] eta: 0:03:25 lr: 0.000388 loss: 5.6763 (5.5318) grad_norm: 1.8753 (inf) time: 0.6300 [2021-03-25 23:58:57 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 940/1251] eta: 0:03:18 lr: 0.000388 loss: 5.7299 (5.5327) grad_norm: 1.9274 (inf) time: 0.6273 [2021-03-25 23:59:03 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 950/1251] eta: 0:03:12 lr: 0.000389 loss: 5.7513 (5.5347) grad_norm: 1.9158 (inf) time: 0.6315 [2021-03-25 23:59:10 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 960/1251] eta: 0:03:06 lr: 0.000389 loss: 5.6994 (5.5349) grad_norm: 1.6660 (inf) time: 0.6342 [2021-03-25 23:59:16 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 970/1251] eta: 0:02:59 lr: 0.000389 loss: 5.5052 (5.5317) grad_norm: 1.7790 (inf) time: 0.6323 [2021-03-25 23:59:22 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 980/1251] eta: 0:02:53 lr: 0.000390 loss: 5.2530 (5.5306) grad_norm: 1.8018 (inf) time: 0.6327 [2021-03-25 23:59:29 swin_base_patch4_window7_224] INFO: Epoch: [7] [ 990/1251] eta: 0:02:46 lr: 0.000390 loss: 5.4948 (5.5312) grad_norm: 1.7354 (inf) time: 0.6403 [2021-03-25 23:59:35 swin_base_patch4_window7_224] INFO: Epoch: [7] [1000/1251] eta: 0:02:40 lr: 0.000391 loss: 5.4234 (5.5298) grad_norm: 1.7210 (inf) time: 0.6425 [2021-03-25 23:59:41 swin_base_patch4_window7_224] INFO: Epoch: [7] [1010/1251] eta: 0:02:34 lr: 0.000391 loss: 5.3791 (5.5292) grad_norm: 1.7916 (inf) time: 0.6339 [2021-03-25 23:59:48 swin_base_patch4_window7_224] INFO: Epoch: [7] [1020/1251] eta: 0:02:27 lr: 0.000391 loss: 5.3777 (5.5281) grad_norm: 1.9797 (inf) time: 0.6296 [2021-03-25 23:59:54 swin_base_patch4_window7_224] INFO: Epoch: [7] [1030/1251] eta: 0:02:21 lr: 0.000392 loss: 5.3848 (5.5276) grad_norm: 1.7517 (inf) time: 0.6284 [2021-03-26 00:00:00 swin_base_patch4_window7_224] INFO: Epoch: [7] [1040/1251] eta: 0:02:14 lr: 0.000392 loss: 5.4632 (5.5272) grad_norm: 1.8111 (inf) time: 0.6320 [2021-03-26 00:00:07 swin_base_patch4_window7_224] INFO: Epoch: [7] [1050/1251] eta: 0:02:08 lr: 0.000393 loss: 5.5186 (5.5273) grad_norm: 1.8197 (inf) time: 0.6389 [2021-03-26 00:00:13 swin_base_patch4_window7_224] INFO: Epoch: [7] [1060/1251] eta: 0:02:02 lr: 0.000393 loss: 5.5186 (5.5256) grad_norm: 2.0940 (inf) time: 0.6383 [2021-03-26 00:00:20 swin_base_patch4_window7_224] INFO: Epoch: [7] [1070/1251] eta: 0:01:55 lr: 0.000393 loss: 5.5781 (5.5264) grad_norm: 1.9259 (inf) time: 0.6366 [2021-03-26 00:00:26 swin_base_patch4_window7_224] INFO: Epoch: [7] [1080/1251] eta: 0:01:49 lr: 0.000394 loss: 5.5781 (5.5253) grad_norm: 1.6648 (inf) time: 0.6298 [2021-03-26 00:00:32 swin_base_patch4_window7_224] INFO: Epoch: [7] [1090/1251] eta: 0:01:42 lr: 0.000394 loss: 5.5539 (5.5249) grad_norm: 1.8350 (inf) time: 0.6280 [2021-03-26 00:00:39 swin_base_patch4_window7_224] INFO: Epoch: [7] [1100/1251] eta: 0:01:36 lr: 0.000395 loss: 5.2935 (5.5219) grad_norm: 2.1041 (inf) time: 0.6354 [2021-03-26 00:00:45 swin_base_patch4_window7_224] INFO: Epoch: [7] [1110/1251] eta: 0:01:30 lr: 0.000395 loss: 5.2935 (5.5208) grad_norm: 1.6903 (inf) time: 0.6322 [2021-03-26 00:00:51 swin_base_patch4_window7_224] INFO: Epoch: [7] [1120/1251] eta: 0:01:23 lr: 0.000395 loss: 5.3818 (5.5196) grad_norm: 1.6903 (inf) time: 0.6268 [2021-03-26 00:00:57 swin_base_patch4_window7_224] INFO: Epoch: [7] [1130/1251] eta: 0:01:17 lr: 0.000396 loss: 5.6044 (5.5195) grad_norm: 1.7840 (inf) time: 0.6324 [2021-03-26 00:01:04 swin_base_patch4_window7_224] INFO: Epoch: [7] [1140/1251] eta: 0:01:10 lr: 0.000396 loss: 5.5607 (5.5187) grad_norm: 2.1479 (inf) time: 0.6348 [2021-03-26 00:01:10 swin_base_patch4_window7_224] INFO: Epoch: [7] [1150/1251] eta: 0:01:04 lr: 0.000397 loss: 5.4597 (5.5183) grad_norm: 1.9480 (inf) time: 0.6312 [2021-03-26 00:01:16 swin_base_patch4_window7_224] INFO: Epoch: [7] [1160/1251] eta: 0:00:58 lr: 0.000397 loss: 5.6786 (5.5194) grad_norm: 1.8185 (inf) time: 0.6341 [2021-03-26 00:01:23 swin_base_patch4_window7_224] INFO: Epoch: [7] [1170/1251] eta: 0:00:51 lr: 0.000397 loss: 5.4932 (5.5181) grad_norm: 1.7880 (inf) time: 0.6354 [2021-03-26 00:01:29 swin_base_patch4_window7_224] INFO: Epoch: [7] [1180/1251] eta: 0:00:45 lr: 0.000398 loss: 5.3848 (5.5165) grad_norm: 1.7199 (inf) time: 0.6356 [2021-03-26 00:01:35 swin_base_patch4_window7_224] INFO: Epoch: [7] [1190/1251] eta: 0:00:38 lr: 0.000398 loss: 5.4375 (5.5172) grad_norm: 1.7982 (inf) time: 0.6355 [2021-03-26 00:01:42 swin_base_patch4_window7_224] INFO: Epoch: [7] [1200/1251] eta: 0:00:32 lr: 0.000399 loss: 5.3643 (5.5158) grad_norm: 1.8448 (inf) time: 0.6358 [2021-03-26 00:01:48 swin_base_patch4_window7_224] INFO: Epoch: [7] [1210/1251] eta: 0:00:26 lr: 0.000399 loss: 5.2825 (5.5152) grad_norm: 1.8384 (inf) time: 0.6362 [2021-03-26 00:01:55 swin_base_patch4_window7_224] INFO: Epoch: [7] [1220/1251] eta: 0:00:19 lr: 0.000399 loss: 5.4825 (5.5139) grad_norm: 1.8384 (inf) time: 0.6375 [2021-03-26 00:02:01 swin_base_patch4_window7_224] INFO: Epoch: [7] [1230/1251] eta: 0:00:13 lr: 0.000400 loss: 5.4825 (5.5127) grad_norm: 1.7996 (inf) time: 0.6365 [2021-03-26 00:02:07 swin_base_patch4_window7_224] INFO: Epoch: [7] [1240/1251] eta: 0:00:07 lr: 0.000400 loss: 5.4233 (5.5123) grad_norm: 1.7996 (inf) time: 0.6301 [2021-03-26 00:02:14 swin_base_patch4_window7_224] INFO: Epoch: [7] [1250/1251] eta: 0:00:00 lr: 0.000401 loss: 5.5477 (5.5122) grad_norm: 1.9143 (inf) time: 0.6288 [2021-03-26 00:02:18 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:49 loss: 3.2509 (3.2509) acc1: 40.6250 (40.6250) acc5: 56.2500 (56.2500) [2021-03-26 00:02:21 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:21 loss: 3.2138 (3.2019) acc1: 37.5000 (33.5227) acc5: 59.3750 (58.8068) [2021-03-26 00:02:23 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 3.2138 (3.2186) acc1: 31.2500 (33.3333) acc5: 57.8125 (58.2589) [2021-03-26 00:02:25 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 3.1589 (3.1908) acc1: 32.8125 (33.9718) acc5: 57.8125 (58.9718) [2021-03-26 00:02:27 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 3.1432 (3.1987) acc1: 34.3750 (33.9558) acc5: 59.3750 (58.5747) [2021-03-26 00:02:28 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 3.1207 (3.1792) acc1: 35.9375 (34.1440) acc5: 59.3750 (58.7200) [2021-03-26 00:02:30 swin_base_patch4_window7_224] INFO: * Acc@1 33.688 Acc@5 59.676 loss 3.171 [2021-03-26 00:02:30 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 33.7% [2021-03-26 00:02:30 swin_base_patch4_window7_224] INFO: Max accuracy: 33.69% [2021-03-26 00:02:34 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 0/1251] eta: 1:20:14 lr: 0.000401 loss: 5.9619 (5.9619) grad_norm: 1.6973 (1.6973) time: 3.8481 [2021-03-26 00:02:41 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 10/1251] eta: 0:19:44 lr: 0.000401 loss: 5.6722 (5.5869) grad_norm: 2.0178 (1.9769) time: 0.9543 [2021-03-26 00:02:47 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 20/1251] eta: 0:16:31 lr: 0.000401 loss: 5.7030 (5.6342) grad_norm: 1.8807 (1.9440) time: 0.6532 [2021-03-26 00:02:54 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 30/1251] eta: 0:15:18 lr: 0.000402 loss: 5.8858 (5.6550) grad_norm: 1.9534 (2.0567) time: 0.6411 [2021-03-26 00:03:00 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 40/1251] eta: 0:14:34 lr: 0.000402 loss: 5.3802 (5.5581) grad_norm: 1.9534 (2.0155) time: 0.6352 [2021-03-26 00:03:06 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 50/1251] eta: 0:14:07 lr: 0.000403 loss: 5.5670 (5.5995) grad_norm: 1.7894 (2.0173) time: 0.6333 [2021-03-26 00:03:13 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 60/1251] eta: 0:13:45 lr: 0.000403 loss: 5.6646 (5.5835) grad_norm: 1.7844 (1.9843) time: 0.6343 [2021-03-26 00:03:19 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 70/1251] eta: 0:13:27 lr: 0.000403 loss: 5.5317 (5.5854) grad_norm: 1.6280 (1.9337) time: 0.6291 [2021-03-26 00:03:25 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 80/1251] eta: 0:13:13 lr: 0.000404 loss: 5.5317 (5.5704) grad_norm: 1.6853 (1.9765) time: 0.6282 [2021-03-26 00:03:32 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 90/1251] eta: 0:12:59 lr: 0.000404 loss: 5.6255 (5.5737) grad_norm: 1.9198 (2.0222) time: 0.6266 [2021-03-26 00:03:38 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 100/1251] eta: 0:12:49 lr: 0.000405 loss: 5.5536 (5.5641) grad_norm: 1.9222 (2.0075) time: 0.6327 [2021-03-26 00:03:44 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 110/1251] eta: 0:12:38 lr: 0.000405 loss: 5.5536 (5.5700) grad_norm: 1.8445 (1.9916) time: 0.6361 [2021-03-26 00:03:51 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 120/1251] eta: 0:12:30 lr: 0.000405 loss: 5.5752 (5.5696) grad_norm: 1.7274 (1.9913) time: 0.6400 [2021-03-26 00:03:57 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 130/1251] eta: 0:12:20 lr: 0.000406 loss: 5.5752 (5.5672) grad_norm: 1.7917 (1.9885) time: 0.6368 [2021-03-26 00:04:04 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 140/1251] eta: 0:12:12 lr: 0.000406 loss: 5.3431 (5.5436) grad_norm: 1.7917 (1.9793) time: 0.6333 [2021-03-26 00:04:10 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 150/1251] eta: 0:12:04 lr: 0.000407 loss: 5.0968 (5.5348) grad_norm: 1.7378 (1.9700) time: 0.6387 [2021-03-26 00:04:16 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 160/1251] eta: 0:11:56 lr: 0.000407 loss: 5.4843 (5.5402) grad_norm: 1.7440 (1.9634) time: 0.6340 [2021-03-26 00:04:22 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 170/1251] eta: 0:11:47 lr: 0.000407 loss: 5.6201 (5.5427) grad_norm: 1.8271 (1.9690) time: 0.6314 [2021-03-26 00:04:29 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 180/1251] eta: 0:11:39 lr: 0.000408 loss: 5.5841 (5.5305) grad_norm: 1.7130 (1.9724) time: 0.6311 [2021-03-26 00:04:35 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 190/1251] eta: 0:11:32 lr: 0.000408 loss: 5.6062 (5.5351) grad_norm: 1.7511 (1.9765) time: 0.6329 [2021-03-26 00:04:42 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 200/1251] eta: 0:11:25 lr: 0.000409 loss: 5.5968 (5.5349) grad_norm: 1.8992 (1.9981) time: 0.6358 [2021-03-26 00:04:48 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 210/1251] eta: 0:11:17 lr: 0.000409 loss: 5.4353 (5.5290) grad_norm: 1.9433 (1.9946) time: 0.6336 [2021-03-26 00:04:54 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 220/1251] eta: 0:11:09 lr: 0.000409 loss: 5.3004 (5.5130) grad_norm: 1.8107 (1.9896) time: 0.6304 [2021-03-26 00:05:01 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 230/1251] eta: 0:11:02 lr: 0.000410 loss: 5.3661 (5.5115) grad_norm: 1.7727 (1.9827) time: 0.6348 [2021-03-26 00:05:07 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 240/1251] eta: 0:10:55 lr: 0.000410 loss: 5.5569 (5.5166) grad_norm: 1.6273 (1.9813) time: 0.6366 [2021-03-26 00:05:13 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 250/1251] eta: 0:10:48 lr: 0.000411 loss: 5.6995 (5.5230) grad_norm: 1.6367 (1.9815) time: 0.6340 [2021-03-26 00:05:20 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 260/1251] eta: 0:10:41 lr: 0.000411 loss: 5.7157 (5.5264) grad_norm: 2.0972 (1.9925) time: 0.6364 [2021-03-26 00:05:26 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 270/1251] eta: 0:10:35 lr: 0.000411 loss: 5.5284 (5.5174) grad_norm: 2.2114 (2.0135) time: 0.6376 [2021-03-26 00:05:32 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 280/1251] eta: 0:10:28 lr: 0.000412 loss: 5.4859 (5.5173) grad_norm: 2.1097 (2.0338) time: 0.6362 [2021-03-26 00:05:39 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 290/1251] eta: 0:10:21 lr: 0.000412 loss: 5.4442 (5.5156) grad_norm: 1.7928 (2.0280) time: 0.6354 [2021-03-26 00:05:45 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 300/1251] eta: 0:10:14 lr: 0.000413 loss: 5.4446 (5.5193) grad_norm: 1.7105 (2.0212) time: 0.6334 [2021-03-26 00:05:52 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 310/1251] eta: 0:10:08 lr: 0.000413 loss: 5.4354 (5.5074) grad_norm: 1.7923 (2.0208) time: 0.6414 [2021-03-26 00:05:58 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 320/1251] eta: 0:10:01 lr: 0.000413 loss: 5.3481 (5.5071) grad_norm: 1.6888 (2.0102) time: 0.6430 [2021-03-26 00:06:04 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 330/1251] eta: 0:09:54 lr: 0.000414 loss: 5.4115 (5.5064) grad_norm: 1.7103 (2.0119) time: 0.6379 [2021-03-26 00:06:11 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 340/1251] eta: 0:09:47 lr: 0.000414 loss: 5.4115 (5.5032) grad_norm: 1.8911 (2.0110) time: 0.6323 [2021-03-26 00:06:17 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 350/1251] eta: 0:09:40 lr: 0.000415 loss: 5.5005 (5.5022) grad_norm: 1.8911 (2.0112) time: 0.6286 [2021-03-26 00:06:23 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 360/1251] eta: 0:09:34 lr: 0.000415 loss: 5.5499 (5.5062) grad_norm: 1.9092 (2.0210) time: 0.6317 [2021-03-26 00:06:29 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 370/1251] eta: 0:09:27 lr: 0.000415 loss: 5.4998 (5.4980) grad_norm: 1.7672 (2.0127) time: 0.6299 [2021-03-26 00:06:36 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 380/1251] eta: 0:09:20 lr: 0.000416 loss: 5.1608 (5.4928) grad_norm: 1.7304 (2.0075) time: 0.6350 [2021-03-26 00:06:42 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 390/1251] eta: 0:09:14 lr: 0.000416 loss: 5.2325 (5.4889) grad_norm: 1.8280 (2.0075) time: 0.6451 [2021-03-26 00:06:49 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 400/1251] eta: 0:09:07 lr: 0.000417 loss: 5.2896 (5.4846) grad_norm: 2.0039 (2.0536) time: 0.6390 [2021-03-26 00:06:55 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 410/1251] eta: 0:09:01 lr: 0.000417 loss: 5.2896 (5.4842) grad_norm: 1.8705 (2.0532) time: 0.6390 [2021-03-26 00:07:01 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 420/1251] eta: 0:08:54 lr: 0.000417 loss: 5.3578 (5.4806) grad_norm: 1.8910 (2.0542) time: 0.6385 [2021-03-26 00:07:08 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 430/1251] eta: 0:08:48 lr: 0.000418 loss: 5.1676 (5.4767) grad_norm: 1.9787 (2.0498) time: 0.6348 [2021-03-26 00:07:14 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 440/1251] eta: 0:08:41 lr: 0.000418 loss: 5.4020 (5.4790) grad_norm: 1.6811 (2.0416) time: 0.6337 [2021-03-26 00:07:20 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 450/1251] eta: 0:08:34 lr: 0.000419 loss: 5.4258 (5.4770) grad_norm: 1.7822 (2.0416) time: 0.6315 [2021-03-26 00:07:27 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 460/1251] eta: 0:08:28 lr: 0.000419 loss: 5.4258 (5.4743) grad_norm: 1.9198 (2.0444) time: 0.6333 [2021-03-26 00:07:33 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 470/1251] eta: 0:08:21 lr: 0.000419 loss: 5.5121 (5.4757) grad_norm: 1.9198 (2.0469) time: 0.6353 [2021-03-26 00:07:40 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 480/1251] eta: 0:08:15 lr: 0.000420 loss: 5.4191 (5.4736) grad_norm: 1.8512 (2.0453) time: 0.6371 [2021-03-26 00:07:46 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 490/1251] eta: 0:08:08 lr: 0.000420 loss: 5.5807 (5.4743) grad_norm: 1.8512 (2.0444) time: 0.6343 [2021-03-26 00:07:52 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 500/1251] eta: 0:08:02 lr: 0.000421 loss: 5.6958 (5.4779) grad_norm: 1.8441 (2.0401) time: 0.6333 [2021-03-26 00:07:59 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 510/1251] eta: 0:07:55 lr: 0.000421 loss: 5.6416 (5.4778) grad_norm: 1.8046 (2.0377) time: 0.6346 [2021-03-26 00:08:05 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 520/1251] eta: 0:07:49 lr: 0.000421 loss: 5.4543 (5.4785) grad_norm: 1.8696 (2.0347) time: 0.6410 [2021-03-26 00:08:11 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 530/1251] eta: 0:07:42 lr: 0.000422 loss: 5.2198 (5.4716) grad_norm: 1.8696 (2.0330) time: 0.6381 [2021-03-26 00:08:18 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 540/1251] eta: 0:07:36 lr: 0.000422 loss: 5.2198 (5.4744) grad_norm: 1.7695 (2.0271) time: 0.6350 [2021-03-26 00:08:24 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 550/1251] eta: 0:07:29 lr: 0.000423 loss: 5.5421 (5.4715) grad_norm: 1.5912 (2.0214) time: 0.6466 [2021-03-26 00:08:31 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 560/1251] eta: 0:07:23 lr: 0.000423 loss: 5.0716 (5.4648) grad_norm: 1.7834 (2.0238) time: 0.6499 [2021-03-26 00:08:37 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 570/1251] eta: 0:07:17 lr: 0.000423 loss: 5.0716 (5.4655) grad_norm: 1.8478 (2.0214) time: 0.6385 [2021-03-26 00:08:43 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 580/1251] eta: 0:07:10 lr: 0.000424 loss: 5.6962 (5.4668) grad_norm: 1.8500 (2.0319) time: 0.6366 [2021-03-26 00:08:50 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 590/1251] eta: 0:07:04 lr: 0.000424 loss: 5.2447 (5.4615) grad_norm: 1.9925 (2.0321) time: 0.6374 [2021-03-26 00:08:56 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 600/1251] eta: 0:06:57 lr: 0.000425 loss: 5.2263 (5.4618) grad_norm: 1.8552 (2.0270) time: 0.6356 [2021-03-26 00:09:02 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 610/1251] eta: 0:06:51 lr: 0.000425 loss: 5.2497 (5.4595) grad_norm: 1.7937 (2.0265) time: 0.6317 [2021-03-26 00:09:09 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 620/1251] eta: 0:06:44 lr: 0.000425 loss: 5.2100 (5.4568) grad_norm: 2.1238 (2.0300) time: 0.6322 [2021-03-26 00:09:15 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 630/1251] eta: 0:06:38 lr: 0.000426 loss: 5.7049 (5.4616) grad_norm: 1.9668 (2.0278) time: 0.6426 [2021-03-26 00:09:22 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 640/1251] eta: 0:06:31 lr: 0.000426 loss: 5.6297 (5.4587) grad_norm: 1.7642 (2.0243) time: 0.6436 [2021-03-26 00:09:28 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 650/1251] eta: 0:06:25 lr: 0.000427 loss: 5.3443 (5.4561) grad_norm: 1.7192 (2.0207) time: 0.6337 [2021-03-26 00:09:34 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 660/1251] eta: 0:06:18 lr: 0.000427 loss: 5.4834 (5.4571) grad_norm: 1.7331 (2.0185) time: 0.6305 [2021-03-26 00:09:41 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 670/1251] eta: 0:06:12 lr: 0.000427 loss: 5.6329 (5.4570) grad_norm: 1.7365 (2.0163) time: 0.6368 [2021-03-26 00:09:47 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 680/1251] eta: 0:06:05 lr: 0.000428 loss: 5.6685 (5.4604) grad_norm: 1.7092 (2.0125) time: 0.6344 [2021-03-26 00:09:53 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 690/1251] eta: 0:05:59 lr: 0.000428 loss: 5.6581 (5.4607) grad_norm: 1.7451 (2.0097) time: 0.6375 [2021-03-26 00:10:00 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 700/1251] eta: 0:05:53 lr: 0.000429 loss: 5.6564 (5.4620) grad_norm: 1.8321 (2.0103) time: 0.6375 [2021-03-26 00:10:06 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 710/1251] eta: 0:05:46 lr: 0.000429 loss: 5.5484 (5.4594) grad_norm: 1.9646 (2.0104) time: 0.6378 [2021-03-26 00:10:13 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 720/1251] eta: 0:05:40 lr: 0.000429 loss: 5.4857 (5.4580) grad_norm: 1.8772 (2.0103) time: 0.6392 [2021-03-26 00:10:19 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 730/1251] eta: 0:05:33 lr: 0.000430 loss: 5.5218 (5.4593) grad_norm: 1.7369 (2.0073) time: 0.6354 [2021-03-26 00:10:25 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 740/1251] eta: 0:05:27 lr: 0.000430 loss: 5.6082 (5.4593) grad_norm: 1.8349 (2.0064) time: 0.6401 [2021-03-26 00:10:32 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 750/1251] eta: 0:05:20 lr: 0.000431 loss: 5.3934 (5.4600) grad_norm: 2.0366 (2.0088) time: 0.6404 [2021-03-26 00:10:38 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 760/1251] eta: 0:05:14 lr: 0.000431 loss: 5.3884 (5.4588) grad_norm: 1.8712 (2.0064) time: 0.6355 [2021-03-26 00:10:44 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 770/1251] eta: 0:05:07 lr: 0.000431 loss: 5.3665 (5.4578) grad_norm: 1.8672 (2.0056) time: 0.6285 [2021-03-26 00:10:51 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 780/1251] eta: 0:05:01 lr: 0.000432 loss: 5.4872 (5.4568) grad_norm: 1.9756 (2.0079) time: 0.6271 [2021-03-26 00:10:57 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 790/1251] eta: 0:04:55 lr: 0.000432 loss: 5.2825 (5.4537) grad_norm: 1.8591 (2.0041) time: 0.6355 [2021-03-26 00:11:03 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 800/1251] eta: 0:04:48 lr: 0.000433 loss: 5.2881 (5.4532) grad_norm: 1.6377 (2.0003) time: 0.6378 [2021-03-26 00:11:10 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 810/1251] eta: 0:04:42 lr: 0.000433 loss: 5.6145 (5.4537) grad_norm: 1.8351 (2.0059) time: 0.6332 [2021-03-26 00:11:16 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 820/1251] eta: 0:04:35 lr: 0.000433 loss: 5.3640 (5.4508) grad_norm: 1.8314 (2.0021) time: 0.6401 [2021-03-26 00:11:23 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 830/1251] eta: 0:04:29 lr: 0.000434 loss: 5.5236 (5.4531) grad_norm: 1.6499 (2.0002) time: 0.6408 [2021-03-26 00:11:29 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 840/1251] eta: 0:04:22 lr: 0.000434 loss: 5.5936 (5.4521) grad_norm: 1.8311 (2.0050) time: 0.6272 [2021-03-26 00:11:35 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 850/1251] eta: 0:04:16 lr: 0.000435 loss: 5.6105 (5.4529) grad_norm: 1.9999 (2.0044) time: 0.6228 [2021-03-26 00:11:41 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 860/1251] eta: 0:04:10 lr: 0.000435 loss: 5.6266 (5.4540) grad_norm: 1.8513 (2.0044) time: 0.6303 [2021-03-26 00:11:48 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 870/1251] eta: 0:04:03 lr: 0.000435 loss: 5.7096 (5.4551) grad_norm: 1.6927 (2.0018) time: 0.6334 [2021-03-26 00:11:54 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 880/1251] eta: 0:03:57 lr: 0.000436 loss: 5.6365 (5.4538) grad_norm: 1.6936 (2.0017) time: 0.6356 [2021-03-26 00:12:00 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 890/1251] eta: 0:03:50 lr: 0.000436 loss: 5.3820 (5.4524) grad_norm: 1.8115 (1.9992) time: 0.6357 [2021-03-26 00:12:07 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 900/1251] eta: 0:03:44 lr: 0.000437 loss: 5.4700 (5.4529) grad_norm: 1.9342 (2.0000) time: 0.6317 [2021-03-26 00:12:13 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 910/1251] eta: 0:03:37 lr: 0.000437 loss: 5.5378 (5.4509) grad_norm: 1.9497 (1.9991) time: 0.6342 [2021-03-26 00:12:19 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 920/1251] eta: 0:03:31 lr: 0.000437 loss: 5.1748 (5.4499) grad_norm: 1.9972 (1.9998) time: 0.6367 [2021-03-26 00:12:26 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 930/1251] eta: 0:03:25 lr: 0.000438 loss: 5.2278 (5.4487) grad_norm: 1.9073 (1.9977) time: 0.6353 [2021-03-26 00:12:32 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 940/1251] eta: 0:03:18 lr: 0.000438 loss: 5.2314 (5.4493) grad_norm: 1.8076 (1.9958) time: 0.6318 [2021-03-26 00:12:38 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 950/1251] eta: 0:03:12 lr: 0.000439 loss: 5.4187 (5.4478) grad_norm: 1.7671 (1.9943) time: 0.6339 [2021-03-26 00:12:45 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 960/1251] eta: 0:03:05 lr: 0.000439 loss: 5.5658 (5.4497) grad_norm: 1.6809 (1.9920) time: 0.6355 [2021-03-26 00:12:51 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 970/1251] eta: 0:02:59 lr: 0.000439 loss: 5.5787 (5.4498) grad_norm: 1.7534 (1.9911) time: 0.6350 [2021-03-26 00:12:57 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 980/1251] eta: 0:02:53 lr: 0.000440 loss: 5.4636 (5.4485) grad_norm: 1.8517 (1.9923) time: 0.6319 [2021-03-26 00:13:04 swin_base_patch4_window7_224] INFO: Epoch: [8] [ 990/1251] eta: 0:02:46 lr: 0.000440 loss: 5.4657 (5.4490) grad_norm: 1.7780 (1.9885) time: 0.6325 [2021-03-26 00:13:10 swin_base_patch4_window7_224] INFO: Epoch: [8] [1000/1251] eta: 0:02:40 lr: 0.000441 loss: 5.5378 (5.4500) grad_norm: 1.7639 (1.9877) time: 0.6408 [2021-03-26 00:13:17 swin_base_patch4_window7_224] INFO: Epoch: [8] [1010/1251] eta: 0:02:33 lr: 0.000441 loss: 5.5947 (5.4516) grad_norm: 1.8666 (1.9864) time: 0.6368 [2021-03-26 00:13:23 swin_base_patch4_window7_224] INFO: Epoch: [8] [1020/1251] eta: 0:02:27 lr: 0.000441 loss: 5.5243 (5.4514) grad_norm: 1.8175 (1.9849) time: 0.6317 [2021-03-26 00:13:29 swin_base_patch4_window7_224] INFO: Epoch: [8] [1030/1251] eta: 0:02:21 lr: 0.000442 loss: 5.5036 (5.4508) grad_norm: 1.9297 (1.9874) time: 0.6303 [2021-03-26 00:13:35 swin_base_patch4_window7_224] INFO: Epoch: [8] [1040/1251] eta: 0:02:14 lr: 0.000442 loss: 5.5726 (5.4520) grad_norm: 1.9646 (1.9869) time: 0.6312 [2021-03-26 00:13:42 swin_base_patch4_window7_224] INFO: Epoch: [8] [1050/1251] eta: 0:02:08 lr: 0.000443 loss: 5.5604 (5.4507) grad_norm: 1.7647 (1.9845) time: 0.6402 [2021-03-26 00:13:48 swin_base_patch4_window7_224] INFO: Epoch: [8] [1060/1251] eta: 0:02:01 lr: 0.000443 loss: 5.6357 (5.4525) grad_norm: 1.7285 (1.9830) time: 0.6386 [2021-03-26 00:13:55 swin_base_patch4_window7_224] INFO: Epoch: [8] [1070/1251] eta: 0:01:55 lr: 0.000443 loss: 5.5400 (5.4506) grad_norm: 1.7401 (1.9836) time: 0.6326 [2021-03-26 00:14:01 swin_base_patch4_window7_224] INFO: Epoch: [8] [1080/1251] eta: 0:01:49 lr: 0.000444 loss: 5.2633 (5.4494) grad_norm: 1.8999 (1.9839) time: 0.6361 [2021-03-26 00:14:07 swin_base_patch4_window7_224] INFO: Epoch: [8] [1090/1251] eta: 0:01:42 lr: 0.000444 loss: 5.6833 (5.4510) grad_norm: 1.9137 (1.9826) time: 0.6388 [2021-03-26 00:14:14 swin_base_patch4_window7_224] INFO: Epoch: [8] [1100/1251] eta: 0:01:36 lr: 0.000445 loss: 5.3988 (5.4472) grad_norm: 1.8516 (1.9820) time: 0.6331 [2021-03-26 00:14:20 swin_base_patch4_window7_224] INFO: Epoch: [8] [1110/1251] eta: 0:01:30 lr: 0.000445 loss: 5.2825 (5.4469) grad_norm: 1.7362 (1.9828) time: 0.6335 [2021-03-26 00:14:26 swin_base_patch4_window7_224] INFO: Epoch: [8] [1120/1251] eta: 0:01:23 lr: 0.000445 loss: 5.4644 (5.4467) grad_norm: 1.9235 (1.9835) time: 0.6338 [2021-03-26 00:14:33 swin_base_patch4_window7_224] INFO: Epoch: [8] [1130/1251] eta: 0:01:17 lr: 0.000446 loss: 5.4780 (5.4458) grad_norm: 1.9235 (1.9824) time: 0.6298 [2021-03-26 00:14:39 swin_base_patch4_window7_224] INFO: Epoch: [8] [1140/1251] eta: 0:01:10 lr: 0.000446 loss: 5.4780 (5.4466) grad_norm: 1.8535 (1.9860) time: 0.6356 [2021-03-26 00:14:45 swin_base_patch4_window7_224] INFO: Epoch: [8] [1150/1251] eta: 0:01:04 lr: 0.000447 loss: 5.4346 (5.4460) grad_norm: 1.8995 (1.9852) time: 0.6332 [2021-03-26 00:14:52 swin_base_patch4_window7_224] INFO: Epoch: [8] [1160/1251] eta: 0:00:58 lr: 0.000447 loss: 5.4239 (5.4458) grad_norm: 2.0545 (1.9891) time: 0.6327 [2021-03-26 00:14:58 swin_base_patch4_window7_224] INFO: Epoch: [8] [1170/1251] eta: 0:00:51 lr: 0.000447 loss: 5.4184 (5.4437) grad_norm: 2.2131 (1.9909) time: 0.6376 [2021-03-26 00:15:04 swin_base_patch4_window7_224] INFO: Epoch: [8] [1180/1251] eta: 0:00:45 lr: 0.000448 loss: 5.2449 (5.4416) grad_norm: 2.0007 (1.9919) time: 0.6387 [2021-03-26 00:15:11 swin_base_patch4_window7_224] INFO: Epoch: [8] [1190/1251] eta: 0:00:38 lr: 0.000448 loss: 5.2615 (5.4409) grad_norm: 1.8690 (1.9906) time: 0.6356 [2021-03-26 00:15:17 swin_base_patch4_window7_224] INFO: Epoch: [8] [1200/1251] eta: 0:00:32 lr: 0.000449 loss: 5.2974 (5.4403) grad_norm: 1.7215 (1.9900) time: 0.6398 [2021-03-26 00:15:24 swin_base_patch4_window7_224] INFO: Epoch: [8] [1210/1251] eta: 0:00:26 lr: 0.000449 loss: 5.4965 (5.4410) grad_norm: 1.7564 (1.9886) time: 0.6424 [2021-03-26 00:15:30 swin_base_patch4_window7_224] INFO: Epoch: [8] [1220/1251] eta: 0:00:19 lr: 0.000449 loss: 5.4919 (5.4394) grad_norm: 1.7564 (1.9909) time: 0.6381 [2021-03-26 00:15:36 swin_base_patch4_window7_224] INFO: Epoch: [8] [1230/1251] eta: 0:00:13 lr: 0.000450 loss: 5.2509 (5.4394) grad_norm: 1.9156 (1.9909) time: 0.6391 [2021-03-26 00:15:43 swin_base_patch4_window7_224] INFO: Epoch: [8] [1240/1251] eta: 0:00:07 lr: 0.000450 loss: 5.4437 (5.4374) grad_norm: 1.9370 (1.9905) time: 0.6359 [2021-03-26 00:15:49 swin_base_patch4_window7_224] INFO: Epoch: [8] [1250/1251] eta: 0:00:00 lr: 0.000451 loss: 5.5196 (5.4385) grad_norm: 1.8018 (1.9920) time: 0.6323 [2021-03-26 00:15:53 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:40 loss: 2.9806 (2.9806) acc1: 34.3750 (34.3750) acc5: 67.1875 (67.1875) [2021-03-26 00:15:55 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 2.9731 (3.0350) acc1: 35.9375 (36.3636) acc5: 62.5000 (62.0739) [2021-03-26 00:15:57 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 2.9928 (3.0281) acc1: 35.9375 (36.6815) acc5: 62.5000 (62.2024) [2021-03-26 00:16:00 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 2.9744 (2.9616) acc1: 35.9375 (37.4496) acc5: 62.5000 (63.4577) [2021-03-26 00:16:02 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 2.9744 (2.9997) acc1: 32.8125 (36.5854) acc5: 62.5000 (62.4238) [2021-03-26 00:16:03 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 3.0739 (3.0288) acc1: 32.8125 (36.0320) acc5: 60.9375 (62.0480) [2021-03-26 00:16:05 swin_base_patch4_window7_224] INFO: * Acc@1 36.460 Acc@5 62.880 loss 3.008 [2021-03-26 00:16:05 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 36.5% [2021-03-26 00:16:05 swin_base_patch4_window7_224] INFO: Max accuracy: 36.46% [2021-03-26 00:16:10 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 0/1251] eta: 1:30:37 lr: 0.000451 loss: 4.8128 (4.8128) grad_norm: 2.6525 (2.6525) time: 4.3464 [2021-03-26 00:16:16 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 10/1251] eta: 0:20:03 lr: 0.000451 loss: 5.1722 (5.2925) grad_norm: 2.0947 (2.2384) time: 0.9699 [2021-03-26 00:16:22 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 20/1251] eta: 0:16:39 lr: 0.000451 loss: 5.1722 (5.2029) grad_norm: 2.0161 (2.2540) time: 0.6351 [2021-03-26 00:16:29 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 30/1251] eta: 0:15:20 lr: 0.000452 loss: 5.4379 (5.3091) grad_norm: 1.9673 (2.1455) time: 0.6356 [2021-03-26 00:16:35 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 40/1251] eta: 0:14:39 lr: 0.000452 loss: 5.4379 (5.3073) grad_norm: 1.8000 (2.0846) time: 0.6363 [2021-03-26 00:16:41 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 50/1251] eta: 0:14:07 lr: 0.000453 loss: 5.5509 (5.3505) grad_norm: 1.7678 (2.0691) time: 0.6313 [2021-03-26 00:16:48 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 60/1251] eta: 0:13:47 lr: 0.000453 loss: 5.4403 (5.3480) grad_norm: 1.9195 (2.1252) time: 0.6306 [2021-03-26 00:16:54 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 70/1251] eta: 0:13:29 lr: 0.000453 loss: 5.5242 (5.3902) grad_norm: 1.9195 (2.1097) time: 0.6317 [2021-03-26 00:17:00 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 80/1251] eta: 0:13:14 lr: 0.000454 loss: 5.5258 (5.3804) grad_norm: 1.9101 (2.1019) time: 0.6269 [2021-03-26 00:17:07 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 90/1251] eta: 0:13:02 lr: 0.000454 loss: 5.4971 (5.4103) grad_norm: 1.8565 (inf) time: 0.6335 [2021-03-26 00:17:13 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 100/1251] eta: 0:12:50 lr: 0.000455 loss: 5.5816 (5.4175) grad_norm: 1.8261 (inf) time: 0.6349 [2021-03-26 00:17:19 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 110/1251] eta: 0:12:39 lr: 0.000455 loss: 5.5253 (5.4172) grad_norm: 1.7022 (inf) time: 0.6267 [2021-03-26 00:17:26 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 120/1251] eta: 0:12:29 lr: 0.000455 loss: 5.6000 (5.4235) grad_norm: 1.6249 (inf) time: 0.6290 [2021-03-26 00:17:32 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 130/1251] eta: 0:12:20 lr: 0.000456 loss: 5.5359 (5.4098) grad_norm: 1.6881 (inf) time: 0.6322 [2021-03-26 00:17:38 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 140/1251] eta: 0:12:12 lr: 0.000456 loss: 5.4431 (5.4132) grad_norm: 1.7414 (inf) time: 0.6355 [2021-03-26 00:17:45 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 150/1251] eta: 0:12:04 lr: 0.000457 loss: 5.2502 (5.3943) grad_norm: 1.6863 (inf) time: 0.6431 [2021-03-26 00:17:51 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 160/1251] eta: 0:11:55 lr: 0.000457 loss: 5.4239 (5.4085) grad_norm: 2.0463 (inf) time: 0.6339 [2021-03-26 00:17:57 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 170/1251] eta: 0:11:47 lr: 0.000457 loss: 5.5093 (5.3998) grad_norm: 1.8621 (inf) time: 0.6311 [2021-03-26 00:18:04 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 180/1251] eta: 0:11:40 lr: 0.000458 loss: 5.1710 (5.3980) grad_norm: 1.8554 (inf) time: 0.6361 [2021-03-26 00:18:10 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 190/1251] eta: 0:11:32 lr: 0.000458 loss: 5.4896 (5.3999) grad_norm: 2.0061 (inf) time: 0.6338 [2021-03-26 00:18:16 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 200/1251] eta: 0:11:25 lr: 0.000459 loss: 5.5207 (5.4015) grad_norm: 1.9975 (inf) time: 0.6354 [2021-03-26 00:18:23 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 210/1251] eta: 0:11:17 lr: 0.000459 loss: 5.4909 (5.4037) grad_norm: 1.8496 (inf) time: 0.6356 [2021-03-26 00:18:29 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 220/1251] eta: 0:11:10 lr: 0.000459 loss: 5.6473 (5.4060) grad_norm: 1.6524 (inf) time: 0.6331 [2021-03-26 00:18:35 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 230/1251] eta: 0:11:03 lr: 0.000460 loss: 5.7612 (5.4203) grad_norm: 1.7976 (inf) time: 0.6331 [2021-03-26 00:18:42 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 240/1251] eta: 0:10:56 lr: 0.000460 loss: 5.7540 (5.4280) grad_norm: 1.9923 (inf) time: 0.6363 [2021-03-26 00:18:48 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 250/1251] eta: 0:10:49 lr: 0.000461 loss: 5.6884 (5.4359) grad_norm: 1.8397 (inf) time: 0.6375 [2021-03-26 00:18:55 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 260/1251] eta: 0:10:42 lr: 0.000461 loss: 5.6142 (5.4350) grad_norm: 1.8105 (inf) time: 0.6352 [2021-03-26 00:19:01 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 270/1251] eta: 0:10:35 lr: 0.000461 loss: 5.2245 (5.4253) grad_norm: 1.8443 (inf) time: 0.6328 [2021-03-26 00:19:07 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 280/1251] eta: 0:10:27 lr: 0.000462 loss: 5.3144 (5.4256) grad_norm: 1.7288 (inf) time: 0.6292 [2021-03-26 00:19:14 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 290/1251] eta: 0:10:21 lr: 0.000462 loss: 5.5347 (5.4282) grad_norm: 1.7015 (inf) time: 0.6329 [2021-03-26 00:19:20 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 300/1251] eta: 0:10:14 lr: 0.000463 loss: 5.2680 (5.4187) grad_norm: 1.7080 (inf) time: 0.6350 [2021-03-26 00:19:26 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 310/1251] eta: 0:10:07 lr: 0.000463 loss: 5.2517 (5.4175) grad_norm: 1.8660 (inf) time: 0.6324 [2021-03-26 00:19:33 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 320/1251] eta: 0:10:00 lr: 0.000463 loss: 5.2875 (5.4125) grad_norm: 1.8309 (inf) time: 0.6356 [2021-03-26 00:19:39 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 330/1251] eta: 0:09:54 lr: 0.000464 loss: 5.2611 (5.4060) grad_norm: 1.6810 (inf) time: 0.6402 [2021-03-26 00:19:45 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 340/1251] eta: 0:09:47 lr: 0.000464 loss: 5.3510 (5.4046) grad_norm: 1.6389 (inf) time: 0.6351 [2021-03-26 00:19:52 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 350/1251] eta: 0:09:40 lr: 0.000465 loss: 5.3364 (5.4025) grad_norm: 1.6984 (inf) time: 0.6358 [2021-03-26 00:19:58 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 360/1251] eta: 0:09:33 lr: 0.000465 loss: 5.3232 (5.4022) grad_norm: 1.7599 (inf) time: 0.6323 [2021-03-26 00:20:04 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 370/1251] eta: 0:09:26 lr: 0.000465 loss: 5.2410 (5.3924) grad_norm: 1.9410 (inf) time: 0.6221 [2021-03-26 00:20:10 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 380/1251] eta: 0:09:20 lr: 0.000466 loss: 5.2719 (5.3955) grad_norm: 1.9125 (inf) time: 0.6292 [2021-03-26 00:20:17 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 390/1251] eta: 0:09:13 lr: 0.000466 loss: 5.5408 (5.3950) grad_norm: 1.8163 (inf) time: 0.6323 [2021-03-26 00:20:23 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 400/1251] eta: 0:09:06 lr: 0.000467 loss: 5.5059 (5.3957) grad_norm: 1.8823 (inf) time: 0.6298 [2021-03-26 00:20:29 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 410/1251] eta: 0:09:00 lr: 0.000467 loss: 5.1777 (5.3935) grad_norm: 1.8190 (inf) time: 0.6300 [2021-03-26 00:20:36 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 420/1251] eta: 0:08:53 lr: 0.000467 loss: 5.2511 (5.3970) grad_norm: 1.6875 (inf) time: 0.6296 [2021-03-26 00:20:42 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 430/1251] eta: 0:08:46 lr: 0.000468 loss: 5.6150 (5.3954) grad_norm: 1.7033 (inf) time: 0.6268 [2021-03-26 00:20:48 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 440/1251] eta: 0:08:40 lr: 0.000468 loss: 5.4009 (5.3960) grad_norm: 1.6958 (inf) time: 0.6307 [2021-03-26 00:20:55 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 450/1251] eta: 0:08:33 lr: 0.000469 loss: 5.4118 (5.3955) grad_norm: 1.6059 (inf) time: 0.6322 [2021-03-26 00:21:01 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 460/1251] eta: 0:08:27 lr: 0.000469 loss: 5.2970 (5.3884) grad_norm: 1.7565 (inf) time: 0.6331 [2021-03-26 00:21:07 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 470/1251] eta: 0:08:20 lr: 0.000469 loss: 5.1907 (5.3861) grad_norm: 1.7565 (inf) time: 0.6322 [2021-03-26 00:21:14 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 480/1251] eta: 0:08:13 lr: 0.000470 loss: 5.4138 (5.3862) grad_norm: 1.7044 (inf) time: 0.6318 [2021-03-26 00:21:20 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 490/1251] eta: 0:08:07 lr: 0.000470 loss: 5.1747 (5.3796) grad_norm: 1.6820 (inf) time: 0.6371 [2021-03-26 00:21:26 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 500/1251] eta: 0:08:00 lr: 0.000471 loss: 5.0660 (5.3792) grad_norm: 1.8662 (inf) time: 0.6306 [2021-03-26 00:21:33 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 510/1251] eta: 0:07:54 lr: 0.000471 loss: 5.5328 (5.3798) grad_norm: 1.9059 (inf) time: 0.6284 [2021-03-26 00:21:39 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 520/1251] eta: 0:07:47 lr: 0.000471 loss: 5.4920 (5.3790) grad_norm: 1.7179 (inf) time: 0.6351 [2021-03-26 00:21:45 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 530/1251] eta: 0:07:41 lr: 0.000472 loss: 5.3797 (5.3789) grad_norm: 1.7176 (inf) time: 0.6381 [2021-03-26 00:21:52 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 540/1251] eta: 0:07:34 lr: 0.000472 loss: 5.2556 (5.3768) grad_norm: 1.9504 (inf) time: 0.6352 [2021-03-26 00:21:58 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 550/1251] eta: 0:07:28 lr: 0.000473 loss: 5.3876 (5.3786) grad_norm: 1.9649 (inf) time: 0.6520 [2021-03-26 00:22:05 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 560/1251] eta: 0:07:22 lr: 0.000473 loss: 5.5275 (5.3799) grad_norm: 1.8755 (inf) time: 0.6517 [2021-03-26 00:22:11 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 570/1251] eta: 0:07:16 lr: 0.000473 loss: 5.2914 (5.3771) grad_norm: 1.7186 (inf) time: 0.6377 [2021-03-26 00:22:17 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 580/1251] eta: 0:07:09 lr: 0.000474 loss: 5.2914 (5.3757) grad_norm: 1.7339 (inf) time: 0.6369 [2021-03-26 00:22:24 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 590/1251] eta: 0:07:03 lr: 0.000474 loss: 5.4828 (5.3765) grad_norm: 1.7957 (inf) time: 0.6334 [2021-03-26 00:22:30 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 600/1251] eta: 0:06:56 lr: 0.000475 loss: 5.4252 (5.3727) grad_norm: 1.8153 (inf) time: 0.6375 [2021-03-26 00:22:37 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 610/1251] eta: 0:06:50 lr: 0.000475 loss: 5.4252 (5.3718) grad_norm: 1.9407 (inf) time: 0.6382 [2021-03-26 00:22:43 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 620/1251] eta: 0:06:43 lr: 0.000475 loss: 5.4776 (5.3712) grad_norm: 2.0518 (inf) time: 0.6331 [2021-03-26 00:22:49 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 630/1251] eta: 0:06:37 lr: 0.000476 loss: 5.1840 (5.3651) grad_norm: 1.8092 (inf) time: 0.6256 [2021-03-26 00:22:56 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 640/1251] eta: 0:06:30 lr: 0.000476 loss: 5.4749 (5.3700) grad_norm: 1.8092 (inf) time: 0.6332 [2021-03-26 00:23:02 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 650/1251] eta: 0:06:24 lr: 0.000477 loss: 5.5207 (5.3692) grad_norm: 1.6533 (inf) time: 0.6427 [2021-03-26 00:23:08 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 660/1251] eta: 0:06:17 lr: 0.000477 loss: 5.4462 (5.3701) grad_norm: 1.7409 (inf) time: 0.6380 [2021-03-26 00:23:15 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 670/1251] eta: 0:06:11 lr: 0.000477 loss: 5.5050 (5.3721) grad_norm: 1.7448 (inf) time: 0.6383 [2021-03-26 00:23:21 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 680/1251] eta: 0:06:05 lr: 0.000478 loss: 5.2400 (5.3683) grad_norm: 1.7119 (inf) time: 0.6357 [2021-03-26 00:23:27 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 690/1251] eta: 0:05:58 lr: 0.000478 loss: 5.3813 (5.3706) grad_norm: 1.6761 (inf) time: 0.6323 [2021-03-26 00:23:34 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 700/1251] eta: 0:05:52 lr: 0.000478 loss: 5.4387 (5.3705) grad_norm: 1.7212 (inf) time: 0.6385 [2021-03-26 00:23:40 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 710/1251] eta: 0:05:45 lr: 0.000479 loss: 5.2597 (5.3691) grad_norm: 1.9323 (inf) time: 0.6396 [2021-03-26 00:23:47 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 720/1251] eta: 0:05:39 lr: 0.000479 loss: 5.3771 (5.3693) grad_norm: 1.9772 (inf) time: 0.6398 [2021-03-26 00:23:53 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 730/1251] eta: 0:05:33 lr: 0.000480 loss: 5.4607 (5.3666) grad_norm: 2.0027 (inf) time: 0.6359 [2021-03-26 00:23:59 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 740/1251] eta: 0:05:26 lr: 0.000480 loss: 5.4792 (5.3671) grad_norm: 1.9429 (inf) time: 0.6391 [2021-03-26 00:24:06 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 750/1251] eta: 0:05:20 lr: 0.000480 loss: 5.6540 (5.3697) grad_norm: 1.7320 (inf) time: 0.6416 [2021-03-26 00:24:12 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 760/1251] eta: 0:05:13 lr: 0.000481 loss: 5.4699 (5.3682) grad_norm: 1.9279 (inf) time: 0.6348 [2021-03-26 00:24:18 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 770/1251] eta: 0:05:07 lr: 0.000481 loss: 5.2338 (5.3677) grad_norm: 2.1216 (inf) time: 0.6344 [2021-03-26 00:24:25 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 780/1251] eta: 0:05:01 lr: 0.000482 loss: 5.4673 (5.3684) grad_norm: 1.9605 (inf) time: 0.6303 [2021-03-26 00:24:31 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 790/1251] eta: 0:04:54 lr: 0.000482 loss: 5.4673 (5.3683) grad_norm: 1.7662 (inf) time: 0.6335 [2021-03-26 00:24:37 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 800/1251] eta: 0:04:48 lr: 0.000482 loss: 5.4055 (5.3678) grad_norm: 1.7615 (inf) time: 0.6317 [2021-03-26 00:24:44 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 810/1251] eta: 0:04:41 lr: 0.000483 loss: 5.4365 (5.3705) grad_norm: 1.8560 (inf) time: 0.6264 [2021-03-26 00:24:50 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 820/1251] eta: 0:04:35 lr: 0.000483 loss: 5.5810 (5.3706) grad_norm: 1.6771 (inf) time: 0.6354 [2021-03-26 00:24:56 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 830/1251] eta: 0:04:28 lr: 0.000484 loss: 5.4277 (5.3701) grad_norm: 1.6405 (inf) time: 0.6392 [2021-03-26 00:25:03 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 840/1251] eta: 0:04:22 lr: 0.000484 loss: 5.1674 (5.3667) grad_norm: 1.8805 (inf) time: 0.6437 [2021-03-26 00:25:09 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 850/1251] eta: 0:04:16 lr: 0.000484 loss: 5.1727 (5.3651) grad_norm: 1.8748 (inf) time: 0.6444 [2021-03-26 00:25:16 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 860/1251] eta: 0:04:09 lr: 0.000485 loss: 5.2483 (5.3636) grad_norm: 1.8119 (inf) time: 0.6384 [2021-03-26 00:25:22 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 870/1251] eta: 0:04:03 lr: 0.000485 loss: 5.2483 (5.3624) grad_norm: 1.7096 (inf) time: 0.6370 [2021-03-26 00:25:28 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 880/1251] eta: 0:03:56 lr: 0.000486 loss: 5.0550 (5.3585) grad_norm: 1.7096 (inf) time: 0.6325 [2021-03-26 00:25:35 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 890/1251] eta: 0:03:50 lr: 0.000486 loss: 5.2897 (5.3595) grad_norm: 1.7742 (inf) time: 0.6383 [2021-03-26 00:25:41 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 900/1251] eta: 0:03:44 lr: 0.000486 loss: 5.3451 (5.3580) grad_norm: 1.7185 (inf) time: 0.6398 [2021-03-26 00:25:48 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 910/1251] eta: 0:03:37 lr: 0.000487 loss: 5.4295 (5.3599) grad_norm: 1.6282 (inf) time: 0.6369 [2021-03-26 00:25:54 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 920/1251] eta: 0:03:31 lr: 0.000487 loss: 5.4253 (5.3587) grad_norm: 1.7978 (inf) time: 0.6402 [2021-03-26 00:26:00 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 930/1251] eta: 0:03:25 lr: 0.000488 loss: 5.0454 (5.3560) grad_norm: 2.1338 (inf) time: 0.6362 [2021-03-26 00:26:07 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 940/1251] eta: 0:03:18 lr: 0.000488 loss: 4.9337 (5.3528) grad_norm: 2.1338 (inf) time: 0.6328 [2021-03-26 00:26:13 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 950/1251] eta: 0:03:12 lr: 0.000488 loss: 5.0597 (5.3515) grad_norm: 2.0135 (inf) time: 0.6333 [2021-03-26 00:26:19 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 960/1251] eta: 0:03:05 lr: 0.000489 loss: 5.2714 (5.3505) grad_norm: 1.8259 (inf) time: 0.6347 [2021-03-26 00:26:26 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 970/1251] eta: 0:02:59 lr: 0.000489 loss: 5.3032 (5.3513) grad_norm: 1.7605 (inf) time: 0.6322 [2021-03-26 00:26:32 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 980/1251] eta: 0:02:53 lr: 0.000490 loss: 5.3392 (5.3500) grad_norm: 1.7367 (inf) time: 0.6325 [2021-03-26 00:26:38 swin_base_patch4_window7_224] INFO: Epoch: [9] [ 990/1251] eta: 0:02:46 lr: 0.000490 loss: 5.3635 (5.3497) grad_norm: 1.7947 (inf) time: 0.6332 [2021-03-26 00:26:45 swin_base_patch4_window7_224] INFO: Epoch: [9] [1000/1251] eta: 0:02:40 lr: 0.000490 loss: 5.3311 (5.3498) grad_norm: 1.8831 (inf) time: 0.6371 [2021-03-26 00:26:51 swin_base_patch4_window7_224] INFO: Epoch: [9] [1010/1251] eta: 0:02:33 lr: 0.000491 loss: 5.3311 (5.3495) grad_norm: 1.6899 (inf) time: 0.6389 [2021-03-26 00:26:57 swin_base_patch4_window7_224] INFO: Epoch: [9] [1020/1251] eta: 0:02:27 lr: 0.000491 loss: 5.2763 (5.3484) grad_norm: 1.7641 (inf) time: 0.6350 [2021-03-26 00:27:04 swin_base_patch4_window7_224] INFO: Epoch: [9] [1030/1251] eta: 0:02:21 lr: 0.000492 loss: 5.3474 (5.3497) grad_norm: 2.0044 (inf) time: 0.6372 [2021-03-26 00:27:10 swin_base_patch4_window7_224] INFO: Epoch: [9] [1040/1251] eta: 0:02:14 lr: 0.000492 loss: 5.4250 (5.3497) grad_norm: 2.0575 (inf) time: 0.6344 [2021-03-26 00:27:16 swin_base_patch4_window7_224] INFO: Epoch: [9] [1050/1251] eta: 0:02:08 lr: 0.000492 loss: 5.3934 (5.3487) grad_norm: 1.8716 (inf) time: 0.6289 [2021-03-26 00:27:23 swin_base_patch4_window7_224] INFO: Epoch: [9] [1060/1251] eta: 0:02:01 lr: 0.000493 loss: 5.2918 (5.3485) grad_norm: 1.6540 (inf) time: 0.6311 [2021-03-26 00:27:29 swin_base_patch4_window7_224] INFO: Epoch: [9] [1070/1251] eta: 0:01:55 lr: 0.000493 loss: 5.4835 (5.3499) grad_norm: 1.6191 (inf) time: 0.6389 [2021-03-26 00:27:36 swin_base_patch4_window7_224] INFO: Epoch: [9] [1080/1251] eta: 0:01:49 lr: 0.000494 loss: 5.4591 (5.3483) grad_norm: 1.5816 (inf) time: 0.6436 [2021-03-26 00:27:42 swin_base_patch4_window7_224] INFO: Epoch: [9] [1090/1251] eta: 0:01:42 lr: 0.000494 loss: 5.4467 (5.3482) grad_norm: 1.7089 (inf) time: 0.6365 [2021-03-26 00:27:48 swin_base_patch4_window7_224] INFO: Epoch: [9] [1100/1251] eta: 0:01:36 lr: 0.000494 loss: 5.4354 (5.3461) grad_norm: 1.7887 (inf) time: 0.6342 [2021-03-26 00:27:55 swin_base_patch4_window7_224] INFO: Epoch: [9] [1110/1251] eta: 0:01:29 lr: 0.000495 loss: 4.8799 (5.3418) grad_norm: 1.8182 (inf) time: 0.6364 [2021-03-26 00:28:01 swin_base_patch4_window7_224] INFO: Epoch: [9] [1120/1251] eta: 0:01:23 lr: 0.000495 loss: 4.9540 (5.3419) grad_norm: 1.8943 (inf) time: 0.6364 [2021-03-26 00:28:07 swin_base_patch4_window7_224] INFO: Epoch: [9] [1130/1251] eta: 0:01:17 lr: 0.000496 loss: 5.4918 (5.3415) grad_norm: 1.8992 (inf) time: 0.6366 [2021-03-26 00:28:14 swin_base_patch4_window7_224] INFO: Epoch: [9] [1140/1251] eta: 0:01:10 lr: 0.000496 loss: 5.2677 (5.3398) grad_norm: 1.8720 (inf) time: 0.6339 [2021-03-26 00:28:20 swin_base_patch4_window7_224] INFO: Epoch: [9] [1150/1251] eta: 0:01:04 lr: 0.000496 loss: 5.4422 (5.3412) grad_norm: 1.9266 (inf) time: 0.6340 [2021-03-26 00:28:26 swin_base_patch4_window7_224] INFO: Epoch: [9] [1160/1251] eta: 0:00:58 lr: 0.000497 loss: 5.4433 (5.3389) grad_norm: 2.0305 (inf) time: 0.6410 [2021-03-26 00:28:33 swin_base_patch4_window7_224] INFO: Epoch: [9] [1170/1251] eta: 0:00:51 lr: 0.000497 loss: 5.0340 (5.3384) grad_norm: 2.0099 (inf) time: 0.6367 [2021-03-26 00:28:39 swin_base_patch4_window7_224] INFO: Epoch: [9] [1180/1251] eta: 0:00:45 lr: 0.000498 loss: 4.9664 (5.3356) grad_norm: 1.8222 (inf) time: 0.6284 [2021-03-26 00:28:45 swin_base_patch4_window7_224] INFO: Epoch: [9] [1190/1251] eta: 0:00:38 lr: 0.000498 loss: 5.1659 (5.3352) grad_norm: 1.6729 (inf) time: 0.6316 [2021-03-26 00:28:52 swin_base_patch4_window7_224] INFO: Epoch: [9] [1200/1251] eta: 0:00:32 lr: 0.000498 loss: 5.2730 (5.3348) grad_norm: 1.8318 (inf) time: 0.6335 [2021-03-26 00:28:58 swin_base_patch4_window7_224] INFO: Epoch: [9] [1210/1251] eta: 0:00:26 lr: 0.000499 loss: 5.5826 (5.3368) grad_norm: 1.7813 (inf) time: 0.6320 [2021-03-26 00:29:04 swin_base_patch4_window7_224] INFO: Epoch: [9] [1220/1251] eta: 0:00:19 lr: 0.000499 loss: 5.3212 (5.3355) grad_norm: 1.7704 (inf) time: 0.6319 [2021-03-26 00:29:11 swin_base_patch4_window7_224] INFO: Epoch: [9] [1230/1251] eta: 0:00:13 lr: 0.000500 loss: 5.1680 (5.3353) grad_norm: 1.7995 (inf) time: 0.6272 [2021-03-26 00:29:17 swin_base_patch4_window7_224] INFO: Epoch: [9] [1240/1251] eta: 0:00:07 lr: 0.000500 loss: 5.1783 (5.3343) grad_norm: 1.7085 (inf) time: 0.6261 [2021-03-26 00:29:23 swin_base_patch4_window7_224] INFO: Epoch: [9] [1250/1251] eta: 0:00:00 lr: 0.000500 loss: 5.4667 (5.3344) grad_norm: 1.6414 (inf) time: 0.6263 [2021-03-26 00:29:28 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:35 loss: 3.0359 (3.0359) acc1: 34.3750 (34.3750) acc5: 64.0625 (64.0625) [2021-03-26 00:29:30 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 2.9218 (2.8279) acc1: 39.0625 (39.6307) acc5: 64.0625 (65.3409) [2021-03-26 00:29:33 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 2.9179 (2.8482) acc1: 39.0625 (39.9554) acc5: 65.6250 (65.6250) [2021-03-26 00:29:35 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 2.9374 (2.8916) acc1: 37.5000 (39.2641) acc5: 64.0625 (64.6673) [2021-03-26 00:29:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 2.9154 (2.8811) acc1: 37.5000 (38.9863) acc5: 62.5000 (64.9009) [2021-03-26 00:29:37 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.9153 (2.8887) acc1: 37.5000 (39.0400) acc5: 64.0625 (64.6720) [2021-03-26 00:29:39 swin_base_patch4_window7_224] INFO: * Acc@1 38.562 Acc@5 64.948 loss 2.887 [2021-03-26 00:29:39 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 38.6% [2021-03-26 00:29:39 swin_base_patch4_window7_224] INFO: Max accuracy: 38.56% [2021-03-26 00:29:44 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 0/1251] eta: 1:32:33 lr: 0.000501 loss: 5.8243 (5.8243) grad_norm: 2.4211 (2.4211) time: 4.4392 [2021-03-26 00:29:50 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 10/1251] eta: 0:20:22 lr: 0.000501 loss: 5.5072 (5.5816) grad_norm: 1.9234 (1.8917) time: 0.9852 [2021-03-26 00:29:57 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 20/1251] eta: 0:16:47 lr: 0.000501 loss: 5.4865 (5.5026) grad_norm: 1.9362 (2.0397) time: 0.6378 [2021-03-26 00:30:03 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 30/1251] eta: 0:15:29 lr: 0.000502 loss: 5.3622 (5.4390) grad_norm: 1.9260 (1.9880) time: 0.6380 [2021-03-26 00:30:09 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 40/1251] eta: 0:14:45 lr: 0.000502 loss: 5.3056 (5.4428) grad_norm: 1.6971 (2.1096) time: 0.6388 [2021-03-26 00:30:16 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 50/1251] eta: 0:14:14 lr: 0.000502 loss: 5.5690 (5.4091) grad_norm: 1.8433 (2.0963) time: 0.6354 [2021-03-26 00:30:22 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 60/1251] eta: 0:13:51 lr: 0.000503 loss: 5.4542 (5.3703) grad_norm: 1.8433 (2.0436) time: 0.6301 [2021-03-26 00:30:28 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 70/1251] eta: 0:13:33 lr: 0.000503 loss: 5.4516 (5.3835) grad_norm: 1.8473 (2.0444) time: 0.6313 [2021-03-26 00:30:35 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 80/1251] eta: 0:13:19 lr: 0.000504 loss: 5.4935 (5.3971) grad_norm: 1.8067 (2.0183) time: 0.6351 [2021-03-26 00:30:41 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 90/1251] eta: 0:13:05 lr: 0.000504 loss: 5.4207 (5.3851) grad_norm: 1.7425 (2.0023) time: 0.6331 [2021-03-26 00:30:47 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 100/1251] eta: 0:12:55 lr: 0.000504 loss: 5.2329 (5.3629) grad_norm: 1.7425 (2.0095) time: 0.6377 [2021-03-26 00:30:54 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 110/1251] eta: 0:12:43 lr: 0.000505 loss: 5.4874 (5.3656) grad_norm: 1.7837 (1.9818) time: 0.6355 [2021-03-26 00:31:00 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 120/1251] eta: 0:12:34 lr: 0.000505 loss: 5.4616 (5.3689) grad_norm: 1.7862 (1.9793) time: 0.6324 [2021-03-26 00:31:06 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 130/1251] eta: 0:12:24 lr: 0.000506 loss: 5.4557 (5.3636) grad_norm: 1.9363 (1.9757) time: 0.6325 [2021-03-26 00:31:13 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 140/1251] eta: 0:12:15 lr: 0.000506 loss: 5.3826 (5.3531) grad_norm: 1.8404 (1.9611) time: 0.6310 [2021-03-26 00:31:19 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 150/1251] eta: 0:12:06 lr: 0.000506 loss: 5.4136 (5.3562) grad_norm: 1.6467 (2.0229) time: 0.6359 [2021-03-26 00:31:25 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 160/1251] eta: 0:11:58 lr: 0.000507 loss: 5.4032 (5.3556) grad_norm: 1.6676 (2.0040) time: 0.6373 [2021-03-26 00:31:32 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 170/1251] eta: 0:11:51 lr: 0.000507 loss: 5.4817 (5.3604) grad_norm: 1.7877 (1.9936) time: 0.6404 [2021-03-26 00:31:38 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 180/1251] eta: 0:11:43 lr: 0.000508 loss: 5.6006 (5.3632) grad_norm: 1.8533 (1.9870) time: 0.6423 [2021-03-26 00:31:45 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 190/1251] eta: 0:11:35 lr: 0.000508 loss: 5.4592 (5.3622) grad_norm: 1.7689 (1.9723) time: 0.6386 [2021-03-26 00:31:51 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 200/1251] eta: 0:11:28 lr: 0.000508 loss: 5.4161 (5.3553) grad_norm: 1.5525 (1.9510) time: 0.6377 [2021-03-26 00:31:57 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 210/1251] eta: 0:11:20 lr: 0.000509 loss: 5.4161 (5.3587) grad_norm: 1.6224 (1.9464) time: 0.6347 [2021-03-26 00:32:04 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 220/1251] eta: 0:11:13 lr: 0.000509 loss: 5.6326 (5.3635) grad_norm: 1.8153 (1.9433) time: 0.6377 [2021-03-26 00:32:10 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 230/1251] eta: 0:11:05 lr: 0.000510 loss: 5.4580 (5.3647) grad_norm: 1.7537 (1.9361) time: 0.6350 [2021-03-26 00:32:16 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 240/1251] eta: 0:10:58 lr: 0.000510 loss: 5.0557 (5.3521) grad_norm: 1.7779 (1.9419) time: 0.6284 [2021-03-26 00:32:23 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 250/1251] eta: 0:10:51 lr: 0.000510 loss: 5.0665 (5.3530) grad_norm: 1.7841 (1.9342) time: 0.6296 [2021-03-26 00:32:29 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 260/1251] eta: 0:10:43 lr: 0.000511 loss: 5.4711 (5.3589) grad_norm: 1.6795 (1.9300) time: 0.6248 [2021-03-26 00:32:35 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 270/1251] eta: 0:10:36 lr: 0.000511 loss: 5.2761 (5.3504) grad_norm: 1.8194 (1.9366) time: 0.6273 [2021-03-26 00:32:42 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 280/1251] eta: 0:10:29 lr: 0.000512 loss: 5.0398 (5.3449) grad_norm: 1.7498 (1.9276) time: 0.6346 [2021-03-26 00:32:48 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 290/1251] eta: 0:10:22 lr: 0.000512 loss: 5.1153 (5.3393) grad_norm: 1.7662 (1.9493) time: 0.6373 [2021-03-26 00:32:54 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 300/1251] eta: 0:10:15 lr: 0.000512 loss: 5.1680 (5.3338) grad_norm: 1.8091 (1.9489) time: 0.6376 [2021-03-26 00:33:01 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 310/1251] eta: 0:10:08 lr: 0.000513 loss: 5.4111 (5.3372) grad_norm: 1.8054 (1.9418) time: 0.6324 [2021-03-26 00:33:07 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 320/1251] eta: 0:10:01 lr: 0.000513 loss: 5.3351 (5.3385) grad_norm: 1.7739 (1.9417) time: 0.6331 [2021-03-26 00:33:13 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 330/1251] eta: 0:09:54 lr: 0.000514 loss: 5.2702 (5.3320) grad_norm: 1.7739 (1.9376) time: 0.6328 [2021-03-26 00:33:20 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 340/1251] eta: 0:09:48 lr: 0.000514 loss: 5.3092 (5.3364) grad_norm: 1.8798 (1.9394) time: 0.6276 [2021-03-26 00:33:26 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 350/1251] eta: 0:09:41 lr: 0.000514 loss: 5.3144 (5.3314) grad_norm: 1.9762 (1.9410) time: 0.6294 [2021-03-26 00:33:32 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 360/1251] eta: 0:09:34 lr: 0.000515 loss: 5.3156 (5.3354) grad_norm: 1.6570 (1.9394) time: 0.6293 [2021-03-26 00:33:38 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 370/1251] eta: 0:09:27 lr: 0.000515 loss: 5.4372 (5.3348) grad_norm: 1.7875 (1.9393) time: 0.6277 [2021-03-26 00:33:45 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 380/1251] eta: 0:09:20 lr: 0.000516 loss: 5.3309 (5.3332) grad_norm: 1.8235 (1.9376) time: 0.6312 [2021-03-26 00:33:51 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 390/1251] eta: 0:09:14 lr: 0.000516 loss: 5.5655 (5.3367) grad_norm: 1.8449 (1.9562) time: 0.6347 [2021-03-26 00:33:58 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 400/1251] eta: 0:09:07 lr: 0.000516 loss: 5.6496 (5.3412) grad_norm: 1.8195 (1.9518) time: 0.6355 [2021-03-26 00:34:04 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 410/1251] eta: 0:09:01 lr: 0.000517 loss: 5.5538 (5.3459) grad_norm: 1.8579 (1.9552) time: 0.6396 [2021-03-26 00:34:10 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 420/1251] eta: 0:08:54 lr: 0.000517 loss: 5.3826 (5.3436) grad_norm: 1.9752 (1.9584) time: 0.6414 [2021-03-26 00:34:17 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 430/1251] eta: 0:08:48 lr: 0.000518 loss: 5.2647 (5.3413) grad_norm: 1.9631 (1.9602) time: 0.6367 [2021-03-26 00:34:23 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 440/1251] eta: 0:08:41 lr: 0.000518 loss: 5.3936 (5.3392) grad_norm: 1.8847 (1.9578) time: 0.6322 [2021-03-26 00:34:29 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 450/1251] eta: 0:08:34 lr: 0.000518 loss: 5.4959 (5.3408) grad_norm: 1.8990 (1.9606) time: 0.6363 [2021-03-26 00:34:36 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 460/1251] eta: 0:08:28 lr: 0.000519 loss: 5.4959 (5.3415) grad_norm: 1.8743 (1.9595) time: 0.6399 [2021-03-26 00:34:42 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 470/1251] eta: 0:08:21 lr: 0.000519 loss: 5.2757 (5.3373) grad_norm: 1.7229 (1.9557) time: 0.6359 [2021-03-26 00:34:48 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 480/1251] eta: 0:08:15 lr: 0.000520 loss: 5.0652 (5.3284) grad_norm: 1.7918 (1.9528) time: 0.6304 [2021-03-26 00:34:55 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 490/1251] eta: 0:08:08 lr: 0.000520 loss: 5.0581 (5.3253) grad_norm: 1.7938 (1.9493) time: 0.6305 [2021-03-26 00:35:01 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 500/1251] eta: 0:08:01 lr: 0.000520 loss: 5.3492 (5.3265) grad_norm: 1.7288 (1.9514) time: 0.6297 [2021-03-26 00:35:07 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 510/1251] eta: 0:07:55 lr: 0.000521 loss: 5.5495 (5.3316) grad_norm: 1.9303 (1.9502) time: 0.6292 [2021-03-26 00:35:14 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 520/1251] eta: 0:07:48 lr: 0.000521 loss: 5.4693 (5.3309) grad_norm: 1.6941 (1.9460) time: 0.6344 [2021-03-26 00:35:20 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 530/1251] eta: 0:07:42 lr: 0.000522 loss: 5.4401 (5.3323) grad_norm: 1.6939 (1.9442) time: 0.6341 [2021-03-26 00:35:26 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 540/1251] eta: 0:07:35 lr: 0.000522 loss: 5.3894 (5.3340) grad_norm: 1.6935 (1.9414) time: 0.6308 [2021-03-26 00:35:33 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 550/1251] eta: 0:07:29 lr: 0.000522 loss: 5.2957 (5.3320) grad_norm: 1.8440 (1.9479) time: 0.6441 [2021-03-26 00:35:39 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 560/1251] eta: 0:07:23 lr: 0.000523 loss: 5.1448 (5.3297) grad_norm: 1.9579 (1.9569) time: 0.6477 [2021-03-26 00:35:46 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 570/1251] eta: 0:07:16 lr: 0.000523 loss: 5.0285 (5.3227) grad_norm: 1.9467 (1.9575) time: 0.6393 [2021-03-26 00:35:52 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 580/1251] eta: 0:07:10 lr: 0.000524 loss: 5.3651 (5.3228) grad_norm: 1.6353 (1.9528) time: 0.6429 [2021-03-26 00:35:58 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 590/1251] eta: 0:07:03 lr: 0.000524 loss: 5.4936 (5.3236) grad_norm: 1.7421 (1.9531) time: 0.6384 [2021-03-26 00:36:05 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 600/1251] eta: 0:06:57 lr: 0.000524 loss: 5.4572 (5.3244) grad_norm: 1.8682 (1.9546) time: 0.6346 [2021-03-26 00:36:11 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 610/1251] eta: 0:06:50 lr: 0.000525 loss: 5.2025 (5.3199) grad_norm: 1.7746 (1.9511) time: 0.6333 [2021-03-26 00:36:17 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 620/1251] eta: 0:06:44 lr: 0.000525 loss: 5.2871 (5.3204) grad_norm: 1.7187 (1.9515) time: 0.6316 [2021-03-26 00:36:24 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 630/1251] eta: 0:06:37 lr: 0.000526 loss: 5.3596 (5.3205) grad_norm: 1.9782 (1.9525) time: 0.6330 [2021-03-26 00:36:30 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 640/1251] eta: 0:06:31 lr: 0.000526 loss: 5.5527 (5.3251) grad_norm: 1.9082 (1.9520) time: 0.6312 [2021-03-26 00:36:36 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 650/1251] eta: 0:06:24 lr: 0.000526 loss: 5.5094 (5.3239) grad_norm: 1.9082 (1.9520) time: 0.6345 [2021-03-26 00:36:43 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 660/1251] eta: 0:06:18 lr: 0.000527 loss: 5.1470 (5.3187) grad_norm: 1.8170 (1.9489) time: 0.6360 [2021-03-26 00:36:49 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 670/1251] eta: 0:06:12 lr: 0.000527 loss: 5.2776 (5.3205) grad_norm: 1.8870 (1.9558) time: 0.6327 [2021-03-26 00:36:55 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 680/1251] eta: 0:06:05 lr: 0.000528 loss: 5.3030 (5.3188) grad_norm: 1.7161 (1.9508) time: 0.6332 [2021-03-26 00:37:02 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 690/1251] eta: 0:05:59 lr: 0.000528 loss: 5.3030 (5.3188) grad_norm: 1.6252 (1.9471) time: 0.6327 [2021-03-26 00:37:08 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 700/1251] eta: 0:05:52 lr: 0.000528 loss: 5.5159 (5.3214) grad_norm: 1.7767 (1.9466) time: 0.6291 [2021-03-26 00:37:14 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 710/1251] eta: 0:05:46 lr: 0.000529 loss: 5.6431 (5.3241) grad_norm: 1.9559 (1.9502) time: 0.6285 [2021-03-26 00:37:21 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 720/1251] eta: 0:05:39 lr: 0.000529 loss: 5.4160 (5.3244) grad_norm: 1.9425 (1.9484) time: 0.6303 [2021-03-26 00:37:27 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 730/1251] eta: 0:05:33 lr: 0.000530 loss: 5.1746 (5.3222) grad_norm: 1.8694 (1.9502) time: 0.6313 [2021-03-26 00:37:34 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 740/1251] eta: 0:05:26 lr: 0.000530 loss: 5.0821 (5.3195) grad_norm: 1.7947 (1.9473) time: 0.6474 [2021-03-26 00:37:40 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 750/1251] eta: 0:05:20 lr: 0.000530 loss: 5.1781 (5.3182) grad_norm: 1.6342 (1.9443) time: 0.6504 [2021-03-26 00:37:46 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 760/1251] eta: 0:05:14 lr: 0.000531 loss: 5.1781 (5.3155) grad_norm: 1.6447 (1.9408) time: 0.6375 [2021-03-26 00:37:53 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 770/1251] eta: 0:05:07 lr: 0.000531 loss: 5.0314 (5.3133) grad_norm: 1.7638 (1.9465) time: 0.6420 [2021-03-26 00:37:59 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 780/1251] eta: 0:05:01 lr: 0.000532 loss: 5.1397 (5.3144) grad_norm: 2.0264 (1.9478) time: 0.6414 [2021-03-26 00:38:06 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 790/1251] eta: 0:04:54 lr: 0.000532 loss: 5.2506 (5.3115) grad_norm: 1.8379 (1.9465) time: 0.6325 [2021-03-26 00:38:12 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 800/1251] eta: 0:04:48 lr: 0.000532 loss: 4.8579 (5.3065) grad_norm: 1.7975 (1.9458) time: 0.6350 [2021-03-26 00:38:18 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 810/1251] eta: 0:04:42 lr: 0.000533 loss: 4.7934 (5.3041) grad_norm: 1.7543 (1.9469) time: 0.6338 [2021-03-26 00:38:25 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 820/1251] eta: 0:04:35 lr: 0.000533 loss: 5.2193 (5.3047) grad_norm: 1.7478 (1.9443) time: 0.6305 [2021-03-26 00:38:31 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 830/1251] eta: 0:04:29 lr: 0.000534 loss: 5.2511 (5.3043) grad_norm: 1.7644 (1.9484) time: 0.6310 [2021-03-26 00:38:37 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 840/1251] eta: 0:04:22 lr: 0.000534 loss: 5.4090 (5.3055) grad_norm: 2.2953 (1.9540) time: 0.6289 [2021-03-26 00:38:43 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 850/1251] eta: 0:04:16 lr: 0.000534 loss: 5.3882 (5.3045) grad_norm: 2.3489 (1.9683) time: 0.6321 [2021-03-26 00:38:50 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 860/1251] eta: 0:04:09 lr: 0.000535 loss: 5.5004 (5.3061) grad_norm: 1.9618 (1.9646) time: 0.6329 [2021-03-26 00:38:56 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 870/1251] eta: 0:04:03 lr: 0.000535 loss: 5.6046 (5.3102) grad_norm: 1.5617 (1.9619) time: 0.6307 [2021-03-26 00:39:02 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 880/1251] eta: 0:03:57 lr: 0.000536 loss: 5.4591 (5.3094) grad_norm: 1.7319 (1.9605) time: 0.6326 [2021-03-26 00:39:09 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 890/1251] eta: 0:03:50 lr: 0.000536 loss: 5.0329 (5.3062) grad_norm: 1.7446 (1.9590) time: 0.6363 [2021-03-26 00:39:15 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 900/1251] eta: 0:03:44 lr: 0.000536 loss: 4.7416 (5.3008) grad_norm: 1.8077 (1.9595) time: 0.6365 [2021-03-26 00:39:22 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 910/1251] eta: 0:03:37 lr: 0.000537 loss: 5.0395 (5.3007) grad_norm: 1.7874 (1.9584) time: 0.6346 [2021-03-26 00:39:28 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 920/1251] eta: 0:03:31 lr: 0.000537 loss: 5.3978 (5.3008) grad_norm: 1.7399 (1.9576) time: 0.6343 [2021-03-26 00:39:34 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 930/1251] eta: 0:03:25 lr: 0.000538 loss: 5.4945 (5.3038) grad_norm: 1.7846 (1.9577) time: 0.6340 [2021-03-26 00:39:40 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 940/1251] eta: 0:03:18 lr: 0.000538 loss: 5.7072 (5.3051) grad_norm: 1.8477 (1.9613) time: 0.6316 [2021-03-26 00:39:47 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 950/1251] eta: 0:03:12 lr: 0.000538 loss: 5.2349 (5.3049) grad_norm: 1.7637 (1.9603) time: 0.6313 [2021-03-26 00:39:53 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 960/1251] eta: 0:03:05 lr: 0.000539 loss: 5.3890 (5.3067) grad_norm: 1.7093 (1.9596) time: 0.6329 [2021-03-26 00:40:00 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 970/1251] eta: 0:02:59 lr: 0.000539 loss: 5.3890 (5.3050) grad_norm: 1.8468 (1.9618) time: 0.6389 [2021-03-26 00:40:06 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 980/1251] eta: 0:02:53 lr: 0.000540 loss: 5.2894 (5.3049) grad_norm: 1.9555 (1.9618) time: 0.6448 [2021-03-26 00:40:12 swin_base_patch4_window7_224] INFO: Epoch: [10] [ 990/1251] eta: 0:02:46 lr: 0.000540 loss: 5.3879 (5.3047) grad_norm: 1.8186 (1.9609) time: 0.6345 [2021-03-26 00:40:19 swin_base_patch4_window7_224] INFO: Epoch: [10] [1000/1251] eta: 0:02:40 lr: 0.000540 loss: 5.1367 (5.3046) grad_norm: 2.0580 (1.9617) time: 0.6310 [2021-03-26 00:40:25 swin_base_patch4_window7_224] INFO: Epoch: [10] [1010/1251] eta: 0:02:33 lr: 0.000541 loss: 4.9866 (5.3005) grad_norm: 2.0808 (1.9672) time: 0.6322 [2021-03-26 00:40:31 swin_base_patch4_window7_224] INFO: Epoch: [10] [1020/1251] eta: 0:02:27 lr: 0.000541 loss: 5.0616 (5.2977) grad_norm: 2.1666 (1.9726) time: 0.6304 [2021-03-26 00:40:38 swin_base_patch4_window7_224] INFO: Epoch: [10] [1030/1251] eta: 0:02:21 lr: 0.000542 loss: 5.2322 (5.2967) grad_norm: 1.9546 (1.9722) time: 0.6376 [2021-03-26 00:40:44 swin_base_patch4_window7_224] INFO: Epoch: [10] [1040/1251] eta: 0:02:14 lr: 0.000542 loss: 5.1955 (5.2957) grad_norm: 1.7449 (1.9705) time: 0.6423 [2021-03-26 00:40:50 swin_base_patch4_window7_224] INFO: Epoch: [10] [1050/1251] eta: 0:02:08 lr: 0.000542 loss: 5.3379 (5.2955) grad_norm: 1.6731 (1.9672) time: 0.6310 [2021-03-26 00:40:57 swin_base_patch4_window7_224] INFO: Epoch: [10] [1060/1251] eta: 0:02:01 lr: 0.000543 loss: 5.1437 (5.2934) grad_norm: 1.5775 (1.9633) time: 0.6247 [2021-03-26 00:41:03 swin_base_patch4_window7_224] INFO: Epoch: [10] [1070/1251] eta: 0:01:55 lr: 0.000543 loss: 5.1437 (5.2918) grad_norm: 1.5775 (1.9613) time: 0.6320 [2021-03-26 00:41:09 swin_base_patch4_window7_224] INFO: Epoch: [10] [1080/1251] eta: 0:01:49 lr: 0.000544 loss: 5.2637 (5.2911) grad_norm: 1.7514 (1.9605) time: 0.6322 [2021-03-26 00:41:16 swin_base_patch4_window7_224] INFO: Epoch: [10] [1090/1251] eta: 0:01:42 lr: 0.000544 loss: 5.0795 (5.2887) grad_norm: 1.9346 (1.9634) time: 0.6297 [2021-03-26 00:41:22 swin_base_patch4_window7_224] INFO: Epoch: [10] [1100/1251] eta: 0:01:36 lr: 0.000544 loss: 5.2012 (5.2880) grad_norm: 1.9433 (1.9624) time: 0.6321 [2021-03-26 00:41:28 swin_base_patch4_window7_224] INFO: Epoch: [10] [1110/1251] eta: 0:01:29 lr: 0.000545 loss: 5.4561 (5.2875) grad_norm: 1.6943 (1.9600) time: 0.6339 [2021-03-26 00:41:35 swin_base_patch4_window7_224] INFO: Epoch: [10] [1120/1251] eta: 0:01:23 lr: 0.000545 loss: 5.4561 (5.2890) grad_norm: 1.8872 (1.9644) time: 0.6384 [2021-03-26 00:41:41 swin_base_patch4_window7_224] INFO: Epoch: [10] [1130/1251] eta: 0:01:17 lr: 0.000546 loss: 5.3272 (5.2853) grad_norm: 1.9230 (1.9634) time: 0.6377 [2021-03-26 00:41:47 swin_base_patch4_window7_224] INFO: Epoch: [10] [1140/1251] eta: 0:01:10 lr: 0.000546 loss: 4.8258 (5.2813) grad_norm: 1.7332 (1.9650) time: 0.6329 [2021-03-26 00:41:54 swin_base_patch4_window7_224] INFO: Epoch: [10] [1150/1251] eta: 0:01:04 lr: 0.000546 loss: 4.8572 (5.2781) grad_norm: 1.6656 (1.9631) time: 0.6348 [2021-03-26 00:42:00 swin_base_patch4_window7_224] INFO: Epoch: [10] [1160/1251] eta: 0:00:58 lr: 0.000547 loss: 5.1937 (5.2793) grad_norm: 1.7490 (inf) time: 0.6325 [2021-03-26 00:42:06 swin_base_patch4_window7_224] INFO: Epoch: [10] [1170/1251] eta: 0:00:51 lr: 0.000547 loss: 5.5244 (5.2805) grad_norm: 2.0312 (inf) time: 0.6306 [2021-03-26 00:42:13 swin_base_patch4_window7_224] INFO: Epoch: [10] [1180/1251] eta: 0:00:45 lr: 0.000548 loss: 5.3865 (5.2791) grad_norm: 1.8111 (inf) time: 0.6315 [2021-03-26 00:42:19 swin_base_patch4_window7_224] INFO: Epoch: [10] [1190/1251] eta: 0:00:38 lr: 0.000548 loss: 5.1135 (5.2778) grad_norm: 1.7907 (inf) time: 0.6305 [2021-03-26 00:42:25 swin_base_patch4_window7_224] INFO: Epoch: [10] [1200/1251] eta: 0:00:32 lr: 0.000548 loss: 5.1875 (5.2780) grad_norm: 1.9209 (inf) time: 0.6320 [2021-03-26 00:42:32 swin_base_patch4_window7_224] INFO: Epoch: [10] [1210/1251] eta: 0:00:26 lr: 0.000549 loss: 5.2444 (5.2776) grad_norm: 1.7168 (inf) time: 0.6355 [2021-03-26 00:42:38 swin_base_patch4_window7_224] INFO: Epoch: [10] [1220/1251] eta: 0:00:19 lr: 0.000549 loss: 5.3199 (5.2773) grad_norm: 1.7168 (inf) time: 0.6412 [2021-03-26 00:42:44 swin_base_patch4_window7_224] INFO: Epoch: [10] [1230/1251] eta: 0:00:13 lr: 0.000550 loss: 5.3678 (5.2769) grad_norm: 1.8452 (inf) time: 0.6426 [2021-03-26 00:42:51 swin_base_patch4_window7_224] INFO: Epoch: [10] [1240/1251] eta: 0:00:07 lr: 0.000550 loss: 5.3270 (5.2779) grad_norm: 1.8569 (inf) time: 0.6345 [2021-03-26 00:42:57 swin_base_patch4_window7_224] INFO: Epoch: [10] [1250/1251] eta: 0:00:00 lr: 0.000550 loss: 5.2735 (5.2782) grad_norm: 1.7154 (inf) time: 0.6211 [2021-03-26 00:43:59 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:04 loss: 2.9603 (2.9603) acc1: 45.3125 (45.3125) acc5: 65.6250 (65.6250) [2021-03-26 00:44:00 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 2.7241 (2.7511) acc1: 45.3125 (43.7500) acc5: 67.1875 (67.3295) [2021-03-26 00:44:01 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 2.6894 (2.7377) acc1: 43.7500 (43.0804) acc5: 65.6250 (67.1131) [2021-03-26 00:44:03 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 2.6554 (2.7017) acc1: 40.6250 (42.7923) acc5: 65.6250 (67.6411) [2021-03-26 00:44:04 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 2.7385 (2.7270) acc1: 40.6250 (42.3018) acc5: 65.6250 (66.8064) [2021-03-26 00:44:05 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.7685 (2.7453) acc1: 40.6250 (41.6320) acc5: 64.0625 (66.4640) [2021-03-26 00:44:07 swin_base_patch4_window7_224] INFO: * Acc@1 40.964 Acc@5 67.418 loss 2.740 [2021-03-26 00:44:07 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 41.0% [2021-03-26 00:44:07 swin_base_patch4_window7_224] INFO: Max accuracy: 40.96% [2021-03-26 00:44:11 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 0/1251] eta: 1:28:54 lr: 0.000550 loss: 5.7562 (5.7562) grad_norm: 2.0611 (2.0611) time: 4.2641 [2021-03-26 00:44:17 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 10/1251] eta: 0:20:12 lr: 0.000551 loss: 5.1024 (5.2653) grad_norm: 1.8013 (1.8250) time: 0.9771 [2021-03-26 00:44:24 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 20/1251] eta: 0:16:37 lr: 0.000551 loss: 5.3979 (5.3755) grad_norm: 1.5713 (1.7873) time: 0.6377 [2021-03-26 00:44:30 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 30/1251] eta: 0:15:17 lr: 0.000552 loss: 5.3979 (5.2754) grad_norm: 1.7065 (1.7863) time: 0.6275 [2021-03-26 00:44:36 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 40/1251] eta: 0:14:37 lr: 0.000552 loss: 5.0004 (5.2324) grad_norm: 1.6759 (1.7596) time: 0.6340 [2021-03-26 00:44:43 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 50/1251] eta: 0:14:08 lr: 0.000552 loss: 4.9381 (5.1859) grad_norm: 1.8388 (1.8734) time: 0.6356 [2021-03-26 00:44:49 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 60/1251] eta: 0:13:48 lr: 0.000553 loss: 4.9730 (5.1796) grad_norm: 1.8388 (1.8614) time: 0.6358 [2021-03-26 00:44:55 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 70/1251] eta: 0:13:31 lr: 0.000553 loss: 5.1217 (5.1628) grad_norm: 1.7288 (1.8656) time: 0.6386 [2021-03-26 00:45:02 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 80/1251] eta: 0:13:16 lr: 0.000554 loss: 5.3254 (5.2006) grad_norm: 1.7800 (1.8862) time: 0.6352 [2021-03-26 00:45:08 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 90/1251] eta: 0:13:03 lr: 0.000554 loss: 5.3004 (5.1819) grad_norm: 1.8668 (1.8851) time: 0.6307 [2021-03-26 00:45:14 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 100/1251] eta: 0:12:52 lr: 0.000554 loss: 5.2830 (5.1931) grad_norm: 1.7174 (1.8717) time: 0.6315 [2021-03-26 00:45:21 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 110/1251] eta: 0:12:41 lr: 0.000555 loss: 5.3510 (5.2011) grad_norm: 1.7174 (1.8810) time: 0.6338 [2021-03-26 00:45:27 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 120/1251] eta: 0:12:33 lr: 0.000555 loss: 5.2981 (5.1884) grad_norm: 1.8612 (1.8915) time: 0.6411 [2021-03-26 00:45:34 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 130/1251] eta: 0:12:23 lr: 0.000556 loss: 5.3969 (5.1989) grad_norm: 1.9652 (1.9299) time: 0.6425 [2021-03-26 00:45:40 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 140/1251] eta: 0:12:14 lr: 0.000556 loss: 5.4621 (5.2005) grad_norm: 1.9021 (1.9520) time: 0.6356 [2021-03-26 00:45:46 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 150/1251] eta: 0:12:06 lr: 0.000556 loss: 5.3325 (5.2064) grad_norm: 1.8556 (1.9500) time: 0.6370 [2021-03-26 00:45:53 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 160/1251] eta: 0:11:58 lr: 0.000557 loss: 5.1144 (5.1872) grad_norm: 1.9529 (1.9916) time: 0.6344 [2021-03-26 00:45:59 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 170/1251] eta: 0:11:49 lr: 0.000557 loss: 5.0229 (5.1806) grad_norm: 1.9725 (2.0042) time: 0.6296 [2021-03-26 00:46:05 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 180/1251] eta: 0:11:42 lr: 0.000558 loss: 5.0801 (5.1767) grad_norm: 1.8947 (1.9932) time: 0.6339 [2021-03-26 00:46:12 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 190/1251] eta: 0:11:34 lr: 0.000558 loss: 5.1756 (5.1666) grad_norm: 1.7954 (1.9854) time: 0.6419 [2021-03-26 00:46:18 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 200/1251] eta: 0:11:27 lr: 0.000558 loss: 5.1933 (5.1690) grad_norm: 1.8338 (1.9851) time: 0.6411 [2021-03-26 00:46:24 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 210/1251] eta: 0:11:19 lr: 0.000559 loss: 5.2216 (5.1746) grad_norm: 1.7195 (1.9758) time: 0.6326 [2021-03-26 00:46:31 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 220/1251] eta: 0:11:12 lr: 0.000559 loss: 5.4931 (5.1730) grad_norm: 1.7195 (1.9857) time: 0.6385 [2021-03-26 00:46:37 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 230/1251] eta: 0:11:05 lr: 0.000560 loss: 5.5113 (5.1843) grad_norm: 1.7522 (1.9803) time: 0.6397 [2021-03-26 00:46:44 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 240/1251] eta: 0:10:58 lr: 0.000560 loss: 5.5759 (5.1971) grad_norm: 1.7522 (1.9793) time: 0.6348 [2021-03-26 00:46:50 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 250/1251] eta: 0:10:51 lr: 0.000560 loss: 5.5209 (5.2069) grad_norm: 2.0725 (2.0016) time: 0.6399 [2021-03-26 00:46:56 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 260/1251] eta: 0:10:44 lr: 0.000561 loss: 5.2504 (5.2048) grad_norm: 1.9231 (1.9962) time: 0.6338 [2021-03-26 00:47:03 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 270/1251] eta: 0:10:36 lr: 0.000561 loss: 5.1645 (5.2036) grad_norm: 1.8142 (1.9963) time: 0.6300 [2021-03-26 00:47:09 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 280/1251] eta: 0:10:30 lr: 0.000562 loss: 5.2050 (5.2032) grad_norm: 1.7083 (1.9926) time: 0.6373 [2021-03-26 00:47:15 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 290/1251] eta: 0:10:22 lr: 0.000562 loss: 5.4212 (5.2088) grad_norm: 1.5491 (1.9814) time: 0.6348 [2021-03-26 00:47:22 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 300/1251] eta: 0:10:16 lr: 0.000562 loss: 5.2683 (5.2061) grad_norm: 1.6206 (1.9768) time: 0.6322 [2021-03-26 00:47:28 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 310/1251] eta: 0:10:08 lr: 0.000563 loss: 5.2873 (5.2171) grad_norm: 1.7535 (1.9680) time: 0.6322 [2021-03-26 00:47:34 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 320/1251] eta: 0:10:02 lr: 0.000563 loss: 5.4194 (5.2200) grad_norm: 1.7247 (1.9766) time: 0.6338 [2021-03-26 00:47:41 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 330/1251] eta: 0:09:55 lr: 0.000564 loss: 5.2935 (5.2249) grad_norm: 1.5368 (1.9609) time: 0.6358 [2021-03-26 00:47:47 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 340/1251] eta: 0:09:48 lr: 0.000564 loss: 5.4066 (5.2280) grad_norm: 1.5683 (1.9605) time: 0.6318 [2021-03-26 00:47:54 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 350/1251] eta: 0:09:42 lr: 0.000564 loss: 4.9469 (5.2178) grad_norm: 1.8666 (1.9711) time: 0.6403 [2021-03-26 00:48:00 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 360/1251] eta: 0:09:35 lr: 0.000565 loss: 4.9469 (5.2188) grad_norm: 1.7875 (1.9645) time: 0.6392 [2021-03-26 00:48:06 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 370/1251] eta: 0:09:28 lr: 0.000565 loss: 5.2527 (5.2218) grad_norm: 1.6432 (1.9570) time: 0.6329 [2021-03-26 00:48:12 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 380/1251] eta: 0:09:21 lr: 0.000566 loss: 5.2795 (5.2216) grad_norm: 1.7272 (1.9578) time: 0.6313 [2021-03-26 00:48:19 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 390/1251] eta: 0:09:15 lr: 0.000566 loss: 5.3085 (5.2255) grad_norm: 1.9682 (1.9597) time: 0.6297 [2021-03-26 00:48:25 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 400/1251] eta: 0:09:08 lr: 0.000566 loss: 5.4342 (5.2266) grad_norm: 1.9682 (1.9609) time: 0.6295 [2021-03-26 00:48:31 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 410/1251] eta: 0:09:01 lr: 0.000567 loss: 5.3770 (5.2236) grad_norm: 1.8549 (1.9691) time: 0.6274 [2021-03-26 00:48:38 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 420/1251] eta: 0:08:54 lr: 0.000567 loss: 5.0848 (5.2179) grad_norm: 1.7346 (1.9630) time: 0.6328 [2021-03-26 00:48:44 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 430/1251] eta: 0:08:48 lr: 0.000568 loss: 5.3857 (5.2227) grad_norm: 1.6112 (1.9610) time: 0.6365 [2021-03-26 00:48:50 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 440/1251] eta: 0:08:41 lr: 0.000568 loss: 5.3995 (5.2248) grad_norm: 1.6314 (1.9591) time: 0.6345 [2021-03-26 00:48:57 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 450/1251] eta: 0:08:35 lr: 0.000568 loss: 4.9162 (5.2172) grad_norm: 1.8209 (1.9608) time: 0.6346 [2021-03-26 00:49:03 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 460/1251] eta: 0:08:28 lr: 0.000569 loss: 4.8578 (5.2156) grad_norm: 1.7497 (1.9561) time: 0.6342 [2021-03-26 00:49:09 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 470/1251] eta: 0:08:21 lr: 0.000569 loss: 5.2845 (5.2129) grad_norm: 1.6285 (1.9557) time: 0.6317 [2021-03-26 00:49:16 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 480/1251] eta: 0:08:15 lr: 0.000570 loss: 5.2506 (5.2143) grad_norm: 1.8808 (1.9531) time: 0.6306 [2021-03-26 00:49:22 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 490/1251] eta: 0:08:08 lr: 0.000570 loss: 5.3304 (5.2161) grad_norm: 1.7954 (1.9490) time: 0.6290 [2021-03-26 00:49:28 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 500/1251] eta: 0:08:01 lr: 0.000570 loss: 5.2519 (5.2142) grad_norm: 1.8585 (1.9589) time: 0.6289 [2021-03-26 00:49:35 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 510/1251] eta: 0:07:55 lr: 0.000571 loss: 5.1314 (5.2120) grad_norm: 1.8691 (1.9552) time: 0.6322 [2021-03-26 00:49:41 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 520/1251] eta: 0:07:48 lr: 0.000571 loss: 5.0746 (5.2094) grad_norm: 1.7029 (1.9512) time: 0.6344 [2021-03-26 00:49:47 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 530/1251] eta: 0:07:42 lr: 0.000572 loss: 5.2234 (5.2120) grad_norm: 1.7019 (1.9456) time: 0.6291 [2021-03-26 00:49:54 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 540/1251] eta: 0:07:35 lr: 0.000572 loss: 5.2189 (5.2129) grad_norm: 1.7347 (1.9439) time: 0.6318 [2021-03-26 00:50:00 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 550/1251] eta: 0:07:29 lr: 0.000572 loss: 5.0557 (5.2066) grad_norm: 1.7039 (1.9390) time: 0.6443 [2021-03-26 00:50:07 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 560/1251] eta: 0:07:23 lr: 0.000573 loss: 5.2638 (5.2101) grad_norm: 1.5397 (1.9349) time: 0.6463 [2021-03-26 00:50:13 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 570/1251] eta: 0:07:16 lr: 0.000573 loss: 5.2898 (5.2102) grad_norm: 1.8533 (1.9386) time: 0.6390 [2021-03-26 00:50:19 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 580/1251] eta: 0:07:10 lr: 0.000574 loss: 5.2591 (5.2108) grad_norm: 1.8329 (1.9378) time: 0.6351 [2021-03-26 00:50:26 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 590/1251] eta: 0:07:03 lr: 0.000574 loss: 5.2370 (5.2106) grad_norm: 1.7446 (1.9390) time: 0.6340 [2021-03-26 00:50:32 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 600/1251] eta: 0:06:57 lr: 0.000574 loss: 5.2263 (5.2087) grad_norm: 1.8833 (1.9409) time: 0.6361 [2021-03-26 00:50:38 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 610/1251] eta: 0:06:50 lr: 0.000575 loss: 5.3291 (5.2098) grad_norm: 1.8250 (1.9379) time: 0.6351 [2021-03-26 00:50:45 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 620/1251] eta: 0:06:44 lr: 0.000575 loss: 5.4331 (5.2122) grad_norm: 1.6938 (1.9361) time: 0.6314 [2021-03-26 00:50:51 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 630/1251] eta: 0:06:37 lr: 0.000576 loss: 5.4331 (5.2139) grad_norm: 1.7746 (1.9394) time: 0.6341 [2021-03-26 00:50:57 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 640/1251] eta: 0:06:31 lr: 0.000576 loss: 5.4728 (5.2182) grad_norm: 1.9087 (1.9403) time: 0.6342 [2021-03-26 00:51:04 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 650/1251] eta: 0:06:24 lr: 0.000576 loss: 5.3641 (5.2205) grad_norm: 1.7212 (1.9351) time: 0.6339 [2021-03-26 00:51:10 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 660/1251] eta: 0:06:18 lr: 0.000577 loss: 5.2385 (5.2192) grad_norm: 1.5417 (1.9351) time: 0.6327 [2021-03-26 00:51:16 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 670/1251] eta: 0:06:11 lr: 0.000577 loss: 5.3542 (5.2229) grad_norm: 1.8881 (1.9366) time: 0.6304 [2021-03-26 00:51:23 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 680/1251] eta: 0:06:05 lr: 0.000578 loss: 5.3542 (5.2228) grad_norm: 1.9089 (1.9344) time: 0.6324 [2021-03-26 00:51:29 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 690/1251] eta: 0:05:58 lr: 0.000578 loss: 5.2849 (5.2246) grad_norm: 1.7294 (1.9325) time: 0.6342 [2021-03-26 00:51:35 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 700/1251] eta: 0:05:52 lr: 0.000578 loss: 5.3770 (5.2262) grad_norm: 1.6797 (1.9296) time: 0.6277 [2021-03-26 00:51:42 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 710/1251] eta: 0:05:46 lr: 0.000579 loss: 5.5360 (5.2308) grad_norm: 1.7689 (1.9332) time: 0.6317 [2021-03-26 00:51:48 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 720/1251] eta: 0:05:39 lr: 0.000579 loss: 5.3327 (5.2291) grad_norm: 1.8582 (1.9310) time: 0.6386 [2021-03-26 00:51:54 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 730/1251] eta: 0:05:33 lr: 0.000580 loss: 5.3360 (5.2325) grad_norm: 1.6298 (1.9263) time: 0.6366 [2021-03-26 00:52:01 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 740/1251] eta: 0:05:26 lr: 0.000580 loss: 5.3390 (5.2299) grad_norm: 1.6315 (1.9275) time: 0.6461 [2021-03-26 00:52:07 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 750/1251] eta: 0:05:20 lr: 0.000580 loss: 5.2534 (5.2291) grad_norm: 1.9432 (1.9286) time: 0.6519 [2021-03-26 00:52:14 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 760/1251] eta: 0:05:14 lr: 0.000581 loss: 5.4130 (5.2312) grad_norm: 1.7341 (1.9270) time: 0.6475 [2021-03-26 00:52:20 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 770/1251] eta: 0:05:07 lr: 0.000581 loss: 5.4204 (5.2315) grad_norm: 1.5641 (1.9276) time: 0.6413 [2021-03-26 00:52:27 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 780/1251] eta: 0:05:01 lr: 0.000582 loss: 5.2594 (5.2311) grad_norm: 1.7187 (1.9259) time: 0.6359 [2021-03-26 00:52:33 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 790/1251] eta: 0:04:54 lr: 0.000582 loss: 5.4095 (5.2327) grad_norm: 1.7628 (1.9348) time: 0.6385 [2021-03-26 00:52:39 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 800/1251] eta: 0:04:48 lr: 0.000582 loss: 5.3501 (5.2336) grad_norm: 1.6688 (1.9313) time: 0.6417 [2021-03-26 00:52:46 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 810/1251] eta: 0:04:42 lr: 0.000583 loss: 5.2426 (5.2322) grad_norm: 1.6688 (1.9306) time: 0.6372 [2021-03-26 00:52:52 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 820/1251] eta: 0:04:35 lr: 0.000583 loss: 5.2218 (5.2326) grad_norm: 1.7680 (1.9285) time: 0.6328 [2021-03-26 00:52:58 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 830/1251] eta: 0:04:29 lr: 0.000584 loss: 5.2724 (5.2333) grad_norm: 1.6955 (1.9290) time: 0.6281 [2021-03-26 00:53:05 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 840/1251] eta: 0:04:22 lr: 0.000584 loss: 5.5213 (5.2346) grad_norm: 1.8377 (1.9335) time: 0.6270 [2021-03-26 00:53:11 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 850/1251] eta: 0:04:16 lr: 0.000584 loss: 5.4136 (5.2375) grad_norm: 1.7146 (1.9315) time: 0.6297 [2021-03-26 00:53:17 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 860/1251] eta: 0:04:09 lr: 0.000585 loss: 5.5497 (5.2398) grad_norm: 1.6860 (1.9301) time: 0.6331 [2021-03-26 00:53:24 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 870/1251] eta: 0:04:03 lr: 0.000585 loss: 5.4219 (5.2401) grad_norm: 1.6929 (1.9287) time: 0.6428 [2021-03-26 00:53:30 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 880/1251] eta: 0:03:57 lr: 0.000586 loss: 5.2139 (5.2359) grad_norm: 1.5985 (1.9260) time: 0.6426 [2021-03-26 00:53:36 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 890/1251] eta: 0:03:50 lr: 0.000586 loss: 5.1353 (5.2338) grad_norm: 1.5719 (1.9239) time: 0.6334 [2021-03-26 00:53:43 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 900/1251] eta: 0:03:44 lr: 0.000586 loss: 5.3212 (5.2349) grad_norm: 1.5719 (1.9218) time: 0.6372 [2021-03-26 00:53:49 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 910/1251] eta: 0:03:37 lr: 0.000587 loss: 5.3223 (5.2339) grad_norm: 1.6403 (1.9195) time: 0.6389 [2021-03-26 00:53:55 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 920/1251] eta: 0:03:31 lr: 0.000587 loss: 5.1897 (5.2329) grad_norm: 1.6439 (1.9196) time: 0.6324 [2021-03-26 00:54:02 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 930/1251] eta: 0:03:25 lr: 0.000588 loss: 5.1472 (5.2310) grad_norm: 1.6439 (1.9215) time: 0.6327 [2021-03-26 00:54:08 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 940/1251] eta: 0:03:18 lr: 0.000588 loss: 4.8354 (5.2272) grad_norm: 1.6720 (1.9229) time: 0.6326 [2021-03-26 00:54:15 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 950/1251] eta: 0:03:12 lr: 0.000588 loss: 4.9245 (5.2260) grad_norm: 1.8977 (1.9260) time: 0.6392 [2021-03-26 00:54:21 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 960/1251] eta: 0:03:06 lr: 0.000589 loss: 5.0612 (5.2243) grad_norm: 1.9868 (1.9267) time: 0.6467 [2021-03-26 00:54:27 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 970/1251] eta: 0:02:59 lr: 0.000589 loss: 5.2097 (5.2237) grad_norm: 1.7708 (1.9244) time: 0.6392 [2021-03-26 00:54:34 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 980/1251] eta: 0:02:53 lr: 0.000590 loss: 5.2449 (5.2228) grad_norm: 1.7728 (1.9234) time: 0.6348 [2021-03-26 00:54:40 swin_base_patch4_window7_224] INFO: Epoch: [11] [ 990/1251] eta: 0:02:46 lr: 0.000590 loss: 5.2333 (5.2227) grad_norm: 1.7402 (1.9210) time: 0.6346 [2021-03-26 00:54:46 swin_base_patch4_window7_224] INFO: Epoch: [11] [1000/1251] eta: 0:02:40 lr: 0.000590 loss: 5.1981 (5.2196) grad_norm: 1.7164 (1.9194) time: 0.6318 [2021-03-26 00:54:53 swin_base_patch4_window7_224] INFO: Epoch: [11] [1010/1251] eta: 0:02:33 lr: 0.000591 loss: 4.8237 (5.2166) grad_norm: 1.7735 (1.9190) time: 0.6288 [2021-03-26 00:54:59 swin_base_patch4_window7_224] INFO: Epoch: [11] [1020/1251] eta: 0:02:27 lr: 0.000591 loss: 4.8944 (5.2148) grad_norm: 1.9675 (1.9201) time: 0.6255 [2021-03-26 00:55:05 swin_base_patch4_window7_224] INFO: Epoch: [11] [1030/1251] eta: 0:02:21 lr: 0.000592 loss: 5.3307 (5.2169) grad_norm: 1.9852 (1.9224) time: 0.6268 [2021-03-26 00:55:12 swin_base_patch4_window7_224] INFO: Epoch: [11] [1040/1251] eta: 0:02:14 lr: 0.000592 loss: 5.3566 (5.2183) grad_norm: 1.7157 (1.9209) time: 0.6315 [2021-03-26 00:55:18 swin_base_patch4_window7_224] INFO: Epoch: [11] [1050/1251] eta: 0:02:08 lr: 0.000592 loss: 5.2342 (5.2170) grad_norm: 1.4675 (1.9161) time: 0.6310 [2021-03-26 00:55:24 swin_base_patch4_window7_224] INFO: Epoch: [11] [1060/1251] eta: 0:02:01 lr: 0.000593 loss: 5.0741 (5.2154) grad_norm: 1.4208 (1.9136) time: 0.6253 [2021-03-26 00:55:30 swin_base_patch4_window7_224] INFO: Epoch: [11] [1070/1251] eta: 0:01:55 lr: 0.000593 loss: 5.0743 (5.2149) grad_norm: 1.5898 (1.9114) time: 0.6228 [2021-03-26 00:55:37 swin_base_patch4_window7_224] INFO: Epoch: [11] [1080/1251] eta: 0:01:49 lr: 0.000594 loss: 5.2352 (5.2157) grad_norm: 1.6465 (1.9133) time: 0.6248 [2021-03-26 00:55:43 swin_base_patch4_window7_224] INFO: Epoch: [11] [1090/1251] eta: 0:01:42 lr: 0.000594 loss: 5.3221 (5.2150) grad_norm: 1.7377 (1.9128) time: 0.6346 [2021-03-26 00:55:49 swin_base_patch4_window7_224] INFO: Epoch: [11] [1100/1251] eta: 0:01:36 lr: 0.000594 loss: 5.2156 (5.2148) grad_norm: 1.8857 (1.9138) time: 0.6427 [2021-03-26 00:55:56 swin_base_patch4_window7_224] INFO: Epoch: [11] [1110/1251] eta: 0:01:29 lr: 0.000595 loss: 5.0978 (5.2148) grad_norm: 1.8458 (1.9113) time: 0.6368 [2021-03-26 00:56:02 swin_base_patch4_window7_224] INFO: Epoch: [11] [1120/1251] eta: 0:01:23 lr: 0.000595 loss: 5.2949 (5.2156) grad_norm: 1.5275 (1.9086) time: 0.6346 [2021-03-26 00:56:08 swin_base_patch4_window7_224] INFO: Epoch: [11] [1130/1251] eta: 0:01:17 lr: 0.000596 loss: 5.3464 (5.2159) grad_norm: 1.7743 (1.9106) time: 0.6355 [2021-03-26 00:56:15 swin_base_patch4_window7_224] INFO: Epoch: [11] [1140/1251] eta: 0:01:10 lr: 0.000596 loss: 5.1796 (5.2151) grad_norm: 1.9669 (1.9116) time: 0.6305 [2021-03-26 00:56:21 swin_base_patch4_window7_224] INFO: Epoch: [11] [1150/1251] eta: 0:01:04 lr: 0.000596 loss: 5.4930 (5.2159) grad_norm: 1.8141 (1.9115) time: 0.6289 [2021-03-26 00:56:27 swin_base_patch4_window7_224] INFO: Epoch: [11] [1160/1251] eta: 0:00:58 lr: 0.000597 loss: 5.4335 (5.2164) grad_norm: 1.6764 (1.9096) time: 0.6245 [2021-03-26 00:56:34 swin_base_patch4_window7_224] INFO: Epoch: [11] [1170/1251] eta: 0:00:51 lr: 0.000597 loss: 5.1841 (5.2145) grad_norm: 1.8094 (1.9090) time: 0.6258 [2021-03-26 00:56:40 swin_base_patch4_window7_224] INFO: Epoch: [11] [1180/1251] eta: 0:00:45 lr: 0.000598 loss: 5.1969 (5.2153) grad_norm: 1.8094 (1.9071) time: 0.6349 [2021-03-26 00:56:46 swin_base_patch4_window7_224] INFO: Epoch: [11] [1190/1251] eta: 0:00:38 lr: 0.000598 loss: 5.4068 (5.2157) grad_norm: 1.5902 (1.9041) time: 0.6307 [2021-03-26 00:56:52 swin_base_patch4_window7_224] INFO: Epoch: [11] [1200/1251] eta: 0:00:32 lr: 0.000598 loss: 5.1817 (5.2152) grad_norm: 1.8039 (1.9073) time: 0.6211 [2021-03-26 00:56:59 swin_base_patch4_window7_224] INFO: Epoch: [11] [1210/1251] eta: 0:00:26 lr: 0.000599 loss: 5.1004 (5.2127) grad_norm: 1.8152 (1.9062) time: 0.6217 [2021-03-26 00:57:05 swin_base_patch4_window7_224] INFO: Epoch: [11] [1220/1251] eta: 0:00:19 lr: 0.000599 loss: 5.0578 (5.2117) grad_norm: 1.6766 (1.9045) time: 0.6293 [2021-03-26 00:57:11 swin_base_patch4_window7_224] INFO: Epoch: [11] [1230/1251] eta: 0:00:13 lr: 0.000600 loss: 5.2125 (5.2107) grad_norm: 1.6946 (1.9041) time: 0.6332 [2021-03-26 00:57:18 swin_base_patch4_window7_224] INFO: Epoch: [11] [1240/1251] eta: 0:00:07 lr: 0.000600 loss: 5.2457 (5.2114) grad_norm: 1.6178 (1.9011) time: 0.6334 [2021-03-26 00:57:24 swin_base_patch4_window7_224] INFO: Epoch: [11] [1250/1251] eta: 0:00:00 lr: 0.000600 loss: 5.3325 (5.2106) grad_norm: 1.4676 (1.8989) time: 0.6323 [2021-03-26 00:57:28 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:44 loss: 2.4716 (2.4716) acc1: 48.4375 (48.4375) acc5: 68.7500 (68.7500) [2021-03-26 00:57:30 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 2.5739 (2.6329) acc1: 43.7500 (43.6080) acc5: 70.3125 (70.1705) [2021-03-26 00:57:32 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 2.5739 (2.5829) acc1: 42.1875 (43.9732) acc5: 70.3125 (70.4613) [2021-03-26 00:57:36 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 2.6071 (2.6278) acc1: 40.6250 (43.0444) acc5: 68.7500 (69.7077) [2021-03-26 00:57:37 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 2.7520 (2.6402) acc1: 42.1875 (43.4451) acc5: 67.1875 (69.5122) [2021-03-26 00:57:38 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.7520 (2.6616) acc1: 42.1875 (42.7200) acc5: 67.1875 (68.9920) [2021-03-26 00:57:40 swin_base_patch4_window7_224] INFO: * Acc@1 42.564 Acc@5 69.150 loss 2.658 [2021-03-26 00:57:40 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 42.6% [2021-03-26 00:57:40 swin_base_patch4_window7_224] INFO: Max accuracy: 42.56% [2021-03-26 00:57:44 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 0/1251] eta: 1:30:40 lr: 0.000600 loss: 5.8955 (5.8955) grad_norm: 1.2778 (1.2778) time: 4.3493 [2021-03-26 00:57:50 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 10/1251] eta: 0:20:13 lr: 0.000601 loss: 5.2095 (5.2120) grad_norm: 1.7161 (1.7274) time: 0.9775 [2021-03-26 00:57:57 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 20/1251] eta: 0:16:41 lr: 0.000601 loss: 5.2095 (5.1379) grad_norm: 1.8750 (1.8989) time: 0.6368 [2021-03-26 00:58:03 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 30/1251] eta: 0:15:26 lr: 0.000602 loss: 5.2310 (5.1395) grad_norm: 1.8640 (1.8971) time: 0.6386 [2021-03-26 00:58:10 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 40/1251] eta: 0:14:42 lr: 0.000602 loss: 5.1360 (5.0844) grad_norm: 1.6761 (1.9155) time: 0.6393 [2021-03-26 00:58:16 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 50/1251] eta: 0:14:13 lr: 0.000602 loss: 5.0829 (5.0517) grad_norm: 1.6983 (1.9121) time: 0.6352 [2021-03-26 00:58:22 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 60/1251] eta: 0:13:49 lr: 0.000603 loss: 4.9646 (5.0264) grad_norm: 1.8933 (1.9988) time: 0.6306 [2021-03-26 00:58:28 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 70/1251] eta: 0:13:30 lr: 0.000603 loss: 5.2497 (5.0568) grad_norm: 1.7179 (1.9568) time: 0.6246 [2021-03-26 00:58:35 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 80/1251] eta: 0:13:15 lr: 0.000604 loss: 5.2199 (5.0668) grad_norm: 1.6294 (1.9166) time: 0.6286 [2021-03-26 00:58:41 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 90/1251] eta: 0:13:03 lr: 0.000604 loss: 5.2174 (5.0757) grad_norm: 1.6489 (1.8914) time: 0.6345 [2021-03-26 00:58:48 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 100/1251] eta: 0:12:52 lr: 0.000604 loss: 5.2750 (5.0790) grad_norm: 1.7059 (1.9012) time: 0.6374 [2021-03-26 00:58:54 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 110/1251] eta: 0:12:41 lr: 0.000605 loss: 5.2780 (5.0900) grad_norm: 1.6166 (1.8795) time: 0.6349 [2021-03-26 00:59:00 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 120/1251] eta: 0:12:33 lr: 0.000605 loss: 5.1567 (5.0871) grad_norm: 1.6166 (1.8666) time: 0.6409 [2021-03-26 00:59:07 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 130/1251] eta: 0:12:23 lr: 0.000606 loss: 5.1014 (5.0983) grad_norm: 1.6577 (1.8583) time: 0.6384 [2021-03-26 00:59:13 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 140/1251] eta: 0:12:16 lr: 0.000606 loss: 5.5556 (5.1326) grad_norm: 1.7481 (1.8942) time: 0.6407 [2021-03-26 00:59:20 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 150/1251] eta: 0:12:07 lr: 0.000606 loss: 5.3545 (5.1328) grad_norm: 1.9290 (1.8900) time: 0.6451 [2021-03-26 00:59:26 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 160/1251] eta: 0:11:58 lr: 0.000607 loss: 5.1154 (5.1300) grad_norm: 1.6608 (1.8740) time: 0.6300 [2021-03-26 00:59:32 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 170/1251] eta: 0:11:50 lr: 0.000607 loss: 5.2277 (5.1391) grad_norm: 1.5844 (1.8632) time: 0.6309 [2021-03-26 00:59:39 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 180/1251] eta: 0:11:43 lr: 0.000608 loss: 5.2277 (5.1306) grad_norm: 1.5561 (1.8535) time: 0.6416 [2021-03-26 00:59:45 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 190/1251] eta: 0:11:35 lr: 0.000608 loss: 5.1355 (5.1329) grad_norm: 1.6985 (1.8488) time: 0.6366 [2021-03-26 00:59:51 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 200/1251] eta: 0:11:27 lr: 0.000608 loss: 5.3375 (5.1413) grad_norm: 1.6275 (1.8356) time: 0.6309 [2021-03-26 00:59:58 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 210/1251] eta: 0:11:19 lr: 0.000609 loss: 5.2728 (5.1403) grad_norm: 1.5706 (1.8255) time: 0.6331 [2021-03-26 01:00:04 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 220/1251] eta: 0:11:12 lr: 0.000609 loss: 5.2586 (5.1452) grad_norm: 1.4777 (1.8114) time: 0.6313 [2021-03-26 01:00:10 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 230/1251] eta: 0:11:05 lr: 0.000610 loss: 5.0758 (5.1385) grad_norm: 1.4777 (1.8063) time: 0.6339 [2021-03-26 01:00:17 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 240/1251] eta: 0:10:57 lr: 0.000610 loss: 5.3855 (5.1435) grad_norm: 1.7292 (1.8121) time: 0.6363 [2021-03-26 01:00:23 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 250/1251] eta: 0:10:51 lr: 0.000610 loss: 5.2399 (5.1369) grad_norm: 1.9621 (1.8182) time: 0.6385 [2021-03-26 01:00:29 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 260/1251] eta: 0:10:43 lr: 0.000611 loss: 5.1196 (5.1386) grad_norm: 1.7287 (1.8086) time: 0.6315 [2021-03-26 01:00:35 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 270/1251] eta: 0:10:36 lr: 0.000611 loss: 5.3229 (5.1466) grad_norm: 1.5577 (1.8105) time: 0.6231 [2021-03-26 01:00:42 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 280/1251] eta: 0:10:29 lr: 0.000612 loss: 5.3229 (5.1488) grad_norm: 1.7035 (1.8054) time: 0.6329 [2021-03-26 01:00:48 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 290/1251] eta: 0:10:22 lr: 0.000612 loss: 5.0772 (5.1467) grad_norm: 1.6027 (1.8029) time: 0.6373 [2021-03-26 01:00:55 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 300/1251] eta: 0:10:15 lr: 0.000612 loss: 5.2240 (5.1451) grad_norm: 1.7066 (1.8243) time: 0.6295 [2021-03-26 01:01:01 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 310/1251] eta: 0:10:08 lr: 0.000613 loss: 5.2106 (5.1354) grad_norm: 1.6314 (1.8186) time: 0.6300 [2021-03-26 01:01:07 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 320/1251] eta: 0:10:01 lr: 0.000613 loss: 5.0346 (5.1293) grad_norm: 1.6314 (1.8180) time: 0.6385 [2021-03-26 01:01:14 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 330/1251] eta: 0:09:55 lr: 0.000614 loss: 5.0346 (5.1281) grad_norm: 1.7689 (1.8228) time: 0.6399 [2021-03-26 01:01:20 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 340/1251] eta: 0:09:48 lr: 0.000614 loss: 5.1301 (5.1319) grad_norm: 1.7689 (1.8207) time: 0.6363 [2021-03-26 01:01:26 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 350/1251] eta: 0:09:41 lr: 0.000614 loss: 5.3459 (5.1310) grad_norm: 1.6863 (1.8151) time: 0.6377 [2021-03-26 01:01:33 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 360/1251] eta: 0:09:35 lr: 0.000615 loss: 5.1889 (5.1332) grad_norm: 1.6077 (1.8172) time: 0.6388 [2021-03-26 01:01:39 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 370/1251] eta: 0:09:28 lr: 0.000615 loss: 5.2925 (5.1368) grad_norm: 1.6077 (1.8122) time: 0.6319 [2021-03-26 01:01:45 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 380/1251] eta: 0:09:21 lr: 0.000616 loss: 4.9923 (5.1255) grad_norm: 1.7858 (1.8158) time: 0.6320 [2021-03-26 01:01:52 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 390/1251] eta: 0:09:14 lr: 0.000616 loss: 4.7400 (5.1243) grad_norm: 1.8333 (1.8134) time: 0.6377 [2021-03-26 01:01:58 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 400/1251] eta: 0:09:08 lr: 0.000616 loss: 5.2824 (5.1255) grad_norm: 1.5793 (1.8157) time: 0.6300 [2021-03-26 01:02:04 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 410/1251] eta: 0:09:01 lr: 0.000617 loss: 5.2824 (5.1269) grad_norm: 1.6464 (1.8116) time: 0.6318 [2021-03-26 01:02:11 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 420/1251] eta: 0:08:54 lr: 0.000617 loss: 4.9929 (5.1212) grad_norm: 1.5506 (1.8072) time: 0.6324 [2021-03-26 01:02:17 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 430/1251] eta: 0:08:48 lr: 0.000618 loss: 5.1822 (5.1240) grad_norm: 1.4678 (1.8003) time: 0.6314 [2021-03-26 01:02:23 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 440/1251] eta: 0:08:41 lr: 0.000618 loss: 5.2622 (5.1250) grad_norm: 1.4460 (1.7956) time: 0.6388 [2021-03-26 01:02:30 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 450/1251] eta: 0:08:34 lr: 0.000618 loss: 5.2622 (5.1243) grad_norm: 1.5914 (1.7938) time: 0.6330 [2021-03-26 01:02:36 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 460/1251] eta: 0:08:28 lr: 0.000619 loss: 5.0299 (5.1160) grad_norm: 1.7467 (1.7967) time: 0.6305 [2021-03-26 01:02:43 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 470/1251] eta: 0:08:22 lr: 0.000619 loss: 5.0607 (5.1158) grad_norm: 1.6265 (1.7902) time: 0.6418 [2021-03-26 01:02:49 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 480/1251] eta: 0:08:15 lr: 0.000620 loss: 5.3795 (5.1218) grad_norm: 1.5525 (1.7871) time: 0.6381 [2021-03-26 01:02:55 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 490/1251] eta: 0:08:08 lr: 0.000620 loss: 5.4369 (5.1223) grad_norm: 1.5918 (1.7854) time: 0.6310 [2021-03-26 01:03:02 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 500/1251] eta: 0:08:02 lr: 0.000620 loss: 5.4217 (5.1244) grad_norm: 1.7439 (1.7925) time: 0.6335 [2021-03-26 01:03:08 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 510/1251] eta: 0:07:55 lr: 0.000621 loss: 5.4815 (5.1309) grad_norm: 1.7090 (1.7905) time: 0.6315 [2021-03-26 01:03:14 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 520/1251] eta: 0:07:49 lr: 0.000621 loss: 5.2494 (5.1282) grad_norm: 1.6738 (1.7890) time: 0.6322 [2021-03-26 01:03:20 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 530/1251] eta: 0:07:42 lr: 0.000622 loss: 5.2788 (5.1288) grad_norm: 1.6424 (1.7857) time: 0.6306 [2021-03-26 01:03:27 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 540/1251] eta: 0:07:35 lr: 0.000622 loss: 5.2895 (5.1279) grad_norm: 1.5977 (1.7819) time: 0.6303 [2021-03-26 01:03:33 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 550/1251] eta: 0:07:29 lr: 0.000622 loss: 5.2087 (5.1290) grad_norm: 1.4587 (1.7756) time: 0.6380 [2021-03-26 01:03:40 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 560/1251] eta: 0:07:23 lr: 0.000623 loss: 5.3508 (5.1333) grad_norm: 1.4344 (1.7707) time: 0.6420 [2021-03-26 01:03:46 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 570/1251] eta: 0:07:16 lr: 0.000623 loss: 5.3508 (5.1314) grad_norm: 1.5671 (1.7678) time: 0.6380 [2021-03-26 01:03:52 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 580/1251] eta: 0:07:10 lr: 0.000624 loss: 4.9806 (5.1287) grad_norm: 1.5196 (1.7629) time: 0.6353 [2021-03-26 01:03:59 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 590/1251] eta: 0:07:03 lr: 0.000624 loss: 5.0421 (5.1265) grad_norm: 1.4778 (1.7603) time: 0.6328 [2021-03-26 01:04:05 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 600/1251] eta: 0:06:57 lr: 0.000624 loss: 5.2788 (5.1303) grad_norm: 1.7367 (1.7618) time: 0.6378 [2021-03-26 01:04:11 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 610/1251] eta: 0:06:50 lr: 0.000625 loss: 5.2975 (5.1318) grad_norm: 1.7663 (1.7628) time: 0.6438 [2021-03-26 01:04:18 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 620/1251] eta: 0:06:44 lr: 0.000625 loss: 5.2950 (5.1342) grad_norm: 1.4927 (1.7619) time: 0.6413 [2021-03-26 01:04:24 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 630/1251] eta: 0:06:38 lr: 0.000626 loss: 5.1727 (5.1313) grad_norm: 1.4992 (1.7602) time: 0.6398 [2021-03-26 01:04:30 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 640/1251] eta: 0:06:31 lr: 0.000626 loss: 4.8208 (5.1287) grad_norm: 1.5643 (1.7577) time: 0.6292 [2021-03-26 01:04:37 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 650/1251] eta: 0:06:25 lr: 0.000626 loss: 5.1231 (5.1301) grad_norm: 1.6013 (1.7559) time: 0.6297 [2021-03-26 01:04:43 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 660/1251] eta: 0:06:18 lr: 0.000627 loss: 5.2002 (5.1311) grad_norm: 1.5683 (1.7527) time: 0.6372 [2021-03-26 01:04:49 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 670/1251] eta: 0:06:11 lr: 0.000627 loss: 5.1050 (5.1308) grad_norm: 1.6368 (1.7513) time: 0.6280 [2021-03-26 01:04:56 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 680/1251] eta: 0:06:05 lr: 0.000628 loss: 5.0366 (5.1282) grad_norm: 1.6380 (1.7492) time: 0.6274 [2021-03-26 01:05:02 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 690/1251] eta: 0:05:59 lr: 0.000628 loss: 5.2692 (5.1298) grad_norm: 1.5664 (1.7458) time: 0.6361 [2021-03-26 01:05:09 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 700/1251] eta: 0:05:52 lr: 0.000628 loss: 5.1788 (5.1288) grad_norm: 1.5904 (1.7487) time: 0.6357 [2021-03-26 01:05:15 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 710/1251] eta: 0:05:46 lr: 0.000629 loss: 5.1079 (5.1281) grad_norm: 1.6318 (1.7492) time: 0.6393 [2021-03-26 01:05:21 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 720/1251] eta: 0:05:39 lr: 0.000629 loss: 5.2201 (5.1301) grad_norm: 1.4166 (1.7469) time: 0.6432 [2021-03-26 01:05:28 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 730/1251] eta: 0:05:33 lr: 0.000630 loss: 5.2830 (5.1283) grad_norm: 1.4285 (1.7444) time: 0.6442 [2021-03-26 01:05:34 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 740/1251] eta: 0:05:27 lr: 0.000630 loss: 5.2585 (5.1290) grad_norm: 1.3883 (1.7398) time: 0.6402 [2021-03-26 01:05:40 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 750/1251] eta: 0:05:20 lr: 0.000630 loss: 5.2585 (5.1286) grad_norm: 1.4961 (inf) time: 0.6287 [2021-03-26 01:05:47 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 760/1251] eta: 0:05:14 lr: 0.000631 loss: 5.2362 (5.1272) grad_norm: 1.4995 (inf) time: 0.6294 [2021-03-26 01:05:53 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 770/1251] eta: 0:05:07 lr: 0.000631 loss: 5.0077 (5.1228) grad_norm: 1.4675 (inf) time: 0.6354 [2021-03-26 01:06:00 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 780/1251] eta: 0:05:01 lr: 0.000632 loss: 5.1732 (5.1254) grad_norm: 1.6783 (inf) time: 0.6372 [2021-03-26 01:06:06 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 790/1251] eta: 0:04:54 lr: 0.000632 loss: 5.1726 (5.1247) grad_norm: 1.6078 (inf) time: 0.6357 [2021-03-26 01:06:12 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 800/1251] eta: 0:04:48 lr: 0.000632 loss: 5.0507 (5.1228) grad_norm: 1.4990 (inf) time: 0.6368 [2021-03-26 01:06:19 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 810/1251] eta: 0:04:42 lr: 0.000633 loss: 5.2763 (5.1258) grad_norm: 1.4930 (inf) time: 0.6366 [2021-03-26 01:06:25 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 820/1251] eta: 0:04:35 lr: 0.000633 loss: 5.3700 (5.1266) grad_norm: 1.5405 (inf) time: 0.6314 [2021-03-26 01:06:31 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 830/1251] eta: 0:04:29 lr: 0.000634 loss: 5.2822 (5.1282) grad_norm: 1.5338 (inf) time: 0.6324 [2021-03-26 01:06:38 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 840/1251] eta: 0:04:22 lr: 0.000634 loss: 5.2651 (5.1253) grad_norm: 1.5111 (inf) time: 0.6373 [2021-03-26 01:06:44 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 850/1251] eta: 0:04:16 lr: 0.000634 loss: 5.2684 (5.1282) grad_norm: 1.6333 (inf) time: 0.6391 [2021-03-26 01:06:50 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 860/1251] eta: 0:04:10 lr: 0.000635 loss: 5.2684 (5.1278) grad_norm: 1.7165 (inf) time: 0.6377 [2021-03-26 01:06:57 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 870/1251] eta: 0:04:03 lr: 0.000635 loss: 5.3291 (5.1315) grad_norm: 1.5216 (inf) time: 0.6405 [2021-03-26 01:07:03 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 880/1251] eta: 0:03:57 lr: 0.000636 loss: 5.4569 (5.1324) grad_norm: 1.4916 (inf) time: 0.6387 [2021-03-26 01:07:09 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 890/1251] eta: 0:03:50 lr: 0.000636 loss: 5.0241 (5.1300) grad_norm: 1.4634 (inf) time: 0.6321 [2021-03-26 01:07:16 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 900/1251] eta: 0:03:44 lr: 0.000636 loss: 4.9576 (5.1313) grad_norm: 1.5680 (inf) time: 0.6295 [2021-03-26 01:07:22 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 910/1251] eta: 0:03:37 lr: 0.000637 loss: 5.1117 (5.1286) grad_norm: 1.5729 (inf) time: 0.6342 [2021-03-26 01:07:29 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 920/1251] eta: 0:03:31 lr: 0.000637 loss: 4.6754 (5.1227) grad_norm: 1.4708 (inf) time: 0.6383 [2021-03-26 01:07:35 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 930/1251] eta: 0:03:25 lr: 0.000638 loss: 4.9683 (5.1236) grad_norm: 1.6500 (inf) time: 0.6332 [2021-03-26 01:07:41 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 940/1251] eta: 0:03:18 lr: 0.000638 loss: 5.1204 (5.1215) grad_norm: 1.8189 (inf) time: 0.6301 [2021-03-26 01:07:47 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 950/1251] eta: 0:03:12 lr: 0.000638 loss: 5.1144 (5.1217) grad_norm: 1.8469 (inf) time: 0.6306 [2021-03-26 01:07:54 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 960/1251] eta: 0:03:05 lr: 0.000639 loss: 5.2545 (5.1209) grad_norm: 2.3119 (inf) time: 0.6335 [2021-03-26 01:08:00 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 970/1251] eta: 0:02:59 lr: 0.000639 loss: 5.1056 (5.1189) grad_norm: 1.8329 (inf) time: 0.6339 [2021-03-26 01:08:07 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 980/1251] eta: 0:02:53 lr: 0.000640 loss: 5.0427 (5.1176) grad_norm: 1.4536 (inf) time: 0.6346 [2021-03-26 01:08:13 swin_base_patch4_window7_224] INFO: Epoch: [12] [ 990/1251] eta: 0:02:46 lr: 0.000640 loss: 5.1824 (5.1202) grad_norm: 1.5867 (inf) time: 0.6364 [2021-03-26 01:08:19 swin_base_patch4_window7_224] INFO: Epoch: [12] [1000/1251] eta: 0:02:40 lr: 0.000640 loss: 5.0457 (5.1186) grad_norm: 1.4252 (inf) time: 0.6372 [2021-03-26 01:08:26 swin_base_patch4_window7_224] INFO: Epoch: [12] [1010/1251] eta: 0:02:33 lr: 0.000641 loss: 5.0457 (5.1186) grad_norm: 1.4692 (inf) time: 0.6353 [2021-03-26 01:08:32 swin_base_patch4_window7_224] INFO: Epoch: [12] [1020/1251] eta: 0:02:27 lr: 0.000641 loss: 5.1384 (5.1183) grad_norm: 1.5789 (inf) time: 0.6359 [2021-03-26 01:08:38 swin_base_patch4_window7_224] INFO: Epoch: [12] [1030/1251] eta: 0:02:21 lr: 0.000642 loss: 5.0978 (5.1183) grad_norm: 1.6099 (inf) time: 0.6340 [2021-03-26 01:08:45 swin_base_patch4_window7_224] INFO: Epoch: [12] [1040/1251] eta: 0:02:14 lr: 0.000642 loss: 5.0978 (5.1172) grad_norm: 1.4186 (inf) time: 0.6315 [2021-03-26 01:08:51 swin_base_patch4_window7_224] INFO: Epoch: [12] [1050/1251] eta: 0:02:08 lr: 0.000642 loss: 5.0609 (5.1160) grad_norm: 1.5600 (inf) time: 0.6341 [2021-03-26 01:08:57 swin_base_patch4_window7_224] INFO: Epoch: [12] [1060/1251] eta: 0:02:01 lr: 0.000643 loss: 5.2016 (5.1160) grad_norm: 1.5608 (inf) time: 0.6365 [2021-03-26 01:09:04 swin_base_patch4_window7_224] INFO: Epoch: [12] [1070/1251] eta: 0:01:55 lr: 0.000643 loss: 5.1962 (5.1170) grad_norm: 1.5866 (inf) time: 0.6393 [2021-03-26 01:09:10 swin_base_patch4_window7_224] INFO: Epoch: [12] [1080/1251] eta: 0:01:49 lr: 0.000644 loss: 5.1948 (5.1157) grad_norm: 1.6437 (inf) time: 0.6405 [2021-03-26 01:09:17 swin_base_patch4_window7_224] INFO: Epoch: [12] [1090/1251] eta: 0:01:42 lr: 0.000644 loss: 5.1799 (5.1138) grad_norm: 1.7454 (inf) time: 0.6419 [2021-03-26 01:09:23 swin_base_patch4_window7_224] INFO: Epoch: [12] [1100/1251] eta: 0:01:36 lr: 0.000644 loss: 5.0579 (5.1135) grad_norm: 1.6706 (inf) time: 0.6371 [2021-03-26 01:09:29 swin_base_patch4_window7_224] INFO: Epoch: [12] [1110/1251] eta: 0:01:30 lr: 0.000645 loss: 5.0334 (5.1127) grad_norm: 1.6370 (inf) time: 0.6353 [2021-03-26 01:09:36 swin_base_patch4_window7_224] INFO: Epoch: [12] [1120/1251] eta: 0:01:23 lr: 0.000645 loss: 4.9702 (5.1119) grad_norm: 1.4724 (inf) time: 0.6379 [2021-03-26 01:09:42 swin_base_patch4_window7_224] INFO: Epoch: [12] [1130/1251] eta: 0:01:17 lr: 0.000646 loss: 5.3591 (5.1145) grad_norm: 1.4724 (inf) time: 0.6356 [2021-03-26 01:09:48 swin_base_patch4_window7_224] INFO: Epoch: [12] [1140/1251] eta: 0:01:10 lr: 0.000646 loss: 5.4396 (5.1158) grad_norm: 1.6834 (inf) time: 0.6390 [2021-03-26 01:09:55 swin_base_patch4_window7_224] INFO: Epoch: [12] [1150/1251] eta: 0:01:04 lr: 0.000646 loss: 5.1391 (5.1161) grad_norm: 1.5962 (inf) time: 0.6364 [2021-03-26 01:10:01 swin_base_patch4_window7_224] INFO: Epoch: [12] [1160/1251] eta: 0:00:58 lr: 0.000647 loss: 5.1391 (5.1152) grad_norm: 1.3822 (inf) time: 0.6353 [2021-03-26 01:10:07 swin_base_patch4_window7_224] INFO: Epoch: [12] [1170/1251] eta: 0:00:51 lr: 0.000647 loss: 4.8164 (5.1114) grad_norm: 1.5823 (inf) time: 0.6364 [2021-03-26 01:10:14 swin_base_patch4_window7_224] INFO: Epoch: [12] [1180/1251] eta: 0:00:45 lr: 0.000648 loss: 4.8164 (5.1105) grad_norm: 1.5269 (inf) time: 0.6375 [2021-03-26 01:10:20 swin_base_patch4_window7_224] INFO: Epoch: [12] [1190/1251] eta: 0:00:38 lr: 0.000648 loss: 5.3294 (5.1117) grad_norm: 1.5761 (inf) time: 0.6434 [2021-03-26 01:10:27 swin_base_patch4_window7_224] INFO: Epoch: [12] [1200/1251] eta: 0:00:32 lr: 0.000648 loss: 5.3397 (5.1128) grad_norm: 1.6414 (inf) time: 0.6405 [2021-03-26 01:10:33 swin_base_patch4_window7_224] INFO: Epoch: [12] [1210/1251] eta: 0:00:26 lr: 0.000649 loss: 5.2863 (5.1117) grad_norm: 1.5780 (inf) time: 0.6344 [2021-03-26 01:10:39 swin_base_patch4_window7_224] INFO: Epoch: [12] [1220/1251] eta: 0:00:19 lr: 0.000649 loss: 5.1472 (5.1119) grad_norm: 1.6510 (inf) time: 0.6358 [2021-03-26 01:10:46 swin_base_patch4_window7_224] INFO: Epoch: [12] [1230/1251] eta: 0:00:13 lr: 0.000650 loss: 5.0956 (5.1087) grad_norm: 1.7046 (inf) time: 0.6365 [2021-03-26 01:10:52 swin_base_patch4_window7_224] INFO: Epoch: [12] [1240/1251] eta: 0:00:07 lr: 0.000650 loss: 4.9661 (5.1089) grad_norm: 1.3767 (inf) time: 0.6301 [2021-03-26 01:10:58 swin_base_patch4_window7_224] INFO: Epoch: [12] [1250/1251] eta: 0:00:00 lr: 0.000650 loss: 5.0008 (5.1093) grad_norm: 1.4598 (inf) time: 0.6282 [2021-03-26 01:11:02 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:49 loss: 2.5885 (2.5885) acc1: 42.1875 (42.1875) acc5: 70.3125 (70.3125) [2021-03-26 01:11:05 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 2.4673 (2.5290) acc1: 42.1875 (44.4602) acc5: 71.8750 (72.0170) [2021-03-26 01:11:08 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 2.4673 (2.5535) acc1: 42.1875 (44.2708) acc5: 71.8750 (71.2054) [2021-03-26 01:11:11 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 2.4288 (2.5077) acc1: 48.4375 (45.9677) acc5: 71.8750 (71.2198) [2021-03-26 01:11:12 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 2.3713 (2.4873) acc1: 48.4375 (45.6555) acc5: 71.8750 (71.5320) [2021-03-26 01:11:13 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.4566 (2.4899) acc1: 45.3125 (45.6960) acc5: 70.3125 (71.4560) [2021-03-26 01:11:15 swin_base_patch4_window7_224] INFO: * Acc@1 45.724 Acc@5 71.996 loss 2.473 [2021-03-26 01:11:15 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 45.7% [2021-03-26 01:11:15 swin_base_patch4_window7_224] INFO: Max accuracy: 45.72% [2021-03-26 01:11:19 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 0/1251] eta: 1:31:41 lr: 0.000650 loss: 3.7904 (3.7904) grad_norm: 1.3511 (1.3511) time: 4.3977 [2021-03-26 01:11:26 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 10/1251] eta: 0:20:22 lr: 0.000651 loss: 4.8768 (4.8005) grad_norm: 1.3579 (1.3877) time: 0.9849 [2021-03-26 01:11:32 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 20/1251] eta: 0:16:44 lr: 0.000651 loss: 5.2003 (4.9799) grad_norm: 1.3913 (1.6126) time: 0.6371 [2021-03-26 01:11:38 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 30/1251] eta: 0:15:23 lr: 0.000652 loss: 5.2995 (4.9715) grad_norm: 1.8477 (1.7002) time: 0.6308 [2021-03-26 01:11:45 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 40/1251] eta: 0:14:41 lr: 0.000652 loss: 4.9002 (4.9504) grad_norm: 1.8811 (1.7672) time: 0.6349 [2021-03-26 01:11:51 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 50/1251] eta: 0:14:11 lr: 0.000652 loss: 4.8814 (4.9479) grad_norm: 1.6860 (1.7559) time: 0.6365 [2021-03-26 01:11:57 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 60/1251] eta: 0:13:48 lr: 0.000653 loss: 5.0196 (4.9997) grad_norm: 1.6815 (1.7688) time: 0.6302 [2021-03-26 01:12:04 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 70/1251] eta: 0:13:31 lr: 0.000653 loss: 5.1511 (5.0013) grad_norm: 1.5388 (1.7283) time: 0.6298 [2021-03-26 01:12:10 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 80/1251] eta: 0:13:15 lr: 0.000654 loss: 4.9357 (4.9928) grad_norm: 1.3505 (1.6926) time: 0.6304 [2021-03-26 01:12:16 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 90/1251] eta: 0:13:04 lr: 0.000654 loss: 4.8493 (4.9766) grad_norm: 1.4245 (1.6804) time: 0.6353 [2021-03-26 01:12:23 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 100/1251] eta: 0:12:53 lr: 0.000654 loss: 4.8493 (4.9798) grad_norm: 1.5961 (1.6934) time: 0.6407 [2021-03-26 01:12:29 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 110/1251] eta: 0:12:42 lr: 0.000655 loss: 5.2062 (4.9844) grad_norm: 1.5415 (1.6930) time: 0.6346 [2021-03-26 01:12:35 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 120/1251] eta: 0:12:31 lr: 0.000655 loss: 5.0660 (4.9781) grad_norm: 1.5070 (1.6801) time: 0.6289 [2021-03-26 01:12:42 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 130/1251] eta: 0:12:23 lr: 0.000656 loss: 5.0660 (4.9908) grad_norm: 1.5070 (1.6767) time: 0.6331 [2021-03-26 01:12:48 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 140/1251] eta: 0:12:15 lr: 0.000656 loss: 5.0856 (4.9885) grad_norm: 1.5778 (1.6742) time: 0.6441 [2021-03-26 01:12:55 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 150/1251] eta: 0:12:06 lr: 0.000656 loss: 5.0514 (4.9969) grad_norm: 1.6645 (1.6784) time: 0.6433 [2021-03-26 01:13:01 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 160/1251] eta: 0:11:58 lr: 0.000657 loss: 4.9055 (4.9856) grad_norm: 1.5348 (1.6701) time: 0.6385 [2021-03-26 01:13:07 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 170/1251] eta: 0:11:50 lr: 0.000657 loss: 4.8700 (4.9821) grad_norm: 1.4706 (1.6614) time: 0.6364 [2021-03-26 01:13:14 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 180/1251] eta: 0:11:42 lr: 0.000658 loss: 5.1185 (5.0085) grad_norm: 1.4748 (1.6741) time: 0.6308 [2021-03-26 01:13:20 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 190/1251] eta: 0:11:35 lr: 0.000658 loss: 5.1185 (4.9939) grad_norm: 1.6075 (1.6757) time: 0.6381 [2021-03-26 01:13:27 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 200/1251] eta: 0:11:28 lr: 0.000658 loss: 4.7548 (4.9865) grad_norm: 1.5507 (1.6721) time: 0.6480 [2021-03-26 01:13:33 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 210/1251] eta: 0:11:20 lr: 0.000659 loss: 5.1358 (5.0009) grad_norm: 1.4881 (1.6652) time: 0.6401 [2021-03-26 01:13:39 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 220/1251] eta: 0:11:13 lr: 0.000659 loss: 5.0079 (4.9979) grad_norm: 1.4881 (1.6681) time: 0.6300 [2021-03-26 01:13:46 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 230/1251] eta: 0:11:05 lr: 0.000660 loss: 5.0079 (4.9970) grad_norm: 1.4661 (1.6646) time: 0.6300 [2021-03-26 01:13:52 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 240/1251] eta: 0:10:58 lr: 0.000660 loss: 5.2799 (5.0051) grad_norm: 1.5288 (1.6658) time: 0.6336 [2021-03-26 01:13:58 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 250/1251] eta: 0:10:51 lr: 0.000660 loss: 5.1717 (5.0123) grad_norm: 1.7735 (1.6911) time: 0.6403 [2021-03-26 01:14:05 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 260/1251] eta: 0:10:44 lr: 0.000661 loss: 5.1165 (5.0087) grad_norm: 1.7325 (1.6863) time: 0.6399 [2021-03-26 01:14:11 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 270/1251] eta: 0:10:37 lr: 0.000661 loss: 4.7538 (4.9980) grad_norm: 1.5849 (1.6818) time: 0.6373 [2021-03-26 01:14:18 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 280/1251] eta: 0:10:30 lr: 0.000662 loss: 4.7987 (4.9965) grad_norm: 1.5554 (1.6872) time: 0.6397 [2021-03-26 01:14:24 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 290/1251] eta: 0:10:23 lr: 0.000662 loss: 4.9683 (4.9890) grad_norm: 1.5816 (1.6916) time: 0.6346 [2021-03-26 01:14:30 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 300/1251] eta: 0:10:16 lr: 0.000662 loss: 4.8644 (4.9797) grad_norm: 1.4445 (1.6897) time: 0.6320 [2021-03-26 01:14:36 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 310/1251] eta: 0:10:09 lr: 0.000663 loss: 4.8695 (4.9793) grad_norm: 1.5416 (1.6940) time: 0.6322 [2021-03-26 01:14:43 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 320/1251] eta: 0:10:02 lr: 0.000663 loss: 5.0558 (4.9838) grad_norm: 1.5416 (1.6904) time: 0.6328 [2021-03-26 01:14:49 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 330/1251] eta: 0:09:55 lr: 0.000664 loss: 5.3607 (4.9910) grad_norm: 1.3644 (1.6796) time: 0.6317 [2021-03-26 01:14:55 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 340/1251] eta: 0:09:48 lr: 0.000664 loss: 5.0865 (4.9862) grad_norm: 1.3644 (1.6744) time: 0.6283 [2021-03-26 01:15:02 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 350/1251] eta: 0:09:41 lr: 0.000664 loss: 4.8130 (4.9835) grad_norm: 1.5930 (1.6779) time: 0.6273 [2021-03-26 01:15:08 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 360/1251] eta: 0:09:34 lr: 0.000665 loss: 5.0116 (4.9827) grad_norm: 1.5751 (1.6762) time: 0.6273 [2021-03-26 01:15:14 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 370/1251] eta: 0:09:28 lr: 0.000665 loss: 5.2000 (4.9904) grad_norm: 1.5168 (1.6731) time: 0.6278 [2021-03-26 01:15:21 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 380/1251] eta: 0:09:21 lr: 0.000666 loss: 5.2876 (4.9927) grad_norm: 1.5565 (1.6784) time: 0.6319 [2021-03-26 01:15:27 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 390/1251] eta: 0:09:14 lr: 0.000666 loss: 5.2577 (4.9890) grad_norm: 1.6212 (1.6794) time: 0.6350 [2021-03-26 01:15:33 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 400/1251] eta: 0:09:08 lr: 0.000666 loss: 5.2577 (4.9901) grad_norm: 1.4085 (1.6743) time: 0.6338 [2021-03-26 01:15:40 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 410/1251] eta: 0:09:01 lr: 0.000667 loss: 5.1534 (4.9853) grad_norm: 1.4085 (1.6720) time: 0.6296 [2021-03-26 01:15:46 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 420/1251] eta: 0:08:54 lr: 0.000667 loss: 4.9616 (4.9870) grad_norm: 1.5300 (1.6776) time: 0.6311 [2021-03-26 01:15:52 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 430/1251] eta: 0:08:48 lr: 0.000668 loss: 5.1033 (4.9885) grad_norm: 1.4849 (1.6727) time: 0.6347 [2021-03-26 01:15:59 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 440/1251] eta: 0:08:41 lr: 0.000668 loss: 5.2524 (4.9965) grad_norm: 1.4036 (1.6700) time: 0.6349 [2021-03-26 01:16:05 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 450/1251] eta: 0:08:34 lr: 0.000668 loss: 5.2608 (5.0013) grad_norm: 1.3902 (1.6652) time: 0.6322 [2021-03-26 01:16:11 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 460/1251] eta: 0:08:28 lr: 0.000669 loss: 5.0112 (4.9960) grad_norm: 1.4836 (1.6642) time: 0.6336 [2021-03-26 01:16:18 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 470/1251] eta: 0:08:21 lr: 0.000669 loss: 4.7428 (4.9938) grad_norm: 1.6147 (1.6660) time: 0.6355 [2021-03-26 01:16:24 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 480/1251] eta: 0:08:15 lr: 0.000670 loss: 4.9311 (4.9942) grad_norm: 1.4034 (1.6631) time: 0.6342 [2021-03-26 01:16:30 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 490/1251] eta: 0:08:08 lr: 0.000670 loss: 5.2517 (5.0006) grad_norm: 1.4034 (1.6589) time: 0.6374 [2021-03-26 01:16:37 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 500/1251] eta: 0:08:02 lr: 0.000670 loss: 5.2517 (5.0042) grad_norm: 1.5582 (1.6586) time: 0.6316 [2021-03-26 01:16:43 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 510/1251] eta: 0:07:55 lr: 0.000671 loss: 5.2098 (5.0088) grad_norm: 1.5765 (1.6568) time: 0.6272 [2021-03-26 01:16:49 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 520/1251] eta: 0:07:48 lr: 0.000671 loss: 5.1698 (5.0102) grad_norm: 1.5007 (1.6537) time: 0.6327 [2021-03-26 01:16:56 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 530/1251] eta: 0:07:42 lr: 0.000672 loss: 4.9035 (5.0055) grad_norm: 1.5644 (1.6541) time: 0.6355 [2021-03-26 01:17:02 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 540/1251] eta: 0:07:35 lr: 0.000672 loss: 4.9035 (5.0059) grad_norm: 1.6567 (1.6571) time: 0.6319 [2021-03-26 01:17:08 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 550/1251] eta: 0:07:29 lr: 0.000672 loss: 4.9561 (5.0006) grad_norm: 1.5975 (1.6565) time: 0.6349 [2021-03-26 01:17:15 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 560/1251] eta: 0:07:22 lr: 0.000673 loss: 4.7781 (4.9977) grad_norm: 1.5648 (1.6574) time: 0.6346 [2021-03-26 01:17:21 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 570/1251] eta: 0:07:16 lr: 0.000673 loss: 5.0309 (4.9990) grad_norm: 1.4583 (1.6543) time: 0.6286 [2021-03-26 01:17:27 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 580/1251] eta: 0:07:09 lr: 0.000674 loss: 5.1189 (5.0015) grad_norm: 1.4575 (1.6531) time: 0.6298 [2021-03-26 01:17:34 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 590/1251] eta: 0:07:03 lr: 0.000674 loss: 5.0887 (5.0036) grad_norm: 1.6110 (1.6590) time: 0.6339 [2021-03-26 01:17:40 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 600/1251] eta: 0:06:56 lr: 0.000674 loss: 4.9252 (5.0020) grad_norm: 1.6258 (1.6626) time: 0.6321 [2021-03-26 01:17:46 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 610/1251] eta: 0:06:50 lr: 0.000675 loss: 5.1014 (5.0035) grad_norm: 1.4952 (1.6617) time: 0.6329 [2021-03-26 01:17:53 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 620/1251] eta: 0:06:43 lr: 0.000675 loss: 5.1014 (5.0047) grad_norm: 1.3769 (1.6560) time: 0.6376 [2021-03-26 01:17:59 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 630/1251] eta: 0:06:37 lr: 0.000676 loss: 5.0499 (5.0040) grad_norm: 1.3025 (1.6540) time: 0.6344 [2021-03-26 01:18:05 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 640/1251] eta: 0:06:31 lr: 0.000676 loss: 4.8339 (5.0004) grad_norm: 1.3644 (1.6498) time: 0.6344 [2021-03-26 01:18:12 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 650/1251] eta: 0:06:24 lr: 0.000676 loss: 4.8339 (4.9982) grad_norm: 1.3625 (1.6458) time: 0.6337 [2021-03-26 01:18:18 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 660/1251] eta: 0:06:18 lr: 0.000677 loss: 5.1147 (5.0002) grad_norm: 1.5035 (1.6454) time: 0.6326 [2021-03-26 01:18:24 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 670/1251] eta: 0:06:11 lr: 0.000677 loss: 5.0108 (4.9979) grad_norm: 1.5035 (1.6431) time: 0.6332 [2021-03-26 01:18:31 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 680/1251] eta: 0:06:05 lr: 0.000678 loss: 4.9637 (4.9979) grad_norm: 1.4214 (1.6426) time: 0.6315 [2021-03-26 01:18:37 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 690/1251] eta: 0:05:58 lr: 0.000678 loss: 5.1082 (4.9998) grad_norm: 1.4480 (1.6403) time: 0.6382 [2021-03-26 01:18:43 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 700/1251] eta: 0:05:52 lr: 0.000678 loss: 5.2002 (5.0001) grad_norm: 1.5428 (1.6422) time: 0.6388 [2021-03-26 01:18:50 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 710/1251] eta: 0:05:45 lr: 0.000679 loss: 4.9004 (4.9984) grad_norm: 1.6277 (1.6419) time: 0.6284 [2021-03-26 01:18:56 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 720/1251] eta: 0:05:39 lr: 0.000679 loss: 4.9004 (4.9984) grad_norm: 1.5337 (1.6407) time: 0.6282 [2021-03-26 01:19:02 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 730/1251] eta: 0:05:33 lr: 0.000679 loss: 5.1072 (4.9987) grad_norm: 1.4656 (1.6410) time: 0.6353 [2021-03-26 01:19:09 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 740/1251] eta: 0:05:26 lr: 0.000680 loss: 5.0763 (5.0010) grad_norm: 1.5384 (1.6455) time: 0.6370 [2021-03-26 01:19:15 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 750/1251] eta: 0:05:20 lr: 0.000680 loss: 4.9883 (4.9991) grad_norm: 1.4082 (1.6427) time: 0.6409 [2021-03-26 01:19:22 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 760/1251] eta: 0:05:13 lr: 0.000681 loss: 4.8898 (4.9956) grad_norm: 1.3747 (1.6390) time: 0.6441 [2021-03-26 01:19:28 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 770/1251] eta: 0:05:07 lr: 0.000681 loss: 4.8338 (4.9924) grad_norm: 1.3805 (1.6365) time: 0.6404 [2021-03-26 01:19:34 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 780/1251] eta: 0:05:01 lr: 0.000681 loss: 4.8484 (4.9920) grad_norm: 1.3935 (1.6347) time: 0.6360 [2021-03-26 01:19:41 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 790/1251] eta: 0:04:54 lr: 0.000682 loss: 4.9317 (4.9886) grad_norm: 1.3636 (1.6312) time: 0.6346 [2021-03-26 01:19:47 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 800/1251] eta: 0:04:48 lr: 0.000682 loss: 4.9317 (4.9901) grad_norm: 1.3466 (1.6294) time: 0.6343 [2021-03-26 01:19:53 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 810/1251] eta: 0:04:41 lr: 0.000683 loss: 5.0575 (4.9898) grad_norm: 1.3576 (1.6286) time: 0.6319 [2021-03-26 01:20:00 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 820/1251] eta: 0:04:35 lr: 0.000683 loss: 5.0575 (4.9909) grad_norm: 1.4683 (1.6292) time: 0.6330 [2021-03-26 01:20:06 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 830/1251] eta: 0:04:28 lr: 0.000683 loss: 5.1452 (4.9907) grad_norm: 1.5069 (1.6303) time: 0.6304 [2021-03-26 01:20:12 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 840/1251] eta: 0:04:22 lr: 0.000684 loss: 5.1733 (4.9927) grad_norm: 1.5958 (1.6309) time: 0.6315 [2021-03-26 01:20:19 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 850/1251] eta: 0:04:16 lr: 0.000684 loss: 5.1462 (4.9906) grad_norm: 1.5958 (1.6300) time: 0.6386 [2021-03-26 01:20:25 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 860/1251] eta: 0:04:09 lr: 0.000685 loss: 5.0118 (4.9926) grad_norm: 1.5262 (1.6285) time: 0.6336 [2021-03-26 01:20:31 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 870/1251] eta: 0:04:03 lr: 0.000685 loss: 5.0834 (4.9918) grad_norm: 1.4607 (1.6263) time: 0.6290 [2021-03-26 01:20:38 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 880/1251] eta: 0:03:56 lr: 0.000685 loss: 5.1554 (4.9912) grad_norm: 1.3970 (1.6265) time: 0.6312 [2021-03-26 01:20:44 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 890/1251] eta: 0:03:50 lr: 0.000686 loss: 5.2968 (4.9916) grad_norm: 1.4410 (1.6250) time: 0.6383 [2021-03-26 01:20:50 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 900/1251] eta: 0:03:44 lr: 0.000686 loss: 5.2968 (4.9931) grad_norm: 1.3800 (1.6223) time: 0.6394 [2021-03-26 01:20:57 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 910/1251] eta: 0:03:37 lr: 0.000687 loss: 5.1957 (4.9944) grad_norm: 1.3800 (1.6214) time: 0.6353 [2021-03-26 01:21:03 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 920/1251] eta: 0:03:31 lr: 0.000687 loss: 4.9635 (4.9906) grad_norm: 1.5406 (1.6218) time: 0.6360 [2021-03-26 01:21:09 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 930/1251] eta: 0:03:24 lr: 0.000687 loss: 4.6028 (4.9863) grad_norm: 1.6365 (1.6221) time: 0.6323 [2021-03-26 01:21:16 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 940/1251] eta: 0:03:18 lr: 0.000688 loss: 4.8898 (4.9876) grad_norm: 1.5214 (1.6193) time: 0.6356 [2021-03-26 01:21:22 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 950/1251] eta: 0:03:12 lr: 0.000688 loss: 4.9206 (4.9879) grad_norm: 1.4261 (1.6192) time: 0.6392 [2021-03-26 01:21:28 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 960/1251] eta: 0:03:05 lr: 0.000689 loss: 4.8802 (4.9863) grad_norm: 1.4036 (1.6165) time: 0.6330 [2021-03-26 01:21:35 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 970/1251] eta: 0:02:59 lr: 0.000689 loss: 4.9645 (4.9843) grad_norm: 1.4106 (1.6201) time: 0.6288 [2021-03-26 01:21:41 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 980/1251] eta: 0:02:52 lr: 0.000689 loss: 5.0904 (4.9874) grad_norm: 1.6621 (1.6195) time: 0.6268 [2021-03-26 01:21:47 swin_base_patch4_window7_224] INFO: Epoch: [13] [ 990/1251] eta: 0:02:46 lr: 0.000690 loss: 5.1060 (4.9875) grad_norm: 1.5284 (1.6195) time: 0.6291 [2021-03-26 01:21:54 swin_base_patch4_window7_224] INFO: Epoch: [13] [1000/1251] eta: 0:02:40 lr: 0.000690 loss: 5.0488 (4.9895) grad_norm: 1.4390 (1.6196) time: 0.6359 [2021-03-26 01:22:00 swin_base_patch4_window7_224] INFO: Epoch: [13] [1010/1251] eta: 0:02:33 lr: 0.000691 loss: 5.2040 (4.9888) grad_norm: 1.4229 (1.6183) time: 0.6419 [2021-03-26 01:22:07 swin_base_patch4_window7_224] INFO: Epoch: [13] [1020/1251] eta: 0:02:27 lr: 0.000691 loss: 4.8652 (4.9881) grad_norm: 1.3952 (1.6171) time: 0.6457 [2021-03-26 01:22:13 swin_base_patch4_window7_224] INFO: Epoch: [13] [1030/1251] eta: 0:02:21 lr: 0.000691 loss: 5.0512 (4.9890) grad_norm: 1.4512 (1.6159) time: 0.6412 [2021-03-26 01:22:19 swin_base_patch4_window7_224] INFO: Epoch: [13] [1040/1251] eta: 0:02:14 lr: 0.000692 loss: 5.1377 (4.9902) grad_norm: 1.4122 (1.6140) time: 0.6367 [2021-03-26 01:22:26 swin_base_patch4_window7_224] INFO: Epoch: [13] [1050/1251] eta: 0:02:08 lr: 0.000692 loss: 5.1048 (4.9911) grad_norm: 1.4540 (1.6136) time: 0.6349 [2021-03-26 01:22:32 swin_base_patch4_window7_224] INFO: Epoch: [13] [1060/1251] eta: 0:02:01 lr: 0.000693 loss: 4.9796 (4.9907) grad_norm: 1.5196 (1.6127) time: 0.6302 [2021-03-26 01:22:38 swin_base_patch4_window7_224] INFO: Epoch: [13] [1070/1251] eta: 0:01:55 lr: 0.000693 loss: 5.1208 (4.9923) grad_norm: 1.5196 (1.6119) time: 0.6322 [2021-03-26 01:22:45 swin_base_patch4_window7_224] INFO: Epoch: [13] [1080/1251] eta: 0:01:49 lr: 0.000693 loss: 4.9399 (4.9889) grad_norm: 1.5464 (1.6116) time: 0.6366 [2021-03-26 01:22:51 swin_base_patch4_window7_224] INFO: Epoch: [13] [1090/1251] eta: 0:01:42 lr: 0.000694 loss: 4.8679 (4.9900) grad_norm: 1.5854 (1.6117) time: 0.6369 [2021-03-26 01:22:57 swin_base_patch4_window7_224] INFO: Epoch: [13] [1100/1251] eta: 0:01:36 lr: 0.000694 loss: 5.0088 (4.9883) grad_norm: 1.6733 (1.6143) time: 0.6358 [2021-03-26 01:23:04 swin_base_patch4_window7_224] INFO: Epoch: [13] [1110/1251] eta: 0:01:29 lr: 0.000695 loss: 4.7506 (4.9865) grad_norm: 1.7277 (1.6152) time: 0.6314 [2021-03-26 01:23:10 swin_base_patch4_window7_224] INFO: Epoch: [13] [1120/1251] eta: 0:01:23 lr: 0.000695 loss: 4.7054 (4.9823) grad_norm: 1.5723 (1.6152) time: 0.6329 [2021-03-26 01:23:16 swin_base_patch4_window7_224] INFO: Epoch: [13] [1130/1251] eta: 0:01:17 lr: 0.000695 loss: 4.8358 (4.9840) grad_norm: 1.5038 (1.6159) time: 0.6348 [2021-03-26 01:23:23 swin_base_patch4_window7_224] INFO: Epoch: [13] [1140/1251] eta: 0:01:10 lr: 0.000696 loss: 5.1742 (4.9841) grad_norm: 1.4772 (1.6144) time: 0.6333 [2021-03-26 01:23:29 swin_base_patch4_window7_224] INFO: Epoch: [13] [1150/1251] eta: 0:01:04 lr: 0.000696 loss: 5.1423 (4.9850) grad_norm: 1.3591 (1.6120) time: 0.6335 [2021-03-26 01:23:35 swin_base_patch4_window7_224] INFO: Epoch: [13] [1160/1251] eta: 0:00:58 lr: 0.000697 loss: 5.2317 (4.9872) grad_norm: 1.4551 (1.6117) time: 0.6317 [2021-03-26 01:23:42 swin_base_patch4_window7_224] INFO: Epoch: [13] [1170/1251] eta: 0:00:51 lr: 0.000697 loss: 5.1775 (4.9866) grad_norm: 1.4829 (1.6113) time: 0.6312 [2021-03-26 01:23:48 swin_base_patch4_window7_224] INFO: Epoch: [13] [1180/1251] eta: 0:00:45 lr: 0.000697 loss: 4.9476 (4.9868) grad_norm: 1.4542 (1.6118) time: 0.6279 [2021-03-26 01:23:54 swin_base_patch4_window7_224] INFO: Epoch: [13] [1190/1251] eta: 0:00:38 lr: 0.000698 loss: 4.8677 (4.9847) grad_norm: 1.4444 (1.6128) time: 0.6316 [2021-03-26 01:24:01 swin_base_patch4_window7_224] INFO: Epoch: [13] [1200/1251] eta: 0:00:32 lr: 0.000698 loss: 4.9352 (4.9830) grad_norm: 1.4796 (1.6127) time: 0.6384 [2021-03-26 01:24:07 swin_base_patch4_window7_224] INFO: Epoch: [13] [1210/1251] eta: 0:00:26 lr: 0.000699 loss: 5.1324 (4.9831) grad_norm: 1.4026 (1.6105) time: 0.6369 [2021-03-26 01:24:13 swin_base_patch4_window7_224] INFO: Epoch: [13] [1220/1251] eta: 0:00:19 lr: 0.000699 loss: 5.1324 (4.9827) grad_norm: 1.3849 (1.6101) time: 0.6365 [2021-03-26 01:24:20 swin_base_patch4_window7_224] INFO: Epoch: [13] [1230/1251] eta: 0:00:13 lr: 0.000699 loss: 5.1328 (4.9829) grad_norm: 1.4663 (1.6095) time: 0.6328 [2021-03-26 01:24:26 swin_base_patch4_window7_224] INFO: Epoch: [13] [1240/1251] eta: 0:00:07 lr: 0.000700 loss: 4.9019 (4.9794) grad_norm: 1.5457 (1.6092) time: 0.6313 [2021-03-26 01:24:32 swin_base_patch4_window7_224] INFO: Epoch: [13] [1250/1251] eta: 0:00:00 lr: 0.000700 loss: 4.8946 (4.9803) grad_norm: 1.5191 (1.6085) time: 0.6265 [2021-03-26 01:24:37 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:10 loss: 2.5665 (2.5665) acc1: 48.4375 (48.4375) acc5: 68.7500 (68.7500) [2021-03-26 01:24:39 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 2.4446 (2.4195) acc1: 45.3125 (45.3125) acc5: 70.3125 (72.3011) [2021-03-26 01:24:42 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 2.3365 (2.3569) acc1: 48.4375 (48.3631) acc5: 75.0000 (74.1071) [2021-03-26 01:24:44 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 2.2848 (2.3542) acc1: 48.4375 (48.1855) acc5: 75.0000 (74.0927) [2021-03-26 01:24:47 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 2.3397 (2.3635) acc1: 45.3125 (47.3323) acc5: 73.4375 (73.7424) [2021-03-26 01:24:48 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.3298 (2.3584) acc1: 46.8750 (47.7440) acc5: 73.4375 (73.8560) [2021-03-26 01:24:49 swin_base_patch4_window7_224] INFO: * Acc@1 48.004 Acc@5 74.068 loss 2.346 [2021-03-26 01:24:49 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 48.0% [2021-03-26 01:24:49 swin_base_patch4_window7_224] INFO: Max accuracy: 48.00% [2021-03-26 01:24:54 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 0/1251] eta: 1:27:12 lr: 0.000700 loss: 5.3198 (5.3198) grad_norm: 1.4041 (1.4041) time: 4.1825 [2021-03-26 01:25:00 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 10/1251] eta: 0:19:47 lr: 0.000701 loss: 5.3198 (5.0992) grad_norm: 1.4041 (1.4042) time: 0.9573 [2021-03-26 01:25:06 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 20/1251] eta: 0:16:23 lr: 0.000701 loss: 5.1485 (4.9516) grad_norm: 1.3965 (1.4677) time: 0.6298 [2021-03-26 01:25:12 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 30/1251] eta: 0:15:11 lr: 0.000701 loss: 5.0653 (4.9754) grad_norm: 1.4183 (1.5361) time: 0.6309 [2021-03-26 01:25:19 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 40/1251] eta: 0:14:30 lr: 0.000702 loss: 5.0653 (4.9430) grad_norm: 1.5485 (1.5318) time: 0.6354 [2021-03-26 01:25:25 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 50/1251] eta: 0:14:04 lr: 0.000702 loss: 5.0774 (4.9282) grad_norm: 1.4683 (1.5521) time: 0.6347 [2021-03-26 01:25:31 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 60/1251] eta: 0:13:41 lr: 0.000703 loss: 5.1573 (4.9607) grad_norm: 1.4264 (1.5333) time: 0.6298 [2021-03-26 01:25:38 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 70/1251] eta: 0:13:25 lr: 0.000703 loss: 5.1573 (4.9644) grad_norm: 1.3887 (1.5360) time: 0.6303 [2021-03-26 01:25:44 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 80/1251] eta: 0:13:14 lr: 0.000703 loss: 5.1507 (4.9673) grad_norm: 1.5316 (1.5335) time: 0.6423 [2021-03-26 01:25:51 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 90/1251] eta: 0:13:02 lr: 0.000704 loss: 5.0486 (4.9743) grad_norm: 1.4816 (1.5249) time: 0.6434 [2021-03-26 01:25:57 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 100/1251] eta: 0:12:50 lr: 0.000704 loss: 5.0441 (4.9787) grad_norm: 1.3971 (1.5117) time: 0.6345 [2021-03-26 01:26:03 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 110/1251] eta: 0:12:39 lr: 0.000705 loss: 5.1214 (4.9829) grad_norm: 1.3132 (1.4891) time: 0.6289 [2021-03-26 01:26:10 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 120/1251] eta: 0:12:30 lr: 0.000705 loss: 5.0792 (4.9742) grad_norm: 1.4125 (1.5024) time: 0.6336 [2021-03-26 01:26:16 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 130/1251] eta: 0:12:21 lr: 0.000705 loss: 5.1211 (4.9849) grad_norm: 1.5117 (1.5080) time: 0.6380 [2021-03-26 01:26:22 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 140/1251] eta: 0:12:13 lr: 0.000706 loss: 5.1211 (4.9791) grad_norm: 1.5032 (1.5160) time: 0.6399 [2021-03-26 01:26:29 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 150/1251] eta: 0:12:06 lr: 0.000706 loss: 4.9642 (4.9690) grad_norm: 1.5504 (1.5227) time: 0.6461 [2021-03-26 01:26:35 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 160/1251] eta: 0:11:57 lr: 0.000707 loss: 5.0825 (4.9851) grad_norm: 1.5776 (1.5243) time: 0.6391 [2021-03-26 01:26:42 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 170/1251] eta: 0:11:49 lr: 0.000707 loss: 4.9925 (4.9608) grad_norm: 1.4052 (1.5189) time: 0.6366 [2021-03-26 01:26:48 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 180/1251] eta: 0:11:41 lr: 0.000707 loss: 4.3299 (4.9268) grad_norm: 1.3936 (1.5158) time: 0.6362 [2021-03-26 01:26:54 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 190/1251] eta: 0:11:33 lr: 0.000708 loss: 4.8212 (4.9371) grad_norm: 1.4771 (1.5154) time: 0.6290 [2021-03-26 01:27:01 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 200/1251] eta: 0:11:26 lr: 0.000708 loss: 5.2213 (4.9417) grad_norm: 1.4792 (1.5139) time: 0.6304 [2021-03-26 01:27:07 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 210/1251] eta: 0:11:18 lr: 0.000709 loss: 4.8396 (4.9337) grad_norm: 1.4346 (1.5188) time: 0.6352 [2021-03-26 01:27:13 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 220/1251] eta: 0:11:11 lr: 0.000709 loss: 4.7149 (4.9279) grad_norm: 1.4212 (1.5125) time: 0.6382 [2021-03-26 01:27:20 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 230/1251] eta: 0:11:04 lr: 0.000709 loss: 4.9923 (4.9370) grad_norm: 1.4137 (1.5065) time: 0.6356 [2021-03-26 01:27:26 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 240/1251] eta: 0:10:57 lr: 0.000710 loss: 5.1434 (4.9478) grad_norm: 1.4358 (1.5108) time: 0.6333 [2021-03-26 01:27:32 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 250/1251] eta: 0:10:50 lr: 0.000710 loss: 4.9971 (4.9440) grad_norm: 1.5298 (1.5132) time: 0.6358 [2021-03-26 01:27:39 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 260/1251] eta: 0:10:43 lr: 0.000711 loss: 4.8256 (4.9459) grad_norm: 1.5298 (1.5202) time: 0.6361 [2021-03-26 01:27:45 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 270/1251] eta: 0:10:36 lr: 0.000711 loss: 5.0650 (4.9425) grad_norm: 1.5356 (1.5249) time: 0.6342 [2021-03-26 01:27:51 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 280/1251] eta: 0:10:28 lr: 0.000711 loss: 5.0650 (4.9446) grad_norm: 1.5356 (1.5294) time: 0.6333 [2021-03-26 01:27:58 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 290/1251] eta: 0:10:21 lr: 0.000712 loss: 4.8979 (4.9417) grad_norm: 1.4706 (1.5266) time: 0.6317 [2021-03-26 01:28:04 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 300/1251] eta: 0:10:15 lr: 0.000712 loss: 4.9530 (4.9450) grad_norm: 1.4297 (1.5237) time: 0.6325 [2021-03-26 01:28:10 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 310/1251] eta: 0:10:08 lr: 0.000713 loss: 4.9071 (4.9376) grad_norm: 1.4787 (1.5272) time: 0.6336 [2021-03-26 01:28:17 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 320/1251] eta: 0:10:01 lr: 0.000713 loss: 4.7949 (4.9387) grad_norm: 1.5747 (1.5407) time: 0.6388 [2021-03-26 01:28:23 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 330/1251] eta: 0:09:55 lr: 0.000713 loss: 5.1763 (4.9444) grad_norm: 1.5545 (1.5405) time: 0.6470 [2021-03-26 01:28:30 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 340/1251] eta: 0:09:48 lr: 0.000714 loss: 4.8998 (4.9367) grad_norm: 1.4938 (1.5367) time: 0.6417 [2021-03-26 01:28:36 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 350/1251] eta: 0:09:41 lr: 0.000714 loss: 4.7828 (4.9351) grad_norm: 1.5925 (1.5391) time: 0.6355 [2021-03-26 01:28:42 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 360/1251] eta: 0:09:35 lr: 0.000715 loss: 5.0673 (4.9404) grad_norm: 1.4969 (1.5333) time: 0.6347 [2021-03-26 01:28:49 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 370/1251] eta: 0:09:28 lr: 0.000715 loss: 5.0673 (4.9339) grad_norm: 1.3807 (1.5320) time: 0.6326 [2021-03-26 01:28:55 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 380/1251] eta: 0:09:21 lr: 0.000715 loss: 4.8191 (4.9354) grad_norm: 1.5123 (1.5347) time: 0.6339 [2021-03-26 01:29:01 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 390/1251] eta: 0:09:14 lr: 0.000716 loss: 5.0759 (4.9343) grad_norm: 1.4784 (1.5361) time: 0.6306 [2021-03-26 01:29:08 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 400/1251] eta: 0:09:07 lr: 0.000716 loss: 5.0690 (4.9346) grad_norm: 1.4784 (1.5346) time: 0.6285 [2021-03-26 01:29:14 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 410/1251] eta: 0:09:01 lr: 0.000717 loss: 5.0690 (4.9383) grad_norm: 1.3196 (1.5288) time: 0.6302 [2021-03-26 01:29:20 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 420/1251] eta: 0:08:54 lr: 0.000717 loss: 4.9374 (4.9366) grad_norm: 1.1987 (1.5254) time: 0.6315 [2021-03-26 01:29:27 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 430/1251] eta: 0:08:47 lr: 0.000717 loss: 4.9383 (4.9399) grad_norm: 1.2353 (1.5234) time: 0.6323 [2021-03-26 01:29:33 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 440/1251] eta: 0:08:41 lr: 0.000718 loss: 4.9746 (4.9333) grad_norm: 1.3282 (1.5248) time: 0.6349 [2021-03-26 01:29:39 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 450/1251] eta: 0:08:34 lr: 0.000718 loss: 4.6501 (4.9309) grad_norm: 1.5922 (1.5270) time: 0.6308 [2021-03-26 01:29:46 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 460/1251] eta: 0:08:28 lr: 0.000719 loss: 5.0783 (4.9369) grad_norm: 1.4962 (1.5245) time: 0.6307 [2021-03-26 01:29:52 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 470/1251] eta: 0:08:21 lr: 0.000719 loss: 5.0500 (4.9281) grad_norm: 1.4074 (1.5241) time: 0.6366 [2021-03-26 01:29:58 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 480/1251] eta: 0:08:14 lr: 0.000719 loss: 4.8202 (4.9247) grad_norm: 1.4343 (1.5259) time: 0.6298 [2021-03-26 01:30:05 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 490/1251] eta: 0:08:08 lr: 0.000720 loss: 5.0991 (4.9272) grad_norm: 1.4468 (1.5260) time: 0.6282 [2021-03-26 01:30:11 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 500/1251] eta: 0:08:01 lr: 0.000720 loss: 5.0887 (4.9263) grad_norm: 1.4923 (1.5259) time: 0.6330 [2021-03-26 01:30:17 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 510/1251] eta: 0:07:55 lr: 0.000721 loss: 5.0480 (4.9267) grad_norm: 1.4792 (1.5282) time: 0.6320 [2021-03-26 01:30:23 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 520/1251] eta: 0:07:48 lr: 0.000721 loss: 4.8141 (4.9240) grad_norm: 1.4035 (1.5234) time: 0.6313 [2021-03-26 01:30:30 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 530/1251] eta: 0:07:42 lr: 0.000721 loss: 4.9116 (4.9230) grad_norm: 1.2668 (1.5200) time: 0.6336 [2021-03-26 01:30:36 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 540/1251] eta: 0:07:35 lr: 0.000722 loss: 4.9116 (4.9171) grad_norm: 1.3941 (1.5204) time: 0.6344 [2021-03-26 01:30:43 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 550/1251] eta: 0:07:29 lr: 0.000722 loss: 4.8996 (4.9188) grad_norm: 1.3941 (1.5177) time: 0.6385 [2021-03-26 01:30:49 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 560/1251] eta: 0:07:22 lr: 0.000723 loss: 5.2764 (4.9224) grad_norm: 1.4446 (1.5213) time: 0.6439 [2021-03-26 01:30:56 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 570/1251] eta: 0:07:16 lr: 0.000723 loss: 5.1356 (4.9222) grad_norm: 1.4121 (1.5186) time: 0.6468 [2021-03-26 01:31:02 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 580/1251] eta: 0:07:10 lr: 0.000723 loss: 5.1703 (4.9260) grad_norm: 1.3880 (1.5159) time: 0.6406 [2021-03-26 01:31:08 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 590/1251] eta: 0:07:03 lr: 0.000724 loss: 5.2972 (4.9313) grad_norm: 1.3283 (1.5139) time: 0.6278 [2021-03-26 01:31:14 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 600/1251] eta: 0:06:56 lr: 0.000724 loss: 5.1393 (4.9314) grad_norm: 1.3541 (1.5128) time: 0.6264 [2021-03-26 01:31:21 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 610/1251] eta: 0:06:50 lr: 0.000725 loss: 4.9642 (4.9282) grad_norm: 1.3885 (1.5104) time: 0.6332 [2021-03-26 01:31:27 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 620/1251] eta: 0:06:44 lr: 0.000725 loss: 4.8462 (4.9252) grad_norm: 1.3917 (1.5135) time: 0.6352 [2021-03-26 01:31:33 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 630/1251] eta: 0:06:37 lr: 0.000725 loss: 4.8993 (4.9265) grad_norm: 1.6589 (1.5151) time: 0.6330 [2021-03-26 01:31:40 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 640/1251] eta: 0:06:31 lr: 0.000726 loss: 4.9726 (4.9267) grad_norm: 1.5505 (1.5172) time: 0.6406 [2021-03-26 01:31:46 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 650/1251] eta: 0:06:24 lr: 0.000726 loss: 4.9726 (4.9239) grad_norm: 1.4855 (1.5171) time: 0.6393 [2021-03-26 01:31:53 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 660/1251] eta: 0:06:18 lr: 0.000727 loss: 5.0085 (4.9275) grad_norm: 1.3894 (1.5152) time: 0.6308 [2021-03-26 01:31:59 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 670/1251] eta: 0:06:11 lr: 0.000727 loss: 5.1327 (4.9262) grad_norm: 1.3163 (1.5148) time: 0.6283 [2021-03-26 01:32:05 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 680/1251] eta: 0:06:05 lr: 0.000727 loss: 5.0627 (4.9274) grad_norm: 1.4020 (1.5143) time: 0.6303 [2021-03-26 01:32:12 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 690/1251] eta: 0:05:58 lr: 0.000728 loss: 5.0627 (4.9278) grad_norm: 1.4564 (1.5156) time: 0.6377 [2021-03-26 01:32:18 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 700/1251] eta: 0:05:52 lr: 0.000728 loss: 4.9527 (4.9283) grad_norm: 1.5536 (1.5159) time: 0.6418 [2021-03-26 01:32:24 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 710/1251] eta: 0:05:46 lr: 0.000729 loss: 4.9890 (4.9296) grad_norm: 1.4856 (1.5144) time: 0.6414 [2021-03-26 01:32:31 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 720/1251] eta: 0:05:39 lr: 0.000729 loss: 5.1697 (4.9324) grad_norm: 1.3940 (1.5146) time: 0.6350 [2021-03-26 01:32:37 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 730/1251] eta: 0:05:33 lr: 0.000729 loss: 5.2069 (4.9348) grad_norm: 1.4162 (1.5134) time: 0.6319 [2021-03-26 01:32:43 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 740/1251] eta: 0:05:26 lr: 0.000730 loss: 5.2150 (4.9372) grad_norm: 1.3647 (1.5126) time: 0.6347 [2021-03-26 01:32:50 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 750/1251] eta: 0:05:20 lr: 0.000730 loss: 5.2375 (4.9407) grad_norm: 1.4414 (1.5122) time: 0.6401 [2021-03-26 01:32:56 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 760/1251] eta: 0:05:14 lr: 0.000731 loss: 5.2375 (4.9436) grad_norm: 1.4549 (1.5127) time: 0.6452 [2021-03-26 01:33:03 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 770/1251] eta: 0:05:07 lr: 0.000731 loss: 5.1840 (4.9442) grad_norm: 1.4549 (1.5116) time: 0.6398 [2021-03-26 01:33:09 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 780/1251] eta: 0:05:01 lr: 0.000731 loss: 5.1092 (4.9427) grad_norm: 1.4588 (1.5122) time: 0.6412 [2021-03-26 01:33:15 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 790/1251] eta: 0:04:54 lr: 0.000732 loss: 5.1282 (4.9447) grad_norm: 1.3912 (1.5114) time: 0.6408 [2021-03-26 01:33:22 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 800/1251] eta: 0:04:48 lr: 0.000732 loss: 4.8806 (4.9439) grad_norm: 1.4147 (1.5144) time: 0.6328 [2021-03-26 01:33:28 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 810/1251] eta: 0:04:41 lr: 0.000733 loss: 5.0353 (4.9460) grad_norm: 1.4178 (1.5136) time: 0.6308 [2021-03-26 01:33:34 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 820/1251] eta: 0:04:35 lr: 0.000733 loss: 4.9880 (4.9434) grad_norm: 1.4266 (1.5173) time: 0.6327 [2021-03-26 01:33:41 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 830/1251] eta: 0:04:29 lr: 0.000733 loss: 4.7311 (4.9411) grad_norm: 1.6860 (1.5193) time: 0.6377 [2021-03-26 01:33:47 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 840/1251] eta: 0:04:22 lr: 0.000734 loss: 4.7005 (4.9383) grad_norm: 1.4909 (1.5185) time: 0.6333 [2021-03-26 01:33:54 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 850/1251] eta: 0:04:16 lr: 0.000734 loss: 4.9128 (4.9368) grad_norm: 1.4482 (1.5187) time: 0.6349 [2021-03-26 01:34:00 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 860/1251] eta: 0:04:09 lr: 0.000735 loss: 4.8433 (4.9359) grad_norm: 1.5019 (1.5194) time: 0.6364 [2021-03-26 01:34:06 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 870/1251] eta: 0:04:03 lr: 0.000735 loss: 5.1007 (4.9375) grad_norm: 1.4391 (1.5194) time: 0.6369 [2021-03-26 01:34:13 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 880/1251] eta: 0:03:57 lr: 0.000735 loss: 5.1619 (4.9366) grad_norm: 1.3698 (1.5164) time: 0.6458 [2021-03-26 01:34:19 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 890/1251] eta: 0:03:50 lr: 0.000736 loss: 5.0732 (4.9374) grad_norm: 1.3372 (1.5150) time: 0.6469 [2021-03-26 01:34:26 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 900/1251] eta: 0:03:44 lr: 0.000736 loss: 4.8330 (4.9374) grad_norm: 1.4020 (1.5144) time: 0.6436 [2021-03-26 01:34:32 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 910/1251] eta: 0:03:38 lr: 0.000737 loss: 4.7992 (4.9359) grad_norm: 1.3230 (1.5123) time: 0.6422 [2021-03-26 01:34:38 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 920/1251] eta: 0:03:31 lr: 0.000737 loss: 5.0371 (4.9339) grad_norm: 1.3230 (1.5112) time: 0.6371 [2021-03-26 01:34:45 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 930/1251] eta: 0:03:25 lr: 0.000737 loss: 4.8138 (4.9305) grad_norm: 1.4538 (1.5120) time: 0.6314 [2021-03-26 01:34:51 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 940/1251] eta: 0:03:18 lr: 0.000738 loss: 4.8138 (4.9282) grad_norm: 1.4703 (1.5123) time: 0.6330 [2021-03-26 01:34:57 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 950/1251] eta: 0:03:12 lr: 0.000738 loss: 4.7319 (4.9262) grad_norm: 1.6554 (1.5139) time: 0.6349 [2021-03-26 01:35:04 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 960/1251] eta: 0:03:05 lr: 0.000739 loss: 5.0073 (4.9281) grad_norm: 1.4048 (1.5121) time: 0.6346 [2021-03-26 01:35:10 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 970/1251] eta: 0:02:59 lr: 0.000739 loss: 5.2102 (4.9292) grad_norm: 1.3441 (1.5121) time: 0.6351 [2021-03-26 01:35:16 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 980/1251] eta: 0:02:53 lr: 0.000739 loss: 5.1805 (4.9302) grad_norm: 1.4110 (1.5113) time: 0.6358 [2021-03-26 01:35:23 swin_base_patch4_window7_224] INFO: Epoch: [14] [ 990/1251] eta: 0:02:46 lr: 0.000740 loss: 5.0654 (4.9310) grad_norm: 1.2848 (1.5087) time: 0.6365 [2021-03-26 01:35:29 swin_base_patch4_window7_224] INFO: Epoch: [14] [1000/1251] eta: 0:02:40 lr: 0.000740 loss: 5.0654 (4.9316) grad_norm: 1.2151 (1.5068) time: 0.6336 [2021-03-26 01:35:35 swin_base_patch4_window7_224] INFO: Epoch: [14] [1010/1251] eta: 0:02:33 lr: 0.000741 loss: 5.0909 (4.9328) grad_norm: 1.3530 (1.5078) time: 0.6334 [2021-03-26 01:35:42 swin_base_patch4_window7_224] INFO: Epoch: [14] [1020/1251] eta: 0:02:27 lr: 0.000741 loss: 5.0650 (4.9328) grad_norm: 1.4996 (1.5082) time: 0.6365 [2021-03-26 01:35:48 swin_base_patch4_window7_224] INFO: Epoch: [14] [1030/1251] eta: 0:02:21 lr: 0.000741 loss: 4.5235 (4.9284) grad_norm: 1.3863 (1.5076) time: 0.6361 [2021-03-26 01:35:55 swin_base_patch4_window7_224] INFO: Epoch: [14] [1040/1251] eta: 0:02:14 lr: 0.000742 loss: 4.9025 (4.9297) grad_norm: 1.4278 (1.5069) time: 0.6330 [2021-03-26 01:36:01 swin_base_patch4_window7_224] INFO: Epoch: [14] [1050/1251] eta: 0:02:08 lr: 0.000742 loss: 5.0574 (4.9278) grad_norm: 1.4366 (1.5063) time: 0.6311 [2021-03-26 01:36:07 swin_base_patch4_window7_224] INFO: Epoch: [14] [1060/1251] eta: 0:02:02 lr: 0.000743 loss: 5.0574 (4.9273) grad_norm: 1.3392 (1.5041) time: 0.6347 [2021-03-26 01:36:14 swin_base_patch4_window7_224] INFO: Epoch: [14] [1070/1251] eta: 0:01:55 lr: 0.000743 loss: 4.9049 (4.9261) grad_norm: 1.3502 (1.5038) time: 0.6354 [2021-03-26 01:36:20 swin_base_patch4_window7_224] INFO: Epoch: [14] [1080/1251] eta: 0:01:49 lr: 0.000743 loss: 4.7857 (4.9250) grad_norm: 1.4164 (1.5027) time: 0.6394 [2021-03-26 01:36:26 swin_base_patch4_window7_224] INFO: Epoch: [14] [1090/1251] eta: 0:01:42 lr: 0.000744 loss: 4.8704 (4.9255) grad_norm: 1.3148 (1.5008) time: 0.6358 [2021-03-26 01:36:33 swin_base_patch4_window7_224] INFO: Epoch: [14] [1100/1251] eta: 0:01:36 lr: 0.000744 loss: 5.0237 (4.9254) grad_norm: 1.3834 (1.5019) time: 0.6283 [2021-03-26 01:36:39 swin_base_patch4_window7_224] INFO: Epoch: [14] [1110/1251] eta: 0:01:30 lr: 0.000745 loss: 4.9855 (4.9226) grad_norm: 1.5129 (1.5016) time: 0.6331 [2021-03-26 01:36:45 swin_base_patch4_window7_224] INFO: Epoch: [14] [1120/1251] eta: 0:01:23 lr: 0.000745 loss: 4.4730 (4.9195) grad_norm: 1.3512 (1.5007) time: 0.6315 [2021-03-26 01:36:51 swin_base_patch4_window7_224] INFO: Epoch: [14] [1130/1251] eta: 0:01:17 lr: 0.000745 loss: 4.8451 (4.9209) grad_norm: 1.4040 (1.5021) time: 0.6270 [2021-03-26 01:36:58 swin_base_patch4_window7_224] INFO: Epoch: [14] [1140/1251] eta: 0:01:10 lr: 0.000746 loss: 5.0057 (4.9211) grad_norm: 1.4926 (1.5017) time: 0.6248 [2021-03-26 01:37:04 swin_base_patch4_window7_224] INFO: Epoch: [14] [1150/1251] eta: 0:01:04 lr: 0.000746 loss: 4.7852 (4.9199) grad_norm: 1.3980 (1.5012) time: 0.6306 [2021-03-26 01:37:10 swin_base_patch4_window7_224] INFO: Epoch: [14] [1160/1251] eta: 0:00:58 lr: 0.000747 loss: 4.7680 (4.9186) grad_norm: 1.3102 (1.4994) time: 0.6338 [2021-03-26 01:37:17 swin_base_patch4_window7_224] INFO: Epoch: [14] [1170/1251] eta: 0:00:51 lr: 0.000747 loss: 4.8801 (4.9187) grad_norm: 1.2458 (1.4972) time: 0.6284 [2021-03-26 01:37:23 swin_base_patch4_window7_224] INFO: Epoch: [14] [1180/1251] eta: 0:00:45 lr: 0.000747 loss: 5.1418 (4.9213) grad_norm: 1.3085 (1.4979) time: 0.6303 [2021-03-26 01:37:29 swin_base_patch4_window7_224] INFO: Epoch: [14] [1190/1251] eta: 0:00:38 lr: 0.000748 loss: 5.1903 (4.9203) grad_norm: 1.3638 (1.4974) time: 0.6335 [2021-03-26 01:37:36 swin_base_patch4_window7_224] INFO: Epoch: [14] [1200/1251] eta: 0:00:32 lr: 0.000748 loss: 4.5570 (4.9180) grad_norm: 1.4199 (1.5003) time: 0.6306 [2021-03-26 01:37:42 swin_base_patch4_window7_224] INFO: Epoch: [14] [1210/1251] eta: 0:00:26 lr: 0.000749 loss: 4.5570 (4.9171) grad_norm: 1.4530 (1.4987) time: 0.6319 [2021-03-26 01:37:48 swin_base_patch4_window7_224] INFO: Epoch: [14] [1220/1251] eta: 0:00:19 lr: 0.000749 loss: 4.6978 (4.9153) grad_norm: 1.2682 (1.4980) time: 0.6393 [2021-03-26 01:37:55 swin_base_patch4_window7_224] INFO: Epoch: [14] [1230/1251] eta: 0:00:13 lr: 0.000749 loss: 4.7637 (4.9147) grad_norm: 1.2794 (1.4970) time: 0.6363 [2021-03-26 01:38:01 swin_base_patch4_window7_224] INFO: Epoch: [14] [1240/1251] eta: 0:00:07 lr: 0.000750 loss: 4.7600 (4.9131) grad_norm: 1.2981 (1.4963) time: 0.6291 [2021-03-26 01:38:07 swin_base_patch4_window7_224] INFO: Epoch: [14] [1250/1251] eta: 0:00:00 lr: 0.000750 loss: 4.7600 (4.9118) grad_norm: 1.2442 (1.4943) time: 0.6208 [2021-03-26 01:38:11 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:35 loss: 2.0158 (2.0158) acc1: 48.4375 (48.4375) acc5: 85.9375 (85.9375) [2021-03-26 01:38:14 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 2.1563 (2.1467) acc1: 53.1250 (54.4034) acc5: 76.5625 (76.2784) [2021-03-26 01:38:16 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 2.1603 (2.1703) acc1: 51.5625 (52.8274) acc5: 76.5625 (76.7113) [2021-03-26 01:38:18 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 2.2602 (2.2290) acc1: 50.0000 (51.7137) acc5: 75.0000 (76.3609) [2021-03-26 01:38:20 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 2.3086 (2.2526) acc1: 48.4375 (50.8003) acc5: 75.0000 (76.2957) [2021-03-26 01:38:21 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.3056 (2.2691) acc1: 50.0000 (50.8160) acc5: 73.4375 (75.9040) [2021-03-26 01:38:23 swin_base_patch4_window7_224] INFO: * Acc@1 50.156 Acc@5 76.022 loss 2.263 [2021-03-26 01:38:23 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 50.2% [2021-03-26 01:38:23 swin_base_patch4_window7_224] INFO: Max accuracy: 50.16% [2021-03-26 01:38:27 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 0/1251] eta: 1:26:20 lr: 0.000750 loss: 4.9684 (4.9684) grad_norm: 1.0854 (1.0854) time: 4.1415 [2021-03-26 01:38:34 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 10/1251] eta: 0:20:13 lr: 0.000751 loss: 5.0437 (5.0294) grad_norm: 1.3352 (1.3130) time: 0.9777 [2021-03-26 01:38:41 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 20/1251] eta: 0:16:48 lr: 0.000751 loss: 5.0437 (5.0440) grad_norm: 1.3352 (1.3427) time: 0.6532 [2021-03-26 01:38:47 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 30/1251] eta: 0:15:26 lr: 0.000751 loss: 4.9546 (4.9823) grad_norm: 1.4404 (1.4240) time: 0.6379 [2021-03-26 01:38:53 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 40/1251] eta: 0:14:42 lr: 0.000752 loss: 4.9243 (4.9544) grad_norm: 1.4459 (1.4269) time: 0.6341 [2021-03-26 01:39:00 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 50/1251] eta: 0:14:15 lr: 0.000752 loss: 4.9272 (4.9772) grad_norm: 1.4727 (1.4804) time: 0.6404 [2021-03-26 01:39:06 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 60/1251] eta: 0:13:52 lr: 0.000753 loss: 4.8787 (4.9084) grad_norm: 1.5661 (1.5156) time: 0.6381 [2021-03-26 01:39:12 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 70/1251] eta: 0:13:35 lr: 0.000753 loss: 4.7466 (4.8690) grad_norm: 1.5791 (1.5454) time: 0.6340 [2021-03-26 01:39:19 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 80/1251] eta: 0:13:20 lr: 0.000753 loss: 4.8743 (4.8548) grad_norm: 1.4351 (1.5278) time: 0.6370 [2021-03-26 01:39:25 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 90/1251] eta: 0:13:09 lr: 0.000754 loss: 4.6779 (4.8368) grad_norm: 1.4090 (1.5194) time: 0.6426 [2021-03-26 01:39:32 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 100/1251] eta: 0:12:57 lr: 0.000754 loss: 4.7973 (4.8556) grad_norm: 1.3586 (1.4931) time: 0.6410 [2021-03-26 01:39:38 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 110/1251] eta: 0:12:46 lr: 0.000755 loss: 4.9601 (4.8497) grad_norm: 1.2621 (1.4800) time: 0.6350 [2021-03-26 01:39:44 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 120/1251] eta: 0:12:35 lr: 0.000755 loss: 5.0137 (4.8581) grad_norm: 1.3428 (1.4773) time: 0.6324 [2021-03-26 01:39:51 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 130/1251] eta: 0:12:26 lr: 0.000755 loss: 5.0580 (4.8777) grad_norm: 1.4041 (1.4844) time: 0.6335 [2021-03-26 01:39:57 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 140/1251] eta: 0:12:16 lr: 0.000756 loss: 5.0366 (4.8828) grad_norm: 1.4998 (1.4835) time: 0.6309 [2021-03-26 01:40:03 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 150/1251] eta: 0:12:07 lr: 0.000756 loss: 4.7037 (4.8657) grad_norm: 1.5038 (1.4845) time: 0.6268 [2021-03-26 01:40:09 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 160/1251] eta: 0:11:58 lr: 0.000757 loss: 4.6305 (4.8717) grad_norm: 1.5038 (1.4862) time: 0.6313 [2021-03-26 01:40:16 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 170/1251] eta: 0:11:51 lr: 0.000757 loss: 5.0170 (4.8653) grad_norm: 1.4687 (1.4880) time: 0.6357 [2021-03-26 01:40:22 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 180/1251] eta: 0:11:42 lr: 0.000757 loss: 4.7208 (4.8507) grad_norm: 1.4658 (1.4909) time: 0.6343 [2021-03-26 01:40:29 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 190/1251] eta: 0:11:35 lr: 0.000758 loss: 4.6444 (4.8334) grad_norm: 1.5660 (1.4932) time: 0.6359 [2021-03-26 01:40:35 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 200/1251] eta: 0:11:27 lr: 0.000758 loss: 4.9401 (4.8412) grad_norm: 1.4467 (1.4883) time: 0.6372 [2021-03-26 01:40:41 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 210/1251] eta: 0:11:20 lr: 0.000759 loss: 5.0174 (4.8549) grad_norm: 1.3333 (1.4811) time: 0.6365 [2021-03-26 01:40:48 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 220/1251] eta: 0:11:12 lr: 0.000759 loss: 4.9759 (4.8497) grad_norm: 1.3597 (1.4782) time: 0.6364 [2021-03-26 01:40:54 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 230/1251] eta: 0:11:05 lr: 0.000759 loss: 4.7433 (4.8460) grad_norm: 1.4417 (1.4787) time: 0.6343 [2021-03-26 01:41:00 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 240/1251] eta: 0:10:58 lr: 0.000760 loss: 4.8693 (4.8443) grad_norm: 1.4208 (1.4778) time: 0.6315 [2021-03-26 01:41:07 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 250/1251] eta: 0:10:51 lr: 0.000760 loss: 4.9713 (4.8511) grad_norm: 1.4265 (1.4803) time: 0.6377 [2021-03-26 01:41:13 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 260/1251] eta: 0:10:44 lr: 0.000761 loss: 5.0275 (4.8497) grad_norm: 1.4711 (1.4826) time: 0.6420 [2021-03-26 01:41:20 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 270/1251] eta: 0:10:37 lr: 0.000761 loss: 4.7654 (4.8452) grad_norm: 1.4861 (1.4828) time: 0.6399 [2021-03-26 01:41:26 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 280/1251] eta: 0:10:30 lr: 0.000761 loss: 4.6306 (4.8382) grad_norm: 1.4660 (1.4807) time: 0.6404 [2021-03-26 01:41:32 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 290/1251] eta: 0:10:23 lr: 0.000762 loss: 4.8456 (4.8394) grad_norm: 1.4007 (1.4784) time: 0.6360 [2021-03-26 01:41:39 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 300/1251] eta: 0:10:16 lr: 0.000762 loss: 4.8421 (4.8430) grad_norm: 1.4036 (1.4776) time: 0.6323 [2021-03-26 01:41:45 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 310/1251] eta: 0:10:09 lr: 0.000763 loss: 4.7787 (4.8467) grad_norm: 1.3818 (1.4753) time: 0.6297 [2021-03-26 01:41:51 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 320/1251] eta: 0:10:02 lr: 0.000763 loss: 4.9736 (4.8517) grad_norm: 1.3330 (1.4786) time: 0.6284 [2021-03-26 01:41:57 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 330/1251] eta: 0:09:55 lr: 0.000763 loss: 4.9713 (4.8483) grad_norm: 1.3222 (1.4731) time: 0.6301 [2021-03-26 01:42:04 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 340/1251] eta: 0:09:48 lr: 0.000764 loss: 4.9084 (4.8561) grad_norm: 1.2875 (1.4733) time: 0.6316 [2021-03-26 01:42:10 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 350/1251] eta: 0:09:42 lr: 0.000764 loss: 5.0601 (4.8581) grad_norm: 1.4109 (1.4801) time: 0.6342 [2021-03-26 01:42:17 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 360/1251] eta: 0:09:35 lr: 0.000765 loss: 4.8383 (4.8582) grad_norm: 1.5421 (1.4811) time: 0.6380 [2021-03-26 01:42:23 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 370/1251] eta: 0:09:28 lr: 0.000765 loss: 4.6200 (4.8474) grad_norm: 1.5420 (1.4893) time: 0.6392 [2021-03-26 01:42:29 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 380/1251] eta: 0:09:22 lr: 0.000765 loss: 4.7109 (4.8474) grad_norm: 1.3749 (1.4857) time: 0.6354 [2021-03-26 01:42:36 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 390/1251] eta: 0:09:15 lr: 0.000766 loss: 4.9750 (4.8443) grad_norm: 1.3030 (1.4845) time: 0.6297 [2021-03-26 01:42:42 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 400/1251] eta: 0:09:08 lr: 0.000766 loss: 4.9083 (4.8404) grad_norm: 1.3245 (1.4806) time: 0.6283 [2021-03-26 01:42:48 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 410/1251] eta: 0:09:01 lr: 0.000767 loss: 5.2740 (4.8507) grad_norm: 1.3203 (1.4755) time: 0.6366 [2021-03-26 01:42:55 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 420/1251] eta: 0:08:55 lr: 0.000767 loss: 5.2564 (4.8517) grad_norm: 1.2834 (1.4727) time: 0.6410 [2021-03-26 01:43:01 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 430/1251] eta: 0:08:48 lr: 0.000767 loss: 5.1205 (4.8526) grad_norm: 1.2983 (1.4697) time: 0.6360 [2021-03-26 01:43:07 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 440/1251] eta: 0:08:42 lr: 0.000768 loss: 4.9390 (4.8528) grad_norm: 1.2983 (1.4663) time: 0.6371 [2021-03-26 01:43:14 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 450/1251] eta: 0:08:35 lr: 0.000768 loss: 5.0824 (4.8618) grad_norm: 1.4051 (1.4675) time: 0.6363 [2021-03-26 01:43:20 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 460/1251] eta: 0:08:29 lr: 0.000769 loss: 5.1822 (4.8677) grad_norm: 1.4051 (1.4665) time: 0.6338 [2021-03-26 01:43:26 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 470/1251] eta: 0:08:22 lr: 0.000769 loss: 5.1822 (4.8719) grad_norm: 1.3979 (1.4674) time: 0.6386 [2021-03-26 01:43:33 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 480/1251] eta: 0:08:15 lr: 0.000769 loss: 4.8995 (4.8652) grad_norm: 1.3893 (1.4650) time: 0.6359 [2021-03-26 01:43:39 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 490/1251] eta: 0:08:09 lr: 0.000770 loss: 4.8699 (4.8623) grad_norm: 1.3893 (1.4641) time: 0.6342 [2021-03-26 01:43:45 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 500/1251] eta: 0:08:02 lr: 0.000770 loss: 4.5378 (4.8597) grad_norm: 1.4766 (1.4655) time: 0.6337 [2021-03-26 01:43:52 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 510/1251] eta: 0:07:56 lr: 0.000771 loss: 4.5378 (4.8557) grad_norm: 1.5284 (1.4712) time: 0.6263 [2021-03-26 01:43:58 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 520/1251] eta: 0:07:49 lr: 0.000771 loss: 4.6591 (4.8516) grad_norm: 1.2960 (1.4686) time: 0.6322 [2021-03-26 01:44:05 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 530/1251] eta: 0:07:43 lr: 0.000771 loss: 4.7390 (4.8509) grad_norm: 1.2719 (1.4663) time: 0.6405 [2021-03-26 01:44:11 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 540/1251] eta: 0:07:36 lr: 0.000772 loss: 4.7390 (4.8505) grad_norm: 1.2831 (1.4632) time: 0.6392 [2021-03-26 01:44:17 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 550/1251] eta: 0:07:30 lr: 0.000772 loss: 4.8123 (4.8506) grad_norm: 1.2547 (1.4602) time: 0.6435 [2021-03-26 01:44:24 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 560/1251] eta: 0:07:23 lr: 0.000773 loss: 4.8398 (4.8488) grad_norm: 1.3020 (1.4590) time: 0.6452 [2021-03-26 01:44:30 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 570/1251] eta: 0:07:17 lr: 0.000773 loss: 4.9202 (4.8495) grad_norm: 1.3567 (1.4573) time: 0.6382 [2021-03-26 01:44:37 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 580/1251] eta: 0:07:10 lr: 0.000773 loss: 5.1427 (4.8534) grad_norm: 1.2965 (1.4538) time: 0.6372 [2021-03-26 01:44:43 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 590/1251] eta: 0:07:04 lr: 0.000774 loss: 5.1618 (4.8519) grad_norm: 1.2404 (1.4534) time: 0.6406 [2021-03-26 01:44:49 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 600/1251] eta: 0:06:58 lr: 0.000774 loss: 4.9826 (4.8549) grad_norm: 1.3331 (1.4538) time: 0.6419 [2021-03-26 01:44:56 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 610/1251] eta: 0:06:51 lr: 0.000775 loss: 4.7757 (4.8520) grad_norm: 1.3431 (1.4526) time: 0.6408 [2021-03-26 01:45:02 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 620/1251] eta: 0:06:45 lr: 0.000775 loss: 4.6408 (4.8496) grad_norm: 1.3538 (1.4524) time: 0.6378 [2021-03-26 01:45:08 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 630/1251] eta: 0:06:38 lr: 0.000775 loss: 4.6967 (4.8452) grad_norm: 1.3538 (1.4513) time: 0.6322 [2021-03-26 01:45:15 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 640/1251] eta: 0:06:32 lr: 0.000776 loss: 4.8815 (4.8488) grad_norm: 1.3042 (1.4492) time: 0.6296 [2021-03-26 01:45:21 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 650/1251] eta: 0:06:25 lr: 0.000776 loss: 5.0755 (4.8520) grad_norm: 1.2046 (1.4463) time: 0.6386 [2021-03-26 01:45:28 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 660/1251] eta: 0:06:19 lr: 0.000777 loss: 5.2936 (4.8584) grad_norm: 1.3433 (1.4455) time: 0.6424 [2021-03-26 01:45:34 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 670/1251] eta: 0:06:12 lr: 0.000777 loss: 5.0747 (4.8577) grad_norm: 1.3433 (1.4438) time: 0.6320 [2021-03-26 01:45:40 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 680/1251] eta: 0:06:06 lr: 0.000777 loss: 4.9849 (4.8588) grad_norm: 1.3386 (1.4437) time: 0.6294 [2021-03-26 01:45:47 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 690/1251] eta: 0:05:59 lr: 0.000778 loss: 4.9947 (4.8615) grad_norm: 1.3774 (1.4439) time: 0.6317 [2021-03-26 01:45:53 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 700/1251] eta: 0:05:53 lr: 0.000778 loss: 4.9947 (4.8624) grad_norm: 1.4385 (1.4455) time: 0.6325 [2021-03-26 01:45:59 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 710/1251] eta: 0:05:46 lr: 0.000779 loss: 5.0167 (4.8628) grad_norm: 1.5715 (1.4508) time: 0.6372 [2021-03-26 01:46:06 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 720/1251] eta: 0:05:40 lr: 0.000779 loss: 5.0943 (4.8650) grad_norm: 1.5139 (1.4510) time: 0.6386 [2021-03-26 01:46:12 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 730/1251] eta: 0:05:33 lr: 0.000779 loss: 5.0943 (4.8641) grad_norm: 1.3880 (1.4496) time: 0.6378 [2021-03-26 01:46:18 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 740/1251] eta: 0:05:27 lr: 0.000780 loss: 4.7270 (4.8617) grad_norm: 1.2004 (1.4476) time: 0.6386 [2021-03-26 01:46:25 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 750/1251] eta: 0:05:21 lr: 0.000780 loss: 4.7270 (4.8601) grad_norm: 1.3808 (1.4491) time: 0.6422 [2021-03-26 01:46:31 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 760/1251] eta: 0:05:14 lr: 0.000781 loss: 4.9475 (4.8598) grad_norm: 1.4435 (1.4485) time: 0.6410 [2021-03-26 01:46:38 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 770/1251] eta: 0:05:08 lr: 0.000781 loss: 4.9850 (4.8615) grad_norm: 1.2390 (1.4478) time: 0.6342 [2021-03-26 01:46:44 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 780/1251] eta: 0:05:01 lr: 0.000781 loss: 4.9850 (4.8633) grad_norm: 1.1949 (1.4455) time: 0.6309 [2021-03-26 01:46:50 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 790/1251] eta: 0:04:55 lr: 0.000782 loss: 4.9309 (4.8598) grad_norm: 1.2372 (1.4447) time: 0.6283 [2021-03-26 01:46:56 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 800/1251] eta: 0:04:48 lr: 0.000782 loss: 4.9765 (4.8625) grad_norm: 1.4539 (1.4479) time: 0.6297 [2021-03-26 01:47:03 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 810/1251] eta: 0:04:42 lr: 0.000783 loss: 5.0937 (4.8635) grad_norm: 1.4475 (1.4460) time: 0.6321 [2021-03-26 01:47:09 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 820/1251] eta: 0:04:35 lr: 0.000783 loss: 5.0527 (4.8615) grad_norm: 1.2567 (1.4440) time: 0.6362 [2021-03-26 01:47:16 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 830/1251] eta: 0:04:29 lr: 0.000783 loss: 4.8752 (4.8637) grad_norm: 1.2078 (1.4420) time: 0.6393 [2021-03-26 01:47:22 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 840/1251] eta: 0:04:23 lr: 0.000784 loss: 4.9789 (4.8640) grad_norm: 1.1821 (1.4414) time: 0.6419 [2021-03-26 01:47:28 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 850/1251] eta: 0:04:16 lr: 0.000784 loss: 4.7844 (4.8622) grad_norm: 1.2849 (1.4411) time: 0.6410 [2021-03-26 01:47:35 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 860/1251] eta: 0:04:10 lr: 0.000785 loss: 4.7844 (4.8654) grad_norm: 1.3417 (1.4408) time: 0.6397 [2021-03-26 01:47:41 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 870/1251] eta: 0:04:03 lr: 0.000785 loss: 5.0232 (4.8641) grad_norm: 1.2665 (1.4396) time: 0.6414 [2021-03-26 01:47:48 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 880/1251] eta: 0:03:57 lr: 0.000785 loss: 4.8370 (4.8631) grad_norm: 1.3825 (1.4389) time: 0.6394 [2021-03-26 01:47:54 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 890/1251] eta: 0:03:51 lr: 0.000786 loss: 4.6465 (4.8598) grad_norm: 1.3942 (1.4391) time: 0.6318 [2021-03-26 01:48:00 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 900/1251] eta: 0:03:44 lr: 0.000786 loss: 4.6706 (4.8591) grad_norm: 1.4726 (1.4404) time: 0.6312 [2021-03-26 01:48:06 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 910/1251] eta: 0:03:38 lr: 0.000787 loss: 4.8810 (4.8583) grad_norm: 1.2701 (1.4392) time: 0.6302 [2021-03-26 01:48:13 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 920/1251] eta: 0:03:31 lr: 0.000787 loss: 4.8810 (4.8580) grad_norm: 1.3383 (1.4406) time: 0.6334 [2021-03-26 01:48:19 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 930/1251] eta: 0:03:25 lr: 0.000787 loss: 4.9850 (4.8569) grad_norm: 1.3820 (1.4393) time: 0.6376 [2021-03-26 01:48:26 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 940/1251] eta: 0:03:19 lr: 0.000788 loss: 4.9850 (4.8578) grad_norm: 1.3865 (1.4401) time: 0.6411 [2021-03-26 01:48:32 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 950/1251] eta: 0:03:12 lr: 0.000788 loss: 4.7299 (4.8544) grad_norm: 1.4195 (1.4400) time: 0.6435 [2021-03-26 01:48:38 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 960/1251] eta: 0:03:06 lr: 0.000789 loss: 4.8113 (4.8560) grad_norm: 1.3498 (1.4385) time: 0.6310 [2021-03-26 01:48:45 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 970/1251] eta: 0:02:59 lr: 0.000789 loss: 4.9920 (4.8565) grad_norm: 1.2559 (1.4360) time: 0.6292 [2021-03-26 01:48:51 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 980/1251] eta: 0:02:53 lr: 0.000789 loss: 4.9457 (4.8562) grad_norm: 1.3304 (1.4373) time: 0.6327 [2021-03-26 01:48:57 swin_base_patch4_window7_224] INFO: Epoch: [15] [ 990/1251] eta: 0:02:46 lr: 0.000790 loss: 5.0113 (4.8557) grad_norm: 1.4399 (1.4418) time: 0.6351 [2021-03-26 01:49:04 swin_base_patch4_window7_224] INFO: Epoch: [15] [1000/1251] eta: 0:02:40 lr: 0.000790 loss: 5.1062 (4.8581) grad_norm: 1.3907 (1.4410) time: 0.6390 [2021-03-26 01:49:10 swin_base_patch4_window7_224] INFO: Epoch: [15] [1010/1251] eta: 0:02:34 lr: 0.000791 loss: 5.1133 (4.8577) grad_norm: 1.3907 (1.4422) time: 0.6353 [2021-03-26 01:49:16 swin_base_patch4_window7_224] INFO: Epoch: [15] [1020/1251] eta: 0:02:27 lr: 0.000791 loss: 4.7554 (4.8565) grad_norm: 1.4552 (1.4424) time: 0.6306 [2021-03-26 01:49:23 swin_base_patch4_window7_224] INFO: Epoch: [15] [1030/1251] eta: 0:02:21 lr: 0.000791 loss: 4.6888 (4.8555) grad_norm: 1.4816 (1.4437) time: 0.6333 [2021-03-26 01:49:29 swin_base_patch4_window7_224] INFO: Epoch: [15] [1040/1251] eta: 0:02:14 lr: 0.000792 loss: 4.8806 (4.8552) grad_norm: 1.4473 (1.4432) time: 0.6353 [2021-03-26 01:49:35 swin_base_patch4_window7_224] INFO: Epoch: [15] [1050/1251] eta: 0:02:08 lr: 0.000792 loss: 4.4881 (4.8508) grad_norm: 1.3427 (1.4433) time: 0.6329 [2021-03-26 01:49:42 swin_base_patch4_window7_224] INFO: Epoch: [15] [1060/1251] eta: 0:02:02 lr: 0.000793 loss: 4.4881 (4.8493) grad_norm: 1.2695 (1.4416) time: 0.6303 [2021-03-26 01:49:48 swin_base_patch4_window7_224] INFO: Epoch: [15] [1070/1251] eta: 0:01:55 lr: 0.000793 loss: 4.9241 (4.8493) grad_norm: 1.2670 (1.4399) time: 0.6313 [2021-03-26 01:49:54 swin_base_patch4_window7_224] INFO: Epoch: [15] [1080/1251] eta: 0:01:49 lr: 0.000793 loss: 4.9460 (4.8499) grad_norm: 1.3131 (1.4404) time: 0.6334 [2021-03-26 01:50:01 swin_base_patch4_window7_224] INFO: Epoch: [15] [1090/1251] eta: 0:01:42 lr: 0.000794 loss: 4.8529 (4.8468) grad_norm: 1.4358 (1.4410) time: 0.6338 [2021-03-26 01:50:07 swin_base_patch4_window7_224] INFO: Epoch: [15] [1100/1251] eta: 0:01:36 lr: 0.000794 loss: 4.8450 (4.8482) grad_norm: 1.4112 (1.4415) time: 0.6309 [2021-03-26 01:50:13 swin_base_patch4_window7_224] INFO: Epoch: [15] [1110/1251] eta: 0:01:30 lr: 0.000795 loss: 4.8596 (4.8473) grad_norm: 1.3213 (1.4406) time: 0.6327 [2021-03-26 01:50:20 swin_base_patch4_window7_224] INFO: Epoch: [15] [1120/1251] eta: 0:01:23 lr: 0.000795 loss: 4.9204 (4.8484) grad_norm: 1.4808 (1.4428) time: 0.6355 [2021-03-26 01:50:26 swin_base_patch4_window7_224] INFO: Epoch: [15] [1130/1251] eta: 0:01:17 lr: 0.000795 loss: 5.1472 (4.8497) grad_norm: 1.4975 (1.4425) time: 0.6323 [2021-03-26 01:50:32 swin_base_patch4_window7_224] INFO: Epoch: [15] [1140/1251] eta: 0:01:10 lr: 0.000796 loss: 5.1472 (4.8495) grad_norm: 1.2931 (1.4419) time: 0.6309 [2021-03-26 01:50:39 swin_base_patch4_window7_224] INFO: Epoch: [15] [1150/1251] eta: 0:01:04 lr: 0.000796 loss: 4.9676 (4.8498) grad_norm: 1.3508 (1.4428) time: 0.6359 [2021-03-26 01:50:45 swin_base_patch4_window7_224] INFO: Epoch: [15] [1160/1251] eta: 0:00:58 lr: 0.000797 loss: 4.9326 (4.8500) grad_norm: 1.4001 (1.4424) time: 0.6403 [2021-03-26 01:50:52 swin_base_patch4_window7_224] INFO: Epoch: [15] [1170/1251] eta: 0:00:51 lr: 0.000797 loss: 4.9326 (4.8504) grad_norm: 1.4001 (1.4420) time: 0.6381 [2021-03-26 01:50:58 swin_base_patch4_window7_224] INFO: Epoch: [15] [1180/1251] eta: 0:00:45 lr: 0.000797 loss: 4.8079 (4.8487) grad_norm: 1.3581 (1.4408) time: 0.6311 [2021-03-26 01:51:04 swin_base_patch4_window7_224] INFO: Epoch: [15] [1190/1251] eta: 0:00:38 lr: 0.000798 loss: 4.8603 (4.8493) grad_norm: 1.2675 (1.4406) time: 0.6297 [2021-03-26 01:51:10 swin_base_patch4_window7_224] INFO: Epoch: [15] [1200/1251] eta: 0:00:32 lr: 0.000798 loss: 5.0117 (4.8484) grad_norm: 1.3931 (1.4413) time: 0.6332 [2021-03-26 01:51:17 swin_base_patch4_window7_224] INFO: Epoch: [15] [1210/1251] eta: 0:00:26 lr: 0.000799 loss: 4.7232 (4.8470) grad_norm: 1.4423 (1.4412) time: 0.6317 [2021-03-26 01:51:23 swin_base_patch4_window7_224] INFO: Epoch: [15] [1220/1251] eta: 0:00:19 lr: 0.000799 loss: 4.6984 (4.8459) grad_norm: 1.3418 (1.4398) time: 0.6347 [2021-03-26 01:51:30 swin_base_patch4_window7_224] INFO: Epoch: [15] [1230/1251] eta: 0:00:13 lr: 0.000799 loss: 4.7251 (4.8447) grad_norm: 1.2144 (1.4380) time: 0.6384 [2021-03-26 01:51:36 swin_base_patch4_window7_224] INFO: Epoch: [15] [1240/1251] eta: 0:00:07 lr: 0.000800 loss: 4.7287 (4.8447) grad_norm: 1.1985 (1.4364) time: 0.6389 [2021-03-26 01:51:42 swin_base_patch4_window7_224] INFO: Epoch: [15] [1250/1251] eta: 0:00:00 lr: 0.000800 loss: 4.7676 (4.8440) grad_norm: 1.3354 (1.4377) time: 0.6327 [2021-03-26 01:52:42 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:09 loss: 2.3519 (2.3519) acc1: 42.1875 (42.1875) acc5: 78.1250 (78.1250) [2021-03-26 01:52:43 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 2.2118 (2.1741) acc1: 50.0000 (52.2727) acc5: 76.5625 (78.1250) [2021-03-26 01:52:44 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 2.1667 (2.1718) acc1: 50.0000 (52.6042) acc5: 76.5625 (77.4554) [2021-03-26 01:52:46 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 2.1650 (2.1840) acc1: 51.5625 (52.2177) acc5: 76.5625 (76.9153) [2021-03-26 01:52:47 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 2.1634 (2.1713) acc1: 53.1250 (52.6677) acc5: 76.5625 (77.0579) [2021-03-26 01:52:48 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.1839 (2.1734) acc1: 50.0000 (52.0640) acc5: 76.5625 (76.8000) [2021-03-26 01:52:50 swin_base_patch4_window7_224] INFO: * Acc@1 51.900 Acc@5 77.428 loss 2.170 [2021-03-26 01:52:50 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 51.9% [2021-03-26 01:52:50 swin_base_patch4_window7_224] INFO: Max accuracy: 51.90% [2021-03-26 01:52:54 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 0/1251] eta: 1:30:31 lr: 0.000800 loss: 4.9471 (4.9471) grad_norm: 1.1957 (1.1957) time: 4.3419 [2021-03-26 01:53:01 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 10/1251] eta: 0:20:11 lr: 0.000801 loss: 4.9609 (4.7837) grad_norm: 1.3315 (1.3637) time: 0.9764 [2021-03-26 01:53:07 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 20/1251] eta: 0:16:34 lr: 0.000801 loss: 5.0102 (4.9046) grad_norm: 1.3472 (1.4899) time: 0.6310 [2021-03-26 01:53:13 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 30/1251] eta: 0:15:17 lr: 0.000801 loss: 5.1386 (4.9175) grad_norm: 1.4463 (1.5425) time: 0.6281 [2021-03-26 01:53:19 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 40/1251] eta: 0:14:35 lr: 0.000802 loss: 4.9685 (4.9137) grad_norm: 1.3262 (1.4767) time: 0.6334 [2021-03-26 01:53:26 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 50/1251] eta: 0:14:08 lr: 0.000802 loss: 4.8617 (4.8813) grad_norm: 1.3240 (1.4676) time: 0.6359 [2021-03-26 01:53:32 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 60/1251] eta: 0:13:48 lr: 0.000803 loss: 4.8339 (4.8989) grad_norm: 1.3122 (1.4510) time: 0.6391 [2021-03-26 01:53:39 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 70/1251] eta: 0:13:31 lr: 0.000803 loss: 4.8293 (4.8822) grad_norm: 1.2174 (1.4222) time: 0.6383 [2021-03-26 01:53:45 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 80/1251] eta: 0:13:15 lr: 0.000803 loss: 4.8293 (4.8887) grad_norm: 1.3114 (1.4131) time: 0.6312 [2021-03-26 01:53:51 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 90/1251] eta: 0:13:02 lr: 0.000804 loss: 4.8312 (4.8809) grad_norm: 1.2296 (1.3902) time: 0.6283 [2021-03-26 01:53:57 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 100/1251] eta: 0:12:50 lr: 0.000804 loss: 4.7547 (4.8589) grad_norm: 1.2243 (1.3871) time: 0.6275 [2021-03-26 01:54:04 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 110/1251] eta: 0:12:41 lr: 0.000805 loss: 4.7553 (4.8508) grad_norm: 1.3498 (1.4052) time: 0.6361 [2021-03-26 01:54:10 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 120/1251] eta: 0:12:31 lr: 0.000805 loss: 4.7553 (4.8355) grad_norm: 1.4293 (1.4030) time: 0.6407 [2021-03-26 01:54:17 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 130/1251] eta: 0:12:23 lr: 0.000805 loss: 4.6313 (4.8294) grad_norm: 1.3528 (1.4060) time: 0.6411 [2021-03-26 01:54:23 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 140/1251] eta: 0:12:15 lr: 0.000806 loss: 4.8622 (4.8332) grad_norm: 1.3649 (1.4024) time: 0.6495 [2021-03-26 01:54:30 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 150/1251] eta: 0:12:07 lr: 0.000806 loss: 4.8168 (4.8225) grad_norm: 1.3649 (1.4161) time: 0.6421 [2021-03-26 01:54:36 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 160/1251] eta: 0:11:59 lr: 0.000807 loss: 4.7836 (4.8185) grad_norm: 1.4687 (1.4238) time: 0.6366 [2021-03-26 01:54:42 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 170/1251] eta: 0:11:51 lr: 0.000807 loss: 4.4847 (4.8033) grad_norm: 1.3987 (1.4176) time: 0.6380 [2021-03-26 01:54:49 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 180/1251] eta: 0:11:43 lr: 0.000807 loss: 4.6054 (4.8000) grad_norm: 1.3122 (1.4168) time: 0.6418 [2021-03-26 01:54:55 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 190/1251] eta: 0:11:36 lr: 0.000808 loss: 4.7302 (4.7971) grad_norm: 1.3451 (1.4151) time: 0.6475 [2021-03-26 01:55:02 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 200/1251] eta: 0:11:29 lr: 0.000808 loss: 4.7728 (4.7955) grad_norm: 1.2322 (1.4034) time: 0.6414 [2021-03-26 01:55:08 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 210/1251] eta: 0:11:21 lr: 0.000809 loss: 4.9249 (4.8011) grad_norm: 1.2161 (1.4067) time: 0.6333 [2021-03-26 01:55:14 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 220/1251] eta: 0:11:13 lr: 0.000809 loss: 4.9935 (4.8013) grad_norm: 1.4025 (1.4137) time: 0.6322 [2021-03-26 01:55:21 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 230/1251] eta: 0:11:06 lr: 0.000809 loss: 4.9925 (4.8052) grad_norm: 1.3854 (1.4126) time: 0.6303 [2021-03-26 01:55:27 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 240/1251] eta: 0:10:58 lr: 0.000810 loss: 4.8814 (4.7903) grad_norm: 1.3546 (1.4111) time: 0.6310 [2021-03-26 01:55:33 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 250/1251] eta: 0:10:51 lr: 0.000810 loss: 4.4665 (4.7890) grad_norm: 1.3387 (1.4131) time: 0.6333 [2021-03-26 01:55:40 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 260/1251] eta: 0:10:44 lr: 0.000811 loss: 4.8227 (4.7900) grad_norm: 1.4011 (1.4134) time: 0.6325 [2021-03-26 01:55:46 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 270/1251] eta: 0:10:36 lr: 0.000811 loss: 5.0002 (4.7980) grad_norm: 1.4109 (1.4133) time: 0.6281 [2021-03-26 01:55:52 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 280/1251] eta: 0:10:30 lr: 0.000811 loss: 5.1316 (4.8064) grad_norm: 1.4239 (1.4202) time: 0.6310 [2021-03-26 01:55:59 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 290/1251] eta: 0:10:23 lr: 0.000812 loss: 4.6845 (4.7911) grad_norm: 1.4031 (1.4130) time: 0.6364 [2021-03-26 01:56:05 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 300/1251] eta: 0:10:16 lr: 0.000812 loss: 4.7685 (4.7970) grad_norm: 1.2365 (1.4100) time: 0.6390 [2021-03-26 01:56:11 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 310/1251] eta: 0:10:09 lr: 0.000813 loss: 4.9487 (4.7940) grad_norm: 1.2925 (1.4091) time: 0.6387 [2021-03-26 01:56:18 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 320/1251] eta: 0:10:02 lr: 0.000813 loss: 4.9506 (4.8036) grad_norm: 1.3826 (1.4085) time: 0.6383 [2021-03-26 01:56:24 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 330/1251] eta: 0:09:56 lr: 0.000813 loss: 4.7890 (4.7906) grad_norm: 1.3719 (1.4048) time: 0.6390 [2021-03-26 01:56:30 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 340/1251] eta: 0:09:49 lr: 0.000814 loss: 4.5207 (4.7889) grad_norm: 1.3629 (1.4019) time: 0.6345 [2021-03-26 01:56:37 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 350/1251] eta: 0:09:42 lr: 0.000814 loss: 4.5618 (4.7893) grad_norm: 1.2861 (1.4012) time: 0.6295 [2021-03-26 01:56:43 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 360/1251] eta: 0:09:35 lr: 0.000815 loss: 4.8110 (4.7889) grad_norm: 1.2861 (1.4015) time: 0.6315 [2021-03-26 01:56:49 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 370/1251] eta: 0:09:28 lr: 0.000815 loss: 4.8628 (4.7854) grad_norm: 1.2198 (1.3963) time: 0.6339 [2021-03-26 01:56:56 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 380/1251] eta: 0:09:21 lr: 0.000815 loss: 4.7901 (4.7887) grad_norm: 1.2903 (1.3958) time: 0.6315 [2021-03-26 01:57:02 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 390/1251] eta: 0:09:15 lr: 0.000816 loss: 4.7630 (4.7855) grad_norm: 1.2920 (1.3910) time: 0.6357 [2021-03-26 01:57:08 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 400/1251] eta: 0:09:08 lr: 0.000816 loss: 4.6518 (4.7854) grad_norm: 1.2743 (1.3946) time: 0.6340 [2021-03-26 01:57:15 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 410/1251] eta: 0:09:01 lr: 0.000817 loss: 5.1180 (4.7948) grad_norm: 1.3439 (1.3943) time: 0.6305 [2021-03-26 01:57:21 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 420/1251] eta: 0:08:55 lr: 0.000817 loss: 5.0323 (4.7963) grad_norm: 1.2884 (1.3934) time: 0.6353 [2021-03-26 01:57:27 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 430/1251] eta: 0:08:48 lr: 0.000817 loss: 4.7252 (4.7920) grad_norm: 1.3033 (1.3934) time: 0.6304 [2021-03-26 01:57:34 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 440/1251] eta: 0:08:41 lr: 0.000818 loss: 4.7074 (4.7928) grad_norm: 1.3033 (1.3899) time: 0.6296 [2021-03-26 01:57:40 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 450/1251] eta: 0:08:35 lr: 0.000818 loss: 4.7074 (4.7933) grad_norm: 1.3638 (1.3933) time: 0.6288 [2021-03-26 01:57:46 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 460/1251] eta: 0:08:28 lr: 0.000819 loss: 4.7253 (4.7939) grad_norm: 1.3952 (1.3913) time: 0.6261 [2021-03-26 01:57:53 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 470/1251] eta: 0:08:21 lr: 0.000819 loss: 4.9580 (4.7970) grad_norm: 1.2301 (1.3879) time: 0.6343 [2021-03-26 01:57:59 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 480/1251] eta: 0:08:15 lr: 0.000819 loss: 4.8916 (4.7959) grad_norm: 1.2301 (1.3862) time: 0.6357 [2021-03-26 01:58:05 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 490/1251] eta: 0:08:08 lr: 0.000820 loss: 4.7283 (4.7952) grad_norm: 1.2921 (1.3843) time: 0.6364 [2021-03-26 01:58:12 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 500/1251] eta: 0:08:02 lr: 0.000820 loss: 4.8665 (4.7968) grad_norm: 1.1739 (1.3800) time: 0.6325 [2021-03-26 01:58:18 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 510/1251] eta: 0:07:55 lr: 0.000821 loss: 4.9065 (4.7967) grad_norm: 1.3298 (1.3816) time: 0.6264 [2021-03-26 01:58:24 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 520/1251] eta: 0:07:49 lr: 0.000821 loss: 4.9065 (4.7978) grad_norm: 1.3438 (1.3796) time: 0.6308 [2021-03-26 01:58:31 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 530/1251] eta: 0:07:42 lr: 0.000821 loss: 4.9926 (4.8012) grad_norm: 1.2331 (1.3792) time: 0.6321 [2021-03-26 01:58:37 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 540/1251] eta: 0:07:35 lr: 0.000822 loss: 4.8433 (4.7959) grad_norm: 1.4071 (1.3825) time: 0.6288 [2021-03-26 01:58:43 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 550/1251] eta: 0:07:29 lr: 0.000822 loss: 4.8353 (4.7991) grad_norm: 1.2874 (1.3805) time: 0.6318 [2021-03-26 01:58:50 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 560/1251] eta: 0:07:23 lr: 0.000823 loss: 5.0375 (4.8006) grad_norm: 1.2642 (1.3802) time: 0.6404 [2021-03-26 01:58:56 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 570/1251] eta: 0:07:16 lr: 0.000823 loss: 5.0375 (4.8054) grad_norm: 1.2642 (1.3775) time: 0.6352 [2021-03-26 01:59:02 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 580/1251] eta: 0:07:10 lr: 0.000823 loss: 4.9399 (4.8028) grad_norm: 1.2687 (1.3762) time: 0.6327 [2021-03-26 01:59:09 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 590/1251] eta: 0:07:03 lr: 0.000824 loss: 4.7976 (4.8031) grad_norm: 1.3346 (1.3771) time: 0.6368 [2021-03-26 01:59:15 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 600/1251] eta: 0:06:57 lr: 0.000824 loss: 5.0783 (4.8124) grad_norm: 1.4221 (1.3773) time: 0.6336 [2021-03-26 01:59:21 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 610/1251] eta: 0:06:50 lr: 0.000825 loss: 5.1019 (4.8114) grad_norm: 1.2955 (1.3757) time: 0.6312 [2021-03-26 01:59:28 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 620/1251] eta: 0:06:44 lr: 0.000825 loss: 4.7075 (4.8087) grad_norm: 1.2464 (1.3752) time: 0.6313 [2021-03-26 01:59:34 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 630/1251] eta: 0:06:37 lr: 0.000825 loss: 4.6895 (4.8081) grad_norm: 1.2464 (1.3737) time: 0.6320 [2021-03-26 01:59:40 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 640/1251] eta: 0:06:31 lr: 0.000826 loss: 5.0907 (4.8106) grad_norm: 1.2987 (1.3755) time: 0.6298 [2021-03-26 01:59:47 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 650/1251] eta: 0:06:24 lr: 0.000826 loss: 4.8241 (4.8086) grad_norm: 1.3573 (1.3743) time: 0.6332 [2021-03-26 01:59:53 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 660/1251] eta: 0:06:18 lr: 0.000827 loss: 4.7557 (4.8098) grad_norm: 1.2153 (1.3736) time: 0.6367 [2021-03-26 01:59:59 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 670/1251] eta: 0:06:11 lr: 0.000827 loss: 4.7014 (4.8096) grad_norm: 1.2645 (1.3724) time: 0.6357 [2021-03-26 02:00:06 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 680/1251] eta: 0:06:05 lr: 0.000827 loss: 4.8057 (4.8098) grad_norm: 1.3618 (1.3734) time: 0.6329 [2021-03-26 02:00:12 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 690/1251] eta: 0:05:58 lr: 0.000828 loss: 4.9716 (4.8084) grad_norm: 1.4723 (1.3736) time: 0.6324 [2021-03-26 02:00:18 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 700/1251] eta: 0:05:52 lr: 0.000828 loss: 4.8659 (4.8079) grad_norm: 1.2804 (1.3725) time: 0.6338 [2021-03-26 02:00:25 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 710/1251] eta: 0:05:45 lr: 0.000829 loss: 4.8659 (4.8074) grad_norm: 1.3343 (1.3736) time: 0.6352 [2021-03-26 02:00:31 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 720/1251] eta: 0:05:39 lr: 0.000829 loss: 4.6311 (4.8029) grad_norm: 1.3978 (1.3762) time: 0.6375 [2021-03-26 02:00:37 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 730/1251] eta: 0:05:33 lr: 0.000829 loss: 4.6311 (4.8033) grad_norm: 1.5215 (1.3787) time: 0.6378 [2021-03-26 02:00:44 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 740/1251] eta: 0:05:26 lr: 0.000830 loss: 4.9471 (4.8040) grad_norm: 1.2707 (1.3758) time: 0.6376 [2021-03-26 02:00:50 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 750/1251] eta: 0:05:20 lr: 0.000830 loss: 4.9337 (4.8030) grad_norm: 1.1911 (1.3746) time: 0.6445 [2021-03-26 02:00:56 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 760/1251] eta: 0:05:13 lr: 0.000831 loss: 4.7310 (4.8024) grad_norm: 1.3158 (1.3748) time: 0.6351 [2021-03-26 02:01:03 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 770/1251] eta: 0:05:07 lr: 0.000831 loss: 5.0106 (4.8063) grad_norm: 1.3293 (1.3755) time: 0.6303 [2021-03-26 02:01:09 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 780/1251] eta: 0:05:01 lr: 0.000831 loss: 4.9597 (4.8022) grad_norm: 1.3293 (1.3748) time: 0.6332 [2021-03-26 02:01:15 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 790/1251] eta: 0:04:54 lr: 0.000832 loss: 4.4546 (4.7993) grad_norm: 1.3308 (1.3760) time: 0.6306 [2021-03-26 02:01:22 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 800/1251] eta: 0:04:48 lr: 0.000832 loss: 4.8536 (4.8001) grad_norm: 1.2988 (1.3750) time: 0.6349 [2021-03-26 02:01:28 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 810/1251] eta: 0:04:41 lr: 0.000833 loss: 4.8536 (4.7988) grad_norm: 1.2383 (1.3729) time: 0.6296 [2021-03-26 02:01:34 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 820/1251] eta: 0:04:35 lr: 0.000833 loss: 4.8868 (4.8031) grad_norm: 1.2536 (1.3738) time: 0.6280 [2021-03-26 02:01:41 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 830/1251] eta: 0:04:28 lr: 0.000833 loss: 5.0418 (4.8051) grad_norm: 1.3561 (1.3734) time: 0.6289 [2021-03-26 02:01:47 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 840/1251] eta: 0:04:22 lr: 0.000834 loss: 4.7854 (4.8023) grad_norm: 1.3366 (1.3731) time: 0.6282 [2021-03-26 02:01:53 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 850/1251] eta: 0:04:15 lr: 0.000834 loss: 4.6397 (4.7992) grad_norm: 1.3750 (1.3727) time: 0.6293 [2021-03-26 02:02:00 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 860/1251] eta: 0:04:09 lr: 0.000835 loss: 4.7897 (4.7998) grad_norm: 1.2500 (1.3705) time: 0.6304 [2021-03-26 02:02:06 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 870/1251] eta: 0:04:03 lr: 0.000835 loss: 4.7179 (4.7969) grad_norm: 1.2901 (1.3737) time: 0.6339 [2021-03-26 02:02:12 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 880/1251] eta: 0:03:56 lr: 0.000835 loss: 4.6731 (4.7979) grad_norm: 1.2965 (1.3730) time: 0.6356 [2021-03-26 02:02:19 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 890/1251] eta: 0:03:50 lr: 0.000836 loss: 4.8740 (4.7985) grad_norm: 1.2424 (1.3732) time: 0.6391 [2021-03-26 02:02:25 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 900/1251] eta: 0:03:44 lr: 0.000836 loss: 4.8506 (4.7986) grad_norm: 1.2264 (1.3714) time: 0.6354 [2021-03-26 02:02:31 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 910/1251] eta: 0:03:37 lr: 0.000837 loss: 4.8521 (4.7969) grad_norm: 1.3014 (1.3723) time: 0.6289 [2021-03-26 02:02:38 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 920/1251] eta: 0:03:31 lr: 0.000837 loss: 4.8522 (4.7966) grad_norm: 1.3315 (1.3723) time: 0.6297 [2021-03-26 02:02:44 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 930/1251] eta: 0:03:24 lr: 0.000837 loss: 4.2496 (4.7917) grad_norm: 1.2849 (1.3713) time: 0.6324 [2021-03-26 02:02:50 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 940/1251] eta: 0:03:18 lr: 0.000838 loss: 4.7433 (4.7948) grad_norm: 1.2886 (1.3711) time: 0.6390 [2021-03-26 02:02:57 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 950/1251] eta: 0:03:12 lr: 0.000838 loss: 5.0982 (4.7951) grad_norm: 1.2297 (1.3697) time: 0.6350 [2021-03-26 02:03:03 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 960/1251] eta: 0:03:05 lr: 0.000839 loss: 4.7720 (4.7938) grad_norm: 1.2294 (1.3690) time: 0.6327 [2021-03-26 02:03:09 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 970/1251] eta: 0:02:59 lr: 0.000839 loss: 4.6171 (4.7922) grad_norm: 1.2294 (1.3674) time: 0.6308 [2021-03-26 02:03:16 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 980/1251] eta: 0:02:52 lr: 0.000839 loss: 4.7803 (4.7941) grad_norm: 1.3186 (1.3697) time: 0.6307 [2021-03-26 02:03:22 swin_base_patch4_window7_224] INFO: Epoch: [16] [ 990/1251] eta: 0:02:46 lr: 0.000840 loss: 4.8351 (4.7939) grad_norm: 1.3186 (1.3686) time: 0.6313 [2021-03-26 02:03:28 swin_base_patch4_window7_224] INFO: Epoch: [16] [1000/1251] eta: 0:02:40 lr: 0.000840 loss: 4.7685 (4.7907) grad_norm: 1.2249 (1.3676) time: 0.6284 [2021-03-26 02:03:35 swin_base_patch4_window7_224] INFO: Epoch: [16] [1010/1251] eta: 0:02:33 lr: 0.000841 loss: 4.3328 (4.7894) grad_norm: 1.2813 (1.3673) time: 0.6337 [2021-03-26 02:03:41 swin_base_patch4_window7_224] INFO: Epoch: [16] [1020/1251] eta: 0:02:27 lr: 0.000841 loss: 4.7261 (4.7875) grad_norm: 1.1254 (1.3652) time: 0.6383 [2021-03-26 02:03:47 swin_base_patch4_window7_224] INFO: Epoch: [16] [1030/1251] eta: 0:02:20 lr: 0.000841 loss: 4.8205 (4.7878) grad_norm: 1.1987 (1.3651) time: 0.6401 [2021-03-26 02:03:54 swin_base_patch4_window7_224] INFO: Epoch: [16] [1040/1251] eta: 0:02:14 lr: 0.000842 loss: 4.6058 (4.7845) grad_norm: 1.3075 (1.3655) time: 0.6386 [2021-03-26 02:04:00 swin_base_patch4_window7_224] INFO: Epoch: [16] [1050/1251] eta: 0:02:08 lr: 0.000842 loss: 4.6058 (4.7842) grad_norm: 1.3075 (1.3649) time: 0.6389 [2021-03-26 02:04:06 swin_base_patch4_window7_224] INFO: Epoch: [16] [1060/1251] eta: 0:02:01 lr: 0.000843 loss: 4.5737 (4.7823) grad_norm: 1.3561 (1.3667) time: 0.6360 [2021-03-26 02:04:13 swin_base_patch4_window7_224] INFO: Epoch: [16] [1070/1251] eta: 0:01:55 lr: 0.000843 loss: 4.5319 (4.7811) grad_norm: 1.3904 (1.3677) time: 0.6313 [2021-03-26 02:04:19 swin_base_patch4_window7_224] INFO: Epoch: [16] [1080/1251] eta: 0:01:48 lr: 0.000843 loss: 4.6292 (4.7784) grad_norm: 1.3242 (1.3676) time: 0.6284 [2021-03-26 02:04:25 swin_base_patch4_window7_224] INFO: Epoch: [16] [1090/1251] eta: 0:01:42 lr: 0.000844 loss: 4.6062 (4.7752) grad_norm: 1.3572 (1.3685) time: 0.6274 [2021-03-26 02:04:32 swin_base_patch4_window7_224] INFO: Epoch: [16] [1100/1251] eta: 0:01:36 lr: 0.000844 loss: 4.6062 (4.7743) grad_norm: 1.2980 (1.3674) time: 0.6298 [2021-03-26 02:04:38 swin_base_patch4_window7_224] INFO: Epoch: [16] [1110/1251] eta: 0:01:29 lr: 0.000845 loss: 4.5693 (4.7724) grad_norm: 1.1630 (1.3655) time: 0.6313 [2021-03-26 02:04:44 swin_base_patch4_window7_224] INFO: Epoch: [16] [1120/1251] eta: 0:01:23 lr: 0.000845 loss: 4.4947 (4.7707) grad_norm: 1.1789 (1.3645) time: 0.6371 [2021-03-26 02:04:51 swin_base_patch4_window7_224] INFO: Epoch: [16] [1130/1251] eta: 0:01:17 lr: 0.000845 loss: 4.7119 (4.7721) grad_norm: 1.2312 (1.3644) time: 0.6358 [2021-03-26 02:04:57 swin_base_patch4_window7_224] INFO: Epoch: [16] [1140/1251] eta: 0:01:10 lr: 0.000846 loss: 4.8139 (4.7710) grad_norm: 1.2784 (1.3643) time: 0.6311 [2021-03-26 02:05:03 swin_base_patch4_window7_224] INFO: Epoch: [16] [1150/1251] eta: 0:01:04 lr: 0.000846 loss: 4.7626 (4.7703) grad_norm: 1.2896 (1.3639) time: 0.6332 [2021-03-26 02:05:10 swin_base_patch4_window7_224] INFO: Epoch: [16] [1160/1251] eta: 0:00:57 lr: 0.000847 loss: 4.7626 (4.7686) grad_norm: 1.2881 (1.3633) time: 0.6341 [2021-03-26 02:05:16 swin_base_patch4_window7_224] INFO: Epoch: [16] [1170/1251] eta: 0:00:51 lr: 0.000847 loss: 4.8811 (4.7697) grad_norm: 1.2501 (1.3637) time: 0.6345 [2021-03-26 02:05:22 swin_base_patch4_window7_224] INFO: Epoch: [16] [1180/1251] eta: 0:00:45 lr: 0.000847 loss: 4.8875 (4.7713) grad_norm: 1.1733 (1.3622) time: 0.6357 [2021-03-26 02:05:29 swin_base_patch4_window7_224] INFO: Epoch: [16] [1190/1251] eta: 0:00:38 lr: 0.000848 loss: 4.7618 (4.7711) grad_norm: 1.1725 (1.3618) time: 0.6323 [2021-03-26 02:05:35 swin_base_patch4_window7_224] INFO: Epoch: [16] [1200/1251] eta: 0:00:32 lr: 0.000848 loss: 4.9130 (4.7729) grad_norm: 1.3106 (1.3610) time: 0.6277 [2021-03-26 02:05:41 swin_base_patch4_window7_224] INFO: Epoch: [16] [1210/1251] eta: 0:00:26 lr: 0.000849 loss: 5.1162 (4.7728) grad_norm: 1.2880 (1.3609) time: 0.6263 [2021-03-26 02:05:48 swin_base_patch4_window7_224] INFO: Epoch: [16] [1220/1251] eta: 0:00:19 lr: 0.000849 loss: 4.9275 (4.7732) grad_norm: 1.2853 (1.3624) time: 0.6315 [2021-03-26 02:05:54 swin_base_patch4_window7_224] INFO: Epoch: [16] [1230/1251] eta: 0:00:13 lr: 0.000849 loss: 4.7554 (4.7732) grad_norm: 1.2869 (1.3625) time: 0.6381 [2021-03-26 02:06:00 swin_base_patch4_window7_224] INFO: Epoch: [16] [1240/1251] eta: 0:00:07 lr: 0.000850 loss: 4.7043 (4.7727) grad_norm: 1.2625 (1.3618) time: 0.6379 [2021-03-26 02:06:07 swin_base_patch4_window7_224] INFO: Epoch: [16] [1250/1251] eta: 0:00:00 lr: 0.000850 loss: 4.7645 (4.7720) grad_norm: 1.3352 (1.3622) time: 0.6338 [2021-03-26 02:06:10 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:18 loss: 2.2393 (2.2393) acc1: 56.2500 (56.2500) acc5: 71.8750 (71.8750) [2021-03-26 02:06:14 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 2.1528 (2.0918) acc1: 54.6875 (52.8409) acc5: 79.6875 (77.6989) [2021-03-26 02:06:15 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 2.0157 (2.0703) acc1: 54.6875 (53.4226) acc5: 79.6875 (78.2738) [2021-03-26 02:06:18 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.9543 (2.0583) acc1: 54.6875 (53.2762) acc5: 79.6875 (78.7802) [2021-03-26 02:06:20 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.9543 (2.0569) acc1: 54.6875 (53.8491) acc5: 79.6875 (78.9634) [2021-03-26 02:06:21 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.9855 (2.0652) acc1: 54.6875 (53.4400) acc5: 79.6875 (79.0400) [2021-03-26 02:06:23 swin_base_patch4_window7_224] INFO: * Acc@1 53.818 Acc@5 79.072 loss 2.058 [2021-03-26 02:06:23 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 53.8% [2021-03-26 02:06:23 swin_base_patch4_window7_224] INFO: Max accuracy: 53.82% [2021-03-26 02:06:27 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 0/1251] eta: 1:31:08 lr: 0.000850 loss: 4.4223 (4.4223) grad_norm: 1.4354 (1.4354) time: 4.3711 [2021-03-26 02:06:33 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 10/1251] eta: 0:20:01 lr: 0.000851 loss: 4.9248 (4.8063) grad_norm: 1.3482 (1.3351) time: 0.9682 [2021-03-26 02:06:40 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 20/1251] eta: 0:16:32 lr: 0.000851 loss: 4.8817 (4.7875) grad_norm: 1.3313 (1.3351) time: 0.6283 [2021-03-26 02:06:46 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 30/1251] eta: 0:15:20 lr: 0.000851 loss: 4.5317 (4.6456) grad_norm: 1.3504 (1.3642) time: 0.6357 [2021-03-26 02:06:53 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 40/1251] eta: 0:14:40 lr: 0.000852 loss: 4.2689 (4.5873) grad_norm: 1.3321 (1.3402) time: 0.6428 [2021-03-26 02:06:59 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 50/1251] eta: 0:14:09 lr: 0.000852 loss: 4.1854 (4.5366) grad_norm: 1.2383 (1.3636) time: 0.6364 [2021-03-26 02:07:05 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 60/1251] eta: 0:13:51 lr: 0.000853 loss: 4.3736 (4.5609) grad_norm: 1.3711 (1.3801) time: 0.6389 [2021-03-26 02:07:12 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 70/1251] eta: 0:13:32 lr: 0.000853 loss: 4.8811 (4.6002) grad_norm: 1.3715 (1.3709) time: 0.6384 [2021-03-26 02:07:18 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 80/1251] eta: 0:13:18 lr: 0.000853 loss: 4.8646 (4.6178) grad_norm: 1.3206 (1.3716) time: 0.6328 [2021-03-26 02:07:24 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 90/1251] eta: 0:13:04 lr: 0.000854 loss: 4.8646 (4.6554) grad_norm: 1.3493 (1.3702) time: 0.6316 [2021-03-26 02:07:31 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 100/1251] eta: 0:12:52 lr: 0.000854 loss: 4.9051 (4.6828) grad_norm: 1.3397 (1.3643) time: 0.6278 [2021-03-26 02:07:37 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 110/1251] eta: 0:12:41 lr: 0.000855 loss: 4.8698 (4.6778) grad_norm: 1.3819 (1.3771) time: 0.6302 [2021-03-26 02:07:43 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 120/1251] eta: 0:12:31 lr: 0.000855 loss: 4.4900 (4.6671) grad_norm: 1.3649 (1.3686) time: 0.6317 [2021-03-26 02:07:49 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 130/1251] eta: 0:12:22 lr: 0.000855 loss: 4.7089 (4.6784) grad_norm: 1.1987 (1.3533) time: 0.6316 [2021-03-26 02:07:56 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 140/1251] eta: 0:12:13 lr: 0.000856 loss: 4.6995 (4.6716) grad_norm: 1.2170 (1.3492) time: 0.6327 [2021-03-26 02:08:02 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 150/1251] eta: 0:12:05 lr: 0.000856 loss: 4.3954 (4.6608) grad_norm: 1.2626 (1.3505) time: 0.6353 [2021-03-26 02:08:08 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 160/1251] eta: 0:11:56 lr: 0.000857 loss: 4.8724 (4.6677) grad_norm: 1.3552 (1.3573) time: 0.6301 [2021-03-26 02:08:15 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 170/1251] eta: 0:11:48 lr: 0.000857 loss: 4.8417 (4.6591) grad_norm: 1.3552 (1.3583) time: 0.6346 [2021-03-26 02:08:21 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 180/1251] eta: 0:11:40 lr: 0.000857 loss: 4.5948 (4.6620) grad_norm: 1.3241 (1.3573) time: 0.6374 [2021-03-26 02:08:27 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 190/1251] eta: 0:11:32 lr: 0.000858 loss: 4.6125 (4.6542) grad_norm: 1.1980 (1.3545) time: 0.6294 [2021-03-26 02:08:34 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 200/1251] eta: 0:11:25 lr: 0.000858 loss: 4.6125 (4.6495) grad_norm: 1.3101 (1.3564) time: 0.6331 [2021-03-26 02:08:40 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 210/1251] eta: 0:11:17 lr: 0.000859 loss: 4.7343 (4.6567) grad_norm: 1.3101 (1.3585) time: 0.6326 [2021-03-26 02:08:46 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 220/1251] eta: 0:11:10 lr: 0.000859 loss: 4.6513 (4.6521) grad_norm: 1.3029 (1.3585) time: 0.6298 [2021-03-26 02:08:53 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 230/1251] eta: 0:11:03 lr: 0.000859 loss: 4.4628 (4.6516) grad_norm: 1.4019 (1.3693) time: 0.6341 [2021-03-26 02:08:59 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 240/1251] eta: 0:10:56 lr: 0.000860 loss: 4.4628 (4.6460) grad_norm: 1.3582 (1.3671) time: 0.6360 [2021-03-26 02:09:05 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 250/1251] eta: 0:10:48 lr: 0.000860 loss: 4.4032 (4.6376) grad_norm: 1.2160 (1.3619) time: 0.6320 [2021-03-26 02:09:12 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 260/1251] eta: 0:10:42 lr: 0.000861 loss: 4.9744 (4.6548) grad_norm: 1.2029 (1.3560) time: 0.6361 [2021-03-26 02:09:18 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 270/1251] eta: 0:10:35 lr: 0.000861 loss: 4.9700 (4.6505) grad_norm: 1.2639 (1.3579) time: 0.6464 [2021-03-26 02:09:25 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 280/1251] eta: 0:10:28 lr: 0.000861 loss: 4.3649 (4.6473) grad_norm: 1.2954 (1.3534) time: 0.6380 [2021-03-26 02:09:31 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 290/1251] eta: 0:10:21 lr: 0.000862 loss: 4.1713 (4.6379) grad_norm: 1.2418 (1.3485) time: 0.6290 [2021-03-26 02:09:37 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 300/1251] eta: 0:10:14 lr: 0.000862 loss: 4.6263 (4.6458) grad_norm: 1.2528 (1.3484) time: 0.6339 [2021-03-26 02:09:44 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 310/1251] eta: 0:10:07 lr: 0.000863 loss: 4.8703 (4.6524) grad_norm: 1.3740 (1.3504) time: 0.6339 [2021-03-26 02:09:50 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 320/1251] eta: 0:10:00 lr: 0.000863 loss: 4.9638 (4.6564) grad_norm: 1.3016 (1.3465) time: 0.6298 [2021-03-26 02:09:56 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 330/1251] eta: 0:09:54 lr: 0.000863 loss: 4.5347 (4.6427) grad_norm: 1.1876 (1.3419) time: 0.6309 [2021-03-26 02:10:03 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 340/1251] eta: 0:09:47 lr: 0.000864 loss: 4.4934 (4.6428) grad_norm: 1.2560 (1.3425) time: 0.6331 [2021-03-26 02:10:09 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 350/1251] eta: 0:09:40 lr: 0.000864 loss: 4.4983 (4.6359) grad_norm: 1.3124 (1.3409) time: 0.6339 [2021-03-26 02:10:15 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 360/1251] eta: 0:09:34 lr: 0.000865 loss: 4.5763 (4.6415) grad_norm: 1.3513 (1.3477) time: 0.6378 [2021-03-26 02:10:22 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 370/1251] eta: 0:09:27 lr: 0.000865 loss: 5.0094 (4.6466) grad_norm: 1.3415 (1.3465) time: 0.6391 [2021-03-26 02:10:28 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 380/1251] eta: 0:09:20 lr: 0.000865 loss: 5.0094 (4.6510) grad_norm: 1.2432 (1.3464) time: 0.6342 [2021-03-26 02:10:34 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 390/1251] eta: 0:09:13 lr: 0.000866 loss: 4.6085 (4.6522) grad_norm: 1.2107 (1.3420) time: 0.6310 [2021-03-26 02:10:41 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 400/1251] eta: 0:09:07 lr: 0.000866 loss: 4.5573 (4.6507) grad_norm: 1.1640 (1.3391) time: 0.6309 [2021-03-26 02:10:47 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 410/1251] eta: 0:09:00 lr: 0.000867 loss: 4.6107 (4.6537) grad_norm: 1.3530 (1.3430) time: 0.6318 [2021-03-26 02:10:53 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 420/1251] eta: 0:08:53 lr: 0.000867 loss: 4.7384 (4.6571) grad_norm: 1.3177 (1.3425) time: 0.6316 [2021-03-26 02:11:00 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 430/1251] eta: 0:08:47 lr: 0.000867 loss: 4.7529 (4.6612) grad_norm: 1.1974 (1.3408) time: 0.6297 [2021-03-26 02:11:06 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 440/1251] eta: 0:08:40 lr: 0.000868 loss: 4.7267 (4.6588) grad_norm: 1.1858 (1.3378) time: 0.6325 [2021-03-26 02:11:12 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 450/1251] eta: 0:08:34 lr: 0.000868 loss: 4.6235 (4.6622) grad_norm: 1.2338 (1.3365) time: 0.6367 [2021-03-26 02:11:19 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 460/1251] eta: 0:08:27 lr: 0.000869 loss: 4.8346 (4.6646) grad_norm: 1.3277 (1.3383) time: 0.6352 [2021-03-26 02:11:25 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 470/1251] eta: 0:08:20 lr: 0.000869 loss: 4.7149 (4.6644) grad_norm: 1.2761 (1.3363) time: 0.6301 [2021-03-26 02:11:31 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 480/1251] eta: 0:08:14 lr: 0.000869 loss: 4.6974 (4.6635) grad_norm: 1.2411 (1.3352) time: 0.6262 [2021-03-26 02:11:37 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 490/1251] eta: 0:08:07 lr: 0.000870 loss: 4.8223 (4.6658) grad_norm: 1.3308 (1.3356) time: 0.6270 [2021-03-26 02:11:44 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 500/1251] eta: 0:08:01 lr: 0.000870 loss: 5.0216 (4.6729) grad_norm: 1.3506 (1.3363) time: 0.6316 [2021-03-26 02:11:50 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 510/1251] eta: 0:07:54 lr: 0.000871 loss: 5.1280 (4.6685) grad_norm: 1.3541 (1.3356) time: 0.6339 [2021-03-26 02:11:57 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 520/1251] eta: 0:07:48 lr: 0.000871 loss: 4.8038 (4.6759) grad_norm: 1.4019 (1.3369) time: 0.6381 [2021-03-26 02:12:03 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 530/1251] eta: 0:07:41 lr: 0.000871 loss: 4.6817 (4.6686) grad_norm: 1.2681 (1.3358) time: 0.6327 [2021-03-26 02:12:09 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 540/1251] eta: 0:07:35 lr: 0.000872 loss: 4.5298 (4.6726) grad_norm: 1.2242 (1.3329) time: 0.6250 [2021-03-26 02:12:16 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 550/1251] eta: 0:07:28 lr: 0.000872 loss: 4.9294 (4.6777) grad_norm: 1.2945 (1.3368) time: 0.6431 [2021-03-26 02:12:22 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 560/1251] eta: 0:07:22 lr: 0.000873 loss: 4.9991 (4.6818) grad_norm: 1.3900 (1.3372) time: 0.6475 [2021-03-26 02:12:28 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 570/1251] eta: 0:07:16 lr: 0.000873 loss: 4.6178 (4.6791) grad_norm: 1.4032 (1.3402) time: 0.6366 [2021-03-26 02:12:35 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 580/1251] eta: 0:07:09 lr: 0.000873 loss: 4.6281 (4.6813) grad_norm: 1.3909 (1.3400) time: 0.6444 [2021-03-26 02:12:41 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 590/1251] eta: 0:07:03 lr: 0.000874 loss: 4.7631 (4.6751) grad_norm: 1.2796 (1.3381) time: 0.6421 [2021-03-26 02:12:48 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 600/1251] eta: 0:06:56 lr: 0.000874 loss: 4.4579 (4.6776) grad_norm: 1.2796 (1.3373) time: 0.6362 [2021-03-26 02:12:54 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 610/1251] eta: 0:06:50 lr: 0.000875 loss: 4.8195 (4.6792) grad_norm: 1.3048 (1.3367) time: 0.6390 [2021-03-26 02:13:01 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 620/1251] eta: 0:06:44 lr: 0.000875 loss: 4.6248 (4.6744) grad_norm: 1.2776 (1.3355) time: 0.6415 [2021-03-26 02:13:07 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 630/1251] eta: 0:06:37 lr: 0.000875 loss: 4.7888 (4.6802) grad_norm: 1.2472 (1.3356) time: 0.6407 [2021-03-26 02:13:13 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 640/1251] eta: 0:06:31 lr: 0.000876 loss: 5.0106 (4.6813) grad_norm: 1.2939 (1.3372) time: 0.6371 [2021-03-26 02:13:20 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 650/1251] eta: 0:06:24 lr: 0.000876 loss: 4.6316 (4.6790) grad_norm: 1.2063 (1.3344) time: 0.6317 [2021-03-26 02:13:26 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 660/1251] eta: 0:06:18 lr: 0.000877 loss: 4.8568 (4.6827) grad_norm: 1.1147 (1.3322) time: 0.6279 [2021-03-26 02:13:32 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 670/1251] eta: 0:06:11 lr: 0.000877 loss: 4.7208 (4.6811) grad_norm: 1.1448 (1.3299) time: 0.6323 [2021-03-26 02:13:39 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 680/1251] eta: 0:06:05 lr: 0.000877 loss: 4.6829 (4.6813) grad_norm: 1.1771 (1.3293) time: 0.6353 [2021-03-26 02:13:45 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 690/1251] eta: 0:05:58 lr: 0.000878 loss: 4.6829 (4.6782) grad_norm: 1.2684 (1.3297) time: 0.6302 [2021-03-26 02:13:51 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 700/1251] eta: 0:05:52 lr: 0.000878 loss: 4.5834 (4.6768) grad_norm: 1.2684 (1.3299) time: 0.6283 [2021-03-26 02:13:57 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 710/1251] eta: 0:05:45 lr: 0.000878 loss: 4.6422 (4.6793) grad_norm: 1.2193 (1.3277) time: 0.6321 [2021-03-26 02:14:04 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 720/1251] eta: 0:05:39 lr: 0.000879 loss: 4.9337 (4.6815) grad_norm: 1.2469 (1.3283) time: 0.6354 [2021-03-26 02:14:10 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 730/1251] eta: 0:05:33 lr: 0.000879 loss: 4.8756 (4.6807) grad_norm: 1.2540 (1.3270) time: 0.6355 [2021-03-26 02:14:17 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 740/1251] eta: 0:05:26 lr: 0.000880 loss: 4.8821 (4.6851) grad_norm: 1.3035 (1.3291) time: 0.6403 [2021-03-26 02:14:23 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 750/1251] eta: 0:05:20 lr: 0.000880 loss: 4.8544 (4.6838) grad_norm: 1.4084 (1.3299) time: 0.6444 [2021-03-26 02:14:29 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 760/1251] eta: 0:05:13 lr: 0.000880 loss: 4.3978 (4.6812) grad_norm: 1.3384 (1.3309) time: 0.6353 [2021-03-26 02:14:36 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 770/1251] eta: 0:05:07 lr: 0.000881 loss: 4.3978 (4.6774) grad_norm: 1.2751 (1.3296) time: 0.6340 [2021-03-26 02:14:42 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 780/1251] eta: 0:05:01 lr: 0.000881 loss: 4.6748 (4.6781) grad_norm: 1.2150 (1.3282) time: 0.6374 [2021-03-26 02:14:48 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 790/1251] eta: 0:04:54 lr: 0.000882 loss: 4.7622 (4.6783) grad_norm: 1.1706 (1.3271) time: 0.6328 [2021-03-26 02:14:55 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 800/1251] eta: 0:04:48 lr: 0.000882 loss: 4.7622 (4.6796) grad_norm: 1.2320 (1.3278) time: 0.6325 [2021-03-26 02:15:01 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 810/1251] eta: 0:04:41 lr: 0.000882 loss: 4.6575 (4.6778) grad_norm: 1.3329 (1.3291) time: 0.6360 [2021-03-26 02:15:07 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 820/1251] eta: 0:04:35 lr: 0.000883 loss: 4.5678 (4.6769) grad_norm: 1.2291 (1.3293) time: 0.6352 [2021-03-26 02:15:14 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 830/1251] eta: 0:04:29 lr: 0.000883 loss: 4.4699 (4.6771) grad_norm: 1.3070 (1.3303) time: 0.6378 [2021-03-26 02:15:20 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 840/1251] eta: 0:04:22 lr: 0.000884 loss: 4.7870 (4.6798) grad_norm: 1.2827 (1.3285) time: 0.6334 [2021-03-26 02:15:26 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 850/1251] eta: 0:04:16 lr: 0.000884 loss: 4.7451 (4.6754) grad_norm: 1.1513 (1.3263) time: 0.6266 [2021-03-26 02:15:33 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 860/1251] eta: 0:04:09 lr: 0.000884 loss: 4.3621 (4.6747) grad_norm: 1.1513 (1.3251) time: 0.6253 [2021-03-26 02:15:39 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 870/1251] eta: 0:04:03 lr: 0.000885 loss: 4.4711 (4.6734) grad_norm: 1.1506 (1.3240) time: 0.6298 [2021-03-26 02:15:45 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 880/1251] eta: 0:03:56 lr: 0.000885 loss: 4.4959 (4.6721) grad_norm: 1.1937 (1.3232) time: 0.6362 [2021-03-26 02:15:52 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 890/1251] eta: 0:03:50 lr: 0.000886 loss: 4.6567 (4.6732) grad_norm: 1.3901 (1.3265) time: 0.6351 [2021-03-26 02:15:58 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 900/1251] eta: 0:03:44 lr: 0.000886 loss: 4.6567 (4.6723) grad_norm: 1.3084 (1.3246) time: 0.6371 [2021-03-26 02:16:04 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 910/1251] eta: 0:03:37 lr: 0.000886 loss: 4.8707 (4.6748) grad_norm: 1.1212 (1.3241) time: 0.6328 [2021-03-26 02:16:11 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 920/1251] eta: 0:03:31 lr: 0.000887 loss: 4.9574 (4.6795) grad_norm: 1.1897 (1.3241) time: 0.6353 [2021-03-26 02:16:17 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 930/1251] eta: 0:03:24 lr: 0.000887 loss: 4.8308 (4.6746) grad_norm: 1.2669 (1.3242) time: 0.6346 [2021-03-26 02:16:23 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 940/1251] eta: 0:03:18 lr: 0.000888 loss: 4.1383 (4.6741) grad_norm: 1.3150 (1.3255) time: 0.6267 [2021-03-26 02:16:30 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 950/1251] eta: 0:03:12 lr: 0.000888 loss: 4.7260 (4.6731) grad_norm: 1.3808 (1.3250) time: 0.6274 [2021-03-26 02:16:36 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 960/1251] eta: 0:03:05 lr: 0.000888 loss: 4.7896 (4.6748) grad_norm: 1.2447 (1.3248) time: 0.6252 [2021-03-26 02:16:42 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 970/1251] eta: 0:02:59 lr: 0.000889 loss: 4.6234 (4.6726) grad_norm: 1.2864 (1.3243) time: 0.6268 [2021-03-26 02:16:49 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 980/1251] eta: 0:02:52 lr: 0.000889 loss: 4.5507 (4.6737) grad_norm: 1.1932 (1.3226) time: 0.6325 [2021-03-26 02:16:55 swin_base_patch4_window7_224] INFO: Epoch: [17] [ 990/1251] eta: 0:02:46 lr: 0.000890 loss: 4.9072 (4.6765) grad_norm: 1.1832 (1.3213) time: 0.6354 [2021-03-26 02:17:01 swin_base_patch4_window7_224] INFO: Epoch: [17] [1000/1251] eta: 0:02:40 lr: 0.000890 loss: 5.0117 (4.6793) grad_norm: 1.2550 (1.3218) time: 0.6336 [2021-03-26 02:17:08 swin_base_patch4_window7_224] INFO: Epoch: [17] [1010/1251] eta: 0:02:33 lr: 0.000890 loss: 5.0117 (4.6832) grad_norm: 1.2770 (1.3214) time: 0.6323 [2021-03-26 02:17:14 swin_base_patch4_window7_224] INFO: Epoch: [17] [1020/1251] eta: 0:02:27 lr: 0.000891 loss: 4.9052 (4.6821) grad_norm: 1.2585 (1.3216) time: 0.6294 [2021-03-26 02:17:20 swin_base_patch4_window7_224] INFO: Epoch: [17] [1030/1251] eta: 0:02:20 lr: 0.000891 loss: 4.5898 (4.6811) grad_norm: 1.3290 (1.3211) time: 0.6221 [2021-03-26 02:17:26 swin_base_patch4_window7_224] INFO: Epoch: [17] [1040/1251] eta: 0:02:14 lr: 0.000892 loss: 4.4666 (4.6788) grad_norm: 1.2723 (1.3207) time: 0.6261 [2021-03-26 02:17:33 swin_base_patch4_window7_224] INFO: Epoch: [17] [1050/1251] eta: 0:02:08 lr: 0.000892 loss: 4.5442 (4.6792) grad_norm: 1.3695 (1.3217) time: 0.6344 [2021-03-26 02:17:39 swin_base_patch4_window7_224] INFO: Epoch: [17] [1060/1251] eta: 0:02:01 lr: 0.000892 loss: 4.6944 (4.6813) grad_norm: 1.3820 (1.3216) time: 0.6394 [2021-03-26 02:17:45 swin_base_patch4_window7_224] INFO: Epoch: [17] [1070/1251] eta: 0:01:55 lr: 0.000893 loss: 5.0617 (4.6839) grad_norm: 1.2368 (1.3209) time: 0.6385 [2021-03-26 02:17:52 swin_base_patch4_window7_224] INFO: Epoch: [17] [1080/1251] eta: 0:01:48 lr: 0.000893 loss: 5.0518 (4.6851) grad_norm: 1.1987 (1.3201) time: 0.6330 [2021-03-26 02:17:58 swin_base_patch4_window7_224] INFO: Epoch: [17] [1090/1251] eta: 0:01:42 lr: 0.000894 loss: 4.7664 (4.6841) grad_norm: 1.2271 (1.3202) time: 0.6288 [2021-03-26 02:18:04 swin_base_patch4_window7_224] INFO: Epoch: [17] [1100/1251] eta: 0:01:36 lr: 0.000894 loss: 4.7784 (4.6856) grad_norm: 1.2963 (1.3217) time: 0.6230 [2021-03-26 02:18:11 swin_base_patch4_window7_224] INFO: Epoch: [17] [1110/1251] eta: 0:01:29 lr: 0.000894 loss: 4.7312 (4.6845) grad_norm: 1.2926 (1.3205) time: 0.6254 [2021-03-26 02:18:17 swin_base_patch4_window7_224] INFO: Epoch: [17] [1120/1251] eta: 0:01:23 lr: 0.000895 loss: 4.7460 (4.6855) grad_norm: 1.1557 (1.3196) time: 0.6264 [2021-03-26 02:18:23 swin_base_patch4_window7_224] INFO: Epoch: [17] [1130/1251] eta: 0:01:17 lr: 0.000895 loss: 4.7752 (4.6862) grad_norm: 1.1394 (1.3186) time: 0.6253 [2021-03-26 02:18:29 swin_base_patch4_window7_224] INFO: Epoch: [17] [1140/1251] eta: 0:01:10 lr: 0.000896 loss: 4.7637 (4.6842) grad_norm: 1.2106 (1.3183) time: 0.6246 [2021-03-26 02:18:36 swin_base_patch4_window7_224] INFO: Epoch: [17] [1150/1251] eta: 0:01:04 lr: 0.000896 loss: 4.9123 (4.6853) grad_norm: 1.2106 (1.3168) time: 0.6260 [2021-03-26 02:18:42 swin_base_patch4_window7_224] INFO: Epoch: [17] [1160/1251] eta: 0:00:57 lr: 0.000896 loss: 4.7456 (4.6835) grad_norm: 1.2558 (1.3183) time: 0.6324 [2021-03-26 02:18:48 swin_base_patch4_window7_224] INFO: Epoch: [17] [1170/1251] eta: 0:00:51 lr: 0.000897 loss: 4.9001 (4.6855) grad_norm: 1.3162 (1.3182) time: 0.6294 [2021-03-26 02:18:54 swin_base_patch4_window7_224] INFO: Epoch: [17] [1180/1251] eta: 0:00:45 lr: 0.000897 loss: 5.0488 (4.6887) grad_norm: 1.2895 (1.3197) time: 0.6293 [2021-03-26 02:19:01 swin_base_patch4_window7_224] INFO: Epoch: [17] [1190/1251] eta: 0:00:38 lr: 0.000898 loss: 4.8414 (4.6876) grad_norm: 1.4951 (1.3219) time: 0.6327 [2021-03-26 02:19:07 swin_base_patch4_window7_224] INFO: Epoch: [17] [1200/1251] eta: 0:00:32 lr: 0.000898 loss: 4.7962 (4.6895) grad_norm: 1.2235 (1.3208) time: 0.6339 [2021-03-26 02:19:13 swin_base_patch4_window7_224] INFO: Epoch: [17] [1210/1251] eta: 0:00:26 lr: 0.000898 loss: 4.8951 (4.6885) grad_norm: 1.2604 (1.3211) time: 0.6354 [2021-03-26 02:19:20 swin_base_patch4_window7_224] INFO: Epoch: [17] [1220/1251] eta: 0:00:19 lr: 0.000899 loss: 4.8945 (4.6881) grad_norm: 1.2577 (1.3201) time: 0.6280 [2021-03-26 02:19:26 swin_base_patch4_window7_224] INFO: Epoch: [17] [1230/1251] eta: 0:00:13 lr: 0.000899 loss: 4.7062 (4.6872) grad_norm: 1.1368 (1.3184) time: 0.6238 [2021-03-26 02:19:32 swin_base_patch4_window7_224] INFO: Epoch: [17] [1240/1251] eta: 0:00:06 lr: 0.000900 loss: 4.7144 (4.6884) grad_norm: 1.2152 (1.3197) time: 0.6246 [2021-03-26 02:19:38 swin_base_patch4_window7_224] INFO: Epoch: [17] [1250/1251] eta: 0:00:00 lr: 0.000900 loss: 5.0104 (4.6920) grad_norm: 1.3147 (1.3204) time: 0.6187 [2021-03-26 02:19:42 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:27 loss: 1.7257 (1.7257) acc1: 57.8125 (57.8125) acc5: 89.0625 (89.0625) [2021-03-26 02:19:45 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.8827 (1.9320) acc1: 56.2500 (55.6818) acc5: 81.2500 (81.5341) [2021-03-26 02:19:47 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.9999 (2.0275) acc1: 53.1250 (54.4643) acc5: 78.1250 (79.6131) [2021-03-26 02:19:50 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 2.0457 (2.0303) acc1: 54.6875 (54.8891) acc5: 78.1250 (79.7379) [2021-03-26 02:19:52 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.9706 (1.9956) acc1: 56.2500 (55.3735) acc5: 82.8125 (80.6021) [2021-03-26 02:19:53 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.8858 (1.9876) acc1: 56.2500 (55.6480) acc5: 81.2500 (80.5760) [2021-03-26 02:19:55 swin_base_patch4_window7_224] INFO: * Acc@1 55.202 Acc@5 80.222 loss 1.977 [2021-03-26 02:19:55 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 55.2% [2021-03-26 02:19:55 swin_base_patch4_window7_224] INFO: Max accuracy: 55.20% [2021-03-26 02:19:59 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 0/1251] eta: 1:30:18 lr: 0.000900 loss: 4.6519 (4.6519) grad_norm: 1.1873 (1.1873) time: 4.3313 [2021-03-26 02:20:05 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 10/1251] eta: 0:20:16 lr: 0.000900 loss: 4.8108 (4.8089) grad_norm: 1.1465 (1.2046) time: 0.9801 [2021-03-26 02:20:12 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 20/1251] eta: 0:16:45 lr: 0.000901 loss: 4.7856 (4.6960) grad_norm: 1.1610 (1.2141) time: 0.6413 [2021-03-26 02:20:18 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 30/1251] eta: 0:15:30 lr: 0.000901 loss: 4.5909 (4.6064) grad_norm: 1.2295 (1.2785) time: 0.6427 [2021-03-26 02:20:25 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 40/1251] eta: 0:14:44 lr: 0.000902 loss: 4.6024 (4.6221) grad_norm: 1.3037 (1.3096) time: 0.6398 [2021-03-26 02:20:31 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 50/1251] eta: 0:14:13 lr: 0.000902 loss: 4.3629 (4.5387) grad_norm: 1.2382 (1.2937) time: 0.6302 [2021-03-26 02:20:37 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 60/1251] eta: 0:13:50 lr: 0.000902 loss: 4.8773 (4.6071) grad_norm: 1.2240 (1.2933) time: 0.6296 [2021-03-26 02:20:43 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 70/1251] eta: 0:13:31 lr: 0.000903 loss: 5.0155 (4.5873) grad_norm: 1.2193 (1.2901) time: 0.6276 [2021-03-26 02:20:50 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 80/1251] eta: 0:13:18 lr: 0.000903 loss: 4.4951 (4.5850) grad_norm: 1.2381 (1.3074) time: 0.6335 [2021-03-26 02:20:56 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 90/1251] eta: 0:13:05 lr: 0.000904 loss: 4.8022 (4.6062) grad_norm: 1.3998 (1.3105) time: 0.6394 [2021-03-26 02:21:02 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 100/1251] eta: 0:12:53 lr: 0.000904 loss: 4.6807 (4.5940) grad_norm: 1.3348 (1.3190) time: 0.6314 [2021-03-26 02:21:09 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 110/1251] eta: 0:12:41 lr: 0.000904 loss: 4.7937 (4.6233) grad_norm: 1.3459 (1.3179) time: 0.6251 [2021-03-26 02:21:15 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 120/1251] eta: 0:12:31 lr: 0.000905 loss: 4.8373 (4.6377) grad_norm: 1.2073 (1.3051) time: 0.6260 [2021-03-26 02:21:21 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 130/1251] eta: 0:12:23 lr: 0.000905 loss: 4.5603 (4.6277) grad_norm: 1.1552 (1.3005) time: 0.6380 [2021-03-26 02:21:28 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 140/1251] eta: 0:12:14 lr: 0.000906 loss: 4.8243 (4.6453) grad_norm: 1.2503 (1.3027) time: 0.6413 [2021-03-26 02:21:34 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 150/1251] eta: 0:12:05 lr: 0.000906 loss: 4.8536 (4.6418) grad_norm: 1.3583 (1.3044) time: 0.6309 [2021-03-26 02:21:40 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 160/1251] eta: 0:11:56 lr: 0.000906 loss: 4.5752 (4.6285) grad_norm: 1.3341 (1.2995) time: 0.6272 [2021-03-26 02:21:47 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 170/1251] eta: 0:11:48 lr: 0.000907 loss: 4.1965 (4.5972) grad_norm: 1.2509 (1.2981) time: 0.6281 [2021-03-26 02:21:53 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 180/1251] eta: 0:11:39 lr: 0.000907 loss: 4.1392 (4.5817) grad_norm: 1.1817 (1.2906) time: 0.6257 [2021-03-26 02:21:59 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 190/1251] eta: 0:11:32 lr: 0.000908 loss: 4.2622 (4.5765) grad_norm: 1.2105 (1.2947) time: 0.6329 [2021-03-26 02:22:06 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 200/1251] eta: 0:11:24 lr: 0.000908 loss: 4.6500 (4.5919) grad_norm: 1.3083 (1.2965) time: 0.6357 [2021-03-26 02:22:12 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 210/1251] eta: 0:11:17 lr: 0.000908 loss: 4.7588 (4.5918) grad_norm: 1.3688 (1.3025) time: 0.6319 [2021-03-26 02:22:18 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 220/1251] eta: 0:11:10 lr: 0.000909 loss: 4.6857 (4.5936) grad_norm: 1.4151 (1.3056) time: 0.6352 [2021-03-26 02:22:25 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 230/1251] eta: 0:11:02 lr: 0.000909 loss: 4.7305 (4.5927) grad_norm: 1.2547 (1.3062) time: 0.6313 [2021-03-26 02:22:31 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 240/1251] eta: 0:10:55 lr: 0.000910 loss: 4.7528 (4.5933) grad_norm: 1.3020 (1.3082) time: 0.6334 [2021-03-26 02:22:37 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 250/1251] eta: 0:10:48 lr: 0.000910 loss: 4.8465 (4.6038) grad_norm: 1.3020 (1.3065) time: 0.6367 [2021-03-26 02:22:44 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 260/1251] eta: 0:10:41 lr: 0.000910 loss: 4.5955 (4.5982) grad_norm: 1.2467 (1.3086) time: 0.6349 [2021-03-26 02:22:50 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 270/1251] eta: 0:10:34 lr: 0.000911 loss: 4.5993 (4.6052) grad_norm: 1.2238 (1.3033) time: 0.6353 [2021-03-26 02:22:56 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 280/1251] eta: 0:10:28 lr: 0.000911 loss: 4.8168 (4.6076) grad_norm: 1.1906 (1.3021) time: 0.6357 [2021-03-26 02:23:03 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 290/1251] eta: 0:10:21 lr: 0.000912 loss: 4.9867 (4.6183) grad_norm: 1.2371 (1.2996) time: 0.6343 [2021-03-26 02:23:09 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 300/1251] eta: 0:10:14 lr: 0.000912 loss: 4.8368 (4.6152) grad_norm: 1.2028 (1.2967) time: 0.6327 [2021-03-26 02:23:15 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 310/1251] eta: 0:10:07 lr: 0.000912 loss: 4.2994 (4.6058) grad_norm: 1.2252 (1.3021) time: 0.6307 [2021-03-26 02:23:22 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 320/1251] eta: 0:10:00 lr: 0.000913 loss: 4.2994 (4.6046) grad_norm: 1.3281 (1.2999) time: 0.6294 [2021-03-26 02:23:28 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 330/1251] eta: 0:09:53 lr: 0.000913 loss: 4.8107 (4.6106) grad_norm: 1.1551 (1.2972) time: 0.6294 [2021-03-26 02:23:34 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 340/1251] eta: 0:09:46 lr: 0.000914 loss: 4.8538 (4.6122) grad_norm: 1.1921 (1.2972) time: 0.6319 [2021-03-26 02:23:41 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 350/1251] eta: 0:09:40 lr: 0.000914 loss: 4.8763 (4.6097) grad_norm: 1.3139 (1.2980) time: 0.6343 [2021-03-26 02:23:47 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 360/1251] eta: 0:09:32 lr: 0.000914 loss: 4.1468 (4.5915) grad_norm: 1.2262 (1.2958) time: 0.6264 [2021-03-26 02:23:53 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 370/1251] eta: 0:09:26 lr: 0.000915 loss: 4.3883 (4.5931) grad_norm: 1.1848 (1.2954) time: 0.6243 [2021-03-26 02:23:59 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 380/1251] eta: 0:09:19 lr: 0.000915 loss: 4.7256 (4.5922) grad_norm: 1.2266 (1.2947) time: 0.6287 [2021-03-26 02:24:06 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 390/1251] eta: 0:09:12 lr: 0.000916 loss: 4.7028 (4.5934) grad_norm: 1.1886 (1.2936) time: 0.6300 [2021-03-26 02:24:12 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 400/1251] eta: 0:09:06 lr: 0.000916 loss: 4.7616 (4.5955) grad_norm: 1.2413 (1.2936) time: 0.6286 [2021-03-26 02:24:18 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 410/1251] eta: 0:08:59 lr: 0.000916 loss: 4.7038 (4.5954) grad_norm: 1.2760 (1.2916) time: 0.6307 [2021-03-26 02:24:25 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 420/1251] eta: 0:08:52 lr: 0.000917 loss: 4.8500 (4.5994) grad_norm: 1.2467 (1.2919) time: 0.6346 [2021-03-26 02:24:31 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 430/1251] eta: 0:08:46 lr: 0.000917 loss: 4.8502 (4.6001) grad_norm: 1.1603 (1.2881) time: 0.6337 [2021-03-26 02:24:37 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 440/1251] eta: 0:08:39 lr: 0.000918 loss: 4.9751 (4.6053) grad_norm: 1.1046 (1.2844) time: 0.6299 [2021-03-26 02:24:44 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 450/1251] eta: 0:08:33 lr: 0.000918 loss: 4.9442 (4.6072) grad_norm: 1.1399 (1.2861) time: 0.6320 [2021-03-26 02:24:50 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 460/1251] eta: 0:08:26 lr: 0.000918 loss: 4.5404 (4.6036) grad_norm: 1.1512 (1.2841) time: 0.6390 [2021-03-26 02:24:56 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 470/1251] eta: 0:08:20 lr: 0.000919 loss: 4.3592 (4.6046) grad_norm: 1.2186 (1.2864) time: 0.6307 [2021-03-26 02:25:02 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 480/1251] eta: 0:08:13 lr: 0.000919 loss: 4.8423 (4.6055) grad_norm: 1.3124 (1.2865) time: 0.6221 [2021-03-26 02:25:09 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 490/1251] eta: 0:08:06 lr: 0.000920 loss: 4.9380 (4.6119) grad_norm: 1.3228 (1.2892) time: 0.6261 [2021-03-26 02:25:15 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 500/1251] eta: 0:08:00 lr: 0.000920 loss: 4.8174 (4.6144) grad_norm: 1.3151 (1.2880) time: 0.6316 [2021-03-26 02:25:21 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 510/1251] eta: 0:07:53 lr: 0.000920 loss: 4.7888 (4.6089) grad_norm: 1.2178 (1.2862) time: 0.6323 [2021-03-26 02:25:28 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 520/1251] eta: 0:07:47 lr: 0.000921 loss: 4.4163 (4.6075) grad_norm: 1.2178 (1.2866) time: 0.6299 [2021-03-26 02:25:34 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 530/1251] eta: 0:07:40 lr: 0.000921 loss: 4.4570 (4.6019) grad_norm: 1.2420 (1.2859) time: 0.6309 [2021-03-26 02:25:40 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 540/1251] eta: 0:07:34 lr: 0.000922 loss: 4.2603 (4.6018) grad_norm: 1.2334 (1.2846) time: 0.6308 [2021-03-26 02:25:47 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 550/1251] eta: 0:07:28 lr: 0.000922 loss: 4.5833 (4.6021) grad_norm: 1.2587 (1.2855) time: 0.6421 [2021-03-26 02:25:53 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 560/1251] eta: 0:07:21 lr: 0.000922 loss: 4.5833 (4.5995) grad_norm: 1.3036 (1.2845) time: 0.6466 [2021-03-26 02:26:00 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 570/1251] eta: 0:07:15 lr: 0.000923 loss: 4.6535 (4.6006) grad_norm: 1.3036 (1.2849) time: 0.6330 [2021-03-26 02:26:06 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 580/1251] eta: 0:07:08 lr: 0.000923 loss: 4.8611 (4.6008) grad_norm: 1.3283 (1.2859) time: 0.6269 [2021-03-26 02:26:12 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 590/1251] eta: 0:07:02 lr: 0.000924 loss: 4.8849 (4.6052) grad_norm: 1.2022 (1.2847) time: 0.6272 [2021-03-26 02:26:18 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 600/1251] eta: 0:06:55 lr: 0.000924 loss: 4.7637 (4.5999) grad_norm: 1.1904 (1.2829) time: 0.6267 [2021-03-26 02:26:25 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 610/1251] eta: 0:06:49 lr: 0.000924 loss: 4.4558 (4.5999) grad_norm: 1.1593 (1.2817) time: 0.6304 [2021-03-26 02:26:31 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 620/1251] eta: 0:06:42 lr: 0.000925 loss: 4.4558 (4.5980) grad_norm: 1.2215 (1.2817) time: 0.6301 [2021-03-26 02:26:37 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 630/1251] eta: 0:06:36 lr: 0.000925 loss: 4.6926 (4.5998) grad_norm: 1.2215 (1.2808) time: 0.6285 [2021-03-26 02:26:44 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 640/1251] eta: 0:06:29 lr: 0.000926 loss: 4.6951 (4.6028) grad_norm: 1.1909 (1.2810) time: 0.6338 [2021-03-26 02:26:50 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 650/1251] eta: 0:06:23 lr: 0.000926 loss: 4.6574 (4.6017) grad_norm: 1.1955 (1.2793) time: 0.6328 [2021-03-26 02:26:56 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 660/1251] eta: 0:06:16 lr: 0.000926 loss: 4.5616 (4.6022) grad_norm: 1.1955 (1.2785) time: 0.6293 [2021-03-26 02:27:03 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 670/1251] eta: 0:06:10 lr: 0.000927 loss: 4.5915 (4.5983) grad_norm: 1.2810 (1.2793) time: 0.6289 [2021-03-26 02:27:09 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 680/1251] eta: 0:06:03 lr: 0.000927 loss: 4.7357 (4.6014) grad_norm: 1.1725 (1.2778) time: 0.6283 [2021-03-26 02:27:15 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 690/1251] eta: 0:05:57 lr: 0.000928 loss: 4.9578 (4.5994) grad_norm: 1.2196 (1.2789) time: 0.6349 [2021-03-26 02:27:22 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 700/1251] eta: 0:05:51 lr: 0.000928 loss: 4.4311 (4.5994) grad_norm: 1.2981 (1.2781) time: 0.6353 [2021-03-26 02:27:28 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 710/1251] eta: 0:05:44 lr: 0.000928 loss: 4.5143 (4.6010) grad_norm: 1.1649 (1.2798) time: 0.6287 [2021-03-26 02:27:34 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 720/1251] eta: 0:05:38 lr: 0.000929 loss: 4.7184 (4.6038) grad_norm: 1.2578 (1.2803) time: 0.6363 [2021-03-26 02:27:41 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 730/1251] eta: 0:05:31 lr: 0.000929 loss: 4.6197 (4.6015) grad_norm: 1.2578 (1.2807) time: 0.6356 [2021-03-26 02:27:47 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 740/1251] eta: 0:05:25 lr: 0.000930 loss: 4.6162 (4.6038) grad_norm: 1.2629 (1.2804) time: 0.6406 [2021-03-26 02:27:53 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 750/1251] eta: 0:05:19 lr: 0.000930 loss: 4.8721 (4.6062) grad_norm: 1.2659 (1.2810) time: 0.6477 [2021-03-26 02:28:00 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 760/1251] eta: 0:05:13 lr: 0.000930 loss: 4.8085 (4.6065) grad_norm: 1.2396 (1.2798) time: 0.6430 [2021-03-26 02:28:06 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 770/1251] eta: 0:05:06 lr: 0.000931 loss: 4.4508 (4.6019) grad_norm: 1.0985 (1.2776) time: 0.6325 [2021-03-26 02:28:12 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 780/1251] eta: 0:05:00 lr: 0.000931 loss: 4.5563 (4.6004) grad_norm: 1.1554 (1.2785) time: 0.6287 [2021-03-26 02:28:19 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 790/1251] eta: 0:04:53 lr: 0.000932 loss: 4.6552 (4.6027) grad_norm: 1.1722 (1.2768) time: 0.6341 [2021-03-26 02:28:25 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 800/1251] eta: 0:04:47 lr: 0.000932 loss: 4.7949 (4.6061) grad_norm: 1.0906 (1.2748) time: 0.6352 [2021-03-26 02:28:31 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 810/1251] eta: 0:04:40 lr: 0.000932 loss: 4.8576 (4.6059) grad_norm: 1.1151 (1.2741) time: 0.6297 [2021-03-26 02:28:38 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 820/1251] eta: 0:04:34 lr: 0.000933 loss: 4.8035 (4.6056) grad_norm: 1.2068 (1.2763) time: 0.6302 [2021-03-26 02:28:44 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 830/1251] eta: 0:04:28 lr: 0.000933 loss: 4.8035 (4.6077) grad_norm: 1.2763 (1.2761) time: 0.6362 [2021-03-26 02:28:50 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 840/1251] eta: 0:04:21 lr: 0.000934 loss: 4.7722 (4.6078) grad_norm: 1.2482 (1.2759) time: 0.6335 [2021-03-26 02:28:57 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 850/1251] eta: 0:04:15 lr: 0.000934 loss: 4.6067 (4.6091) grad_norm: 1.3911 (1.2793) time: 0.6286 [2021-03-26 02:29:03 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 860/1251] eta: 0:04:08 lr: 0.000934 loss: 4.9053 (4.6080) grad_norm: 1.2845 (1.2784) time: 0.6251 [2021-03-26 02:29:09 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 870/1251] eta: 0:04:02 lr: 0.000935 loss: 4.8070 (4.6073) grad_norm: 1.0759 (1.2760) time: 0.6246 [2021-03-26 02:29:16 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 880/1251] eta: 0:03:56 lr: 0.000935 loss: 4.8070 (4.6082) grad_norm: 1.0702 (1.2758) time: 0.6299 [2021-03-26 02:29:22 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 890/1251] eta: 0:03:49 lr: 0.000936 loss: 4.6367 (4.6051) grad_norm: 1.2108 (1.2755) time: 0.6346 [2021-03-26 02:29:28 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 900/1251] eta: 0:03:43 lr: 0.000936 loss: 4.6251 (4.6032) grad_norm: 1.2108 (1.2752) time: 0.6307 [2021-03-26 02:29:35 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 910/1251] eta: 0:03:37 lr: 0.000936 loss: 4.6320 (4.6004) grad_norm: 1.2122 (1.2753) time: 0.6314 [2021-03-26 02:29:41 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 920/1251] eta: 0:03:30 lr: 0.000937 loss: 4.6651 (4.6007) grad_norm: 1.2102 (1.2741) time: 0.6310 [2021-03-26 02:29:47 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 930/1251] eta: 0:03:24 lr: 0.000937 loss: 4.7614 (4.6028) grad_norm: 1.1940 (1.2739) time: 0.6320 [2021-03-26 02:29:53 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 940/1251] eta: 0:03:17 lr: 0.000938 loss: 4.8242 (4.6040) grad_norm: 1.2596 (1.2750) time: 0.6330 [2021-03-26 02:30:00 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 950/1251] eta: 0:03:11 lr: 0.000938 loss: 4.8801 (4.6050) grad_norm: 1.2844 (1.2742) time: 0.6326 [2021-03-26 02:30:06 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 960/1251] eta: 0:03:05 lr: 0.000938 loss: 4.5070 (4.6050) grad_norm: 1.1753 (1.2747) time: 0.6312 [2021-03-26 02:30:12 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 970/1251] eta: 0:02:58 lr: 0.000939 loss: 4.6162 (4.6049) grad_norm: 1.1412 (1.2737) time: 0.6316 [2021-03-26 02:30:19 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 980/1251] eta: 0:02:52 lr: 0.000939 loss: 4.6162 (4.6020) grad_norm: 1.1407 (1.2732) time: 0.6308 [2021-03-26 02:30:25 swin_base_patch4_window7_224] INFO: Epoch: [18] [ 990/1251] eta: 0:02:46 lr: 0.000940 loss: 4.4182 (4.6024) grad_norm: 1.2720 (1.2730) time: 0.6307 [2021-03-26 02:30:31 swin_base_patch4_window7_224] INFO: Epoch: [18] [1000/1251] eta: 0:02:39 lr: 0.000940 loss: 4.7563 (4.6030) grad_norm: 1.2118 (1.2725) time: 0.6336 [2021-03-26 02:30:38 swin_base_patch4_window7_224] INFO: Epoch: [18] [1010/1251] eta: 0:02:33 lr: 0.000940 loss: 4.5441 (4.6014) grad_norm: 1.2759 (1.2732) time: 0.6298 [2021-03-26 02:30:44 swin_base_patch4_window7_224] INFO: Epoch: [18] [1020/1251] eta: 0:02:26 lr: 0.000941 loss: 4.5729 (4.6021) grad_norm: 1.2664 (1.2729) time: 0.6305 [2021-03-26 02:30:50 swin_base_patch4_window7_224] INFO: Epoch: [18] [1030/1251] eta: 0:02:20 lr: 0.000941 loss: 4.5729 (4.6020) grad_norm: 1.2221 (1.2729) time: 0.6345 [2021-03-26 02:30:57 swin_base_patch4_window7_224] INFO: Epoch: [18] [1040/1251] eta: 0:02:14 lr: 0.000942 loss: 4.6399 (4.6035) grad_norm: 1.1441 (1.2717) time: 0.6309 [2021-03-26 02:31:03 swin_base_patch4_window7_224] INFO: Epoch: [18] [1050/1251] eta: 0:02:07 lr: 0.000942 loss: 4.7523 (4.6043) grad_norm: 1.0478 (1.2703) time: 0.6284 [2021-03-26 02:31:09 swin_base_patch4_window7_224] INFO: Epoch: [18] [1060/1251] eta: 0:02:01 lr: 0.000942 loss: 4.8389 (4.6063) grad_norm: 1.1118 (1.2699) time: 0.6266 [2021-03-26 02:31:15 swin_base_patch4_window7_224] INFO: Epoch: [18] [1070/1251] eta: 0:01:55 lr: 0.000943 loss: 4.7656 (4.6062) grad_norm: 1.1506 (1.2695) time: 0.6247 [2021-03-26 02:31:22 swin_base_patch4_window7_224] INFO: Epoch: [18] [1080/1251] eta: 0:01:48 lr: 0.000943 loss: 4.6051 (4.6075) grad_norm: 1.1506 (1.2695) time: 0.6307 [2021-03-26 02:31:28 swin_base_patch4_window7_224] INFO: Epoch: [18] [1090/1251] eta: 0:01:42 lr: 0.000944 loss: 4.8442 (4.6095) grad_norm: 1.2234 (1.2692) time: 0.6369 [2021-03-26 02:31:35 swin_base_patch4_window7_224] INFO: Epoch: [18] [1100/1251] eta: 0:01:35 lr: 0.000944 loss: 4.8442 (4.6104) grad_norm: 1.1884 (1.2683) time: 0.6353 [2021-03-26 02:31:41 swin_base_patch4_window7_224] INFO: Epoch: [18] [1110/1251] eta: 0:01:29 lr: 0.000944 loss: 4.6933 (4.6124) grad_norm: 1.1607 (1.2681) time: 0.6309 [2021-03-26 02:31:47 swin_base_patch4_window7_224] INFO: Epoch: [18] [1120/1251] eta: 0:01:23 lr: 0.000945 loss: 4.6758 (4.6121) grad_norm: 1.1607 (1.2671) time: 0.6269 [2021-03-26 02:31:53 swin_base_patch4_window7_224] INFO: Epoch: [18] [1130/1251] eta: 0:01:16 lr: 0.000945 loss: 4.5664 (4.6099) grad_norm: 1.0896 (1.2659) time: 0.6257 [2021-03-26 02:32:00 swin_base_patch4_window7_224] INFO: Epoch: [18] [1140/1251] eta: 0:01:10 lr: 0.000946 loss: 4.4755 (4.6102) grad_norm: 1.1424 (1.2656) time: 0.6280 [2021-03-26 02:32:06 swin_base_patch4_window7_224] INFO: Epoch: [18] [1150/1251] eta: 0:01:04 lr: 0.000946 loss: 4.5948 (4.6107) grad_norm: 1.2180 (1.2663) time: 0.6281 [2021-03-26 02:32:12 swin_base_patch4_window7_224] INFO: Epoch: [18] [1160/1251] eta: 0:00:57 lr: 0.000946 loss: 4.8651 (4.6136) grad_norm: 1.1959 (1.2650) time: 0.6329 [2021-03-26 02:32:19 swin_base_patch4_window7_224] INFO: Epoch: [18] [1170/1251] eta: 0:00:51 lr: 0.000947 loss: 4.8532 (4.6128) grad_norm: 1.2509 (1.2660) time: 0.6341 [2021-03-26 02:32:25 swin_base_patch4_window7_224] INFO: Epoch: [18] [1180/1251] eta: 0:00:45 lr: 0.000947 loss: 4.4613 (4.6129) grad_norm: 1.3161 (1.2666) time: 0.6294 [2021-03-26 02:32:31 swin_base_patch4_window7_224] INFO: Epoch: [18] [1190/1251] eta: 0:00:38 lr: 0.000948 loss: 4.4834 (4.6133) grad_norm: 1.1791 (1.2654) time: 0.6228 [2021-03-26 02:32:37 swin_base_patch4_window7_224] INFO: Epoch: [18] [1200/1251] eta: 0:00:32 lr: 0.000948 loss: 4.7417 (4.6147) grad_norm: 1.1072 (1.2649) time: 0.6264 [2021-03-26 02:32:44 swin_base_patch4_window7_224] INFO: Epoch: [18] [1210/1251] eta: 0:00:26 lr: 0.000948 loss: 4.7087 (4.6123) grad_norm: 1.1820 (1.2678) time: 0.6377 [2021-03-26 02:32:50 swin_base_patch4_window7_224] INFO: Epoch: [18] [1220/1251] eta: 0:00:19 lr: 0.000949 loss: 4.5712 (4.6123) grad_norm: 1.1724 (1.2672) time: 0.6351 [2021-03-26 02:32:56 swin_base_patch4_window7_224] INFO: Epoch: [18] [1230/1251] eta: 0:00:13 lr: 0.000949 loss: 4.6377 (4.6117) grad_norm: 1.1724 (1.2670) time: 0.6284 [2021-03-26 02:33:03 swin_base_patch4_window7_224] INFO: Epoch: [18] [1240/1251] eta: 0:00:06 lr: 0.000950 loss: 4.5207 (4.6100) grad_norm: 1.1974 (1.2664) time: 0.6268 [2021-03-26 02:33:09 swin_base_patch4_window7_224] INFO: Epoch: [18] [1250/1251] eta: 0:00:00 lr: 0.000950 loss: 4.7009 (4.6114) grad_norm: 1.1754 (1.2666) time: 0.6248 [2021-03-26 02:33:13 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:34 loss: 1.9637 (1.9637) acc1: 51.5625 (51.5625) acc5: 85.9375 (85.9375) [2021-03-26 02:33:15 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.9414 (1.9477) acc1: 57.8125 (58.8068) acc5: 82.8125 (81.3920) [2021-03-26 02:33:17 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.8766 (1.8876) acc1: 59.3750 (59.3750) acc5: 81.2500 (80.9524) [2021-03-26 02:33:19 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.9143 (1.9227) acc1: 57.8125 (57.3589) acc5: 78.1250 (80.3931) [2021-03-26 02:33:22 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.9362 (1.9207) acc1: 54.6875 (57.2790) acc5: 79.6875 (80.6402) [2021-03-26 02:33:23 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.9545 (1.9429) acc1: 53.1250 (56.5120) acc5: 81.2500 (80.3520) [2021-03-26 02:33:25 swin_base_patch4_window7_224] INFO: * Acc@1 57.046 Acc@5 80.978 loss 1.933 [2021-03-26 02:33:25 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 57.0% [2021-03-26 02:33:25 swin_base_patch4_window7_224] INFO: Max accuracy: 57.05% [2021-03-26 02:33:30 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 0/1251] eta: 1:29:16 lr: 0.000950 loss: 4.4415 (4.4415) grad_norm: 1.4090 (1.4090) time: 4.2815 [2021-03-26 02:33:36 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 10/1251] eta: 0:20:19 lr: 0.000950 loss: 4.4480 (4.4703) grad_norm: 1.2866 (1.3461) time: 0.9823 [2021-03-26 02:33:42 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 20/1251] eta: 0:16:39 lr: 0.000951 loss: 4.4480 (4.3456) grad_norm: 1.2224 (1.2572) time: 0.6383 [2021-03-26 02:33:49 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 30/1251] eta: 0:15:24 lr: 0.000951 loss: 4.3727 (4.3854) grad_norm: 1.1374 (1.2537) time: 0.6329 [2021-03-26 02:33:55 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 40/1251] eta: 0:14:37 lr: 0.000952 loss: 4.3975 (4.4399) grad_norm: 1.1612 (1.2412) time: 0.6324 [2021-03-26 02:34:02 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 50/1251] eta: 0:14:10 lr: 0.000952 loss: 4.4965 (4.4304) grad_norm: 1.1772 (1.2645) time: 0.6324 [2021-03-26 02:34:08 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 60/1251] eta: 0:13:48 lr: 0.000952 loss: 4.5992 (4.4529) grad_norm: 1.3543 (1.2941) time: 0.6368 [2021-03-26 02:34:14 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 70/1251] eta: 0:13:29 lr: 0.000953 loss: 4.7763 (4.4833) grad_norm: 1.2427 (1.2808) time: 0.6288 [2021-03-26 02:34:20 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 80/1251] eta: 0:13:15 lr: 0.000953 loss: 4.5865 (4.4676) grad_norm: 1.1961 (1.2837) time: 0.6295 [2021-03-26 02:34:27 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 90/1251] eta: 0:13:01 lr: 0.000954 loss: 4.4681 (4.4722) grad_norm: 1.1986 (1.2835) time: 0.6287 [2021-03-26 02:34:33 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 100/1251] eta: 0:12:50 lr: 0.000954 loss: 4.6530 (4.5101) grad_norm: 1.1986 (1.2702) time: 0.6278 [2021-03-26 02:34:39 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 110/1251] eta: 0:12:38 lr: 0.000954 loss: 4.6530 (4.5070) grad_norm: 1.2054 (1.2686) time: 0.6270 [2021-03-26 02:34:46 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 120/1251] eta: 0:12:28 lr: 0.000955 loss: 4.7642 (4.5290) grad_norm: 1.2985 (1.2720) time: 0.6254 [2021-03-26 02:34:52 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 130/1251] eta: 0:12:20 lr: 0.000955 loss: 4.7642 (4.5328) grad_norm: 1.2247 (1.2677) time: 0.6340 [2021-03-26 02:34:58 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 140/1251] eta: 0:12:10 lr: 0.000956 loss: 4.5988 (4.5380) grad_norm: 1.1012 (1.2556) time: 0.6295 [2021-03-26 02:35:04 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 150/1251] eta: 0:12:02 lr: 0.000956 loss: 4.6757 (4.5430) grad_norm: 1.1780 (1.2579) time: 0.6272 [2021-03-26 02:35:11 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 160/1251] eta: 0:11:53 lr: 0.000956 loss: 4.6752 (4.5479) grad_norm: 1.2018 (1.2519) time: 0.6309 [2021-03-26 02:35:17 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 170/1251] eta: 0:11:46 lr: 0.000957 loss: 4.6146 (4.5542) grad_norm: 1.1584 (1.2615) time: 0.6334 [2021-03-26 02:35:24 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 180/1251] eta: 0:11:38 lr: 0.000957 loss: 4.6080 (4.5535) grad_norm: 1.4409 (1.2746) time: 0.6391 [2021-03-26 02:35:30 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 190/1251] eta: 0:11:31 lr: 0.000958 loss: 4.6699 (4.5612) grad_norm: 1.3139 (1.2722) time: 0.6393 [2021-03-26 02:35:36 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 200/1251] eta: 0:11:24 lr: 0.000958 loss: 4.7220 (4.5672) grad_norm: 1.1595 (1.2723) time: 0.6409 [2021-03-26 02:35:43 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 210/1251] eta: 0:11:16 lr: 0.000958 loss: 4.6586 (4.5640) grad_norm: 1.2208 (1.2713) time: 0.6348 [2021-03-26 02:35:49 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 220/1251] eta: 0:11:09 lr: 0.000959 loss: 4.6586 (4.5696) grad_norm: 1.1828 (1.2723) time: 0.6337 [2021-03-26 02:35:55 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 230/1251] eta: 0:11:02 lr: 0.000959 loss: 4.5880 (4.5635) grad_norm: 1.1088 (1.2660) time: 0.6310 [2021-03-26 02:36:02 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 240/1251] eta: 0:10:54 lr: 0.000960 loss: 4.7896 (4.5821) grad_norm: 1.0740 (1.2594) time: 0.6279 [2021-03-26 02:36:08 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 250/1251] eta: 0:10:47 lr: 0.000960 loss: 4.8582 (4.5803) grad_norm: 1.1152 (1.2601) time: 0.6344 [2021-03-26 02:36:14 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 260/1251] eta: 0:10:41 lr: 0.000960 loss: 4.6743 (4.5771) grad_norm: 1.2447 (1.2609) time: 0.6358 [2021-03-26 02:36:21 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 270/1251] eta: 0:10:33 lr: 0.000961 loss: 4.3975 (4.5650) grad_norm: 1.2378 (1.2611) time: 0.6307 [2021-03-26 02:36:27 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 280/1251] eta: 0:10:26 lr: 0.000961 loss: 4.4608 (4.5696) grad_norm: 1.1864 (1.2598) time: 0.6265 [2021-03-26 02:36:33 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 290/1251] eta: 0:10:19 lr: 0.000962 loss: 4.6876 (4.5717) grad_norm: 1.1188 (1.2544) time: 0.6273 [2021-03-26 02:36:39 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 300/1251] eta: 0:10:12 lr: 0.000962 loss: 4.5954 (4.5652) grad_norm: 1.2080 (1.2584) time: 0.6286 [2021-03-26 02:36:46 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 310/1251] eta: 0:10:06 lr: 0.000962 loss: 4.5112 (4.5602) grad_norm: 1.2916 (1.2607) time: 0.6333 [2021-03-26 02:36:52 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 320/1251] eta: 0:09:59 lr: 0.000963 loss: 4.5905 (4.5638) grad_norm: 1.2679 (1.2592) time: 0.6339 [2021-03-26 02:36:58 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 330/1251] eta: 0:09:52 lr: 0.000963 loss: 4.7452 (4.5742) grad_norm: 1.1997 (1.2594) time: 0.6336 [2021-03-26 02:37:05 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 340/1251] eta: 0:09:45 lr: 0.000964 loss: 4.7308 (4.5752) grad_norm: 1.2461 (1.2623) time: 0.6343 [2021-03-26 02:37:11 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 350/1251] eta: 0:09:38 lr: 0.000964 loss: 4.6058 (4.5701) grad_norm: 1.2461 (1.2665) time: 0.6250 [2021-03-26 02:37:17 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 360/1251] eta: 0:09:32 lr: 0.000964 loss: 4.3954 (4.5585) grad_norm: 1.1848 (1.2644) time: 0.6272 [2021-03-26 02:37:24 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 370/1251] eta: 0:09:25 lr: 0.000965 loss: 4.4966 (4.5624) grad_norm: 1.1605 (1.2624) time: 0.6323 [2021-03-26 02:37:30 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 380/1251] eta: 0:09:18 lr: 0.000965 loss: 4.7291 (4.5675) grad_norm: 1.1524 (1.2606) time: 0.6231 [2021-03-26 02:37:36 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 390/1251] eta: 0:09:11 lr: 0.000966 loss: 4.8964 (4.5732) grad_norm: 1.1784 (1.2593) time: 0.6212 [2021-03-26 02:37:42 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 400/1251] eta: 0:09:04 lr: 0.000966 loss: 4.8220 (4.5754) grad_norm: 1.2032 (1.2588) time: 0.6238 [2021-03-26 02:37:49 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 410/1251] eta: 0:08:58 lr: 0.000966 loss: 4.6010 (4.5730) grad_norm: 1.1795 (1.2584) time: 0.6279 [2021-03-26 02:37:55 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 420/1251] eta: 0:08:51 lr: 0.000967 loss: 4.6301 (4.5725) grad_norm: 1.1145 (1.2560) time: 0.6265 [2021-03-26 02:38:01 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 430/1251] eta: 0:08:45 lr: 0.000967 loss: 4.6915 (4.5739) grad_norm: 1.2316 (1.2567) time: 0.6251 [2021-03-26 02:38:07 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 440/1251] eta: 0:08:38 lr: 0.000968 loss: 4.6915 (4.5767) grad_norm: 1.1980 (1.2555) time: 0.6304 [2021-03-26 02:38:14 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 450/1251] eta: 0:08:32 lr: 0.000968 loss: 4.6582 (4.5749) grad_norm: 1.1308 (1.2528) time: 0.6356 [2021-03-26 02:38:20 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 460/1251] eta: 0:08:25 lr: 0.000968 loss: 4.6582 (4.5745) grad_norm: 1.0870 (1.2510) time: 0.6331 [2021-03-26 02:38:26 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 470/1251] eta: 0:08:18 lr: 0.000969 loss: 4.6766 (4.5732) grad_norm: 1.1770 (1.2534) time: 0.6290 [2021-03-26 02:38:33 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 480/1251] eta: 0:08:12 lr: 0.000969 loss: 4.7746 (4.5776) grad_norm: 1.2543 (1.2526) time: 0.6279 [2021-03-26 02:38:39 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 490/1251] eta: 0:08:05 lr: 0.000970 loss: 4.7746 (4.5765) grad_norm: 1.2332 (1.2531) time: 0.6312 [2021-03-26 02:38:45 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 500/1251] eta: 0:07:59 lr: 0.000970 loss: 4.8529 (4.5814) grad_norm: 1.1671 (1.2528) time: 0.6326 [2021-03-26 02:38:52 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 510/1251] eta: 0:07:52 lr: 0.000970 loss: 4.8204 (4.5845) grad_norm: 1.1409 (1.2525) time: 0.6296 [2021-03-26 02:38:58 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 520/1251] eta: 0:07:46 lr: 0.000971 loss: 4.5781 (4.5783) grad_norm: 1.1841 (1.2510) time: 0.6305 [2021-03-26 02:39:04 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 530/1251] eta: 0:07:39 lr: 0.000971 loss: 4.5781 (4.5797) grad_norm: 1.1184 (1.2481) time: 0.6262 [2021-03-26 02:39:11 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 540/1251] eta: 0:07:33 lr: 0.000972 loss: 4.7455 (4.5852) grad_norm: 1.0740 (1.2476) time: 0.6327 [2021-03-26 02:39:17 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 550/1251] eta: 0:07:27 lr: 0.000972 loss: 4.7455 (4.5870) grad_norm: 1.2477 (1.2473) time: 0.6477 [2021-03-26 02:39:23 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 560/1251] eta: 0:07:20 lr: 0.000972 loss: 4.7315 (4.5882) grad_norm: 1.2052 (1.2463) time: 0.6405 [2021-03-26 02:39:30 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 570/1251] eta: 0:07:14 lr: 0.000973 loss: 4.7740 (4.5904) grad_norm: 1.2052 (1.2471) time: 0.6309 [2021-03-26 02:39:36 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 580/1251] eta: 0:07:08 lr: 0.000973 loss: 4.7957 (4.5915) grad_norm: 1.1785 (1.2468) time: 0.6364 [2021-03-26 02:39:42 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 590/1251] eta: 0:07:01 lr: 0.000974 loss: 4.5675 (4.5898) grad_norm: 1.1516 (1.2465) time: 0.6305 [2021-03-26 02:39:49 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 600/1251] eta: 0:06:55 lr: 0.000974 loss: 4.3971 (4.5880) grad_norm: 1.1924 (1.2465) time: 0.6291 [2021-03-26 02:39:55 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 610/1251] eta: 0:06:48 lr: 0.000974 loss: 4.3774 (4.5843) grad_norm: 1.2126 (1.2489) time: 0.6336 [2021-03-26 02:40:01 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 620/1251] eta: 0:06:42 lr: 0.000975 loss: 4.3305 (4.5820) grad_norm: 1.1963 (1.2469) time: 0.6276 [2021-03-26 02:40:08 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 630/1251] eta: 0:06:35 lr: 0.000975 loss: 4.4506 (4.5837) grad_norm: 1.0680 (1.2439) time: 0.6256 [2021-03-26 02:40:14 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 640/1251] eta: 0:06:29 lr: 0.000976 loss: 4.7698 (4.5855) grad_norm: 1.0680 (1.2414) time: 0.6229 [2021-03-26 02:40:20 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 650/1251] eta: 0:06:22 lr: 0.000976 loss: 4.7454 (4.5851) grad_norm: 1.0920 (1.2395) time: 0.6216 [2021-03-26 02:40:26 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 660/1251] eta: 0:06:16 lr: 0.000976 loss: 4.4920 (4.5802) grad_norm: 1.0999 (1.2374) time: 0.6237 [2021-03-26 02:40:32 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 670/1251] eta: 0:06:09 lr: 0.000977 loss: 4.4329 (4.5799) grad_norm: 1.0999 (1.2365) time: 0.6269 [2021-03-26 02:40:39 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 680/1251] eta: 0:06:03 lr: 0.000977 loss: 4.1114 (4.5722) grad_norm: 1.0687 (1.2357) time: 0.6329 [2021-03-26 02:40:45 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 690/1251] eta: 0:05:56 lr: 0.000978 loss: 4.3648 (4.5736) grad_norm: 1.2610 (1.2369) time: 0.6347 [2021-03-26 02:40:51 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 700/1251] eta: 0:05:50 lr: 0.000978 loss: 4.6593 (4.5736) grad_norm: 1.1986 (1.2347) time: 0.6293 [2021-03-26 02:40:58 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 710/1251] eta: 0:05:44 lr: 0.000978 loss: 4.5356 (4.5752) grad_norm: 1.0351 (1.2332) time: 0.6256 [2021-03-26 02:41:04 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 720/1251] eta: 0:05:37 lr: 0.000979 loss: 4.6669 (4.5762) grad_norm: 1.1167 (1.2324) time: 0.6265 [2021-03-26 02:41:10 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 730/1251] eta: 0:05:31 lr: 0.000979 loss: 4.6849 (4.5758) grad_norm: 1.1432 (1.2311) time: 0.6295 [2021-03-26 02:41:17 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 740/1251] eta: 0:05:24 lr: 0.000980 loss: 4.7581 (4.5778) grad_norm: 1.1185 (1.2292) time: 0.6390 [2021-03-26 02:41:23 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 750/1251] eta: 0:05:18 lr: 0.000980 loss: 4.7557 (4.5771) grad_norm: 1.0949 (1.2276) time: 0.6372 [2021-03-26 02:41:29 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 760/1251] eta: 0:05:12 lr: 0.000980 loss: 4.6418 (4.5766) grad_norm: 1.0903 (1.2266) time: 0.6265 [2021-03-26 02:41:36 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 770/1251] eta: 0:05:05 lr: 0.000981 loss: 4.8520 (4.5822) grad_norm: 1.0714 (1.2249) time: 0.6238 [2021-03-26 02:41:42 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 780/1251] eta: 0:04:59 lr: 0.000981 loss: 4.9234 (4.5852) grad_norm: 1.1111 (1.2244) time: 0.6233 [2021-03-26 02:41:48 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 790/1251] eta: 0:04:52 lr: 0.000982 loss: 4.4764 (4.5830) grad_norm: 1.1640 (1.2234) time: 0.6295 [2021-03-26 02:41:54 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 800/1251] eta: 0:04:46 lr: 0.000982 loss: 4.5510 (4.5822) grad_norm: 1.1799 (1.2237) time: 0.6336 [2021-03-26 02:42:01 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 810/1251] eta: 0:04:40 lr: 0.000982 loss: 4.8578 (4.5857) grad_norm: 1.1928 (1.2244) time: 0.6289 [2021-03-26 02:42:07 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 820/1251] eta: 0:04:33 lr: 0.000983 loss: 4.9503 (4.5860) grad_norm: 1.1688 (1.2243) time: 0.6326 [2021-03-26 02:42:13 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 830/1251] eta: 0:04:27 lr: 0.000983 loss: 4.5259 (4.5862) grad_norm: 1.1688 (1.2256) time: 0.6354 [2021-03-26 02:42:20 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 840/1251] eta: 0:04:21 lr: 0.000984 loss: 4.5252 (4.5843) grad_norm: 1.2561 (inf) time: 0.6282 [2021-03-26 02:42:26 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 850/1251] eta: 0:04:14 lr: 0.000984 loss: 4.4280 (4.5840) grad_norm: 1.1270 (inf) time: 0.6274 [2021-03-26 02:42:32 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 860/1251] eta: 0:04:08 lr: 0.000984 loss: 4.7051 (4.5860) grad_norm: 1.2338 (inf) time: 0.6349 [2021-03-26 02:42:39 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 870/1251] eta: 0:04:01 lr: 0.000985 loss: 4.6445 (4.5854) grad_norm: 1.2715 (inf) time: 0.6359 [2021-03-26 02:42:45 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 880/1251] eta: 0:03:55 lr: 0.000985 loss: 4.7522 (4.5870) grad_norm: 1.1657 (inf) time: 0.6307 [2021-03-26 02:42:51 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 890/1251] eta: 0:03:49 lr: 0.000986 loss: 4.8490 (4.5888) grad_norm: 1.1117 (inf) time: 0.6295 [2021-03-26 02:42:58 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 900/1251] eta: 0:03:42 lr: 0.000986 loss: 4.8490 (4.5893) grad_norm: 1.1117 (inf) time: 0.6277 [2021-03-26 02:43:04 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 910/1251] eta: 0:03:36 lr: 0.000986 loss: 4.8912 (4.5895) grad_norm: 1.1971 (inf) time: 0.6228 [2021-03-26 02:43:10 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 920/1251] eta: 0:03:30 lr: 0.000987 loss: 4.6824 (4.5902) grad_norm: 1.3363 (inf) time: 0.6235 [2021-03-26 02:43:16 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 930/1251] eta: 0:03:23 lr: 0.000987 loss: 4.6043 (4.5899) grad_norm: 1.2468 (inf) time: 0.6278 [2021-03-26 02:43:23 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 940/1251] eta: 0:03:17 lr: 0.000988 loss: 4.6043 (4.5888) grad_norm: 1.1933 (inf) time: 0.6340 [2021-03-26 02:43:29 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 950/1251] eta: 0:03:11 lr: 0.000988 loss: 4.6295 (4.5893) grad_norm: 1.1933 (inf) time: 0.6380 [2021-03-26 02:43:35 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 960/1251] eta: 0:03:04 lr: 0.000988 loss: 4.6127 (4.5888) grad_norm: 1.1376 (inf) time: 0.6321 [2021-03-26 02:43:42 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 970/1251] eta: 0:02:58 lr: 0.000989 loss: 4.7979 (4.5941) grad_norm: 1.1251 (inf) time: 0.6332 [2021-03-26 02:43:48 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 980/1251] eta: 0:02:51 lr: 0.000989 loss: 4.9449 (4.5959) grad_norm: 1.1866 (inf) time: 0.6308 [2021-03-26 02:43:54 swin_base_patch4_window7_224] INFO: Epoch: [19] [ 990/1251] eta: 0:02:45 lr: 0.000990 loss: 4.7420 (4.5963) grad_norm: 1.2205 (inf) time: 0.6253 [2021-03-26 02:44:01 swin_base_patch4_window7_224] INFO: Epoch: [19] [1000/1251] eta: 0:02:39 lr: 0.000990 loss: 4.6926 (4.5974) grad_norm: 1.1669 (inf) time: 0.6323 [2021-03-26 02:44:07 swin_base_patch4_window7_224] INFO: Epoch: [19] [1010/1251] eta: 0:02:32 lr: 0.000990 loss: 4.7956 (4.5975) grad_norm: 1.0658 (inf) time: 0.6338 [2021-03-26 02:44:13 swin_base_patch4_window7_224] INFO: Epoch: [19] [1020/1251] eta: 0:02:26 lr: 0.000991 loss: 4.3076 (4.5922) grad_norm: 1.2311 (inf) time: 0.6287 [2021-03-26 02:44:19 swin_base_patch4_window7_224] INFO: Epoch: [19] [1030/1251] eta: 0:02:20 lr: 0.000991 loss: 4.2607 (4.5902) grad_norm: 1.2577 (inf) time: 0.6249 [2021-03-26 02:44:26 swin_base_patch4_window7_224] INFO: Epoch: [19] [1040/1251] eta: 0:02:13 lr: 0.000992 loss: 4.4137 (4.5881) grad_norm: 1.2172 (inf) time: 0.6257 [2021-03-26 02:44:32 swin_base_patch4_window7_224] INFO: Epoch: [19] [1050/1251] eta: 0:02:07 lr: 0.000992 loss: 4.5102 (4.5889) grad_norm: 1.1458 (inf) time: 0.6251 [2021-03-26 02:44:38 swin_base_patch4_window7_224] INFO: Epoch: [19] [1060/1251] eta: 0:02:01 lr: 0.000992 loss: 4.4975 (4.5856) grad_norm: 1.2003 (inf) time: 0.6307 [2021-03-26 02:44:45 swin_base_patch4_window7_224] INFO: Epoch: [19] [1070/1251] eta: 0:01:54 lr: 0.000993 loss: 4.1662 (4.5839) grad_norm: 1.2599 (inf) time: 0.6403 [2021-03-26 02:44:51 swin_base_patch4_window7_224] INFO: Epoch: [19] [1080/1251] eta: 0:01:48 lr: 0.000993 loss: 4.6581 (4.5850) grad_norm: 1.2612 (inf) time: 0.6394 [2021-03-26 02:44:57 swin_base_patch4_window7_224] INFO: Epoch: [19] [1090/1251] eta: 0:01:42 lr: 0.000994 loss: 4.6581 (4.5847) grad_norm: 1.2612 (inf) time: 0.6330 [2021-03-26 02:45:04 swin_base_patch4_window7_224] INFO: Epoch: [19] [1100/1251] eta: 0:01:35 lr: 0.000994 loss: 4.6704 (4.5859) grad_norm: 1.1408 (inf) time: 0.6274 [2021-03-26 02:45:10 swin_base_patch4_window7_224] INFO: Epoch: [19] [1110/1251] eta: 0:01:29 lr: 0.000994 loss: 4.7536 (4.5846) grad_norm: 1.1387 (inf) time: 0.6283 [2021-03-26 02:45:16 swin_base_patch4_window7_224] INFO: Epoch: [19] [1120/1251] eta: 0:01:23 lr: 0.000995 loss: 4.6588 (4.5857) grad_norm: 1.1540 (inf) time: 0.6289 [2021-03-26 02:45:22 swin_base_patch4_window7_224] INFO: Epoch: [19] [1130/1251] eta: 0:01:16 lr: 0.000995 loss: 4.7532 (4.5847) grad_norm: 1.2154 (inf) time: 0.6247 [2021-03-26 02:45:29 swin_base_patch4_window7_224] INFO: Epoch: [19] [1140/1251] eta: 0:01:10 lr: 0.000996 loss: 4.2178 (4.5824) grad_norm: 1.1050 (inf) time: 0.6271 [2021-03-26 02:45:35 swin_base_patch4_window7_224] INFO: Epoch: [19] [1150/1251] eta: 0:01:04 lr: 0.000996 loss: 4.4384 (4.5823) grad_norm: 1.0477 (inf) time: 0.6281 [2021-03-26 02:45:41 swin_base_patch4_window7_224] INFO: Epoch: [19] [1160/1251] eta: 0:00:57 lr: 0.000996 loss: 4.6322 (4.5811) grad_norm: 1.0551 (inf) time: 0.6257 [2021-03-26 02:45:48 swin_base_patch4_window7_224] INFO: Epoch: [19] [1170/1251] eta: 0:00:51 lr: 0.000997 loss: 4.7582 (4.5812) grad_norm: 1.1109 (inf) time: 0.6267 [2021-03-26 02:45:54 swin_base_patch4_window7_224] INFO: Epoch: [19] [1180/1251] eta: 0:00:44 lr: 0.000997 loss: 4.7417 (4.5817) grad_norm: 1.1533 (inf) time: 0.6285 [2021-03-26 02:46:00 swin_base_patch4_window7_224] INFO: Epoch: [19] [1190/1251] eta: 0:00:38 lr: 0.000998 loss: 4.7936 (4.5845) grad_norm: 1.1299 (inf) time: 0.6283 [2021-03-26 02:46:06 swin_base_patch4_window7_224] INFO: Epoch: [19] [1200/1251] eta: 0:00:32 lr: 0.000998 loss: 4.9251 (4.5838) grad_norm: 1.1141 (inf) time: 0.6268 [2021-03-26 02:46:13 swin_base_patch4_window7_224] INFO: Epoch: [19] [1210/1251] eta: 0:00:25 lr: 0.000998 loss: 4.8805 (4.5866) grad_norm: 1.0919 (inf) time: 0.6275 [2021-03-26 02:46:19 swin_base_patch4_window7_224] INFO: Epoch: [19] [1220/1251] eta: 0:00:19 lr: 0.000999 loss: 4.7954 (4.5841) grad_norm: 1.1325 (inf) time: 0.6272 [2021-03-26 02:46:25 swin_base_patch4_window7_224] INFO: Epoch: [19] [1230/1251] eta: 0:00:13 lr: 0.000999 loss: 4.6691 (4.5851) grad_norm: 1.1955 (inf) time: 0.6265 [2021-03-26 02:46:31 swin_base_patch4_window7_224] INFO: Epoch: [19] [1240/1251] eta: 0:00:06 lr: 0.001000 loss: 4.7439 (4.5858) grad_norm: 1.1681 (inf) time: 0.6258 [2021-03-26 02:46:38 swin_base_patch4_window7_224] INFO: Epoch: [19] [1250/1251] eta: 0:00:00 lr: 0.001000 loss: 4.8607 (4.5849) grad_norm: 1.1909 (inf) time: 0.6215 [2021-03-26 02:46:42 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:45 loss: 1.9239 (1.9239) acc1: 54.6875 (54.6875) acc5: 79.6875 (79.6875) [2021-03-26 02:46:44 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.7528 (1.8101) acc1: 57.8125 (59.5170) acc5: 85.9375 (83.9489) [2021-03-26 02:46:47 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.8471 (1.8871) acc1: 56.2500 (57.0685) acc5: 82.8125 (82.3661) [2021-03-26 02:46:48 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.9503 (1.8999) acc1: 54.6875 (56.3508) acc5: 81.2500 (82.3085) [2021-03-26 02:46:50 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.9272 (1.9009) acc1: 56.2500 (56.8598) acc5: 81.2500 (81.7835) [2021-03-26 02:46:52 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.8854 (1.8979) acc1: 56.2500 (57.2160) acc5: 81.2500 (81.8560) [2021-03-26 02:46:54 swin_base_patch4_window7_224] INFO: * Acc@1 57.784 Acc@5 81.904 loss 1.886 [2021-03-26 02:46:54 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 57.8% [2021-03-26 02:46:54 swin_base_patch4_window7_224] INFO: Max accuracy: 57.78% [2021-03-26 02:46:58 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 0/1251] eta: 1:31:15 lr: 0.000989 loss: 4.5302 (4.5302) grad_norm: 1.5159 (1.5159) time: 4.3766 [2021-03-26 02:47:05 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 10/1251] eta: 0:20:19 lr: 0.000989 loss: 4.5302 (4.5856) grad_norm: 1.2419 (1.2287) time: 0.9829 [2021-03-26 02:47:11 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 20/1251] eta: 0:16:44 lr: 0.000989 loss: 4.6996 (4.6020) grad_norm: 1.1688 (1.2447) time: 0.6377 [2021-03-26 02:47:17 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 30/1251] eta: 0:15:19 lr: 0.000989 loss: 4.3560 (4.5544) grad_norm: 1.1125 (1.1970) time: 0.6271 [2021-03-26 02:47:24 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 40/1251] eta: 0:14:35 lr: 0.000989 loss: 4.3290 (4.4936) grad_norm: 1.1047 (1.1835) time: 0.6253 [2021-03-26 02:47:30 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 50/1251] eta: 0:14:06 lr: 0.000989 loss: 4.2900 (4.4819) grad_norm: 1.1117 (1.1749) time: 0.6300 [2021-03-26 02:47:36 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 60/1251] eta: 0:13:45 lr: 0.000989 loss: 4.4633 (4.5073) grad_norm: 1.1543 (1.1820) time: 0.6324 [2021-03-26 02:47:43 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 70/1251] eta: 0:13:29 lr: 0.000989 loss: 4.7072 (4.5314) grad_norm: 1.1656 (1.1830) time: 0.6344 [2021-03-26 02:47:49 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 80/1251] eta: 0:13:14 lr: 0.000989 loss: 4.4837 (4.5435) grad_norm: 1.1577 (1.1886) time: 0.6341 [2021-03-26 02:47:55 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 90/1251] eta: 0:13:01 lr: 0.000989 loss: 4.4559 (4.5229) grad_norm: 1.1577 (1.1845) time: 0.6307 [2021-03-26 02:48:01 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 100/1251] eta: 0:12:49 lr: 0.000989 loss: 4.0755 (4.4798) grad_norm: 1.1369 (1.1813) time: 0.6293 [2021-03-26 02:48:08 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 110/1251] eta: 0:12:39 lr: 0.000989 loss: 4.3133 (4.4855) grad_norm: 1.1591 (1.1877) time: 0.6309 [2021-03-26 02:48:14 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 120/1251] eta: 0:12:30 lr: 0.000989 loss: 4.5109 (4.4821) grad_norm: 1.3025 (1.2076) time: 0.6379 [2021-03-26 02:48:20 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 130/1251] eta: 0:12:20 lr: 0.000989 loss: 4.3919 (4.4688) grad_norm: 1.1281 (1.1992) time: 0.6344 [2021-03-26 02:48:27 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 140/1251] eta: 0:12:11 lr: 0.000989 loss: 4.3919 (4.4613) grad_norm: 1.0761 (1.1990) time: 0.6287 [2021-03-26 02:48:33 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 150/1251] eta: 0:12:03 lr: 0.000989 loss: 4.7542 (4.4792) grad_norm: 1.0923 (1.1952) time: 0.6302 [2021-03-26 02:48:39 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 160/1251] eta: 0:11:54 lr: 0.000989 loss: 4.8943 (4.4863) grad_norm: 1.1104 (1.1938) time: 0.6284 [2021-03-26 02:48:46 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 170/1251] eta: 0:11:46 lr: 0.000989 loss: 4.2058 (4.4626) grad_norm: 1.1104 (1.1884) time: 0.6280 [2021-03-26 02:48:52 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 180/1251] eta: 0:11:37 lr: 0.000989 loss: 4.4150 (4.4790) grad_norm: 1.1882 (1.1941) time: 0.6226 [2021-03-26 02:48:58 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 190/1251] eta: 0:11:30 lr: 0.000989 loss: 4.7348 (4.4943) grad_norm: 1.1171 (1.1900) time: 0.6254 [2021-03-26 02:49:05 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 200/1251] eta: 0:11:23 lr: 0.000989 loss: 4.8338 (4.5147) grad_norm: 1.0997 (1.1863) time: 0.6363 [2021-03-26 02:49:11 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 210/1251] eta: 0:11:16 lr: 0.000989 loss: 4.8942 (4.5247) grad_norm: 1.1397 (1.1902) time: 0.6419 [2021-03-26 02:49:17 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 220/1251] eta: 0:11:08 lr: 0.000989 loss: 4.6545 (4.5295) grad_norm: 1.1242 (1.1864) time: 0.6355 [2021-03-26 02:49:24 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 230/1251] eta: 0:11:01 lr: 0.000989 loss: 4.6545 (4.5316) grad_norm: 1.1237 (1.1840) time: 0.6305 [2021-03-26 02:49:30 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 240/1251] eta: 0:10:54 lr: 0.000989 loss: 4.5817 (4.5252) grad_norm: 1.1237 (1.1829) time: 0.6322 [2021-03-26 02:49:36 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 250/1251] eta: 0:10:47 lr: 0.000989 loss: 4.5431 (4.5247) grad_norm: 1.0868 (1.1810) time: 0.6315 [2021-03-26 02:49:43 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 260/1251] eta: 0:10:40 lr: 0.000989 loss: 4.4715 (4.5221) grad_norm: 1.0868 (1.1785) time: 0.6365 [2021-03-26 02:49:49 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 270/1251] eta: 0:10:33 lr: 0.000989 loss: 4.3873 (4.5213) grad_norm: 1.1469 (1.1819) time: 0.6361 [2021-03-26 02:49:55 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 280/1251] eta: 0:10:26 lr: 0.000989 loss: 4.5942 (4.5276) grad_norm: 1.1556 (1.1828) time: 0.6300 [2021-03-26 02:50:02 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 290/1251] eta: 0:10:19 lr: 0.000989 loss: 4.6786 (4.5246) grad_norm: 1.0959 (1.1814) time: 0.6335 [2021-03-26 02:50:08 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 300/1251] eta: 0:10:13 lr: 0.000989 loss: 4.4482 (4.5247) grad_norm: 1.1247 (1.1803) time: 0.6371 [2021-03-26 02:50:14 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 310/1251] eta: 0:10:06 lr: 0.000989 loss: 4.5083 (4.5244) grad_norm: 1.1530 (1.1825) time: 0.6340 [2021-03-26 02:50:21 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 320/1251] eta: 0:09:59 lr: 0.000989 loss: 4.5238 (4.5311) grad_norm: 1.2401 (1.1850) time: 0.6345 [2021-03-26 02:50:27 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 330/1251] eta: 0:09:52 lr: 0.000989 loss: 4.5118 (4.5244) grad_norm: 1.2166 (1.1845) time: 0.6322 [2021-03-26 02:50:33 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 340/1251] eta: 0:09:45 lr: 0.000989 loss: 4.5817 (4.5270) grad_norm: 1.1724 (1.1815) time: 0.6253 [2021-03-26 02:50:39 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 350/1251] eta: 0:09:38 lr: 0.000989 loss: 4.6857 (4.5273) grad_norm: 1.0290 (1.1793) time: 0.6221 [2021-03-26 02:50:46 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 360/1251] eta: 0:09:32 lr: 0.000989 loss: 4.4234 (4.5205) grad_norm: 1.0377 (1.1767) time: 0.6258 [2021-03-26 02:50:52 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 370/1251] eta: 0:09:25 lr: 0.000989 loss: 4.4365 (4.5199) grad_norm: 1.1139 (1.1767) time: 0.6271 [2021-03-26 02:50:58 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 380/1251] eta: 0:09:18 lr: 0.000989 loss: 4.6272 (4.5221) grad_norm: 1.1487 (1.1768) time: 0.6294 [2021-03-26 02:51:05 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 390/1251] eta: 0:09:11 lr: 0.000989 loss: 4.5768 (4.5190) grad_norm: 1.1896 (1.1780) time: 0.6310 [2021-03-26 02:51:11 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 400/1251] eta: 0:09:05 lr: 0.000989 loss: 4.4947 (4.5140) grad_norm: 1.2883 (1.1812) time: 0.6299 [2021-03-26 02:51:17 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 410/1251] eta: 0:08:58 lr: 0.000989 loss: 4.2868 (4.5118) grad_norm: 1.2692 (1.1852) time: 0.6363 [2021-03-26 02:51:24 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 420/1251] eta: 0:08:52 lr: 0.000989 loss: 4.8036 (4.5216) grad_norm: 1.0804 (1.1823) time: 0.6362 [2021-03-26 02:51:30 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 430/1251] eta: 0:08:45 lr: 0.000989 loss: 4.8036 (4.5271) grad_norm: 1.0540 (1.1791) time: 0.6351 [2021-03-26 02:51:36 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 440/1251] eta: 0:08:39 lr: 0.000989 loss: 4.4272 (4.5180) grad_norm: 1.0358 (1.1769) time: 0.6370 [2021-03-26 02:51:43 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 450/1251] eta: 0:08:32 lr: 0.000989 loss: 3.9340 (4.5126) grad_norm: 1.0601 (1.1766) time: 0.6336 [2021-03-26 02:51:49 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 460/1251] eta: 0:08:26 lr: 0.000989 loss: 4.3898 (4.5159) grad_norm: 1.1148 (1.1772) time: 0.6347 [2021-03-26 02:51:55 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 470/1251] eta: 0:08:19 lr: 0.000989 loss: 4.8160 (4.5159) grad_norm: 1.1661 (1.1791) time: 0.6369 [2021-03-26 02:52:02 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 480/1251] eta: 0:08:13 lr: 0.000989 loss: 4.4327 (4.5077) grad_norm: 1.1445 (1.1780) time: 0.6328 [2021-03-26 02:52:08 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 490/1251] eta: 0:08:06 lr: 0.000989 loss: 4.0715 (4.5042) grad_norm: 1.1340 (1.1789) time: 0.6273 [2021-03-26 02:52:14 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 500/1251] eta: 0:08:00 lr: 0.000989 loss: 4.4131 (4.5011) grad_norm: 1.1283 (1.1776) time: 0.6282 [2021-03-26 02:52:21 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 510/1251] eta: 0:07:53 lr: 0.000989 loss: 4.2871 (4.4941) grad_norm: 1.0457 (1.1759) time: 0.6293 [2021-03-26 02:52:27 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 520/1251] eta: 0:07:46 lr: 0.000989 loss: 4.2871 (4.4944) grad_norm: 1.0705 (1.1768) time: 0.6249 [2021-03-26 02:52:33 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 530/1251] eta: 0:07:40 lr: 0.000989 loss: 4.6023 (4.4960) grad_norm: 1.1645 (1.1781) time: 0.6253 [2021-03-26 02:52:39 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 540/1251] eta: 0:07:33 lr: 0.000989 loss: 4.6312 (4.4926) grad_norm: 1.2345 (1.1824) time: 0.6287 [2021-03-26 02:52:46 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 550/1251] eta: 0:07:27 lr: 0.000989 loss: 4.5919 (4.4950) grad_norm: 1.1287 (1.1809) time: 0.6365 [2021-03-26 02:52:52 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 560/1251] eta: 0:07:21 lr: 0.000989 loss: 4.5919 (4.4955) grad_norm: 1.0819 (1.1794) time: 0.6372 [2021-03-26 02:52:58 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 570/1251] eta: 0:07:14 lr: 0.000989 loss: 4.5196 (4.4993) grad_norm: 1.1391 (1.1783) time: 0.6292 [2021-03-26 02:53:05 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 580/1251] eta: 0:07:08 lr: 0.000989 loss: 4.5196 (4.4990) grad_norm: 1.1504 (1.1786) time: 0.6318 [2021-03-26 02:53:11 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 590/1251] eta: 0:07:01 lr: 0.000989 loss: 4.5348 (4.4997) grad_norm: 1.0640 (1.1762) time: 0.6285 [2021-03-26 02:53:17 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 600/1251] eta: 0:06:55 lr: 0.000989 loss: 4.7492 (4.5034) grad_norm: 1.0601 (1.1761) time: 0.6214 [2021-03-26 02:53:24 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 610/1251] eta: 0:06:48 lr: 0.000989 loss: 4.6969 (4.5032) grad_norm: 1.0601 (1.1739) time: 0.6260 [2021-03-26 02:53:30 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 620/1251] eta: 0:06:42 lr: 0.000989 loss: 4.5776 (4.5000) grad_norm: 1.0751 (1.1756) time: 0.6309 [2021-03-26 02:53:36 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 630/1251] eta: 0:06:35 lr: 0.000989 loss: 4.5776 (4.4984) grad_norm: 1.1915 (1.1781) time: 0.6350 [2021-03-26 02:53:43 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 640/1251] eta: 0:06:29 lr: 0.000989 loss: 4.6376 (4.4982) grad_norm: 1.1203 (1.1768) time: 0.6331 [2021-03-26 02:53:49 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 650/1251] eta: 0:06:22 lr: 0.000989 loss: 4.4474 (4.4970) grad_norm: 1.1335 (1.1769) time: 0.6263 [2021-03-26 02:53:55 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 660/1251] eta: 0:06:16 lr: 0.000989 loss: 4.4888 (4.4960) grad_norm: 1.1766 (1.1774) time: 0.6272 [2021-03-26 02:54:01 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 670/1251] eta: 0:06:10 lr: 0.000989 loss: 4.4436 (4.4951) grad_norm: 1.1706 (1.1765) time: 0.6300 [2021-03-26 02:54:08 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 680/1251] eta: 0:06:03 lr: 0.000989 loss: 4.2833 (4.4919) grad_norm: 1.2376 (1.1786) time: 0.6365 [2021-03-26 02:54:14 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 690/1251] eta: 0:05:57 lr: 0.000989 loss: 4.5490 (4.4944) grad_norm: 1.2376 (1.1779) time: 0.6343 [2021-03-26 02:54:20 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 700/1251] eta: 0:05:50 lr: 0.000989 loss: 4.7262 (4.4968) grad_norm: 1.2159 (1.1792) time: 0.6272 [2021-03-26 02:54:27 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 710/1251] eta: 0:05:44 lr: 0.000989 loss: 4.5946 (4.4956) grad_norm: 1.2015 (1.1796) time: 0.6328 [2021-03-26 02:54:33 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 720/1251] eta: 0:05:38 lr: 0.000989 loss: 4.5946 (4.4971) grad_norm: 1.1553 (1.1790) time: 0.6362 [2021-03-26 02:54:39 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 730/1251] eta: 0:05:31 lr: 0.000989 loss: 4.5297 (4.4943) grad_norm: 1.2236 (1.1807) time: 0.6326 [2021-03-26 02:54:46 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 740/1251] eta: 0:05:25 lr: 0.000989 loss: 4.6651 (4.4984) grad_norm: 1.2596 (1.1811) time: 0.6427 [2021-03-26 02:54:52 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 750/1251] eta: 0:05:19 lr: 0.000989 loss: 4.5762 (4.4932) grad_norm: 1.1598 (1.1806) time: 0.6457 [2021-03-26 02:54:59 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 760/1251] eta: 0:05:12 lr: 0.000989 loss: 4.1254 (4.4897) grad_norm: 1.1682 (1.1824) time: 0.6326 [2021-03-26 02:55:05 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 770/1251] eta: 0:05:06 lr: 0.000989 loss: 4.2490 (4.4894) grad_norm: 1.0545 (1.1804) time: 0.6271 [2021-03-26 02:55:11 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 780/1251] eta: 0:04:59 lr: 0.000989 loss: 4.5316 (4.4889) grad_norm: 1.0211 (1.1802) time: 0.6299 [2021-03-26 02:55:17 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 790/1251] eta: 0:04:53 lr: 0.000988 loss: 4.5316 (4.4906) grad_norm: 1.0370 (1.1789) time: 0.6328 [2021-03-26 02:55:24 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 800/1251] eta: 0:04:46 lr: 0.000988 loss: 4.5078 (4.4893) grad_norm: 1.1280 (1.1840) time: 0.6271 [2021-03-26 02:55:30 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 810/1251] eta: 0:04:40 lr: 0.000988 loss: 4.6252 (4.4904) grad_norm: 1.4581 (1.1866) time: 0.6319 [2021-03-26 02:55:36 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 820/1251] eta: 0:04:34 lr: 0.000988 loss: 4.6275 (4.4906) grad_norm: 1.2363 (1.1864) time: 0.6337 [2021-03-26 02:55:43 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 830/1251] eta: 0:04:27 lr: 0.000988 loss: 4.5860 (4.4944) grad_norm: 1.0547 (1.1847) time: 0.6255 [2021-03-26 02:55:49 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 840/1251] eta: 0:04:21 lr: 0.000988 loss: 4.7575 (4.4958) grad_norm: 1.0478 (1.1852) time: 0.6271 [2021-03-26 02:55:55 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 850/1251] eta: 0:04:15 lr: 0.000988 loss: 4.8034 (4.4976) grad_norm: 1.1758 (1.1853) time: 0.6301 [2021-03-26 02:56:01 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 860/1251] eta: 0:04:08 lr: 0.000988 loss: 4.5242 (4.4944) grad_norm: 1.1156 (1.1836) time: 0.6248 [2021-03-26 02:56:08 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 870/1251] eta: 0:04:02 lr: 0.000988 loss: 4.3002 (4.4901) grad_norm: 1.0855 (1.1833) time: 0.6320 [2021-03-26 02:56:14 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 880/1251] eta: 0:03:55 lr: 0.000988 loss: 4.3002 (4.4884) grad_norm: 1.0932 (1.1819) time: 0.6348 [2021-03-26 02:56:20 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 890/1251] eta: 0:03:49 lr: 0.000988 loss: 4.3561 (4.4847) grad_norm: 1.0068 (1.1801) time: 0.6244 [2021-03-26 02:56:27 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 900/1251] eta: 0:03:43 lr: 0.000988 loss: 4.4585 (4.4855) grad_norm: 1.1000 (1.1800) time: 0.6236 [2021-03-26 02:56:33 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 910/1251] eta: 0:03:36 lr: 0.000988 loss: 4.6058 (4.4866) grad_norm: 1.1463 (1.1797) time: 0.6236 [2021-03-26 02:56:39 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 920/1251] eta: 0:03:30 lr: 0.000988 loss: 4.7697 (4.4880) grad_norm: 1.0975 (1.1788) time: 0.6247 [2021-03-26 02:56:45 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 930/1251] eta: 0:03:23 lr: 0.000988 loss: 4.3172 (4.4854) grad_norm: 1.1614 (1.1804) time: 0.6249 [2021-03-26 02:56:52 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 940/1251] eta: 0:03:17 lr: 0.000988 loss: 4.4669 (4.4863) grad_norm: 1.2377 (1.1811) time: 0.6290 [2021-03-26 02:56:58 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 950/1251] eta: 0:03:11 lr: 0.000988 loss: 4.5727 (4.4849) grad_norm: 1.0891 (1.1794) time: 0.6279 [2021-03-26 02:57:04 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 960/1251] eta: 0:03:04 lr: 0.000988 loss: 4.5456 (4.4837) grad_norm: 1.0991 (1.1795) time: 0.6263 [2021-03-26 02:57:11 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 970/1251] eta: 0:02:58 lr: 0.000988 loss: 4.3588 (4.4796) grad_norm: 1.1586 (1.1798) time: 0.6309 [2021-03-26 02:57:17 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 980/1251] eta: 0:02:52 lr: 0.000988 loss: 4.3131 (4.4777) grad_norm: 1.1608 (1.1796) time: 0.6284 [2021-03-26 02:57:23 swin_base_patch4_window7_224] INFO: Epoch: [20] [ 990/1251] eta: 0:02:45 lr: 0.000988 loss: 4.5235 (4.4787) grad_norm: 1.0438 (1.1780) time: 0.6252 [2021-03-26 02:57:29 swin_base_patch4_window7_224] INFO: Epoch: [20] [1000/1251] eta: 0:02:39 lr: 0.000988 loss: 4.5953 (4.4772) grad_norm: 1.0368 (1.1774) time: 0.6298 [2021-03-26 02:57:36 swin_base_patch4_window7_224] INFO: Epoch: [20] [1010/1251] eta: 0:02:32 lr: 0.000988 loss: 4.5953 (4.4777) grad_norm: 1.0582 (1.1767) time: 0.6305 [2021-03-26 02:57:42 swin_base_patch4_window7_224] INFO: Epoch: [20] [1020/1251] eta: 0:02:26 lr: 0.000988 loss: 4.5845 (4.4779) grad_norm: 1.0582 (1.1753) time: 0.6268 [2021-03-26 02:57:48 swin_base_patch4_window7_224] INFO: Epoch: [20] [1030/1251] eta: 0:02:20 lr: 0.000988 loss: 4.5274 (4.4767) grad_norm: 1.0650 (1.1761) time: 0.6268 [2021-03-26 02:57:54 swin_base_patch4_window7_224] INFO: Epoch: [20] [1040/1251] eta: 0:02:13 lr: 0.000988 loss: 4.5274 (4.4762) grad_norm: 1.1582 (1.1755) time: 0.6232 [2021-03-26 02:58:01 swin_base_patch4_window7_224] INFO: Epoch: [20] [1050/1251] eta: 0:02:07 lr: 0.000988 loss: 4.2644 (4.4748) grad_norm: 1.1444 (1.1756) time: 0.6227 [2021-03-26 02:58:07 swin_base_patch4_window7_224] INFO: Epoch: [20] [1060/1251] eta: 0:02:01 lr: 0.000988 loss: 4.4367 (4.4738) grad_norm: 1.1444 (1.1759) time: 0.6273 [2021-03-26 02:58:13 swin_base_patch4_window7_224] INFO: Epoch: [20] [1070/1251] eta: 0:01:54 lr: 0.000988 loss: 4.6014 (4.4760) grad_norm: 1.1340 (1.1758) time: 0.6247 [2021-03-26 02:58:19 swin_base_patch4_window7_224] INFO: Epoch: [20] [1080/1251] eta: 0:01:48 lr: 0.000988 loss: 4.6831 (4.4761) grad_norm: 1.2455 (1.1773) time: 0.6263 [2021-03-26 02:58:26 swin_base_patch4_window7_224] INFO: Epoch: [20] [1090/1251] eta: 0:01:42 lr: 0.000988 loss: 4.6831 (4.4770) grad_norm: 1.2813 (1.1781) time: 0.6340 [2021-03-26 02:58:32 swin_base_patch4_window7_224] INFO: Epoch: [20] [1100/1251] eta: 0:01:35 lr: 0.000988 loss: 4.5208 (4.4747) grad_norm: 1.1337 (1.1779) time: 0.6336 [2021-03-26 02:58:39 swin_base_patch4_window7_224] INFO: Epoch: [20] [1110/1251] eta: 0:01:29 lr: 0.000988 loss: 4.4635 (4.4746) grad_norm: 1.1164 (1.1778) time: 0.6375 [2021-03-26 02:58:45 swin_base_patch4_window7_224] INFO: Epoch: [20] [1120/1251] eta: 0:01:23 lr: 0.000988 loss: 4.6049 (4.4761) grad_norm: 1.0696 (1.1763) time: 0.6357 [2021-03-26 02:58:51 swin_base_patch4_window7_224] INFO: Epoch: [20] [1130/1251] eta: 0:01:16 lr: 0.000988 loss: 4.3481 (4.4740) grad_norm: 1.0927 (1.1767) time: 0.6307 [2021-03-26 02:58:58 swin_base_patch4_window7_224] INFO: Epoch: [20] [1140/1251] eta: 0:01:10 lr: 0.000988 loss: 4.0291 (4.4731) grad_norm: 1.2648 (1.1775) time: 0.6323 [2021-03-26 02:59:04 swin_base_patch4_window7_224] INFO: Epoch: [20] [1150/1251] eta: 0:01:04 lr: 0.000988 loss: 4.6893 (4.4744) grad_norm: 1.2042 (1.1775) time: 0.6346 [2021-03-26 02:59:10 swin_base_patch4_window7_224] INFO: Epoch: [20] [1160/1251] eta: 0:00:57 lr: 0.000988 loss: 4.7527 (4.4755) grad_norm: 1.1891 (1.1784) time: 0.6335 [2021-03-26 02:59:16 swin_base_patch4_window7_224] INFO: Epoch: [20] [1170/1251] eta: 0:00:51 lr: 0.000988 loss: 4.4904 (4.4751) grad_norm: 1.1887 (1.1785) time: 0.6282 [2021-03-26 02:59:23 swin_base_patch4_window7_224] INFO: Epoch: [20] [1180/1251] eta: 0:00:45 lr: 0.000988 loss: 4.6326 (4.4758) grad_norm: 1.1669 (1.1784) time: 0.6267 [2021-03-26 02:59:29 swin_base_patch4_window7_224] INFO: Epoch: [20] [1190/1251] eta: 0:00:38 lr: 0.000988 loss: 4.3182 (4.4736) grad_norm: 1.1535 (1.1791) time: 0.6311 [2021-03-26 02:59:35 swin_base_patch4_window7_224] INFO: Epoch: [20] [1200/1251] eta: 0:00:32 lr: 0.000988 loss: 4.3532 (4.4756) grad_norm: 1.1153 (1.1782) time: 0.6317 [2021-03-26 02:59:42 swin_base_patch4_window7_224] INFO: Epoch: [20] [1210/1251] eta: 0:00:25 lr: 0.000988 loss: 4.7140 (4.4744) grad_norm: 1.0276 (1.1776) time: 0.6317 [2021-03-26 02:59:48 swin_base_patch4_window7_224] INFO: Epoch: [20] [1220/1251] eta: 0:00:19 lr: 0.000988 loss: 4.3860 (4.4744) grad_norm: 1.0863 (1.1771) time: 0.6311 [2021-03-26 02:59:54 swin_base_patch4_window7_224] INFO: Epoch: [20] [1230/1251] eta: 0:00:13 lr: 0.000988 loss: 4.5754 (4.4756) grad_norm: 1.0981 (1.1761) time: 0.6248 [2021-03-26 03:00:01 swin_base_patch4_window7_224] INFO: Epoch: [20] [1240/1251] eta: 0:00:06 lr: 0.000988 loss: 4.8524 (4.4785) grad_norm: 1.1188 (1.1764) time: 0.6263 [2021-03-26 03:00:07 swin_base_patch4_window7_224] INFO: Epoch: [20] [1250/1251] eta: 0:00:00 lr: 0.000988 loss: 4.7915 (4.4783) grad_norm: 1.0909 (1.1760) time: 0.6264 [2021-03-26 03:01:00 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:15 loss: 2.0222 (2.0222) acc1: 53.1250 (53.1250) acc5: 79.6875 (79.6875) [2021-03-26 03:01:01 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 1.8418 (1.8536) acc1: 57.8125 (58.5227) acc5: 82.8125 (83.5227) [2021-03-26 03:01:02 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:06 loss: 1.7945 (1.8292) acc1: 59.3750 (59.3006) acc5: 82.8125 (83.1845) [2021-03-26 03:01:04 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.8197 (1.8343) acc1: 59.3750 (59.0222) acc5: 82.8125 (83.4173) [2021-03-26 03:01:05 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.8437 (1.8326) acc1: 59.3750 (59.2607) acc5: 82.8125 (83.3079) [2021-03-26 03:01:06 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.8177 (1.8385) acc1: 56.2500 (59.0720) acc5: 84.3750 (83.3600) [2021-03-26 03:01:08 swin_base_patch4_window7_224] INFO: * Acc@1 59.502 Acc@5 83.508 loss 1.820 [2021-03-26 03:01:08 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 59.5% [2021-03-26 03:01:08 swin_base_patch4_window7_224] INFO: Max accuracy: 59.50% [2021-03-26 03:01:12 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 0/1251] eta: 1:32:03 lr: 0.000988 loss: 3.8594 (3.8594) grad_norm: 1.0799 (1.0799) time: 4.4150 [2021-03-26 03:01:19 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 10/1251] eta: 0:20:18 lr: 0.000988 loss: 4.6390 (4.6337) grad_norm: 1.1266 (1.1215) time: 0.9822 [2021-03-26 03:01:25 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 20/1251] eta: 0:16:40 lr: 0.000988 loss: 4.6245 (4.6288) grad_norm: 1.1905 (1.1820) time: 0.6328 [2021-03-26 03:01:31 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 30/1251] eta: 0:15:19 lr: 0.000988 loss: 4.6245 (4.6069) grad_norm: 1.2231 (1.1698) time: 0.6266 [2021-03-26 03:01:38 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 40/1251] eta: 0:14:36 lr: 0.000988 loss: 4.5131 (4.5468) grad_norm: 1.2247 (1.1946) time: 0.6305 [2021-03-26 03:01:44 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 50/1251] eta: 0:14:07 lr: 0.000988 loss: 4.5422 (4.5595) grad_norm: 1.2162 (1.1877) time: 0.6323 [2021-03-26 03:01:50 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 60/1251] eta: 0:13:45 lr: 0.000988 loss: 4.7628 (4.5351) grad_norm: 1.1641 (1.1921) time: 0.6288 [2021-03-26 03:01:56 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 70/1251] eta: 0:13:25 lr: 0.000988 loss: 4.7288 (4.5662) grad_norm: 1.1572 (1.1832) time: 0.6215 [2021-03-26 03:02:03 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 80/1251] eta: 0:13:10 lr: 0.000988 loss: 4.6565 (4.5453) grad_norm: 1.1216 (1.2067) time: 0.6203 [2021-03-26 03:02:09 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 90/1251] eta: 0:12:57 lr: 0.000988 loss: 4.6463 (4.5604) grad_norm: 1.1177 (1.1955) time: 0.6264 [2021-03-26 03:02:15 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 100/1251] eta: 0:12:45 lr: 0.000988 loss: 4.6565 (4.5421) grad_norm: 1.0967 (1.1867) time: 0.6258 [2021-03-26 03:02:22 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 110/1251] eta: 0:12:34 lr: 0.000988 loss: 4.7676 (4.5486) grad_norm: 1.0706 (1.1755) time: 0.6243 [2021-03-26 03:02:28 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 120/1251] eta: 0:12:25 lr: 0.000988 loss: 4.5594 (4.5450) grad_norm: 1.0840 (1.1771) time: 0.6289 [2021-03-26 03:02:34 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 130/1251] eta: 0:12:16 lr: 0.000988 loss: 4.5479 (4.5339) grad_norm: 1.1519 (1.1725) time: 0.6318 [2021-03-26 03:02:40 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 140/1251] eta: 0:12:07 lr: 0.000988 loss: 4.3235 (4.5191) grad_norm: 1.1519 (1.1705) time: 0.6256 [2021-03-26 03:02:47 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 150/1251] eta: 0:11:58 lr: 0.000988 loss: 4.6263 (4.5368) grad_norm: 1.1939 (1.1740) time: 0.6211 [2021-03-26 03:02:53 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 160/1251] eta: 0:11:49 lr: 0.000988 loss: 4.8032 (4.5366) grad_norm: 1.1469 (1.1701) time: 0.6232 [2021-03-26 03:02:59 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 170/1251] eta: 0:11:41 lr: 0.000988 loss: 4.4871 (4.5293) grad_norm: 1.0553 (1.1647) time: 0.6278 [2021-03-26 03:03:05 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 180/1251] eta: 0:11:34 lr: 0.000988 loss: 4.5274 (4.5267) grad_norm: 1.0535 (1.1684) time: 0.6338 [2021-03-26 03:03:12 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 190/1251] eta: 0:11:26 lr: 0.000988 loss: 4.6083 (4.5310) grad_norm: 1.1095 (1.1672) time: 0.6313 [2021-03-26 03:03:18 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 200/1251] eta: 0:11:19 lr: 0.000988 loss: 4.5639 (4.5237) grad_norm: 1.0583 (1.1608) time: 0.6225 [2021-03-26 03:03:24 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 210/1251] eta: 0:11:11 lr: 0.000988 loss: 4.3554 (4.5043) grad_norm: 1.0226 (1.1569) time: 0.6212 [2021-03-26 03:03:30 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 220/1251] eta: 0:11:04 lr: 0.000988 loss: 4.4284 (4.5011) grad_norm: 1.1468 (1.1563) time: 0.6269 [2021-03-26 03:03:37 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 230/1251] eta: 0:10:56 lr: 0.000988 loss: 4.5027 (4.5034) grad_norm: 1.1129 (1.1526) time: 0.6260 [2021-03-26 03:03:43 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 240/1251] eta: 0:10:49 lr: 0.000988 loss: 4.6979 (4.4949) grad_norm: 1.0930 (1.1496) time: 0.6263 [2021-03-26 03:03:49 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 250/1251] eta: 0:10:43 lr: 0.000988 loss: 4.5750 (4.4947) grad_norm: 1.0687 (1.1491) time: 0.6353 [2021-03-26 03:03:56 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 260/1251] eta: 0:10:36 lr: 0.000988 loss: 4.5750 (4.4970) grad_norm: 1.0687 (1.1457) time: 0.6291 [2021-03-26 03:04:02 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 270/1251] eta: 0:10:28 lr: 0.000988 loss: 4.7486 (4.5126) grad_norm: 1.1483 (1.1482) time: 0.6203 [2021-03-26 03:04:08 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 280/1251] eta: 0:10:22 lr: 0.000988 loss: 4.7417 (4.5136) grad_norm: 1.2297 (1.1536) time: 0.6297 [2021-03-26 03:04:15 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 290/1251] eta: 0:10:15 lr: 0.000988 loss: 4.5278 (4.5079) grad_norm: 1.2315 (1.1573) time: 0.6360 [2021-03-26 03:04:21 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 300/1251] eta: 0:10:08 lr: 0.000988 loss: 4.6153 (4.5143) grad_norm: 1.1427 (1.1564) time: 0.6319 [2021-03-26 03:04:27 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 310/1251] eta: 0:10:02 lr: 0.000988 loss: 4.4645 (4.5114) grad_norm: 1.0747 (1.1575) time: 0.6315 [2021-03-26 03:04:33 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 320/1251] eta: 0:09:55 lr: 0.000988 loss: 4.5785 (4.5107) grad_norm: 1.1436 (1.1622) time: 0.6294 [2021-03-26 03:04:40 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 330/1251] eta: 0:09:49 lr: 0.000988 loss: 4.4429 (4.5010) grad_norm: 1.2148 (1.1643) time: 0.6312 [2021-03-26 03:04:46 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 340/1251] eta: 0:09:42 lr: 0.000988 loss: 4.4084 (4.4982) grad_norm: 1.2101 (1.1651) time: 0.6315 [2021-03-26 03:04:52 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 350/1251] eta: 0:09:35 lr: 0.000988 loss: 4.3425 (4.4901) grad_norm: 1.2305 (1.1693) time: 0.6301 [2021-03-26 03:04:59 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 360/1251] eta: 0:09:28 lr: 0.000988 loss: 4.3425 (4.4859) grad_norm: 1.1597 (1.1670) time: 0.6269 [2021-03-26 03:05:05 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 370/1251] eta: 0:09:22 lr: 0.000988 loss: 3.9240 (4.4693) grad_norm: 1.1096 (1.1663) time: 0.6243 [2021-03-26 03:05:11 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 380/1251] eta: 0:09:15 lr: 0.000988 loss: 4.2780 (4.4744) grad_norm: 1.1153 (1.1686) time: 0.6339 [2021-03-26 03:05:18 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 390/1251] eta: 0:09:09 lr: 0.000988 loss: 4.8454 (4.4866) grad_norm: 1.2398 (1.1703) time: 0.6318 [2021-03-26 03:05:24 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 400/1251] eta: 0:09:02 lr: 0.000988 loss: 4.8444 (4.4858) grad_norm: 1.0931 (1.1700) time: 0.6305 [2021-03-26 03:05:30 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 410/1251] eta: 0:08:56 lr: 0.000988 loss: 4.6571 (4.4893) grad_norm: 1.0719 (1.1663) time: 0.6284 [2021-03-26 03:05:36 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 420/1251] eta: 0:08:49 lr: 0.000988 loss: 4.5948 (4.4896) grad_norm: 1.0438 (1.1656) time: 0.6243 [2021-03-26 03:05:43 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 430/1251] eta: 0:08:42 lr: 0.000988 loss: 4.5432 (4.4882) grad_norm: 1.1651 (1.1659) time: 0.6237 [2021-03-26 03:05:49 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 440/1251] eta: 0:08:36 lr: 0.000988 loss: 4.4900 (4.4895) grad_norm: 1.1475 (1.1668) time: 0.6218 [2021-03-26 03:05:55 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 450/1251] eta: 0:08:29 lr: 0.000988 loss: 4.5043 (4.4922) grad_norm: 1.1110 (1.1654) time: 0.6214 [2021-03-26 03:06:01 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 460/1251] eta: 0:08:22 lr: 0.000988 loss: 4.5595 (4.4914) grad_norm: 1.0792 (1.1646) time: 0.6206 [2021-03-26 03:06:08 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 470/1251] eta: 0:08:16 lr: 0.000988 loss: 4.2594 (4.4889) grad_norm: 1.1820 (1.1652) time: 0.6268 [2021-03-26 03:06:14 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 480/1251] eta: 0:08:10 lr: 0.000988 loss: 4.2152 (4.4850) grad_norm: 1.1932 (1.1665) time: 0.6370 [2021-03-26 03:06:20 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 490/1251] eta: 0:08:03 lr: 0.000988 loss: 4.1987 (4.4746) grad_norm: 1.1886 (1.1679) time: 0.6377 [2021-03-26 03:06:26 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 500/1251] eta: 0:07:57 lr: 0.000988 loss: 4.4745 (4.4776) grad_norm: 1.2205 (1.1687) time: 0.6239 [2021-03-26 03:06:33 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 510/1251] eta: 0:07:50 lr: 0.000988 loss: 4.5743 (4.4778) grad_norm: 1.1021 (1.1687) time: 0.6251 [2021-03-26 03:06:39 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 520/1251] eta: 0:07:44 lr: 0.000988 loss: 4.5062 (4.4766) grad_norm: 1.0539 (1.1666) time: 0.6335 [2021-03-26 03:06:45 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 530/1251] eta: 0:07:37 lr: 0.000988 loss: 4.4434 (4.4794) grad_norm: 1.1408 (1.1672) time: 0.6266 [2021-03-26 03:06:52 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 540/1251] eta: 0:07:31 lr: 0.000988 loss: 4.4434 (4.4815) grad_norm: 1.1546 (1.1672) time: 0.6183 [2021-03-26 03:06:58 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 550/1251] eta: 0:07:24 lr: 0.000988 loss: 4.5668 (4.4800) grad_norm: 1.1491 (1.1658) time: 0.6261 [2021-03-26 03:07:04 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 560/1251] eta: 0:07:18 lr: 0.000988 loss: 4.5668 (4.4804) grad_norm: 1.1901 (1.1663) time: 0.6379 [2021-03-26 03:07:11 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 570/1251] eta: 0:07:12 lr: 0.000988 loss: 4.3929 (4.4743) grad_norm: 1.1962 (1.1662) time: 0.6364 [2021-03-26 03:07:17 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 580/1251] eta: 0:07:05 lr: 0.000988 loss: 4.4475 (4.4763) grad_norm: 1.0408 (1.1642) time: 0.6299 [2021-03-26 03:07:23 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 590/1251] eta: 0:06:59 lr: 0.000988 loss: 4.6825 (4.4809) grad_norm: 0.9950 (1.1618) time: 0.6229 [2021-03-26 03:07:29 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 600/1251] eta: 0:06:52 lr: 0.000988 loss: 4.7033 (4.4826) grad_norm: 1.0037 (1.1598) time: 0.6243 [2021-03-26 03:07:36 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 610/1251] eta: 0:06:46 lr: 0.000988 loss: 4.5520 (4.4840) grad_norm: 1.0853 (1.1622) time: 0.6333 [2021-03-26 03:07:42 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 620/1251] eta: 0:06:40 lr: 0.000988 loss: 4.5057 (4.4799) grad_norm: 1.2510 (1.1631) time: 0.6348 [2021-03-26 03:07:48 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 630/1251] eta: 0:06:33 lr: 0.000988 loss: 4.5831 (4.4820) grad_norm: 1.1462 (1.1619) time: 0.6308 [2021-03-26 03:07:55 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 640/1251] eta: 0:06:27 lr: 0.000987 loss: 4.5473 (4.4805) grad_norm: 1.0755 (1.1623) time: 0.6237 [2021-03-26 03:08:01 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 650/1251] eta: 0:06:21 lr: 0.000987 loss: 4.5055 (4.4809) grad_norm: 1.1379 (1.1623) time: 0.6264 [2021-03-26 03:08:07 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 660/1251] eta: 0:06:14 lr: 0.000987 loss: 4.5315 (4.4789) grad_norm: 1.1366 (1.1617) time: 0.6315 [2021-03-26 03:08:14 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 670/1251] eta: 0:06:08 lr: 0.000987 loss: 4.4257 (4.4779) grad_norm: 1.1362 (1.1627) time: 0.6324 [2021-03-26 03:08:20 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 680/1251] eta: 0:06:01 lr: 0.000987 loss: 4.6524 (4.4799) grad_norm: 1.1639 (1.1634) time: 0.6321 [2021-03-26 03:08:26 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 690/1251] eta: 0:05:55 lr: 0.000987 loss: 4.7999 (4.4816) grad_norm: 1.1638 (1.1642) time: 0.6262 [2021-03-26 03:08:32 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 700/1251] eta: 0:05:49 lr: 0.000987 loss: 4.6271 (4.4815) grad_norm: 1.1892 (1.1656) time: 0.6253 [2021-03-26 03:08:39 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 710/1251] eta: 0:05:42 lr: 0.000987 loss: 4.3748 (4.4786) grad_norm: 1.1215 (inf) time: 0.6242 [2021-03-26 03:08:45 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 720/1251] eta: 0:05:36 lr: 0.000987 loss: 4.2109 (4.4778) grad_norm: 1.0592 (inf) time: 0.6269 [2021-03-26 03:08:51 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 730/1251] eta: 0:05:30 lr: 0.000987 loss: 4.2811 (4.4775) grad_norm: 1.0949 (inf) time: 0.6376 [2021-03-26 03:08:58 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 740/1251] eta: 0:05:23 lr: 0.000987 loss: 4.3388 (4.4743) grad_norm: 1.0360 (inf) time: 0.6346 [2021-03-26 03:09:04 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 750/1251] eta: 0:05:17 lr: 0.000987 loss: 4.4439 (4.4735) grad_norm: 1.0582 (inf) time: 0.6311 [2021-03-26 03:09:11 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 760/1251] eta: 0:05:11 lr: 0.000987 loss: 4.6112 (4.4739) grad_norm: 1.1280 (inf) time: 0.6491 [2021-03-26 03:09:17 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 770/1251] eta: 0:05:04 lr: 0.000987 loss: 4.5836 (4.4725) grad_norm: 1.2182 (inf) time: 0.6423 [2021-03-26 03:09:23 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 780/1251] eta: 0:04:58 lr: 0.000987 loss: 4.5836 (4.4741) grad_norm: 1.2139 (inf) time: 0.6274 [2021-03-26 03:09:29 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 790/1251] eta: 0:04:52 lr: 0.000987 loss: 4.5514 (4.4715) grad_norm: 1.1888 (inf) time: 0.6245 [2021-03-26 03:09:36 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 800/1251] eta: 0:04:45 lr: 0.000987 loss: 4.4195 (4.4706) grad_norm: 1.1590 (inf) time: 0.6193 [2021-03-26 03:09:42 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 810/1251] eta: 0:04:39 lr: 0.000987 loss: 4.4735 (4.4709) grad_norm: 1.0950 (inf) time: 0.6254 [2021-03-26 03:09:48 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 820/1251] eta: 0:04:33 lr: 0.000987 loss: 4.8387 (4.4757) grad_norm: 1.1215 (inf) time: 0.6367 [2021-03-26 03:09:55 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 830/1251] eta: 0:04:26 lr: 0.000987 loss: 4.7174 (4.4750) grad_norm: 1.2031 (inf) time: 0.6355 [2021-03-26 03:10:01 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 840/1251] eta: 0:04:20 lr: 0.000987 loss: 4.5623 (4.4774) grad_norm: 1.0391 (inf) time: 0.6272 [2021-03-26 03:10:07 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 850/1251] eta: 0:04:13 lr: 0.000987 loss: 4.5256 (4.4775) grad_norm: 1.1183 (inf) time: 0.6270 [2021-03-26 03:10:13 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 860/1251] eta: 0:04:07 lr: 0.000987 loss: 4.5057 (4.4768) grad_norm: 1.2031 (inf) time: 0.6319 [2021-03-26 03:10:20 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 870/1251] eta: 0:04:01 lr: 0.000987 loss: 4.6170 (4.4759) grad_norm: 1.1478 (inf) time: 0.6302 [2021-03-26 03:10:26 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 880/1251] eta: 0:03:54 lr: 0.000987 loss: 4.4845 (4.4766) grad_norm: 1.1199 (inf) time: 0.6275 [2021-03-26 03:10:32 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 890/1251] eta: 0:03:48 lr: 0.000987 loss: 4.6729 (4.4793) grad_norm: 1.1794 (inf) time: 0.6313 [2021-03-26 03:10:39 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 900/1251] eta: 0:03:42 lr: 0.000987 loss: 4.5154 (4.4770) grad_norm: 1.1751 (inf) time: 0.6269 [2021-03-26 03:10:45 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 910/1251] eta: 0:03:35 lr: 0.000987 loss: 4.2730 (4.4769) grad_norm: 1.0967 (inf) time: 0.6285 [2021-03-26 03:10:51 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 920/1251] eta: 0:03:29 lr: 0.000987 loss: 4.4742 (4.4744) grad_norm: 1.0967 (inf) time: 0.6350 [2021-03-26 03:10:58 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 930/1251] eta: 0:03:23 lr: 0.000987 loss: 4.6179 (4.4761) grad_norm: 1.0894 (inf) time: 0.6325 [2021-03-26 03:11:04 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 940/1251] eta: 0:03:16 lr: 0.000987 loss: 4.5548 (4.4726) grad_norm: 1.0588 (inf) time: 0.6269 [2021-03-26 03:11:10 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 950/1251] eta: 0:03:10 lr: 0.000987 loss: 4.1590 (4.4702) grad_norm: 1.1203 (inf) time: 0.6258 [2021-03-26 03:11:16 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 960/1251] eta: 0:03:04 lr: 0.000987 loss: 4.0700 (4.4661) grad_norm: 1.2021 (inf) time: 0.6280 [2021-03-26 03:11:23 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 970/1251] eta: 0:02:57 lr: 0.000987 loss: 4.2270 (4.4659) grad_norm: 1.1891 (inf) time: 0.6311 [2021-03-26 03:11:29 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 980/1251] eta: 0:02:51 lr: 0.000987 loss: 4.4970 (4.4648) grad_norm: 1.1636 (inf) time: 0.6277 [2021-03-26 03:11:35 swin_base_patch4_window7_224] INFO: Epoch: [21] [ 990/1251] eta: 0:02:45 lr: 0.000987 loss: 4.5775 (4.4669) grad_norm: 1.0823 (inf) time: 0.6252 [2021-03-26 03:11:42 swin_base_patch4_window7_224] INFO: Epoch: [21] [1000/1251] eta: 0:02:38 lr: 0.000987 loss: 4.6275 (4.4675) grad_norm: 1.1134 (inf) time: 0.6304 [2021-03-26 03:11:48 swin_base_patch4_window7_224] INFO: Epoch: [21] [1010/1251] eta: 0:02:32 lr: 0.000987 loss: 4.4653 (4.4654) grad_norm: 1.1258 (inf) time: 0.6298 [2021-03-26 03:11:54 swin_base_patch4_window7_224] INFO: Epoch: [21] [1020/1251] eta: 0:02:26 lr: 0.000987 loss: 4.5226 (4.4665) grad_norm: 1.1804 (inf) time: 0.6303 [2021-03-26 03:12:00 swin_base_patch4_window7_224] INFO: Epoch: [21] [1030/1251] eta: 0:02:19 lr: 0.000987 loss: 4.4363 (4.4632) grad_norm: 1.1540 (inf) time: 0.6273 [2021-03-26 03:12:07 swin_base_patch4_window7_224] INFO: Epoch: [21] [1040/1251] eta: 0:02:13 lr: 0.000987 loss: 4.1394 (4.4611) grad_norm: 1.0834 (inf) time: 0.6232 [2021-03-26 03:12:13 swin_base_patch4_window7_224] INFO: Epoch: [21] [1050/1251] eta: 0:02:07 lr: 0.000987 loss: 4.5516 (4.4629) grad_norm: 1.1244 (inf) time: 0.6278 [2021-03-26 03:12:19 swin_base_patch4_window7_224] INFO: Epoch: [21] [1060/1251] eta: 0:02:00 lr: 0.000987 loss: 4.7404 (4.4635) grad_norm: 1.0966 (inf) time: 0.6282 [2021-03-26 03:12:25 swin_base_patch4_window7_224] INFO: Epoch: [21] [1070/1251] eta: 0:01:54 lr: 0.000987 loss: 4.3868 (4.4596) grad_norm: 1.0375 (inf) time: 0.6256 [2021-03-26 03:12:32 swin_base_patch4_window7_224] INFO: Epoch: [21] [1080/1251] eta: 0:01:48 lr: 0.000987 loss: 4.0632 (4.4607) grad_norm: 1.1665 (inf) time: 0.6253 [2021-03-26 03:12:38 swin_base_patch4_window7_224] INFO: Epoch: [21] [1090/1251] eta: 0:01:41 lr: 0.000987 loss: 4.6921 (4.4613) grad_norm: 1.1970 (inf) time: 0.6326 [2021-03-26 03:12:44 swin_base_patch4_window7_224] INFO: Epoch: [21] [1100/1251] eta: 0:01:35 lr: 0.000987 loss: 4.3848 (4.4600) grad_norm: 1.0664 (inf) time: 0.6273 [2021-03-26 03:12:50 swin_base_patch4_window7_224] INFO: Epoch: [21] [1110/1251] eta: 0:01:29 lr: 0.000987 loss: 4.2491 (4.4603) grad_norm: 1.0290 (inf) time: 0.6168 [2021-03-26 03:12:57 swin_base_patch4_window7_224] INFO: Epoch: [21] [1120/1251] eta: 0:01:22 lr: 0.000987 loss: 4.5788 (4.4622) grad_norm: 1.1717 (inf) time: 0.6202 [2021-03-26 03:13:03 swin_base_patch4_window7_224] INFO: Epoch: [21] [1130/1251] eta: 0:01:16 lr: 0.000987 loss: 4.5788 (4.4629) grad_norm: 1.2786 (inf) time: 0.6302 [2021-03-26 03:13:09 swin_base_patch4_window7_224] INFO: Epoch: [21] [1140/1251] eta: 0:01:10 lr: 0.000987 loss: 4.5667 (4.4617) grad_norm: 1.0997 (inf) time: 0.6324 [2021-03-26 03:13:15 swin_base_patch4_window7_224] INFO: Epoch: [21] [1150/1251] eta: 0:01:03 lr: 0.000987 loss: 4.3552 (4.4602) grad_norm: 0.9984 (inf) time: 0.6219 [2021-03-26 03:13:22 swin_base_patch4_window7_224] INFO: Epoch: [21] [1160/1251] eta: 0:00:57 lr: 0.000987 loss: 4.4329 (4.4588) grad_norm: 1.0609 (inf) time: 0.6264 [2021-03-26 03:13:28 swin_base_patch4_window7_224] INFO: Epoch: [21] [1170/1251] eta: 0:00:51 lr: 0.000987 loss: 4.4617 (4.4596) grad_norm: 1.0819 (inf) time: 0.6279 [2021-03-26 03:13:34 swin_base_patch4_window7_224] INFO: Epoch: [21] [1180/1251] eta: 0:00:44 lr: 0.000987 loss: 4.5040 (4.4583) grad_norm: 1.0819 (inf) time: 0.6215 [2021-03-26 03:13:41 swin_base_patch4_window7_224] INFO: Epoch: [21] [1190/1251] eta: 0:00:38 lr: 0.000987 loss: 4.4003 (4.4581) grad_norm: 1.0504 (inf) time: 0.6287 [2021-03-26 03:13:47 swin_base_patch4_window7_224] INFO: Epoch: [21] [1200/1251] eta: 0:00:32 lr: 0.000987 loss: 4.2722 (4.4555) grad_norm: 1.0524 (inf) time: 0.6342 [2021-03-26 03:13:53 swin_base_patch4_window7_224] INFO: Epoch: [21] [1210/1251] eta: 0:00:25 lr: 0.000987 loss: 4.4841 (4.4571) grad_norm: 1.0562 (inf) time: 0.6315 [2021-03-26 03:13:59 swin_base_patch4_window7_224] INFO: Epoch: [21] [1220/1251] eta: 0:00:19 lr: 0.000987 loss: 4.7792 (4.4574) grad_norm: 1.0907 (inf) time: 0.6265 [2021-03-26 03:14:06 swin_base_patch4_window7_224] INFO: Epoch: [21] [1230/1251] eta: 0:00:13 lr: 0.000987 loss: 4.6181 (4.4571) grad_norm: 1.0995 (inf) time: 0.6264 [2021-03-26 03:14:12 swin_base_patch4_window7_224] INFO: Epoch: [21] [1240/1251] eta: 0:00:06 lr: 0.000987 loss: 4.4132 (4.4556) grad_norm: 1.1826 (inf) time: 0.6193 [2021-03-26 03:14:18 swin_base_patch4_window7_224] INFO: Epoch: [21] [1250/1251] eta: 0:00:00 lr: 0.000987 loss: 4.1348 (4.4541) grad_norm: 1.1093 (inf) time: 0.6079 [2021-03-26 03:14:22 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:43 loss: 1.5226 (1.5226) acc1: 65.6250 (65.6250) acc5: 82.8125 (82.8125) [2021-03-26 03:14:25 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.7475 (1.7751) acc1: 60.9375 (59.2330) acc5: 81.2500 (82.1023) [2021-03-26 03:14:27 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.7317 (1.7462) acc1: 59.3750 (59.3006) acc5: 82.8125 (83.1845) [2021-03-26 03:14:29 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.6132 (1.7197) acc1: 60.9375 (60.5343) acc5: 84.3750 (83.7198) [2021-03-26 03:14:31 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.7075 (1.7242) acc1: 60.9375 (60.2515) acc5: 84.3750 (83.8415) [2021-03-26 03:14:32 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.7699 (1.7362) acc1: 59.3750 (60.1920) acc5: 82.8125 (83.5520) [2021-03-26 03:14:34 swin_base_patch4_window7_224] INFO: * Acc@1 60.426 Acc@5 84.188 loss 1.720 [2021-03-26 03:14:34 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 60.4% [2021-03-26 03:14:34 swin_base_patch4_window7_224] INFO: Max accuracy: 60.43% [2021-03-26 03:14:39 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 0/1251] eta: 1:32:38 lr: 0.000987 loss: 5.0823 (5.0823) grad_norm: 1.2045 (1.2045) time: 4.4434 [2021-03-26 03:14:45 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 10/1251] eta: 0:20:12 lr: 0.000987 loss: 4.7571 (4.6429) grad_norm: 1.2337 (1.1901) time: 0.9768 [2021-03-26 03:14:52 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 20/1251] eta: 0:16:46 lr: 0.000987 loss: 4.7848 (4.6520) grad_norm: 1.1072 (1.1257) time: 0.6363 [2021-03-26 03:14:58 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 30/1251] eta: 0:15:25 lr: 0.000987 loss: 4.8135 (4.5958) grad_norm: 1.1004 (1.1362) time: 0.6375 [2021-03-26 03:15:04 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 40/1251] eta: 0:14:40 lr: 0.000987 loss: 4.6619 (4.5577) grad_norm: 1.1004 (1.1167) time: 0.6320 [2021-03-26 03:15:11 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 50/1251] eta: 0:14:11 lr: 0.000987 loss: 4.2402 (4.4745) grad_norm: 1.1124 (1.1287) time: 0.6337 [2021-03-26 03:15:17 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 60/1251] eta: 0:13:48 lr: 0.000987 loss: 4.2402 (4.4569) grad_norm: 1.1804 (1.1455) time: 0.6307 [2021-03-26 03:15:23 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 70/1251] eta: 0:13:29 lr: 0.000987 loss: 4.4443 (4.4540) grad_norm: 1.1563 (1.1480) time: 0.6256 [2021-03-26 03:15:29 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 80/1251] eta: 0:13:14 lr: 0.000987 loss: 4.6465 (4.4418) grad_norm: 1.1244 (1.1435) time: 0.6252 [2021-03-26 03:15:36 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 90/1251] eta: 0:13:01 lr: 0.000987 loss: 4.4700 (4.4314) grad_norm: 1.1226 (1.1420) time: 0.6270 [2021-03-26 03:15:42 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 100/1251] eta: 0:12:48 lr: 0.000987 loss: 4.0849 (4.4081) grad_norm: 1.1573 (1.1476) time: 0.6270 [2021-03-26 03:15:48 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 110/1251] eta: 0:12:38 lr: 0.000987 loss: 4.3724 (4.4164) grad_norm: 1.1575 (1.1492) time: 0.6275 [2021-03-26 03:15:55 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 120/1251] eta: 0:12:28 lr: 0.000987 loss: 4.4406 (4.4036) grad_norm: 1.1575 (1.1581) time: 0.6286 [2021-03-26 03:16:01 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 130/1251] eta: 0:12:18 lr: 0.000987 loss: 4.2741 (4.3994) grad_norm: 1.1470 (1.1523) time: 0.6246 [2021-03-26 03:16:07 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 140/1251] eta: 0:12:09 lr: 0.000987 loss: 4.5018 (4.4130) grad_norm: 1.1623 (1.1547) time: 0.6255 [2021-03-26 03:16:14 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 150/1251] eta: 0:12:02 lr: 0.000987 loss: 4.6700 (4.4172) grad_norm: 1.1850 (1.1560) time: 0.6401 [2021-03-26 03:16:20 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 160/1251] eta: 0:11:53 lr: 0.000987 loss: 4.3231 (4.3963) grad_norm: 1.0352 (1.1480) time: 0.6398 [2021-03-26 03:16:26 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 170/1251] eta: 0:11:45 lr: 0.000987 loss: 4.3231 (4.4014) grad_norm: 1.0209 (1.1447) time: 0.6301 [2021-03-26 03:16:32 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 180/1251] eta: 0:11:37 lr: 0.000987 loss: 4.6755 (4.4115) grad_norm: 1.1305 (1.1482) time: 0.6300 [2021-03-26 03:16:39 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 190/1251] eta: 0:11:29 lr: 0.000987 loss: 4.5207 (4.3995) grad_norm: 1.1630 (1.1498) time: 0.6260 [2021-03-26 03:16:45 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 200/1251] eta: 0:11:22 lr: 0.000987 loss: 4.3579 (4.4062) grad_norm: 1.1840 (1.1518) time: 0.6274 [2021-03-26 03:16:51 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 210/1251] eta: 0:11:15 lr: 0.000987 loss: 4.4195 (4.4059) grad_norm: 1.1233 (1.1491) time: 0.6321 [2021-03-26 03:16:58 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 220/1251] eta: 0:11:08 lr: 0.000987 loss: 4.1322 (4.3936) grad_norm: 1.0889 (1.1503) time: 0.6355 [2021-03-26 03:17:04 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 230/1251] eta: 0:11:00 lr: 0.000987 loss: 4.2768 (4.3927) grad_norm: 1.1830 (1.1503) time: 0.6299 [2021-03-26 03:17:10 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 240/1251] eta: 0:10:52 lr: 0.000987 loss: 4.5175 (4.3930) grad_norm: 1.2425 (1.1575) time: 0.6226 [2021-03-26 03:17:17 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 250/1251] eta: 0:10:46 lr: 0.000987 loss: 4.4737 (4.3961) grad_norm: 1.2738 (1.1628) time: 0.6295 [2021-03-26 03:17:23 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 260/1251] eta: 0:10:38 lr: 0.000987 loss: 4.4952 (4.3984) grad_norm: 1.1242 (1.1597) time: 0.6285 [2021-03-26 03:17:29 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 270/1251] eta: 0:10:31 lr: 0.000987 loss: 4.3299 (4.3932) grad_norm: 1.0358 (1.1583) time: 0.6248 [2021-03-26 03:17:35 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 280/1251] eta: 0:10:24 lr: 0.000987 loss: 4.5880 (4.4003) grad_norm: 1.0358 (1.1558) time: 0.6286 [2021-03-26 03:17:42 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 290/1251] eta: 0:10:18 lr: 0.000987 loss: 4.5931 (4.4030) grad_norm: 1.1086 (1.1569) time: 0.6342 [2021-03-26 03:17:48 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 300/1251] eta: 0:10:11 lr: 0.000987 loss: 4.5931 (4.4088) grad_norm: 1.1358 (1.1572) time: 0.6360 [2021-03-26 03:17:54 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 310/1251] eta: 0:10:04 lr: 0.000987 loss: 4.5518 (4.4076) grad_norm: 1.1561 (1.1605) time: 0.6303 [2021-03-26 03:18:01 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 320/1251] eta: 0:09:57 lr: 0.000987 loss: 4.5518 (4.4124) grad_norm: 1.1899 (1.1631) time: 0.6257 [2021-03-26 03:18:07 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 330/1251] eta: 0:09:50 lr: 0.000987 loss: 4.5946 (4.4180) grad_norm: 1.1074 (1.1598) time: 0.6224 [2021-03-26 03:18:13 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 340/1251] eta: 0:09:43 lr: 0.000987 loss: 4.5946 (4.4178) grad_norm: 1.0893 (1.1594) time: 0.6262 [2021-03-26 03:18:19 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 350/1251] eta: 0:09:36 lr: 0.000987 loss: 4.6390 (4.4220) grad_norm: 1.1449 (1.1592) time: 0.6254 [2021-03-26 03:18:26 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 360/1251] eta: 0:09:30 lr: 0.000987 loss: 4.6809 (4.4231) grad_norm: 1.0855 (1.1566) time: 0.6252 [2021-03-26 03:18:32 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 370/1251] eta: 0:09:23 lr: 0.000987 loss: 4.4472 (4.4219) grad_norm: 1.0770 (1.1583) time: 0.6322 [2021-03-26 03:18:38 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 380/1251] eta: 0:09:17 lr: 0.000987 loss: 4.3399 (4.4160) grad_norm: 1.0738 (1.1547) time: 0.6305 [2021-03-26 03:18:44 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 390/1251] eta: 0:09:10 lr: 0.000987 loss: 4.2938 (4.4124) grad_norm: 1.1370 (1.1541) time: 0.6264 [2021-03-26 03:18:51 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 400/1251] eta: 0:09:03 lr: 0.000987 loss: 4.4582 (4.4168) grad_norm: 1.1453 (1.1543) time: 0.6239 [2021-03-26 03:18:57 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 410/1251] eta: 0:08:56 lr: 0.000987 loss: 4.6382 (4.4189) grad_norm: 1.1680 (1.1552) time: 0.6248 [2021-03-26 03:19:03 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 420/1251] eta: 0:08:50 lr: 0.000987 loss: 4.1857 (4.4109) grad_norm: 1.1680 (1.1547) time: 0.6275 [2021-03-26 03:19:09 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 430/1251] eta: 0:08:43 lr: 0.000987 loss: 4.3792 (4.4121) grad_norm: 1.0448 (1.1518) time: 0.6218 [2021-03-26 03:19:16 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 440/1251] eta: 0:08:37 lr: 0.000987 loss: 4.4604 (4.4090) grad_norm: 1.0013 (1.1505) time: 0.6220 [2021-03-26 03:19:22 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 450/1251] eta: 0:08:30 lr: 0.000986 loss: 4.6265 (4.4138) grad_norm: 1.0686 (1.1499) time: 0.6276 [2021-03-26 03:19:28 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 460/1251] eta: 0:08:23 lr: 0.000986 loss: 4.5792 (4.4075) grad_norm: 1.1471 (1.1501) time: 0.6243 [2021-03-26 03:19:34 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 470/1251] eta: 0:08:17 lr: 0.000986 loss: 4.2172 (4.4087) grad_norm: 1.1471 (1.1500) time: 0.6244 [2021-03-26 03:19:41 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 480/1251] eta: 0:08:10 lr: 0.000986 loss: 4.5203 (4.4110) grad_norm: 1.0260 (1.1488) time: 0.6236 [2021-03-26 03:19:47 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 490/1251] eta: 0:08:04 lr: 0.000986 loss: 4.4358 (4.4074) grad_norm: 1.1383 (1.1489) time: 0.6202 [2021-03-26 03:19:53 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 500/1251] eta: 0:07:57 lr: 0.000986 loss: 4.4358 (4.4073) grad_norm: 1.1640 (1.1498) time: 0.6251 [2021-03-26 03:19:59 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 510/1251] eta: 0:07:51 lr: 0.000986 loss: 4.3901 (4.4055) grad_norm: 1.2400 (1.1528) time: 0.6298 [2021-03-26 03:20:06 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 520/1251] eta: 0:07:44 lr: 0.000986 loss: 4.4950 (4.4070) grad_norm: 1.1580 (1.1522) time: 0.6263 [2021-03-26 03:20:12 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 530/1251] eta: 0:07:38 lr: 0.000986 loss: 4.5157 (4.4050) grad_norm: 1.0566 (1.1512) time: 0.6247 [2021-03-26 03:20:18 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 540/1251] eta: 0:07:31 lr: 0.000986 loss: 4.1869 (4.4012) grad_norm: 1.0815 (1.1495) time: 0.6281 [2021-03-26 03:20:25 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 550/1251] eta: 0:07:25 lr: 0.000986 loss: 4.1264 (4.3961) grad_norm: 1.0992 (1.1505) time: 0.6346 [2021-03-26 03:20:31 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 560/1251] eta: 0:07:18 lr: 0.000986 loss: 4.3661 (4.4005) grad_norm: 1.0992 (1.1492) time: 0.6348 [2021-03-26 03:20:37 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 570/1251] eta: 0:07:12 lr: 0.000986 loss: 4.7217 (4.4047) grad_norm: 1.0897 (1.1482) time: 0.6323 [2021-03-26 03:20:44 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 580/1251] eta: 0:07:06 lr: 0.000986 loss: 4.1735 (4.3945) grad_norm: 1.0256 (1.1468) time: 0.6361 [2021-03-26 03:20:50 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 590/1251] eta: 0:06:59 lr: 0.000986 loss: 4.2473 (4.4005) grad_norm: 1.0103 (1.1452) time: 0.6314 [2021-03-26 03:20:56 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 600/1251] eta: 0:06:53 lr: 0.000986 loss: 4.5499 (4.4004) grad_norm: 1.0507 (1.1451) time: 0.6270 [2021-03-26 03:21:02 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 610/1251] eta: 0:06:46 lr: 0.000986 loss: 3.9462 (4.3941) grad_norm: 1.0823 (1.1449) time: 0.6276 [2021-03-26 03:21:09 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 620/1251] eta: 0:06:40 lr: 0.000986 loss: 3.9462 (4.3921) grad_norm: 1.0471 (1.1435) time: 0.6243 [2021-03-26 03:21:15 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 630/1251] eta: 0:06:34 lr: 0.000986 loss: 4.6310 (4.3975) grad_norm: 1.0728 (1.1439) time: 0.6293 [2021-03-26 03:21:21 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 640/1251] eta: 0:06:27 lr: 0.000986 loss: 4.7268 (4.3934) grad_norm: 1.1134 (1.1436) time: 0.6360 [2021-03-26 03:21:28 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 650/1251] eta: 0:06:21 lr: 0.000986 loss: 4.4845 (4.3955) grad_norm: 1.1274 (1.1443) time: 0.6289 [2021-03-26 03:21:34 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 660/1251] eta: 0:06:14 lr: 0.000986 loss: 4.4319 (4.3950) grad_norm: 1.2186 (1.1457) time: 0.6235 [2021-03-26 03:21:40 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 670/1251] eta: 0:06:08 lr: 0.000986 loss: 4.2706 (4.3902) grad_norm: 1.1214 (1.1449) time: 0.6256 [2021-03-26 03:21:46 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 680/1251] eta: 0:06:02 lr: 0.000986 loss: 4.3511 (4.3924) grad_norm: 1.0917 (1.1445) time: 0.6212 [2021-03-26 03:21:53 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 690/1251] eta: 0:05:55 lr: 0.000986 loss: 4.4985 (4.3884) grad_norm: 1.1162 (1.1448) time: 0.6256 [2021-03-26 03:21:59 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 700/1251] eta: 0:05:49 lr: 0.000986 loss: 4.0764 (4.3876) grad_norm: 1.0417 (1.1450) time: 0.6337 [2021-03-26 03:22:05 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 710/1251] eta: 0:05:42 lr: 0.000986 loss: 4.5053 (4.3903) grad_norm: 1.0228 (1.1431) time: 0.6257 [2021-03-26 03:22:11 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 720/1251] eta: 0:05:36 lr: 0.000986 loss: 4.3695 (4.3848) grad_norm: 1.0228 (1.1431) time: 0.6236 [2021-03-26 03:22:18 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 730/1251] eta: 0:05:30 lr: 0.000986 loss: 4.4311 (4.3875) grad_norm: 1.1375 (1.1433) time: 0.6335 [2021-03-26 03:22:24 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 740/1251] eta: 0:05:23 lr: 0.000986 loss: 4.6094 (4.3917) grad_norm: 1.1375 (1.1432) time: 0.6420 [2021-03-26 03:22:31 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 750/1251] eta: 0:05:17 lr: 0.000986 loss: 4.5524 (4.3910) grad_norm: 1.1505 (1.1440) time: 0.6363 [2021-03-26 03:22:37 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 760/1251] eta: 0:05:11 lr: 0.000986 loss: 4.3400 (4.3902) grad_norm: 1.0961 (1.1425) time: 0.6304 [2021-03-26 03:22:43 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 770/1251] eta: 0:05:04 lr: 0.000986 loss: 4.3400 (4.3917) grad_norm: 1.0288 (1.1416) time: 0.6336 [2021-03-26 03:22:50 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 780/1251] eta: 0:04:58 lr: 0.000986 loss: 4.3458 (4.3915) grad_norm: 1.1295 (1.1427) time: 0.6369 [2021-03-26 03:22:56 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 790/1251] eta: 0:04:52 lr: 0.000986 loss: 4.5829 (4.3946) grad_norm: 1.1713 (1.1438) time: 0.6366 [2021-03-26 03:23:02 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 800/1251] eta: 0:04:45 lr: 0.000986 loss: 4.4712 (4.3930) grad_norm: 1.0417 (1.1423) time: 0.6302 [2021-03-26 03:23:09 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 810/1251] eta: 0:04:39 lr: 0.000986 loss: 4.3198 (4.3918) grad_norm: 1.0131 (1.1422) time: 0.6273 [2021-03-26 03:23:15 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 820/1251] eta: 0:04:33 lr: 0.000986 loss: 4.3712 (4.3899) grad_norm: 1.1935 (1.1426) time: 0.6277 [2021-03-26 03:23:21 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 830/1251] eta: 0:04:26 lr: 0.000986 loss: 4.1969 (4.3866) grad_norm: 1.1829 (1.1425) time: 0.6270 [2021-03-26 03:23:28 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 840/1251] eta: 0:04:20 lr: 0.000986 loss: 4.4356 (4.3888) grad_norm: 1.0211 (1.1416) time: 0.6342 [2021-03-26 03:23:34 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 850/1251] eta: 0:04:14 lr: 0.000986 loss: 4.5627 (4.3886) grad_norm: 1.0480 (1.1409) time: 0.6436 [2021-03-26 03:23:40 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 860/1251] eta: 0:04:07 lr: 0.000986 loss: 4.4385 (4.3878) grad_norm: 1.0693 (1.1404) time: 0.6364 [2021-03-26 03:23:47 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 870/1251] eta: 0:04:01 lr: 0.000986 loss: 4.1862 (4.3854) grad_norm: 1.0241 (1.1403) time: 0.6269 [2021-03-26 03:23:53 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 880/1251] eta: 0:03:55 lr: 0.000986 loss: 4.3768 (4.3857) grad_norm: 1.0998 (1.1411) time: 0.6292 [2021-03-26 03:23:59 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 890/1251] eta: 0:03:48 lr: 0.000986 loss: 4.3768 (4.3844) grad_norm: 1.2153 (1.1415) time: 0.6361 [2021-03-26 03:24:06 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 900/1251] eta: 0:03:42 lr: 0.000986 loss: 4.4400 (4.3847) grad_norm: 1.1765 (1.1416) time: 0.6333 [2021-03-26 03:24:12 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 910/1251] eta: 0:03:36 lr: 0.000986 loss: 4.5594 (4.3837) grad_norm: 1.1508 (1.1432) time: 0.6307 [2021-03-26 03:24:18 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 920/1251] eta: 0:03:29 lr: 0.000986 loss: 4.1478 (4.3816) grad_norm: 1.1007 (1.1426) time: 0.6274 [2021-03-26 03:24:24 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 930/1251] eta: 0:03:23 lr: 0.000986 loss: 4.3700 (4.3815) grad_norm: 1.0645 (1.1426) time: 0.6248 [2021-03-26 03:24:31 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 940/1251] eta: 0:03:16 lr: 0.000986 loss: 4.5140 (4.3818) grad_norm: 1.1094 (1.1447) time: 0.6294 [2021-03-26 03:24:37 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 950/1251] eta: 0:03:10 lr: 0.000986 loss: 4.5445 (4.3814) grad_norm: 1.1919 (1.1452) time: 0.6281 [2021-03-26 03:24:43 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 960/1251] eta: 0:03:04 lr: 0.000986 loss: 4.1305 (4.3795) grad_norm: 1.2816 (1.1464) time: 0.6288 [2021-03-26 03:24:49 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 970/1251] eta: 0:02:57 lr: 0.000986 loss: 4.1572 (4.3787) grad_norm: 1.0886 (1.1456) time: 0.6247 [2021-03-26 03:24:56 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 980/1251] eta: 0:02:51 lr: 0.000986 loss: 4.3424 (4.3785) grad_norm: 1.0286 (1.1454) time: 0.6209 [2021-03-26 03:25:02 swin_base_patch4_window7_224] INFO: Epoch: [22] [ 990/1251] eta: 0:02:45 lr: 0.000986 loss: 4.5698 (4.3812) grad_norm: 1.1005 (1.1450) time: 0.6329 [2021-03-26 03:25:08 swin_base_patch4_window7_224] INFO: Epoch: [22] [1000/1251] eta: 0:02:38 lr: 0.000986 loss: 4.3529 (4.3804) grad_norm: 1.1005 (1.1459) time: 0.6364 [2021-03-26 03:25:15 swin_base_patch4_window7_224] INFO: Epoch: [22] [1010/1251] eta: 0:02:32 lr: 0.000986 loss: 4.1084 (4.3788) grad_norm: 1.1116 (1.1464) time: 0.6387 [2021-03-26 03:25:21 swin_base_patch4_window7_224] INFO: Epoch: [22] [1020/1251] eta: 0:02:26 lr: 0.000986 loss: 4.3121 (4.3797) grad_norm: 1.0800 (1.1466) time: 0.6329 [2021-03-26 03:25:27 swin_base_patch4_window7_224] INFO: Epoch: [22] [1030/1251] eta: 0:02:19 lr: 0.000986 loss: 4.3683 (4.3805) grad_norm: 1.0800 (1.1464) time: 0.6194 [2021-03-26 03:25:33 swin_base_patch4_window7_224] INFO: Epoch: [22] [1040/1251] eta: 0:02:13 lr: 0.000986 loss: 4.5484 (4.3820) grad_norm: 1.0937 (1.1467) time: 0.6203 [2021-03-26 03:25:40 swin_base_patch4_window7_224] INFO: Epoch: [22] [1050/1251] eta: 0:02:07 lr: 0.000986 loss: 4.5954 (4.3795) grad_norm: 1.1228 (1.1460) time: 0.6249 [2021-03-26 03:25:46 swin_base_patch4_window7_224] INFO: Epoch: [22] [1060/1251] eta: 0:02:00 lr: 0.000986 loss: 4.5954 (4.3806) grad_norm: 1.0622 (1.1456) time: 0.6296 [2021-03-26 03:25:52 swin_base_patch4_window7_224] INFO: Epoch: [22] [1070/1251] eta: 0:01:54 lr: 0.000986 loss: 4.6154 (4.3809) grad_norm: 1.0622 (1.1449) time: 0.6238 [2021-03-26 03:25:59 swin_base_patch4_window7_224] INFO: Epoch: [22] [1080/1251] eta: 0:01:48 lr: 0.000986 loss: 4.6136 (4.3809) grad_norm: 1.0740 (1.1452) time: 0.6295 [2021-03-26 03:26:05 swin_base_patch4_window7_224] INFO: Epoch: [22] [1090/1251] eta: 0:01:41 lr: 0.000986 loss: 4.5315 (4.3827) grad_norm: 1.1312 (1.1452) time: 0.6380 [2021-03-26 03:26:11 swin_base_patch4_window7_224] INFO: Epoch: [22] [1100/1251] eta: 0:01:35 lr: 0.000986 loss: 4.7146 (4.3860) grad_norm: 1.1129 (1.1450) time: 0.6345 [2021-03-26 03:26:18 swin_base_patch4_window7_224] INFO: Epoch: [22] [1110/1251] eta: 0:01:29 lr: 0.000986 loss: 4.6154 (4.3854) grad_norm: 1.1129 (1.1444) time: 0.6310 [2021-03-26 03:26:24 swin_base_patch4_window7_224] INFO: Epoch: [22] [1120/1251] eta: 0:01:22 lr: 0.000986 loss: 4.5568 (4.3842) grad_norm: 1.0778 (1.1442) time: 0.6315 [2021-03-26 03:26:30 swin_base_patch4_window7_224] INFO: Epoch: [22] [1130/1251] eta: 0:01:16 lr: 0.000986 loss: 4.3811 (4.3837) grad_norm: 1.0561 (1.1438) time: 0.6393 [2021-03-26 03:26:37 swin_base_patch4_window7_224] INFO: Epoch: [22] [1140/1251] eta: 0:01:10 lr: 0.000986 loss: 4.5090 (4.3861) grad_norm: 1.1172 (1.1453) time: 0.6400 [2021-03-26 03:26:43 swin_base_patch4_window7_224] INFO: Epoch: [22] [1150/1251] eta: 0:01:03 lr: 0.000986 loss: 4.3812 (4.3839) grad_norm: 1.1137 (1.1446) time: 0.6263 [2021-03-26 03:26:49 swin_base_patch4_window7_224] INFO: Epoch: [22] [1160/1251] eta: 0:00:57 lr: 0.000986 loss: 4.3122 (4.3844) grad_norm: 1.0132 (1.1443) time: 0.6163 [2021-03-26 03:26:55 swin_base_patch4_window7_224] INFO: Epoch: [22] [1170/1251] eta: 0:00:51 lr: 0.000986 loss: 4.6123 (4.3862) grad_norm: 1.0772 (inf) time: 0.6188 [2021-03-26 03:27:02 swin_base_patch4_window7_224] INFO: Epoch: [22] [1180/1251] eta: 0:00:44 lr: 0.000986 loss: 4.6117 (4.3873) grad_norm: 1.0990 (inf) time: 0.6272 [2021-03-26 03:27:08 swin_base_patch4_window7_224] INFO: Epoch: [22] [1190/1251] eta: 0:00:38 lr: 0.000986 loss: 4.5038 (4.3872) grad_norm: 1.0949 (inf) time: 0.6308 [2021-03-26 03:27:14 swin_base_patch4_window7_224] INFO: Epoch: [22] [1200/1251] eta: 0:00:32 lr: 0.000986 loss: 4.5134 (4.3878) grad_norm: 0.9739 (inf) time: 0.6209 [2021-03-26 03:27:20 swin_base_patch4_window7_224] INFO: Epoch: [22] [1210/1251] eta: 0:00:25 lr: 0.000986 loss: 4.6053 (4.3884) grad_norm: 1.0173 (inf) time: 0.6188 [2021-03-26 03:27:27 swin_base_patch4_window7_224] INFO: Epoch: [22] [1220/1251] eta: 0:00:19 lr: 0.000986 loss: 4.3423 (4.3862) grad_norm: 1.0930 (inf) time: 0.6275 [2021-03-26 03:27:33 swin_base_patch4_window7_224] INFO: Epoch: [22] [1230/1251] eta: 0:00:13 lr: 0.000986 loss: 4.4804 (4.3878) grad_norm: 1.0876 (inf) time: 0.6275 [2021-03-26 03:27:39 swin_base_patch4_window7_224] INFO: Epoch: [22] [1240/1251] eta: 0:00:06 lr: 0.000986 loss: 4.5929 (4.3863) grad_norm: 1.1144 (inf) time: 0.6250 [2021-03-26 03:27:45 swin_base_patch4_window7_224] INFO: Epoch: [22] [1250/1251] eta: 0:00:00 lr: 0.000986 loss: 4.2553 (4.3836) grad_norm: 1.1289 (inf) time: 0.6182 [2021-03-26 03:27:49 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:58 loss: 1.1363 (1.1363) acc1: 70.3125 (70.3125) acc5: 96.8750 (96.8750) [2021-03-26 03:27:52 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.7610 (1.6923) acc1: 60.9375 (60.0852) acc5: 82.8125 (84.2330) [2021-03-26 03:27:54 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.6318 (1.6898) acc1: 60.9375 (61.0119) acc5: 82.8125 (84.3750) [2021-03-26 03:27:57 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.6318 (1.6902) acc1: 60.9375 (60.9879) acc5: 84.3750 (84.2238) [2021-03-26 03:27:58 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.7030 (1.6868) acc1: 59.3750 (60.8613) acc5: 84.3750 (84.6418) [2021-03-26 03:28:00 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.7212 (1.6959) acc1: 60.9375 (60.7040) acc5: 84.3750 (84.8640) [2021-03-26 03:28:03 swin_base_patch4_window7_224] INFO: * Acc@1 61.866 Acc@5 84.988 loss 1.675 [2021-03-26 03:28:03 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 61.9% [2021-03-26 03:28:03 swin_base_patch4_window7_224] INFO: Max accuracy: 61.87% [2021-03-26 03:28:07 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 0/1251] eta: 1:29:25 lr: 0.000986 loss: 3.3519 (3.3519) grad_norm: 0.9277 (0.9277) time: 4.2887 [2021-03-26 03:28:13 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 10/1251] eta: 0:19:58 lr: 0.000986 loss: 4.2383 (4.1976) grad_norm: 1.0181 (1.0329) time: 0.9657 [2021-03-26 03:28:19 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 20/1251] eta: 0:16:31 lr: 0.000986 loss: 4.4957 (4.4003) grad_norm: 1.0970 (1.0761) time: 0.6310 [2021-03-26 03:28:26 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 30/1251] eta: 0:15:09 lr: 0.000986 loss: 4.6605 (4.3705) grad_norm: 1.1133 (1.0947) time: 0.6230 [2021-03-26 03:28:32 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 40/1251] eta: 0:14:27 lr: 0.000986 loss: 4.3869 (4.3338) grad_norm: 1.0699 (1.0890) time: 0.6233 [2021-03-26 03:28:38 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 50/1251] eta: 0:13:59 lr: 0.000986 loss: 4.2934 (4.3195) grad_norm: 1.0604 (1.1051) time: 0.6282 [2021-03-26 03:28:44 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 60/1251] eta: 0:13:37 lr: 0.000986 loss: 4.4369 (4.3195) grad_norm: 1.1743 (1.1208) time: 0.6250 [2021-03-26 03:28:51 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 70/1251] eta: 0:13:21 lr: 0.000986 loss: 4.4369 (4.3034) grad_norm: 1.0963 (1.1156) time: 0.6262 [2021-03-26 03:28:57 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 80/1251] eta: 0:13:07 lr: 0.000986 loss: 4.3949 (4.3203) grad_norm: 1.1765 (1.1204) time: 0.6307 [2021-03-26 03:29:03 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 90/1251] eta: 0:12:54 lr: 0.000986 loss: 4.5784 (4.3425) grad_norm: 1.0911 (1.1174) time: 0.6260 [2021-03-26 03:29:10 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 100/1251] eta: 0:12:43 lr: 0.000986 loss: 4.6425 (4.3629) grad_norm: 1.0833 (1.1213) time: 0.6275 [2021-03-26 03:29:16 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 110/1251] eta: 0:12:33 lr: 0.000986 loss: 4.5654 (4.3563) grad_norm: 1.1329 (1.1272) time: 0.6320 [2021-03-26 03:29:22 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 120/1251] eta: 0:12:24 lr: 0.000986 loss: 3.9726 (4.3287) grad_norm: 1.0822 (1.1291) time: 0.6293 [2021-03-26 03:29:28 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 130/1251] eta: 0:12:14 lr: 0.000986 loss: 4.0667 (4.3106) grad_norm: 1.1651 (1.1412) time: 0.6268 [2021-03-26 03:29:35 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 140/1251] eta: 0:12:06 lr: 0.000986 loss: 4.1176 (4.3039) grad_norm: 1.1733 (1.1436) time: 0.6290 [2021-03-26 03:29:41 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 150/1251] eta: 0:11:57 lr: 0.000986 loss: 4.0540 (4.2850) grad_norm: 1.1087 (1.1373) time: 0.6295 [2021-03-26 03:29:47 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 160/1251] eta: 0:11:49 lr: 0.000986 loss: 4.1392 (4.2916) grad_norm: 1.0933 (1.1371) time: 0.6219 [2021-03-26 03:29:53 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 170/1251] eta: 0:11:41 lr: 0.000986 loss: 4.2973 (4.2956) grad_norm: 1.2107 (1.1505) time: 0.6227 [2021-03-26 03:30:00 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 180/1251] eta: 0:11:33 lr: 0.000986 loss: 4.2934 (4.2841) grad_norm: 1.1700 (1.1467) time: 0.6306 [2021-03-26 03:30:06 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 190/1251] eta: 0:11:26 lr: 0.000986 loss: 4.5652 (4.2978) grad_norm: 1.1029 (1.1498) time: 0.6336 [2021-03-26 03:30:13 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 200/1251] eta: 0:11:19 lr: 0.000986 loss: 4.5876 (4.2990) grad_norm: 1.1099 (1.1474) time: 0.6358 [2021-03-26 03:30:19 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 210/1251] eta: 0:11:12 lr: 0.000986 loss: 4.4057 (4.3060) grad_norm: 1.1003 (1.1506) time: 0.6363 [2021-03-26 03:30:25 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 220/1251] eta: 0:11:05 lr: 0.000985 loss: 4.4656 (4.3083) grad_norm: 1.0686 (1.1478) time: 0.6303 [2021-03-26 03:30:31 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 230/1251] eta: 0:10:58 lr: 0.000985 loss: 4.4135 (4.3065) grad_norm: 1.0432 (1.1437) time: 0.6289 [2021-03-26 03:30:38 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 240/1251] eta: 0:10:51 lr: 0.000985 loss: 4.3541 (4.3062) grad_norm: 1.0986 (1.1425) time: 0.6353 [2021-03-26 03:30:44 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 250/1251] eta: 0:10:44 lr: 0.000985 loss: 4.3401 (4.3040) grad_norm: 1.0986 (1.1428) time: 0.6352 [2021-03-26 03:30:51 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 260/1251] eta: 0:10:37 lr: 0.000985 loss: 4.4255 (4.3128) grad_norm: 1.1458 (1.1461) time: 0.6346 [2021-03-26 03:30:57 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 270/1251] eta: 0:10:31 lr: 0.000985 loss: 4.5091 (4.3101) grad_norm: 1.1458 (1.1451) time: 0.6375 [2021-03-26 03:31:03 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 280/1251] eta: 0:10:24 lr: 0.000985 loss: 4.4471 (4.3107) grad_norm: 1.0697 (1.1412) time: 0.6353 [2021-03-26 03:31:09 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 290/1251] eta: 0:10:17 lr: 0.000985 loss: 4.5002 (4.3146) grad_norm: 1.0738 (1.1400) time: 0.6258 [2021-03-26 03:31:16 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 300/1251] eta: 0:10:09 lr: 0.000985 loss: 4.4988 (4.3038) grad_norm: 1.0439 (1.1368) time: 0.6195 [2021-03-26 03:31:22 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 310/1251] eta: 0:10:02 lr: 0.000985 loss: 4.4808 (4.3131) grad_norm: 1.0243 (1.1337) time: 0.6215 [2021-03-26 03:31:28 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 320/1251] eta: 0:09:56 lr: 0.000985 loss: 4.5620 (4.3153) grad_norm: 1.0470 (1.1335) time: 0.6244 [2021-03-26 03:31:34 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 330/1251] eta: 0:09:49 lr: 0.000985 loss: 4.4066 (4.3165) grad_norm: 1.1181 (1.1323) time: 0.6277 [2021-03-26 03:31:41 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 340/1251] eta: 0:09:42 lr: 0.000985 loss: 4.4066 (4.3200) grad_norm: 0.9866 (1.1281) time: 0.6244 [2021-03-26 03:31:47 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 350/1251] eta: 0:09:35 lr: 0.000985 loss: 4.3559 (4.3146) grad_norm: 0.9669 (1.1249) time: 0.6206 [2021-03-26 03:31:53 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 360/1251] eta: 0:09:28 lr: 0.000985 loss: 4.2165 (4.3135) grad_norm: 0.9730 (1.1223) time: 0.6241 [2021-03-26 03:31:59 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 370/1251] eta: 0:09:22 lr: 0.000985 loss: 4.2877 (4.3195) grad_norm: 1.0259 (1.1236) time: 0.6299 [2021-03-26 03:32:06 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 380/1251] eta: 0:09:15 lr: 0.000985 loss: 4.7247 (4.3261) grad_norm: 1.0407 (1.1244) time: 0.6220 [2021-03-26 03:32:12 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 390/1251] eta: 0:09:08 lr: 0.000985 loss: 4.5946 (4.3308) grad_norm: 1.1146 (1.1271) time: 0.6221 [2021-03-26 03:32:18 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 400/1251] eta: 0:09:02 lr: 0.000985 loss: 4.3444 (4.3283) grad_norm: 1.2729 (1.1304) time: 0.6292 [2021-03-26 03:32:24 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 410/1251] eta: 0:08:55 lr: 0.000985 loss: 4.1170 (4.3257) grad_norm: 1.2119 (1.1310) time: 0.6239 [2021-03-26 03:32:31 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 420/1251] eta: 0:08:49 lr: 0.000985 loss: 4.0356 (4.3153) grad_norm: 1.0807 (1.1309) time: 0.6267 [2021-03-26 03:32:37 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 430/1251] eta: 0:08:42 lr: 0.000985 loss: 4.1752 (4.3182) grad_norm: 1.1178 (1.1338) time: 0.6286 [2021-03-26 03:32:43 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 440/1251] eta: 0:08:35 lr: 0.000985 loss: 4.4347 (4.3151) grad_norm: 1.1292 (1.1342) time: 0.6219 [2021-03-26 03:32:50 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 450/1251] eta: 0:08:29 lr: 0.000985 loss: 4.4804 (4.3153) grad_norm: 1.1201 (1.1374) time: 0.6271 [2021-03-26 03:32:56 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 460/1251] eta: 0:08:23 lr: 0.000985 loss: 4.4804 (4.3156) grad_norm: 1.1067 (1.1367) time: 0.6338 [2021-03-26 03:33:02 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 470/1251] eta: 0:08:16 lr: 0.000985 loss: 4.3392 (4.3125) grad_norm: 1.1266 (1.1366) time: 0.6343 [2021-03-26 03:33:08 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 480/1251] eta: 0:08:10 lr: 0.000985 loss: 4.4343 (4.3155) grad_norm: 1.1068 (1.1345) time: 0.6310 [2021-03-26 03:33:15 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 490/1251] eta: 0:08:03 lr: 0.000985 loss: 4.4244 (4.3148) grad_norm: 1.0617 (1.1331) time: 0.6210 [2021-03-26 03:33:21 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 500/1251] eta: 0:07:57 lr: 0.000985 loss: 4.3662 (4.3153) grad_norm: 1.0930 (1.1328) time: 0.6217 [2021-03-26 03:33:27 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 510/1251] eta: 0:07:50 lr: 0.000985 loss: 4.4427 (4.3224) grad_norm: 1.0926 (1.1328) time: 0.6317 [2021-03-26 03:33:34 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 520/1251] eta: 0:07:44 lr: 0.000985 loss: 4.7423 (4.3303) grad_norm: 1.1714 (1.1357) time: 0.6337 [2021-03-26 03:33:40 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 530/1251] eta: 0:07:37 lr: 0.000985 loss: 4.5330 (4.3292) grad_norm: 1.1989 (1.1374) time: 0.6290 [2021-03-26 03:33:46 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 540/1251] eta: 0:07:31 lr: 0.000985 loss: 4.3765 (4.3310) grad_norm: 1.0642 (1.1357) time: 0.6291 [2021-03-26 03:33:53 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 550/1251] eta: 0:07:25 lr: 0.000985 loss: 4.3765 (4.3288) grad_norm: 1.0939 (1.1377) time: 0.6471 [2021-03-26 03:33:59 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 560/1251] eta: 0:07:19 lr: 0.000985 loss: 4.4609 (4.3342) grad_norm: 1.1346 (1.1382) time: 0.6489 [2021-03-26 03:34:06 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 570/1251] eta: 0:07:12 lr: 0.000985 loss: 4.7177 (4.3430) grad_norm: 1.0734 (1.1375) time: 0.6388 [2021-03-26 03:34:12 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 580/1251] eta: 0:07:06 lr: 0.000985 loss: 4.6729 (4.3452) grad_norm: 1.1265 (1.1384) time: 0.6328 [2021-03-26 03:34:18 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 590/1251] eta: 0:06:59 lr: 0.000985 loss: 4.4701 (4.3407) grad_norm: 1.0742 (1.1363) time: 0.6226 [2021-03-26 03:34:24 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 600/1251] eta: 0:06:53 lr: 0.000985 loss: 4.2287 (4.3410) grad_norm: 1.0701 (1.1349) time: 0.6230 [2021-03-26 03:34:31 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 610/1251] eta: 0:06:46 lr: 0.000985 loss: 4.4017 (4.3362) grad_norm: 1.0551 (1.1333) time: 0.6229 [2021-03-26 03:34:37 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 620/1251] eta: 0:06:40 lr: 0.000985 loss: 4.2914 (4.3385) grad_norm: 0.9934 (1.1313) time: 0.6199 [2021-03-26 03:34:43 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 630/1251] eta: 0:06:33 lr: 0.000985 loss: 4.5826 (4.3388) grad_norm: 0.9934 (1.1304) time: 0.6243 [2021-03-26 03:34:49 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 640/1251] eta: 0:06:27 lr: 0.000985 loss: 4.4737 (4.3396) grad_norm: 1.0090 (1.1292) time: 0.6245 [2021-03-26 03:34:56 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 650/1251] eta: 0:06:21 lr: 0.000985 loss: 4.4224 (4.3388) grad_norm: 0.9822 (1.1281) time: 0.6254 [2021-03-26 03:35:02 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 660/1251] eta: 0:06:14 lr: 0.000985 loss: 4.3862 (4.3374) grad_norm: 1.1258 (1.1288) time: 0.6314 [2021-03-26 03:35:08 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 670/1251] eta: 0:06:08 lr: 0.000985 loss: 4.4250 (4.3370) grad_norm: 1.1553 (1.1291) time: 0.6303 [2021-03-26 03:35:14 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 680/1251] eta: 0:06:02 lr: 0.000985 loss: 4.2353 (4.3350) grad_norm: 1.1882 (1.1306) time: 0.6310 [2021-03-26 03:35:21 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 690/1251] eta: 0:05:55 lr: 0.000985 loss: 4.3667 (4.3381) grad_norm: 1.0914 (1.1305) time: 0.6265 [2021-03-26 03:35:27 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 700/1251] eta: 0:05:49 lr: 0.000985 loss: 4.5955 (4.3372) grad_norm: 1.0914 (1.1310) time: 0.6313 [2021-03-26 03:35:33 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 710/1251] eta: 0:05:42 lr: 0.000985 loss: 4.4587 (4.3402) grad_norm: 1.1193 (1.1305) time: 0.6309 [2021-03-26 03:35:39 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 720/1251] eta: 0:05:36 lr: 0.000985 loss: 4.5783 (4.3408) grad_norm: 1.0418 (1.1291) time: 0.6171 [2021-03-26 03:35:46 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 730/1251] eta: 0:05:29 lr: 0.000985 loss: 4.6301 (4.3433) grad_norm: 1.0298 (1.1284) time: 0.6210 [2021-03-26 03:35:52 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 740/1251] eta: 0:05:23 lr: 0.000985 loss: 4.6301 (4.3457) grad_norm: 1.1064 (1.1303) time: 0.6392 [2021-03-26 03:35:58 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 750/1251] eta: 0:05:17 lr: 0.000985 loss: 4.2725 (4.3408) grad_norm: 1.0645 (1.1284) time: 0.6362 [2021-03-26 03:36:05 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 760/1251] eta: 0:05:11 lr: 0.000985 loss: 3.8457 (4.3372) grad_norm: 0.9864 (1.1267) time: 0.6279 [2021-03-26 03:36:11 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 770/1251] eta: 0:05:04 lr: 0.000985 loss: 4.4133 (4.3386) grad_norm: 1.0815 (1.1269) time: 0.6305 [2021-03-26 03:36:17 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 780/1251] eta: 0:04:58 lr: 0.000985 loss: 4.3232 (4.3355) grad_norm: 1.1713 (1.1286) time: 0.6371 [2021-03-26 03:36:24 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 790/1251] eta: 0:04:52 lr: 0.000985 loss: 4.3568 (4.3387) grad_norm: 1.1862 (1.1296) time: 0.6368 [2021-03-26 03:36:30 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 800/1251] eta: 0:04:45 lr: 0.000985 loss: 4.5618 (4.3395) grad_norm: 1.0714 (1.1278) time: 0.6233 [2021-03-26 03:36:36 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 810/1251] eta: 0:04:39 lr: 0.000985 loss: 4.3641 (4.3393) grad_norm: 0.9991 (1.1273) time: 0.6194 [2021-03-26 03:36:42 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 820/1251] eta: 0:04:32 lr: 0.000985 loss: 4.3242 (4.3361) grad_norm: 1.0028 (1.1263) time: 0.6259 [2021-03-26 03:36:49 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 830/1251] eta: 0:04:26 lr: 0.000985 loss: 4.3092 (4.3348) grad_norm: 1.0980 (1.1273) time: 0.6370 [2021-03-26 03:36:55 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 840/1251] eta: 0:04:20 lr: 0.000985 loss: 4.2308 (4.3321) grad_norm: 1.0980 (1.1271) time: 0.6351 [2021-03-26 03:37:01 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 850/1251] eta: 0:04:13 lr: 0.000985 loss: 4.0420 (4.3306) grad_norm: 1.0442 (1.1260) time: 0.6272 [2021-03-26 03:37:08 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 860/1251] eta: 0:04:07 lr: 0.000985 loss: 4.0583 (4.3316) grad_norm: 1.1291 (1.1269) time: 0.6304 [2021-03-26 03:37:14 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 870/1251] eta: 0:04:01 lr: 0.000985 loss: 4.2702 (4.3308) grad_norm: 1.1093 (1.1259) time: 0.6307 [2021-03-26 03:37:20 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 880/1251] eta: 0:03:54 lr: 0.000985 loss: 4.4590 (4.3326) grad_norm: 1.0459 (1.1260) time: 0.6285 [2021-03-26 03:37:27 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 890/1251] eta: 0:03:48 lr: 0.000985 loss: 4.4590 (4.3308) grad_norm: 1.1498 (1.1266) time: 0.6260 [2021-03-26 03:37:33 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 900/1251] eta: 0:03:42 lr: 0.000985 loss: 4.3409 (4.3329) grad_norm: 1.0983 (1.1271) time: 0.6284 [2021-03-26 03:37:39 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 910/1251] eta: 0:03:35 lr: 0.000985 loss: 4.3738 (4.3358) grad_norm: 1.0983 (1.1269) time: 0.6275 [2021-03-26 03:37:45 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 920/1251] eta: 0:03:29 lr: 0.000985 loss: 4.6345 (4.3377) grad_norm: 0.9956 (1.1250) time: 0.6175 [2021-03-26 03:37:52 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 930/1251] eta: 0:03:23 lr: 0.000985 loss: 4.4775 (4.3368) grad_norm: 0.9640 (1.1239) time: 0.6247 [2021-03-26 03:37:58 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 940/1251] eta: 0:03:16 lr: 0.000985 loss: 4.2762 (4.3353) grad_norm: 0.9854 (1.1232) time: 0.6288 [2021-03-26 03:38:04 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 950/1251] eta: 0:03:10 lr: 0.000985 loss: 4.4367 (4.3379) grad_norm: 1.0479 (1.1230) time: 0.6244 [2021-03-26 03:38:10 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 960/1251] eta: 0:03:03 lr: 0.000985 loss: 4.4132 (4.3348) grad_norm: 1.1018 (1.1230) time: 0.6208 [2021-03-26 03:38:17 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 970/1251] eta: 0:02:57 lr: 0.000985 loss: 4.0744 (4.3329) grad_norm: 1.1018 (1.1232) time: 0.6200 [2021-03-26 03:38:23 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 980/1251] eta: 0:02:51 lr: 0.000985 loss: 4.3601 (4.3331) grad_norm: 1.1299 (1.1244) time: 0.6222 [2021-03-26 03:38:29 swin_base_patch4_window7_224] INFO: Epoch: [23] [ 990/1251] eta: 0:02:44 lr: 0.000985 loss: 4.3239 (4.3300) grad_norm: 1.2381 (1.1258) time: 0.6261 [2021-03-26 03:38:35 swin_base_patch4_window7_224] INFO: Epoch: [23] [1000/1251] eta: 0:02:38 lr: 0.000985 loss: 4.3239 (4.3309) grad_norm: 1.1615 (1.1264) time: 0.6328 [2021-03-26 03:38:42 swin_base_patch4_window7_224] INFO: Epoch: [23] [1010/1251] eta: 0:02:32 lr: 0.000985 loss: 4.3422 (4.3289) grad_norm: 1.0712 (1.1254) time: 0.6317 [2021-03-26 03:38:48 swin_base_patch4_window7_224] INFO: Epoch: [23] [1020/1251] eta: 0:02:25 lr: 0.000985 loss: 4.2226 (4.3289) grad_norm: 1.0005 (1.1242) time: 0.6308 [2021-03-26 03:38:54 swin_base_patch4_window7_224] INFO: Epoch: [23] [1030/1251] eta: 0:02:19 lr: 0.000985 loss: 4.4489 (4.3297) grad_norm: 1.0179 (1.1245) time: 0.6284 [2021-03-26 03:39:00 swin_base_patch4_window7_224] INFO: Epoch: [23] [1040/1251] eta: 0:02:13 lr: 0.000985 loss: 4.4998 (4.3317) grad_norm: 1.1513 (1.1259) time: 0.6242 [2021-03-26 03:39:07 swin_base_patch4_window7_224] INFO: Epoch: [23] [1050/1251] eta: 0:02:06 lr: 0.000985 loss: 4.5348 (4.3326) grad_norm: 1.1518 (1.1263) time: 0.6256 [2021-03-26 03:39:13 swin_base_patch4_window7_224] INFO: Epoch: [23] [1060/1251] eta: 0:02:00 lr: 0.000985 loss: 4.5177 (4.3336) grad_norm: 1.0577 (1.1254) time: 0.6235 [2021-03-26 03:39:19 swin_base_patch4_window7_224] INFO: Epoch: [23] [1070/1251] eta: 0:01:54 lr: 0.000985 loss: 4.5177 (4.3323) grad_norm: 1.1113 (1.1262) time: 0.6214 [2021-03-26 03:39:26 swin_base_patch4_window7_224] INFO: Epoch: [23] [1080/1251] eta: 0:01:48 lr: 0.000985 loss: 4.3259 (4.3317) grad_norm: 1.1113 (1.1267) time: 0.6290 [2021-03-26 03:39:32 swin_base_patch4_window7_224] INFO: Epoch: [23] [1090/1251] eta: 0:01:41 lr: 0.000985 loss: 4.3955 (4.3318) grad_norm: 1.1210 (1.1274) time: 0.6319 [2021-03-26 03:39:38 swin_base_patch4_window7_224] INFO: Epoch: [23] [1100/1251] eta: 0:01:35 lr: 0.000985 loss: 4.3955 (4.3332) grad_norm: 1.1066 (1.1270) time: 0.6263 [2021-03-26 03:39:44 swin_base_patch4_window7_224] INFO: Epoch: [23] [1110/1251] eta: 0:01:29 lr: 0.000985 loss: 4.1958 (4.3303) grad_norm: 1.0708 (1.1266) time: 0.6235 [2021-03-26 03:39:51 swin_base_patch4_window7_224] INFO: Epoch: [23] [1120/1251] eta: 0:01:22 lr: 0.000985 loss: 3.9481 (4.3291) grad_norm: 1.0942 (1.1265) time: 0.6305 [2021-03-26 03:39:57 swin_base_patch4_window7_224] INFO: Epoch: [23] [1130/1251] eta: 0:01:16 lr: 0.000985 loss: 4.2922 (4.3289) grad_norm: 1.0962 (1.1265) time: 0.6295 [2021-03-26 03:40:03 swin_base_patch4_window7_224] INFO: Epoch: [23] [1140/1251] eta: 0:01:10 lr: 0.000985 loss: 4.4073 (4.3286) grad_norm: 1.1077 (1.1272) time: 0.6247 [2021-03-26 03:40:09 swin_base_patch4_window7_224] INFO: Epoch: [23] [1150/1251] eta: 0:01:03 lr: 0.000985 loss: 4.2844 (4.3271) grad_norm: 1.0835 (1.1265) time: 0.6268 [2021-03-26 03:40:16 swin_base_patch4_window7_224] INFO: Epoch: [23] [1160/1251] eta: 0:00:57 lr: 0.000985 loss: 4.2507 (4.3261) grad_norm: 1.0233 (1.1269) time: 0.6269 [2021-03-26 03:40:22 swin_base_patch4_window7_224] INFO: Epoch: [23] [1170/1251] eta: 0:00:51 lr: 0.000985 loss: 4.2710 (4.3270) grad_norm: 1.0915 (1.1271) time: 0.6276 [2021-03-26 03:40:28 swin_base_patch4_window7_224] INFO: Epoch: [23] [1180/1251] eta: 0:00:44 lr: 0.000985 loss: 4.5021 (4.3289) grad_norm: 0.9998 (1.1258) time: 0.6220 [2021-03-26 03:40:35 swin_base_patch4_window7_224] INFO: Epoch: [23] [1190/1251] eta: 0:00:38 lr: 0.000985 loss: 4.5912 (4.3294) grad_norm: 0.9865 (1.1257) time: 0.6261 [2021-03-26 03:40:41 swin_base_patch4_window7_224] INFO: Epoch: [23] [1200/1251] eta: 0:00:32 lr: 0.000985 loss: 4.6833 (4.3300) grad_norm: 1.0363 (1.1255) time: 0.6260 [2021-03-26 03:40:47 swin_base_patch4_window7_224] INFO: Epoch: [23] [1210/1251] eta: 0:00:25 lr: 0.000984 loss: 4.4841 (4.3283) grad_norm: 1.0184 (1.1249) time: 0.6165 [2021-03-26 03:40:53 swin_base_patch4_window7_224] INFO: Epoch: [23] [1220/1251] eta: 0:00:19 lr: 0.000984 loss: 4.5056 (4.3318) grad_norm: 1.0339 (1.1244) time: 0.6253 [2021-03-26 03:40:59 swin_base_patch4_window7_224] INFO: Epoch: [23] [1230/1251] eta: 0:00:13 lr: 0.000984 loss: 4.4448 (4.3312) grad_norm: 1.0035 (1.1233) time: 0.6265 [2021-03-26 03:41:06 swin_base_patch4_window7_224] INFO: Epoch: [23] [1240/1251] eta: 0:00:06 lr: 0.000984 loss: 4.3144 (4.3308) grad_norm: 0.9749 (1.1233) time: 0.6173 [2021-03-26 03:41:12 swin_base_patch4_window7_224] INFO: Epoch: [23] [1250/1251] eta: 0:00:00 lr: 0.000984 loss: 4.3743 (4.3312) grad_norm: 1.0793 (1.1235) time: 0.6134 [2021-03-26 03:41:16 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:07 loss: 1.3306 (1.3306) acc1: 65.6250 (65.6250) acc5: 93.7500 (93.7500) [2021-03-26 03:41:18 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.6498 (1.6374) acc1: 60.9375 (62.0739) acc5: 89.0625 (87.3580) [2021-03-26 03:41:21 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.6498 (1.6374) acc1: 62.5000 (63.0208) acc5: 85.9375 (86.0863) [2021-03-26 03:41:23 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.5826 (1.6360) acc1: 62.5000 (62.8528) acc5: 84.3750 (85.5847) [2021-03-26 03:41:25 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.6321 (1.6522) acc1: 62.5000 (62.8430) acc5: 84.3750 (85.0610) [2021-03-26 03:41:26 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.6433 (1.6474) acc1: 64.0625 (63.1040) acc5: 85.9375 (85.3440) [2021-03-26 03:41:29 swin_base_patch4_window7_224] INFO: * Acc@1 62.812 Acc@5 85.814 loss 1.645 [2021-03-26 03:41:29 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 62.8% [2021-03-26 03:41:29 swin_base_patch4_window7_224] INFO: Max accuracy: 62.81% [2021-03-26 03:41:33 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 0/1251] eta: 1:32:41 lr: 0.000984 loss: 4.7500 (4.7500) grad_norm: 0.9348 (0.9348) time: 4.4453 [2021-03-26 03:41:40 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 10/1251] eta: 0:20:09 lr: 0.000984 loss: 4.2877 (4.2191) grad_norm: 0.9573 (0.9594) time: 0.9745 [2021-03-26 03:41:46 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 20/1251] eta: 0:16:32 lr: 0.000984 loss: 4.1771 (4.1771) grad_norm: 0.9830 (0.9784) time: 0.6240 [2021-03-26 03:41:52 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 30/1251] eta: 0:15:12 lr: 0.000984 loss: 4.3773 (4.2881) grad_norm: 1.0321 (1.0630) time: 0.6223 [2021-03-26 03:41:58 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 40/1251] eta: 0:14:30 lr: 0.000984 loss: 4.5321 (4.3050) grad_norm: 1.1355 (1.0734) time: 0.6276 [2021-03-26 03:42:05 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 50/1251] eta: 0:13:59 lr: 0.000984 loss: 4.3884 (4.3318) grad_norm: 1.0712 (1.0823) time: 0.6250 [2021-03-26 03:42:11 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 60/1251] eta: 0:13:39 lr: 0.000984 loss: 4.3194 (4.2848) grad_norm: 1.1943 (1.1118) time: 0.6242 [2021-03-26 03:42:17 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 70/1251] eta: 0:13:22 lr: 0.000984 loss: 4.3194 (4.2804) grad_norm: 1.2170 (1.1222) time: 0.6295 [2021-03-26 03:42:23 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 80/1251] eta: 0:13:07 lr: 0.000984 loss: 4.4562 (4.3202) grad_norm: 1.1294 (1.1248) time: 0.6272 [2021-03-26 03:42:30 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 90/1251] eta: 0:12:54 lr: 0.000984 loss: 4.7121 (4.3376) grad_norm: 1.0940 (1.1324) time: 0.6222 [2021-03-26 03:42:36 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 100/1251] eta: 0:12:42 lr: 0.000984 loss: 4.6309 (4.3405) grad_norm: 1.0662 (1.1324) time: 0.6182 [2021-03-26 03:42:42 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 110/1251] eta: 0:12:31 lr: 0.000984 loss: 4.5917 (4.3654) grad_norm: 1.0428 (1.1241) time: 0.6225 [2021-03-26 03:42:48 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 120/1251] eta: 0:12:23 lr: 0.000984 loss: 4.2695 (4.3410) grad_norm: 1.0526 (1.1199) time: 0.6330 [2021-03-26 03:42:55 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 130/1251] eta: 0:12:13 lr: 0.000984 loss: 4.2695 (4.3543) grad_norm: 0.9962 (1.1141) time: 0.6268 [2021-03-26 03:43:01 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 140/1251] eta: 0:12:05 lr: 0.000984 loss: 4.5182 (4.3390) grad_norm: 1.0178 (1.1192) time: 0.6254 [2021-03-26 03:43:07 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 150/1251] eta: 0:11:57 lr: 0.000984 loss: 4.3957 (4.3485) grad_norm: 1.2085 (1.1269) time: 0.6377 [2021-03-26 03:43:14 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 160/1251] eta: 0:11:49 lr: 0.000984 loss: 4.3957 (4.3367) grad_norm: 1.0681 (1.1213) time: 0.6308 [2021-03-26 03:43:20 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 170/1251] eta: 0:11:40 lr: 0.000984 loss: 4.3535 (4.3423) grad_norm: 1.0303 (1.1208) time: 0.6201 [2021-03-26 03:43:26 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 180/1251] eta: 0:11:32 lr: 0.000984 loss: 4.5464 (4.3479) grad_norm: 1.1284 (1.1225) time: 0.6182 [2021-03-26 03:43:32 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 190/1251] eta: 0:11:24 lr: 0.000984 loss: 4.4113 (4.3443) grad_norm: 1.0348 (1.1183) time: 0.6211 [2021-03-26 03:43:39 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 200/1251] eta: 0:11:17 lr: 0.000984 loss: 3.9175 (4.3205) grad_norm: 1.0763 (1.1213) time: 0.6263 [2021-03-26 03:43:45 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 210/1251] eta: 0:11:10 lr: 0.000984 loss: 3.9175 (4.3058) grad_norm: 1.0897 (1.1182) time: 0.6308 [2021-03-26 03:43:51 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 220/1251] eta: 0:11:03 lr: 0.000984 loss: 4.1565 (4.3084) grad_norm: 1.0507 (1.1185) time: 0.6310 [2021-03-26 03:43:57 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 230/1251] eta: 0:10:55 lr: 0.000984 loss: 4.5096 (4.3252) grad_norm: 1.0471 (1.1160) time: 0.6199 [2021-03-26 03:44:04 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 240/1251] eta: 0:10:48 lr: 0.000984 loss: 4.4753 (4.3301) grad_norm: 1.0093 (1.1132) time: 0.6197 [2021-03-26 03:44:10 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 250/1251] eta: 0:10:41 lr: 0.000984 loss: 4.4522 (4.3283) grad_norm: 0.9732 (1.1091) time: 0.6258 [2021-03-26 03:44:16 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 260/1251] eta: 0:10:34 lr: 0.000984 loss: 4.4787 (4.3243) grad_norm: 1.0010 (1.1113) time: 0.6216 [2021-03-26 03:44:22 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 270/1251] eta: 0:10:27 lr: 0.000984 loss: 4.3620 (4.3192) grad_norm: 1.1161 (1.1128) time: 0.6249 [2021-03-26 03:44:29 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 280/1251] eta: 0:10:20 lr: 0.000984 loss: 4.3709 (4.3245) grad_norm: 1.1377 (1.1185) time: 0.6324 [2021-03-26 03:44:35 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 290/1251] eta: 0:10:13 lr: 0.000984 loss: 4.4650 (4.3242) grad_norm: 1.1117 (1.1178) time: 0.6298 [2021-03-26 03:44:41 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 300/1251] eta: 0:10:06 lr: 0.000984 loss: 4.3828 (4.3251) grad_norm: 1.1025 (1.1238) time: 0.6234 [2021-03-26 03:44:47 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 310/1251] eta: 0:09:59 lr: 0.000984 loss: 4.3289 (4.3247) grad_norm: 1.1449 (1.1211) time: 0.6196 [2021-03-26 03:44:54 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 320/1251] eta: 0:09:53 lr: 0.000984 loss: 4.2297 (4.3223) grad_norm: 1.0601 (1.1212) time: 0.6248 [2021-03-26 03:45:00 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 330/1251] eta: 0:09:46 lr: 0.000984 loss: 4.2883 (4.3205) grad_norm: 1.0991 (1.1207) time: 0.6296 [2021-03-26 03:45:06 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 340/1251] eta: 0:09:39 lr: 0.000984 loss: 4.3482 (4.3240) grad_norm: 1.0073 (1.1163) time: 0.6250 [2021-03-26 03:45:12 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 350/1251] eta: 0:09:33 lr: 0.000984 loss: 4.2154 (4.3227) grad_norm: 0.9906 (1.1142) time: 0.6209 [2021-03-26 03:45:18 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 360/1251] eta: 0:09:26 lr: 0.000984 loss: 4.2438 (4.3224) grad_norm: 1.0367 (1.1129) time: 0.6191 [2021-03-26 03:45:25 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 370/1251] eta: 0:09:20 lr: 0.000984 loss: 4.3701 (4.3221) grad_norm: 1.0824 (1.1141) time: 0.6284 [2021-03-26 03:45:31 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 380/1251] eta: 0:09:13 lr: 0.000984 loss: 4.4186 (4.3145) grad_norm: 1.1307 (1.1153) time: 0.6315 [2021-03-26 03:45:37 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 390/1251] eta: 0:09:06 lr: 0.000984 loss: 3.8051 (4.3077) grad_norm: 1.1286 (1.1151) time: 0.6263 [2021-03-26 03:45:44 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 400/1251] eta: 0:09:00 lr: 0.000984 loss: 4.2535 (4.3122) grad_norm: 1.1666 (1.1195) time: 0.6278 [2021-03-26 03:45:50 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 410/1251] eta: 0:08:53 lr: 0.000984 loss: 4.4406 (4.3160) grad_norm: 1.1666 (1.1216) time: 0.6241 [2021-03-26 03:45:56 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 420/1251] eta: 0:08:47 lr: 0.000984 loss: 4.5692 (4.3187) grad_norm: 1.0304 (1.1195) time: 0.6228 [2021-03-26 03:46:02 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 430/1251] eta: 0:08:40 lr: 0.000984 loss: 4.4905 (4.3130) grad_norm: 1.0449 (1.1198) time: 0.6272 [2021-03-26 03:46:09 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 440/1251] eta: 0:08:34 lr: 0.000984 loss: 4.3289 (4.3152) grad_norm: 1.0391 (1.1174) time: 0.6204 [2021-03-26 03:46:15 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 450/1251] eta: 0:08:27 lr: 0.000984 loss: 4.4311 (4.3152) grad_norm: 1.0292 (1.1159) time: 0.6145 [2021-03-26 03:46:21 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 460/1251] eta: 0:08:20 lr: 0.000984 loss: 4.6321 (4.3233) grad_norm: 1.0824 (1.1164) time: 0.6188 [2021-03-26 03:46:27 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 470/1251] eta: 0:08:14 lr: 0.000984 loss: 4.6321 (4.3236) grad_norm: 1.0438 (1.1143) time: 0.6183 [2021-03-26 03:46:33 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 480/1251] eta: 0:08:07 lr: 0.000984 loss: 4.2744 (4.3234) grad_norm: 1.0438 (1.1153) time: 0.6192 [2021-03-26 03:46:40 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 490/1251] eta: 0:08:01 lr: 0.000984 loss: 4.0606 (4.3165) grad_norm: 1.0887 (1.1156) time: 0.6221 [2021-03-26 03:46:46 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 500/1251] eta: 0:07:54 lr: 0.000984 loss: 4.0286 (4.3101) grad_norm: 0.9761 (1.1133) time: 0.6267 [2021-03-26 03:46:52 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 510/1251] eta: 0:07:48 lr: 0.000984 loss: 3.9768 (4.3036) grad_norm: 0.9936 (1.1129) time: 0.6260 [2021-03-26 03:46:58 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 520/1251] eta: 0:07:42 lr: 0.000984 loss: 3.9768 (4.3036) grad_norm: 1.0221 (1.1115) time: 0.6238 [2021-03-26 03:47:05 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 530/1251] eta: 0:07:35 lr: 0.000984 loss: 4.4348 (4.3021) grad_norm: 1.0019 (1.1103) time: 0.6243 [2021-03-26 03:47:11 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 540/1251] eta: 0:07:29 lr: 0.000984 loss: 4.1955 (4.2965) grad_norm: 1.0457 (1.1113) time: 0.6270 [2021-03-26 03:47:17 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 550/1251] eta: 0:07:23 lr: 0.000984 loss: 3.9466 (4.2905) grad_norm: 1.1314 (1.1123) time: 0.6398 [2021-03-26 03:47:24 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 560/1251] eta: 0:07:16 lr: 0.000984 loss: 4.2739 (4.2897) grad_norm: 1.1289 (1.1120) time: 0.6372 [2021-03-26 03:47:30 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 570/1251] eta: 0:07:10 lr: 0.000984 loss: 4.3363 (4.2899) grad_norm: 1.0969 (1.1116) time: 0.6254 [2021-03-26 03:47:36 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 580/1251] eta: 0:07:03 lr: 0.000984 loss: 4.4492 (4.2872) grad_norm: 1.0464 (1.1108) time: 0.6263 [2021-03-26 03:47:43 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 590/1251] eta: 0:06:57 lr: 0.000984 loss: 4.3823 (4.2896) grad_norm: 1.0910 (1.1110) time: 0.6324 [2021-03-26 03:47:49 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 600/1251] eta: 0:06:51 lr: 0.000984 loss: 4.3126 (4.2914) grad_norm: 1.1033 (1.1114) time: 0.6367 [2021-03-26 03:47:55 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 610/1251] eta: 0:06:45 lr: 0.000984 loss: 4.3126 (4.2894) grad_norm: 1.0107 (1.1102) time: 0.6312 [2021-03-26 03:48:01 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 620/1251] eta: 0:06:38 lr: 0.000984 loss: 4.1925 (4.2900) grad_norm: 0.9919 (1.1088) time: 0.6248 [2021-03-26 03:48:08 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 630/1251] eta: 0:06:32 lr: 0.000984 loss: 4.3924 (4.2932) grad_norm: 1.0461 (1.1087) time: 0.6299 [2021-03-26 03:48:14 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 640/1251] eta: 0:06:25 lr: 0.000984 loss: 4.5227 (4.2957) grad_norm: 1.0951 (1.1098) time: 0.6304 [2021-03-26 03:48:20 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 650/1251] eta: 0:06:19 lr: 0.000984 loss: 4.4565 (4.2930) grad_norm: 1.0951 (1.1089) time: 0.6235 [2021-03-26 03:48:26 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 660/1251] eta: 0:06:13 lr: 0.000984 loss: 4.0218 (4.2890) grad_norm: 1.0739 (1.1088) time: 0.6251 [2021-03-26 03:48:33 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 670/1251] eta: 0:06:06 lr: 0.000984 loss: 4.1471 (4.2876) grad_norm: 1.0224 (1.1069) time: 0.6276 [2021-03-26 03:48:39 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 680/1251] eta: 0:06:00 lr: 0.000984 loss: 4.3148 (4.2868) grad_norm: 0.9686 (1.1058) time: 0.6281 [2021-03-26 03:48:45 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 690/1251] eta: 0:05:54 lr: 0.000984 loss: 4.3573 (4.2861) grad_norm: 1.0332 (1.1074) time: 0.6338 [2021-03-26 03:48:52 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 700/1251] eta: 0:05:47 lr: 0.000984 loss: 4.3208 (4.2869) grad_norm: 1.1076 (1.1073) time: 0.6302 [2021-03-26 03:48:58 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 710/1251] eta: 0:05:41 lr: 0.000984 loss: 4.3208 (4.2879) grad_norm: 1.0851 (1.1070) time: 0.6272 [2021-03-26 03:49:04 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 720/1251] eta: 0:05:35 lr: 0.000984 loss: 4.2869 (4.2864) grad_norm: 1.1183 (1.1079) time: 0.6302 [2021-03-26 03:49:11 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 730/1251] eta: 0:05:28 lr: 0.000984 loss: 4.3804 (4.2888) grad_norm: 1.0681 (1.1072) time: 0.6277 [2021-03-26 03:49:17 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 740/1251] eta: 0:05:22 lr: 0.000984 loss: 4.6242 (4.2903) grad_norm: 1.0152 (1.1064) time: 0.6294 [2021-03-26 03:49:23 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 750/1251] eta: 0:05:16 lr: 0.000984 loss: 4.5513 (4.2933) grad_norm: 0.9627 (1.1052) time: 0.6318 [2021-03-26 03:49:30 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 760/1251] eta: 0:05:09 lr: 0.000984 loss: 4.4482 (4.2944) grad_norm: 1.0882 (1.1058) time: 0.6323 [2021-03-26 03:49:36 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 770/1251] eta: 0:05:03 lr: 0.000984 loss: 4.5134 (4.2981) grad_norm: 1.1001 (1.1055) time: 0.6295 [2021-03-26 03:49:42 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 780/1251] eta: 0:04:57 lr: 0.000984 loss: 4.5134 (4.2984) grad_norm: 1.0599 (1.1055) time: 0.6202 [2021-03-26 03:49:48 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 790/1251] eta: 0:04:50 lr: 0.000984 loss: 4.5795 (4.3035) grad_norm: 1.0482 (1.1053) time: 0.6209 [2021-03-26 03:49:54 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 800/1251] eta: 0:04:44 lr: 0.000984 loss: 4.6016 (4.3062) grad_norm: 1.0790 (1.1068) time: 0.6252 [2021-03-26 03:50:01 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 810/1251] eta: 0:04:38 lr: 0.000984 loss: 4.6122 (4.3076) grad_norm: 1.0790 (1.1066) time: 0.6218 [2021-03-26 03:50:07 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 820/1251] eta: 0:04:31 lr: 0.000984 loss: 4.5144 (4.3086) grad_norm: 1.1188 (1.1103) time: 0.6240 [2021-03-26 03:50:13 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 830/1251] eta: 0:04:25 lr: 0.000984 loss: 4.2915 (4.3082) grad_norm: 1.1188 (1.1099) time: 0.6305 [2021-03-26 03:50:20 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 840/1251] eta: 0:04:19 lr: 0.000984 loss: 4.4040 (4.3106) grad_norm: 1.0005 (1.1082) time: 0.6290 [2021-03-26 03:50:26 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 850/1251] eta: 0:04:12 lr: 0.000984 loss: 4.4455 (4.3128) grad_norm: 0.9843 (1.1070) time: 0.6207 [2021-03-26 03:50:32 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 860/1251] eta: 0:04:06 lr: 0.000984 loss: 4.5771 (4.3144) grad_norm: 0.9876 (1.1056) time: 0.6215 [2021-03-26 03:50:38 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 870/1251] eta: 0:04:00 lr: 0.000984 loss: 4.2254 (4.3122) grad_norm: 0.9928 (1.1042) time: 0.6314 [2021-03-26 03:50:45 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 880/1251] eta: 0:03:53 lr: 0.000984 loss: 4.2922 (4.3115) grad_norm: 0.9991 (1.1034) time: 0.6343 [2021-03-26 03:50:51 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 890/1251] eta: 0:03:47 lr: 0.000984 loss: 4.3308 (4.3122) grad_norm: 1.0704 (1.1033) time: 0.6343 [2021-03-26 03:50:57 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 900/1251] eta: 0:03:41 lr: 0.000984 loss: 4.3308 (4.3102) grad_norm: 1.0996 (1.1044) time: 0.6278 [2021-03-26 03:51:03 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 910/1251] eta: 0:03:34 lr: 0.000983 loss: 4.4689 (4.3136) grad_norm: 1.1666 (1.1049) time: 0.6224 [2021-03-26 03:51:10 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 920/1251] eta: 0:03:28 lr: 0.000983 loss: 4.3572 (4.3085) grad_norm: 1.0698 (1.1045) time: 0.6229 [2021-03-26 03:51:16 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 930/1251] eta: 0:03:22 lr: 0.000983 loss: 4.1048 (4.3052) grad_norm: 1.0053 (1.1058) time: 0.6251 [2021-03-26 03:51:22 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 940/1251] eta: 0:03:16 lr: 0.000983 loss: 4.2881 (4.3060) grad_norm: 1.0881 (1.1059) time: 0.6276 [2021-03-26 03:51:29 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 950/1251] eta: 0:03:09 lr: 0.000983 loss: 4.0876 (4.3033) grad_norm: 1.1303 (1.1083) time: 0.6276 [2021-03-26 03:51:35 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 960/1251] eta: 0:03:03 lr: 0.000983 loss: 4.0694 (4.3022) grad_norm: 1.0464 (1.1076) time: 0.6277 [2021-03-26 03:51:41 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 970/1251] eta: 0:02:57 lr: 0.000983 loss: 4.1556 (4.3010) grad_norm: 0.9992 (1.1070) time: 0.6237 [2021-03-26 03:51:47 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 980/1251] eta: 0:02:50 lr: 0.000983 loss: 4.3357 (4.3006) grad_norm: 1.0658 (1.1079) time: 0.6267 [2021-03-26 03:51:54 swin_base_patch4_window7_224] INFO: Epoch: [24] [ 990/1251] eta: 0:02:44 lr: 0.000983 loss: 4.4108 (4.3015) grad_norm: 1.1332 (1.1080) time: 0.6292 [2021-03-26 03:52:00 swin_base_patch4_window7_224] INFO: Epoch: [24] [1000/1251] eta: 0:02:38 lr: 0.000983 loss: 4.4108 (4.2993) grad_norm: 1.0921 (1.1084) time: 0.6292 [2021-03-26 03:52:06 swin_base_patch4_window7_224] INFO: Epoch: [24] [1010/1251] eta: 0:02:31 lr: 0.000983 loss: 4.2225 (4.2990) grad_norm: 1.0921 (1.1085) time: 0.6280 [2021-03-26 03:52:12 swin_base_patch4_window7_224] INFO: Epoch: [24] [1020/1251] eta: 0:02:25 lr: 0.000983 loss: 4.4562 (4.3011) grad_norm: 1.0808 (1.1080) time: 0.6265 [2021-03-26 03:52:19 swin_base_patch4_window7_224] INFO: Epoch: [24] [1030/1251] eta: 0:02:19 lr: 0.000983 loss: 4.6713 (4.3030) grad_norm: 1.0030 (1.1079) time: 0.6272 [2021-03-26 03:52:25 swin_base_patch4_window7_224] INFO: Epoch: [24] [1040/1251] eta: 0:02:12 lr: 0.000983 loss: 4.5041 (4.3038) grad_norm: 0.9565 (1.1072) time: 0.6224 [2021-03-26 03:52:31 swin_base_patch4_window7_224] INFO: Epoch: [24] [1050/1251] eta: 0:02:06 lr: 0.000983 loss: 4.3614 (4.3037) grad_norm: 1.0202 (1.1073) time: 0.6193 [2021-03-26 03:52:37 swin_base_patch4_window7_224] INFO: Epoch: [24] [1060/1251] eta: 0:02:00 lr: 0.000983 loss: 4.5025 (4.3057) grad_norm: 1.0913 (1.1071) time: 0.6294 [2021-03-26 03:52:44 swin_base_patch4_window7_224] INFO: Epoch: [24] [1070/1251] eta: 0:01:54 lr: 0.000983 loss: 4.5619 (4.3073) grad_norm: 1.0309 (1.1068) time: 0.6338 [2021-03-26 03:52:50 swin_base_patch4_window7_224] INFO: Epoch: [24] [1080/1251] eta: 0:01:47 lr: 0.000983 loss: 4.3722 (4.3078) grad_norm: 1.0003 (1.1058) time: 0.6247 [2021-03-26 03:52:56 swin_base_patch4_window7_224] INFO: Epoch: [24] [1090/1251] eta: 0:01:41 lr: 0.000983 loss: 4.4448 (4.3088) grad_norm: 0.9894 (1.1055) time: 0.6227 [2021-03-26 03:53:02 swin_base_patch4_window7_224] INFO: Epoch: [24] [1100/1251] eta: 0:01:35 lr: 0.000983 loss: 4.4912 (4.3095) grad_norm: 1.0135 (1.1048) time: 0.6264 [2021-03-26 03:53:09 swin_base_patch4_window7_224] INFO: Epoch: [24] [1110/1251] eta: 0:01:28 lr: 0.000983 loss: 4.6751 (4.3137) grad_norm: 1.0355 (1.1044) time: 0.6273 [2021-03-26 03:53:15 swin_base_patch4_window7_224] INFO: Epoch: [24] [1120/1251] eta: 0:01:22 lr: 0.000983 loss: 4.7564 (4.3159) grad_norm: 1.0808 (1.1043) time: 0.6251 [2021-03-26 03:53:21 swin_base_patch4_window7_224] INFO: Epoch: [24] [1130/1251] eta: 0:01:16 lr: 0.000983 loss: 4.4909 (4.3168) grad_norm: 1.0808 (1.1041) time: 0.6235 [2021-03-26 03:53:28 swin_base_patch4_window7_224] INFO: Epoch: [24] [1140/1251] eta: 0:01:09 lr: 0.000983 loss: 4.4753 (4.3152) grad_norm: 1.1137 (1.1047) time: 0.6284 [2021-03-26 03:53:34 swin_base_patch4_window7_224] INFO: Epoch: [24] [1150/1251] eta: 0:01:03 lr: 0.000983 loss: 4.1530 (4.3159) grad_norm: 1.1460 (1.1053) time: 0.6312 [2021-03-26 03:53:40 swin_base_patch4_window7_224] INFO: Epoch: [24] [1160/1251] eta: 0:00:57 lr: 0.000983 loss: 4.2433 (4.3132) grad_norm: 1.0980 (1.1048) time: 0.6285 [2021-03-26 03:53:46 swin_base_patch4_window7_224] INFO: Epoch: [24] [1170/1251] eta: 0:00:51 lr: 0.000983 loss: 4.2029 (4.3116) grad_norm: 1.0130 (1.1046) time: 0.6292 [2021-03-26 03:53:53 swin_base_patch4_window7_224] INFO: Epoch: [24] [1180/1251] eta: 0:00:44 lr: 0.000983 loss: 4.1302 (4.3090) grad_norm: 1.0582 (1.1039) time: 0.6303 [2021-03-26 03:53:59 swin_base_patch4_window7_224] INFO: Epoch: [24] [1190/1251] eta: 0:00:38 lr: 0.000983 loss: 4.1421 (4.3084) grad_norm: 1.0654 (1.1045) time: 0.6281 [2021-03-26 03:54:05 swin_base_patch4_window7_224] INFO: Epoch: [24] [1200/1251] eta: 0:00:32 lr: 0.000983 loss: 4.1421 (4.3069) grad_norm: 1.0879 (1.1049) time: 0.6264 [2021-03-26 03:54:12 swin_base_patch4_window7_224] INFO: Epoch: [24] [1210/1251] eta: 0:00:25 lr: 0.000983 loss: 4.4109 (4.3071) grad_norm: 1.0829 (1.1047) time: 0.6284 [2021-03-26 03:54:18 swin_base_patch4_window7_224] INFO: Epoch: [24] [1220/1251] eta: 0:00:19 lr: 0.000983 loss: 4.4813 (4.3075) grad_norm: 1.0829 (1.1049) time: 0.6305 [2021-03-26 03:54:24 swin_base_patch4_window7_224] INFO: Epoch: [24] [1230/1251] eta: 0:00:13 lr: 0.000983 loss: 4.3642 (4.3074) grad_norm: 1.0009 (1.1044) time: 0.6282 [2021-03-26 03:54:30 swin_base_patch4_window7_224] INFO: Epoch: [24] [1240/1251] eta: 0:00:06 lr: 0.000983 loss: 4.3524 (4.3084) grad_norm: 1.0009 (1.1044) time: 0.6261 [2021-03-26 03:54:37 swin_base_patch4_window7_224] INFO: Epoch: [24] [1250/1251] eta: 0:00:00 lr: 0.000983 loss: 4.3017 (4.3072) grad_norm: 1.1119 (1.1052) time: 0.6206 [2021-03-26 03:54:42 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:24 loss: 1.5059 (1.5059) acc1: 65.6250 (65.6250) acc5: 85.9375 (85.9375) [2021-03-26 03:54:44 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.5690 (1.5943) acc1: 64.0625 (64.0625) acc5: 85.9375 (85.6534) [2021-03-26 03:54:46 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.5343 (1.5816) acc1: 64.0625 (64.3601) acc5: 85.9375 (85.4911) [2021-03-26 03:54:48 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.5234 (1.5872) acc1: 64.0625 (63.6593) acc5: 84.3750 (85.0302) [2021-03-26 03:54:50 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.5857 (1.5803) acc1: 60.9375 (63.3003) acc5: 84.3750 (85.7088) [2021-03-26 03:54:51 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.4701 (1.5695) acc1: 64.0625 (63.9040) acc5: 87.5000 (86.0800) [2021-03-26 03:54:54 swin_base_patch4_window7_224] INFO: * Acc@1 63.896 Acc@5 86.418 loss 1.555 [2021-03-26 03:54:54 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 63.9% [2021-03-26 03:54:54 swin_base_patch4_window7_224] INFO: Max accuracy: 63.90% [2021-03-26 03:54:58 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 0/1251] eta: 1:25:55 lr: 0.000983 loss: 4.9938 (4.9938) grad_norm: 0.9363 (0.9363) time: 4.1208 [2021-03-26 03:55:05 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 10/1251] eta: 0:19:36 lr: 0.000983 loss: 4.6652 (4.5828) grad_norm: 0.9508 (0.9856) time: 0.9484 [2021-03-26 03:55:11 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 20/1251] eta: 0:16:19 lr: 0.000983 loss: 4.3252 (4.3543) grad_norm: 0.9612 (1.0033) time: 0.6298 [2021-03-26 03:55:17 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 30/1251] eta: 0:15:05 lr: 0.000983 loss: 4.0365 (4.2427) grad_norm: 1.0460 (1.0371) time: 0.6277 [2021-03-26 03:55:23 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 40/1251] eta: 0:14:22 lr: 0.000983 loss: 4.1196 (4.2572) grad_norm: 1.0687 (1.0560) time: 0.6243 [2021-03-26 03:55:30 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 50/1251] eta: 0:13:55 lr: 0.000983 loss: 4.1196 (4.1616) grad_norm: 1.0540 (1.0558) time: 0.6244 [2021-03-26 03:55:36 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 60/1251] eta: 0:13:34 lr: 0.000983 loss: 4.3660 (4.2429) grad_norm: 1.0396 (1.0567) time: 0.6250 [2021-03-26 03:55:42 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 70/1251] eta: 0:13:20 lr: 0.000983 loss: 4.5738 (4.2430) grad_norm: 1.1661 (1.0821) time: 0.6321 [2021-03-26 03:55:49 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 80/1251] eta: 0:13:06 lr: 0.000983 loss: 4.1494 (4.2362) grad_norm: 1.1143 (1.0793) time: 0.6359 [2021-03-26 03:55:55 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 90/1251] eta: 0:12:56 lr: 0.000983 loss: 4.4068 (4.2553) grad_norm: 1.0677 (1.0774) time: 0.6356 [2021-03-26 03:56:01 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 100/1251] eta: 0:12:44 lr: 0.000983 loss: 4.3239 (4.2540) grad_norm: 1.0113 (1.0753) time: 0.6330 [2021-03-26 03:56:08 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 110/1251] eta: 0:12:33 lr: 0.000983 loss: 4.2634 (4.2577) grad_norm: 0.9830 (1.0675) time: 0.6232 [2021-03-26 03:56:14 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 120/1251] eta: 0:12:24 lr: 0.000983 loss: 4.3042 (4.2614) grad_norm: 1.0108 (1.0714) time: 0.6292 [2021-03-26 03:56:20 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 130/1251] eta: 0:12:15 lr: 0.000983 loss: 4.3042 (4.2546) grad_norm: 1.1764 (1.0834) time: 0.6322 [2021-03-26 03:56:27 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 140/1251] eta: 0:12:07 lr: 0.000983 loss: 4.1691 (4.2492) grad_norm: 1.2032 (1.0891) time: 0.6323 [2021-03-26 03:56:33 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 150/1251] eta: 0:11:58 lr: 0.000983 loss: 4.3567 (4.2656) grad_norm: 1.1577 (1.0960) time: 0.6282 [2021-03-26 03:56:39 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 160/1251] eta: 0:11:49 lr: 0.000983 loss: 4.6014 (4.2732) grad_norm: 1.1552 (1.0980) time: 0.6219 [2021-03-26 03:56:45 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 170/1251] eta: 0:11:41 lr: 0.000983 loss: 4.4267 (4.2648) grad_norm: 1.0583 (1.0969) time: 0.6255 [2021-03-26 03:56:52 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 180/1251] eta: 0:11:33 lr: 0.000983 loss: 4.3326 (4.2589) grad_norm: 1.0583 (1.0980) time: 0.6258 [2021-03-26 03:56:58 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 190/1251] eta: 0:11:26 lr: 0.000983 loss: 4.4021 (4.2703) grad_norm: 1.1363 (1.1043) time: 0.6302 [2021-03-26 03:57:04 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 200/1251] eta: 0:11:18 lr: 0.000983 loss: 4.4327 (4.2810) grad_norm: 1.0967 (1.0990) time: 0.6292 [2021-03-26 03:57:10 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 210/1251] eta: 0:11:11 lr: 0.000983 loss: 4.4337 (4.2777) grad_norm: 0.9819 (1.0957) time: 0.6246 [2021-03-26 03:57:17 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 220/1251] eta: 0:11:04 lr: 0.000983 loss: 4.3212 (4.2730) grad_norm: 1.0349 (1.0988) time: 0.6280 [2021-03-26 03:57:23 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 230/1251] eta: 0:10:57 lr: 0.000983 loss: 4.3669 (4.2793) grad_norm: 1.0349 (1.0975) time: 0.6283 [2021-03-26 03:57:29 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 240/1251] eta: 0:10:49 lr: 0.000983 loss: 4.4148 (4.2818) grad_norm: 1.0866 (1.1017) time: 0.6254 [2021-03-26 03:57:35 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 250/1251] eta: 0:10:42 lr: 0.000983 loss: 4.3631 (4.2841) grad_norm: 1.0866 (1.1033) time: 0.6270 [2021-03-26 03:57:42 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 260/1251] eta: 0:10:36 lr: 0.000983 loss: 4.3033 (4.2798) grad_norm: 1.0711 (1.1024) time: 0.6309 [2021-03-26 03:57:48 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 270/1251] eta: 0:10:29 lr: 0.000983 loss: 4.0527 (4.2639) grad_norm: 1.0933 (1.1015) time: 0.6350 [2021-03-26 03:57:54 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 280/1251] eta: 0:10:22 lr: 0.000983 loss: 3.6289 (4.2616) grad_norm: 1.0564 (1.1010) time: 0.6277 [2021-03-26 03:58:01 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 290/1251] eta: 0:10:15 lr: 0.000983 loss: 4.1366 (4.2570) grad_norm: 1.0320 (1.1004) time: 0.6193 [2021-03-26 03:58:07 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 300/1251] eta: 0:10:08 lr: 0.000983 loss: 4.3652 (4.2668) grad_norm: 1.1040 (1.1039) time: 0.6202 [2021-03-26 03:58:13 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 310/1251] eta: 0:10:01 lr: 0.000983 loss: 4.3652 (4.2658) grad_norm: 0.9928 (1.0982) time: 0.6172 [2021-03-26 03:58:19 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 320/1251] eta: 0:09:53 lr: 0.000983 loss: 4.4642 (4.2719) grad_norm: 0.8953 (1.0935) time: 0.6143 [2021-03-26 03:58:25 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 330/1251] eta: 0:09:47 lr: 0.000983 loss: 4.3115 (4.2674) grad_norm: 0.9513 (1.0903) time: 0.6222 [2021-03-26 03:58:32 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 340/1251] eta: 0:09:40 lr: 0.000983 loss: 4.2187 (4.2666) grad_norm: 1.0012 (1.0899) time: 0.6274 [2021-03-26 03:58:38 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 350/1251] eta: 0:09:33 lr: 0.000983 loss: 4.1560 (4.2632) grad_norm: 1.0446 (1.0888) time: 0.6225 [2021-03-26 03:58:44 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 360/1251] eta: 0:09:27 lr: 0.000983 loss: 4.1533 (4.2556) grad_norm: 1.0933 (1.0904) time: 0.6314 [2021-03-26 03:58:50 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 370/1251] eta: 0:09:20 lr: 0.000983 loss: 4.2447 (4.2541) grad_norm: 1.1216 (1.0914) time: 0.6301 [2021-03-26 03:58:57 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 380/1251] eta: 0:09:14 lr: 0.000983 loss: 4.2680 (4.2575) grad_norm: 1.1038 (1.0910) time: 0.6267 [2021-03-26 03:59:03 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 390/1251] eta: 0:09:07 lr: 0.000983 loss: 4.4611 (4.2592) grad_norm: 1.0220 (1.0893) time: 0.6304 [2021-03-26 03:59:09 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 400/1251] eta: 0:09:01 lr: 0.000983 loss: 4.3850 (4.2626) grad_norm: 1.0343 (1.0935) time: 0.6252 [2021-03-26 03:59:16 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 410/1251] eta: 0:08:54 lr: 0.000983 loss: 4.3336 (4.2624) grad_norm: 1.2480 (1.0974) time: 0.6274 [2021-03-26 03:59:22 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 420/1251] eta: 0:08:47 lr: 0.000983 loss: 4.1357 (4.2582) grad_norm: 1.0934 (1.0962) time: 0.6229 [2021-03-26 03:59:28 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 430/1251] eta: 0:08:41 lr: 0.000983 loss: 4.3070 (4.2623) grad_norm: 1.0498 (1.0975) time: 0.6177 [2021-03-26 03:59:34 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 440/1251] eta: 0:08:34 lr: 0.000983 loss: 4.3197 (4.2654) grad_norm: 1.2086 (1.1025) time: 0.6225 [2021-03-26 03:59:40 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 450/1251] eta: 0:08:28 lr: 0.000983 loss: 4.4534 (4.2660) grad_norm: 1.2670 (1.1040) time: 0.6230 [2021-03-26 03:59:47 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 460/1251] eta: 0:08:21 lr: 0.000983 loss: 4.1151 (4.2560) grad_norm: 0.9653 (1.1014) time: 0.6190 [2021-03-26 03:59:53 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 470/1251] eta: 0:08:14 lr: 0.000983 loss: 3.9974 (4.2552) grad_norm: 0.9415 (1.0981) time: 0.6207 [2021-03-26 03:59:59 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 480/1251] eta: 0:08:08 lr: 0.000983 loss: 4.2620 (4.2566) grad_norm: 0.9897 (1.0968) time: 0.6196 [2021-03-26 04:00:05 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 490/1251] eta: 0:08:01 lr: 0.000983 loss: 4.4824 (4.2606) grad_norm: 0.9897 (1.0951) time: 0.6189 [2021-03-26 04:00:12 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 500/1251] eta: 0:07:55 lr: 0.000983 loss: 4.6236 (4.2670) grad_norm: 1.0015 (1.0965) time: 0.6269 [2021-03-26 04:00:18 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 510/1251] eta: 0:07:49 lr: 0.000983 loss: 4.6236 (4.2707) grad_norm: 1.1102 (1.0975) time: 0.6362 [2021-03-26 04:00:24 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 520/1251] eta: 0:07:42 lr: 0.000983 loss: 4.6968 (4.2765) grad_norm: 1.1668 (1.1000) time: 0.6350 [2021-03-26 04:00:30 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 530/1251] eta: 0:07:36 lr: 0.000983 loss: 4.4460 (4.2752) grad_norm: 1.1190 (1.0987) time: 0.6263 [2021-03-26 04:00:37 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 540/1251] eta: 0:07:29 lr: 0.000983 loss: 4.2858 (4.2741) grad_norm: 1.0519 (1.0993) time: 0.6238 [2021-03-26 04:00:43 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 550/1251] eta: 0:07:23 lr: 0.000983 loss: 4.2980 (4.2739) grad_norm: 1.0023 (1.0972) time: 0.6365 [2021-03-26 04:00:50 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 560/1251] eta: 0:07:17 lr: 0.000983 loss: 4.2224 (4.2744) grad_norm: 1.0004 (1.0965) time: 0.6411 [2021-03-26 04:00:56 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 570/1251] eta: 0:07:11 lr: 0.000983 loss: 4.2224 (4.2731) grad_norm: 1.0002 (1.0951) time: 0.6265 [2021-03-26 04:01:02 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 580/1251] eta: 0:07:04 lr: 0.000983 loss: 3.9540 (4.2681) grad_norm: 1.0034 (1.0960) time: 0.6215 [2021-03-26 04:01:08 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 590/1251] eta: 0:06:58 lr: 0.000982 loss: 4.1170 (4.2702) grad_norm: 1.0488 (1.0959) time: 0.6235 [2021-03-26 04:01:14 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 600/1251] eta: 0:06:51 lr: 0.000982 loss: 4.3986 (4.2708) grad_norm: 1.0548 (1.0973) time: 0.6275 [2021-03-26 04:01:21 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 610/1251] eta: 0:06:45 lr: 0.000982 loss: 4.1760 (4.2679) grad_norm: 1.0747 (1.0977) time: 0.6272 [2021-03-26 04:01:27 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 620/1251] eta: 0:06:38 lr: 0.000982 loss: 4.1479 (4.2659) grad_norm: 1.0654 (1.0981) time: 0.6209 [2021-03-26 04:01:33 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 630/1251] eta: 0:06:32 lr: 0.000982 loss: 4.2140 (4.2662) grad_norm: 1.1520 (1.1011) time: 0.6213 [2021-03-26 04:01:39 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 640/1251] eta: 0:06:26 lr: 0.000982 loss: 4.4070 (4.2669) grad_norm: 1.0234 (1.0990) time: 0.6212 [2021-03-26 04:01:46 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 650/1251] eta: 0:06:19 lr: 0.000982 loss: 4.3564 (4.2676) grad_norm: 0.9811 (1.0984) time: 0.6224 [2021-03-26 04:01:52 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 660/1251] eta: 0:06:13 lr: 0.000982 loss: 4.2666 (4.2685) grad_norm: 1.0173 (1.0968) time: 0.6269 [2021-03-26 04:01:58 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 670/1251] eta: 0:06:06 lr: 0.000982 loss: 4.5059 (4.2699) grad_norm: 1.0278 (1.0967) time: 0.6242 [2021-03-26 04:02:04 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 680/1251] eta: 0:06:00 lr: 0.000982 loss: 4.5059 (4.2715) grad_norm: 1.1201 (1.0991) time: 0.6253 [2021-03-26 04:02:11 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 690/1251] eta: 0:05:54 lr: 0.000982 loss: 4.3745 (4.2663) grad_norm: 1.0785 (1.0983) time: 0.6328 [2021-03-26 04:02:17 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 700/1251] eta: 0:05:48 lr: 0.000982 loss: 4.3745 (4.2646) grad_norm: 0.9804 (1.0986) time: 0.6338 [2021-03-26 04:02:23 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 710/1251] eta: 0:05:41 lr: 0.000982 loss: 4.0327 (4.2595) grad_norm: 1.0843 (1.0991) time: 0.6253 [2021-03-26 04:02:30 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 720/1251] eta: 0:05:35 lr: 0.000982 loss: 4.1680 (4.2595) grad_norm: 1.0158 (1.0979) time: 0.6327 [2021-03-26 04:02:36 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 730/1251] eta: 0:05:29 lr: 0.000982 loss: 4.2469 (4.2590) grad_norm: 1.0158 (1.0969) time: 0.6385 [2021-03-26 04:02:42 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 740/1251] eta: 0:05:22 lr: 0.000982 loss: 4.1700 (4.2567) grad_norm: 1.0337 (1.0965) time: 0.6346 [2021-03-26 04:02:49 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 750/1251] eta: 0:05:16 lr: 0.000982 loss: 4.1756 (4.2568) grad_norm: 1.0694 (1.0961) time: 0.6313 [2021-03-26 04:02:55 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 760/1251] eta: 0:05:10 lr: 0.000982 loss: 4.1756 (4.2554) grad_norm: 1.1096 (1.0970) time: 0.6269 [2021-03-26 04:03:01 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 770/1251] eta: 0:05:03 lr: 0.000982 loss: 4.1309 (4.2543) grad_norm: 1.1308 (1.0968) time: 0.6282 [2021-03-26 04:03:08 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 780/1251] eta: 0:04:57 lr: 0.000982 loss: 4.1309 (4.2525) grad_norm: 1.0594 (1.0967) time: 0.6282 [2021-03-26 04:03:14 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 790/1251] eta: 0:04:51 lr: 0.000982 loss: 4.2052 (4.2542) grad_norm: 1.0594 (1.0963) time: 0.6289 [2021-03-26 04:03:20 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 800/1251] eta: 0:04:44 lr: 0.000982 loss: 4.3941 (4.2537) grad_norm: 1.0684 (1.0968) time: 0.6275 [2021-03-26 04:03:26 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 810/1251] eta: 0:04:38 lr: 0.000982 loss: 4.2273 (4.2542) grad_norm: 1.0780 (1.0972) time: 0.6277 [2021-03-26 04:03:33 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 820/1251] eta: 0:04:32 lr: 0.000982 loss: 4.3562 (4.2534) grad_norm: 1.0780 (1.0974) time: 0.6271 [2021-03-26 04:03:39 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 830/1251] eta: 0:04:25 lr: 0.000982 loss: 4.3562 (4.2555) grad_norm: 1.2112 (1.0998) time: 0.6328 [2021-03-26 04:03:45 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 840/1251] eta: 0:04:19 lr: 0.000982 loss: 4.3323 (4.2564) grad_norm: 1.2119 (1.1000) time: 0.6398 [2021-03-26 04:03:52 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 850/1251] eta: 0:04:13 lr: 0.000982 loss: 4.5125 (4.2580) grad_norm: 1.0480 (1.0993) time: 0.6340 [2021-03-26 04:03:58 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 860/1251] eta: 0:04:06 lr: 0.000982 loss: 4.3214 (4.2561) grad_norm: 1.0708 (1.0994) time: 0.6276 [2021-03-26 04:04:04 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 870/1251] eta: 0:04:00 lr: 0.000982 loss: 4.2555 (4.2569) grad_norm: 1.0909 (1.0995) time: 0.6217 [2021-03-26 04:04:10 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 880/1251] eta: 0:03:54 lr: 0.000982 loss: 4.6016 (4.2602) grad_norm: 1.1471 (1.1014) time: 0.6218 [2021-03-26 04:04:17 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 890/1251] eta: 0:03:47 lr: 0.000982 loss: 4.5551 (4.2610) grad_norm: 1.0370 (1.1003) time: 0.6273 [2021-03-26 04:04:23 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 900/1251] eta: 0:03:41 lr: 0.000982 loss: 4.3712 (4.2624) grad_norm: 1.0007 (1.1000) time: 0.6214 [2021-03-26 04:04:29 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 910/1251] eta: 0:03:35 lr: 0.000982 loss: 4.4107 (4.2636) grad_norm: 1.0768 (1.0998) time: 0.6241 [2021-03-26 04:04:36 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 920/1251] eta: 0:03:28 lr: 0.000982 loss: 4.4607 (4.2644) grad_norm: 1.0778 (1.1006) time: 0.6337 [2021-03-26 04:04:42 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 930/1251] eta: 0:03:22 lr: 0.000982 loss: 4.4607 (4.2650) grad_norm: 1.0778 (1.1006) time: 0.6278 [2021-03-26 04:04:48 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 940/1251] eta: 0:03:16 lr: 0.000982 loss: 4.5731 (4.2679) grad_norm: 1.1418 (1.1019) time: 0.6239 [2021-03-26 04:04:54 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 950/1251] eta: 0:03:09 lr: 0.000982 loss: 4.3692 (4.2668) grad_norm: 1.1147 (1.1012) time: 0.6274 [2021-03-26 04:05:01 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 960/1251] eta: 0:03:03 lr: 0.000982 loss: 4.1894 (4.2655) grad_norm: 0.9830 (1.0999) time: 0.6264 [2021-03-26 04:05:07 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 970/1251] eta: 0:02:57 lr: 0.000982 loss: 4.1828 (4.2666) grad_norm: 1.0044 (1.0993) time: 0.6238 [2021-03-26 04:05:13 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 980/1251] eta: 0:02:50 lr: 0.000982 loss: 4.2027 (4.2658) grad_norm: 1.0210 (1.0990) time: 0.6230 [2021-03-26 04:05:19 swin_base_patch4_window7_224] INFO: Epoch: [25] [ 990/1251] eta: 0:02:44 lr: 0.000982 loss: 4.2027 (4.2662) grad_norm: 1.0819 (1.1005) time: 0.6214 [2021-03-26 04:05:25 swin_base_patch4_window7_224] INFO: Epoch: [25] [1000/1251] eta: 0:02:38 lr: 0.000982 loss: 4.4005 (4.2667) grad_norm: 1.0932 (1.1001) time: 0.6211 [2021-03-26 04:05:32 swin_base_patch4_window7_224] INFO: Epoch: [25] [1010/1251] eta: 0:02:31 lr: 0.000982 loss: 4.4185 (4.2651) grad_norm: 1.0343 (1.0994) time: 0.6215 [2021-03-26 04:05:38 swin_base_patch4_window7_224] INFO: Epoch: [25] [1020/1251] eta: 0:02:25 lr: 0.000982 loss: 4.2671 (4.2641) grad_norm: 0.9538 (1.0977) time: 0.6164 [2021-03-26 04:05:44 swin_base_patch4_window7_224] INFO: Epoch: [25] [1030/1251] eta: 0:02:19 lr: 0.000982 loss: 4.2806 (4.2648) grad_norm: 0.9558 (1.0972) time: 0.6208 [2021-03-26 04:05:50 swin_base_patch4_window7_224] INFO: Epoch: [25] [1040/1251] eta: 0:02:12 lr: 0.000982 loss: 4.4631 (4.2664) grad_norm: 1.0146 (1.0967) time: 0.6315 [2021-03-26 04:05:57 swin_base_patch4_window7_224] INFO: Epoch: [25] [1050/1251] eta: 0:02:06 lr: 0.000982 loss: 4.5074 (4.2664) grad_norm: 1.0226 (1.0960) time: 0.6283 [2021-03-26 04:06:03 swin_base_patch4_window7_224] INFO: Epoch: [25] [1060/1251] eta: 0:02:00 lr: 0.000982 loss: 4.5576 (4.2691) grad_norm: 1.0501 (1.0961) time: 0.6209 [2021-03-26 04:06:09 swin_base_patch4_window7_224] INFO: Epoch: [25] [1070/1251] eta: 0:01:54 lr: 0.000982 loss: 4.5618 (4.2707) grad_norm: 1.1009 (1.0959) time: 0.6225 [2021-03-26 04:06:15 swin_base_patch4_window7_224] INFO: Epoch: [25] [1080/1251] eta: 0:01:47 lr: 0.000982 loss: 4.4910 (4.2706) grad_norm: 1.1378 (1.0966) time: 0.6313 [2021-03-26 04:06:22 swin_base_patch4_window7_224] INFO: Epoch: [25] [1090/1251] eta: 0:01:41 lr: 0.000982 loss: 4.1659 (4.2683) grad_norm: 1.0718 (1.0961) time: 0.6309 [2021-03-26 04:06:28 swin_base_patch4_window7_224] INFO: Epoch: [25] [1100/1251] eta: 0:01:35 lr: 0.000982 loss: 4.0456 (4.2664) grad_norm: 0.9679 (1.0950) time: 0.6213 [2021-03-26 04:06:34 swin_base_patch4_window7_224] INFO: Epoch: [25] [1110/1251] eta: 0:01:28 lr: 0.000982 loss: 4.3198 (4.2675) grad_norm: 0.9926 (1.0949) time: 0.6164 [2021-03-26 04:06:40 swin_base_patch4_window7_224] INFO: Epoch: [25] [1120/1251] eta: 0:01:22 lr: 0.000982 loss: 4.4086 (4.2679) grad_norm: 1.1228 (1.0959) time: 0.6175 [2021-03-26 04:06:46 swin_base_patch4_window7_224] INFO: Epoch: [25] [1130/1251] eta: 0:01:16 lr: 0.000982 loss: 4.4086 (4.2676) grad_norm: 1.0639 (1.0950) time: 0.6184 [2021-03-26 04:06:53 swin_base_patch4_window7_224] INFO: Epoch: [25] [1140/1251] eta: 0:01:09 lr: 0.000982 loss: 4.3206 (4.2672) grad_norm: 0.9731 (1.0944) time: 0.6133 [2021-03-26 04:06:59 swin_base_patch4_window7_224] INFO: Epoch: [25] [1150/1251] eta: 0:01:03 lr: 0.000982 loss: 4.3206 (4.2682) grad_norm: 1.0462 (1.0949) time: 0.6169 [2021-03-26 04:07:05 swin_base_patch4_window7_224] INFO: Epoch: [25] [1160/1251] eta: 0:00:57 lr: 0.000982 loss: 4.2632 (4.2672) grad_norm: 1.1029 (1.0954) time: 0.6313 [2021-03-26 04:07:11 swin_base_patch4_window7_224] INFO: Epoch: [25] [1170/1251] eta: 0:00:50 lr: 0.000982 loss: 4.5480 (4.2693) grad_norm: 1.1007 (1.0953) time: 0.6308 [2021-03-26 04:07:18 swin_base_patch4_window7_224] INFO: Epoch: [25] [1180/1251] eta: 0:00:44 lr: 0.000982 loss: 4.1793 (4.2659) grad_norm: 1.1003 (1.0951) time: 0.6220 [2021-03-26 04:07:24 swin_base_patch4_window7_224] INFO: Epoch: [25] [1190/1251] eta: 0:00:38 lr: 0.000982 loss: 4.1084 (4.2677) grad_norm: 1.1081 (1.0957) time: 0.6199 [2021-03-26 04:07:30 swin_base_patch4_window7_224] INFO: Epoch: [25] [1200/1251] eta: 0:00:32 lr: 0.000982 loss: 4.3287 (4.2679) grad_norm: 1.0760 (1.0953) time: 0.6231 [2021-03-26 04:07:36 swin_base_patch4_window7_224] INFO: Epoch: [25] [1210/1251] eta: 0:00:25 lr: 0.000982 loss: 4.3020 (4.2659) grad_norm: 0.9740 (1.0945) time: 0.6278 [2021-03-26 04:07:43 swin_base_patch4_window7_224] INFO: Epoch: [25] [1220/1251] eta: 0:00:19 lr: 0.000982 loss: 4.0314 (4.2642) grad_norm: 0.9633 (1.0942) time: 0.6250 [2021-03-26 04:07:49 swin_base_patch4_window7_224] INFO: Epoch: [25] [1230/1251] eta: 0:00:13 lr: 0.000982 loss: 4.0888 (4.2626) grad_norm: 1.0154 (1.0941) time: 0.6205 [2021-03-26 04:07:55 swin_base_patch4_window7_224] INFO: Epoch: [25] [1240/1251] eta: 0:00:06 lr: 0.000982 loss: 4.0064 (4.2609) grad_norm: 1.1340 (1.0948) time: 0.6229 [2021-03-26 04:08:01 swin_base_patch4_window7_224] INFO: Epoch: [25] [1250/1251] eta: 0:00:00 lr: 0.000982 loss: 4.1545 (4.2610) grad_norm: 1.0694 (1.0943) time: 0.6245 [2021-03-26 04:09:10 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:19 loss: 1.8272 (1.8272) acc1: 59.3750 (59.3750) acc5: 79.6875 (79.6875) [2021-03-26 04:09:11 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 1.4811 (1.5370) acc1: 65.6250 (65.3409) acc5: 89.0625 (86.7898) [2021-03-26 04:09:13 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:06 loss: 1.4770 (1.5437) acc1: 65.6250 (65.1042) acc5: 87.5000 (86.3095) [2021-03-26 04:09:14 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.4496 (1.5253) acc1: 65.6250 (65.3226) acc5: 87.5000 (86.9456) [2021-03-26 04:09:16 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.5058 (1.5405) acc1: 64.0625 (64.6723) acc5: 87.5000 (86.7759) [2021-03-26 04:09:17 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.5522 (1.5529) acc1: 62.5000 (64.5120) acc5: 85.9375 (86.9440) [2021-03-26 04:09:19 swin_base_patch4_window7_224] INFO: * Acc@1 64.758 Acc@5 86.962 loss 1.541 [2021-03-26 04:09:19 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 64.8% [2021-03-26 04:09:19 swin_base_patch4_window7_224] INFO: Max accuracy: 64.76% [2021-03-26 04:09:23 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 0/1251] eta: 1:30:09 lr: 0.000982 loss: 4.3354 (4.3354) grad_norm: 1.0775 (1.0775) time: 4.3238 [2021-03-26 04:09:30 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 10/1251] eta: 0:20:00 lr: 0.000982 loss: 4.1543 (4.0883) grad_norm: 1.0775 (1.0465) time: 0.9677 [2021-03-26 04:09:36 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 20/1251] eta: 0:16:31 lr: 0.000982 loss: 4.1543 (4.1087) grad_norm: 1.0671 (1.0566) time: 0.6295 [2021-03-26 04:09:42 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 30/1251] eta: 0:15:13 lr: 0.000982 loss: 4.1940 (4.0709) grad_norm: 1.0864 (1.0904) time: 0.6279 [2021-03-26 04:09:49 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 40/1251] eta: 0:14:33 lr: 0.000982 loss: 4.3529 (4.1576) grad_norm: 1.0980 (1.0826) time: 0.6332 [2021-03-26 04:09:55 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 50/1251] eta: 0:14:03 lr: 0.000982 loss: 4.4548 (4.1892) grad_norm: 1.0359 (1.0923) time: 0.6316 [2021-03-26 04:10:01 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 60/1251] eta: 0:13:41 lr: 0.000982 loss: 4.3294 (4.2026) grad_norm: 1.0741 (1.1022) time: 0.6251 [2021-03-26 04:10:07 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 70/1251] eta: 0:13:23 lr: 0.000982 loss: 4.3268 (4.1840) grad_norm: 1.0875 (1.0964) time: 0.6239 [2021-03-26 04:10:14 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 80/1251] eta: 0:13:08 lr: 0.000982 loss: 4.1958 (4.1978) grad_norm: 1.0875 (1.0939) time: 0.6246 [2021-03-26 04:10:20 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 90/1251] eta: 0:12:55 lr: 0.000982 loss: 4.1958 (4.1937) grad_norm: 1.0282 (1.0883) time: 0.6252 [2021-03-26 04:10:26 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 100/1251] eta: 0:12:44 lr: 0.000982 loss: 4.0439 (4.1857) grad_norm: 1.0745 (1.0949) time: 0.6241 [2021-03-26 04:10:32 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 110/1251] eta: 0:12:32 lr: 0.000982 loss: 4.1448 (4.1949) grad_norm: 1.0745 (1.0890) time: 0.6212 [2021-03-26 04:10:39 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 120/1251] eta: 0:12:22 lr: 0.000982 loss: 4.4321 (4.2015) grad_norm: 1.0536 (1.0935) time: 0.6209 [2021-03-26 04:10:45 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 130/1251] eta: 0:12:14 lr: 0.000982 loss: 4.3870 (4.2015) grad_norm: 1.0870 (1.0955) time: 0.6303 [2021-03-26 04:10:51 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 140/1251] eta: 0:12:05 lr: 0.000982 loss: 4.2703 (4.1828) grad_norm: 1.0407 (1.0917) time: 0.6282 [2021-03-26 04:10:57 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 150/1251] eta: 0:11:56 lr: 0.000982 loss: 4.1558 (4.1792) grad_norm: 1.0967 (1.0995) time: 0.6201 [2021-03-26 04:11:04 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 160/1251] eta: 0:11:48 lr: 0.000982 loss: 4.3315 (4.1852) grad_norm: 1.1323 (1.0978) time: 0.6227 [2021-03-26 04:11:10 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 170/1251] eta: 0:11:40 lr: 0.000982 loss: 4.1638 (4.1724) grad_norm: 1.0854 (1.0979) time: 0.6270 [2021-03-26 04:11:16 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 180/1251] eta: 0:11:33 lr: 0.000982 loss: 3.9133 (4.1500) grad_norm: 1.0507 (1.0973) time: 0.6323 [2021-03-26 04:11:22 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 190/1251] eta: 0:11:25 lr: 0.000982 loss: 4.0837 (4.1627) grad_norm: 1.1226 (1.1019) time: 0.6292 [2021-03-26 04:11:29 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 200/1251] eta: 0:11:18 lr: 0.000982 loss: 4.3806 (4.1737) grad_norm: 1.1692 (1.1054) time: 0.6279 [2021-03-26 04:11:35 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 210/1251] eta: 0:11:11 lr: 0.000982 loss: 4.3660 (4.1860) grad_norm: 1.0754 (1.1051) time: 0.6315 [2021-03-26 04:11:41 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 220/1251] eta: 0:11:03 lr: 0.000982 loss: 4.2380 (4.1730) grad_norm: 1.0696 (1.1050) time: 0.6251 [2021-03-26 04:11:48 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 230/1251] eta: 0:10:56 lr: 0.000982 loss: 3.9033 (4.1650) grad_norm: 1.1538 (1.1084) time: 0.6239 [2021-03-26 04:11:54 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 240/1251] eta: 0:10:48 lr: 0.000981 loss: 4.0974 (4.1663) grad_norm: 1.0983 (1.1094) time: 0.6243 [2021-03-26 04:12:00 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 250/1251] eta: 0:10:41 lr: 0.000981 loss: 4.3688 (4.1759) grad_norm: 1.0767 (1.1072) time: 0.6154 [2021-03-26 04:12:06 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 260/1251] eta: 0:10:34 lr: 0.000981 loss: 4.3437 (4.1776) grad_norm: 0.9759 (1.1029) time: 0.6193 [2021-03-26 04:12:12 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 270/1251] eta: 0:10:27 lr: 0.000981 loss: 4.3335 (4.1825) grad_norm: 0.9489 (1.1008) time: 0.6311 [2021-03-26 04:12:19 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 280/1251] eta: 0:10:20 lr: 0.000981 loss: 4.2250 (4.1758) grad_norm: 1.0284 (1.0989) time: 0.6264 [2021-03-26 04:12:25 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 290/1251] eta: 0:10:13 lr: 0.000981 loss: 4.3767 (4.1870) grad_norm: 1.0120 (1.0971) time: 0.6240 [2021-03-26 04:12:31 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 300/1251] eta: 0:10:06 lr: 0.000981 loss: 4.6622 (4.2001) grad_norm: 1.0420 (1.0996) time: 0.6246 [2021-03-26 04:12:37 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 310/1251] eta: 0:09:59 lr: 0.000981 loss: 4.6622 (4.2055) grad_norm: 1.0420 (1.0970) time: 0.6200 [2021-03-26 04:12:44 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 320/1251] eta: 0:09:53 lr: 0.000981 loss: 4.4252 (4.2047) grad_norm: 0.9747 (1.0951) time: 0.6206 [2021-03-26 04:12:50 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 330/1251] eta: 0:09:46 lr: 0.000981 loss: 4.5320 (4.2178) grad_norm: 1.0032 (1.0945) time: 0.6218 [2021-03-26 04:12:56 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 340/1251] eta: 0:09:39 lr: 0.000981 loss: 4.5320 (4.2185) grad_norm: 1.0668 (1.0958) time: 0.6203 [2021-03-26 04:13:02 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 350/1251] eta: 0:09:32 lr: 0.000981 loss: 4.1961 (4.2119) grad_norm: 1.1440 (1.0994) time: 0.6183 [2021-03-26 04:13:08 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 360/1251] eta: 0:09:26 lr: 0.000981 loss: 4.1648 (4.2089) grad_norm: 1.1440 (1.0997) time: 0.6242 [2021-03-26 04:13:15 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 370/1251] eta: 0:09:19 lr: 0.000981 loss: 4.1648 (4.2018) grad_norm: 1.1527 (1.1039) time: 0.6303 [2021-03-26 04:13:21 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 380/1251] eta: 0:09:13 lr: 0.000981 loss: 4.0842 (4.1955) grad_norm: 1.1412 (1.1043) time: 0.6293 [2021-03-26 04:13:27 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 390/1251] eta: 0:09:06 lr: 0.000981 loss: 4.1087 (4.2001) grad_norm: 1.0936 (1.1050) time: 0.6332 [2021-03-26 04:13:34 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 400/1251] eta: 0:09:00 lr: 0.000981 loss: 4.3209 (4.1972) grad_norm: 1.1460 (1.1063) time: 0.6317 [2021-03-26 04:13:40 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 410/1251] eta: 0:08:53 lr: 0.000981 loss: 4.3321 (4.1999) grad_norm: 1.0761 (1.1037) time: 0.6221 [2021-03-26 04:13:46 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 420/1251] eta: 0:08:46 lr: 0.000981 loss: 4.4464 (4.1998) grad_norm: 0.9317 (1.1012) time: 0.6150 [2021-03-26 04:13:52 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 430/1251] eta: 0:08:40 lr: 0.000981 loss: 4.0123 (4.1965) grad_norm: 0.9314 (1.0997) time: 0.6157 [2021-03-26 04:13:58 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 440/1251] eta: 0:08:33 lr: 0.000981 loss: 3.9890 (4.1926) grad_norm: 0.9753 (1.0981) time: 0.6179 [2021-03-26 04:14:05 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 450/1251] eta: 0:08:27 lr: 0.000981 loss: 4.2074 (4.1931) grad_norm: 0.9753 (1.0970) time: 0.6178 [2021-03-26 04:14:11 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 460/1251] eta: 0:08:20 lr: 0.000981 loss: 3.8852 (4.1861) grad_norm: 1.0058 (1.0958) time: 0.6297 [2021-03-26 04:14:17 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 470/1251] eta: 0:08:14 lr: 0.000981 loss: 3.9709 (4.1868) grad_norm: 1.1093 (1.0965) time: 0.6296 [2021-03-26 04:14:23 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 480/1251] eta: 0:08:07 lr: 0.000981 loss: 4.2055 (4.1878) grad_norm: 1.1228 (1.0979) time: 0.6250 [2021-03-26 04:14:30 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 490/1251] eta: 0:08:01 lr: 0.000981 loss: 4.1102 (4.1878) grad_norm: 1.0141 (1.0955) time: 0.6240 [2021-03-26 04:14:36 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 500/1251] eta: 0:07:54 lr: 0.000981 loss: 4.5137 (4.1947) grad_norm: 0.9742 (1.0943) time: 0.6201 [2021-03-26 04:14:42 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 510/1251] eta: 0:07:48 lr: 0.000981 loss: 4.6148 (4.1937) grad_norm: 1.0669 (1.0948) time: 0.6247 [2021-03-26 04:14:48 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 520/1251] eta: 0:07:42 lr: 0.000981 loss: 4.3425 (4.1971) grad_norm: 1.1299 (1.0964) time: 0.6277 [2021-03-26 04:14:55 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 530/1251] eta: 0:07:35 lr: 0.000981 loss: 4.3086 (4.2015) grad_norm: 1.1373 (1.0983) time: 0.6286 [2021-03-26 04:15:01 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 540/1251] eta: 0:07:29 lr: 0.000981 loss: 4.4265 (4.2046) grad_norm: 1.0385 (1.0958) time: 0.6266 [2021-03-26 04:15:07 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 550/1251] eta: 0:07:22 lr: 0.000981 loss: 4.4265 (4.2009) grad_norm: 0.9617 (1.0927) time: 0.6275 [2021-03-26 04:15:14 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 560/1251] eta: 0:07:16 lr: 0.000981 loss: 4.3453 (4.2039) grad_norm: 0.9267 (1.0926) time: 0.6278 [2021-03-26 04:15:20 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 570/1251] eta: 0:07:10 lr: 0.000981 loss: 4.3453 (4.2030) grad_norm: 1.1380 (1.0936) time: 0.6322 [2021-03-26 04:15:26 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 580/1251] eta: 0:07:03 lr: 0.000981 loss: 4.3004 (4.2028) grad_norm: 1.1027 (1.0941) time: 0.6330 [2021-03-26 04:15:33 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 590/1251] eta: 0:06:57 lr: 0.000981 loss: 4.3071 (4.2055) grad_norm: 1.0972 (1.0944) time: 0.6333 [2021-03-26 04:15:39 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 600/1251] eta: 0:06:51 lr: 0.000981 loss: 4.3071 (4.2072) grad_norm: 1.0352 (1.0932) time: 0.6352 [2021-03-26 04:15:45 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 610/1251] eta: 0:06:44 lr: 0.000981 loss: 4.2789 (4.2062) grad_norm: 0.9764 (1.0923) time: 0.6252 [2021-03-26 04:15:51 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 620/1251] eta: 0:06:38 lr: 0.000981 loss: 4.0632 (4.1999) grad_norm: 1.0852 (1.0930) time: 0.6184 [2021-03-26 04:15:58 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 630/1251] eta: 0:06:32 lr: 0.000981 loss: 3.8949 (4.1974) grad_norm: 1.0852 (1.0922) time: 0.6232 [2021-03-26 04:16:04 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 640/1251] eta: 0:06:25 lr: 0.000981 loss: 4.2361 (4.1999) grad_norm: 1.0527 (1.0915) time: 0.6249 [2021-03-26 04:16:10 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 650/1251] eta: 0:06:19 lr: 0.000981 loss: 4.3251 (4.1987) grad_norm: 1.0195 (1.0907) time: 0.6270 [2021-03-26 04:16:16 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 660/1251] eta: 0:06:13 lr: 0.000981 loss: 4.2944 (4.1986) grad_norm: 1.0195 (1.0903) time: 0.6315 [2021-03-26 04:16:23 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 670/1251] eta: 0:06:06 lr: 0.000981 loss: 4.3591 (4.1989) grad_norm: 1.0137 (1.0888) time: 0.6214 [2021-03-26 04:16:29 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 680/1251] eta: 0:06:00 lr: 0.000981 loss: 4.2776 (4.2004) grad_norm: 0.9551 (1.0893) time: 0.6168 [2021-03-26 04:16:35 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 690/1251] eta: 0:05:53 lr: 0.000981 loss: 4.2194 (4.1973) grad_norm: 1.1951 (1.0906) time: 0.6257 [2021-03-26 04:16:41 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 700/1251] eta: 0:05:47 lr: 0.000981 loss: 4.3209 (4.1973) grad_norm: 1.1791 (1.0920) time: 0.6311 [2021-03-26 04:16:48 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 710/1251] eta: 0:05:41 lr: 0.000981 loss: 4.3209 (4.1987) grad_norm: 1.2043 (1.0945) time: 0.6285 [2021-03-26 04:16:54 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 720/1251] eta: 0:05:34 lr: 0.000981 loss: 4.4794 (4.2027) grad_norm: 1.1076 (1.0941) time: 0.6283 [2021-03-26 04:17:00 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 730/1251] eta: 0:05:28 lr: 0.000981 loss: 4.1145 (4.1992) grad_norm: 1.0707 (1.0946) time: 0.6345 [2021-03-26 04:17:07 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 740/1251] eta: 0:05:22 lr: 0.000981 loss: 4.0404 (4.2008) grad_norm: 1.0929 (1.0957) time: 0.6373 [2021-03-26 04:17:13 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 750/1251] eta: 0:05:16 lr: 0.000981 loss: 4.0844 (4.1980) grad_norm: 1.0969 (1.0954) time: 0.6333 [2021-03-26 04:17:19 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 760/1251] eta: 0:05:09 lr: 0.000981 loss: 4.1537 (4.1994) grad_norm: 1.0375 (1.0945) time: 0.6322 [2021-03-26 04:17:25 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 770/1251] eta: 0:05:03 lr: 0.000981 loss: 4.3137 (4.2000) grad_norm: 0.9799 (1.0932) time: 0.6220 [2021-03-26 04:17:32 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 780/1251] eta: 0:04:57 lr: 0.000981 loss: 4.3318 (4.2011) grad_norm: 0.9811 (1.0932) time: 0.6172 [2021-03-26 04:17:38 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 790/1251] eta: 0:04:50 lr: 0.000981 loss: 4.3907 (4.2036) grad_norm: 1.1211 (1.0932) time: 0.6249 [2021-03-26 04:17:44 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 800/1251] eta: 0:04:44 lr: 0.000981 loss: 4.5671 (4.2069) grad_norm: 1.0261 (1.0922) time: 0.6244 [2021-03-26 04:17:50 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 810/1251] eta: 0:04:37 lr: 0.000981 loss: 4.5522 (4.2085) grad_norm: 0.9864 (1.0909) time: 0.6215 [2021-03-26 04:17:57 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 820/1251] eta: 0:04:31 lr: 0.000981 loss: 4.3464 (4.2081) grad_norm: 1.0700 (1.0918) time: 0.6251 [2021-03-26 04:18:03 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 830/1251] eta: 0:04:25 lr: 0.000981 loss: 4.2848 (4.2102) grad_norm: 1.1278 (1.0924) time: 0.6284 [2021-03-26 04:18:09 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 840/1251] eta: 0:04:18 lr: 0.000981 loss: 4.0967 (4.2067) grad_norm: 1.1081 (1.0920) time: 0.6228 [2021-03-26 04:18:15 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 850/1251] eta: 0:04:12 lr: 0.000981 loss: 4.0713 (4.2084) grad_norm: 1.0657 (1.0930) time: 0.6266 [2021-03-26 04:18:22 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 860/1251] eta: 0:04:06 lr: 0.000981 loss: 4.4454 (4.2103) grad_norm: 1.1213 (1.0930) time: 0.6267 [2021-03-26 04:18:28 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 870/1251] eta: 0:04:00 lr: 0.000981 loss: 4.3201 (4.2076) grad_norm: 1.0365 (1.0930) time: 0.6185 [2021-03-26 04:18:34 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 880/1251] eta: 0:03:53 lr: 0.000981 loss: 4.1222 (4.2067) grad_norm: 1.0692 (1.0948) time: 0.6197 [2021-03-26 04:18:40 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 890/1251] eta: 0:03:47 lr: 0.000981 loss: 4.1196 (4.2032) grad_norm: 1.1673 (1.0946) time: 0.6262 [2021-03-26 04:18:47 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 900/1251] eta: 0:03:41 lr: 0.000981 loss: 4.2257 (4.2030) grad_norm: 1.0572 (1.0948) time: 0.6362 [2021-03-26 04:18:53 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 910/1251] eta: 0:03:34 lr: 0.000981 loss: 4.1705 (4.1988) grad_norm: 1.0689 (1.0960) time: 0.6290 [2021-03-26 04:18:59 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 920/1251] eta: 0:03:28 lr: 0.000981 loss: 4.1705 (4.1991) grad_norm: 1.0604 (1.0957) time: 0.6198 [2021-03-26 04:19:06 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 930/1251] eta: 0:03:22 lr: 0.000981 loss: 4.2391 (4.1985) grad_norm: 1.0707 (1.0969) time: 0.6257 [2021-03-26 04:19:12 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 940/1251] eta: 0:03:15 lr: 0.000981 loss: 4.2391 (4.1988) grad_norm: 1.1204 (1.0959) time: 0.6288 [2021-03-26 04:19:18 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 950/1251] eta: 0:03:09 lr: 0.000981 loss: 4.3950 (4.2032) grad_norm: 0.9235 (1.0944) time: 0.6213 [2021-03-26 04:19:24 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 960/1251] eta: 0:03:03 lr: 0.000981 loss: 4.5620 (4.2045) grad_norm: 0.9258 (1.0936) time: 0.6197 [2021-03-26 04:19:30 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 970/1251] eta: 0:02:56 lr: 0.000981 loss: 4.4263 (4.2044) grad_norm: 0.9704 (1.0930) time: 0.6243 [2021-03-26 04:19:37 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 980/1251] eta: 0:02:50 lr: 0.000981 loss: 4.4066 (4.2054) grad_norm: 0.9945 (1.0922) time: 0.6230 [2021-03-26 04:19:43 swin_base_patch4_window7_224] INFO: Epoch: [26] [ 990/1251] eta: 0:02:44 lr: 0.000981 loss: 4.4628 (4.2083) grad_norm: 0.9604 (1.0903) time: 0.6214 [2021-03-26 04:19:49 swin_base_patch4_window7_224] INFO: Epoch: [26] [1000/1251] eta: 0:02:37 lr: 0.000981 loss: 4.4765 (4.2081) grad_norm: 0.9604 (1.0900) time: 0.6260 [2021-03-26 04:19:55 swin_base_patch4_window7_224] INFO: Epoch: [26] [1010/1251] eta: 0:02:31 lr: 0.000981 loss: 4.3294 (4.2101) grad_norm: 1.0461 (1.0901) time: 0.6271 [2021-03-26 04:20:02 swin_base_patch4_window7_224] INFO: Epoch: [26] [1020/1251] eta: 0:02:25 lr: 0.000981 loss: 4.4543 (4.2110) grad_norm: 1.0461 (1.0900) time: 0.6200 [2021-03-26 04:20:08 swin_base_patch4_window7_224] INFO: Epoch: [26] [1030/1251] eta: 0:02:19 lr: 0.000981 loss: 4.3395 (4.2106) grad_norm: 1.0276 (1.0898) time: 0.6214 [2021-03-26 04:20:14 swin_base_patch4_window7_224] INFO: Epoch: [26] [1040/1251] eta: 0:02:12 lr: 0.000981 loss: 4.1312 (4.2108) grad_norm: 1.0276 (1.0901) time: 0.6249 [2021-03-26 04:20:20 swin_base_patch4_window7_224] INFO: Epoch: [26] [1050/1251] eta: 0:02:06 lr: 0.000981 loss: 4.1863 (4.2114) grad_norm: 1.0731 (1.0907) time: 0.6256 [2021-03-26 04:20:27 swin_base_patch4_window7_224] INFO: Epoch: [26] [1060/1251] eta: 0:02:00 lr: 0.000981 loss: 4.1863 (4.2109) grad_norm: 1.0498 (1.0904) time: 0.6295 [2021-03-26 04:20:33 swin_base_patch4_window7_224] INFO: Epoch: [26] [1070/1251] eta: 0:01:53 lr: 0.000981 loss: 4.3862 (4.2137) grad_norm: 1.0487 (1.0900) time: 0.6289 [2021-03-26 04:20:39 swin_base_patch4_window7_224] INFO: Epoch: [26] [1080/1251] eta: 0:01:47 lr: 0.000981 loss: 4.4924 (4.2139) grad_norm: 1.0583 (1.0898) time: 0.6207 [2021-03-26 04:20:45 swin_base_patch4_window7_224] INFO: Epoch: [26] [1090/1251] eta: 0:01:41 lr: 0.000981 loss: 4.4883 (4.2174) grad_norm: 1.0586 (1.0899) time: 0.6223 [2021-03-26 04:20:52 swin_base_patch4_window7_224] INFO: Epoch: [26] [1100/1251] eta: 0:01:34 lr: 0.000981 loss: 4.3599 (4.2167) grad_norm: 1.0951 (1.0901) time: 0.6257 [2021-03-26 04:20:58 swin_base_patch4_window7_224] INFO: Epoch: [26] [1110/1251] eta: 0:01:28 lr: 0.000981 loss: 4.1713 (4.2153) grad_norm: 1.0744 (1.0903) time: 0.6237 [2021-03-26 04:21:04 swin_base_patch4_window7_224] INFO: Epoch: [26] [1120/1251] eta: 0:01:22 lr: 0.000980 loss: 4.0474 (4.2121) grad_norm: 1.0838 (1.0906) time: 0.6269 [2021-03-26 04:21:10 swin_base_patch4_window7_224] INFO: Epoch: [26] [1130/1251] eta: 0:01:16 lr: 0.000980 loss: 3.9219 (4.2106) grad_norm: 1.0788 (1.0904) time: 0.6286 [2021-03-26 04:21:17 swin_base_patch4_window7_224] INFO: Epoch: [26] [1140/1251] eta: 0:01:09 lr: 0.000980 loss: 3.9219 (4.2083) grad_norm: 1.0315 (1.0910) time: 0.6220 [2021-03-26 04:21:23 swin_base_patch4_window7_224] INFO: Epoch: [26] [1150/1251] eta: 0:01:03 lr: 0.000980 loss: 4.0640 (4.2084) grad_norm: 1.0436 (1.0914) time: 0.6236 [2021-03-26 04:21:29 swin_base_patch4_window7_224] INFO: Epoch: [26] [1160/1251] eta: 0:00:57 lr: 0.000980 loss: 4.2583 (4.2076) grad_norm: 1.1030 (1.0919) time: 0.6267 [2021-03-26 04:21:35 swin_base_patch4_window7_224] INFO: Epoch: [26] [1170/1251] eta: 0:00:50 lr: 0.000980 loss: 4.1452 (4.2072) grad_norm: 0.9987 (1.0905) time: 0.6185 [2021-03-26 04:21:42 swin_base_patch4_window7_224] INFO: Epoch: [26] [1180/1251] eta: 0:00:44 lr: 0.000980 loss: 4.1452 (4.2070) grad_norm: 0.9378 (1.0903) time: 0.6222 [2021-03-26 04:21:48 swin_base_patch4_window7_224] INFO: Epoch: [26] [1190/1251] eta: 0:00:38 lr: 0.000980 loss: 4.2021 (4.2059) grad_norm: 1.0015 (1.0903) time: 0.6259 [2021-03-26 04:21:54 swin_base_patch4_window7_224] INFO: Epoch: [26] [1200/1251] eta: 0:00:32 lr: 0.000980 loss: 3.9251 (4.2022) grad_norm: 1.0806 (1.0906) time: 0.6252 [2021-03-26 04:22:00 swin_base_patch4_window7_224] INFO: Epoch: [26] [1210/1251] eta: 0:00:25 lr: 0.000980 loss: 3.9251 (4.2022) grad_norm: 1.0544 (1.0905) time: 0.6266 [2021-03-26 04:22:07 swin_base_patch4_window7_224] INFO: Epoch: [26] [1220/1251] eta: 0:00:19 lr: 0.000980 loss: 4.5825 (4.2053) grad_norm: 1.0705 (1.0914) time: 0.6289 [2021-03-26 04:22:13 swin_base_patch4_window7_224] INFO: Epoch: [26] [1230/1251] eta: 0:00:13 lr: 0.000980 loss: 4.4311 (4.2028) grad_norm: 1.0910 (1.0910) time: 0.6286 [2021-03-26 04:22:19 swin_base_patch4_window7_224] INFO: Epoch: [26] [1240/1251] eta: 0:00:06 lr: 0.000980 loss: 3.8387 (4.2014) grad_norm: 1.0299 (1.0910) time: 0.6175 [2021-03-26 04:22:25 swin_base_patch4_window7_224] INFO: Epoch: [26] [1250/1251] eta: 0:00:00 lr: 0.000980 loss: 4.2276 (4.2016) grad_norm: 1.0793 (1.0910) time: 0.6091 [2021-03-26 04:22:29 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:42 loss: 1.7541 (1.7541) acc1: 57.8125 (57.8125) acc5: 81.2500 (81.2500) [2021-03-26 04:22:31 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.5936 (1.5568) acc1: 62.5000 (63.7784) acc5: 87.5000 (86.3636) [2021-03-26 04:22:34 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.5607 (1.5650) acc1: 64.0625 (63.6905) acc5: 87.5000 (86.3839) [2021-03-26 04:22:36 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.5368 (1.5266) acc1: 65.6250 (64.5161) acc5: 85.9375 (86.9456) [2021-03-26 04:22:38 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.5013 (1.5213) acc1: 64.0625 (64.6341) acc5: 87.5000 (87.0046) [2021-03-26 04:22:39 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.5013 (1.5095) acc1: 65.6250 (65.2800) acc5: 87.5000 (87.1040) [2021-03-26 04:22:42 swin_base_patch4_window7_224] INFO: * Acc@1 65.126 Acc@5 87.378 loss 1.491 [2021-03-26 04:22:42 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 65.1% [2021-03-26 04:22:42 swin_base_patch4_window7_224] INFO: Max accuracy: 65.13% [2021-03-26 04:22:46 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 0/1251] eta: 1:32:19 lr: 0.000980 loss: 4.3340 (4.3340) grad_norm: 1.8838 (1.8838) time: 4.4277 [2021-03-26 04:22:53 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 10/1251] eta: 0:20:05 lr: 0.000980 loss: 3.8866 (3.7738) grad_norm: 1.1046 (1.2174) time: 0.9716 [2021-03-26 04:22:59 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 20/1251] eta: 0:16:31 lr: 0.000980 loss: 4.1884 (3.9437) grad_norm: 1.1054 (1.1763) time: 0.6246 [2021-03-26 04:23:05 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 30/1251] eta: 0:15:13 lr: 0.000980 loss: 4.4638 (4.1095) grad_norm: 1.0938 (1.1431) time: 0.6250 [2021-03-26 04:23:11 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 40/1251] eta: 0:14:30 lr: 0.000980 loss: 4.3518 (4.1389) grad_norm: 1.0242 (1.1094) time: 0.6283 [2021-03-26 04:23:18 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 50/1251] eta: 0:14:03 lr: 0.000980 loss: 4.0119 (4.1197) grad_norm: 1.0238 (1.0995) time: 0.6312 [2021-03-26 04:23:24 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 60/1251] eta: 0:13:40 lr: 0.000980 loss: 4.1406 (4.1165) grad_norm: 1.0193 (1.0878) time: 0.6280 [2021-03-26 04:23:30 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 70/1251] eta: 0:13:23 lr: 0.000980 loss: 4.3879 (4.1437) grad_norm: 1.1245 (1.0970) time: 0.6246 [2021-03-26 04:23:36 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 80/1251] eta: 0:13:07 lr: 0.000980 loss: 4.4129 (4.1845) grad_norm: 0.9912 (1.0741) time: 0.6225 [2021-03-26 04:23:43 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 90/1251] eta: 0:12:54 lr: 0.000980 loss: 4.4494 (4.2128) grad_norm: 0.9273 (1.0672) time: 0.6196 [2021-03-26 04:23:49 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 100/1251] eta: 0:12:42 lr: 0.000980 loss: 4.5241 (4.2352) grad_norm: 1.0416 (1.0678) time: 0.6216 [2021-03-26 04:23:55 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 110/1251] eta: 0:12:31 lr: 0.000980 loss: 4.5100 (4.2235) grad_norm: 1.0657 (1.0701) time: 0.6229 [2021-03-26 04:24:01 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 120/1251] eta: 0:12:22 lr: 0.000980 loss: 4.2500 (4.2294) grad_norm: 1.0254 (1.0700) time: 0.6249 [2021-03-26 04:24:08 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 130/1251] eta: 0:12:13 lr: 0.000980 loss: 4.1223 (4.1969) grad_norm: 1.0395 (1.0711) time: 0.6276 [2021-03-26 04:24:14 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 140/1251] eta: 0:12:04 lr: 0.000980 loss: 3.9512 (4.1801) grad_norm: 1.0313 (1.0664) time: 0.6232 [2021-03-26 04:24:20 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 150/1251] eta: 0:11:55 lr: 0.000980 loss: 4.0734 (4.1782) grad_norm: 0.9974 (1.0633) time: 0.6222 [2021-03-26 04:24:26 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 160/1251] eta: 0:11:47 lr: 0.000980 loss: 4.1271 (4.1785) grad_norm: 1.0099 (1.0668) time: 0.6239 [2021-03-26 04:24:33 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 170/1251] eta: 0:11:39 lr: 0.000980 loss: 4.1271 (4.1658) grad_norm: 1.0935 (1.0723) time: 0.6213 [2021-03-26 04:24:39 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 180/1251] eta: 0:11:31 lr: 0.000980 loss: 3.4768 (4.1399) grad_norm: 1.0293 (1.0709) time: 0.6235 [2021-03-26 04:24:45 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 190/1251] eta: 0:11:23 lr: 0.000980 loss: 3.9239 (4.1417) grad_norm: 1.0115 (1.0706) time: 0.6260 [2021-03-26 04:24:51 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 200/1251] eta: 0:11:16 lr: 0.000980 loss: 4.2808 (4.1460) grad_norm: 1.0534 (1.0716) time: 0.6279 [2021-03-26 04:24:58 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 210/1251] eta: 0:11:09 lr: 0.000980 loss: 4.2808 (4.1350) grad_norm: 1.0534 (1.0698) time: 0.6310 [2021-03-26 04:25:04 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 220/1251] eta: 0:11:02 lr: 0.000980 loss: 4.0462 (4.1258) grad_norm: 1.0506 (1.0703) time: 0.6310 [2021-03-26 04:25:10 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 230/1251] eta: 0:10:55 lr: 0.000980 loss: 4.1873 (4.1334) grad_norm: 0.9993 (1.0660) time: 0.6278 [2021-03-26 04:25:17 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 240/1251] eta: 0:10:48 lr: 0.000980 loss: 4.2192 (4.1302) grad_norm: 0.9965 (1.0653) time: 0.6258 [2021-03-26 04:25:23 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 250/1251] eta: 0:10:41 lr: 0.000980 loss: 4.1000 (4.1311) grad_norm: 1.0238 (1.0633) time: 0.6271 [2021-03-26 04:25:29 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 260/1251] eta: 0:10:34 lr: 0.000980 loss: 4.1000 (4.1328) grad_norm: 1.0238 (1.0625) time: 0.6242 [2021-03-26 04:25:35 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 270/1251] eta: 0:10:27 lr: 0.000980 loss: 4.2309 (4.1350) grad_norm: 1.0434 (1.0642) time: 0.6235 [2021-03-26 04:25:42 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 280/1251] eta: 0:10:20 lr: 0.000980 loss: 4.2119 (4.1322) grad_norm: 1.0374 (1.0636) time: 0.6277 [2021-03-26 04:25:48 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 290/1251] eta: 0:10:13 lr: 0.000980 loss: 4.3185 (4.1418) grad_norm: 1.0956 (1.0671) time: 0.6227 [2021-03-26 04:25:54 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 300/1251] eta: 0:10:06 lr: 0.000980 loss: 4.2434 (4.1447) grad_norm: 1.0458 (1.0662) time: 0.6190 [2021-03-26 04:26:00 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 310/1251] eta: 0:09:59 lr: 0.000980 loss: 3.9500 (4.1370) grad_norm: 1.0226 (1.0668) time: 0.6255 [2021-03-26 04:26:06 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 320/1251] eta: 0:09:52 lr: 0.000980 loss: 4.0696 (4.1459) grad_norm: 1.0408 (1.0667) time: 0.6239 [2021-03-26 04:26:13 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 330/1251] eta: 0:09:46 lr: 0.000980 loss: 4.3906 (4.1390) grad_norm: 1.0349 (1.0693) time: 0.6260 [2021-03-26 04:26:19 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 340/1251] eta: 0:09:39 lr: 0.000980 loss: 4.2011 (4.1393) grad_norm: 1.0364 (1.0692) time: 0.6312 [2021-03-26 04:26:25 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 350/1251] eta: 0:09:33 lr: 0.000980 loss: 4.2022 (4.1401) grad_norm: 0.9800 (1.0678) time: 0.6252 [2021-03-26 04:26:32 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 360/1251] eta: 0:09:26 lr: 0.000980 loss: 4.3620 (4.1462) grad_norm: 0.9884 (1.0664) time: 0.6225 [2021-03-26 04:26:38 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 370/1251] eta: 0:09:19 lr: 0.000980 loss: 4.2336 (4.1427) grad_norm: 1.0491 (1.0694) time: 0.6243 [2021-03-26 04:26:44 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 380/1251] eta: 0:09:13 lr: 0.000980 loss: 4.1033 (4.1442) grad_norm: 1.0579 (1.0669) time: 0.6245 [2021-03-26 04:26:50 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 390/1251] eta: 0:09:06 lr: 0.000980 loss: 4.3666 (4.1481) grad_norm: 0.9964 (1.0663) time: 0.6234 [2021-03-26 04:26:57 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 400/1251] eta: 0:09:00 lr: 0.000980 loss: 3.8339 (4.1406) grad_norm: 1.0581 (1.0674) time: 0.6288 [2021-03-26 04:27:03 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 410/1251] eta: 0:08:53 lr: 0.000980 loss: 4.3789 (4.1520) grad_norm: 1.1324 (1.0693) time: 0.6268 [2021-03-26 04:27:09 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 420/1251] eta: 0:08:47 lr: 0.000980 loss: 4.3789 (4.1459) grad_norm: 1.1243 (1.0725) time: 0.6251 [2021-03-26 04:27:15 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 430/1251] eta: 0:08:40 lr: 0.000980 loss: 4.0310 (4.1397) grad_norm: 1.1055 (1.0740) time: 0.6304 [2021-03-26 04:27:22 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 440/1251] eta: 0:08:34 lr: 0.000980 loss: 3.9412 (4.1364) grad_norm: 1.1055 (1.0747) time: 0.6267 [2021-03-26 04:27:28 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 450/1251] eta: 0:08:27 lr: 0.000980 loss: 3.8259 (4.1269) grad_norm: 1.0771 (1.0748) time: 0.6254 [2021-03-26 04:27:34 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 460/1251] eta: 0:08:21 lr: 0.000980 loss: 4.2654 (4.1332) grad_norm: 1.0137 (1.0735) time: 0.6215 [2021-03-26 04:27:40 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 470/1251] eta: 0:08:14 lr: 0.000980 loss: 4.3541 (4.1332) grad_norm: 1.0327 (1.0737) time: 0.6192 [2021-03-26 04:27:46 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 480/1251] eta: 0:08:07 lr: 0.000980 loss: 4.3346 (4.1324) grad_norm: 1.0327 (1.0720) time: 0.6188 [2021-03-26 04:27:53 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 490/1251] eta: 0:08:01 lr: 0.000980 loss: 4.0563 (4.1303) grad_norm: 0.9754 (1.0714) time: 0.6156 [2021-03-26 04:27:59 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 500/1251] eta: 0:07:54 lr: 0.000980 loss: 4.1893 (4.1356) grad_norm: 1.0017 (1.0716) time: 0.6219 [2021-03-26 04:28:05 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 510/1251] eta: 0:07:48 lr: 0.000980 loss: 4.1983 (4.1384) grad_norm: 1.0283 (1.0717) time: 0.6249 [2021-03-26 04:28:11 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 520/1251] eta: 0:07:41 lr: 0.000980 loss: 4.1776 (4.1356) grad_norm: 1.0195 (inf) time: 0.6190 [2021-03-26 04:28:17 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 530/1251] eta: 0:07:35 lr: 0.000980 loss: 4.3055 (4.1415) grad_norm: 1.1335 (inf) time: 0.6173 [2021-03-26 04:28:24 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 540/1251] eta: 0:07:28 lr: 0.000980 loss: 4.4487 (4.1417) grad_norm: 1.0749 (inf) time: 0.6178 [2021-03-26 04:28:30 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 550/1251] eta: 0:07:22 lr: 0.000980 loss: 4.4881 (4.1460) grad_norm: 1.0655 (inf) time: 0.6279 [2021-03-26 04:28:36 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 560/1251] eta: 0:07:16 lr: 0.000980 loss: 4.3026 (4.1437) grad_norm: 1.0804 (inf) time: 0.6409 [2021-03-26 04:28:43 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 570/1251] eta: 0:07:10 lr: 0.000980 loss: 3.7896 (4.1367) grad_norm: 1.0676 (inf) time: 0.6309 [2021-03-26 04:28:49 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 580/1251] eta: 0:07:03 lr: 0.000980 loss: 3.9833 (4.1390) grad_norm: 1.0624 (inf) time: 0.6225 [2021-03-26 04:28:55 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 590/1251] eta: 0:06:57 lr: 0.000980 loss: 4.4581 (4.1449) grad_norm: 0.9903 (inf) time: 0.6203 [2021-03-26 04:29:01 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 600/1251] eta: 0:06:50 lr: 0.000980 loss: 4.6493 (4.1521) grad_norm: 0.9819 (inf) time: 0.6254 [2021-03-26 04:29:08 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 610/1251] eta: 0:06:44 lr: 0.000980 loss: 4.3974 (4.1539) grad_norm: 0.9859 (inf) time: 0.6266 [2021-03-26 04:29:14 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 620/1251] eta: 0:06:37 lr: 0.000980 loss: 4.2342 (4.1559) grad_norm: 0.9855 (inf) time: 0.6161 [2021-03-26 04:29:20 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 630/1251] eta: 0:06:31 lr: 0.000980 loss: 4.1675 (4.1586) grad_norm: 1.0037 (inf) time: 0.6158 [2021-03-26 04:29:26 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 640/1251] eta: 0:06:25 lr: 0.000980 loss: 4.1675 (4.1552) grad_norm: 1.0617 (inf) time: 0.6257 [2021-03-26 04:29:32 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 650/1251] eta: 0:06:18 lr: 0.000980 loss: 3.9956 (4.1526) grad_norm: 1.1019 (inf) time: 0.6274 [2021-03-26 04:29:39 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 660/1251] eta: 0:06:12 lr: 0.000980 loss: 4.0295 (4.1520) grad_norm: 1.0885 (inf) time: 0.6209 [2021-03-26 04:29:45 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 670/1251] eta: 0:06:06 lr: 0.000980 loss: 4.2775 (4.1546) grad_norm: 1.0885 (inf) time: 0.6239 [2021-03-26 04:29:51 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 680/1251] eta: 0:05:59 lr: 0.000980 loss: 4.2747 (4.1548) grad_norm: 1.0860 (inf) time: 0.6260 [2021-03-26 04:29:57 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 690/1251] eta: 0:05:53 lr: 0.000980 loss: 4.1240 (4.1537) grad_norm: 1.0549 (inf) time: 0.6226 [2021-03-26 04:30:04 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 700/1251] eta: 0:05:47 lr: 0.000980 loss: 4.2891 (4.1531) grad_norm: 0.9902 (inf) time: 0.6226 [2021-03-26 04:30:10 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 710/1251] eta: 0:05:40 lr: 0.000980 loss: 4.4849 (4.1578) grad_norm: 1.0141 (inf) time: 0.6165 [2021-03-26 04:30:16 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 720/1251] eta: 0:05:34 lr: 0.000980 loss: 4.4223 (4.1588) grad_norm: 0.9869 (inf) time: 0.6109 [2021-03-26 04:30:22 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 730/1251] eta: 0:05:27 lr: 0.000979 loss: 4.1939 (4.1583) grad_norm: 1.0272 (inf) time: 0.6227 [2021-03-26 04:30:28 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 740/1251] eta: 0:05:21 lr: 0.000979 loss: 4.1831 (4.1581) grad_norm: 0.9791 (inf) time: 0.6302 [2021-03-26 04:30:35 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 750/1251] eta: 0:05:15 lr: 0.000979 loss: 4.2269 (4.1577) grad_norm: 0.9934 (inf) time: 0.6333 [2021-03-26 04:30:41 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 760/1251] eta: 0:05:09 lr: 0.000979 loss: 4.2348 (4.1577) grad_norm: 1.0688 (inf) time: 0.6313 [2021-03-26 04:30:47 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 770/1251] eta: 0:05:02 lr: 0.000979 loss: 4.1578 (4.1562) grad_norm: 1.1331 (inf) time: 0.6272 [2021-03-26 04:30:54 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 780/1251] eta: 0:04:56 lr: 0.000979 loss: 4.3022 (4.1585) grad_norm: 1.0530 (inf) time: 0.6241 [2021-03-26 04:31:00 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 790/1251] eta: 0:04:50 lr: 0.000979 loss: 4.3571 (4.1577) grad_norm: 1.0338 (inf) time: 0.6215 [2021-03-26 04:31:06 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 800/1251] eta: 0:04:43 lr: 0.000979 loss: 4.1226 (4.1584) grad_norm: 0.9628 (inf) time: 0.6192 [2021-03-26 04:31:12 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 810/1251] eta: 0:04:37 lr: 0.000979 loss: 4.2039 (4.1601) grad_norm: 0.9875 (inf) time: 0.6228 [2021-03-26 04:31:19 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 820/1251] eta: 0:04:31 lr: 0.000979 loss: 4.0169 (4.1562) grad_norm: 1.0044 (inf) time: 0.6331 [2021-03-26 04:31:25 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 830/1251] eta: 0:04:24 lr: 0.000979 loss: 4.1200 (4.1575) grad_norm: 1.0837 (inf) time: 0.6352 [2021-03-26 04:31:31 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 840/1251] eta: 0:04:18 lr: 0.000979 loss: 4.2032 (4.1563) grad_norm: 1.1872 (inf) time: 0.6310 [2021-03-26 04:31:38 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 850/1251] eta: 0:04:12 lr: 0.000979 loss: 4.2032 (4.1545) grad_norm: 1.1586 (inf) time: 0.6282 [2021-03-26 04:31:44 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 860/1251] eta: 0:04:06 lr: 0.000979 loss: 4.0195 (4.1533) grad_norm: 1.1509 (inf) time: 0.6348 [2021-03-26 04:31:50 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 870/1251] eta: 0:03:59 lr: 0.000979 loss: 4.0195 (4.1511) grad_norm: 1.0745 (inf) time: 0.6344 [2021-03-26 04:31:57 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 880/1251] eta: 0:03:53 lr: 0.000979 loss: 4.1190 (4.1496) grad_norm: 1.0745 (inf) time: 0.6309 [2021-03-26 04:32:03 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 890/1251] eta: 0:03:47 lr: 0.000979 loss: 4.1922 (4.1517) grad_norm: 1.1205 (inf) time: 0.6328 [2021-03-26 04:32:09 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 900/1251] eta: 0:03:40 lr: 0.000979 loss: 4.1617 (4.1495) grad_norm: 1.1184 (inf) time: 0.6268 [2021-03-26 04:32:15 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 910/1251] eta: 0:03:34 lr: 0.000979 loss: 4.1398 (4.1508) grad_norm: 1.0914 (inf) time: 0.6240 [2021-03-26 04:32:22 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 920/1251] eta: 0:03:28 lr: 0.000979 loss: 4.2746 (4.1536) grad_norm: 1.0339 (inf) time: 0.6256 [2021-03-26 04:32:28 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 930/1251] eta: 0:03:22 lr: 0.000979 loss: 4.5060 (4.1581) grad_norm: 1.0493 (inf) time: 0.6320 [2021-03-26 04:32:34 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 940/1251] eta: 0:03:15 lr: 0.000979 loss: 4.4198 (4.1596) grad_norm: 1.0561 (inf) time: 0.6288 [2021-03-26 04:32:40 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 950/1251] eta: 0:03:09 lr: 0.000979 loss: 4.3166 (4.1604) grad_norm: 0.9562 (inf) time: 0.6208 [2021-03-26 04:32:47 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 960/1251] eta: 0:03:03 lr: 0.000979 loss: 4.2854 (4.1602) grad_norm: 1.0059 (inf) time: 0.6293 [2021-03-26 04:32:53 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 970/1251] eta: 0:02:56 lr: 0.000979 loss: 4.1462 (4.1600) grad_norm: 1.0821 (inf) time: 0.6323 [2021-03-26 04:32:59 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 980/1251] eta: 0:02:50 lr: 0.000979 loss: 4.2853 (4.1611) grad_norm: 1.0788 (inf) time: 0.6225 [2021-03-26 04:33:05 swin_base_patch4_window7_224] INFO: Epoch: [27] [ 990/1251] eta: 0:02:44 lr: 0.000979 loss: 4.4496 (4.1633) grad_norm: 1.0096 (inf) time: 0.6147 [2021-03-26 04:33:12 swin_base_patch4_window7_224] INFO: Epoch: [27] [1000/1251] eta: 0:02:37 lr: 0.000979 loss: 4.3934 (4.1637) grad_norm: 0.9512 (inf) time: 0.6214 [2021-03-26 04:33:18 swin_base_patch4_window7_224] INFO: Epoch: [27] [1010/1251] eta: 0:02:31 lr: 0.000979 loss: 4.2093 (4.1635) grad_norm: 0.9532 (inf) time: 0.6226 [2021-03-26 04:33:24 swin_base_patch4_window7_224] INFO: Epoch: [27] [1020/1251] eta: 0:02:25 lr: 0.000979 loss: 4.1804 (4.1633) grad_norm: 1.0390 (inf) time: 0.6198 [2021-03-26 04:33:30 swin_base_patch4_window7_224] INFO: Epoch: [27] [1030/1251] eta: 0:02:18 lr: 0.000979 loss: 4.1804 (4.1612) grad_norm: 1.0668 (inf) time: 0.6212 [2021-03-26 04:33:36 swin_base_patch4_window7_224] INFO: Epoch: [27] [1040/1251] eta: 0:02:12 lr: 0.000979 loss: 4.1971 (4.1603) grad_norm: 1.0804 (inf) time: 0.6194 [2021-03-26 04:33:43 swin_base_patch4_window7_224] INFO: Epoch: [27] [1050/1251] eta: 0:02:06 lr: 0.000979 loss: 4.1971 (4.1603) grad_norm: 1.1015 (inf) time: 0.6245 [2021-03-26 04:33:49 swin_base_patch4_window7_224] INFO: Epoch: [27] [1060/1251] eta: 0:02:00 lr: 0.000979 loss: 4.4381 (4.1634) grad_norm: 1.0404 (inf) time: 0.6317 [2021-03-26 04:33:55 swin_base_patch4_window7_224] INFO: Epoch: [27] [1070/1251] eta: 0:01:53 lr: 0.000979 loss: 4.3986 (4.1623) grad_norm: 1.0298 (inf) time: 0.6284 [2021-03-26 04:34:02 swin_base_patch4_window7_224] INFO: Epoch: [27] [1080/1251] eta: 0:01:47 lr: 0.000979 loss: 4.2574 (4.1633) grad_norm: 1.0393 (inf) time: 0.6260 [2021-03-26 04:34:08 swin_base_patch4_window7_224] INFO: Epoch: [27] [1090/1251] eta: 0:01:41 lr: 0.000979 loss: 4.2650 (4.1635) grad_norm: 0.9926 (inf) time: 0.6213 [2021-03-26 04:34:14 swin_base_patch4_window7_224] INFO: Epoch: [27] [1100/1251] eta: 0:01:34 lr: 0.000979 loss: 4.3765 (4.1659) grad_norm: 0.9411 (inf) time: 0.6132 [2021-03-26 04:34:20 swin_base_patch4_window7_224] INFO: Epoch: [27] [1110/1251] eta: 0:01:28 lr: 0.000979 loss: 4.2316 (4.1649) grad_norm: 1.0313 (inf) time: 0.6180 [2021-03-26 04:34:26 swin_base_patch4_window7_224] INFO: Epoch: [27] [1120/1251] eta: 0:01:22 lr: 0.000979 loss: 4.1961 (4.1640) grad_norm: 1.0378 (inf) time: 0.6202 [2021-03-26 04:34:33 swin_base_patch4_window7_224] INFO: Epoch: [27] [1130/1251] eta: 0:01:15 lr: 0.000979 loss: 4.1903 (4.1640) grad_norm: 0.9766 (inf) time: 0.6177 [2021-03-26 04:34:39 swin_base_patch4_window7_224] INFO: Epoch: [27] [1140/1251] eta: 0:01:09 lr: 0.000979 loss: 4.1903 (4.1643) grad_norm: 1.0172 (inf) time: 0.6221 [2021-03-26 04:34:45 swin_base_patch4_window7_224] INFO: Epoch: [27] [1150/1251] eta: 0:01:03 lr: 0.000979 loss: 4.2419 (4.1654) grad_norm: 1.0400 (inf) time: 0.6243 [2021-03-26 04:34:51 swin_base_patch4_window7_224] INFO: Epoch: [27] [1160/1251] eta: 0:00:57 lr: 0.000979 loss: 4.3170 (4.1651) grad_norm: 0.9531 (inf) time: 0.6197 [2021-03-26 04:34:58 swin_base_patch4_window7_224] INFO: Epoch: [27] [1170/1251] eta: 0:00:50 lr: 0.000979 loss: 4.4330 (4.1681) grad_norm: 0.9545 (inf) time: 0.6265 [2021-03-26 04:35:04 swin_base_patch4_window7_224] INFO: Epoch: [27] [1180/1251] eta: 0:00:44 lr: 0.000979 loss: 4.4330 (4.1697) grad_norm: 1.1151 (inf) time: 0.6347 [2021-03-26 04:35:10 swin_base_patch4_window7_224] INFO: Epoch: [27] [1190/1251] eta: 0:00:38 lr: 0.000979 loss: 4.3770 (4.1713) grad_norm: 1.1314 (inf) time: 0.6296 [2021-03-26 04:35:16 swin_base_patch4_window7_224] INFO: Epoch: [27] [1200/1251] eta: 0:00:32 lr: 0.000979 loss: 4.2754 (4.1709) grad_norm: 1.1296 (inf) time: 0.6233 [2021-03-26 04:35:23 swin_base_patch4_window7_224] INFO: Epoch: [27] [1210/1251] eta: 0:00:25 lr: 0.000979 loss: 4.0450 (4.1674) grad_norm: 1.0672 (inf) time: 0.6190 [2021-03-26 04:35:29 swin_base_patch4_window7_224] INFO: Epoch: [27] [1220/1251] eta: 0:00:19 lr: 0.000979 loss: 4.0860 (4.1674) grad_norm: 0.9864 (inf) time: 0.6134 [2021-03-26 04:35:35 swin_base_patch4_window7_224] INFO: Epoch: [27] [1230/1251] eta: 0:00:13 lr: 0.000979 loss: 4.2989 (4.1671) grad_norm: 0.9483 (inf) time: 0.6118 [2021-03-26 04:35:41 swin_base_patch4_window7_224] INFO: Epoch: [27] [1240/1251] eta: 0:00:06 lr: 0.000979 loss: 3.8807 (4.1659) grad_norm: 0.9661 (inf) time: 0.6150 [2021-03-26 04:35:47 swin_base_patch4_window7_224] INFO: Epoch: [27] [1250/1251] eta: 0:00:00 lr: 0.000979 loss: 3.8807 (4.1647) grad_norm: 0.9717 (inf) time: 0.6122 [2021-03-26 04:35:50 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:14 loss: 1.8430 (1.8430) acc1: 57.8125 (57.8125) acc5: 82.8125 (82.8125) [2021-03-26 04:35:54 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.5073 (1.5742) acc1: 67.1875 (65.3409) acc5: 85.9375 (86.5057) [2021-03-26 04:35:56 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.4974 (1.5423) acc1: 67.1875 (65.4018) acc5: 87.5000 (87.6488) [2021-03-26 04:35:58 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.4484 (1.5374) acc1: 67.1875 (65.4738) acc5: 89.0625 (87.7016) [2021-03-26 04:36:00 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.5897 (1.5514) acc1: 65.6250 (64.9390) acc5: 84.3750 (87.1189) [2021-03-26 04:36:01 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.5488 (1.5349) acc1: 65.6250 (65.6320) acc5: 85.9375 (87.2320) [2021-03-26 04:36:04 swin_base_patch4_window7_224] INFO: * Acc@1 65.790 Acc@5 87.638 loss 1.518 [2021-03-26 04:36:04 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 65.8% [2021-03-26 04:36:04 swin_base_patch4_window7_224] INFO: Max accuracy: 65.79% [2021-03-26 04:36:08 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 0/1251] eta: 1:25:02 lr: 0.000979 loss: 4.3638 (4.3638) grad_norm: 0.9228 (0.9228) time: 4.0789 [2021-03-26 04:36:15 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 10/1251] eta: 0:20:08 lr: 0.000979 loss: 4.3638 (4.2443) grad_norm: 1.1177 (1.1138) time: 0.9738 [2021-03-26 04:36:21 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 20/1251] eta: 0:16:30 lr: 0.000979 loss: 3.9876 (4.0303) grad_norm: 1.0133 (1.0477) time: 0.6405 [2021-03-26 04:36:27 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 30/1251] eta: 0:15:08 lr: 0.000979 loss: 3.9876 (4.0558) grad_norm: 1.0271 (1.0935) time: 0.6182 [2021-03-26 04:36:34 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 40/1251] eta: 0:14:29 lr: 0.000979 loss: 4.3415 (4.1060) grad_norm: 1.1820 (1.0995) time: 0.6273 [2021-03-26 04:36:40 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 50/1251] eta: 0:14:01 lr: 0.000979 loss: 4.2769 (4.0592) grad_norm: 1.0514 (1.0899) time: 0.6329 [2021-03-26 04:36:46 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 60/1251] eta: 0:13:41 lr: 0.000979 loss: 4.2769 (4.1004) grad_norm: 1.0208 (1.0817) time: 0.6332 [2021-03-26 04:36:52 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 70/1251] eta: 0:13:22 lr: 0.000979 loss: 4.2947 (4.1139) grad_norm: 1.0049 (1.0799) time: 0.6266 [2021-03-26 04:36:59 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 80/1251] eta: 0:13:09 lr: 0.000979 loss: 4.1213 (4.0955) grad_norm: 1.0742 (1.0786) time: 0.6246 [2021-03-26 04:37:05 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 90/1251] eta: 0:12:57 lr: 0.000979 loss: 4.3182 (4.1413) grad_norm: 1.1124 (1.0866) time: 0.6323 [2021-03-26 04:37:11 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 100/1251] eta: 0:12:45 lr: 0.000979 loss: 4.5013 (4.1739) grad_norm: 1.1185 (1.0914) time: 0.6294 [2021-03-26 04:37:18 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 110/1251] eta: 0:12:35 lr: 0.000979 loss: 4.5252 (4.1940) grad_norm: 1.0924 (1.0995) time: 0.6279 [2021-03-26 04:37:24 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 120/1251] eta: 0:12:26 lr: 0.000979 loss: 4.3833 (4.1872) grad_norm: 1.0334 (1.0877) time: 0.6324 [2021-03-26 04:37:30 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 130/1251] eta: 0:12:16 lr: 0.000979 loss: 4.2055 (4.1848) grad_norm: 1.0254 (1.0896) time: 0.6315 [2021-03-26 04:37:37 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 140/1251] eta: 0:12:08 lr: 0.000979 loss: 4.3108 (4.2030) grad_norm: 1.0593 (1.0854) time: 0.6345 [2021-03-26 04:37:43 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 150/1251] eta: 0:11:59 lr: 0.000979 loss: 4.3989 (4.2089) grad_norm: 0.9758 (1.0785) time: 0.6268 [2021-03-26 04:37:49 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 160/1251] eta: 0:11:51 lr: 0.000979 loss: 4.4832 (4.2299) grad_norm: 1.0191 (1.0815) time: 0.6231 [2021-03-26 04:37:55 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 170/1251] eta: 0:11:43 lr: 0.000979 loss: 4.4051 (4.2277) grad_norm: 1.0256 (1.0735) time: 0.6300 [2021-03-26 04:38:02 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 180/1251] eta: 0:11:35 lr: 0.000979 loss: 4.2491 (4.2355) grad_norm: 0.9846 (1.0721) time: 0.6251 [2021-03-26 04:38:08 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 190/1251] eta: 0:11:27 lr: 0.000979 loss: 4.3326 (4.2285) grad_norm: 1.0303 (1.0736) time: 0.6264 [2021-03-26 04:38:14 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 200/1251] eta: 0:11:19 lr: 0.000979 loss: 4.1480 (4.2223) grad_norm: 1.0678 (1.0734) time: 0.6277 [2021-03-26 04:38:20 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 210/1251] eta: 0:11:12 lr: 0.000979 loss: 4.2646 (4.2235) grad_norm: 1.0346 (1.0732) time: 0.6256 [2021-03-26 04:38:27 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 220/1251] eta: 0:11:05 lr: 0.000979 loss: 4.4191 (4.2380) grad_norm: 1.0258 (1.0724) time: 0.6267 [2021-03-26 04:38:33 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 230/1251] eta: 0:10:57 lr: 0.000979 loss: 4.4516 (4.2424) grad_norm: 1.0287 (1.0718) time: 0.6291 [2021-03-26 04:38:39 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 240/1251] eta: 0:10:50 lr: 0.000979 loss: 4.3759 (4.2385) grad_norm: 1.0287 (1.0700) time: 0.6245 [2021-03-26 04:38:46 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 250/1251] eta: 0:10:43 lr: 0.000979 loss: 4.0100 (4.2233) grad_norm: 0.9881 (1.0711) time: 0.6297 [2021-03-26 04:38:52 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 260/1251] eta: 0:10:36 lr: 0.000979 loss: 3.7622 (4.2100) grad_norm: 1.0933 (1.0734) time: 0.6324 [2021-03-26 04:38:58 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 270/1251] eta: 0:10:29 lr: 0.000979 loss: 3.9057 (4.2063) grad_norm: 1.1032 (1.0740) time: 0.6276 [2021-03-26 04:39:04 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 280/1251] eta: 0:10:23 lr: 0.000979 loss: 4.1722 (4.2002) grad_norm: 1.1358 (1.0766) time: 0.6294 [2021-03-26 04:39:11 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 290/1251] eta: 0:10:16 lr: 0.000979 loss: 4.0661 (4.1932) grad_norm: 1.1023 (1.0777) time: 0.6268 [2021-03-26 04:39:17 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 300/1251] eta: 0:10:09 lr: 0.000979 loss: 4.0933 (4.1938) grad_norm: 1.0886 (1.0783) time: 0.6255 [2021-03-26 04:39:23 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 310/1251] eta: 0:10:02 lr: 0.000979 loss: 4.2612 (4.1911) grad_norm: 1.0321 (1.0765) time: 0.6264 [2021-03-26 04:39:29 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 320/1251] eta: 0:09:55 lr: 0.000978 loss: 3.9689 (4.1859) grad_norm: 1.0677 (1.0790) time: 0.6263 [2021-03-26 04:39:36 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 330/1251] eta: 0:09:48 lr: 0.000978 loss: 3.8575 (4.1743) grad_norm: 1.1558 (1.0836) time: 0.6298 [2021-03-26 04:39:42 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 340/1251] eta: 0:09:42 lr: 0.000978 loss: 3.8575 (4.1730) grad_norm: 1.1381 (1.0840) time: 0.6321 [2021-03-26 04:39:48 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 350/1251] eta: 0:09:35 lr: 0.000978 loss: 4.0014 (4.1654) grad_norm: 1.0240 (1.0813) time: 0.6253 [2021-03-26 04:39:55 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 360/1251] eta: 0:09:28 lr: 0.000978 loss: 4.1040 (4.1692) grad_norm: 0.9654 (1.0785) time: 0.6220 [2021-03-26 04:40:01 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 370/1251] eta: 0:09:21 lr: 0.000978 loss: 3.8982 (4.1561) grad_norm: 0.9976 (1.0792) time: 0.6210 [2021-03-26 04:40:07 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 380/1251] eta: 0:09:15 lr: 0.000978 loss: 3.7442 (4.1488) grad_norm: 1.0598 (1.0796) time: 0.6217 [2021-03-26 04:40:13 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 390/1251] eta: 0:09:08 lr: 0.000978 loss: 3.9990 (4.1506) grad_norm: 1.0765 (1.0785) time: 0.6211 [2021-03-26 04:40:19 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 400/1251] eta: 0:09:01 lr: 0.000978 loss: 4.1785 (4.1523) grad_norm: 1.0998 (1.0807) time: 0.6233 [2021-03-26 04:40:26 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 410/1251] eta: 0:08:55 lr: 0.000978 loss: 4.0681 (4.1512) grad_norm: 1.1495 (1.0827) time: 0.6251 [2021-03-26 04:40:32 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 420/1251] eta: 0:08:48 lr: 0.000978 loss: 3.9719 (4.1464) grad_norm: 1.0051 (1.0811) time: 0.6245 [2021-03-26 04:40:38 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 430/1251] eta: 0:08:41 lr: 0.000978 loss: 3.9078 (4.1424) grad_norm: 0.9948 (1.0799) time: 0.6226 [2021-03-26 04:40:44 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 440/1251] eta: 0:08:35 lr: 0.000978 loss: 4.3060 (4.1487) grad_norm: 1.0666 (1.0811) time: 0.6202 [2021-03-26 04:40:51 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 450/1251] eta: 0:08:28 lr: 0.000978 loss: 4.3060 (4.1506) grad_norm: 1.0666 (1.0820) time: 0.6237 [2021-03-26 04:40:57 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 460/1251] eta: 0:08:22 lr: 0.000978 loss: 4.1996 (4.1539) grad_norm: 1.0451 (1.0821) time: 0.6247 [2021-03-26 04:41:03 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 470/1251] eta: 0:08:15 lr: 0.000978 loss: 4.4263 (4.1539) grad_norm: 1.1010 (1.0840) time: 0.6291 [2021-03-26 04:41:09 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 480/1251] eta: 0:08:09 lr: 0.000978 loss: 4.3822 (4.1512) grad_norm: 1.0636 (1.0834) time: 0.6282 [2021-03-26 04:41:16 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 490/1251] eta: 0:08:02 lr: 0.000978 loss: 4.3014 (4.1545) grad_norm: 1.0636 (1.0851) time: 0.6259 [2021-03-26 04:41:22 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 500/1251] eta: 0:07:56 lr: 0.000978 loss: 4.2897 (4.1502) grad_norm: 1.0733 (1.0850) time: 0.6272 [2021-03-26 04:41:28 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 510/1251] eta: 0:07:49 lr: 0.000978 loss: 3.6472 (4.1435) grad_norm: 1.0009 (1.0833) time: 0.6248 [2021-03-26 04:41:34 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 520/1251] eta: 0:07:43 lr: 0.000978 loss: 4.1384 (4.1433) grad_norm: 1.0009 (1.0841) time: 0.6223 [2021-03-26 04:41:41 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 530/1251] eta: 0:07:36 lr: 0.000978 loss: 4.2222 (4.1433) grad_norm: 1.1102 (1.0829) time: 0.6247 [2021-03-26 04:41:47 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 540/1251] eta: 0:07:30 lr: 0.000978 loss: 4.2439 (4.1426) grad_norm: 1.0408 (1.0828) time: 0.6215 [2021-03-26 04:41:53 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 550/1251] eta: 0:07:24 lr: 0.000978 loss: 4.2614 (4.1447) grad_norm: 1.0408 (1.0826) time: 0.6288 [2021-03-26 04:42:00 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 560/1251] eta: 0:07:17 lr: 0.000978 loss: 4.4108 (4.1457) grad_norm: 1.0907 (1.0845) time: 0.6362 [2021-03-26 04:42:06 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 570/1251] eta: 0:07:11 lr: 0.000978 loss: 4.5361 (4.1498) grad_norm: 1.0677 (1.0841) time: 0.6298 [2021-03-26 04:42:12 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 580/1251] eta: 0:07:04 lr: 0.000978 loss: 4.5079 (4.1571) grad_norm: 1.0241 (1.0842) time: 0.6251 [2021-03-26 04:42:18 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 590/1251] eta: 0:06:58 lr: 0.000978 loss: 4.4357 (4.1551) grad_norm: 0.9798 (1.0835) time: 0.6204 [2021-03-26 04:42:25 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 600/1251] eta: 0:06:52 lr: 0.000978 loss: 4.4651 (4.1612) grad_norm: 0.9588 (1.0825) time: 0.6232 [2021-03-26 04:42:31 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 610/1251] eta: 0:06:45 lr: 0.000978 loss: 4.4602 (4.1605) grad_norm: 0.9797 (1.0808) time: 0.6225 [2021-03-26 04:42:37 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 620/1251] eta: 0:06:39 lr: 0.000978 loss: 4.0578 (4.1537) grad_norm: 1.0139 (1.0808) time: 0.6193 [2021-03-26 04:42:43 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 630/1251] eta: 0:06:32 lr: 0.000978 loss: 4.0578 (4.1555) grad_norm: 1.0333 (1.0799) time: 0.6220 [2021-03-26 04:42:49 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 640/1251] eta: 0:06:26 lr: 0.000978 loss: 4.1347 (4.1514) grad_norm: 0.9650 (1.0783) time: 0.6228 [2021-03-26 04:42:56 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 650/1251] eta: 0:06:19 lr: 0.000978 loss: 3.8649 (4.1490) grad_norm: 0.9592 (1.0765) time: 0.6254 [2021-03-26 04:43:02 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 660/1251] eta: 0:06:13 lr: 0.000978 loss: 4.1593 (4.1468) grad_norm: 1.0329 (1.0770) time: 0.6272 [2021-03-26 04:43:08 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 670/1251] eta: 0:06:07 lr: 0.000978 loss: 4.2522 (4.1474) grad_norm: 1.0384 (1.0763) time: 0.6239 [2021-03-26 04:43:14 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 680/1251] eta: 0:06:00 lr: 0.000978 loss: 4.2522 (4.1454) grad_norm: 0.9514 (1.0747) time: 0.6176 [2021-03-26 04:43:20 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 690/1251] eta: 0:05:54 lr: 0.000978 loss: 3.8233 (4.1387) grad_norm: 0.9476 (1.0740) time: 0.6155 [2021-03-26 04:43:27 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 700/1251] eta: 0:05:47 lr: 0.000978 loss: 3.9012 (4.1411) grad_norm: 1.0405 (1.0746) time: 0.6211 [2021-03-26 04:43:33 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 710/1251] eta: 0:05:41 lr: 0.000978 loss: 4.0377 (4.1372) grad_norm: 1.0961 (1.0765) time: 0.6250 [2021-03-26 04:43:39 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 720/1251] eta: 0:05:35 lr: 0.000978 loss: 4.0442 (4.1379) grad_norm: 1.1395 (1.0769) time: 0.6262 [2021-03-26 04:43:46 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 730/1251] eta: 0:05:28 lr: 0.000978 loss: 4.3691 (4.1415) grad_norm: 1.0776 (1.0765) time: 0.6294 [2021-03-26 04:43:52 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 740/1251] eta: 0:05:22 lr: 0.000978 loss: 3.9743 (4.1333) grad_norm: 1.0471 (1.0752) time: 0.6347 [2021-03-26 04:43:58 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 750/1251] eta: 0:05:16 lr: 0.000978 loss: 3.7872 (4.1326) grad_norm: 0.9453 (1.0732) time: 0.6257 [2021-03-26 04:44:04 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 760/1251] eta: 0:05:09 lr: 0.000978 loss: 4.1634 (4.1348) grad_norm: 0.9332 (1.0722) time: 0.6222 [2021-03-26 04:44:11 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 770/1251] eta: 0:05:03 lr: 0.000978 loss: 4.4002 (4.1375) grad_norm: 1.0216 (1.0724) time: 0.6288 [2021-03-26 04:44:17 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 780/1251] eta: 0:04:57 lr: 0.000978 loss: 4.3774 (4.1375) grad_norm: 0.9898 (1.0714) time: 0.6256 [2021-03-26 04:44:23 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 790/1251] eta: 0:04:50 lr: 0.000978 loss: 4.1730 (4.1361) grad_norm: 1.0469 (1.0718) time: 0.6318 [2021-03-26 04:44:30 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 800/1251] eta: 0:04:44 lr: 0.000978 loss: 4.1607 (4.1374) grad_norm: 1.0743 (1.0720) time: 0.6319 [2021-03-26 04:44:36 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 810/1251] eta: 0:04:38 lr: 0.000978 loss: 4.1607 (4.1369) grad_norm: 1.0296 (1.0710) time: 0.6235 [2021-03-26 04:44:42 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 820/1251] eta: 0:04:31 lr: 0.000978 loss: 4.2312 (4.1386) grad_norm: 1.0364 (1.0727) time: 0.6261 [2021-03-26 04:44:48 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 830/1251] eta: 0:04:25 lr: 0.000978 loss: 4.2312 (4.1352) grad_norm: 1.1497 (1.0734) time: 0.6289 [2021-03-26 04:44:55 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 840/1251] eta: 0:04:19 lr: 0.000978 loss: 3.8663 (4.1321) grad_norm: 1.1341 (1.0743) time: 0.6284 [2021-03-26 04:45:01 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 850/1251] eta: 0:04:12 lr: 0.000978 loss: 4.0364 (4.1319) grad_norm: 1.0838 (1.0747) time: 0.6268 [2021-03-26 04:45:07 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 860/1251] eta: 0:04:06 lr: 0.000978 loss: 4.0745 (4.1283) grad_norm: 1.0093 (1.0740) time: 0.6255 [2021-03-26 04:45:14 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 870/1251] eta: 0:04:00 lr: 0.000978 loss: 3.7983 (4.1250) grad_norm: 0.9875 (1.0732) time: 0.6342 [2021-03-26 04:45:20 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 880/1251] eta: 0:03:53 lr: 0.000978 loss: 4.0858 (4.1260) grad_norm: 1.0079 (1.0726) time: 0.6339 [2021-03-26 04:45:26 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 890/1251] eta: 0:03:47 lr: 0.000978 loss: 3.9907 (4.1232) grad_norm: 1.0409 (1.0725) time: 0.6322 [2021-03-26 04:45:33 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 900/1251] eta: 0:03:41 lr: 0.000978 loss: 3.9898 (4.1251) grad_norm: 1.1199 (1.0739) time: 0.6366 [2021-03-26 04:45:39 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 910/1251] eta: 0:03:35 lr: 0.000978 loss: 4.3136 (4.1253) grad_norm: 1.0260 (1.0726) time: 0.6284 [2021-03-26 04:45:45 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 920/1251] eta: 0:03:28 lr: 0.000978 loss: 4.2465 (4.1265) grad_norm: 0.9669 (1.0724) time: 0.6153 [2021-03-26 04:45:51 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 930/1251] eta: 0:03:22 lr: 0.000978 loss: 4.3773 (4.1287) grad_norm: 1.1132 (1.0739) time: 0.6158 [2021-03-26 04:45:57 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 940/1251] eta: 0:03:15 lr: 0.000978 loss: 4.3773 (4.1271) grad_norm: 1.1155 (1.0740) time: 0.6183 [2021-03-26 04:46:03 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 950/1251] eta: 0:03:09 lr: 0.000978 loss: 3.6707 (4.1225) grad_norm: 0.9928 (1.0739) time: 0.6174 [2021-03-26 04:46:10 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 960/1251] eta: 0:03:03 lr: 0.000978 loss: 3.7173 (4.1205) grad_norm: 0.9874 (1.0733) time: 0.6207 [2021-03-26 04:46:16 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 970/1251] eta: 0:02:57 lr: 0.000978 loss: 4.0212 (4.1190) grad_norm: 1.0366 (1.0734) time: 0.6203 [2021-03-26 04:46:22 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 980/1251] eta: 0:02:50 lr: 0.000978 loss: 4.2020 (4.1180) grad_norm: 1.0736 (1.0732) time: 0.6218 [2021-03-26 04:46:28 swin_base_patch4_window7_224] INFO: Epoch: [28] [ 990/1251] eta: 0:02:44 lr: 0.000978 loss: 4.0743 (4.1178) grad_norm: 1.1008 (1.0739) time: 0.6240 [2021-03-26 04:46:35 swin_base_patch4_window7_224] INFO: Epoch: [28] [1000/1251] eta: 0:02:38 lr: 0.000978 loss: 4.2080 (4.1179) grad_norm: 1.0579 (1.0736) time: 0.6235 [2021-03-26 04:46:41 swin_base_patch4_window7_224] INFO: Epoch: [28] [1010/1251] eta: 0:02:31 lr: 0.000978 loss: 4.3586 (4.1177) grad_norm: 0.9979 (1.0727) time: 0.6233 [2021-03-26 04:46:47 swin_base_patch4_window7_224] INFO: Epoch: [28] [1020/1251] eta: 0:02:25 lr: 0.000978 loss: 4.3961 (4.1202) grad_norm: 1.0450 (1.0729) time: 0.6238 [2021-03-26 04:46:53 swin_base_patch4_window7_224] INFO: Epoch: [28] [1030/1251] eta: 0:02:19 lr: 0.000978 loss: 4.0194 (4.1177) grad_norm: 1.1527 (1.0741) time: 0.6267 [2021-03-26 04:47:00 swin_base_patch4_window7_224] INFO: Epoch: [28] [1040/1251] eta: 0:02:12 lr: 0.000978 loss: 4.0194 (4.1187) grad_norm: 1.1212 (1.0744) time: 0.6269 [2021-03-26 04:47:06 swin_base_patch4_window7_224] INFO: Epoch: [28] [1050/1251] eta: 0:02:06 lr: 0.000978 loss: 4.0689 (4.1162) grad_norm: 1.0520 (1.0736) time: 0.6241 [2021-03-26 04:47:12 swin_base_patch4_window7_224] INFO: Epoch: [28] [1060/1251] eta: 0:02:00 lr: 0.000978 loss: 3.9813 (4.1146) grad_norm: 0.9433 (1.0724) time: 0.6247 [2021-03-26 04:47:18 swin_base_patch4_window7_224] INFO: Epoch: [28] [1070/1251] eta: 0:01:53 lr: 0.000978 loss: 4.0133 (4.1137) grad_norm: 1.0171 (1.0726) time: 0.6266 [2021-03-26 04:47:25 swin_base_patch4_window7_224] INFO: Epoch: [28] [1080/1251] eta: 0:01:47 lr: 0.000978 loss: 4.1784 (4.1140) grad_norm: 1.0120 (1.0719) time: 0.6295 [2021-03-26 04:47:31 swin_base_patch4_window7_224] INFO: Epoch: [28] [1090/1251] eta: 0:01:41 lr: 0.000978 loss: 4.1837 (4.1122) grad_norm: 1.0263 (1.0719) time: 0.6251 [2021-03-26 04:47:37 swin_base_patch4_window7_224] INFO: Epoch: [28] [1100/1251] eta: 0:01:35 lr: 0.000978 loss: 4.1044 (4.1107) grad_norm: 1.0600 (1.0723) time: 0.6225 [2021-03-26 04:47:43 swin_base_patch4_window7_224] INFO: Epoch: [28] [1110/1251] eta: 0:01:28 lr: 0.000978 loss: 4.1312 (4.1111) grad_norm: 1.0502 (1.0725) time: 0.6245 [2021-03-26 04:47:50 swin_base_patch4_window7_224] INFO: Epoch: [28] [1120/1251] eta: 0:01:22 lr: 0.000978 loss: 4.1312 (4.1097) grad_norm: 1.0320 (1.0720) time: 0.6245 [2021-03-26 04:47:56 swin_base_patch4_window7_224] INFO: Epoch: [28] [1130/1251] eta: 0:01:16 lr: 0.000977 loss: 4.3064 (4.1129) grad_norm: 1.0098 (1.0712) time: 0.6244 [2021-03-26 04:48:02 swin_base_patch4_window7_224] INFO: Epoch: [28] [1140/1251] eta: 0:01:09 lr: 0.000977 loss: 4.3077 (4.1128) grad_norm: 1.0190 (1.0719) time: 0.6213 [2021-03-26 04:48:08 swin_base_patch4_window7_224] INFO: Epoch: [28] [1150/1251] eta: 0:01:03 lr: 0.000977 loss: 4.2962 (4.1137) grad_norm: 1.1209 (1.0728) time: 0.6248 [2021-03-26 04:48:15 swin_base_patch4_window7_224] INFO: Epoch: [28] [1160/1251] eta: 0:00:57 lr: 0.000977 loss: 3.9097 (4.1131) grad_norm: 1.1212 (1.0729) time: 0.6245 [2021-03-26 04:48:21 swin_base_patch4_window7_224] INFO: Epoch: [28] [1170/1251] eta: 0:00:50 lr: 0.000977 loss: 4.0451 (4.1129) grad_norm: 1.1034 (1.0730) time: 0.6224 [2021-03-26 04:48:27 swin_base_patch4_window7_224] INFO: Epoch: [28] [1180/1251] eta: 0:00:44 lr: 0.000977 loss: 4.2227 (4.1132) grad_norm: 1.0462 (1.0735) time: 0.6253 [2021-03-26 04:48:33 swin_base_patch4_window7_224] INFO: Epoch: [28] [1190/1251] eta: 0:00:38 lr: 0.000977 loss: 4.0855 (4.1124) grad_norm: 1.0814 (1.0740) time: 0.6267 [2021-03-26 04:48:40 swin_base_patch4_window7_224] INFO: Epoch: [28] [1200/1251] eta: 0:00:32 lr: 0.000977 loss: 4.0459 (4.1115) grad_norm: 1.0814 (1.0740) time: 0.6267 [2021-03-26 04:48:46 swin_base_patch4_window7_224] INFO: Epoch: [28] [1210/1251] eta: 0:00:25 lr: 0.000977 loss: 4.0439 (4.1108) grad_norm: 1.1039 (1.0745) time: 0.6236 [2021-03-26 04:48:52 swin_base_patch4_window7_224] INFO: Epoch: [28] [1220/1251] eta: 0:00:19 lr: 0.000977 loss: 4.1527 (4.1120) grad_norm: 1.1110 (1.0748) time: 0.6208 [2021-03-26 04:48:58 swin_base_patch4_window7_224] INFO: Epoch: [28] [1230/1251] eta: 0:00:13 lr: 0.000977 loss: 4.2782 (4.1128) grad_norm: 1.0605 (1.0744) time: 0.6193 [2021-03-26 04:49:04 swin_base_patch4_window7_224] INFO: Epoch: [28] [1240/1251] eta: 0:00:06 lr: 0.000977 loss: 4.1679 (4.1138) grad_norm: 1.0456 (1.0742) time: 0.6159 [2021-03-26 04:49:11 swin_base_patch4_window7_224] INFO: Epoch: [28] [1250/1251] eta: 0:00:00 lr: 0.000977 loss: 4.3018 (4.1170) grad_norm: 1.0597 (1.0744) time: 0.6125 [2021-03-26 04:49:15 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:54 loss: 1.4089 (1.4089) acc1: 67.1875 (67.1875) acc5: 89.0625 (89.0625) [2021-03-26 04:49:17 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.5791 (1.5895) acc1: 60.9375 (62.3580) acc5: 85.9375 (85.9375) [2021-03-26 04:49:20 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.4812 (1.5011) acc1: 62.5000 (64.7321) acc5: 85.9375 (86.9048) [2021-03-26 04:49:22 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.4168 (1.4682) acc1: 65.6250 (65.6250) acc5: 87.5000 (87.4496) [2021-03-26 04:49:24 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.4615 (1.4853) acc1: 65.6250 (65.5869) acc5: 87.5000 (87.3476) [2021-03-26 04:49:25 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.4710 (1.4794) acc1: 64.0625 (65.5680) acc5: 87.5000 (87.4240) [2021-03-26 04:49:28 swin_base_patch4_window7_224] INFO: * Acc@1 66.324 Acc@5 88.040 loss 1.452 [2021-03-26 04:49:28 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 66.3% [2021-03-26 04:49:28 swin_base_patch4_window7_224] INFO: Max accuracy: 66.32% [2021-03-26 04:49:32 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 0/1251] eta: 1:28:22 lr: 0.000977 loss: 4.3642 (4.3642) grad_norm: 0.7170 (0.7170) time: 4.2389 [2021-03-26 04:49:38 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 10/1251] eta: 0:20:00 lr: 0.000977 loss: 4.3387 (4.2531) grad_norm: 0.9709 (0.9900) time: 0.9676 [2021-03-26 04:49:45 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 20/1251] eta: 0:16:35 lr: 0.000977 loss: 4.2264 (4.0278) grad_norm: 1.0459 (1.0519) time: 0.6371 [2021-03-26 04:49:51 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 30/1251] eta: 0:15:17 lr: 0.000977 loss: 3.9140 (4.0546) grad_norm: 1.0342 (1.0345) time: 0.6325 [2021-03-26 04:49:57 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 40/1251] eta: 0:14:32 lr: 0.000977 loss: 3.9696 (4.0436) grad_norm: 1.0547 (1.0663) time: 0.6278 [2021-03-26 04:50:03 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 50/1251] eta: 0:14:03 lr: 0.000977 loss: 3.9696 (4.0075) grad_norm: 1.0686 (1.0608) time: 0.6268 [2021-03-26 04:50:10 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 60/1251] eta: 0:13:42 lr: 0.000977 loss: 3.6693 (3.9695) grad_norm: 1.0368 (1.0670) time: 0.6287 [2021-03-26 04:50:16 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 70/1251] eta: 0:13:24 lr: 0.000977 loss: 3.5958 (3.9547) grad_norm: 0.9835 (1.0645) time: 0.6260 [2021-03-26 04:50:22 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 80/1251] eta: 0:13:08 lr: 0.000977 loss: 4.1911 (3.9983) grad_norm: 1.0106 (1.0684) time: 0.6208 [2021-03-26 04:50:28 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 90/1251] eta: 0:12:55 lr: 0.000977 loss: 4.2454 (4.0070) grad_norm: 1.0387 (1.0638) time: 0.6225 [2021-03-26 04:50:35 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 100/1251] eta: 0:12:43 lr: 0.000977 loss: 4.0453 (4.0144) grad_norm: 0.9517 (1.0535) time: 0.6226 [2021-03-26 04:50:41 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 110/1251] eta: 0:12:32 lr: 0.000977 loss: 4.0453 (4.0016) grad_norm: 1.1086 (1.0748) time: 0.6208 [2021-03-26 04:50:47 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 120/1251] eta: 0:12:22 lr: 0.000977 loss: 4.3082 (4.0262) grad_norm: 1.2209 (1.0742) time: 0.6222 [2021-03-26 04:50:53 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 130/1251] eta: 0:12:12 lr: 0.000977 loss: 4.3098 (4.0380) grad_norm: 1.0803 (1.0740) time: 0.6216 [2021-03-26 04:51:00 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 140/1251] eta: 0:12:05 lr: 0.000977 loss: 4.0022 (4.0297) grad_norm: 1.1421 (1.0849) time: 0.6308 [2021-03-26 04:51:06 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 150/1251] eta: 0:11:56 lr: 0.000977 loss: 4.0022 (4.0249) grad_norm: 1.1544 (1.0873) time: 0.6327 [2021-03-26 04:51:12 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 160/1251] eta: 0:11:48 lr: 0.000977 loss: 4.3347 (4.0576) grad_norm: 0.9874 (1.0800) time: 0.6223 [2021-03-26 04:51:18 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 170/1251] eta: 0:11:39 lr: 0.000977 loss: 4.3581 (4.0620) grad_norm: 0.9855 (1.0786) time: 0.6184 [2021-03-26 04:51:24 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 180/1251] eta: 0:11:31 lr: 0.000977 loss: 4.1083 (4.0605) grad_norm: 1.0087 (1.0775) time: 0.6214 [2021-03-26 04:51:31 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 190/1251] eta: 0:11:24 lr: 0.000977 loss: 4.0521 (4.0551) grad_norm: 1.0316 (1.0790) time: 0.6234 [2021-03-26 04:51:37 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 200/1251] eta: 0:11:16 lr: 0.000977 loss: 3.9334 (4.0398) grad_norm: 1.0435 (1.0791) time: 0.6279 [2021-03-26 04:51:43 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 210/1251] eta: 0:11:09 lr: 0.000977 loss: 4.1262 (4.0454) grad_norm: 1.0074 (1.0745) time: 0.6287 [2021-03-26 04:51:50 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 220/1251] eta: 0:11:02 lr: 0.000977 loss: 4.3053 (4.0558) grad_norm: 0.9715 (1.0729) time: 0.6227 [2021-03-26 04:51:56 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 230/1251] eta: 0:10:54 lr: 0.000977 loss: 4.2862 (4.0632) grad_norm: 1.0361 (1.0738) time: 0.6217 [2021-03-26 04:52:02 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 240/1251] eta: 0:10:47 lr: 0.000977 loss: 4.2287 (4.0724) grad_norm: 1.0609 (1.0742) time: 0.6209 [2021-03-26 04:52:08 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 250/1251] eta: 0:10:40 lr: 0.000977 loss: 4.2036 (4.0716) grad_norm: 1.0011 (1.0718) time: 0.6259 [2021-03-26 04:52:15 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 260/1251] eta: 0:10:34 lr: 0.000977 loss: 4.0589 (4.0684) grad_norm: 1.0112 (1.0714) time: 0.6319 [2021-03-26 04:52:21 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 270/1251] eta: 0:10:27 lr: 0.000977 loss: 4.2551 (4.0698) grad_norm: 1.0707 (1.0752) time: 0.6316 [2021-03-26 04:52:27 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 280/1251] eta: 0:10:20 lr: 0.000977 loss: 3.9529 (4.0641) grad_norm: 1.1088 (1.0754) time: 0.6249 [2021-03-26 04:52:33 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 290/1251] eta: 0:10:13 lr: 0.000977 loss: 3.8924 (4.0599) grad_norm: 1.1017 (1.0759) time: 0.6257 [2021-03-26 04:52:40 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 300/1251] eta: 0:10:06 lr: 0.000977 loss: 4.0661 (4.0572) grad_norm: 0.9787 (1.0735) time: 0.6232 [2021-03-26 04:52:46 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 310/1251] eta: 0:09:59 lr: 0.000977 loss: 4.3788 (4.0685) grad_norm: 1.0008 (1.0728) time: 0.6196 [2021-03-26 04:52:52 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 320/1251] eta: 0:09:52 lr: 0.000977 loss: 4.4308 (4.0744) grad_norm: 1.0947 (1.0751) time: 0.6216 [2021-03-26 04:52:58 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 330/1251] eta: 0:09:46 lr: 0.000977 loss: 4.3009 (4.0801) grad_norm: 1.1563 (1.0782) time: 0.6228 [2021-03-26 04:53:05 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 340/1251] eta: 0:09:39 lr: 0.000977 loss: 4.1761 (4.0768) grad_norm: 1.1563 (1.0812) time: 0.6351 [2021-03-26 04:53:11 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 350/1251] eta: 0:09:33 lr: 0.000977 loss: 3.9206 (4.0717) grad_norm: 1.0354 (1.0777) time: 0.6335 [2021-03-26 04:53:17 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 360/1251] eta: 0:09:26 lr: 0.000977 loss: 4.0093 (4.0757) grad_norm: 1.0148 (1.0794) time: 0.6244 [2021-03-26 04:53:24 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 370/1251] eta: 0:09:20 lr: 0.000977 loss: 4.0366 (4.0761) grad_norm: 1.0806 (1.0807) time: 0.6293 [2021-03-26 04:53:30 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 380/1251] eta: 0:09:13 lr: 0.000977 loss: 4.2937 (4.0833) grad_norm: 1.0747 (1.0834) time: 0.6333 [2021-03-26 04:53:36 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 390/1251] eta: 0:09:07 lr: 0.000977 loss: 4.3378 (4.0878) grad_norm: 0.9973 (1.0824) time: 0.6275 [2021-03-26 04:53:42 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 400/1251] eta: 0:09:00 lr: 0.000977 loss: 4.2137 (4.0826) grad_norm: 1.0838 (1.0837) time: 0.6233 [2021-03-26 04:53:49 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 410/1251] eta: 0:08:53 lr: 0.000977 loss: 3.9831 (4.0819) grad_norm: 1.0240 (1.0848) time: 0.6216 [2021-03-26 04:53:55 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 420/1251] eta: 0:08:47 lr: 0.000977 loss: 3.9845 (4.0777) grad_norm: 1.0128 (1.0856) time: 0.6196 [2021-03-26 04:54:01 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 430/1251] eta: 0:08:40 lr: 0.000977 loss: 3.9966 (4.0793) grad_norm: 1.0343 (1.0845) time: 0.6179 [2021-03-26 04:54:07 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 440/1251] eta: 0:08:34 lr: 0.000977 loss: 4.1905 (4.0791) grad_norm: 1.0807 (1.0847) time: 0.6228 [2021-03-26 04:54:13 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 450/1251] eta: 0:08:27 lr: 0.000977 loss: 3.9500 (4.0779) grad_norm: 1.0882 (1.0850) time: 0.6278 [2021-03-26 04:54:20 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 460/1251] eta: 0:08:21 lr: 0.000977 loss: 4.0990 (4.0771) grad_norm: 0.9970 (1.0839) time: 0.6243 [2021-03-26 04:54:26 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 470/1251] eta: 0:08:14 lr: 0.000977 loss: 4.0990 (4.0777) grad_norm: 1.0432 (1.0840) time: 0.6230 [2021-03-26 04:54:32 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 480/1251] eta: 0:08:08 lr: 0.000977 loss: 4.4108 (4.0867) grad_norm: 1.0621 (1.0833) time: 0.6247 [2021-03-26 04:54:38 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 490/1251] eta: 0:08:01 lr: 0.000977 loss: 4.4693 (4.0902) grad_norm: 1.0352 (1.0835) time: 0.6278 [2021-03-26 04:54:45 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 500/1251] eta: 0:07:55 lr: 0.000977 loss: 4.1015 (4.0878) grad_norm: 1.0398 (1.0839) time: 0.6281 [2021-03-26 04:54:51 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 510/1251] eta: 0:07:48 lr: 0.000977 loss: 4.0989 (4.0869) grad_norm: 0.9794 (1.0803) time: 0.6224 [2021-03-26 04:54:57 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 520/1251] eta: 0:07:42 lr: 0.000977 loss: 4.0989 (4.0844) grad_norm: 0.9645 (1.0818) time: 0.6243 [2021-03-26 04:55:03 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 530/1251] eta: 0:07:36 lr: 0.000977 loss: 3.8436 (4.0841) grad_norm: 1.0965 (1.0817) time: 0.6283 [2021-03-26 04:55:10 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 540/1251] eta: 0:07:29 lr: 0.000977 loss: 3.8436 (4.0814) grad_norm: 1.0603 (1.0817) time: 0.6241 [2021-03-26 04:55:16 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 550/1251] eta: 0:07:23 lr: 0.000977 loss: 4.1715 (4.0828) grad_norm: 1.1188 (1.0825) time: 0.6347 [2021-03-26 04:55:22 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 560/1251] eta: 0:07:16 lr: 0.000977 loss: 4.3712 (4.0821) grad_norm: 1.0792 (1.0820) time: 0.6329 [2021-03-26 04:55:29 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 570/1251] eta: 0:07:10 lr: 0.000977 loss: 4.1822 (4.0825) grad_norm: 0.9956 (1.0815) time: 0.6234 [2021-03-26 04:55:35 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 580/1251] eta: 0:07:04 lr: 0.000977 loss: 4.1822 (4.0791) grad_norm: 1.0512 (1.0812) time: 0.6273 [2021-03-26 04:55:41 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 590/1251] eta: 0:06:57 lr: 0.000977 loss: 4.0610 (4.0809) grad_norm: 1.0046 (1.0800) time: 0.6239 [2021-03-26 04:55:47 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 600/1251] eta: 0:06:51 lr: 0.000977 loss: 4.0355 (4.0798) grad_norm: 0.9837 (1.0777) time: 0.6161 [2021-03-26 04:55:54 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 610/1251] eta: 0:06:44 lr: 0.000977 loss: 4.2331 (4.0845) grad_norm: 1.0136 (1.0784) time: 0.6197 [2021-03-26 04:56:00 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 620/1251] eta: 0:06:38 lr: 0.000977 loss: 4.2398 (4.0839) grad_norm: 1.0136 (1.0766) time: 0.6251 [2021-03-26 04:56:06 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 630/1251] eta: 0:06:31 lr: 0.000977 loss: 4.2944 (4.0853) grad_norm: 1.0114 (1.0769) time: 0.6211 [2021-03-26 04:56:12 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 640/1251] eta: 0:06:25 lr: 0.000977 loss: 4.3610 (4.0866) grad_norm: 1.0851 (1.0760) time: 0.6266 [2021-03-26 04:56:19 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 650/1251] eta: 0:06:19 lr: 0.000977 loss: 4.2758 (4.0884) grad_norm: 1.0136 (1.0753) time: 0.6315 [2021-03-26 04:56:25 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 660/1251] eta: 0:06:13 lr: 0.000977 loss: 4.2758 (4.0905) grad_norm: 1.0179 (1.0762) time: 0.6286 [2021-03-26 04:56:31 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 670/1251] eta: 0:06:06 lr: 0.000977 loss: 4.1979 (4.0860) grad_norm: 1.0653 (1.0777) time: 0.6280 [2021-03-26 04:56:37 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 680/1251] eta: 0:06:00 lr: 0.000976 loss: 4.2558 (4.0903) grad_norm: 1.0993 (1.0772) time: 0.6279 [2021-03-26 04:56:44 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 690/1251] eta: 0:05:54 lr: 0.000976 loss: 4.3590 (4.0919) grad_norm: 1.0923 (1.0777) time: 0.6277 [2021-03-26 04:56:50 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 700/1251] eta: 0:05:47 lr: 0.000976 loss: 4.1564 (4.0925) grad_norm: 1.0313 (1.0797) time: 0.6208 [2021-03-26 04:56:56 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 710/1251] eta: 0:05:41 lr: 0.000976 loss: 4.1193 (4.0947) grad_norm: 0.9868 (1.0787) time: 0.6130 [2021-03-26 04:57:02 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 720/1251] eta: 0:05:34 lr: 0.000976 loss: 4.3860 (4.0962) grad_norm: 0.9868 (1.0776) time: 0.6188 [2021-03-26 04:57:08 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 730/1251] eta: 0:05:28 lr: 0.000976 loss: 4.3232 (4.0954) grad_norm: 1.0190 (1.0778) time: 0.6225 [2021-03-26 04:57:15 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 740/1251] eta: 0:05:22 lr: 0.000976 loss: 4.0129 (4.0939) grad_norm: 1.0407 (1.0770) time: 0.6249 [2021-03-26 04:57:21 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 750/1251] eta: 0:05:15 lr: 0.000976 loss: 3.9835 (4.0919) grad_norm: 0.9200 (1.0753) time: 0.6290 [2021-03-26 04:57:27 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 760/1251] eta: 0:05:09 lr: 0.000976 loss: 4.2006 (4.0933) grad_norm: 1.0106 (1.0769) time: 0.6298 [2021-03-26 04:57:34 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 770/1251] eta: 0:05:03 lr: 0.000976 loss: 4.1358 (4.0916) grad_norm: 1.0932 (1.0764) time: 0.6315 [2021-03-26 04:57:40 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 780/1251] eta: 0:04:56 lr: 0.000976 loss: 4.1358 (4.0925) grad_norm: 1.0589 (1.0764) time: 0.6297 [2021-03-26 04:57:46 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 790/1251] eta: 0:04:50 lr: 0.000976 loss: 4.1499 (4.0884) grad_norm: 1.1377 (1.0777) time: 0.6318 [2021-03-26 04:57:52 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 800/1251] eta: 0:04:44 lr: 0.000976 loss: 4.1985 (4.0902) grad_norm: 1.0820 (1.0772) time: 0.6257 [2021-03-26 04:57:59 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 810/1251] eta: 0:04:37 lr: 0.000976 loss: 4.2174 (4.0889) grad_norm: 1.0170 (1.0772) time: 0.6208 [2021-03-26 04:58:05 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 820/1251] eta: 0:04:31 lr: 0.000976 loss: 4.0548 (4.0890) grad_norm: 1.1701 (1.0787) time: 0.6321 [2021-03-26 04:58:11 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 830/1251] eta: 0:04:25 lr: 0.000976 loss: 4.0503 (4.0888) grad_norm: 1.1337 (1.0788) time: 0.6307 [2021-03-26 04:58:18 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 840/1251] eta: 0:04:18 lr: 0.000976 loss: 4.0105 (4.0883) grad_norm: 1.0318 (1.0786) time: 0.6256 [2021-03-26 04:58:24 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 850/1251] eta: 0:04:12 lr: 0.000976 loss: 4.0034 (4.0876) grad_norm: 1.0275 (1.0787) time: 0.6261 [2021-03-26 04:58:30 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 860/1251] eta: 0:04:06 lr: 0.000976 loss: 4.3976 (4.0899) grad_norm: 1.0712 (1.0796) time: 0.6244 [2021-03-26 04:58:36 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 870/1251] eta: 0:04:00 lr: 0.000976 loss: 4.3305 (4.0888) grad_norm: 1.1384 (1.0803) time: 0.6309 [2021-03-26 04:58:43 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 880/1251] eta: 0:03:53 lr: 0.000976 loss: 4.0362 (4.0888) grad_norm: 1.1492 (1.0809) time: 0.6356 [2021-03-26 04:58:49 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 890/1251] eta: 0:03:47 lr: 0.000976 loss: 4.1985 (4.0893) grad_norm: 1.1549 (1.0821) time: 0.6353 [2021-03-26 04:58:55 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 900/1251] eta: 0:03:41 lr: 0.000976 loss: 4.3125 (4.0920) grad_norm: 1.1057 (1.0817) time: 0.6291 [2021-03-26 04:59:02 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 910/1251] eta: 0:03:34 lr: 0.000976 loss: 4.2660 (4.0900) grad_norm: 1.0218 (1.0814) time: 0.6224 [2021-03-26 04:59:08 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 920/1251] eta: 0:03:28 lr: 0.000976 loss: 3.7998 (4.0872) grad_norm: 0.9602 (1.0803) time: 0.6195 [2021-03-26 04:59:14 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 930/1251] eta: 0:03:22 lr: 0.000976 loss: 3.7116 (4.0836) grad_norm: 0.9728 (1.0800) time: 0.6162 [2021-03-26 04:59:20 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 940/1251] eta: 0:03:15 lr: 0.000976 loss: 4.0009 (4.0845) grad_norm: 1.0509 (1.0800) time: 0.6255 [2021-03-26 04:59:27 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 950/1251] eta: 0:03:09 lr: 0.000976 loss: 4.1266 (4.0830) grad_norm: 1.0589 (1.0802) time: 0.6299 [2021-03-26 04:59:33 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 960/1251] eta: 0:03:03 lr: 0.000976 loss: 4.0321 (4.0855) grad_norm: 0.9791 (1.0787) time: 0.6213 [2021-03-26 04:59:39 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 970/1251] eta: 0:02:56 lr: 0.000976 loss: 4.0321 (4.0855) grad_norm: 0.9444 (1.0779) time: 0.6227 [2021-03-26 04:59:45 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 980/1251] eta: 0:02:50 lr: 0.000976 loss: 3.9511 (4.0843) grad_norm: 1.0320 (1.0778) time: 0.6234 [2021-03-26 04:59:51 swin_base_patch4_window7_224] INFO: Epoch: [29] [ 990/1251] eta: 0:02:44 lr: 0.000976 loss: 3.9950 (4.0849) grad_norm: 0.9833 (1.0768) time: 0.6190 [2021-03-26 04:59:58 swin_base_patch4_window7_224] INFO: Epoch: [29] [1000/1251] eta: 0:02:37 lr: 0.000976 loss: 4.2366 (4.0859) grad_norm: 0.9683 (1.0759) time: 0.6199 [2021-03-26 05:00:04 swin_base_patch4_window7_224] INFO: Epoch: [29] [1010/1251] eta: 0:02:31 lr: 0.000976 loss: 4.3303 (4.0876) grad_norm: 1.0227 (1.0759) time: 0.6239 [2021-03-26 05:00:10 swin_base_patch4_window7_224] INFO: Epoch: [29] [1020/1251] eta: 0:02:25 lr: 0.000976 loss: 4.2645 (4.0879) grad_norm: 1.0707 (1.0751) time: 0.6273 [2021-03-26 05:00:16 swin_base_patch4_window7_224] INFO: Epoch: [29] [1030/1251] eta: 0:02:19 lr: 0.000976 loss: 4.2875 (4.0911) grad_norm: 1.0094 (1.0745) time: 0.6216 [2021-03-26 05:00:23 swin_base_patch4_window7_224] INFO: Epoch: [29] [1040/1251] eta: 0:02:12 lr: 0.000976 loss: 4.3807 (4.0914) grad_norm: 1.0639 (1.0752) time: 0.6242 [2021-03-26 05:00:29 swin_base_patch4_window7_224] INFO: Epoch: [29] [1050/1251] eta: 0:02:06 lr: 0.000976 loss: 4.2480 (4.0938) grad_norm: 1.1429 (1.0764) time: 0.6264 [2021-03-26 05:00:35 swin_base_patch4_window7_224] INFO: Epoch: [29] [1060/1251] eta: 0:02:00 lr: 0.000976 loss: 3.9926 (4.0912) grad_norm: 1.1008 (1.0762) time: 0.6244 [2021-03-26 05:00:41 swin_base_patch4_window7_224] INFO: Epoch: [29] [1070/1251] eta: 0:01:53 lr: 0.000976 loss: 4.0811 (4.0929) grad_norm: 1.0380 (1.0764) time: 0.6257 [2021-03-26 05:00:48 swin_base_patch4_window7_224] INFO: Epoch: [29] [1080/1251] eta: 0:01:47 lr: 0.000976 loss: 4.1674 (4.0935) grad_norm: 1.0632 (1.0762) time: 0.6307 [2021-03-26 05:00:54 swin_base_patch4_window7_224] INFO: Epoch: [29] [1090/1251] eta: 0:01:41 lr: 0.000976 loss: 4.1354 (4.0925) grad_norm: 1.1023 (1.0782) time: 0.6372 [2021-03-26 05:01:00 swin_base_patch4_window7_224] INFO: Epoch: [29] [1100/1251] eta: 0:01:34 lr: 0.000976 loss: 3.7733 (4.0902) grad_norm: 1.1899 (1.0791) time: 0.6315 [2021-03-26 05:01:07 swin_base_patch4_window7_224] INFO: Epoch: [29] [1110/1251] eta: 0:01:28 lr: 0.000976 loss: 3.9851 (4.0922) grad_norm: 1.0736 (1.0803) time: 0.6265 [2021-03-26 05:01:13 swin_base_patch4_window7_224] INFO: Epoch: [29] [1120/1251] eta: 0:01:22 lr: 0.000976 loss: 4.2780 (4.0933) grad_norm: 0.9969 (1.0802) time: 0.6252 [2021-03-26 05:01:19 swin_base_patch4_window7_224] INFO: Epoch: [29] [1130/1251] eta: 0:01:16 lr: 0.000976 loss: 4.0390 (4.0931) grad_norm: 0.9969 (1.0795) time: 0.6223 [2021-03-26 05:01:25 swin_base_patch4_window7_224] INFO: Epoch: [29] [1140/1251] eta: 0:01:09 lr: 0.000976 loss: 4.1565 (4.0946) grad_norm: 1.0350 (1.0793) time: 0.6201 [2021-03-26 05:01:31 swin_base_patch4_window7_224] INFO: Epoch: [29] [1150/1251] eta: 0:01:03 lr: 0.000976 loss: 4.1728 (4.0944) grad_norm: 1.0291 (1.0786) time: 0.6202 [2021-03-26 05:01:38 swin_base_patch4_window7_224] INFO: Epoch: [29] [1160/1251] eta: 0:00:57 lr: 0.000976 loss: 4.0322 (4.0943) grad_norm: 1.0314 (1.0781) time: 0.6264 [2021-03-26 05:01:44 swin_base_patch4_window7_224] INFO: Epoch: [29] [1170/1251] eta: 0:00:50 lr: 0.000976 loss: 4.0422 (4.0935) grad_norm: 0.9560 (1.0769) time: 0.6221 [2021-03-26 05:01:50 swin_base_patch4_window7_224] INFO: Epoch: [29] [1180/1251] eta: 0:00:44 lr: 0.000976 loss: 4.2014 (4.0936) grad_norm: 0.9560 (1.0765) time: 0.6157 [2021-03-26 05:01:56 swin_base_patch4_window7_224] INFO: Epoch: [29] [1190/1251] eta: 0:00:38 lr: 0.000976 loss: 4.2439 (4.0937) grad_norm: 1.0346 (1.0762) time: 0.6218 [2021-03-26 05:02:03 swin_base_patch4_window7_224] INFO: Epoch: [29] [1200/1251] eta: 0:00:32 lr: 0.000976 loss: 4.1586 (4.0926) grad_norm: 1.0968 (1.0769) time: 0.6300 [2021-03-26 05:02:09 swin_base_patch4_window7_224] INFO: Epoch: [29] [1210/1251] eta: 0:00:25 lr: 0.000976 loss: 3.9899 (4.0918) grad_norm: 1.1071 (1.0770) time: 0.6304 [2021-03-26 05:02:15 swin_base_patch4_window7_224] INFO: Epoch: [29] [1220/1251] eta: 0:00:19 lr: 0.000976 loss: 3.9899 (4.0906) grad_norm: 1.0134 (1.0767) time: 0.6271 [2021-03-26 05:02:21 swin_base_patch4_window7_224] INFO: Epoch: [29] [1230/1251] eta: 0:00:13 lr: 0.000976 loss: 4.1348 (4.0905) grad_norm: 1.0134 (1.0770) time: 0.6221 [2021-03-26 05:02:28 swin_base_patch4_window7_224] INFO: Epoch: [29] [1240/1251] eta: 0:00:06 lr: 0.000976 loss: 4.0788 (4.0902) grad_norm: 1.1103 (1.0783) time: 0.6190 [2021-03-26 05:02:34 swin_base_patch4_window7_224] INFO: Epoch: [29] [1250/1251] eta: 0:00:00 lr: 0.000976 loss: 4.0788 (4.0899) grad_norm: 1.1740 (1.0796) time: 0.6152 [2021-03-26 05:02:38 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:06 loss: 1.3461 (1.3461) acc1: 70.3125 (70.3125) acc5: 89.0625 (89.0625) [2021-03-26 05:02:40 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.3461 (1.4392) acc1: 70.3125 (66.1932) acc5: 90.6250 (88.9205) [2021-03-26 05:02:42 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.4532 (1.4596) acc1: 67.1875 (66.5923) acc5: 89.0625 (88.0208) [2021-03-26 05:02:45 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.4629 (1.4634) acc1: 65.6250 (66.6835) acc5: 87.5000 (88.0040) [2021-03-26 05:02:47 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.3987 (1.4485) acc1: 67.1875 (67.2637) acc5: 89.0625 (88.2241) [2021-03-26 05:02:48 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.4672 (1.4734) acc1: 67.1875 (66.6240) acc5: 87.5000 (87.6800) [2021-03-26 05:02:50 swin_base_patch4_window7_224] INFO: * Acc@1 67.106 Acc@5 88.430 loss 1.455 [2021-03-26 05:02:50 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 67.1% [2021-03-26 05:02:50 swin_base_patch4_window7_224] INFO: Max accuracy: 67.11% [2021-03-26 05:02:54 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 0/1251] eta: 1:25:10 lr: 0.000976 loss: 4.4166 (4.4166) grad_norm: 1.2310 (1.2310) time: 4.0854 [2021-03-26 05:03:00 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 10/1251] eta: 0:19:29 lr: 0.000976 loss: 4.4166 (4.2096) grad_norm: 1.0428 (1.0937) time: 0.9426 [2021-03-26 05:03:07 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 20/1251] eta: 0:16:23 lr: 0.000976 loss: 4.0464 (4.0975) grad_norm: 1.0368 (1.0849) time: 0.6347 [2021-03-26 05:03:13 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 30/1251] eta: 0:15:09 lr: 0.000976 loss: 4.0464 (4.0697) grad_norm: 1.0290 (1.0824) time: 0.6358 [2021-03-26 05:03:19 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 40/1251] eta: 0:14:24 lr: 0.000976 loss: 4.0829 (4.0636) grad_norm: 0.9962 (1.0652) time: 0.6245 [2021-03-26 05:03:26 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 50/1251] eta: 0:13:57 lr: 0.000976 loss: 4.2511 (4.1001) grad_norm: 1.0755 (1.0861) time: 0.6249 [2021-03-26 05:03:32 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 60/1251] eta: 0:13:37 lr: 0.000976 loss: 4.2752 (4.1137) grad_norm: 1.1117 (1.0878) time: 0.6305 [2021-03-26 05:03:38 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 70/1251] eta: 0:13:19 lr: 0.000976 loss: 3.9957 (4.0436) grad_norm: 1.1117 (1.0958) time: 0.6254 [2021-03-26 05:03:44 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 80/1251] eta: 0:13:06 lr: 0.000976 loss: 3.9957 (4.0544) grad_norm: 1.0774 (1.0863) time: 0.6265 [2021-03-26 05:03:51 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 90/1251] eta: 0:12:53 lr: 0.000976 loss: 4.0455 (4.0390) grad_norm: 1.0340 (1.0847) time: 0.6280 [2021-03-26 05:03:57 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 100/1251] eta: 0:12:41 lr: 0.000976 loss: 3.9653 (4.0318) grad_norm: 1.0278 (1.0811) time: 0.6228 [2021-03-26 05:04:03 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 110/1251] eta: 0:12:32 lr: 0.000976 loss: 4.3557 (4.0643) grad_norm: 1.0314 (1.0826) time: 0.6269 [2021-03-26 05:04:09 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 120/1251] eta: 0:12:22 lr: 0.000976 loss: 4.4520 (4.0919) grad_norm: 1.0898 (1.0956) time: 0.6285 [2021-03-26 05:04:16 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 130/1251] eta: 0:12:13 lr: 0.000976 loss: 4.2584 (4.0904) grad_norm: 1.0707 (1.0940) time: 0.6243 [2021-03-26 05:04:22 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 140/1251] eta: 0:12:05 lr: 0.000976 loss: 4.2569 (4.0905) grad_norm: 1.0665 (1.0971) time: 0.6318 [2021-03-26 05:04:28 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 150/1251] eta: 0:11:57 lr: 0.000976 loss: 3.9264 (4.0769) grad_norm: 1.1273 (1.0995) time: 0.6340 [2021-03-26 05:04:35 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 160/1251] eta: 0:11:48 lr: 0.000976 loss: 4.0764 (4.0922) grad_norm: 1.0165 (1.0900) time: 0.6243 [2021-03-26 05:04:41 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 170/1251] eta: 0:11:39 lr: 0.000976 loss: 4.3008 (4.0949) grad_norm: 0.9376 (inf) time: 0.6134 [2021-03-26 05:04:47 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 180/1251] eta: 0:11:32 lr: 0.000976 loss: 4.1300 (4.0921) grad_norm: 0.9583 (inf) time: 0.6202 [2021-03-26 05:04:53 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 190/1251] eta: 0:11:24 lr: 0.000976 loss: 4.2624 (4.1074) grad_norm: 1.0013 (inf) time: 0.6310 [2021-03-26 05:05:00 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 200/1251] eta: 0:11:17 lr: 0.000976 loss: 4.2661 (4.1076) grad_norm: 1.0228 (inf) time: 0.6290 [2021-03-26 05:05:06 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 210/1251] eta: 0:11:09 lr: 0.000976 loss: 3.9857 (4.1002) grad_norm: 1.0808 (inf) time: 0.6270 [2021-03-26 05:05:12 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 220/1251] eta: 0:11:02 lr: 0.000975 loss: 3.7392 (4.0759) grad_norm: 1.0193 (inf) time: 0.6254 [2021-03-26 05:05:18 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 230/1251] eta: 0:10:55 lr: 0.000975 loss: 4.0137 (4.0781) grad_norm: 0.9517 (inf) time: 0.6223 [2021-03-26 05:05:24 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 240/1251] eta: 0:10:47 lr: 0.000975 loss: 4.1502 (4.0781) grad_norm: 0.9516 (inf) time: 0.6192 [2021-03-26 05:05:31 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 250/1251] eta: 0:10:40 lr: 0.000975 loss: 3.9700 (4.0840) grad_norm: 1.0240 (inf) time: 0.6226 [2021-03-26 05:05:37 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 260/1251] eta: 0:10:33 lr: 0.000975 loss: 3.7484 (4.0760) grad_norm: 1.0758 (inf) time: 0.6255 [2021-03-26 05:05:43 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 270/1251] eta: 0:10:26 lr: 0.000975 loss: 4.2511 (4.0887) grad_norm: 1.0758 (inf) time: 0.6250 [2021-03-26 05:05:50 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 280/1251] eta: 0:10:20 lr: 0.000975 loss: 4.1477 (4.0828) grad_norm: 1.1198 (inf) time: 0.6254 [2021-03-26 05:05:56 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 290/1251] eta: 0:10:13 lr: 0.000975 loss: 4.0664 (4.0820) grad_norm: 1.2931 (inf) time: 0.6268 [2021-03-26 05:06:02 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 300/1251] eta: 0:10:06 lr: 0.000975 loss: 3.9511 (4.0759) grad_norm: 1.2931 (inf) time: 0.6240 [2021-03-26 05:06:08 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 310/1251] eta: 0:09:59 lr: 0.000975 loss: 3.9170 (4.0681) grad_norm: 1.1389 (inf) time: 0.6159 [2021-03-26 05:06:14 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 320/1251] eta: 0:09:52 lr: 0.000975 loss: 4.0548 (4.0668) grad_norm: 0.9910 (inf) time: 0.6178 [2021-03-26 05:06:21 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 330/1251] eta: 0:09:45 lr: 0.000975 loss: 4.2513 (4.0729) grad_norm: 1.0200 (inf) time: 0.6265 [2021-03-26 05:06:27 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 340/1251] eta: 0:09:39 lr: 0.000975 loss: 4.1765 (4.0696) grad_norm: 0.9682 (inf) time: 0.6224 [2021-03-26 05:06:33 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 350/1251] eta: 0:09:32 lr: 0.000975 loss: 4.1765 (4.0750) grad_norm: 0.9580 (inf) time: 0.6180 [2021-03-26 05:06:39 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 360/1251] eta: 0:09:25 lr: 0.000975 loss: 4.3387 (4.0784) grad_norm: 1.0129 (inf) time: 0.6246 [2021-03-26 05:06:46 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 370/1251] eta: 0:09:19 lr: 0.000975 loss: 4.2060 (4.0761) grad_norm: 1.1096 (inf) time: 0.6322 [2021-03-26 05:06:52 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 380/1251] eta: 0:09:12 lr: 0.000975 loss: 4.1607 (4.0760) grad_norm: 1.0402 (inf) time: 0.6317 [2021-03-26 05:06:58 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 390/1251] eta: 0:09:06 lr: 0.000975 loss: 4.1607 (4.0741) grad_norm: 1.0055 (inf) time: 0.6256 [2021-03-26 05:07:04 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 400/1251] eta: 0:08:59 lr: 0.000975 loss: 4.1838 (4.0754) grad_norm: 0.9686 (inf) time: 0.6233 [2021-03-26 05:07:11 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 410/1251] eta: 0:08:53 lr: 0.000975 loss: 4.0993 (4.0695) grad_norm: 0.9908 (inf) time: 0.6226 [2021-03-26 05:07:17 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 420/1251] eta: 0:08:46 lr: 0.000975 loss: 3.7122 (4.0649) grad_norm: 1.0387 (inf) time: 0.6252 [2021-03-26 05:07:23 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 430/1251] eta: 0:08:40 lr: 0.000975 loss: 4.2122 (4.0669) grad_norm: 1.0506 (inf) time: 0.6297 [2021-03-26 05:07:29 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 440/1251] eta: 0:08:33 lr: 0.000975 loss: 4.1645 (4.0661) grad_norm: 1.0385 (inf) time: 0.6243 [2021-03-26 05:07:36 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 450/1251] eta: 0:08:27 lr: 0.000975 loss: 4.1362 (4.0654) grad_norm: 1.0038 (inf) time: 0.6181 [2021-03-26 05:07:42 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 460/1251] eta: 0:08:20 lr: 0.000975 loss: 4.1500 (4.0626) grad_norm: 0.9756 (inf) time: 0.6187 [2021-03-26 05:07:48 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 470/1251] eta: 0:08:13 lr: 0.000975 loss: 4.1410 (4.0644) grad_norm: 0.9649 (inf) time: 0.6210 [2021-03-26 05:07:54 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 480/1251] eta: 0:08:07 lr: 0.000975 loss: 4.0949 (4.0613) grad_norm: 0.9649 (inf) time: 0.6236 [2021-03-26 05:08:00 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 490/1251] eta: 0:08:01 lr: 0.000975 loss: 3.9420 (4.0601) grad_norm: 1.0067 (inf) time: 0.6227 [2021-03-26 05:08:07 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 500/1251] eta: 0:07:54 lr: 0.000975 loss: 3.9514 (4.0589) grad_norm: 0.9780 (inf) time: 0.6193 [2021-03-26 05:08:13 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 510/1251] eta: 0:07:48 lr: 0.000975 loss: 4.0507 (4.0575) grad_norm: 1.0359 (inf) time: 0.6228 [2021-03-26 05:08:19 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 520/1251] eta: 0:07:41 lr: 0.000975 loss: 4.0469 (4.0553) grad_norm: 1.0971 (inf) time: 0.6256 [2021-03-26 05:08:25 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 530/1251] eta: 0:07:35 lr: 0.000975 loss: 4.0469 (4.0553) grad_norm: 1.0274 (inf) time: 0.6250 [2021-03-26 05:08:32 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 540/1251] eta: 0:07:28 lr: 0.000975 loss: 4.0343 (4.0504) grad_norm: 1.0124 (inf) time: 0.6261 [2021-03-26 05:08:38 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 550/1251] eta: 0:07:22 lr: 0.000975 loss: 4.0731 (4.0512) grad_norm: 0.9818 (inf) time: 0.6355 [2021-03-26 05:08:44 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 560/1251] eta: 0:07:16 lr: 0.000975 loss: 4.1309 (4.0533) grad_norm: 0.9631 (inf) time: 0.6349 [2021-03-26 05:08:51 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 570/1251] eta: 0:07:09 lr: 0.000975 loss: 4.1145 (4.0585) grad_norm: 1.0305 (inf) time: 0.6247 [2021-03-26 05:08:57 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 580/1251] eta: 0:07:03 lr: 0.000975 loss: 4.2228 (4.0603) grad_norm: 1.1134 (inf) time: 0.6283 [2021-03-26 05:09:03 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 590/1251] eta: 0:06:57 lr: 0.000975 loss: 4.2228 (4.0618) grad_norm: 1.1162 (inf) time: 0.6317 [2021-03-26 05:09:10 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 600/1251] eta: 0:06:51 lr: 0.000975 loss: 4.3224 (4.0640) grad_norm: 1.0546 (inf) time: 0.6328 [2021-03-26 05:09:16 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 610/1251] eta: 0:06:44 lr: 0.000975 loss: 4.3138 (4.0650) grad_norm: 1.0411 (inf) time: 0.6340 [2021-03-26 05:09:22 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 620/1251] eta: 0:06:38 lr: 0.000975 loss: 4.2610 (4.0660) grad_norm: 1.1141 (inf) time: 0.6274 [2021-03-26 05:09:28 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 630/1251] eta: 0:06:32 lr: 0.000975 loss: 4.2148 (4.0677) grad_norm: 1.0647 (inf) time: 0.6240 [2021-03-26 05:09:35 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 640/1251] eta: 0:06:25 lr: 0.000975 loss: 4.1858 (4.0698) grad_norm: 1.0543 (inf) time: 0.6251 [2021-03-26 05:09:41 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 650/1251] eta: 0:06:19 lr: 0.000975 loss: 4.1023 (4.0670) grad_norm: 0.9830 (inf) time: 0.6254 [2021-03-26 05:09:47 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 660/1251] eta: 0:06:12 lr: 0.000975 loss: 4.1023 (4.0695) grad_norm: 0.9777 (inf) time: 0.6306 [2021-03-26 05:09:53 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 670/1251] eta: 0:06:06 lr: 0.000975 loss: 4.0084 (4.0671) grad_norm: 0.9777 (inf) time: 0.6273 [2021-03-26 05:10:00 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 680/1251] eta: 0:06:00 lr: 0.000975 loss: 4.2494 (4.0707) grad_norm: 0.9447 (inf) time: 0.6174 [2021-03-26 05:10:06 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 690/1251] eta: 0:05:53 lr: 0.000975 loss: 4.2441 (4.0702) grad_norm: 0.9963 (inf) time: 0.6234 [2021-03-26 05:10:12 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 700/1251] eta: 0:05:47 lr: 0.000975 loss: 4.0406 (4.0680) grad_norm: 1.1554 (inf) time: 0.6325 [2021-03-26 05:10:19 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 710/1251] eta: 0:05:41 lr: 0.000975 loss: 4.2647 (4.0705) grad_norm: 1.0795 (inf) time: 0.6321 [2021-03-26 05:10:25 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 720/1251] eta: 0:05:34 lr: 0.000975 loss: 4.2818 (4.0680) grad_norm: 1.0506 (inf) time: 0.6275 [2021-03-26 05:10:31 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 730/1251] eta: 0:05:28 lr: 0.000975 loss: 4.2655 (4.0742) grad_norm: 1.1168 (inf) time: 0.6303 [2021-03-26 05:10:38 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 740/1251] eta: 0:05:22 lr: 0.000975 loss: 4.4479 (4.0766) grad_norm: 1.1388 (inf) time: 0.6364 [2021-03-26 05:10:44 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 750/1251] eta: 0:05:16 lr: 0.000975 loss: 4.3199 (4.0777) grad_norm: 1.0699 (inf) time: 0.6404 [2021-03-26 05:10:50 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 760/1251] eta: 0:05:09 lr: 0.000975 loss: 4.3138 (4.0805) grad_norm: 1.0832 (inf) time: 0.6344 [2021-03-26 05:10:57 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 770/1251] eta: 0:05:03 lr: 0.000975 loss: 4.2543 (4.0785) grad_norm: 1.0564 (inf) time: 0.6329 [2021-03-26 05:11:03 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 780/1251] eta: 0:04:57 lr: 0.000975 loss: 3.7978 (4.0743) grad_norm: 0.9678 (inf) time: 0.6308 [2021-03-26 05:11:09 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 790/1251] eta: 0:04:50 lr: 0.000975 loss: 4.0206 (4.0741) grad_norm: 1.0105 (inf) time: 0.6220 [2021-03-26 05:11:15 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 800/1251] eta: 0:04:44 lr: 0.000975 loss: 4.1053 (4.0734) grad_norm: 1.0465 (inf) time: 0.6247 [2021-03-26 05:11:22 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 810/1251] eta: 0:04:38 lr: 0.000975 loss: 4.0622 (4.0733) grad_norm: 1.0632 (inf) time: 0.6252 [2021-03-26 05:11:28 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 820/1251] eta: 0:04:31 lr: 0.000975 loss: 4.0622 (4.0721) grad_norm: 1.0956 (inf) time: 0.6265 [2021-03-26 05:11:34 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 830/1251] eta: 0:04:25 lr: 0.000975 loss: 4.1746 (4.0741) grad_norm: 1.0927 (inf) time: 0.6249 [2021-03-26 05:11:40 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 840/1251] eta: 0:04:19 lr: 0.000975 loss: 4.1746 (4.0751) grad_norm: 1.0402 (inf) time: 0.6208 [2021-03-26 05:11:47 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 850/1251] eta: 0:04:12 lr: 0.000975 loss: 4.0567 (4.0727) grad_norm: 1.0241 (inf) time: 0.6288 [2021-03-26 05:11:53 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 860/1251] eta: 0:04:06 lr: 0.000975 loss: 4.3174 (4.0749) grad_norm: 1.1265 (inf) time: 0.6322 [2021-03-26 05:11:59 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 870/1251] eta: 0:04:00 lr: 0.000975 loss: 4.1761 (4.0713) grad_norm: 1.0103 (inf) time: 0.6228 [2021-03-26 05:12:05 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 880/1251] eta: 0:03:53 lr: 0.000975 loss: 3.7811 (4.0717) grad_norm: 0.9912 (inf) time: 0.6178 [2021-03-26 05:12:12 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 890/1251] eta: 0:03:47 lr: 0.000975 loss: 4.0761 (4.0707) grad_norm: 1.0263 (inf) time: 0.6209 [2021-03-26 05:12:18 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 900/1251] eta: 0:03:41 lr: 0.000975 loss: 4.1733 (4.0734) grad_norm: 1.1681 (inf) time: 0.6296 [2021-03-26 05:12:24 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 910/1251] eta: 0:03:34 lr: 0.000975 loss: 4.1842 (4.0733) grad_norm: 1.0825 (inf) time: 0.6354 [2021-03-26 05:12:31 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 920/1251] eta: 0:03:28 lr: 0.000975 loss: 4.0152 (4.0699) grad_norm: 1.0825 (inf) time: 0.6358 [2021-03-26 05:12:37 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 930/1251] eta: 0:03:22 lr: 0.000975 loss: 4.0583 (4.0682) grad_norm: 1.0883 (inf) time: 0.6257 [2021-03-26 05:12:43 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 940/1251] eta: 0:03:15 lr: 0.000975 loss: 3.9443 (4.0676) grad_norm: 0.9731 (inf) time: 0.6200 [2021-03-26 05:12:49 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 950/1251] eta: 0:03:09 lr: 0.000975 loss: 4.0016 (4.0683) grad_norm: 0.9577 (inf) time: 0.6231 [2021-03-26 05:12:56 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 960/1251] eta: 0:03:03 lr: 0.000975 loss: 4.0190 (4.0675) grad_norm: 1.0314 (inf) time: 0.6337 [2021-03-26 05:13:02 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 970/1251] eta: 0:02:57 lr: 0.000975 loss: 3.8059 (4.0649) grad_norm: 0.9974 (inf) time: 0.6329 [2021-03-26 05:13:08 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 980/1251] eta: 0:02:50 lr: 0.000975 loss: 4.0231 (4.0644) grad_norm: 1.0528 (inf) time: 0.6198 [2021-03-26 05:13:14 swin_base_patch4_window7_224] INFO: Epoch: [30] [ 990/1251] eta: 0:02:44 lr: 0.000974 loss: 4.4337 (4.0686) grad_norm: 1.0533 (inf) time: 0.6179 [2021-03-26 05:13:20 swin_base_patch4_window7_224] INFO: Epoch: [30] [1000/1251] eta: 0:02:38 lr: 0.000974 loss: 4.3941 (4.0687) grad_norm: 1.0447 (inf) time: 0.6170 [2021-03-26 05:13:27 swin_base_patch4_window7_224] INFO: Epoch: [30] [1010/1251] eta: 0:02:31 lr: 0.000974 loss: 3.9735 (4.0663) grad_norm: 1.0447 (inf) time: 0.6143 [2021-03-26 05:13:33 swin_base_patch4_window7_224] INFO: Epoch: [30] [1020/1251] eta: 0:02:25 lr: 0.000974 loss: 3.4309 (4.0641) grad_norm: 1.0667 (inf) time: 0.6155 [2021-03-26 05:13:39 swin_base_patch4_window7_224] INFO: Epoch: [30] [1030/1251] eta: 0:02:19 lr: 0.000974 loss: 3.8070 (4.0634) grad_norm: 1.0907 (inf) time: 0.6220 [2021-03-26 05:13:45 swin_base_patch4_window7_224] INFO: Epoch: [30] [1040/1251] eta: 0:02:12 lr: 0.000974 loss: 4.0567 (4.0638) grad_norm: 1.0797 (inf) time: 0.6252 [2021-03-26 05:13:52 swin_base_patch4_window7_224] INFO: Epoch: [30] [1050/1251] eta: 0:02:06 lr: 0.000974 loss: 4.2776 (4.0652) grad_norm: 1.0734 (inf) time: 0.6246 [2021-03-26 05:13:58 swin_base_patch4_window7_224] INFO: Epoch: [30] [1060/1251] eta: 0:02:00 lr: 0.000974 loss: 4.2861 (4.0647) grad_norm: 1.0665 (inf) time: 0.6248 [2021-03-26 05:14:04 swin_base_patch4_window7_224] INFO: Epoch: [30] [1070/1251] eta: 0:01:53 lr: 0.000974 loss: 4.0625 (4.0637) grad_norm: 1.0423 (inf) time: 0.6224 [2021-03-26 05:14:10 swin_base_patch4_window7_224] INFO: Epoch: [30] [1080/1251] eta: 0:01:47 lr: 0.000974 loss: 3.9646 (4.0636) grad_norm: 1.0030 (inf) time: 0.6242 [2021-03-26 05:14:17 swin_base_patch4_window7_224] INFO: Epoch: [30] [1090/1251] eta: 0:01:41 lr: 0.000974 loss: 4.1335 (4.0638) grad_norm: 1.0030 (inf) time: 0.6256 [2021-03-26 05:14:23 swin_base_patch4_window7_224] INFO: Epoch: [30] [1100/1251] eta: 0:01:34 lr: 0.000974 loss: 4.0324 (4.0622) grad_norm: 1.1148 (inf) time: 0.6277 [2021-03-26 05:14:29 swin_base_patch4_window7_224] INFO: Epoch: [30] [1110/1251] eta: 0:01:28 lr: 0.000974 loss: 3.9892 (4.0623) grad_norm: 1.0510 (inf) time: 0.6295 [2021-03-26 05:14:35 swin_base_patch4_window7_224] INFO: Epoch: [30] [1120/1251] eta: 0:01:22 lr: 0.000974 loss: 3.8631 (4.0610) grad_norm: 0.9480 (inf) time: 0.6219 [2021-03-26 05:14:42 swin_base_patch4_window7_224] INFO: Epoch: [30] [1130/1251] eta: 0:01:16 lr: 0.000974 loss: 3.8554 (4.0598) grad_norm: 0.9696 (inf) time: 0.6263 [2021-03-26 05:14:48 swin_base_patch4_window7_224] INFO: Epoch: [30] [1140/1251] eta: 0:01:09 lr: 0.000974 loss: 4.0873 (4.0600) grad_norm: 1.0892 (inf) time: 0.6326 [2021-03-26 05:14:54 swin_base_patch4_window7_224] INFO: Epoch: [30] [1150/1251] eta: 0:01:03 lr: 0.000974 loss: 4.3684 (4.0600) grad_norm: 1.0380 (inf) time: 0.6269 [2021-03-26 05:15:00 swin_base_patch4_window7_224] INFO: Epoch: [30] [1160/1251] eta: 0:00:57 lr: 0.000974 loss: 4.1554 (4.0607) grad_norm: 1.0294 (inf) time: 0.6249 [2021-03-26 05:15:07 swin_base_patch4_window7_224] INFO: Epoch: [30] [1170/1251] eta: 0:00:50 lr: 0.000974 loss: 4.1478 (4.0602) grad_norm: 1.0065 (inf) time: 0.6219 [2021-03-26 05:15:13 swin_base_patch4_window7_224] INFO: Epoch: [30] [1180/1251] eta: 0:00:44 lr: 0.000974 loss: 3.9342 (4.0608) grad_norm: 0.9811 (inf) time: 0.6166 [2021-03-26 05:15:19 swin_base_patch4_window7_224] INFO: Epoch: [30] [1190/1251] eta: 0:00:38 lr: 0.000974 loss: 4.0457 (4.0603) grad_norm: 0.9559 (inf) time: 0.6145 [2021-03-26 05:15:25 swin_base_patch4_window7_224] INFO: Epoch: [30] [1200/1251] eta: 0:00:32 lr: 0.000974 loss: 4.3285 (4.0609) grad_norm: 1.0355 (inf) time: 0.6209 [2021-03-26 05:15:31 swin_base_patch4_window7_224] INFO: Epoch: [30] [1210/1251] eta: 0:00:25 lr: 0.000974 loss: 4.3266 (4.0631) grad_norm: 1.0355 (inf) time: 0.6280 [2021-03-26 05:15:38 swin_base_patch4_window7_224] INFO: Epoch: [30] [1220/1251] eta: 0:00:19 lr: 0.000974 loss: 4.2455 (4.0627) grad_norm: 1.0312 (inf) time: 0.6239 [2021-03-26 05:15:44 swin_base_patch4_window7_224] INFO: Epoch: [30] [1230/1251] eta: 0:00:13 lr: 0.000974 loss: 4.0153 (4.0606) grad_norm: 1.0820 (inf) time: 0.6263 [2021-03-26 05:15:50 swin_base_patch4_window7_224] INFO: Epoch: [30] [1240/1251] eta: 0:00:06 lr: 0.000974 loss: 3.6978 (4.0587) grad_norm: 0.9885 (inf) time: 0.6198 [2021-03-26 05:15:56 swin_base_patch4_window7_224] INFO: Epoch: [30] [1250/1251] eta: 0:00:00 lr: 0.000974 loss: 3.9962 (4.0588) grad_norm: 0.9893 (inf) time: 0.6116 [2021-03-26 05:17:05 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:10 loss: 1.6608 (1.6608) acc1: 64.0625 (64.0625) acc5: 85.9375 (85.9375) [2021-03-26 05:17:06 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 1.5316 (1.4577) acc1: 65.6250 (65.7670) acc5: 87.5000 (88.3523) [2021-03-26 05:17:08 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.3409 (1.3914) acc1: 68.7500 (68.7500) acc5: 89.0625 (88.6161) [2021-03-26 05:17:09 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.3866 (1.4204) acc1: 68.7500 (67.4395) acc5: 89.0625 (88.0544) [2021-03-26 05:17:11 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.3952 (1.4126) acc1: 64.0625 (67.1875) acc5: 87.5000 (88.3384) [2021-03-26 05:17:12 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.4686 (1.4247) acc1: 67.1875 (66.9120) acc5: 87.5000 (88.2880) [2021-03-26 05:17:15 swin_base_patch4_window7_224] INFO: * Acc@1 67.594 Acc@5 88.722 loss 1.406 [2021-03-26 05:17:15 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 67.6% [2021-03-26 05:17:15 swin_base_patch4_window7_224] INFO: Max accuracy: 67.59% [2021-03-26 05:17:19 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 0/1251] eta: 1:23:30 lr: 0.000974 loss: 3.3474 (3.3474) grad_norm: 1.0996 (1.0996) time: 4.0051 [2021-03-26 05:17:25 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 10/1251] eta: 0:19:58 lr: 0.000974 loss: 4.1246 (4.1139) grad_norm: 1.0399 (1.0584) time: 0.9658 [2021-03-26 05:17:32 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 20/1251] eta: 0:16:26 lr: 0.000974 loss: 4.1030 (4.1423) grad_norm: 1.0565 (1.1194) time: 0.6411 [2021-03-26 05:17:38 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 30/1251] eta: 0:15:10 lr: 0.000974 loss: 3.9761 (4.0214) grad_norm: 1.0638 (1.0802) time: 0.6243 [2021-03-26 05:17:44 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 40/1251] eta: 0:14:30 lr: 0.000974 loss: 3.5937 (3.9058) grad_norm: 1.1061 (1.1019) time: 0.6326 [2021-03-26 05:17:50 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 50/1251] eta: 0:14:00 lr: 0.000974 loss: 3.4623 (3.8802) grad_norm: 1.1641 (1.1308) time: 0.6300 [2021-03-26 05:17:57 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 60/1251] eta: 0:13:38 lr: 0.000974 loss: 3.6960 (3.8673) grad_norm: 1.0745 (1.1171) time: 0.6230 [2021-03-26 05:18:03 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 70/1251] eta: 0:13:21 lr: 0.000974 loss: 3.7372 (3.8404) grad_norm: 1.0104 (1.1049) time: 0.6234 [2021-03-26 05:18:09 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 80/1251] eta: 0:13:07 lr: 0.000974 loss: 3.7859 (3.8536) grad_norm: 1.0205 (1.1048) time: 0.6259 [2021-03-26 05:18:15 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 90/1251] eta: 0:12:53 lr: 0.000974 loss: 4.0807 (3.8965) grad_norm: 0.9778 (1.0927) time: 0.6213 [2021-03-26 05:18:22 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 100/1251] eta: 0:12:41 lr: 0.000974 loss: 4.2746 (3.9470) grad_norm: 0.9894 (1.0958) time: 0.6191 [2021-03-26 05:18:28 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 110/1251] eta: 0:12:31 lr: 0.000974 loss: 4.5102 (3.9802) grad_norm: 1.0256 (1.0880) time: 0.6275 [2021-03-26 05:18:34 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 120/1251] eta: 0:12:22 lr: 0.000974 loss: 4.4281 (4.0078) grad_norm: 1.0159 (1.0808) time: 0.6289 [2021-03-26 05:18:41 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 130/1251] eta: 0:12:14 lr: 0.000974 loss: 4.2619 (4.0164) grad_norm: 1.0299 (1.0863) time: 0.6346 [2021-03-26 05:18:47 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 140/1251] eta: 0:12:06 lr: 0.000974 loss: 4.1241 (4.0097) grad_norm: 1.1386 (1.0924) time: 0.6377 [2021-03-26 05:18:53 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 150/1251] eta: 0:11:56 lr: 0.000974 loss: 3.9459 (4.0073) grad_norm: 1.0623 (1.0845) time: 0.6239 [2021-03-26 05:18:59 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 160/1251] eta: 0:11:48 lr: 0.000974 loss: 3.8442 (3.9916) grad_norm: 0.9642 (1.0803) time: 0.6218 [2021-03-26 05:19:06 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 170/1251] eta: 0:11:40 lr: 0.000974 loss: 3.9210 (4.0096) grad_norm: 0.9642 (1.0747) time: 0.6228 [2021-03-26 05:19:12 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 180/1251] eta: 0:11:32 lr: 0.000974 loss: 4.3018 (4.0255) grad_norm: 0.9223 (1.0677) time: 0.6198 [2021-03-26 05:19:18 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 190/1251] eta: 0:11:24 lr: 0.000974 loss: 4.2622 (4.0145) grad_norm: 0.9687 (1.0656) time: 0.6241 [2021-03-26 05:19:24 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 200/1251] eta: 0:11:17 lr: 0.000974 loss: 4.2390 (4.0286) grad_norm: 1.0657 (1.0687) time: 0.6280 [2021-03-26 05:19:31 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 210/1251] eta: 0:11:10 lr: 0.000974 loss: 4.2896 (4.0372) grad_norm: 1.1148 (1.0695) time: 0.6308 [2021-03-26 05:19:37 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 220/1251] eta: 0:11:03 lr: 0.000974 loss: 4.2074 (4.0337) grad_norm: 1.1148 (1.0734) time: 0.6294 [2021-03-26 05:19:43 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 230/1251] eta: 0:10:55 lr: 0.000974 loss: 3.8223 (4.0237) grad_norm: 1.0639 (1.0732) time: 0.6244 [2021-03-26 05:19:49 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 240/1251] eta: 0:10:48 lr: 0.000974 loss: 3.8456 (4.0209) grad_norm: 1.0091 (1.0719) time: 0.6220 [2021-03-26 05:19:56 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 250/1251] eta: 0:10:41 lr: 0.000974 loss: 4.1353 (4.0236) grad_norm: 1.0054 (1.0713) time: 0.6303 [2021-03-26 05:20:02 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 260/1251] eta: 0:10:34 lr: 0.000974 loss: 4.0945 (4.0196) grad_norm: 1.1004 (1.0742) time: 0.6278 [2021-03-26 05:20:08 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 270/1251] eta: 0:10:27 lr: 0.000974 loss: 4.2698 (4.0291) grad_norm: 1.0776 (1.0734) time: 0.6248 [2021-03-26 05:20:14 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 280/1251] eta: 0:10:20 lr: 0.000974 loss: 4.4025 (4.0318) grad_norm: 0.9757 (1.0716) time: 0.6248 [2021-03-26 05:20:21 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 290/1251] eta: 0:10:14 lr: 0.000974 loss: 4.2492 (4.0343) grad_norm: 1.0293 (1.0707) time: 0.6243 [2021-03-26 05:20:27 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 300/1251] eta: 0:10:06 lr: 0.000974 loss: 4.2776 (4.0438) grad_norm: 1.0279 (1.0684) time: 0.6238 [2021-03-26 05:20:33 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 310/1251] eta: 0:10:00 lr: 0.000974 loss: 4.2799 (4.0506) grad_norm: 0.9944 (1.0681) time: 0.6223 [2021-03-26 05:20:39 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 320/1251] eta: 0:09:53 lr: 0.000974 loss: 4.2104 (4.0478) grad_norm: 1.0156 (1.0699) time: 0.6269 [2021-03-26 05:20:46 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 330/1251] eta: 0:09:47 lr: 0.000974 loss: 4.2238 (4.0562) grad_norm: 1.0854 (1.0697) time: 0.6302 [2021-03-26 05:20:52 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 340/1251] eta: 0:09:40 lr: 0.000974 loss: 4.2413 (4.0578) grad_norm: 1.0496 (1.0685) time: 0.6295 [2021-03-26 05:20:58 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 350/1251] eta: 0:09:33 lr: 0.000974 loss: 4.0579 (4.0542) grad_norm: 1.0292 (1.0698) time: 0.6290 [2021-03-26 05:21:05 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 360/1251] eta: 0:09:27 lr: 0.000974 loss: 3.7701 (4.0508) grad_norm: 1.0187 (1.0684) time: 0.6320 [2021-03-26 05:21:11 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 370/1251] eta: 0:09:20 lr: 0.000974 loss: 4.0495 (4.0444) grad_norm: 0.9564 (1.0684) time: 0.6275 [2021-03-26 05:21:17 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 380/1251] eta: 0:09:13 lr: 0.000974 loss: 4.0495 (4.0428) grad_norm: 0.9602 (1.0670) time: 0.6198 [2021-03-26 05:21:23 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 390/1251] eta: 0:09:07 lr: 0.000974 loss: 3.9620 (4.0399) grad_norm: 1.0307 (1.0695) time: 0.6211 [2021-03-26 05:21:30 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 400/1251] eta: 0:09:00 lr: 0.000974 loss: 4.0840 (4.0498) grad_norm: 1.0513 (1.0690) time: 0.6282 [2021-03-26 05:21:36 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 410/1251] eta: 0:08:54 lr: 0.000974 loss: 4.1673 (4.0470) grad_norm: 1.0340 (1.0687) time: 0.6209 [2021-03-26 05:21:42 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 420/1251] eta: 0:08:47 lr: 0.000974 loss: 4.0238 (4.0514) grad_norm: 1.0175 (1.0683) time: 0.6272 [2021-03-26 05:21:48 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 430/1251] eta: 0:08:41 lr: 0.000974 loss: 4.2813 (4.0508) grad_norm: 1.0099 (1.0670) time: 0.6340 [2021-03-26 05:21:55 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 440/1251] eta: 0:08:34 lr: 0.000974 loss: 4.1248 (4.0501) grad_norm: 0.9616 (1.0645) time: 0.6180 [2021-03-26 05:22:01 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 450/1251] eta: 0:08:28 lr: 0.000974 loss: 4.1248 (4.0516) grad_norm: 0.9698 (1.0642) time: 0.6188 [2021-03-26 05:22:07 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 460/1251] eta: 0:08:21 lr: 0.000974 loss: 4.1691 (4.0532) grad_norm: 0.9798 (1.0628) time: 0.6259 [2021-03-26 05:22:13 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 470/1251] eta: 0:08:14 lr: 0.000974 loss: 4.0902 (4.0498) grad_norm: 1.0308 (1.0640) time: 0.6220 [2021-03-26 05:22:19 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 480/1251] eta: 0:08:08 lr: 0.000974 loss: 4.0902 (4.0524) grad_norm: 1.0698 (1.0635) time: 0.6203 [2021-03-26 05:22:26 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 490/1251] eta: 0:08:01 lr: 0.000973 loss: 4.0151 (4.0485) grad_norm: 1.0207 (1.0630) time: 0.6224 [2021-03-26 05:22:32 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 500/1251] eta: 0:07:55 lr: 0.000973 loss: 3.8277 (4.0515) grad_norm: 0.9795 (1.0626) time: 0.6212 [2021-03-26 05:22:38 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 510/1251] eta: 0:07:48 lr: 0.000973 loss: 3.9021 (4.0507) grad_norm: 0.9795 (1.0618) time: 0.6191 [2021-03-26 05:22:44 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 520/1251] eta: 0:07:42 lr: 0.000973 loss: 3.8472 (4.0492) grad_norm: 1.0178 (1.0608) time: 0.6243 [2021-03-26 05:22:51 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 530/1251] eta: 0:07:36 lr: 0.000973 loss: 4.0674 (4.0501) grad_norm: 1.0210 (1.0602) time: 0.6299 [2021-03-26 05:22:57 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 540/1251] eta: 0:07:29 lr: 0.000973 loss: 4.1205 (4.0527) grad_norm: 1.0266 (1.0607) time: 0.6314 [2021-03-26 05:23:03 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 550/1251] eta: 0:07:23 lr: 0.000973 loss: 3.7265 (4.0451) grad_norm: 1.0872 (1.0624) time: 0.6381 [2021-03-26 05:23:10 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 560/1251] eta: 0:07:17 lr: 0.000973 loss: 3.4677 (4.0441) grad_norm: 1.0575 (1.0625) time: 0.6366 [2021-03-26 05:23:16 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 570/1251] eta: 0:07:10 lr: 0.000973 loss: 3.9706 (4.0478) grad_norm: 1.0264 (1.0612) time: 0.6252 [2021-03-26 05:23:22 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 580/1251] eta: 0:07:04 lr: 0.000973 loss: 4.0081 (4.0490) grad_norm: 0.9793 (1.0601) time: 0.6248 [2021-03-26 05:23:29 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 590/1251] eta: 0:06:57 lr: 0.000973 loss: 4.0384 (4.0482) grad_norm: 0.9793 (1.0596) time: 0.6268 [2021-03-26 05:23:35 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 600/1251] eta: 0:06:51 lr: 0.000973 loss: 4.2019 (4.0473) grad_norm: 1.0252 (1.0590) time: 0.6355 [2021-03-26 05:23:41 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 610/1251] eta: 0:06:45 lr: 0.000973 loss: 4.2019 (4.0465) grad_norm: 1.0341 (1.0597) time: 0.6403 [2021-03-26 05:23:47 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 620/1251] eta: 0:06:38 lr: 0.000973 loss: 4.4723 (4.0535) grad_norm: 1.0305 (1.0587) time: 0.6262 [2021-03-26 05:23:54 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 630/1251] eta: 0:06:32 lr: 0.000973 loss: 4.3423 (4.0538) grad_norm: 1.0010 (1.0590) time: 0.6182 [2021-03-26 05:24:00 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 640/1251] eta: 0:06:26 lr: 0.000973 loss: 4.1938 (4.0558) grad_norm: 1.0748 (1.0598) time: 0.6215 [2021-03-26 05:24:06 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 650/1251] eta: 0:06:19 lr: 0.000973 loss: 4.2353 (4.0557) grad_norm: 1.0748 (1.0590) time: 0.6195 [2021-03-26 05:24:12 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 660/1251] eta: 0:06:13 lr: 0.000973 loss: 4.2353 (4.0555) grad_norm: 0.9993 (1.0595) time: 0.6203 [2021-03-26 05:24:19 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 670/1251] eta: 0:06:07 lr: 0.000973 loss: 4.3426 (4.0576) grad_norm: 1.0406 (1.0612) time: 0.6315 [2021-03-26 05:24:25 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 680/1251] eta: 0:06:00 lr: 0.000973 loss: 4.3426 (4.0582) grad_norm: 1.1312 (1.0630) time: 0.6363 [2021-03-26 05:24:31 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 690/1251] eta: 0:05:54 lr: 0.000973 loss: 4.2438 (4.0616) grad_norm: 1.0933 (1.0628) time: 0.6275 [2021-03-26 05:24:37 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 700/1251] eta: 0:05:47 lr: 0.000973 loss: 4.4611 (4.0645) grad_norm: 1.0080 (1.0617) time: 0.6210 [2021-03-26 05:24:44 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 710/1251] eta: 0:05:41 lr: 0.000973 loss: 4.2415 (4.0631) grad_norm: 1.0446 (1.0619) time: 0.6288 [2021-03-26 05:24:50 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 720/1251] eta: 0:05:35 lr: 0.000973 loss: 4.2415 (4.0654) grad_norm: 1.0292 (1.0608) time: 0.6250 [2021-03-26 05:24:56 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 730/1251] eta: 0:05:28 lr: 0.000973 loss: 4.2501 (4.0652) grad_norm: 0.9510 (1.0602) time: 0.6153 [2021-03-26 05:25:02 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 740/1251] eta: 0:05:22 lr: 0.000973 loss: 4.3168 (4.0689) grad_norm: 0.9404 (1.0586) time: 0.6197 [2021-03-26 05:25:09 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 750/1251] eta: 0:05:16 lr: 0.000973 loss: 4.3769 (4.0699) grad_norm: 1.0208 (1.0594) time: 0.6355 [2021-03-26 05:25:15 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 760/1251] eta: 0:05:09 lr: 0.000973 loss: 3.7613 (4.0663) grad_norm: 1.1543 (1.0607) time: 0.6408 [2021-03-26 05:25:21 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 770/1251] eta: 0:05:03 lr: 0.000973 loss: 3.7191 (4.0623) grad_norm: 1.1912 (1.0623) time: 0.6303 [2021-03-26 05:25:28 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 780/1251] eta: 0:04:57 lr: 0.000973 loss: 4.0165 (4.0620) grad_norm: 1.1487 (1.0640) time: 0.6310 [2021-03-26 05:25:34 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 790/1251] eta: 0:04:50 lr: 0.000973 loss: 4.2936 (4.0627) grad_norm: 1.0496 (1.0641) time: 0.6297 [2021-03-26 05:25:40 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 800/1251] eta: 0:04:44 lr: 0.000973 loss: 4.2936 (4.0664) grad_norm: 0.9945 (1.0636) time: 0.6258 [2021-03-26 05:25:47 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 810/1251] eta: 0:04:38 lr: 0.000973 loss: 4.2799 (4.0691) grad_norm: 1.0653 (1.0636) time: 0.6253 [2021-03-26 05:25:53 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 820/1251] eta: 0:04:31 lr: 0.000973 loss: 4.1981 (4.0695) grad_norm: 1.0653 (1.0643) time: 0.6256 [2021-03-26 05:25:59 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 830/1251] eta: 0:04:25 lr: 0.000973 loss: 3.9379 (4.0676) grad_norm: 1.0590 (1.0648) time: 0.6325 [2021-03-26 05:26:06 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 840/1251] eta: 0:04:19 lr: 0.000973 loss: 3.9379 (4.0676) grad_norm: 1.1024 (1.0656) time: 0.6339 [2021-03-26 05:26:12 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 850/1251] eta: 0:04:13 lr: 0.000973 loss: 4.0613 (4.0688) grad_norm: 1.0987 (1.0656) time: 0.6293 [2021-03-26 05:26:18 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 860/1251] eta: 0:04:06 lr: 0.000973 loss: 4.1796 (4.0683) grad_norm: 1.0070 (1.0653) time: 0.6315 [2021-03-26 05:26:24 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 870/1251] eta: 0:04:00 lr: 0.000973 loss: 4.1824 (4.0690) grad_norm: 1.0262 (1.0649) time: 0.6273 [2021-03-26 05:26:31 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 880/1251] eta: 0:03:54 lr: 0.000973 loss: 4.0309 (4.0683) grad_norm: 1.0262 (1.0645) time: 0.6321 [2021-03-26 05:26:37 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 890/1251] eta: 0:03:47 lr: 0.000973 loss: 4.0309 (4.0675) grad_norm: 1.0662 (1.0647) time: 0.6371 [2021-03-26 05:26:43 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 900/1251] eta: 0:03:41 lr: 0.000973 loss: 4.1997 (4.0680) grad_norm: 1.0703 (1.0646) time: 0.6322 [2021-03-26 05:26:50 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 910/1251] eta: 0:03:35 lr: 0.000973 loss: 4.2338 (4.0693) grad_norm: 1.0633 (1.0646) time: 0.6279 [2021-03-26 05:26:56 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 920/1251] eta: 0:03:28 lr: 0.000973 loss: 4.2175 (4.0699) grad_norm: 1.0689 (1.0657) time: 0.6210 [2021-03-26 05:27:02 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 930/1251] eta: 0:03:22 lr: 0.000973 loss: 4.0550 (4.0685) grad_norm: 1.0688 (1.0649) time: 0.6220 [2021-03-26 05:27:08 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 940/1251] eta: 0:03:16 lr: 0.000973 loss: 4.0550 (4.0683) grad_norm: 0.9605 (1.0639) time: 0.6281 [2021-03-26 05:27:15 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 950/1251] eta: 0:03:09 lr: 0.000973 loss: 4.1623 (4.0688) grad_norm: 0.9771 (1.0632) time: 0.6306 [2021-03-26 05:27:21 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 960/1251] eta: 0:03:03 lr: 0.000973 loss: 4.3088 (4.0696) grad_norm: 0.9586 (1.0624) time: 0.6238 [2021-03-26 05:27:27 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 970/1251] eta: 0:02:57 lr: 0.000973 loss: 4.3263 (4.0695) grad_norm: 0.9586 (1.0625) time: 0.6235 [2021-03-26 05:27:33 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 980/1251] eta: 0:02:50 lr: 0.000973 loss: 4.3227 (4.0707) grad_norm: 0.9735 (1.0616) time: 0.6222 [2021-03-26 05:27:40 swin_base_patch4_window7_224] INFO: Epoch: [31] [ 990/1251] eta: 0:02:44 lr: 0.000973 loss: 4.0299 (4.0691) grad_norm: 1.0110 (1.0620) time: 0.6184 [2021-03-26 05:27:46 swin_base_patch4_window7_224] INFO: Epoch: [31] [1000/1251] eta: 0:02:38 lr: 0.000973 loss: 3.9574 (4.0658) grad_norm: 1.0494 (1.0617) time: 0.6217 [2021-03-26 05:27:52 swin_base_patch4_window7_224] INFO: Epoch: [31] [1010/1251] eta: 0:02:31 lr: 0.000973 loss: 3.8960 (4.0638) grad_norm: 1.0494 (1.0624) time: 0.6302 [2021-03-26 05:27:58 swin_base_patch4_window7_224] INFO: Epoch: [31] [1020/1251] eta: 0:02:25 lr: 0.000973 loss: 4.0222 (4.0626) grad_norm: 1.0637 (1.0623) time: 0.6285 [2021-03-26 05:28:05 swin_base_patch4_window7_224] INFO: Epoch: [31] [1030/1251] eta: 0:02:19 lr: 0.000973 loss: 4.0447 (4.0622) grad_norm: 1.0252 (1.0617) time: 0.6188 [2021-03-26 05:28:11 swin_base_patch4_window7_224] INFO: Epoch: [31] [1040/1251] eta: 0:02:12 lr: 0.000973 loss: 4.2188 (4.0637) grad_norm: 1.0252 (1.0614) time: 0.6290 [2021-03-26 05:28:17 swin_base_patch4_window7_224] INFO: Epoch: [31] [1050/1251] eta: 0:02:06 lr: 0.000973 loss: 4.1976 (4.0634) grad_norm: 0.9622 (1.0598) time: 0.6275 [2021-03-26 05:28:23 swin_base_patch4_window7_224] INFO: Epoch: [31] [1060/1251] eta: 0:02:00 lr: 0.000973 loss: 4.0726 (4.0619) grad_norm: 0.9726 (1.0601) time: 0.6244 [2021-03-26 05:28:30 swin_base_patch4_window7_224] INFO: Epoch: [31] [1070/1251] eta: 0:01:54 lr: 0.000973 loss: 3.7925 (4.0602) grad_norm: 1.0586 (1.0603) time: 0.6354 [2021-03-26 05:28:36 swin_base_patch4_window7_224] INFO: Epoch: [31] [1080/1251] eta: 0:01:47 lr: 0.000973 loss: 4.0476 (4.0615) grad_norm: 1.0471 (1.0602) time: 0.6275 [2021-03-26 05:28:42 swin_base_patch4_window7_224] INFO: Epoch: [31] [1090/1251] eta: 0:01:41 lr: 0.000973 loss: 4.2492 (4.0620) grad_norm: 1.0669 (1.0609) time: 0.6175 [2021-03-26 05:28:48 swin_base_patch4_window7_224] INFO: Epoch: [31] [1100/1251] eta: 0:01:35 lr: 0.000973 loss: 3.9882 (4.0601) grad_norm: 1.0197 (1.0604) time: 0.6185 [2021-03-26 05:28:55 swin_base_patch4_window7_224] INFO: Epoch: [31] [1110/1251] eta: 0:01:28 lr: 0.000973 loss: 3.8368 (4.0584) grad_norm: 1.0241 (1.0604) time: 0.6201 [2021-03-26 05:29:01 swin_base_patch4_window7_224] INFO: Epoch: [31] [1120/1251] eta: 0:01:22 lr: 0.000973 loss: 3.7583 (4.0577) grad_norm: 1.0485 (1.0607) time: 0.6268 [2021-03-26 05:29:07 swin_base_patch4_window7_224] INFO: Epoch: [31] [1130/1251] eta: 0:01:16 lr: 0.000973 loss: 4.1997 (4.0578) grad_norm: 1.0701 (1.0607) time: 0.6329 [2021-03-26 05:29:14 swin_base_patch4_window7_224] INFO: Epoch: [31] [1140/1251] eta: 0:01:09 lr: 0.000973 loss: 4.1823 (4.0585) grad_norm: 1.0434 (1.0606) time: 0.6292 [2021-03-26 05:29:20 swin_base_patch4_window7_224] INFO: Epoch: [31] [1150/1251] eta: 0:01:03 lr: 0.000973 loss: 4.0937 (4.0570) grad_norm: 1.0167 (1.0605) time: 0.6237 [2021-03-26 05:29:26 swin_base_patch4_window7_224] INFO: Epoch: [31] [1160/1251] eta: 0:00:57 lr: 0.000973 loss: 4.2380 (4.0593) grad_norm: 1.0167 (1.0601) time: 0.6187 [2021-03-26 05:29:32 swin_base_patch4_window7_224] INFO: Epoch: [31] [1170/1251] eta: 0:00:50 lr: 0.000973 loss: 4.2700 (4.0587) grad_norm: 1.0388 (1.0606) time: 0.6207 [2021-03-26 05:29:38 swin_base_patch4_window7_224] INFO: Epoch: [31] [1180/1251] eta: 0:00:44 lr: 0.000973 loss: 3.6430 (4.0561) grad_norm: 1.0169 (1.0600) time: 0.6215 [2021-03-26 05:29:45 swin_base_patch4_window7_224] INFO: Epoch: [31] [1190/1251] eta: 0:00:38 lr: 0.000973 loss: 3.5745 (4.0553) grad_norm: 1.0169 (1.0596) time: 0.6187 [2021-03-26 05:29:51 swin_base_patch4_window7_224] INFO: Epoch: [31] [1200/1251] eta: 0:00:32 lr: 0.000973 loss: 4.1443 (4.0563) grad_norm: 1.1199 (1.0616) time: 0.6229 [2021-03-26 05:29:57 swin_base_patch4_window7_224] INFO: Epoch: [31] [1210/1251] eta: 0:00:25 lr: 0.000973 loss: 4.2880 (4.0593) grad_norm: 1.1115 (1.0614) time: 0.6217 [2021-03-26 05:30:03 swin_base_patch4_window7_224] INFO: Epoch: [31] [1220/1251] eta: 0:00:19 lr: 0.000973 loss: 4.2880 (4.0589) grad_norm: 0.9428 (1.0604) time: 0.6227 [2021-03-26 05:30:09 swin_base_patch4_window7_224] INFO: Epoch: [31] [1230/1251] eta: 0:00:13 lr: 0.000972 loss: 4.2833 (4.0595) grad_norm: 0.9428 (1.0601) time: 0.6251 [2021-03-26 05:30:16 swin_base_patch4_window7_224] INFO: Epoch: [31] [1240/1251] eta: 0:00:06 lr: 0.000972 loss: 4.0245 (4.0580) grad_norm: 0.9697 (1.0598) time: 0.6295 [2021-03-26 05:30:22 swin_base_patch4_window7_224] INFO: Epoch: [31] [1250/1251] eta: 0:00:00 lr: 0.000972 loss: 3.8987 (4.0559) grad_norm: 1.0353 (1.0601) time: 0.6265 [2021-03-26 05:30:27 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:59 loss: 1.4764 (1.4764) acc1: 76.5625 (76.5625) acc5: 84.3750 (84.3750) [2021-03-26 05:30:29 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.3615 (1.3161) acc1: 68.7500 (68.7500) acc5: 89.0625 (87.9261) [2021-03-26 05:30:31 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.2627 (1.3328) acc1: 67.1875 (69.1220) acc5: 89.0625 (88.4673) [2021-03-26 05:30:33 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.3824 (1.3522) acc1: 68.7500 (68.4980) acc5: 89.0625 (88.3569) [2021-03-26 05:30:35 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.3421 (1.3566) acc1: 68.7500 (68.3308) acc5: 89.0625 (88.4909) [2021-03-26 05:30:36 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.4755 (1.3721) acc1: 67.1875 (68.0640) acc5: 87.5000 (88.5120) [2021-03-26 05:30:39 swin_base_patch4_window7_224] INFO: * Acc@1 67.878 Acc@5 89.112 loss 1.354 [2021-03-26 05:30:39 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 67.9% [2021-03-26 05:30:39 swin_base_patch4_window7_224] INFO: Max accuracy: 67.88% [2021-03-26 05:30:43 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 0/1251] eta: 1:29:27 lr: 0.000972 loss: 3.7393 (3.7393) grad_norm: 1.1531 (1.1531) time: 4.2909 [2021-03-26 05:30:50 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 10/1251] eta: 0:19:59 lr: 0.000972 loss: 4.1356 (3.8469) grad_norm: 1.1413 (1.1410) time: 0.9663 [2021-03-26 05:30:56 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 20/1251] eta: 0:16:25 lr: 0.000972 loss: 4.1356 (4.0157) grad_norm: 1.0874 (1.0777) time: 0.6260 [2021-03-26 05:31:02 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 30/1251] eta: 0:15:07 lr: 0.000972 loss: 3.8345 (3.9696) grad_norm: 0.9994 (1.0659) time: 0.6203 [2021-03-26 05:31:08 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 40/1251] eta: 0:14:26 lr: 0.000972 loss: 3.8470 (3.9815) grad_norm: 1.0457 (1.0650) time: 0.6260 [2021-03-26 05:31:15 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 50/1251] eta: 0:13:58 lr: 0.000972 loss: 4.0074 (4.0006) grad_norm: 1.0585 (1.0745) time: 0.6296 [2021-03-26 05:31:21 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 60/1251] eta: 0:13:36 lr: 0.000972 loss: 4.2546 (4.0381) grad_norm: 0.9686 (1.0641) time: 0.6232 [2021-03-26 05:31:27 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 70/1251] eta: 0:13:17 lr: 0.000972 loss: 4.0202 (4.0001) grad_norm: 1.0041 (1.0596) time: 0.6173 [2021-03-26 05:31:33 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 80/1251] eta: 0:13:03 lr: 0.000972 loss: 4.0147 (4.0019) grad_norm: 1.0397 (1.0580) time: 0.6208 [2021-03-26 05:31:40 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 90/1251] eta: 0:12:52 lr: 0.000972 loss: 3.8650 (3.9850) grad_norm: 1.0203 (1.0537) time: 0.6299 [2021-03-26 05:31:46 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 100/1251] eta: 0:12:41 lr: 0.000972 loss: 3.8111 (3.9929) grad_norm: 1.0203 (1.0498) time: 0.6290 [2021-03-26 05:31:52 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 110/1251] eta: 0:12:30 lr: 0.000972 loss: 4.2040 (4.0166) grad_norm: 1.0074 (1.0452) time: 0.6230 [2021-03-26 05:31:58 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 120/1251] eta: 0:12:20 lr: 0.000972 loss: 4.2040 (4.0219) grad_norm: 1.0267 (1.0512) time: 0.6208 [2021-03-26 05:32:05 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 130/1251] eta: 0:12:12 lr: 0.000972 loss: 4.1179 (4.0166) grad_norm: 1.0974 (1.0578) time: 0.6281 [2021-03-26 05:32:11 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 140/1251] eta: 0:12:04 lr: 0.000972 loss: 4.0089 (4.0220) grad_norm: 1.0880 (1.0589) time: 0.6342 [2021-03-26 05:32:17 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 150/1251] eta: 0:11:56 lr: 0.000972 loss: 3.9998 (4.0182) grad_norm: 1.1122 (1.0628) time: 0.6321 [2021-03-26 05:32:23 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 160/1251] eta: 0:11:48 lr: 0.000972 loss: 3.8446 (4.0133) grad_norm: 1.1079 (1.0629) time: 0.6310 [2021-03-26 05:32:30 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 170/1251] eta: 0:11:39 lr: 0.000972 loss: 3.8686 (4.0162) grad_norm: 1.0392 (1.0596) time: 0.6247 [2021-03-26 05:32:36 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 180/1251] eta: 0:11:31 lr: 0.000972 loss: 3.9616 (4.0066) grad_norm: 1.0362 (1.0601) time: 0.6199 [2021-03-26 05:32:42 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 190/1251] eta: 0:11:24 lr: 0.000972 loss: 4.1243 (4.0160) grad_norm: 1.0565 (1.0689) time: 0.6228 [2021-03-26 05:32:48 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 200/1251] eta: 0:11:16 lr: 0.000972 loss: 4.2279 (4.0179) grad_norm: 1.1174 (1.0660) time: 0.6266 [2021-03-26 05:32:55 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 210/1251] eta: 0:11:10 lr: 0.000972 loss: 3.9405 (4.0022) grad_norm: 1.0375 (1.0695) time: 0.6311 [2021-03-26 05:33:01 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 220/1251] eta: 0:11:02 lr: 0.000972 loss: 3.9405 (4.0001) grad_norm: 1.0499 (1.0678) time: 0.6305 [2021-03-26 05:33:07 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 230/1251] eta: 0:10:56 lr: 0.000972 loss: 4.1713 (4.0105) grad_norm: 1.0390 (1.0634) time: 0.6308 [2021-03-26 05:33:14 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 240/1251] eta: 0:10:48 lr: 0.000972 loss: 4.3412 (4.0266) grad_norm: 0.9829 (1.0646) time: 0.6297 [2021-03-26 05:33:20 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 250/1251] eta: 0:10:41 lr: 0.000972 loss: 4.2650 (4.0342) grad_norm: 0.9797 (1.0627) time: 0.6189 [2021-03-26 05:33:26 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 260/1251] eta: 0:10:34 lr: 0.000972 loss: 4.3348 (4.0501) grad_norm: 0.9658 (1.0614) time: 0.6187 [2021-03-26 05:33:32 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 270/1251] eta: 0:10:27 lr: 0.000972 loss: 4.3644 (4.0581) grad_norm: 1.0479 (1.0647) time: 0.6231 [2021-03-26 05:33:38 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 280/1251] eta: 0:10:20 lr: 0.000972 loss: 4.4018 (4.0609) grad_norm: 1.0796 (1.0646) time: 0.6235 [2021-03-26 05:33:45 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 290/1251] eta: 0:10:12 lr: 0.000972 loss: 3.9640 (4.0533) grad_norm: 0.9827 (1.0613) time: 0.6156 [2021-03-26 05:33:51 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 300/1251] eta: 0:10:06 lr: 0.000972 loss: 3.9259 (4.0491) grad_norm: 0.9874 (1.0599) time: 0.6161 [2021-03-26 05:33:57 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 310/1251] eta: 0:09:59 lr: 0.000972 loss: 3.9277 (4.0460) grad_norm: 1.0281 (1.0595) time: 0.6222 [2021-03-26 05:34:03 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 320/1251] eta: 0:09:52 lr: 0.000972 loss: 4.0299 (4.0370) grad_norm: 1.0806 (1.0632) time: 0.6213 [2021-03-26 05:34:10 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 330/1251] eta: 0:09:45 lr: 0.000972 loss: 4.0299 (4.0340) grad_norm: 1.1020 (1.0635) time: 0.6273 [2021-03-26 05:34:16 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 340/1251] eta: 0:09:39 lr: 0.000972 loss: 4.1006 (4.0376) grad_norm: 1.0275 (1.0638) time: 0.6329 [2021-03-26 05:34:22 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 350/1251] eta: 0:09:32 lr: 0.000972 loss: 4.1112 (4.0427) grad_norm: 1.0394 (1.0638) time: 0.6274 [2021-03-26 05:34:28 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 360/1251] eta: 0:09:26 lr: 0.000972 loss: 4.1855 (4.0425) grad_norm: 1.0647 (1.0634) time: 0.6240 [2021-03-26 05:34:35 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 370/1251] eta: 0:09:19 lr: 0.000972 loss: 3.9713 (4.0363) grad_norm: 1.0647 (1.0639) time: 0.6249 [2021-03-26 05:34:41 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 380/1251] eta: 0:09:12 lr: 0.000972 loss: 3.9288 (4.0353) grad_norm: 1.0523 (1.0646) time: 0.6233 [2021-03-26 05:34:47 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 390/1251] eta: 0:09:06 lr: 0.000972 loss: 4.0194 (4.0381) grad_norm: 1.0271 (1.0630) time: 0.6201 [2021-03-26 05:34:53 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 400/1251] eta: 0:08:59 lr: 0.000972 loss: 3.9484 (4.0369) grad_norm: 0.9794 (1.0611) time: 0.6202 [2021-03-26 05:34:59 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 410/1251] eta: 0:08:52 lr: 0.000972 loss: 3.8997 (4.0318) grad_norm: 1.0123 (1.0605) time: 0.6183 [2021-03-26 05:35:06 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 420/1251] eta: 0:08:46 lr: 0.000972 loss: 4.2254 (4.0377) grad_norm: 1.0352 (1.0631) time: 0.6168 [2021-03-26 05:35:12 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 430/1251] eta: 0:08:39 lr: 0.000972 loss: 4.2864 (4.0444) grad_norm: 1.0948 (1.0641) time: 0.6245 [2021-03-26 05:35:18 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 440/1251] eta: 0:08:33 lr: 0.000972 loss: 4.2717 (4.0469) grad_norm: 1.0562 (1.0636) time: 0.6255 [2021-03-26 05:35:24 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 450/1251] eta: 0:08:26 lr: 0.000972 loss: 4.0813 (4.0508) grad_norm: 1.0069 (1.0626) time: 0.6216 [2021-03-26 05:35:31 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 460/1251] eta: 0:08:20 lr: 0.000972 loss: 4.0334 (4.0520) grad_norm: 0.9865 (1.0606) time: 0.6201 [2021-03-26 05:35:37 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 470/1251] eta: 0:08:13 lr: 0.000972 loss: 3.9904 (4.0549) grad_norm: 0.9485 (1.0583) time: 0.6207 [2021-03-26 05:35:43 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 480/1251] eta: 0:08:07 lr: 0.000972 loss: 4.1511 (4.0545) grad_norm: 0.9726 (1.0590) time: 0.6243 [2021-03-26 05:35:49 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 490/1251] eta: 0:08:00 lr: 0.000972 loss: 4.1931 (4.0597) grad_norm: 1.0053 (1.0577) time: 0.6263 [2021-03-26 05:35:55 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 500/1251] eta: 0:07:54 lr: 0.000972 loss: 4.3521 (4.0606) grad_norm: 0.9718 (1.0570) time: 0.6214 [2021-03-26 05:36:02 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 510/1251] eta: 0:07:47 lr: 0.000972 loss: 3.8538 (4.0521) grad_norm: 0.9659 (1.0551) time: 0.6170 [2021-03-26 05:36:08 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 520/1251] eta: 0:07:41 lr: 0.000972 loss: 3.7345 (4.0497) grad_norm: 1.0025 (1.0545) time: 0.6273 [2021-03-26 05:36:14 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 530/1251] eta: 0:07:35 lr: 0.000972 loss: 3.7409 (4.0451) grad_norm: 1.0967 (1.0583) time: 0.6345 [2021-03-26 05:36:21 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 540/1251] eta: 0:07:28 lr: 0.000972 loss: 3.9393 (4.0490) grad_norm: 1.1222 (1.0596) time: 0.6268 [2021-03-26 05:36:27 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 550/1251] eta: 0:07:22 lr: 0.000972 loss: 4.2463 (4.0477) grad_norm: 1.0679 (1.0595) time: 0.6354 [2021-03-26 05:36:33 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 560/1251] eta: 0:07:16 lr: 0.000972 loss: 4.1358 (4.0491) grad_norm: 1.0483 (1.0599) time: 0.6358 [2021-03-26 05:36:39 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 570/1251] eta: 0:07:09 lr: 0.000972 loss: 4.0361 (4.0502) grad_norm: 1.0680 (1.0605) time: 0.6216 [2021-03-26 05:36:46 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 580/1251] eta: 0:07:03 lr: 0.000972 loss: 4.0361 (4.0463) grad_norm: 0.9982 (1.0596) time: 0.6188 [2021-03-26 05:36:52 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 590/1251] eta: 0:06:56 lr: 0.000972 loss: 4.1164 (4.0464) grad_norm: 0.9875 (1.0591) time: 0.6199 [2021-03-26 05:36:58 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 600/1251] eta: 0:06:50 lr: 0.000972 loss: 4.0417 (4.0419) grad_norm: 1.0393 (1.0612) time: 0.6225 [2021-03-26 05:37:04 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 610/1251] eta: 0:06:44 lr: 0.000972 loss: 4.1680 (4.0465) grad_norm: 1.1332 (1.0616) time: 0.6263 [2021-03-26 05:37:11 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 620/1251] eta: 0:06:37 lr: 0.000972 loss: 4.3192 (4.0456) grad_norm: 1.0513 (1.0625) time: 0.6272 [2021-03-26 05:37:17 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 630/1251] eta: 0:06:31 lr: 0.000972 loss: 4.0662 (4.0453) grad_norm: 1.0513 (1.0623) time: 0.6254 [2021-03-26 05:37:23 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 640/1251] eta: 0:06:25 lr: 0.000972 loss: 4.0662 (4.0474) grad_norm: 1.0537 (1.0624) time: 0.6261 [2021-03-26 05:37:29 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 650/1251] eta: 0:06:18 lr: 0.000972 loss: 3.9126 (4.0431) grad_norm: 1.0452 (1.0632) time: 0.6235 [2021-03-26 05:37:36 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 660/1251] eta: 0:06:12 lr: 0.000972 loss: 3.7574 (4.0392) grad_norm: 1.0493 (1.0629) time: 0.6281 [2021-03-26 05:37:42 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 670/1251] eta: 0:06:06 lr: 0.000972 loss: 4.0311 (4.0381) grad_norm: 0.9962 (1.0612) time: 0.6283 [2021-03-26 05:37:48 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 680/1251] eta: 0:05:59 lr: 0.000972 loss: 4.0265 (4.0353) grad_norm: 1.0214 (1.0623) time: 0.6222 [2021-03-26 05:37:54 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 690/1251] eta: 0:05:53 lr: 0.000972 loss: 4.1434 (4.0401) grad_norm: 1.1041 (1.0632) time: 0.6205 [2021-03-26 05:38:01 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 700/1251] eta: 0:05:47 lr: 0.000972 loss: 4.2251 (4.0410) grad_norm: 1.0534 (1.0634) time: 0.6260 [2021-03-26 05:38:07 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 710/1251] eta: 0:05:40 lr: 0.000971 loss: 3.9399 (4.0375) grad_norm: 1.0204 (1.0638) time: 0.6251 [2021-03-26 05:38:13 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 720/1251] eta: 0:05:34 lr: 0.000971 loss: 3.9399 (4.0380) grad_norm: 1.0638 (1.0639) time: 0.6257 [2021-03-26 05:38:19 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 730/1251] eta: 0:05:28 lr: 0.000971 loss: 4.1857 (4.0368) grad_norm: 1.0747 (1.0634) time: 0.6250 [2021-03-26 05:38:26 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 740/1251] eta: 0:05:21 lr: 0.000971 loss: 3.9789 (4.0351) grad_norm: 1.0471 (1.0634) time: 0.6222 [2021-03-26 05:38:32 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 750/1251] eta: 0:05:15 lr: 0.000971 loss: 3.9479 (4.0342) grad_norm: 0.9529 (1.0632) time: 0.6315 [2021-03-26 05:38:38 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 760/1251] eta: 0:05:09 lr: 0.000971 loss: 3.9797 (4.0319) grad_norm: 0.9756 (1.0636) time: 0.6276 [2021-03-26 05:38:44 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 770/1251] eta: 0:05:02 lr: 0.000971 loss: 4.0356 (4.0303) grad_norm: 1.0630 (1.0646) time: 0.6217 [2021-03-26 05:38:51 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 780/1251] eta: 0:04:56 lr: 0.000971 loss: 4.1181 (4.0322) grad_norm: 1.0363 (1.0641) time: 0.6243 [2021-03-26 05:38:57 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 790/1251] eta: 0:04:50 lr: 0.000971 loss: 4.0522 (4.0297) grad_norm: 1.0284 (1.0648) time: 0.6266 [2021-03-26 05:39:03 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 800/1251] eta: 0:04:43 lr: 0.000971 loss: 3.7363 (4.0264) grad_norm: 1.0284 (1.0644) time: 0.6224 [2021-03-26 05:39:09 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 810/1251] eta: 0:04:37 lr: 0.000971 loss: 3.8185 (4.0245) grad_norm: 0.9831 (1.0644) time: 0.6180 [2021-03-26 05:39:16 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 820/1251] eta: 0:04:31 lr: 0.000971 loss: 3.9326 (4.0219) grad_norm: 1.0019 (1.0640) time: 0.6210 [2021-03-26 05:39:22 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 830/1251] eta: 0:04:24 lr: 0.000971 loss: 4.0558 (4.0254) grad_norm: 0.9963 (1.0632) time: 0.6189 [2021-03-26 05:39:28 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 840/1251] eta: 0:04:18 lr: 0.000971 loss: 4.3508 (4.0261) grad_norm: 1.0062 (1.0628) time: 0.6202 [2021-03-26 05:39:34 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 850/1251] eta: 0:04:12 lr: 0.000971 loss: 4.1663 (4.0265) grad_norm: 1.0836 (1.0633) time: 0.6312 [2021-03-26 05:39:41 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 860/1251] eta: 0:04:05 lr: 0.000971 loss: 3.8786 (4.0230) grad_norm: 1.0836 (1.0640) time: 0.6395 [2021-03-26 05:39:47 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 870/1251] eta: 0:03:59 lr: 0.000971 loss: 4.0440 (4.0253) grad_norm: 1.0525 (1.0638) time: 0.6339 [2021-03-26 05:39:53 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 880/1251] eta: 0:03:53 lr: 0.000971 loss: 4.1714 (4.0221) grad_norm: 1.0935 (1.0647) time: 0.6239 [2021-03-26 05:40:00 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 890/1251] eta: 0:03:47 lr: 0.000971 loss: 3.8414 (4.0212) grad_norm: 1.0829 (1.0643) time: 0.6286 [2021-03-26 05:40:06 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 900/1251] eta: 0:03:40 lr: 0.000971 loss: 3.7849 (4.0196) grad_norm: 0.9845 (1.0641) time: 0.6235 [2021-03-26 05:40:12 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 910/1251] eta: 0:03:34 lr: 0.000971 loss: 3.7671 (4.0177) grad_norm: 1.0137 (1.0635) time: 0.6155 [2021-03-26 05:40:18 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 920/1251] eta: 0:03:28 lr: 0.000971 loss: 3.8203 (4.0165) grad_norm: 0.9860 (1.0629) time: 0.6168 [2021-03-26 05:40:24 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 930/1251] eta: 0:03:21 lr: 0.000971 loss: 3.9172 (4.0162) grad_norm: 0.9860 (1.0624) time: 0.6188 [2021-03-26 05:40:30 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 940/1251] eta: 0:03:15 lr: 0.000971 loss: 3.9172 (4.0169) grad_norm: 0.9805 (1.0618) time: 0.6170 [2021-03-26 05:40:37 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 950/1251] eta: 0:03:09 lr: 0.000971 loss: 4.1551 (4.0174) grad_norm: 0.9591 (1.0606) time: 0.6146 [2021-03-26 05:40:43 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 960/1251] eta: 0:03:02 lr: 0.000971 loss: 4.1741 (4.0193) grad_norm: 0.9397 (1.0600) time: 0.6267 [2021-03-26 05:40:49 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 970/1251] eta: 0:02:56 lr: 0.000971 loss: 4.1741 (4.0185) grad_norm: 0.9973 (1.0598) time: 0.6327 [2021-03-26 05:40:55 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 980/1251] eta: 0:02:50 lr: 0.000971 loss: 4.2573 (4.0208) grad_norm: 0.9973 (1.0596) time: 0.6236 [2021-03-26 05:41:02 swin_base_patch4_window7_224] INFO: Epoch: [32] [ 990/1251] eta: 0:02:43 lr: 0.000971 loss: 4.1527 (4.0212) grad_norm: 1.0212 (1.0600) time: 0.6227 [2021-03-26 05:41:08 swin_base_patch4_window7_224] INFO: Epoch: [32] [1000/1251] eta: 0:02:37 lr: 0.000971 loss: 4.0932 (4.0228) grad_norm: 1.1179 (1.0607) time: 0.6292 [2021-03-26 05:41:14 swin_base_patch4_window7_224] INFO: Epoch: [32] [1010/1251] eta: 0:02:31 lr: 0.000971 loss: 4.0796 (4.0217) grad_norm: 1.0434 (1.0609) time: 0.6231 [2021-03-26 05:41:20 swin_base_patch4_window7_224] INFO: Epoch: [32] [1020/1251] eta: 0:02:25 lr: 0.000971 loss: 4.0158 (4.0219) grad_norm: 0.9677 (1.0607) time: 0.6155 [2021-03-26 05:41:27 swin_base_patch4_window7_224] INFO: Epoch: [32] [1030/1251] eta: 0:02:18 lr: 0.000971 loss: 3.9766 (4.0220) grad_norm: 0.9847 (1.0603) time: 0.6191 [2021-03-26 05:41:33 swin_base_patch4_window7_224] INFO: Epoch: [32] [1040/1251] eta: 0:02:12 lr: 0.000971 loss: 4.0329 (4.0230) grad_norm: 1.0162 (1.0602) time: 0.6242 [2021-03-26 05:41:39 swin_base_patch4_window7_224] INFO: Epoch: [32] [1050/1251] eta: 0:02:06 lr: 0.000971 loss: 4.0897 (4.0247) grad_norm: 1.0162 (1.0603) time: 0.6235 [2021-03-26 05:41:45 swin_base_patch4_window7_224] INFO: Epoch: [32] [1060/1251] eta: 0:01:59 lr: 0.000971 loss: 4.2662 (4.0259) grad_norm: 0.9560 (1.0599) time: 0.6172 [2021-03-26 05:41:51 swin_base_patch4_window7_224] INFO: Epoch: [32] [1070/1251] eta: 0:01:53 lr: 0.000971 loss: 4.0970 (4.0269) grad_norm: 0.9560 (1.0592) time: 0.6139 [2021-03-26 05:41:58 swin_base_patch4_window7_224] INFO: Epoch: [32] [1080/1251] eta: 0:01:47 lr: 0.000971 loss: 4.0970 (4.0280) grad_norm: 0.9677 (1.0589) time: 0.6195 [2021-03-26 05:42:04 swin_base_patch4_window7_224] INFO: Epoch: [32] [1090/1251] eta: 0:01:41 lr: 0.000971 loss: 4.4155 (4.0294) grad_norm: 1.0655 (1.0589) time: 0.6299 [2021-03-26 05:42:10 swin_base_patch4_window7_224] INFO: Epoch: [32] [1100/1251] eta: 0:01:34 lr: 0.000971 loss: 4.4155 (4.0314) grad_norm: 1.0263 (1.0590) time: 0.6345 [2021-03-26 05:42:16 swin_base_patch4_window7_224] INFO: Epoch: [32] [1110/1251] eta: 0:01:28 lr: 0.000971 loss: 4.4552 (4.0348) grad_norm: 0.9952 (1.0584) time: 0.6254 [2021-03-26 05:42:23 swin_base_patch4_window7_224] INFO: Epoch: [32] [1120/1251] eta: 0:01:22 lr: 0.000971 loss: 4.3381 (4.0358) grad_norm: 0.9684 (1.0578) time: 0.6155 [2021-03-26 05:42:29 swin_base_patch4_window7_224] INFO: Epoch: [32] [1130/1251] eta: 0:01:15 lr: 0.000971 loss: 4.1275 (4.0340) grad_norm: 0.9961 (1.0577) time: 0.6175 [2021-03-26 05:42:35 swin_base_patch4_window7_224] INFO: Epoch: [32] [1140/1251] eta: 0:01:09 lr: 0.000971 loss: 4.0589 (4.0331) grad_norm: 1.0244 (1.0580) time: 0.6225 [2021-03-26 05:42:41 swin_base_patch4_window7_224] INFO: Epoch: [32] [1150/1251] eta: 0:01:03 lr: 0.000971 loss: 4.0589 (4.0333) grad_norm: 1.0513 (1.0580) time: 0.6247 [2021-03-26 05:42:48 swin_base_patch4_window7_224] INFO: Epoch: [32] [1160/1251] eta: 0:00:57 lr: 0.000971 loss: 4.0918 (4.0331) grad_norm: 1.0821 (1.0587) time: 0.6277 [2021-03-26 05:42:54 swin_base_patch4_window7_224] INFO: Epoch: [32] [1170/1251] eta: 0:00:50 lr: 0.000971 loss: 4.0918 (4.0325) grad_norm: 1.0576 (1.0583) time: 0.6237 [2021-03-26 05:43:00 swin_base_patch4_window7_224] INFO: Epoch: [32] [1180/1251] eta: 0:00:44 lr: 0.000971 loss: 3.9788 (4.0324) grad_norm: 1.0270 (1.0584) time: 0.6235 [2021-03-26 05:43:06 swin_base_patch4_window7_224] INFO: Epoch: [32] [1190/1251] eta: 0:00:38 lr: 0.000971 loss: 3.9220 (4.0314) grad_norm: 1.0718 (1.0588) time: 0.6246 [2021-03-26 05:43:12 swin_base_patch4_window7_224] INFO: Epoch: [32] [1200/1251] eta: 0:00:31 lr: 0.000971 loss: 3.8903 (4.0300) grad_norm: 1.0584 (1.0582) time: 0.6198 [2021-03-26 05:43:19 swin_base_patch4_window7_224] INFO: Epoch: [32] [1210/1251] eta: 0:00:25 lr: 0.000971 loss: 3.8111 (4.0272) grad_norm: 0.9856 (1.0583) time: 0.6233 [2021-03-26 05:43:25 swin_base_patch4_window7_224] INFO: Epoch: [32] [1220/1251] eta: 0:00:19 lr: 0.000971 loss: 3.8595 (4.0280) grad_norm: 1.0033 (1.0579) time: 0.6280 [2021-03-26 05:43:31 swin_base_patch4_window7_224] INFO: Epoch: [32] [1230/1251] eta: 0:00:13 lr: 0.000971 loss: 4.1165 (4.0265) grad_norm: 0.9505 (1.0575) time: 0.6251 [2021-03-26 05:43:37 swin_base_patch4_window7_224] INFO: Epoch: [32] [1240/1251] eta: 0:00:06 lr: 0.000971 loss: 4.0275 (4.0263) grad_norm: 1.0010 (1.0577) time: 0.6161 [2021-03-26 05:43:43 swin_base_patch4_window7_224] INFO: Epoch: [32] [1250/1251] eta: 0:00:00 lr: 0.000971 loss: 4.0300 (4.0277) grad_norm: 1.0323 (1.0582) time: 0.6088 [2021-03-26 05:43:48 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:17 loss: 1.4107 (1.4107) acc1: 73.4375 (73.4375) acc5: 87.5000 (87.5000) [2021-03-26 05:43:50 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.3563 (1.3633) acc1: 68.7500 (69.6023) acc5: 89.0625 (89.0625) [2021-03-26 05:43:53 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.3915 (1.3674) acc1: 67.1875 (68.8244) acc5: 89.0625 (89.0625) [2021-03-26 05:43:54 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.3915 (1.3643) acc1: 67.1875 (69.2540) acc5: 89.0625 (89.2137) [2021-03-26 05:43:56 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.3483 (1.3900) acc1: 67.1875 (68.5213) acc5: 89.0625 (89.1768) [2021-03-26 05:43:57 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.4594 (1.4036) acc1: 65.6250 (68.0320) acc5: 89.0625 (89.1520) [2021-03-26 05:44:00 swin_base_patch4_window7_224] INFO: * Acc@1 68.066 Acc@5 89.372 loss 1.394 [2021-03-26 05:44:00 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 68.1% [2021-03-26 05:44:00 swin_base_patch4_window7_224] INFO: Max accuracy: 68.07% [2021-03-26 05:44:05 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 0/1251] eta: 1:33:11 lr: 0.000971 loss: 4.4211 (4.4211) grad_norm: 1.2739 (1.2739) time: 4.4695 [2021-03-26 05:44:11 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 10/1251] eta: 0:20:07 lr: 0.000971 loss: 4.2909 (4.1395) grad_norm: 1.0121 (1.0148) time: 0.9732 [2021-03-26 05:44:17 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 20/1251] eta: 0:16:35 lr: 0.000971 loss: 4.2253 (4.1055) grad_norm: 1.0146 (1.0378) time: 0.6260 [2021-03-26 05:44:23 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 30/1251] eta: 0:15:13 lr: 0.000971 loss: 4.0508 (4.0331) grad_norm: 0.9720 (1.0073) time: 0.6244 [2021-03-26 05:44:30 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 40/1251] eta: 0:14:29 lr: 0.000971 loss: 3.9563 (3.9757) grad_norm: 0.9307 (1.0060) time: 0.6216 [2021-03-26 05:44:36 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 50/1251] eta: 0:14:01 lr: 0.000971 loss: 3.9563 (3.9728) grad_norm: 1.0302 (1.0258) time: 0.6270 [2021-03-26 05:44:42 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 60/1251] eta: 0:13:39 lr: 0.000971 loss: 4.0925 (3.9297) grad_norm: 1.0902 (1.0319) time: 0.6286 [2021-03-26 05:44:48 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 70/1251] eta: 0:13:21 lr: 0.000971 loss: 3.7579 (3.9348) grad_norm: 1.0236 (1.0307) time: 0.6221 [2021-03-26 05:44:55 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 80/1251] eta: 0:13:06 lr: 0.000971 loss: 4.2489 (3.9659) grad_norm: 1.0756 (1.0355) time: 0.6199 [2021-03-26 05:45:01 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 90/1251] eta: 0:12:53 lr: 0.000971 loss: 4.2489 (3.9734) grad_norm: 0.9880 (1.0274) time: 0.6212 [2021-03-26 05:45:07 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 100/1251] eta: 0:12:42 lr: 0.000971 loss: 4.1254 (3.9881) grad_norm: 0.9867 (1.0358) time: 0.6249 [2021-03-26 05:45:13 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 110/1251] eta: 0:12:32 lr: 0.000971 loss: 4.0444 (3.9996) grad_norm: 1.0408 (1.0371) time: 0.6290 [2021-03-26 05:45:20 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 120/1251] eta: 0:12:22 lr: 0.000971 loss: 4.0945 (4.0034) grad_norm: 1.0408 (1.0396) time: 0.6258 [2021-03-26 05:45:26 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 130/1251] eta: 0:12:13 lr: 0.000971 loss: 4.0945 (4.0088) grad_norm: 1.0551 (1.0487) time: 0.6289 [2021-03-26 05:45:32 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 140/1251] eta: 0:12:05 lr: 0.000971 loss: 3.8719 (3.9955) grad_norm: 1.0309 (1.0468) time: 0.6338 [2021-03-26 05:45:39 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 150/1251] eta: 0:11:57 lr: 0.000971 loss: 3.9226 (3.9934) grad_norm: 1.0109 (1.0484) time: 0.6303 [2021-03-26 05:45:45 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 160/1251] eta: 0:11:49 lr: 0.000971 loss: 4.1958 (4.0023) grad_norm: 1.0948 (1.0495) time: 0.6340 [2021-03-26 05:45:51 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 170/1251] eta: 0:11:41 lr: 0.000970 loss: 4.2892 (4.0011) grad_norm: 1.0300 (1.0503) time: 0.6278 [2021-03-26 05:45:57 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 180/1251] eta: 0:11:33 lr: 0.000970 loss: 4.0045 (3.9847) grad_norm: 1.0090 (1.0510) time: 0.6195 [2021-03-26 05:46:04 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 190/1251] eta: 0:11:25 lr: 0.000970 loss: 3.8462 (3.9760) grad_norm: 0.9914 (1.0519) time: 0.6230 [2021-03-26 05:46:10 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 200/1251] eta: 0:11:17 lr: 0.000970 loss: 3.9939 (3.9800) grad_norm: 1.0064 (1.0545) time: 0.6210 [2021-03-26 05:46:16 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 210/1251] eta: 0:11:09 lr: 0.000970 loss: 4.0076 (3.9785) grad_norm: 1.0064 (1.0518) time: 0.6195 [2021-03-26 05:46:22 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 220/1251] eta: 0:11:02 lr: 0.000970 loss: 3.8806 (3.9601) grad_norm: 0.9723 (1.0517) time: 0.6183 [2021-03-26 05:46:28 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 230/1251] eta: 0:10:55 lr: 0.000970 loss: 4.0332 (3.9695) grad_norm: 1.0589 (1.0523) time: 0.6237 [2021-03-26 05:46:35 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 240/1251] eta: 0:10:48 lr: 0.000970 loss: 4.2311 (3.9694) grad_norm: 1.0769 (1.0541) time: 0.6273 [2021-03-26 05:46:41 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 250/1251] eta: 0:10:40 lr: 0.000970 loss: 4.1935 (3.9702) grad_norm: 1.0769 (1.0564) time: 0.6239 [2021-03-26 05:46:47 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 260/1251] eta: 0:10:33 lr: 0.000970 loss: 3.9278 (3.9651) grad_norm: 1.0349 (1.0554) time: 0.6239 [2021-03-26 05:46:53 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 270/1251] eta: 0:10:27 lr: 0.000970 loss: 3.9089 (3.9618) grad_norm: 1.0182 (1.0554) time: 0.6273 [2021-03-26 05:47:00 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 280/1251] eta: 0:10:20 lr: 0.000970 loss: 4.2774 (3.9742) grad_norm: 0.9969 (1.0555) time: 0.6248 [2021-03-26 05:47:06 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 290/1251] eta: 0:10:13 lr: 0.000970 loss: 4.1804 (3.9758) grad_norm: 1.0374 (1.0575) time: 0.6227 [2021-03-26 05:47:12 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 300/1251] eta: 0:10:06 lr: 0.000970 loss: 4.0951 (3.9845) grad_norm: 1.0643 (1.0589) time: 0.6241 [2021-03-26 05:47:18 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 310/1251] eta: 0:09:59 lr: 0.000970 loss: 4.1144 (3.9818) grad_norm: 1.0156 (1.0578) time: 0.6204 [2021-03-26 05:47:25 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 320/1251] eta: 0:09:52 lr: 0.000970 loss: 4.0793 (3.9827) grad_norm: 0.9952 (1.0596) time: 0.6207 [2021-03-26 05:47:31 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 330/1251] eta: 0:09:46 lr: 0.000970 loss: 3.8155 (3.9725) grad_norm: 1.1328 (1.0616) time: 0.6259 [2021-03-26 05:47:37 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 340/1251] eta: 0:09:39 lr: 0.000970 loss: 3.9390 (3.9747) grad_norm: 1.0650 (1.0608) time: 0.6313 [2021-03-26 05:47:43 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 350/1251] eta: 0:09:33 lr: 0.000970 loss: 4.0736 (3.9755) grad_norm: 1.0037 (1.0579) time: 0.6293 [2021-03-26 05:47:50 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 360/1251] eta: 0:09:26 lr: 0.000970 loss: 3.5449 (3.9645) grad_norm: 1.0429 (1.0611) time: 0.6229 [2021-03-26 05:47:56 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 370/1251] eta: 0:09:19 lr: 0.000970 loss: 3.6170 (3.9624) grad_norm: 1.0898 (1.0622) time: 0.6202 [2021-03-26 05:48:02 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 380/1251] eta: 0:09:12 lr: 0.000970 loss: 4.0934 (3.9640) grad_norm: 1.0311 (1.0599) time: 0.6224 [2021-03-26 05:48:08 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 390/1251] eta: 0:09:06 lr: 0.000970 loss: 4.2717 (3.9667) grad_norm: 0.9846 (1.0590) time: 0.6258 [2021-03-26 05:48:15 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 400/1251] eta: 0:08:59 lr: 0.000970 loss: 4.0452 (3.9631) grad_norm: 0.9558 (1.0562) time: 0.6206 [2021-03-26 05:48:21 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 410/1251] eta: 0:08:53 lr: 0.000970 loss: 3.9266 (3.9638) grad_norm: 0.9625 (1.0565) time: 0.6207 [2021-03-26 05:48:27 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 420/1251] eta: 0:08:46 lr: 0.000970 loss: 3.7271 (3.9573) grad_norm: 1.0380 (inf) time: 0.6207 [2021-03-26 05:48:33 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 430/1251] eta: 0:08:39 lr: 0.000970 loss: 3.6866 (3.9572) grad_norm: 1.0552 (inf) time: 0.6184 [2021-03-26 05:48:39 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 440/1251] eta: 0:08:33 lr: 0.000970 loss: 3.7885 (3.9536) grad_norm: 1.0576 (inf) time: 0.6234 [2021-03-26 05:48:46 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 450/1251] eta: 0:08:26 lr: 0.000970 loss: 3.8706 (3.9536) grad_norm: 0.9996 (inf) time: 0.6256 [2021-03-26 05:48:52 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 460/1251] eta: 0:08:20 lr: 0.000970 loss: 4.0716 (3.9534) grad_norm: 0.9639 (inf) time: 0.6234 [2021-03-26 05:48:58 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 470/1251] eta: 0:08:13 lr: 0.000970 loss: 3.9697 (3.9474) grad_norm: 0.9862 (inf) time: 0.6218 [2021-03-26 05:49:04 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 480/1251] eta: 0:08:07 lr: 0.000970 loss: 3.9873 (3.9526) grad_norm: 1.0020 (inf) time: 0.6199 [2021-03-26 05:49:10 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 490/1251] eta: 0:08:00 lr: 0.000970 loss: 3.9252 (3.9470) grad_norm: 0.9371 (inf) time: 0.6112 [2021-03-26 05:49:17 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 500/1251] eta: 0:07:54 lr: 0.000970 loss: 4.0404 (3.9486) grad_norm: 0.9777 (inf) time: 0.6152 [2021-03-26 05:49:23 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 510/1251] eta: 0:07:47 lr: 0.000970 loss: 4.0610 (3.9508) grad_norm: 1.0214 (inf) time: 0.6231 [2021-03-26 05:49:29 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 520/1251] eta: 0:07:41 lr: 0.000970 loss: 3.9930 (3.9521) grad_norm: 0.9948 (inf) time: 0.6185 [2021-03-26 05:49:35 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 530/1251] eta: 0:07:34 lr: 0.000970 loss: 4.1158 (3.9546) grad_norm: 1.0363 (inf) time: 0.6217 [2021-03-26 05:49:41 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 540/1251] eta: 0:07:28 lr: 0.000970 loss: 3.9434 (3.9510) grad_norm: 1.0777 (inf) time: 0.6259 [2021-03-26 05:49:48 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 550/1251] eta: 0:07:22 lr: 0.000970 loss: 3.7225 (3.9472) grad_norm: 0.9721 (inf) time: 0.6352 [2021-03-26 05:49:54 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 560/1251] eta: 0:07:15 lr: 0.000970 loss: 3.6031 (3.9430) grad_norm: 0.9866 (inf) time: 0.6363 [2021-03-26 05:50:01 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 570/1251] eta: 0:07:09 lr: 0.000970 loss: 3.8497 (3.9440) grad_norm: 1.0846 (inf) time: 0.6302 [2021-03-26 05:50:07 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 580/1251] eta: 0:07:03 lr: 0.000970 loss: 3.9649 (3.9407) grad_norm: 0.9841 (inf) time: 0.6251 [2021-03-26 05:50:13 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 590/1251] eta: 0:06:56 lr: 0.000970 loss: 3.9498 (3.9424) grad_norm: 0.9841 (inf) time: 0.6217 [2021-03-26 05:50:19 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 600/1251] eta: 0:06:50 lr: 0.000970 loss: 3.9606 (3.9447) grad_norm: 1.0784 (inf) time: 0.6260 [2021-03-26 05:50:25 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 610/1251] eta: 0:06:44 lr: 0.000970 loss: 4.1152 (3.9454) grad_norm: 1.0007 (inf) time: 0.6226 [2021-03-26 05:50:32 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 620/1251] eta: 0:06:37 lr: 0.000970 loss: 4.1152 (3.9462) grad_norm: 0.9803 (inf) time: 0.6188 [2021-03-26 05:50:38 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 630/1251] eta: 0:06:31 lr: 0.000970 loss: 4.2993 (3.9522) grad_norm: 0.9792 (inf) time: 0.6210 [2021-03-26 05:50:44 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 640/1251] eta: 0:06:25 lr: 0.000970 loss: 4.0707 (3.9480) grad_norm: 1.0057 (inf) time: 0.6294 [2021-03-26 05:50:50 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 650/1251] eta: 0:06:18 lr: 0.000970 loss: 3.7626 (3.9475) grad_norm: 0.9703 (inf) time: 0.6247 [2021-03-26 05:50:57 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 660/1251] eta: 0:06:12 lr: 0.000970 loss: 4.2296 (3.9502) grad_norm: 0.9990 (inf) time: 0.6207 [2021-03-26 05:51:03 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 670/1251] eta: 0:06:05 lr: 0.000970 loss: 4.2881 (3.9566) grad_norm: 1.0793 (inf) time: 0.6224 [2021-03-26 05:51:09 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 680/1251] eta: 0:05:59 lr: 0.000970 loss: 4.4073 (3.9615) grad_norm: 1.0321 (inf) time: 0.6224 [2021-03-26 05:51:15 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 690/1251] eta: 0:05:53 lr: 0.000970 loss: 4.1295 (3.9597) grad_norm: 0.9951 (inf) time: 0.6204 [2021-03-26 05:51:22 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 700/1251] eta: 0:05:46 lr: 0.000970 loss: 4.1616 (3.9628) grad_norm: 1.0199 (inf) time: 0.6264 [2021-03-26 05:51:28 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 710/1251] eta: 0:05:40 lr: 0.000970 loss: 4.3306 (3.9669) grad_norm: 1.0001 (inf) time: 0.6286 [2021-03-26 05:51:34 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 720/1251] eta: 0:05:34 lr: 0.000970 loss: 4.2887 (3.9684) grad_norm: 0.9485 (inf) time: 0.6213 [2021-03-26 05:51:40 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 730/1251] eta: 0:05:27 lr: 0.000970 loss: 3.9563 (3.9694) grad_norm: 0.9590 (inf) time: 0.6241 [2021-03-26 05:51:47 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 740/1251] eta: 0:05:21 lr: 0.000970 loss: 3.9563 (3.9675) grad_norm: 1.0608 (inf) time: 0.6371 [2021-03-26 05:51:53 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 750/1251] eta: 0:05:15 lr: 0.000970 loss: 4.1135 (3.9694) grad_norm: 1.0310 (inf) time: 0.6355 [2021-03-26 05:51:59 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 760/1251] eta: 0:05:09 lr: 0.000970 loss: 4.1954 (3.9717) grad_norm: 0.9780 (inf) time: 0.6235 [2021-03-26 05:52:05 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 770/1251] eta: 0:05:02 lr: 0.000970 loss: 4.0706 (3.9731) grad_norm: 0.9752 (inf) time: 0.6203 [2021-03-26 05:52:12 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 780/1251] eta: 0:04:56 lr: 0.000970 loss: 4.0198 (3.9753) grad_norm: 0.9661 (inf) time: 0.6235 [2021-03-26 05:52:18 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 790/1251] eta: 0:04:49 lr: 0.000970 loss: 4.4078 (3.9781) grad_norm: 0.9558 (inf) time: 0.6222 [2021-03-26 05:52:24 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 800/1251] eta: 0:04:43 lr: 0.000970 loss: 4.0621 (3.9756) grad_norm: 0.9558 (inf) time: 0.6209 [2021-03-26 05:52:30 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 810/1251] eta: 0:04:37 lr: 0.000970 loss: 3.9746 (3.9754) grad_norm: 1.0076 (inf) time: 0.6280 [2021-03-26 05:52:37 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 820/1251] eta: 0:04:31 lr: 0.000970 loss: 3.9746 (3.9752) grad_norm: 1.0300 (inf) time: 0.6270 [2021-03-26 05:52:43 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 830/1251] eta: 0:04:24 lr: 0.000970 loss: 3.9984 (3.9745) grad_norm: 1.0383 (inf) time: 0.6330 [2021-03-26 05:52:49 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 840/1251] eta: 0:04:18 lr: 0.000970 loss: 4.0345 (3.9774) grad_norm: 1.0892 (inf) time: 0.6315 [2021-03-26 05:52:56 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 850/1251] eta: 0:04:12 lr: 0.000970 loss: 4.1063 (3.9757) grad_norm: 1.0711 (inf) time: 0.6244 [2021-03-26 05:53:02 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 860/1251] eta: 0:04:05 lr: 0.000970 loss: 4.0797 (3.9777) grad_norm: 1.0312 (inf) time: 0.6208 [2021-03-26 05:53:08 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 870/1251] eta: 0:03:59 lr: 0.000970 loss: 3.8622 (3.9757) grad_norm: 0.9542 (inf) time: 0.6184 [2021-03-26 05:53:14 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 880/1251] eta: 0:03:53 lr: 0.000969 loss: 3.7932 (3.9729) grad_norm: 1.0015 (inf) time: 0.6228 [2021-03-26 05:53:20 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 890/1251] eta: 0:03:46 lr: 0.000969 loss: 4.0971 (3.9742) grad_norm: 1.0340 (inf) time: 0.6249 [2021-03-26 05:53:27 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 900/1251] eta: 0:03:40 lr: 0.000969 loss: 4.2148 (3.9759) grad_norm: 1.0231 (inf) time: 0.6249 [2021-03-26 05:53:33 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 910/1251] eta: 0:03:34 lr: 0.000969 loss: 4.1586 (3.9767) grad_norm: 1.0219 (inf) time: 0.6230 [2021-03-26 05:53:39 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 920/1251] eta: 0:03:28 lr: 0.000969 loss: 4.1586 (3.9795) grad_norm: 0.9973 (inf) time: 0.6191 [2021-03-26 05:53:45 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 930/1251] eta: 0:03:21 lr: 0.000969 loss: 4.0759 (3.9797) grad_norm: 0.9425 (inf) time: 0.6216 [2021-03-26 05:53:52 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 940/1251] eta: 0:03:15 lr: 0.000969 loss: 4.0748 (3.9816) grad_norm: 0.9629 (inf) time: 0.6210 [2021-03-26 05:53:58 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 950/1251] eta: 0:03:09 lr: 0.000969 loss: 4.1868 (3.9832) grad_norm: 1.0057 (inf) time: 0.6223 [2021-03-26 05:54:04 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 960/1251] eta: 0:03:02 lr: 0.000969 loss: 4.1868 (3.9827) grad_norm: 1.0639 (inf) time: 0.6314 [2021-03-26 05:54:10 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 970/1251] eta: 0:02:56 lr: 0.000969 loss: 4.0810 (3.9843) grad_norm: 1.0689 (inf) time: 0.6336 [2021-03-26 05:54:17 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 980/1251] eta: 0:02:50 lr: 0.000969 loss: 4.2237 (3.9866) grad_norm: 1.0365 (inf) time: 0.6234 [2021-03-26 05:54:23 swin_base_patch4_window7_224] INFO: Epoch: [33] [ 990/1251] eta: 0:02:43 lr: 0.000969 loss: 3.9627 (3.9842) grad_norm: 1.0365 (inf) time: 0.6178 [2021-03-26 05:54:29 swin_base_patch4_window7_224] INFO: Epoch: [33] [1000/1251] eta: 0:02:37 lr: 0.000969 loss: 3.8671 (3.9839) grad_norm: 1.0297 (inf) time: 0.6222 [2021-03-26 05:54:35 swin_base_patch4_window7_224] INFO: Epoch: [33] [1010/1251] eta: 0:02:31 lr: 0.000969 loss: 3.8671 (3.9815) grad_norm: 1.0469 (inf) time: 0.6239 [2021-03-26 05:54:42 swin_base_patch4_window7_224] INFO: Epoch: [33] [1020/1251] eta: 0:02:25 lr: 0.000969 loss: 4.0306 (3.9836) grad_norm: 1.0734 (inf) time: 0.6313 [2021-03-26 05:54:48 swin_base_patch4_window7_224] INFO: Epoch: [33] [1030/1251] eta: 0:02:18 lr: 0.000969 loss: 4.1742 (3.9845) grad_norm: 1.0265 (inf) time: 0.6266 [2021-03-26 05:54:54 swin_base_patch4_window7_224] INFO: Epoch: [33] [1040/1251] eta: 0:02:12 lr: 0.000969 loss: 4.2149 (3.9862) grad_norm: 1.0048 (inf) time: 0.6193 [2021-03-26 05:55:00 swin_base_patch4_window7_224] INFO: Epoch: [33] [1050/1251] eta: 0:02:06 lr: 0.000969 loss: 4.2149 (3.9874) grad_norm: 1.0315 (inf) time: 0.6288 [2021-03-26 05:55:07 swin_base_patch4_window7_224] INFO: Epoch: [33] [1060/1251] eta: 0:01:59 lr: 0.000969 loss: 4.1983 (3.9880) grad_norm: 1.0046 (inf) time: 0.6327 [2021-03-26 05:55:13 swin_base_patch4_window7_224] INFO: Epoch: [33] [1070/1251] eta: 0:01:53 lr: 0.000969 loss: 4.0665 (3.9867) grad_norm: 0.9533 (inf) time: 0.6231 [2021-03-26 05:55:19 swin_base_patch4_window7_224] INFO: Epoch: [33] [1080/1251] eta: 0:01:47 lr: 0.000969 loss: 4.0763 (3.9866) grad_norm: 0.9393 (inf) time: 0.6215 [2021-03-26 05:55:25 swin_base_patch4_window7_224] INFO: Epoch: [33] [1090/1251] eta: 0:01:41 lr: 0.000969 loss: 4.0701 (3.9852) grad_norm: 0.9857 (inf) time: 0.6245 [2021-03-26 05:55:32 swin_base_patch4_window7_224] INFO: Epoch: [33] [1100/1251] eta: 0:01:34 lr: 0.000969 loss: 3.8086 (3.9831) grad_norm: 1.0121 (inf) time: 0.6228 [2021-03-26 05:55:38 swin_base_patch4_window7_224] INFO: Epoch: [33] [1110/1251] eta: 0:01:28 lr: 0.000969 loss: 4.0869 (3.9850) grad_norm: 1.0826 (inf) time: 0.6249 [2021-03-26 05:55:44 swin_base_patch4_window7_224] INFO: Epoch: [33] [1120/1251] eta: 0:01:22 lr: 0.000969 loss: 4.2062 (3.9866) grad_norm: 1.1025 (inf) time: 0.6322 [2021-03-26 05:55:51 swin_base_patch4_window7_224] INFO: Epoch: [33] [1130/1251] eta: 0:01:15 lr: 0.000969 loss: 4.0800 (3.9863) grad_norm: 1.1025 (inf) time: 0.6342 [2021-03-26 05:55:57 swin_base_patch4_window7_224] INFO: Epoch: [33] [1140/1251] eta: 0:01:09 lr: 0.000969 loss: 3.8918 (3.9859) grad_norm: 1.0713 (inf) time: 0.6319 [2021-03-26 05:56:03 swin_base_patch4_window7_224] INFO: Epoch: [33] [1150/1251] eta: 0:01:03 lr: 0.000969 loss: 4.1573 (3.9865) grad_norm: 1.0641 (inf) time: 0.6339 [2021-03-26 05:56:09 swin_base_patch4_window7_224] INFO: Epoch: [33] [1160/1251] eta: 0:00:57 lr: 0.000969 loss: 4.2440 (3.9862) grad_norm: 1.0783 (inf) time: 0.6284 [2021-03-26 05:56:16 swin_base_patch4_window7_224] INFO: Epoch: [33] [1170/1251] eta: 0:00:50 lr: 0.000969 loss: 3.7934 (3.9861) grad_norm: 1.0853 (inf) time: 0.6262 [2021-03-26 05:56:22 swin_base_patch4_window7_224] INFO: Epoch: [33] [1180/1251] eta: 0:00:44 lr: 0.000969 loss: 3.9537 (3.9857) grad_norm: 1.1098 (inf) time: 0.6309 [2021-03-26 05:56:28 swin_base_patch4_window7_224] INFO: Epoch: [33] [1190/1251] eta: 0:00:38 lr: 0.000969 loss: 3.9537 (3.9852) grad_norm: 1.1203 (inf) time: 0.6275 [2021-03-26 05:56:35 swin_base_patch4_window7_224] INFO: Epoch: [33] [1200/1251] eta: 0:00:32 lr: 0.000969 loss: 3.9847 (3.9855) grad_norm: 0.9704 (inf) time: 0.6221 [2021-03-26 05:56:41 swin_base_patch4_window7_224] INFO: Epoch: [33] [1210/1251] eta: 0:00:25 lr: 0.000969 loss: 3.9847 (3.9852) grad_norm: 0.9948 (inf) time: 0.6304 [2021-03-26 05:56:47 swin_base_patch4_window7_224] INFO: Epoch: [33] [1220/1251] eta: 0:00:19 lr: 0.000969 loss: 4.4076 (3.9888) grad_norm: 1.0301 (inf) time: 0.6264 [2021-03-26 05:56:53 swin_base_patch4_window7_224] INFO: Epoch: [33] [1230/1251] eta: 0:00:13 lr: 0.000969 loss: 4.3971 (3.9895) grad_norm: 0.9224 (inf) time: 0.6150 [2021-03-26 05:56:59 swin_base_patch4_window7_224] INFO: Epoch: [33] [1240/1251] eta: 0:00:06 lr: 0.000969 loss: 4.1354 (3.9898) grad_norm: 0.9988 (inf) time: 0.6170 [2021-03-26 05:57:06 swin_base_patch4_window7_224] INFO: Epoch: [33] [1250/1251] eta: 0:00:00 lr: 0.000969 loss: 3.9349 (3.9895) grad_norm: 1.0291 (inf) time: 0.6138 [2021-03-26 05:57:10 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:10 loss: 1.1374 (1.1374) acc1: 73.4375 (73.4375) acc5: 90.6250 (90.6250) [2021-03-26 05:57:13 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.2063 (1.2899) acc1: 70.3125 (69.6023) acc5: 90.6250 (89.6307) [2021-03-26 05:57:15 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.4035 (1.3513) acc1: 67.1875 (68.1548) acc5: 87.5000 (88.9137) [2021-03-26 05:57:16 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.3452 (1.3393) acc1: 67.1875 (68.3468) acc5: 90.6250 (89.1129) [2021-03-26 05:57:18 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2908 (1.3596) acc1: 68.7500 (67.6448) acc5: 90.6250 (89.1768) [2021-03-26 05:57:20 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3312 (1.3547) acc1: 67.9245 (67.8080) acc5: 90.6250 (89.3760) [2021-03-26 05:57:23 swin_base_patch4_window7_224] INFO: * Acc@1 68.826 Acc@5 89.642 loss 1.330 [2021-03-26 05:57:23 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 68.8% [2021-03-26 05:57:23 swin_base_patch4_window7_224] INFO: Max accuracy: 68.83% [2021-03-26 05:57:27 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 0/1251] eta: 1:28:45 lr: 0.000969 loss: 4.0776 (4.0776) grad_norm: 1.1140 (1.1140) time: 4.2570 [2021-03-26 05:57:34 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 10/1251] eta: 0:19:51 lr: 0.000969 loss: 4.2795 (4.1302) grad_norm: 0.9278 (0.9547) time: 0.9601 [2021-03-26 05:57:40 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 20/1251] eta: 0:16:23 lr: 0.000969 loss: 4.2302 (4.0142) grad_norm: 1.0181 (1.0094) time: 0.6265 [2021-03-26 05:57:46 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 30/1251] eta: 0:15:07 lr: 0.000969 loss: 3.4828 (3.7847) grad_norm: 1.0501 (1.0151) time: 0.6238 [2021-03-26 05:57:52 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 40/1251] eta: 0:14:27 lr: 0.000969 loss: 3.7383 (3.8432) grad_norm: 1.0304 (1.0301) time: 0.6293 [2021-03-26 05:57:59 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 50/1251] eta: 0:13:58 lr: 0.000969 loss: 3.9808 (3.8518) grad_norm: 0.9523 (1.0153) time: 0.6275 [2021-03-26 05:58:05 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 60/1251] eta: 0:13:36 lr: 0.000969 loss: 4.0367 (3.8755) grad_norm: 0.9507 (1.0146) time: 0.6231 [2021-03-26 05:58:11 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 70/1251] eta: 0:13:20 lr: 0.000969 loss: 3.9112 (3.8394) grad_norm: 1.0285 (1.0158) time: 0.6280 [2021-03-26 05:58:17 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 80/1251] eta: 0:13:05 lr: 0.000969 loss: 3.7031 (3.8337) grad_norm: 0.9974 (1.0125) time: 0.6257 [2021-03-26 05:58:23 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 90/1251] eta: 0:12:52 lr: 0.000969 loss: 3.8688 (3.8396) grad_norm: 0.9643 (1.0159) time: 0.6182 [2021-03-26 05:58:30 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 100/1251] eta: 0:12:40 lr: 0.000969 loss: 4.1622 (3.8744) grad_norm: 1.0355 (1.0218) time: 0.6208 [2021-03-26 05:58:36 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 110/1251] eta: 0:12:30 lr: 0.000969 loss: 4.4541 (3.9018) grad_norm: 1.0361 (1.0244) time: 0.6231 [2021-03-26 05:58:42 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 120/1251] eta: 0:12:19 lr: 0.000969 loss: 4.2998 (3.9170) grad_norm: 0.9894 (1.0225) time: 0.6173 [2021-03-26 05:58:48 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 130/1251] eta: 0:12:09 lr: 0.000969 loss: 4.1224 (3.9042) grad_norm: 1.0066 (1.0238) time: 0.6166 [2021-03-26 05:58:55 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 140/1251] eta: 0:12:01 lr: 0.000969 loss: 4.0501 (3.9077) grad_norm: 0.9835 (1.0202) time: 0.6219 [2021-03-26 05:59:01 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 150/1251] eta: 0:11:53 lr: 0.000969 loss: 4.0214 (3.9100) grad_norm: 0.9571 (1.0260) time: 0.6248 [2021-03-26 05:59:07 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 160/1251] eta: 0:11:44 lr: 0.000969 loss: 3.7115 (3.8956) grad_norm: 1.0402 (1.0244) time: 0.6227 [2021-03-26 05:59:13 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 170/1251] eta: 0:11:37 lr: 0.000969 loss: 3.8479 (3.9020) grad_norm: 0.9797 (1.0264) time: 0.6243 [2021-03-26 05:59:20 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 180/1251] eta: 0:11:29 lr: 0.000969 loss: 3.9385 (3.9089) grad_norm: 1.0274 (1.0260) time: 0.6294 [2021-03-26 05:59:26 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 190/1251] eta: 0:11:22 lr: 0.000969 loss: 3.9255 (3.8994) grad_norm: 0.9737 (1.0215) time: 0.6244 [2021-03-26 05:59:32 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 200/1251] eta: 0:11:14 lr: 0.000969 loss: 4.0131 (3.9155) grad_norm: 0.9727 (1.0217) time: 0.6249 [2021-03-26 05:59:38 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 210/1251] eta: 0:11:08 lr: 0.000969 loss: 4.1557 (3.9252) grad_norm: 1.0340 (1.0235) time: 0.6324 [2021-03-26 05:59:45 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 220/1251] eta: 0:11:01 lr: 0.000969 loss: 4.1243 (3.9189) grad_norm: 1.0876 (1.0334) time: 0.6366 [2021-03-26 05:59:51 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 230/1251] eta: 0:10:54 lr: 0.000969 loss: 3.8326 (3.9215) grad_norm: 1.1445 (1.0351) time: 0.6277 [2021-03-26 05:59:57 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 240/1251] eta: 0:10:47 lr: 0.000969 loss: 4.0440 (3.9226) grad_norm: 1.0289 (1.0338) time: 0.6212 [2021-03-26 06:00:04 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 250/1251] eta: 0:10:40 lr: 0.000969 loss: 4.0114 (3.9181) grad_norm: 1.0289 (1.0365) time: 0.6311 [2021-03-26 06:00:10 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 260/1251] eta: 0:10:33 lr: 0.000969 loss: 3.8908 (3.9184) grad_norm: 1.0396 (1.0361) time: 0.6275 [2021-03-26 06:00:16 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 270/1251] eta: 0:10:26 lr: 0.000969 loss: 4.1903 (3.9331) grad_norm: 0.9857 (1.0346) time: 0.6198 [2021-03-26 06:00:22 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 280/1251] eta: 0:10:19 lr: 0.000969 loss: 4.1298 (3.9257) grad_norm: 0.9870 (1.0344) time: 0.6203 [2021-03-26 06:00:28 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 290/1251] eta: 0:10:12 lr: 0.000969 loss: 4.1194 (3.9336) grad_norm: 1.0388 (1.0366) time: 0.6237 [2021-03-26 06:00:35 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 300/1251] eta: 0:10:05 lr: 0.000969 loss: 4.2747 (3.9338) grad_norm: 0.9540 (1.0337) time: 0.6194 [2021-03-26 06:00:41 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 310/1251] eta: 0:09:58 lr: 0.000969 loss: 4.0795 (3.9373) grad_norm: 0.9814 (1.0349) time: 0.6167 [2021-03-26 06:00:47 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 320/1251] eta: 0:09:52 lr: 0.000968 loss: 4.0772 (3.9338) grad_norm: 1.0671 (1.0368) time: 0.6276 [2021-03-26 06:00:53 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 330/1251] eta: 0:09:45 lr: 0.000968 loss: 4.0259 (3.9430) grad_norm: 1.0128 (1.0346) time: 0.6297 [2021-03-26 06:01:00 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 340/1251] eta: 0:09:38 lr: 0.000968 loss: 4.4539 (3.9522) grad_norm: 0.9483 (1.0323) time: 0.6222 [2021-03-26 06:01:06 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 350/1251] eta: 0:09:31 lr: 0.000968 loss: 4.1797 (3.9497) grad_norm: 0.9510 (1.0315) time: 0.6202 [2021-03-26 06:01:12 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 360/1251] eta: 0:09:25 lr: 0.000968 loss: 3.7641 (3.9400) grad_norm: 0.9922 (1.0320) time: 0.6233 [2021-03-26 06:01:18 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 370/1251] eta: 0:09:18 lr: 0.000968 loss: 3.8147 (3.9436) grad_norm: 1.1009 (1.0355) time: 0.6244 [2021-03-26 06:01:25 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 380/1251] eta: 0:09:12 lr: 0.000968 loss: 4.0383 (3.9473) grad_norm: 1.0559 (1.0352) time: 0.6227 [2021-03-26 06:01:31 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 390/1251] eta: 0:09:05 lr: 0.000968 loss: 3.9845 (3.9452) grad_norm: 1.1453 (1.0392) time: 0.6237 [2021-03-26 06:01:37 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 400/1251] eta: 0:08:58 lr: 0.000968 loss: 3.7173 (3.9415) grad_norm: 1.1332 (1.0400) time: 0.6238 [2021-03-26 06:01:43 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 410/1251] eta: 0:08:52 lr: 0.000968 loss: 3.6400 (3.9331) grad_norm: 1.0715 (1.0399) time: 0.6221 [2021-03-26 06:01:49 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 420/1251] eta: 0:08:45 lr: 0.000968 loss: 3.8030 (3.9336) grad_norm: 1.0515 (inf) time: 0.6195 [2021-03-26 06:01:56 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 430/1251] eta: 0:08:39 lr: 0.000968 loss: 3.9073 (3.9323) grad_norm: 1.1171 (inf) time: 0.6216 [2021-03-26 06:02:02 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 440/1251] eta: 0:08:32 lr: 0.000968 loss: 3.8815 (3.9311) grad_norm: 1.0671 (inf) time: 0.6245 [2021-03-26 06:02:08 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 450/1251] eta: 0:08:26 lr: 0.000968 loss: 4.0200 (3.9337) grad_norm: 1.0451 (inf) time: 0.6198 [2021-03-26 06:02:14 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 460/1251] eta: 0:08:19 lr: 0.000968 loss: 4.0200 (3.9278) grad_norm: 0.9990 (inf) time: 0.6191 [2021-03-26 06:02:20 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 470/1251] eta: 0:08:13 lr: 0.000968 loss: 4.0214 (3.9320) grad_norm: 0.9796 (inf) time: 0.6163 [2021-03-26 06:02:27 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 480/1251] eta: 0:08:06 lr: 0.000968 loss: 4.0795 (3.9332) grad_norm: 0.9419 (inf) time: 0.6117 [2021-03-26 06:02:33 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 490/1251] eta: 0:08:00 lr: 0.000968 loss: 4.0296 (3.9299) grad_norm: 1.0931 (inf) time: 0.6219 [2021-03-26 06:02:39 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 500/1251] eta: 0:07:53 lr: 0.000968 loss: 4.0988 (3.9372) grad_norm: 1.1356 (inf) time: 0.6324 [2021-03-26 06:02:45 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 510/1251] eta: 0:07:47 lr: 0.000968 loss: 4.2148 (3.9397) grad_norm: 1.1233 (inf) time: 0.6276 [2021-03-26 06:02:52 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 520/1251] eta: 0:07:40 lr: 0.000968 loss: 4.1560 (3.9412) grad_norm: 0.9664 (inf) time: 0.6217 [2021-03-26 06:02:58 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 530/1251] eta: 0:07:34 lr: 0.000968 loss: 4.0804 (3.9450) grad_norm: 1.0053 (inf) time: 0.6200 [2021-03-26 06:03:04 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 540/1251] eta: 0:07:28 lr: 0.000968 loss: 4.0804 (3.9473) grad_norm: 0.9623 (inf) time: 0.6226 [2021-03-26 06:03:10 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 550/1251] eta: 0:07:22 lr: 0.000968 loss: 4.1692 (3.9521) grad_norm: 0.9623 (inf) time: 0.6338 [2021-03-26 06:03:17 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 560/1251] eta: 0:07:15 lr: 0.000968 loss: 4.1692 (3.9567) grad_norm: 0.9910 (inf) time: 0.6374 [2021-03-26 06:03:23 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 570/1251] eta: 0:07:09 lr: 0.000968 loss: 4.2336 (3.9578) grad_norm: 1.0825 (inf) time: 0.6259 [2021-03-26 06:03:29 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 580/1251] eta: 0:07:02 lr: 0.000968 loss: 4.2136 (3.9601) grad_norm: 1.0945 (inf) time: 0.6158 [2021-03-26 06:03:35 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 590/1251] eta: 0:06:56 lr: 0.000968 loss: 4.0009 (3.9605) grad_norm: 1.0060 (inf) time: 0.6227 [2021-03-26 06:03:42 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 600/1251] eta: 0:06:50 lr: 0.000968 loss: 3.8229 (3.9562) grad_norm: 0.9584 (inf) time: 0.6272 [2021-03-26 06:03:48 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 610/1251] eta: 0:06:43 lr: 0.000968 loss: 3.7726 (3.9545) grad_norm: 1.0243 (inf) time: 0.6334 [2021-03-26 06:03:54 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 620/1251] eta: 0:06:37 lr: 0.000968 loss: 3.8486 (3.9523) grad_norm: 1.0467 (inf) time: 0.6293 [2021-03-26 06:04:01 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 630/1251] eta: 0:06:31 lr: 0.000968 loss: 4.0368 (3.9531) grad_norm: 0.9853 (inf) time: 0.6179 [2021-03-26 06:04:07 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 640/1251] eta: 0:06:24 lr: 0.000968 loss: 4.1175 (3.9553) grad_norm: 1.0329 (inf) time: 0.6233 [2021-03-26 06:04:13 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 650/1251] eta: 0:06:18 lr: 0.000968 loss: 4.2728 (3.9620) grad_norm: 1.0656 (inf) time: 0.6262 [2021-03-26 06:04:19 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 660/1251] eta: 0:06:12 lr: 0.000968 loss: 4.2068 (3.9615) grad_norm: 1.0757 (inf) time: 0.6246 [2021-03-26 06:04:25 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 670/1251] eta: 0:06:05 lr: 0.000968 loss: 4.1245 (3.9638) grad_norm: 1.0434 (inf) time: 0.6216 [2021-03-26 06:04:32 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 680/1251] eta: 0:05:59 lr: 0.000968 loss: 4.1245 (3.9643) grad_norm: 0.9735 (inf) time: 0.6169 [2021-03-26 06:04:38 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 690/1251] eta: 0:05:53 lr: 0.000968 loss: 4.0766 (3.9649) grad_norm: 1.0850 (inf) time: 0.6226 [2021-03-26 06:04:44 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 700/1251] eta: 0:05:46 lr: 0.000968 loss: 4.0764 (3.9664) grad_norm: 1.1158 (inf) time: 0.6289 [2021-03-26 06:04:50 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 710/1251] eta: 0:05:40 lr: 0.000968 loss: 4.2149 (3.9691) grad_norm: 0.9845 (inf) time: 0.6283 [2021-03-26 06:04:57 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 720/1251] eta: 0:05:34 lr: 0.000968 loss: 4.2077 (3.9715) grad_norm: 1.0510 (inf) time: 0.6323 [2021-03-26 06:05:03 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 730/1251] eta: 0:05:27 lr: 0.000968 loss: 4.1352 (3.9700) grad_norm: 1.0498 (inf) time: 0.6366 [2021-03-26 06:05:10 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 740/1251] eta: 0:05:21 lr: 0.000968 loss: 4.0607 (3.9710) grad_norm: 1.0261 (inf) time: 0.6415 [2021-03-26 06:05:16 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 750/1251] eta: 0:05:15 lr: 0.000968 loss: 4.1607 (3.9724) grad_norm: 1.0460 (inf) time: 0.6356 [2021-03-26 06:05:22 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 760/1251] eta: 0:05:09 lr: 0.000968 loss: 4.1607 (3.9752) grad_norm: 1.0460 (inf) time: 0.6248 [2021-03-26 06:05:28 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 770/1251] eta: 0:05:02 lr: 0.000968 loss: 4.1357 (3.9711) grad_norm: 1.0117 (inf) time: 0.6220 [2021-03-26 06:05:35 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 780/1251] eta: 0:04:56 lr: 0.000968 loss: 4.1425 (3.9738) grad_norm: 1.0048 (inf) time: 0.6177 [2021-03-26 06:05:41 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 790/1251] eta: 0:04:50 lr: 0.000968 loss: 4.2583 (3.9722) grad_norm: 1.0003 (inf) time: 0.6236 [2021-03-26 06:05:47 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 800/1251] eta: 0:04:43 lr: 0.000968 loss: 4.0142 (3.9735) grad_norm: 1.0003 (inf) time: 0.6327 [2021-03-26 06:05:53 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 810/1251] eta: 0:04:37 lr: 0.000968 loss: 4.0961 (3.9761) grad_norm: 0.9893 (inf) time: 0.6257 [2021-03-26 06:06:00 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 820/1251] eta: 0:04:31 lr: 0.000968 loss: 4.1040 (3.9744) grad_norm: 0.9965 (inf) time: 0.6241 [2021-03-26 06:06:06 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 830/1251] eta: 0:04:24 lr: 0.000968 loss: 4.0813 (3.9737) grad_norm: 1.1042 (inf) time: 0.6248 [2021-03-26 06:06:12 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 840/1251] eta: 0:04:18 lr: 0.000968 loss: 4.0813 (3.9761) grad_norm: 1.0835 (inf) time: 0.6227 [2021-03-26 06:06:18 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 850/1251] eta: 0:04:12 lr: 0.000968 loss: 4.0135 (3.9762) grad_norm: 1.0264 (inf) time: 0.6231 [2021-03-26 06:06:25 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 860/1251] eta: 0:04:05 lr: 0.000968 loss: 4.0135 (3.9746) grad_norm: 0.9876 (inf) time: 0.6193 [2021-03-26 06:06:31 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 870/1251] eta: 0:03:59 lr: 0.000968 loss: 3.9929 (3.9752) grad_norm: 1.0031 (inf) time: 0.6195 [2021-03-26 06:06:37 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 880/1251] eta: 0:03:53 lr: 0.000968 loss: 3.9929 (3.9749) grad_norm: 1.0394 (inf) time: 0.6212 [2021-03-26 06:06:43 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 890/1251] eta: 0:03:46 lr: 0.000968 loss: 4.0905 (3.9759) grad_norm: 0.9799 (inf) time: 0.6197 [2021-03-26 06:06:49 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 900/1251] eta: 0:03:40 lr: 0.000968 loss: 4.1609 (3.9774) grad_norm: 0.9364 (inf) time: 0.6181 [2021-03-26 06:06:55 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 910/1251] eta: 0:03:34 lr: 0.000968 loss: 4.0595 (3.9775) grad_norm: 0.9486 (inf) time: 0.6165 [2021-03-26 06:07:02 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 920/1251] eta: 0:03:27 lr: 0.000968 loss: 3.9897 (3.9787) grad_norm: 1.0289 (inf) time: 0.6194 [2021-03-26 06:07:08 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 930/1251] eta: 0:03:21 lr: 0.000968 loss: 4.0432 (3.9783) grad_norm: 1.0996 (inf) time: 0.6264 [2021-03-26 06:07:14 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 940/1251] eta: 0:03:15 lr: 0.000968 loss: 3.7816 (3.9767) grad_norm: 1.0853 (inf) time: 0.6282 [2021-03-26 06:07:21 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 950/1251] eta: 0:03:09 lr: 0.000968 loss: 3.9569 (3.9760) grad_norm: 0.9721 (inf) time: 0.6280 [2021-03-26 06:07:27 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 960/1251] eta: 0:03:02 lr: 0.000968 loss: 3.9516 (3.9730) grad_norm: 1.0606 (inf) time: 0.6259 [2021-03-26 06:07:33 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 970/1251] eta: 0:02:56 lr: 0.000968 loss: 3.8740 (3.9721) grad_norm: 1.1160 (inf) time: 0.6250 [2021-03-26 06:07:39 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 980/1251] eta: 0:02:50 lr: 0.000968 loss: 3.4800 (3.9709) grad_norm: 1.0422 (inf) time: 0.6280 [2021-03-26 06:07:46 swin_base_patch4_window7_224] INFO: Epoch: [34] [ 990/1251] eta: 0:02:43 lr: 0.000968 loss: 4.1162 (3.9726) grad_norm: 1.0538 (inf) time: 0.6288 [2021-03-26 06:07:52 swin_base_patch4_window7_224] INFO: Epoch: [34] [1000/1251] eta: 0:02:37 lr: 0.000967 loss: 3.9460 (3.9695) grad_norm: 1.0424 (inf) time: 0.6233 [2021-03-26 06:07:58 swin_base_patch4_window7_224] INFO: Epoch: [34] [1010/1251] eta: 0:02:31 lr: 0.000967 loss: 3.6272 (3.9689) grad_norm: 1.0170 (inf) time: 0.6210 [2021-03-26 06:08:04 swin_base_patch4_window7_224] INFO: Epoch: [34] [1020/1251] eta: 0:02:25 lr: 0.000967 loss: 4.0799 (3.9703) grad_norm: 1.0177 (inf) time: 0.6268 [2021-03-26 06:08:11 swin_base_patch4_window7_224] INFO: Epoch: [34] [1030/1251] eta: 0:02:18 lr: 0.000967 loss: 4.0799 (3.9701) grad_norm: 0.9860 (inf) time: 0.6266 [2021-03-26 06:08:17 swin_base_patch4_window7_224] INFO: Epoch: [34] [1040/1251] eta: 0:02:12 lr: 0.000967 loss: 3.9291 (3.9689) grad_norm: 0.9821 (inf) time: 0.6206 [2021-03-26 06:08:23 swin_base_patch4_window7_224] INFO: Epoch: [34] [1050/1251] eta: 0:02:06 lr: 0.000967 loss: 3.6578 (3.9665) grad_norm: 0.9710 (inf) time: 0.6189 [2021-03-26 06:08:29 swin_base_patch4_window7_224] INFO: Epoch: [34] [1060/1251] eta: 0:01:59 lr: 0.000967 loss: 3.9450 (3.9672) grad_norm: 1.0388 (inf) time: 0.6249 [2021-03-26 06:08:35 swin_base_patch4_window7_224] INFO: Epoch: [34] [1070/1251] eta: 0:01:53 lr: 0.000967 loss: 4.2484 (3.9698) grad_norm: 1.0633 (inf) time: 0.6214 [2021-03-26 06:08:42 swin_base_patch4_window7_224] INFO: Epoch: [34] [1080/1251] eta: 0:01:47 lr: 0.000967 loss: 4.1742 (3.9693) grad_norm: 0.9868 (inf) time: 0.6166 [2021-03-26 06:08:48 swin_base_patch4_window7_224] INFO: Epoch: [34] [1090/1251] eta: 0:01:41 lr: 0.000967 loss: 3.8457 (3.9667) grad_norm: 0.9963 (inf) time: 0.6199 [2021-03-26 06:08:54 swin_base_patch4_window7_224] INFO: Epoch: [34] [1100/1251] eta: 0:01:34 lr: 0.000967 loss: 3.7994 (3.9678) grad_norm: 1.0255 (inf) time: 0.6228 [2021-03-26 06:09:00 swin_base_patch4_window7_224] INFO: Epoch: [34] [1110/1251] eta: 0:01:28 lr: 0.000967 loss: 3.8796 (3.9651) grad_norm: 1.0383 (inf) time: 0.6197 [2021-03-26 06:09:06 swin_base_patch4_window7_224] INFO: Epoch: [34] [1120/1251] eta: 0:01:22 lr: 0.000967 loss: 3.8796 (3.9667) grad_norm: 1.0774 (inf) time: 0.6207 [2021-03-26 06:09:13 swin_base_patch4_window7_224] INFO: Epoch: [34] [1130/1251] eta: 0:01:15 lr: 0.000967 loss: 4.0045 (3.9668) grad_norm: 1.0774 (inf) time: 0.6209 [2021-03-26 06:09:19 swin_base_patch4_window7_224] INFO: Epoch: [34] [1140/1251] eta: 0:01:09 lr: 0.000967 loss: 4.0333 (3.9678) grad_norm: 1.0656 (inf) time: 0.6193 [2021-03-26 06:09:25 swin_base_patch4_window7_224] INFO: Epoch: [34] [1150/1251] eta: 0:01:03 lr: 0.000967 loss: 4.1151 (3.9688) grad_norm: 1.0576 (inf) time: 0.6224 [2021-03-26 06:09:31 swin_base_patch4_window7_224] INFO: Epoch: [34] [1160/1251] eta: 0:00:57 lr: 0.000967 loss: 4.2087 (3.9714) grad_norm: 1.0576 (inf) time: 0.6214 [2021-03-26 06:09:37 swin_base_patch4_window7_224] INFO: Epoch: [34] [1170/1251] eta: 0:00:50 lr: 0.000967 loss: 4.2087 (3.9708) grad_norm: 0.9612 (inf) time: 0.6175 [2021-03-26 06:09:44 swin_base_patch4_window7_224] INFO: Epoch: [34] [1180/1251] eta: 0:00:44 lr: 0.000967 loss: 4.1005 (3.9711) grad_norm: 0.9720 (inf) time: 0.6218 [2021-03-26 06:09:50 swin_base_patch4_window7_224] INFO: Epoch: [34] [1190/1251] eta: 0:00:38 lr: 0.000967 loss: 4.2193 (3.9730) grad_norm: 1.0087 (inf) time: 0.6279 [2021-03-26 06:09:56 swin_base_patch4_window7_224] INFO: Epoch: [34] [1200/1251] eta: 0:00:31 lr: 0.000967 loss: 4.1428 (3.9689) grad_norm: 1.0131 (inf) time: 0.6267 [2021-03-26 06:10:03 swin_base_patch4_window7_224] INFO: Epoch: [34] [1210/1251] eta: 0:00:25 lr: 0.000967 loss: 4.0563 (3.9703) grad_norm: 1.0164 (inf) time: 0.6268 [2021-03-26 06:10:09 swin_base_patch4_window7_224] INFO: Epoch: [34] [1220/1251] eta: 0:00:19 lr: 0.000967 loss: 4.1687 (3.9706) grad_norm: 1.0408 (inf) time: 0.6267 [2021-03-26 06:10:15 swin_base_patch4_window7_224] INFO: Epoch: [34] [1230/1251] eta: 0:00:13 lr: 0.000967 loss: 4.0385 (3.9694) grad_norm: 1.0533 (inf) time: 0.6226 [2021-03-26 06:10:21 swin_base_patch4_window7_224] INFO: Epoch: [34] [1240/1251] eta: 0:00:06 lr: 0.000967 loss: 3.7556 (3.9667) grad_norm: 1.0633 (inf) time: 0.6221 [2021-03-26 06:10:27 swin_base_patch4_window7_224] INFO: Epoch: [34] [1250/1251] eta: 0:00:00 lr: 0.000967 loss: 3.9923 (3.9675) grad_norm: 1.0712 (inf) time: 0.6143 [2021-03-26 06:10:31 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:41 loss: 1.3280 (1.3280) acc1: 71.8750 (71.8750) acc5: 85.9375 (85.9375) [2021-03-26 06:10:33 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:13 loss: 1.3973 (1.4108) acc1: 67.1875 (68.8920) acc5: 85.9375 (86.3636) [2021-03-26 06:10:35 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:07 loss: 1.4019 (1.4143) acc1: 67.1875 (67.7083) acc5: 87.5000 (87.6488) [2021-03-26 06:10:37 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 1.3290 (1.3517) acc1: 68.7500 (68.8508) acc5: 90.6250 (88.7097) [2021-03-26 06:10:38 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2553 (1.3195) acc1: 70.3125 (69.3598) acc5: 92.1875 (89.6723) [2021-03-26 06:10:40 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2634 (1.3240) acc1: 70.3125 (68.9920) acc5: 90.6250 (89.6960) [2021-03-26 06:10:45 swin_base_patch4_window7_224] INFO: * Acc@1 69.376 Acc@5 89.798 loss 1.321 [2021-03-26 06:10:45 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 69.4% [2021-03-26 06:10:45 swin_base_patch4_window7_224] INFO: Max accuracy: 69.38% [2021-03-26 06:10:49 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 0/1251] eta: 1:25:17 lr: 0.000967 loss: 4.3876 (4.3876) grad_norm: 0.9995 (0.9995) time: 4.0906 [2021-03-26 06:10:56 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 10/1251] eta: 0:19:43 lr: 0.000967 loss: 4.1114 (3.9244) grad_norm: 0.9216 (0.9062) time: 0.9535 [2021-03-26 06:11:02 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 20/1251] eta: 0:16:16 lr: 0.000967 loss: 4.0890 (3.8352) grad_norm: 0.9566 (0.9625) time: 0.6287 [2021-03-26 06:11:08 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 30/1251] eta: 0:15:04 lr: 0.000967 loss: 3.9901 (3.8873) grad_norm: 1.0511 (1.0126) time: 0.6242 [2021-03-26 06:11:14 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 40/1251] eta: 0:14:26 lr: 0.000967 loss: 4.0593 (3.9516) grad_norm: 1.1228 (1.0447) time: 0.6340 [2021-03-26 06:11:21 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 50/1251] eta: 0:13:55 lr: 0.000967 loss: 4.0124 (3.9360) grad_norm: 1.0001 (1.0379) time: 0.6244 [2021-03-26 06:11:27 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 60/1251] eta: 0:13:34 lr: 0.000967 loss: 3.9594 (3.9522) grad_norm: 1.0001 (1.0372) time: 0.6182 [2021-03-26 06:11:33 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 70/1251] eta: 0:13:16 lr: 0.000967 loss: 4.1492 (3.9657) grad_norm: 1.0037 (1.0310) time: 0.6211 [2021-03-26 06:11:39 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 80/1251] eta: 0:13:01 lr: 0.000967 loss: 4.1415 (3.9490) grad_norm: 0.9889 (1.0360) time: 0.6190 [2021-03-26 06:11:45 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 90/1251] eta: 0:12:49 lr: 0.000967 loss: 3.9652 (3.9535) grad_norm: 0.9889 (1.0338) time: 0.6233 [2021-03-26 06:11:52 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 100/1251] eta: 0:12:37 lr: 0.000967 loss: 3.9652 (3.9510) grad_norm: 0.9503 (1.0311) time: 0.6209 [2021-03-26 06:11:58 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 110/1251] eta: 0:12:28 lr: 0.000967 loss: 3.7633 (3.9321) grad_norm: 1.0381 (1.0352) time: 0.6241 [2021-03-26 06:12:04 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 120/1251] eta: 0:12:19 lr: 0.000967 loss: 3.9918 (3.9537) grad_norm: 1.0742 (1.0425) time: 0.6304 [2021-03-26 06:12:11 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 130/1251] eta: 0:12:11 lr: 0.000967 loss: 3.9918 (3.9473) grad_norm: 1.0772 (1.0501) time: 0.6323 [2021-03-26 06:12:17 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 140/1251] eta: 0:12:02 lr: 0.000967 loss: 3.9423 (3.9569) grad_norm: 1.1435 (1.0518) time: 0.6305 [2021-03-26 06:12:23 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 150/1251] eta: 0:11:55 lr: 0.000967 loss: 4.1168 (3.9656) grad_norm: 1.1249 (1.0549) time: 0.6303 [2021-03-26 06:12:30 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 160/1251] eta: 0:11:47 lr: 0.000967 loss: 3.9400 (3.9476) grad_norm: 1.1249 (1.0602) time: 0.6342 [2021-03-26 06:12:36 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 170/1251] eta: 0:11:39 lr: 0.000967 loss: 3.8286 (3.9518) grad_norm: 1.0645 (1.0558) time: 0.6254 [2021-03-26 06:12:42 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 180/1251] eta: 0:11:31 lr: 0.000967 loss: 4.1042 (3.9420) grad_norm: 0.9873 (1.0625) time: 0.6234 [2021-03-26 06:12:48 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 190/1251] eta: 0:11:23 lr: 0.000967 loss: 4.1042 (3.9522) grad_norm: 1.1010 (1.0655) time: 0.6265 [2021-03-26 06:12:54 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 200/1251] eta: 0:11:15 lr: 0.000967 loss: 4.0208 (3.9458) grad_norm: 1.0210 (1.0620) time: 0.6199 [2021-03-26 06:13:01 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 210/1251] eta: 0:11:08 lr: 0.000967 loss: 3.9658 (3.9527) grad_norm: 0.9885 (1.0617) time: 0.6152 [2021-03-26 06:13:07 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 220/1251] eta: 0:11:00 lr: 0.000967 loss: 4.1613 (3.9569) grad_norm: 1.0120 (1.0601) time: 0.6179 [2021-03-26 06:13:13 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 230/1251] eta: 0:10:53 lr: 0.000967 loss: 3.8320 (3.9478) grad_norm: 0.9705 (1.0578) time: 0.6204 [2021-03-26 06:13:19 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 240/1251] eta: 0:10:46 lr: 0.000967 loss: 3.7607 (3.9412) grad_norm: 0.9837 (1.0574) time: 0.6223 [2021-03-26 06:13:25 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 250/1251] eta: 0:10:39 lr: 0.000967 loss: 4.0207 (3.9502) grad_norm: 1.0257 (1.0570) time: 0.6206 [2021-03-26 06:13:32 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 260/1251] eta: 0:10:31 lr: 0.000967 loss: 4.0207 (3.9502) grad_norm: 1.0071 (1.0550) time: 0.6159 [2021-03-26 06:13:38 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 270/1251] eta: 0:10:25 lr: 0.000967 loss: 4.2427 (3.9614) grad_norm: 1.0384 (1.0556) time: 0.6247 [2021-03-26 06:13:44 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 280/1251] eta: 0:10:18 lr: 0.000967 loss: 3.8850 (3.9580) grad_norm: 1.0817 (1.0561) time: 0.6308 [2021-03-26 06:13:50 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 290/1251] eta: 0:10:11 lr: 0.000967 loss: 3.8850 (3.9618) grad_norm: 1.1286 (1.0612) time: 0.6289 [2021-03-26 06:13:57 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 300/1251] eta: 0:10:05 lr: 0.000967 loss: 4.0451 (3.9625) grad_norm: 1.0918 (1.0607) time: 0.6240 [2021-03-26 06:14:03 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 310/1251] eta: 0:09:57 lr: 0.000967 loss: 3.8428 (3.9564) grad_norm: 0.9682 (1.0586) time: 0.6157 [2021-03-26 06:14:09 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 320/1251] eta: 0:09:51 lr: 0.000967 loss: 4.0475 (3.9564) grad_norm: 1.0133 (1.0585) time: 0.6183 [2021-03-26 06:14:15 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 330/1251] eta: 0:09:44 lr: 0.000967 loss: 4.1685 (3.9665) grad_norm: 1.0677 (1.0651) time: 0.6248 [2021-03-26 06:14:22 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 340/1251] eta: 0:09:38 lr: 0.000967 loss: 4.2225 (3.9730) grad_norm: 1.1904 (1.0675) time: 0.6275 [2021-03-26 06:14:28 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 350/1251] eta: 0:09:31 lr: 0.000967 loss: 4.1515 (3.9729) grad_norm: 1.1010 (1.0660) time: 0.6237 [2021-03-26 06:14:34 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 360/1251] eta: 0:09:24 lr: 0.000967 loss: 3.9237 (3.9716) grad_norm: 1.0072 (1.0654) time: 0.6235 [2021-03-26 06:14:40 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 370/1251] eta: 0:09:18 lr: 0.000967 loss: 4.0917 (3.9751) grad_norm: 1.0151 (1.0640) time: 0.6276 [2021-03-26 06:14:47 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 380/1251] eta: 0:09:11 lr: 0.000967 loss: 4.1650 (3.9802) grad_norm: 1.0282 (1.0656) time: 0.6261 [2021-03-26 06:14:53 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 390/1251] eta: 0:09:05 lr: 0.000967 loss: 4.1436 (3.9831) grad_norm: 1.1137 (1.0675) time: 0.6274 [2021-03-26 06:14:59 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 400/1251] eta: 0:08:58 lr: 0.000967 loss: 4.1436 (3.9855) grad_norm: 1.1106 (1.0689) time: 0.6241 [2021-03-26 06:15:05 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 410/1251] eta: 0:08:52 lr: 0.000967 loss: 4.3328 (3.9924) grad_norm: 1.0501 (1.0689) time: 0.6251 [2021-03-26 06:15:12 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 420/1251] eta: 0:08:45 lr: 0.000966 loss: 4.2281 (3.9928) grad_norm: 0.9948 (1.0678) time: 0.6254 [2021-03-26 06:15:18 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 430/1251] eta: 0:08:39 lr: 0.000966 loss: 3.9943 (3.9885) grad_norm: 0.9833 (1.0661) time: 0.6193 [2021-03-26 06:15:24 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 440/1251] eta: 0:08:32 lr: 0.000966 loss: 4.0671 (3.9898) grad_norm: 0.9212 (1.0637) time: 0.6176 [2021-03-26 06:15:30 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 450/1251] eta: 0:08:25 lr: 0.000966 loss: 4.0394 (3.9892) grad_norm: 0.8928 (1.0609) time: 0.6142 [2021-03-26 06:15:36 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 460/1251] eta: 0:08:19 lr: 0.000966 loss: 4.0151 (3.9919) grad_norm: 0.9222 (1.0610) time: 0.6179 [2021-03-26 06:15:42 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 470/1251] eta: 0:08:12 lr: 0.000966 loss: 4.1595 (3.9965) grad_norm: 1.0327 (1.0611) time: 0.6192 [2021-03-26 06:15:49 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 480/1251] eta: 0:08:06 lr: 0.000966 loss: 4.0432 (3.9935) grad_norm: 0.9604 (1.0596) time: 0.6140 [2021-03-26 06:15:55 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 490/1251] eta: 0:07:59 lr: 0.000966 loss: 4.0151 (3.9947) grad_norm: 0.9720 (1.0593) time: 0.6161 [2021-03-26 06:16:01 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 500/1251] eta: 0:07:53 lr: 0.000966 loss: 4.1654 (3.9917) grad_norm: 0.9720 (1.0578) time: 0.6176 [2021-03-26 06:16:07 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 510/1251] eta: 0:07:46 lr: 0.000966 loss: 3.8712 (3.9894) grad_norm: 0.9457 (1.0562) time: 0.6194 [2021-03-26 06:16:13 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 520/1251] eta: 0:07:40 lr: 0.000966 loss: 3.9868 (3.9890) grad_norm: 0.9876 (1.0564) time: 0.6241 [2021-03-26 06:16:20 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 530/1251] eta: 0:07:34 lr: 0.000966 loss: 3.9632 (3.9867) grad_norm: 0.9876 (1.0571) time: 0.6213 [2021-03-26 06:16:26 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 540/1251] eta: 0:07:27 lr: 0.000966 loss: 3.8525 (3.9858) grad_norm: 1.0033 (1.0584) time: 0.6275 [2021-03-26 06:16:32 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 550/1251] eta: 0:07:21 lr: 0.000966 loss: 3.9685 (3.9838) grad_norm: 1.0480 (1.0586) time: 0.6464 [2021-03-26 06:16:39 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 560/1251] eta: 0:07:15 lr: 0.000966 loss: 3.9737 (3.9836) grad_norm: 1.0412 (1.0578) time: 0.6404 [2021-03-26 06:16:45 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 570/1251] eta: 0:07:09 lr: 0.000966 loss: 4.1756 (3.9865) grad_norm: 0.9674 (1.0566) time: 0.6206 [2021-03-26 06:16:51 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 580/1251] eta: 0:07:02 lr: 0.000966 loss: 4.2605 (3.9903) grad_norm: 0.9141 (1.0543) time: 0.6182 [2021-03-26 06:16:57 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 590/1251] eta: 0:06:56 lr: 0.000966 loss: 4.1683 (3.9907) grad_norm: 0.9901 (1.0546) time: 0.6254 [2021-03-26 06:17:04 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 600/1251] eta: 0:06:49 lr: 0.000966 loss: 4.1210 (3.9924) grad_norm: 1.0245 (1.0544) time: 0.6253 [2021-03-26 06:17:10 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 610/1251] eta: 0:06:43 lr: 0.000966 loss: 4.0931 (3.9917) grad_norm: 1.0051 (1.0534) time: 0.6204 [2021-03-26 06:17:16 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 620/1251] eta: 0:06:37 lr: 0.000966 loss: 3.8535 (3.9896) grad_norm: 0.9916 (1.0531) time: 0.6199 [2021-03-26 06:17:22 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 630/1251] eta: 0:06:30 lr: 0.000966 loss: 3.8167 (3.9840) grad_norm: 0.9981 (1.0536) time: 0.6279 [2021-03-26 06:17:29 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 640/1251] eta: 0:06:24 lr: 0.000966 loss: 3.7636 (3.9808) grad_norm: 1.0388 (1.0534) time: 0.6281 [2021-03-26 06:17:35 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 650/1251] eta: 0:06:18 lr: 0.000966 loss: 4.0589 (3.9807) grad_norm: 1.0050 (1.0529) time: 0.6183 [2021-03-26 06:17:41 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 660/1251] eta: 0:06:11 lr: 0.000966 loss: 3.9582 (3.9785) grad_norm: 0.9940 (1.0517) time: 0.6195 [2021-03-26 06:17:47 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 670/1251] eta: 0:06:05 lr: 0.000966 loss: 3.8375 (3.9749) grad_norm: 1.0141 (1.0514) time: 0.6268 [2021-03-26 06:17:54 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 680/1251] eta: 0:05:59 lr: 0.000966 loss: 4.0160 (3.9761) grad_norm: 1.0160 (1.0519) time: 0.6318 [2021-03-26 06:18:00 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 690/1251] eta: 0:05:52 lr: 0.000966 loss: 4.0888 (3.9740) grad_norm: 1.0110 (1.0526) time: 0.6315 [2021-03-26 06:18:06 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 700/1251] eta: 0:05:46 lr: 0.000966 loss: 4.0382 (3.9708) grad_norm: 1.0235 (1.0537) time: 0.6229 [2021-03-26 06:18:12 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 710/1251] eta: 0:05:40 lr: 0.000966 loss: 4.1636 (3.9728) grad_norm: 1.0573 (1.0552) time: 0.6203 [2021-03-26 06:18:19 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 720/1251] eta: 0:05:33 lr: 0.000966 loss: 4.1636 (3.9713) grad_norm: 1.0562 (1.0551) time: 0.6262 [2021-03-26 06:18:25 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 730/1251] eta: 0:05:27 lr: 0.000966 loss: 3.9197 (3.9695) grad_norm: 0.9853 (1.0550) time: 0.6255 [2021-03-26 06:18:31 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 740/1251] eta: 0:05:21 lr: 0.000966 loss: 3.7598 (3.9661) grad_norm: 1.1100 (1.0559) time: 0.6292 [2021-03-26 06:18:38 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 750/1251] eta: 0:05:15 lr: 0.000966 loss: 3.5090 (3.9629) grad_norm: 1.1575 (1.0570) time: 0.6383 [2021-03-26 06:18:44 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 760/1251] eta: 0:05:08 lr: 0.000966 loss: 3.9991 (3.9662) grad_norm: 1.0245 (1.0573) time: 0.6355 [2021-03-26 06:18:50 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 770/1251] eta: 0:05:02 lr: 0.000966 loss: 4.0615 (3.9629) grad_norm: 1.0148 (1.0568) time: 0.6233 [2021-03-26 06:18:56 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 780/1251] eta: 0:04:56 lr: 0.000966 loss: 4.0513 (3.9647) grad_norm: 1.0243 (1.0571) time: 0.6264 [2021-03-26 06:19:03 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 790/1251] eta: 0:04:49 lr: 0.000966 loss: 4.1029 (3.9629) grad_norm: 1.0452 (1.0576) time: 0.6336 [2021-03-26 06:19:09 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 800/1251] eta: 0:04:43 lr: 0.000966 loss: 4.1958 (3.9669) grad_norm: 1.0764 (1.0582) time: 0.6295 [2021-03-26 06:19:15 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 810/1251] eta: 0:04:37 lr: 0.000966 loss: 4.0495 (3.9670) grad_norm: 1.0849 (1.0590) time: 0.6242 [2021-03-26 06:19:21 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 820/1251] eta: 0:04:30 lr: 0.000966 loss: 3.9604 (3.9685) grad_norm: 1.0552 (1.0584) time: 0.6196 [2021-03-26 06:19:28 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 830/1251] eta: 0:04:24 lr: 0.000966 loss: 3.9905 (3.9685) grad_norm: 1.0120 (1.0591) time: 0.6224 [2021-03-26 06:19:34 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 840/1251] eta: 0:04:18 lr: 0.000966 loss: 3.9858 (3.9677) grad_norm: 1.0408 (1.0594) time: 0.6288 [2021-03-26 06:19:40 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 850/1251] eta: 0:04:12 lr: 0.000966 loss: 4.0365 (3.9661) grad_norm: 1.0352 (1.0592) time: 0.6305 [2021-03-26 06:19:47 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 860/1251] eta: 0:04:05 lr: 0.000966 loss: 4.0745 (3.9689) grad_norm: 1.0025 (1.0587) time: 0.6285 [2021-03-26 06:19:53 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 870/1251] eta: 0:03:59 lr: 0.000966 loss: 4.3120 (3.9715) grad_norm: 1.0181 (1.0591) time: 0.6232 [2021-03-26 06:19:59 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 880/1251] eta: 0:03:53 lr: 0.000966 loss: 4.1812 (3.9715) grad_norm: 1.1185 (1.0602) time: 0.6233 [2021-03-26 06:20:05 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 890/1251] eta: 0:03:46 lr: 0.000966 loss: 3.7516 (3.9687) grad_norm: 1.0474 (1.0595) time: 0.6233 [2021-03-26 06:20:11 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 900/1251] eta: 0:03:40 lr: 0.000966 loss: 3.7516 (3.9679) grad_norm: 0.9744 (1.0593) time: 0.6171 [2021-03-26 06:20:18 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 910/1251] eta: 0:03:34 lr: 0.000966 loss: 3.9083 (3.9676) grad_norm: 0.9885 (1.0584) time: 0.6189 [2021-03-26 06:20:24 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 920/1251] eta: 0:03:27 lr: 0.000966 loss: 4.1548 (3.9684) grad_norm: 0.9444 (1.0575) time: 0.6185 [2021-03-26 06:20:30 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 930/1251] eta: 0:03:21 lr: 0.000966 loss: 4.1808 (3.9700) grad_norm: 1.0046 (1.0575) time: 0.6258 [2021-03-26 06:20:36 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 940/1251] eta: 0:03:15 lr: 0.000966 loss: 4.1509 (3.9721) grad_norm: 1.0376 (1.0575) time: 0.6281 [2021-03-26 06:20:43 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 950/1251] eta: 0:03:09 lr: 0.000966 loss: 4.1450 (3.9736) grad_norm: 1.0092 (1.0567) time: 0.6203 [2021-03-26 06:20:49 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 960/1251] eta: 0:03:02 lr: 0.000966 loss: 4.0820 (3.9738) grad_norm: 0.9519 (1.0567) time: 0.6227 [2021-03-26 06:20:55 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 970/1251] eta: 0:02:56 lr: 0.000966 loss: 4.1520 (3.9743) grad_norm: 0.9465 (1.0559) time: 0.6197 [2021-03-26 06:21:01 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 980/1251] eta: 0:02:50 lr: 0.000966 loss: 3.9176 (3.9727) grad_norm: 0.9581 (1.0554) time: 0.6152 [2021-03-26 06:21:07 swin_base_patch4_window7_224] INFO: Epoch: [35] [ 990/1251] eta: 0:02:43 lr: 0.000966 loss: 4.0361 (3.9742) grad_norm: 1.0604 (1.0552) time: 0.6161 [2021-03-26 06:21:14 swin_base_patch4_window7_224] INFO: Epoch: [35] [1000/1251] eta: 0:02:37 lr: 0.000966 loss: 4.1975 (3.9754) grad_norm: 1.0310 (1.0551) time: 0.6190 [2021-03-26 06:21:20 swin_base_patch4_window7_224] INFO: Epoch: [35] [1010/1251] eta: 0:02:31 lr: 0.000966 loss: 4.1975 (3.9760) grad_norm: 1.0246 (1.0552) time: 0.6202 [2021-03-26 06:21:26 swin_base_patch4_window7_224] INFO: Epoch: [35] [1020/1251] eta: 0:02:24 lr: 0.000966 loss: 4.1174 (3.9777) grad_norm: 1.0370 (1.0556) time: 0.6237 [2021-03-26 06:21:32 swin_base_patch4_window7_224] INFO: Epoch: [35] [1030/1251] eta: 0:02:18 lr: 0.000966 loss: 4.0640 (3.9753) grad_norm: 1.0776 (1.0551) time: 0.6254 [2021-03-26 06:21:38 swin_base_patch4_window7_224] INFO: Epoch: [35] [1040/1251] eta: 0:02:12 lr: 0.000966 loss: 3.6367 (3.9728) grad_norm: 1.0257 (1.0558) time: 0.6206 [2021-03-26 06:21:45 swin_base_patch4_window7_224] INFO: Epoch: [35] [1050/1251] eta: 0:02:06 lr: 0.000966 loss: 3.9044 (3.9734) grad_norm: 0.9811 (1.0554) time: 0.6220 [2021-03-26 06:21:51 swin_base_patch4_window7_224] INFO: Epoch: [35] [1060/1251] eta: 0:01:59 lr: 0.000966 loss: 3.9044 (3.9710) grad_norm: 1.0187 (1.0554) time: 0.6245 [2021-03-26 06:21:57 swin_base_patch4_window7_224] INFO: Epoch: [35] [1070/1251] eta: 0:01:53 lr: 0.000966 loss: 3.9236 (3.9696) grad_norm: 1.0357 (1.0554) time: 0.6232 [2021-03-26 06:22:03 swin_base_patch4_window7_224] INFO: Epoch: [35] [1080/1251] eta: 0:01:47 lr: 0.000965 loss: 3.7353 (3.9672) grad_norm: 1.0710 (1.0560) time: 0.6213 [2021-03-26 06:22:10 swin_base_patch4_window7_224] INFO: Epoch: [35] [1090/1251] eta: 0:01:40 lr: 0.000965 loss: 3.7353 (3.9664) grad_norm: 0.9962 (1.0555) time: 0.6206 [2021-03-26 06:22:16 swin_base_patch4_window7_224] INFO: Epoch: [35] [1100/1251] eta: 0:01:34 lr: 0.000965 loss: 3.9960 (3.9671) grad_norm: 0.9962 (1.0553) time: 0.6232 [2021-03-26 06:22:22 swin_base_patch4_window7_224] INFO: Epoch: [35] [1110/1251] eta: 0:01:28 lr: 0.000965 loss: 4.0984 (3.9681) grad_norm: 1.0541 (1.0551) time: 0.6243 [2021-03-26 06:22:28 swin_base_patch4_window7_224] INFO: Epoch: [35] [1120/1251] eta: 0:01:22 lr: 0.000965 loss: 4.1467 (3.9659) grad_norm: 1.0216 (1.0548) time: 0.6251 [2021-03-26 06:22:34 swin_base_patch4_window7_224] INFO: Epoch: [35] [1130/1251] eta: 0:01:15 lr: 0.000965 loss: 3.8101 (3.9653) grad_norm: 0.9873 (1.0545) time: 0.6211 [2021-03-26 06:22:41 swin_base_patch4_window7_224] INFO: Epoch: [35] [1140/1251] eta: 0:01:09 lr: 0.000965 loss: 3.9777 (3.9652) grad_norm: 1.0294 (1.0553) time: 0.6225 [2021-03-26 06:22:47 swin_base_patch4_window7_224] INFO: Epoch: [35] [1150/1251] eta: 0:01:03 lr: 0.000965 loss: 4.0024 (3.9648) grad_norm: 1.0294 (1.0550) time: 0.6288 [2021-03-26 06:22:53 swin_base_patch4_window7_224] INFO: Epoch: [35] [1160/1251] eta: 0:00:57 lr: 0.000965 loss: 4.0691 (3.9664) grad_norm: 0.9921 (1.0548) time: 0.6276 [2021-03-26 06:22:59 swin_base_patch4_window7_224] INFO: Epoch: [35] [1170/1251] eta: 0:00:50 lr: 0.000965 loss: 4.2489 (3.9680) grad_norm: 1.0295 (1.0551) time: 0.6230 [2021-03-26 06:23:06 swin_base_patch4_window7_224] INFO: Epoch: [35] [1180/1251] eta: 0:00:44 lr: 0.000965 loss: 4.0964 (3.9669) grad_norm: 0.9900 (1.0544) time: 0.6269 [2021-03-26 06:23:12 swin_base_patch4_window7_224] INFO: Epoch: [35] [1190/1251] eta: 0:00:38 lr: 0.000965 loss: 4.0457 (3.9680) grad_norm: 0.9664 (1.0539) time: 0.6320 [2021-03-26 06:23:18 swin_base_patch4_window7_224] INFO: Epoch: [35] [1200/1251] eta: 0:00:31 lr: 0.000965 loss: 4.0401 (3.9658) grad_norm: 0.9798 (1.0546) time: 0.6242 [2021-03-26 06:23:25 swin_base_patch4_window7_224] INFO: Epoch: [35] [1210/1251] eta: 0:00:25 lr: 0.000965 loss: 3.8017 (3.9653) grad_norm: 1.0687 (1.0547) time: 0.6225 [2021-03-26 06:23:31 swin_base_patch4_window7_224] INFO: Epoch: [35] [1220/1251] eta: 0:00:19 lr: 0.000965 loss: 3.9881 (3.9674) grad_norm: 1.0269 (1.0546) time: 0.6314 [2021-03-26 06:23:37 swin_base_patch4_window7_224] INFO: Epoch: [35] [1230/1251] eta: 0:00:13 lr: 0.000965 loss: 4.0266 (3.9681) grad_norm: 1.0305 (1.0547) time: 0.6312 [2021-03-26 06:23:43 swin_base_patch4_window7_224] INFO: Epoch: [35] [1240/1251] eta: 0:00:06 lr: 0.000965 loss: 3.9205 (3.9670) grad_norm: 0.9921 (1.0544) time: 0.6212 [2021-03-26 06:23:50 swin_base_patch4_window7_224] INFO: Epoch: [35] [1250/1251] eta: 0:00:00 lr: 0.000965 loss: 3.9646 (3.9676) grad_norm: 0.9795 (1.0544) time: 0.6248 [2021-03-26 06:24:50 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:14 loss: 1.3814 (1.3814) acc1: 73.4375 (73.4375) acc5: 87.5000 (87.5000) [2021-03-26 06:24:51 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 1.3567 (1.3282) acc1: 70.3125 (70.8807) acc5: 87.5000 (89.7727) [2021-03-26 06:24:52 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.3439 (1.3407) acc1: 68.7500 (70.2381) acc5: 89.0625 (89.6577) [2021-03-26 06:24:54 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.2954 (1.3564) acc1: 67.1875 (68.4980) acc5: 89.0625 (88.9113) [2021-03-26 06:24:55 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.3293 (1.3466) acc1: 67.1875 (68.6738) acc5: 90.6250 (89.2530) [2021-03-26 06:24:56 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3279 (1.3221) acc1: 68.7500 (69.3440) acc5: 90.6250 (89.5360) [2021-03-26 06:24:59 swin_base_patch4_window7_224] INFO: * Acc@1 69.796 Acc@5 89.934 loss 1.297 [2021-03-26 06:24:59 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 69.8% [2021-03-26 06:24:59 swin_base_patch4_window7_224] INFO: Max accuracy: 69.80% [2021-03-26 06:25:03 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 0/1251] eta: 1:31:42 lr: 0.000965 loss: 4.2035 (4.2035) grad_norm: 1.0211 (1.0211) time: 4.3985 [2021-03-26 06:25:10 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 10/1251] eta: 0:20:38 lr: 0.000965 loss: 3.9665 (3.8932) grad_norm: 1.0428 (1.0875) time: 0.9982 [2021-03-26 06:25:16 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 20/1251] eta: 0:16:43 lr: 0.000965 loss: 3.9326 (3.9171) grad_norm: 1.0205 (1.0433) time: 0.6360 [2021-03-26 06:25:22 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 30/1251] eta: 0:15:25 lr: 0.000965 loss: 3.8267 (3.9017) grad_norm: 1.0184 (1.0611) time: 0.6253 [2021-03-26 06:25:29 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 40/1251] eta: 0:14:38 lr: 0.000965 loss: 3.9162 (3.9298) grad_norm: 1.0221 (1.0470) time: 0.6318 [2021-03-26 06:25:35 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 50/1251] eta: 0:14:07 lr: 0.000965 loss: 4.2975 (4.0076) grad_norm: 1.0221 (1.0540) time: 0.6245 [2021-03-26 06:25:41 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 60/1251] eta: 0:13:47 lr: 0.000965 loss: 4.2998 (4.0230) grad_norm: 1.0315 (1.0533) time: 0.6307 [2021-03-26 06:25:48 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 70/1251] eta: 0:13:28 lr: 0.000965 loss: 4.2354 (4.0261) grad_norm: 1.1031 (1.0592) time: 0.6311 [2021-03-26 06:25:54 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 80/1251] eta: 0:13:11 lr: 0.000965 loss: 4.1045 (4.0171) grad_norm: 1.0975 (inf) time: 0.6198 [2021-03-26 06:26:00 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 90/1251] eta: 0:12:59 lr: 0.000965 loss: 4.0951 (4.0159) grad_norm: 1.0649 (inf) time: 0.6266 [2021-03-26 06:26:06 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 100/1251] eta: 0:12:47 lr: 0.000965 loss: 4.1219 (4.0203) grad_norm: 1.0284 (inf) time: 0.6293 [2021-03-26 06:26:13 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 110/1251] eta: 0:12:37 lr: 0.000965 loss: 4.1695 (4.0064) grad_norm: 1.0284 (inf) time: 0.6276 [2021-03-26 06:26:19 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 120/1251] eta: 0:12:27 lr: 0.000965 loss: 3.8945 (3.9870) grad_norm: 1.0570 (inf) time: 0.6288 [2021-03-26 06:26:25 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 130/1251] eta: 0:12:17 lr: 0.000965 loss: 4.0720 (3.9933) grad_norm: 1.0502 (inf) time: 0.6228 [2021-03-26 06:26:31 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 140/1251] eta: 0:12:08 lr: 0.000965 loss: 4.1180 (3.9943) grad_norm: 0.9551 (inf) time: 0.6251 [2021-03-26 06:26:38 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 150/1251] eta: 0:11:59 lr: 0.000965 loss: 4.0020 (4.0017) grad_norm: 1.0006 (inf) time: 0.6288 [2021-03-26 06:26:44 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 160/1251] eta: 0:11:51 lr: 0.000965 loss: 3.8319 (3.9816) grad_norm: 1.0339 (inf) time: 0.6275 [2021-03-26 06:26:50 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 170/1251] eta: 0:11:42 lr: 0.000965 loss: 3.6532 (3.9842) grad_norm: 1.0110 (inf) time: 0.6212 [2021-03-26 06:26:57 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 180/1251] eta: 0:11:35 lr: 0.000965 loss: 4.1283 (3.9840) grad_norm: 1.0887 (inf) time: 0.6286 [2021-03-26 06:27:03 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 190/1251] eta: 0:11:27 lr: 0.000965 loss: 3.8569 (3.9836) grad_norm: 1.0887 (inf) time: 0.6314 [2021-03-26 06:27:09 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 200/1251] eta: 0:11:20 lr: 0.000965 loss: 4.0492 (3.9867) grad_norm: 0.9446 (inf) time: 0.6262 [2021-03-26 06:27:15 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 210/1251] eta: 0:11:12 lr: 0.000965 loss: 3.9545 (3.9784) grad_norm: 0.9364 (inf) time: 0.6245 [2021-03-26 06:27:21 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 220/1251] eta: 0:11:04 lr: 0.000965 loss: 4.0118 (3.9749) grad_norm: 0.9615 (inf) time: 0.6151 [2021-03-26 06:27:28 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 230/1251] eta: 0:10:56 lr: 0.000965 loss: 4.1283 (3.9772) grad_norm: 1.0002 (inf) time: 0.6181 [2021-03-26 06:27:34 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 240/1251] eta: 0:10:49 lr: 0.000965 loss: 4.0759 (3.9767) grad_norm: 1.0863 (inf) time: 0.6252 [2021-03-26 06:27:40 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 250/1251] eta: 0:10:42 lr: 0.000965 loss: 4.2166 (3.9830) grad_norm: 1.0863 (inf) time: 0.6251 [2021-03-26 06:27:46 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 260/1251] eta: 0:10:35 lr: 0.000965 loss: 4.2166 (3.9818) grad_norm: 1.0422 (inf) time: 0.6276 [2021-03-26 06:27:53 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 270/1251] eta: 0:10:28 lr: 0.000965 loss: 4.1873 (3.9899) grad_norm: 0.9714 (inf) time: 0.6197 [2021-03-26 06:27:59 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 280/1251] eta: 0:10:20 lr: 0.000965 loss: 4.2438 (3.9948) grad_norm: 0.9230 (inf) time: 0.6113 [2021-03-26 06:28:05 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 290/1251] eta: 0:10:13 lr: 0.000965 loss: 4.0568 (3.9845) grad_norm: 0.9716 (inf) time: 0.6170 [2021-03-26 06:28:11 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 300/1251] eta: 0:10:07 lr: 0.000965 loss: 3.7543 (3.9763) grad_norm: 1.0089 (inf) time: 0.6271 [2021-03-26 06:28:17 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 310/1251] eta: 0:10:00 lr: 0.000965 loss: 3.9208 (3.9782) grad_norm: 0.9857 (inf) time: 0.6294 [2021-03-26 06:28:24 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 320/1251] eta: 0:09:53 lr: 0.000965 loss: 3.8955 (3.9606) grad_norm: 1.0420 (inf) time: 0.6232 [2021-03-26 06:28:30 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 330/1251] eta: 0:09:46 lr: 0.000965 loss: 3.5996 (3.9612) grad_norm: 1.0441 (inf) time: 0.6234 [2021-03-26 06:28:36 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 340/1251] eta: 0:09:40 lr: 0.000965 loss: 3.9193 (3.9580) grad_norm: 1.0530 (inf) time: 0.6226 [2021-03-26 06:28:42 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 350/1251] eta: 0:09:33 lr: 0.000965 loss: 3.8620 (3.9601) grad_norm: 1.0530 (inf) time: 0.6203 [2021-03-26 06:28:49 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 360/1251] eta: 0:09:26 lr: 0.000965 loss: 3.9699 (3.9649) grad_norm: 1.0028 (inf) time: 0.6241 [2021-03-26 06:28:55 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 370/1251] eta: 0:09:20 lr: 0.000965 loss: 4.1996 (3.9634) grad_norm: 1.1060 (inf) time: 0.6287 [2021-03-26 06:29:01 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 380/1251] eta: 0:09:13 lr: 0.000965 loss: 3.9276 (3.9597) grad_norm: 1.0815 (inf) time: 0.6267 [2021-03-26 06:29:07 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 390/1251] eta: 0:09:06 lr: 0.000965 loss: 4.0263 (3.9628) grad_norm: 1.0092 (inf) time: 0.6205 [2021-03-26 06:29:14 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 400/1251] eta: 0:09:00 lr: 0.000965 loss: 4.2062 (3.9616) grad_norm: 1.0163 (inf) time: 0.6200 [2021-03-26 06:29:20 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 410/1251] eta: 0:08:53 lr: 0.000965 loss: 3.9532 (3.9596) grad_norm: 1.0154 (inf) time: 0.6241 [2021-03-26 06:29:26 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 420/1251] eta: 0:08:46 lr: 0.000965 loss: 3.9532 (3.9577) grad_norm: 1.0121 (inf) time: 0.6222 [2021-03-26 06:29:32 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 430/1251] eta: 0:08:40 lr: 0.000965 loss: 3.9800 (3.9574) grad_norm: 1.0202 (inf) time: 0.6252 [2021-03-26 06:29:39 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 440/1251] eta: 0:08:34 lr: 0.000965 loss: 3.8211 (3.9521) grad_norm: 1.0884 (inf) time: 0.6268 [2021-03-26 06:29:45 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 450/1251] eta: 0:08:27 lr: 0.000965 loss: 3.9840 (3.9580) grad_norm: 1.0239 (inf) time: 0.6233 [2021-03-26 06:29:51 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 460/1251] eta: 0:08:21 lr: 0.000965 loss: 4.1492 (3.9537) grad_norm: 0.9951 (inf) time: 0.6279 [2021-03-26 06:29:57 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 470/1251] eta: 0:08:14 lr: 0.000965 loss: 3.9246 (3.9531) grad_norm: 0.9785 (inf) time: 0.6279 [2021-03-26 06:30:04 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 480/1251] eta: 0:08:08 lr: 0.000965 loss: 3.8086 (3.9466) grad_norm: 1.0000 (inf) time: 0.6262 [2021-03-26 06:30:10 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 490/1251] eta: 0:08:01 lr: 0.000964 loss: 3.5228 (3.9450) grad_norm: 1.0773 (inf) time: 0.6243 [2021-03-26 06:30:16 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 500/1251] eta: 0:07:55 lr: 0.000964 loss: 3.5065 (3.9343) grad_norm: 0.9492 (inf) time: 0.6190 [2021-03-26 06:30:22 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 510/1251] eta: 0:07:48 lr: 0.000964 loss: 3.7175 (3.9369) grad_norm: 1.0054 (inf) time: 0.6183 [2021-03-26 06:30:28 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 520/1251] eta: 0:07:42 lr: 0.000964 loss: 4.0393 (3.9369) grad_norm: 1.0298 (inf) time: 0.6168 [2021-03-26 06:30:35 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 530/1251] eta: 0:07:35 lr: 0.000964 loss: 4.0393 (3.9358) grad_norm: 1.0413 (inf) time: 0.6197 [2021-03-26 06:30:41 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 540/1251] eta: 0:07:29 lr: 0.000964 loss: 3.7983 (3.9320) grad_norm: 1.0876 (inf) time: 0.6253 [2021-03-26 06:30:47 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 550/1251] eta: 0:07:23 lr: 0.000964 loss: 3.7021 (3.9303) grad_norm: 1.0988 (inf) time: 0.6339 [2021-03-26 06:30:54 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 560/1251] eta: 0:07:16 lr: 0.000964 loss: 4.0606 (3.9343) grad_norm: 1.0648 (inf) time: 0.6383 [2021-03-26 06:31:00 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 570/1251] eta: 0:07:10 lr: 0.000964 loss: 4.0606 (3.9327) grad_norm: 1.0648 (inf) time: 0.6344 [2021-03-26 06:31:06 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 580/1251] eta: 0:07:04 lr: 0.000964 loss: 3.9504 (3.9338) grad_norm: 1.0670 (inf) time: 0.6301 [2021-03-26 06:31:12 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 590/1251] eta: 0:06:57 lr: 0.000964 loss: 3.8472 (3.9302) grad_norm: 1.0166 (inf) time: 0.6255 [2021-03-26 06:31:19 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 600/1251] eta: 0:06:51 lr: 0.000964 loss: 3.7877 (3.9296) grad_norm: 1.0166 (inf) time: 0.6303 [2021-03-26 06:31:25 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 610/1251] eta: 0:06:44 lr: 0.000964 loss: 3.9159 (3.9251) grad_norm: 0.9880 (inf) time: 0.6249 [2021-03-26 06:31:31 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 620/1251] eta: 0:06:38 lr: 0.000964 loss: 3.9030 (3.9250) grad_norm: 0.9450 (inf) time: 0.6214 [2021-03-26 06:31:38 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 630/1251] eta: 0:06:32 lr: 0.000964 loss: 3.9030 (3.9242) grad_norm: 1.0415 (inf) time: 0.6379 [2021-03-26 06:31:44 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 640/1251] eta: 0:06:26 lr: 0.000964 loss: 4.2471 (3.9296) grad_norm: 1.0306 (inf) time: 0.6387 [2021-03-26 06:31:50 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 650/1251] eta: 0:06:19 lr: 0.000964 loss: 4.3086 (3.9337) grad_norm: 1.0092 (inf) time: 0.6282 [2021-03-26 06:31:57 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 660/1251] eta: 0:06:13 lr: 0.000964 loss: 4.2483 (3.9360) grad_norm: 1.0463 (inf) time: 0.6270 [2021-03-26 06:32:03 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 670/1251] eta: 0:06:06 lr: 0.000964 loss: 4.0815 (3.9352) grad_norm: 1.0387 (inf) time: 0.6257 [2021-03-26 06:32:09 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 680/1251] eta: 0:06:00 lr: 0.000964 loss: 3.9456 (3.9354) grad_norm: 1.0312 (inf) time: 0.6259 [2021-03-26 06:32:15 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 690/1251] eta: 0:05:54 lr: 0.000964 loss: 4.2219 (3.9402) grad_norm: 1.0192 (inf) time: 0.6257 [2021-03-26 06:32:22 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 700/1251] eta: 0:05:47 lr: 0.000964 loss: 4.0693 (3.9361) grad_norm: 0.9861 (inf) time: 0.6218 [2021-03-26 06:32:28 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 710/1251] eta: 0:05:41 lr: 0.000964 loss: 3.6556 (3.9355) grad_norm: 0.9489 (inf) time: 0.6177 [2021-03-26 06:32:34 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 720/1251] eta: 0:05:35 lr: 0.000964 loss: 3.7990 (3.9323) grad_norm: 1.0069 (inf) time: 0.6228 [2021-03-26 06:32:40 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 730/1251] eta: 0:05:28 lr: 0.000964 loss: 3.9084 (3.9336) grad_norm: 1.0689 (inf) time: 0.6287 [2021-03-26 06:32:47 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 740/1251] eta: 0:05:22 lr: 0.000964 loss: 3.9601 (3.9338) grad_norm: 1.0631 (inf) time: 0.6336 [2021-03-26 06:32:53 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 750/1251] eta: 0:05:16 lr: 0.000964 loss: 4.0353 (3.9347) grad_norm: 1.0541 (inf) time: 0.6348 [2021-03-26 06:32:59 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 760/1251] eta: 0:05:09 lr: 0.000964 loss: 4.0353 (3.9339) grad_norm: 0.9789 (inf) time: 0.6230 [2021-03-26 06:33:05 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 770/1251] eta: 0:05:03 lr: 0.000964 loss: 3.4361 (3.9285) grad_norm: 0.9438 (inf) time: 0.6180 [2021-03-26 06:33:12 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 780/1251] eta: 0:04:57 lr: 0.000964 loss: 3.7762 (3.9308) grad_norm: 1.0688 (inf) time: 0.6252 [2021-03-26 06:33:18 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 790/1251] eta: 0:04:50 lr: 0.000964 loss: 4.1613 (3.9337) grad_norm: 1.0974 (inf) time: 0.6319 [2021-03-26 06:33:24 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 800/1251] eta: 0:04:44 lr: 0.000964 loss: 4.0946 (3.9345) grad_norm: 0.9942 (inf) time: 0.6257 [2021-03-26 06:33:30 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 810/1251] eta: 0:04:38 lr: 0.000964 loss: 3.8357 (3.9307) grad_norm: 0.9986 (inf) time: 0.6213 [2021-03-26 06:33:37 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 820/1251] eta: 0:04:31 lr: 0.000964 loss: 3.4936 (3.9281) grad_norm: 1.0720 (inf) time: 0.6250 [2021-03-26 06:33:43 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 830/1251] eta: 0:04:25 lr: 0.000964 loss: 3.6488 (3.9246) grad_norm: 1.1053 (inf) time: 0.6238 [2021-03-26 06:33:49 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 840/1251] eta: 0:04:19 lr: 0.000964 loss: 3.6561 (3.9220) grad_norm: 1.0466 (inf) time: 0.6264 [2021-03-26 06:33:55 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 850/1251] eta: 0:04:12 lr: 0.000964 loss: 3.9627 (3.9219) grad_norm: 0.9949 (inf) time: 0.6287 [2021-03-26 06:34:02 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 860/1251] eta: 0:04:06 lr: 0.000964 loss: 4.0482 (3.9222) grad_norm: 0.9593 (inf) time: 0.6212 [2021-03-26 06:34:08 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 870/1251] eta: 0:04:00 lr: 0.000964 loss: 4.0066 (3.9218) grad_norm: 0.9602 (inf) time: 0.6177 [2021-03-26 06:34:14 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 880/1251] eta: 0:03:53 lr: 0.000964 loss: 4.0066 (3.9220) grad_norm: 1.0227 (inf) time: 0.6186 [2021-03-26 06:34:20 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 890/1251] eta: 0:03:47 lr: 0.000964 loss: 4.1236 (3.9225) grad_norm: 0.9064 (inf) time: 0.6178 [2021-03-26 06:34:26 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 900/1251] eta: 0:03:40 lr: 0.000964 loss: 4.0976 (3.9233) grad_norm: 0.9316 (inf) time: 0.6175 [2021-03-26 06:34:33 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 910/1251] eta: 0:03:34 lr: 0.000964 loss: 4.3398 (3.9288) grad_norm: 1.0269 (inf) time: 0.6205 [2021-03-26 06:34:39 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 920/1251] eta: 0:03:28 lr: 0.000964 loss: 4.3431 (3.9301) grad_norm: 1.0269 (inf) time: 0.6190 [2021-03-26 06:34:45 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 930/1251] eta: 0:03:22 lr: 0.000964 loss: 4.0514 (3.9304) grad_norm: 1.0376 (inf) time: 0.6178 [2021-03-26 06:34:51 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 940/1251] eta: 0:03:15 lr: 0.000964 loss: 4.1055 (3.9314) grad_norm: 1.0304 (inf) time: 0.6251 [2021-03-26 06:34:57 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 950/1251] eta: 0:03:09 lr: 0.000964 loss: 4.1266 (3.9307) grad_norm: 1.0248 (inf) time: 0.6252 [2021-03-26 06:35:04 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 960/1251] eta: 0:03:03 lr: 0.000964 loss: 4.0029 (3.9311) grad_norm: 1.0452 (inf) time: 0.6278 [2021-03-26 06:35:10 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 970/1251] eta: 0:02:56 lr: 0.000964 loss: 4.0340 (3.9322) grad_norm: 1.0405 (inf) time: 0.6274 [2021-03-26 06:35:16 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 980/1251] eta: 0:02:50 lr: 0.000964 loss: 4.0340 (3.9312) grad_norm: 0.9365 (inf) time: 0.6195 [2021-03-26 06:35:22 swin_base_patch4_window7_224] INFO: Epoch: [36] [ 990/1251] eta: 0:02:44 lr: 0.000964 loss: 4.0726 (3.9322) grad_norm: 0.9763 (inf) time: 0.6209 [2021-03-26 06:35:29 swin_base_patch4_window7_224] INFO: Epoch: [36] [1000/1251] eta: 0:02:37 lr: 0.000964 loss: 4.0726 (3.9314) grad_norm: 1.0429 (inf) time: 0.6244 [2021-03-26 06:35:35 swin_base_patch4_window7_224] INFO: Epoch: [36] [1010/1251] eta: 0:02:31 lr: 0.000964 loss: 3.7760 (3.9311) grad_norm: 1.0051 (inf) time: 0.6255 [2021-03-26 06:35:41 swin_base_patch4_window7_224] INFO: Epoch: [36] [1020/1251] eta: 0:02:25 lr: 0.000964 loss: 3.8586 (3.9310) grad_norm: 0.9862 (inf) time: 0.6236 [2021-03-26 06:35:47 swin_base_patch4_window7_224] INFO: Epoch: [36] [1030/1251] eta: 0:02:18 lr: 0.000964 loss: 3.8957 (3.9319) grad_norm: 1.0481 (inf) time: 0.6231 [2021-03-26 06:35:54 swin_base_patch4_window7_224] INFO: Epoch: [36] [1040/1251] eta: 0:02:12 lr: 0.000964 loss: 3.9325 (3.9306) grad_norm: 1.0438 (inf) time: 0.6256 [2021-03-26 06:36:00 swin_base_patch4_window7_224] INFO: Epoch: [36] [1050/1251] eta: 0:02:06 lr: 0.000964 loss: 3.9765 (3.9309) grad_norm: 1.0538 (inf) time: 0.6249 [2021-03-26 06:36:06 swin_base_patch4_window7_224] INFO: Epoch: [36] [1060/1251] eta: 0:02:00 lr: 0.000964 loss: 4.1316 (3.9310) grad_norm: 1.0544 (inf) time: 0.6246 [2021-03-26 06:36:12 swin_base_patch4_window7_224] INFO: Epoch: [36] [1070/1251] eta: 0:01:53 lr: 0.000964 loss: 4.0927 (3.9313) grad_norm: 0.9892 (inf) time: 0.6193 [2021-03-26 06:36:19 swin_base_patch4_window7_224] INFO: Epoch: [36] [1080/1251] eta: 0:01:47 lr: 0.000964 loss: 4.1663 (3.9323) grad_norm: 1.0352 (inf) time: 0.6222 [2021-03-26 06:36:25 swin_base_patch4_window7_224] INFO: Epoch: [36] [1090/1251] eta: 0:01:41 lr: 0.000964 loss: 4.2881 (3.9338) grad_norm: 1.0100 (inf) time: 0.6305 [2021-03-26 06:36:31 swin_base_patch4_window7_224] INFO: Epoch: [36] [1100/1251] eta: 0:01:34 lr: 0.000964 loss: 3.9712 (3.9323) grad_norm: 0.9912 (inf) time: 0.6320 [2021-03-26 06:36:37 swin_base_patch4_window7_224] INFO: Epoch: [36] [1110/1251] eta: 0:01:28 lr: 0.000964 loss: 4.0200 (3.9344) grad_norm: 0.9239 (inf) time: 0.6254 [2021-03-26 06:36:44 swin_base_patch4_window7_224] INFO: Epoch: [36] [1120/1251] eta: 0:01:22 lr: 0.000964 loss: 4.1839 (3.9347) grad_norm: 0.9219 (inf) time: 0.6165 [2021-03-26 06:36:50 swin_base_patch4_window7_224] INFO: Epoch: [36] [1130/1251] eta: 0:01:16 lr: 0.000963 loss: 4.1812 (3.9354) grad_norm: 0.9805 (inf) time: 0.6181 [2021-03-26 06:36:56 swin_base_patch4_window7_224] INFO: Epoch: [36] [1140/1251] eta: 0:01:09 lr: 0.000963 loss: 3.9995 (3.9368) grad_norm: 0.9724 (inf) time: 0.6139 [2021-03-26 06:37:02 swin_base_patch4_window7_224] INFO: Epoch: [36] [1150/1251] eta: 0:01:03 lr: 0.000963 loss: 3.9995 (3.9372) grad_norm: 0.9863 (inf) time: 0.6151 [2021-03-26 06:37:08 swin_base_patch4_window7_224] INFO: Epoch: [36] [1160/1251] eta: 0:00:57 lr: 0.000963 loss: 4.2381 (3.9408) grad_norm: 1.0413 (inf) time: 0.6235 [2021-03-26 06:37:15 swin_base_patch4_window7_224] INFO: Epoch: [36] [1170/1251] eta: 0:00:50 lr: 0.000963 loss: 4.0145 (3.9395) grad_norm: 1.0542 (inf) time: 0.6204 [2021-03-26 06:37:21 swin_base_patch4_window7_224] INFO: Epoch: [36] [1180/1251] eta: 0:00:44 lr: 0.000963 loss: 3.9761 (3.9399) grad_norm: 1.0993 (inf) time: 0.6251 [2021-03-26 06:37:27 swin_base_patch4_window7_224] INFO: Epoch: [36] [1190/1251] eta: 0:00:38 lr: 0.000963 loss: 4.1544 (3.9400) grad_norm: 1.1097 (inf) time: 0.6310 [2021-03-26 06:37:33 swin_base_patch4_window7_224] INFO: Epoch: [36] [1200/1251] eta: 0:00:32 lr: 0.000963 loss: 4.0180 (3.9390) grad_norm: 1.0775 (inf) time: 0.6296 [2021-03-26 06:37:40 swin_base_patch4_window7_224] INFO: Epoch: [36] [1210/1251] eta: 0:00:25 lr: 0.000963 loss: 3.9710 (3.9368) grad_norm: 1.0989 (inf) time: 0.6258 [2021-03-26 06:37:46 swin_base_patch4_window7_224] INFO: Epoch: [36] [1220/1251] eta: 0:00:19 lr: 0.000963 loss: 3.7555 (3.9376) grad_norm: 1.0319 (inf) time: 0.6209 [2021-03-26 06:37:52 swin_base_patch4_window7_224] INFO: Epoch: [36] [1230/1251] eta: 0:00:13 lr: 0.000963 loss: 4.1524 (3.9386) grad_norm: 0.9634 (inf) time: 0.6226 [2021-03-26 06:37:58 swin_base_patch4_window7_224] INFO: Epoch: [36] [1240/1251] eta: 0:00:06 lr: 0.000963 loss: 4.1359 (3.9382) grad_norm: 1.0321 (inf) time: 0.6211 [2021-03-26 06:38:04 swin_base_patch4_window7_224] INFO: Epoch: [36] [1250/1251] eta: 0:00:00 lr: 0.000963 loss: 4.0429 (3.9384) grad_norm: 1.0608 (inf) time: 0.6154 [2021-03-26 06:38:09 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:00 loss: 1.0725 (1.0725) acc1: 78.1250 (78.1250) acc5: 92.1875 (92.1875) [2021-03-26 06:38:11 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.3895 (1.3872) acc1: 70.3125 (68.8920) acc5: 87.5000 (87.6420) [2021-03-26 06:38:14 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.3019 (1.3079) acc1: 70.3125 (70.4613) acc5: 89.0625 (89.2857) [2021-03-26 06:38:16 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.2923 (1.2992) acc1: 70.3125 (70.7661) acc5: 90.6250 (89.6169) [2021-03-26 06:38:18 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.3155 (1.2974) acc1: 68.7500 (70.3506) acc5: 90.6250 (89.5579) [2021-03-26 06:38:19 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3240 (1.3167) acc1: 67.1875 (69.6640) acc5: 90.6250 (89.4400) [2021-03-26 06:38:21 swin_base_patch4_window7_224] INFO: * Acc@1 69.956 Acc@5 90.084 loss 1.303 [2021-03-26 06:38:21 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 70.0% [2021-03-26 06:38:21 swin_base_patch4_window7_224] INFO: Max accuracy: 69.96% [2021-03-26 06:38:25 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 0/1251] eta: 1:31:39 lr: 0.000963 loss: 3.7346 (3.7346) grad_norm: 1.0575 (1.0575) time: 4.3959 [2021-03-26 06:38:32 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 10/1251] eta: 0:20:06 lr: 0.000963 loss: 4.1269 (4.1082) grad_norm: 1.1565 (1.1709) time: 0.9726 [2021-03-26 06:38:38 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 20/1251] eta: 0:16:34 lr: 0.000963 loss: 3.5653 (3.8234) grad_norm: 1.0580 (1.0973) time: 0.6286 [2021-03-26 06:38:44 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 30/1251] eta: 0:15:13 lr: 0.000963 loss: 3.8427 (3.9141) grad_norm: 1.0395 (1.0965) time: 0.6250 [2021-03-26 06:38:50 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 40/1251] eta: 0:14:28 lr: 0.000963 loss: 3.9382 (3.8792) grad_norm: 1.0020 (1.0662) time: 0.6221 [2021-03-26 06:38:57 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 50/1251] eta: 0:13:59 lr: 0.000963 loss: 4.1883 (3.9741) grad_norm: 1.0020 (1.0644) time: 0.6214 [2021-03-26 06:39:03 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 60/1251] eta: 0:13:36 lr: 0.000963 loss: 4.1883 (3.9656) grad_norm: 1.0374 (1.0659) time: 0.6214 [2021-03-26 06:39:09 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 70/1251] eta: 0:13:20 lr: 0.000963 loss: 3.9306 (3.9402) grad_norm: 1.0708 (1.0713) time: 0.6246 [2021-03-26 06:39:15 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 80/1251] eta: 0:13:04 lr: 0.000963 loss: 4.2725 (3.9960) grad_norm: 1.1344 (1.0819) time: 0.6219 [2021-03-26 06:39:22 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 90/1251] eta: 0:12:53 lr: 0.000963 loss: 4.3329 (3.9873) grad_norm: 1.0395 (1.0791) time: 0.6236 [2021-03-26 06:39:28 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 100/1251] eta: 0:12:41 lr: 0.000963 loss: 3.9292 (3.9825) grad_norm: 0.9973 (1.0697) time: 0.6255 [2021-03-26 06:39:34 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 110/1251] eta: 0:12:30 lr: 0.000963 loss: 3.9521 (3.9761) grad_norm: 0.9629 (1.0618) time: 0.6230 [2021-03-26 06:39:40 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 120/1251] eta: 0:12:20 lr: 0.000963 loss: 4.0688 (3.9876) grad_norm: 1.0004 (1.0638) time: 0.6221 [2021-03-26 06:39:46 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 130/1251] eta: 0:12:10 lr: 0.000963 loss: 4.1897 (3.9883) grad_norm: 1.0140 (1.0588) time: 0.6176 [2021-03-26 06:39:53 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 140/1251] eta: 0:12:03 lr: 0.000963 loss: 4.0092 (3.9872) grad_norm: 1.0199 (1.0621) time: 0.6268 [2021-03-26 06:39:59 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 150/1251] eta: 0:11:54 lr: 0.000963 loss: 3.8782 (3.9618) grad_norm: 1.0897 (1.0619) time: 0.6288 [2021-03-26 06:40:05 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 160/1251] eta: 0:11:46 lr: 0.000963 loss: 3.5808 (3.9531) grad_norm: 1.0264 (1.0608) time: 0.6220 [2021-03-26 06:40:11 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 170/1251] eta: 0:11:37 lr: 0.000963 loss: 3.9670 (3.9632) grad_norm: 1.0100 (1.0607) time: 0.6214 [2021-03-26 06:40:18 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 180/1251] eta: 0:11:30 lr: 0.000963 loss: 4.1088 (3.9631) grad_norm: 0.9539 (1.0534) time: 0.6236 [2021-03-26 06:40:24 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 190/1251] eta: 0:11:23 lr: 0.000963 loss: 3.9877 (3.9630) grad_norm: 0.9353 (1.0497) time: 0.6273 [2021-03-26 06:40:30 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 200/1251] eta: 0:11:16 lr: 0.000963 loss: 3.9877 (3.9613) grad_norm: 0.9916 (1.0474) time: 0.6305 [2021-03-26 06:40:37 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 210/1251] eta: 0:11:09 lr: 0.000963 loss: 3.9048 (3.9526) grad_norm: 1.0010 (1.0481) time: 0.6360 [2021-03-26 06:40:43 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 220/1251] eta: 0:11:02 lr: 0.000963 loss: 3.6040 (3.9505) grad_norm: 1.0519 (1.0494) time: 0.6324 [2021-03-26 06:40:49 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 230/1251] eta: 0:10:55 lr: 0.000963 loss: 4.0012 (3.9420) grad_norm: 1.0519 (1.0512) time: 0.6285 [2021-03-26 06:40:56 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 240/1251] eta: 0:10:48 lr: 0.000963 loss: 4.0926 (3.9429) grad_norm: 1.0254 (1.0509) time: 0.6287 [2021-03-26 06:41:02 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 250/1251] eta: 0:10:41 lr: 0.000963 loss: 4.1189 (3.9394) grad_norm: 1.0467 (1.0507) time: 0.6252 [2021-03-26 06:41:08 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 260/1251] eta: 0:10:33 lr: 0.000963 loss: 4.1464 (3.9402) grad_norm: 1.0829 (1.0537) time: 0.6208 [2021-03-26 06:41:14 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 270/1251] eta: 0:10:27 lr: 0.000963 loss: 4.0565 (3.9365) grad_norm: 1.0928 (1.0542) time: 0.6252 [2021-03-26 06:41:21 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 280/1251] eta: 0:10:20 lr: 0.000963 loss: 4.1702 (3.9441) grad_norm: 1.0274 (1.0539) time: 0.6276 [2021-03-26 06:41:27 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 290/1251] eta: 0:10:13 lr: 0.000963 loss: 4.3179 (3.9506) grad_norm: 1.0343 (1.0551) time: 0.6242 [2021-03-26 06:41:33 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 300/1251] eta: 0:10:06 lr: 0.000963 loss: 4.0490 (3.9468) grad_norm: 1.0542 (1.0579) time: 0.6287 [2021-03-26 06:41:39 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 310/1251] eta: 0:10:00 lr: 0.000963 loss: 3.9811 (3.9513) grad_norm: 1.0446 (1.0574) time: 0.6305 [2021-03-26 06:41:46 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 320/1251] eta: 0:09:53 lr: 0.000963 loss: 4.0686 (3.9527) grad_norm: 1.0933 (1.0591) time: 0.6281 [2021-03-26 06:41:52 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 330/1251] eta: 0:09:47 lr: 0.000963 loss: 4.1402 (3.9469) grad_norm: 1.1015 (1.0592) time: 0.6342 [2021-03-26 06:41:58 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 340/1251] eta: 0:09:40 lr: 0.000963 loss: 3.9546 (3.9446) grad_norm: 1.0294 (1.0608) time: 0.6322 [2021-03-26 06:42:05 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 350/1251] eta: 0:09:33 lr: 0.000963 loss: 4.0194 (3.9511) grad_norm: 1.0191 (1.0602) time: 0.6225 [2021-03-26 06:42:11 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 360/1251] eta: 0:09:27 lr: 0.000963 loss: 4.1616 (3.9529) grad_norm: 1.0026 (1.0588) time: 0.6250 [2021-03-26 06:42:17 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 370/1251] eta: 0:09:20 lr: 0.000963 loss: 4.0676 (3.9522) grad_norm: 1.0108 (1.0584) time: 0.6263 [2021-03-26 06:42:23 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 380/1251] eta: 0:09:13 lr: 0.000963 loss: 3.9106 (3.9465) grad_norm: 0.9963 (1.0575) time: 0.6204 [2021-03-26 06:42:30 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 390/1251] eta: 0:09:07 lr: 0.000963 loss: 3.9300 (3.9482) grad_norm: 1.0398 (1.0571) time: 0.6237 [2021-03-26 06:42:36 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 400/1251] eta: 0:09:00 lr: 0.000963 loss: 3.9537 (3.9427) grad_norm: 1.0413 (1.0588) time: 0.6327 [2021-03-26 06:42:42 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 410/1251] eta: 0:08:54 lr: 0.000963 loss: 3.9603 (3.9420) grad_norm: 1.0618 (1.0601) time: 0.6330 [2021-03-26 06:42:48 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 420/1251] eta: 0:08:47 lr: 0.000963 loss: 3.6369 (3.9309) grad_norm: 1.1113 (1.0631) time: 0.6276 [2021-03-26 06:42:55 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 430/1251] eta: 0:08:41 lr: 0.000963 loss: 3.6369 (3.9333) grad_norm: 1.0648 (1.0615) time: 0.6217 [2021-03-26 06:43:01 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 440/1251] eta: 0:08:34 lr: 0.000963 loss: 4.0031 (3.9318) grad_norm: 0.9676 (1.0612) time: 0.6227 [2021-03-26 06:43:07 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 450/1251] eta: 0:08:28 lr: 0.000963 loss: 3.6642 (3.9254) grad_norm: 1.0255 (1.0611) time: 0.6250 [2021-03-26 06:43:13 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 460/1251] eta: 0:08:21 lr: 0.000963 loss: 3.4044 (3.9177) grad_norm: 0.9847 (1.0590) time: 0.6250 [2021-03-26 06:43:20 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 470/1251] eta: 0:08:15 lr: 0.000963 loss: 3.5155 (3.9135) grad_norm: 0.9228 (1.0569) time: 0.6233 [2021-03-26 06:43:26 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 480/1251] eta: 0:08:08 lr: 0.000963 loss: 4.0437 (3.9185) grad_norm: 0.9517 (1.0555) time: 0.6211 [2021-03-26 06:43:32 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 490/1251] eta: 0:08:02 lr: 0.000963 loss: 4.1873 (3.9239) grad_norm: 0.9874 (1.0547) time: 0.6228 [2021-03-26 06:43:38 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 500/1251] eta: 0:07:55 lr: 0.000963 loss: 4.2466 (3.9293) grad_norm: 1.0085 (1.0543) time: 0.6240 [2021-03-26 06:43:45 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 510/1251] eta: 0:07:49 lr: 0.000963 loss: 4.2808 (3.9319) grad_norm: 0.9968 (1.0537) time: 0.6248 [2021-03-26 06:43:51 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 520/1251] eta: 0:07:42 lr: 0.000962 loss: 4.2046 (3.9296) grad_norm: 1.0074 (1.0546) time: 0.6262 [2021-03-26 06:43:57 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 530/1251] eta: 0:07:36 lr: 0.000962 loss: 4.0141 (3.9311) grad_norm: 1.0737 (1.0562) time: 0.6305 [2021-03-26 06:44:03 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 540/1251] eta: 0:07:29 lr: 0.000962 loss: 4.0141 (3.9345) grad_norm: 1.0897 (1.0565) time: 0.6314 [2021-03-26 06:44:10 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 550/1251] eta: 0:07:23 lr: 0.000962 loss: 4.0619 (3.9360) grad_norm: 0.9754 (1.0566) time: 0.6332 [2021-03-26 06:44:16 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 560/1251] eta: 0:07:17 lr: 0.000962 loss: 4.1007 (3.9355) grad_norm: 0.9455 (1.0558) time: 0.6319 [2021-03-26 06:44:22 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 570/1251] eta: 0:07:10 lr: 0.000962 loss: 4.1996 (3.9338) grad_norm: 0.9455 (1.0544) time: 0.6232 [2021-03-26 06:44:29 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 580/1251] eta: 0:07:04 lr: 0.000962 loss: 4.0493 (3.9334) grad_norm: 1.0147 (1.0544) time: 0.6264 [2021-03-26 06:44:35 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 590/1251] eta: 0:06:58 lr: 0.000962 loss: 3.7614 (3.9294) grad_norm: 1.0185 (1.0533) time: 0.6272 [2021-03-26 06:44:41 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 600/1251] eta: 0:06:51 lr: 0.000962 loss: 4.0341 (3.9327) grad_norm: 0.9874 (1.0536) time: 0.6243 [2021-03-26 06:44:47 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 610/1251] eta: 0:06:45 lr: 0.000962 loss: 4.0601 (3.9321) grad_norm: 0.9897 (1.0546) time: 0.6231 [2021-03-26 06:44:54 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 620/1251] eta: 0:06:38 lr: 0.000962 loss: 3.8531 (3.9298) grad_norm: 1.0054 (1.0546) time: 0.6229 [2021-03-26 06:45:00 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 630/1251] eta: 0:06:32 lr: 0.000962 loss: 3.6370 (3.9255) grad_norm: 0.9948 (1.0533) time: 0.6207 [2021-03-26 06:45:06 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 640/1251] eta: 0:06:25 lr: 0.000962 loss: 4.1902 (3.9282) grad_norm: 1.0087 (1.0534) time: 0.6218 [2021-03-26 06:45:12 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 650/1251] eta: 0:06:19 lr: 0.000962 loss: 4.2426 (3.9305) grad_norm: 1.0087 (1.0527) time: 0.6318 [2021-03-26 06:45:19 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 660/1251] eta: 0:06:13 lr: 0.000962 loss: 4.0429 (3.9328) grad_norm: 0.9894 (1.0519) time: 0.6255 [2021-03-26 06:45:25 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 670/1251] eta: 0:06:06 lr: 0.000962 loss: 3.9465 (3.9333) grad_norm: 0.9671 (1.0507) time: 0.6163 [2021-03-26 06:45:31 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 680/1251] eta: 0:06:00 lr: 0.000962 loss: 4.0538 (3.9364) grad_norm: 0.9784 (1.0501) time: 0.6202 [2021-03-26 06:45:37 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 690/1251] eta: 0:05:54 lr: 0.000962 loss: 3.9660 (3.9348) grad_norm: 1.0914 (1.0524) time: 0.6286 [2021-03-26 06:45:43 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 700/1251] eta: 0:05:47 lr: 0.000962 loss: 3.6487 (3.9304) grad_norm: 1.0184 (1.0506) time: 0.6257 [2021-03-26 06:45:50 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 710/1251] eta: 0:05:41 lr: 0.000962 loss: 3.9258 (3.9320) grad_norm: 0.9932 (1.0516) time: 0.6205 [2021-03-26 06:45:56 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 720/1251] eta: 0:05:34 lr: 0.000962 loss: 4.1280 (3.9357) grad_norm: 1.1026 (1.0523) time: 0.6211 [2021-03-26 06:46:02 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 730/1251] eta: 0:05:28 lr: 0.000962 loss: 4.1348 (3.9369) grad_norm: 1.0032 (1.0510) time: 0.6220 [2021-03-26 06:46:09 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 740/1251] eta: 0:05:22 lr: 0.000962 loss: 4.1691 (3.9383) grad_norm: 0.9879 (1.0503) time: 0.6378 [2021-03-26 06:46:15 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 750/1251] eta: 0:05:16 lr: 0.000962 loss: 4.0467 (3.9382) grad_norm: 1.0441 (1.0510) time: 0.6374 [2021-03-26 06:46:21 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 760/1251] eta: 0:05:09 lr: 0.000962 loss: 3.9992 (3.9380) grad_norm: 1.0168 (1.0504) time: 0.6276 [2021-03-26 06:46:27 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 770/1251] eta: 0:05:03 lr: 0.000962 loss: 3.8229 (3.9359) grad_norm: 1.0168 (1.0518) time: 0.6292 [2021-03-26 06:46:34 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 780/1251] eta: 0:04:57 lr: 0.000962 loss: 3.6241 (3.9328) grad_norm: 1.0538 (1.0531) time: 0.6297 [2021-03-26 06:46:40 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 790/1251] eta: 0:04:50 lr: 0.000962 loss: 3.9381 (3.9324) grad_norm: 1.0538 (1.0534) time: 0.6315 [2021-03-26 06:46:46 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 800/1251] eta: 0:04:44 lr: 0.000962 loss: 4.0358 (3.9358) grad_norm: 0.9907 (1.0524) time: 0.6257 [2021-03-26 06:46:53 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 810/1251] eta: 0:04:38 lr: 0.000962 loss: 4.0511 (3.9344) grad_norm: 0.9907 (1.0521) time: 0.6212 [2021-03-26 06:46:59 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 820/1251] eta: 0:04:31 lr: 0.000962 loss: 4.0689 (3.9355) grad_norm: 0.9464 (1.0509) time: 0.6184 [2021-03-26 06:47:05 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 830/1251] eta: 0:04:25 lr: 0.000962 loss: 4.1196 (3.9351) grad_norm: 0.9402 (1.0500) time: 0.6151 [2021-03-26 06:47:11 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 840/1251] eta: 0:04:19 lr: 0.000962 loss: 3.5503 (3.9298) grad_norm: 1.0223 (1.0511) time: 0.6244 [2021-03-26 06:47:17 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 850/1251] eta: 0:04:12 lr: 0.000962 loss: 4.0563 (3.9306) grad_norm: 1.0918 (1.0513) time: 0.6218 [2021-03-26 06:47:23 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 860/1251] eta: 0:04:06 lr: 0.000962 loss: 4.1057 (3.9301) grad_norm: 1.0294 (1.0516) time: 0.6131 [2021-03-26 06:47:30 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 870/1251] eta: 0:03:59 lr: 0.000962 loss: 3.9555 (3.9310) grad_norm: 0.9694 (1.0505) time: 0.6155 [2021-03-26 06:47:36 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 880/1251] eta: 0:03:53 lr: 0.000962 loss: 4.0841 (3.9323) grad_norm: 0.9694 (1.0504) time: 0.6251 [2021-03-26 06:47:42 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 890/1251] eta: 0:03:47 lr: 0.000962 loss: 4.0841 (3.9323) grad_norm: 0.9657 (1.0499) time: 0.6247 [2021-03-26 06:47:48 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 900/1251] eta: 0:03:40 lr: 0.000962 loss: 4.0176 (3.9328) grad_norm: 0.9921 (1.0511) time: 0.6159 [2021-03-26 06:47:55 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 910/1251] eta: 0:03:34 lr: 0.000962 loss: 3.7988 (3.9286) grad_norm: 1.0254 (1.0507) time: 0.6218 [2021-03-26 06:48:01 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 920/1251] eta: 0:03:28 lr: 0.000962 loss: 3.6487 (3.9279) grad_norm: 0.9657 (1.0504) time: 0.6275 [2021-03-26 06:48:07 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 930/1251] eta: 0:03:22 lr: 0.000962 loss: 4.2523 (3.9302) grad_norm: 1.0628 (1.0519) time: 0.6290 [2021-03-26 06:48:13 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 940/1251] eta: 0:03:15 lr: 0.000962 loss: 4.2934 (3.9331) grad_norm: 1.0674 (1.0519) time: 0.6270 [2021-03-26 06:48:20 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 950/1251] eta: 0:03:09 lr: 0.000962 loss: 3.9954 (3.9323) grad_norm: 0.9930 (1.0520) time: 0.6231 [2021-03-26 06:48:26 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 960/1251] eta: 0:03:03 lr: 0.000962 loss: 3.9678 (3.9312) grad_norm: 0.9853 (1.0514) time: 0.6193 [2021-03-26 06:48:32 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 970/1251] eta: 0:02:56 lr: 0.000962 loss: 3.9346 (3.9318) grad_norm: 1.0523 (1.0518) time: 0.6224 [2021-03-26 06:48:38 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 980/1251] eta: 0:02:50 lr: 0.000962 loss: 4.0326 (3.9319) grad_norm: 1.0520 (1.0513) time: 0.6233 [2021-03-26 06:48:45 swin_base_patch4_window7_224] INFO: Epoch: [37] [ 990/1251] eta: 0:02:44 lr: 0.000962 loss: 4.1755 (3.9347) grad_norm: 1.0557 (1.0522) time: 0.6263 [2021-03-26 06:48:51 swin_base_patch4_window7_224] INFO: Epoch: [37] [1000/1251] eta: 0:02:37 lr: 0.000962 loss: 4.0950 (3.9353) grad_norm: 1.0909 (1.0518) time: 0.6255 [2021-03-26 06:48:57 swin_base_patch4_window7_224] INFO: Epoch: [37] [1010/1251] eta: 0:02:31 lr: 0.000962 loss: 3.7186 (3.9328) grad_norm: 1.0048 (1.0512) time: 0.6179 [2021-03-26 06:49:03 swin_base_patch4_window7_224] INFO: Epoch: [37] [1020/1251] eta: 0:02:25 lr: 0.000962 loss: 3.9469 (3.9337) grad_norm: 1.0255 (1.0511) time: 0.6253 [2021-03-26 06:49:09 swin_base_patch4_window7_224] INFO: Epoch: [37] [1030/1251] eta: 0:02:18 lr: 0.000962 loss: 4.0381 (3.9335) grad_norm: 1.0257 (1.0510) time: 0.6233 [2021-03-26 06:49:16 swin_base_patch4_window7_224] INFO: Epoch: [37] [1040/1251] eta: 0:02:12 lr: 0.000962 loss: 4.1817 (3.9351) grad_norm: 1.0787 (1.0520) time: 0.6283 [2021-03-26 06:49:22 swin_base_patch4_window7_224] INFO: Epoch: [37] [1050/1251] eta: 0:02:06 lr: 0.000962 loss: 4.0518 (3.9338) grad_norm: 1.0139 (1.0514) time: 0.6294 [2021-03-26 06:49:28 swin_base_patch4_window7_224] INFO: Epoch: [37] [1060/1251] eta: 0:02:00 lr: 0.000962 loss: 3.9335 (3.9356) grad_norm: 0.9896 (1.0515) time: 0.6216 [2021-03-26 06:49:35 swin_base_patch4_window7_224] INFO: Epoch: [37] [1070/1251] eta: 0:01:53 lr: 0.000962 loss: 4.1500 (3.9381) grad_norm: 0.9951 (1.0510) time: 0.6277 [2021-03-26 06:49:41 swin_base_patch4_window7_224] INFO: Epoch: [37] [1080/1251] eta: 0:01:47 lr: 0.000962 loss: 4.1787 (3.9398) grad_norm: 0.9726 (1.0505) time: 0.6234 [2021-03-26 06:49:47 swin_base_patch4_window7_224] INFO: Epoch: [37] [1090/1251] eta: 0:01:41 lr: 0.000962 loss: 3.9312 (3.9375) grad_norm: 1.0109 (1.0502) time: 0.6206 [2021-03-26 06:49:53 swin_base_patch4_window7_224] INFO: Epoch: [37] [1100/1251] eta: 0:01:34 lr: 0.000962 loss: 3.7362 (3.9372) grad_norm: 1.0198 (1.0501) time: 0.6221 [2021-03-26 06:49:59 swin_base_patch4_window7_224] INFO: Epoch: [37] [1110/1251] eta: 0:01:28 lr: 0.000962 loss: 3.8214 (3.9375) grad_norm: 1.0446 (1.0504) time: 0.6257 [2021-03-26 06:50:06 swin_base_patch4_window7_224] INFO: Epoch: [37] [1120/1251] eta: 0:01:22 lr: 0.000962 loss: 4.0293 (3.9375) grad_norm: 1.1244 (1.0519) time: 0.6317 [2021-03-26 06:50:12 swin_base_patch4_window7_224] INFO: Epoch: [37] [1130/1251] eta: 0:01:16 lr: 0.000962 loss: 4.0594 (3.9403) grad_norm: 1.0880 (1.0517) time: 0.6296 [2021-03-26 06:50:18 swin_base_patch4_window7_224] INFO: Epoch: [37] [1140/1251] eta: 0:01:09 lr: 0.000962 loss: 3.9745 (3.9391) grad_norm: 1.0201 (1.0515) time: 0.6296 [2021-03-26 06:50:25 swin_base_patch4_window7_224] INFO: Epoch: [37] [1150/1251] eta: 0:01:03 lr: 0.000961 loss: 3.9745 (3.9401) grad_norm: 0.9909 (1.0515) time: 0.6249 [2021-03-26 06:50:31 swin_base_patch4_window7_224] INFO: Epoch: [37] [1160/1251] eta: 0:00:57 lr: 0.000961 loss: 4.0970 (3.9408) grad_norm: 0.9702 (1.0506) time: 0.6152 [2021-03-26 06:50:37 swin_base_patch4_window7_224] INFO: Epoch: [37] [1170/1251] eta: 0:00:50 lr: 0.000961 loss: 4.0182 (3.9387) grad_norm: 0.9941 (1.0508) time: 0.6187 [2021-03-26 06:50:43 swin_base_patch4_window7_224] INFO: Epoch: [37] [1180/1251] eta: 0:00:44 lr: 0.000961 loss: 4.0234 (3.9398) grad_norm: 1.0562 (1.0505) time: 0.6197 [2021-03-26 06:50:49 swin_base_patch4_window7_224] INFO: Epoch: [37] [1190/1251] eta: 0:00:38 lr: 0.000961 loss: 4.3703 (3.9429) grad_norm: 0.9601 (1.0499) time: 0.6170 [2021-03-26 06:50:55 swin_base_patch4_window7_224] INFO: Epoch: [37] [1200/1251] eta: 0:00:32 lr: 0.000961 loss: 4.3123 (3.9414) grad_norm: 0.9835 (1.0496) time: 0.6181 [2021-03-26 06:51:02 swin_base_patch4_window7_224] INFO: Epoch: [37] [1210/1251] eta: 0:00:25 lr: 0.000961 loss: 3.8272 (3.9402) grad_norm: 1.0071 (inf) time: 0.6140 [2021-03-26 06:51:08 swin_base_patch4_window7_224] INFO: Epoch: [37] [1220/1251] eta: 0:00:19 lr: 0.000961 loss: 3.9423 (3.9394) grad_norm: 1.0389 (inf) time: 0.6196 [2021-03-26 06:51:14 swin_base_patch4_window7_224] INFO: Epoch: [37] [1230/1251] eta: 0:00:13 lr: 0.000961 loss: 3.8426 (3.9381) grad_norm: 1.0231 (inf) time: 0.6257 [2021-03-26 06:51:20 swin_base_patch4_window7_224] INFO: Epoch: [37] [1240/1251] eta: 0:00:06 lr: 0.000961 loss: 4.0413 (3.9396) grad_norm: 0.9716 (inf) time: 0.6182 [2021-03-26 06:51:26 swin_base_patch4_window7_224] INFO: Epoch: [37] [1250/1251] eta: 0:00:00 lr: 0.000961 loss: 4.1670 (3.9405) grad_norm: 0.9628 (inf) time: 0.6115 [2021-03-26 06:51:30 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:27 loss: 1.4625 (1.4625) acc1: 64.0625 (64.0625) acc5: 84.3750 (84.3750) [2021-03-26 06:51:33 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.2552 (1.2677) acc1: 68.7500 (70.0284) acc5: 92.1875 (91.1932) [2021-03-26 06:51:34 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.3630 (1.3636) acc1: 67.1875 (68.0804) acc5: 90.6250 (89.6577) [2021-03-26 06:51:38 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.3941 (1.3517) acc1: 67.1875 (69.1028) acc5: 89.0625 (89.3649) [2021-03-26 06:51:40 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2905 (1.3348) acc1: 68.7500 (69.2835) acc5: 89.0625 (89.6341) [2021-03-26 06:51:41 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2824 (1.3319) acc1: 68.7500 (69.4720) acc5: 90.5660 (89.5360) [2021-03-26 06:51:44 swin_base_patch4_window7_224] INFO: * Acc@1 70.100 Acc@5 90.278 loss 1.298 [2021-03-26 06:51:44 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 70.1% [2021-03-26 06:51:44 swin_base_patch4_window7_224] INFO: Max accuracy: 70.10% [2021-03-26 06:51:49 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 0/1251] eta: 1:31:31 lr: 0.000961 loss: 4.1942 (4.1942) grad_norm: 0.8957 (0.8957) time: 4.3894 [2021-03-26 06:51:55 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 10/1251] eta: 0:20:12 lr: 0.000961 loss: 3.8967 (3.8235) grad_norm: 0.9394 (0.9558) time: 0.9769 [2021-03-26 06:52:01 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 20/1251] eta: 0:16:39 lr: 0.000961 loss: 3.9413 (3.9209) grad_norm: 1.0177 (1.0661) time: 0.6335 [2021-03-26 06:52:08 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 30/1251] eta: 0:15:24 lr: 0.000961 loss: 3.9951 (3.8943) grad_norm: 1.1499 (1.1085) time: 0.6360 [2021-03-26 06:52:14 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 40/1251] eta: 0:14:38 lr: 0.000961 loss: 3.9951 (3.8700) grad_norm: 1.0982 (1.1079) time: 0.6334 [2021-03-26 06:52:20 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 50/1251] eta: 0:14:07 lr: 0.000961 loss: 3.9784 (3.8619) grad_norm: 1.0751 (1.1110) time: 0.6254 [2021-03-26 06:52:26 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 60/1251] eta: 0:13:44 lr: 0.000961 loss: 4.1210 (3.9142) grad_norm: 0.9969 (1.1032) time: 0.6248 [2021-03-26 06:52:33 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 70/1251] eta: 0:13:26 lr: 0.000961 loss: 4.0700 (3.9316) grad_norm: 0.9969 (1.0905) time: 0.6258 [2021-03-26 06:52:39 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 80/1251] eta: 0:13:11 lr: 0.000961 loss: 3.7995 (3.9122) grad_norm: 1.0449 (1.0930) time: 0.6253 [2021-03-26 06:52:45 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 90/1251] eta: 0:12:59 lr: 0.000961 loss: 3.7984 (3.9138) grad_norm: 1.0457 (1.0884) time: 0.6314 [2021-03-26 06:52:52 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 100/1251] eta: 0:12:47 lr: 0.000961 loss: 3.9565 (3.9192) grad_norm: 1.0348 (1.0875) time: 0.6315 [2021-03-26 06:52:58 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 110/1251] eta: 0:12:35 lr: 0.000961 loss: 4.0753 (3.9270) grad_norm: 1.0700 (1.0835) time: 0.6212 [2021-03-26 06:53:04 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 120/1251] eta: 0:12:25 lr: 0.000961 loss: 3.9777 (3.9179) grad_norm: 1.0285 (1.0847) time: 0.6204 [2021-03-26 06:53:10 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 130/1251] eta: 0:12:16 lr: 0.000961 loss: 3.9777 (3.9244) grad_norm: 1.0285 (1.0809) time: 0.6243 [2021-03-26 06:53:16 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 140/1251] eta: 0:12:07 lr: 0.000961 loss: 4.0447 (3.9193) grad_norm: 1.0371 (1.0776) time: 0.6268 [2021-03-26 06:53:23 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 150/1251] eta: 0:11:58 lr: 0.000961 loss: 4.0447 (3.9193) grad_norm: 1.0212 (1.0752) time: 0.6291 [2021-03-26 06:53:29 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 160/1251] eta: 0:11:50 lr: 0.000961 loss: 4.0105 (3.9149) grad_norm: 0.9959 (1.0729) time: 0.6249 [2021-03-26 06:53:35 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 170/1251] eta: 0:11:42 lr: 0.000961 loss: 4.0105 (3.9260) grad_norm: 0.9959 (1.0715) time: 0.6243 [2021-03-26 06:53:42 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 180/1251] eta: 0:11:34 lr: 0.000961 loss: 4.3261 (3.9410) grad_norm: 1.0147 (1.0734) time: 0.6272 [2021-03-26 06:53:48 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 190/1251] eta: 0:11:26 lr: 0.000961 loss: 4.2449 (3.9441) grad_norm: 1.0011 (1.0688) time: 0.6268 [2021-03-26 06:53:54 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 200/1251] eta: 0:11:19 lr: 0.000961 loss: 4.1554 (3.9469) grad_norm: 1.0199 (1.0714) time: 0.6291 [2021-03-26 06:54:00 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 210/1251] eta: 0:11:11 lr: 0.000961 loss: 4.1215 (3.9533) grad_norm: 0.9921 (1.0670) time: 0.6224 [2021-03-26 06:54:06 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 220/1251] eta: 0:11:03 lr: 0.000961 loss: 4.0675 (3.9593) grad_norm: 0.9502 (1.0632) time: 0.6198 [2021-03-26 06:54:13 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 230/1251] eta: 0:10:56 lr: 0.000961 loss: 4.0269 (3.9569) grad_norm: 0.9744 (1.0621) time: 0.6252 [2021-03-26 06:54:19 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 240/1251] eta: 0:10:49 lr: 0.000961 loss: 4.0468 (3.9651) grad_norm: 1.0231 (1.0602) time: 0.6249 [2021-03-26 06:54:25 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 250/1251] eta: 0:10:42 lr: 0.000961 loss: 4.1067 (3.9738) grad_norm: 1.0059 (1.0580) time: 0.6209 [2021-03-26 06:54:31 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 260/1251] eta: 0:10:35 lr: 0.000961 loss: 4.3182 (3.9894) grad_norm: 1.0154 (1.0585) time: 0.6211 [2021-03-26 06:54:38 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 270/1251] eta: 0:10:27 lr: 0.000961 loss: 4.1926 (3.9853) grad_norm: 1.0389 (1.0590) time: 0.6228 [2021-03-26 06:54:44 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 280/1251] eta: 0:10:21 lr: 0.000961 loss: 3.7460 (3.9771) grad_norm: 1.0140 (1.0581) time: 0.6257 [2021-03-26 06:54:50 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 290/1251] eta: 0:10:13 lr: 0.000961 loss: 3.8454 (3.9804) grad_norm: 0.9955 (1.0556) time: 0.6205 [2021-03-26 06:54:56 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 300/1251] eta: 0:10:06 lr: 0.000961 loss: 3.8319 (3.9707) grad_norm: 0.9678 (1.0540) time: 0.6150 [2021-03-26 06:55:02 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 310/1251] eta: 0:09:59 lr: 0.000961 loss: 3.7981 (3.9700) grad_norm: 0.9726 (1.0529) time: 0.6188 [2021-03-26 06:55:09 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 320/1251] eta: 0:09:53 lr: 0.000961 loss: 4.0086 (3.9648) grad_norm: 0.9939 (1.0513) time: 0.6237 [2021-03-26 06:55:15 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 330/1251] eta: 0:09:46 lr: 0.000961 loss: 4.0745 (3.9712) grad_norm: 1.0396 (1.0543) time: 0.6292 [2021-03-26 06:55:21 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 340/1251] eta: 0:09:40 lr: 0.000961 loss: 4.1896 (3.9744) grad_norm: 1.0745 (1.0538) time: 0.6308 [2021-03-26 06:55:28 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 350/1251] eta: 0:09:33 lr: 0.000961 loss: 4.1531 (3.9713) grad_norm: 0.9585 (1.0523) time: 0.6258 [2021-03-26 06:55:34 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 360/1251] eta: 0:09:26 lr: 0.000961 loss: 3.9858 (3.9738) grad_norm: 0.9813 (1.0523) time: 0.6230 [2021-03-26 06:55:40 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 370/1251] eta: 0:09:19 lr: 0.000961 loss: 4.1628 (3.9778) grad_norm: 0.9837 (1.0512) time: 0.6216 [2021-03-26 06:55:46 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 380/1251] eta: 0:09:13 lr: 0.000961 loss: 4.1004 (3.9763) grad_norm: 0.9778 (1.0513) time: 0.6187 [2021-03-26 06:55:53 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 390/1251] eta: 0:09:06 lr: 0.000961 loss: 3.9288 (3.9709) grad_norm: 1.0711 (1.0535) time: 0.6271 [2021-03-26 06:55:59 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 400/1251] eta: 0:09:00 lr: 0.000961 loss: 3.8805 (3.9706) grad_norm: 1.0352 (1.0518) time: 0.6257 [2021-03-26 06:56:05 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 410/1251] eta: 0:08:53 lr: 0.000961 loss: 4.0204 (3.9683) grad_norm: 0.9292 (1.0489) time: 0.6194 [2021-03-26 06:56:11 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 420/1251] eta: 0:08:46 lr: 0.000961 loss: 4.1043 (3.9699) grad_norm: 0.9229 (1.0487) time: 0.6209 [2021-03-26 06:56:17 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 430/1251] eta: 0:08:40 lr: 0.000961 loss: 3.9696 (3.9666) grad_norm: 1.0282 (1.0521) time: 0.6242 [2021-03-26 06:56:24 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 440/1251] eta: 0:08:33 lr: 0.000961 loss: 3.8133 (3.9617) grad_norm: 1.0360 (1.0526) time: 0.6254 [2021-03-26 06:56:30 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 450/1251] eta: 0:08:27 lr: 0.000961 loss: 3.9245 (3.9639) grad_norm: 1.0292 (1.0549) time: 0.6247 [2021-03-26 06:56:36 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 460/1251] eta: 0:08:21 lr: 0.000961 loss: 4.0300 (3.9626) grad_norm: 1.0725 (1.0560) time: 0.6289 [2021-03-26 06:56:42 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 470/1251] eta: 0:08:14 lr: 0.000961 loss: 4.1057 (3.9654) grad_norm: 1.0348 (1.0543) time: 0.6248 [2021-03-26 06:56:49 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 480/1251] eta: 0:08:07 lr: 0.000961 loss: 4.2451 (3.9703) grad_norm: 0.9565 (1.0541) time: 0.6187 [2021-03-26 06:56:55 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 490/1251] eta: 0:08:01 lr: 0.000961 loss: 3.9413 (3.9646) grad_norm: 1.0113 (1.0532) time: 0.6192 [2021-03-26 06:57:01 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 500/1251] eta: 0:07:54 lr: 0.000961 loss: 3.9406 (3.9684) grad_norm: 1.0309 (1.0541) time: 0.6193 [2021-03-26 06:57:07 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 510/1251] eta: 0:07:48 lr: 0.000960 loss: 3.9777 (3.9684) grad_norm: 0.9528 (1.0517) time: 0.6150 [2021-03-26 06:57:13 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 520/1251] eta: 0:07:41 lr: 0.000960 loss: 3.9252 (3.9675) grad_norm: 0.9113 (1.0509) time: 0.6222 [2021-03-26 06:57:20 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 530/1251] eta: 0:07:35 lr: 0.000960 loss: 3.9713 (3.9661) grad_norm: 1.0051 (1.0519) time: 0.6325 [2021-03-26 06:57:26 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 540/1251] eta: 0:07:29 lr: 0.000960 loss: 3.9713 (3.9630) grad_norm: 1.0610 (1.0519) time: 0.6290 [2021-03-26 06:57:32 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 550/1251] eta: 0:07:22 lr: 0.000960 loss: 3.8636 (3.9619) grad_norm: 0.9645 (1.0504) time: 0.6345 [2021-03-26 06:57:39 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 560/1251] eta: 0:07:16 lr: 0.000960 loss: 3.6882 (3.9560) grad_norm: 0.9696 (1.0502) time: 0.6340 [2021-03-26 06:57:45 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 570/1251] eta: 0:07:10 lr: 0.000960 loss: 3.8660 (3.9568) grad_norm: 1.0065 (1.0513) time: 0.6291 [2021-03-26 06:57:51 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 580/1251] eta: 0:07:03 lr: 0.000960 loss: 3.9981 (3.9547) grad_norm: 1.0065 (1.0509) time: 0.6280 [2021-03-26 06:57:57 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 590/1251] eta: 0:06:57 lr: 0.000960 loss: 4.0485 (3.9561) grad_norm: 0.9948 (1.0506) time: 0.6211 [2021-03-26 06:58:04 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 600/1251] eta: 0:06:50 lr: 0.000960 loss: 4.0485 (3.9530) grad_norm: 0.9753 (1.0492) time: 0.6182 [2021-03-26 06:58:10 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 610/1251] eta: 0:06:44 lr: 0.000960 loss: 3.7941 (3.9497) grad_norm: 0.9535 (1.0482) time: 0.6166 [2021-03-26 06:58:16 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 620/1251] eta: 0:06:37 lr: 0.000960 loss: 4.0282 (3.9527) grad_norm: 0.9822 (1.0482) time: 0.6141 [2021-03-26 06:58:22 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 630/1251] eta: 0:06:31 lr: 0.000960 loss: 4.0628 (3.9536) grad_norm: 1.1410 (1.0492) time: 0.6204 [2021-03-26 06:58:28 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 640/1251] eta: 0:06:25 lr: 0.000960 loss: 3.9178 (3.9502) grad_norm: 1.1423 (1.0514) time: 0.6241 [2021-03-26 06:58:35 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 650/1251] eta: 0:06:19 lr: 0.000960 loss: 4.0582 (3.9531) grad_norm: 1.0489 (1.0517) time: 0.6327 [2021-03-26 06:58:41 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 660/1251] eta: 0:06:12 lr: 0.000960 loss: 4.0120 (3.9470) grad_norm: 1.0116 (1.0512) time: 0.6284 [2021-03-26 06:58:47 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 670/1251] eta: 0:06:06 lr: 0.000960 loss: 3.9084 (3.9486) grad_norm: 0.9871 (1.0508) time: 0.6171 [2021-03-26 06:58:53 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 680/1251] eta: 0:05:59 lr: 0.000960 loss: 4.2436 (3.9518) grad_norm: 1.0203 (1.0510) time: 0.6256 [2021-03-26 06:59:00 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 690/1251] eta: 0:05:53 lr: 0.000960 loss: 4.0415 (3.9515) grad_norm: 1.0203 (1.0505) time: 0.6263 [2021-03-26 06:59:06 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 700/1251] eta: 0:05:47 lr: 0.000960 loss: 4.0585 (3.9560) grad_norm: 1.0304 (1.0507) time: 0.6266 [2021-03-26 06:59:12 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 710/1251] eta: 0:05:40 lr: 0.000960 loss: 4.1415 (3.9574) grad_norm: 1.0279 (1.0505) time: 0.6290 [2021-03-26 06:59:18 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 720/1251] eta: 0:05:34 lr: 0.000960 loss: 3.9315 (3.9560) grad_norm: 0.9533 (1.0498) time: 0.6239 [2021-03-26 06:59:25 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 730/1251] eta: 0:05:28 lr: 0.000960 loss: 3.8746 (3.9525) grad_norm: 0.9630 (1.0493) time: 0.6245 [2021-03-26 06:59:31 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 740/1251] eta: 0:05:22 lr: 0.000960 loss: 3.8759 (3.9523) grad_norm: 1.0290 (1.0488) time: 0.6356 [2021-03-26 06:59:38 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 750/1251] eta: 0:05:15 lr: 0.000960 loss: 4.1589 (3.9565) grad_norm: 1.0048 (1.0489) time: 0.6368 [2021-03-26 06:59:44 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 760/1251] eta: 0:05:09 lr: 0.000960 loss: 4.2201 (3.9540) grad_norm: 1.0431 (1.0505) time: 0.6306 [2021-03-26 06:59:50 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 770/1251] eta: 0:05:03 lr: 0.000960 loss: 3.8158 (3.9518) grad_norm: 1.1309 (1.0525) time: 0.6301 [2021-03-26 06:59:56 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 780/1251] eta: 0:04:56 lr: 0.000960 loss: 3.5596 (3.9479) grad_norm: 1.1286 (1.0529) time: 0.6269 [2021-03-26 07:00:03 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 790/1251] eta: 0:04:50 lr: 0.000960 loss: 3.8781 (3.9464) grad_norm: 1.0332 (1.0530) time: 0.6253 [2021-03-26 07:00:09 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 800/1251] eta: 0:04:44 lr: 0.000960 loss: 3.9981 (3.9498) grad_norm: 0.9952 (1.0520) time: 0.6247 [2021-03-26 07:00:15 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 810/1251] eta: 0:04:37 lr: 0.000960 loss: 3.9981 (3.9481) grad_norm: 0.9762 (1.0518) time: 0.6225 [2021-03-26 07:00:21 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 820/1251] eta: 0:04:31 lr: 0.000960 loss: 3.9823 (3.9480) grad_norm: 1.0505 (1.0522) time: 0.6268 [2021-03-26 07:00:28 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 830/1251] eta: 0:04:25 lr: 0.000960 loss: 4.1484 (3.9502) grad_norm: 1.0586 (1.0524) time: 0.6294 [2021-03-26 07:00:34 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 840/1251] eta: 0:04:18 lr: 0.000960 loss: 4.1983 (3.9515) grad_norm: 1.0387 (1.0525) time: 0.6325 [2021-03-26 07:00:40 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 850/1251] eta: 0:04:12 lr: 0.000960 loss: 4.1530 (3.9504) grad_norm: 1.0320 (1.0521) time: 0.6295 [2021-03-26 07:00:46 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 860/1251] eta: 0:04:06 lr: 0.000960 loss: 4.1530 (3.9540) grad_norm: 1.0320 (1.0517) time: 0.6204 [2021-03-26 07:00:53 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 870/1251] eta: 0:03:59 lr: 0.000960 loss: 4.2568 (3.9539) grad_norm: 0.9951 (1.0507) time: 0.6199 [2021-03-26 07:00:59 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 880/1251] eta: 0:03:53 lr: 0.000960 loss: 4.0178 (3.9535) grad_norm: 0.9951 (1.0511) time: 0.6205 [2021-03-26 07:01:05 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 890/1251] eta: 0:03:47 lr: 0.000960 loss: 3.8314 (3.9514) grad_norm: 1.0321 (1.0511) time: 0.6191 [2021-03-26 07:01:11 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 900/1251] eta: 0:03:40 lr: 0.000960 loss: 4.2103 (3.9562) grad_norm: 0.9679 (1.0506) time: 0.6226 [2021-03-26 07:01:18 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 910/1251] eta: 0:03:34 lr: 0.000960 loss: 4.1974 (3.9580) grad_norm: 0.9916 (1.0501) time: 0.6225 [2021-03-26 07:01:24 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 920/1251] eta: 0:03:28 lr: 0.000960 loss: 3.9204 (3.9556) grad_norm: 1.0305 (1.0503) time: 0.6260 [2021-03-26 07:01:30 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 930/1251] eta: 0:03:21 lr: 0.000960 loss: 3.9737 (3.9552) grad_norm: 1.0305 (1.0495) time: 0.6279 [2021-03-26 07:01:36 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 940/1251] eta: 0:03:15 lr: 0.000960 loss: 4.0434 (3.9541) grad_norm: 1.0122 (1.0492) time: 0.6289 [2021-03-26 07:01:43 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 950/1251] eta: 0:03:09 lr: 0.000960 loss: 4.1400 (3.9551) grad_norm: 1.0202 (1.0492) time: 0.6284 [2021-03-26 07:01:49 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 960/1251] eta: 0:03:03 lr: 0.000960 loss: 4.0933 (3.9545) grad_norm: 1.0077 (1.0494) time: 0.6246 [2021-03-26 07:01:55 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 970/1251] eta: 0:02:56 lr: 0.000960 loss: 4.1179 (3.9553) grad_norm: 1.0247 (1.0500) time: 0.6274 [2021-03-26 07:02:01 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 980/1251] eta: 0:02:50 lr: 0.000960 loss: 4.1179 (3.9556) grad_norm: 1.0039 (1.0492) time: 0.6211 [2021-03-26 07:02:08 swin_base_patch4_window7_224] INFO: Epoch: [38] [ 990/1251] eta: 0:02:44 lr: 0.000960 loss: 3.8792 (3.9530) grad_norm: 1.0163 (1.0496) time: 0.6250 [2021-03-26 07:02:14 swin_base_patch4_window7_224] INFO: Epoch: [38] [1000/1251] eta: 0:02:37 lr: 0.000960 loss: 3.7204 (3.9533) grad_norm: 1.0292 (1.0494) time: 0.6292 [2021-03-26 07:02:20 swin_base_patch4_window7_224] INFO: Epoch: [38] [1010/1251] eta: 0:02:31 lr: 0.000960 loss: 3.7204 (3.9492) grad_norm: 1.0344 (1.0494) time: 0.6211 [2021-03-26 07:02:26 swin_base_patch4_window7_224] INFO: Epoch: [38] [1020/1251] eta: 0:02:25 lr: 0.000960 loss: 4.0243 (3.9510) grad_norm: 1.0439 (1.0500) time: 0.6241 [2021-03-26 07:02:33 swin_base_patch4_window7_224] INFO: Epoch: [38] [1030/1251] eta: 0:02:18 lr: 0.000960 loss: 4.0898 (3.9506) grad_norm: 0.9892 (1.0505) time: 0.6257 [2021-03-26 07:02:39 swin_base_patch4_window7_224] INFO: Epoch: [38] [1040/1251] eta: 0:02:12 lr: 0.000960 loss: 4.0299 (3.9500) grad_norm: 1.0219 (1.0513) time: 0.6258 [2021-03-26 07:02:45 swin_base_patch4_window7_224] INFO: Epoch: [38] [1050/1251] eta: 0:02:06 lr: 0.000960 loss: 4.0299 (3.9505) grad_norm: 1.0382 (1.0516) time: 0.6245 [2021-03-26 07:02:51 swin_base_patch4_window7_224] INFO: Epoch: [38] [1060/1251] eta: 0:02:00 lr: 0.000960 loss: 4.0358 (3.9488) grad_norm: 1.0712 (1.0525) time: 0.6241 [2021-03-26 07:02:58 swin_base_patch4_window7_224] INFO: Epoch: [38] [1070/1251] eta: 0:01:53 lr: 0.000960 loss: 3.9357 (3.9489) grad_norm: 1.0797 (1.0527) time: 0.6323 [2021-03-26 07:03:04 swin_base_patch4_window7_224] INFO: Epoch: [38] [1080/1251] eta: 0:01:47 lr: 0.000960 loss: 4.2091 (3.9490) grad_norm: 1.0639 (1.0528) time: 0.6280 [2021-03-26 07:03:10 swin_base_patch4_window7_224] INFO: Epoch: [38] [1090/1251] eta: 0:01:41 lr: 0.000960 loss: 4.1229 (3.9494) grad_norm: 1.0012 (1.0525) time: 0.6271 [2021-03-26 07:03:17 swin_base_patch4_window7_224] INFO: Epoch: [38] [1100/1251] eta: 0:01:34 lr: 0.000960 loss: 3.9230 (3.9467) grad_norm: 0.9941 (1.0521) time: 0.6321 [2021-03-26 07:03:23 swin_base_patch4_window7_224] INFO: Epoch: [38] [1110/1251] eta: 0:01:28 lr: 0.000960 loss: 3.7373 (3.9475) grad_norm: 1.0257 (1.0522) time: 0.6255 [2021-03-26 07:03:29 swin_base_patch4_window7_224] INFO: Epoch: [38] [1120/1251] eta: 0:01:22 lr: 0.000960 loss: 3.8532 (3.9438) grad_norm: 1.1006 (1.0527) time: 0.6265 [2021-03-26 07:03:35 swin_base_patch4_window7_224] INFO: Epoch: [38] [1130/1251] eta: 0:01:16 lr: 0.000959 loss: 3.8532 (3.9423) grad_norm: 1.0985 (1.0529) time: 0.6293 [2021-03-26 07:03:42 swin_base_patch4_window7_224] INFO: Epoch: [38] [1140/1251] eta: 0:01:09 lr: 0.000959 loss: 4.0465 (3.9428) grad_norm: 1.0292 (1.0530) time: 0.6267 [2021-03-26 07:03:48 swin_base_patch4_window7_224] INFO: Epoch: [38] [1150/1251] eta: 0:01:03 lr: 0.000959 loss: 4.0372 (3.9442) grad_norm: 1.0141 (1.0534) time: 0.6242 [2021-03-26 07:03:54 swin_base_patch4_window7_224] INFO: Epoch: [38] [1160/1251] eta: 0:00:57 lr: 0.000959 loss: 4.0047 (3.9445) grad_norm: 1.0393 (1.0537) time: 0.6201 [2021-03-26 07:04:00 swin_base_patch4_window7_224] INFO: Epoch: [38] [1170/1251] eta: 0:00:50 lr: 0.000959 loss: 3.8671 (3.9432) grad_norm: 1.0548 (1.0535) time: 0.6215 [2021-03-26 07:04:07 swin_base_patch4_window7_224] INFO: Epoch: [38] [1180/1251] eta: 0:00:44 lr: 0.000959 loss: 3.6704 (3.9393) grad_norm: 0.9971 (1.0531) time: 0.6220 [2021-03-26 07:04:13 swin_base_patch4_window7_224] INFO: Epoch: [38] [1190/1251] eta: 0:00:38 lr: 0.000959 loss: 3.6860 (3.9381) grad_norm: 0.9744 (1.0530) time: 0.6278 [2021-03-26 07:04:19 swin_base_patch4_window7_224] INFO: Epoch: [38] [1200/1251] eta: 0:00:32 lr: 0.000959 loss: 3.7620 (3.9369) grad_norm: 0.9667 (1.0522) time: 0.6258 [2021-03-26 07:04:25 swin_base_patch4_window7_224] INFO: Epoch: [38] [1210/1251] eta: 0:00:25 lr: 0.000959 loss: 4.0443 (3.9378) grad_norm: 0.9234 (1.0518) time: 0.6185 [2021-03-26 07:04:31 swin_base_patch4_window7_224] INFO: Epoch: [38] [1220/1251] eta: 0:00:19 lr: 0.000959 loss: 4.1062 (3.9384) grad_norm: 0.9234 (1.0519) time: 0.6200 [2021-03-26 07:04:38 swin_base_patch4_window7_224] INFO: Epoch: [38] [1230/1251] eta: 0:00:13 lr: 0.000959 loss: 4.0385 (3.9384) grad_norm: 1.0576 (1.0526) time: 0.6238 [2021-03-26 07:04:44 swin_base_patch4_window7_224] INFO: Epoch: [38] [1240/1251] eta: 0:00:06 lr: 0.000959 loss: 4.0385 (3.9390) grad_norm: 1.0502 (1.0528) time: 0.6220 [2021-03-26 07:04:50 swin_base_patch4_window7_224] INFO: Epoch: [38] [1250/1251] eta: 0:00:00 lr: 0.000959 loss: 3.9681 (3.9367) grad_norm: 1.0193 (1.0535) time: 0.6099 [2021-03-26 07:04:55 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:07 loss: 1.3083 (1.3083) acc1: 70.3125 (70.3125) acc5: 92.1875 (92.1875) [2021-03-26 07:04:57 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.1880 (1.2266) acc1: 71.8750 (71.0227) acc5: 92.1875 (91.7614) [2021-03-26 07:04:59 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.1880 (1.2239) acc1: 71.8750 (71.5030) acc5: 90.6250 (91.2946) [2021-03-26 07:05:01 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.2825 (1.2546) acc1: 68.7500 (70.4133) acc5: 90.6250 (91.0282) [2021-03-26 07:05:03 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.3002 (1.2721) acc1: 68.7500 (70.5030) acc5: 89.0625 (90.3582) [2021-03-26 07:05:04 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3080 (1.2928) acc1: 67.1875 (69.9520) acc5: 89.0625 (90.3360) [2021-03-26 07:05:07 swin_base_patch4_window7_224] INFO: * Acc@1 70.674 Acc@5 90.580 loss 1.265 [2021-03-26 07:05:07 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 70.7% [2021-03-26 07:05:07 swin_base_patch4_window7_224] INFO: Max accuracy: 70.67% [2021-03-26 07:05:11 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 0/1251] eta: 1:33:36 lr: 0.000959 loss: 3.4693 (3.4693) grad_norm: 0.8879 (0.8879) time: 4.4893 [2021-03-26 07:05:18 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 10/1251] eta: 0:20:26 lr: 0.000959 loss: 4.0293 (3.9549) grad_norm: 0.9572 (0.9886) time: 0.9883 [2021-03-26 07:05:24 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 20/1251] eta: 0:16:36 lr: 0.000959 loss: 4.0727 (4.0108) grad_norm: 0.9692 (0.9943) time: 0.6252 [2021-03-26 07:05:30 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 30/1251] eta: 0:15:13 lr: 0.000959 loss: 3.9777 (3.9291) grad_norm: 0.9877 (0.9982) time: 0.6164 [2021-03-26 07:05:36 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 40/1251] eta: 0:14:27 lr: 0.000959 loss: 3.6799 (3.8577) grad_norm: 0.9768 (0.9942) time: 0.6183 [2021-03-26 07:05:43 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 50/1251] eta: 0:13:58 lr: 0.000959 loss: 3.8481 (3.8613) grad_norm: 0.9946 (1.0377) time: 0.6199 [2021-03-26 07:05:49 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 60/1251] eta: 0:13:39 lr: 0.000959 loss: 3.9861 (3.8526) grad_norm: 1.1285 (1.0617) time: 0.6297 [2021-03-26 07:05:55 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 70/1251] eta: 0:13:23 lr: 0.000959 loss: 3.9861 (3.8481) grad_norm: 1.0776 (1.0630) time: 0.6361 [2021-03-26 07:06:02 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 80/1251] eta: 0:13:08 lr: 0.000959 loss: 3.8022 (3.8429) grad_norm: 1.0506 (1.0680) time: 0.6304 [2021-03-26 07:06:08 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 90/1251] eta: 0:12:55 lr: 0.000959 loss: 3.8853 (3.8723) grad_norm: 1.0253 (1.0597) time: 0.6242 [2021-03-26 07:06:14 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 100/1251] eta: 0:12:44 lr: 0.000959 loss: 4.1556 (3.8915) grad_norm: 1.0578 (1.0636) time: 0.6282 [2021-03-26 07:06:20 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 110/1251] eta: 0:12:35 lr: 0.000959 loss: 4.1566 (3.9098) grad_norm: 1.1273 (1.0730) time: 0.6325 [2021-03-26 07:06:27 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 120/1251] eta: 0:12:25 lr: 0.000959 loss: 4.0282 (3.9094) grad_norm: 1.1069 (1.0735) time: 0.6316 [2021-03-26 07:06:33 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 130/1251] eta: 0:12:16 lr: 0.000959 loss: 4.0834 (3.9423) grad_norm: 1.0279 (1.0663) time: 0.6307 [2021-03-26 07:06:39 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 140/1251] eta: 0:12:07 lr: 0.000959 loss: 4.1505 (3.9431) grad_norm: 0.9814 (1.0632) time: 0.6276 [2021-03-26 07:06:45 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 150/1251] eta: 0:11:58 lr: 0.000959 loss: 4.1607 (3.9471) grad_norm: 0.9875 (1.0650) time: 0.6206 [2021-03-26 07:06:52 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 160/1251] eta: 0:11:49 lr: 0.000959 loss: 4.1607 (3.9418) grad_norm: 1.0335 (1.0646) time: 0.6221 [2021-03-26 07:06:58 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 170/1251] eta: 0:11:41 lr: 0.000959 loss: 3.7558 (3.9310) grad_norm: 1.0335 (1.0639) time: 0.6265 [2021-03-26 07:07:04 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 180/1251] eta: 0:11:34 lr: 0.000959 loss: 3.8407 (3.9272) grad_norm: 1.0108 (1.0634) time: 0.6289 [2021-03-26 07:07:11 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 190/1251] eta: 0:11:26 lr: 0.000959 loss: 3.9828 (3.9350) grad_norm: 1.0244 (1.0638) time: 0.6318 [2021-03-26 07:07:17 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 200/1251] eta: 0:11:19 lr: 0.000959 loss: 4.0899 (3.9293) grad_norm: 0.9940 (1.0633) time: 0.6357 [2021-03-26 07:07:23 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 210/1251] eta: 0:11:12 lr: 0.000959 loss: 3.8355 (3.9191) grad_norm: 0.9940 (1.0600) time: 0.6349 [2021-03-26 07:07:30 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 220/1251] eta: 0:11:04 lr: 0.000959 loss: 3.8685 (3.9270) grad_norm: 1.0205 (1.0624) time: 0.6241 [2021-03-26 07:07:36 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 230/1251] eta: 0:10:57 lr: 0.000959 loss: 3.8805 (3.9287) grad_norm: 1.1297 (1.0673) time: 0.6232 [2021-03-26 07:07:42 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 240/1251] eta: 0:10:50 lr: 0.000959 loss: 3.8519 (3.9246) grad_norm: 1.0664 (1.0652) time: 0.6292 [2021-03-26 07:07:48 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 250/1251] eta: 0:10:43 lr: 0.000959 loss: 3.6563 (3.9115) grad_norm: 0.9767 (1.0622) time: 0.6266 [2021-03-26 07:07:55 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 260/1251] eta: 0:10:36 lr: 0.000959 loss: 3.7426 (3.9178) grad_norm: 1.0077 (1.0611) time: 0.6276 [2021-03-26 07:08:01 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 270/1251] eta: 0:10:29 lr: 0.000959 loss: 4.0134 (3.9202) grad_norm: 1.0077 (1.0617) time: 0.6253 [2021-03-26 07:08:07 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 280/1251] eta: 0:10:22 lr: 0.000959 loss: 3.9627 (3.9140) grad_norm: 1.0607 (1.0614) time: 0.6184 [2021-03-26 07:08:13 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 290/1251] eta: 0:10:15 lr: 0.000959 loss: 3.7183 (3.9062) grad_norm: 1.0803 (1.0624) time: 0.6216 [2021-03-26 07:08:19 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 300/1251] eta: 0:10:08 lr: 0.000959 loss: 3.7532 (3.9060) grad_norm: 1.1306 (1.0650) time: 0.6222 [2021-03-26 07:08:26 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 310/1251] eta: 0:10:01 lr: 0.000959 loss: 3.7532 (3.9045) grad_norm: 1.1399 (1.0701) time: 0.6246 [2021-03-26 07:08:32 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 320/1251] eta: 0:09:54 lr: 0.000959 loss: 4.0532 (3.9104) grad_norm: 0.9971 (1.0677) time: 0.6247 [2021-03-26 07:08:38 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 330/1251] eta: 0:09:47 lr: 0.000959 loss: 4.0325 (3.9086) grad_norm: 1.0815 (1.0711) time: 0.6229 [2021-03-26 07:08:44 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 340/1251] eta: 0:09:40 lr: 0.000959 loss: 4.0148 (3.9085) grad_norm: 1.0309 (1.0686) time: 0.6222 [2021-03-26 07:08:51 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 350/1251] eta: 0:09:34 lr: 0.000959 loss: 4.1380 (3.9117) grad_norm: 0.9815 (1.0677) time: 0.6218 [2021-03-26 07:08:57 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 360/1251] eta: 0:09:27 lr: 0.000959 loss: 4.0529 (3.9043) grad_norm: 0.9825 (1.0659) time: 0.6192 [2021-03-26 07:09:03 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 370/1251] eta: 0:09:20 lr: 0.000959 loss: 4.0254 (3.9057) grad_norm: 0.9773 (1.0649) time: 0.6134 [2021-03-26 07:09:09 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 380/1251] eta: 0:09:13 lr: 0.000959 loss: 4.0254 (3.9123) grad_norm: 0.9979 (1.0630) time: 0.6170 [2021-03-26 07:09:15 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 390/1251] eta: 0:09:07 lr: 0.000959 loss: 4.0068 (3.9131) grad_norm: 1.0249 (1.0626) time: 0.6259 [2021-03-26 07:09:22 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 400/1251] eta: 0:09:00 lr: 0.000959 loss: 4.2267 (3.9187) grad_norm: 1.0467 (1.0629) time: 0.6270 [2021-03-26 07:09:28 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 410/1251] eta: 0:08:53 lr: 0.000959 loss: 4.0185 (3.9174) grad_norm: 1.0467 (1.0625) time: 0.6218 [2021-03-26 07:09:34 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 420/1251] eta: 0:08:47 lr: 0.000959 loss: 4.0185 (3.9215) grad_norm: 1.0361 (1.0618) time: 0.6210 [2021-03-26 07:09:41 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 430/1251] eta: 0:08:40 lr: 0.000959 loss: 4.1708 (3.9261) grad_norm: 1.0278 (1.0618) time: 0.6302 [2021-03-26 07:09:47 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 440/1251] eta: 0:08:34 lr: 0.000959 loss: 4.0709 (3.9261) grad_norm: 1.1077 (1.0639) time: 0.6316 [2021-03-26 07:09:53 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 450/1251] eta: 0:08:27 lr: 0.000959 loss: 3.8350 (3.9231) grad_norm: 1.0112 (1.0617) time: 0.6236 [2021-03-26 07:09:59 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 460/1251] eta: 0:08:21 lr: 0.000959 loss: 3.7663 (3.9168) grad_norm: 1.0279 (1.0636) time: 0.6281 [2021-03-26 07:10:06 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 470/1251] eta: 0:08:15 lr: 0.000959 loss: 3.8391 (3.9211) grad_norm: 1.0806 (1.0641) time: 0.6284 [2021-03-26 07:10:12 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 480/1251] eta: 0:08:08 lr: 0.000958 loss: 4.1697 (3.9268) grad_norm: 1.0576 (1.0632) time: 0.6283 [2021-03-26 07:10:18 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 490/1251] eta: 0:08:02 lr: 0.000958 loss: 4.0547 (3.9265) grad_norm: 1.0535 (1.0634) time: 0.6283 [2021-03-26 07:10:24 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 500/1251] eta: 0:07:55 lr: 0.000958 loss: 3.9858 (3.9211) grad_norm: 1.0433 (1.0634) time: 0.6218 [2021-03-26 07:10:31 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 510/1251] eta: 0:07:49 lr: 0.000958 loss: 3.9858 (3.9232) grad_norm: 1.0670 (1.0666) time: 0.6267 [2021-03-26 07:10:37 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 520/1251] eta: 0:07:42 lr: 0.000958 loss: 4.0636 (3.9277) grad_norm: 0.9989 (1.0640) time: 0.6254 [2021-03-26 07:10:43 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 530/1251] eta: 0:07:36 lr: 0.000958 loss: 3.7326 (3.9216) grad_norm: 0.9276 (1.0624) time: 0.6200 [2021-03-26 07:10:49 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 540/1251] eta: 0:07:29 lr: 0.000958 loss: 3.5947 (3.9185) grad_norm: 0.9263 (1.0604) time: 0.6198 [2021-03-26 07:10:56 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 550/1251] eta: 0:07:23 lr: 0.000958 loss: 3.8536 (3.9193) grad_norm: 0.9574 (1.0603) time: 0.6343 [2021-03-26 07:11:02 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 560/1251] eta: 0:07:17 lr: 0.000958 loss: 4.0104 (3.9215) grad_norm: 1.1080 (1.0641) time: 0.6446 [2021-03-26 07:11:08 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 570/1251] eta: 0:07:11 lr: 0.000958 loss: 4.2072 (3.9264) grad_norm: 1.1080 (1.0641) time: 0.6369 [2021-03-26 07:11:15 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 580/1251] eta: 0:07:04 lr: 0.000958 loss: 4.1222 (3.9282) grad_norm: 1.0139 (1.0635) time: 0.6314 [2021-03-26 07:11:21 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 590/1251] eta: 0:06:58 lr: 0.000958 loss: 4.1189 (3.9289) grad_norm: 0.9694 (1.0623) time: 0.6217 [2021-03-26 07:11:27 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 600/1251] eta: 0:06:51 lr: 0.000958 loss: 4.0094 (3.9319) grad_norm: 0.9717 (1.0619) time: 0.6205 [2021-03-26 07:11:34 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 610/1251] eta: 0:06:45 lr: 0.000958 loss: 4.1502 (3.9376) grad_norm: 1.0694 (1.0627) time: 0.6294 [2021-03-26 07:11:40 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 620/1251] eta: 0:06:39 lr: 0.000958 loss: 4.2030 (3.9373) grad_norm: 1.0931 (1.0635) time: 0.6285 [2021-03-26 07:11:46 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 630/1251] eta: 0:06:32 lr: 0.000958 loss: 3.9775 (3.9385) grad_norm: 1.0396 (1.0636) time: 0.6239 [2021-03-26 07:11:52 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 640/1251] eta: 0:06:26 lr: 0.000958 loss: 3.8991 (3.9341) grad_norm: 1.0117 (1.0632) time: 0.6285 [2021-03-26 07:11:59 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 650/1251] eta: 0:06:19 lr: 0.000958 loss: 3.7487 (3.9335) grad_norm: 1.0012 (1.0622) time: 0.6290 [2021-03-26 07:12:05 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 660/1251] eta: 0:06:13 lr: 0.000958 loss: 3.7979 (3.9317) grad_norm: 0.9425 (1.0606) time: 0.6263 [2021-03-26 07:12:11 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 670/1251] eta: 0:06:07 lr: 0.000958 loss: 4.0638 (3.9358) grad_norm: 1.0033 (1.0605) time: 0.6275 [2021-03-26 07:12:17 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 680/1251] eta: 0:06:00 lr: 0.000958 loss: 4.0322 (3.9322) grad_norm: 1.0182 (1.0608) time: 0.6265 [2021-03-26 07:12:24 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 690/1251] eta: 0:05:54 lr: 0.000958 loss: 3.7345 (3.9273) grad_norm: 1.0223 (1.0615) time: 0.6245 [2021-03-26 07:12:30 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 700/1251] eta: 0:05:48 lr: 0.000958 loss: 3.7814 (3.9244) grad_norm: 1.0573 (1.0616) time: 0.6206 [2021-03-26 07:12:36 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 710/1251] eta: 0:05:41 lr: 0.000958 loss: 3.9838 (3.9256) grad_norm: 1.0269 (1.0615) time: 0.6226 [2021-03-26 07:12:42 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 720/1251] eta: 0:05:35 lr: 0.000958 loss: 3.9838 (3.9246) grad_norm: 1.0269 (1.0612) time: 0.6296 [2021-03-26 07:12:49 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 730/1251] eta: 0:05:29 lr: 0.000958 loss: 4.0908 (3.9276) grad_norm: 1.0272 (1.0614) time: 0.6322 [2021-03-26 07:12:55 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 740/1251] eta: 0:05:22 lr: 0.000958 loss: 4.0908 (3.9242) grad_norm: 1.1244 (1.0625) time: 0.6420 [2021-03-26 07:13:02 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 750/1251] eta: 0:05:16 lr: 0.000958 loss: 3.7172 (3.9230) grad_norm: 1.1308 (1.0637) time: 0.6457 [2021-03-26 07:13:08 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 760/1251] eta: 0:05:10 lr: 0.000958 loss: 4.0655 (3.9217) grad_norm: 1.0725 (1.0638) time: 0.6431 [2021-03-26 07:13:14 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 770/1251] eta: 0:05:03 lr: 0.000958 loss: 4.0655 (3.9215) grad_norm: 0.9921 (1.0632) time: 0.6315 [2021-03-26 07:13:20 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 780/1251] eta: 0:04:57 lr: 0.000958 loss: 4.0488 (3.9195) grad_norm: 0.9763 (inf) time: 0.6158 [2021-03-26 07:13:27 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 790/1251] eta: 0:04:51 lr: 0.000958 loss: 4.0488 (3.9163) grad_norm: 0.9602 (inf) time: 0.6187 [2021-03-26 07:13:33 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 800/1251] eta: 0:04:44 lr: 0.000958 loss: 3.9168 (3.9167) grad_norm: 1.0374 (inf) time: 0.6241 [2021-03-26 07:13:39 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 810/1251] eta: 0:04:38 lr: 0.000958 loss: 3.8941 (3.9161) grad_norm: 1.0437 (inf) time: 0.6206 [2021-03-26 07:13:45 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 820/1251] eta: 0:04:32 lr: 0.000958 loss: 3.8935 (3.9158) grad_norm: 0.9586 (inf) time: 0.6154 [2021-03-26 07:13:51 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 830/1251] eta: 0:04:25 lr: 0.000958 loss: 3.8730 (3.9146) grad_norm: 0.9452 (inf) time: 0.6129 [2021-03-26 07:13:58 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 840/1251] eta: 0:04:19 lr: 0.000958 loss: 3.8730 (3.9141) grad_norm: 0.9644 (inf) time: 0.6197 [2021-03-26 07:14:04 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 850/1251] eta: 0:04:12 lr: 0.000958 loss: 3.8959 (3.9127) grad_norm: 1.1286 (inf) time: 0.6324 [2021-03-26 07:14:10 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 860/1251] eta: 0:04:06 lr: 0.000958 loss: 4.1372 (3.9157) grad_norm: 1.1286 (inf) time: 0.6368 [2021-03-26 07:14:17 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 870/1251] eta: 0:04:00 lr: 0.000958 loss: 4.1727 (3.9145) grad_norm: 1.0806 (inf) time: 0.6311 [2021-03-26 07:14:23 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 880/1251] eta: 0:03:54 lr: 0.000958 loss: 3.8680 (3.9120) grad_norm: 0.9533 (inf) time: 0.6257 [2021-03-26 07:14:29 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 890/1251] eta: 0:03:47 lr: 0.000958 loss: 3.7234 (3.9118) grad_norm: 0.9658 (inf) time: 0.6224 [2021-03-26 07:14:35 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 900/1251] eta: 0:03:41 lr: 0.000958 loss: 4.1514 (3.9149) grad_norm: 1.0579 (inf) time: 0.6247 [2021-03-26 07:14:42 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 910/1251] eta: 0:03:35 lr: 0.000958 loss: 4.1484 (3.9134) grad_norm: 1.0789 (inf) time: 0.6274 [2021-03-26 07:14:48 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 920/1251] eta: 0:03:28 lr: 0.000958 loss: 3.5641 (3.9094) grad_norm: 1.0848 (inf) time: 0.6249 [2021-03-26 07:14:54 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 930/1251] eta: 0:03:22 lr: 0.000958 loss: 3.6323 (3.9086) grad_norm: 1.0209 (inf) time: 0.6252 [2021-03-26 07:15:00 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 940/1251] eta: 0:03:16 lr: 0.000958 loss: 3.7700 (3.9075) grad_norm: 0.9932 (inf) time: 0.6255 [2021-03-26 07:15:07 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 950/1251] eta: 0:03:09 lr: 0.000958 loss: 4.0867 (3.9106) grad_norm: 0.9999 (inf) time: 0.6234 [2021-03-26 07:15:13 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 960/1251] eta: 0:03:03 lr: 0.000958 loss: 4.1369 (3.9103) grad_norm: 1.0793 (inf) time: 0.6310 [2021-03-26 07:15:19 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 970/1251] eta: 0:02:57 lr: 0.000958 loss: 3.8156 (3.9094) grad_norm: 1.0887 (inf) time: 0.6342 [2021-03-26 07:15:26 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 980/1251] eta: 0:02:50 lr: 0.000958 loss: 3.9067 (3.9094) grad_norm: 1.1104 (inf) time: 0.6256 [2021-03-26 07:15:32 swin_base_patch4_window7_224] INFO: Epoch: [39] [ 990/1251] eta: 0:02:44 lr: 0.000958 loss: 4.2018 (3.9088) grad_norm: 1.0851 (inf) time: 0.6245 [2021-03-26 07:15:38 swin_base_patch4_window7_224] INFO: Epoch: [39] [1000/1251] eta: 0:02:38 lr: 0.000958 loss: 4.0818 (3.9085) grad_norm: 1.0107 (inf) time: 0.6225 [2021-03-26 07:15:44 swin_base_patch4_window7_224] INFO: Epoch: [39] [1010/1251] eta: 0:02:31 lr: 0.000958 loss: 3.8839 (3.9072) grad_norm: 1.0107 (inf) time: 0.6231 [2021-03-26 07:15:51 swin_base_patch4_window7_224] INFO: Epoch: [39] [1020/1251] eta: 0:02:25 lr: 0.000958 loss: 3.9345 (3.9088) grad_norm: 1.0594 (inf) time: 0.6267 [2021-03-26 07:15:57 swin_base_patch4_window7_224] INFO: Epoch: [39] [1030/1251] eta: 0:02:19 lr: 0.000958 loss: 4.3301 (3.9123) grad_norm: 1.0453 (inf) time: 0.6276 [2021-03-26 07:16:03 swin_base_patch4_window7_224] INFO: Epoch: [39] [1040/1251] eta: 0:02:12 lr: 0.000958 loss: 4.1860 (3.9119) grad_norm: 1.0148 (inf) time: 0.6307 [2021-03-26 07:16:09 swin_base_patch4_window7_224] INFO: Epoch: [39] [1050/1251] eta: 0:02:06 lr: 0.000958 loss: 3.7836 (3.9110) grad_norm: 1.0654 (inf) time: 0.6286 [2021-03-26 07:16:16 swin_base_patch4_window7_224] INFO: Epoch: [39] [1060/1251] eta: 0:02:00 lr: 0.000958 loss: 3.9216 (3.9105) grad_norm: 0.9760 (inf) time: 0.6204 [2021-03-26 07:16:22 swin_base_patch4_window7_224] INFO: Epoch: [39] [1070/1251] eta: 0:01:54 lr: 0.000958 loss: 3.8583 (3.9090) grad_norm: 0.9770 (inf) time: 0.6215 [2021-03-26 07:16:28 swin_base_patch4_window7_224] INFO: Epoch: [39] [1080/1251] eta: 0:01:47 lr: 0.000957 loss: 3.9266 (3.9116) grad_norm: 1.0316 (inf) time: 0.6298 [2021-03-26 07:16:34 swin_base_patch4_window7_224] INFO: Epoch: [39] [1090/1251] eta: 0:01:41 lr: 0.000957 loss: 4.0623 (3.9128) grad_norm: 1.0960 (inf) time: 0.6332 [2021-03-26 07:16:41 swin_base_patch4_window7_224] INFO: Epoch: [39] [1100/1251] eta: 0:01:35 lr: 0.000957 loss: 4.0149 (3.9127) grad_norm: 1.0893 (inf) time: 0.6308 [2021-03-26 07:16:47 swin_base_patch4_window7_224] INFO: Epoch: [39] [1110/1251] eta: 0:01:28 lr: 0.000957 loss: 4.0658 (3.9152) grad_norm: 1.0318 (inf) time: 0.6209 [2021-03-26 07:16:53 swin_base_patch4_window7_224] INFO: Epoch: [39] [1120/1251] eta: 0:01:22 lr: 0.000957 loss: 3.9839 (3.9144) grad_norm: 1.0700 (inf) time: 0.6173 [2021-03-26 07:16:59 swin_base_patch4_window7_224] INFO: Epoch: [39] [1130/1251] eta: 0:01:16 lr: 0.000957 loss: 3.8269 (3.9149) grad_norm: 1.0127 (inf) time: 0.6239 [2021-03-26 07:17:06 swin_base_patch4_window7_224] INFO: Epoch: [39] [1140/1251] eta: 0:01:09 lr: 0.000957 loss: 3.8696 (3.9151) grad_norm: 0.9917 (inf) time: 0.6215 [2021-03-26 07:17:12 swin_base_patch4_window7_224] INFO: Epoch: [39] [1150/1251] eta: 0:01:03 lr: 0.000957 loss: 4.0325 (3.9175) grad_norm: 0.9564 (inf) time: 0.6230 [2021-03-26 07:17:18 swin_base_patch4_window7_224] INFO: Epoch: [39] [1160/1251] eta: 0:00:57 lr: 0.000957 loss: 4.3466 (3.9204) grad_norm: 1.0089 (inf) time: 0.6277 [2021-03-26 07:17:24 swin_base_patch4_window7_224] INFO: Epoch: [39] [1170/1251] eta: 0:00:50 lr: 0.000957 loss: 3.9223 (3.9185) grad_norm: 0.9983 (inf) time: 0.6225 [2021-03-26 07:17:30 swin_base_patch4_window7_224] INFO: Epoch: [39] [1180/1251] eta: 0:00:44 lr: 0.000957 loss: 3.7801 (3.9164) grad_norm: 0.9640 (inf) time: 0.6196 [2021-03-26 07:17:37 swin_base_patch4_window7_224] INFO: Epoch: [39] [1190/1251] eta: 0:00:38 lr: 0.000957 loss: 3.9894 (3.9189) grad_norm: 0.9584 (inf) time: 0.6192 [2021-03-26 07:17:43 swin_base_patch4_window7_224] INFO: Epoch: [39] [1200/1251] eta: 0:00:32 lr: 0.000957 loss: 4.1204 (3.9201) grad_norm: 0.9854 (inf) time: 0.6237 [2021-03-26 07:17:49 swin_base_patch4_window7_224] INFO: Epoch: [39] [1210/1251] eta: 0:00:25 lr: 0.000957 loss: 4.0037 (3.9174) grad_norm: 1.0737 (inf) time: 0.6259 [2021-03-26 07:17:55 swin_base_patch4_window7_224] INFO: Epoch: [39] [1220/1251] eta: 0:00:19 lr: 0.000957 loss: 3.3942 (3.9155) grad_norm: 1.0419 (inf) time: 0.6239 [2021-03-26 07:18:02 swin_base_patch4_window7_224] INFO: Epoch: [39] [1230/1251] eta: 0:00:13 lr: 0.000957 loss: 3.7549 (3.9145) grad_norm: 1.0521 (inf) time: 0.6274 [2021-03-26 07:18:08 swin_base_patch4_window7_224] INFO: Epoch: [39] [1240/1251] eta: 0:00:06 lr: 0.000957 loss: 3.9072 (3.9146) grad_norm: 1.0536 (inf) time: 0.6261 [2021-03-26 07:18:14 swin_base_patch4_window7_224] INFO: Epoch: [39] [1250/1251] eta: 0:00:00 lr: 0.000957 loss: 3.8746 (3.9117) grad_norm: 1.0419 (inf) time: 0.6227 [2021-03-26 07:18:19 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:05 loss: 1.4753 (1.4753) acc1: 67.1875 (67.1875) acc5: 90.6250 (90.6250) [2021-03-26 07:18:21 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.2703 (1.2756) acc1: 70.3125 (70.7386) acc5: 89.0625 (89.9148) [2021-03-26 07:18:24 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.3032 (1.3191) acc1: 68.7500 (69.1964) acc5: 89.0625 (89.9554) [2021-03-26 07:18:26 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.3908 (1.3123) acc1: 67.1875 (69.7581) acc5: 90.6250 (90.1714) [2021-03-26 07:18:27 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.3635 (1.3253) acc1: 67.1875 (69.3979) acc5: 89.0625 (90.1296) [2021-03-26 07:18:28 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3310 (1.3109) acc1: 68.7500 (70.0160) acc5: 90.5660 (90.4320) [2021-03-26 07:18:30 swin_base_patch4_window7_224] INFO: * Acc@1 70.578 Acc@5 90.600 loss 1.293 [2021-03-26 07:18:30 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 70.6% [2021-03-26 07:18:30 swin_base_patch4_window7_224] INFO: Max accuracy: 70.67% [2021-03-26 07:18:34 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 0/1251] eta: 1:26:29 lr: 0.000957 loss: 2.6342 (2.6342) grad_norm: 0.9925 (0.9925) time: 4.1482 [2021-03-26 07:18:41 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 10/1251] eta: 0:20:02 lr: 0.000957 loss: 3.8574 (3.7854) grad_norm: 0.9925 (1.0323) time: 0.9689 [2021-03-26 07:18:47 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 20/1251] eta: 0:16:32 lr: 0.000957 loss: 3.9235 (3.8748) grad_norm: 1.0949 (1.0798) time: 0.6388 [2021-03-26 07:18:53 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 30/1251] eta: 0:15:16 lr: 0.000957 loss: 3.9855 (3.9521) grad_norm: 1.1455 (1.1071) time: 0.6305 [2021-03-26 07:19:00 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 40/1251] eta: 0:14:36 lr: 0.000957 loss: 3.9743 (3.9173) grad_norm: 1.1146 (1.1128) time: 0.6368 [2021-03-26 07:19:06 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 50/1251] eta: 0:14:06 lr: 0.000957 loss: 3.8706 (3.9035) grad_norm: 1.1112 (1.1145) time: 0.6342 [2021-03-26 07:19:12 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 60/1251] eta: 0:13:42 lr: 0.000957 loss: 3.9342 (3.8849) grad_norm: 1.0763 (1.0979) time: 0.6236 [2021-03-26 07:19:18 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 70/1251] eta: 0:13:25 lr: 0.000957 loss: 3.6556 (3.8287) grad_norm: 0.9998 (1.0883) time: 0.6231 [2021-03-26 07:19:25 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 80/1251] eta: 0:13:09 lr: 0.000957 loss: 3.6556 (3.8589) grad_norm: 1.0157 (1.0796) time: 0.6224 [2021-03-26 07:19:31 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 90/1251] eta: 0:12:56 lr: 0.000957 loss: 3.6975 (3.8254) grad_norm: 0.9687 (1.0697) time: 0.6209 [2021-03-26 07:19:37 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 100/1251] eta: 0:12:44 lr: 0.000957 loss: 3.6547 (3.8322) grad_norm: 0.9878 (1.0653) time: 0.6234 [2021-03-26 07:19:44 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 110/1251] eta: 0:12:35 lr: 0.000957 loss: 3.8717 (3.8151) grad_norm: 1.0457 (1.0670) time: 0.6349 [2021-03-26 07:19:50 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 120/1251] eta: 0:12:24 lr: 0.000957 loss: 3.9726 (3.8326) grad_norm: 0.9629 (1.0577) time: 0.6316 [2021-03-26 07:19:56 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 130/1251] eta: 0:12:15 lr: 0.000957 loss: 4.0287 (3.8368) grad_norm: 0.9451 (1.0544) time: 0.6206 [2021-03-26 07:20:02 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 140/1251] eta: 0:12:07 lr: 0.000957 loss: 3.9500 (3.8393) grad_norm: 1.0057 (1.0516) time: 0.6319 [2021-03-26 07:20:09 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 150/1251] eta: 0:11:59 lr: 0.000957 loss: 3.7789 (3.8507) grad_norm: 1.0059 (1.0493) time: 0.6343 [2021-03-26 07:20:15 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 160/1251] eta: 0:11:50 lr: 0.000957 loss: 3.8904 (3.8497) grad_norm: 1.0059 (1.0509) time: 0.6232 [2021-03-26 07:20:21 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 170/1251] eta: 0:11:41 lr: 0.000957 loss: 4.1500 (3.8624) grad_norm: 1.0420 (1.0508) time: 0.6170 [2021-03-26 07:20:27 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 180/1251] eta: 0:11:34 lr: 0.000957 loss: 3.9290 (3.8583) grad_norm: 1.1385 (1.0602) time: 0.6260 [2021-03-26 07:20:34 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 190/1251] eta: 0:11:26 lr: 0.000957 loss: 3.9290 (3.8590) grad_norm: 1.1310 (1.0605) time: 0.6322 [2021-03-26 07:20:40 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 200/1251] eta: 0:11:19 lr: 0.000957 loss: 4.0326 (3.8558) grad_norm: 1.0533 (1.0642) time: 0.6338 [2021-03-26 07:20:46 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 210/1251] eta: 0:11:11 lr: 0.000957 loss: 4.0656 (3.8550) grad_norm: 0.9809 (1.0591) time: 0.6230 [2021-03-26 07:20:52 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 220/1251] eta: 0:11:04 lr: 0.000957 loss: 3.9377 (3.8541) grad_norm: 0.9731 (1.0631) time: 0.6193 [2021-03-26 07:20:59 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 230/1251] eta: 0:10:56 lr: 0.000957 loss: 3.8717 (3.8581) grad_norm: 1.0352 (1.0631) time: 0.6267 [2021-03-26 07:21:05 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 240/1251] eta: 0:10:49 lr: 0.000957 loss: 4.0532 (3.8656) grad_norm: 0.9512 (1.0584) time: 0.6214 [2021-03-26 07:21:11 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 250/1251] eta: 0:10:41 lr: 0.000957 loss: 4.1168 (3.8747) grad_norm: 0.9236 (1.0577) time: 0.6179 [2021-03-26 07:21:17 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 260/1251] eta: 0:10:34 lr: 0.000957 loss: 4.0531 (3.8709) grad_norm: 1.0365 (1.0568) time: 0.6202 [2021-03-26 07:21:24 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 270/1251] eta: 0:10:27 lr: 0.000957 loss: 3.8971 (3.8627) grad_norm: 1.0446 (1.0569) time: 0.6254 [2021-03-26 07:21:30 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 280/1251] eta: 0:10:20 lr: 0.000957 loss: 3.4067 (3.8539) grad_norm: 1.0259 (1.0554) time: 0.6245 [2021-03-26 07:21:36 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 290/1251] eta: 0:10:13 lr: 0.000957 loss: 3.6639 (3.8588) grad_norm: 0.9791 (1.0514) time: 0.6168 [2021-03-26 07:21:42 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 300/1251] eta: 0:10:06 lr: 0.000957 loss: 3.9251 (3.8636) grad_norm: 0.9502 (1.0505) time: 0.6188 [2021-03-26 07:21:48 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 310/1251] eta: 0:10:00 lr: 0.000957 loss: 4.1404 (3.8747) grad_norm: 1.0132 (1.0510) time: 0.6261 [2021-03-26 07:21:55 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 320/1251] eta: 0:09:53 lr: 0.000957 loss: 4.0709 (3.8621) grad_norm: 1.0156 (1.0522) time: 0.6276 [2021-03-26 07:22:01 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 330/1251] eta: 0:09:46 lr: 0.000957 loss: 3.6912 (3.8632) grad_norm: 1.0083 (1.0517) time: 0.6296 [2021-03-26 07:22:07 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 340/1251] eta: 0:09:40 lr: 0.000957 loss: 4.0200 (3.8697) grad_norm: 1.0355 (1.0522) time: 0.6300 [2021-03-26 07:22:14 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 350/1251] eta: 0:09:33 lr: 0.000957 loss: 3.9690 (3.8649) grad_norm: 1.0355 (1.0515) time: 0.6307 [2021-03-26 07:22:20 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 360/1251] eta: 0:09:27 lr: 0.000957 loss: 4.0708 (3.8806) grad_norm: 1.0041 (1.0510) time: 0.6302 [2021-03-26 07:22:26 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 370/1251] eta: 0:09:20 lr: 0.000957 loss: 4.3782 (3.8894) grad_norm: 1.0014 (1.0506) time: 0.6243 [2021-03-26 07:22:32 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 380/1251] eta: 0:09:13 lr: 0.000957 loss: 4.2196 (3.8958) grad_norm: 1.0337 (1.0516) time: 0.6222 [2021-03-26 07:22:39 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 390/1251] eta: 0:09:07 lr: 0.000957 loss: 4.0781 (3.9005) grad_norm: 1.0771 (1.0532) time: 0.6246 [2021-03-26 07:22:45 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 400/1251] eta: 0:09:00 lr: 0.000957 loss: 4.1028 (3.9034) grad_norm: 1.0441 (1.0521) time: 0.6250 [2021-03-26 07:22:51 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 410/1251] eta: 0:08:54 lr: 0.000957 loss: 4.1747 (3.9064) grad_norm: 1.0441 (1.0533) time: 0.6296 [2021-03-26 07:22:57 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 420/1251] eta: 0:08:47 lr: 0.000956 loss: 4.1688 (3.9119) grad_norm: 1.0888 (1.0553) time: 0.6282 [2021-03-26 07:23:04 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 430/1251] eta: 0:08:41 lr: 0.000956 loss: 4.0966 (3.9169) grad_norm: 1.1060 (1.0570) time: 0.6288 [2021-03-26 07:23:10 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 440/1251] eta: 0:08:34 lr: 0.000956 loss: 4.0354 (3.9169) grad_norm: 1.0261 (1.0571) time: 0.6277 [2021-03-26 07:23:16 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 450/1251] eta: 0:08:28 lr: 0.000956 loss: 3.7519 (3.9073) grad_norm: 1.1006 (1.0591) time: 0.6228 [2021-03-26 07:23:23 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 460/1251] eta: 0:08:21 lr: 0.000956 loss: 3.9139 (3.9109) grad_norm: 1.0402 (1.0576) time: 0.6280 [2021-03-26 07:23:29 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 470/1251] eta: 0:08:15 lr: 0.000956 loss: 3.9739 (3.9091) grad_norm: 0.9852 (1.0564) time: 0.6254 [2021-03-26 07:23:35 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 480/1251] eta: 0:08:08 lr: 0.000956 loss: 3.8160 (3.9101) grad_norm: 0.9992 (1.0560) time: 0.6227 [2021-03-26 07:23:41 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 490/1251] eta: 0:08:02 lr: 0.000956 loss: 3.9961 (3.9069) grad_norm: 1.0186 (1.0551) time: 0.6249 [2021-03-26 07:23:47 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 500/1251] eta: 0:07:55 lr: 0.000956 loss: 3.9961 (3.9106) grad_norm: 0.9953 (1.0539) time: 0.6224 [2021-03-26 07:23:54 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 510/1251] eta: 0:07:49 lr: 0.000956 loss: 4.0454 (3.9118) grad_norm: 1.0214 (1.0544) time: 0.6226 [2021-03-26 07:24:00 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 520/1251] eta: 0:07:42 lr: 0.000956 loss: 4.0427 (3.9133) grad_norm: 1.0837 (1.0546) time: 0.6254 [2021-03-26 07:24:06 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 530/1251] eta: 0:07:36 lr: 0.000956 loss: 3.9635 (3.9154) grad_norm: 1.0715 (1.0545) time: 0.6258 [2021-03-26 07:24:12 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 540/1251] eta: 0:07:29 lr: 0.000956 loss: 3.8580 (3.9134) grad_norm: 1.0277 (1.0543) time: 0.6261 [2021-03-26 07:24:19 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 550/1251] eta: 0:07:23 lr: 0.000956 loss: 3.9421 (3.9149) grad_norm: 1.0420 (1.0549) time: 0.6385 [2021-03-26 07:24:25 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 560/1251] eta: 0:07:17 lr: 0.000956 loss: 3.7765 (3.9094) grad_norm: 1.0342 (1.0548) time: 0.6327 [2021-03-26 07:24:31 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 570/1251] eta: 0:07:10 lr: 0.000956 loss: 3.6683 (3.9094) grad_norm: 0.9982 (1.0549) time: 0.6169 [2021-03-26 07:24:38 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 580/1251] eta: 0:07:04 lr: 0.000956 loss: 3.8151 (3.9022) grad_norm: 1.0091 (1.0545) time: 0.6215 [2021-03-26 07:24:44 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 590/1251] eta: 0:06:58 lr: 0.000956 loss: 3.2370 (3.8933) grad_norm: 1.0380 (1.0562) time: 0.6281 [2021-03-26 07:24:50 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 600/1251] eta: 0:06:51 lr: 0.000956 loss: 3.6315 (3.8956) grad_norm: 1.0659 (1.0558) time: 0.6349 [2021-03-26 07:24:57 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 610/1251] eta: 0:06:45 lr: 0.000956 loss: 3.7623 (3.8927) grad_norm: 1.0646 (1.0566) time: 0.6329 [2021-03-26 07:25:03 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 620/1251] eta: 0:06:39 lr: 0.000956 loss: 3.5469 (3.8905) grad_norm: 1.1564 (1.0593) time: 0.6300 [2021-03-26 07:25:09 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 630/1251] eta: 0:06:32 lr: 0.000956 loss: 3.9547 (3.8926) grad_norm: 1.1251 (1.0595) time: 0.6264 [2021-03-26 07:25:15 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 640/1251] eta: 0:06:26 lr: 0.000956 loss: 4.0571 (3.8912) grad_norm: 1.0749 (1.0596) time: 0.6242 [2021-03-26 07:25:22 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 650/1251] eta: 0:06:19 lr: 0.000956 loss: 4.0770 (3.8960) grad_norm: 0.9963 (1.0579) time: 0.6252 [2021-03-26 07:25:28 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 660/1251] eta: 0:06:13 lr: 0.000956 loss: 4.1398 (3.8993) grad_norm: 0.9877 (1.0582) time: 0.6204 [2021-03-26 07:25:34 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 670/1251] eta: 0:06:07 lr: 0.000956 loss: 3.8286 (3.8966) grad_norm: 1.0779 (1.0587) time: 0.6225 [2021-03-26 07:25:40 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 680/1251] eta: 0:06:00 lr: 0.000956 loss: 4.0028 (3.9007) grad_norm: 1.0263 (1.0581) time: 0.6268 [2021-03-26 07:25:46 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 690/1251] eta: 0:05:54 lr: 0.000956 loss: 4.0882 (3.9042) grad_norm: 0.9968 (1.0571) time: 0.6222 [2021-03-26 07:25:53 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 700/1251] eta: 0:05:47 lr: 0.000956 loss: 4.0415 (3.9043) grad_norm: 1.0166 (1.0573) time: 0.6202 [2021-03-26 07:25:59 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 710/1251] eta: 0:05:41 lr: 0.000956 loss: 3.9017 (3.8986) grad_norm: 1.0166 (1.0570) time: 0.6241 [2021-03-26 07:26:05 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 720/1251] eta: 0:05:35 lr: 0.000956 loss: 3.7503 (3.8973) grad_norm: 0.9437 (1.0562) time: 0.6340 [2021-03-26 07:26:12 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 730/1251] eta: 0:05:28 lr: 0.000956 loss: 3.8045 (3.8972) grad_norm: 0.9389 (1.0554) time: 0.6306 [2021-03-26 07:26:18 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 740/1251] eta: 0:05:22 lr: 0.000956 loss: 3.7650 (3.8926) grad_norm: 0.9178 (1.0541) time: 0.6243 [2021-03-26 07:26:24 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 750/1251] eta: 0:05:16 lr: 0.000956 loss: 3.4531 (3.8896) grad_norm: 0.9422 (1.0535) time: 0.6330 [2021-03-26 07:26:31 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 760/1251] eta: 0:05:09 lr: 0.000956 loss: 3.6913 (3.8875) grad_norm: 1.0484 (1.0543) time: 0.6341 [2021-03-26 07:26:37 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 770/1251] eta: 0:05:03 lr: 0.000956 loss: 3.9877 (3.8878) grad_norm: 1.0869 (1.0550) time: 0.6382 [2021-03-26 07:26:43 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 780/1251] eta: 0:04:57 lr: 0.000956 loss: 3.9097 (3.8856) grad_norm: 1.0869 (1.0558) time: 0.6358 [2021-03-26 07:26:50 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 790/1251] eta: 0:04:51 lr: 0.000956 loss: 4.0151 (3.8889) grad_norm: 1.0144 (1.0551) time: 0.6271 [2021-03-26 07:26:56 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 800/1251] eta: 0:04:44 lr: 0.000956 loss: 4.0151 (3.8864) grad_norm: 1.0563 (1.0560) time: 0.6254 [2021-03-26 07:27:02 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 810/1251] eta: 0:04:38 lr: 0.000956 loss: 4.0723 (3.8890) grad_norm: 1.0917 (1.0558) time: 0.6222 [2021-03-26 07:27:08 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 820/1251] eta: 0:04:31 lr: 0.000956 loss: 4.1593 (3.8898) grad_norm: 1.0514 (1.0559) time: 0.6190 [2021-03-26 07:27:14 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 830/1251] eta: 0:04:25 lr: 0.000956 loss: 4.0003 (3.8922) grad_norm: 1.0917 (1.0568) time: 0.6213 [2021-03-26 07:27:21 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 840/1251] eta: 0:04:19 lr: 0.000956 loss: 4.1847 (3.8935) grad_norm: 1.1012 (1.0571) time: 0.6294 [2021-03-26 07:27:27 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 850/1251] eta: 0:04:12 lr: 0.000956 loss: 4.1695 (3.8931) grad_norm: 1.0542 (1.0563) time: 0.6242 [2021-03-26 07:27:33 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 860/1251] eta: 0:04:06 lr: 0.000956 loss: 4.1695 (3.8965) grad_norm: 1.0024 (1.0565) time: 0.6284 [2021-03-26 07:27:40 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 870/1251] eta: 0:04:00 lr: 0.000956 loss: 4.0838 (3.8958) grad_norm: 1.0412 (1.0563) time: 0.6333 [2021-03-26 07:27:46 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 880/1251] eta: 0:03:53 lr: 0.000956 loss: 3.9550 (3.8974) grad_norm: 1.0333 (1.0562) time: 0.6203 [2021-03-26 07:27:52 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 890/1251] eta: 0:03:47 lr: 0.000956 loss: 3.8428 (3.8970) grad_norm: 1.0239 (1.0555) time: 0.6218 [2021-03-26 07:27:58 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 900/1251] eta: 0:03:41 lr: 0.000956 loss: 3.8368 (3.8970) grad_norm: 1.0364 (1.0572) time: 0.6304 [2021-03-26 07:28:05 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 910/1251] eta: 0:03:35 lr: 0.000956 loss: 3.9673 (3.8985) grad_norm: 1.0953 (1.0571) time: 0.6356 [2021-03-26 07:28:11 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 920/1251] eta: 0:03:28 lr: 0.000956 loss: 3.9673 (3.8999) grad_norm: 1.0804 (1.0578) time: 0.6377 [2021-03-26 07:28:17 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 930/1251] eta: 0:03:22 lr: 0.000956 loss: 3.9097 (3.8982) grad_norm: 1.0277 (1.0573) time: 0.6294 [2021-03-26 07:28:24 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 940/1251] eta: 0:03:16 lr: 0.000956 loss: 3.8725 (3.8992) grad_norm: 1.0042 (1.0572) time: 0.6231 [2021-03-26 07:28:30 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 950/1251] eta: 0:03:09 lr: 0.000956 loss: 3.8189 (3.8951) grad_norm: 1.0252 (1.0582) time: 0.6271 [2021-03-26 07:28:36 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 960/1251] eta: 0:03:03 lr: 0.000956 loss: 3.5460 (3.8934) grad_norm: 0.9949 (1.0574) time: 0.6224 [2021-03-26 07:28:42 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 970/1251] eta: 0:02:57 lr: 0.000956 loss: 3.6531 (3.8916) grad_norm: 0.9917 (1.0577) time: 0.6179 [2021-03-26 07:28:48 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 980/1251] eta: 0:02:50 lr: 0.000956 loss: 4.0137 (3.8928) grad_norm: 1.1118 (1.0592) time: 0.6220 [2021-03-26 07:28:55 swin_base_patch4_window7_224] INFO: Epoch: [40] [ 990/1251] eta: 0:02:44 lr: 0.000956 loss: 4.0232 (3.8929) grad_norm: 1.0104 (1.0590) time: 0.6266 [2021-03-26 07:29:01 swin_base_patch4_window7_224] INFO: Epoch: [40] [1000/1251] eta: 0:02:38 lr: 0.000956 loss: 4.0463 (3.8957) grad_norm: 0.9989 (1.0600) time: 0.6252 [2021-03-26 07:29:07 swin_base_patch4_window7_224] INFO: Epoch: [40] [1010/1251] eta: 0:02:31 lr: 0.000955 loss: 4.1100 (3.8973) grad_norm: 1.0576 (1.0601) time: 0.6218 [2021-03-26 07:29:13 swin_base_patch4_window7_224] INFO: Epoch: [40] [1020/1251] eta: 0:02:25 lr: 0.000955 loss: 4.1100 (3.8994) grad_norm: 1.0576 (1.0603) time: 0.6236 [2021-03-26 07:29:20 swin_base_patch4_window7_224] INFO: Epoch: [40] [1030/1251] eta: 0:02:19 lr: 0.000955 loss: 3.9400 (3.8982) grad_norm: 1.0089 (1.0595) time: 0.6233 [2021-03-26 07:29:26 swin_base_patch4_window7_224] INFO: Epoch: [40] [1040/1251] eta: 0:02:12 lr: 0.000955 loss: 3.6343 (3.8973) grad_norm: 0.9972 (1.0590) time: 0.6187 [2021-03-26 07:29:32 swin_base_patch4_window7_224] INFO: Epoch: [40] [1050/1251] eta: 0:02:06 lr: 0.000955 loss: 4.0172 (3.8987) grad_norm: 1.0238 (1.0592) time: 0.6195 [2021-03-26 07:29:38 swin_base_patch4_window7_224] INFO: Epoch: [40] [1060/1251] eta: 0:02:00 lr: 0.000955 loss: 4.2033 (3.8994) grad_norm: 1.0249 (1.0593) time: 0.6210 [2021-03-26 07:29:44 swin_base_patch4_window7_224] INFO: Epoch: [40] [1070/1251] eta: 0:01:53 lr: 0.000955 loss: 4.0771 (3.9001) grad_norm: 1.0098 (1.0593) time: 0.6204 [2021-03-26 07:29:51 swin_base_patch4_window7_224] INFO: Epoch: [40] [1080/1251] eta: 0:01:47 lr: 0.000955 loss: 4.1298 (3.9000) grad_norm: 1.0009 (1.0584) time: 0.6175 [2021-03-26 07:29:57 swin_base_patch4_window7_224] INFO: Epoch: [40] [1090/1251] eta: 0:01:41 lr: 0.000955 loss: 3.9016 (3.8967) grad_norm: 0.9806 (1.0582) time: 0.6119 [2021-03-26 07:30:03 swin_base_patch4_window7_224] INFO: Epoch: [40] [1100/1251] eta: 0:01:35 lr: 0.000955 loss: 3.7682 (3.8950) grad_norm: 1.0168 (1.0577) time: 0.6179 [2021-03-26 07:30:09 swin_base_patch4_window7_224] INFO: Epoch: [40] [1110/1251] eta: 0:01:28 lr: 0.000955 loss: 3.8452 (3.8944) grad_norm: 1.0477 (1.0581) time: 0.6242 [2021-03-26 07:30:16 swin_base_patch4_window7_224] INFO: Epoch: [40] [1120/1251] eta: 0:01:22 lr: 0.000955 loss: 4.0058 (3.8950) grad_norm: 1.0422 (1.0582) time: 0.6297 [2021-03-26 07:30:22 swin_base_patch4_window7_224] INFO: Epoch: [40] [1130/1251] eta: 0:01:16 lr: 0.000955 loss: 4.1425 (3.8974) grad_norm: 1.0350 (1.0579) time: 0.6343 [2021-03-26 07:30:28 swin_base_patch4_window7_224] INFO: Epoch: [40] [1140/1251] eta: 0:01:09 lr: 0.000955 loss: 4.1025 (3.8956) grad_norm: 1.0350 (1.0579) time: 0.6265 [2021-03-26 07:30:34 swin_base_patch4_window7_224] INFO: Epoch: [40] [1150/1251] eta: 0:01:03 lr: 0.000955 loss: 3.8820 (3.8961) grad_norm: 1.0287 (1.0579) time: 0.6216 [2021-03-26 07:30:40 swin_base_patch4_window7_224] INFO: Epoch: [40] [1160/1251] eta: 0:00:57 lr: 0.000955 loss: 4.0754 (3.8975) grad_norm: 1.0038 (1.0577) time: 0.6188 [2021-03-26 07:30:47 swin_base_patch4_window7_224] INFO: Epoch: [40] [1170/1251] eta: 0:00:50 lr: 0.000955 loss: 3.8425 (3.8945) grad_norm: 0.9804 (1.0571) time: 0.6175 [2021-03-26 07:30:53 swin_base_patch4_window7_224] INFO: Epoch: [40] [1180/1251] eta: 0:00:44 lr: 0.000955 loss: 3.5266 (3.8917) grad_norm: 0.9587 (1.0566) time: 0.6223 [2021-03-26 07:30:59 swin_base_patch4_window7_224] INFO: Epoch: [40] [1190/1251] eta: 0:00:38 lr: 0.000955 loss: 3.2693 (3.8889) grad_norm: 0.9938 (1.0565) time: 0.6221 [2021-03-26 07:31:05 swin_base_patch4_window7_224] INFO: Epoch: [40] [1200/1251] eta: 0:00:32 lr: 0.000955 loss: 3.5826 (3.8883) grad_norm: 0.9938 (1.0560) time: 0.6206 [2021-03-26 07:31:12 swin_base_patch4_window7_224] INFO: Epoch: [40] [1210/1251] eta: 0:00:25 lr: 0.000955 loss: 3.5445 (3.8848) grad_norm: 1.0026 (1.0560) time: 0.6225 [2021-03-26 07:31:18 swin_base_patch4_window7_224] INFO: Epoch: [40] [1220/1251] eta: 0:00:19 lr: 0.000955 loss: 3.9803 (3.8848) grad_norm: 1.0095 (1.0556) time: 0.6237 [2021-03-26 07:31:24 swin_base_patch4_window7_224] INFO: Epoch: [40] [1230/1251] eta: 0:00:13 lr: 0.000955 loss: 3.9895 (3.8848) grad_norm: 0.9503 (1.0550) time: 0.6203 [2021-03-26 07:31:30 swin_base_patch4_window7_224] INFO: Epoch: [40] [1240/1251] eta: 0:00:06 lr: 0.000955 loss: 3.9632 (3.8848) grad_norm: 0.9987 (1.0550) time: 0.6163 [2021-03-26 07:31:36 swin_base_patch4_window7_224] INFO: Epoch: [40] [1250/1251] eta: 0:00:00 lr: 0.000955 loss: 3.9661 (3.8847) grad_norm: 1.0286 (1.0550) time: 0.6086 [2021-03-26 07:32:32 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:04 loss: 1.3397 (1.3397) acc1: 67.1875 (67.1875) acc5: 92.1875 (92.1875) [2021-03-26 07:32:34 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 1.3397 (1.3275) acc1: 68.7500 (69.3182) acc5: 90.6250 (89.6307) [2021-03-26 07:32:35 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.2196 (1.2799) acc1: 70.3125 (70.3869) acc5: 90.6250 (90.3274) [2021-03-26 07:32:36 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.2235 (1.2642) acc1: 70.3125 (70.7157) acc5: 92.1875 (90.6754) [2021-03-26 07:32:38 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.2235 (1.2491) acc1: 71.8750 (70.6174) acc5: 92.1875 (90.8537) [2021-03-26 07:32:39 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2670 (1.2727) acc1: 70.3125 (70.3680) acc5: 92.1875 (90.7840) [2021-03-26 07:32:42 swin_base_patch4_window7_224] INFO: * Acc@1 70.986 Acc@5 90.710 loss 1.257 [2021-03-26 07:32:42 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 71.0% [2021-03-26 07:32:42 swin_base_patch4_window7_224] INFO: Max accuracy: 70.99% [2021-03-26 07:32:46 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 0/1251] eta: 1:26:38 lr: 0.000955 loss: 4.2185 (4.2185) grad_norm: 1.1420 (1.1420) time: 4.1552 [2021-03-26 07:32:52 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 10/1251] eta: 0:19:44 lr: 0.000955 loss: 4.1400 (4.0432) grad_norm: 1.0525 (1.0965) time: 0.9543 [2021-03-26 07:32:59 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 20/1251] eta: 0:16:30 lr: 0.000955 loss: 3.8718 (3.9451) grad_norm: 1.0793 (1.1102) time: 0.6374 [2021-03-26 07:33:05 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 30/1251] eta: 0:15:15 lr: 0.000955 loss: 3.5883 (3.7144) grad_norm: 1.1198 (1.1135) time: 0.6374 [2021-03-26 07:33:11 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 40/1251] eta: 0:14:31 lr: 0.000955 loss: 3.6508 (3.7642) grad_norm: 1.0556 (1.0989) time: 0.6302 [2021-03-26 07:33:17 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 50/1251] eta: 0:14:02 lr: 0.000955 loss: 4.1485 (3.8256) grad_norm: 1.0347 (1.1014) time: 0.6257 [2021-03-26 07:33:24 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 60/1251] eta: 0:13:39 lr: 0.000955 loss: 4.0933 (3.8275) grad_norm: 1.0656 (1.0985) time: 0.6236 [2021-03-26 07:33:30 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 70/1251] eta: 0:13:22 lr: 0.000955 loss: 4.0933 (3.8756) grad_norm: 1.0706 (1.0944) time: 0.6233 [2021-03-26 07:33:36 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 80/1251] eta: 0:13:07 lr: 0.000955 loss: 4.0220 (3.8806) grad_norm: 1.0706 (1.0877) time: 0.6232 [2021-03-26 07:33:42 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 90/1251] eta: 0:12:54 lr: 0.000955 loss: 3.8637 (3.8654) grad_norm: 0.9815 (1.0816) time: 0.6249 [2021-03-26 07:33:49 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 100/1251] eta: 0:12:43 lr: 0.000955 loss: 3.8637 (3.8728) grad_norm: 1.0096 (1.0783) time: 0.6283 [2021-03-26 07:33:55 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 110/1251] eta: 0:12:34 lr: 0.000955 loss: 4.0260 (3.8826) grad_norm: 1.0573 (1.0771) time: 0.6328 [2021-03-26 07:34:01 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 120/1251] eta: 0:12:24 lr: 0.000955 loss: 3.9362 (3.8837) grad_norm: 1.0446 (1.0759) time: 0.6312 [2021-03-26 07:34:07 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 130/1251] eta: 0:12:14 lr: 0.000955 loss: 4.1156 (3.8985) grad_norm: 1.0412 (1.0742) time: 0.6237 [2021-03-26 07:34:14 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 140/1251] eta: 0:12:06 lr: 0.000955 loss: 4.1236 (3.9038) grad_norm: 1.0376 (1.0750) time: 0.6268 [2021-03-26 07:34:20 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 150/1251] eta: 0:11:57 lr: 0.000955 loss: 3.9971 (3.9000) grad_norm: 1.0352 (1.0748) time: 0.6290 [2021-03-26 07:34:26 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 160/1251] eta: 0:11:49 lr: 0.000955 loss: 3.8555 (3.8960) grad_norm: 0.9907 (1.0674) time: 0.6259 [2021-03-26 07:34:32 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 170/1251] eta: 0:11:40 lr: 0.000955 loss: 3.7682 (3.8833) grad_norm: 0.9285 (1.0615) time: 0.6185 [2021-03-26 07:34:39 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 180/1251] eta: 0:11:32 lr: 0.000955 loss: 3.9588 (3.8881) grad_norm: 0.9633 (1.0595) time: 0.6202 [2021-03-26 07:34:45 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 190/1251] eta: 0:11:24 lr: 0.000955 loss: 3.7085 (3.8683) grad_norm: 0.9969 (1.0554) time: 0.6208 [2021-03-26 07:34:51 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 200/1251] eta: 0:11:17 lr: 0.000955 loss: 3.7294 (3.8646) grad_norm: 0.9969 (1.0540) time: 0.6196 [2021-03-26 07:34:57 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 210/1251] eta: 0:11:09 lr: 0.000955 loss: 4.0418 (3.8743) grad_norm: 1.0591 (1.0555) time: 0.6262 [2021-03-26 07:35:04 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 220/1251] eta: 0:11:02 lr: 0.000955 loss: 4.0379 (3.8822) grad_norm: 1.0645 (1.0603) time: 0.6269 [2021-03-26 07:35:10 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 230/1251] eta: 0:10:56 lr: 0.000955 loss: 4.0128 (3.8858) grad_norm: 1.0673 (1.0614) time: 0.6344 [2021-03-26 07:35:16 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 240/1251] eta: 0:10:49 lr: 0.000955 loss: 4.1437 (3.8935) grad_norm: 1.1042 (1.0655) time: 0.6357 [2021-03-26 07:35:23 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 250/1251] eta: 0:10:41 lr: 0.000955 loss: 4.1600 (3.9064) grad_norm: 1.0910 (1.0704) time: 0.6246 [2021-03-26 07:35:29 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 260/1251] eta: 0:10:34 lr: 0.000955 loss: 4.0332 (3.8954) grad_norm: 1.0805 (1.0709) time: 0.6191 [2021-03-26 07:35:35 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 270/1251] eta: 0:10:27 lr: 0.000955 loss: 4.0332 (3.8997) grad_norm: 1.0751 (1.0724) time: 0.6197 [2021-03-26 07:35:41 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 280/1251] eta: 0:10:20 lr: 0.000955 loss: 3.8560 (3.8866) grad_norm: 0.9990 (1.0697) time: 0.6199 [2021-03-26 07:35:47 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 290/1251] eta: 0:10:13 lr: 0.000955 loss: 3.7204 (3.8877) grad_norm: 0.9990 (1.0682) time: 0.6237 [2021-03-26 07:35:54 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 300/1251] eta: 0:10:06 lr: 0.000955 loss: 4.1203 (3.8881) grad_norm: 1.0207 (1.0673) time: 0.6249 [2021-03-26 07:36:00 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 310/1251] eta: 0:09:59 lr: 0.000955 loss: 4.1598 (3.8910) grad_norm: 1.0557 (1.0681) time: 0.6244 [2021-03-26 07:36:06 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 320/1251] eta: 0:09:53 lr: 0.000955 loss: 4.0706 (3.8986) grad_norm: 1.0141 (1.0674) time: 0.6275 [2021-03-26 07:36:12 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 330/1251] eta: 0:09:46 lr: 0.000955 loss: 4.0706 (3.8953) grad_norm: 1.0022 (1.0666) time: 0.6254 [2021-03-26 07:36:19 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 340/1251] eta: 0:09:39 lr: 0.000954 loss: 3.7342 (3.8910) grad_norm: 0.9652 (1.0642) time: 0.6190 [2021-03-26 07:36:25 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 350/1251] eta: 0:09:32 lr: 0.000954 loss: 4.1447 (3.9023) grad_norm: 0.9621 (1.0619) time: 0.6184 [2021-03-26 07:36:31 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 360/1251] eta: 0:09:26 lr: 0.000954 loss: 4.1642 (3.8987) grad_norm: 0.9971 (1.0640) time: 0.6230 [2021-03-26 07:36:37 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 370/1251] eta: 0:09:19 lr: 0.000954 loss: 3.6950 (3.8936) grad_norm: 1.1083 (1.0633) time: 0.6245 [2021-03-26 07:36:44 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 380/1251] eta: 0:09:13 lr: 0.000954 loss: 3.8611 (3.8947) grad_norm: 0.9836 (1.0614) time: 0.6251 [2021-03-26 07:36:50 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 390/1251] eta: 0:09:06 lr: 0.000954 loss: 3.9016 (3.8954) grad_norm: 0.9776 (1.0595) time: 0.6218 [2021-03-26 07:36:56 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 400/1251] eta: 0:08:59 lr: 0.000954 loss: 3.9199 (3.8923) grad_norm: 1.0284 (1.0601) time: 0.6197 [2021-03-26 07:37:02 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 410/1251] eta: 0:08:52 lr: 0.000954 loss: 3.6269 (3.8832) grad_norm: 1.0441 (1.0597) time: 0.6171 [2021-03-26 07:37:08 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 420/1251] eta: 0:08:46 lr: 0.000954 loss: 3.6269 (3.8823) grad_norm: 1.0314 (1.0587) time: 0.6222 [2021-03-26 07:37:15 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 430/1251] eta: 0:08:39 lr: 0.000954 loss: 3.7174 (3.8807) grad_norm: 1.0227 (1.0591) time: 0.6276 [2021-03-26 07:37:21 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 440/1251] eta: 0:08:33 lr: 0.000954 loss: 3.7153 (3.8773) grad_norm: 1.0654 (1.0614) time: 0.6249 [2021-03-26 07:37:27 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 450/1251] eta: 0:08:26 lr: 0.000954 loss: 3.9639 (3.8812) grad_norm: 1.0175 (1.0588) time: 0.6227 [2021-03-26 07:37:33 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 460/1251] eta: 0:08:20 lr: 0.000954 loss: 4.0613 (3.8848) grad_norm: 0.9609 (1.0574) time: 0.6169 [2021-03-26 07:37:39 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 470/1251] eta: 0:08:13 lr: 0.000954 loss: 3.8835 (3.8776) grad_norm: 0.9710 (1.0561) time: 0.6172 [2021-03-26 07:37:46 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 480/1251] eta: 0:08:07 lr: 0.000954 loss: 3.4364 (3.8703) grad_norm: 0.9953 (1.0549) time: 0.6252 [2021-03-26 07:37:52 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 490/1251] eta: 0:08:00 lr: 0.000954 loss: 3.7205 (3.8700) grad_norm: 0.9958 (1.0547) time: 0.6225 [2021-03-26 07:37:58 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 500/1251] eta: 0:07:54 lr: 0.000954 loss: 3.8269 (3.8685) grad_norm: 0.9954 (1.0539) time: 0.6153 [2021-03-26 07:38:04 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 510/1251] eta: 0:07:47 lr: 0.000954 loss: 3.7772 (3.8652) grad_norm: 1.0923 (1.0573) time: 0.6171 [2021-03-26 07:38:10 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 520/1251] eta: 0:07:41 lr: 0.000954 loss: 3.7882 (3.8651) grad_norm: 1.1113 (1.0567) time: 0.6167 [2021-03-26 07:38:17 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 530/1251] eta: 0:07:34 lr: 0.000954 loss: 3.9234 (3.8640) grad_norm: 0.9936 (1.0563) time: 0.6168 [2021-03-26 07:38:23 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 540/1251] eta: 0:07:28 lr: 0.000954 loss: 3.9552 (3.8640) grad_norm: 0.9936 (1.0555) time: 0.6164 [2021-03-26 07:38:29 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 550/1251] eta: 0:07:22 lr: 0.000954 loss: 3.9134 (3.8641) grad_norm: 0.9792 (1.0541) time: 0.6294 [2021-03-26 07:38:35 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 560/1251] eta: 0:07:15 lr: 0.000954 loss: 3.8294 (3.8644) grad_norm: 1.0019 (1.0536) time: 0.6343 [2021-03-26 07:38:42 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 570/1251] eta: 0:07:09 lr: 0.000954 loss: 3.8149 (3.8621) grad_norm: 1.0431 (1.0531) time: 0.6301 [2021-03-26 07:38:48 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 580/1251] eta: 0:07:03 lr: 0.000954 loss: 3.8149 (3.8614) grad_norm: 0.9912 (1.0529) time: 0.6270 [2021-03-26 07:38:54 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 590/1251] eta: 0:06:56 lr: 0.000954 loss: 3.8184 (3.8590) grad_norm: 0.9769 (1.0526) time: 0.6172 [2021-03-26 07:39:00 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 600/1251] eta: 0:06:50 lr: 0.000954 loss: 4.0156 (3.8651) grad_norm: 0.9571 (1.0526) time: 0.6183 [2021-03-26 07:39:07 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 610/1251] eta: 0:06:43 lr: 0.000954 loss: 4.1086 (3.8683) grad_norm: 1.0607 (1.0544) time: 0.6246 [2021-03-26 07:39:13 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 620/1251] eta: 0:06:37 lr: 0.000954 loss: 4.0076 (3.8668) grad_norm: 1.0856 (1.0542) time: 0.6300 [2021-03-26 07:39:19 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 630/1251] eta: 0:06:31 lr: 0.000954 loss: 4.0076 (3.8694) grad_norm: 1.0011 (1.0540) time: 0.6273 [2021-03-26 07:39:25 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 640/1251] eta: 0:06:24 lr: 0.000954 loss: 4.1978 (3.8718) grad_norm: 1.0011 (1.0534) time: 0.6231 [2021-03-26 07:39:32 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 650/1251] eta: 0:06:18 lr: 0.000954 loss: 3.9454 (3.8731) grad_norm: 1.0378 (1.0546) time: 0.6319 [2021-03-26 07:39:38 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 660/1251] eta: 0:06:12 lr: 0.000954 loss: 3.8711 (3.8722) grad_norm: 1.0710 (1.0543) time: 0.6306 [2021-03-26 07:39:44 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 670/1251] eta: 0:06:05 lr: 0.000954 loss: 3.8632 (3.8735) grad_norm: 1.0710 (1.0553) time: 0.6211 [2021-03-26 07:39:50 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 680/1251] eta: 0:05:59 lr: 0.000954 loss: 3.9337 (3.8728) grad_norm: 1.0368 (1.0545) time: 0.6175 [2021-03-26 07:39:57 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 690/1251] eta: 0:05:53 lr: 0.000954 loss: 3.9162 (3.8745) grad_norm: 0.9584 (1.0535) time: 0.6211 [2021-03-26 07:40:03 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 700/1251] eta: 0:05:46 lr: 0.000954 loss: 3.8661 (3.8705) grad_norm: 1.0226 (1.0533) time: 0.6285 [2021-03-26 07:40:09 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 710/1251] eta: 0:05:40 lr: 0.000954 loss: 3.6033 (3.8702) grad_norm: 0.9859 (1.0522) time: 0.6245 [2021-03-26 07:40:15 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 720/1251] eta: 0:05:34 lr: 0.000954 loss: 3.9036 (3.8706) grad_norm: 0.9756 (1.0528) time: 0.6168 [2021-03-26 07:40:22 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 730/1251] eta: 0:05:27 lr: 0.000954 loss: 3.9036 (3.8706) grad_norm: 0.9857 (1.0527) time: 0.6174 [2021-03-26 07:40:28 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 740/1251] eta: 0:05:21 lr: 0.000954 loss: 3.7668 (3.8705) grad_norm: 1.0395 (1.0529) time: 0.6253 [2021-03-26 07:40:34 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 750/1251] eta: 0:05:15 lr: 0.000954 loss: 3.9347 (3.8747) grad_norm: 0.9684 (1.0521) time: 0.6268 [2021-03-26 07:40:40 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 760/1251] eta: 0:05:08 lr: 0.000954 loss: 3.9347 (3.8715) grad_norm: 0.9684 (1.0516) time: 0.6229 [2021-03-26 07:40:47 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 770/1251] eta: 0:05:02 lr: 0.000954 loss: 3.8174 (3.8718) grad_norm: 0.9842 (1.0513) time: 0.6221 [2021-03-26 07:40:53 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 780/1251] eta: 0:04:56 lr: 0.000954 loss: 4.0353 (3.8709) grad_norm: 1.0509 (1.0522) time: 0.6217 [2021-03-26 07:40:59 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 790/1251] eta: 0:04:49 lr: 0.000954 loss: 4.0673 (3.8739) grad_norm: 1.1286 (1.0537) time: 0.6242 [2021-03-26 07:41:05 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 800/1251] eta: 0:04:43 lr: 0.000954 loss: 3.9765 (3.8717) grad_norm: 1.0931 (1.0529) time: 0.6264 [2021-03-26 07:41:11 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 810/1251] eta: 0:04:37 lr: 0.000954 loss: 3.9302 (3.8718) grad_norm: 0.9372 (1.0519) time: 0.6154 [2021-03-26 07:41:18 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 820/1251] eta: 0:04:30 lr: 0.000954 loss: 3.9302 (3.8734) grad_norm: 0.9885 (1.0524) time: 0.6169 [2021-03-26 07:41:24 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 830/1251] eta: 0:04:24 lr: 0.000954 loss: 4.0294 (3.8756) grad_norm: 1.1330 (1.0539) time: 0.6296 [2021-03-26 07:41:30 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 840/1251] eta: 0:04:18 lr: 0.000954 loss: 4.1599 (3.8798) grad_norm: 1.1060 (1.0534) time: 0.6354 [2021-03-26 07:41:37 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 850/1251] eta: 0:04:11 lr: 0.000954 loss: 4.1430 (3.8818) grad_norm: 1.0823 (inf) time: 0.6299 [2021-03-26 07:41:43 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 860/1251] eta: 0:04:05 lr: 0.000954 loss: 3.9845 (3.8820) grad_norm: 1.0995 (inf) time: 0.6255 [2021-03-26 07:41:49 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 870/1251] eta: 0:03:59 lr: 0.000954 loss: 3.8887 (3.8836) grad_norm: 1.0541 (inf) time: 0.6293 [2021-03-26 07:41:55 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 880/1251] eta: 0:03:53 lr: 0.000954 loss: 3.9911 (3.8848) grad_norm: 1.0585 (inf) time: 0.6217 [2021-03-26 07:42:01 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 890/1251] eta: 0:03:46 lr: 0.000954 loss: 3.9194 (3.8836) grad_norm: 1.0732 (inf) time: 0.6201 [2021-03-26 07:42:08 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 900/1251] eta: 0:03:40 lr: 0.000954 loss: 3.7735 (3.8823) grad_norm: 1.0906 (inf) time: 0.6302 [2021-03-26 07:42:14 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 910/1251] eta: 0:03:34 lr: 0.000953 loss: 3.9457 (3.8811) grad_norm: 0.9852 (inf) time: 0.6278 [2021-03-26 07:42:20 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 920/1251] eta: 0:03:27 lr: 0.000953 loss: 3.9457 (3.8795) grad_norm: 0.9784 (inf) time: 0.6215 [2021-03-26 07:42:27 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 930/1251] eta: 0:03:21 lr: 0.000953 loss: 4.0210 (3.8817) grad_norm: 1.0036 (inf) time: 0.6275 [2021-03-26 07:42:33 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 940/1251] eta: 0:03:15 lr: 0.000953 loss: 4.1554 (3.8863) grad_norm: 1.1128 (inf) time: 0.6331 [2021-03-26 07:42:39 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 950/1251] eta: 0:03:09 lr: 0.000953 loss: 4.0980 (3.8864) grad_norm: 1.1446 (inf) time: 0.6317 [2021-03-26 07:42:46 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 960/1251] eta: 0:03:02 lr: 0.000953 loss: 4.0980 (3.8897) grad_norm: 1.0933 (inf) time: 0.6277 [2021-03-26 07:42:52 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 970/1251] eta: 0:02:56 lr: 0.000953 loss: 4.0873 (3.8873) grad_norm: 1.0471 (inf) time: 0.6264 [2021-03-26 07:42:58 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 980/1251] eta: 0:02:50 lr: 0.000953 loss: 3.6471 (3.8861) grad_norm: 1.0263 (inf) time: 0.6244 [2021-03-26 07:43:04 swin_base_patch4_window7_224] INFO: Epoch: [41] [ 990/1251] eta: 0:02:43 lr: 0.000953 loss: 3.8066 (3.8847) grad_norm: 1.0263 (inf) time: 0.6216 [2021-03-26 07:43:11 swin_base_patch4_window7_224] INFO: Epoch: [41] [1000/1251] eta: 0:02:37 lr: 0.000953 loss: 3.8496 (3.8839) grad_norm: 1.0432 (inf) time: 0.6279 [2021-03-26 07:43:17 swin_base_patch4_window7_224] INFO: Epoch: [41] [1010/1251] eta: 0:02:31 lr: 0.000953 loss: 3.9055 (3.8836) grad_norm: 1.0432 (inf) time: 0.6222 [2021-03-26 07:43:23 swin_base_patch4_window7_224] INFO: Epoch: [41] [1020/1251] eta: 0:02:25 lr: 0.000953 loss: 4.0896 (3.8867) grad_norm: 0.9679 (inf) time: 0.6169 [2021-03-26 07:43:29 swin_base_patch4_window7_224] INFO: Epoch: [41] [1030/1251] eta: 0:02:18 lr: 0.000953 loss: 4.0429 (3.8857) grad_norm: 1.0185 (inf) time: 0.6232 [2021-03-26 07:43:35 swin_base_patch4_window7_224] INFO: Epoch: [41] [1040/1251] eta: 0:02:12 lr: 0.000953 loss: 3.8533 (3.8862) grad_norm: 1.0322 (inf) time: 0.6194 [2021-03-26 07:43:41 swin_base_patch4_window7_224] INFO: Epoch: [41] [1050/1251] eta: 0:02:06 lr: 0.000953 loss: 3.8262 (3.8832) grad_norm: 0.9664 (inf) time: 0.6167 [2021-03-26 07:43:48 swin_base_patch4_window7_224] INFO: Epoch: [41] [1060/1251] eta: 0:01:59 lr: 0.000953 loss: 3.5190 (3.8804) grad_norm: 1.0133 (inf) time: 0.6158 [2021-03-26 07:43:54 swin_base_patch4_window7_224] INFO: Epoch: [41] [1070/1251] eta: 0:01:53 lr: 0.000953 loss: 3.6539 (3.8797) grad_norm: 1.0164 (inf) time: 0.6184 [2021-03-26 07:44:00 swin_base_patch4_window7_224] INFO: Epoch: [41] [1080/1251] eta: 0:01:47 lr: 0.000953 loss: 3.9866 (3.8817) grad_norm: 1.0081 (inf) time: 0.6173 [2021-03-26 07:44:06 swin_base_patch4_window7_224] INFO: Epoch: [41] [1090/1251] eta: 0:01:40 lr: 0.000953 loss: 4.0589 (3.8827) grad_norm: 1.0092 (inf) time: 0.6179 [2021-03-26 07:44:12 swin_base_patch4_window7_224] INFO: Epoch: [41] [1100/1251] eta: 0:01:34 lr: 0.000953 loss: 4.0967 (3.8846) grad_norm: 1.0092 (inf) time: 0.6237 [2021-03-26 07:44:19 swin_base_patch4_window7_224] INFO: Epoch: [41] [1110/1251] eta: 0:01:28 lr: 0.000953 loss: 4.0441 (3.8841) grad_norm: 1.0875 (inf) time: 0.6230 [2021-03-26 07:44:25 swin_base_patch4_window7_224] INFO: Epoch: [41] [1120/1251] eta: 0:01:22 lr: 0.000953 loss: 4.1135 (3.8868) grad_norm: 1.1144 (inf) time: 0.6278 [2021-03-26 07:44:31 swin_base_patch4_window7_224] INFO: Epoch: [41] [1130/1251] eta: 0:01:15 lr: 0.000953 loss: 4.0630 (3.8877) grad_norm: 1.1560 (inf) time: 0.6290 [2021-03-26 07:44:38 swin_base_patch4_window7_224] INFO: Epoch: [41] [1140/1251] eta: 0:01:09 lr: 0.000953 loss: 3.8292 (3.8870) grad_norm: 1.0860 (inf) time: 0.6275 [2021-03-26 07:44:44 swin_base_patch4_window7_224] INFO: Epoch: [41] [1150/1251] eta: 0:01:03 lr: 0.000953 loss: 3.8479 (3.8884) grad_norm: 1.0814 (inf) time: 0.6257 [2021-03-26 07:44:50 swin_base_patch4_window7_224] INFO: Epoch: [41] [1160/1251] eta: 0:00:57 lr: 0.000953 loss: 3.9915 (3.8884) grad_norm: 0.9812 (inf) time: 0.6177 [2021-03-26 07:44:56 swin_base_patch4_window7_224] INFO: Epoch: [41] [1170/1251] eta: 0:00:50 lr: 0.000953 loss: 3.9627 (3.8890) grad_norm: 0.9794 (inf) time: 0.6160 [2021-03-26 07:45:02 swin_base_patch4_window7_224] INFO: Epoch: [41] [1180/1251] eta: 0:00:44 lr: 0.000953 loss: 4.0354 (3.8910) grad_norm: 1.0527 (inf) time: 0.6248 [2021-03-26 07:45:09 swin_base_patch4_window7_224] INFO: Epoch: [41] [1190/1251] eta: 0:00:38 lr: 0.000953 loss: 4.0286 (3.8897) grad_norm: 1.0910 (inf) time: 0.6300 [2021-03-26 07:45:15 swin_base_patch4_window7_224] INFO: Epoch: [41] [1200/1251] eta: 0:00:31 lr: 0.000953 loss: 3.8671 (3.8878) grad_norm: 1.0910 (inf) time: 0.6291 [2021-03-26 07:45:21 swin_base_patch4_window7_224] INFO: Epoch: [41] [1210/1251] eta: 0:00:25 lr: 0.000953 loss: 3.6710 (3.8881) grad_norm: 1.0446 (inf) time: 0.6335 [2021-03-26 07:45:28 swin_base_patch4_window7_224] INFO: Epoch: [41] [1220/1251] eta: 0:00:19 lr: 0.000953 loss: 3.8066 (3.8878) grad_norm: 1.0591 (inf) time: 0.6265 [2021-03-26 07:45:34 swin_base_patch4_window7_224] INFO: Epoch: [41] [1230/1251] eta: 0:00:13 lr: 0.000953 loss: 3.9023 (3.8862) grad_norm: 1.0591 (inf) time: 0.6165 [2021-03-26 07:45:40 swin_base_patch4_window7_224] INFO: Epoch: [41] [1240/1251] eta: 0:00:06 lr: 0.000953 loss: 3.8186 (3.8863) grad_norm: 0.9920 (inf) time: 0.6257 [2021-03-26 07:45:46 swin_base_patch4_window7_224] INFO: Epoch: [41] [1250/1251] eta: 0:00:00 lr: 0.000953 loss: 4.0008 (3.8870) grad_norm: 1.0454 (inf) time: 0.6320 [2021-03-26 07:45:52 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:25 loss: 0.9858 (0.9858) acc1: 81.2500 (81.2500) acc5: 93.7500 (93.7500) [2021-03-26 07:45:54 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.3637 (1.2726) acc1: 70.3125 (71.5909) acc5: 90.6250 (91.1932) [2021-03-26 07:45:56 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.3637 (1.2932) acc1: 68.7500 (71.3542) acc5: 89.0625 (90.4018) [2021-03-26 07:45:58 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.3017 (1.3047) acc1: 71.8750 (71.6230) acc5: 89.0625 (90.4738) [2021-03-26 07:46:00 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2719 (1.3051) acc1: 71.8750 (71.6082) acc5: 90.6250 (90.6250) [2021-03-26 07:46:01 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2774 (1.3011) acc1: 69.8113 (71.3600) acc5: 90.6250 (90.6240) [2021-03-26 07:46:04 swin_base_patch4_window7_224] INFO: * Acc@1 71.174 Acc@5 90.920 loss 1.282 [2021-03-26 07:46:04 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 71.2% [2021-03-26 07:46:04 swin_base_patch4_window7_224] INFO: Max accuracy: 71.17% [2021-03-26 07:46:08 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 0/1251] eta: 1:28:47 lr: 0.000953 loss: 3.7584 (3.7584) grad_norm: 1.0824 (1.0824) time: 4.2584 [2021-03-26 07:46:15 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 10/1251] eta: 0:19:52 lr: 0.000953 loss: 4.1506 (4.1228) grad_norm: 0.9660 (1.0929) time: 0.9609 [2021-03-26 07:46:21 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 20/1251] eta: 0:16:18 lr: 0.000953 loss: 4.1506 (4.0707) grad_norm: 0.9660 (1.0571) time: 0.6219 [2021-03-26 07:46:27 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 30/1251] eta: 0:15:05 lr: 0.000953 loss: 4.0652 (3.9991) grad_norm: 1.0493 (1.0513) time: 0.6208 [2021-03-26 07:46:33 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 40/1251] eta: 0:14:21 lr: 0.000953 loss: 4.0164 (4.0381) grad_norm: 1.1029 (1.0759) time: 0.6236 [2021-03-26 07:46:39 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 50/1251] eta: 0:13:51 lr: 0.000953 loss: 4.0110 (3.9881) grad_norm: 0.9983 (1.0612) time: 0.6157 [2021-03-26 07:46:46 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 60/1251] eta: 0:13:28 lr: 0.000953 loss: 3.9174 (3.9444) grad_norm: 0.9778 (1.0560) time: 0.6120 [2021-03-26 07:46:52 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 70/1251] eta: 0:13:11 lr: 0.000953 loss: 4.0663 (3.9606) grad_norm: 1.0263 (1.0517) time: 0.6155 [2021-03-26 07:46:58 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 80/1251] eta: 0:12:57 lr: 0.000953 loss: 3.9330 (3.9302) grad_norm: 0.9805 (1.0415) time: 0.6177 [2021-03-26 07:47:04 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 90/1251] eta: 0:12:45 lr: 0.000953 loss: 3.7248 (3.9054) grad_norm: 0.9805 (1.0448) time: 0.6205 [2021-03-26 07:47:11 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 100/1251] eta: 0:12:35 lr: 0.000953 loss: 3.7967 (3.9044) grad_norm: 1.0376 (1.0528) time: 0.6279 [2021-03-26 07:47:17 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 110/1251] eta: 0:12:25 lr: 0.000953 loss: 3.8288 (3.8747) grad_norm: 1.0057 (1.0512) time: 0.6240 [2021-03-26 07:47:23 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 120/1251] eta: 0:12:17 lr: 0.000953 loss: 3.5092 (3.8387) grad_norm: 1.0169 (1.0536) time: 0.6291 [2021-03-26 07:47:29 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 130/1251] eta: 0:12:09 lr: 0.000953 loss: 3.7156 (3.8302) grad_norm: 1.0990 (1.0599) time: 0.6375 [2021-03-26 07:47:36 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 140/1251] eta: 0:12:01 lr: 0.000953 loss: 3.7368 (3.8309) grad_norm: 1.1009 (1.0630) time: 0.6308 [2021-03-26 07:47:42 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 150/1251] eta: 0:11:52 lr: 0.000953 loss: 3.8889 (3.8375) grad_norm: 1.1175 (1.0681) time: 0.6236 [2021-03-26 07:47:48 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 160/1251] eta: 0:11:44 lr: 0.000953 loss: 3.9706 (3.8418) grad_norm: 1.0694 (1.0711) time: 0.6191 [2021-03-26 07:47:54 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 170/1251] eta: 0:11:35 lr: 0.000953 loss: 3.9448 (3.8421) grad_norm: 0.9681 (1.0627) time: 0.6135 [2021-03-26 07:48:00 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 180/1251] eta: 0:11:28 lr: 0.000953 loss: 4.0362 (3.8628) grad_norm: 0.9665 (1.0670) time: 0.6192 [2021-03-26 07:48:07 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 190/1251] eta: 0:11:20 lr: 0.000953 loss: 4.0654 (3.8614) grad_norm: 1.0661 (1.0673) time: 0.6236 [2021-03-26 07:48:13 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 200/1251] eta: 0:11:12 lr: 0.000953 loss: 3.9563 (3.8519) grad_norm: 0.9745 (1.0624) time: 0.6166 [2021-03-26 07:48:19 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 210/1251] eta: 0:11:04 lr: 0.000953 loss: 4.0170 (3.8561) grad_norm: 0.9640 (1.0573) time: 0.6151 [2021-03-26 07:48:25 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 220/1251] eta: 0:10:57 lr: 0.000953 loss: 4.0583 (3.8660) grad_norm: 0.9640 (1.0555) time: 0.6177 [2021-03-26 07:48:31 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 230/1251] eta: 0:10:50 lr: 0.000952 loss: 3.8852 (3.8575) grad_norm: 0.9436 (1.0523) time: 0.6242 [2021-03-26 07:48:38 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 240/1251] eta: 0:10:44 lr: 0.000952 loss: 3.5959 (3.8439) grad_norm: 1.0383 (1.0554) time: 0.6337 [2021-03-26 07:48:44 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 250/1251] eta: 0:10:37 lr: 0.000952 loss: 3.4013 (3.8428) grad_norm: 1.0873 (1.0550) time: 0.6313 [2021-03-26 07:48:50 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 260/1251] eta: 0:10:31 lr: 0.000952 loss: 3.6766 (3.8398) grad_norm: 1.0003 (1.0547) time: 0.6296 [2021-03-26 07:48:57 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 270/1251] eta: 0:10:24 lr: 0.000952 loss: 3.9995 (3.8459) grad_norm: 1.0718 (1.0587) time: 0.6325 [2021-03-26 07:49:03 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 280/1251] eta: 0:10:18 lr: 0.000952 loss: 3.9134 (3.8381) grad_norm: 1.0445 (1.0580) time: 0.6347 [2021-03-26 07:49:09 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 290/1251] eta: 0:10:11 lr: 0.000952 loss: 3.6133 (3.8366) grad_norm: 1.0502 (1.0610) time: 0.6307 [2021-03-26 07:49:16 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 300/1251] eta: 0:10:04 lr: 0.000952 loss: 3.7719 (3.8315) grad_norm: 1.0819 (1.0597) time: 0.6204 [2021-03-26 07:49:22 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 310/1251] eta: 0:09:57 lr: 0.000952 loss: 3.7719 (3.8327) grad_norm: 1.0884 (1.0614) time: 0.6245 [2021-03-26 07:49:28 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 320/1251] eta: 0:09:51 lr: 0.000952 loss: 4.1264 (3.8393) grad_norm: 1.1259 (1.0650) time: 0.6330 [2021-03-26 07:49:34 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 330/1251] eta: 0:09:44 lr: 0.000952 loss: 4.0349 (3.8400) grad_norm: 1.0857 (1.0643) time: 0.6269 [2021-03-26 07:49:41 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 340/1251] eta: 0:09:38 lr: 0.000952 loss: 4.1372 (3.8436) grad_norm: 1.0354 (1.0650) time: 0.6221 [2021-03-26 07:49:47 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 350/1251] eta: 0:09:31 lr: 0.000952 loss: 4.0540 (3.8452) grad_norm: 1.0255 (1.0628) time: 0.6227 [2021-03-26 07:49:53 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 360/1251] eta: 0:09:24 lr: 0.000952 loss: 3.7342 (3.8374) grad_norm: 0.9873 (1.0628) time: 0.6189 [2021-03-26 07:49:59 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 370/1251] eta: 0:09:18 lr: 0.000952 loss: 3.5483 (3.8332) grad_norm: 0.9647 (1.0600) time: 0.6203 [2021-03-26 07:50:05 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 380/1251] eta: 0:09:11 lr: 0.000952 loss: 4.0780 (3.8369) grad_norm: 0.9968 (1.0614) time: 0.6217 [2021-03-26 07:50:12 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 390/1251] eta: 0:09:04 lr: 0.000952 loss: 4.1252 (3.8408) grad_norm: 1.0733 (1.0623) time: 0.6223 [2021-03-26 07:50:18 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 400/1251] eta: 0:08:58 lr: 0.000952 loss: 4.0269 (3.8452) grad_norm: 1.0415 (1.0608) time: 0.6294 [2021-03-26 07:50:24 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 410/1251] eta: 0:08:52 lr: 0.000952 loss: 4.1239 (3.8436) grad_norm: 0.9606 (1.0591) time: 0.6266 [2021-03-26 07:50:30 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 420/1251] eta: 0:08:45 lr: 0.000952 loss: 3.5599 (3.8347) grad_norm: 0.9541 (1.0576) time: 0.6208 [2021-03-26 07:50:37 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 430/1251] eta: 0:08:39 lr: 0.000952 loss: 3.6150 (3.8319) grad_norm: 0.9850 (1.0602) time: 0.6265 [2021-03-26 07:50:43 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 440/1251] eta: 0:08:32 lr: 0.000952 loss: 4.0400 (3.8378) grad_norm: 1.1274 (1.0631) time: 0.6257 [2021-03-26 07:50:49 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 450/1251] eta: 0:08:26 lr: 0.000952 loss: 4.0475 (3.8351) grad_norm: 1.1274 (1.0675) time: 0.6239 [2021-03-26 07:50:55 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 460/1251] eta: 0:08:19 lr: 0.000952 loss: 4.0417 (3.8347) grad_norm: 0.9659 (1.0650) time: 0.6198 [2021-03-26 07:51:02 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 470/1251] eta: 0:08:13 lr: 0.000952 loss: 3.7025 (3.8328) grad_norm: 0.9472 (1.0632) time: 0.6154 [2021-03-26 07:51:08 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 480/1251] eta: 0:08:06 lr: 0.000952 loss: 3.7729 (3.8339) grad_norm: 0.9791 (1.0642) time: 0.6201 [2021-03-26 07:51:14 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 490/1251] eta: 0:08:00 lr: 0.000952 loss: 3.9163 (3.8363) grad_norm: 0.9967 (1.0632) time: 0.6220 [2021-03-26 07:51:20 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 500/1251] eta: 0:07:53 lr: 0.000952 loss: 3.9385 (3.8374) grad_norm: 0.9971 (1.0640) time: 0.6256 [2021-03-26 07:51:27 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 510/1251] eta: 0:07:47 lr: 0.000952 loss: 3.9289 (3.8339) grad_norm: 1.0530 (1.0641) time: 0.6274 [2021-03-26 07:51:33 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 520/1251] eta: 0:07:41 lr: 0.000952 loss: 4.0688 (3.8398) grad_norm: 1.0584 (1.0655) time: 0.6309 [2021-03-26 07:51:39 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 530/1251] eta: 0:07:34 lr: 0.000952 loss: 4.0119 (3.8377) grad_norm: 1.0391 (1.0649) time: 0.6360 [2021-03-26 07:51:46 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 540/1251] eta: 0:07:28 lr: 0.000952 loss: 3.7330 (3.8369) grad_norm: 1.0026 (1.0645) time: 0.6281 [2021-03-26 07:51:52 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 550/1251] eta: 0:07:22 lr: 0.000952 loss: 3.7330 (3.8327) grad_norm: 1.0026 (1.0644) time: 0.6328 [2021-03-26 07:51:59 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 560/1251] eta: 0:07:16 lr: 0.000952 loss: 3.9224 (3.8359) grad_norm: 1.0618 (1.0648) time: 0.6503 [2021-03-26 07:52:05 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 570/1251] eta: 0:07:09 lr: 0.000952 loss: 4.0660 (3.8359) grad_norm: 1.0801 (1.0652) time: 0.6373 [2021-03-26 07:52:11 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 580/1251] eta: 0:07:03 lr: 0.000952 loss: 4.2107 (3.8430) grad_norm: 1.0801 (1.0648) time: 0.6210 [2021-03-26 07:52:17 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 590/1251] eta: 0:06:57 lr: 0.000952 loss: 3.9639 (3.8408) grad_norm: 0.9906 (1.0642) time: 0.6216 [2021-03-26 07:52:23 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 600/1251] eta: 0:06:50 lr: 0.000952 loss: 3.8574 (3.8405) grad_norm: 0.9925 (1.0644) time: 0.6250 [2021-03-26 07:52:30 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 610/1251] eta: 0:06:44 lr: 0.000952 loss: 3.8609 (3.8441) grad_norm: 1.0637 (1.0655) time: 0.6302 [2021-03-26 07:52:36 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 620/1251] eta: 0:06:38 lr: 0.000952 loss: 4.0847 (3.8489) grad_norm: 1.0507 (1.0647) time: 0.6285 [2021-03-26 07:52:42 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 630/1251] eta: 0:06:31 lr: 0.000952 loss: 4.0561 (3.8432) grad_norm: 1.0547 (1.0657) time: 0.6299 [2021-03-26 07:52:49 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 640/1251] eta: 0:06:25 lr: 0.000952 loss: 3.9699 (3.8425) grad_norm: 1.1078 (1.0666) time: 0.6264 [2021-03-26 07:52:55 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 650/1251] eta: 0:06:19 lr: 0.000952 loss: 4.0145 (3.8443) grad_norm: 1.0777 (1.0665) time: 0.6257 [2021-03-26 07:53:01 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 660/1251] eta: 0:06:12 lr: 0.000952 loss: 3.8557 (3.8388) grad_norm: 1.1219 (1.0677) time: 0.6323 [2021-03-26 07:53:07 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 670/1251] eta: 0:06:06 lr: 0.000952 loss: 3.3222 (3.8350) grad_norm: 1.1104 (1.0676) time: 0.6265 [2021-03-26 07:53:14 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 680/1251] eta: 0:06:00 lr: 0.000952 loss: 3.8502 (3.8366) grad_norm: 1.0254 (1.0675) time: 0.6238 [2021-03-26 07:53:20 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 690/1251] eta: 0:05:53 lr: 0.000952 loss: 4.0827 (3.8373) grad_norm: 1.0646 (1.0676) time: 0.6278 [2021-03-26 07:53:26 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 700/1251] eta: 0:05:47 lr: 0.000952 loss: 3.6793 (3.8338) grad_norm: 1.0671 (1.0680) time: 0.6267 [2021-03-26 07:53:33 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 710/1251] eta: 0:05:41 lr: 0.000952 loss: 3.5649 (3.8324) grad_norm: 1.0305 (1.0680) time: 0.6295 [2021-03-26 07:53:39 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 720/1251] eta: 0:05:34 lr: 0.000952 loss: 3.8358 (3.8317) grad_norm: 1.0527 (1.0691) time: 0.6320 [2021-03-26 07:53:45 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 730/1251] eta: 0:05:28 lr: 0.000952 loss: 3.6467 (3.8291) grad_norm: 1.0089 (1.0673) time: 0.6266 [2021-03-26 07:53:51 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 740/1251] eta: 0:05:22 lr: 0.000952 loss: 4.1109 (3.8323) grad_norm: 1.0019 (1.0679) time: 0.6264 [2021-03-26 07:53:58 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 750/1251] eta: 0:05:15 lr: 0.000952 loss: 4.1109 (3.8329) grad_norm: 1.0920 (1.0690) time: 0.6313 [2021-03-26 07:54:04 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 760/1251] eta: 0:05:09 lr: 0.000952 loss: 3.9273 (3.8338) grad_norm: 1.0899 (1.0696) time: 0.6272 [2021-03-26 07:54:10 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 770/1251] eta: 0:05:03 lr: 0.000952 loss: 3.9273 (3.8339) grad_norm: 1.0899 (1.0699) time: 0.6242 [2021-03-26 07:54:17 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 780/1251] eta: 0:04:56 lr: 0.000952 loss: 3.8313 (3.8299) grad_norm: 1.1107 (1.0706) time: 0.6339 [2021-03-26 07:54:23 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 790/1251] eta: 0:04:50 lr: 0.000951 loss: 3.6466 (3.8285) grad_norm: 1.0792 (1.0707) time: 0.6355 [2021-03-26 07:54:29 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 800/1251] eta: 0:04:44 lr: 0.000951 loss: 3.8780 (3.8290) grad_norm: 1.0792 (1.0712) time: 0.6243 [2021-03-26 07:54:35 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 810/1251] eta: 0:04:37 lr: 0.000951 loss: 3.8780 (3.8290) grad_norm: 1.1195 (1.0722) time: 0.6228 [2021-03-26 07:54:42 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 820/1251] eta: 0:04:31 lr: 0.000951 loss: 3.9711 (3.8309) grad_norm: 1.0196 (1.0723) time: 0.6256 [2021-03-26 07:54:48 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 830/1251] eta: 0:04:25 lr: 0.000951 loss: 4.0203 (3.8326) grad_norm: 1.0196 (1.0719) time: 0.6217 [2021-03-26 07:54:54 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 840/1251] eta: 0:04:18 lr: 0.000951 loss: 3.5567 (3.8272) grad_norm: 0.9847 (1.0709) time: 0.6247 [2021-03-26 07:55:00 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 850/1251] eta: 0:04:12 lr: 0.000951 loss: 3.4366 (3.8271) grad_norm: 0.9531 (1.0702) time: 0.6239 [2021-03-26 07:55:06 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 860/1251] eta: 0:04:06 lr: 0.000951 loss: 3.7526 (3.8279) grad_norm: 0.9657 (1.0699) time: 0.6183 [2021-03-26 07:55:13 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 870/1251] eta: 0:03:59 lr: 0.000951 loss: 3.9249 (3.8288) grad_norm: 1.0169 (1.0696) time: 0.6288 [2021-03-26 07:55:19 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 880/1251] eta: 0:03:53 lr: 0.000951 loss: 4.0250 (3.8287) grad_norm: 1.0719 (1.0698) time: 0.6330 [2021-03-26 07:55:25 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 890/1251] eta: 0:03:47 lr: 0.000951 loss: 4.0250 (3.8291) grad_norm: 1.0245 (1.0696) time: 0.6234 [2021-03-26 07:55:32 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 900/1251] eta: 0:03:40 lr: 0.000951 loss: 3.9407 (3.8291) grad_norm: 0.9951 (1.0690) time: 0.6179 [2021-03-26 07:55:38 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 910/1251] eta: 0:03:34 lr: 0.000951 loss: 4.0849 (3.8299) grad_norm: 1.0011 (1.0690) time: 0.6190 [2021-03-26 07:55:44 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 920/1251] eta: 0:03:28 lr: 0.000951 loss: 3.8448 (3.8275) grad_norm: 1.0269 (1.0687) time: 0.6196 [2021-03-26 07:55:50 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 930/1251] eta: 0:03:21 lr: 0.000951 loss: 3.7304 (3.8278) grad_norm: 0.9652 (1.0683) time: 0.6208 [2021-03-26 07:55:56 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 940/1251] eta: 0:03:15 lr: 0.000951 loss: 3.7304 (3.8250) grad_norm: 0.9248 (1.0666) time: 0.6222 [2021-03-26 07:56:03 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 950/1251] eta: 0:03:09 lr: 0.000951 loss: 3.8114 (3.8282) grad_norm: 0.9861 (1.0680) time: 0.6230 [2021-03-26 07:56:09 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 960/1251] eta: 0:03:03 lr: 0.000951 loss: 4.0098 (3.8277) grad_norm: 1.1055 (1.0693) time: 0.6238 [2021-03-26 07:56:15 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 970/1251] eta: 0:02:56 lr: 0.000951 loss: 3.8557 (3.8274) grad_norm: 1.1882 (1.0709) time: 0.6261 [2021-03-26 07:56:21 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 980/1251] eta: 0:02:50 lr: 0.000951 loss: 3.8723 (3.8281) grad_norm: 1.1882 (1.0718) time: 0.6320 [2021-03-26 07:56:28 swin_base_patch4_window7_224] INFO: Epoch: [42] [ 990/1251] eta: 0:02:44 lr: 0.000951 loss: 3.9886 (3.8310) grad_norm: 1.1429 (1.0718) time: 0.6285 [2021-03-26 07:56:34 swin_base_patch4_window7_224] INFO: Epoch: [42] [1000/1251] eta: 0:02:37 lr: 0.000951 loss: 3.8342 (3.8297) grad_norm: 0.9932 (1.0714) time: 0.6196 [2021-03-26 07:56:40 swin_base_patch4_window7_224] INFO: Epoch: [42] [1010/1251] eta: 0:02:31 lr: 0.000951 loss: 3.8342 (3.8313) grad_norm: 0.9661 (1.0703) time: 0.6139 [2021-03-26 07:56:46 swin_base_patch4_window7_224] INFO: Epoch: [42] [1020/1251] eta: 0:02:25 lr: 0.000951 loss: 3.9010 (3.8293) grad_norm: 0.9970 (1.0704) time: 0.6194 [2021-03-26 07:56:53 swin_base_patch4_window7_224] INFO: Epoch: [42] [1030/1251] eta: 0:02:18 lr: 0.000951 loss: 3.8696 (3.8308) grad_norm: 1.0564 (1.0702) time: 0.6334 [2021-03-26 07:56:59 swin_base_patch4_window7_224] INFO: Epoch: [42] [1040/1251] eta: 0:02:12 lr: 0.000951 loss: 4.0323 (3.8317) grad_norm: 1.0763 (1.0705) time: 0.6283 [2021-03-26 07:57:05 swin_base_patch4_window7_224] INFO: Epoch: [42] [1050/1251] eta: 0:02:06 lr: 0.000951 loss: 4.0323 (3.8351) grad_norm: 1.0763 (1.0704) time: 0.6178 [2021-03-26 07:57:11 swin_base_patch4_window7_224] INFO: Epoch: [42] [1060/1251] eta: 0:02:00 lr: 0.000951 loss: 4.1398 (3.8356) grad_norm: 1.0145 (1.0703) time: 0.6212 [2021-03-26 07:57:17 swin_base_patch4_window7_224] INFO: Epoch: [42] [1070/1251] eta: 0:01:53 lr: 0.000951 loss: 4.0107 (3.8355) grad_norm: 1.0041 (1.0695) time: 0.6217 [2021-03-26 07:57:24 swin_base_patch4_window7_224] INFO: Epoch: [42] [1080/1251] eta: 0:01:47 lr: 0.000951 loss: 3.8803 (3.8347) grad_norm: 1.0552 (1.0703) time: 0.6242 [2021-03-26 07:57:30 swin_base_patch4_window7_224] INFO: Epoch: [42] [1090/1251] eta: 0:01:41 lr: 0.000951 loss: 3.8803 (3.8345) grad_norm: 1.0690 (1.0701) time: 0.6271 [2021-03-26 07:57:36 swin_base_patch4_window7_224] INFO: Epoch: [42] [1100/1251] eta: 0:01:34 lr: 0.000951 loss: 3.5592 (3.8312) grad_norm: 1.0145 (1.0692) time: 0.6229 [2021-03-26 07:57:43 swin_base_patch4_window7_224] INFO: Epoch: [42] [1110/1251] eta: 0:01:28 lr: 0.000951 loss: 3.6065 (3.8318) grad_norm: 1.0078 (1.0693) time: 0.6295 [2021-03-26 07:57:49 swin_base_patch4_window7_224] INFO: Epoch: [42] [1120/1251] eta: 0:01:22 lr: 0.000951 loss: 3.5429 (3.8286) grad_norm: 1.0412 (1.0692) time: 0.6263 [2021-03-26 07:57:55 swin_base_patch4_window7_224] INFO: Epoch: [42] [1130/1251] eta: 0:01:16 lr: 0.000951 loss: 3.5429 (3.8268) grad_norm: 1.0335 (1.0696) time: 0.6213 [2021-03-26 07:58:01 swin_base_patch4_window7_224] INFO: Epoch: [42] [1140/1251] eta: 0:01:09 lr: 0.000951 loss: 3.7383 (3.8271) grad_norm: 1.0301 (1.0692) time: 0.6240 [2021-03-26 07:58:07 swin_base_patch4_window7_224] INFO: Epoch: [42] [1150/1251] eta: 0:01:03 lr: 0.000951 loss: 3.9348 (3.8292) grad_norm: 0.9817 (1.0688) time: 0.6231 [2021-03-26 07:58:14 swin_base_patch4_window7_224] INFO: Epoch: [42] [1160/1251] eta: 0:00:57 lr: 0.000951 loss: 4.0033 (3.8302) grad_norm: 0.9778 (1.0686) time: 0.6243 [2021-03-26 07:58:20 swin_base_patch4_window7_224] INFO: Epoch: [42] [1170/1251] eta: 0:00:50 lr: 0.000951 loss: 3.9019 (3.8304) grad_norm: 1.0123 (1.0686) time: 0.6219 [2021-03-26 07:58:26 swin_base_patch4_window7_224] INFO: Epoch: [42] [1180/1251] eta: 0:00:44 lr: 0.000951 loss: 3.9019 (3.8304) grad_norm: 1.0334 (1.0689) time: 0.6287 [2021-03-26 07:58:33 swin_base_patch4_window7_224] INFO: Epoch: [42] [1190/1251] eta: 0:00:38 lr: 0.000951 loss: 3.9208 (3.8314) grad_norm: 1.0095 (1.0681) time: 0.6304 [2021-03-26 07:58:39 swin_base_patch4_window7_224] INFO: Epoch: [42] [1200/1251] eta: 0:00:32 lr: 0.000951 loss: 4.1915 (3.8326) grad_norm: 1.0095 (1.0678) time: 0.6208 [2021-03-26 07:58:45 swin_base_patch4_window7_224] INFO: Epoch: [42] [1210/1251] eta: 0:00:25 lr: 0.000951 loss: 3.8518 (3.8323) grad_norm: 1.0443 (1.0677) time: 0.6205 [2021-03-26 07:58:51 swin_base_patch4_window7_224] INFO: Epoch: [42] [1220/1251] eta: 0:00:19 lr: 0.000951 loss: 3.8246 (3.8331) grad_norm: 1.0631 (1.0679) time: 0.6221 [2021-03-26 07:58:57 swin_base_patch4_window7_224] INFO: Epoch: [42] [1230/1251] eta: 0:00:13 lr: 0.000951 loss: 3.8000 (3.8324) grad_norm: 1.0295 (1.0680) time: 0.6187 [2021-03-26 07:59:03 swin_base_patch4_window7_224] INFO: Epoch: [42] [1240/1251] eta: 0:00:06 lr: 0.000951 loss: 3.9174 (3.8326) grad_norm: 1.0295 (1.0676) time: 0.6140 [2021-03-26 07:59:10 swin_base_patch4_window7_224] INFO: Epoch: [42] [1250/1251] eta: 0:00:00 lr: 0.000951 loss: 3.8760 (3.8317) grad_norm: 1.0238 (1.0673) time: 0.6140 [2021-03-26 07:59:13 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:22 loss: 1.0420 (1.0420) acc1: 75.0000 (75.0000) acc5: 96.8750 (96.8750) [2021-03-26 07:59:15 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:13 loss: 1.2410 (1.2597) acc1: 70.3125 (70.5966) acc5: 89.0625 (90.1989) [2021-03-26 07:59:17 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:07 loss: 1.2560 (1.2677) acc1: 70.3125 (70.3125) acc5: 89.0625 (89.8810) [2021-03-26 07:59:19 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 1.2180 (1.2554) acc1: 68.7500 (70.5645) acc5: 90.6250 (90.0202) [2021-03-26 07:59:21 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1810 (1.2350) acc1: 71.8750 (71.2652) acc5: 90.6250 (90.2820) [2021-03-26 07:59:22 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2167 (1.2274) acc1: 70.3125 (71.2320) acc5: 90.6250 (90.6560) [2021-03-26 07:59:27 swin_base_patch4_window7_224] INFO: * Acc@1 71.286 Acc@5 91.192 loss 1.214 [2021-03-26 07:59:27 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 71.3% [2021-03-26 07:59:27 swin_base_patch4_window7_224] INFO: Max accuracy: 71.29% [2021-03-26 07:59:31 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 0/1251] eta: 1:26:29 lr: 0.000951 loss: 4.1641 (4.1641) grad_norm: 0.9330 (0.9330) time: 4.1481 [2021-03-26 07:59:37 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 10/1251] eta: 0:19:49 lr: 0.000951 loss: 4.1247 (3.8403) grad_norm: 0.9347 (0.9911) time: 0.9586 [2021-03-26 07:59:43 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 20/1251] eta: 0:16:19 lr: 0.000951 loss: 3.9262 (3.8512) grad_norm: 1.0113 (1.0295) time: 0.6280 [2021-03-26 07:59:50 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 30/1251] eta: 0:15:06 lr: 0.000951 loss: 4.0329 (3.9853) grad_norm: 1.0475 (1.0969) time: 0.6233 [2021-03-26 07:59:56 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 40/1251] eta: 0:14:28 lr: 0.000951 loss: 4.0528 (3.9611) grad_norm: 1.1332 (1.1002) time: 0.6347 [2021-03-26 08:00:02 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 50/1251] eta: 0:13:58 lr: 0.000951 loss: 3.9497 (3.9451) grad_norm: 1.0388 (1.0928) time: 0.6295 [2021-03-26 08:00:09 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 60/1251] eta: 0:13:35 lr: 0.000951 loss: 4.0030 (3.9450) grad_norm: 1.0164 (1.0920) time: 0.6189 [2021-03-26 08:00:15 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 70/1251] eta: 0:13:18 lr: 0.000951 loss: 4.0803 (3.9231) grad_norm: 0.9808 (1.0836) time: 0.6195 [2021-03-26 08:00:21 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 80/1251] eta: 0:13:03 lr: 0.000951 loss: 3.9899 (3.9079) grad_norm: 0.9848 (1.0737) time: 0.6192 [2021-03-26 08:00:27 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 90/1251] eta: 0:12:52 lr: 0.000950 loss: 4.0333 (3.9172) grad_norm: 1.0456 (1.0762) time: 0.6260 [2021-03-26 08:00:34 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 100/1251] eta: 0:12:41 lr: 0.000950 loss: 3.9580 (3.9159) grad_norm: 1.0716 (1.0783) time: 0.6350 [2021-03-26 08:00:40 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 110/1251] eta: 0:12:31 lr: 0.000950 loss: 3.9275 (3.9209) grad_norm: 1.0716 (1.0894) time: 0.6306 [2021-03-26 08:00:46 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 120/1251] eta: 0:12:22 lr: 0.000950 loss: 3.9275 (3.9175) grad_norm: 1.1090 (1.0889) time: 0.6288 [2021-03-26 08:00:52 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 130/1251] eta: 0:12:13 lr: 0.000950 loss: 3.8755 (3.9015) grad_norm: 1.0633 (1.0861) time: 0.6292 [2021-03-26 08:00:59 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 140/1251] eta: 0:12:04 lr: 0.000950 loss: 3.8771 (3.8976) grad_norm: 1.0253 (1.0831) time: 0.6264 [2021-03-26 08:01:05 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 150/1251] eta: 0:11:55 lr: 0.000950 loss: 4.0487 (3.9127) grad_norm: 1.0541 (1.0832) time: 0.6244 [2021-03-26 08:01:11 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 160/1251] eta: 0:11:47 lr: 0.000950 loss: 4.0232 (3.9044) grad_norm: 1.0771 (1.0803) time: 0.6194 [2021-03-26 08:01:17 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 170/1251] eta: 0:11:39 lr: 0.000950 loss: 3.6366 (3.8957) grad_norm: 1.0490 (1.0804) time: 0.6205 [2021-03-26 08:01:24 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 180/1251] eta: 0:11:30 lr: 0.000950 loss: 3.5597 (3.8778) grad_norm: 1.0236 (1.0765) time: 0.6209 [2021-03-26 08:01:30 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 190/1251] eta: 0:11:24 lr: 0.000950 loss: 3.8539 (3.8681) grad_norm: 0.9689 (1.0773) time: 0.6299 [2021-03-26 08:01:36 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 200/1251] eta: 0:11:17 lr: 0.000950 loss: 3.9441 (3.8720) grad_norm: 1.0077 (1.0779) time: 0.6382 [2021-03-26 08:01:43 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 210/1251] eta: 0:11:09 lr: 0.000950 loss: 4.0440 (3.8627) grad_norm: 1.0876 (1.0784) time: 0.6284 [2021-03-26 08:01:49 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 220/1251] eta: 0:11:02 lr: 0.000950 loss: 3.9759 (3.8550) grad_norm: 1.0525 (1.0753) time: 0.6256 [2021-03-26 08:01:55 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 230/1251] eta: 0:10:55 lr: 0.000950 loss: 3.8755 (3.8532) grad_norm: 1.0628 (1.0762) time: 0.6275 [2021-03-26 08:02:01 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 240/1251] eta: 0:10:48 lr: 0.000950 loss: 3.9225 (3.8680) grad_norm: 1.0628 (1.0732) time: 0.6252 [2021-03-26 08:02:08 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 250/1251] eta: 0:10:41 lr: 0.000950 loss: 3.9177 (3.8645) grad_norm: 1.0025 (1.0719) time: 0.6269 [2021-03-26 08:02:14 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 260/1251] eta: 0:10:35 lr: 0.000950 loss: 3.7559 (3.8620) grad_norm: 1.0469 (1.0750) time: 0.6354 [2021-03-26 08:02:20 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 270/1251] eta: 0:10:27 lr: 0.000950 loss: 3.8210 (3.8656) grad_norm: 1.0471 (1.0738) time: 0.6299 [2021-03-26 08:02:26 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 280/1251] eta: 0:10:20 lr: 0.000950 loss: 3.9831 (3.8648) grad_norm: 1.0571 (1.0763) time: 0.6208 [2021-03-26 08:02:33 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 290/1251] eta: 0:10:13 lr: 0.000950 loss: 3.8872 (3.8666) grad_norm: 1.0275 (1.0740) time: 0.6203 [2021-03-26 08:02:39 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 300/1251] eta: 0:10:06 lr: 0.000950 loss: 4.1167 (3.8768) grad_norm: 1.0077 (1.0738) time: 0.6220 [2021-03-26 08:02:45 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 310/1251] eta: 0:10:00 lr: 0.000950 loss: 4.0803 (3.8612) grad_norm: 1.0577 (1.0723) time: 0.6259 [2021-03-26 08:02:51 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 320/1251] eta: 0:09:53 lr: 0.000950 loss: 3.4655 (3.8596) grad_norm: 1.0019 (1.0714) time: 0.6242 [2021-03-26 08:02:58 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 330/1251] eta: 0:09:46 lr: 0.000950 loss: 3.5161 (3.8468) grad_norm: 0.9526 (1.0689) time: 0.6231 [2021-03-26 08:03:04 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 340/1251] eta: 0:09:40 lr: 0.000950 loss: 3.6368 (3.8438) grad_norm: 1.0113 (1.0682) time: 0.6259 [2021-03-26 08:03:10 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 350/1251] eta: 0:09:33 lr: 0.000950 loss: 3.9736 (3.8459) grad_norm: 1.0165 (1.0668) time: 0.6244 [2021-03-26 08:03:16 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 360/1251] eta: 0:09:26 lr: 0.000950 loss: 3.9736 (3.8448) grad_norm: 0.9601 (1.0656) time: 0.6214 [2021-03-26 08:03:23 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 370/1251] eta: 0:09:19 lr: 0.000950 loss: 3.6667 (3.8409) grad_norm: 0.9601 (1.0662) time: 0.6217 [2021-03-26 08:03:29 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 380/1251] eta: 0:09:13 lr: 0.000950 loss: 3.6179 (3.8406) grad_norm: 1.0243 (1.0659) time: 0.6224 [2021-03-26 08:03:35 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 390/1251] eta: 0:09:06 lr: 0.000950 loss: 3.9441 (3.8402) grad_norm: 1.0099 (1.0660) time: 0.6262 [2021-03-26 08:03:41 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 400/1251] eta: 0:09:00 lr: 0.000950 loss: 4.0740 (3.8460) grad_norm: 0.9742 (1.0639) time: 0.6247 [2021-03-26 08:03:48 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 410/1251] eta: 0:08:53 lr: 0.000950 loss: 3.9933 (3.8510) grad_norm: 0.9631 (1.0635) time: 0.6221 [2021-03-26 08:03:54 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 420/1251] eta: 0:08:46 lr: 0.000950 loss: 3.9352 (3.8492) grad_norm: 0.9631 (1.0609) time: 0.6184 [2021-03-26 08:04:00 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 430/1251] eta: 0:08:39 lr: 0.000950 loss: 3.9847 (3.8489) grad_norm: 0.9520 (1.0590) time: 0.6121 [2021-03-26 08:04:06 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 440/1251] eta: 0:08:33 lr: 0.000950 loss: 4.1368 (3.8531) grad_norm: 1.0553 (1.0592) time: 0.6181 [2021-03-26 08:04:12 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 450/1251] eta: 0:08:27 lr: 0.000950 loss: 4.1368 (3.8533) grad_norm: 1.0614 (1.0592) time: 0.6306 [2021-03-26 08:04:19 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 460/1251] eta: 0:08:20 lr: 0.000950 loss: 3.8913 (3.8532) grad_norm: 1.0026 (1.0583) time: 0.6265 [2021-03-26 08:04:25 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 470/1251] eta: 0:08:14 lr: 0.000950 loss: 4.0581 (3.8594) grad_norm: 1.0262 (1.0585) time: 0.6182 [2021-03-26 08:04:31 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 480/1251] eta: 0:08:07 lr: 0.000950 loss: 4.1243 (3.8615) grad_norm: 1.0699 (1.0582) time: 0.6198 [2021-03-26 08:04:37 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 490/1251] eta: 0:08:01 lr: 0.000950 loss: 4.1243 (3.8635) grad_norm: 1.0144 (1.0580) time: 0.6217 [2021-03-26 08:04:43 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 500/1251] eta: 0:07:54 lr: 0.000950 loss: 3.7873 (3.8594) grad_norm: 0.9820 (1.0570) time: 0.6206 [2021-03-26 08:04:50 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 510/1251] eta: 0:07:47 lr: 0.000950 loss: 3.7975 (3.8571) grad_norm: 1.0046 (1.0583) time: 0.6173 [2021-03-26 08:04:56 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 520/1251] eta: 0:07:41 lr: 0.000950 loss: 3.8822 (3.8570) grad_norm: 1.1451 (1.0593) time: 0.6186 [2021-03-26 08:05:02 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 530/1251] eta: 0:07:35 lr: 0.000950 loss: 3.8822 (3.8565) grad_norm: 1.1084 (1.0600) time: 0.6189 [2021-03-26 08:05:08 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 540/1251] eta: 0:07:28 lr: 0.000950 loss: 3.8983 (3.8547) grad_norm: 1.0987 (1.0612) time: 0.6266 [2021-03-26 08:05:15 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 550/1251] eta: 0:07:22 lr: 0.000950 loss: 3.8554 (3.8544) grad_norm: 1.0848 (1.0625) time: 0.6415 [2021-03-26 08:05:21 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 560/1251] eta: 0:07:16 lr: 0.000950 loss: 3.6461 (3.8470) grad_norm: 1.1013 (1.0642) time: 0.6389 [2021-03-26 08:05:27 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 570/1251] eta: 0:07:09 lr: 0.000950 loss: 3.7799 (3.8466) grad_norm: 1.1160 (1.0659) time: 0.6265 [2021-03-26 08:05:34 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 580/1251] eta: 0:07:03 lr: 0.000950 loss: 3.7799 (3.8389) grad_norm: 1.0760 (1.0650) time: 0.6257 [2021-03-26 08:05:40 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 590/1251] eta: 0:06:57 lr: 0.000950 loss: 3.8184 (3.8416) grad_norm: 1.0571 (1.0681) time: 0.6286 [2021-03-26 08:05:46 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 600/1251] eta: 0:06:50 lr: 0.000950 loss: 3.9812 (3.8435) grad_norm: 1.0983 (1.0699) time: 0.6320 [2021-03-26 08:05:53 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 610/1251] eta: 0:06:44 lr: 0.000950 loss: 3.7730 (3.8378) grad_norm: 1.0615 (1.0690) time: 0.6335 [2021-03-26 08:05:59 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 620/1251] eta: 0:06:38 lr: 0.000950 loss: 3.4146 (3.8320) grad_norm: 1.0249 (1.0685) time: 0.6281 [2021-03-26 08:06:05 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 630/1251] eta: 0:06:31 lr: 0.000950 loss: 3.6893 (3.8302) grad_norm: 1.0249 (1.0682) time: 0.6253 [2021-03-26 08:06:11 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 640/1251] eta: 0:06:25 lr: 0.000949 loss: 3.8458 (3.8336) grad_norm: 1.0076 (1.0677) time: 0.6263 [2021-03-26 08:06:18 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 650/1251] eta: 0:06:19 lr: 0.000949 loss: 3.8458 (3.8327) grad_norm: 1.0567 (1.0677) time: 0.6245 [2021-03-26 08:06:24 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 660/1251] eta: 0:06:12 lr: 0.000949 loss: 3.5653 (3.8307) grad_norm: 1.1038 (1.0690) time: 0.6315 [2021-03-26 08:06:30 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 670/1251] eta: 0:06:06 lr: 0.000949 loss: 3.8313 (3.8318) grad_norm: 1.0743 (1.0693) time: 0.6311 [2021-03-26 08:06:36 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 680/1251] eta: 0:06:00 lr: 0.000949 loss: 4.0829 (3.8329) grad_norm: 1.0354 (1.0692) time: 0.6242 [2021-03-26 08:06:43 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 690/1251] eta: 0:05:53 lr: 0.000949 loss: 4.0695 (3.8346) grad_norm: 1.0565 (1.0692) time: 0.6268 [2021-03-26 08:06:49 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 700/1251] eta: 0:05:47 lr: 0.000949 loss: 3.8944 (3.8335) grad_norm: 0.9878 (1.0681) time: 0.6226 [2021-03-26 08:06:55 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 710/1251] eta: 0:05:41 lr: 0.000949 loss: 3.8697 (3.8367) grad_norm: 0.9695 (1.0670) time: 0.6156 [2021-03-26 08:07:01 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 720/1251] eta: 0:05:34 lr: 0.000949 loss: 3.8806 (3.8342) grad_norm: 0.9684 (1.0661) time: 0.6160 [2021-03-26 08:07:07 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 730/1251] eta: 0:05:28 lr: 0.000949 loss: 3.9091 (3.8354) grad_norm: 0.9524 (1.0658) time: 0.6194 [2021-03-26 08:07:14 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 740/1251] eta: 0:05:22 lr: 0.000949 loss: 3.9091 (3.8330) grad_norm: 0.9657 (1.0655) time: 0.6315 [2021-03-26 08:07:20 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 750/1251] eta: 0:05:15 lr: 0.000949 loss: 3.8843 (3.8325) grad_norm: 1.0007 (1.0649) time: 0.6316 [2021-03-26 08:07:26 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 760/1251] eta: 0:05:09 lr: 0.000949 loss: 3.9630 (3.8322) grad_norm: 1.0694 (1.0653) time: 0.6222 [2021-03-26 08:07:33 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 770/1251] eta: 0:05:03 lr: 0.000949 loss: 4.0123 (3.8344) grad_norm: 1.0283 (1.0650) time: 0.6257 [2021-03-26 08:07:39 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 780/1251] eta: 0:04:56 lr: 0.000949 loss: 3.9806 (3.8362) grad_norm: 0.9978 (1.0658) time: 0.6275 [2021-03-26 08:07:45 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 790/1251] eta: 0:04:50 lr: 0.000949 loss: 3.9806 (3.8384) grad_norm: 1.0982 (1.0664) time: 0.6316 [2021-03-26 08:07:51 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 800/1251] eta: 0:04:44 lr: 0.000949 loss: 3.9882 (3.8396) grad_norm: 1.0685 (1.0671) time: 0.6292 [2021-03-26 08:07:58 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 810/1251] eta: 0:04:37 lr: 0.000949 loss: 3.9726 (3.8407) grad_norm: 1.0685 (1.0675) time: 0.6223 [2021-03-26 08:08:04 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 820/1251] eta: 0:04:31 lr: 0.000949 loss: 3.8992 (3.8387) grad_norm: 1.0616 (1.0673) time: 0.6221 [2021-03-26 08:08:10 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 830/1251] eta: 0:04:25 lr: 0.000949 loss: 3.9134 (3.8403) grad_norm: 1.0370 (inf) time: 0.6190 [2021-03-26 08:08:16 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 840/1251] eta: 0:04:18 lr: 0.000949 loss: 3.9863 (3.8407) grad_norm: 1.0320 (inf) time: 0.6215 [2021-03-26 08:08:23 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 850/1251] eta: 0:04:12 lr: 0.000949 loss: 3.9601 (3.8388) grad_norm: 1.1072 (inf) time: 0.6266 [2021-03-26 08:08:29 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 860/1251] eta: 0:04:06 lr: 0.000949 loss: 3.5835 (3.8359) grad_norm: 1.0692 (inf) time: 0.6267 [2021-03-26 08:08:35 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 870/1251] eta: 0:03:59 lr: 0.000949 loss: 3.7103 (3.8353) grad_norm: 1.0223 (inf) time: 0.6310 [2021-03-26 08:08:41 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 880/1251] eta: 0:03:53 lr: 0.000949 loss: 3.8283 (3.8343) grad_norm: 1.0446 (inf) time: 0.6265 [2021-03-26 08:08:48 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 890/1251] eta: 0:03:47 lr: 0.000949 loss: 3.9067 (3.8360) grad_norm: 1.0295 (inf) time: 0.6210 [2021-03-26 08:08:54 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 900/1251] eta: 0:03:40 lr: 0.000949 loss: 3.8948 (3.8337) grad_norm: 0.9671 (inf) time: 0.6213 [2021-03-26 08:09:00 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 910/1251] eta: 0:03:34 lr: 0.000949 loss: 3.3987 (3.8299) grad_norm: 0.9853 (inf) time: 0.6194 [2021-03-26 08:09:06 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 920/1251] eta: 0:03:28 lr: 0.000949 loss: 3.5809 (3.8285) grad_norm: 1.0122 (inf) time: 0.6173 [2021-03-26 08:09:13 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 930/1251] eta: 0:03:21 lr: 0.000949 loss: 3.7967 (3.8294) grad_norm: 0.9946 (inf) time: 0.6294 [2021-03-26 08:09:19 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 940/1251] eta: 0:03:15 lr: 0.000949 loss: 3.6803 (3.8262) grad_norm: 0.9545 (inf) time: 0.6375 [2021-03-26 08:09:25 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 950/1251] eta: 0:03:09 lr: 0.000949 loss: 3.6803 (3.8252) grad_norm: 1.0878 (inf) time: 0.6329 [2021-03-26 08:09:31 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 960/1251] eta: 0:03:03 lr: 0.000949 loss: 3.7033 (3.8259) grad_norm: 1.0055 (inf) time: 0.6212 [2021-03-26 08:09:38 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 970/1251] eta: 0:02:56 lr: 0.000949 loss: 3.7040 (3.8233) grad_norm: 0.9255 (inf) time: 0.6159 [2021-03-26 08:09:44 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 980/1251] eta: 0:02:50 lr: 0.000949 loss: 3.8272 (3.8235) grad_norm: 0.9855 (inf) time: 0.6269 [2021-03-26 08:09:50 swin_base_patch4_window7_224] INFO: Epoch: [43] [ 990/1251] eta: 0:02:44 lr: 0.000949 loss: 4.0356 (3.8233) grad_norm: 1.0050 (inf) time: 0.6223 [2021-03-26 08:09:56 swin_base_patch4_window7_224] INFO: Epoch: [43] [1000/1251] eta: 0:02:37 lr: 0.000949 loss: 3.9124 (3.8231) grad_norm: 1.0050 (inf) time: 0.6200 [2021-03-26 08:10:03 swin_base_patch4_window7_224] INFO: Epoch: [43] [1010/1251] eta: 0:02:31 lr: 0.000949 loss: 3.8716 (3.8235) grad_norm: 1.0929 (inf) time: 0.6275 [2021-03-26 08:10:09 swin_base_patch4_window7_224] INFO: Epoch: [43] [1020/1251] eta: 0:02:25 lr: 0.000949 loss: 3.7341 (3.8233) grad_norm: 1.1094 (inf) time: 0.6255 [2021-03-26 08:10:15 swin_base_patch4_window7_224] INFO: Epoch: [43] [1030/1251] eta: 0:02:18 lr: 0.000949 loss: 3.6808 (3.8234) grad_norm: 1.0477 (inf) time: 0.6246 [2021-03-26 08:10:21 swin_base_patch4_window7_224] INFO: Epoch: [43] [1040/1251] eta: 0:02:12 lr: 0.000949 loss: 3.8423 (3.8237) grad_norm: 1.0116 (inf) time: 0.6222 [2021-03-26 08:10:27 swin_base_patch4_window7_224] INFO: Epoch: [43] [1050/1251] eta: 0:02:06 lr: 0.000949 loss: 3.9678 (3.8222) grad_norm: 1.0128 (inf) time: 0.6177 [2021-03-26 08:10:34 swin_base_patch4_window7_224] INFO: Epoch: [43] [1060/1251] eta: 0:02:00 lr: 0.000949 loss: 4.0918 (3.8235) grad_norm: 1.0262 (inf) time: 0.6207 [2021-03-26 08:10:40 swin_base_patch4_window7_224] INFO: Epoch: [43] [1070/1251] eta: 0:01:53 lr: 0.000949 loss: 4.0918 (3.8240) grad_norm: 1.0910 (inf) time: 0.6241 [2021-03-26 08:10:46 swin_base_patch4_window7_224] INFO: Epoch: [43] [1080/1251] eta: 0:01:47 lr: 0.000949 loss: 3.8470 (3.8253) grad_norm: 1.0690 (inf) time: 0.6277 [2021-03-26 08:10:52 swin_base_patch4_window7_224] INFO: Epoch: [43] [1090/1251] eta: 0:01:41 lr: 0.000949 loss: 3.9810 (3.8264) grad_norm: 0.9941 (inf) time: 0.6276 [2021-03-26 08:10:59 swin_base_patch4_window7_224] INFO: Epoch: [43] [1100/1251] eta: 0:01:34 lr: 0.000949 loss: 3.9810 (3.8262) grad_norm: 0.9200 (inf) time: 0.6192 [2021-03-26 08:11:05 swin_base_patch4_window7_224] INFO: Epoch: [43] [1110/1251] eta: 0:01:28 lr: 0.000949 loss: 3.8782 (3.8284) grad_norm: 0.9258 (inf) time: 0.6153 [2021-03-26 08:11:11 swin_base_patch4_window7_224] INFO: Epoch: [43] [1120/1251] eta: 0:01:22 lr: 0.000949 loss: 3.9350 (3.8296) grad_norm: 0.9396 (inf) time: 0.6227 [2021-03-26 08:11:17 swin_base_patch4_window7_224] INFO: Epoch: [43] [1130/1251] eta: 0:01:15 lr: 0.000949 loss: 3.8868 (3.8287) grad_norm: 0.9827 (inf) time: 0.6203 [2021-03-26 08:11:23 swin_base_patch4_window7_224] INFO: Epoch: [43] [1140/1251] eta: 0:01:09 lr: 0.000949 loss: 3.8746 (3.8283) grad_norm: 0.9846 (inf) time: 0.6170 [2021-03-26 08:11:30 swin_base_patch4_window7_224] INFO: Epoch: [43] [1150/1251] eta: 0:01:03 lr: 0.000949 loss: 3.9436 (3.8301) grad_norm: 0.9849 (inf) time: 0.6233 [2021-03-26 08:11:36 swin_base_patch4_window7_224] INFO: Epoch: [43] [1160/1251] eta: 0:00:57 lr: 0.000949 loss: 3.8958 (3.8279) grad_norm: 0.9849 (inf) time: 0.6249 [2021-03-26 08:11:42 swin_base_patch4_window7_224] INFO: Epoch: [43] [1170/1251] eta: 0:00:50 lr: 0.000949 loss: 3.7066 (3.8279) grad_norm: 0.9965 (inf) time: 0.6291 [2021-03-26 08:11:48 swin_base_patch4_window7_224] INFO: Epoch: [43] [1180/1251] eta: 0:00:44 lr: 0.000949 loss: 3.6268 (3.8259) grad_norm: 0.9972 (inf) time: 0.6276 [2021-03-26 08:11:55 swin_base_patch4_window7_224] INFO: Epoch: [43] [1190/1251] eta: 0:00:38 lr: 0.000948 loss: 3.9525 (3.8272) grad_norm: 1.0873 (inf) time: 0.6281 [2021-03-26 08:12:01 swin_base_patch4_window7_224] INFO: Epoch: [43] [1200/1251] eta: 0:00:32 lr: 0.000948 loss: 3.9525 (3.8257) grad_norm: 1.0052 (inf) time: 0.6248 [2021-03-26 08:12:07 swin_base_patch4_window7_224] INFO: Epoch: [43] [1210/1251] eta: 0:00:25 lr: 0.000948 loss: 3.7934 (3.8263) grad_norm: 0.9494 (inf) time: 0.6148 [2021-03-26 08:12:13 swin_base_patch4_window7_224] INFO: Epoch: [43] [1220/1251] eta: 0:00:19 lr: 0.000948 loss: 3.7636 (3.8249) grad_norm: 0.9904 (inf) time: 0.6140 [2021-03-26 08:12:19 swin_base_patch4_window7_224] INFO: Epoch: [43] [1230/1251] eta: 0:00:13 lr: 0.000948 loss: 3.7636 (3.8249) grad_norm: 1.0088 (inf) time: 0.6180 [2021-03-26 08:12:26 swin_base_patch4_window7_224] INFO: Epoch: [43] [1240/1251] eta: 0:00:06 lr: 0.000948 loss: 3.9356 (3.8257) grad_norm: 1.0088 (inf) time: 0.6184 [2021-03-26 08:12:32 swin_base_patch4_window7_224] INFO: Epoch: [43] [1250/1251] eta: 0:00:00 lr: 0.000948 loss: 3.9198 (3.8246) grad_norm: 0.9595 (inf) time: 0.6148 [2021-03-26 08:12:36 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:35 loss: 1.4481 (1.4481) acc1: 68.7500 (68.7500) acc5: 87.5000 (87.5000) [2021-03-26 08:12:39 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.4107 (1.3275) acc1: 71.8750 (71.1648) acc5: 90.6250 (89.7727) [2021-03-26 08:12:40 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.3283 (1.2987) acc1: 70.3125 (70.6845) acc5: 90.6250 (90.5506) [2021-03-26 08:12:43 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.3007 (1.2829) acc1: 68.7500 (70.8669) acc5: 90.6250 (90.8266) [2021-03-26 08:12:44 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2438 (1.2859) acc1: 70.3125 (70.2744) acc5: 90.6250 (90.7774) [2021-03-26 08:12:46 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1854 (1.2631) acc1: 70.3125 (70.7520) acc5: 92.1875 (91.1040) [2021-03-26 08:12:49 swin_base_patch4_window7_224] INFO: * Acc@1 71.396 Acc@5 91.122 loss 1.235 [2021-03-26 08:12:49 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 71.4% [2021-03-26 08:12:49 swin_base_patch4_window7_224] INFO: Max accuracy: 71.40% [2021-03-26 08:12:53 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 0/1251] eta: 1:32:55 lr: 0.000948 loss: 3.5764 (3.5764) grad_norm: 0.8470 (0.8470) time: 4.4572 [2021-03-26 08:12:59 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 10/1251] eta: 0:20:26 lr: 0.000948 loss: 3.8603 (3.7408) grad_norm: 1.0071 (1.0530) time: 0.9882 [2021-03-26 08:13:06 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 20/1251] eta: 0:16:39 lr: 0.000948 loss: 3.8814 (3.7903) grad_norm: 0.9793 (1.0334) time: 0.6296 [2021-03-26 08:13:12 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 30/1251] eta: 0:15:17 lr: 0.000948 loss: 3.9971 (3.8972) grad_norm: 1.0481 (1.0452) time: 0.6210 [2021-03-26 08:13:18 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 40/1251] eta: 0:14:33 lr: 0.000948 loss: 3.7684 (3.8051) grad_norm: 1.0862 (1.0652) time: 0.6271 [2021-03-26 08:13:24 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 50/1251] eta: 0:14:01 lr: 0.000948 loss: 3.8664 (3.8432) grad_norm: 0.9998 (1.0529) time: 0.6215 [2021-03-26 08:13:30 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 60/1251] eta: 0:13:38 lr: 0.000948 loss: 3.9061 (3.8378) grad_norm: 0.9849 (1.0465) time: 0.6175 [2021-03-26 08:13:37 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 70/1251] eta: 0:13:22 lr: 0.000948 loss: 3.8296 (3.8231) grad_norm: 0.9730 (1.0478) time: 0.6258 [2021-03-26 08:13:43 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 80/1251] eta: 0:13:07 lr: 0.000948 loss: 4.0454 (3.8364) grad_norm: 1.0067 (1.0572) time: 0.6262 [2021-03-26 08:13:49 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 90/1251] eta: 0:12:55 lr: 0.000948 loss: 3.8290 (3.8110) grad_norm: 1.0880 (1.0615) time: 0.6292 [2021-03-26 08:13:56 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 100/1251] eta: 0:12:44 lr: 0.000948 loss: 3.8391 (3.8279) grad_norm: 1.0721 (1.0594) time: 0.6331 [2021-03-26 08:14:02 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 110/1251] eta: 0:12:34 lr: 0.000948 loss: 3.9414 (3.8118) grad_norm: 1.0037 (1.0527) time: 0.6279 [2021-03-26 08:14:08 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 120/1251] eta: 0:12:23 lr: 0.000948 loss: 3.8951 (3.8091) grad_norm: 1.0037 (1.0521) time: 0.6216 [2021-03-26 08:14:14 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 130/1251] eta: 0:12:14 lr: 0.000948 loss: 3.9078 (3.8187) grad_norm: 0.9930 (1.0530) time: 0.6220 [2021-03-26 08:14:21 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 140/1251] eta: 0:12:06 lr: 0.000948 loss: 3.7379 (3.7905) grad_norm: 1.0949 (1.0564) time: 0.6324 [2021-03-26 08:14:27 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 150/1251] eta: 0:11:57 lr: 0.000948 loss: 3.8591 (3.7961) grad_norm: 1.0927 (1.0564) time: 0.6276 [2021-03-26 08:14:33 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 160/1251] eta: 0:11:49 lr: 0.000948 loss: 4.0522 (3.8116) grad_norm: 1.0120 (1.0566) time: 0.6261 [2021-03-26 08:14:40 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 170/1251] eta: 0:11:42 lr: 0.000948 loss: 4.0685 (3.8022) grad_norm: 1.0483 (1.0602) time: 0.6383 [2021-03-26 08:14:46 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 180/1251] eta: 0:11:34 lr: 0.000948 loss: 3.8856 (3.8109) grad_norm: 1.0609 (1.0601) time: 0.6356 [2021-03-26 08:14:52 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 190/1251] eta: 0:11:27 lr: 0.000948 loss: 3.8982 (3.8135) grad_norm: 1.0233 (1.0578) time: 0.6310 [2021-03-26 08:14:59 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 200/1251] eta: 0:11:19 lr: 0.000948 loss: 3.7389 (3.8008) grad_norm: 1.0175 (1.0570) time: 0.6277 [2021-03-26 08:15:05 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 210/1251] eta: 0:11:12 lr: 0.000948 loss: 3.7378 (3.8086) grad_norm: 1.0182 (1.0545) time: 0.6302 [2021-03-26 08:15:11 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 220/1251] eta: 0:11:05 lr: 0.000948 loss: 3.8933 (3.7983) grad_norm: 1.0387 (1.0554) time: 0.6298 [2021-03-26 08:15:17 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 230/1251] eta: 0:10:57 lr: 0.000948 loss: 3.8640 (3.7964) grad_norm: 1.0585 (1.0593) time: 0.6235 [2021-03-26 08:15:24 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 240/1251] eta: 0:10:50 lr: 0.000948 loss: 3.9319 (3.7963) grad_norm: 1.1599 (1.0698) time: 0.6277 [2021-03-26 08:15:30 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 250/1251] eta: 0:10:43 lr: 0.000948 loss: 3.5177 (3.7900) grad_norm: 1.0836 (1.0672) time: 0.6241 [2021-03-26 08:15:36 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 260/1251] eta: 0:10:36 lr: 0.000948 loss: 3.6373 (3.7944) grad_norm: 0.9758 (1.0632) time: 0.6196 [2021-03-26 08:15:42 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 270/1251] eta: 0:10:29 lr: 0.000948 loss: 3.9319 (3.7944) grad_norm: 0.9796 (1.0630) time: 0.6238 [2021-03-26 08:15:49 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 280/1251] eta: 0:10:22 lr: 0.000948 loss: 4.1061 (3.8003) grad_norm: 1.0116 (1.0642) time: 0.6251 [2021-03-26 08:15:55 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 290/1251] eta: 0:10:15 lr: 0.000948 loss: 4.1061 (3.8051) grad_norm: 1.0312 (1.0685) time: 0.6248 [2021-03-26 08:16:01 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 300/1251] eta: 0:10:08 lr: 0.000948 loss: 4.0675 (3.8081) grad_norm: 0.9754 (1.0658) time: 0.6217 [2021-03-26 08:16:07 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 310/1251] eta: 0:10:01 lr: 0.000948 loss: 3.9617 (3.8069) grad_norm: 0.9754 (1.0660) time: 0.6256 [2021-03-26 08:16:14 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 320/1251] eta: 0:09:54 lr: 0.000948 loss: 4.0262 (3.8113) grad_norm: 1.0174 (1.0653) time: 0.6245 [2021-03-26 08:16:20 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 330/1251] eta: 0:09:47 lr: 0.000948 loss: 4.1904 (3.8232) grad_norm: 1.0913 (1.0678) time: 0.6235 [2021-03-26 08:16:26 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 340/1251] eta: 0:09:40 lr: 0.000948 loss: 3.8603 (3.8179) grad_norm: 0.9969 (1.0656) time: 0.6225 [2021-03-26 08:16:32 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 350/1251] eta: 0:09:34 lr: 0.000948 loss: 3.7428 (3.8209) grad_norm: 0.9743 (1.0640) time: 0.6208 [2021-03-26 08:16:39 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 360/1251] eta: 0:09:27 lr: 0.000948 loss: 3.7788 (3.8131) grad_norm: 0.9788 (1.0624) time: 0.6273 [2021-03-26 08:16:45 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 370/1251] eta: 0:09:20 lr: 0.000948 loss: 3.7605 (3.8152) grad_norm: 0.9974 (1.0628) time: 0.6237 [2021-03-26 08:16:51 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 380/1251] eta: 0:09:14 lr: 0.000948 loss: 4.0486 (3.8193) grad_norm: 1.0530 (1.0642) time: 0.6209 [2021-03-26 08:16:57 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 390/1251] eta: 0:09:07 lr: 0.000948 loss: 4.0958 (3.8215) grad_norm: 1.0483 (1.0635) time: 0.6266 [2021-03-26 08:17:03 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 400/1251] eta: 0:09:00 lr: 0.000948 loss: 4.0822 (3.8252) grad_norm: 0.9939 (1.0615) time: 0.6228 [2021-03-26 08:17:10 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 410/1251] eta: 0:08:54 lr: 0.000948 loss: 3.8643 (3.8247) grad_norm: 0.9712 (1.0596) time: 0.6181 [2021-03-26 08:17:16 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 420/1251] eta: 0:08:47 lr: 0.000948 loss: 3.8019 (3.8233) grad_norm: 1.0115 (1.0591) time: 0.6252 [2021-03-26 08:17:22 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 430/1251] eta: 0:08:41 lr: 0.000948 loss: 3.9050 (3.8240) grad_norm: 1.0683 (1.0599) time: 0.6253 [2021-03-26 08:17:28 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 440/1251] eta: 0:08:34 lr: 0.000948 loss: 4.0421 (3.8298) grad_norm: 1.0455 (1.0588) time: 0.6251 [2021-03-26 08:17:35 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 450/1251] eta: 0:08:27 lr: 0.000948 loss: 3.9865 (3.8288) grad_norm: 1.0083 (1.0579) time: 0.6211 [2021-03-26 08:17:41 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 460/1251] eta: 0:08:21 lr: 0.000948 loss: 3.7966 (3.8217) grad_norm: 1.0039 (1.0572) time: 0.6172 [2021-03-26 08:17:47 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 470/1251] eta: 0:08:14 lr: 0.000948 loss: 4.0308 (3.8279) grad_norm: 1.0446 (1.0617) time: 0.6226 [2021-03-26 08:17:53 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 480/1251] eta: 0:08:08 lr: 0.000947 loss: 4.0415 (3.8286) grad_norm: 1.0551 (1.0621) time: 0.6274 [2021-03-26 08:18:00 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 490/1251] eta: 0:08:01 lr: 0.000947 loss: 4.0179 (3.8271) grad_norm: 1.0477 (1.0620) time: 0.6253 [2021-03-26 08:18:06 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 500/1251] eta: 0:07:55 lr: 0.000947 loss: 4.0486 (3.8245) grad_norm: 1.0659 (1.0641) time: 0.6242 [2021-03-26 08:18:12 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 510/1251] eta: 0:07:48 lr: 0.000947 loss: 3.9212 (3.8267) grad_norm: 1.0255 (1.0629) time: 0.6208 [2021-03-26 08:18:18 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 520/1251] eta: 0:07:42 lr: 0.000947 loss: 4.1282 (3.8341) grad_norm: 0.9967 (1.0642) time: 0.6241 [2021-03-26 08:18:25 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 530/1251] eta: 0:07:36 lr: 0.000947 loss: 4.1282 (3.8325) grad_norm: 1.1245 (1.0656) time: 0.6286 [2021-03-26 08:18:31 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 540/1251] eta: 0:07:29 lr: 0.000947 loss: 3.8889 (3.8340) grad_norm: 1.1129 (1.0666) time: 0.6236 [2021-03-26 08:18:37 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 550/1251] eta: 0:07:23 lr: 0.000947 loss: 3.9364 (3.8337) grad_norm: 1.0760 (1.0674) time: 0.6365 [2021-03-26 08:18:44 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 560/1251] eta: 0:07:17 lr: 0.000947 loss: 3.9803 (3.8362) grad_norm: 1.0817 (1.0688) time: 0.6449 [2021-03-26 08:18:50 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 570/1251] eta: 0:07:10 lr: 0.000947 loss: 3.9363 (3.8361) grad_norm: 1.0817 (1.0689) time: 0.6311 [2021-03-26 08:18:56 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 580/1251] eta: 0:07:04 lr: 0.000947 loss: 3.9220 (3.8351) grad_norm: 1.0123 (1.0680) time: 0.6204 [2021-03-26 08:19:02 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 590/1251] eta: 0:06:58 lr: 0.000947 loss: 3.9396 (3.8366) grad_norm: 1.0106 (1.0682) time: 0.6233 [2021-03-26 08:19:09 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 600/1251] eta: 0:06:51 lr: 0.000947 loss: 3.8285 (3.8355) grad_norm: 1.0072 (1.0667) time: 0.6257 [2021-03-26 08:19:15 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 610/1251] eta: 0:06:45 lr: 0.000947 loss: 3.6164 (3.8322) grad_norm: 0.9379 (1.0643) time: 0.6203 [2021-03-26 08:19:21 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 620/1251] eta: 0:06:38 lr: 0.000947 loss: 3.7321 (3.8298) grad_norm: 0.9541 (1.0635) time: 0.6224 [2021-03-26 08:19:27 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 630/1251] eta: 0:06:32 lr: 0.000947 loss: 3.8780 (3.8280) grad_norm: 1.0029 (1.0622) time: 0.6256 [2021-03-26 08:19:34 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 640/1251] eta: 0:06:25 lr: 0.000947 loss: 3.9022 (3.8273) grad_norm: 0.9693 (1.0609) time: 0.6227 [2021-03-26 08:19:40 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 650/1251] eta: 0:06:19 lr: 0.000947 loss: 3.9489 (3.8296) grad_norm: 0.9635 (1.0603) time: 0.6229 [2021-03-26 08:19:46 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 660/1251] eta: 0:06:13 lr: 0.000947 loss: 4.1092 (3.8335) grad_norm: 0.9768 (1.0595) time: 0.6218 [2021-03-26 08:19:52 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 670/1251] eta: 0:06:06 lr: 0.000947 loss: 3.8720 (3.8301) grad_norm: 0.9807 (1.0586) time: 0.6205 [2021-03-26 08:19:58 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 680/1251] eta: 0:06:00 lr: 0.000947 loss: 3.6213 (3.8282) grad_norm: 0.9807 (1.0578) time: 0.6216 [2021-03-26 08:20:05 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 690/1251] eta: 0:05:53 lr: 0.000947 loss: 3.7495 (3.8278) grad_norm: 0.9739 (1.0567) time: 0.6245 [2021-03-26 08:20:11 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 700/1251] eta: 0:05:47 lr: 0.000947 loss: 3.6514 (3.8257) grad_norm: 0.9578 (1.0562) time: 0.6252 [2021-03-26 08:20:17 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 710/1251] eta: 0:05:41 lr: 0.000947 loss: 4.0163 (3.8284) grad_norm: 1.0861 (1.0573) time: 0.6305 [2021-03-26 08:20:24 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 720/1251] eta: 0:05:34 lr: 0.000947 loss: 4.0193 (3.8245) grad_norm: 1.1237 (1.0583) time: 0.6288 [2021-03-26 08:20:30 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 730/1251] eta: 0:05:28 lr: 0.000947 loss: 3.6206 (3.8216) grad_norm: 1.0495 (1.0576) time: 0.6206 [2021-03-26 08:20:36 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 740/1251] eta: 0:05:22 lr: 0.000947 loss: 3.8040 (3.8224) grad_norm: 1.0057 (1.0573) time: 0.6323 [2021-03-26 08:20:42 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 750/1251] eta: 0:05:16 lr: 0.000947 loss: 3.9571 (3.8230) grad_norm: 1.0005 (1.0562) time: 0.6371 [2021-03-26 08:20:49 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 760/1251] eta: 0:05:09 lr: 0.000947 loss: 3.6158 (3.8211) grad_norm: 1.0080 (1.0564) time: 0.6296 [2021-03-26 08:20:55 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 770/1251] eta: 0:05:03 lr: 0.000947 loss: 3.8682 (3.8215) grad_norm: 1.0182 (1.0558) time: 0.6236 [2021-03-26 08:21:01 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 780/1251] eta: 0:04:57 lr: 0.000947 loss: 3.8682 (3.8182) grad_norm: 0.9644 (1.0549) time: 0.6252 [2021-03-26 08:21:08 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 790/1251] eta: 0:04:50 lr: 0.000947 loss: 3.5708 (3.8155) grad_norm: 0.9861 (1.0548) time: 0.6299 [2021-03-26 08:21:14 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 800/1251] eta: 0:04:44 lr: 0.000947 loss: 3.7280 (3.8165) grad_norm: 1.0090 (1.0550) time: 0.6264 [2021-03-26 08:21:20 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 810/1251] eta: 0:04:38 lr: 0.000947 loss: 3.9996 (3.8135) grad_norm: 1.0264 (1.0552) time: 0.6257 [2021-03-26 08:21:26 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 820/1251] eta: 0:04:31 lr: 0.000947 loss: 4.0660 (3.8199) grad_norm: 0.9967 (1.0545) time: 0.6271 [2021-03-26 08:21:33 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 830/1251] eta: 0:04:25 lr: 0.000947 loss: 4.0938 (3.8202) grad_norm: 1.0115 (1.0553) time: 0.6243 [2021-03-26 08:21:39 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 840/1251] eta: 0:04:19 lr: 0.000947 loss: 3.7806 (3.8176) grad_norm: 1.0295 (1.0553) time: 0.6230 [2021-03-26 08:21:45 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 850/1251] eta: 0:04:12 lr: 0.000947 loss: 3.7491 (3.8184) grad_norm: 1.0051 (1.0547) time: 0.6223 [2021-03-26 08:21:51 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 860/1251] eta: 0:04:06 lr: 0.000947 loss: 3.6031 (3.8155) grad_norm: 1.0051 (1.0546) time: 0.6194 [2021-03-26 08:21:57 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 870/1251] eta: 0:04:00 lr: 0.000947 loss: 3.8590 (3.8172) grad_norm: 0.9595 (1.0538) time: 0.6182 [2021-03-26 08:22:04 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 880/1251] eta: 0:03:53 lr: 0.000947 loss: 3.8377 (3.8169) grad_norm: 0.9780 (1.0538) time: 0.6213 [2021-03-26 08:22:10 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 890/1251] eta: 0:03:47 lr: 0.000947 loss: 4.0400 (3.8211) grad_norm: 1.0050 (1.0541) time: 0.6189 [2021-03-26 08:22:16 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 900/1251] eta: 0:03:41 lr: 0.000947 loss: 4.0077 (3.8194) grad_norm: 1.0136 (1.0548) time: 0.6212 [2021-03-26 08:22:22 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 910/1251] eta: 0:03:34 lr: 0.000947 loss: 3.6513 (3.8219) grad_norm: 1.0259 (1.0549) time: 0.6285 [2021-03-26 08:22:29 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 920/1251] eta: 0:03:28 lr: 0.000947 loss: 4.1582 (3.8239) grad_norm: 1.0218 (1.0546) time: 0.6264 [2021-03-26 08:22:35 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 930/1251] eta: 0:03:22 lr: 0.000947 loss: 4.1582 (3.8238) grad_norm: 0.9835 (1.0540) time: 0.6232 [2021-03-26 08:22:41 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 940/1251] eta: 0:03:15 lr: 0.000947 loss: 3.7673 (3.8246) grad_norm: 0.9957 (1.0535) time: 0.6204 [2021-03-26 08:22:47 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 950/1251] eta: 0:03:09 lr: 0.000947 loss: 4.0164 (3.8254) grad_norm: 0.9730 (1.0526) time: 0.6187 [2021-03-26 08:22:53 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 960/1251] eta: 0:03:03 lr: 0.000947 loss: 3.7439 (3.8235) grad_norm: 0.9730 (1.0524) time: 0.6201 [2021-03-26 08:23:00 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 970/1251] eta: 0:02:56 lr: 0.000947 loss: 3.8062 (3.8248) grad_norm: 1.0046 (1.0521) time: 0.6204 [2021-03-26 08:23:06 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 980/1251] eta: 0:02:50 lr: 0.000947 loss: 3.9409 (3.8246) grad_norm: 1.0046 (1.0522) time: 0.6166 [2021-03-26 08:23:12 swin_base_patch4_window7_224] INFO: Epoch: [44] [ 990/1251] eta: 0:02:44 lr: 0.000947 loss: 3.8588 (3.8236) grad_norm: 0.9457 (1.0516) time: 0.6182 [2021-03-26 08:23:18 swin_base_patch4_window7_224] INFO: Epoch: [44] [1000/1251] eta: 0:02:37 lr: 0.000947 loss: 3.8724 (3.8236) grad_norm: 0.9460 (1.0525) time: 0.6222 [2021-03-26 08:23:24 swin_base_patch4_window7_224] INFO: Epoch: [44] [1010/1251] eta: 0:02:31 lr: 0.000947 loss: 3.9040 (3.8241) grad_norm: 1.1794 (1.0537) time: 0.6257 [2021-03-26 08:23:31 swin_base_patch4_window7_224] INFO: Epoch: [44] [1020/1251] eta: 0:02:25 lr: 0.000946 loss: 3.9224 (3.8252) grad_norm: 1.1546 (1.0538) time: 0.6263 [2021-03-26 08:23:37 swin_base_patch4_window7_224] INFO: Epoch: [44] [1030/1251] eta: 0:02:18 lr: 0.000946 loss: 3.8994 (3.8245) grad_norm: 1.1546 (1.0551) time: 0.6254 [2021-03-26 08:23:43 swin_base_patch4_window7_224] INFO: Epoch: [44] [1040/1251] eta: 0:02:12 lr: 0.000946 loss: 3.6165 (3.8230) grad_norm: 1.0633 (1.0550) time: 0.6232 [2021-03-26 08:23:49 swin_base_patch4_window7_224] INFO: Epoch: [44] [1050/1251] eta: 0:02:06 lr: 0.000946 loss: 3.6165 (3.8212) grad_norm: 1.0002 (1.0547) time: 0.6209 [2021-03-26 08:23:56 swin_base_patch4_window7_224] INFO: Epoch: [44] [1060/1251] eta: 0:02:00 lr: 0.000946 loss: 3.8791 (3.8221) grad_norm: 0.9614 (1.0548) time: 0.6172 [2021-03-26 08:24:02 swin_base_patch4_window7_224] INFO: Epoch: [44] [1070/1251] eta: 0:01:53 lr: 0.000946 loss: 3.9852 (3.8234) grad_norm: 0.9823 (1.0546) time: 0.6188 [2021-03-26 08:24:08 swin_base_patch4_window7_224] INFO: Epoch: [44] [1080/1251] eta: 0:01:47 lr: 0.000946 loss: 3.8013 (3.8205) grad_norm: 1.0256 (1.0543) time: 0.6232 [2021-03-26 08:24:14 swin_base_patch4_window7_224] INFO: Epoch: [44] [1090/1251] eta: 0:01:41 lr: 0.000946 loss: 3.6343 (3.8203) grad_norm: 1.0068 (1.0540) time: 0.6257 [2021-03-26 08:24:20 swin_base_patch4_window7_224] INFO: Epoch: [44] [1100/1251] eta: 0:01:34 lr: 0.000946 loss: 3.8320 (3.8208) grad_norm: 0.9891 (1.0536) time: 0.6237 [2021-03-26 08:24:27 swin_base_patch4_window7_224] INFO: Epoch: [44] [1110/1251] eta: 0:01:28 lr: 0.000946 loss: 3.7385 (3.8190) grad_norm: 1.0477 (1.0541) time: 0.6200 [2021-03-26 08:24:33 swin_base_patch4_window7_224] INFO: Epoch: [44] [1120/1251] eta: 0:01:22 lr: 0.000946 loss: 3.7385 (3.8173) grad_norm: 1.0614 (1.0542) time: 0.6240 [2021-03-26 08:24:39 swin_base_patch4_window7_224] INFO: Epoch: [44] [1130/1251] eta: 0:01:16 lr: 0.000946 loss: 3.8520 (3.8180) grad_norm: 1.0694 (1.0547) time: 0.6242 [2021-03-26 08:24:45 swin_base_patch4_window7_224] INFO: Epoch: [44] [1140/1251] eta: 0:01:09 lr: 0.000946 loss: 3.8094 (3.8167) grad_norm: 1.0177 (1.0545) time: 0.6222 [2021-03-26 08:24:52 swin_base_patch4_window7_224] INFO: Epoch: [44] [1150/1251] eta: 0:01:03 lr: 0.000946 loss: 3.9296 (3.8180) grad_norm: 0.9804 (1.0545) time: 0.6204 [2021-03-26 08:24:58 swin_base_patch4_window7_224] INFO: Epoch: [44] [1160/1251] eta: 0:00:57 lr: 0.000946 loss: 3.9554 (3.8162) grad_norm: 0.9804 (1.0540) time: 0.6169 [2021-03-26 08:25:04 swin_base_patch4_window7_224] INFO: Epoch: [44] [1170/1251] eta: 0:00:50 lr: 0.000946 loss: 4.1378 (3.8171) grad_norm: 1.0246 (1.0542) time: 0.6191 [2021-03-26 08:25:10 swin_base_patch4_window7_224] INFO: Epoch: [44] [1180/1251] eta: 0:00:44 lr: 0.000946 loss: 4.1378 (3.8155) grad_norm: 0.9975 (1.0535) time: 0.6188 [2021-03-26 08:25:16 swin_base_patch4_window7_224] INFO: Epoch: [44] [1190/1251] eta: 0:00:38 lr: 0.000946 loss: 3.8217 (3.8157) grad_norm: 0.9933 (1.0534) time: 0.6201 [2021-03-26 08:25:23 swin_base_patch4_window7_224] INFO: Epoch: [44] [1200/1251] eta: 0:00:32 lr: 0.000946 loss: 3.9287 (3.8171) grad_norm: 1.0137 (1.0534) time: 0.6213 [2021-03-26 08:25:29 swin_base_patch4_window7_224] INFO: Epoch: [44] [1210/1251] eta: 0:00:25 lr: 0.000946 loss: 4.0178 (3.8170) grad_norm: 1.0500 (1.0538) time: 0.6226 [2021-03-26 08:25:35 swin_base_patch4_window7_224] INFO: Epoch: [44] [1220/1251] eta: 0:00:19 lr: 0.000946 loss: 3.9293 (3.8156) grad_norm: 1.0691 (1.0547) time: 0.6247 [2021-03-26 08:25:41 swin_base_patch4_window7_224] INFO: Epoch: [44] [1230/1251] eta: 0:00:13 lr: 0.000946 loss: 3.9293 (3.8176) grad_norm: 1.0624 (1.0552) time: 0.6245 [2021-03-26 08:25:47 swin_base_patch4_window7_224] INFO: Epoch: [44] [1240/1251] eta: 0:00:06 lr: 0.000946 loss: 4.0507 (3.8189) grad_norm: 1.0212 (1.0549) time: 0.6223 [2021-03-26 08:25:54 swin_base_patch4_window7_224] INFO: Epoch: [44] [1250/1251] eta: 0:00:00 lr: 0.000946 loss: 4.0230 (3.8198) grad_norm: 0.9734 (1.0545) time: 0.6088 [2021-03-26 08:25:58 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:44 loss: 0.8980 (0.8980) acc1: 78.1250 (78.1250) acc5: 96.8750 (96.8750) [2021-03-26 08:26:00 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.1908 (1.1643) acc1: 70.3125 (71.5909) acc5: 93.7500 (92.8977) [2021-03-26 08:26:03 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.2335 (1.2002) acc1: 70.3125 (71.8006) acc5: 90.6250 (91.8155) [2021-03-26 08:26:05 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.2222 (1.1886) acc1: 73.4375 (71.8246) acc5: 90.6250 (91.8347) [2021-03-26 08:26:08 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2041 (1.2142) acc1: 70.3125 (71.3796) acc5: 90.6250 (91.6159) [2021-03-26 08:26:09 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2109 (1.2123) acc1: 70.3125 (71.2320) acc5: 90.6250 (91.6480) [2021-03-26 08:26:11 swin_base_patch4_window7_224] INFO: * Acc@1 71.752 Acc@5 91.338 loss 1.202 [2021-03-26 08:26:11 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 71.8% [2021-03-26 08:26:11 swin_base_patch4_window7_224] INFO: Max accuracy: 71.75% [2021-03-26 08:26:15 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 0/1251] eta: 1:25:57 lr: 0.000946 loss: 4.4859 (4.4859) grad_norm: 0.7927 (0.7927) time: 4.1230 [2021-03-26 08:26:22 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 10/1251] eta: 0:19:35 lr: 0.000946 loss: 3.8483 (3.9361) grad_norm: 0.9730 (1.0134) time: 0.9469 [2021-03-26 08:26:28 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 20/1251] eta: 0:16:13 lr: 0.000946 loss: 3.9215 (4.0458) grad_norm: 1.0034 (1.0192) time: 0.6246 [2021-03-26 08:26:34 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 30/1251] eta: 0:15:04 lr: 0.000946 loss: 4.0446 (4.0375) grad_norm: 1.0040 (1.0071) time: 0.6273 [2021-03-26 08:26:40 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 40/1251] eta: 0:14:21 lr: 0.000946 loss: 3.7542 (3.9970) grad_norm: 1.0184 (1.0401) time: 0.6273 [2021-03-26 08:26:47 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 50/1251] eta: 0:13:54 lr: 0.000946 loss: 3.7057 (3.9246) grad_norm: 1.1312 (1.0610) time: 0.6227 [2021-03-26 08:26:53 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 60/1251] eta: 0:13:33 lr: 0.000946 loss: 3.8962 (3.9366) grad_norm: 1.0613 (1.0675) time: 0.6248 [2021-03-26 08:26:59 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 70/1251] eta: 0:13:17 lr: 0.000946 loss: 3.9229 (3.9158) grad_norm: 0.9897 (1.0603) time: 0.6252 [2021-03-26 08:27:05 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 80/1251] eta: 0:13:01 lr: 0.000946 loss: 3.9812 (3.9159) grad_norm: 0.9745 (1.0542) time: 0.6192 [2021-03-26 08:27:11 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 90/1251] eta: 0:12:49 lr: 0.000946 loss: 4.1049 (3.9415) grad_norm: 1.0834 (1.0692) time: 0.6192 [2021-03-26 08:27:18 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 100/1251] eta: 0:12:38 lr: 0.000946 loss: 3.9869 (3.9263) grad_norm: 1.0321 (1.0634) time: 0.6239 [2021-03-26 08:27:24 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 110/1251] eta: 0:12:28 lr: 0.000946 loss: 3.9055 (3.9354) grad_norm: 1.0146 (1.0622) time: 0.6242 [2021-03-26 08:27:30 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 120/1251] eta: 0:12:18 lr: 0.000946 loss: 3.9055 (3.9178) grad_norm: 0.9989 (1.0525) time: 0.6240 [2021-03-26 08:27:36 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 130/1251] eta: 0:12:09 lr: 0.000946 loss: 3.8803 (3.9319) grad_norm: 0.9771 (1.0488) time: 0.6208 [2021-03-26 08:27:43 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 140/1251] eta: 0:12:00 lr: 0.000946 loss: 3.8532 (3.9171) grad_norm: 0.9771 (1.0431) time: 0.6237 [2021-03-26 08:27:49 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 150/1251] eta: 0:11:52 lr: 0.000946 loss: 3.6208 (3.9056) grad_norm: 0.9740 (1.0416) time: 0.6229 [2021-03-26 08:27:55 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 160/1251] eta: 0:11:44 lr: 0.000946 loss: 3.8872 (3.8844) grad_norm: 1.0398 (1.0455) time: 0.6233 [2021-03-26 08:28:01 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 170/1251] eta: 0:11:37 lr: 0.000946 loss: 3.8872 (3.8740) grad_norm: 1.1628 (1.0613) time: 0.6317 [2021-03-26 08:28:08 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 180/1251] eta: 0:11:30 lr: 0.000946 loss: 3.9568 (3.8694) grad_norm: 1.1883 (1.0682) time: 0.6337 [2021-03-26 08:28:14 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 190/1251] eta: 0:11:23 lr: 0.000946 loss: 4.0764 (3.8822) grad_norm: 1.0958 (1.0681) time: 0.6402 [2021-03-26 08:28:20 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 200/1251] eta: 0:11:15 lr: 0.000946 loss: 4.0463 (3.8724) grad_norm: 1.0129 (1.0653) time: 0.6318 [2021-03-26 08:28:27 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 210/1251] eta: 0:11:08 lr: 0.000946 loss: 4.0280 (3.8783) grad_norm: 0.9930 (1.0648) time: 0.6233 [2021-03-26 08:28:33 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 220/1251] eta: 0:11:01 lr: 0.000946 loss: 4.0280 (3.8810) grad_norm: 1.0520 (1.0661) time: 0.6254 [2021-03-26 08:28:39 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 230/1251] eta: 0:10:54 lr: 0.000946 loss: 3.9543 (3.8857) grad_norm: 1.0305 (1.0712) time: 0.6217 [2021-03-26 08:28:45 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 240/1251] eta: 0:10:46 lr: 0.000946 loss: 3.8484 (3.8687) grad_norm: 1.0043 (1.0704) time: 0.6203 [2021-03-26 08:28:52 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 250/1251] eta: 0:10:39 lr: 0.000946 loss: 3.9248 (3.8627) grad_norm: 1.1331 (1.0745) time: 0.6192 [2021-03-26 08:28:58 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 260/1251] eta: 0:10:33 lr: 0.000946 loss: 3.9273 (3.8608) grad_norm: 1.0800 (1.0724) time: 0.6287 [2021-03-26 08:29:04 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 270/1251] eta: 0:10:26 lr: 0.000946 loss: 3.7675 (3.8573) grad_norm: 0.9814 (1.0690) time: 0.6285 [2021-03-26 08:29:10 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 280/1251] eta: 0:10:19 lr: 0.000946 loss: 3.4689 (3.8495) grad_norm: 1.0062 (1.0704) time: 0.6273 [2021-03-26 08:29:17 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 290/1251] eta: 0:10:12 lr: 0.000946 loss: 3.7312 (3.8453) grad_norm: 1.0431 (1.0701) time: 0.6276 [2021-03-26 08:29:23 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 300/1251] eta: 0:10:05 lr: 0.000945 loss: 3.9698 (3.8465) grad_norm: 1.0534 (1.0772) time: 0.6241 [2021-03-26 08:29:29 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 310/1251] eta: 0:09:58 lr: 0.000945 loss: 3.9698 (3.8517) grad_norm: 1.0659 (1.0769) time: 0.6218 [2021-03-26 08:29:35 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 320/1251] eta: 0:09:52 lr: 0.000945 loss: 3.9322 (3.8517) grad_norm: 0.9842 (1.0762) time: 0.6188 [2021-03-26 08:29:42 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 330/1251] eta: 0:09:45 lr: 0.000945 loss: 3.9322 (3.8490) grad_norm: 0.9842 (1.0740) time: 0.6229 [2021-03-26 08:29:48 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 340/1251] eta: 0:09:38 lr: 0.000945 loss: 3.8862 (3.8487) grad_norm: 1.0215 (1.0733) time: 0.6234 [2021-03-26 08:29:54 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 350/1251] eta: 0:09:31 lr: 0.000945 loss: 4.0191 (3.8480) grad_norm: 1.0310 (1.0726) time: 0.6204 [2021-03-26 08:30:00 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 360/1251] eta: 0:09:25 lr: 0.000945 loss: 4.0434 (3.8498) grad_norm: 1.0488 (1.0749) time: 0.6273 [2021-03-26 08:30:07 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 370/1251] eta: 0:09:19 lr: 0.000945 loss: 3.9736 (3.8477) grad_norm: 1.0909 (1.0749) time: 0.6327 [2021-03-26 08:30:13 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 380/1251] eta: 0:09:12 lr: 0.000945 loss: 3.9394 (3.8498) grad_norm: 1.0255 (1.0733) time: 0.6266 [2021-03-26 08:30:19 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 390/1251] eta: 0:09:05 lr: 0.000945 loss: 3.9394 (3.8509) grad_norm: 0.9983 (1.0715) time: 0.6189 [2021-03-26 08:30:25 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 400/1251] eta: 0:08:59 lr: 0.000945 loss: 3.9811 (3.8511) grad_norm: 1.0118 (1.0708) time: 0.6195 [2021-03-26 08:30:32 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 410/1251] eta: 0:08:52 lr: 0.000945 loss: 3.9811 (3.8479) grad_norm: 1.0456 (1.0713) time: 0.6272 [2021-03-26 08:30:38 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 420/1251] eta: 0:08:46 lr: 0.000945 loss: 4.0216 (3.8500) grad_norm: 1.0456 (1.0703) time: 0.6214 [2021-03-26 08:30:44 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 430/1251] eta: 0:08:39 lr: 0.000945 loss: 4.0096 (3.8494) grad_norm: 1.0411 (1.0701) time: 0.6154 [2021-03-26 08:30:50 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 440/1251] eta: 0:08:32 lr: 0.000945 loss: 3.7299 (3.8440) grad_norm: 1.0526 (1.0724) time: 0.6215 [2021-03-26 08:30:56 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 450/1251] eta: 0:08:26 lr: 0.000945 loss: 3.7156 (3.8433) grad_norm: 1.0526 (1.0720) time: 0.6190 [2021-03-26 08:31:02 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 460/1251] eta: 0:08:19 lr: 0.000945 loss: 3.7548 (3.8362) grad_norm: 0.9937 (1.0707) time: 0.6166 [2021-03-26 08:31:09 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 470/1251] eta: 0:08:13 lr: 0.000945 loss: 3.7548 (3.8366) grad_norm: 0.9859 (1.0686) time: 0.6201 [2021-03-26 08:31:15 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 480/1251] eta: 0:08:06 lr: 0.000945 loss: 3.9939 (3.8383) grad_norm: 0.9909 (1.0681) time: 0.6191 [2021-03-26 08:31:21 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 490/1251] eta: 0:08:00 lr: 0.000945 loss: 3.9983 (3.8381) grad_norm: 0.9987 (1.0682) time: 0.6157 [2021-03-26 08:31:27 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 500/1251] eta: 0:07:53 lr: 0.000945 loss: 4.0104 (3.8406) grad_norm: 1.0111 (1.0690) time: 0.6204 [2021-03-26 08:31:33 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 510/1251] eta: 0:07:47 lr: 0.000945 loss: 3.9946 (3.8408) grad_norm: 1.1209 (1.0717) time: 0.6230 [2021-03-26 08:31:40 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 520/1251] eta: 0:07:40 lr: 0.000945 loss: 3.9461 (3.8378) grad_norm: 1.1408 (1.0732) time: 0.6248 [2021-03-26 08:31:46 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 530/1251] eta: 0:07:34 lr: 0.000945 loss: 4.1902 (3.8408) grad_norm: 1.0390 (1.0713) time: 0.6230 [2021-03-26 08:31:52 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 540/1251] eta: 0:07:27 lr: 0.000945 loss: 4.1117 (3.8432) grad_norm: 0.9609 (1.0695) time: 0.6153 [2021-03-26 08:31:59 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 550/1251] eta: 0:07:21 lr: 0.000945 loss: 4.0200 (3.8453) grad_norm: 0.9744 (1.0690) time: 0.6300 [2021-03-26 08:32:05 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 560/1251] eta: 0:07:15 lr: 0.000945 loss: 3.9585 (3.8436) grad_norm: 0.9750 (1.0671) time: 0.6352 [2021-03-26 08:32:11 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 570/1251] eta: 0:07:09 lr: 0.000945 loss: 3.7034 (3.8405) grad_norm: 1.0344 (1.0689) time: 0.6279 [2021-03-26 08:32:17 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 580/1251] eta: 0:07:02 lr: 0.000945 loss: 3.6643 (3.8355) grad_norm: 1.0801 (1.0696) time: 0.6248 [2021-03-26 08:32:23 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 590/1251] eta: 0:06:56 lr: 0.000945 loss: 3.7717 (3.8370) grad_norm: 1.0089 (1.0677) time: 0.6197 [2021-03-26 08:32:30 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 600/1251] eta: 0:06:49 lr: 0.000945 loss: 3.7717 (3.8324) grad_norm: 0.9762 (1.0669) time: 0.6186 [2021-03-26 08:32:36 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 610/1251] eta: 0:06:43 lr: 0.000945 loss: 3.9085 (3.8339) grad_norm: 1.0280 (1.0684) time: 0.6233 [2021-03-26 08:32:42 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 620/1251] eta: 0:06:37 lr: 0.000945 loss: 4.0858 (3.8356) grad_norm: 1.0222 (1.0678) time: 0.6255 [2021-03-26 08:32:48 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 630/1251] eta: 0:06:30 lr: 0.000945 loss: 3.9921 (3.8362) grad_norm: 0.9862 (1.0670) time: 0.6214 [2021-03-26 08:32:55 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 640/1251] eta: 0:06:24 lr: 0.000945 loss: 3.9515 (3.8338) grad_norm: 0.9870 (1.0659) time: 0.6198 [2021-03-26 08:33:01 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 650/1251] eta: 0:06:18 lr: 0.000945 loss: 3.7975 (3.8324) grad_norm: 0.9415 (1.0643) time: 0.6176 [2021-03-26 08:33:07 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 660/1251] eta: 0:06:11 lr: 0.000945 loss: 3.7975 (3.8312) grad_norm: 0.9884 (1.0638) time: 0.6192 [2021-03-26 08:33:13 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 670/1251] eta: 0:06:05 lr: 0.000945 loss: 3.9821 (3.8322) grad_norm: 1.0221 (1.0643) time: 0.6233 [2021-03-26 08:33:19 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 680/1251] eta: 0:05:59 lr: 0.000945 loss: 3.9821 (3.8312) grad_norm: 1.0283 (1.0645) time: 0.6248 [2021-03-26 08:33:26 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 690/1251] eta: 0:05:52 lr: 0.000945 loss: 3.8270 (3.8330) grad_norm: 1.0360 (1.0648) time: 0.6275 [2021-03-26 08:33:32 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 700/1251] eta: 0:05:46 lr: 0.000945 loss: 3.8169 (3.8320) grad_norm: 1.0652 (1.0655) time: 0.6291 [2021-03-26 08:33:38 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 710/1251] eta: 0:05:40 lr: 0.000945 loss: 3.7719 (3.8301) grad_norm: 1.0321 (1.0649) time: 0.6226 [2021-03-26 08:33:44 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 720/1251] eta: 0:05:33 lr: 0.000945 loss: 3.8119 (3.8298) grad_norm: 0.9890 (1.0640) time: 0.6192 [2021-03-26 08:33:51 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 730/1251] eta: 0:05:27 lr: 0.000945 loss: 3.8134 (3.8277) grad_norm: 0.9835 (1.0634) time: 0.6238 [2021-03-26 08:33:57 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 740/1251] eta: 0:05:21 lr: 0.000945 loss: 3.8134 (3.8249) grad_norm: 1.0307 (1.0636) time: 0.6325 [2021-03-26 08:34:03 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 750/1251] eta: 0:05:14 lr: 0.000945 loss: 3.8183 (3.8260) grad_norm: 1.0438 (1.0634) time: 0.6333 [2021-03-26 08:34:10 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 760/1251] eta: 0:05:08 lr: 0.000945 loss: 4.1070 (3.8278) grad_norm: 1.0355 (1.0631) time: 0.6292 [2021-03-26 08:34:16 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 770/1251] eta: 0:05:02 lr: 0.000945 loss: 4.0275 (3.8313) grad_norm: 1.0372 (1.0647) time: 0.6266 [2021-03-26 08:34:22 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 780/1251] eta: 0:04:56 lr: 0.000945 loss: 3.9609 (3.8265) grad_norm: 1.0303 (1.0643) time: 0.6213 [2021-03-26 08:34:28 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 790/1251] eta: 0:04:49 lr: 0.000945 loss: 3.7828 (3.8252) grad_norm: 0.9972 (1.0636) time: 0.6206 [2021-03-26 08:34:35 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 800/1251] eta: 0:04:43 lr: 0.000945 loss: 3.8555 (3.8270) grad_norm: 1.0341 (1.0639) time: 0.6226 [2021-03-26 08:34:41 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 810/1251] eta: 0:04:37 lr: 0.000945 loss: 4.1198 (3.8277) grad_norm: 0.9974 (1.0633) time: 0.6214 [2021-03-26 08:34:47 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 820/1251] eta: 0:04:30 lr: 0.000944 loss: 3.9181 (3.8266) grad_norm: 0.9974 (1.0642) time: 0.6247 [2021-03-26 08:34:53 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 830/1251] eta: 0:04:24 lr: 0.000944 loss: 3.9181 (3.8292) grad_norm: 0.9874 (1.0633) time: 0.6240 [2021-03-26 08:34:59 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 840/1251] eta: 0:04:18 lr: 0.000944 loss: 3.7604 (3.8267) grad_norm: 0.9874 (1.0637) time: 0.6220 [2021-03-26 08:35:06 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 850/1251] eta: 0:04:11 lr: 0.000944 loss: 3.6883 (3.8267) grad_norm: 1.0517 (1.0635) time: 0.6239 [2021-03-26 08:35:12 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 860/1251] eta: 0:04:05 lr: 0.000944 loss: 3.9330 (3.8276) grad_norm: 0.9578 (1.0624) time: 0.6276 [2021-03-26 08:35:18 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 870/1251] eta: 0:03:59 lr: 0.000944 loss: 3.9028 (3.8269) grad_norm: 0.9909 (1.0624) time: 0.6272 [2021-03-26 08:35:25 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 880/1251] eta: 0:03:52 lr: 0.000944 loss: 4.0265 (3.8268) grad_norm: 1.1061 (1.0635) time: 0.6238 [2021-03-26 08:35:31 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 890/1251] eta: 0:03:46 lr: 0.000944 loss: 3.5059 (3.8232) grad_norm: 1.0669 (1.0628) time: 0.6247 [2021-03-26 08:35:37 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 900/1251] eta: 0:03:40 lr: 0.000944 loss: 3.6096 (3.8229) grad_norm: 0.9592 (1.0615) time: 0.6203 [2021-03-26 08:35:43 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 910/1251] eta: 0:03:34 lr: 0.000944 loss: 3.8340 (3.8242) grad_norm: 0.9313 (1.0606) time: 0.6162 [2021-03-26 08:35:49 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 920/1251] eta: 0:03:27 lr: 0.000944 loss: 3.8056 (3.8227) grad_norm: 0.9574 (1.0602) time: 0.6166 [2021-03-26 08:35:55 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 930/1251] eta: 0:03:21 lr: 0.000944 loss: 3.6775 (3.8214) grad_norm: 0.9866 (inf) time: 0.6189 [2021-03-26 08:36:02 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 940/1251] eta: 0:03:15 lr: 0.000944 loss: 3.8193 (3.8182) grad_norm: 1.0523 (inf) time: 0.6209 [2021-03-26 08:36:08 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 950/1251] eta: 0:03:08 lr: 0.000944 loss: 3.8256 (3.8156) grad_norm: 1.0765 (inf) time: 0.6243 [2021-03-26 08:36:14 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 960/1251] eta: 0:03:02 lr: 0.000944 loss: 3.6580 (3.8151) grad_norm: 1.1307 (inf) time: 0.6294 [2021-03-26 08:36:21 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 970/1251] eta: 0:02:56 lr: 0.000944 loss: 3.8702 (3.8157) grad_norm: 1.0473 (inf) time: 0.6295 [2021-03-26 08:36:27 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 980/1251] eta: 0:02:50 lr: 0.000944 loss: 3.8530 (3.8158) grad_norm: 1.0291 (inf) time: 0.6240 [2021-03-26 08:36:33 swin_base_patch4_window7_224] INFO: Epoch: [45] [ 990/1251] eta: 0:02:43 lr: 0.000944 loss: 3.9422 (3.8156) grad_norm: 1.0622 (inf) time: 0.6294 [2021-03-26 08:36:39 swin_base_patch4_window7_224] INFO: Epoch: [45] [1000/1251] eta: 0:02:37 lr: 0.000944 loss: 3.9422 (3.8143) grad_norm: 1.0767 (inf) time: 0.6338 [2021-03-26 08:36:46 swin_base_patch4_window7_224] INFO: Epoch: [45] [1010/1251] eta: 0:02:31 lr: 0.000944 loss: 3.8366 (3.8151) grad_norm: 0.9698 (inf) time: 0.6249 [2021-03-26 08:36:52 swin_base_patch4_window7_224] INFO: Epoch: [45] [1020/1251] eta: 0:02:24 lr: 0.000944 loss: 3.8830 (3.8166) grad_norm: 0.9899 (inf) time: 0.6210 [2021-03-26 08:36:58 swin_base_patch4_window7_224] INFO: Epoch: [45] [1030/1251] eta: 0:02:18 lr: 0.000944 loss: 3.9653 (3.8192) grad_norm: 1.0216 (inf) time: 0.6280 [2021-03-26 08:37:04 swin_base_patch4_window7_224] INFO: Epoch: [45] [1040/1251] eta: 0:02:12 lr: 0.000944 loss: 3.7155 (3.8176) grad_norm: 1.0213 (inf) time: 0.6242 [2021-03-26 08:37:11 swin_base_patch4_window7_224] INFO: Epoch: [45] [1050/1251] eta: 0:02:06 lr: 0.000944 loss: 3.6808 (3.8184) grad_norm: 0.9963 (inf) time: 0.6232 [2021-03-26 08:37:17 swin_base_patch4_window7_224] INFO: Epoch: [45] [1060/1251] eta: 0:01:59 lr: 0.000944 loss: 3.6983 (3.8165) grad_norm: 1.0202 (inf) time: 0.6276 [2021-03-26 08:37:23 swin_base_patch4_window7_224] INFO: Epoch: [45] [1070/1251] eta: 0:01:53 lr: 0.000944 loss: 3.6983 (3.8162) grad_norm: 1.0966 (inf) time: 0.6238 [2021-03-26 08:37:29 swin_base_patch4_window7_224] INFO: Epoch: [45] [1080/1251] eta: 0:01:47 lr: 0.000944 loss: 3.6271 (3.8151) grad_norm: 1.0778 (inf) time: 0.6232 [2021-03-26 08:37:36 swin_base_patch4_window7_224] INFO: Epoch: [45] [1090/1251] eta: 0:01:40 lr: 0.000944 loss: 3.7472 (3.8158) grad_norm: 1.0751 (inf) time: 0.6246 [2021-03-26 08:37:42 swin_base_patch4_window7_224] INFO: Epoch: [45] [1100/1251] eta: 0:01:34 lr: 0.000944 loss: 3.8264 (3.8142) grad_norm: 1.0633 (inf) time: 0.6252 [2021-03-26 08:37:48 swin_base_patch4_window7_224] INFO: Epoch: [45] [1110/1251] eta: 0:01:28 lr: 0.000944 loss: 3.5842 (3.8135) grad_norm: 1.0258 (inf) time: 0.6201 [2021-03-26 08:37:54 swin_base_patch4_window7_224] INFO: Epoch: [45] [1120/1251] eta: 0:01:22 lr: 0.000944 loss: 3.9272 (3.8162) grad_norm: 1.0010 (inf) time: 0.6199 [2021-03-26 08:38:00 swin_base_patch4_window7_224] INFO: Epoch: [45] [1130/1251] eta: 0:01:15 lr: 0.000944 loss: 3.9746 (3.8146) grad_norm: 1.0437 (inf) time: 0.6206 [2021-03-26 08:38:07 swin_base_patch4_window7_224] INFO: Epoch: [45] [1140/1251] eta: 0:01:09 lr: 0.000944 loss: 3.6857 (3.8141) grad_norm: 1.0560 (inf) time: 0.6242 [2021-03-26 08:38:13 swin_base_patch4_window7_224] INFO: Epoch: [45] [1150/1251] eta: 0:01:03 lr: 0.000944 loss: 3.6821 (3.8135) grad_norm: 1.0619 (inf) time: 0.6283 [2021-03-26 08:38:19 swin_base_patch4_window7_224] INFO: Epoch: [45] [1160/1251] eta: 0:00:57 lr: 0.000944 loss: 3.7730 (3.8144) grad_norm: 1.0754 (inf) time: 0.6275 [2021-03-26 08:38:26 swin_base_patch4_window7_224] INFO: Epoch: [45] [1170/1251] eta: 0:00:50 lr: 0.000944 loss: 3.7468 (3.8113) grad_norm: 1.1328 (inf) time: 0.6317 [2021-03-26 08:38:32 swin_base_patch4_window7_224] INFO: Epoch: [45] [1180/1251] eta: 0:00:44 lr: 0.000944 loss: 3.5439 (3.8110) grad_norm: 1.1046 (inf) time: 0.6300 [2021-03-26 08:38:38 swin_base_patch4_window7_224] INFO: Epoch: [45] [1190/1251] eta: 0:00:38 lr: 0.000944 loss: 3.7409 (3.8101) grad_norm: 1.0476 (inf) time: 0.6256 [2021-03-26 08:38:44 swin_base_patch4_window7_224] INFO: Epoch: [45] [1200/1251] eta: 0:00:31 lr: 0.000944 loss: 3.7409 (3.8090) grad_norm: 1.0639 (inf) time: 0.6259 [2021-03-26 08:38:51 swin_base_patch4_window7_224] INFO: Epoch: [45] [1210/1251] eta: 0:00:25 lr: 0.000944 loss: 3.6302 (3.8077) grad_norm: 1.1108 (inf) time: 0.6322 [2021-03-26 08:38:57 swin_base_patch4_window7_224] INFO: Epoch: [45] [1220/1251] eta: 0:00:19 lr: 0.000944 loss: 3.9441 (3.8090) grad_norm: 1.0004 (inf) time: 0.6338 [2021-03-26 08:39:03 swin_base_patch4_window7_224] INFO: Epoch: [45] [1230/1251] eta: 0:00:13 lr: 0.000944 loss: 4.1000 (3.8088) grad_norm: 0.9545 (inf) time: 0.6252 [2021-03-26 08:39:10 swin_base_patch4_window7_224] INFO: Epoch: [45] [1240/1251] eta: 0:00:06 lr: 0.000944 loss: 3.9237 (3.8106) grad_norm: 1.0071 (inf) time: 0.6204 [2021-03-26 08:39:16 swin_base_patch4_window7_224] INFO: Epoch: [45] [1250/1251] eta: 0:00:00 lr: 0.000944 loss: 4.0060 (3.8108) grad_norm: 1.1424 (inf) time: 0.6177 [2021-03-26 08:40:15 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 1.2814 (1.2814) acc1: 70.3125 (70.3125) acc5: 95.3125 (95.3125) [2021-03-26 08:40:16 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 1.2771 (1.2297) acc1: 70.3125 (70.7386) acc5: 90.6250 (91.3352) [2021-03-26 08:40:18 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.1573 (1.2114) acc1: 70.3125 (71.5030) acc5: 90.6250 (90.7738) [2021-03-26 08:40:19 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.1989 (1.2355) acc1: 70.3125 (70.9173) acc5: 89.0625 (90.3730) [2021-03-26 08:40:20 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.1989 (1.2307) acc1: 68.7500 (71.0366) acc5: 89.0625 (90.2058) [2021-03-26 08:40:22 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2118 (1.2337) acc1: 68.7500 (70.7200) acc5: 89.0625 (90.2720) [2021-03-26 08:40:24 swin_base_patch4_window7_224] INFO: * Acc@1 71.880 Acc@5 91.316 loss 1.191 [2021-03-26 08:40:24 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 71.9% [2021-03-26 08:40:24 swin_base_patch4_window7_224] INFO: Max accuracy: 71.88% [2021-03-26 08:40:29 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 0/1251] eta: 1:27:37 lr: 0.000944 loss: 2.4467 (2.4467) grad_norm: 1.1246 (1.1246) time: 4.2026 [2021-03-26 08:40:35 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 10/1251] eta: 0:19:44 lr: 0.000944 loss: 3.7237 (3.5253) grad_norm: 1.0382 (1.0531) time: 0.9546 [2021-03-26 08:40:41 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 20/1251] eta: 0:16:18 lr: 0.000944 loss: 3.7688 (3.5670) grad_norm: 0.9745 (1.0170) time: 0.6249 [2021-03-26 08:40:47 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 30/1251] eta: 0:15:02 lr: 0.000944 loss: 3.7688 (3.6520) grad_norm: 0.9660 (1.0251) time: 0.6201 [2021-03-26 08:40:54 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 40/1251] eta: 0:14:23 lr: 0.000944 loss: 3.9319 (3.7671) grad_norm: 0.9864 (1.0188) time: 0.6266 [2021-03-26 08:41:00 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 50/1251] eta: 0:13:54 lr: 0.000944 loss: 4.1551 (3.8124) grad_norm: 1.0660 (1.0655) time: 0.6259 [2021-03-26 08:41:06 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 60/1251] eta: 0:13:34 lr: 0.000944 loss: 4.1984 (3.8606) grad_norm: 1.1149 (1.0638) time: 0.6236 [2021-03-26 08:41:12 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 70/1251] eta: 0:13:17 lr: 0.000944 loss: 4.1867 (3.8840) grad_norm: 1.0223 (1.0609) time: 0.6254 [2021-03-26 08:41:19 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 80/1251] eta: 0:13:02 lr: 0.000944 loss: 4.0375 (3.8761) grad_norm: 1.0768 (1.0626) time: 0.6222 [2021-03-26 08:41:25 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 90/1251] eta: 0:12:49 lr: 0.000943 loss: 4.0736 (3.9007) grad_norm: 1.0855 (1.0660) time: 0.6201 [2021-03-26 08:41:31 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 100/1251] eta: 0:12:39 lr: 0.000943 loss: 3.9340 (3.8816) grad_norm: 1.0467 (1.0747) time: 0.6252 [2021-03-26 08:41:37 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 110/1251] eta: 0:12:29 lr: 0.000943 loss: 3.7823 (3.8506) grad_norm: 1.0182 (1.0687) time: 0.6279 [2021-03-26 08:41:44 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 120/1251] eta: 0:12:19 lr: 0.000943 loss: 3.8831 (3.8466) grad_norm: 1.0169 (1.0632) time: 0.6232 [2021-03-26 08:41:50 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 130/1251] eta: 0:12:10 lr: 0.000943 loss: 3.8831 (3.8485) grad_norm: 0.9777 (1.0607) time: 0.6218 [2021-03-26 08:41:56 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 140/1251] eta: 0:12:01 lr: 0.000943 loss: 3.9897 (3.8559) grad_norm: 1.0071 (1.0622) time: 0.6240 [2021-03-26 08:42:02 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 150/1251] eta: 0:11:53 lr: 0.000943 loss: 3.9581 (3.8565) grad_norm: 1.1012 (1.0682) time: 0.6270 [2021-03-26 08:42:09 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 160/1251] eta: 0:11:46 lr: 0.000943 loss: 3.8409 (3.8518) grad_norm: 1.1327 (1.0720) time: 0.6311 [2021-03-26 08:42:15 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 170/1251] eta: 0:11:38 lr: 0.000943 loss: 3.8544 (3.8397) grad_norm: 1.1157 (1.0731) time: 0.6303 [2021-03-26 08:42:21 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 180/1251] eta: 0:11:30 lr: 0.000943 loss: 3.7399 (3.8343) grad_norm: 1.0174 (1.0717) time: 0.6239 [2021-03-26 08:42:27 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 190/1251] eta: 0:11:22 lr: 0.000943 loss: 3.7832 (3.8279) grad_norm: 1.0174 (1.0719) time: 0.6230 [2021-03-26 08:42:34 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 200/1251] eta: 0:11:16 lr: 0.000943 loss: 3.8266 (3.8339) grad_norm: 1.0416 (1.0711) time: 0.6323 [2021-03-26 08:42:40 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 210/1251] eta: 0:11:08 lr: 0.000943 loss: 3.7239 (3.8230) grad_norm: 1.0379 (1.0711) time: 0.6331 [2021-03-26 08:42:46 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 220/1251] eta: 0:11:01 lr: 0.000943 loss: 3.8423 (3.8351) grad_norm: 1.0829 (1.0742) time: 0.6240 [2021-03-26 08:42:52 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 230/1251] eta: 0:10:54 lr: 0.000943 loss: 4.0904 (3.8362) grad_norm: 1.0829 (1.0761) time: 0.6224 [2021-03-26 08:42:59 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 240/1251] eta: 0:10:47 lr: 0.000943 loss: 3.8688 (3.8353) grad_norm: 1.0618 (1.0816) time: 0.6221 [2021-03-26 08:43:05 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 250/1251] eta: 0:10:40 lr: 0.000943 loss: 3.9747 (3.8381) grad_norm: 1.0408 (1.0827) time: 0.6236 [2021-03-26 08:43:11 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 260/1251] eta: 0:10:33 lr: 0.000943 loss: 3.9747 (3.8359) grad_norm: 1.0756 (1.0870) time: 0.6348 [2021-03-26 08:43:18 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 270/1251] eta: 0:10:26 lr: 0.000943 loss: 3.6540 (3.8224) grad_norm: 1.0173 (1.0835) time: 0.6327 [2021-03-26 08:43:24 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 280/1251] eta: 0:10:20 lr: 0.000943 loss: 3.6368 (3.8166) grad_norm: 0.9969 (1.0821) time: 0.6248 [2021-03-26 08:43:30 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 290/1251] eta: 0:10:13 lr: 0.000943 loss: 3.8455 (3.8157) grad_norm: 1.0268 (1.0810) time: 0.6238 [2021-03-26 08:43:36 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 300/1251] eta: 0:10:06 lr: 0.000943 loss: 3.8469 (3.8143) grad_norm: 1.0009 (1.0785) time: 0.6177 [2021-03-26 08:43:43 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 310/1251] eta: 0:09:59 lr: 0.000943 loss: 3.6007 (3.8021) grad_norm: 1.0136 (1.0782) time: 0.6225 [2021-03-26 08:43:49 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 320/1251] eta: 0:09:52 lr: 0.000943 loss: 3.5935 (3.7948) grad_norm: 1.0799 (1.0777) time: 0.6240 [2021-03-26 08:43:55 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 330/1251] eta: 0:09:45 lr: 0.000943 loss: 3.4607 (3.7839) grad_norm: 1.0885 (1.0784) time: 0.6242 [2021-03-26 08:44:01 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 340/1251] eta: 0:09:39 lr: 0.000943 loss: 3.6436 (3.7821) grad_norm: 1.0389 (1.0774) time: 0.6275 [2021-03-26 08:44:08 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 350/1251] eta: 0:09:32 lr: 0.000943 loss: 3.6701 (3.7811) grad_norm: 1.0753 (1.0829) time: 0.6271 [2021-03-26 08:44:14 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 360/1251] eta: 0:09:26 lr: 0.000943 loss: 3.7354 (3.7778) grad_norm: 1.0753 (1.0816) time: 0.6241 [2021-03-26 08:44:20 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 370/1251] eta: 0:09:19 lr: 0.000943 loss: 3.4757 (3.7746) grad_norm: 1.0012 (1.0808) time: 0.6209 [2021-03-26 08:44:26 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 380/1251] eta: 0:09:12 lr: 0.000943 loss: 3.7944 (3.7770) grad_norm: 1.0012 (1.0808) time: 0.6279 [2021-03-26 08:44:33 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 390/1251] eta: 0:09:06 lr: 0.000943 loss: 3.9002 (3.7750) grad_norm: 1.0179 (1.0793) time: 0.6262 [2021-03-26 08:44:39 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 400/1251] eta: 0:08:59 lr: 0.000943 loss: 3.9161 (3.7852) grad_norm: 1.0253 (1.0788) time: 0.6246 [2021-03-26 08:44:45 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 410/1251] eta: 0:08:53 lr: 0.000943 loss: 3.8445 (3.7849) grad_norm: 1.0438 (1.0795) time: 0.6294 [2021-03-26 08:44:51 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 420/1251] eta: 0:08:46 lr: 0.000943 loss: 3.7656 (3.7854) grad_norm: 1.0371 (1.0788) time: 0.6240 [2021-03-26 08:44:57 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 430/1251] eta: 0:08:40 lr: 0.000943 loss: 4.0829 (3.7876) grad_norm: 1.0370 (1.0771) time: 0.6171 [2021-03-26 08:45:04 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 440/1251] eta: 0:08:33 lr: 0.000943 loss: 3.8597 (3.7866) grad_norm: 1.0288 (1.0781) time: 0.6161 [2021-03-26 08:45:10 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 450/1251] eta: 0:08:26 lr: 0.000943 loss: 3.6821 (3.7884) grad_norm: 1.0113 (1.0774) time: 0.6179 [2021-03-26 08:45:16 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 460/1251] eta: 0:08:20 lr: 0.000943 loss: 3.7031 (3.7872) grad_norm: 0.9959 (1.0766) time: 0.6270 [2021-03-26 08:45:22 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 470/1251] eta: 0:08:14 lr: 0.000943 loss: 3.8292 (3.7874) grad_norm: 0.9959 (1.0771) time: 0.6290 [2021-03-26 08:45:29 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 480/1251] eta: 0:08:07 lr: 0.000943 loss: 3.8334 (3.7864) grad_norm: 0.9968 (1.0759) time: 0.6235 [2021-03-26 08:45:35 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 490/1251] eta: 0:08:01 lr: 0.000943 loss: 3.8814 (3.7914) grad_norm: 1.0222 (1.0762) time: 0.6296 [2021-03-26 08:45:41 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 500/1251] eta: 0:07:54 lr: 0.000943 loss: 4.0481 (3.7995) grad_norm: 1.0048 (1.0754) time: 0.6310 [2021-03-26 08:45:48 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 510/1251] eta: 0:07:48 lr: 0.000943 loss: 4.0535 (3.8019) grad_norm: 1.0153 (1.0751) time: 0.6249 [2021-03-26 08:45:54 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 520/1251] eta: 0:07:41 lr: 0.000943 loss: 3.7965 (3.8049) grad_norm: 1.0066 (1.0734) time: 0.6219 [2021-03-26 08:46:00 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 530/1251] eta: 0:07:35 lr: 0.000943 loss: 3.9367 (3.8071) grad_norm: 0.9836 (1.0731) time: 0.6204 [2021-03-26 08:46:06 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 540/1251] eta: 0:07:28 lr: 0.000943 loss: 3.6559 (3.8024) grad_norm: 1.0551 (1.0729) time: 0.6195 [2021-03-26 08:46:13 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 550/1251] eta: 0:07:22 lr: 0.000943 loss: 3.5405 (3.8004) grad_norm: 1.0746 (1.0738) time: 0.6284 [2021-03-26 08:46:19 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 560/1251] eta: 0:07:16 lr: 0.000943 loss: 3.9704 (3.8041) grad_norm: 1.0921 (1.0757) time: 0.6305 [2021-03-26 08:46:25 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 570/1251] eta: 0:07:09 lr: 0.000943 loss: 3.9704 (3.8058) grad_norm: 1.0416 (1.0750) time: 0.6235 [2021-03-26 08:46:31 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 580/1251] eta: 0:07:03 lr: 0.000943 loss: 3.9054 (3.8047) grad_norm: 1.0223 (1.0745) time: 0.6200 [2021-03-26 08:46:37 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 590/1251] eta: 0:06:57 lr: 0.000943 loss: 3.9061 (3.8033) grad_norm: 1.0316 (1.0737) time: 0.6214 [2021-03-26 08:46:44 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 600/1251] eta: 0:06:50 lr: 0.000943 loss: 3.5428 (3.8011) grad_norm: 1.0316 (1.0727) time: 0.6281 [2021-03-26 08:46:50 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 610/1251] eta: 0:06:44 lr: 0.000942 loss: 3.4241 (3.7955) grad_norm: 1.0383 (1.0739) time: 0.6312 [2021-03-26 08:46:56 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 620/1251] eta: 0:06:38 lr: 0.000942 loss: 3.6593 (3.7962) grad_norm: 1.0614 (1.0738) time: 0.6285 [2021-03-26 08:47:02 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 630/1251] eta: 0:06:31 lr: 0.000942 loss: 3.9701 (3.7941) grad_norm: 1.0249 (1.0726) time: 0.6217 [2021-03-26 08:47:09 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 640/1251] eta: 0:06:25 lr: 0.000942 loss: 3.9701 (3.7987) grad_norm: 1.0427 (1.0724) time: 0.6197 [2021-03-26 08:47:15 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 650/1251] eta: 0:06:18 lr: 0.000942 loss: 4.0694 (3.7974) grad_norm: 1.0556 (1.0717) time: 0.6210 [2021-03-26 08:47:21 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 660/1251] eta: 0:06:12 lr: 0.000942 loss: 4.0175 (3.8016) grad_norm: 1.0083 (1.0713) time: 0.6239 [2021-03-26 08:47:27 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 670/1251] eta: 0:06:06 lr: 0.000942 loss: 3.8678 (3.7985) grad_norm: 1.0024 (1.0698) time: 0.6289 [2021-03-26 08:47:34 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 680/1251] eta: 0:05:59 lr: 0.000942 loss: 3.5903 (3.7975) grad_norm: 1.0237 (1.0700) time: 0.6294 [2021-03-26 08:47:40 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 690/1251] eta: 0:05:53 lr: 0.000942 loss: 3.8139 (3.7979) grad_norm: 1.0522 (1.0695) time: 0.6381 [2021-03-26 08:47:47 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 700/1251] eta: 0:05:47 lr: 0.000942 loss: 3.7337 (3.7940) grad_norm: 1.0122 (1.0692) time: 0.6425 [2021-03-26 08:47:53 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 710/1251] eta: 0:05:41 lr: 0.000942 loss: 3.7337 (3.7944) grad_norm: 1.0080 (1.0682) time: 0.6328 [2021-03-26 08:47:59 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 720/1251] eta: 0:05:34 lr: 0.000942 loss: 3.8754 (3.7945) grad_norm: 1.0324 (1.0688) time: 0.6333 [2021-03-26 08:48:06 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 730/1251] eta: 0:05:28 lr: 0.000942 loss: 3.8754 (3.7957) grad_norm: 1.1107 (1.0697) time: 0.6396 [2021-03-26 08:48:12 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 740/1251] eta: 0:05:22 lr: 0.000942 loss: 4.0139 (3.7961) grad_norm: 1.0657 (1.0695) time: 0.6439 [2021-03-26 08:48:18 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 750/1251] eta: 0:05:16 lr: 0.000942 loss: 3.6925 (3.7906) grad_norm: 1.0863 (1.0710) time: 0.6400 [2021-03-26 08:48:25 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 760/1251] eta: 0:05:09 lr: 0.000942 loss: 3.7625 (3.7928) grad_norm: 1.0018 (1.0702) time: 0.6267 [2021-03-26 08:48:31 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 770/1251] eta: 0:05:03 lr: 0.000942 loss: 4.1924 (3.7957) grad_norm: 1.0018 (1.0698) time: 0.6210 [2021-03-26 08:48:37 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 780/1251] eta: 0:04:57 lr: 0.000942 loss: 3.9998 (3.7977) grad_norm: 0.9819 (1.0683) time: 0.6171 [2021-03-26 08:48:43 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 790/1251] eta: 0:04:50 lr: 0.000942 loss: 3.8231 (3.7992) grad_norm: 0.9649 (1.0669) time: 0.6222 [2021-03-26 08:48:50 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 800/1251] eta: 0:04:44 lr: 0.000942 loss: 3.7545 (3.7971) grad_norm: 1.0404 (1.0674) time: 0.6306 [2021-03-26 08:48:56 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 810/1251] eta: 0:04:38 lr: 0.000942 loss: 3.6264 (3.7945) grad_norm: 1.0840 (1.0684) time: 0.6314 [2021-03-26 08:49:02 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 820/1251] eta: 0:04:31 lr: 0.000942 loss: 3.6301 (3.7927) grad_norm: 1.1653 (1.0701) time: 0.6259 [2021-03-26 08:49:08 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 830/1251] eta: 0:04:25 lr: 0.000942 loss: 3.6768 (3.7884) grad_norm: 1.0064 (1.0691) time: 0.6195 [2021-03-26 08:49:15 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 840/1251] eta: 0:04:19 lr: 0.000942 loss: 3.7176 (3.7900) grad_norm: 0.9892 (1.0691) time: 0.6192 [2021-03-26 08:49:21 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 850/1251] eta: 0:04:12 lr: 0.000942 loss: 3.8285 (3.7869) grad_norm: 1.0030 (1.0683) time: 0.6251 [2021-03-26 08:49:27 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 860/1251] eta: 0:04:06 lr: 0.000942 loss: 3.5368 (3.7852) grad_norm: 1.0030 (1.0676) time: 0.6286 [2021-03-26 08:49:33 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 870/1251] eta: 0:04:00 lr: 0.000942 loss: 3.8243 (3.7840) grad_norm: 1.0020 (1.0670) time: 0.6252 [2021-03-26 08:49:40 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 880/1251] eta: 0:03:53 lr: 0.000942 loss: 3.7552 (3.7811) grad_norm: 1.1073 (1.0694) time: 0.6269 [2021-03-26 08:49:46 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 890/1251] eta: 0:03:47 lr: 0.000942 loss: 3.9062 (3.7873) grad_norm: 1.2133 (1.0708) time: 0.6277 [2021-03-26 08:49:52 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 900/1251] eta: 0:03:41 lr: 0.000942 loss: 4.1648 (3.7874) grad_norm: 1.1272 (1.0707) time: 0.6305 [2021-03-26 08:49:58 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 910/1251] eta: 0:03:34 lr: 0.000942 loss: 3.8767 (3.7867) grad_norm: 0.9972 (1.0706) time: 0.6248 [2021-03-26 08:50:05 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 920/1251] eta: 0:03:28 lr: 0.000942 loss: 3.8767 (3.7879) grad_norm: 0.9715 (1.0690) time: 0.6203 [2021-03-26 08:50:11 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 930/1251] eta: 0:03:22 lr: 0.000942 loss: 3.7492 (3.7901) grad_norm: 0.9715 (1.0694) time: 0.6315 [2021-03-26 08:50:17 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 940/1251] eta: 0:03:15 lr: 0.000942 loss: 3.7485 (3.7885) grad_norm: 1.0274 (1.0689) time: 0.6368 [2021-03-26 08:50:24 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 950/1251] eta: 0:03:09 lr: 0.000942 loss: 3.8813 (3.7913) grad_norm: 1.0437 (1.0692) time: 0.6333 [2021-03-26 08:50:30 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 960/1251] eta: 0:03:03 lr: 0.000942 loss: 4.0791 (3.7941) grad_norm: 1.1177 (1.0697) time: 0.6227 [2021-03-26 08:50:36 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 970/1251] eta: 0:02:56 lr: 0.000942 loss: 3.9201 (3.7922) grad_norm: 1.1050 (1.0702) time: 0.6165 [2021-03-26 08:50:42 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 980/1251] eta: 0:02:50 lr: 0.000942 loss: 3.5406 (3.7903) grad_norm: 1.0448 (1.0700) time: 0.6195 [2021-03-26 08:50:49 swin_base_patch4_window7_224] INFO: Epoch: [46] [ 990/1251] eta: 0:02:44 lr: 0.000942 loss: 3.6991 (3.7898) grad_norm: 1.0030 (1.0693) time: 0.6205 [2021-03-26 08:50:55 swin_base_patch4_window7_224] INFO: Epoch: [46] [1000/1251] eta: 0:02:38 lr: 0.000942 loss: 3.6991 (3.7880) grad_norm: 1.0030 (1.0693) time: 0.6206 [2021-03-26 08:51:01 swin_base_patch4_window7_224] INFO: Epoch: [46] [1010/1251] eta: 0:02:31 lr: 0.000942 loss: 3.5862 (3.7864) grad_norm: 1.0390 (1.0693) time: 0.6256 [2021-03-26 08:51:07 swin_base_patch4_window7_224] INFO: Epoch: [46] [1020/1251] eta: 0:02:25 lr: 0.000942 loss: 3.6766 (3.7844) grad_norm: 0.9850 (1.0687) time: 0.6282 [2021-03-26 08:51:14 swin_base_patch4_window7_224] INFO: Epoch: [46] [1030/1251] eta: 0:02:19 lr: 0.000942 loss: 3.5753 (3.7827) grad_norm: 0.9850 (1.0682) time: 0.6263 [2021-03-26 08:51:20 swin_base_patch4_window7_224] INFO: Epoch: [46] [1040/1251] eta: 0:02:12 lr: 0.000942 loss: 3.8209 (3.7822) grad_norm: 1.0254 (1.0683) time: 0.6244 [2021-03-26 08:51:26 swin_base_patch4_window7_224] INFO: Epoch: [46] [1050/1251] eta: 0:02:06 lr: 0.000942 loss: 3.6460 (3.7811) grad_norm: 1.0866 (1.0689) time: 0.6251 [2021-03-26 08:51:32 swin_base_patch4_window7_224] INFO: Epoch: [46] [1060/1251] eta: 0:02:00 lr: 0.000942 loss: 3.6324 (3.7810) grad_norm: 1.1146 (1.0695) time: 0.6288 [2021-03-26 08:51:39 swin_base_patch4_window7_224] INFO: Epoch: [46] [1070/1251] eta: 0:01:53 lr: 0.000942 loss: 3.8175 (3.7811) grad_norm: 1.1146 (1.0697) time: 0.6287 [2021-03-26 08:51:45 swin_base_patch4_window7_224] INFO: Epoch: [46] [1080/1251] eta: 0:01:47 lr: 0.000942 loss: 3.7106 (3.7785) grad_norm: 1.0341 (1.0691) time: 0.6207 [2021-03-26 08:51:51 swin_base_patch4_window7_224] INFO: Epoch: [46] [1090/1251] eta: 0:01:41 lr: 0.000942 loss: 3.6067 (3.7773) grad_norm: 0.9360 (1.0679) time: 0.6175 [2021-03-26 08:51:57 swin_base_patch4_window7_224] INFO: Epoch: [46] [1100/1251] eta: 0:01:34 lr: 0.000942 loss: 3.7944 (3.7772) grad_norm: 0.9471 (1.0673) time: 0.6185 [2021-03-26 08:52:03 swin_base_patch4_window7_224] INFO: Epoch: [46] [1110/1251] eta: 0:01:28 lr: 0.000942 loss: 3.7944 (3.7774) grad_norm: 1.0139 (1.0673) time: 0.6246 [2021-03-26 08:52:10 swin_base_patch4_window7_224] INFO: Epoch: [46] [1120/1251] eta: 0:01:22 lr: 0.000942 loss: 3.9145 (3.7780) grad_norm: 1.0238 (1.0671) time: 0.6286 [2021-03-26 08:52:16 swin_base_patch4_window7_224] INFO: Epoch: [46] [1130/1251] eta: 0:01:16 lr: 0.000941 loss: 4.0243 (3.7814) grad_norm: 1.0424 (1.0673) time: 0.6221 [2021-03-26 08:52:22 swin_base_patch4_window7_224] INFO: Epoch: [46] [1140/1251] eta: 0:01:09 lr: 0.000941 loss: 3.9781 (3.7822) grad_norm: 1.0438 (1.0673) time: 0.6215 [2021-03-26 08:52:28 swin_base_patch4_window7_224] INFO: Epoch: [46] [1150/1251] eta: 0:01:03 lr: 0.000941 loss: 4.0226 (3.7827) grad_norm: 1.0438 (1.0671) time: 0.6218 [2021-03-26 08:52:35 swin_base_patch4_window7_224] INFO: Epoch: [46] [1160/1251] eta: 0:00:57 lr: 0.000941 loss: 4.0495 (3.7844) grad_norm: 1.0430 (1.0672) time: 0.6260 [2021-03-26 08:52:41 swin_base_patch4_window7_224] INFO: Epoch: [46] [1170/1251] eta: 0:00:50 lr: 0.000941 loss: 3.8962 (3.7845) grad_norm: 1.0343 (1.0664) time: 0.6250 [2021-03-26 08:52:47 swin_base_patch4_window7_224] INFO: Epoch: [46] [1180/1251] eta: 0:00:44 lr: 0.000941 loss: 3.7981 (3.7838) grad_norm: 1.0105 (1.0663) time: 0.6184 [2021-03-26 08:52:53 swin_base_patch4_window7_224] INFO: Epoch: [46] [1190/1251] eta: 0:00:38 lr: 0.000941 loss: 3.7443 (3.7825) grad_norm: 1.0717 (1.0664) time: 0.6191 [2021-03-26 08:53:00 swin_base_patch4_window7_224] INFO: Epoch: [46] [1200/1251] eta: 0:00:32 lr: 0.000941 loss: 3.8951 (3.7840) grad_norm: 1.0616 (1.0664) time: 0.6263 [2021-03-26 08:53:06 swin_base_patch4_window7_224] INFO: Epoch: [46] [1210/1251] eta: 0:00:25 lr: 0.000941 loss: 3.9764 (3.7859) grad_norm: 1.0616 (1.0673) time: 0.6279 [2021-03-26 08:53:12 swin_base_patch4_window7_224] INFO: Epoch: [46] [1220/1251] eta: 0:00:19 lr: 0.000941 loss: 3.9468 (3.7857) grad_norm: 1.0109 (1.0663) time: 0.6212 [2021-03-26 08:53:18 swin_base_patch4_window7_224] INFO: Epoch: [46] [1230/1251] eta: 0:00:13 lr: 0.000941 loss: 3.8126 (3.7860) grad_norm: 0.9607 (1.0658) time: 0.6204 [2021-03-26 08:53:24 swin_base_patch4_window7_224] INFO: Epoch: [46] [1240/1251] eta: 0:00:06 lr: 0.000941 loss: 3.8951 (3.7873) grad_norm: 0.9729 (1.0659) time: 0.6202 [2021-03-26 08:53:31 swin_base_patch4_window7_224] INFO: Epoch: [46] [1250/1251] eta: 0:00:00 lr: 0.000941 loss: 4.0523 (3.7891) grad_norm: 0.9827 (1.0655) time: 0.6135 [2021-03-26 08:53:34 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 1.1973 (1.1973) acc1: 70.3125 (70.3125) acc5: 93.7500 (93.7500) [2021-03-26 08:53:37 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.1824 (1.2200) acc1: 71.8750 (69.6023) acc5: 92.1875 (91.3352) [2021-03-26 08:53:39 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.1183 (1.1845) acc1: 71.8750 (72.5446) acc5: 92.1875 (91.9643) [2021-03-26 08:53:42 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.2048 (1.2068) acc1: 71.8750 (71.4718) acc5: 90.6250 (91.5827) [2021-03-26 08:53:43 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2165 (1.2031) acc1: 71.8750 (71.7226) acc5: 90.6250 (91.6540) [2021-03-26 08:53:44 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2335 (1.2042) acc1: 71.8750 (71.5520) acc5: 92.1875 (91.6480) [2021-03-26 08:53:48 swin_base_patch4_window7_224] INFO: * Acc@1 72.308 Acc@5 91.584 loss 1.175 [2021-03-26 08:53:48 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 72.3% [2021-03-26 08:53:48 swin_base_patch4_window7_224] INFO: Max accuracy: 72.31% [2021-03-26 08:53:53 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 0/1251] eta: 1:32:45 lr: 0.000941 loss: 4.0629 (4.0629) grad_norm: 1.0340 (1.0340) time: 4.4486 [2021-03-26 08:53:59 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 10/1251] eta: 0:20:14 lr: 0.000941 loss: 4.1858 (3.9448) grad_norm: 1.0875 (1.0586) time: 0.9787 [2021-03-26 08:54:05 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 20/1251] eta: 0:16:31 lr: 0.000941 loss: 3.5378 (3.7434) grad_norm: 0.9933 (1.0210) time: 0.6237 [2021-03-26 08:54:12 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 30/1251] eta: 0:15:11 lr: 0.000941 loss: 3.5378 (3.7358) grad_norm: 1.0328 (1.0521) time: 0.6193 [2021-03-26 08:54:18 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 40/1251] eta: 0:14:27 lr: 0.000941 loss: 3.6174 (3.6683) grad_norm: 1.0637 (1.0664) time: 0.6220 [2021-03-26 08:54:24 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 50/1251] eta: 0:13:57 lr: 0.000941 loss: 3.5866 (3.6979) grad_norm: 1.0220 (1.0592) time: 0.6201 [2021-03-26 08:54:30 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 60/1251] eta: 0:13:38 lr: 0.000941 loss: 3.8172 (3.6931) grad_norm: 1.0031 (1.0506) time: 0.6277 [2021-03-26 08:54:36 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 70/1251] eta: 0:13:18 lr: 0.000941 loss: 3.8250 (3.7469) grad_norm: 0.9769 (1.0454) time: 0.6240 [2021-03-26 08:54:43 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 80/1251] eta: 0:13:04 lr: 0.000941 loss: 3.7593 (3.7564) grad_norm: 0.9760 (1.0490) time: 0.6192 [2021-03-26 08:54:49 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 90/1251] eta: 0:12:51 lr: 0.000941 loss: 3.7992 (3.7779) grad_norm: 1.0756 (1.0567) time: 0.6235 [2021-03-26 08:54:55 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 100/1251] eta: 0:12:40 lr: 0.000941 loss: 3.8882 (3.7674) grad_norm: 1.0865 (1.0574) time: 0.6229 [2021-03-26 08:55:02 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 110/1251] eta: 0:12:31 lr: 0.000941 loss: 3.7106 (3.7595) grad_norm: 0.9984 (1.0516) time: 0.6317 [2021-03-26 08:55:08 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 120/1251] eta: 0:12:23 lr: 0.000941 loss: 3.6238 (3.7414) grad_norm: 1.0349 (1.0545) time: 0.6402 [2021-03-26 08:55:14 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 130/1251] eta: 0:12:14 lr: 0.000941 loss: 3.6762 (3.7598) grad_norm: 1.0520 (1.0552) time: 0.6370 [2021-03-26 08:55:21 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 140/1251] eta: 0:12:05 lr: 0.000941 loss: 3.8303 (3.7537) grad_norm: 0.9814 (1.0489) time: 0.6270 [2021-03-26 08:55:27 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 150/1251] eta: 0:11:57 lr: 0.000941 loss: 3.6380 (3.7450) grad_norm: 0.9590 (1.0490) time: 0.6271 [2021-03-26 08:55:33 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 160/1251] eta: 0:11:50 lr: 0.000941 loss: 3.9701 (3.7697) grad_norm: 1.0192 (1.0488) time: 0.6339 [2021-03-26 08:55:39 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 170/1251] eta: 0:11:41 lr: 0.000941 loss: 4.0146 (3.7742) grad_norm: 1.0412 (1.0511) time: 0.6289 [2021-03-26 08:55:46 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 180/1251] eta: 0:11:33 lr: 0.000941 loss: 3.7350 (3.7735) grad_norm: 1.0513 (1.0529) time: 0.6245 [2021-03-26 08:55:52 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 190/1251] eta: 0:11:26 lr: 0.000941 loss: 3.7732 (3.7849) grad_norm: 1.0487 (1.0516) time: 0.6257 [2021-03-26 08:55:58 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 200/1251] eta: 0:11:18 lr: 0.000941 loss: 3.8648 (3.7828) grad_norm: 0.9484 (1.0454) time: 0.6205 [2021-03-26 08:56:04 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 210/1251] eta: 0:11:10 lr: 0.000941 loss: 3.8373 (3.7742) grad_norm: 0.9065 (1.0408) time: 0.6163 [2021-03-26 08:56:10 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 220/1251] eta: 0:11:02 lr: 0.000941 loss: 3.7438 (3.7715) grad_norm: 0.9820 (1.0425) time: 0.6166 [2021-03-26 08:56:17 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 230/1251] eta: 0:10:55 lr: 0.000941 loss: 3.6413 (3.7635) grad_norm: 1.0411 (1.0417) time: 0.6238 [2021-03-26 08:56:23 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 240/1251] eta: 0:10:48 lr: 0.000941 loss: 3.6956 (3.7647) grad_norm: 1.0576 (1.0453) time: 0.6283 [2021-03-26 08:56:29 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 250/1251] eta: 0:10:41 lr: 0.000941 loss: 3.8949 (3.7752) grad_norm: 1.0752 (1.0457) time: 0.6255 [2021-03-26 08:56:36 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 260/1251] eta: 0:10:34 lr: 0.000941 loss: 3.7910 (3.7619) grad_norm: 1.0060 (1.0489) time: 0.6254 [2021-03-26 08:56:42 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 270/1251] eta: 0:10:27 lr: 0.000941 loss: 3.5299 (3.7575) grad_norm: 0.9966 (1.0481) time: 0.6292 [2021-03-26 08:56:48 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 280/1251] eta: 0:10:20 lr: 0.000941 loss: 3.9742 (3.7673) grad_norm: 0.9775 (1.0483) time: 0.6301 [2021-03-26 08:56:54 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 290/1251] eta: 0:10:14 lr: 0.000941 loss: 4.0051 (3.7674) grad_norm: 1.0898 (1.0506) time: 0.6272 [2021-03-26 08:57:01 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 300/1251] eta: 0:10:06 lr: 0.000941 loss: 3.9312 (3.7656) grad_norm: 1.0849 (1.0501) time: 0.6215 [2021-03-26 08:57:07 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 310/1251] eta: 0:10:00 lr: 0.000941 loss: 3.7330 (3.7631) grad_norm: 1.0273 (1.0508) time: 0.6309 [2021-03-26 08:57:13 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 320/1251] eta: 0:09:54 lr: 0.000941 loss: 3.7330 (3.7723) grad_norm: 1.0344 (1.0525) time: 0.6378 [2021-03-26 08:57:20 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 330/1251] eta: 0:09:47 lr: 0.000941 loss: 3.9513 (3.7771) grad_norm: 1.0621 (1.0518) time: 0.6317 [2021-03-26 08:57:26 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 340/1251] eta: 0:09:40 lr: 0.000941 loss: 3.9030 (3.7763) grad_norm: 1.0417 (1.0502) time: 0.6281 [2021-03-26 08:57:32 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 350/1251] eta: 0:09:34 lr: 0.000941 loss: 3.6908 (3.7725) grad_norm: 1.0272 (1.0504) time: 0.6236 [2021-03-26 08:57:38 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 360/1251] eta: 0:09:27 lr: 0.000941 loss: 3.7488 (3.7776) grad_norm: 1.0037 (1.0488) time: 0.6180 [2021-03-26 08:57:45 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 370/1251] eta: 0:09:20 lr: 0.000941 loss: 3.9356 (3.7745) grad_norm: 0.9678 (1.0483) time: 0.6190 [2021-03-26 08:57:51 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 380/1251] eta: 0:09:13 lr: 0.000940 loss: 3.6127 (3.7749) grad_norm: 1.0017 (1.0500) time: 0.6251 [2021-03-26 08:57:57 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 390/1251] eta: 0:09:07 lr: 0.000940 loss: 3.5980 (3.7646) grad_norm: 0.9992 (1.0484) time: 0.6243 [2021-03-26 08:58:03 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 400/1251] eta: 0:09:01 lr: 0.000940 loss: 3.7242 (3.7677) grad_norm: 1.0754 (1.0520) time: 0.6327 [2021-03-26 08:58:10 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 410/1251] eta: 0:08:54 lr: 0.000940 loss: 4.1497 (3.7713) grad_norm: 1.1295 (1.0563) time: 0.6361 [2021-03-26 08:58:16 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 420/1251] eta: 0:08:48 lr: 0.000940 loss: 4.0169 (3.7785) grad_norm: 1.0778 (1.0553) time: 0.6292 [2021-03-26 08:58:22 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 430/1251] eta: 0:08:41 lr: 0.000940 loss: 3.8811 (3.7832) grad_norm: 1.0085 (1.0546) time: 0.6317 [2021-03-26 08:58:29 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 440/1251] eta: 0:08:35 lr: 0.000940 loss: 3.9346 (3.7860) grad_norm: 1.0469 (1.0566) time: 0.6344 [2021-03-26 08:58:35 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 450/1251] eta: 0:08:28 lr: 0.000940 loss: 4.0049 (3.7839) grad_norm: 1.0503 (1.0561) time: 0.6315 [2021-03-26 08:58:41 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 460/1251] eta: 0:08:22 lr: 0.000940 loss: 3.6948 (3.7791) grad_norm: 1.1062 (1.0590) time: 0.6316 [2021-03-26 08:58:48 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 470/1251] eta: 0:08:15 lr: 0.000940 loss: 3.6603 (3.7786) grad_norm: 1.1002 (1.0585) time: 0.6258 [2021-03-26 08:58:54 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 480/1251] eta: 0:08:09 lr: 0.000940 loss: 3.5603 (3.7717) grad_norm: 1.0381 (1.0584) time: 0.6224 [2021-03-26 08:59:00 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 490/1251] eta: 0:08:02 lr: 0.000940 loss: 3.3505 (3.7665) grad_norm: 1.0337 (1.0576) time: 0.6235 [2021-03-26 08:59:06 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 500/1251] eta: 0:07:56 lr: 0.000940 loss: 3.7402 (3.7675) grad_norm: 1.0969 (inf) time: 0.6229 [2021-03-26 08:59:12 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 510/1251] eta: 0:07:49 lr: 0.000940 loss: 3.8752 (3.7699) grad_norm: 1.1238 (inf) time: 0.6218 [2021-03-26 08:59:19 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 520/1251] eta: 0:07:43 lr: 0.000940 loss: 3.8849 (3.7703) grad_norm: 1.0450 (inf) time: 0.6275 [2021-03-26 08:59:25 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 530/1251] eta: 0:07:37 lr: 0.000940 loss: 3.8853 (3.7707) grad_norm: 1.0226 (inf) time: 0.6333 [2021-03-26 08:59:31 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 540/1251] eta: 0:07:30 lr: 0.000940 loss: 3.8380 (3.7701) grad_norm: 1.0051 (inf) time: 0.6258 [2021-03-26 08:59:38 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 550/1251] eta: 0:07:24 lr: 0.000940 loss: 3.8380 (3.7737) grad_norm: 1.0905 (inf) time: 0.6349 [2021-03-26 08:59:44 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 560/1251] eta: 0:07:18 lr: 0.000940 loss: 4.1065 (3.7793) grad_norm: 1.1213 (inf) time: 0.6409 [2021-03-26 08:59:51 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 570/1251] eta: 0:07:11 lr: 0.000940 loss: 4.1065 (3.7818) grad_norm: 1.1296 (inf) time: 0.6353 [2021-03-26 08:59:57 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 580/1251] eta: 0:07:05 lr: 0.000940 loss: 3.8753 (3.7795) grad_norm: 1.0661 (inf) time: 0.6311 [2021-03-26 09:00:03 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 590/1251] eta: 0:06:58 lr: 0.000940 loss: 3.9183 (3.7812) grad_norm: 1.0014 (inf) time: 0.6234 [2021-03-26 09:00:09 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 600/1251] eta: 0:06:52 lr: 0.000940 loss: 3.9995 (3.7832) grad_norm: 1.0750 (inf) time: 0.6298 [2021-03-26 09:00:16 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 610/1251] eta: 0:06:46 lr: 0.000940 loss: 3.9995 (3.7845) grad_norm: 1.0053 (inf) time: 0.6293 [2021-03-26 09:00:22 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 620/1251] eta: 0:06:39 lr: 0.000940 loss: 4.0291 (3.7856) grad_norm: 1.0053 (inf) time: 0.6201 [2021-03-26 09:00:28 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 630/1251] eta: 0:06:33 lr: 0.000940 loss: 3.9738 (3.7861) grad_norm: 1.0246 (inf) time: 0.6217 [2021-03-26 09:00:34 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 640/1251] eta: 0:06:26 lr: 0.000940 loss: 3.9078 (3.7860) grad_norm: 1.0246 (inf) time: 0.6232 [2021-03-26 09:00:40 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 650/1251] eta: 0:06:20 lr: 0.000940 loss: 3.8891 (3.7883) grad_norm: 1.0849 (inf) time: 0.6211 [2021-03-26 09:00:47 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 660/1251] eta: 0:06:13 lr: 0.000940 loss: 3.8599 (3.7844) grad_norm: 1.0966 (inf) time: 0.6217 [2021-03-26 09:00:53 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 670/1251] eta: 0:06:07 lr: 0.000940 loss: 3.6662 (3.7810) grad_norm: 1.0844 (inf) time: 0.6242 [2021-03-26 09:00:59 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 680/1251] eta: 0:06:01 lr: 0.000940 loss: 3.6695 (3.7784) grad_norm: 1.0764 (inf) time: 0.6260 [2021-03-26 09:01:06 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 690/1251] eta: 0:05:54 lr: 0.000940 loss: 3.8147 (3.7784) grad_norm: 1.0315 (inf) time: 0.6284 [2021-03-26 09:01:12 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 700/1251] eta: 0:05:48 lr: 0.000940 loss: 3.9579 (3.7813) grad_norm: 1.0359 (inf) time: 0.6258 [2021-03-26 09:01:18 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 710/1251] eta: 0:05:42 lr: 0.000940 loss: 4.0829 (3.7838) grad_norm: 1.0434 (inf) time: 0.6270 [2021-03-26 09:01:24 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 720/1251] eta: 0:05:35 lr: 0.000940 loss: 4.1348 (3.7878) grad_norm: 1.0814 (inf) time: 0.6272 [2021-03-26 09:01:31 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 730/1251] eta: 0:05:29 lr: 0.000940 loss: 3.9710 (3.7906) grad_norm: 1.0814 (inf) time: 0.6275 [2021-03-26 09:01:37 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 740/1251] eta: 0:05:22 lr: 0.000940 loss: 3.9070 (3.7892) grad_norm: 1.0956 (inf) time: 0.6266 [2021-03-26 09:01:43 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 750/1251] eta: 0:05:16 lr: 0.000940 loss: 3.7116 (3.7868) grad_norm: 0.9647 (inf) time: 0.6241 [2021-03-26 09:01:49 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 760/1251] eta: 0:05:10 lr: 0.000940 loss: 3.9345 (3.7916) grad_norm: 0.9686 (inf) time: 0.6254 [2021-03-26 09:01:56 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 770/1251] eta: 0:05:03 lr: 0.000940 loss: 4.0021 (3.7904) grad_norm: 1.0453 (inf) time: 0.6240 [2021-03-26 09:02:02 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 780/1251] eta: 0:04:57 lr: 0.000940 loss: 3.8028 (3.7901) grad_norm: 1.0316 (inf) time: 0.6253 [2021-03-26 09:02:08 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 790/1251] eta: 0:04:51 lr: 0.000940 loss: 3.7679 (3.7890) grad_norm: 1.0199 (inf) time: 0.6212 [2021-03-26 09:02:14 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 800/1251] eta: 0:04:44 lr: 0.000940 loss: 3.9275 (3.7929) grad_norm: 0.9843 (inf) time: 0.6187 [2021-03-26 09:02:21 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 810/1251] eta: 0:04:38 lr: 0.000940 loss: 4.1176 (3.7940) grad_norm: 1.0293 (inf) time: 0.6266 [2021-03-26 09:02:27 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 820/1251] eta: 0:04:32 lr: 0.000940 loss: 3.6319 (3.7908) grad_norm: 1.0932 (inf) time: 0.6363 [2021-03-26 09:02:33 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 830/1251] eta: 0:04:25 lr: 0.000940 loss: 3.8626 (3.7944) grad_norm: 1.0502 (inf) time: 0.6264 [2021-03-26 09:02:39 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 840/1251] eta: 0:04:19 lr: 0.000940 loss: 4.1151 (3.7953) grad_norm: 0.9813 (inf) time: 0.6183 [2021-03-26 09:02:46 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 850/1251] eta: 0:04:13 lr: 0.000940 loss: 3.9510 (3.7947) grad_norm: 1.0369 (inf) time: 0.6270 [2021-03-26 09:02:52 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 860/1251] eta: 0:04:06 lr: 0.000940 loss: 3.5865 (3.7902) grad_norm: 1.0464 (inf) time: 0.6340 [2021-03-26 09:02:58 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 870/1251] eta: 0:04:00 lr: 0.000940 loss: 3.5608 (3.7890) grad_norm: 1.1183 (inf) time: 0.6313 [2021-03-26 09:03:05 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 880/1251] eta: 0:03:54 lr: 0.000940 loss: 3.8314 (3.7900) grad_norm: 1.0563 (inf) time: 0.6249 [2021-03-26 09:03:11 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 890/1251] eta: 0:03:47 lr: 0.000939 loss: 3.4979 (3.7869) grad_norm: 1.0563 (inf) time: 0.6243 [2021-03-26 09:03:17 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 900/1251] eta: 0:03:41 lr: 0.000939 loss: 3.4533 (3.7819) grad_norm: 1.0087 (inf) time: 0.6235 [2021-03-26 09:03:23 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 910/1251] eta: 0:03:35 lr: 0.000939 loss: 3.6938 (3.7819) grad_norm: 1.0221 (inf) time: 0.6240 [2021-03-26 09:03:29 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 920/1251] eta: 0:03:28 lr: 0.000939 loss: 3.8099 (3.7824) grad_norm: 1.0156 (inf) time: 0.6241 [2021-03-26 09:03:36 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 930/1251] eta: 0:03:22 lr: 0.000939 loss: 3.6565 (3.7805) grad_norm: 0.9889 (inf) time: 0.6198 [2021-03-26 09:03:42 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 940/1251] eta: 0:03:16 lr: 0.000939 loss: 3.6282 (3.7758) grad_norm: 0.9931 (inf) time: 0.6178 [2021-03-26 09:03:48 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 950/1251] eta: 0:03:09 lr: 0.000939 loss: 3.9572 (3.7789) grad_norm: 1.0273 (inf) time: 0.6238 [2021-03-26 09:03:54 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 960/1251] eta: 0:03:03 lr: 0.000939 loss: 3.9094 (3.7779) grad_norm: 1.0533 (inf) time: 0.6282 [2021-03-26 09:04:01 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 970/1251] eta: 0:02:57 lr: 0.000939 loss: 3.6862 (3.7762) grad_norm: 1.0666 (inf) time: 0.6275 [2021-03-26 09:04:07 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 980/1251] eta: 0:02:50 lr: 0.000939 loss: 3.5449 (3.7745) grad_norm: 1.0658 (inf) time: 0.6251 [2021-03-26 09:04:13 swin_base_patch4_window7_224] INFO: Epoch: [47] [ 990/1251] eta: 0:02:44 lr: 0.000939 loss: 3.4666 (3.7738) grad_norm: 1.0575 (inf) time: 0.6233 [2021-03-26 09:04:19 swin_base_patch4_window7_224] INFO: Epoch: [47] [1000/1251] eta: 0:02:38 lr: 0.000939 loss: 3.8609 (3.7749) grad_norm: 0.9824 (inf) time: 0.6226 [2021-03-26 09:04:26 swin_base_patch4_window7_224] INFO: Epoch: [47] [1010/1251] eta: 0:02:31 lr: 0.000939 loss: 4.1110 (3.7792) grad_norm: 0.9824 (inf) time: 0.6261 [2021-03-26 09:04:32 swin_base_patch4_window7_224] INFO: Epoch: [47] [1020/1251] eta: 0:02:25 lr: 0.000939 loss: 4.0776 (3.7802) grad_norm: 1.0030 (inf) time: 0.6250 [2021-03-26 09:04:38 swin_base_patch4_window7_224] INFO: Epoch: [47] [1030/1251] eta: 0:02:19 lr: 0.000939 loss: 3.9208 (3.7801) grad_norm: 1.0249 (inf) time: 0.6275 [2021-03-26 09:04:44 swin_base_patch4_window7_224] INFO: Epoch: [47] [1040/1251] eta: 0:02:12 lr: 0.000939 loss: 3.9208 (3.7797) grad_norm: 1.0527 (inf) time: 0.6298 [2021-03-26 09:04:51 swin_base_patch4_window7_224] INFO: Epoch: [47] [1050/1251] eta: 0:02:06 lr: 0.000939 loss: 3.7594 (3.7776) grad_norm: 1.0181 (inf) time: 0.6281 [2021-03-26 09:04:57 swin_base_patch4_window7_224] INFO: Epoch: [47] [1060/1251] eta: 0:02:00 lr: 0.000939 loss: 3.7594 (3.7776) grad_norm: 1.0569 (inf) time: 0.6264 [2021-03-26 09:05:03 swin_base_patch4_window7_224] INFO: Epoch: [47] [1070/1251] eta: 0:01:54 lr: 0.000939 loss: 4.1032 (3.7808) grad_norm: 1.0068 (inf) time: 0.6198 [2021-03-26 09:05:09 swin_base_patch4_window7_224] INFO: Epoch: [47] [1080/1251] eta: 0:01:47 lr: 0.000939 loss: 4.0874 (3.7808) grad_norm: 0.9666 (inf) time: 0.6198 [2021-03-26 09:05:16 swin_base_patch4_window7_224] INFO: Epoch: [47] [1090/1251] eta: 0:01:41 lr: 0.000939 loss: 3.8501 (3.7801) grad_norm: 0.9839 (inf) time: 0.6171 [2021-03-26 09:05:22 swin_base_patch4_window7_224] INFO: Epoch: [47] [1100/1251] eta: 0:01:35 lr: 0.000939 loss: 3.8739 (3.7806) grad_norm: 1.0252 (inf) time: 0.6193 [2021-03-26 09:05:28 swin_base_patch4_window7_224] INFO: Epoch: [47] [1110/1251] eta: 0:01:28 lr: 0.000939 loss: 3.8493 (3.7794) grad_norm: 0.9742 (inf) time: 0.6204 [2021-03-26 09:05:34 swin_base_patch4_window7_224] INFO: Epoch: [47] [1120/1251] eta: 0:01:22 lr: 0.000939 loss: 3.6506 (3.7779) grad_norm: 0.9869 (inf) time: 0.6167 [2021-03-26 09:05:40 swin_base_patch4_window7_224] INFO: Epoch: [47] [1130/1251] eta: 0:01:16 lr: 0.000939 loss: 3.7191 (3.7779) grad_norm: 1.1234 (inf) time: 0.6213 [2021-03-26 09:05:47 swin_base_patch4_window7_224] INFO: Epoch: [47] [1140/1251] eta: 0:01:09 lr: 0.000939 loss: 3.7059 (3.7761) grad_norm: 1.0387 (inf) time: 0.6216 [2021-03-26 09:05:53 swin_base_patch4_window7_224] INFO: Epoch: [47] [1150/1251] eta: 0:01:03 lr: 0.000939 loss: 3.8454 (3.7788) grad_norm: 1.0304 (inf) time: 0.6195 [2021-03-26 09:05:59 swin_base_patch4_window7_224] INFO: Epoch: [47] [1160/1251] eta: 0:00:57 lr: 0.000939 loss: 3.8672 (3.7782) grad_norm: 1.1899 (inf) time: 0.6268 [2021-03-26 09:06:05 swin_base_patch4_window7_224] INFO: Epoch: [47] [1170/1251] eta: 0:00:50 lr: 0.000939 loss: 3.9652 (3.7796) grad_norm: 1.1171 (inf) time: 0.6266 [2021-03-26 09:06:11 swin_base_patch4_window7_224] INFO: Epoch: [47] [1180/1251] eta: 0:00:44 lr: 0.000939 loss: 4.0176 (3.7812) grad_norm: 0.9507 (inf) time: 0.6193 [2021-03-26 09:06:18 swin_base_patch4_window7_224] INFO: Epoch: [47] [1190/1251] eta: 0:00:38 lr: 0.000939 loss: 3.7234 (3.7787) grad_norm: 0.9667 (inf) time: 0.6206 [2021-03-26 09:06:24 swin_base_patch4_window7_224] INFO: Epoch: [47] [1200/1251] eta: 0:00:32 lr: 0.000939 loss: 3.9248 (3.7809) grad_norm: 0.9289 (inf) time: 0.6185 [2021-03-26 09:06:30 swin_base_patch4_window7_224] INFO: Epoch: [47] [1210/1251] eta: 0:00:25 lr: 0.000939 loss: 3.9869 (3.7797) grad_norm: 0.9620 (inf) time: 0.6134 [2021-03-26 09:06:36 swin_base_patch4_window7_224] INFO: Epoch: [47] [1220/1251] eta: 0:00:19 lr: 0.000939 loss: 4.0432 (3.7815) grad_norm: 1.0490 (inf) time: 0.6173 [2021-03-26 09:06:42 swin_base_patch4_window7_224] INFO: Epoch: [47] [1230/1251] eta: 0:00:13 lr: 0.000939 loss: 4.0036 (3.7806) grad_norm: 1.0809 (inf) time: 0.6226 [2021-03-26 09:06:49 swin_base_patch4_window7_224] INFO: Epoch: [47] [1240/1251] eta: 0:00:06 lr: 0.000939 loss: 3.8843 (3.7818) grad_norm: 1.0896 (inf) time: 0.6259 [2021-03-26 09:06:55 swin_base_patch4_window7_224] INFO: Epoch: [47] [1250/1251] eta: 0:00:00 lr: 0.000939 loss: 4.0617 (3.7845) grad_norm: 1.0951 (inf) time: 0.6277 [2021-03-26 09:07:01 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:15 loss: 1.0645 (1.0645) acc1: 70.3125 (70.3125) acc5: 96.8750 (96.8750) [2021-03-26 09:07:03 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.1393 (1.1920) acc1: 70.3125 (72.7273) acc5: 92.1875 (92.6136) [2021-03-26 09:07:06 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.1891 (1.2646) acc1: 70.3125 (70.9821) acc5: 92.1875 (91.8155) [2021-03-26 09:07:07 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.2422 (1.2673) acc1: 68.7500 (70.4637) acc5: 90.6250 (91.2298) [2021-03-26 09:07:09 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2422 (1.2623) acc1: 70.3125 (71.1890) acc5: 87.5000 (90.7393) [2021-03-26 09:07:10 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1371 (1.2404) acc1: 73.4375 (71.5520) acc5: 92.1875 (91.1680) [2021-03-26 09:07:15 swin_base_patch4_window7_224] INFO: * Acc@1 72.360 Acc@5 91.586 loss 1.212 [2021-03-26 09:07:15 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 72.4% [2021-03-26 09:07:15 swin_base_patch4_window7_224] INFO: Max accuracy: 72.36% [2021-03-26 09:07:19 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 0/1251] eta: 1:20:53 lr: 0.000939 loss: 4.3553 (4.3553) grad_norm: 0.9948 (0.9948) time: 3.8800 [2021-03-26 09:07:25 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 10/1251] eta: 0:19:48 lr: 0.000939 loss: 4.0296 (3.9961) grad_norm: 1.0618 (1.0744) time: 0.9575 [2021-03-26 09:07:32 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 20/1251] eta: 0:16:24 lr: 0.000939 loss: 3.8279 (3.8458) grad_norm: 1.0910 (1.0864) time: 0.6456 [2021-03-26 09:07:38 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 30/1251] eta: 0:15:08 lr: 0.000939 loss: 3.5694 (3.7809) grad_norm: 1.0131 (1.0647) time: 0.6264 [2021-03-26 09:07:44 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 40/1251] eta: 0:14:26 lr: 0.000939 loss: 3.8605 (3.8214) grad_norm: 1.0402 (1.0705) time: 0.6275 [2021-03-26 09:07:51 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 50/1251] eta: 0:13:58 lr: 0.000939 loss: 3.9438 (3.8230) grad_norm: 1.0547 (1.0699) time: 0.6282 [2021-03-26 09:07:57 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 60/1251] eta: 0:13:37 lr: 0.000939 loss: 3.9291 (3.8050) grad_norm: 1.0513 (1.0822) time: 0.6268 [2021-03-26 09:08:03 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 70/1251] eta: 0:13:20 lr: 0.000939 loss: 3.8251 (3.8029) grad_norm: 1.0790 (1.0865) time: 0.6259 [2021-03-26 09:08:09 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 80/1251] eta: 0:13:06 lr: 0.000939 loss: 3.7464 (3.8008) grad_norm: 1.0591 (1.0808) time: 0.6267 [2021-03-26 09:08:16 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 90/1251] eta: 0:12:54 lr: 0.000939 loss: 3.7661 (3.8102) grad_norm: 1.0217 (1.0797) time: 0.6274 [2021-03-26 09:08:22 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 100/1251] eta: 0:12:43 lr: 0.000939 loss: 3.8542 (3.8098) grad_norm: 1.0128 (1.0709) time: 0.6277 [2021-03-26 09:08:28 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 110/1251] eta: 0:12:32 lr: 0.000939 loss: 3.8542 (3.8219) grad_norm: 1.0499 (1.0826) time: 0.6278 [2021-03-26 09:08:34 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 120/1251] eta: 0:12:22 lr: 0.000939 loss: 3.7601 (3.8198) grad_norm: 1.0499 (1.0773) time: 0.6236 [2021-03-26 09:08:41 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 130/1251] eta: 0:12:13 lr: 0.000939 loss: 3.9640 (3.8096) grad_norm: 1.0080 (1.0730) time: 0.6251 [2021-03-26 09:08:47 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 140/1251] eta: 0:12:05 lr: 0.000938 loss: 3.9385 (3.8182) grad_norm: 1.0260 (1.0680) time: 0.6297 [2021-03-26 09:08:53 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 150/1251] eta: 0:11:56 lr: 0.000938 loss: 3.7999 (3.7905) grad_norm: 1.0177 (1.0670) time: 0.6267 [2021-03-26 09:09:00 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 160/1251] eta: 0:11:48 lr: 0.000938 loss: 3.6075 (3.8076) grad_norm: 1.0041 (1.0624) time: 0.6271 [2021-03-26 09:09:06 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 170/1251] eta: 0:11:40 lr: 0.000938 loss: 3.9998 (3.8216) grad_norm: 0.9645 (1.0581) time: 0.6286 [2021-03-26 09:09:12 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 180/1251] eta: 0:11:32 lr: 0.000938 loss: 3.8121 (3.8060) grad_norm: 1.0204 (1.0634) time: 0.6243 [2021-03-26 09:09:18 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 190/1251] eta: 0:11:25 lr: 0.000938 loss: 3.6496 (3.8097) grad_norm: 1.1265 (1.0624) time: 0.6250 [2021-03-26 09:09:25 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 200/1251] eta: 0:11:18 lr: 0.000938 loss: 3.8140 (3.8094) grad_norm: 1.0565 (1.0626) time: 0.6378 [2021-03-26 09:09:31 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 210/1251] eta: 0:11:11 lr: 0.000938 loss: 3.7253 (3.7953) grad_norm: 1.0757 (1.0688) time: 0.6339 [2021-03-26 09:09:37 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 220/1251] eta: 0:11:03 lr: 0.000938 loss: 3.5373 (3.7826) grad_norm: 1.0584 (1.0671) time: 0.6199 [2021-03-26 09:09:43 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 230/1251] eta: 0:10:56 lr: 0.000938 loss: 3.6263 (3.7803) grad_norm: 1.0584 (1.0690) time: 0.6246 [2021-03-26 09:09:50 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 240/1251] eta: 0:10:49 lr: 0.000938 loss: 3.6183 (3.7697) grad_norm: 1.1078 (1.0728) time: 0.6343 [2021-03-26 09:09:56 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 250/1251] eta: 0:10:42 lr: 0.000938 loss: 3.8049 (3.7772) grad_norm: 1.0629 (1.0725) time: 0.6283 [2021-03-26 09:10:02 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 260/1251] eta: 0:10:35 lr: 0.000938 loss: 3.8897 (3.7710) grad_norm: 1.0405 (1.0705) time: 0.6181 [2021-03-26 09:10:08 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 270/1251] eta: 0:10:28 lr: 0.000938 loss: 3.6597 (3.7688) grad_norm: 0.9898 (1.0670) time: 0.6224 [2021-03-26 09:10:15 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 280/1251] eta: 0:10:21 lr: 0.000938 loss: 3.7652 (3.7688) grad_norm: 1.0034 (1.0651) time: 0.6306 [2021-03-26 09:10:21 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 290/1251] eta: 0:10:14 lr: 0.000938 loss: 3.7126 (3.7612) grad_norm: 1.0342 (1.0656) time: 0.6268 [2021-03-26 09:10:27 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 300/1251] eta: 0:10:07 lr: 0.000938 loss: 3.7674 (3.7683) grad_norm: 1.0052 (1.0651) time: 0.6229 [2021-03-26 09:10:34 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 310/1251] eta: 0:10:00 lr: 0.000938 loss: 3.8233 (3.7669) grad_norm: 0.9708 (1.0645) time: 0.6241 [2021-03-26 09:10:40 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 320/1251] eta: 0:09:54 lr: 0.000938 loss: 3.8233 (3.7695) grad_norm: 1.0205 (1.0666) time: 0.6245 [2021-03-26 09:10:46 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 330/1251] eta: 0:09:47 lr: 0.000938 loss: 3.6923 (3.7618) grad_norm: 1.1142 (1.0680) time: 0.6217 [2021-03-26 09:10:52 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 340/1251] eta: 0:09:40 lr: 0.000938 loss: 3.6923 (3.7684) grad_norm: 1.0434 (1.0663) time: 0.6196 [2021-03-26 09:10:59 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 350/1251] eta: 0:09:33 lr: 0.000938 loss: 4.0116 (3.7699) grad_norm: 1.0434 (1.0661) time: 0.6290 [2021-03-26 09:11:05 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 360/1251] eta: 0:09:27 lr: 0.000938 loss: 3.8824 (3.7687) grad_norm: 1.0666 (1.0682) time: 0.6396 [2021-03-26 09:11:11 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 370/1251] eta: 0:09:20 lr: 0.000938 loss: 3.8244 (3.7643) grad_norm: 1.0908 (1.0687) time: 0.6284 [2021-03-26 09:11:17 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 380/1251] eta: 0:09:14 lr: 0.000938 loss: 3.8244 (3.7592) grad_norm: 1.1012 (1.0697) time: 0.6238 [2021-03-26 09:11:24 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 390/1251] eta: 0:09:07 lr: 0.000938 loss: 4.0504 (3.7686) grad_norm: 1.1105 (1.0719) time: 0.6307 [2021-03-26 09:11:30 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 400/1251] eta: 0:09:01 lr: 0.000938 loss: 4.1191 (3.7692) grad_norm: 1.1218 (1.0725) time: 0.6305 [2021-03-26 09:11:36 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 410/1251] eta: 0:08:54 lr: 0.000938 loss: 3.9681 (3.7701) grad_norm: 1.1061 (1.0731) time: 0.6283 [2021-03-26 09:11:43 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 420/1251] eta: 0:08:48 lr: 0.000938 loss: 4.0137 (3.7738) grad_norm: 1.0503 (1.0719) time: 0.6225 [2021-03-26 09:11:49 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 430/1251] eta: 0:08:41 lr: 0.000938 loss: 3.8768 (3.7697) grad_norm: 1.0606 (1.0737) time: 0.6273 [2021-03-26 09:11:55 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 440/1251] eta: 0:08:34 lr: 0.000938 loss: 3.7870 (3.7706) grad_norm: 1.0869 (1.0745) time: 0.6247 [2021-03-26 09:12:01 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 450/1251] eta: 0:08:28 lr: 0.000938 loss: 3.6645 (3.7708) grad_norm: 1.0372 (1.0755) time: 0.6218 [2021-03-26 09:12:08 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 460/1251] eta: 0:08:22 lr: 0.000938 loss: 3.6645 (3.7671) grad_norm: 1.0823 (1.0759) time: 0.6313 [2021-03-26 09:12:14 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 470/1251] eta: 0:08:15 lr: 0.000938 loss: 3.7822 (3.7704) grad_norm: 1.0730 (1.0757) time: 0.6328 [2021-03-26 09:12:20 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 480/1251] eta: 0:08:09 lr: 0.000938 loss: 3.8947 (3.7727) grad_norm: 1.0694 (1.0768) time: 0.6314 [2021-03-26 09:12:27 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 490/1251] eta: 0:08:02 lr: 0.000938 loss: 4.1008 (3.7789) grad_norm: 1.0847 (1.0768) time: 0.6329 [2021-03-26 09:12:33 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 500/1251] eta: 0:07:56 lr: 0.000938 loss: 4.1255 (3.7841) grad_norm: 1.0966 (1.0775) time: 0.6334 [2021-03-26 09:12:39 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 510/1251] eta: 0:07:50 lr: 0.000938 loss: 3.9475 (3.7848) grad_norm: 1.1356 (1.0785) time: 0.6290 [2021-03-26 09:12:45 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 520/1251] eta: 0:07:43 lr: 0.000938 loss: 3.5948 (3.7805) grad_norm: 1.0487 (1.0796) time: 0.6249 [2021-03-26 09:12:52 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 530/1251] eta: 0:07:37 lr: 0.000938 loss: 3.5531 (3.7800) grad_norm: 1.0487 (1.0801) time: 0.6273 [2021-03-26 09:12:58 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 540/1251] eta: 0:07:30 lr: 0.000938 loss: 3.9069 (3.7840) grad_norm: 1.0715 (1.0799) time: 0.6243 [2021-03-26 09:13:04 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 550/1251] eta: 0:07:24 lr: 0.000938 loss: 4.1735 (3.7869) grad_norm: 1.0318 (1.0786) time: 0.6292 [2021-03-26 09:13:11 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 560/1251] eta: 0:07:17 lr: 0.000938 loss: 3.5639 (3.7853) grad_norm: 0.9778 (1.0773) time: 0.6304 [2021-03-26 09:13:17 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 570/1251] eta: 0:07:11 lr: 0.000938 loss: 3.8800 (3.7880) grad_norm: 0.9702 (1.0761) time: 0.6216 [2021-03-26 09:13:23 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 580/1251] eta: 0:07:05 lr: 0.000938 loss: 3.8224 (3.7851) grad_norm: 1.0310 (1.0759) time: 0.6268 [2021-03-26 09:13:29 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 590/1251] eta: 0:06:58 lr: 0.000938 loss: 3.8043 (3.7903) grad_norm: 1.0315 (1.0752) time: 0.6295 [2021-03-26 09:13:36 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 600/1251] eta: 0:06:52 lr: 0.000938 loss: 4.0845 (3.7922) grad_norm: 1.0459 (1.0759) time: 0.6248 [2021-03-26 09:13:42 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 610/1251] eta: 0:06:45 lr: 0.000938 loss: 3.8843 (3.7926) grad_norm: 1.0146 (1.0745) time: 0.6221 [2021-03-26 09:13:48 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 620/1251] eta: 0:06:39 lr: 0.000938 loss: 3.8725 (3.7928) grad_norm: 1.0146 (1.0753) time: 0.6254 [2021-03-26 09:13:54 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 630/1251] eta: 0:06:33 lr: 0.000938 loss: 3.6963 (3.7934) grad_norm: 1.0492 (1.0745) time: 0.6285 [2021-03-26 09:14:01 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 640/1251] eta: 0:06:26 lr: 0.000937 loss: 3.6963 (3.7952) grad_norm: 0.9997 (1.0730) time: 0.6276 [2021-03-26 09:14:07 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 650/1251] eta: 0:06:20 lr: 0.000937 loss: 3.7538 (3.7964) grad_norm: 0.9997 (1.0727) time: 0.6294 [2021-03-26 09:14:13 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 660/1251] eta: 0:06:13 lr: 0.000937 loss: 3.8860 (3.7931) grad_norm: 1.0221 (1.0722) time: 0.6271 [2021-03-26 09:14:19 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 670/1251] eta: 0:06:07 lr: 0.000937 loss: 3.9028 (3.7939) grad_norm: 1.0152 (1.0717) time: 0.6220 [2021-03-26 09:14:26 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 680/1251] eta: 0:06:01 lr: 0.000937 loss: 3.9460 (3.7944) grad_norm: 1.0410 (1.0718) time: 0.6275 [2021-03-26 09:14:32 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 690/1251] eta: 0:05:54 lr: 0.000937 loss: 3.9727 (3.7974) grad_norm: 1.0640 (1.0719) time: 0.6287 [2021-03-26 09:14:38 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 700/1251] eta: 0:05:48 lr: 0.000937 loss: 4.1248 (3.7997) grad_norm: 1.0900 (1.0727) time: 0.6251 [2021-03-26 09:14:45 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 710/1251] eta: 0:05:42 lr: 0.000937 loss: 4.1577 (3.8025) grad_norm: 1.0514 (1.0719) time: 0.6287 [2021-03-26 09:14:51 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 720/1251] eta: 0:05:35 lr: 0.000937 loss: 3.8103 (3.7958) grad_norm: 1.0306 (1.0720) time: 0.6310 [2021-03-26 09:14:57 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 730/1251] eta: 0:05:29 lr: 0.000937 loss: 3.5790 (3.7953) grad_norm: 1.0387 (1.0730) time: 0.6248 [2021-03-26 09:15:03 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 740/1251] eta: 0:05:22 lr: 0.000937 loss: 3.9153 (3.7960) grad_norm: 1.0387 (1.0735) time: 0.6214 [2021-03-26 09:15:10 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 750/1251] eta: 0:05:16 lr: 0.000937 loss: 4.1578 (3.7988) grad_norm: 1.0478 (1.0735) time: 0.6353 [2021-03-26 09:15:16 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 760/1251] eta: 0:05:10 lr: 0.000937 loss: 4.1501 (3.7995) grad_norm: 1.0836 (1.0746) time: 0.6327 [2021-03-26 09:15:22 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 770/1251] eta: 0:05:03 lr: 0.000937 loss: 3.8857 (3.7978) grad_norm: 1.0807 (1.0745) time: 0.6225 [2021-03-26 09:15:29 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 780/1251] eta: 0:04:57 lr: 0.000937 loss: 4.0338 (3.8013) grad_norm: 1.0486 (1.0754) time: 0.6285 [2021-03-26 09:15:35 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 790/1251] eta: 0:04:51 lr: 0.000937 loss: 4.1164 (3.8056) grad_norm: 1.1135 (1.0753) time: 0.6263 [2021-03-26 09:15:41 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 800/1251] eta: 0:04:44 lr: 0.000937 loss: 3.9895 (3.8059) grad_norm: 1.0710 (1.0754) time: 0.6222 [2021-03-26 09:15:47 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 810/1251] eta: 0:04:38 lr: 0.000937 loss: 3.8185 (3.8023) grad_norm: 1.0496 (1.0752) time: 0.6270 [2021-03-26 09:15:54 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 820/1251] eta: 0:04:32 lr: 0.000937 loss: 3.3861 (3.7992) grad_norm: 1.0502 (1.0758) time: 0.6258 [2021-03-26 09:16:00 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 830/1251] eta: 0:04:25 lr: 0.000937 loss: 3.5570 (3.7989) grad_norm: 1.0297 (1.0751) time: 0.6238 [2021-03-26 09:16:06 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 840/1251] eta: 0:04:19 lr: 0.000937 loss: 3.7898 (3.7981) grad_norm: 0.9779 (1.0742) time: 0.6266 [2021-03-26 09:16:12 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 850/1251] eta: 0:04:13 lr: 0.000937 loss: 3.7107 (3.7952) grad_norm: 1.0072 (1.0742) time: 0.6275 [2021-03-26 09:16:19 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 860/1251] eta: 0:04:06 lr: 0.000937 loss: 3.9250 (3.7961) grad_norm: 1.0357 (1.0739) time: 0.6338 [2021-03-26 09:16:25 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 870/1251] eta: 0:04:00 lr: 0.000937 loss: 3.9250 (3.7951) grad_norm: 1.0564 (1.0745) time: 0.6311 [2021-03-26 09:16:31 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 880/1251] eta: 0:03:54 lr: 0.000937 loss: 3.9205 (3.7979) grad_norm: 1.0397 (1.0742) time: 0.6227 [2021-03-26 09:16:37 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 890/1251] eta: 0:03:47 lr: 0.000937 loss: 3.5709 (3.7933) grad_norm: 1.0029 (1.0733) time: 0.6250 [2021-03-26 09:16:44 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 900/1251] eta: 0:03:41 lr: 0.000937 loss: 3.4390 (3.7922) grad_norm: 0.9588 (1.0730) time: 0.6235 [2021-03-26 09:16:50 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 910/1251] eta: 0:03:35 lr: 0.000937 loss: 3.9974 (3.7934) grad_norm: 1.0112 (1.0726) time: 0.6248 [2021-03-26 09:16:56 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 920/1251] eta: 0:03:28 lr: 0.000937 loss: 3.9812 (3.7924) grad_norm: 1.0326 (1.0728) time: 0.6255 [2021-03-26 09:17:03 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 930/1251] eta: 0:03:22 lr: 0.000937 loss: 3.9314 (3.7936) grad_norm: 1.0932 (1.0739) time: 0.6299 [2021-03-26 09:17:09 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 940/1251] eta: 0:03:16 lr: 0.000937 loss: 3.9314 (3.7960) grad_norm: 1.0673 (1.0742) time: 0.6339 [2021-03-26 09:17:15 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 950/1251] eta: 0:03:09 lr: 0.000937 loss: 3.7839 (3.7946) grad_norm: 0.9996 (1.0739) time: 0.6347 [2021-03-26 09:17:22 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 960/1251] eta: 0:03:03 lr: 0.000937 loss: 3.6179 (3.7927) grad_norm: 1.0243 (1.0737) time: 0.6349 [2021-03-26 09:17:28 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 970/1251] eta: 0:02:57 lr: 0.000937 loss: 3.7253 (3.7917) grad_norm: 1.0243 (1.0737) time: 0.6229 [2021-03-26 09:17:34 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 980/1251] eta: 0:02:50 lr: 0.000937 loss: 3.7742 (3.7913) grad_norm: 1.0311 (1.0739) time: 0.6167 [2021-03-26 09:17:40 swin_base_patch4_window7_224] INFO: Epoch: [48] [ 990/1251] eta: 0:02:44 lr: 0.000937 loss: 3.9348 (3.7945) grad_norm: 1.1140 (1.0746) time: 0.6235 [2021-03-26 09:17:46 swin_base_patch4_window7_224] INFO: Epoch: [48] [1000/1251] eta: 0:02:38 lr: 0.000937 loss: 3.9086 (3.7925) grad_norm: 1.1261 (1.0753) time: 0.6283 [2021-03-26 09:17:53 swin_base_patch4_window7_224] INFO: Epoch: [48] [1010/1251] eta: 0:02:32 lr: 0.000937 loss: 3.7047 (3.7933) grad_norm: 1.0771 (1.0746) time: 0.6264 [2021-03-26 09:17:59 swin_base_patch4_window7_224] INFO: Epoch: [48] [1020/1251] eta: 0:02:25 lr: 0.000937 loss: 3.6179 (3.7911) grad_norm: 1.0114 (1.0739) time: 0.6249 [2021-03-26 09:18:05 swin_base_patch4_window7_224] INFO: Epoch: [48] [1030/1251] eta: 0:02:19 lr: 0.000937 loss: 3.5972 (3.7905) grad_norm: 1.0114 (1.0734) time: 0.6178 [2021-03-26 09:18:11 swin_base_patch4_window7_224] INFO: Epoch: [48] [1040/1251] eta: 0:02:13 lr: 0.000937 loss: 3.7263 (3.7901) grad_norm: 1.0723 (1.0742) time: 0.6173 [2021-03-26 09:18:17 swin_base_patch4_window7_224] INFO: Epoch: [48] [1050/1251] eta: 0:02:06 lr: 0.000937 loss: 3.6585 (3.7881) grad_norm: 0.9992 (1.0735) time: 0.6192 [2021-03-26 09:18:24 swin_base_patch4_window7_224] INFO: Epoch: [48] [1060/1251] eta: 0:02:00 lr: 0.000937 loss: 3.7733 (3.7883) grad_norm: 0.9854 (1.0727) time: 0.6199 [2021-03-26 09:18:30 swin_base_patch4_window7_224] INFO: Epoch: [48] [1070/1251] eta: 0:01:54 lr: 0.000937 loss: 3.9131 (3.7894) grad_norm: 0.9854 (1.0724) time: 0.6198 [2021-03-26 09:18:36 swin_base_patch4_window7_224] INFO: Epoch: [48] [1080/1251] eta: 0:01:47 lr: 0.000937 loss: 3.8468 (3.7890) grad_norm: 0.9875 (1.0720) time: 0.6196 [2021-03-26 09:18:42 swin_base_patch4_window7_224] INFO: Epoch: [48] [1090/1251] eta: 0:01:41 lr: 0.000937 loss: 3.6123 (3.7871) grad_norm: 1.0098 (1.0722) time: 0.6225 [2021-03-26 09:18:49 swin_base_patch4_window7_224] INFO: Epoch: [48] [1100/1251] eta: 0:01:35 lr: 0.000937 loss: 3.9184 (3.7892) grad_norm: 1.0721 (1.0728) time: 0.6258 [2021-03-26 09:18:55 swin_base_patch4_window7_224] INFO: Epoch: [48] [1110/1251] eta: 0:01:28 lr: 0.000937 loss: 3.9184 (3.7892) grad_norm: 1.0869 (1.0730) time: 0.6316 [2021-03-26 09:19:01 swin_base_patch4_window7_224] INFO: Epoch: [48] [1120/1251] eta: 0:01:22 lr: 0.000937 loss: 3.7106 (3.7850) grad_norm: 1.1007 (1.0734) time: 0.6270 [2021-03-26 09:19:07 swin_base_patch4_window7_224] INFO: Epoch: [48] [1130/1251] eta: 0:01:16 lr: 0.000936 loss: 3.6008 (3.7849) grad_norm: 0.9593 (1.0723) time: 0.6246 [2021-03-26 09:19:14 swin_base_patch4_window7_224] INFO: Epoch: [48] [1140/1251] eta: 0:01:09 lr: 0.000936 loss: 3.7037 (3.7836) grad_norm: 1.0088 (1.0730) time: 0.6281 [2021-03-26 09:19:20 swin_base_patch4_window7_224] INFO: Epoch: [48] [1150/1251] eta: 0:01:03 lr: 0.000936 loss: 3.6405 (3.7834) grad_norm: 1.0521 (1.0726) time: 0.6237 [2021-03-26 09:19:26 swin_base_patch4_window7_224] INFO: Epoch: [48] [1160/1251] eta: 0:00:57 lr: 0.000936 loss: 3.7430 (3.7830) grad_norm: 0.9941 (1.0721) time: 0.6184 [2021-03-26 09:19:32 swin_base_patch4_window7_224] INFO: Epoch: [48] [1170/1251] eta: 0:00:50 lr: 0.000936 loss: 3.8604 (3.7849) grad_norm: 0.9706 (1.0715) time: 0.6180 [2021-03-26 09:19:38 swin_base_patch4_window7_224] INFO: Epoch: [48] [1180/1251] eta: 0:00:44 lr: 0.000936 loss: 3.9761 (3.7854) grad_norm: 0.9889 (1.0718) time: 0.6178 [2021-03-26 09:19:45 swin_base_patch4_window7_224] INFO: Epoch: [48] [1190/1251] eta: 0:00:38 lr: 0.000936 loss: 3.9339 (3.7859) grad_norm: 1.0609 (1.0720) time: 0.6189 [2021-03-26 09:19:51 swin_base_patch4_window7_224] INFO: Epoch: [48] [1200/1251] eta: 0:00:32 lr: 0.000936 loss: 3.7912 (3.7858) grad_norm: 1.0451 (1.0719) time: 0.6272 [2021-03-26 09:19:57 swin_base_patch4_window7_224] INFO: Epoch: [48] [1210/1251] eta: 0:00:25 lr: 0.000936 loss: 3.7454 (3.7845) grad_norm: 1.0360 (1.0713) time: 0.6309 [2021-03-26 09:20:03 swin_base_patch4_window7_224] INFO: Epoch: [48] [1220/1251] eta: 0:00:19 lr: 0.000936 loss: 3.8810 (3.7853) grad_norm: 0.9632 (1.0706) time: 0.6211 [2021-03-26 09:20:10 swin_base_patch4_window7_224] INFO: Epoch: [48] [1230/1251] eta: 0:00:13 lr: 0.000936 loss: 3.9078 (3.7871) grad_norm: 0.9904 (1.0703) time: 0.6220 [2021-03-26 09:20:16 swin_base_patch4_window7_224] INFO: Epoch: [48] [1240/1251] eta: 0:00:06 lr: 0.000936 loss: 3.5524 (3.7844) grad_norm: 1.0287 (1.0701) time: 0.6209 [2021-03-26 09:20:22 swin_base_patch4_window7_224] INFO: Epoch: [48] [1250/1251] eta: 0:00:00 lr: 0.000936 loss: 3.5065 (3.7838) grad_norm: 1.0477 (1.0704) time: 0.6106 [2021-03-26 09:20:26 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:27 loss: 1.0505 (1.0505) acc1: 75.0000 (75.0000) acc5: 90.6250 (90.6250) [2021-03-26 09:20:29 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0644 (1.1514) acc1: 73.4375 (73.8636) acc5: 90.6250 (91.0511) [2021-03-26 09:20:32 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.1020 (1.2058) acc1: 71.8750 (71.8006) acc5: 90.6250 (90.3274) [2021-03-26 09:20:33 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1263 (1.2063) acc1: 70.3125 (71.6734) acc5: 90.6250 (90.4738) [2021-03-26 09:20:35 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1934 (1.2167) acc1: 70.3125 (71.4939) acc5: 90.6250 (90.7393) [2021-03-26 09:20:37 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1934 (1.2270) acc1: 70.3125 (71.2000) acc5: 92.1875 (90.8480) [2021-03-26 09:20:40 swin_base_patch4_window7_224] INFO: * Acc@1 72.174 Acc@5 91.548 loss 1.192 [2021-03-26 09:20:40 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 72.2% [2021-03-26 09:20:40 swin_base_patch4_window7_224] INFO: Max accuracy: 72.36% [2021-03-26 09:20:44 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 0/1251] eta: 1:29:19 lr: 0.000936 loss: 4.0906 (4.0906) grad_norm: 1.2699 (1.2699) time: 4.2844 [2021-03-26 09:20:50 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 10/1251] eta: 0:19:45 lr: 0.000936 loss: 3.9166 (3.8936) grad_norm: 1.0635 (1.0665) time: 0.9556 [2021-03-26 09:20:56 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 20/1251] eta: 0:16:23 lr: 0.000936 loss: 3.8466 (3.7149) grad_norm: 0.9906 (1.0336) time: 0.6245 [2021-03-26 09:21:02 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 30/1251] eta: 0:15:02 lr: 0.000936 loss: 3.6545 (3.7222) grad_norm: 0.9425 (1.0189) time: 0.6196 [2021-03-26 09:21:09 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 40/1251] eta: 0:14:19 lr: 0.000936 loss: 3.8011 (3.7496) grad_norm: 0.9740 (1.0104) time: 0.6155 [2021-03-26 09:21:15 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 50/1251] eta: 0:13:55 lr: 0.000936 loss: 4.1196 (3.8162) grad_norm: 1.0170 (1.0309) time: 0.6284 [2021-03-26 09:21:21 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 60/1251] eta: 0:13:34 lr: 0.000936 loss: 3.9287 (3.7413) grad_norm: 1.0389 (1.0310) time: 0.6320 [2021-03-26 09:21:28 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 70/1251] eta: 0:13:17 lr: 0.000936 loss: 3.8109 (3.7714) grad_norm: 1.0568 (1.0466) time: 0.6233 [2021-03-26 09:21:34 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 80/1251] eta: 0:13:03 lr: 0.000936 loss: 3.7595 (3.7511) grad_norm: 1.0432 (1.0401) time: 0.6221 [2021-03-26 09:21:40 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 90/1251] eta: 0:12:51 lr: 0.000936 loss: 3.8613 (3.7477) grad_norm: 1.0035 (1.0387) time: 0.6256 [2021-03-26 09:21:46 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 100/1251] eta: 0:12:40 lr: 0.000936 loss: 3.8945 (3.7309) grad_norm: 1.0084 (1.0362) time: 0.6287 [2021-03-26 09:21:53 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 110/1251] eta: 0:12:29 lr: 0.000936 loss: 3.8229 (3.7368) grad_norm: 1.0103 (1.0371) time: 0.6244 [2021-03-26 09:21:59 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 120/1251] eta: 0:12:21 lr: 0.000936 loss: 3.8171 (3.7396) grad_norm: 1.0155 (1.0391) time: 0.6272 [2021-03-26 09:22:05 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 130/1251] eta: 0:12:11 lr: 0.000936 loss: 3.6919 (3.7296) grad_norm: 1.0590 (1.0448) time: 0.6264 [2021-03-26 09:22:11 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 140/1251] eta: 0:12:03 lr: 0.000936 loss: 3.6201 (3.7283) grad_norm: 1.0854 (1.0479) time: 0.6286 [2021-03-26 09:22:18 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 150/1251] eta: 0:11:55 lr: 0.000936 loss: 3.6201 (3.7249) grad_norm: 1.0330 (1.0477) time: 0.6304 [2021-03-26 09:22:24 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 160/1251] eta: 0:11:47 lr: 0.000936 loss: 3.8174 (3.7296) grad_norm: 0.9704 (1.0435) time: 0.6249 [2021-03-26 09:22:30 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 170/1251] eta: 0:11:39 lr: 0.000936 loss: 3.6053 (3.7035) grad_norm: 1.0303 (1.0406) time: 0.6304 [2021-03-26 09:22:37 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 180/1251] eta: 0:11:32 lr: 0.000936 loss: 3.4938 (3.7091) grad_norm: 1.0303 (1.0414) time: 0.6315 [2021-03-26 09:22:43 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 190/1251] eta: 0:11:24 lr: 0.000936 loss: 3.7887 (3.7064) grad_norm: 1.0148 (1.0417) time: 0.6315 [2021-03-26 09:22:49 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 200/1251] eta: 0:11:17 lr: 0.000936 loss: 3.6304 (3.7051) grad_norm: 1.0237 (1.0404) time: 0.6255 [2021-03-26 09:22:55 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 210/1251] eta: 0:11:09 lr: 0.000936 loss: 3.5633 (3.6908) grad_norm: 1.0332 (1.0411) time: 0.6231 [2021-03-26 09:23:02 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 220/1251] eta: 0:11:02 lr: 0.000936 loss: 3.8009 (3.6996) grad_norm: 1.0894 (1.0458) time: 0.6264 [2021-03-26 09:23:08 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 230/1251] eta: 0:10:55 lr: 0.000936 loss: 3.9775 (3.7086) grad_norm: 1.0599 (1.0420) time: 0.6222 [2021-03-26 09:23:14 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 240/1251] eta: 0:10:48 lr: 0.000936 loss: 3.9138 (3.7136) grad_norm: 0.9572 (1.0429) time: 0.6280 [2021-03-26 09:23:20 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 250/1251] eta: 0:10:41 lr: 0.000936 loss: 3.9082 (3.7157) grad_norm: 1.0215 (1.0474) time: 0.6292 [2021-03-26 09:23:27 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 260/1251] eta: 0:10:34 lr: 0.000936 loss: 3.9082 (3.7160) grad_norm: 1.0215 (1.0474) time: 0.6210 [2021-03-26 09:23:33 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 270/1251] eta: 0:10:27 lr: 0.000936 loss: 3.8769 (3.7150) grad_norm: 1.0255 (1.0479) time: 0.6220 [2021-03-26 09:23:39 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 280/1251] eta: 0:10:20 lr: 0.000936 loss: 3.8465 (3.7173) grad_norm: 1.0346 (1.0472) time: 0.6220 [2021-03-26 09:23:45 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 290/1251] eta: 0:10:13 lr: 0.000936 loss: 3.8604 (3.7192) grad_norm: 1.0057 (1.0447) time: 0.6208 [2021-03-26 09:23:52 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 300/1251] eta: 0:10:06 lr: 0.000936 loss: 3.7111 (3.7157) grad_norm: 0.9867 (1.0439) time: 0.6246 [2021-03-26 09:23:58 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 310/1251] eta: 0:09:59 lr: 0.000936 loss: 3.7111 (3.7166) grad_norm: 0.9867 (1.0429) time: 0.6237 [2021-03-26 09:24:04 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 320/1251] eta: 0:09:52 lr: 0.000936 loss: 3.8020 (3.7135) grad_norm: 0.9841 (1.0428) time: 0.6249 [2021-03-26 09:24:10 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 330/1251] eta: 0:09:46 lr: 0.000936 loss: 3.8817 (3.7179) grad_norm: 1.0297 (1.0444) time: 0.6275 [2021-03-26 09:24:17 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 340/1251] eta: 0:09:39 lr: 0.000936 loss: 3.8890 (3.7153) grad_norm: 1.0589 (1.0440) time: 0.6238 [2021-03-26 09:24:23 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 350/1251] eta: 0:09:32 lr: 0.000936 loss: 3.6975 (3.7129) grad_norm: 1.0589 (1.0451) time: 0.6257 [2021-03-26 09:24:29 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 360/1251] eta: 0:09:26 lr: 0.000936 loss: 3.8009 (3.7174) grad_norm: 1.1100 (1.0470) time: 0.6252 [2021-03-26 09:24:35 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 370/1251] eta: 0:09:19 lr: 0.000935 loss: 3.7760 (3.7185) grad_norm: 1.0905 (1.0476) time: 0.6276 [2021-03-26 09:24:42 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 380/1251] eta: 0:09:13 lr: 0.000935 loss: 3.9019 (3.7237) grad_norm: 1.1084 (1.0522) time: 0.6305 [2021-03-26 09:24:48 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 390/1251] eta: 0:09:06 lr: 0.000935 loss: 3.5681 (3.7163) grad_norm: 1.0608 (1.0526) time: 0.6251 [2021-03-26 09:24:54 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 400/1251] eta: 0:09:00 lr: 0.000935 loss: 3.7789 (3.7265) grad_norm: 1.0608 (1.0527) time: 0.6241 [2021-03-26 09:25:00 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 410/1251] eta: 0:08:53 lr: 0.000935 loss: 3.9462 (3.7254) grad_norm: 1.0731 (1.0531) time: 0.6231 [2021-03-26 09:25:07 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 420/1251] eta: 0:08:46 lr: 0.000935 loss: 3.7612 (3.7249) grad_norm: 1.0342 (1.0525) time: 0.6199 [2021-03-26 09:25:13 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 430/1251] eta: 0:08:40 lr: 0.000935 loss: 3.7934 (3.7233) grad_norm: 1.0266 (1.0525) time: 0.6224 [2021-03-26 09:25:19 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 440/1251] eta: 0:08:33 lr: 0.000935 loss: 3.9355 (3.7305) grad_norm: 1.0236 (1.0519) time: 0.6285 [2021-03-26 09:25:25 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 450/1251] eta: 0:08:27 lr: 0.000935 loss: 4.0183 (3.7340) grad_norm: 1.0103 (1.0520) time: 0.6255 [2021-03-26 09:25:31 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 460/1251] eta: 0:08:20 lr: 0.000935 loss: 3.9448 (3.7340) grad_norm: 0.9997 (1.0497) time: 0.6151 [2021-03-26 09:25:38 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 470/1251] eta: 0:08:14 lr: 0.000935 loss: 3.7131 (3.7302) grad_norm: 0.9920 (1.0511) time: 0.6226 [2021-03-26 09:25:44 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 480/1251] eta: 0:08:07 lr: 0.000935 loss: 3.7506 (3.7317) grad_norm: 1.0427 (1.0537) time: 0.6295 [2021-03-26 09:25:50 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 490/1251] eta: 0:08:01 lr: 0.000935 loss: 3.9436 (3.7364) grad_norm: 1.0796 (1.0540) time: 0.6238 [2021-03-26 09:25:57 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 500/1251] eta: 0:07:54 lr: 0.000935 loss: 3.8768 (3.7314) grad_norm: 1.0883 (1.0554) time: 0.6250 [2021-03-26 09:26:03 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 510/1251] eta: 0:07:48 lr: 0.000935 loss: 3.6815 (3.7331) grad_norm: 1.0756 (1.0556) time: 0.6291 [2021-03-26 09:26:09 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 520/1251] eta: 0:07:42 lr: 0.000935 loss: 4.0872 (3.7381) grad_norm: 0.9619 (1.0538) time: 0.6212 [2021-03-26 09:26:15 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 530/1251] eta: 0:07:35 lr: 0.000935 loss: 3.8849 (3.7352) grad_norm: 1.0323 (1.0554) time: 0.6221 [2021-03-26 09:26:22 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 540/1251] eta: 0:07:29 lr: 0.000935 loss: 3.7611 (3.7345) grad_norm: 1.0694 (1.0555) time: 0.6292 [2021-03-26 09:26:28 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 550/1251] eta: 0:07:23 lr: 0.000935 loss: 3.7635 (3.7323) grad_norm: 1.0746 (1.0558) time: 0.6332 [2021-03-26 09:26:34 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 560/1251] eta: 0:07:16 lr: 0.000935 loss: 3.6656 (3.7312) grad_norm: 1.0516 (1.0556) time: 0.6355 [2021-03-26 09:26:40 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 570/1251] eta: 0:07:10 lr: 0.000935 loss: 3.9167 (3.7352) grad_norm: 1.0033 (1.0546) time: 0.6263 [2021-03-26 09:26:47 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 580/1251] eta: 0:07:03 lr: 0.000935 loss: 3.9716 (3.7349) grad_norm: 0.9318 (1.0529) time: 0.6201 [2021-03-26 09:26:53 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 590/1251] eta: 0:06:57 lr: 0.000935 loss: 3.9716 (3.7379) grad_norm: 0.9321 (1.0520) time: 0.6269 [2021-03-26 09:26:59 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 600/1251] eta: 0:06:51 lr: 0.000935 loss: 3.9733 (3.7407) grad_norm: 0.9696 (1.0509) time: 0.6320 [2021-03-26 09:27:06 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 610/1251] eta: 0:06:44 lr: 0.000935 loss: 3.8286 (3.7417) grad_norm: 1.0179 (1.0530) time: 0.6309 [2021-03-26 09:27:12 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 620/1251] eta: 0:06:38 lr: 0.000935 loss: 3.7355 (3.7451) grad_norm: 1.0950 (1.0531) time: 0.6313 [2021-03-26 09:27:18 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 630/1251] eta: 0:06:32 lr: 0.000935 loss: 4.0031 (3.7476) grad_norm: 1.0292 (1.0525) time: 0.6218 [2021-03-26 09:27:24 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 640/1251] eta: 0:06:25 lr: 0.000935 loss: 3.9832 (3.7504) grad_norm: 1.0090 (1.0523) time: 0.6203 [2021-03-26 09:27:31 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 650/1251] eta: 0:06:19 lr: 0.000935 loss: 3.9661 (3.7533) grad_norm: 1.0411 (1.0548) time: 0.6230 [2021-03-26 09:27:37 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 660/1251] eta: 0:06:12 lr: 0.000935 loss: 3.8062 (3.7506) grad_norm: 1.0418 (1.0545) time: 0.6221 [2021-03-26 09:27:43 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 670/1251] eta: 0:06:06 lr: 0.000935 loss: 3.5858 (3.7510) grad_norm: 1.0338 (1.0544) time: 0.6350 [2021-03-26 09:27:49 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 680/1251] eta: 0:06:00 lr: 0.000935 loss: 3.7706 (3.7480) grad_norm: 1.0067 (1.0533) time: 0.6339 [2021-03-26 09:27:56 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 690/1251] eta: 0:05:53 lr: 0.000935 loss: 3.7706 (3.7461) grad_norm: 0.9730 (1.0526) time: 0.6207 [2021-03-26 09:28:02 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 700/1251] eta: 0:05:47 lr: 0.000935 loss: 3.7311 (3.7471) grad_norm: 0.9879 (1.0525) time: 0.6303 [2021-03-26 09:28:08 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 710/1251] eta: 0:05:41 lr: 0.000935 loss: 3.7498 (3.7479) grad_norm: 1.0348 (1.0534) time: 0.6323 [2021-03-26 09:28:15 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 720/1251] eta: 0:05:35 lr: 0.000935 loss: 3.7656 (3.7487) grad_norm: 1.0425 (1.0534) time: 0.6300 [2021-03-26 09:28:21 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 730/1251] eta: 0:05:28 lr: 0.000935 loss: 3.8486 (3.7507) grad_norm: 1.0245 (1.0543) time: 0.6298 [2021-03-26 09:28:27 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 740/1251] eta: 0:05:22 lr: 0.000935 loss: 3.8486 (3.7496) grad_norm: 1.1143 (1.0559) time: 0.6282 [2021-03-26 09:28:34 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 750/1251] eta: 0:05:16 lr: 0.000935 loss: 3.8732 (3.7500) grad_norm: 1.1424 (1.0570) time: 0.6340 [2021-03-26 09:28:40 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 760/1251] eta: 0:05:09 lr: 0.000935 loss: 3.9850 (3.7514) grad_norm: 1.1255 (1.0578) time: 0.6335 [2021-03-26 09:28:46 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 770/1251] eta: 0:05:03 lr: 0.000935 loss: 3.8849 (3.7505) grad_norm: 1.0690 (1.0571) time: 0.6245 [2021-03-26 09:28:52 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 780/1251] eta: 0:04:57 lr: 0.000935 loss: 3.6884 (3.7482) grad_norm: 1.0648 (1.0580) time: 0.6256 [2021-03-26 09:28:59 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 790/1251] eta: 0:04:50 lr: 0.000935 loss: 3.8469 (3.7498) grad_norm: 1.0648 (1.0577) time: 0.6259 [2021-03-26 09:29:05 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 800/1251] eta: 0:04:44 lr: 0.000935 loss: 3.8469 (3.7478) grad_norm: 1.0253 (1.0579) time: 0.6244 [2021-03-26 09:29:11 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 810/1251] eta: 0:04:38 lr: 0.000935 loss: 3.5262 (3.7445) grad_norm: 1.0629 (1.0584) time: 0.6238 [2021-03-26 09:29:17 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 820/1251] eta: 0:04:31 lr: 0.000935 loss: 3.5264 (3.7442) grad_norm: 0.9771 (1.0573) time: 0.6175 [2021-03-26 09:29:24 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 830/1251] eta: 0:04:25 lr: 0.000935 loss: 3.8953 (3.7437) grad_norm: 0.9771 (1.0571) time: 0.6213 [2021-03-26 09:29:30 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 840/1251] eta: 0:04:19 lr: 0.000935 loss: 3.7397 (3.7435) grad_norm: 1.0380 (1.0577) time: 0.6270 [2021-03-26 09:29:36 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 850/1251] eta: 0:04:12 lr: 0.000935 loss: 3.6600 (3.7448) grad_norm: 1.0380 (1.0582) time: 0.6299 [2021-03-26 09:29:42 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 860/1251] eta: 0:04:06 lr: 0.000934 loss: 3.7094 (3.7437) grad_norm: 1.1504 (1.0603) time: 0.6315 [2021-03-26 09:29:49 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 870/1251] eta: 0:04:00 lr: 0.000934 loss: 3.7905 (3.7448) grad_norm: 1.0976 (1.0601) time: 0.6293 [2021-03-26 09:29:55 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 880/1251] eta: 0:03:53 lr: 0.000934 loss: 3.9405 (3.7476) grad_norm: 1.0805 (1.0609) time: 0.6252 [2021-03-26 09:30:01 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 890/1251] eta: 0:03:47 lr: 0.000934 loss: 3.9228 (3.7486) grad_norm: 1.1158 (1.0620) time: 0.6241 [2021-03-26 09:30:07 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 900/1251] eta: 0:03:41 lr: 0.000934 loss: 3.8071 (3.7486) grad_norm: 1.1034 (inf) time: 0.6198 [2021-03-26 09:30:14 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 910/1251] eta: 0:03:34 lr: 0.000934 loss: 3.8321 (3.7493) grad_norm: 1.0625 (inf) time: 0.6182 [2021-03-26 09:30:20 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 920/1251] eta: 0:03:28 lr: 0.000934 loss: 3.8919 (3.7475) grad_norm: 1.0074 (inf) time: 0.6244 [2021-03-26 09:30:26 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 930/1251] eta: 0:03:22 lr: 0.000934 loss: 3.7956 (3.7480) grad_norm: 1.0090 (inf) time: 0.6250 [2021-03-26 09:30:32 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 940/1251] eta: 0:03:15 lr: 0.000934 loss: 3.6295 (3.7455) grad_norm: 1.1365 (inf) time: 0.6279 [2021-03-26 09:30:39 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 950/1251] eta: 0:03:09 lr: 0.000934 loss: 3.5658 (3.7469) grad_norm: 1.0601 (inf) time: 0.6308 [2021-03-26 09:30:45 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 960/1251] eta: 0:03:03 lr: 0.000934 loss: 3.5930 (3.7451) grad_norm: 1.0231 (inf) time: 0.6210 [2021-03-26 09:30:51 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 970/1251] eta: 0:02:56 lr: 0.000934 loss: 3.5612 (3.7447) grad_norm: 1.0757 (inf) time: 0.6253 [2021-03-26 09:30:57 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 980/1251] eta: 0:02:50 lr: 0.000934 loss: 3.5480 (3.7431) grad_norm: 1.0711 (inf) time: 0.6304 [2021-03-26 09:31:04 swin_base_patch4_window7_224] INFO: Epoch: [49] [ 990/1251] eta: 0:02:44 lr: 0.000934 loss: 3.7911 (3.7457) grad_norm: 1.0870 (inf) time: 0.6251 [2021-03-26 09:31:10 swin_base_patch4_window7_224] INFO: Epoch: [49] [1000/1251] eta: 0:02:38 lr: 0.000934 loss: 4.1739 (3.7476) grad_norm: 1.1467 (inf) time: 0.6296 [2021-03-26 09:31:16 swin_base_patch4_window7_224] INFO: Epoch: [49] [1010/1251] eta: 0:02:31 lr: 0.000934 loss: 3.9255 (3.7466) grad_norm: 1.0173 (inf) time: 0.6317 [2021-03-26 09:31:23 swin_base_patch4_window7_224] INFO: Epoch: [49] [1020/1251] eta: 0:02:25 lr: 0.000934 loss: 3.7184 (3.7460) grad_norm: 1.0201 (inf) time: 0.6287 [2021-03-26 09:31:29 swin_base_patch4_window7_224] INFO: Epoch: [49] [1030/1251] eta: 0:02:19 lr: 0.000934 loss: 3.8784 (3.7459) grad_norm: 1.0134 (inf) time: 0.6262 [2021-03-26 09:31:35 swin_base_patch4_window7_224] INFO: Epoch: [49] [1040/1251] eta: 0:02:12 lr: 0.000934 loss: 3.9645 (3.7470) grad_norm: 0.9836 (inf) time: 0.6286 [2021-03-26 09:31:42 swin_base_patch4_window7_224] INFO: Epoch: [49] [1050/1251] eta: 0:02:06 lr: 0.000934 loss: 3.8427 (3.7464) grad_norm: 1.1058 (inf) time: 0.6347 [2021-03-26 09:31:48 swin_base_patch4_window7_224] INFO: Epoch: [49] [1060/1251] eta: 0:02:00 lr: 0.000934 loss: 3.8427 (3.7467) grad_norm: 1.0695 (inf) time: 0.6320 [2021-03-26 09:31:54 swin_base_patch4_window7_224] INFO: Epoch: [49] [1070/1251] eta: 0:01:53 lr: 0.000934 loss: 3.9495 (3.7488) grad_norm: 1.0025 (inf) time: 0.6215 [2021-03-26 09:32:00 swin_base_patch4_window7_224] INFO: Epoch: [49] [1080/1251] eta: 0:01:47 lr: 0.000934 loss: 3.4899 (3.7440) grad_norm: 0.9556 (inf) time: 0.6183 [2021-03-26 09:32:06 swin_base_patch4_window7_224] INFO: Epoch: [49] [1090/1251] eta: 0:01:41 lr: 0.000934 loss: 3.4529 (3.7445) grad_norm: 1.0466 (inf) time: 0.6223 [2021-03-26 09:32:13 swin_base_patch4_window7_224] INFO: Epoch: [49] [1100/1251] eta: 0:01:35 lr: 0.000934 loss: 3.8527 (3.7462) grad_norm: 1.0932 (inf) time: 0.6241 [2021-03-26 09:32:19 swin_base_patch4_window7_224] INFO: Epoch: [49] [1110/1251] eta: 0:01:28 lr: 0.000934 loss: 3.8469 (3.7469) grad_norm: 1.0932 (inf) time: 0.6225 [2021-03-26 09:32:25 swin_base_patch4_window7_224] INFO: Epoch: [49] [1120/1251] eta: 0:01:22 lr: 0.000934 loss: 3.7501 (3.7444) grad_norm: 1.0220 (inf) time: 0.6205 [2021-03-26 09:32:31 swin_base_patch4_window7_224] INFO: Epoch: [49] [1130/1251] eta: 0:01:16 lr: 0.000934 loss: 3.7501 (3.7438) grad_norm: 1.0481 (inf) time: 0.6276 [2021-03-26 09:32:38 swin_base_patch4_window7_224] INFO: Epoch: [49] [1140/1251] eta: 0:01:09 lr: 0.000934 loss: 3.8707 (3.7452) grad_norm: 1.0481 (inf) time: 0.6260 [2021-03-26 09:32:44 swin_base_patch4_window7_224] INFO: Epoch: [49] [1150/1251] eta: 0:01:03 lr: 0.000934 loss: 3.9561 (3.7478) grad_norm: 1.0218 (inf) time: 0.6175 [2021-03-26 09:32:50 swin_base_patch4_window7_224] INFO: Epoch: [49] [1160/1251] eta: 0:00:57 lr: 0.000934 loss: 3.9657 (3.7489) grad_norm: 0.9886 (inf) time: 0.6193 [2021-03-26 09:32:56 swin_base_patch4_window7_224] INFO: Epoch: [49] [1170/1251] eta: 0:00:50 lr: 0.000934 loss: 3.7943 (3.7480) grad_norm: 0.9886 (inf) time: 0.6170 [2021-03-26 09:33:02 swin_base_patch4_window7_224] INFO: Epoch: [49] [1180/1251] eta: 0:00:44 lr: 0.000934 loss: 3.5812 (3.7462) grad_norm: 1.0331 (inf) time: 0.6176 [2021-03-26 09:33:09 swin_base_patch4_window7_224] INFO: Epoch: [49] [1190/1251] eta: 0:00:38 lr: 0.000934 loss: 3.6380 (3.7465) grad_norm: 1.0637 (inf) time: 0.6241 [2021-03-26 09:33:15 swin_base_patch4_window7_224] INFO: Epoch: [49] [1200/1251] eta: 0:00:32 lr: 0.000934 loss: 3.6380 (3.7459) grad_norm: 1.0137 (inf) time: 0.6254 [2021-03-26 09:33:21 swin_base_patch4_window7_224] INFO: Epoch: [49] [1210/1251] eta: 0:00:25 lr: 0.000934 loss: 3.9637 (3.7483) grad_norm: 1.0137 (inf) time: 0.6223 [2021-03-26 09:33:27 swin_base_patch4_window7_224] INFO: Epoch: [49] [1220/1251] eta: 0:00:19 lr: 0.000934 loss: 3.7300 (3.7438) grad_norm: 1.0552 (inf) time: 0.6206 [2021-03-26 09:33:34 swin_base_patch4_window7_224] INFO: Epoch: [49] [1230/1251] eta: 0:00:13 lr: 0.000934 loss: 3.6291 (3.7452) grad_norm: 1.0744 (inf) time: 0.6292 [2021-03-26 09:33:40 swin_base_patch4_window7_224] INFO: Epoch: [49] [1240/1251] eta: 0:00:06 lr: 0.000934 loss: 4.0395 (3.7479) grad_norm: 1.2274 (inf) time: 0.6344 [2021-03-26 09:33:46 swin_base_patch4_window7_224] INFO: Epoch: [49] [1250/1251] eta: 0:00:00 lr: 0.000934 loss: 4.0395 (3.7502) grad_norm: 1.0795 (inf) time: 0.6258 [2021-03-26 09:33:53 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:06 loss: 1.4211 (1.4211) acc1: 62.5000 (62.5000) acc5: 85.9375 (85.9375) [2021-03-26 09:33:54 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.2587 (1.2765) acc1: 71.8750 (70.5966) acc5: 90.6250 (90.4830) [2021-03-26 09:33:56 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.1896 (1.2788) acc1: 71.8750 (71.2054) acc5: 90.6250 (90.3274) [2021-03-26 09:33:59 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1602 (1.2342) acc1: 73.4375 (71.5726) acc5: 92.1875 (91.1794) [2021-03-26 09:34:01 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2008 (1.2263) acc1: 73.4375 (71.8750) acc5: 90.6250 (91.1966) [2021-03-26 09:34:02 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2008 (1.2231) acc1: 70.3125 (71.6800) acc5: 90.6250 (91.2000) [2021-03-26 09:34:05 swin_base_patch4_window7_224] INFO: * Acc@1 72.780 Acc@5 91.746 loss 1.188 [2021-03-26 09:34:05 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 72.8% [2021-03-26 09:34:05 swin_base_patch4_window7_224] INFO: Max accuracy: 72.78% [2021-03-26 09:34:10 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 0/1251] eta: 1:32:13 lr: 0.000934 loss: 3.4259 (3.4259) grad_norm: 1.0702 (1.0702) time: 4.4236 [2021-03-26 09:34:16 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 10/1251] eta: 0:20:11 lr: 0.000934 loss: 3.5426 (3.6412) grad_norm: 1.1636 (1.1607) time: 0.9764 [2021-03-26 09:34:22 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 20/1251] eta: 0:16:47 lr: 0.000934 loss: 3.5762 (3.7326) grad_norm: 1.1734 (1.1850) time: 0.6378 [2021-03-26 09:34:29 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 30/1251] eta: 0:15:20 lr: 0.000934 loss: 3.7768 (3.7286) grad_norm: 1.1734 (1.1563) time: 0.6320 [2021-03-26 09:34:35 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 40/1251] eta: 0:14:36 lr: 0.000934 loss: 3.6484 (3.6926) grad_norm: 1.0230 (1.1250) time: 0.6252 [2021-03-26 09:34:41 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 50/1251] eta: 0:14:09 lr: 0.000934 loss: 3.3852 (3.6716) grad_norm: 1.0230 (1.1191) time: 0.6338 [2021-03-26 09:34:48 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 60/1251] eta: 0:13:45 lr: 0.000934 loss: 3.8790 (3.7250) grad_norm: 1.0836 (1.1180) time: 0.6300 [2021-03-26 09:34:54 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 70/1251] eta: 0:13:28 lr: 0.000934 loss: 3.8998 (3.7262) grad_norm: 1.0646 (1.1078) time: 0.6266 [2021-03-26 09:35:00 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 80/1251] eta: 0:13:12 lr: 0.000934 loss: 3.6215 (3.7158) grad_norm: 1.0630 (1.1073) time: 0.6271 [2021-03-26 09:35:06 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 90/1251] eta: 0:12:58 lr: 0.000933 loss: 3.7105 (3.7341) grad_norm: 1.0862 (1.1089) time: 0.6229 [2021-03-26 09:35:13 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 100/1251] eta: 0:12:46 lr: 0.000933 loss: 3.9722 (3.7102) grad_norm: 1.0912 (1.1166) time: 0.6233 [2021-03-26 09:35:19 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 110/1251] eta: 0:12:35 lr: 0.000933 loss: 3.8633 (3.7297) grad_norm: 1.0591 (1.1103) time: 0.6222 [2021-03-26 09:35:25 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 120/1251] eta: 0:12:25 lr: 0.000933 loss: 4.0073 (3.7610) grad_norm: 1.0209 (1.1049) time: 0.6245 [2021-03-26 09:35:32 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 130/1251] eta: 0:12:17 lr: 0.000933 loss: 3.7590 (3.7427) grad_norm: 1.0246 (1.1031) time: 0.6343 [2021-03-26 09:35:38 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 140/1251] eta: 0:12:08 lr: 0.000933 loss: 3.7469 (3.7623) grad_norm: 1.0218 (1.0953) time: 0.6309 [2021-03-26 09:35:44 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 150/1251] eta: 0:11:58 lr: 0.000933 loss: 3.9463 (3.7619) grad_norm: 0.9953 (1.0936) time: 0.6188 [2021-03-26 09:35:50 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 160/1251] eta: 0:11:49 lr: 0.000933 loss: 3.6829 (3.7578) grad_norm: 1.0379 (1.0879) time: 0.6177 [2021-03-26 09:35:56 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 170/1251] eta: 0:11:41 lr: 0.000933 loss: 3.9345 (3.7668) grad_norm: 1.0342 (1.0852) time: 0.6207 [2021-03-26 09:36:03 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 180/1251] eta: 0:11:33 lr: 0.000933 loss: 3.7560 (3.7586) grad_norm: 1.0687 (1.0863) time: 0.6230 [2021-03-26 09:36:09 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 190/1251] eta: 0:11:26 lr: 0.000933 loss: 3.7560 (3.7678) grad_norm: 1.0109 (1.0817) time: 0.6329 [2021-03-26 09:36:15 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 200/1251] eta: 0:11:18 lr: 0.000933 loss: 3.8758 (3.7546) grad_norm: 0.9681 (1.0750) time: 0.6273 [2021-03-26 09:36:21 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 210/1251] eta: 0:11:11 lr: 0.000933 loss: 3.8150 (3.7528) grad_norm: 0.9981 (1.0784) time: 0.6230 [2021-03-26 09:36:28 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 220/1251] eta: 0:11:04 lr: 0.000933 loss: 3.7996 (3.7514) grad_norm: 1.0547 (1.0768) time: 0.6346 [2021-03-26 09:36:34 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 230/1251] eta: 0:10:57 lr: 0.000933 loss: 3.7996 (3.7531) grad_norm: 1.0333 (1.0763) time: 0.6319 [2021-03-26 09:36:40 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 240/1251] eta: 0:10:50 lr: 0.000933 loss: 3.8659 (3.7582) grad_norm: 1.0282 (1.0769) time: 0.6257 [2021-03-26 09:36:46 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 250/1251] eta: 0:10:42 lr: 0.000933 loss: 3.7065 (3.7480) grad_norm: 1.0177 (1.0772) time: 0.6204 [2021-03-26 09:36:53 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 260/1251] eta: 0:10:35 lr: 0.000933 loss: 3.7065 (3.7534) grad_norm: 1.0157 (1.0742) time: 0.6171 [2021-03-26 09:36:59 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 270/1251] eta: 0:10:28 lr: 0.000933 loss: 4.0848 (3.7585) grad_norm: 1.0299 (1.0771) time: 0.6194 [2021-03-26 09:37:05 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 280/1251] eta: 0:10:20 lr: 0.000933 loss: 4.0560 (3.7618) grad_norm: 1.0299 (1.0755) time: 0.6181 [2021-03-26 09:37:11 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 290/1251] eta: 0:10:14 lr: 0.000933 loss: 3.7885 (3.7567) grad_norm: 1.0261 (1.0749) time: 0.6234 [2021-03-26 09:37:17 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 300/1251] eta: 0:10:06 lr: 0.000933 loss: 3.7333 (3.7455) grad_norm: 0.9921 (1.0729) time: 0.6224 [2021-03-26 09:37:24 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 310/1251] eta: 0:10:00 lr: 0.000933 loss: 3.8021 (3.7594) grad_norm: 1.0751 (1.0751) time: 0.6188 [2021-03-26 09:37:30 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 320/1251] eta: 0:09:53 lr: 0.000933 loss: 4.0259 (3.7641) grad_norm: 1.1672 (1.0788) time: 0.6296 [2021-03-26 09:37:36 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 330/1251] eta: 0:09:47 lr: 0.000933 loss: 4.0074 (3.7724) grad_norm: 1.1184 (1.0796) time: 0.6302 [2021-03-26 09:37:43 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 340/1251] eta: 0:09:40 lr: 0.000933 loss: 3.8924 (3.7714) grad_norm: 1.0136 (1.0775) time: 0.6224 [2021-03-26 09:37:49 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 350/1251] eta: 0:09:33 lr: 0.000933 loss: 3.8828 (3.7831) grad_norm: 1.0136 (1.0765) time: 0.6196 [2021-03-26 09:37:55 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 360/1251] eta: 0:09:26 lr: 0.000933 loss: 3.9011 (3.7864) grad_norm: 1.0199 (1.0761) time: 0.6199 [2021-03-26 09:38:01 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 370/1251] eta: 0:09:19 lr: 0.000933 loss: 3.8474 (3.7818) grad_norm: 1.0846 (1.0773) time: 0.6212 [2021-03-26 09:38:08 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 380/1251] eta: 0:09:13 lr: 0.000933 loss: 3.8201 (3.7833) grad_norm: 1.1341 (1.0783) time: 0.6292 [2021-03-26 09:38:14 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 390/1251] eta: 0:09:06 lr: 0.000933 loss: 3.8896 (3.7826) grad_norm: 1.0605 (1.0772) time: 0.6283 [2021-03-26 09:38:20 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 400/1251] eta: 0:09:00 lr: 0.000933 loss: 3.8578 (3.7861) grad_norm: 1.0456 (1.0775) time: 0.6211 [2021-03-26 09:38:26 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 410/1251] eta: 0:08:53 lr: 0.000933 loss: 3.7477 (3.7831) grad_norm: 1.0644 (1.0774) time: 0.6217 [2021-03-26 09:38:32 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 420/1251] eta: 0:08:47 lr: 0.000933 loss: 3.7586 (3.7869) grad_norm: 1.1326 (1.0794) time: 0.6254 [2021-03-26 09:38:39 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 430/1251] eta: 0:08:40 lr: 0.000933 loss: 4.0521 (3.7925) grad_norm: 1.0821 (1.0779) time: 0.6272 [2021-03-26 09:38:45 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 440/1251] eta: 0:08:34 lr: 0.000933 loss: 3.9541 (3.7897) grad_norm: 1.0289 (1.0779) time: 0.6257 [2021-03-26 09:38:51 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 450/1251] eta: 0:08:27 lr: 0.000933 loss: 3.9154 (3.7895) grad_norm: 1.0304 (1.0772) time: 0.6221 [2021-03-26 09:38:57 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 460/1251] eta: 0:08:21 lr: 0.000933 loss: 3.8271 (3.7898) grad_norm: 1.0801 (1.0778) time: 0.6251 [2021-03-26 09:39:04 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 470/1251] eta: 0:08:14 lr: 0.000933 loss: 3.8361 (3.7896) grad_norm: 1.0805 (1.0783) time: 0.6300 [2021-03-26 09:39:10 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 480/1251] eta: 0:08:08 lr: 0.000933 loss: 3.8361 (3.7865) grad_norm: 1.0673 (1.0794) time: 0.6256 [2021-03-26 09:39:16 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 490/1251] eta: 0:08:01 lr: 0.000933 loss: 3.6413 (3.7801) grad_norm: 1.1149 (1.0800) time: 0.6307 [2021-03-26 09:39:23 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 500/1251] eta: 0:07:55 lr: 0.000933 loss: 3.6802 (3.7829) grad_norm: 1.0489 (1.0791) time: 0.6332 [2021-03-26 09:39:29 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 510/1251] eta: 0:07:49 lr: 0.000933 loss: 4.0078 (3.7826) grad_norm: 0.9833 (1.0780) time: 0.6255 [2021-03-26 09:39:35 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 520/1251] eta: 0:07:42 lr: 0.000933 loss: 3.7287 (3.7783) grad_norm: 1.1105 (1.0800) time: 0.6266 [2021-03-26 09:39:41 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 530/1251] eta: 0:07:36 lr: 0.000933 loss: 3.7363 (3.7814) grad_norm: 1.1006 (1.0792) time: 0.6272 [2021-03-26 09:39:48 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 540/1251] eta: 0:07:29 lr: 0.000933 loss: 3.9756 (3.7824) grad_norm: 1.0702 (1.0791) time: 0.6220 [2021-03-26 09:39:54 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 550/1251] eta: 0:07:23 lr: 0.000933 loss: 3.9756 (3.7868) grad_norm: 1.0570 (1.0785) time: 0.6309 [2021-03-26 09:40:00 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 560/1251] eta: 0:07:17 lr: 0.000933 loss: 3.8550 (3.7841) grad_norm: 1.0211 (1.0793) time: 0.6417 [2021-03-26 09:40:07 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 570/1251] eta: 0:07:10 lr: 0.000932 loss: 3.7888 (3.7856) grad_norm: 1.0445 (1.0784) time: 0.6342 [2021-03-26 09:40:13 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 580/1251] eta: 0:07:04 lr: 0.000932 loss: 3.9468 (3.7862) grad_norm: 0.9650 (1.0766) time: 0.6215 [2021-03-26 09:40:19 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 590/1251] eta: 0:06:58 lr: 0.000932 loss: 3.7961 (3.7848) grad_norm: 0.9577 (1.0753) time: 0.6222 [2021-03-26 09:40:25 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 600/1251] eta: 0:06:51 lr: 0.000932 loss: 3.5457 (3.7823) grad_norm: 0.9877 (1.0749) time: 0.6250 [2021-03-26 09:40:32 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 610/1251] eta: 0:06:45 lr: 0.000932 loss: 3.6309 (3.7808) grad_norm: 1.0851 (1.0757) time: 0.6239 [2021-03-26 09:40:38 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 620/1251] eta: 0:06:38 lr: 0.000932 loss: 3.8702 (3.7783) grad_norm: 1.0157 (1.0744) time: 0.6256 [2021-03-26 09:40:44 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 630/1251] eta: 0:06:32 lr: 0.000932 loss: 3.8015 (3.7783) grad_norm: 0.9661 (1.0727) time: 0.6233 [2021-03-26 09:40:50 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 640/1251] eta: 0:06:26 lr: 0.000932 loss: 3.7666 (3.7776) grad_norm: 0.9813 (1.0718) time: 0.6234 [2021-03-26 09:40:57 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 650/1251] eta: 0:06:19 lr: 0.000932 loss: 3.7223 (3.7749) grad_norm: 0.9843 (1.0717) time: 0.6262 [2021-03-26 09:41:03 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 660/1251] eta: 0:06:13 lr: 0.000932 loss: 3.7439 (3.7765) grad_norm: 1.0803 (1.0740) time: 0.6299 [2021-03-26 09:41:09 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 670/1251] eta: 0:06:06 lr: 0.000932 loss: 3.8666 (3.7755) grad_norm: 1.1688 (1.0746) time: 0.6267 [2021-03-26 09:41:15 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 680/1251] eta: 0:06:00 lr: 0.000932 loss: 3.9799 (3.7779) grad_norm: 1.0814 (1.0742) time: 0.6190 [2021-03-26 09:41:22 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 690/1251] eta: 0:05:54 lr: 0.000932 loss: 3.9916 (3.7792) grad_norm: 1.0408 (1.0742) time: 0.6176 [2021-03-26 09:41:28 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 700/1251] eta: 0:05:47 lr: 0.000932 loss: 3.6803 (3.7763) grad_norm: 1.0154 (1.0753) time: 0.6202 [2021-03-26 09:41:34 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 710/1251] eta: 0:05:41 lr: 0.000932 loss: 3.7974 (3.7766) grad_norm: 1.0490 (1.0752) time: 0.6235 [2021-03-26 09:41:40 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 720/1251] eta: 0:05:34 lr: 0.000932 loss: 3.9076 (3.7805) grad_norm: 1.0688 (1.0761) time: 0.6253 [2021-03-26 09:41:46 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 730/1251] eta: 0:05:28 lr: 0.000932 loss: 3.9076 (3.7775) grad_norm: 1.0415 (1.0762) time: 0.6225 [2021-03-26 09:41:53 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 740/1251] eta: 0:05:22 lr: 0.000932 loss: 3.5406 (3.7774) grad_norm: 1.0057 (1.0757) time: 0.6264 [2021-03-26 09:41:59 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 750/1251] eta: 0:05:16 lr: 0.000932 loss: 3.6808 (3.7748) grad_norm: 1.0402 (1.0758) time: 0.6340 [2021-03-26 09:42:06 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 760/1251] eta: 0:05:09 lr: 0.000932 loss: 3.8479 (3.7780) grad_norm: 1.0942 (1.0769) time: 0.6347 [2021-03-26 09:42:12 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 770/1251] eta: 0:05:03 lr: 0.000932 loss: 4.0603 (3.7788) grad_norm: 1.0681 (1.0759) time: 0.6326 [2021-03-26 09:42:18 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 780/1251] eta: 0:04:57 lr: 0.000932 loss: 3.9322 (3.7809) grad_norm: 1.0060 (1.0769) time: 0.6324 [2021-03-26 09:42:24 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 790/1251] eta: 0:04:50 lr: 0.000932 loss: 4.1548 (3.7858) grad_norm: 1.0143 (1.0756) time: 0.6339 [2021-03-26 09:42:31 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 800/1251] eta: 0:04:44 lr: 0.000932 loss: 3.9309 (3.7849) grad_norm: 1.0061 (1.0755) time: 0.6323 [2021-03-26 09:42:37 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 810/1251] eta: 0:04:38 lr: 0.000932 loss: 3.7267 (3.7841) grad_norm: 1.0039 (1.0750) time: 0.6268 [2021-03-26 09:42:43 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 820/1251] eta: 0:04:31 lr: 0.000932 loss: 3.8905 (3.7875) grad_norm: 0.9944 (1.0746) time: 0.6213 [2021-03-26 09:42:50 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 830/1251] eta: 0:04:25 lr: 0.000932 loss: 3.8905 (3.7866) grad_norm: 1.0294 (1.0742) time: 0.6243 [2021-03-26 09:42:56 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 840/1251] eta: 0:04:19 lr: 0.000932 loss: 3.7198 (3.7870) grad_norm: 1.0294 (1.0742) time: 0.6299 [2021-03-26 09:43:02 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 850/1251] eta: 0:04:12 lr: 0.000932 loss: 3.8000 (3.7864) grad_norm: 1.0727 (1.0745) time: 0.6308 [2021-03-26 09:43:08 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 860/1251] eta: 0:04:06 lr: 0.000932 loss: 3.7106 (3.7843) grad_norm: 1.0664 (1.0743) time: 0.6272 [2021-03-26 09:43:15 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 870/1251] eta: 0:04:00 lr: 0.000932 loss: 3.7106 (3.7858) grad_norm: 1.0789 (1.0747) time: 0.6262 [2021-03-26 09:43:21 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 880/1251] eta: 0:03:53 lr: 0.000932 loss: 3.9765 (3.7866) grad_norm: 1.0465 (1.0744) time: 0.6229 [2021-03-26 09:43:27 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 890/1251] eta: 0:03:47 lr: 0.000932 loss: 3.9765 (3.7879) grad_norm: 1.0262 (1.0741) time: 0.6212 [2021-03-26 09:43:33 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 900/1251] eta: 0:03:41 lr: 0.000932 loss: 4.0216 (3.7894) grad_norm: 1.0698 (1.0737) time: 0.6227 [2021-03-26 09:43:40 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 910/1251] eta: 0:03:34 lr: 0.000932 loss: 3.8206 (3.7877) grad_norm: 1.0433 (1.0736) time: 0.6223 [2021-03-26 09:43:46 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 920/1251] eta: 0:03:28 lr: 0.000932 loss: 3.7139 (3.7850) grad_norm: 1.0433 (1.0742) time: 0.6261 [2021-03-26 09:43:52 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 930/1251] eta: 0:03:22 lr: 0.000932 loss: 3.7280 (3.7842) grad_norm: 1.0466 (1.0740) time: 0.6272 [2021-03-26 09:43:58 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 940/1251] eta: 0:03:15 lr: 0.000932 loss: 3.8578 (3.7844) grad_norm: 1.0430 (1.0736) time: 0.6265 [2021-03-26 09:44:05 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 950/1251] eta: 0:03:09 lr: 0.000932 loss: 3.9096 (3.7839) grad_norm: 1.0582 (1.0731) time: 0.6255 [2021-03-26 09:44:11 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 960/1251] eta: 0:03:03 lr: 0.000932 loss: 4.0309 (3.7861) grad_norm: 1.0164 (1.0724) time: 0.6240 [2021-03-26 09:44:17 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 970/1251] eta: 0:02:57 lr: 0.000932 loss: 3.9332 (3.7833) grad_norm: 0.9802 (1.0712) time: 0.6251 [2021-03-26 09:44:23 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 980/1251] eta: 0:02:50 lr: 0.000932 loss: 3.6876 (3.7813) grad_norm: 0.9805 (1.0714) time: 0.6242 [2021-03-26 09:44:30 swin_base_patch4_window7_224] INFO: Epoch: [50] [ 990/1251] eta: 0:02:44 lr: 0.000932 loss: 3.7298 (3.7816) grad_norm: 0.9805 (1.0706) time: 0.6201 [2021-03-26 09:44:36 swin_base_patch4_window7_224] INFO: Epoch: [50] [1000/1251] eta: 0:02:38 lr: 0.000932 loss: 3.7874 (3.7804) grad_norm: 0.9691 (1.0699) time: 0.6169 [2021-03-26 09:44:42 swin_base_patch4_window7_224] INFO: Epoch: [50] [1010/1251] eta: 0:02:31 lr: 0.000932 loss: 3.7874 (3.7814) grad_norm: 1.0675 (1.0708) time: 0.6319 [2021-03-26 09:44:48 swin_base_patch4_window7_224] INFO: Epoch: [50] [1020/1251] eta: 0:02:25 lr: 0.000932 loss: 3.8783 (3.7817) grad_norm: 1.0772 (1.0709) time: 0.6361 [2021-03-26 09:44:55 swin_base_patch4_window7_224] INFO: Epoch: [50] [1030/1251] eta: 0:02:19 lr: 0.000932 loss: 3.6701 (3.7800) grad_norm: 1.0177 (1.0703) time: 0.6222 [2021-03-26 09:45:01 swin_base_patch4_window7_224] INFO: Epoch: [50] [1040/1251] eta: 0:02:12 lr: 0.000932 loss: 3.6701 (3.7798) grad_norm: 0.9850 (1.0698) time: 0.6193 [2021-03-26 09:45:07 swin_base_patch4_window7_224] INFO: Epoch: [50] [1050/1251] eta: 0:02:06 lr: 0.000931 loss: 3.7244 (3.7774) grad_norm: 1.0108 (1.0701) time: 0.6215 [2021-03-26 09:45:13 swin_base_patch4_window7_224] INFO: Epoch: [50] [1060/1251] eta: 0:02:00 lr: 0.000931 loss: 3.7695 (3.7767) grad_norm: 1.0453 (1.0693) time: 0.6255 [2021-03-26 09:45:20 swin_base_patch4_window7_224] INFO: Epoch: [50] [1070/1251] eta: 0:01:53 lr: 0.000931 loss: 3.8785 (3.7771) grad_norm: 1.0175 (1.0694) time: 0.6239 [2021-03-26 09:45:26 swin_base_patch4_window7_224] INFO: Epoch: [50] [1080/1251] eta: 0:01:47 lr: 0.000931 loss: 3.7463 (3.7760) grad_norm: 0.9969 (1.0686) time: 0.6234 [2021-03-26 09:45:32 swin_base_patch4_window7_224] INFO: Epoch: [50] [1090/1251] eta: 0:01:41 lr: 0.000931 loss: 3.8712 (3.7768) grad_norm: 0.9629 (1.0676) time: 0.6238 [2021-03-26 09:45:38 swin_base_patch4_window7_224] INFO: Epoch: [50] [1100/1251] eta: 0:01:35 lr: 0.000931 loss: 3.9237 (3.7765) grad_norm: 1.0050 (1.0679) time: 0.6287 [2021-03-26 09:45:45 swin_base_patch4_window7_224] INFO: Epoch: [50] [1110/1251] eta: 0:01:28 lr: 0.000931 loss: 3.9971 (3.7774) grad_norm: 1.0954 (1.0683) time: 0.6343 [2021-03-26 09:45:51 swin_base_patch4_window7_224] INFO: Epoch: [50] [1120/1251] eta: 0:01:22 lr: 0.000931 loss: 4.0924 (3.7811) grad_norm: 1.0909 (1.0687) time: 0.6289 [2021-03-26 09:45:57 swin_base_patch4_window7_224] INFO: Epoch: [50] [1130/1251] eta: 0:01:16 lr: 0.000931 loss: 4.0393 (3.7810) grad_norm: 1.0096 (1.0680) time: 0.6214 [2021-03-26 09:46:03 swin_base_patch4_window7_224] INFO: Epoch: [50] [1140/1251] eta: 0:01:09 lr: 0.000931 loss: 3.8094 (3.7809) grad_norm: 0.9689 (1.0674) time: 0.6172 [2021-03-26 09:46:10 swin_base_patch4_window7_224] INFO: Epoch: [50] [1150/1251] eta: 0:01:03 lr: 0.000931 loss: 3.8094 (3.7805) grad_norm: 0.9951 (1.0671) time: 0.6202 [2021-03-26 09:46:16 swin_base_patch4_window7_224] INFO: Epoch: [50] [1160/1251] eta: 0:00:57 lr: 0.000931 loss: 3.7718 (3.7795) grad_norm: 1.0384 (1.0671) time: 0.6226 [2021-03-26 09:46:22 swin_base_patch4_window7_224] INFO: Epoch: [50] [1170/1251] eta: 0:00:50 lr: 0.000931 loss: 3.8756 (3.7792) grad_norm: 1.0384 (1.0681) time: 0.6227 [2021-03-26 09:46:28 swin_base_patch4_window7_224] INFO: Epoch: [50] [1180/1251] eta: 0:00:44 lr: 0.000931 loss: 3.9620 (3.7794) grad_norm: 1.0618 (1.0679) time: 0.6264 [2021-03-26 09:46:34 swin_base_patch4_window7_224] INFO: Epoch: [50] [1190/1251] eta: 0:00:38 lr: 0.000931 loss: 3.9608 (3.7808) grad_norm: 1.0118 (1.0672) time: 0.6232 [2021-03-26 09:46:41 swin_base_patch4_window7_224] INFO: Epoch: [50] [1200/1251] eta: 0:00:32 lr: 0.000931 loss: 3.9608 (3.7791) grad_norm: 0.9461 (1.0671) time: 0.6250 [2021-03-26 09:46:47 swin_base_patch4_window7_224] INFO: Epoch: [50] [1210/1251] eta: 0:00:25 lr: 0.000931 loss: 4.0253 (3.7806) grad_norm: 0.9376 (1.0662) time: 0.6300 [2021-03-26 09:46:53 swin_base_patch4_window7_224] INFO: Epoch: [50] [1220/1251] eta: 0:00:19 lr: 0.000931 loss: 4.0391 (3.7809) grad_norm: 0.9345 (1.0655) time: 0.6226 [2021-03-26 09:46:59 swin_base_patch4_window7_224] INFO: Epoch: [50] [1230/1251] eta: 0:00:13 lr: 0.000931 loss: 3.7243 (3.7794) grad_norm: 1.0523 (1.0659) time: 0.6209 [2021-03-26 09:47:06 swin_base_patch4_window7_224] INFO: Epoch: [50] [1240/1251] eta: 0:00:06 lr: 0.000931 loss: 3.8799 (3.7810) grad_norm: 1.0918 (1.0658) time: 0.6250 [2021-03-26 09:47:12 swin_base_patch4_window7_224] INFO: Epoch: [50] [1250/1251] eta: 0:00:00 lr: 0.000931 loss: 3.9117 (3.7804) grad_norm: 1.1078 (1.0672) time: 0.6204 [2021-03-26 09:48:22 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:15 loss: 1.1422 (1.1422) acc1: 76.5625 (76.5625) acc5: 90.6250 (90.6250) [2021-03-26 09:48:24 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:11 loss: 1.0932 (1.1427) acc1: 76.5625 (74.4318) acc5: 92.1875 (91.9034) [2021-03-26 09:48:25 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:06 loss: 1.0871 (1.1673) acc1: 75.0000 (73.1399) acc5: 92.1875 (91.9643) [2021-03-26 09:48:26 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.1252 (1.1620) acc1: 75.0000 (73.2863) acc5: 92.1875 (91.8851) [2021-03-26 09:48:28 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.1561 (1.1559) acc1: 73.4375 (73.1707) acc5: 92.1875 (92.2256) [2021-03-26 09:48:29 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1650 (1.1640) acc1: 71.8750 (73.1200) acc5: 93.7500 (92.2240) [2021-03-26 09:48:33 swin_base_patch4_window7_224] INFO: * Acc@1 73.016 Acc@5 91.998 loss 1.148 [2021-03-26 09:48:33 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.0% [2021-03-26 09:48:33 swin_base_patch4_window7_224] INFO: Max accuracy: 73.02% [2021-03-26 09:48:37 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 0/1251] eta: 1:29:30 lr: 0.000931 loss: 2.4309 (2.4309) grad_norm: 1.1073 (1.1073) time: 4.2927 [2021-03-26 09:48:43 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 10/1251] eta: 0:20:15 lr: 0.000931 loss: 3.8154 (3.7322) grad_norm: 1.1291 (1.1315) time: 0.9796 [2021-03-26 09:48:50 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 20/1251] eta: 0:16:35 lr: 0.000931 loss: 3.8330 (3.6629) grad_norm: 1.1407 (1.1227) time: 0.6349 [2021-03-26 09:48:56 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 30/1251] eta: 0:15:13 lr: 0.000931 loss: 3.8499 (3.7256) grad_norm: 1.0859 (1.1119) time: 0.6204 [2021-03-26 09:49:02 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 40/1251] eta: 0:14:28 lr: 0.000931 loss: 3.8069 (3.6983) grad_norm: 0.9879 (1.0866) time: 0.6201 [2021-03-26 09:49:08 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 50/1251] eta: 0:13:58 lr: 0.000931 loss: 3.8069 (3.7339) grad_norm: 0.9555 (1.0708) time: 0.6210 [2021-03-26 09:49:14 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 60/1251] eta: 0:13:38 lr: 0.000931 loss: 3.7551 (3.6932) grad_norm: 0.9970 (1.0622) time: 0.6255 [2021-03-26 09:49:21 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 70/1251] eta: 0:13:18 lr: 0.000931 loss: 3.7551 (3.7257) grad_norm: 0.9945 (1.0553) time: 0.6208 [2021-03-26 09:49:27 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 80/1251] eta: 0:13:04 lr: 0.000931 loss: 3.9943 (3.7484) grad_norm: 0.9938 (1.0545) time: 0.6171 [2021-03-26 09:49:33 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 90/1251] eta: 0:12:51 lr: 0.000931 loss: 3.9730 (3.7598) grad_norm: 1.0120 (1.0561) time: 0.6223 [2021-03-26 09:49:39 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 100/1251] eta: 0:12:39 lr: 0.000931 loss: 3.8567 (3.7740) grad_norm: 1.0208 (1.0570) time: 0.6203 [2021-03-26 09:49:45 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 110/1251] eta: 0:12:29 lr: 0.000931 loss: 3.8887 (3.7837) grad_norm: 1.0246 (1.0538) time: 0.6211 [2021-03-26 09:49:52 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 120/1251] eta: 0:12:19 lr: 0.000931 loss: 3.8381 (3.7686) grad_norm: 1.0375 (1.0641) time: 0.6215 [2021-03-26 09:49:58 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 130/1251] eta: 0:12:10 lr: 0.000931 loss: 3.9069 (3.7884) grad_norm: 1.0729 (1.0654) time: 0.6226 [2021-03-26 09:50:04 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 140/1251] eta: 0:12:01 lr: 0.000931 loss: 3.7637 (3.7677) grad_norm: 1.0612 (1.0638) time: 0.6237 [2021-03-26 09:50:11 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 150/1251] eta: 0:11:54 lr: 0.000931 loss: 3.4709 (3.7533) grad_norm: 1.0601 (1.0629) time: 0.6296 [2021-03-26 09:50:17 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 160/1251] eta: 0:11:45 lr: 0.000931 loss: 3.7812 (3.7719) grad_norm: 1.0749 (1.0662) time: 0.6286 [2021-03-26 09:50:23 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 170/1251] eta: 0:11:37 lr: 0.000931 loss: 3.8391 (3.7646) grad_norm: 1.0348 (1.0660) time: 0.6195 [2021-03-26 09:50:29 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 180/1251] eta: 0:11:29 lr: 0.000931 loss: 3.7530 (3.7626) grad_norm: 1.0375 (1.0679) time: 0.6201 [2021-03-26 09:50:35 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 190/1251] eta: 0:11:22 lr: 0.000931 loss: 3.7530 (3.7638) grad_norm: 1.1547 (1.0777) time: 0.6283 [2021-03-26 09:50:42 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 200/1251] eta: 0:11:15 lr: 0.000931 loss: 3.6562 (3.7679) grad_norm: 1.1882 (1.0837) time: 0.6303 [2021-03-26 09:50:48 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 210/1251] eta: 0:11:07 lr: 0.000931 loss: 3.8371 (3.7702) grad_norm: 1.1296 (1.0832) time: 0.6199 [2021-03-26 09:50:54 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 220/1251] eta: 0:11:00 lr: 0.000931 loss: 3.9101 (3.7766) grad_norm: 1.0369 (1.0815) time: 0.6181 [2021-03-26 09:51:00 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 230/1251] eta: 0:10:53 lr: 0.000931 loss: 3.9048 (3.7673) grad_norm: 1.0689 (1.0829) time: 0.6261 [2021-03-26 09:51:07 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 240/1251] eta: 0:10:46 lr: 0.000931 loss: 3.4080 (3.7576) grad_norm: 1.0630 (1.0802) time: 0.6276 [2021-03-26 09:51:13 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 250/1251] eta: 0:10:39 lr: 0.000931 loss: 3.6156 (3.7523) grad_norm: 0.9979 (1.0772) time: 0.6224 [2021-03-26 09:51:19 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 260/1251] eta: 0:10:32 lr: 0.000931 loss: 3.8890 (3.7619) grad_norm: 0.9979 (1.0765) time: 0.6209 [2021-03-26 09:51:25 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 270/1251] eta: 0:10:25 lr: 0.000930 loss: 3.9913 (3.7674) grad_norm: 1.0350 (1.0752) time: 0.6275 [2021-03-26 09:51:32 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 280/1251] eta: 0:10:18 lr: 0.000930 loss: 3.9307 (3.7645) grad_norm: 1.0322 (1.0732) time: 0.6272 [2021-03-26 09:51:38 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 290/1251] eta: 0:10:11 lr: 0.000930 loss: 3.5595 (3.7570) grad_norm: 1.0031 (1.0714) time: 0.6225 [2021-03-26 09:51:44 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 300/1251] eta: 0:10:05 lr: 0.000930 loss: 3.7171 (3.7619) grad_norm: 0.9766 (1.0712) time: 0.6239 [2021-03-26 09:51:50 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 310/1251] eta: 0:09:58 lr: 0.000930 loss: 3.9172 (3.7563) grad_norm: 1.0717 (1.0743) time: 0.6308 [2021-03-26 09:51:57 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 320/1251] eta: 0:09:51 lr: 0.000930 loss: 3.5765 (3.7541) grad_norm: 1.0717 (1.0740) time: 0.6305 [2021-03-26 09:52:03 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 330/1251] eta: 0:09:45 lr: 0.000930 loss: 3.4010 (3.7469) grad_norm: 1.0559 (1.0719) time: 0.6248 [2021-03-26 09:52:09 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 340/1251] eta: 0:09:38 lr: 0.000930 loss: 3.4010 (3.7464) grad_norm: 1.0097 (1.0722) time: 0.6267 [2021-03-26 09:52:15 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 350/1251] eta: 0:09:31 lr: 0.000930 loss: 3.7489 (3.7450) grad_norm: 0.9985 (1.0719) time: 0.6197 [2021-03-26 09:52:22 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 360/1251] eta: 0:09:25 lr: 0.000930 loss: 3.4661 (3.7353) grad_norm: 0.9883 (1.0700) time: 0.6157 [2021-03-26 09:52:28 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 370/1251] eta: 0:09:18 lr: 0.000930 loss: 3.4284 (3.7384) grad_norm: 0.9887 (1.0691) time: 0.6229 [2021-03-26 09:52:34 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 380/1251] eta: 0:09:12 lr: 0.000930 loss: 4.1483 (3.7508) grad_norm: 1.0261 (1.0699) time: 0.6285 [2021-03-26 09:52:40 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 390/1251] eta: 0:09:05 lr: 0.000930 loss: 4.1483 (3.7458) grad_norm: 1.0737 (1.0698) time: 0.6272 [2021-03-26 09:52:47 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 400/1251] eta: 0:08:59 lr: 0.000930 loss: 3.7142 (3.7422) grad_norm: 1.0672 (1.0695) time: 0.6295 [2021-03-26 09:52:53 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 410/1251] eta: 0:08:52 lr: 0.000930 loss: 3.7477 (3.7410) grad_norm: 1.0518 (1.0705) time: 0.6273 [2021-03-26 09:52:59 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 420/1251] eta: 0:08:45 lr: 0.000930 loss: 3.7912 (3.7456) grad_norm: 1.0466 (1.0699) time: 0.6162 [2021-03-26 09:53:05 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 430/1251] eta: 0:08:39 lr: 0.000930 loss: 3.9599 (3.7497) grad_norm: 1.0461 (1.0702) time: 0.6176 [2021-03-26 09:53:12 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 440/1251] eta: 0:08:33 lr: 0.000930 loss: 3.9248 (3.7497) grad_norm: 1.0932 (1.0728) time: 0.6266 [2021-03-26 09:53:18 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 450/1251] eta: 0:08:26 lr: 0.000930 loss: 3.8865 (3.7505) grad_norm: 1.1262 (1.0732) time: 0.6262 [2021-03-26 09:53:24 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 460/1251] eta: 0:08:20 lr: 0.000930 loss: 3.7448 (3.7431) grad_norm: 1.0167 (1.0719) time: 0.6256 [2021-03-26 09:53:30 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 470/1251] eta: 0:08:13 lr: 0.000930 loss: 3.5716 (3.7416) grad_norm: 1.0506 (1.0727) time: 0.6325 [2021-03-26 09:53:37 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 480/1251] eta: 0:08:07 lr: 0.000930 loss: 3.6060 (3.7406) grad_norm: 1.0894 (1.0732) time: 0.6319 [2021-03-26 09:53:43 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 490/1251] eta: 0:08:01 lr: 0.000930 loss: 3.7612 (3.7406) grad_norm: 1.0229 (1.0727) time: 0.6255 [2021-03-26 09:53:49 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 500/1251] eta: 0:07:54 lr: 0.000930 loss: 4.0232 (3.7485) grad_norm: 1.0860 (1.0733) time: 0.6275 [2021-03-26 09:53:56 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 510/1251] eta: 0:07:48 lr: 0.000930 loss: 4.0948 (3.7515) grad_norm: 1.0860 (1.0732) time: 0.6259 [2021-03-26 09:54:02 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 520/1251] eta: 0:07:41 lr: 0.000930 loss: 3.9029 (3.7490) grad_norm: 1.0493 (1.0729) time: 0.6241 [2021-03-26 09:54:08 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 530/1251] eta: 0:07:35 lr: 0.000930 loss: 3.8391 (3.7517) grad_norm: 1.0493 (1.0729) time: 0.6252 [2021-03-26 09:54:14 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 540/1251] eta: 0:07:29 lr: 0.000930 loss: 3.7873 (3.7508) grad_norm: 1.0811 (1.0735) time: 0.6279 [2021-03-26 09:54:21 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 550/1251] eta: 0:07:22 lr: 0.000930 loss: 3.7651 (3.7494) grad_norm: 1.0378 (1.0729) time: 0.6314 [2021-03-26 09:54:27 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 560/1251] eta: 0:07:16 lr: 0.000930 loss: 3.8164 (3.7502) grad_norm: 1.0227 (1.0729) time: 0.6300 [2021-03-26 09:54:33 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 570/1251] eta: 0:07:10 lr: 0.000930 loss: 3.9079 (3.7497) grad_norm: 1.0777 (1.0736) time: 0.6385 [2021-03-26 09:54:40 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 580/1251] eta: 0:07:03 lr: 0.000930 loss: 3.8196 (3.7505) grad_norm: 1.0677 (1.0728) time: 0.6376 [2021-03-26 09:54:46 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 590/1251] eta: 0:06:57 lr: 0.000930 loss: 3.8965 (3.7508) grad_norm: 1.0411 (1.0729) time: 0.6270 [2021-03-26 09:54:52 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 600/1251] eta: 0:06:51 lr: 0.000930 loss: 3.6814 (3.7487) grad_norm: 1.0399 (1.0725) time: 0.6252 [2021-03-26 09:54:59 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 610/1251] eta: 0:06:44 lr: 0.000930 loss: 3.6899 (3.7512) grad_norm: 1.0501 (1.0747) time: 0.6289 [2021-03-26 09:55:05 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 620/1251] eta: 0:06:38 lr: 0.000930 loss: 4.0338 (3.7540) grad_norm: 1.0930 (1.0756) time: 0.6299 [2021-03-26 09:55:11 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 630/1251] eta: 0:06:32 lr: 0.000930 loss: 3.5838 (3.7470) grad_norm: 1.0649 (1.0748) time: 0.6269 [2021-03-26 09:55:17 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 640/1251] eta: 0:06:25 lr: 0.000930 loss: 3.4869 (3.7449) grad_norm: 1.0547 (1.0765) time: 0.6208 [2021-03-26 09:55:24 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 650/1251] eta: 0:06:19 lr: 0.000930 loss: 3.9149 (3.7464) grad_norm: 1.0413 (1.0763) time: 0.6278 [2021-03-26 09:55:30 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 660/1251] eta: 0:06:13 lr: 0.000930 loss: 3.8669 (3.7474) grad_norm: 1.0413 (inf) time: 0.6314 [2021-03-26 09:55:36 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 670/1251] eta: 0:06:06 lr: 0.000930 loss: 3.8484 (3.7487) grad_norm: 1.0269 (inf) time: 0.6204 [2021-03-26 09:55:42 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 680/1251] eta: 0:06:00 lr: 0.000930 loss: 3.8484 (3.7494) grad_norm: 0.9895 (inf) time: 0.6201 [2021-03-26 09:55:48 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 690/1251] eta: 0:05:53 lr: 0.000930 loss: 3.7630 (3.7501) grad_norm: 0.9953 (inf) time: 0.6190 [2021-03-26 09:55:55 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 700/1251] eta: 0:05:47 lr: 0.000930 loss: 3.6962 (3.7489) grad_norm: 1.0225 (inf) time: 0.6212 [2021-03-26 09:56:01 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 710/1251] eta: 0:05:41 lr: 0.000930 loss: 3.4466 (3.7452) grad_norm: 1.0496 (inf) time: 0.6281 [2021-03-26 09:56:07 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 720/1251] eta: 0:05:34 lr: 0.000930 loss: 3.7524 (3.7455) grad_norm: 1.0635 (inf) time: 0.6288 [2021-03-26 09:56:14 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 730/1251] eta: 0:05:28 lr: 0.000930 loss: 3.6917 (3.7418) grad_norm: 1.0883 (inf) time: 0.6274 [2021-03-26 09:56:20 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 740/1251] eta: 0:05:22 lr: 0.000929 loss: 3.7092 (3.7395) grad_norm: 1.0427 (inf) time: 0.6276 [2021-03-26 09:56:26 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 750/1251] eta: 0:05:15 lr: 0.000929 loss: 3.7092 (3.7379) grad_norm: 1.0427 (inf) time: 0.6316 [2021-03-26 09:56:32 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 760/1251] eta: 0:05:09 lr: 0.000929 loss: 3.6249 (3.7373) grad_norm: 1.0418 (inf) time: 0.6281 [2021-03-26 09:56:39 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 770/1251] eta: 0:05:03 lr: 0.000929 loss: 3.6984 (3.7355) grad_norm: 0.9837 (inf) time: 0.6221 [2021-03-26 09:56:45 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 780/1251] eta: 0:04:56 lr: 0.000929 loss: 3.9943 (3.7400) grad_norm: 1.0056 (inf) time: 0.6225 [2021-03-26 09:56:51 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 790/1251] eta: 0:04:50 lr: 0.000929 loss: 3.7681 (3.7376) grad_norm: 0.9847 (inf) time: 0.6242 [2021-03-26 09:56:57 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 800/1251] eta: 0:04:44 lr: 0.000929 loss: 3.7645 (3.7397) grad_norm: 0.9391 (inf) time: 0.6249 [2021-03-26 09:57:04 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 810/1251] eta: 0:04:37 lr: 0.000929 loss: 4.0057 (3.7423) grad_norm: 1.1053 (inf) time: 0.6224 [2021-03-26 09:57:10 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 820/1251] eta: 0:04:31 lr: 0.000929 loss: 3.9917 (3.7429) grad_norm: 1.0659 (inf) time: 0.6223 [2021-03-26 09:57:16 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 830/1251] eta: 0:04:25 lr: 0.000929 loss: 3.8649 (3.7434) grad_norm: 1.0768 (inf) time: 0.6238 [2021-03-26 09:57:22 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 840/1251] eta: 0:04:18 lr: 0.000929 loss: 3.8649 (3.7443) grad_norm: 1.0817 (inf) time: 0.6210 [2021-03-26 09:57:28 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 850/1251] eta: 0:04:12 lr: 0.000929 loss: 3.7655 (3.7424) grad_norm: 1.0286 (inf) time: 0.6191 [2021-03-26 09:57:35 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 860/1251] eta: 0:04:06 lr: 0.000929 loss: 3.7332 (3.7408) grad_norm: 0.9943 (inf) time: 0.6226 [2021-03-26 09:57:41 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 870/1251] eta: 0:03:59 lr: 0.000929 loss: 3.6380 (3.7381) grad_norm: 0.9440 (inf) time: 0.6196 [2021-03-26 09:57:47 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 880/1251] eta: 0:03:53 lr: 0.000929 loss: 3.7308 (3.7391) grad_norm: 0.9451 (inf) time: 0.6193 [2021-03-26 09:57:53 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 890/1251] eta: 0:03:47 lr: 0.000929 loss: 3.9231 (3.7412) grad_norm: 0.9826 (inf) time: 0.6220 [2021-03-26 09:58:00 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 900/1251] eta: 0:03:40 lr: 0.000929 loss: 3.8084 (3.7394) grad_norm: 0.9891 (inf) time: 0.6215 [2021-03-26 09:58:06 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 910/1251] eta: 0:03:34 lr: 0.000929 loss: 3.8124 (3.7414) grad_norm: 0.9742 (inf) time: 0.6258 [2021-03-26 09:58:12 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 920/1251] eta: 0:03:28 lr: 0.000929 loss: 3.6311 (3.7375) grad_norm: 0.9726 (inf) time: 0.6245 [2021-03-26 09:58:18 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 930/1251] eta: 0:03:21 lr: 0.000929 loss: 3.5381 (3.7377) grad_norm: 1.0758 (inf) time: 0.6273 [2021-03-26 09:58:25 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 940/1251] eta: 0:03:15 lr: 0.000929 loss: 3.7346 (3.7390) grad_norm: 1.0179 (inf) time: 0.6331 [2021-03-26 09:58:31 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 950/1251] eta: 0:03:09 lr: 0.000929 loss: 3.9365 (3.7403) grad_norm: 1.0084 (inf) time: 0.6264 [2021-03-26 09:58:37 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 960/1251] eta: 0:03:03 lr: 0.000929 loss: 3.8809 (3.7395) grad_norm: 1.0573 (inf) time: 0.6248 [2021-03-26 09:58:43 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 970/1251] eta: 0:02:56 lr: 0.000929 loss: 3.6539 (3.7393) grad_norm: 1.0573 (inf) time: 0.6309 [2021-03-26 09:58:50 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 980/1251] eta: 0:02:50 lr: 0.000929 loss: 3.3650 (3.7371) grad_norm: 1.0897 (inf) time: 0.6378 [2021-03-26 09:58:56 swin_base_patch4_window7_224] INFO: Epoch: [51] [ 990/1251] eta: 0:02:44 lr: 0.000929 loss: 3.6552 (3.7386) grad_norm: 1.1027 (inf) time: 0.6323 [2021-03-26 09:59:02 swin_base_patch4_window7_224] INFO: Epoch: [51] [1000/1251] eta: 0:02:37 lr: 0.000929 loss: 3.6552 (3.7345) grad_norm: 1.1027 (inf) time: 0.6207 [2021-03-26 09:59:09 swin_base_patch4_window7_224] INFO: Epoch: [51] [1010/1251] eta: 0:02:31 lr: 0.000929 loss: 3.6506 (3.7348) grad_norm: 1.0475 (inf) time: 0.6274 [2021-03-26 09:59:15 swin_base_patch4_window7_224] INFO: Epoch: [51] [1020/1251] eta: 0:02:25 lr: 0.000929 loss: 3.9812 (3.7354) grad_norm: 1.0475 (inf) time: 0.6302 [2021-03-26 09:59:21 swin_base_patch4_window7_224] INFO: Epoch: [51] [1030/1251] eta: 0:02:19 lr: 0.000929 loss: 3.7490 (3.7336) grad_norm: 1.0636 (inf) time: 0.6253 [2021-03-26 09:59:27 swin_base_patch4_window7_224] INFO: Epoch: [51] [1040/1251] eta: 0:02:12 lr: 0.000929 loss: 3.7065 (3.7328) grad_norm: 1.0122 (inf) time: 0.6234 [2021-03-26 09:59:34 swin_base_patch4_window7_224] INFO: Epoch: [51] [1050/1251] eta: 0:02:06 lr: 0.000929 loss: 3.7413 (3.7327) grad_norm: 1.0122 (inf) time: 0.6221 [2021-03-26 09:59:40 swin_base_patch4_window7_224] INFO: Epoch: [51] [1060/1251] eta: 0:02:00 lr: 0.000929 loss: 3.7413 (3.7335) grad_norm: 1.0469 (inf) time: 0.6223 [2021-03-26 09:59:46 swin_base_patch4_window7_224] INFO: Epoch: [51] [1070/1251] eta: 0:01:53 lr: 0.000929 loss: 3.8070 (3.7347) grad_norm: 1.0405 (inf) time: 0.6282 [2021-03-26 09:59:52 swin_base_patch4_window7_224] INFO: Epoch: [51] [1080/1251] eta: 0:01:47 lr: 0.000929 loss: 3.8578 (3.7343) grad_norm: 0.9668 (inf) time: 0.6256 [2021-03-26 09:59:59 swin_base_patch4_window7_224] INFO: Epoch: [51] [1090/1251] eta: 0:01:41 lr: 0.000929 loss: 3.9049 (3.7354) grad_norm: 1.0986 (inf) time: 0.6273 [2021-03-26 10:00:05 swin_base_patch4_window7_224] INFO: Epoch: [51] [1100/1251] eta: 0:01:34 lr: 0.000929 loss: 3.9923 (3.7370) grad_norm: 1.0989 (inf) time: 0.6352 [2021-03-26 10:00:11 swin_base_patch4_window7_224] INFO: Epoch: [51] [1110/1251] eta: 0:01:28 lr: 0.000929 loss: 3.7436 (3.7368) grad_norm: 1.0405 (inf) time: 0.6285 [2021-03-26 10:00:18 swin_base_patch4_window7_224] INFO: Epoch: [51] [1120/1251] eta: 0:01:22 lr: 0.000929 loss: 3.7436 (3.7363) grad_norm: 1.0592 (inf) time: 0.6246 [2021-03-26 10:00:24 swin_base_patch4_window7_224] INFO: Epoch: [51] [1130/1251] eta: 0:01:16 lr: 0.000929 loss: 3.8840 (3.7388) grad_norm: 1.0834 (inf) time: 0.6266 [2021-03-26 10:00:30 swin_base_patch4_window7_224] INFO: Epoch: [51] [1140/1251] eta: 0:01:09 lr: 0.000929 loss: 3.7664 (3.7368) grad_norm: 1.0683 (inf) time: 0.6233 [2021-03-26 10:00:36 swin_base_patch4_window7_224] INFO: Epoch: [51] [1150/1251] eta: 0:01:03 lr: 0.000929 loss: 3.7650 (3.7382) grad_norm: 1.0731 (inf) time: 0.6225 [2021-03-26 10:00:43 swin_base_patch4_window7_224] INFO: Epoch: [51] [1160/1251] eta: 0:00:57 lr: 0.000929 loss: 3.8015 (3.7380) grad_norm: 1.0707 (inf) time: 0.6249 [2021-03-26 10:00:49 swin_base_patch4_window7_224] INFO: Epoch: [51] [1170/1251] eta: 0:00:50 lr: 0.000929 loss: 3.5529 (3.7358) grad_norm: 1.0539 (inf) time: 0.6243 [2021-03-26 10:00:55 swin_base_patch4_window7_224] INFO: Epoch: [51] [1180/1251] eta: 0:00:44 lr: 0.000929 loss: 3.9188 (3.7378) grad_norm: 1.0527 (inf) time: 0.6228 [2021-03-26 10:01:01 swin_base_patch4_window7_224] INFO: Epoch: [51] [1190/1251] eta: 0:00:38 lr: 0.000929 loss: 4.0140 (3.7378) grad_norm: 1.0899 (inf) time: 0.6265 [2021-03-26 10:01:08 swin_base_patch4_window7_224] INFO: Epoch: [51] [1200/1251] eta: 0:00:32 lr: 0.000929 loss: 3.8737 (3.7373) grad_norm: 1.1511 (inf) time: 0.6282 [2021-03-26 10:01:14 swin_base_patch4_window7_224] INFO: Epoch: [51] [1210/1251] eta: 0:00:25 lr: 0.000928 loss: 3.7367 (3.7361) grad_norm: 1.0786 (inf) time: 0.6263 [2021-03-26 10:01:20 swin_base_patch4_window7_224] INFO: Epoch: [51] [1220/1251] eta: 0:00:19 lr: 0.000928 loss: 3.7509 (3.7378) grad_norm: 1.0463 (inf) time: 0.6254 [2021-03-26 10:01:26 swin_base_patch4_window7_224] INFO: Epoch: [51] [1230/1251] eta: 0:00:13 lr: 0.000928 loss: 3.8568 (3.7386) grad_norm: 1.0229 (inf) time: 0.6223 [2021-03-26 10:01:33 swin_base_patch4_window7_224] INFO: Epoch: [51] [1240/1251] eta: 0:00:06 lr: 0.000928 loss: 3.9562 (3.7373) grad_norm: 1.1042 (inf) time: 0.6244 [2021-03-26 10:01:39 swin_base_patch4_window7_224] INFO: Epoch: [51] [1250/1251] eta: 0:00:00 lr: 0.000928 loss: 3.9618 (3.7390) grad_norm: 1.1243 (inf) time: 0.6222 [2021-03-26 10:01:43 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:42 loss: 1.1895 (1.1895) acc1: 71.8750 (71.8750) acc5: 89.0625 (89.0625) [2021-03-26 10:01:45 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 1.2579 (1.2678) acc1: 68.7500 (68.6080) acc5: 90.6250 (90.9091) [2021-03-26 10:01:48 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.2293 (1.2314) acc1: 71.8750 (70.3869) acc5: 90.6250 (91.3690) [2021-03-26 10:01:51 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1713 (1.2095) acc1: 71.8750 (71.3206) acc5: 92.1875 (91.6835) [2021-03-26 10:01:53 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1800 (1.2150) acc1: 71.8750 (71.3796) acc5: 92.1875 (91.5777) [2021-03-26 10:01:54 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1412 (1.1989) acc1: 71.8750 (71.7760) acc5: 92.1875 (91.7760) [2021-03-26 10:01:56 swin_base_patch4_window7_224] INFO: * Acc@1 73.038 Acc@5 91.974 loss 1.162 [2021-03-26 10:01:56 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.0% [2021-03-26 10:01:56 swin_base_patch4_window7_224] INFO: Max accuracy: 73.04% [2021-03-26 10:02:01 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 0/1251] eta: 1:31:28 lr: 0.000928 loss: 3.5333 (3.5333) grad_norm: 1.1075 (1.1075) time: 4.3874 [2021-03-26 10:02:07 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 10/1251] eta: 0:20:08 lr: 0.000928 loss: 3.6339 (3.8343) grad_norm: 1.0868 (1.0707) time: 0.9737 [2021-03-26 10:02:13 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 20/1251] eta: 0:16:34 lr: 0.000928 loss: 3.7106 (3.7298) grad_norm: 1.0662 (1.0958) time: 0.6290 [2021-03-26 10:02:20 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 30/1251] eta: 0:15:17 lr: 0.000928 loss: 3.7043 (3.6634) grad_norm: 1.0758 (1.0996) time: 0.6296 [2021-03-26 10:02:26 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 40/1251] eta: 0:14:33 lr: 0.000928 loss: 3.7962 (3.7544) grad_norm: 1.0688 (1.0921) time: 0.6305 [2021-03-26 10:02:32 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 50/1251] eta: 0:14:03 lr: 0.000928 loss: 3.8639 (3.7099) grad_norm: 1.0108 (1.0720) time: 0.6255 [2021-03-26 10:02:38 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 60/1251] eta: 0:13:41 lr: 0.000928 loss: 4.0198 (3.7748) grad_norm: 0.9641 (1.0586) time: 0.6249 [2021-03-26 10:02:44 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 70/1251] eta: 0:13:21 lr: 0.000928 loss: 4.0444 (3.7577) grad_norm: 0.9953 (1.0768) time: 0.6200 [2021-03-26 10:02:51 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 80/1251] eta: 0:13:06 lr: 0.000928 loss: 3.4192 (3.7131) grad_norm: 1.0555 (1.0817) time: 0.6176 [2021-03-26 10:02:57 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 90/1251] eta: 0:12:54 lr: 0.000928 loss: 3.5530 (3.7059) grad_norm: 1.0920 (1.0900) time: 0.6233 [2021-03-26 10:03:03 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 100/1251] eta: 0:12:42 lr: 0.000928 loss: 3.5998 (3.6967) grad_norm: 1.0821 (1.0852) time: 0.6239 [2021-03-26 10:03:09 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 110/1251] eta: 0:12:31 lr: 0.000928 loss: 3.8520 (3.7099) grad_norm: 1.0094 (1.0774) time: 0.6223 [2021-03-26 10:03:16 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 120/1251] eta: 0:12:22 lr: 0.000928 loss: 3.8816 (3.7235) grad_norm: 1.0614 (1.0941) time: 0.6253 [2021-03-26 10:03:22 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 130/1251] eta: 0:12:12 lr: 0.000928 loss: 4.0668 (3.7417) grad_norm: 1.0909 (1.0908) time: 0.6262 [2021-03-26 10:03:28 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 140/1251] eta: 0:12:04 lr: 0.000928 loss: 4.0123 (3.7618) grad_norm: 1.0494 (1.0872) time: 0.6239 [2021-03-26 10:03:34 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 150/1251] eta: 0:11:55 lr: 0.000928 loss: 4.0123 (3.7784) grad_norm: 1.0516 (1.0827) time: 0.6245 [2021-03-26 10:03:41 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 160/1251] eta: 0:11:47 lr: 0.000928 loss: 4.0928 (3.7946) grad_norm: 1.0057 (1.0798) time: 0.6290 [2021-03-26 10:03:47 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 170/1251] eta: 0:11:39 lr: 0.000928 loss: 3.8163 (3.7743) grad_norm: 0.9687 (1.0761) time: 0.6232 [2021-03-26 10:03:53 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 180/1251] eta: 0:11:31 lr: 0.000928 loss: 3.7299 (3.7728) grad_norm: 1.0370 (1.0828) time: 0.6211 [2021-03-26 10:03:59 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 190/1251] eta: 0:11:24 lr: 0.000928 loss: 3.7651 (3.7627) grad_norm: 1.1332 (1.0854) time: 0.6278 [2021-03-26 10:04:06 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 200/1251] eta: 0:11:16 lr: 0.000928 loss: 3.6691 (3.7584) grad_norm: 1.0898 (1.0860) time: 0.6235 [2021-03-26 10:04:12 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 210/1251] eta: 0:11:09 lr: 0.000928 loss: 3.6358 (3.7527) grad_norm: 1.0737 (1.0856) time: 0.6253 [2021-03-26 10:04:18 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 220/1251] eta: 0:11:02 lr: 0.000928 loss: 3.8066 (3.7693) grad_norm: 1.0617 (1.0853) time: 0.6292 [2021-03-26 10:04:24 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 230/1251] eta: 0:10:54 lr: 0.000928 loss: 3.9896 (3.7762) grad_norm: 1.0340 (1.0816) time: 0.6251 [2021-03-26 10:04:31 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 240/1251] eta: 0:10:48 lr: 0.000928 loss: 3.9006 (3.7694) grad_norm: 1.0363 (1.0844) time: 0.6265 [2021-03-26 10:04:37 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 250/1251] eta: 0:10:41 lr: 0.000928 loss: 3.6810 (3.7570) grad_norm: 1.0524 (1.0840) time: 0.6316 [2021-03-26 10:04:43 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 260/1251] eta: 0:10:34 lr: 0.000928 loss: 3.6584 (3.7605) grad_norm: 1.0037 (1.0842) time: 0.6324 [2021-03-26 10:04:50 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 270/1251] eta: 0:10:27 lr: 0.000928 loss: 3.8240 (3.7577) grad_norm: 1.0199 (1.0841) time: 0.6262 [2021-03-26 10:04:56 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 280/1251] eta: 0:10:20 lr: 0.000928 loss: 3.7959 (3.7537) grad_norm: 1.0138 (1.0815) time: 0.6223 [2021-03-26 10:05:02 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 290/1251] eta: 0:10:13 lr: 0.000928 loss: 3.7959 (3.7447) grad_norm: 1.0447 (1.0867) time: 0.6280 [2021-03-26 10:05:08 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 300/1251] eta: 0:10:07 lr: 0.000928 loss: 3.8876 (3.7491) grad_norm: 1.1801 (1.0888) time: 0.6283 [2021-03-26 10:05:15 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 310/1251] eta: 0:10:00 lr: 0.000928 loss: 3.8050 (3.7458) grad_norm: 1.1592 (1.0915) time: 0.6314 [2021-03-26 10:05:21 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 320/1251] eta: 0:09:53 lr: 0.000928 loss: 3.5703 (3.7368) grad_norm: 1.0870 (1.0908) time: 0.6308 [2021-03-26 10:05:27 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 330/1251] eta: 0:09:47 lr: 0.000928 loss: 3.7717 (3.7389) grad_norm: 1.0448 (1.0904) time: 0.6259 [2021-03-26 10:05:34 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 340/1251] eta: 0:09:40 lr: 0.000928 loss: 3.9093 (3.7423) grad_norm: 1.0261 (1.0899) time: 0.6266 [2021-03-26 10:05:40 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 350/1251] eta: 0:09:33 lr: 0.000928 loss: 3.9146 (3.7478) grad_norm: 1.0345 (1.0896) time: 0.6223 [2021-03-26 10:05:46 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 360/1251] eta: 0:09:26 lr: 0.000928 loss: 3.9338 (3.7447) grad_norm: 1.0704 (1.0882) time: 0.6219 [2021-03-26 10:05:52 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 370/1251] eta: 0:09:20 lr: 0.000928 loss: 3.8649 (3.7478) grad_norm: 1.0156 (1.0862) time: 0.6248 [2021-03-26 10:05:59 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 380/1251] eta: 0:09:13 lr: 0.000928 loss: 3.9357 (3.7542) grad_norm: 1.0187 (1.0857) time: 0.6290 [2021-03-26 10:06:05 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 390/1251] eta: 0:09:07 lr: 0.000928 loss: 4.0187 (3.7580) grad_norm: 1.0575 (1.0879) time: 0.6293 [2021-03-26 10:06:11 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 400/1251] eta: 0:09:01 lr: 0.000928 loss: 3.9104 (3.7616) grad_norm: 1.1264 (1.0867) time: 0.6317 [2021-03-26 10:06:17 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 410/1251] eta: 0:08:54 lr: 0.000928 loss: 4.0331 (3.7640) grad_norm: 1.0182 (1.0862) time: 0.6297 [2021-03-26 10:06:24 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 420/1251] eta: 0:08:47 lr: 0.000928 loss: 3.9379 (3.7624) grad_norm: 1.0279 (1.0849) time: 0.6254 [2021-03-26 10:06:30 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 430/1251] eta: 0:08:41 lr: 0.000927 loss: 3.8590 (3.7639) grad_norm: 1.0795 (1.0871) time: 0.6304 [2021-03-26 10:06:36 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 440/1251] eta: 0:08:34 lr: 0.000927 loss: 3.8797 (3.7665) grad_norm: 1.1021 (1.0872) time: 0.6277 [2021-03-26 10:06:42 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 450/1251] eta: 0:08:28 lr: 0.000927 loss: 4.0054 (3.7704) grad_norm: 1.0029 (1.0856) time: 0.6233 [2021-03-26 10:06:49 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 460/1251] eta: 0:08:21 lr: 0.000927 loss: 4.0054 (3.7711) grad_norm: 1.0340 (1.0864) time: 0.6252 [2021-03-26 10:06:55 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 470/1251] eta: 0:08:15 lr: 0.000927 loss: 3.9650 (3.7720) grad_norm: 1.0681 (1.0866) time: 0.6311 [2021-03-26 10:07:01 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 480/1251] eta: 0:08:08 lr: 0.000927 loss: 3.9839 (3.7758) grad_norm: 1.0356 (1.0858) time: 0.6275 [2021-03-26 10:07:08 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 490/1251] eta: 0:08:02 lr: 0.000927 loss: 3.9839 (3.7772) grad_norm: 1.0234 (1.0857) time: 0.6209 [2021-03-26 10:07:14 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 500/1251] eta: 0:07:55 lr: 0.000927 loss: 3.9264 (3.7796) grad_norm: 0.9995 (1.0843) time: 0.6225 [2021-03-26 10:07:20 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 510/1251] eta: 0:07:49 lr: 0.000927 loss: 3.8833 (3.7794) grad_norm: 1.0099 (1.0848) time: 0.6264 [2021-03-26 10:07:26 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 520/1251] eta: 0:07:43 lr: 0.000927 loss: 3.8833 (3.7833) grad_norm: 1.0739 (1.0844) time: 0.6265 [2021-03-26 10:07:33 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 530/1251] eta: 0:07:36 lr: 0.000927 loss: 3.8855 (3.7837) grad_norm: 1.0874 (1.0850) time: 0.6238 [2021-03-26 10:07:39 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 540/1251] eta: 0:07:30 lr: 0.000927 loss: 3.6787 (3.7798) grad_norm: 1.1456 (1.0857) time: 0.6256 [2021-03-26 10:07:45 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 550/1251] eta: 0:07:23 lr: 0.000927 loss: 3.5502 (3.7773) grad_norm: 1.1086 (1.0848) time: 0.6326 [2021-03-26 10:07:51 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 560/1251] eta: 0:07:17 lr: 0.000927 loss: 3.8815 (3.7805) grad_norm: 0.9986 (1.0853) time: 0.6310 [2021-03-26 10:07:58 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 570/1251] eta: 0:07:11 lr: 0.000927 loss: 3.8815 (3.7765) grad_norm: 1.0220 (1.0845) time: 0.6241 [2021-03-26 10:08:04 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 580/1251] eta: 0:07:04 lr: 0.000927 loss: 3.7149 (3.7771) grad_norm: 1.0220 (1.0840) time: 0.6273 [2021-03-26 10:08:10 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 590/1251] eta: 0:06:58 lr: 0.000927 loss: 3.9933 (3.7750) grad_norm: 1.0230 (1.0837) time: 0.6299 [2021-03-26 10:08:17 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 600/1251] eta: 0:06:52 lr: 0.000927 loss: 3.7854 (3.7724) grad_norm: 1.0230 (1.0835) time: 0.6345 [2021-03-26 10:08:23 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 610/1251] eta: 0:06:45 lr: 0.000927 loss: 3.6768 (3.7667) grad_norm: 1.0738 (1.0842) time: 0.6345 [2021-03-26 10:08:29 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 620/1251] eta: 0:06:39 lr: 0.000927 loss: 3.8605 (3.7702) grad_norm: 1.0738 (1.0846) time: 0.6276 [2021-03-26 10:08:35 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 630/1251] eta: 0:06:32 lr: 0.000927 loss: 3.8787 (3.7700) grad_norm: 1.0059 (1.0829) time: 0.6232 [2021-03-26 10:08:42 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 640/1251] eta: 0:06:26 lr: 0.000927 loss: 3.5148 (3.7667) grad_norm: 0.9573 (1.0814) time: 0.6201 [2021-03-26 10:08:48 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 650/1251] eta: 0:06:20 lr: 0.000927 loss: 3.8013 (3.7674) grad_norm: 1.0039 (1.0812) time: 0.6274 [2021-03-26 10:08:54 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 660/1251] eta: 0:06:13 lr: 0.000927 loss: 3.7518 (3.7649) grad_norm: 1.0671 (1.0821) time: 0.6333 [2021-03-26 10:09:00 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 670/1251] eta: 0:06:07 lr: 0.000927 loss: 3.7518 (3.7659) grad_norm: 1.0812 (1.0822) time: 0.6237 [2021-03-26 10:09:07 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 680/1251] eta: 0:06:00 lr: 0.000927 loss: 3.8177 (3.7619) grad_norm: 1.0525 (1.0823) time: 0.6234 [2021-03-26 10:09:13 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 690/1251] eta: 0:05:54 lr: 0.000927 loss: 3.5877 (3.7614) grad_norm: 1.0872 (1.0827) time: 0.6303 [2021-03-26 10:09:19 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 700/1251] eta: 0:05:48 lr: 0.000927 loss: 3.8581 (3.7610) grad_norm: 1.0294 (1.0820) time: 0.6248 [2021-03-26 10:09:26 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 710/1251] eta: 0:05:41 lr: 0.000927 loss: 3.8581 (3.7637) grad_norm: 1.0255 (1.0819) time: 0.6262 [2021-03-26 10:09:32 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 720/1251] eta: 0:05:35 lr: 0.000927 loss: 4.0542 (3.7670) grad_norm: 1.0515 (1.0823) time: 0.6244 [2021-03-26 10:09:38 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 730/1251] eta: 0:05:29 lr: 0.000927 loss: 3.9300 (3.7618) grad_norm: 1.0526 (1.0820) time: 0.6225 [2021-03-26 10:09:44 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 740/1251] eta: 0:05:22 lr: 0.000927 loss: 3.6670 (3.7650) grad_norm: 1.0456 (1.0820) time: 0.6298 [2021-03-26 10:09:51 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 750/1251] eta: 0:05:16 lr: 0.000927 loss: 3.8861 (3.7647) grad_norm: 1.0980 (1.0821) time: 0.6417 [2021-03-26 10:09:57 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 760/1251] eta: 0:05:10 lr: 0.000927 loss: 3.8213 (3.7628) grad_norm: 1.0846 (1.0818) time: 0.6379 [2021-03-26 10:10:03 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 770/1251] eta: 0:05:03 lr: 0.000927 loss: 3.5153 (3.7585) grad_norm: 1.0141 (1.0816) time: 0.6212 [2021-03-26 10:10:10 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 780/1251] eta: 0:04:57 lr: 0.000927 loss: 3.2866 (3.7542) grad_norm: 1.0014 (1.0811) time: 0.6213 [2021-03-26 10:10:16 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 790/1251] eta: 0:04:51 lr: 0.000927 loss: 3.4736 (3.7523) grad_norm: 1.0404 (1.0817) time: 0.6299 [2021-03-26 10:10:22 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 800/1251] eta: 0:04:44 lr: 0.000927 loss: 3.9453 (3.7527) grad_norm: 1.0475 (1.0819) time: 0.6329 [2021-03-26 10:10:28 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 810/1251] eta: 0:04:38 lr: 0.000927 loss: 3.9453 (3.7521) grad_norm: 0.9787 (1.0808) time: 0.6234 [2021-03-26 10:10:35 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 820/1251] eta: 0:04:32 lr: 0.000927 loss: 3.8060 (3.7522) grad_norm: 0.9731 (1.0795) time: 0.6213 [2021-03-26 10:10:41 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 830/1251] eta: 0:04:25 lr: 0.000927 loss: 3.8541 (3.7542) grad_norm: 1.0024 (1.0795) time: 0.6258 [2021-03-26 10:10:47 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 840/1251] eta: 0:04:19 lr: 0.000927 loss: 3.7586 (3.7534) grad_norm: 1.0332 (1.0795) time: 0.6235 [2021-03-26 10:10:53 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 850/1251] eta: 0:04:13 lr: 0.000927 loss: 3.6430 (3.7531) grad_norm: 1.0557 (1.0809) time: 0.6233 [2021-03-26 10:11:00 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 860/1251] eta: 0:04:06 lr: 0.000927 loss: 3.7642 (3.7551) grad_norm: 1.1304 (1.0809) time: 0.6230 [2021-03-26 10:11:06 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 870/1251] eta: 0:04:00 lr: 0.000927 loss: 3.8791 (3.7557) grad_norm: 1.0635 (1.0809) time: 0.6279 [2021-03-26 10:11:12 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 880/1251] eta: 0:03:54 lr: 0.000927 loss: 3.7151 (3.7544) grad_norm: 1.0304 (1.0806) time: 0.6277 [2021-03-26 10:11:18 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 890/1251] eta: 0:03:47 lr: 0.000926 loss: 3.8136 (3.7582) grad_norm: 1.0363 (1.0809) time: 0.6257 [2021-03-26 10:11:25 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 900/1251] eta: 0:03:41 lr: 0.000926 loss: 3.9637 (3.7573) grad_norm: 1.0834 (1.0806) time: 0.6274 [2021-03-26 10:11:31 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 910/1251] eta: 0:03:35 lr: 0.000926 loss: 3.7459 (3.7556) grad_norm: 0.9839 (1.0797) time: 0.6205 [2021-03-26 10:11:37 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 920/1251] eta: 0:03:28 lr: 0.000926 loss: 3.6181 (3.7546) grad_norm: 1.0455 (1.0802) time: 0.6254 [2021-03-26 10:11:43 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 930/1251] eta: 0:03:22 lr: 0.000926 loss: 3.5266 (3.7504) grad_norm: 1.0542 (1.0797) time: 0.6281 [2021-03-26 10:11:50 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 940/1251] eta: 0:03:16 lr: 0.000926 loss: 3.7559 (3.7529) grad_norm: 1.0542 (1.0806) time: 0.6228 [2021-03-26 10:11:56 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 950/1251] eta: 0:03:09 lr: 0.000926 loss: 3.8800 (3.7525) grad_norm: 1.0375 (1.0799) time: 0.6286 [2021-03-26 10:12:02 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 960/1251] eta: 0:03:03 lr: 0.000926 loss: 3.8692 (3.7536) grad_norm: 1.0349 (1.0798) time: 0.6291 [2021-03-26 10:12:08 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 970/1251] eta: 0:02:57 lr: 0.000926 loss: 3.8658 (3.7518) grad_norm: 1.0380 (1.0795) time: 0.6205 [2021-03-26 10:12:15 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 980/1251] eta: 0:02:50 lr: 0.000926 loss: 3.9027 (3.7533) grad_norm: 0.9902 (1.0797) time: 0.6173 [2021-03-26 10:12:21 swin_base_patch4_window7_224] INFO: Epoch: [52] [ 990/1251] eta: 0:02:44 lr: 0.000926 loss: 4.0143 (3.7529) grad_norm: 1.0995 (1.0801) time: 0.6198 [2021-03-26 10:12:27 swin_base_patch4_window7_224] INFO: Epoch: [52] [1000/1251] eta: 0:02:38 lr: 0.000926 loss: 3.9860 (3.7549) grad_norm: 1.0324 (1.0790) time: 0.6209 [2021-03-26 10:12:33 swin_base_patch4_window7_224] INFO: Epoch: [52] [1010/1251] eta: 0:02:31 lr: 0.000926 loss: 3.8993 (3.7535) grad_norm: 0.9627 (1.0789) time: 0.6184 [2021-03-26 10:12:39 swin_base_patch4_window7_224] INFO: Epoch: [52] [1020/1251] eta: 0:02:25 lr: 0.000926 loss: 3.6999 (3.7526) grad_norm: 1.0218 (1.0787) time: 0.6190 [2021-03-26 10:12:46 swin_base_patch4_window7_224] INFO: Epoch: [52] [1030/1251] eta: 0:02:19 lr: 0.000926 loss: 3.7524 (3.7558) grad_norm: 1.0322 (1.0786) time: 0.6205 [2021-03-26 10:12:52 swin_base_patch4_window7_224] INFO: Epoch: [52] [1040/1251] eta: 0:02:12 lr: 0.000926 loss: 3.7524 (3.7557) grad_norm: 1.0559 (1.0790) time: 0.6228 [2021-03-26 10:12:58 swin_base_patch4_window7_224] INFO: Epoch: [52] [1050/1251] eta: 0:02:06 lr: 0.000926 loss: 3.9239 (3.7573) grad_norm: 1.0559 (1.0793) time: 0.6266 [2021-03-26 10:13:05 swin_base_patch4_window7_224] INFO: Epoch: [52] [1060/1251] eta: 0:02:00 lr: 0.000926 loss: 3.9698 (3.7593) grad_norm: 1.0844 (1.0797) time: 0.6317 [2021-03-26 10:13:11 swin_base_patch4_window7_224] INFO: Epoch: [52] [1070/1251] eta: 0:01:53 lr: 0.000926 loss: 3.7572 (3.7573) grad_norm: 1.0186 (1.0785) time: 0.6306 [2021-03-26 10:13:17 swin_base_patch4_window7_224] INFO: Epoch: [52] [1080/1251] eta: 0:01:47 lr: 0.000926 loss: 3.7929 (3.7594) grad_norm: 0.9914 (1.0782) time: 0.6281 [2021-03-26 10:13:23 swin_base_patch4_window7_224] INFO: Epoch: [52] [1090/1251] eta: 0:01:41 lr: 0.000926 loss: 3.9052 (3.7597) grad_norm: 1.0685 (1.0783) time: 0.6285 [2021-03-26 10:13:30 swin_base_patch4_window7_224] INFO: Epoch: [52] [1100/1251] eta: 0:01:35 lr: 0.000926 loss: 3.6798 (3.7594) grad_norm: 1.0674 (1.0792) time: 0.6291 [2021-03-26 10:13:36 swin_base_patch4_window7_224] INFO: Epoch: [52] [1110/1251] eta: 0:01:28 lr: 0.000926 loss: 3.9010 (3.7610) grad_norm: 1.1441 (1.0802) time: 0.6242 [2021-03-26 10:13:42 swin_base_patch4_window7_224] INFO: Epoch: [52] [1120/1251] eta: 0:01:22 lr: 0.000926 loss: 3.8138 (3.7591) grad_norm: 1.1184 (1.0808) time: 0.6188 [2021-03-26 10:13:48 swin_base_patch4_window7_224] INFO: Epoch: [52] [1130/1251] eta: 0:01:16 lr: 0.000926 loss: 3.6330 (3.7584) grad_norm: 1.0382 (1.0802) time: 0.6219 [2021-03-26 10:13:55 swin_base_patch4_window7_224] INFO: Epoch: [52] [1140/1251] eta: 0:01:09 lr: 0.000926 loss: 3.7721 (3.7582) grad_norm: 1.0167 (1.0795) time: 0.6231 [2021-03-26 10:14:01 swin_base_patch4_window7_224] INFO: Epoch: [52] [1150/1251] eta: 0:01:03 lr: 0.000926 loss: 3.8307 (3.7597) grad_norm: 1.0353 (1.0803) time: 0.6242 [2021-03-26 10:14:07 swin_base_patch4_window7_224] INFO: Epoch: [52] [1160/1251] eta: 0:00:57 lr: 0.000926 loss: 3.8640 (3.7600) grad_norm: 1.1085 (1.0808) time: 0.6227 [2021-03-26 10:14:13 swin_base_patch4_window7_224] INFO: Epoch: [52] [1170/1251] eta: 0:00:50 lr: 0.000926 loss: 3.6082 (3.7557) grad_norm: 1.0273 (1.0804) time: 0.6240 [2021-03-26 10:14:19 swin_base_patch4_window7_224] INFO: Epoch: [52] [1180/1251] eta: 0:00:44 lr: 0.000926 loss: 3.9179 (3.7597) grad_norm: 1.0273 (1.0805) time: 0.6223 [2021-03-26 10:14:26 swin_base_patch4_window7_224] INFO: Epoch: [52] [1190/1251] eta: 0:00:38 lr: 0.000926 loss: 4.1316 (3.7616) grad_norm: 1.0319 (1.0800) time: 0.6185 [2021-03-26 10:14:32 swin_base_patch4_window7_224] INFO: Epoch: [52] [1200/1251] eta: 0:00:32 lr: 0.000926 loss: 3.7290 (3.7602) grad_norm: 0.9995 (1.0793) time: 0.6200 [2021-03-26 10:14:38 swin_base_patch4_window7_224] INFO: Epoch: [52] [1210/1251] eta: 0:00:25 lr: 0.000926 loss: 3.6775 (3.7605) grad_norm: 1.0731 (1.0800) time: 0.6333 [2021-03-26 10:14:45 swin_base_patch4_window7_224] INFO: Epoch: [52] [1220/1251] eta: 0:00:19 lr: 0.000926 loss: 3.7982 (3.7587) grad_norm: 1.0731 (1.0797) time: 0.6336 [2021-03-26 10:14:51 swin_base_patch4_window7_224] INFO: Epoch: [52] [1230/1251] eta: 0:00:13 lr: 0.000926 loss: 3.6605 (3.7578) grad_norm: 1.0157 (1.0794) time: 0.6213 [2021-03-26 10:14:57 swin_base_patch4_window7_224] INFO: Epoch: [52] [1240/1251] eta: 0:00:06 lr: 0.000926 loss: 3.6736 (3.7581) grad_norm: 1.0157 (1.0788) time: 0.6163 [2021-03-26 10:15:03 swin_base_patch4_window7_224] INFO: Epoch: [52] [1250/1251] eta: 0:00:00 lr: 0.000926 loss: 3.6736 (3.7583) grad_norm: 1.0374 (1.0784) time: 0.6138 [2021-03-26 10:15:08 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:24 loss: 0.9767 (0.9767) acc1: 76.5625 (76.5625) acc5: 95.3125 (95.3125) [2021-03-26 10:15:11 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:21 loss: 1.2232 (1.2301) acc1: 71.8750 (71.7330) acc5: 93.7500 (91.9034) [2021-03-26 10:15:14 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.2207 (1.2094) acc1: 71.8750 (72.3958) acc5: 90.6250 (91.5923) [2021-03-26 10:15:16 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.2207 (1.2105) acc1: 73.4375 (73.0847) acc5: 90.6250 (91.2298) [2021-03-26 10:15:18 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1665 (1.1860) acc1: 75.0000 (73.5137) acc5: 92.1875 (91.5777) [2021-03-26 10:15:19 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1665 (1.1862) acc1: 73.4375 (73.0880) acc5: 92.1875 (91.7120) [2021-03-26 10:15:20 swin_base_patch4_window7_224] INFO: * Acc@1 73.368 Acc@5 91.872 loss 1.168 [2021-03-26 10:15:20 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.4% [2021-03-26 10:15:20 swin_base_patch4_window7_224] INFO: Max accuracy: 73.37% [2021-03-26 10:15:25 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 0/1251] eta: 1:27:13 lr: 0.000926 loss: 4.3026 (4.3026) grad_norm: 1.1865 (1.1865) time: 4.1835 [2021-03-26 10:15:31 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 10/1251] eta: 0:19:32 lr: 0.000926 loss: 3.3464 (3.4679) grad_norm: 1.1189 (1.1202) time: 0.9449 [2021-03-26 10:15:37 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 20/1251] eta: 0:16:19 lr: 0.000926 loss: 3.3464 (3.4482) grad_norm: 1.1051 (1.0982) time: 0.6261 [2021-03-26 10:15:43 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 30/1251] eta: 0:15:03 lr: 0.000926 loss: 3.6750 (3.5567) grad_norm: 1.0583 (1.0805) time: 0.6277 [2021-03-26 10:15:50 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 40/1251] eta: 0:14:24 lr: 0.000926 loss: 3.6968 (3.5861) grad_norm: 0.9923 (1.0622) time: 0.6283 [2021-03-26 10:15:56 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 50/1251] eta: 0:13:56 lr: 0.000926 loss: 3.7804 (3.6350) grad_norm: 0.9812 (1.0460) time: 0.6278 [2021-03-26 10:16:02 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 60/1251] eta: 0:13:35 lr: 0.000926 loss: 3.9598 (3.6699) grad_norm: 0.9967 (1.0455) time: 0.6252 [2021-03-26 10:16:09 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 70/1251] eta: 0:13:18 lr: 0.000926 loss: 3.9135 (3.7101) grad_norm: 1.0463 (1.0430) time: 0.6257 [2021-03-26 10:16:15 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 80/1251] eta: 0:13:04 lr: 0.000926 loss: 3.8188 (3.6736) grad_norm: 1.0463 (1.0452) time: 0.6232 [2021-03-26 10:16:21 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 90/1251] eta: 0:12:51 lr: 0.000926 loss: 3.6277 (3.6772) grad_norm: 1.0063 (1.0435) time: 0.6227 [2021-03-26 10:16:27 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 100/1251] eta: 0:12:39 lr: 0.000925 loss: 3.8503 (3.6923) grad_norm: 1.0311 (1.0430) time: 0.6222 [2021-03-26 10:16:33 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 110/1251] eta: 0:12:29 lr: 0.000925 loss: 3.9231 (3.6946) grad_norm: 1.0426 (1.0549) time: 0.6240 [2021-03-26 10:16:40 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 120/1251] eta: 0:12:20 lr: 0.000925 loss: 3.7871 (3.6820) grad_norm: 1.0791 (1.0614) time: 0.6269 [2021-03-26 10:16:46 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 130/1251] eta: 0:12:11 lr: 0.000925 loss: 3.8095 (3.6994) grad_norm: 1.0352 (1.0634) time: 0.6271 [2021-03-26 10:16:52 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 140/1251] eta: 0:12:03 lr: 0.000925 loss: 3.8095 (3.6934) grad_norm: 1.0151 (1.0694) time: 0.6317 [2021-03-26 10:16:59 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 150/1251] eta: 0:11:55 lr: 0.000925 loss: 3.6867 (3.6704) grad_norm: 1.0564 (1.0682) time: 0.6312 [2021-03-26 10:17:05 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 160/1251] eta: 0:11:47 lr: 0.000925 loss: 3.6867 (3.6860) grad_norm: 0.9843 (1.0659) time: 0.6278 [2021-03-26 10:17:11 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 170/1251] eta: 0:11:39 lr: 0.000925 loss: 4.0120 (3.6834) grad_norm: 1.0463 (1.0693) time: 0.6264 [2021-03-26 10:17:17 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 180/1251] eta: 0:11:32 lr: 0.000925 loss: 3.7619 (3.6862) grad_norm: 1.0649 (1.0671) time: 0.6287 [2021-03-26 10:17:24 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 190/1251] eta: 0:11:24 lr: 0.000925 loss: 3.6942 (3.6792) grad_norm: 1.0427 (1.0664) time: 0.6321 [2021-03-26 10:17:30 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 200/1251] eta: 0:11:17 lr: 0.000925 loss: 3.6942 (3.6812) grad_norm: 1.0664 (1.0688) time: 0.6328 [2021-03-26 10:17:37 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 210/1251] eta: 0:11:11 lr: 0.000925 loss: 3.6969 (3.6840) grad_norm: 1.0877 (1.0689) time: 0.6396 [2021-03-26 10:17:43 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 220/1251] eta: 0:11:03 lr: 0.000925 loss: 3.8376 (3.7010) grad_norm: 1.0614 (1.0670) time: 0.6330 [2021-03-26 10:17:49 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 230/1251] eta: 0:10:56 lr: 0.000925 loss: 3.9295 (3.6982) grad_norm: 1.0572 (1.0677) time: 0.6253 [2021-03-26 10:17:55 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 240/1251] eta: 0:10:49 lr: 0.000925 loss: 3.5817 (3.6998) grad_norm: 1.0572 (1.0680) time: 0.6322 [2021-03-26 10:18:02 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 250/1251] eta: 0:10:42 lr: 0.000925 loss: 3.5564 (3.6988) grad_norm: 0.9797 (1.0644) time: 0.6271 [2021-03-26 10:18:08 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 260/1251] eta: 0:10:35 lr: 0.000925 loss: 3.9209 (3.7049) grad_norm: 1.0594 (1.0687) time: 0.6241 [2021-03-26 10:18:14 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 270/1251] eta: 0:10:28 lr: 0.000925 loss: 3.8749 (3.7029) grad_norm: 1.0726 (1.0676) time: 0.6264 [2021-03-26 10:18:20 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 280/1251] eta: 0:10:21 lr: 0.000925 loss: 3.9072 (3.7098) grad_norm: 0.9653 (1.0636) time: 0.6190 [2021-03-26 10:18:26 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 290/1251] eta: 0:10:14 lr: 0.000925 loss: 3.9985 (3.7093) grad_norm: 0.9401 (1.0612) time: 0.6153 [2021-03-26 10:18:33 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 300/1251] eta: 0:10:07 lr: 0.000925 loss: 3.5572 (3.7066) grad_norm: 0.9922 (1.0614) time: 0.6207 [2021-03-26 10:18:39 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 310/1251] eta: 0:10:00 lr: 0.000925 loss: 3.7216 (3.7072) grad_norm: 1.0433 (1.0612) time: 0.6267 [2021-03-26 10:18:45 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 320/1251] eta: 0:09:53 lr: 0.000925 loss: 3.4556 (3.6936) grad_norm: 1.1451 (1.0674) time: 0.6253 [2021-03-26 10:18:52 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 330/1251] eta: 0:09:47 lr: 0.000925 loss: 3.5667 (3.6992) grad_norm: 1.1451 (1.0673) time: 0.6304 [2021-03-26 10:18:58 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 340/1251] eta: 0:09:40 lr: 0.000925 loss: 3.7530 (3.6921) grad_norm: 1.0816 (1.0678) time: 0.6285 [2021-03-26 10:19:04 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 350/1251] eta: 0:09:33 lr: 0.000925 loss: 3.5119 (3.6903) grad_norm: 1.0574 (1.0684) time: 0.6223 [2021-03-26 10:19:10 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 360/1251] eta: 0:09:27 lr: 0.000925 loss: 3.9131 (3.6934) grad_norm: 1.0574 (1.0692) time: 0.6300 [2021-03-26 10:19:17 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 370/1251] eta: 0:09:20 lr: 0.000925 loss: 3.7124 (3.6954) grad_norm: 1.1030 (1.0703) time: 0.6326 [2021-03-26 10:19:23 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 380/1251] eta: 0:09:14 lr: 0.000925 loss: 3.7124 (3.6966) grad_norm: 1.0705 (1.0691) time: 0.6301 [2021-03-26 10:19:29 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 390/1251] eta: 0:09:07 lr: 0.000925 loss: 3.7852 (3.6935) grad_norm: 1.0058 (1.0683) time: 0.6238 [2021-03-26 10:19:36 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 400/1251] eta: 0:09:01 lr: 0.000925 loss: 3.6953 (3.6941) grad_norm: 1.0316 (1.0691) time: 0.6275 [2021-03-26 10:19:42 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 410/1251] eta: 0:08:54 lr: 0.000925 loss: 3.7871 (3.6950) grad_norm: 1.0909 (1.0699) time: 0.6366 [2021-03-26 10:19:48 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 420/1251] eta: 0:08:48 lr: 0.000925 loss: 3.7871 (3.6980) grad_norm: 1.0275 (1.0678) time: 0.6303 [2021-03-26 10:19:54 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 430/1251] eta: 0:08:41 lr: 0.000925 loss: 3.8352 (3.6971) grad_norm: 0.9647 (1.0676) time: 0.6209 [2021-03-26 10:20:01 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 440/1251] eta: 0:08:34 lr: 0.000925 loss: 3.8352 (3.6966) grad_norm: 1.0982 (1.0705) time: 0.6189 [2021-03-26 10:20:07 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 450/1251] eta: 0:08:28 lr: 0.000925 loss: 3.7375 (3.7001) grad_norm: 1.1202 (1.0699) time: 0.6195 [2021-03-26 10:20:13 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 460/1251] eta: 0:08:21 lr: 0.000925 loss: 3.7753 (3.7000) grad_norm: 1.0098 (1.0690) time: 0.6208 [2021-03-26 10:20:19 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 470/1251] eta: 0:08:15 lr: 0.000925 loss: 3.8948 (3.7060) grad_norm: 0.9865 (1.0679) time: 0.6226 [2021-03-26 10:20:25 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 480/1251] eta: 0:08:08 lr: 0.000925 loss: 3.7463 (3.7025) grad_norm: 1.0073 (1.0682) time: 0.6234 [2021-03-26 10:20:32 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 490/1251] eta: 0:08:02 lr: 0.000925 loss: 3.7818 (3.7053) grad_norm: 1.0096 (1.0691) time: 0.6244 [2021-03-26 10:20:38 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 500/1251] eta: 0:07:55 lr: 0.000925 loss: 3.7818 (3.7044) grad_norm: 1.0060 (inf) time: 0.6194 [2021-03-26 10:20:44 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 510/1251] eta: 0:07:49 lr: 0.000925 loss: 3.7743 (3.7065) grad_norm: 1.0522 (inf) time: 0.6222 [2021-03-26 10:20:50 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 520/1251] eta: 0:07:42 lr: 0.000925 loss: 3.8408 (3.7085) grad_norm: 1.0945 (inf) time: 0.6270 [2021-03-26 10:20:57 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 530/1251] eta: 0:07:36 lr: 0.000925 loss: 3.9051 (3.7135) grad_norm: 1.0730 (inf) time: 0.6199 [2021-03-26 10:21:03 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 540/1251] eta: 0:07:29 lr: 0.000925 loss: 4.0286 (3.7166) grad_norm: 1.1253 (inf) time: 0.6228 [2021-03-26 10:21:09 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 550/1251] eta: 0:07:23 lr: 0.000924 loss: 4.0875 (3.7264) grad_norm: 1.1035 (inf) time: 0.6444 [2021-03-26 10:21:16 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 560/1251] eta: 0:07:17 lr: 0.000924 loss: 3.8579 (3.7246) grad_norm: 1.0539 (inf) time: 0.6445 [2021-03-26 10:21:22 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 570/1251] eta: 0:07:11 lr: 0.000924 loss: 3.6683 (3.7197) grad_norm: 1.0539 (inf) time: 0.6252 [2021-03-26 10:21:28 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 580/1251] eta: 0:07:04 lr: 0.000924 loss: 3.8010 (3.7206) grad_norm: 1.0307 (inf) time: 0.6224 [2021-03-26 10:21:35 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 590/1251] eta: 0:06:58 lr: 0.000924 loss: 3.8912 (3.7201) grad_norm: 1.0008 (inf) time: 0.6274 [2021-03-26 10:21:41 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 600/1251] eta: 0:06:51 lr: 0.000924 loss: 3.8887 (3.7152) grad_norm: 0.9982 (inf) time: 0.6346 [2021-03-26 10:21:47 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 610/1251] eta: 0:06:45 lr: 0.000924 loss: 3.7432 (3.7151) grad_norm: 1.0743 (inf) time: 0.6286 [2021-03-26 10:21:53 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 620/1251] eta: 0:06:39 lr: 0.000924 loss: 3.8138 (3.7168) grad_norm: 0.9665 (inf) time: 0.6233 [2021-03-26 10:22:00 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 630/1251] eta: 0:06:32 lr: 0.000924 loss: 3.8970 (3.7161) grad_norm: 0.9928 (inf) time: 0.6278 [2021-03-26 10:22:06 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 640/1251] eta: 0:06:26 lr: 0.000924 loss: 3.7663 (3.7171) grad_norm: 1.0242 (inf) time: 0.6283 [2021-03-26 10:22:12 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 650/1251] eta: 0:06:20 lr: 0.000924 loss: 3.9240 (3.7207) grad_norm: 1.0242 (inf) time: 0.6279 [2021-03-26 10:22:18 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 660/1251] eta: 0:06:13 lr: 0.000924 loss: 3.9191 (3.7159) grad_norm: 1.0348 (inf) time: 0.6259 [2021-03-26 10:22:25 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 670/1251] eta: 0:06:07 lr: 0.000924 loss: 3.9191 (3.7185) grad_norm: 1.0783 (inf) time: 0.6283 [2021-03-26 10:22:31 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 680/1251] eta: 0:06:00 lr: 0.000924 loss: 3.6791 (3.7164) grad_norm: 1.0681 (inf) time: 0.6293 [2021-03-26 10:22:37 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 690/1251] eta: 0:05:54 lr: 0.000924 loss: 3.6188 (3.7155) grad_norm: 1.0163 (inf) time: 0.6201 [2021-03-26 10:22:43 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 700/1251] eta: 0:05:48 lr: 0.000924 loss: 3.7468 (3.7164) grad_norm: 1.0534 (inf) time: 0.6198 [2021-03-26 10:22:50 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 710/1251] eta: 0:05:41 lr: 0.000924 loss: 3.5589 (3.7148) grad_norm: 1.0967 (inf) time: 0.6260 [2021-03-26 10:22:56 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 720/1251] eta: 0:05:35 lr: 0.000924 loss: 3.5589 (3.7152) grad_norm: 1.0377 (inf) time: 0.6244 [2021-03-26 10:23:02 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 730/1251] eta: 0:05:29 lr: 0.000924 loss: 3.7370 (3.7132) grad_norm: 1.0377 (inf) time: 0.6278 [2021-03-26 10:23:09 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 740/1251] eta: 0:05:22 lr: 0.000924 loss: 3.7370 (3.7157) grad_norm: 1.0360 (inf) time: 0.6313 [2021-03-26 10:23:15 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 750/1251] eta: 0:05:16 lr: 0.000924 loss: 3.9299 (3.7149) grad_norm: 0.9655 (inf) time: 0.6293 [2021-03-26 10:23:21 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 760/1251] eta: 0:05:09 lr: 0.000924 loss: 3.9277 (3.7157) grad_norm: 0.9776 (inf) time: 0.6221 [2021-03-26 10:23:27 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 770/1251] eta: 0:05:03 lr: 0.000924 loss: 4.0466 (3.7190) grad_norm: 1.0245 (inf) time: 0.6253 [2021-03-26 10:23:34 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 780/1251] eta: 0:04:57 lr: 0.000924 loss: 3.6772 (3.7150) grad_norm: 1.0331 (inf) time: 0.6391 [2021-03-26 10:23:40 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 790/1251] eta: 0:04:51 lr: 0.000924 loss: 3.5921 (3.7148) grad_norm: 1.0299 (inf) time: 0.6350 [2021-03-26 10:23:46 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 800/1251] eta: 0:04:44 lr: 0.000924 loss: 3.5169 (3.7130) grad_norm: 1.0324 (inf) time: 0.6235 [2021-03-26 10:23:52 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 810/1251] eta: 0:04:38 lr: 0.000924 loss: 3.3964 (3.7086) grad_norm: 1.0983 (inf) time: 0.6209 [2021-03-26 10:23:59 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 820/1251] eta: 0:04:31 lr: 0.000924 loss: 3.5424 (3.7078) grad_norm: 1.0379 (inf) time: 0.6212 [2021-03-26 10:24:05 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 830/1251] eta: 0:04:25 lr: 0.000924 loss: 3.6728 (3.7060) grad_norm: 1.0186 (inf) time: 0.6189 [2021-03-26 10:24:11 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 840/1251] eta: 0:04:19 lr: 0.000924 loss: 3.4099 (3.7035) grad_norm: 1.0336 (inf) time: 0.6247 [2021-03-26 10:24:17 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 850/1251] eta: 0:04:12 lr: 0.000924 loss: 3.4219 (3.7040) grad_norm: 1.0672 (inf) time: 0.6286 [2021-03-26 10:24:24 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 860/1251] eta: 0:04:06 lr: 0.000924 loss: 3.8381 (3.7033) grad_norm: 1.0672 (inf) time: 0.6193 [2021-03-26 10:24:30 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 870/1251] eta: 0:04:00 lr: 0.000924 loss: 3.8381 (3.7056) grad_norm: 1.0536 (inf) time: 0.6173 [2021-03-26 10:24:36 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 880/1251] eta: 0:03:53 lr: 0.000924 loss: 3.9237 (3.7084) grad_norm: 1.0536 (inf) time: 0.6245 [2021-03-26 10:24:42 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 890/1251] eta: 0:03:47 lr: 0.000924 loss: 3.9237 (3.7082) grad_norm: 1.0518 (inf) time: 0.6268 [2021-03-26 10:24:49 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 900/1251] eta: 0:03:41 lr: 0.000924 loss: 3.7322 (3.7061) grad_norm: 1.0501 (inf) time: 0.6231 [2021-03-26 10:24:55 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 910/1251] eta: 0:03:34 lr: 0.000924 loss: 3.7198 (3.7068) grad_norm: 1.0241 (inf) time: 0.6253 [2021-03-26 10:25:01 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 920/1251] eta: 0:03:28 lr: 0.000924 loss: 3.7724 (3.7076) grad_norm: 1.0241 (inf) time: 0.6231 [2021-03-26 10:25:07 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 930/1251] eta: 0:03:22 lr: 0.000924 loss: 3.6976 (3.7065) grad_norm: 1.0163 (inf) time: 0.6251 [2021-03-26 10:25:14 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 940/1251] eta: 0:03:15 lr: 0.000924 loss: 3.6793 (3.7049) grad_norm: 1.0351 (inf) time: 0.6295 [2021-03-26 10:25:20 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 950/1251] eta: 0:03:09 lr: 0.000924 loss: 3.6793 (3.7030) grad_norm: 1.1289 (inf) time: 0.6277 [2021-03-26 10:25:26 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 960/1251] eta: 0:03:03 lr: 0.000924 loss: 3.3459 (3.7015) grad_norm: 1.0539 (inf) time: 0.6281 [2021-03-26 10:25:33 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 970/1251] eta: 0:02:57 lr: 0.000924 loss: 3.8307 (3.7025) grad_norm: 1.0474 (inf) time: 0.6306 [2021-03-26 10:25:39 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 980/1251] eta: 0:02:50 lr: 0.000924 loss: 3.8342 (3.7032) grad_norm: 1.0037 (inf) time: 0.6328 [2021-03-26 10:25:45 swin_base_patch4_window7_224] INFO: Epoch: [53] [ 990/1251] eta: 0:02:44 lr: 0.000924 loss: 3.9328 (3.7065) grad_norm: 1.0058 (inf) time: 0.6267 [2021-03-26 10:25:51 swin_base_patch4_window7_224] INFO: Epoch: [53] [1000/1251] eta: 0:02:38 lr: 0.000923 loss: 3.9868 (3.7057) grad_norm: 1.0072 (inf) time: 0.6233 [2021-03-26 10:25:58 swin_base_patch4_window7_224] INFO: Epoch: [53] [1010/1251] eta: 0:02:31 lr: 0.000923 loss: 3.6095 (3.7056) grad_norm: 1.0370 (inf) time: 0.6227 [2021-03-26 10:26:04 swin_base_patch4_window7_224] INFO: Epoch: [53] [1020/1251] eta: 0:02:25 lr: 0.000923 loss: 3.6003 (3.7022) grad_norm: 1.0563 (inf) time: 0.6197 [2021-03-26 10:26:10 swin_base_patch4_window7_224] INFO: Epoch: [53] [1030/1251] eta: 0:02:19 lr: 0.000923 loss: 3.4447 (3.7021) grad_norm: 1.0892 (inf) time: 0.6213 [2021-03-26 10:26:16 swin_base_patch4_window7_224] INFO: Epoch: [53] [1040/1251] eta: 0:02:12 lr: 0.000923 loss: 3.7512 (3.7036) grad_norm: 1.0097 (inf) time: 0.6256 [2021-03-26 10:26:22 swin_base_patch4_window7_224] INFO: Epoch: [53] [1050/1251] eta: 0:02:06 lr: 0.000923 loss: 3.9491 (3.7037) grad_norm: 1.1040 (inf) time: 0.6252 [2021-03-26 10:26:29 swin_base_patch4_window7_224] INFO: Epoch: [53] [1060/1251] eta: 0:02:00 lr: 0.000923 loss: 3.8979 (3.7048) grad_norm: 1.0793 (inf) time: 0.6225 [2021-03-26 10:26:35 swin_base_patch4_window7_224] INFO: Epoch: [53] [1070/1251] eta: 0:01:53 lr: 0.000923 loss: 3.7823 (3.7038) grad_norm: 1.0548 (inf) time: 0.6210 [2021-03-26 10:26:41 swin_base_patch4_window7_224] INFO: Epoch: [53] [1080/1251] eta: 0:01:47 lr: 0.000923 loss: 3.5074 (3.7027) grad_norm: 1.0268 (inf) time: 0.6231 [2021-03-26 10:26:47 swin_base_patch4_window7_224] INFO: Epoch: [53] [1090/1251] eta: 0:01:41 lr: 0.000923 loss: 3.8050 (3.7051) grad_norm: 1.0889 (inf) time: 0.6303 [2021-03-26 10:26:54 swin_base_patch4_window7_224] INFO: Epoch: [53] [1100/1251] eta: 0:01:35 lr: 0.000923 loss: 3.8050 (3.7033) grad_norm: 1.0350 (inf) time: 0.6285 [2021-03-26 10:27:00 swin_base_patch4_window7_224] INFO: Epoch: [53] [1110/1251] eta: 0:01:28 lr: 0.000923 loss: 3.7369 (3.7048) grad_norm: 1.0097 (inf) time: 0.6200 [2021-03-26 10:27:06 swin_base_patch4_window7_224] INFO: Epoch: [53] [1120/1251] eta: 0:01:22 lr: 0.000923 loss: 3.8871 (3.7052) grad_norm: 1.0732 (inf) time: 0.6226 [2021-03-26 10:27:12 swin_base_patch4_window7_224] INFO: Epoch: [53] [1130/1251] eta: 0:01:16 lr: 0.000923 loss: 3.6977 (3.7042) grad_norm: 1.0425 (inf) time: 0.6281 [2021-03-26 10:27:19 swin_base_patch4_window7_224] INFO: Epoch: [53] [1140/1251] eta: 0:01:09 lr: 0.000923 loss: 3.6977 (3.7048) grad_norm: 0.9922 (inf) time: 0.6290 [2021-03-26 10:27:25 swin_base_patch4_window7_224] INFO: Epoch: [53] [1150/1251] eta: 0:01:03 lr: 0.000923 loss: 3.6088 (3.7034) grad_norm: 0.9922 (inf) time: 0.6272 [2021-03-26 10:27:31 swin_base_patch4_window7_224] INFO: Epoch: [53] [1160/1251] eta: 0:00:57 lr: 0.000923 loss: 3.4151 (3.7028) grad_norm: 1.0014 (inf) time: 0.6225 [2021-03-26 10:27:37 swin_base_patch4_window7_224] INFO: Epoch: [53] [1170/1251] eta: 0:00:50 lr: 0.000923 loss: 3.9196 (3.7043) grad_norm: 1.0019 (inf) time: 0.6190 [2021-03-26 10:27:44 swin_base_patch4_window7_224] INFO: Epoch: [53] [1180/1251] eta: 0:00:44 lr: 0.000923 loss: 3.9047 (3.7039) grad_norm: 0.9748 (inf) time: 0.6169 [2021-03-26 10:27:50 swin_base_patch4_window7_224] INFO: Epoch: [53] [1190/1251] eta: 0:00:38 lr: 0.000923 loss: 3.8145 (3.7032) grad_norm: 0.9496 (inf) time: 0.6186 [2021-03-26 10:27:56 swin_base_patch4_window7_224] INFO: Epoch: [53] [1200/1251] eta: 0:00:32 lr: 0.000923 loss: 3.9133 (3.7055) grad_norm: 0.9976 (inf) time: 0.6245 [2021-03-26 10:28:02 swin_base_patch4_window7_224] INFO: Epoch: [53] [1210/1251] eta: 0:00:25 lr: 0.000923 loss: 3.9133 (3.7062) grad_norm: 1.1000 (inf) time: 0.6278 [2021-03-26 10:28:09 swin_base_patch4_window7_224] INFO: Epoch: [53] [1220/1251] eta: 0:00:19 lr: 0.000923 loss: 3.6851 (3.7052) grad_norm: 1.0394 (inf) time: 0.6262 [2021-03-26 10:28:15 swin_base_patch4_window7_224] INFO: Epoch: [53] [1230/1251] eta: 0:00:13 lr: 0.000923 loss: 3.3995 (3.7027) grad_norm: 1.0024 (inf) time: 0.6246 [2021-03-26 10:28:21 swin_base_patch4_window7_224] INFO: Epoch: [53] [1240/1251] eta: 0:00:06 lr: 0.000923 loss: 3.3980 (3.7033) grad_norm: 1.0474 (inf) time: 0.6191 [2021-03-26 10:28:27 swin_base_patch4_window7_224] INFO: Epoch: [53] [1250/1251] eta: 0:00:00 lr: 0.000923 loss: 3.3980 (3.6995) grad_norm: 1.1474 (inf) time: 0.6130 [2021-03-26 10:28:32 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:12 loss: 1.1885 (1.1885) acc1: 67.1875 (67.1875) acc5: 92.1875 (92.1875) [2021-03-26 10:28:33 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.1489 (1.1183) acc1: 75.0000 (72.8693) acc5: 93.7500 (91.7614) [2021-03-26 10:28:36 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0883 (1.1168) acc1: 75.0000 (72.8423) acc5: 93.7500 (92.7083) [2021-03-26 10:28:39 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0267 (1.0986) acc1: 75.0000 (73.2359) acc5: 92.1875 (92.2883) [2021-03-26 10:28:41 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1078 (1.1386) acc1: 71.8750 (72.5610) acc5: 90.6250 (91.7683) [2021-03-26 10:28:42 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1779 (1.1348) acc1: 71.8750 (72.4800) acc5: 90.6250 (91.7760) [2021-03-26 10:28:46 swin_base_patch4_window7_224] INFO: * Acc@1 73.128 Acc@5 91.904 loss 1.121 [2021-03-26 10:28:46 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.1% [2021-03-26 10:28:46 swin_base_patch4_window7_224] INFO: Max accuracy: 73.37% [2021-03-26 10:28:50 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 0/1251] eta: 1:30:31 lr: 0.000923 loss: 2.8317 (2.8317) grad_norm: 1.0497 (1.0497) time: 4.3417 [2021-03-26 10:28:57 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 10/1251] eta: 0:20:05 lr: 0.000923 loss: 3.9960 (3.8807) grad_norm: 1.0517 (1.0926) time: 0.9713 [2021-03-26 10:29:03 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 20/1251] eta: 0:16:32 lr: 0.000923 loss: 3.9227 (3.8956) grad_norm: 1.0517 (1.0985) time: 0.6296 [2021-03-26 10:29:09 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 30/1251] eta: 0:15:19 lr: 0.000923 loss: 3.8257 (3.8325) grad_norm: 1.0931 (1.1195) time: 0.6326 [2021-03-26 10:29:16 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 40/1251] eta: 0:14:36 lr: 0.000923 loss: 3.8257 (3.8166) grad_norm: 1.0931 (1.1028) time: 0.6376 [2021-03-26 10:29:22 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 50/1251] eta: 0:14:08 lr: 0.000923 loss: 3.9369 (3.7972) grad_norm: 1.0553 (1.0909) time: 0.6351 [2021-03-26 10:29:28 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 60/1251] eta: 0:13:43 lr: 0.000923 loss: 3.8956 (3.8008) grad_norm: 1.0542 (1.0801) time: 0.6253 [2021-03-26 10:29:34 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 70/1251] eta: 0:13:24 lr: 0.000923 loss: 3.8956 (3.8075) grad_norm: 1.0010 (1.0731) time: 0.6156 [2021-03-26 10:29:40 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 80/1251] eta: 0:13:08 lr: 0.000923 loss: 3.8326 (3.7707) grad_norm: 1.0010 (1.0786) time: 0.6169 [2021-03-26 10:29:47 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 90/1251] eta: 0:12:54 lr: 0.000923 loss: 3.8326 (3.7823) grad_norm: 0.9984 (1.0720) time: 0.6158 [2021-03-26 10:29:53 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 100/1251] eta: 0:12:42 lr: 0.000923 loss: 3.9387 (3.7642) grad_norm: 0.9711 (1.0734) time: 0.6197 [2021-03-26 10:29:59 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 110/1251] eta: 0:12:31 lr: 0.000923 loss: 3.9387 (3.7775) grad_norm: 0.9646 (1.0660) time: 0.6204 [2021-03-26 10:30:05 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 120/1251] eta: 0:12:22 lr: 0.000923 loss: 3.9014 (3.7903) grad_norm: 1.0224 (1.0653) time: 0.6237 [2021-03-26 10:30:12 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 130/1251] eta: 0:12:13 lr: 0.000923 loss: 3.7429 (3.7889) grad_norm: 1.0426 (1.0648) time: 0.6333 [2021-03-26 10:30:18 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 140/1251] eta: 0:12:05 lr: 0.000923 loss: 3.7845 (3.7912) grad_norm: 1.0852 (1.0725) time: 0.6354 [2021-03-26 10:30:24 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 150/1251] eta: 0:11:56 lr: 0.000923 loss: 3.9925 (3.8002) grad_norm: 1.2056 (1.0802) time: 0.6280 [2021-03-26 10:30:30 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 160/1251] eta: 0:11:48 lr: 0.000923 loss: 3.8988 (3.7890) grad_norm: 1.1443 (1.0854) time: 0.6204 [2021-03-26 10:30:37 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 170/1251] eta: 0:11:41 lr: 0.000923 loss: 3.5698 (3.7668) grad_norm: 1.0685 (1.0849) time: 0.6315 [2021-03-26 10:30:43 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 180/1251] eta: 0:11:33 lr: 0.000923 loss: 3.7309 (3.7710) grad_norm: 1.0300 (1.0814) time: 0.6309 [2021-03-26 10:30:49 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 190/1251] eta: 0:11:24 lr: 0.000923 loss: 3.7373 (3.7559) grad_norm: 0.9967 (1.0837) time: 0.6180 [2021-03-26 10:30:55 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 200/1251] eta: 0:11:17 lr: 0.000922 loss: 3.7889 (3.7600) grad_norm: 1.0313 (1.0832) time: 0.6176 [2021-03-26 10:31:02 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 210/1251] eta: 0:11:09 lr: 0.000922 loss: 3.5941 (3.7524) grad_norm: 1.0029 (1.0818) time: 0.6187 [2021-03-26 10:31:08 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 220/1251] eta: 0:11:02 lr: 0.000922 loss: 3.5751 (3.7436) grad_norm: 1.0811 (1.0853) time: 0.6253 [2021-03-26 10:31:14 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 230/1251] eta: 0:10:55 lr: 0.000922 loss: 3.5751 (3.7373) grad_norm: 1.1542 (1.0865) time: 0.6321 [2021-03-26 10:31:21 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 240/1251] eta: 0:10:48 lr: 0.000922 loss: 3.5859 (3.7378) grad_norm: 1.1033 (1.0896) time: 0.6291 [2021-03-26 10:31:27 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 250/1251] eta: 0:10:41 lr: 0.000922 loss: 3.9210 (3.7476) grad_norm: 1.1033 (1.0892) time: 0.6283 [2021-03-26 10:31:33 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 260/1251] eta: 0:10:34 lr: 0.000922 loss: 3.9026 (3.7525) grad_norm: 1.0533 (1.0873) time: 0.6289 [2021-03-26 10:31:39 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 270/1251] eta: 0:10:27 lr: 0.000922 loss: 3.7759 (3.7533) grad_norm: 1.0425 (1.0871) time: 0.6248 [2021-03-26 10:31:45 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 280/1251] eta: 0:10:20 lr: 0.000922 loss: 3.7415 (3.7536) grad_norm: 1.0045 (1.0854) time: 0.6199 [2021-03-26 10:31:52 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 290/1251] eta: 0:10:13 lr: 0.000922 loss: 3.5297 (3.7447) grad_norm: 0.9774 (1.0871) time: 0.6215 [2021-03-26 10:31:58 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 300/1251] eta: 0:10:06 lr: 0.000922 loss: 3.3497 (3.7331) grad_norm: 1.1325 (1.0913) time: 0.6269 [2021-03-26 10:32:04 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 310/1251] eta: 0:10:00 lr: 0.000922 loss: 3.3728 (3.7283) grad_norm: 1.0529 (1.0875) time: 0.6270 [2021-03-26 10:32:11 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 320/1251] eta: 0:09:53 lr: 0.000922 loss: 3.6273 (3.7258) grad_norm: 0.9767 (1.0878) time: 0.6260 [2021-03-26 10:32:17 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 330/1251] eta: 0:09:46 lr: 0.000922 loss: 3.7380 (3.7293) grad_norm: 1.0170 (1.0885) time: 0.6258 [2021-03-26 10:32:23 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 340/1251] eta: 0:09:40 lr: 0.000922 loss: 3.7702 (3.7324) grad_norm: 1.0232 (1.0884) time: 0.6254 [2021-03-26 10:32:29 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 350/1251] eta: 0:09:33 lr: 0.000922 loss: 3.8362 (3.7348) grad_norm: 1.0275 (1.0875) time: 0.6275 [2021-03-26 10:32:36 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 360/1251] eta: 0:09:26 lr: 0.000922 loss: 3.8247 (3.7315) grad_norm: 0.9792 (1.0841) time: 0.6230 [2021-03-26 10:32:42 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 370/1251] eta: 0:09:19 lr: 0.000922 loss: 3.7142 (3.7314) grad_norm: 0.9801 (1.0821) time: 0.6151 [2021-03-26 10:32:48 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 380/1251] eta: 0:09:12 lr: 0.000922 loss: 3.5725 (3.7241) grad_norm: 1.0239 (1.0820) time: 0.6162 [2021-03-26 10:32:54 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 390/1251] eta: 0:09:06 lr: 0.000922 loss: 3.5725 (3.7246) grad_norm: 1.0307 (1.0834) time: 0.6216 [2021-03-26 10:33:00 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 400/1251] eta: 0:08:59 lr: 0.000922 loss: 3.8064 (3.7251) grad_norm: 1.0113 (1.0816) time: 0.6176 [2021-03-26 10:33:06 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 410/1251] eta: 0:08:52 lr: 0.000922 loss: 3.7139 (3.7236) grad_norm: 0.9542 (1.0787) time: 0.6144 [2021-03-26 10:33:13 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 420/1251] eta: 0:08:46 lr: 0.000922 loss: 3.7139 (3.7225) grad_norm: 1.0270 (1.0787) time: 0.6294 [2021-03-26 10:33:19 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 430/1251] eta: 0:08:40 lr: 0.000922 loss: 4.0259 (3.7287) grad_norm: 1.0760 (1.0789) time: 0.6338 [2021-03-26 10:33:25 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 440/1251] eta: 0:08:33 lr: 0.000922 loss: 3.8981 (3.7217) grad_norm: 1.0706 (1.0807) time: 0.6270 [2021-03-26 10:33:32 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 450/1251] eta: 0:08:27 lr: 0.000922 loss: 3.8981 (3.7237) grad_norm: 1.0684 (1.0801) time: 0.6234 [2021-03-26 10:33:38 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 460/1251] eta: 0:08:20 lr: 0.000922 loss: 3.9863 (3.7232) grad_norm: 1.0038 (1.0781) time: 0.6156 [2021-03-26 10:33:44 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 470/1251] eta: 0:08:13 lr: 0.000922 loss: 3.7773 (3.7205) grad_norm: 1.0424 (1.0775) time: 0.6149 [2021-03-26 10:33:50 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 480/1251] eta: 0:08:07 lr: 0.000922 loss: 3.8063 (3.7246) grad_norm: 1.0622 (1.0775) time: 0.6212 [2021-03-26 10:33:56 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 490/1251] eta: 0:08:00 lr: 0.000922 loss: 3.9155 (3.7262) grad_norm: 1.0653 (1.0767) time: 0.6222 [2021-03-26 10:34:02 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 500/1251] eta: 0:07:54 lr: 0.000922 loss: 3.6777 (3.7226) grad_norm: 1.0538 (1.0759) time: 0.6172 [2021-03-26 10:34:09 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 510/1251] eta: 0:07:47 lr: 0.000922 loss: 3.8002 (3.7250) grad_norm: 1.0715 (1.0783) time: 0.6183 [2021-03-26 10:34:15 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 520/1251] eta: 0:07:41 lr: 0.000922 loss: 3.8002 (3.7249) grad_norm: 1.1617 (1.0794) time: 0.6249 [2021-03-26 10:34:21 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 530/1251] eta: 0:07:35 lr: 0.000922 loss: 3.5937 (3.7203) grad_norm: 1.1353 (1.0804) time: 0.6331 [2021-03-26 10:34:28 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 540/1251] eta: 0:07:29 lr: 0.000922 loss: 3.5937 (3.7203) grad_norm: 1.0588 (1.0804) time: 0.6380 [2021-03-26 10:34:34 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 550/1251] eta: 0:07:22 lr: 0.000922 loss: 3.9322 (3.7258) grad_norm: 1.0972 (1.0816) time: 0.6357 [2021-03-26 10:34:40 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 560/1251] eta: 0:07:16 lr: 0.000922 loss: 3.9322 (3.7272) grad_norm: 1.0741 (1.0807) time: 0.6320 [2021-03-26 10:34:47 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 570/1251] eta: 0:07:10 lr: 0.000922 loss: 3.5308 (3.7195) grad_norm: 1.0174 (1.0800) time: 0.6270 [2021-03-26 10:34:53 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 580/1251] eta: 0:07:03 lr: 0.000922 loss: 3.7404 (3.7260) grad_norm: 1.0204 (1.0788) time: 0.6229 [2021-03-26 10:34:59 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 590/1251] eta: 0:06:57 lr: 0.000922 loss: 3.8637 (3.7263) grad_norm: 0.9708 (1.0782) time: 0.6179 [2021-03-26 10:35:05 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 600/1251] eta: 0:06:50 lr: 0.000922 loss: 3.7474 (3.7273) grad_norm: 1.0069 (1.0775) time: 0.6264 [2021-03-26 10:35:11 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 610/1251] eta: 0:06:44 lr: 0.000922 loss: 3.7296 (3.7244) grad_norm: 0.9851 (1.0759) time: 0.6255 [2021-03-26 10:35:18 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 620/1251] eta: 0:06:37 lr: 0.000922 loss: 3.8743 (3.7285) grad_norm: 0.9629 (1.0751) time: 0.6153 [2021-03-26 10:35:24 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 630/1251] eta: 0:06:31 lr: 0.000922 loss: 4.0391 (3.7345) grad_norm: 0.9540 (1.0736) time: 0.6160 [2021-03-26 10:35:30 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 640/1251] eta: 0:06:25 lr: 0.000922 loss: 3.9749 (3.7346) grad_norm: 0.9925 (1.0729) time: 0.6229 [2021-03-26 10:35:36 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 650/1251] eta: 0:06:18 lr: 0.000921 loss: 3.6400 (3.7347) grad_norm: 1.0071 (1.0719) time: 0.6225 [2021-03-26 10:35:42 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 660/1251] eta: 0:06:12 lr: 0.000921 loss: 3.7148 (3.7349) grad_norm: 1.0257 (1.0724) time: 0.6157 [2021-03-26 10:35:49 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 670/1251] eta: 0:06:05 lr: 0.000921 loss: 3.9459 (3.7372) grad_norm: 1.1108 (1.0741) time: 0.6209 [2021-03-26 10:35:55 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 680/1251] eta: 0:05:59 lr: 0.000921 loss: 3.9147 (3.7388) grad_norm: 1.0654 (1.0730) time: 0.6208 [2021-03-26 10:36:01 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 690/1251] eta: 0:05:53 lr: 0.000921 loss: 3.9147 (3.7405) grad_norm: 1.0595 (1.0742) time: 0.6193 [2021-03-26 10:36:07 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 700/1251] eta: 0:05:46 lr: 0.000921 loss: 3.8959 (3.7418) grad_norm: 1.1434 (1.0752) time: 0.6258 [2021-03-26 10:36:14 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 710/1251] eta: 0:05:40 lr: 0.000921 loss: 3.8959 (3.7436) grad_norm: 1.0927 (1.0760) time: 0.6304 [2021-03-26 10:36:20 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 720/1251] eta: 0:05:34 lr: 0.000921 loss: 3.9656 (3.7441) grad_norm: 1.0900 (1.0763) time: 0.6312 [2021-03-26 10:36:26 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 730/1251] eta: 0:05:28 lr: 0.000921 loss: 3.7245 (3.7410) grad_norm: 1.0902 (1.0771) time: 0.6352 [2021-03-26 10:36:33 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 740/1251] eta: 0:05:21 lr: 0.000921 loss: 3.5944 (3.7380) grad_norm: 1.0537 (1.0763) time: 0.6372 [2021-03-26 10:36:39 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 750/1251] eta: 0:05:15 lr: 0.000921 loss: 3.6355 (3.7413) grad_norm: 1.0578 (1.0773) time: 0.6353 [2021-03-26 10:36:45 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 760/1251] eta: 0:05:09 lr: 0.000921 loss: 4.1594 (3.7429) grad_norm: 1.1294 (1.0781) time: 0.6339 [2021-03-26 10:36:52 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 770/1251] eta: 0:05:02 lr: 0.000921 loss: 3.8222 (3.7442) grad_norm: 1.1036 (1.0782) time: 0.6310 [2021-03-26 10:36:58 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 780/1251] eta: 0:04:56 lr: 0.000921 loss: 3.7880 (3.7455) grad_norm: 1.0686 (1.0782) time: 0.6209 [2021-03-26 10:37:04 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 790/1251] eta: 0:04:50 lr: 0.000921 loss: 3.7312 (3.7462) grad_norm: 1.0609 (1.0784) time: 0.6211 [2021-03-26 10:37:10 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 800/1251] eta: 0:04:43 lr: 0.000921 loss: 3.8380 (3.7476) grad_norm: 1.0968 (1.0785) time: 0.6253 [2021-03-26 10:37:17 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 810/1251] eta: 0:04:37 lr: 0.000921 loss: 4.0333 (3.7497) grad_norm: 0.9719 (1.0773) time: 0.6219 [2021-03-26 10:37:23 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 820/1251] eta: 0:04:31 lr: 0.000921 loss: 4.1138 (3.7543) grad_norm: 0.9719 (1.0770) time: 0.6175 [2021-03-26 10:37:29 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 830/1251] eta: 0:04:24 lr: 0.000921 loss: 3.8585 (3.7545) grad_norm: 1.0694 (1.0784) time: 0.6177 [2021-03-26 10:37:35 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 840/1251] eta: 0:04:18 lr: 0.000921 loss: 3.6434 (3.7513) grad_norm: 1.0806 (1.0779) time: 0.6240 [2021-03-26 10:37:42 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 850/1251] eta: 0:04:12 lr: 0.000921 loss: 3.7797 (3.7528) grad_norm: 1.0252 (1.0777) time: 0.6310 [2021-03-26 10:37:48 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 860/1251] eta: 0:04:06 lr: 0.000921 loss: 3.9749 (3.7528) grad_norm: 1.0688 (1.0784) time: 0.6373 [2021-03-26 10:37:54 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 870/1251] eta: 0:03:59 lr: 0.000921 loss: 3.6507 (3.7512) grad_norm: 1.1320 (1.0786) time: 0.6304 [2021-03-26 10:38:00 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 880/1251] eta: 0:03:53 lr: 0.000921 loss: 3.8618 (3.7556) grad_norm: 1.1174 (1.0789) time: 0.6238 [2021-03-26 10:38:07 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 890/1251] eta: 0:03:47 lr: 0.000921 loss: 4.1543 (3.7595) grad_norm: 1.0532 (1.0786) time: 0.6308 [2021-03-26 10:38:13 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 900/1251] eta: 0:03:40 lr: 0.000921 loss: 3.9370 (3.7571) grad_norm: 1.0532 (1.0787) time: 0.6270 [2021-03-26 10:38:19 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 910/1251] eta: 0:03:34 lr: 0.000921 loss: 3.8200 (3.7590) grad_norm: 1.0931 (1.0799) time: 0.6213 [2021-03-26 10:38:25 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 920/1251] eta: 0:03:28 lr: 0.000921 loss: 4.0121 (3.7577) grad_norm: 1.1154 (1.0808) time: 0.6264 [2021-03-26 10:38:32 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 930/1251] eta: 0:03:21 lr: 0.000921 loss: 3.9544 (3.7568) grad_norm: 1.0314 (1.0805) time: 0.6309 [2021-03-26 10:38:38 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 940/1251] eta: 0:03:15 lr: 0.000921 loss: 3.7590 (3.7563) grad_norm: 1.0473 (1.0813) time: 0.6322 [2021-03-26 10:38:44 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 950/1251] eta: 0:03:09 lr: 0.000921 loss: 3.7170 (3.7539) grad_norm: 1.1131 (1.0819) time: 0.6332 [2021-03-26 10:38:51 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 960/1251] eta: 0:03:03 lr: 0.000921 loss: 3.4794 (3.7530) grad_norm: 1.0499 (1.0813) time: 0.6278 [2021-03-26 10:38:57 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 970/1251] eta: 0:02:56 lr: 0.000921 loss: 3.8957 (3.7526) grad_norm: 0.9753 (1.0803) time: 0.6263 [2021-03-26 10:39:03 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 980/1251] eta: 0:02:50 lr: 0.000921 loss: 3.9837 (3.7545) grad_norm: 0.9989 (1.0805) time: 0.6346 [2021-03-26 10:39:10 swin_base_patch4_window7_224] INFO: Epoch: [54] [ 990/1251] eta: 0:02:44 lr: 0.000921 loss: 4.0006 (3.7567) grad_norm: 1.0505 (1.0801) time: 0.6269 [2021-03-26 10:39:16 swin_base_patch4_window7_224] INFO: Epoch: [54] [1000/1251] eta: 0:02:37 lr: 0.000921 loss: 3.9168 (3.7571) grad_norm: 1.0248 (1.0802) time: 0.6162 [2021-03-26 10:39:22 swin_base_patch4_window7_224] INFO: Epoch: [54] [1010/1251] eta: 0:02:31 lr: 0.000921 loss: 3.8448 (3.7587) grad_norm: 0.9871 (1.0793) time: 0.6235 [2021-03-26 10:39:28 swin_base_patch4_window7_224] INFO: Epoch: [54] [1020/1251] eta: 0:02:25 lr: 0.000921 loss: 3.9448 (3.7591) grad_norm: 0.9947 (1.0790) time: 0.6239 [2021-03-26 10:39:34 swin_base_patch4_window7_224] INFO: Epoch: [54] [1030/1251] eta: 0:02:18 lr: 0.000921 loss: 3.8943 (3.7583) grad_norm: 1.0395 (1.0784) time: 0.6142 [2021-03-26 10:39:41 swin_base_patch4_window7_224] INFO: Epoch: [54] [1040/1251] eta: 0:02:12 lr: 0.000921 loss: 3.8492 (3.7588) grad_norm: 1.0444 (1.0791) time: 0.6206 [2021-03-26 10:39:47 swin_base_patch4_window7_224] INFO: Epoch: [54] [1050/1251] eta: 0:02:06 lr: 0.000921 loss: 3.7802 (3.7572) grad_norm: 1.0535 (1.0793) time: 0.6288 [2021-03-26 10:39:53 swin_base_patch4_window7_224] INFO: Epoch: [54] [1060/1251] eta: 0:02:00 lr: 0.000921 loss: 3.7473 (3.7559) grad_norm: 1.0535 (1.0789) time: 0.6257 [2021-03-26 10:39:59 swin_base_patch4_window7_224] INFO: Epoch: [54] [1070/1251] eta: 0:01:53 lr: 0.000921 loss: 3.9133 (3.7576) grad_norm: 1.0423 (1.0789) time: 0.6176 [2021-03-26 10:40:06 swin_base_patch4_window7_224] INFO: Epoch: [54] [1080/1251] eta: 0:01:47 lr: 0.000921 loss: 3.8646 (3.7568) grad_norm: 1.0317 (1.0791) time: 0.6188 [2021-03-26 10:40:12 swin_base_patch4_window7_224] INFO: Epoch: [54] [1090/1251] eta: 0:01:41 lr: 0.000921 loss: 3.7753 (3.7568) grad_norm: 1.0876 (1.0794) time: 0.6306 [2021-03-26 10:40:18 swin_base_patch4_window7_224] INFO: Epoch: [54] [1100/1251] eta: 0:01:34 lr: 0.000920 loss: 3.7753 (3.7565) grad_norm: 1.0655 (1.0798) time: 0.6347 [2021-03-26 10:40:24 swin_base_patch4_window7_224] INFO: Epoch: [54] [1110/1251] eta: 0:01:28 lr: 0.000920 loss: 3.8688 (3.7569) grad_norm: 1.0655 (1.0803) time: 0.6257 [2021-03-26 10:40:31 swin_base_patch4_window7_224] INFO: Epoch: [54] [1120/1251] eta: 0:01:22 lr: 0.000920 loss: 3.8688 (3.7568) grad_norm: 1.0757 (1.0803) time: 0.6256 [2021-03-26 10:40:37 swin_base_patch4_window7_224] INFO: Epoch: [54] [1130/1251] eta: 0:01:16 lr: 0.000920 loss: 3.6394 (3.7546) grad_norm: 1.0844 (1.0813) time: 0.6283 [2021-03-26 10:40:43 swin_base_patch4_window7_224] INFO: Epoch: [54] [1140/1251] eta: 0:01:09 lr: 0.000920 loss: 3.6394 (3.7537) grad_norm: 1.0602 (1.0809) time: 0.6242 [2021-03-26 10:40:50 swin_base_patch4_window7_224] INFO: Epoch: [54] [1150/1251] eta: 0:01:03 lr: 0.000920 loss: 3.5483 (3.7527) grad_norm: 1.0302 (1.0804) time: 0.6295 [2021-03-26 10:40:56 swin_base_patch4_window7_224] INFO: Epoch: [54] [1160/1251] eta: 0:00:57 lr: 0.000920 loss: 3.8964 (3.7539) grad_norm: 1.0747 (1.0815) time: 0.6303 [2021-03-26 10:41:02 swin_base_patch4_window7_224] INFO: Epoch: [54] [1170/1251] eta: 0:00:50 lr: 0.000920 loss: 3.9546 (3.7569) grad_norm: 1.1067 (1.0812) time: 0.6258 [2021-03-26 10:41:08 swin_base_patch4_window7_224] INFO: Epoch: [54] [1180/1251] eta: 0:00:44 lr: 0.000920 loss: 3.9404 (3.7553) grad_norm: 1.1067 (1.0822) time: 0.6233 [2021-03-26 10:41:15 swin_base_patch4_window7_224] INFO: Epoch: [54] [1190/1251] eta: 0:00:38 lr: 0.000920 loss: 3.6592 (3.7554) grad_norm: 1.1024 (1.0820) time: 0.6221 [2021-03-26 10:41:21 swin_base_patch4_window7_224] INFO: Epoch: [54] [1200/1251] eta: 0:00:32 lr: 0.000920 loss: 3.8731 (3.7555) grad_norm: 1.0121 (1.0814) time: 0.6188 [2021-03-26 10:41:27 swin_base_patch4_window7_224] INFO: Epoch: [54] [1210/1251] eta: 0:00:25 lr: 0.000920 loss: 3.7359 (3.7533) grad_norm: 1.0095 (1.0808) time: 0.6161 [2021-03-26 10:41:33 swin_base_patch4_window7_224] INFO: Epoch: [54] [1220/1251] eta: 0:00:19 lr: 0.000920 loss: 3.4545 (3.7517) grad_norm: 1.0095 (1.0811) time: 0.6175 [2021-03-26 10:41:39 swin_base_patch4_window7_224] INFO: Epoch: [54] [1230/1251] eta: 0:00:13 lr: 0.000920 loss: 3.5561 (3.7506) grad_norm: 1.1655 (1.0829) time: 0.6239 [2021-03-26 10:41:45 swin_base_patch4_window7_224] INFO: Epoch: [54] [1240/1251] eta: 0:00:06 lr: 0.000920 loss: 3.8476 (3.7496) grad_norm: 1.0871 (1.0826) time: 0.6227 [2021-03-26 10:41:52 swin_base_patch4_window7_224] INFO: Epoch: [54] [1250/1251] eta: 0:00:00 lr: 0.000920 loss: 3.9572 (3.7501) grad_norm: 1.0611 (1.0841) time: 0.6196 [2021-03-26 10:41:55 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:27 loss: 1.2844 (1.2844) acc1: 71.8750 (71.8750) acc5: 85.9375 (85.9375) [2021-03-26 10:41:58 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.1454 (1.1238) acc1: 73.4375 (73.1534) acc5: 90.6250 (91.0511) [2021-03-26 10:42:01 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0611 (1.1359) acc1: 73.4375 (72.6190) acc5: 92.1875 (92.0387) [2021-03-26 10:42:03 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0509 (1.1448) acc1: 73.4375 (72.0766) acc5: 92.1875 (92.3387) [2021-03-26 10:42:05 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2183 (1.1748) acc1: 71.8750 (71.5320) acc5: 92.1875 (91.9970) [2021-03-26 10:42:06 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2922 (1.1862) acc1: 71.8750 (71.9680) acc5: 90.6250 (91.8720) [2021-03-26 10:42:09 swin_base_patch4_window7_224] INFO: * Acc@1 73.164 Acc@5 92.118 loss 1.155 [2021-03-26 10:42:09 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.2% [2021-03-26 10:42:09 swin_base_patch4_window7_224] INFO: Max accuracy: 73.37% [2021-03-26 10:42:14 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 0/1251] eta: 1:29:20 lr: 0.000920 loss: 3.9234 (3.9234) grad_norm: 0.9224 (0.9224) time: 4.2854 [2021-03-26 10:42:20 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 10/1251] eta: 0:19:46 lr: 0.000920 loss: 3.9150 (3.6908) grad_norm: 0.9857 (1.0054) time: 0.9560 [2021-03-26 10:42:26 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 20/1251] eta: 0:16:18 lr: 0.000920 loss: 3.8102 (3.7437) grad_norm: 0.9890 (1.0149) time: 0.6199 [2021-03-26 10:42:32 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 30/1251] eta: 0:14:59 lr: 0.000920 loss: 3.7941 (3.7562) grad_norm: 0.9681 (1.0004) time: 0.6166 [2021-03-26 10:42:38 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 40/1251] eta: 0:14:19 lr: 0.000920 loss: 3.7995 (3.7455) grad_norm: 0.9681 (1.0079) time: 0.6209 [2021-03-26 10:42:45 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 50/1251] eta: 0:13:50 lr: 0.000920 loss: 3.8288 (3.7252) grad_norm: 1.0376 (1.0185) time: 0.6218 [2021-03-26 10:42:51 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 60/1251] eta: 0:13:30 lr: 0.000920 loss: 3.6296 (3.6955) grad_norm: 1.0577 (1.0285) time: 0.6199 [2021-03-26 10:42:57 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 70/1251] eta: 0:13:14 lr: 0.000920 loss: 3.5247 (3.6709) grad_norm: 1.0923 (1.0434) time: 0.6237 [2021-03-26 10:43:03 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 80/1251] eta: 0:12:59 lr: 0.000920 loss: 3.7779 (3.6895) grad_norm: 1.0524 (1.0403) time: 0.6208 [2021-03-26 10:43:09 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 90/1251] eta: 0:12:46 lr: 0.000920 loss: 3.8185 (3.7048) grad_norm: 1.0003 (1.0378) time: 0.6174 [2021-03-26 10:43:16 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 100/1251] eta: 0:12:36 lr: 0.000920 loss: 3.7754 (3.6958) grad_norm: 1.0057 (1.0442) time: 0.6217 [2021-03-26 10:43:22 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 110/1251] eta: 0:12:26 lr: 0.000920 loss: 3.6945 (3.6986) grad_norm: 1.0057 (1.0453) time: 0.6269 [2021-03-26 10:43:28 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 120/1251] eta: 0:12:16 lr: 0.000920 loss: 3.9140 (3.7159) grad_norm: 0.9931 (1.0460) time: 0.6236 [2021-03-26 10:43:34 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 130/1251] eta: 0:12:07 lr: 0.000920 loss: 3.9146 (3.7199) grad_norm: 1.0545 (1.0505) time: 0.6205 [2021-03-26 10:43:41 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 140/1251] eta: 0:11:59 lr: 0.000920 loss: 3.9267 (3.7400) grad_norm: 1.0973 (1.0575) time: 0.6274 [2021-03-26 10:43:47 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 150/1251] eta: 0:11:51 lr: 0.000920 loss: 3.9267 (3.7308) grad_norm: 1.0993 (1.0586) time: 0.6266 [2021-03-26 10:43:53 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 160/1251] eta: 0:11:43 lr: 0.000920 loss: 3.8746 (3.7440) grad_norm: 1.0506 (1.0574) time: 0.6195 [2021-03-26 10:43:59 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 170/1251] eta: 0:11:34 lr: 0.000920 loss: 3.9594 (3.7429) grad_norm: 1.0694 (1.0606) time: 0.6169 [2021-03-26 10:44:06 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 180/1251] eta: 0:11:27 lr: 0.000920 loss: 3.7720 (3.7392) grad_norm: 1.0897 (1.0601) time: 0.6234 [2021-03-26 10:44:12 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 190/1251] eta: 0:11:20 lr: 0.000920 loss: 3.7720 (3.7369) grad_norm: 1.0261 (1.0637) time: 0.6301 [2021-03-26 10:44:18 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 200/1251] eta: 0:11:13 lr: 0.000920 loss: 3.9977 (3.7488) grad_norm: 1.1125 (1.0703) time: 0.6332 [2021-03-26 10:44:24 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 210/1251] eta: 0:11:06 lr: 0.000920 loss: 4.0720 (3.7483) grad_norm: 1.1470 (1.0710) time: 0.6280 [2021-03-26 10:44:31 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 220/1251] eta: 0:10:59 lr: 0.000920 loss: 3.8101 (3.7480) grad_norm: 1.0757 (1.0706) time: 0.6212 [2021-03-26 10:44:37 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 230/1251] eta: 0:10:51 lr: 0.000920 loss: 3.6902 (3.7447) grad_norm: 1.0347 (1.0715) time: 0.6200 [2021-03-26 10:44:43 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 240/1251] eta: 0:10:44 lr: 0.000920 loss: 3.5494 (3.7322) grad_norm: 1.0388 (1.0699) time: 0.6198 [2021-03-26 10:44:49 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 250/1251] eta: 0:10:37 lr: 0.000920 loss: 3.7992 (3.7475) grad_norm: 1.0414 (1.0701) time: 0.6242 [2021-03-26 10:44:55 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 260/1251] eta: 0:10:30 lr: 0.000920 loss: 4.0216 (3.7507) grad_norm: 1.0940 (1.0720) time: 0.6228 [2021-03-26 10:45:02 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 270/1251] eta: 0:10:24 lr: 0.000920 loss: 3.6330 (3.7389) grad_norm: 1.0523 (1.0697) time: 0.6220 [2021-03-26 10:45:08 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 280/1251] eta: 0:10:17 lr: 0.000920 loss: 3.4280 (3.7339) grad_norm: 1.0605 (1.0719) time: 0.6286 [2021-03-26 10:45:14 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 290/1251] eta: 0:10:11 lr: 0.000919 loss: 3.3660 (3.7230) grad_norm: 1.0816 (1.0732) time: 0.6347 [2021-03-26 10:45:21 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 300/1251] eta: 0:10:04 lr: 0.000919 loss: 3.3660 (3.7172) grad_norm: 1.1169 (1.0759) time: 0.6339 [2021-03-26 10:45:27 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 310/1251] eta: 0:09:58 lr: 0.000919 loss: 3.5311 (3.7195) grad_norm: 1.1321 (1.0800) time: 0.6301 [2021-03-26 10:45:33 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 320/1251] eta: 0:09:51 lr: 0.000919 loss: 3.5311 (3.7148) grad_norm: 1.1130 (1.0776) time: 0.6272 [2021-03-26 10:45:40 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 330/1251] eta: 0:09:44 lr: 0.000919 loss: 3.8046 (3.7159) grad_norm: 1.0382 (1.0770) time: 0.6247 [2021-03-26 10:45:46 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 340/1251] eta: 0:09:38 lr: 0.000919 loss: 3.6760 (3.7111) grad_norm: 1.0789 (1.0774) time: 0.6271 [2021-03-26 10:45:52 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 350/1251] eta: 0:09:31 lr: 0.000919 loss: 3.5763 (3.7072) grad_norm: 1.0644 (1.0771) time: 0.6276 [2021-03-26 10:45:58 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 360/1251] eta: 0:09:25 lr: 0.000919 loss: 3.7682 (3.7068) grad_norm: 1.0619 (1.0771) time: 0.6276 [2021-03-26 10:46:05 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 370/1251] eta: 0:09:18 lr: 0.000919 loss: 3.6931 (3.7080) grad_norm: 0.9893 (1.0745) time: 0.6224 [2021-03-26 10:46:11 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 380/1251] eta: 0:09:11 lr: 0.000919 loss: 3.6805 (3.7085) grad_norm: 0.9796 (1.0731) time: 0.6184 [2021-03-26 10:46:17 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 390/1251] eta: 0:09:05 lr: 0.000919 loss: 3.4570 (3.7007) grad_norm: 1.0405 (1.0737) time: 0.6238 [2021-03-26 10:46:23 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 400/1251] eta: 0:08:59 lr: 0.000919 loss: 3.6334 (3.7022) grad_norm: 1.0540 (1.0726) time: 0.6311 [2021-03-26 10:46:30 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 410/1251] eta: 0:08:52 lr: 0.000919 loss: 3.8662 (3.7063) grad_norm: 1.0540 (1.0737) time: 0.6261 [2021-03-26 10:46:36 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 420/1251] eta: 0:08:46 lr: 0.000919 loss: 3.8662 (3.7090) grad_norm: 1.1148 (1.0765) time: 0.6282 [2021-03-26 10:46:42 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 430/1251] eta: 0:08:39 lr: 0.000919 loss: 3.7412 (3.7055) grad_norm: 1.0670 (1.0761) time: 0.6346 [2021-03-26 10:46:48 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 440/1251] eta: 0:08:33 lr: 0.000919 loss: 3.7412 (3.7038) grad_norm: 1.0498 (1.0761) time: 0.6233 [2021-03-26 10:46:54 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 450/1251] eta: 0:08:26 lr: 0.000919 loss: 3.7518 (3.7011) grad_norm: 1.0041 (1.0743) time: 0.6131 [2021-03-26 10:47:01 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 460/1251] eta: 0:08:19 lr: 0.000919 loss: 3.6056 (3.7002) grad_norm: 1.0041 (1.0743) time: 0.6139 [2021-03-26 10:47:07 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 470/1251] eta: 0:08:13 lr: 0.000919 loss: 3.6056 (3.6965) grad_norm: 0.9941 (1.0729) time: 0.6218 [2021-03-26 10:47:13 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 480/1251] eta: 0:08:06 lr: 0.000919 loss: 3.7481 (3.6978) grad_norm: 1.0845 (1.0745) time: 0.6222 [2021-03-26 10:47:19 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 490/1251] eta: 0:08:00 lr: 0.000919 loss: 3.7481 (3.6993) grad_norm: 1.1419 (1.0757) time: 0.6223 [2021-03-26 10:47:26 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 500/1251] eta: 0:07:54 lr: 0.000919 loss: 3.8863 (3.7018) grad_norm: 1.0827 (1.0749) time: 0.6227 [2021-03-26 10:47:32 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 510/1251] eta: 0:07:47 lr: 0.000919 loss: 3.9628 (3.7047) grad_norm: 1.0098 (1.0740) time: 0.6215 [2021-03-26 10:47:38 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 520/1251] eta: 0:07:41 lr: 0.000919 loss: 3.7741 (3.7063) grad_norm: 1.0432 (1.0750) time: 0.6192 [2021-03-26 10:47:44 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 530/1251] eta: 0:07:34 lr: 0.000919 loss: 3.7700 (3.7061) grad_norm: 1.0432 (1.0748) time: 0.6180 [2021-03-26 10:47:50 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 540/1251] eta: 0:07:28 lr: 0.000919 loss: 3.7291 (3.7079) grad_norm: 1.0038 (1.0743) time: 0.6190 [2021-03-26 10:47:57 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 550/1251] eta: 0:07:22 lr: 0.000919 loss: 3.8791 (3.7111) grad_norm: 1.0672 (1.0757) time: 0.6360 [2021-03-26 10:48:03 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 560/1251] eta: 0:07:15 lr: 0.000919 loss: 3.8480 (3.7125) grad_norm: 1.1036 (1.0765) time: 0.6415 [2021-03-26 10:48:09 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 570/1251] eta: 0:07:09 lr: 0.000919 loss: 3.8272 (3.7130) grad_norm: 1.0354 (1.0760) time: 0.6268 [2021-03-26 10:48:16 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 580/1251] eta: 0:07:03 lr: 0.000919 loss: 3.8272 (3.7144) grad_norm: 1.0263 (1.0762) time: 0.6224 [2021-03-26 10:48:22 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 590/1251] eta: 0:06:56 lr: 0.000919 loss: 3.8152 (3.7137) grad_norm: 1.0199 (1.0764) time: 0.6271 [2021-03-26 10:48:28 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 600/1251] eta: 0:06:50 lr: 0.000919 loss: 3.6999 (3.7128) grad_norm: 1.0235 (1.0759) time: 0.6356 [2021-03-26 10:48:35 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 610/1251] eta: 0:06:44 lr: 0.000919 loss: 3.6769 (3.7124) grad_norm: 1.0138 (1.0756) time: 0.6335 [2021-03-26 10:48:41 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 620/1251] eta: 0:06:37 lr: 0.000919 loss: 3.8780 (3.7155) grad_norm: 0.9737 (1.0740) time: 0.6205 [2021-03-26 10:48:47 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 630/1251] eta: 0:06:31 lr: 0.000919 loss: 3.9586 (3.7193) grad_norm: 1.0060 (1.0741) time: 0.6158 [2021-03-26 10:48:53 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 640/1251] eta: 0:06:24 lr: 0.000919 loss: 3.8990 (3.7211) grad_norm: 1.0095 (1.0730) time: 0.6201 [2021-03-26 10:49:00 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 650/1251] eta: 0:06:18 lr: 0.000919 loss: 3.7775 (3.7190) grad_norm: 1.0333 (1.0731) time: 0.6290 [2021-03-26 10:49:06 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 660/1251] eta: 0:06:12 lr: 0.000919 loss: 3.7561 (3.7192) grad_norm: 1.0438 (1.0731) time: 0.6327 [2021-03-26 10:49:12 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 670/1251] eta: 0:06:06 lr: 0.000919 loss: 3.7356 (3.7145) grad_norm: 1.0527 (1.0738) time: 0.6259 [2021-03-26 10:49:18 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 680/1251] eta: 0:05:59 lr: 0.000919 loss: 3.6643 (3.7159) grad_norm: 1.0899 (1.0741) time: 0.6245 [2021-03-26 10:49:25 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 690/1251] eta: 0:05:53 lr: 0.000919 loss: 3.7090 (3.7153) grad_norm: 1.0627 (1.0740) time: 0.6226 [2021-03-26 10:49:31 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 700/1251] eta: 0:05:47 lr: 0.000919 loss: 3.7090 (3.7131) grad_norm: 1.0611 (1.0757) time: 0.6294 [2021-03-26 10:49:37 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 710/1251] eta: 0:05:40 lr: 0.000919 loss: 3.6040 (3.7108) grad_norm: 1.0745 (1.0760) time: 0.6319 [2021-03-26 10:49:43 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 720/1251] eta: 0:05:34 lr: 0.000919 loss: 3.5618 (3.7092) grad_norm: 1.1015 (1.0776) time: 0.6284 [2021-03-26 10:49:50 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 730/1251] eta: 0:05:28 lr: 0.000918 loss: 3.6574 (3.7121) grad_norm: 1.0510 (1.0768) time: 0.6340 [2021-03-26 10:49:56 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 740/1251] eta: 0:05:21 lr: 0.000918 loss: 3.8997 (3.7129) grad_norm: 1.0170 (inf) time: 0.6337 [2021-03-26 10:50:02 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 750/1251] eta: 0:05:15 lr: 0.000918 loss: 3.8604 (3.7118) grad_norm: 1.0797 (inf) time: 0.6296 [2021-03-26 10:50:09 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 760/1251] eta: 0:05:09 lr: 0.000918 loss: 3.7661 (3.7107) grad_norm: 1.0797 (inf) time: 0.6274 [2021-03-26 10:50:15 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 770/1251] eta: 0:05:02 lr: 0.000918 loss: 3.6804 (3.7076) grad_norm: 1.0475 (inf) time: 0.6286 [2021-03-26 10:50:21 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 780/1251] eta: 0:04:56 lr: 0.000918 loss: 3.5708 (3.7057) grad_norm: 1.0300 (inf) time: 0.6300 [2021-03-26 10:50:28 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 790/1251] eta: 0:04:50 lr: 0.000918 loss: 3.7681 (3.7060) grad_norm: 1.0403 (inf) time: 0.6355 [2021-03-26 10:50:34 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 800/1251] eta: 0:04:44 lr: 0.000918 loss: 3.5508 (3.7043) grad_norm: 1.0753 (inf) time: 0.6328 [2021-03-26 10:50:40 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 810/1251] eta: 0:04:37 lr: 0.000918 loss: 3.8176 (3.7060) grad_norm: 1.0025 (inf) time: 0.6289 [2021-03-26 10:50:47 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 820/1251] eta: 0:04:31 lr: 0.000918 loss: 3.6430 (3.7018) grad_norm: 1.0038 (inf) time: 0.6268 [2021-03-26 10:50:53 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 830/1251] eta: 0:04:25 lr: 0.000918 loss: 3.5326 (3.7005) grad_norm: 1.0216 (inf) time: 0.6201 [2021-03-26 10:50:59 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 840/1251] eta: 0:04:18 lr: 0.000918 loss: 3.6525 (3.7005) grad_norm: 1.0216 (inf) time: 0.6294 [2021-03-26 10:51:05 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 850/1251] eta: 0:04:12 lr: 0.000918 loss: 3.7852 (3.6997) grad_norm: 1.0467 (inf) time: 0.6335 [2021-03-26 10:51:12 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 860/1251] eta: 0:04:06 lr: 0.000918 loss: 3.8875 (3.7010) grad_norm: 1.0394 (inf) time: 0.6255 [2021-03-26 10:51:18 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 870/1251] eta: 0:03:59 lr: 0.000918 loss: 3.6982 (3.6996) grad_norm: 1.0186 (inf) time: 0.6215 [2021-03-26 10:51:24 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 880/1251] eta: 0:03:53 lr: 0.000918 loss: 3.8922 (3.7031) grad_norm: 1.0298 (inf) time: 0.6251 [2021-03-26 10:51:30 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 890/1251] eta: 0:03:47 lr: 0.000918 loss: 3.9203 (3.7032) grad_norm: 1.0715 (inf) time: 0.6236 [2021-03-26 10:51:37 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 900/1251] eta: 0:03:40 lr: 0.000918 loss: 3.7771 (3.7033) grad_norm: 1.0017 (inf) time: 0.6219 [2021-03-26 10:51:43 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 910/1251] eta: 0:03:34 lr: 0.000918 loss: 3.7741 (3.7050) grad_norm: 1.0017 (inf) time: 0.6216 [2021-03-26 10:51:49 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 920/1251] eta: 0:03:28 lr: 0.000918 loss: 3.6017 (3.7022) grad_norm: 1.0432 (inf) time: 0.6212 [2021-03-26 10:51:55 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 930/1251] eta: 0:03:22 lr: 0.000918 loss: 3.6382 (3.7037) grad_norm: 1.0323 (inf) time: 0.6283 [2021-03-26 10:52:02 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 940/1251] eta: 0:03:15 lr: 0.000918 loss: 3.9422 (3.7068) grad_norm: 0.9853 (inf) time: 0.6300 [2021-03-26 10:52:08 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 950/1251] eta: 0:03:09 lr: 0.000918 loss: 3.8077 (3.7078) grad_norm: 1.0020 (inf) time: 0.6247 [2021-03-26 10:52:14 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 960/1251] eta: 0:03:03 lr: 0.000918 loss: 4.1252 (3.7118) grad_norm: 1.0457 (inf) time: 0.6220 [2021-03-26 10:52:20 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 970/1251] eta: 0:02:56 lr: 0.000918 loss: 3.8850 (3.7102) grad_norm: 1.0867 (inf) time: 0.6284 [2021-03-26 10:52:27 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 980/1251] eta: 0:02:50 lr: 0.000918 loss: 3.7551 (3.7085) grad_norm: 1.0483 (inf) time: 0.6255 [2021-03-26 10:52:33 swin_base_patch4_window7_224] INFO: Epoch: [55] [ 990/1251] eta: 0:02:44 lr: 0.000918 loss: 3.9287 (3.7108) grad_norm: 1.0909 (inf) time: 0.6199 [2021-03-26 10:52:39 swin_base_patch4_window7_224] INFO: Epoch: [55] [1000/1251] eta: 0:02:37 lr: 0.000918 loss: 3.9556 (3.7126) grad_norm: 1.0638 (inf) time: 0.6215 [2021-03-26 10:52:45 swin_base_patch4_window7_224] INFO: Epoch: [55] [1010/1251] eta: 0:02:31 lr: 0.000918 loss: 3.7766 (3.7106) grad_norm: 1.0486 (inf) time: 0.6268 [2021-03-26 10:52:52 swin_base_patch4_window7_224] INFO: Epoch: [55] [1020/1251] eta: 0:02:25 lr: 0.000918 loss: 3.6103 (3.7111) grad_norm: 1.0312 (inf) time: 0.6285 [2021-03-26 10:52:58 swin_base_patch4_window7_224] INFO: Epoch: [55] [1030/1251] eta: 0:02:19 lr: 0.000918 loss: 3.8685 (3.7111) grad_norm: 1.1457 (inf) time: 0.6282 [2021-03-26 10:53:04 swin_base_patch4_window7_224] INFO: Epoch: [55] [1040/1251] eta: 0:02:12 lr: 0.000918 loss: 3.8685 (3.7123) grad_norm: 1.0382 (inf) time: 0.6263 [2021-03-26 10:53:10 swin_base_patch4_window7_224] INFO: Epoch: [55] [1050/1251] eta: 0:02:06 lr: 0.000918 loss: 3.6570 (3.7115) grad_norm: 1.0169 (inf) time: 0.6211 [2021-03-26 10:53:17 swin_base_patch4_window7_224] INFO: Epoch: [55] [1060/1251] eta: 0:02:00 lr: 0.000918 loss: 3.6665 (3.7121) grad_norm: 1.0353 (inf) time: 0.6238 [2021-03-26 10:53:23 swin_base_patch4_window7_224] INFO: Epoch: [55] [1070/1251] eta: 0:01:53 lr: 0.000918 loss: 3.5085 (3.7068) grad_norm: 1.0353 (inf) time: 0.6289 [2021-03-26 10:53:29 swin_base_patch4_window7_224] INFO: Epoch: [55] [1080/1251] eta: 0:01:47 lr: 0.000918 loss: 3.2938 (3.7073) grad_norm: 1.1053 (inf) time: 0.6310 [2021-03-26 10:53:35 swin_base_patch4_window7_224] INFO: Epoch: [55] [1090/1251] eta: 0:01:41 lr: 0.000918 loss: 3.9799 (3.7074) grad_norm: 1.1149 (inf) time: 0.6301 [2021-03-26 10:53:42 swin_base_patch4_window7_224] INFO: Epoch: [55] [1100/1251] eta: 0:01:34 lr: 0.000918 loss: 3.8573 (3.7074) grad_norm: 1.1101 (inf) time: 0.6283 [2021-03-26 10:53:48 swin_base_patch4_window7_224] INFO: Epoch: [55] [1110/1251] eta: 0:01:28 lr: 0.000918 loss: 3.8573 (3.7092) grad_norm: 1.1517 (inf) time: 0.6243 [2021-03-26 10:53:54 swin_base_patch4_window7_224] INFO: Epoch: [55] [1120/1251] eta: 0:01:22 lr: 0.000918 loss: 4.0022 (3.7095) grad_norm: 1.0914 (inf) time: 0.6209 [2021-03-26 10:54:01 swin_base_patch4_window7_224] INFO: Epoch: [55] [1130/1251] eta: 0:01:16 lr: 0.000918 loss: 4.0309 (3.7118) grad_norm: 1.0120 (inf) time: 0.6269 [2021-03-26 10:54:07 swin_base_patch4_window7_224] INFO: Epoch: [55] [1140/1251] eta: 0:01:09 lr: 0.000918 loss: 3.8834 (3.7117) grad_norm: 1.0302 (inf) time: 0.6321 [2021-03-26 10:54:13 swin_base_patch4_window7_224] INFO: Epoch: [55] [1150/1251] eta: 0:01:03 lr: 0.000918 loss: 3.8085 (3.7122) grad_norm: 1.0302 (inf) time: 0.6240 [2021-03-26 10:54:19 swin_base_patch4_window7_224] INFO: Epoch: [55] [1160/1251] eta: 0:00:57 lr: 0.000918 loss: 3.5911 (3.7105) grad_norm: 1.1264 (inf) time: 0.6247 [2021-03-26 10:54:25 swin_base_patch4_window7_224] INFO: Epoch: [55] [1170/1251] eta: 0:00:50 lr: 0.000917 loss: 3.5595 (3.7098) grad_norm: 1.0343 (inf) time: 0.6227 [2021-03-26 10:54:32 swin_base_patch4_window7_224] INFO: Epoch: [55] [1180/1251] eta: 0:00:44 lr: 0.000917 loss: 3.4951 (3.7074) grad_norm: 0.9895 (inf) time: 0.6183 [2021-03-26 10:54:38 swin_base_patch4_window7_224] INFO: Epoch: [55] [1190/1251] eta: 0:00:38 lr: 0.000917 loss: 3.3883 (3.7057) grad_norm: 1.0418 (inf) time: 0.6248 [2021-03-26 10:54:44 swin_base_patch4_window7_224] INFO: Epoch: [55] [1200/1251] eta: 0:00:32 lr: 0.000917 loss: 3.1847 (3.7025) grad_norm: 1.1110 (inf) time: 0.6233 [2021-03-26 10:54:50 swin_base_patch4_window7_224] INFO: Epoch: [55] [1210/1251] eta: 0:00:25 lr: 0.000917 loss: 3.8899 (3.7042) grad_norm: 1.0409 (inf) time: 0.6214 [2021-03-26 10:54:57 swin_base_patch4_window7_224] INFO: Epoch: [55] [1220/1251] eta: 0:00:19 lr: 0.000917 loss: 3.9303 (3.7030) grad_norm: 1.0036 (inf) time: 0.6207 [2021-03-26 10:55:03 swin_base_patch4_window7_224] INFO: Epoch: [55] [1230/1251] eta: 0:00:13 lr: 0.000917 loss: 3.5665 (3.7026) grad_norm: 1.0036 (inf) time: 0.6221 [2021-03-26 10:55:09 swin_base_patch4_window7_224] INFO: Epoch: [55] [1240/1251] eta: 0:00:06 lr: 0.000917 loss: 3.5665 (3.7015) grad_norm: 1.0051 (inf) time: 0.6188 [2021-03-26 10:55:15 swin_base_patch4_window7_224] INFO: Epoch: [55] [1250/1251] eta: 0:00:00 lr: 0.000917 loss: 3.6402 (3.7021) grad_norm: 0.9873 (inf) time: 0.6101 [2021-03-26 10:56:16 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:02 loss: 1.2388 (1.2388) acc1: 70.3125 (70.3125) acc5: 90.6250 (90.6250) [2021-03-26 10:56:18 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 1.2340 (1.2359) acc1: 70.3125 (72.5852) acc5: 90.6250 (90.3409) [2021-03-26 10:56:19 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.1430 (1.1905) acc1: 70.3125 (71.7262) acc5: 92.1875 (91.6667) [2021-03-26 10:56:21 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.1948 (1.2125) acc1: 70.3125 (71.8246) acc5: 92.1875 (91.5323) [2021-03-26 10:56:22 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.2064 (1.1860) acc1: 73.4375 (72.3323) acc5: 92.1875 (91.8064) [2021-03-26 10:56:23 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0336 (1.1847) acc1: 71.8750 (72.2240) acc5: 92.1875 (91.7440) [2021-03-26 10:56:26 swin_base_patch4_window7_224] INFO: * Acc@1 73.444 Acc@5 92.052 loss 1.157 [2021-03-26 10:56:26 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.4% [2021-03-26 10:56:26 swin_base_patch4_window7_224] INFO: Max accuracy: 73.44% [2021-03-26 10:56:31 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 0/1251] eta: 1:31:32 lr: 0.000917 loss: 3.8966 (3.8966) grad_norm: 1.0829 (1.0829) time: 4.3902 [2021-03-26 10:56:37 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 10/1251] eta: 0:20:12 lr: 0.000917 loss: 3.7788 (3.4851) grad_norm: 1.0813 (1.1012) time: 0.9771 [2021-03-26 10:56:43 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 20/1251] eta: 0:16:37 lr: 0.000917 loss: 3.8375 (3.7533) grad_norm: 1.0809 (1.0871) time: 0.6309 [2021-03-26 10:56:50 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 30/1251] eta: 0:15:13 lr: 0.000917 loss: 3.8473 (3.6924) grad_norm: 1.0131 (1.0672) time: 0.6217 [2021-03-26 10:56:56 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 40/1251] eta: 0:14:27 lr: 0.000917 loss: 3.7558 (3.6628) grad_norm: 0.9911 (1.0560) time: 0.6176 [2021-03-26 10:57:02 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 50/1251] eta: 0:13:58 lr: 0.000917 loss: 3.7012 (3.6133) grad_norm: 0.9705 (1.0463) time: 0.6222 [2021-03-26 10:57:08 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 60/1251] eta: 0:13:36 lr: 0.000917 loss: 3.6541 (3.6507) grad_norm: 0.9930 (1.0483) time: 0.6229 [2021-03-26 10:57:14 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 70/1251] eta: 0:13:18 lr: 0.000917 loss: 3.9583 (3.6619) grad_norm: 0.9938 (1.0502) time: 0.6187 [2021-03-26 10:57:21 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 80/1251] eta: 0:13:05 lr: 0.000917 loss: 3.5712 (3.6521) grad_norm: 1.0876 (1.0659) time: 0.6248 [2021-03-26 10:57:27 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 90/1251] eta: 0:12:51 lr: 0.000917 loss: 3.5277 (3.6590) grad_norm: 1.0526 (1.0605) time: 0.6231 [2021-03-26 10:57:33 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 100/1251] eta: 0:12:40 lr: 0.000917 loss: 3.8883 (3.6855) grad_norm: 1.0487 (1.0620) time: 0.6199 [2021-03-26 10:57:39 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 110/1251] eta: 0:12:31 lr: 0.000917 loss: 3.8898 (3.7024) grad_norm: 1.0621 (1.0644) time: 0.6309 [2021-03-26 10:57:46 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 120/1251] eta: 0:12:20 lr: 0.000917 loss: 3.6688 (3.6739) grad_norm: 1.0621 (1.0608) time: 0.6258 [2021-03-26 10:57:52 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 130/1251] eta: 0:12:11 lr: 0.000917 loss: 3.7266 (3.6816) grad_norm: 1.0380 (1.0577) time: 0.6202 [2021-03-26 10:57:58 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 140/1251] eta: 0:12:02 lr: 0.000917 loss: 3.9676 (3.6986) grad_norm: 0.9837 (1.0547) time: 0.6221 [2021-03-26 10:58:04 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 150/1251] eta: 0:11:53 lr: 0.000917 loss: 4.0058 (3.7147) grad_norm: 0.9879 (1.0597) time: 0.6203 [2021-03-26 10:58:10 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 160/1251] eta: 0:11:45 lr: 0.000917 loss: 3.8479 (3.6969) grad_norm: 1.0716 (1.0629) time: 0.6203 [2021-03-26 10:58:17 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 170/1251] eta: 0:11:37 lr: 0.000917 loss: 3.6603 (3.6962) grad_norm: 1.0494 (1.0659) time: 0.6196 [2021-03-26 10:58:23 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 180/1251] eta: 0:11:29 lr: 0.000917 loss: 3.6603 (3.7041) grad_norm: 1.0218 (1.0645) time: 0.6210 [2021-03-26 10:58:29 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 190/1251] eta: 0:11:21 lr: 0.000917 loss: 3.7278 (3.7070) grad_norm: 1.0350 (1.0633) time: 0.6177 [2021-03-26 10:58:35 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 200/1251] eta: 0:11:14 lr: 0.000917 loss: 3.7116 (3.6899) grad_norm: 0.9744 (1.0587) time: 0.6228 [2021-03-26 10:58:42 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 210/1251] eta: 0:11:07 lr: 0.000917 loss: 3.5264 (3.6903) grad_norm: 1.0044 (1.0592) time: 0.6295 [2021-03-26 10:58:48 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 220/1251] eta: 0:11:00 lr: 0.000917 loss: 3.8663 (3.6930) grad_norm: 1.0184 (1.0596) time: 0.6265 [2021-03-26 10:58:54 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 230/1251] eta: 0:10:52 lr: 0.000917 loss: 3.8283 (3.6917) grad_norm: 0.9969 (1.0584) time: 0.6254 [2021-03-26 10:59:00 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 240/1251] eta: 0:10:45 lr: 0.000917 loss: 3.8283 (3.6976) grad_norm: 1.0155 (1.0575) time: 0.6230 [2021-03-26 10:59:06 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 250/1251] eta: 0:10:38 lr: 0.000917 loss: 3.6325 (3.6924) grad_norm: 0.9943 (1.0561) time: 0.6148 [2021-03-26 10:59:13 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 260/1251] eta: 0:10:31 lr: 0.000917 loss: 3.3967 (3.6904) grad_norm: 1.0447 (1.0574) time: 0.6163 [2021-03-26 10:59:19 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 270/1251] eta: 0:10:24 lr: 0.000917 loss: 3.7786 (3.6867) grad_norm: 1.0732 (1.0584) time: 0.6310 [2021-03-26 10:59:25 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 280/1251] eta: 0:10:18 lr: 0.000917 loss: 3.7399 (3.6918) grad_norm: 1.0732 (1.0594) time: 0.6328 [2021-03-26 10:59:32 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 290/1251] eta: 0:10:11 lr: 0.000917 loss: 4.0767 (3.7069) grad_norm: 1.0325 (1.0583) time: 0.6301 [2021-03-26 10:59:38 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 300/1251] eta: 0:10:04 lr: 0.000917 loss: 3.9780 (3.7097) grad_norm: 1.0250 (1.0569) time: 0.6272 [2021-03-26 10:59:44 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 310/1251] eta: 0:09:58 lr: 0.000917 loss: 3.8170 (3.7026) grad_norm: 1.0277 (1.0566) time: 0.6218 [2021-03-26 10:59:50 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 320/1251] eta: 0:09:51 lr: 0.000917 loss: 3.7428 (3.7082) grad_norm: 1.0487 (1.0589) time: 0.6223 [2021-03-26 10:59:56 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 330/1251] eta: 0:09:44 lr: 0.000917 loss: 3.9742 (3.7187) grad_norm: 1.0651 (inf) time: 0.6184 [2021-03-26 11:00:03 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 340/1251] eta: 0:09:37 lr: 0.000917 loss: 3.9550 (3.7243) grad_norm: 1.0031 (inf) time: 0.6179 [2021-03-26 11:00:09 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 350/1251] eta: 0:09:31 lr: 0.000916 loss: 3.7760 (3.7229) grad_norm: 1.0557 (inf) time: 0.6288 [2021-03-26 11:00:15 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 360/1251] eta: 0:09:24 lr: 0.000916 loss: 3.7760 (3.7239) grad_norm: 1.0557 (inf) time: 0.6291 [2021-03-26 11:00:22 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 370/1251] eta: 0:09:18 lr: 0.000916 loss: 3.8138 (3.7255) grad_norm: 1.0493 (inf) time: 0.6281 [2021-03-26 11:00:28 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 380/1251] eta: 0:09:11 lr: 0.000916 loss: 3.7969 (3.7269) grad_norm: 1.0563 (inf) time: 0.6281 [2021-03-26 11:00:34 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 390/1251] eta: 0:09:05 lr: 0.000916 loss: 3.7969 (3.7258) grad_norm: 1.0474 (inf) time: 0.6222 [2021-03-26 11:00:40 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 400/1251] eta: 0:08:58 lr: 0.000916 loss: 3.8079 (3.7274) grad_norm: 1.0379 (inf) time: 0.6207 [2021-03-26 11:00:46 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 410/1251] eta: 0:08:52 lr: 0.000916 loss: 3.7969 (3.7232) grad_norm: 1.0156 (inf) time: 0.6216 [2021-03-26 11:00:53 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 420/1251] eta: 0:08:45 lr: 0.000916 loss: 3.5640 (3.7143) grad_norm: 1.0251 (inf) time: 0.6248 [2021-03-26 11:00:59 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 430/1251] eta: 0:08:39 lr: 0.000916 loss: 3.6097 (3.7147) grad_norm: 1.0183 (inf) time: 0.6259 [2021-03-26 11:01:05 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 440/1251] eta: 0:08:32 lr: 0.000916 loss: 3.7866 (3.7123) grad_norm: 0.9662 (inf) time: 0.6240 [2021-03-26 11:01:11 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 450/1251] eta: 0:08:26 lr: 0.000916 loss: 3.8294 (3.7158) grad_norm: 0.9819 (inf) time: 0.6221 [2021-03-26 11:01:18 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 460/1251] eta: 0:08:19 lr: 0.000916 loss: 3.8440 (3.7163) grad_norm: 1.1223 (inf) time: 0.6241 [2021-03-26 11:01:24 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 470/1251] eta: 0:08:13 lr: 0.000916 loss: 3.7679 (3.7156) grad_norm: 1.0582 (inf) time: 0.6246 [2021-03-26 11:01:30 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 480/1251] eta: 0:08:06 lr: 0.000916 loss: 3.9356 (3.7227) grad_norm: 1.0406 (inf) time: 0.6254 [2021-03-26 11:01:36 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 490/1251] eta: 0:08:00 lr: 0.000916 loss: 3.8761 (3.7199) grad_norm: 1.0255 (inf) time: 0.6248 [2021-03-26 11:01:43 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 500/1251] eta: 0:07:54 lr: 0.000916 loss: 3.7264 (3.7206) grad_norm: 1.0549 (inf) time: 0.6261 [2021-03-26 11:01:49 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 510/1251] eta: 0:07:47 lr: 0.000916 loss: 3.7733 (3.7210) grad_norm: 1.0664 (inf) time: 0.6239 [2021-03-26 11:01:55 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 520/1251] eta: 0:07:41 lr: 0.000916 loss: 3.7733 (3.7224) grad_norm: 1.0306 (inf) time: 0.6208 [2021-03-26 11:02:01 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 530/1251] eta: 0:07:34 lr: 0.000916 loss: 3.6866 (3.7210) grad_norm: 1.0266 (inf) time: 0.6258 [2021-03-26 11:02:08 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 540/1251] eta: 0:07:28 lr: 0.000916 loss: 3.6814 (3.7227) grad_norm: 1.0011 (inf) time: 0.6328 [2021-03-26 11:02:14 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 550/1251] eta: 0:07:22 lr: 0.000916 loss: 3.9217 (3.7256) grad_norm: 1.0000 (inf) time: 0.6368 [2021-03-26 11:02:20 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 560/1251] eta: 0:07:16 lr: 0.000916 loss: 3.8929 (3.7244) grad_norm: 1.0705 (inf) time: 0.6302 [2021-03-26 11:02:27 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 570/1251] eta: 0:07:09 lr: 0.000916 loss: 3.6470 (3.7225) grad_norm: 1.1468 (inf) time: 0.6270 [2021-03-26 11:02:33 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 580/1251] eta: 0:07:03 lr: 0.000916 loss: 3.5737 (3.7268) grad_norm: 1.0081 (inf) time: 0.6267 [2021-03-26 11:02:39 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 590/1251] eta: 0:06:57 lr: 0.000916 loss: 3.9522 (3.7218) grad_norm: 1.0203 (inf) time: 0.6283 [2021-03-26 11:02:46 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 600/1251] eta: 0:06:50 lr: 0.000916 loss: 3.8582 (3.7222) grad_norm: 1.0420 (inf) time: 0.6272 [2021-03-26 11:02:52 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 610/1251] eta: 0:06:44 lr: 0.000916 loss: 3.9013 (3.7276) grad_norm: 1.0370 (inf) time: 0.6234 [2021-03-26 11:02:58 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 620/1251] eta: 0:06:37 lr: 0.000916 loss: 3.8527 (3.7290) grad_norm: 0.9978 (inf) time: 0.6218 [2021-03-26 11:03:04 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 630/1251] eta: 0:06:31 lr: 0.000916 loss: 3.8163 (3.7284) grad_norm: 1.0284 (inf) time: 0.6225 [2021-03-26 11:03:10 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 640/1251] eta: 0:06:25 lr: 0.000916 loss: 3.8067 (3.7273) grad_norm: 1.0676 (inf) time: 0.6265 [2021-03-26 11:03:17 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 650/1251] eta: 0:06:18 lr: 0.000916 loss: 3.8496 (3.7299) grad_norm: 1.0893 (inf) time: 0.6237 [2021-03-26 11:03:23 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 660/1251] eta: 0:06:12 lr: 0.000916 loss: 3.8849 (3.7290) grad_norm: 1.0662 (inf) time: 0.6245 [2021-03-26 11:03:29 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 670/1251] eta: 0:06:06 lr: 0.000916 loss: 3.8519 (3.7297) grad_norm: 1.0662 (inf) time: 0.6258 [2021-03-26 11:03:35 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 680/1251] eta: 0:05:59 lr: 0.000916 loss: 3.8631 (3.7313) grad_norm: 1.0367 (inf) time: 0.6235 [2021-03-26 11:03:42 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 690/1251] eta: 0:05:53 lr: 0.000916 loss: 3.7937 (3.7302) grad_norm: 1.0208 (inf) time: 0.6191 [2021-03-26 11:03:48 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 700/1251] eta: 0:05:46 lr: 0.000916 loss: 3.4641 (3.7264) grad_norm: 1.0121 (inf) time: 0.6174 [2021-03-26 11:03:54 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 710/1251] eta: 0:05:40 lr: 0.000916 loss: 3.6278 (3.7281) grad_norm: 1.0084 (inf) time: 0.6172 [2021-03-26 11:04:00 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 720/1251] eta: 0:05:34 lr: 0.000916 loss: 3.9721 (3.7266) grad_norm: 0.9826 (inf) time: 0.6159 [2021-03-26 11:04:06 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 730/1251] eta: 0:05:27 lr: 0.000916 loss: 3.9224 (3.7268) grad_norm: 1.0481 (inf) time: 0.6185 [2021-03-26 11:04:13 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 740/1251] eta: 0:05:21 lr: 0.000916 loss: 3.4500 (3.7197) grad_norm: 1.0986 (inf) time: 0.6314 [2021-03-26 11:04:19 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 750/1251] eta: 0:05:15 lr: 0.000916 loss: 3.2343 (3.7196) grad_norm: 1.0877 (inf) time: 0.6384 [2021-03-26 11:04:26 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 760/1251] eta: 0:05:09 lr: 0.000916 loss: 3.6860 (3.7174) grad_norm: 1.0870 (inf) time: 0.6360 [2021-03-26 11:04:32 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 770/1251] eta: 0:05:02 lr: 0.000916 loss: 3.7761 (3.7187) grad_norm: 1.1102 (inf) time: 0.6352 [2021-03-26 11:04:38 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 780/1251] eta: 0:04:56 lr: 0.000915 loss: 3.8370 (3.7180) grad_norm: 1.1102 (inf) time: 0.6255 [2021-03-26 11:04:44 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 790/1251] eta: 0:04:50 lr: 0.000915 loss: 3.7386 (3.7166) grad_norm: 1.1236 (inf) time: 0.6254 [2021-03-26 11:04:51 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 800/1251] eta: 0:04:43 lr: 0.000915 loss: 4.0189 (3.7191) grad_norm: 1.0434 (inf) time: 0.6274 [2021-03-26 11:04:57 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 810/1251] eta: 0:04:37 lr: 0.000915 loss: 4.1513 (3.7225) grad_norm: 1.0080 (inf) time: 0.6281 [2021-03-26 11:05:03 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 820/1251] eta: 0:04:31 lr: 0.000915 loss: 3.8157 (3.7193) grad_norm: 1.1124 (inf) time: 0.6335 [2021-03-26 11:05:10 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 830/1251] eta: 0:04:25 lr: 0.000915 loss: 3.5474 (3.7173) grad_norm: 1.0929 (inf) time: 0.6363 [2021-03-26 11:05:16 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 840/1251] eta: 0:04:18 lr: 0.000915 loss: 3.7694 (3.7162) grad_norm: 1.0139 (inf) time: 0.6312 [2021-03-26 11:05:22 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 850/1251] eta: 0:04:12 lr: 0.000915 loss: 3.8843 (3.7151) grad_norm: 0.9902 (inf) time: 0.6227 [2021-03-26 11:05:28 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 860/1251] eta: 0:04:06 lr: 0.000915 loss: 3.9958 (3.7186) grad_norm: 1.0214 (inf) time: 0.6261 [2021-03-26 11:05:35 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 870/1251] eta: 0:03:59 lr: 0.000915 loss: 3.8597 (3.7163) grad_norm: 1.0024 (inf) time: 0.6270 [2021-03-26 11:05:41 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 880/1251] eta: 0:03:53 lr: 0.000915 loss: 3.3457 (3.7127) grad_norm: 0.9981 (inf) time: 0.6183 [2021-03-26 11:05:47 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 890/1251] eta: 0:03:47 lr: 0.000915 loss: 3.8136 (3.7146) grad_norm: 0.9839 (inf) time: 0.6215 [2021-03-26 11:05:53 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 900/1251] eta: 0:03:40 lr: 0.000915 loss: 4.0137 (3.7181) grad_norm: 1.0766 (inf) time: 0.6265 [2021-03-26 11:06:00 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 910/1251] eta: 0:03:34 lr: 0.000915 loss: 4.0137 (3.7223) grad_norm: 1.1396 (inf) time: 0.6258 [2021-03-26 11:06:06 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 920/1251] eta: 0:03:28 lr: 0.000915 loss: 3.9106 (3.7219) grad_norm: 1.0605 (inf) time: 0.6292 [2021-03-26 11:06:12 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 930/1251] eta: 0:03:21 lr: 0.000915 loss: 3.7932 (3.7222) grad_norm: 1.0722 (inf) time: 0.6287 [2021-03-26 11:06:18 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 940/1251] eta: 0:03:15 lr: 0.000915 loss: 3.7264 (3.7217) grad_norm: 1.0812 (inf) time: 0.6291 [2021-03-26 11:06:25 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 950/1251] eta: 0:03:09 lr: 0.000915 loss: 3.6393 (3.7198) grad_norm: 1.1135 (inf) time: 0.6288 [2021-03-26 11:06:31 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 960/1251] eta: 0:03:03 lr: 0.000915 loss: 3.8033 (3.7210) grad_norm: 1.0973 (inf) time: 0.6258 [2021-03-26 11:06:37 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 970/1251] eta: 0:02:56 lr: 0.000915 loss: 3.9206 (3.7231) grad_norm: 1.0530 (inf) time: 0.6181 [2021-03-26 11:06:43 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 980/1251] eta: 0:02:50 lr: 0.000915 loss: 3.9206 (3.7241) grad_norm: 1.0160 (inf) time: 0.6217 [2021-03-26 11:06:50 swin_base_patch4_window7_224] INFO: Epoch: [56] [ 990/1251] eta: 0:02:44 lr: 0.000915 loss: 4.0097 (3.7278) grad_norm: 1.0622 (inf) time: 0.6248 [2021-03-26 11:06:56 swin_base_patch4_window7_224] INFO: Epoch: [56] [1000/1251] eta: 0:02:37 lr: 0.000915 loss: 3.9619 (3.7297) grad_norm: 1.0622 (inf) time: 0.6205 [2021-03-26 11:07:02 swin_base_patch4_window7_224] INFO: Epoch: [56] [1010/1251] eta: 0:02:31 lr: 0.000915 loss: 3.6440 (3.7273) grad_norm: 1.0934 (inf) time: 0.6274 [2021-03-26 11:07:08 swin_base_patch4_window7_224] INFO: Epoch: [56] [1020/1251] eta: 0:02:25 lr: 0.000915 loss: 3.6286 (3.7257) grad_norm: 1.1006 (inf) time: 0.6291 [2021-03-26 11:07:15 swin_base_patch4_window7_224] INFO: Epoch: [56] [1030/1251] eta: 0:02:18 lr: 0.000915 loss: 3.6651 (3.7227) grad_norm: 1.0899 (inf) time: 0.6249 [2021-03-26 11:07:21 swin_base_patch4_window7_224] INFO: Epoch: [56] [1040/1251] eta: 0:02:12 lr: 0.000915 loss: 3.5397 (3.7217) grad_norm: 1.0647 (inf) time: 0.6229 [2021-03-26 11:07:27 swin_base_patch4_window7_224] INFO: Epoch: [56] [1050/1251] eta: 0:02:06 lr: 0.000915 loss: 3.4789 (3.7197) grad_norm: 1.0689 (inf) time: 0.6203 [2021-03-26 11:07:33 swin_base_patch4_window7_224] INFO: Epoch: [56] [1060/1251] eta: 0:02:00 lr: 0.000915 loss: 3.6984 (3.7197) grad_norm: 1.0851 (inf) time: 0.6189 [2021-03-26 11:07:39 swin_base_patch4_window7_224] INFO: Epoch: [56] [1070/1251] eta: 0:01:53 lr: 0.000915 loss: 3.9398 (3.7219) grad_norm: 1.0034 (inf) time: 0.6182 [2021-03-26 11:07:46 swin_base_patch4_window7_224] INFO: Epoch: [56] [1080/1251] eta: 0:01:47 lr: 0.000915 loss: 4.0272 (3.7230) grad_norm: 1.1021 (inf) time: 0.6237 [2021-03-26 11:07:52 swin_base_patch4_window7_224] INFO: Epoch: [56] [1090/1251] eta: 0:01:41 lr: 0.000915 loss: 3.6286 (3.7210) grad_norm: 1.0999 (inf) time: 0.6272 [2021-03-26 11:07:58 swin_base_patch4_window7_224] INFO: Epoch: [56] [1100/1251] eta: 0:01:34 lr: 0.000915 loss: 3.7424 (3.7217) grad_norm: 1.0470 (inf) time: 0.6287 [2021-03-26 11:08:05 swin_base_patch4_window7_224] INFO: Epoch: [56] [1110/1251] eta: 0:01:28 lr: 0.000915 loss: 3.7424 (3.7214) grad_norm: 1.0109 (inf) time: 0.6344 [2021-03-26 11:08:11 swin_base_patch4_window7_224] INFO: Epoch: [56] [1120/1251] eta: 0:01:22 lr: 0.000915 loss: 3.5608 (3.7205) grad_norm: 1.0192 (inf) time: 0.6316 [2021-03-26 11:08:17 swin_base_patch4_window7_224] INFO: Epoch: [56] [1130/1251] eta: 0:01:16 lr: 0.000915 loss: 3.6049 (3.7212) grad_norm: 1.0375 (inf) time: 0.6304 [2021-03-26 11:08:24 swin_base_patch4_window7_224] INFO: Epoch: [56] [1140/1251] eta: 0:01:09 lr: 0.000915 loss: 3.6049 (3.7193) grad_norm: 1.0553 (inf) time: 0.6293 [2021-03-26 11:08:30 swin_base_patch4_window7_224] INFO: Epoch: [56] [1150/1251] eta: 0:01:03 lr: 0.000915 loss: 3.6845 (3.7192) grad_norm: 1.0766 (inf) time: 0.6267 [2021-03-26 11:08:36 swin_base_patch4_window7_224] INFO: Epoch: [56] [1160/1251] eta: 0:00:57 lr: 0.000915 loss: 3.7633 (3.7196) grad_norm: 1.0744 (inf) time: 0.6302 [2021-03-26 11:08:42 swin_base_patch4_window7_224] INFO: Epoch: [56] [1170/1251] eta: 0:00:50 lr: 0.000915 loss: 3.7692 (3.7182) grad_norm: 1.0314 (inf) time: 0.6303 [2021-03-26 11:08:49 swin_base_patch4_window7_224] INFO: Epoch: [56] [1180/1251] eta: 0:00:44 lr: 0.000915 loss: 3.7692 (3.7187) grad_norm: 1.0314 (inf) time: 0.6247 [2021-03-26 11:08:55 swin_base_patch4_window7_224] INFO: Epoch: [56] [1190/1251] eta: 0:00:38 lr: 0.000915 loss: 3.8127 (3.7207) grad_norm: 1.0529 (inf) time: 0.6216 [2021-03-26 11:09:01 swin_base_patch4_window7_224] INFO: Epoch: [56] [1200/1251] eta: 0:00:32 lr: 0.000915 loss: 3.8646 (3.7195) grad_norm: 1.0488 (inf) time: 0.6198 [2021-03-26 11:09:07 swin_base_patch4_window7_224] INFO: Epoch: [56] [1210/1251] eta: 0:00:25 lr: 0.000915 loss: 3.8646 (3.7202) grad_norm: 1.0488 (inf) time: 0.6216 [2021-03-26 11:09:14 swin_base_patch4_window7_224] INFO: Epoch: [56] [1220/1251] eta: 0:00:19 lr: 0.000914 loss: 4.0683 (3.7230) grad_norm: 1.0053 (inf) time: 0.6262 [2021-03-26 11:09:20 swin_base_patch4_window7_224] INFO: Epoch: [56] [1230/1251] eta: 0:00:13 lr: 0.000914 loss: 3.8978 (3.7216) grad_norm: 1.0036 (inf) time: 0.6228 [2021-03-26 11:09:26 swin_base_patch4_window7_224] INFO: Epoch: [56] [1240/1251] eta: 0:00:06 lr: 0.000914 loss: 3.5563 (3.7217) grad_norm: 1.0188 (inf) time: 0.6180 [2021-03-26 11:09:32 swin_base_patch4_window7_224] INFO: Epoch: [56] [1250/1251] eta: 0:00:00 lr: 0.000914 loss: 3.7899 (3.7225) grad_norm: 1.0162 (inf) time: 0.6117 [2021-03-26 11:09:39 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:30 loss: 1.4855 (1.4855) acc1: 70.3125 (70.3125) acc5: 89.0625 (89.0625) [2021-03-26 11:09:41 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.1922 (1.2280) acc1: 71.8750 (72.1591) acc5: 90.6250 (90.7670) [2021-03-26 11:09:43 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.1680 (1.2505) acc1: 71.8750 (71.8750) acc5: 90.6250 (90.6994) [2021-03-26 11:09:45 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.1571 (1.1959) acc1: 71.8750 (72.2782) acc5: 92.1875 (91.2802) [2021-03-26 11:09:48 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0762 (1.1866) acc1: 71.8750 (72.9802) acc5: 92.1875 (91.5396) [2021-03-26 11:09:49 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1459 (1.1769) acc1: 73.4375 (73.3440) acc5: 90.6250 (91.8080) [2021-03-26 11:09:52 swin_base_patch4_window7_224] INFO: * Acc@1 73.478 Acc@5 92.066 loss 1.157 [2021-03-26 11:09:52 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.5% [2021-03-26 11:09:52 swin_base_patch4_window7_224] INFO: Max accuracy: 73.48% [2021-03-26 11:09:57 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 0/1251] eta: 1:26:01 lr: 0.000914 loss: 2.8122 (2.8122) grad_norm: 0.9982 (0.9982) time: 4.1257 [2021-03-26 11:10:03 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 10/1251] eta: 0:19:56 lr: 0.000914 loss: 4.1855 (4.0028) grad_norm: 1.1492 (1.1557) time: 0.9642 [2021-03-26 11:10:09 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 20/1251] eta: 0:16:27 lr: 0.000914 loss: 3.6355 (3.5926) grad_norm: 1.1102 (1.1606) time: 0.6364 [2021-03-26 11:10:16 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 30/1251] eta: 0:15:11 lr: 0.000914 loss: 3.2748 (3.5474) grad_norm: 1.0455 (1.1227) time: 0.6262 [2021-03-26 11:10:22 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 40/1251] eta: 0:14:29 lr: 0.000914 loss: 3.5455 (3.5847) grad_norm: 1.0874 (1.1207) time: 0.6297 [2021-03-26 11:10:28 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 50/1251] eta: 0:14:01 lr: 0.000914 loss: 3.5722 (3.5628) grad_norm: 1.0975 (1.1140) time: 0.6304 [2021-03-26 11:10:34 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 60/1251] eta: 0:13:39 lr: 0.000914 loss: 3.5722 (3.5818) grad_norm: 1.0445 (1.0963) time: 0.6259 [2021-03-26 11:10:41 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 70/1251] eta: 0:13:21 lr: 0.000914 loss: 3.7271 (3.5862) grad_norm: 0.9950 (1.0862) time: 0.6216 [2021-03-26 11:10:47 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 80/1251] eta: 0:13:07 lr: 0.000914 loss: 3.9094 (3.6318) grad_norm: 1.0104 (1.0860) time: 0.6258 [2021-03-26 11:10:53 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 90/1251] eta: 0:12:54 lr: 0.000914 loss: 4.0509 (3.6621) grad_norm: 1.0424 (1.0796) time: 0.6263 [2021-03-26 11:10:59 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 100/1251] eta: 0:12:43 lr: 0.000914 loss: 4.0203 (3.6803) grad_norm: 1.0643 (1.0828) time: 0.6260 [2021-03-26 11:11:06 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 110/1251] eta: 0:12:32 lr: 0.000914 loss: 3.9431 (3.6792) grad_norm: 1.0522 (1.0806) time: 0.6266 [2021-03-26 11:11:12 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 120/1251] eta: 0:12:22 lr: 0.000914 loss: 3.7115 (3.6527) grad_norm: 1.0425 (1.0788) time: 0.6239 [2021-03-26 11:11:18 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 130/1251] eta: 0:12:13 lr: 0.000914 loss: 3.5990 (3.6530) grad_norm: 1.0425 (1.0821) time: 0.6258 [2021-03-26 11:11:24 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 140/1251] eta: 0:12:04 lr: 0.000914 loss: 3.7614 (3.6728) grad_norm: 1.0560 (1.0817) time: 0.6254 [2021-03-26 11:11:31 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 150/1251] eta: 0:11:55 lr: 0.000914 loss: 3.8017 (3.6794) grad_norm: 1.0376 (1.0762) time: 0.6197 [2021-03-26 11:11:37 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 160/1251] eta: 0:11:47 lr: 0.000914 loss: 3.7708 (3.6834) grad_norm: 1.0376 (1.0756) time: 0.6186 [2021-03-26 11:11:43 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 170/1251] eta: 0:11:39 lr: 0.000914 loss: 3.8941 (3.6859) grad_norm: 1.0355 (1.0751) time: 0.6227 [2021-03-26 11:11:49 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 180/1251] eta: 0:11:31 lr: 0.000914 loss: 3.7629 (3.6892) grad_norm: 1.0303 (1.0781) time: 0.6237 [2021-03-26 11:11:56 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 190/1251] eta: 0:11:24 lr: 0.000914 loss: 3.9844 (3.6907) grad_norm: 1.1231 (1.0815) time: 0.6303 [2021-03-26 11:12:02 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 200/1251] eta: 0:11:17 lr: 0.000914 loss: 3.8011 (3.6875) grad_norm: 1.1351 (1.0826) time: 0.6340 [2021-03-26 11:12:08 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 210/1251] eta: 0:11:09 lr: 0.000914 loss: 3.5781 (3.6739) grad_norm: 1.1351 (1.0841) time: 0.6281 [2021-03-26 11:12:14 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 220/1251] eta: 0:11:02 lr: 0.000914 loss: 3.4597 (3.6701) grad_norm: 0.9959 (1.0800) time: 0.6202 [2021-03-26 11:12:21 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 230/1251] eta: 0:10:55 lr: 0.000914 loss: 3.6117 (3.6676) grad_norm: 0.9928 (1.0777) time: 0.6217 [2021-03-26 11:12:27 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 240/1251] eta: 0:10:48 lr: 0.000914 loss: 3.6966 (3.6663) grad_norm: 1.0281 (1.0767) time: 0.6316 [2021-03-26 11:12:33 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 250/1251] eta: 0:10:41 lr: 0.000914 loss: 3.6280 (3.6630) grad_norm: 1.0148 (1.0732) time: 0.6277 [2021-03-26 11:12:39 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 260/1251] eta: 0:10:33 lr: 0.000914 loss: 3.5839 (3.6635) grad_norm: 1.0302 (1.0736) time: 0.6198 [2021-03-26 11:12:46 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 270/1251] eta: 0:10:27 lr: 0.000914 loss: 3.5757 (3.6621) grad_norm: 1.0743 (1.0766) time: 0.6231 [2021-03-26 11:12:52 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 280/1251] eta: 0:10:20 lr: 0.000914 loss: 3.7289 (3.6653) grad_norm: 1.0594 (1.0759) time: 0.6262 [2021-03-26 11:12:58 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 290/1251] eta: 0:10:13 lr: 0.000914 loss: 3.9647 (3.6632) grad_norm: 0.9997 (1.0748) time: 0.6211 [2021-03-26 11:13:04 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 300/1251] eta: 0:10:06 lr: 0.000914 loss: 3.5945 (3.6633) grad_norm: 1.0981 (1.0760) time: 0.6179 [2021-03-26 11:13:11 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 310/1251] eta: 0:09:59 lr: 0.000914 loss: 3.5945 (3.6690) grad_norm: 1.0795 (1.0752) time: 0.6226 [2021-03-26 11:13:17 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 320/1251] eta: 0:09:52 lr: 0.000914 loss: 4.0019 (3.6754) grad_norm: 1.0168 (1.0735) time: 0.6243 [2021-03-26 11:13:23 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 330/1251] eta: 0:09:45 lr: 0.000914 loss: 3.9880 (3.6805) grad_norm: 1.0570 (1.0755) time: 0.6244 [2021-03-26 11:13:29 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 340/1251] eta: 0:09:39 lr: 0.000914 loss: 3.7478 (3.6732) grad_norm: 1.1813 (1.0804) time: 0.6265 [2021-03-26 11:13:36 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 350/1251] eta: 0:09:32 lr: 0.000914 loss: 3.6287 (3.6772) grad_norm: 1.0674 (1.0800) time: 0.6238 [2021-03-26 11:13:42 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 360/1251] eta: 0:09:25 lr: 0.000914 loss: 3.8677 (3.6831) grad_norm: 1.0499 (1.0798) time: 0.6232 [2021-03-26 11:13:48 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 370/1251] eta: 0:09:19 lr: 0.000914 loss: 3.9308 (3.6873) grad_norm: 1.1399 (1.0848) time: 0.6286 [2021-03-26 11:13:54 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 380/1251] eta: 0:09:12 lr: 0.000914 loss: 3.9062 (3.6881) grad_norm: 1.1399 (1.0850) time: 0.6284 [2021-03-26 11:14:01 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 390/1251] eta: 0:09:06 lr: 0.000913 loss: 3.9212 (3.6967) grad_norm: 1.0577 (1.0846) time: 0.6209 [2021-03-26 11:14:07 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 400/1251] eta: 0:08:59 lr: 0.000913 loss: 4.1245 (3.7056) grad_norm: 1.0546 (1.0828) time: 0.6182 [2021-03-26 11:14:13 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 410/1251] eta: 0:08:52 lr: 0.000913 loss: 3.6563 (3.7016) grad_norm: 1.0415 (1.0829) time: 0.6199 [2021-03-26 11:14:19 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 420/1251] eta: 0:08:46 lr: 0.000913 loss: 3.5141 (3.7026) grad_norm: 1.0174 (1.0818) time: 0.6238 [2021-03-26 11:14:25 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 430/1251] eta: 0:08:39 lr: 0.000913 loss: 3.8656 (3.7028) grad_norm: 1.0138 (1.0813) time: 0.6250 [2021-03-26 11:14:32 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 440/1251] eta: 0:08:33 lr: 0.000913 loss: 3.8273 (3.7016) grad_norm: 1.0398 (1.0804) time: 0.6274 [2021-03-26 11:14:38 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 450/1251] eta: 0:08:26 lr: 0.000913 loss: 3.8273 (3.7071) grad_norm: 0.9893 (1.0791) time: 0.6236 [2021-03-26 11:14:44 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 460/1251] eta: 0:08:20 lr: 0.000913 loss: 3.7313 (3.7054) grad_norm: 1.0547 (1.0800) time: 0.6180 [2021-03-26 11:14:50 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 470/1251] eta: 0:08:13 lr: 0.000913 loss: 3.6141 (3.7082) grad_norm: 1.1030 (1.0798) time: 0.6227 [2021-03-26 11:14:57 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 480/1251] eta: 0:08:07 lr: 0.000913 loss: 3.6821 (3.7023) grad_norm: 1.0400 (1.0792) time: 0.6235 [2021-03-26 11:15:03 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 490/1251] eta: 0:08:00 lr: 0.000913 loss: 3.4838 (3.7025) grad_norm: 0.9888 (1.0792) time: 0.6221 [2021-03-26 11:15:09 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 500/1251] eta: 0:07:54 lr: 0.000913 loss: 3.6185 (3.7008) grad_norm: 1.0380 (1.0794) time: 0.6262 [2021-03-26 11:15:15 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 510/1251] eta: 0:07:48 lr: 0.000913 loss: 3.7639 (3.7024) grad_norm: 1.0589 (1.0788) time: 0.6264 [2021-03-26 11:15:22 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 520/1251] eta: 0:07:41 lr: 0.000913 loss: 3.8653 (3.7054) grad_norm: 1.0586 (1.0789) time: 0.6256 [2021-03-26 11:15:28 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 530/1251] eta: 0:07:35 lr: 0.000913 loss: 3.8739 (3.7055) grad_norm: 0.9846 (1.0771) time: 0.6261 [2021-03-26 11:15:34 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 540/1251] eta: 0:07:28 lr: 0.000913 loss: 3.8083 (3.7078) grad_norm: 0.9846 (1.0765) time: 0.6201 [2021-03-26 11:15:41 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 550/1251] eta: 0:07:22 lr: 0.000913 loss: 3.8083 (3.7086) grad_norm: 1.0396 (1.0762) time: 0.6317 [2021-03-26 11:15:47 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 560/1251] eta: 0:07:16 lr: 0.000913 loss: 3.8769 (3.7064) grad_norm: 1.0568 (1.0773) time: 0.6349 [2021-03-26 11:15:53 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 570/1251] eta: 0:07:10 lr: 0.000913 loss: 3.7597 (3.7042) grad_norm: 1.0352 (1.0762) time: 0.6296 [2021-03-26 11:15:59 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 580/1251] eta: 0:07:03 lr: 0.000913 loss: 3.6165 (3.6976) grad_norm: 1.0128 (1.0755) time: 0.6275 [2021-03-26 11:16:06 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 590/1251] eta: 0:06:57 lr: 0.000913 loss: 3.6276 (3.6964) grad_norm: 1.0778 (1.0768) time: 0.6211 [2021-03-26 11:16:12 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 600/1251] eta: 0:06:50 lr: 0.000913 loss: 3.6276 (3.6923) grad_norm: 1.1070 (1.0776) time: 0.6269 [2021-03-26 11:16:18 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 610/1251] eta: 0:06:44 lr: 0.000913 loss: 3.5997 (3.6931) grad_norm: 1.0659 (1.0776) time: 0.6313 [2021-03-26 11:16:25 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 620/1251] eta: 0:06:38 lr: 0.000913 loss: 3.5997 (3.6869) grad_norm: 1.0634 (1.0772) time: 0.6329 [2021-03-26 11:16:31 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 630/1251] eta: 0:06:32 lr: 0.000913 loss: 3.7323 (3.6890) grad_norm: 1.0833 (1.0779) time: 0.6398 [2021-03-26 11:16:37 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 640/1251] eta: 0:06:25 lr: 0.000913 loss: 3.8928 (3.6883) grad_norm: 1.1102 (1.0793) time: 0.6392 [2021-03-26 11:16:44 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 650/1251] eta: 0:06:19 lr: 0.000913 loss: 3.8034 (3.6890) grad_norm: 1.0589 (1.0792) time: 0.6330 [2021-03-26 11:16:50 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 660/1251] eta: 0:06:13 lr: 0.000913 loss: 3.7951 (3.6904) grad_norm: 1.0292 (1.0788) time: 0.6257 [2021-03-26 11:16:56 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 670/1251] eta: 0:06:06 lr: 0.000913 loss: 3.7819 (3.6926) grad_norm: 1.0784 (1.0799) time: 0.6261 [2021-03-26 11:17:03 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 680/1251] eta: 0:06:00 lr: 0.000913 loss: 3.7819 (3.6942) grad_norm: 1.1024 (1.0806) time: 0.6364 [2021-03-26 11:17:09 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 690/1251] eta: 0:05:54 lr: 0.000913 loss: 3.6311 (3.6956) grad_norm: 1.1546 (1.0821) time: 0.6345 [2021-03-26 11:17:15 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 700/1251] eta: 0:05:47 lr: 0.000913 loss: 3.9928 (3.6989) grad_norm: 1.2160 (1.0849) time: 0.6255 [2021-03-26 11:17:21 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 710/1251] eta: 0:05:41 lr: 0.000913 loss: 3.9928 (3.7015) grad_norm: 1.1283 (1.0847) time: 0.6205 [2021-03-26 11:17:28 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 720/1251] eta: 0:05:35 lr: 0.000913 loss: 3.7429 (3.6995) grad_norm: 1.0853 (1.0860) time: 0.6209 [2021-03-26 11:17:34 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 730/1251] eta: 0:05:28 lr: 0.000913 loss: 3.5618 (3.6987) grad_norm: 1.0269 (1.0849) time: 0.6245 [2021-03-26 11:17:40 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 740/1251] eta: 0:05:22 lr: 0.000913 loss: 3.7041 (3.6971) grad_norm: 0.9850 (1.0844) time: 0.6306 [2021-03-26 11:17:46 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 750/1251] eta: 0:05:16 lr: 0.000913 loss: 3.5799 (3.6942) grad_norm: 1.0649 (1.0844) time: 0.6348 [2021-03-26 11:17:53 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 760/1251] eta: 0:05:09 lr: 0.000913 loss: 3.5753 (3.6923) grad_norm: 1.0378 (1.0831) time: 0.6320 [2021-03-26 11:17:59 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 770/1251] eta: 0:05:03 lr: 0.000913 loss: 3.7955 (3.6931) grad_norm: 0.9583 (1.0818) time: 0.6235 [2021-03-26 11:18:05 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 780/1251] eta: 0:04:57 lr: 0.000913 loss: 3.8792 (3.6950) grad_norm: 0.9817 (1.0815) time: 0.6273 [2021-03-26 11:18:12 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 790/1251] eta: 0:04:50 lr: 0.000913 loss: 3.9217 (3.6978) grad_norm: 1.0636 (1.0815) time: 0.6433 [2021-03-26 11:18:18 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 800/1251] eta: 0:04:44 lr: 0.000913 loss: 3.8094 (3.6970) grad_norm: 1.1109 (1.0817) time: 0.6411 [2021-03-26 11:18:24 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 810/1251] eta: 0:04:38 lr: 0.000913 loss: 3.8559 (3.6998) grad_norm: 1.0258 (1.0808) time: 0.6300 [2021-03-26 11:18:31 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 820/1251] eta: 0:04:31 lr: 0.000912 loss: 3.8676 (3.6994) grad_norm: 1.0258 (1.0820) time: 0.6248 [2021-03-26 11:18:37 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 830/1251] eta: 0:04:25 lr: 0.000912 loss: 3.6966 (3.6956) grad_norm: 1.0368 (1.0814) time: 0.6234 [2021-03-26 11:18:43 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 840/1251] eta: 0:04:19 lr: 0.000912 loss: 3.4015 (3.6960) grad_norm: 1.0274 (1.0813) time: 0.6197 [2021-03-26 11:18:49 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 850/1251] eta: 0:04:12 lr: 0.000912 loss: 3.4015 (3.6942) grad_norm: 1.0196 (1.0806) time: 0.6149 [2021-03-26 11:18:55 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 860/1251] eta: 0:04:06 lr: 0.000912 loss: 3.5382 (3.6929) grad_norm: 1.0306 (1.0807) time: 0.6194 [2021-03-26 11:19:02 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 870/1251] eta: 0:04:00 lr: 0.000912 loss: 3.5461 (3.6909) grad_norm: 1.0348 (1.0801) time: 0.6226 [2021-03-26 11:19:08 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 880/1251] eta: 0:03:53 lr: 0.000912 loss: 3.4790 (3.6900) grad_norm: 1.0282 (1.0796) time: 0.6235 [2021-03-26 11:19:14 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 890/1251] eta: 0:03:47 lr: 0.000912 loss: 3.4790 (3.6866) grad_norm: 1.0543 (1.0792) time: 0.6198 [2021-03-26 11:19:20 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 900/1251] eta: 0:03:41 lr: 0.000912 loss: 3.5927 (3.6873) grad_norm: 1.0404 (1.0789) time: 0.6230 [2021-03-26 11:19:27 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 910/1251] eta: 0:03:34 lr: 0.000912 loss: 3.8824 (3.6897) grad_norm: 1.0231 (1.0783) time: 0.6265 [2021-03-26 11:19:33 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 920/1251] eta: 0:03:28 lr: 0.000912 loss: 3.8824 (3.6902) grad_norm: 1.0231 (1.0789) time: 0.6243 [2021-03-26 11:19:39 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 930/1251] eta: 0:03:22 lr: 0.000912 loss: 3.9171 (3.6916) grad_norm: 1.0997 (1.0788) time: 0.6270 [2021-03-26 11:19:46 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 940/1251] eta: 0:03:15 lr: 0.000912 loss: 4.0512 (3.6930) grad_norm: 1.0831 (1.0797) time: 0.6325 [2021-03-26 11:19:52 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 950/1251] eta: 0:03:09 lr: 0.000912 loss: 4.0260 (3.6937) grad_norm: 1.0569 (1.0796) time: 0.6305 [2021-03-26 11:19:58 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 960/1251] eta: 0:03:03 lr: 0.000912 loss: 3.9812 (3.6940) grad_norm: 1.0156 (1.0793) time: 0.6240 [2021-03-26 11:20:04 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 970/1251] eta: 0:02:57 lr: 0.000912 loss: 3.9243 (3.6959) grad_norm: 1.1108 (1.0802) time: 0.6261 [2021-03-26 11:20:11 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 980/1251] eta: 0:02:50 lr: 0.000912 loss: 3.9243 (3.6982) grad_norm: 1.1459 (1.0804) time: 0.6308 [2021-03-26 11:20:17 swin_base_patch4_window7_224] INFO: Epoch: [57] [ 990/1251] eta: 0:02:44 lr: 0.000912 loss: 3.8597 (3.6973) grad_norm: 1.1127 (1.0805) time: 0.6314 [2021-03-26 11:20:23 swin_base_patch4_window7_224] INFO: Epoch: [57] [1000/1251] eta: 0:02:38 lr: 0.000912 loss: 3.8557 (3.6999) grad_norm: 1.0474 (1.0798) time: 0.6246 [2021-03-26 11:20:29 swin_base_patch4_window7_224] INFO: Epoch: [57] [1010/1251] eta: 0:02:31 lr: 0.000912 loss: 3.9081 (3.7009) grad_norm: 1.0059 (1.0794) time: 0.6205 [2021-03-26 11:20:36 swin_base_patch4_window7_224] INFO: Epoch: [57] [1020/1251] eta: 0:02:25 lr: 0.000912 loss: 3.7416 (3.6990) grad_norm: 1.0493 (1.0798) time: 0.6224 [2021-03-26 11:20:42 swin_base_patch4_window7_224] INFO: Epoch: [57] [1030/1251] eta: 0:02:19 lr: 0.000912 loss: 3.5626 (3.6984) grad_norm: 1.0689 (1.0796) time: 0.6241 [2021-03-26 11:20:48 swin_base_patch4_window7_224] INFO: Epoch: [57] [1040/1251] eta: 0:02:12 lr: 0.000912 loss: 3.6188 (3.6993) grad_norm: 1.0362 (1.0791) time: 0.6236 [2021-03-26 11:20:54 swin_base_patch4_window7_224] INFO: Epoch: [57] [1050/1251] eta: 0:02:06 lr: 0.000912 loss: 3.6188 (3.6972) grad_norm: 0.9989 (1.0787) time: 0.6276 [2021-03-26 11:21:01 swin_base_patch4_window7_224] INFO: Epoch: [57] [1060/1251] eta: 0:02:00 lr: 0.000912 loss: 3.3927 (3.6954) grad_norm: 1.0050 (1.0785) time: 0.6295 [2021-03-26 11:21:07 swin_base_patch4_window7_224] INFO: Epoch: [57] [1070/1251] eta: 0:01:53 lr: 0.000912 loss: 3.7837 (3.6961) grad_norm: 1.0050 (1.0779) time: 0.6309 [2021-03-26 11:21:13 swin_base_patch4_window7_224] INFO: Epoch: [57] [1080/1251] eta: 0:01:47 lr: 0.000912 loss: 3.9021 (3.6976) grad_norm: 0.9992 (1.0771) time: 0.6341 [2021-03-26 11:21:20 swin_base_patch4_window7_224] INFO: Epoch: [57] [1090/1251] eta: 0:01:41 lr: 0.000912 loss: 3.9793 (3.6976) grad_norm: 1.0107 (1.0771) time: 0.6272 [2021-03-26 11:21:26 swin_base_patch4_window7_224] INFO: Epoch: [57] [1100/1251] eta: 0:01:35 lr: 0.000912 loss: 3.9630 (3.6979) grad_norm: 1.0299 (1.0768) time: 0.6213 [2021-03-26 11:21:32 swin_base_patch4_window7_224] INFO: Epoch: [57] [1110/1251] eta: 0:01:28 lr: 0.000912 loss: 3.9630 (3.6994) grad_norm: 1.0287 (1.0768) time: 0.6208 [2021-03-26 11:21:38 swin_base_patch4_window7_224] INFO: Epoch: [57] [1120/1251] eta: 0:01:22 lr: 0.000912 loss: 3.5935 (3.6968) grad_norm: 1.0888 (1.0785) time: 0.6221 [2021-03-26 11:21:44 swin_base_patch4_window7_224] INFO: Epoch: [57] [1130/1251] eta: 0:01:16 lr: 0.000912 loss: 3.5456 (3.6955) grad_norm: 1.1284 (1.0784) time: 0.6235 [2021-03-26 11:21:51 swin_base_patch4_window7_224] INFO: Epoch: [57] [1140/1251] eta: 0:01:09 lr: 0.000912 loss: 3.9419 (3.6974) grad_norm: 1.0261 (1.0782) time: 0.6192 [2021-03-26 11:21:57 swin_base_patch4_window7_224] INFO: Epoch: [57] [1150/1251] eta: 0:01:03 lr: 0.000912 loss: 3.9462 (3.6983) grad_norm: 0.9968 (1.0779) time: 0.6194 [2021-03-26 11:22:03 swin_base_patch4_window7_224] INFO: Epoch: [57] [1160/1251] eta: 0:00:57 lr: 0.000912 loss: 3.7238 (3.6996) grad_norm: 0.9901 (1.0777) time: 0.6245 [2021-03-26 11:22:09 swin_base_patch4_window7_224] INFO: Epoch: [57] [1170/1251] eta: 0:00:50 lr: 0.000912 loss: 3.6981 (3.6991) grad_norm: 1.0897 (1.0780) time: 0.6251 [2021-03-26 11:22:16 swin_base_patch4_window7_224] INFO: Epoch: [57] [1180/1251] eta: 0:00:44 lr: 0.000912 loss: 3.4966 (3.6975) grad_norm: 1.0699 (1.0779) time: 0.6214 [2021-03-26 11:22:22 swin_base_patch4_window7_224] INFO: Epoch: [57] [1190/1251] eta: 0:00:38 lr: 0.000912 loss: 3.5467 (3.6964) grad_norm: 1.1257 (1.0794) time: 0.6273 [2021-03-26 11:22:28 swin_base_patch4_window7_224] INFO: Epoch: [57] [1200/1251] eta: 0:00:32 lr: 0.000912 loss: 3.5899 (3.6972) grad_norm: 1.1179 (1.0794) time: 0.6272 [2021-03-26 11:22:34 swin_base_patch4_window7_224] INFO: Epoch: [57] [1210/1251] eta: 0:00:25 lr: 0.000912 loss: 3.6698 (3.6934) grad_norm: 1.0108 (1.0792) time: 0.6193 [2021-03-26 11:22:41 swin_base_patch4_window7_224] INFO: Epoch: [57] [1220/1251] eta: 0:00:19 lr: 0.000912 loss: 3.4786 (3.6910) grad_norm: 1.0463 (1.0794) time: 0.6222 [2021-03-26 11:22:47 swin_base_patch4_window7_224] INFO: Epoch: [57] [1230/1251] eta: 0:00:13 lr: 0.000912 loss: 3.5397 (3.6904) grad_norm: 1.1129 (1.0796) time: 0.6260 [2021-03-26 11:22:53 swin_base_patch4_window7_224] INFO: Epoch: [57] [1240/1251] eta: 0:00:06 lr: 0.000911 loss: 3.6889 (3.6906) grad_norm: 1.1233 (1.0806) time: 0.6186 [2021-03-26 11:22:59 swin_base_patch4_window7_224] INFO: Epoch: [57] [1250/1251] eta: 0:00:00 lr: 0.000911 loss: 3.6889 (3.6909) grad_norm: 1.1095 (1.0804) time: 0.6135 [2021-03-26 11:23:04 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:13 loss: 1.1694 (1.1694) acc1: 65.6250 (65.6250) acc5: 95.3125 (95.3125) [2021-03-26 11:23:07 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.1208 (1.1521) acc1: 71.8750 (70.8807) acc5: 93.7500 (92.8977) [2021-03-26 11:23:08 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.1208 (1.1368) acc1: 71.8750 (71.2054) acc5: 92.1875 (93.1548) [2021-03-26 11:23:10 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0157 (1.1257) acc1: 73.4375 (71.9758) acc5: 92.1875 (92.8427) [2021-03-26 11:23:12 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1138 (1.1312) acc1: 71.8750 (72.0274) acc5: 92.1875 (92.5305) [2021-03-26 11:23:13 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1764 (1.1450) acc1: 71.8750 (72.1600) acc5: 90.6250 (92.2240) [2021-03-26 11:23:18 swin_base_patch4_window7_224] INFO: * Acc@1 73.458 Acc@5 92.228 loss 1.122 [2021-03-26 11:23:18 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.5% [2021-03-26 11:23:18 swin_base_patch4_window7_224] INFO: Max accuracy: 73.48% [2021-03-26 11:23:23 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 0/1251] eta: 1:33:44 lr: 0.000911 loss: 4.1261 (4.1261) grad_norm: 0.9142 (0.9142) time: 4.4960 [2021-03-26 11:23:29 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 10/1251] eta: 0:20:26 lr: 0.000911 loss: 3.3152 (3.3453) grad_norm: 1.0294 (1.0565) time: 0.9883 [2021-03-26 11:23:35 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 20/1251] eta: 0:16:43 lr: 0.000911 loss: 3.3152 (3.5034) grad_norm: 1.0294 (1.0564) time: 0.6311 [2021-03-26 11:23:41 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 30/1251] eta: 0:15:19 lr: 0.000911 loss: 3.5674 (3.4862) grad_norm: 1.0272 (1.0839) time: 0.6239 [2021-03-26 11:23:48 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 40/1251] eta: 0:14:33 lr: 0.000911 loss: 3.7241 (3.5541) grad_norm: 1.1313 (1.0996) time: 0.6229 [2021-03-26 11:23:54 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 50/1251] eta: 0:14:03 lr: 0.000911 loss: 3.7729 (3.5674) grad_norm: 1.1252 (1.0989) time: 0.6235 [2021-03-26 11:24:00 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 60/1251] eta: 0:13:42 lr: 0.000911 loss: 3.5242 (3.5592) grad_norm: 1.1460 (1.1162) time: 0.6283 [2021-03-26 11:24:06 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 70/1251] eta: 0:13:24 lr: 0.000911 loss: 3.6189 (3.5850) grad_norm: 1.1460 (1.1126) time: 0.6271 [2021-03-26 11:24:13 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 80/1251] eta: 0:13:09 lr: 0.000911 loss: 3.8397 (3.6315) grad_norm: 1.0296 (1.1051) time: 0.6223 [2021-03-26 11:24:19 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 90/1251] eta: 0:12:56 lr: 0.000911 loss: 3.9807 (3.6726) grad_norm: 1.0252 (1.1046) time: 0.6239 [2021-03-26 11:24:25 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 100/1251] eta: 0:12:43 lr: 0.000911 loss: 3.9807 (3.6753) grad_norm: 1.1217 (1.1091) time: 0.6214 [2021-03-26 11:24:31 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 110/1251] eta: 0:12:32 lr: 0.000911 loss: 3.6713 (3.6731) grad_norm: 1.0645 (1.1063) time: 0.6201 [2021-03-26 11:24:38 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 120/1251] eta: 0:12:24 lr: 0.000911 loss: 3.6075 (3.6592) grad_norm: 1.0159 (1.1116) time: 0.6290 [2021-03-26 11:24:44 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 130/1251] eta: 0:12:15 lr: 0.000911 loss: 3.7149 (3.6640) grad_norm: 1.0410 (1.1085) time: 0.6347 [2021-03-26 11:24:50 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 140/1251] eta: 0:12:06 lr: 0.000911 loss: 3.7835 (3.6615) grad_norm: 1.0876 (1.1159) time: 0.6312 [2021-03-26 11:24:57 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 150/1251] eta: 0:11:58 lr: 0.000911 loss: 3.8642 (3.6735) grad_norm: 1.1603 (1.1180) time: 0.6275 [2021-03-26 11:25:03 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 160/1251] eta: 0:11:49 lr: 0.000911 loss: 3.8643 (3.6819) grad_norm: 1.0135 (1.1098) time: 0.6219 [2021-03-26 11:25:09 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 170/1251] eta: 0:11:41 lr: 0.000911 loss: 3.7965 (3.6883) grad_norm: 0.9984 (1.1053) time: 0.6203 [2021-03-26 11:25:15 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 180/1251] eta: 0:11:34 lr: 0.000911 loss: 3.7451 (3.6887) grad_norm: 1.0504 (1.1059) time: 0.6324 [2021-03-26 11:25:22 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 190/1251] eta: 0:11:26 lr: 0.000911 loss: 3.8513 (3.6917) grad_norm: 1.0609 (1.1050) time: 0.6307 [2021-03-26 11:25:28 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 200/1251] eta: 0:11:18 lr: 0.000911 loss: 3.9168 (3.6898) grad_norm: 1.0277 (1.1000) time: 0.6212 [2021-03-26 11:25:34 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 210/1251] eta: 0:11:11 lr: 0.000911 loss: 3.8449 (3.6964) grad_norm: 1.0455 (1.0996) time: 0.6252 [2021-03-26 11:25:40 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 220/1251] eta: 0:11:03 lr: 0.000911 loss: 3.7844 (3.6933) grad_norm: 1.0638 (1.1014) time: 0.6242 [2021-03-26 11:25:47 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 230/1251] eta: 0:10:56 lr: 0.000911 loss: 3.5792 (3.6844) grad_norm: 1.0620 (1.1018) time: 0.6236 [2021-03-26 11:25:53 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 240/1251] eta: 0:10:48 lr: 0.000911 loss: 3.7571 (3.6817) grad_norm: 0.9868 (1.0980) time: 0.6199 [2021-03-26 11:25:59 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 250/1251] eta: 0:10:41 lr: 0.000911 loss: 3.7089 (3.6804) grad_norm: 0.9851 (1.0966) time: 0.6171 [2021-03-26 11:26:05 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 260/1251] eta: 0:10:34 lr: 0.000911 loss: 3.7317 (3.6850) grad_norm: 1.0131 (1.0958) time: 0.6243 [2021-03-26 11:26:11 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 270/1251] eta: 0:10:27 lr: 0.000911 loss: 3.9244 (3.6875) grad_norm: 1.0596 (1.0974) time: 0.6257 [2021-03-26 11:26:18 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 280/1251] eta: 0:10:20 lr: 0.000911 loss: 3.9099 (3.6906) grad_norm: 1.0881 (1.0970) time: 0.6210 [2021-03-26 11:26:24 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 290/1251] eta: 0:10:13 lr: 0.000911 loss: 3.9099 (3.6922) grad_norm: 1.0697 (1.0962) time: 0.6210 [2021-03-26 11:26:30 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 300/1251] eta: 0:10:06 lr: 0.000911 loss: 3.7794 (3.6904) grad_norm: 1.0697 (1.0972) time: 0.6292 [2021-03-26 11:26:37 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 310/1251] eta: 0:10:00 lr: 0.000911 loss: 3.7398 (3.6893) grad_norm: 1.0893 (1.0990) time: 0.6368 [2021-03-26 11:26:43 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 320/1251] eta: 0:09:54 lr: 0.000911 loss: 3.7398 (3.6920) grad_norm: 1.1264 (1.1016) time: 0.6376 [2021-03-26 11:26:49 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 330/1251] eta: 0:09:47 lr: 0.000911 loss: 3.9966 (3.7009) grad_norm: 1.1185 (1.1033) time: 0.6299 [2021-03-26 11:26:55 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 340/1251] eta: 0:09:40 lr: 0.000911 loss: 3.9239 (3.7001) grad_norm: 1.0658 (1.1002) time: 0.6245 [2021-03-26 11:27:02 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 350/1251] eta: 0:09:33 lr: 0.000911 loss: 3.8290 (3.7024) grad_norm: 0.9895 (1.0968) time: 0.6215 [2021-03-26 11:27:08 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 360/1251] eta: 0:09:27 lr: 0.000911 loss: 3.7972 (3.7048) grad_norm: 1.0201 (1.1010) time: 0.6234 [2021-03-26 11:27:14 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 370/1251] eta: 0:09:20 lr: 0.000911 loss: 3.7219 (3.7015) grad_norm: 1.1469 (1.1017) time: 0.6248 [2021-03-26 11:27:20 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 380/1251] eta: 0:09:13 lr: 0.000911 loss: 3.6437 (3.6963) grad_norm: 1.1109 (1.1018) time: 0.6248 [2021-03-26 11:27:27 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 390/1251] eta: 0:09:07 lr: 0.000911 loss: 3.6589 (3.7004) grad_norm: 1.0821 (1.1020) time: 0.6229 [2021-03-26 11:27:33 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 400/1251] eta: 0:09:00 lr: 0.000911 loss: 3.9511 (3.7030) grad_norm: 1.0514 (1.1002) time: 0.6209 [2021-03-26 11:27:39 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 410/1251] eta: 0:08:53 lr: 0.000910 loss: 3.8832 (3.7060) grad_norm: 1.0350 (1.1006) time: 0.6223 [2021-03-26 11:27:45 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 420/1251] eta: 0:08:47 lr: 0.000910 loss: 3.9247 (3.7067) grad_norm: 1.0091 (1.0986) time: 0.6281 [2021-03-26 11:27:52 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 430/1251] eta: 0:08:40 lr: 0.000910 loss: 3.9671 (3.7141) grad_norm: 0.9799 (1.0968) time: 0.6288 [2021-03-26 11:27:58 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 440/1251] eta: 0:08:34 lr: 0.000910 loss: 3.9671 (3.7198) grad_norm: 1.0046 (1.0963) time: 0.6274 [2021-03-26 11:28:04 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 450/1251] eta: 0:08:28 lr: 0.000910 loss: 3.8083 (3.7192) grad_norm: 1.0702 (1.0961) time: 0.6300 [2021-03-26 11:28:10 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 460/1251] eta: 0:08:21 lr: 0.000910 loss: 3.6265 (3.7157) grad_norm: 0.9817 (1.0939) time: 0.6227 [2021-03-26 11:28:17 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 470/1251] eta: 0:08:14 lr: 0.000910 loss: 3.7462 (3.7158) grad_norm: 1.0207 (1.0933) time: 0.6188 [2021-03-26 11:28:23 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 480/1251] eta: 0:08:08 lr: 0.000910 loss: 3.8784 (3.7184) grad_norm: 1.0345 (1.0917) time: 0.6208 [2021-03-26 11:28:29 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 490/1251] eta: 0:08:01 lr: 0.000910 loss: 3.5724 (3.7136) grad_norm: 1.0356 (1.0911) time: 0.6229 [2021-03-26 11:28:35 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 500/1251] eta: 0:07:55 lr: 0.000910 loss: 3.4349 (3.7073) grad_norm: 1.0757 (1.0913) time: 0.6234 [2021-03-26 11:28:42 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 510/1251] eta: 0:07:49 lr: 0.000910 loss: 3.8869 (3.7162) grad_norm: 1.1602 (1.0947) time: 0.6326 [2021-03-26 11:28:48 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 520/1251] eta: 0:07:42 lr: 0.000910 loss: 3.8963 (3.7162) grad_norm: 1.1975 (1.0959) time: 0.6340 [2021-03-26 11:28:54 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 530/1251] eta: 0:07:36 lr: 0.000910 loss: 3.6635 (3.7171) grad_norm: 1.0919 (1.0949) time: 0.6246 [2021-03-26 11:29:00 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 540/1251] eta: 0:07:29 lr: 0.000910 loss: 3.8759 (3.7235) grad_norm: 1.0212 (1.0947) time: 0.6207 [2021-03-26 11:29:07 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 550/1251] eta: 0:07:23 lr: 0.000910 loss: 3.8525 (3.7209) grad_norm: 1.0423 (1.0943) time: 0.6403 [2021-03-26 11:29:13 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 560/1251] eta: 0:07:17 lr: 0.000910 loss: 3.7143 (3.7203) grad_norm: 1.0760 (1.0952) time: 0.6416 [2021-03-26 11:29:20 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 570/1251] eta: 0:07:10 lr: 0.000910 loss: 3.9943 (3.7250) grad_norm: 1.1478 (1.0964) time: 0.6248 [2021-03-26 11:29:26 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 580/1251] eta: 0:07:04 lr: 0.000910 loss: 4.1024 (3.7316) grad_norm: 1.1041 (1.0956) time: 0.6299 [2021-03-26 11:29:32 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 590/1251] eta: 0:06:58 lr: 0.000910 loss: 3.7423 (3.7277) grad_norm: 1.1492 (1.0969) time: 0.6337 [2021-03-26 11:29:39 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 600/1251] eta: 0:06:52 lr: 0.000910 loss: 3.7312 (3.7283) grad_norm: 1.1437 (1.0974) time: 0.6384 [2021-03-26 11:29:45 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 610/1251] eta: 0:06:45 lr: 0.000910 loss: 3.8150 (3.7282) grad_norm: 1.0874 (1.0971) time: 0.6332 [2021-03-26 11:29:51 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 620/1251] eta: 0:06:39 lr: 0.000910 loss: 3.8911 (3.7284) grad_norm: 1.0404 (1.0972) time: 0.6264 [2021-03-26 11:29:57 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 630/1251] eta: 0:06:33 lr: 0.000910 loss: 3.8038 (3.7261) grad_norm: 1.0462 (1.0970) time: 0.6314 [2021-03-26 11:30:04 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 640/1251] eta: 0:06:26 lr: 0.000910 loss: 3.8099 (3.7272) grad_norm: 1.0810 (1.0961) time: 0.6285 [2021-03-26 11:30:10 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 650/1251] eta: 0:06:20 lr: 0.000910 loss: 3.8388 (3.7302) grad_norm: 0.9801 (1.0946) time: 0.6184 [2021-03-26 11:30:16 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 660/1251] eta: 0:06:13 lr: 0.000910 loss: 4.0071 (3.7320) grad_norm: 1.0339 (1.0946) time: 0.6220 [2021-03-26 11:30:22 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 670/1251] eta: 0:06:07 lr: 0.000910 loss: 4.0071 (3.7332) grad_norm: 1.0908 (1.0942) time: 0.6260 [2021-03-26 11:30:29 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 680/1251] eta: 0:06:00 lr: 0.000910 loss: 3.7455 (3.7318) grad_norm: 1.0805 (1.0940) time: 0.6234 [2021-03-26 11:30:35 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 690/1251] eta: 0:05:54 lr: 0.000910 loss: 3.7217 (3.7283) grad_norm: 1.0513 (1.0950) time: 0.6253 [2021-03-26 11:30:41 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 700/1251] eta: 0:05:48 lr: 0.000910 loss: 3.7923 (3.7288) grad_norm: 1.1107 (1.0969) time: 0.6330 [2021-03-26 11:30:48 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 710/1251] eta: 0:05:41 lr: 0.000910 loss: 3.7530 (3.7295) grad_norm: 1.1211 (1.0978) time: 0.6313 [2021-03-26 11:30:54 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 720/1251] eta: 0:05:35 lr: 0.000910 loss: 3.7530 (3.7303) grad_norm: 1.0873 (1.0975) time: 0.6265 [2021-03-26 11:31:00 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 730/1251] eta: 0:05:29 lr: 0.000910 loss: 3.8463 (3.7321) grad_norm: 1.0527 (1.0976) time: 0.6335 [2021-03-26 11:31:07 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 740/1251] eta: 0:05:23 lr: 0.000910 loss: 3.7559 (3.7301) grad_norm: 1.0848 (1.0982) time: 0.6367 [2021-03-26 11:31:13 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 750/1251] eta: 0:05:16 lr: 0.000910 loss: 3.5904 (3.7302) grad_norm: 1.0848 (1.0988) time: 0.6408 [2021-03-26 11:31:19 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 760/1251] eta: 0:05:10 lr: 0.000910 loss: 3.6273 (3.7278) grad_norm: 1.0640 (1.0986) time: 0.6394 [2021-03-26 11:31:26 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 770/1251] eta: 0:05:04 lr: 0.000910 loss: 3.7706 (3.7274) grad_norm: 1.0000 (1.0971) time: 0.6280 [2021-03-26 11:31:32 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 780/1251] eta: 0:04:57 lr: 0.000910 loss: 3.9007 (3.7261) grad_norm: 0.9873 (1.0964) time: 0.6201 [2021-03-26 11:31:38 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 790/1251] eta: 0:04:51 lr: 0.000910 loss: 3.8030 (3.7253) grad_norm: 1.0734 (1.0966) time: 0.6266 [2021-03-26 11:31:44 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 800/1251] eta: 0:04:45 lr: 0.000910 loss: 3.7966 (3.7258) grad_norm: 1.0776 (1.0959) time: 0.6317 [2021-03-26 11:31:51 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 810/1251] eta: 0:04:38 lr: 0.000910 loss: 3.9515 (3.7264) grad_norm: 0.9933 (1.0949) time: 0.6232 [2021-03-26 11:31:57 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 820/1251] eta: 0:04:32 lr: 0.000910 loss: 3.9239 (3.7261) grad_norm: 0.9804 (1.0939) time: 0.6161 [2021-03-26 11:32:03 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 830/1251] eta: 0:04:25 lr: 0.000909 loss: 3.6838 (3.7252) grad_norm: 1.0135 (1.0937) time: 0.6232 [2021-03-26 11:32:09 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 840/1251] eta: 0:04:19 lr: 0.000909 loss: 3.8208 (3.7262) grad_norm: 1.0926 (1.0945) time: 0.6288 [2021-03-26 11:32:16 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 850/1251] eta: 0:04:13 lr: 0.000909 loss: 3.7114 (3.7231) grad_norm: 1.1209 (1.0946) time: 0.6281 [2021-03-26 11:32:22 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 860/1251] eta: 0:04:06 lr: 0.000909 loss: 3.7055 (3.7229) grad_norm: 1.0624 (1.0948) time: 0.6313 [2021-03-26 11:32:28 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 870/1251] eta: 0:04:00 lr: 0.000909 loss: 3.7348 (3.7217) grad_norm: 1.0434 (1.0946) time: 0.6340 [2021-03-26 11:32:34 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 880/1251] eta: 0:03:54 lr: 0.000909 loss: 3.8966 (3.7232) grad_norm: 0.9896 (1.0932) time: 0.6262 [2021-03-26 11:32:41 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 890/1251] eta: 0:03:47 lr: 0.000909 loss: 3.6704 (3.7224) grad_norm: 0.9604 (1.0929) time: 0.6244 [2021-03-26 11:32:47 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 900/1251] eta: 0:03:41 lr: 0.000909 loss: 3.6551 (3.7230) grad_norm: 1.0159 (1.0924) time: 0.6302 [2021-03-26 11:32:53 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 910/1251] eta: 0:03:35 lr: 0.000909 loss: 3.5616 (3.7199) grad_norm: 1.0845 (1.0936) time: 0.6254 [2021-03-26 11:33:00 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 920/1251] eta: 0:03:28 lr: 0.000909 loss: 3.8384 (3.7226) grad_norm: 1.0875 (1.0935) time: 0.6264 [2021-03-26 11:33:06 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 930/1251] eta: 0:03:22 lr: 0.000909 loss: 3.9185 (3.7237) grad_norm: 1.0431 (1.0932) time: 0.6285 [2021-03-26 11:33:12 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 940/1251] eta: 0:03:16 lr: 0.000909 loss: 3.8304 (3.7244) grad_norm: 1.0597 (1.0932) time: 0.6264 [2021-03-26 11:33:18 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 950/1251] eta: 0:03:09 lr: 0.000909 loss: 3.7493 (3.7236) grad_norm: 1.0529 (1.0928) time: 0.6284 [2021-03-26 11:33:25 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 960/1251] eta: 0:03:03 lr: 0.000909 loss: 3.5471 (3.7216) grad_norm: 1.0448 (1.0925) time: 0.6274 [2021-03-26 11:33:31 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 970/1251] eta: 0:02:57 lr: 0.000909 loss: 3.6066 (3.7227) grad_norm: 1.0716 (1.0927) time: 0.6239 [2021-03-26 11:33:37 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 980/1251] eta: 0:02:51 lr: 0.000909 loss: 3.9400 (3.7234) grad_norm: 1.1181 (1.0932) time: 0.6282 [2021-03-26 11:33:44 swin_base_patch4_window7_224] INFO: Epoch: [58] [ 990/1251] eta: 0:02:44 lr: 0.000909 loss: 3.7763 (3.7217) grad_norm: 1.0930 (1.0936) time: 0.6346 [2021-03-26 11:33:50 swin_base_patch4_window7_224] INFO: Epoch: [58] [1000/1251] eta: 0:02:38 lr: 0.000909 loss: 3.4880 (3.7192) grad_norm: 1.0825 (1.0936) time: 0.6378 [2021-03-26 11:33:56 swin_base_patch4_window7_224] INFO: Epoch: [58] [1010/1251] eta: 0:02:32 lr: 0.000909 loss: 3.6697 (3.7187) grad_norm: 1.1024 (1.0938) time: 0.6335 [2021-03-26 11:34:02 swin_base_patch4_window7_224] INFO: Epoch: [58] [1020/1251] eta: 0:02:25 lr: 0.000909 loss: 3.8495 (3.7194) grad_norm: 1.1048 (1.0943) time: 0.6237 [2021-03-26 11:34:09 swin_base_patch4_window7_224] INFO: Epoch: [58] [1030/1251] eta: 0:02:19 lr: 0.000909 loss: 3.9102 (3.7197) grad_norm: 1.0524 (1.0941) time: 0.6215 [2021-03-26 11:34:15 swin_base_patch4_window7_224] INFO: Epoch: [58] [1040/1251] eta: 0:02:13 lr: 0.000909 loss: 3.7871 (3.7183) grad_norm: 1.0135 (1.0932) time: 0.6254 [2021-03-26 11:34:21 swin_base_patch4_window7_224] INFO: Epoch: [58] [1050/1251] eta: 0:02:06 lr: 0.000909 loss: 3.7871 (3.7196) grad_norm: 1.0293 (1.0931) time: 0.6245 [2021-03-26 11:34:27 swin_base_patch4_window7_224] INFO: Epoch: [58] [1060/1251] eta: 0:02:00 lr: 0.000909 loss: 3.8161 (3.7184) grad_norm: 1.0821 (1.0944) time: 0.6244 [2021-03-26 11:34:34 swin_base_patch4_window7_224] INFO: Epoch: [58] [1070/1251] eta: 0:01:54 lr: 0.000909 loss: 3.8161 (3.7197) grad_norm: 1.1022 (1.0952) time: 0.6305 [2021-03-26 11:34:40 swin_base_patch4_window7_224] INFO: Epoch: [58] [1080/1251] eta: 0:01:47 lr: 0.000909 loss: 3.8670 (3.7206) grad_norm: 1.0661 (1.0956) time: 0.6289 [2021-03-26 11:34:46 swin_base_patch4_window7_224] INFO: Epoch: [58] [1090/1251] eta: 0:01:41 lr: 0.000909 loss: 3.8778 (3.7199) grad_norm: 1.0661 (1.0954) time: 0.6266 [2021-03-26 11:34:53 swin_base_patch4_window7_224] INFO: Epoch: [58] [1100/1251] eta: 0:01:35 lr: 0.000909 loss: 3.4510 (3.7174) grad_norm: 1.0467 (1.0949) time: 0.6271 [2021-03-26 11:34:59 swin_base_patch4_window7_224] INFO: Epoch: [58] [1110/1251] eta: 0:01:28 lr: 0.000909 loss: 3.5013 (3.7172) grad_norm: 1.0252 (1.0945) time: 0.6231 [2021-03-26 11:35:05 swin_base_patch4_window7_224] INFO: Epoch: [58] [1120/1251] eta: 0:01:22 lr: 0.000909 loss: 3.8913 (3.7184) grad_norm: 1.0774 (1.0953) time: 0.6250 [2021-03-26 11:35:11 swin_base_patch4_window7_224] INFO: Epoch: [58] [1130/1251] eta: 0:01:16 lr: 0.000909 loss: 3.6578 (3.7170) grad_norm: 1.1311 (1.0958) time: 0.6311 [2021-03-26 11:35:18 swin_base_patch4_window7_224] INFO: Epoch: [58] [1140/1251] eta: 0:01:09 lr: 0.000909 loss: 3.4574 (3.7151) grad_norm: 1.0796 (1.0958) time: 0.6324 [2021-03-26 11:35:24 swin_base_patch4_window7_224] INFO: Epoch: [58] [1150/1251] eta: 0:01:03 lr: 0.000909 loss: 3.5717 (3.7138) grad_norm: 1.0729 (1.0960) time: 0.6337 [2021-03-26 11:35:30 swin_base_patch4_window7_224] INFO: Epoch: [58] [1160/1251] eta: 0:00:57 lr: 0.000909 loss: 3.5516 (3.7103) grad_norm: 1.0729 (1.0963) time: 0.6349 [2021-03-26 11:35:37 swin_base_patch4_window7_224] INFO: Epoch: [58] [1170/1251] eta: 0:00:51 lr: 0.000909 loss: 3.6823 (3.7109) grad_norm: 1.0529 (1.0959) time: 0.6260 [2021-03-26 11:35:43 swin_base_patch4_window7_224] INFO: Epoch: [58] [1180/1251] eta: 0:00:44 lr: 0.000909 loss: 3.9028 (3.7119) grad_norm: 1.0005 (1.0953) time: 0.6212 [2021-03-26 11:35:49 swin_base_patch4_window7_224] INFO: Epoch: [58] [1190/1251] eta: 0:00:38 lr: 0.000909 loss: 3.8487 (3.7123) grad_norm: 1.0272 (1.0955) time: 0.6305 [2021-03-26 11:35:56 swin_base_patch4_window7_224] INFO: Epoch: [58] [1200/1251] eta: 0:00:32 lr: 0.000909 loss: 3.7512 (3.7119) grad_norm: 1.1252 (1.0965) time: 0.6333 [2021-03-26 11:36:02 swin_base_patch4_window7_224] INFO: Epoch: [58] [1210/1251] eta: 0:00:25 lr: 0.000909 loss: 3.9167 (3.7121) grad_norm: 1.1252 (1.0965) time: 0.6304 [2021-03-26 11:36:08 swin_base_patch4_window7_224] INFO: Epoch: [58] [1220/1251] eta: 0:00:19 lr: 0.000909 loss: 3.6399 (3.7113) grad_norm: 1.0847 (1.0967) time: 0.6296 [2021-03-26 11:36:14 swin_base_patch4_window7_224] INFO: Epoch: [58] [1230/1251] eta: 0:00:13 lr: 0.000909 loss: 3.6399 (3.7113) grad_norm: 1.0734 (1.0968) time: 0.6247 [2021-03-26 11:36:21 swin_base_patch4_window7_224] INFO: Epoch: [58] [1240/1251] eta: 0:00:06 lr: 0.000909 loss: 3.8071 (3.7129) grad_norm: 1.1177 (1.0978) time: 0.6257 [2021-03-26 11:36:27 swin_base_patch4_window7_224] INFO: Epoch: [58] [1250/1251] eta: 0:00:00 lr: 0.000908 loss: 3.7978 (3.7114) grad_norm: 1.1651 (1.0979) time: 0.6224 [2021-03-26 11:36:32 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:58 loss: 1.1192 (1.1192) acc1: 81.2500 (81.2500) acc5: 92.1875 (92.1875) [2021-03-26 11:36:34 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.2069 (1.1770) acc1: 75.0000 (74.5739) acc5: 90.6250 (90.7670) [2021-03-26 11:36:36 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.1977 (1.2014) acc1: 70.3125 (72.2470) acc5: 90.6250 (91.2946) [2021-03-26 11:36:38 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1023 (1.1403) acc1: 71.8750 (74.0927) acc5: 93.7500 (91.7843) [2021-03-26 11:36:41 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1047 (1.1550) acc1: 73.4375 (73.1326) acc5: 92.1875 (91.6540) [2021-03-26 11:36:42 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1002 (1.1329) acc1: 71.8750 (73.4080) acc5: 92.1875 (91.9680) [2021-03-26 11:36:46 swin_base_patch4_window7_224] INFO: * Acc@1 74.088 Acc@5 92.354 loss 1.112 [2021-03-26 11:36:46 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.1% [2021-03-26 11:36:46 swin_base_patch4_window7_224] INFO: Max accuracy: 74.09% [2021-03-26 11:36:50 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 0/1251] eta: 1:29:07 lr: 0.000908 loss: 4.0998 (4.0998) grad_norm: 1.0663 (1.0663) time: 4.2745 [2021-03-26 11:36:56 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 10/1251] eta: 0:19:59 lr: 0.000908 loss: 3.8643 (3.7525) grad_norm: 1.0264 (1.0287) time: 0.9664 [2021-03-26 11:37:03 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 20/1251] eta: 0:16:34 lr: 0.000908 loss: 3.6403 (3.6486) grad_norm: 1.0367 (1.0456) time: 0.6346 [2021-03-26 11:37:09 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 30/1251] eta: 0:15:13 lr: 0.000908 loss: 3.7187 (3.7070) grad_norm: 1.0367 (1.0361) time: 0.6276 [2021-03-26 11:37:15 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 40/1251] eta: 0:14:28 lr: 0.000908 loss: 3.9740 (3.7464) grad_norm: 1.0255 (1.0544) time: 0.6225 [2021-03-26 11:37:22 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 50/1251] eta: 0:14:02 lr: 0.000908 loss: 3.7094 (3.7054) grad_norm: 1.1210 (1.0761) time: 0.6304 [2021-03-26 11:37:28 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 60/1251] eta: 0:13:40 lr: 0.000908 loss: 3.6420 (3.6873) grad_norm: 1.1210 (1.0867) time: 0.6305 [2021-03-26 11:37:34 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 70/1251] eta: 0:13:23 lr: 0.000908 loss: 3.6881 (3.6563) grad_norm: 1.0208 (1.0879) time: 0.6266 [2021-03-26 11:37:40 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 80/1251] eta: 0:13:08 lr: 0.000908 loss: 3.4525 (3.6245) grad_norm: 1.0293 (1.0878) time: 0.6242 [2021-03-26 11:37:47 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 90/1251] eta: 0:12:55 lr: 0.000908 loss: 3.5412 (3.6033) grad_norm: 1.0393 (1.0825) time: 0.6226 [2021-03-26 11:37:53 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 100/1251] eta: 0:12:42 lr: 0.000908 loss: 3.7508 (3.6239) grad_norm: 1.0393 (1.0847) time: 0.6219 [2021-03-26 11:37:59 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 110/1251] eta: 0:12:34 lr: 0.000908 loss: 3.9072 (3.6542) grad_norm: 1.0512 (1.0835) time: 0.6296 [2021-03-26 11:38:05 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 120/1251] eta: 0:12:24 lr: 0.000908 loss: 3.8587 (3.6582) grad_norm: 1.0512 (1.0815) time: 0.6328 [2021-03-26 11:38:12 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 130/1251] eta: 0:12:14 lr: 0.000908 loss: 3.7453 (3.6404) grad_norm: 1.0221 (1.0793) time: 0.6212 [2021-03-26 11:38:18 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 140/1251] eta: 0:12:06 lr: 0.000908 loss: 3.6210 (3.6308) grad_norm: 1.0740 (1.0809) time: 0.6290 [2021-03-26 11:38:24 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 150/1251] eta: 0:11:57 lr: 0.000908 loss: 3.5896 (3.6207) grad_norm: 1.1206 (1.0839) time: 0.6313 [2021-03-26 11:38:30 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 160/1251] eta: 0:11:49 lr: 0.000908 loss: 3.7417 (3.6384) grad_norm: 1.0681 (1.0867) time: 0.6224 [2021-03-26 11:38:37 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 170/1251] eta: 0:11:41 lr: 0.000908 loss: 3.7417 (3.6396) grad_norm: 1.0911 (1.0918) time: 0.6311 [2021-03-26 11:38:43 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 180/1251] eta: 0:11:33 lr: 0.000908 loss: 3.7294 (3.6386) grad_norm: 1.0679 (1.0928) time: 0.6327 [2021-03-26 11:38:49 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 190/1251] eta: 0:11:26 lr: 0.000908 loss: 3.8780 (3.6570) grad_norm: 1.0436 (1.0951) time: 0.6275 [2021-03-26 11:38:56 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 200/1251] eta: 0:11:19 lr: 0.000908 loss: 3.9641 (3.6654) grad_norm: 1.0473 (1.0950) time: 0.6297 [2021-03-26 11:39:02 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 210/1251] eta: 0:11:11 lr: 0.000908 loss: 3.7366 (3.6697) grad_norm: 1.0553 (1.0930) time: 0.6236 [2021-03-26 11:39:08 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 220/1251] eta: 0:11:03 lr: 0.000908 loss: 3.7899 (3.6834) grad_norm: 1.0827 (1.0938) time: 0.6172 [2021-03-26 11:39:14 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 230/1251] eta: 0:10:56 lr: 0.000908 loss: 3.9980 (3.6793) grad_norm: 1.0812 (1.0931) time: 0.6257 [2021-03-26 11:39:21 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 240/1251] eta: 0:10:49 lr: 0.000908 loss: 3.5624 (3.6839) grad_norm: 0.9927 (1.0893) time: 0.6257 [2021-03-26 11:39:27 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 250/1251] eta: 0:10:42 lr: 0.000908 loss: 3.5624 (3.6789) grad_norm: 1.0056 (1.0893) time: 0.6218 [2021-03-26 11:39:33 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 260/1251] eta: 0:10:35 lr: 0.000908 loss: 3.5164 (3.6773) grad_norm: 1.0567 (1.0910) time: 0.6316 [2021-03-26 11:39:39 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 270/1251] eta: 0:10:28 lr: 0.000908 loss: 3.8137 (3.6878) grad_norm: 1.0567 (1.0897) time: 0.6303 [2021-03-26 11:39:46 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 280/1251] eta: 0:10:21 lr: 0.000908 loss: 3.7591 (3.6814) grad_norm: 1.0228 (1.0893) time: 0.6198 [2021-03-26 11:39:52 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 290/1251] eta: 0:10:14 lr: 0.000908 loss: 3.5502 (3.6805) grad_norm: 1.0372 (1.0894) time: 0.6181 [2021-03-26 11:39:58 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 300/1251] eta: 0:10:06 lr: 0.000908 loss: 3.8026 (3.6850) grad_norm: 1.0231 (1.0861) time: 0.6169 [2021-03-26 11:40:04 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 310/1251] eta: 0:10:00 lr: 0.000908 loss: 4.0384 (3.6989) grad_norm: 0.9589 (1.0834) time: 0.6185 [2021-03-26 11:40:10 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 320/1251] eta: 0:09:53 lr: 0.000908 loss: 3.9895 (3.7026) grad_norm: 0.9668 (1.0815) time: 0.6246 [2021-03-26 11:40:17 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 330/1251] eta: 0:09:46 lr: 0.000908 loss: 3.6862 (3.6985) grad_norm: 1.0080 (1.0841) time: 0.6233 [2021-03-26 11:40:23 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 340/1251] eta: 0:09:40 lr: 0.000908 loss: 3.6908 (3.6970) grad_norm: 1.1279 (1.0857) time: 0.6279 [2021-03-26 11:40:29 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 350/1251] eta: 0:09:33 lr: 0.000908 loss: 3.7863 (3.6993) grad_norm: 0.9747 (1.0828) time: 0.6279 [2021-03-26 11:40:35 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 360/1251] eta: 0:09:26 lr: 0.000908 loss: 3.7863 (3.7010) grad_norm: 0.9595 (1.0813) time: 0.6192 [2021-03-26 11:40:42 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 370/1251] eta: 0:09:20 lr: 0.000908 loss: 3.6399 (3.6929) grad_norm: 1.0086 (1.0818) time: 0.6228 [2021-03-26 11:40:48 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 380/1251] eta: 0:09:13 lr: 0.000908 loss: 3.6383 (3.6918) grad_norm: 1.0733 (1.0829) time: 0.6276 [2021-03-26 11:40:54 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 390/1251] eta: 0:09:06 lr: 0.000908 loss: 3.7271 (3.6953) grad_norm: 1.0851 (1.0843) time: 0.6202 [2021-03-26 11:41:00 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 400/1251] eta: 0:08:59 lr: 0.000908 loss: 3.6884 (3.6856) grad_norm: 1.1395 (1.0858) time: 0.6179 [2021-03-26 11:41:06 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 410/1251] eta: 0:08:53 lr: 0.000908 loss: 3.3428 (3.6782) grad_norm: 1.0481 (1.0843) time: 0.6178 [2021-03-26 11:41:13 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 420/1251] eta: 0:08:46 lr: 0.000907 loss: 3.5466 (3.6791) grad_norm: 1.0209 (1.0834) time: 0.6195 [2021-03-26 11:41:19 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 430/1251] eta: 0:08:40 lr: 0.000907 loss: 3.7121 (3.6756) grad_norm: 1.0280 (1.0836) time: 0.6257 [2021-03-26 11:41:25 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 440/1251] eta: 0:08:33 lr: 0.000907 loss: 3.7541 (3.6787) grad_norm: 1.0683 (1.0833) time: 0.6289 [2021-03-26 11:41:32 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 450/1251] eta: 0:08:27 lr: 0.000907 loss: 3.4060 (3.6706) grad_norm: 1.0683 (1.0839) time: 0.6351 [2021-03-26 11:41:38 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 460/1251] eta: 0:08:21 lr: 0.000907 loss: 3.5057 (3.6780) grad_norm: 1.0549 (1.0845) time: 0.6309 [2021-03-26 11:41:44 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 470/1251] eta: 0:08:14 lr: 0.000907 loss: 4.0996 (3.6811) grad_norm: 1.0760 (1.0851) time: 0.6227 [2021-03-26 11:41:50 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 480/1251] eta: 0:08:08 lr: 0.000907 loss: 3.9372 (3.6787) grad_norm: 1.0706 (1.0848) time: 0.6241 [2021-03-26 11:41:57 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 490/1251] eta: 0:08:01 lr: 0.000907 loss: 3.8001 (3.6809) grad_norm: 1.0532 (1.0844) time: 0.6327 [2021-03-26 11:42:03 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 500/1251] eta: 0:07:55 lr: 0.000907 loss: 3.7651 (3.6790) grad_norm: 1.0317 (1.0832) time: 0.6333 [2021-03-26 11:42:09 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 510/1251] eta: 0:07:48 lr: 0.000907 loss: 3.7651 (3.6804) grad_norm: 1.0940 (1.0845) time: 0.6259 [2021-03-26 11:42:15 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 520/1251] eta: 0:07:42 lr: 0.000907 loss: 3.8754 (3.6832) grad_norm: 1.0495 (1.0832) time: 0.6235 [2021-03-26 11:42:22 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 530/1251] eta: 0:07:36 lr: 0.000907 loss: 3.9155 (3.6867) grad_norm: 1.0233 (1.0831) time: 0.6223 [2021-03-26 11:42:28 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 540/1251] eta: 0:07:29 lr: 0.000907 loss: 3.8476 (3.6890) grad_norm: 1.0304 (1.0831) time: 0.6301 [2021-03-26 11:42:35 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 550/1251] eta: 0:07:23 lr: 0.000907 loss: 4.0492 (3.6951) grad_norm: 1.0515 (1.0834) time: 0.6468 [2021-03-26 11:42:41 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 560/1251] eta: 0:07:17 lr: 0.000907 loss: 3.9077 (3.6949) grad_norm: 1.0515 (1.0835) time: 0.6383 [2021-03-26 11:42:47 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 570/1251] eta: 0:07:10 lr: 0.000907 loss: 3.7844 (3.6943) grad_norm: 1.0606 (1.0841) time: 0.6219 [2021-03-26 11:42:53 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 580/1251] eta: 0:07:04 lr: 0.000907 loss: 3.6694 (3.6954) grad_norm: 1.0606 (1.0844) time: 0.6287 [2021-03-26 11:43:00 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 590/1251] eta: 0:06:58 lr: 0.000907 loss: 3.6937 (3.6981) grad_norm: 1.0625 (1.0842) time: 0.6253 [2021-03-26 11:43:06 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 600/1251] eta: 0:06:51 lr: 0.000907 loss: 3.6636 (3.6956) grad_norm: 1.0420 (1.0837) time: 0.6226 [2021-03-26 11:43:12 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 610/1251] eta: 0:06:45 lr: 0.000907 loss: 3.6595 (3.6930) grad_norm: 1.0695 (1.0858) time: 0.6301 [2021-03-26 11:43:19 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 620/1251] eta: 0:06:39 lr: 0.000907 loss: 3.6891 (3.6949) grad_norm: 1.0785 (1.0856) time: 0.6319 [2021-03-26 11:43:25 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 630/1251] eta: 0:06:32 lr: 0.000907 loss: 3.8056 (3.6949) grad_norm: 1.0460 (1.0848) time: 0.6342 [2021-03-26 11:43:31 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 640/1251] eta: 0:06:26 lr: 0.000907 loss: 3.8056 (3.6918) grad_norm: 1.0955 (1.0856) time: 0.6275 [2021-03-26 11:43:37 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 650/1251] eta: 0:06:19 lr: 0.000907 loss: 3.6476 (3.6910) grad_norm: 1.0646 (1.0844) time: 0.6268 [2021-03-26 11:43:44 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 660/1251] eta: 0:06:13 lr: 0.000907 loss: 3.9105 (3.6972) grad_norm: 1.0368 (inf) time: 0.6280 [2021-03-26 11:43:50 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 670/1251] eta: 0:06:07 lr: 0.000907 loss: 3.9597 (3.6987) grad_norm: 1.0643 (inf) time: 0.6240 [2021-03-26 11:43:56 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 680/1251] eta: 0:06:00 lr: 0.000907 loss: 3.5829 (3.6962) grad_norm: 1.0643 (inf) time: 0.6253 [2021-03-26 11:44:02 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 690/1251] eta: 0:05:54 lr: 0.000907 loss: 3.5829 (3.6972) grad_norm: 1.1477 (inf) time: 0.6217 [2021-03-26 11:44:09 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 700/1251] eta: 0:05:47 lr: 0.000907 loss: 3.7938 (3.6981) grad_norm: 1.1439 (inf) time: 0.6216 [2021-03-26 11:44:15 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 710/1251] eta: 0:05:41 lr: 0.000907 loss: 3.7207 (3.6956) grad_norm: 1.0885 (inf) time: 0.6215 [2021-03-26 11:44:21 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 720/1251] eta: 0:05:35 lr: 0.000907 loss: 3.4142 (3.6915) grad_norm: 1.0202 (inf) time: 0.6186 [2021-03-26 11:44:27 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 730/1251] eta: 0:05:28 lr: 0.000907 loss: 3.7405 (3.6932) grad_norm: 1.0417 (inf) time: 0.6267 [2021-03-26 11:44:34 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 740/1251] eta: 0:05:22 lr: 0.000907 loss: 3.6784 (3.6916) grad_norm: 1.0753 (inf) time: 0.6388 [2021-03-26 11:44:40 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 750/1251] eta: 0:05:16 lr: 0.000907 loss: 3.6005 (3.6922) grad_norm: 1.0473 (inf) time: 0.6401 [2021-03-26 11:44:46 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 760/1251] eta: 0:05:10 lr: 0.000907 loss: 3.7828 (3.6936) grad_norm: 1.0104 (inf) time: 0.6301 [2021-03-26 11:44:53 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 770/1251] eta: 0:05:03 lr: 0.000907 loss: 3.8284 (3.6936) grad_norm: 1.0957 (inf) time: 0.6237 [2021-03-26 11:44:59 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 780/1251] eta: 0:04:57 lr: 0.000907 loss: 3.8526 (3.6932) grad_norm: 1.0850 (inf) time: 0.6250 [2021-03-26 11:45:05 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 790/1251] eta: 0:04:51 lr: 0.000907 loss: 3.8356 (3.6948) grad_norm: 1.0812 (inf) time: 0.6316 [2021-03-26 11:45:12 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 800/1251] eta: 0:04:44 lr: 0.000907 loss: 3.8356 (3.6967) grad_norm: 1.0137 (inf) time: 0.6338 [2021-03-26 11:45:18 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 810/1251] eta: 0:04:38 lr: 0.000907 loss: 3.8726 (3.6961) grad_norm: 1.0615 (inf) time: 0.6286 [2021-03-26 11:45:24 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 820/1251] eta: 0:04:32 lr: 0.000907 loss: 3.6180 (3.6932) grad_norm: 1.1501 (inf) time: 0.6270 [2021-03-26 11:45:30 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 830/1251] eta: 0:04:25 lr: 0.000906 loss: 3.7277 (3.6989) grad_norm: 1.1435 (inf) time: 0.6297 [2021-03-26 11:45:37 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 840/1251] eta: 0:04:19 lr: 0.000906 loss: 4.0193 (3.7003) grad_norm: 1.1266 (inf) time: 0.6328 [2021-03-26 11:45:43 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 850/1251] eta: 0:04:13 lr: 0.000906 loss: 3.9319 (3.7024) grad_norm: 1.0676 (inf) time: 0.6281 [2021-03-26 11:45:49 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 860/1251] eta: 0:04:06 lr: 0.000906 loss: 3.8844 (3.7038) grad_norm: 1.0698 (inf) time: 0.6292 [2021-03-26 11:45:56 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 870/1251] eta: 0:04:00 lr: 0.000906 loss: 3.8837 (3.7043) grad_norm: 1.0659 (inf) time: 0.6288 [2021-03-26 11:46:02 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 880/1251] eta: 0:03:54 lr: 0.000906 loss: 3.8481 (3.7058) grad_norm: 0.9911 (inf) time: 0.6164 [2021-03-26 11:46:08 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 890/1251] eta: 0:03:47 lr: 0.000906 loss: 3.7478 (3.7062) grad_norm: 1.0630 (inf) time: 0.6162 [2021-03-26 11:46:14 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 900/1251] eta: 0:03:41 lr: 0.000906 loss: 3.7366 (3.7070) grad_norm: 1.0458 (inf) time: 0.6216 [2021-03-26 11:46:20 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 910/1251] eta: 0:03:34 lr: 0.000906 loss: 3.7951 (3.7079) grad_norm: 0.9888 (inf) time: 0.6166 [2021-03-26 11:46:26 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 920/1251] eta: 0:03:28 lr: 0.000906 loss: 3.8453 (3.7096) grad_norm: 1.0371 (inf) time: 0.6121 [2021-03-26 11:46:33 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 930/1251] eta: 0:03:22 lr: 0.000906 loss: 3.8849 (3.7121) grad_norm: 1.0573 (inf) time: 0.6255 [2021-03-26 11:46:39 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 940/1251] eta: 0:03:16 lr: 0.000906 loss: 3.8974 (3.7135) grad_norm: 1.0609 (inf) time: 0.6350 [2021-03-26 11:46:45 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 950/1251] eta: 0:03:09 lr: 0.000906 loss: 3.7796 (3.7133) grad_norm: 1.0864 (inf) time: 0.6363 [2021-03-26 11:46:52 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 960/1251] eta: 0:03:03 lr: 0.000906 loss: 3.6970 (3.7142) grad_norm: 1.0864 (inf) time: 0.6337 [2021-03-26 11:46:58 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 970/1251] eta: 0:02:57 lr: 0.000906 loss: 3.6970 (3.7114) grad_norm: 1.0764 (inf) time: 0.6242 [2021-03-26 11:47:04 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 980/1251] eta: 0:02:50 lr: 0.000906 loss: 3.6544 (3.7127) grad_norm: 1.0710 (inf) time: 0.6290 [2021-03-26 11:47:11 swin_base_patch4_window7_224] INFO: Epoch: [59] [ 990/1251] eta: 0:02:44 lr: 0.000906 loss: 3.8375 (3.7148) grad_norm: 1.0848 (inf) time: 0.6319 [2021-03-26 11:47:17 swin_base_patch4_window7_224] INFO: Epoch: [59] [1000/1251] eta: 0:02:38 lr: 0.000906 loss: 4.0218 (3.7163) grad_norm: 1.0562 (inf) time: 0.6320 [2021-03-26 11:47:23 swin_base_patch4_window7_224] INFO: Epoch: [59] [1010/1251] eta: 0:02:31 lr: 0.000906 loss: 3.9819 (3.7169) grad_norm: 1.0250 (inf) time: 0.6311 [2021-03-26 11:47:30 swin_base_patch4_window7_224] INFO: Epoch: [59] [1020/1251] eta: 0:02:25 lr: 0.000906 loss: 3.6682 (3.7161) grad_norm: 1.0526 (inf) time: 0.6300 [2021-03-26 11:47:36 swin_base_patch4_window7_224] INFO: Epoch: [59] [1030/1251] eta: 0:02:19 lr: 0.000906 loss: 3.5778 (3.7164) grad_norm: 1.0367 (inf) time: 0.6283 [2021-03-26 11:47:42 swin_base_patch4_window7_224] INFO: Epoch: [59] [1040/1251] eta: 0:02:12 lr: 0.000906 loss: 3.8832 (3.7180) grad_norm: 1.0528 (inf) time: 0.6247 [2021-03-26 11:47:48 swin_base_patch4_window7_224] INFO: Epoch: [59] [1050/1251] eta: 0:02:06 lr: 0.000906 loss: 3.8832 (3.7191) grad_norm: 1.0350 (inf) time: 0.6261 [2021-03-26 11:47:55 swin_base_patch4_window7_224] INFO: Epoch: [59] [1060/1251] eta: 0:02:00 lr: 0.000906 loss: 3.8482 (3.7194) grad_norm: 0.9856 (inf) time: 0.6236 [2021-03-26 11:48:01 swin_base_patch4_window7_224] INFO: Epoch: [59] [1070/1251] eta: 0:01:54 lr: 0.000906 loss: 3.6590 (3.7171) grad_norm: 1.0492 (inf) time: 0.6252 [2021-03-26 11:48:07 swin_base_patch4_window7_224] INFO: Epoch: [59] [1080/1251] eta: 0:01:47 lr: 0.000906 loss: 3.6862 (3.7176) grad_norm: 0.9756 (inf) time: 0.6309 [2021-03-26 11:48:13 swin_base_patch4_window7_224] INFO: Epoch: [59] [1090/1251] eta: 0:01:41 lr: 0.000906 loss: 3.6862 (3.7175) grad_norm: 1.0202 (inf) time: 0.6330 [2021-03-26 11:48:20 swin_base_patch4_window7_224] INFO: Epoch: [59] [1100/1251] eta: 0:01:35 lr: 0.000906 loss: 3.8890 (3.7208) grad_norm: 1.0356 (inf) time: 0.6289 [2021-03-26 11:48:26 swin_base_patch4_window7_224] INFO: Epoch: [59] [1110/1251] eta: 0:01:28 lr: 0.000906 loss: 3.7959 (3.7191) grad_norm: 1.0693 (inf) time: 0.6246 [2021-03-26 11:48:32 swin_base_patch4_window7_224] INFO: Epoch: [59] [1120/1251] eta: 0:01:22 lr: 0.000906 loss: 3.7359 (3.7204) grad_norm: 1.1024 (inf) time: 0.6306 [2021-03-26 11:48:39 swin_base_patch4_window7_224] INFO: Epoch: [59] [1130/1251] eta: 0:01:16 lr: 0.000906 loss: 3.9093 (3.7210) grad_norm: 1.0897 (inf) time: 0.6314 [2021-03-26 11:48:45 swin_base_patch4_window7_224] INFO: Epoch: [59] [1140/1251] eta: 0:01:09 lr: 0.000906 loss: 3.8110 (3.7210) grad_norm: 1.1455 (inf) time: 0.6259 [2021-03-26 11:48:51 swin_base_patch4_window7_224] INFO: Epoch: [59] [1150/1251] eta: 0:01:03 lr: 0.000906 loss: 3.7305 (3.7215) grad_norm: 1.0778 (inf) time: 0.6261 [2021-03-26 11:48:57 swin_base_patch4_window7_224] INFO: Epoch: [59] [1160/1251] eta: 0:00:57 lr: 0.000906 loss: 3.6278 (3.7195) grad_norm: 1.0778 (inf) time: 0.6307 [2021-03-26 11:49:04 swin_base_patch4_window7_224] INFO: Epoch: [59] [1170/1251] eta: 0:00:51 lr: 0.000906 loss: 3.5940 (3.7189) grad_norm: 1.1056 (inf) time: 0.6306 [2021-03-26 11:49:10 swin_base_patch4_window7_224] INFO: Epoch: [59] [1180/1251] eta: 0:00:44 lr: 0.000906 loss: 3.8497 (3.7195) grad_norm: 1.0166 (inf) time: 0.6292 [2021-03-26 11:49:16 swin_base_patch4_window7_224] INFO: Epoch: [59] [1190/1251] eta: 0:00:38 lr: 0.000906 loss: 3.7854 (3.7181) grad_norm: 1.0318 (inf) time: 0.6270 [2021-03-26 11:49:22 swin_base_patch4_window7_224] INFO: Epoch: [59] [1200/1251] eta: 0:00:32 lr: 0.000906 loss: 3.4822 (3.7166) grad_norm: 1.0318 (inf) time: 0.6213 [2021-03-26 11:49:29 swin_base_patch4_window7_224] INFO: Epoch: [59] [1210/1251] eta: 0:00:25 lr: 0.000906 loss: 3.5739 (3.7162) grad_norm: 0.9783 (inf) time: 0.6172 [2021-03-26 11:49:35 swin_base_patch4_window7_224] INFO: Epoch: [59] [1220/1251] eta: 0:00:19 lr: 0.000906 loss: 3.7743 (3.7182) grad_norm: 0.9822 (inf) time: 0.6251 [2021-03-26 11:49:41 swin_base_patch4_window7_224] INFO: Epoch: [59] [1230/1251] eta: 0:00:13 lr: 0.000906 loss: 3.8256 (3.7168) grad_norm: 1.0235 (inf) time: 0.6301 [2021-03-26 11:49:47 swin_base_patch4_window7_224] INFO: Epoch: [59] [1240/1251] eta: 0:00:06 lr: 0.000905 loss: 3.9015 (3.7182) grad_norm: 1.0644 (inf) time: 0.6201 [2021-03-26 11:49:54 swin_base_patch4_window7_224] INFO: Epoch: [59] [1250/1251] eta: 0:00:00 lr: 0.000905 loss: 3.9422 (3.7182) grad_norm: 1.0644 (inf) time: 0.6199 [2021-03-26 11:49:59 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:26 loss: 1.4418 (1.4418) acc1: 65.6250 (65.6250) acc5: 90.6250 (90.6250) [2021-03-26 11:50:01 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.1344 (1.1653) acc1: 71.8750 (72.1591) acc5: 92.1875 (92.4716) [2021-03-26 11:50:03 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0996 (1.1306) acc1: 73.4375 (73.3631) acc5: 92.1875 (92.4107) [2021-03-26 11:50:07 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.1056 (1.1608) acc1: 73.4375 (72.8327) acc5: 90.6250 (91.5827) [2021-03-26 11:50:08 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1528 (1.1437) acc1: 73.4375 (73.2088) acc5: 90.6250 (91.8445) [2021-03-26 11:50:09 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1528 (1.1288) acc1: 71.8750 (73.2160) acc5: 92.1875 (91.8720) [2021-03-26 11:50:13 swin_base_patch4_window7_224] INFO: * Acc@1 74.192 Acc@5 92.474 loss 1.097 [2021-03-26 11:50:13 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.2% [2021-03-26 11:50:13 swin_base_patch4_window7_224] INFO: Max accuracy: 74.19% [2021-03-26 11:50:17 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 0/1251] eta: 1:30:58 lr: 0.000905 loss: 3.7247 (3.7247) grad_norm: 1.0652 (1.0652) time: 4.3632 [2021-03-26 11:50:23 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 10/1251] eta: 0:20:02 lr: 0.000905 loss: 3.5422 (3.5066) grad_norm: 1.1005 (1.1107) time: 0.9687 [2021-03-26 11:50:30 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 20/1251] eta: 0:16:30 lr: 0.000905 loss: 3.2846 (3.4018) grad_norm: 1.0628 (1.0593) time: 0.6264 [2021-03-26 11:50:36 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 30/1251] eta: 0:15:09 lr: 0.000905 loss: 3.4730 (3.5496) grad_norm: 1.0628 (1.0903) time: 0.6219 [2021-03-26 11:50:42 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 40/1251] eta: 0:14:27 lr: 0.000905 loss: 3.7231 (3.5455) grad_norm: 1.0743 (1.0983) time: 0.6237 [2021-03-26 11:50:48 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 50/1251] eta: 0:13:59 lr: 0.000905 loss: 3.6856 (3.6231) grad_norm: 1.0895 (1.0991) time: 0.6286 [2021-03-26 11:50:55 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 60/1251] eta: 0:13:38 lr: 0.000905 loss: 3.9361 (3.6407) grad_norm: 1.0624 (1.1016) time: 0.6269 [2021-03-26 11:51:01 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 70/1251] eta: 0:13:20 lr: 0.000905 loss: 3.7651 (3.6352) grad_norm: 1.0557 (1.1122) time: 0.6229 [2021-03-26 11:51:07 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 80/1251] eta: 0:13:06 lr: 0.000905 loss: 3.6667 (3.6389) grad_norm: 1.1454 (1.1115) time: 0.6262 [2021-03-26 11:51:13 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 90/1251] eta: 0:12:54 lr: 0.000905 loss: 3.6914 (3.6420) grad_norm: 1.0993 (1.1137) time: 0.6276 [2021-03-26 11:51:20 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 100/1251] eta: 0:12:42 lr: 0.000905 loss: 3.6678 (3.6295) grad_norm: 1.0562 (1.1113) time: 0.6253 [2021-03-26 11:51:26 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 110/1251] eta: 0:12:32 lr: 0.000905 loss: 3.6678 (3.6357) grad_norm: 1.1110 (1.1202) time: 0.6265 [2021-03-26 11:51:32 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 120/1251] eta: 0:12:23 lr: 0.000905 loss: 3.7866 (3.6417) grad_norm: 1.1690 (1.1208) time: 0.6317 [2021-03-26 11:51:39 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 130/1251] eta: 0:12:15 lr: 0.000905 loss: 3.6908 (3.6330) grad_norm: 1.1477 (1.1194) time: 0.6380 [2021-03-26 11:51:45 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 140/1251] eta: 0:12:07 lr: 0.000905 loss: 3.7953 (3.6529) grad_norm: 1.0586 (1.1136) time: 0.6398 [2021-03-26 11:51:51 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 150/1251] eta: 0:11:58 lr: 0.000905 loss: 3.7953 (3.6440) grad_norm: 1.0112 (1.1065) time: 0.6291 [2021-03-26 11:51:58 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 160/1251] eta: 0:11:50 lr: 0.000905 loss: 3.6880 (3.6433) grad_norm: 1.0325 (1.1067) time: 0.6271 [2021-03-26 11:52:04 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 170/1251] eta: 0:11:42 lr: 0.000905 loss: 4.0217 (3.6690) grad_norm: 1.0287 (1.0993) time: 0.6251 [2021-03-26 11:52:10 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 180/1251] eta: 0:11:34 lr: 0.000905 loss: 3.9346 (3.6646) grad_norm: 1.0266 (1.0988) time: 0.6242 [2021-03-26 11:52:17 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 190/1251] eta: 0:11:27 lr: 0.000905 loss: 3.7881 (3.6726) grad_norm: 1.0969 (1.1027) time: 0.6356 [2021-03-26 11:52:23 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 200/1251] eta: 0:11:20 lr: 0.000905 loss: 3.7227 (3.6755) grad_norm: 1.1712 (1.1060) time: 0.6334 [2021-03-26 11:52:29 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 210/1251] eta: 0:11:12 lr: 0.000905 loss: 3.7227 (3.6730) grad_norm: 1.1167 (1.1028) time: 0.6277 [2021-03-26 11:52:35 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 220/1251] eta: 0:11:05 lr: 0.000905 loss: 3.8206 (3.6794) grad_norm: 0.9989 (1.0983) time: 0.6246 [2021-03-26 11:52:42 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 230/1251] eta: 0:10:57 lr: 0.000905 loss: 3.8823 (3.6830) grad_norm: 1.0426 (1.1031) time: 0.6234 [2021-03-26 11:52:48 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 240/1251] eta: 0:10:50 lr: 0.000905 loss: 3.7494 (3.6785) grad_norm: 1.0639 (1.1006) time: 0.6237 [2021-03-26 11:52:54 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 250/1251] eta: 0:10:43 lr: 0.000905 loss: 3.6724 (3.6822) grad_norm: 1.0299 (1.1028) time: 0.6281 [2021-03-26 11:53:00 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 260/1251] eta: 0:10:36 lr: 0.000905 loss: 3.6724 (3.6811) grad_norm: 1.0352 (1.1020) time: 0.6280 [2021-03-26 11:53:07 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 270/1251] eta: 0:10:28 lr: 0.000905 loss: 3.7766 (3.6858) grad_norm: 1.0554 (1.1056) time: 0.6203 [2021-03-26 11:53:13 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 280/1251] eta: 0:10:22 lr: 0.000905 loss: 3.7766 (3.6904) grad_norm: 1.0554 (1.1043) time: 0.6214 [2021-03-26 11:53:19 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 290/1251] eta: 0:10:15 lr: 0.000905 loss: 3.8534 (3.6855) grad_norm: 0.9902 (1.1016) time: 0.6305 [2021-03-26 11:53:26 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 300/1251] eta: 0:10:08 lr: 0.000905 loss: 3.5938 (3.6810) grad_norm: 1.0211 (1.1014) time: 0.6338 [2021-03-26 11:53:32 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 310/1251] eta: 0:10:01 lr: 0.000905 loss: 3.5938 (3.6786) grad_norm: 1.0145 (1.0985) time: 0.6259 [2021-03-26 11:53:38 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 320/1251] eta: 0:09:54 lr: 0.000905 loss: 3.8383 (3.6759) grad_norm: 1.0145 (1.0993) time: 0.6219 [2021-03-26 11:53:44 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 330/1251] eta: 0:09:48 lr: 0.000905 loss: 3.6335 (3.6667) grad_norm: 1.0689 (1.0980) time: 0.6245 [2021-03-26 11:53:50 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 340/1251] eta: 0:09:41 lr: 0.000905 loss: 3.5567 (3.6689) grad_norm: 0.9971 (1.0964) time: 0.6255 [2021-03-26 11:53:57 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 350/1251] eta: 0:09:34 lr: 0.000905 loss: 3.9736 (3.6756) grad_norm: 1.0060 (1.0939) time: 0.6240 [2021-03-26 11:54:03 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 360/1251] eta: 0:09:27 lr: 0.000905 loss: 4.0741 (3.6833) grad_norm: 1.0060 (1.0938) time: 0.6187 [2021-03-26 11:54:09 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 370/1251] eta: 0:09:20 lr: 0.000905 loss: 3.8025 (3.6846) grad_norm: 1.0918 (1.0942) time: 0.6194 [2021-03-26 11:54:15 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 380/1251] eta: 0:09:14 lr: 0.000905 loss: 3.8025 (3.6866) grad_norm: 1.0621 (1.0932) time: 0.6232 [2021-03-26 11:54:22 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 390/1251] eta: 0:09:07 lr: 0.000905 loss: 3.8782 (3.6860) grad_norm: 1.0357 (1.0949) time: 0.6237 [2021-03-26 11:54:28 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 400/1251] eta: 0:09:01 lr: 0.000904 loss: 3.9171 (3.6887) grad_norm: 1.1034 (1.0971) time: 0.6240 [2021-03-26 11:54:34 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 410/1251] eta: 0:08:54 lr: 0.000904 loss: 3.8954 (3.6904) grad_norm: 1.0759 (1.0960) time: 0.6227 [2021-03-26 11:54:40 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 420/1251] eta: 0:08:47 lr: 0.000904 loss: 3.7112 (3.6879) grad_norm: 1.0705 (1.0974) time: 0.6247 [2021-03-26 11:54:47 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 430/1251] eta: 0:08:41 lr: 0.000904 loss: 3.6570 (3.6869) grad_norm: 1.0747 (1.0966) time: 0.6285 [2021-03-26 11:54:53 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 440/1251] eta: 0:08:34 lr: 0.000904 loss: 3.6603 (3.6845) grad_norm: 1.0433 (1.0976) time: 0.6257 [2021-03-26 11:54:59 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 450/1251] eta: 0:08:28 lr: 0.000904 loss: 3.8178 (3.6861) grad_norm: 1.0144 (1.0980) time: 0.6221 [2021-03-26 11:55:05 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 460/1251] eta: 0:08:21 lr: 0.000904 loss: 3.8983 (3.6905) grad_norm: 1.0790 (1.0997) time: 0.6252 [2021-03-26 11:55:12 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 470/1251] eta: 0:08:15 lr: 0.000904 loss: 3.8870 (3.6898) grad_norm: 1.1012 (1.1002) time: 0.6293 [2021-03-26 11:55:18 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 480/1251] eta: 0:08:08 lr: 0.000904 loss: 3.7811 (3.6890) grad_norm: 1.0762 (1.0999) time: 0.6292 [2021-03-26 11:55:24 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 490/1251] eta: 0:08:02 lr: 0.000904 loss: 3.6141 (3.6850) grad_norm: 1.0674 (1.1005) time: 0.6277 [2021-03-26 11:55:30 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 500/1251] eta: 0:07:56 lr: 0.000904 loss: 3.5995 (3.6842) grad_norm: 1.1488 (1.1015) time: 0.6260 [2021-03-26 11:55:37 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 510/1251] eta: 0:07:49 lr: 0.000904 loss: 3.7760 (3.6866) grad_norm: 1.1077 (1.1008) time: 0.6214 [2021-03-26 11:55:43 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 520/1251] eta: 0:07:42 lr: 0.000904 loss: 3.7898 (3.6893) grad_norm: 1.1198 (1.1027) time: 0.6171 [2021-03-26 11:55:49 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 530/1251] eta: 0:07:36 lr: 0.000904 loss: 3.8628 (3.6932) grad_norm: 1.0802 (1.1006) time: 0.6221 [2021-03-26 11:55:55 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 540/1251] eta: 0:07:29 lr: 0.000904 loss: 3.9538 (3.6955) grad_norm: 0.9705 (1.1006) time: 0.6237 [2021-03-26 11:56:02 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 550/1251] eta: 0:07:23 lr: 0.000904 loss: 3.9274 (3.6978) grad_norm: 1.0735 (1.1006) time: 0.6321 [2021-03-26 11:56:08 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 560/1251] eta: 0:07:17 lr: 0.000904 loss: 3.8436 (3.7023) grad_norm: 1.1066 (1.1002) time: 0.6364 [2021-03-26 11:56:14 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 570/1251] eta: 0:07:11 lr: 0.000904 loss: 3.8072 (3.7033) grad_norm: 1.0484 (1.0992) time: 0.6314 [2021-03-26 11:56:21 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 580/1251] eta: 0:07:04 lr: 0.000904 loss: 3.6953 (3.7027) grad_norm: 1.0484 (1.0983) time: 0.6350 [2021-03-26 11:56:27 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 590/1251] eta: 0:06:58 lr: 0.000904 loss: 3.6953 (3.7060) grad_norm: 1.0234 (1.0969) time: 0.6309 [2021-03-26 11:56:33 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 600/1251] eta: 0:06:51 lr: 0.000904 loss: 3.8509 (3.7068) grad_norm: 1.0496 (1.0987) time: 0.6267 [2021-03-26 11:56:40 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 610/1251] eta: 0:06:45 lr: 0.000904 loss: 3.8509 (3.7089) grad_norm: 1.1755 (1.1009) time: 0.6302 [2021-03-26 11:56:46 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 620/1251] eta: 0:06:39 lr: 0.000904 loss: 3.8605 (3.7090) grad_norm: 1.1211 (1.1014) time: 0.6326 [2021-03-26 11:56:52 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 630/1251] eta: 0:06:32 lr: 0.000904 loss: 3.7981 (3.7076) grad_norm: 0.9802 (1.0989) time: 0.6216 [2021-03-26 11:56:58 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 640/1251] eta: 0:06:26 lr: 0.000904 loss: 3.8366 (3.7115) grad_norm: 0.9802 (1.0981) time: 0.6163 [2021-03-26 11:57:04 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 650/1251] eta: 0:06:19 lr: 0.000904 loss: 3.9119 (3.7113) grad_norm: 0.9968 (1.0968) time: 0.6193 [2021-03-26 11:57:11 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 660/1251] eta: 0:06:13 lr: 0.000904 loss: 3.8144 (3.7118) grad_norm: 0.9666 (1.0950) time: 0.6150 [2021-03-26 11:57:17 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 670/1251] eta: 0:06:06 lr: 0.000904 loss: 3.8144 (3.7116) grad_norm: 1.0204 (1.0944) time: 0.6157 [2021-03-26 11:57:23 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 680/1251] eta: 0:06:00 lr: 0.000904 loss: 3.8261 (3.7143) grad_norm: 1.0367 (1.0939) time: 0.6264 [2021-03-26 11:57:29 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 690/1251] eta: 0:05:54 lr: 0.000904 loss: 3.7828 (3.7122) grad_norm: 1.0426 (1.0941) time: 0.6345 [2021-03-26 11:57:36 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 700/1251] eta: 0:05:47 lr: 0.000904 loss: 3.6790 (3.7127) grad_norm: 1.0939 (1.0942) time: 0.6249 [2021-03-26 11:57:42 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 710/1251] eta: 0:05:41 lr: 0.000904 loss: 3.6951 (3.7133) grad_norm: 1.0645 (1.0949) time: 0.6175 [2021-03-26 11:57:48 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 720/1251] eta: 0:05:35 lr: 0.000904 loss: 3.7589 (3.7149) grad_norm: 1.0645 (1.0945) time: 0.6282 [2021-03-26 11:57:54 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 730/1251] eta: 0:05:28 lr: 0.000904 loss: 3.7986 (3.7143) grad_norm: 1.1019 (1.0962) time: 0.6332 [2021-03-26 11:58:01 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 740/1251] eta: 0:05:22 lr: 0.000904 loss: 3.8013 (3.7162) grad_norm: 1.1408 (1.0968) time: 0.6366 [2021-03-26 11:58:07 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 750/1251] eta: 0:05:16 lr: 0.000904 loss: 3.8013 (3.7130) grad_norm: 1.0679 (1.0958) time: 0.6376 [2021-03-26 11:58:13 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 760/1251] eta: 0:05:10 lr: 0.000904 loss: 3.2910 (3.7094) grad_norm: 1.0514 (1.0966) time: 0.6323 [2021-03-26 11:58:20 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 770/1251] eta: 0:05:03 lr: 0.000904 loss: 3.5812 (3.7107) grad_norm: 1.1295 (1.0972) time: 0.6268 [2021-03-26 11:58:26 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 780/1251] eta: 0:04:57 lr: 0.000904 loss: 3.7262 (3.7109) grad_norm: 1.0716 (1.0972) time: 0.6181 [2021-03-26 11:58:32 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 790/1251] eta: 0:04:51 lr: 0.000904 loss: 3.8537 (3.7129) grad_norm: 1.1064 (1.0979) time: 0.6256 [2021-03-26 11:58:39 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 800/1251] eta: 0:04:44 lr: 0.000904 loss: 3.8537 (3.7116) grad_norm: 1.1392 (1.0982) time: 0.6347 [2021-03-26 11:58:45 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 810/1251] eta: 0:04:38 lr: 0.000903 loss: 3.5712 (3.7100) grad_norm: 1.1392 (1.0991) time: 0.6275 [2021-03-26 11:58:51 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 820/1251] eta: 0:04:32 lr: 0.000903 loss: 3.8046 (3.7116) grad_norm: 1.0519 (1.0983) time: 0.6254 [2021-03-26 11:58:57 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 830/1251] eta: 0:04:25 lr: 0.000903 loss: 3.7843 (3.7085) grad_norm: 1.0576 (1.0985) time: 0.6288 [2021-03-26 11:59:04 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 840/1251] eta: 0:04:19 lr: 0.000903 loss: 3.6862 (3.7078) grad_norm: 1.0727 (1.0982) time: 0.6296 [2021-03-26 11:59:10 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 850/1251] eta: 0:04:13 lr: 0.000903 loss: 3.7338 (3.7072) grad_norm: 1.0947 (1.0982) time: 0.6304 [2021-03-26 11:59:16 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 860/1251] eta: 0:04:06 lr: 0.000903 loss: 3.7784 (3.7082) grad_norm: 1.1052 (1.0986) time: 0.6249 [2021-03-26 11:59:23 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 870/1251] eta: 0:04:00 lr: 0.000903 loss: 3.6543 (3.7044) grad_norm: 1.1079 (1.0988) time: 0.6289 [2021-03-26 11:59:29 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 880/1251] eta: 0:03:54 lr: 0.000903 loss: 3.5780 (3.7040) grad_norm: 1.1012 (1.0991) time: 0.6346 [2021-03-26 11:59:35 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 890/1251] eta: 0:03:47 lr: 0.000903 loss: 3.6872 (3.7042) grad_norm: 1.1001 (1.0985) time: 0.6300 [2021-03-26 11:59:41 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 900/1251] eta: 0:03:41 lr: 0.000903 loss: 3.6401 (3.7015) grad_norm: 1.0383 (1.0983) time: 0.6286 [2021-03-26 11:59:48 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 910/1251] eta: 0:03:35 lr: 0.000903 loss: 3.6401 (3.7019) grad_norm: 1.0549 (1.0982) time: 0.6251 [2021-03-26 11:59:54 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 920/1251] eta: 0:03:28 lr: 0.000903 loss: 3.9187 (3.7017) grad_norm: 1.0619 (1.0988) time: 0.6262 [2021-03-26 12:00:00 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 930/1251] eta: 0:03:22 lr: 0.000903 loss: 3.6601 (3.6995) grad_norm: 1.0829 (1.0989) time: 0.6309 [2021-03-26 12:00:07 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 940/1251] eta: 0:03:16 lr: 0.000903 loss: 3.4457 (3.6995) grad_norm: 1.1523 (1.1004) time: 0.6328 [2021-03-26 12:00:13 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 950/1251] eta: 0:03:09 lr: 0.000903 loss: 3.6463 (3.6977) grad_norm: 1.1440 (1.1006) time: 0.6309 [2021-03-26 12:00:19 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 960/1251] eta: 0:03:03 lr: 0.000903 loss: 3.6830 (3.6963) grad_norm: 1.1440 (1.1013) time: 0.6312 [2021-03-26 12:00:25 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 970/1251] eta: 0:02:57 lr: 0.000903 loss: 3.8027 (3.6994) grad_norm: 1.1641 (1.1019) time: 0.6284 [2021-03-26 12:00:32 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 980/1251] eta: 0:02:50 lr: 0.000903 loss: 3.6908 (3.6962) grad_norm: 1.0564 (1.1017) time: 0.6233 [2021-03-26 12:00:38 swin_base_patch4_window7_224] INFO: Epoch: [60] [ 990/1251] eta: 0:02:44 lr: 0.000903 loss: 3.6908 (3.6976) grad_norm: 1.0588 (1.1030) time: 0.6259 [2021-03-26 12:00:44 swin_base_patch4_window7_224] INFO: Epoch: [60] [1000/1251] eta: 0:02:38 lr: 0.000903 loss: 3.8770 (3.6977) grad_norm: 1.0420 (1.1025) time: 0.6212 [2021-03-26 12:00:50 swin_base_patch4_window7_224] INFO: Epoch: [60] [1010/1251] eta: 0:02:31 lr: 0.000903 loss: 3.9847 (3.6996) grad_norm: 1.0381 (1.1028) time: 0.6206 [2021-03-26 12:00:57 swin_base_patch4_window7_224] INFO: Epoch: [60] [1020/1251] eta: 0:02:25 lr: 0.000903 loss: 3.9280 (3.6998) grad_norm: 1.0613 (1.1030) time: 0.6232 [2021-03-26 12:01:03 swin_base_patch4_window7_224] INFO: Epoch: [60] [1030/1251] eta: 0:02:19 lr: 0.000903 loss: 3.9114 (3.7017) grad_norm: 1.0626 (1.1028) time: 0.6248 [2021-03-26 12:01:09 swin_base_patch4_window7_224] INFO: Epoch: [60] [1040/1251] eta: 0:02:13 lr: 0.000903 loss: 3.9099 (3.7009) grad_norm: 1.0414 (1.1027) time: 0.6266 [2021-03-26 12:01:15 swin_base_patch4_window7_224] INFO: Epoch: [60] [1050/1251] eta: 0:02:06 lr: 0.000903 loss: 3.7669 (3.7019) grad_norm: 1.0266 (1.1020) time: 0.6224 [2021-03-26 12:01:22 swin_base_patch4_window7_224] INFO: Epoch: [60] [1060/1251] eta: 0:02:00 lr: 0.000903 loss: 3.9664 (3.7042) grad_norm: 1.0146 (1.1019) time: 0.6262 [2021-03-26 12:01:28 swin_base_patch4_window7_224] INFO: Epoch: [60] [1070/1251] eta: 0:01:54 lr: 0.000903 loss: 3.8862 (3.7047) grad_norm: 1.1354 (1.1023) time: 0.6347 [2021-03-26 12:01:34 swin_base_patch4_window7_224] INFO: Epoch: [60] [1080/1251] eta: 0:01:47 lr: 0.000903 loss: 3.8828 (3.7069) grad_norm: 1.1090 (1.1019) time: 0.6286 [2021-03-26 12:01:40 swin_base_patch4_window7_224] INFO: Epoch: [60] [1090/1251] eta: 0:01:41 lr: 0.000903 loss: 3.8333 (3.7057) grad_norm: 1.1245 (1.1026) time: 0.6202 [2021-03-26 12:01:47 swin_base_patch4_window7_224] INFO: Epoch: [60] [1100/1251] eta: 0:01:35 lr: 0.000903 loss: 3.5870 (3.7036) grad_norm: 1.0740 (1.1022) time: 0.6220 [2021-03-26 12:01:53 swin_base_patch4_window7_224] INFO: Epoch: [60] [1110/1251] eta: 0:01:28 lr: 0.000903 loss: 3.8079 (3.7054) grad_norm: 1.0168 (1.1014) time: 0.6217 [2021-03-26 12:01:59 swin_base_patch4_window7_224] INFO: Epoch: [60] [1120/1251] eta: 0:01:22 lr: 0.000903 loss: 3.8983 (3.7048) grad_norm: 1.0305 (1.1025) time: 0.6221 [2021-03-26 12:02:05 swin_base_patch4_window7_224] INFO: Epoch: [60] [1130/1251] eta: 0:01:16 lr: 0.000903 loss: 3.5544 (3.7048) grad_norm: 1.1972 (1.1029) time: 0.6254 [2021-03-26 12:02:12 swin_base_patch4_window7_224] INFO: Epoch: [60] [1140/1251] eta: 0:01:09 lr: 0.000903 loss: 3.8146 (3.7051) grad_norm: 1.1181 (1.1028) time: 0.6231 [2021-03-26 12:02:18 swin_base_patch4_window7_224] INFO: Epoch: [60] [1150/1251] eta: 0:01:03 lr: 0.000903 loss: 3.4976 (3.7023) grad_norm: 1.0513 (1.1029) time: 0.6169 [2021-03-26 12:02:24 swin_base_patch4_window7_224] INFO: Epoch: [60] [1160/1251] eta: 0:00:57 lr: 0.000903 loss: 3.7703 (3.7048) grad_norm: 1.1068 (1.1039) time: 0.6204 [2021-03-26 12:02:30 swin_base_patch4_window7_224] INFO: Epoch: [60] [1170/1251] eta: 0:00:51 lr: 0.000903 loss: 3.7824 (3.7055) grad_norm: 1.1068 (1.1036) time: 0.6275 [2021-03-26 12:02:37 swin_base_patch4_window7_224] INFO: Epoch: [60] [1180/1251] eta: 0:00:44 lr: 0.000903 loss: 3.6900 (3.7060) grad_norm: 1.0431 (1.1031) time: 0.6256 [2021-03-26 12:02:43 swin_base_patch4_window7_224] INFO: Epoch: [60] [1190/1251] eta: 0:00:38 lr: 0.000903 loss: 3.6916 (3.7052) grad_norm: 1.0198 (1.1025) time: 0.6246 [2021-03-26 12:02:49 swin_base_patch4_window7_224] INFO: Epoch: [60] [1200/1251] eta: 0:00:32 lr: 0.000903 loss: 3.9199 (3.7049) grad_norm: 1.0198 (1.1020) time: 0.6215 [2021-03-26 12:02:55 swin_base_patch4_window7_224] INFO: Epoch: [60] [1210/1251] eta: 0:00:25 lr: 0.000902 loss: 3.6913 (3.7040) grad_norm: 1.0506 (1.1020) time: 0.6183 [2021-03-26 12:03:01 swin_base_patch4_window7_224] INFO: Epoch: [60] [1220/1251] eta: 0:00:19 lr: 0.000902 loss: 3.6913 (3.7051) grad_norm: 1.1196 (1.1025) time: 0.6225 [2021-03-26 12:03:08 swin_base_patch4_window7_224] INFO: Epoch: [60] [1230/1251] eta: 0:00:13 lr: 0.000902 loss: 3.5836 (3.7041) grad_norm: 1.1221 (1.1033) time: 0.6219 [2021-03-26 12:03:14 swin_base_patch4_window7_224] INFO: Epoch: [60] [1240/1251] eta: 0:00:06 lr: 0.000902 loss: 3.3944 (3.7025) grad_norm: 1.0661 (1.1031) time: 0.6220 [2021-03-26 12:03:20 swin_base_patch4_window7_224] INFO: Epoch: [60] [1250/1251] eta: 0:00:00 lr: 0.000902 loss: 3.7913 (3.7028) grad_norm: 1.0661 (1.1028) time: 0.6159 [2021-03-26 12:04:20 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:04 loss: 0.9308 (0.9308) acc1: 76.5625 (76.5625) acc5: 95.3125 (95.3125) [2021-03-26 12:04:21 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 1.2421 (1.1666) acc1: 70.3125 (72.1591) acc5: 90.6250 (91.0511) [2021-03-26 12:04:23 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.1032 (1.1436) acc1: 71.8750 (72.8423) acc5: 90.6250 (91.8155) [2021-03-26 12:04:24 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.1574 (1.1872) acc1: 71.8750 (71.5222) acc5: 92.1875 (91.4819) [2021-03-26 12:04:25 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.1574 (1.1474) acc1: 71.8750 (72.5991) acc5: 92.1875 (91.9970) [2021-03-26 12:04:26 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0369 (1.1468) acc1: 71.8750 (72.6400) acc5: 92.1875 (92.0000) [2021-03-26 12:04:30 swin_base_patch4_window7_224] INFO: * Acc@1 73.716 Acc@5 92.424 loss 1.120 [2021-03-26 12:04:30 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.7% [2021-03-26 12:04:30 swin_base_patch4_window7_224] INFO: Max accuracy: 74.19% [2021-03-26 12:04:35 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 0/1251] eta: 1:28:10 lr: 0.000902 loss: 4.4602 (4.4602) grad_norm: 1.1724 (1.1724) time: 4.2291 [2021-03-26 12:04:41 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 10/1251] eta: 0:20:03 lr: 0.000902 loss: 3.8361 (3.5478) grad_norm: 1.0950 (1.0925) time: 0.9697 [2021-03-26 12:04:47 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 20/1251] eta: 0:16:31 lr: 0.000902 loss: 3.5115 (3.5571) grad_norm: 1.0286 (1.0615) time: 0.6343 [2021-03-26 12:04:54 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 30/1251] eta: 0:15:18 lr: 0.000902 loss: 3.4600 (3.5549) grad_norm: 1.0190 (1.0611) time: 0.6330 [2021-03-26 12:05:00 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 40/1251] eta: 0:14:33 lr: 0.000902 loss: 3.4737 (3.5834) grad_norm: 1.0472 (1.0728) time: 0.6331 [2021-03-26 12:05:06 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 50/1251] eta: 0:14:05 lr: 0.000902 loss: 3.7224 (3.6049) grad_norm: 1.0887 (1.0770) time: 0.6285 [2021-03-26 12:05:13 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 60/1251] eta: 0:13:42 lr: 0.000902 loss: 3.7789 (3.6070) grad_norm: 1.0357 (1.0670) time: 0.6274 [2021-03-26 12:05:19 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 70/1251] eta: 0:13:26 lr: 0.000902 loss: 3.5844 (3.6023) grad_norm: 1.0262 (1.0730) time: 0.6286 [2021-03-26 12:05:25 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 80/1251] eta: 0:13:10 lr: 0.000902 loss: 3.5844 (3.5889) grad_norm: 1.0508 (1.0759) time: 0.6293 [2021-03-26 12:05:31 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 90/1251] eta: 0:12:56 lr: 0.000902 loss: 3.7804 (3.6375) grad_norm: 1.0450 (1.0735) time: 0.6211 [2021-03-26 12:05:38 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 100/1251] eta: 0:12:45 lr: 0.000902 loss: 4.0266 (3.6661) grad_norm: 1.0327 (1.0749) time: 0.6235 [2021-03-26 12:05:44 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 110/1251] eta: 0:12:35 lr: 0.000902 loss: 3.8052 (3.6505) grad_norm: 1.0327 (1.0714) time: 0.6283 [2021-03-26 12:05:50 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 120/1251] eta: 0:12:24 lr: 0.000902 loss: 3.7528 (3.6639) grad_norm: 0.9838 (1.0711) time: 0.6260 [2021-03-26 12:05:56 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 130/1251] eta: 0:12:16 lr: 0.000902 loss: 3.7941 (3.6695) grad_norm: 0.9838 (1.0678) time: 0.6288 [2021-03-26 12:06:03 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 140/1251] eta: 0:12:07 lr: 0.000902 loss: 3.7936 (3.6769) grad_norm: 1.0313 (1.0705) time: 0.6301 [2021-03-26 12:06:09 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 150/1251] eta: 0:11:58 lr: 0.000902 loss: 3.5965 (3.6617) grad_norm: 1.0599 (1.0724) time: 0.6240 [2021-03-26 12:06:15 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 160/1251] eta: 0:11:49 lr: 0.000902 loss: 3.3335 (3.6468) grad_norm: 1.0479 (1.0752) time: 0.6227 [2021-03-26 12:06:21 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 170/1251] eta: 0:11:41 lr: 0.000902 loss: 3.5350 (3.6505) grad_norm: 1.0738 (1.0755) time: 0.6237 [2021-03-26 12:06:28 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 180/1251] eta: 0:11:33 lr: 0.000902 loss: 3.8853 (3.6491) grad_norm: 1.1035 (1.0812) time: 0.6256 [2021-03-26 12:06:34 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 190/1251] eta: 0:11:26 lr: 0.000902 loss: 3.7759 (3.6517) grad_norm: 1.0845 (1.0812) time: 0.6288 [2021-03-26 12:06:40 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 200/1251] eta: 0:11:18 lr: 0.000902 loss: 3.7753 (3.6594) grad_norm: 1.0171 (1.0794) time: 0.6252 [2021-03-26 12:06:47 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 210/1251] eta: 0:11:11 lr: 0.000902 loss: 3.7753 (3.6642) grad_norm: 1.0701 (1.0819) time: 0.6291 [2021-03-26 12:06:53 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 220/1251] eta: 0:11:04 lr: 0.000902 loss: 3.4866 (3.6605) grad_norm: 1.0446 (1.0826) time: 0.6360 [2021-03-26 12:06:59 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 230/1251] eta: 0:10:57 lr: 0.000902 loss: 3.9165 (3.6780) grad_norm: 1.0448 (1.0822) time: 0.6306 [2021-03-26 12:07:05 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 240/1251] eta: 0:10:50 lr: 0.000902 loss: 3.9769 (3.6814) grad_norm: 1.0592 (1.0816) time: 0.6246 [2021-03-26 12:07:12 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 250/1251] eta: 0:10:43 lr: 0.000902 loss: 3.7416 (3.6758) grad_norm: 1.0592 (1.0830) time: 0.6272 [2021-03-26 12:07:18 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 260/1251] eta: 0:10:36 lr: 0.000902 loss: 3.6249 (3.6683) grad_norm: 1.0955 (1.0844) time: 0.6343 [2021-03-26 12:07:24 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 270/1251] eta: 0:10:29 lr: 0.000902 loss: 3.5746 (3.6692) grad_norm: 1.0600 (1.0819) time: 0.6329 [2021-03-26 12:07:31 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 280/1251] eta: 0:10:22 lr: 0.000902 loss: 3.8275 (3.6780) grad_norm: 1.0195 (1.0828) time: 0.6255 [2021-03-26 12:07:37 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 290/1251] eta: 0:10:15 lr: 0.000902 loss: 3.9584 (3.6806) grad_norm: 1.1232 (inf) time: 0.6145 [2021-03-26 12:07:43 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 300/1251] eta: 0:10:08 lr: 0.000902 loss: 3.8814 (3.6835) grad_norm: 1.1232 (inf) time: 0.6155 [2021-03-26 12:07:49 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 310/1251] eta: 0:10:01 lr: 0.000902 loss: 3.7487 (3.6799) grad_norm: 1.1173 (inf) time: 0.6283 [2021-03-26 12:07:55 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 320/1251] eta: 0:09:54 lr: 0.000902 loss: 3.7058 (3.6857) grad_norm: 1.1165 (inf) time: 0.6287 [2021-03-26 12:08:02 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 330/1251] eta: 0:09:47 lr: 0.000902 loss: 3.7058 (3.6874) grad_norm: 1.0407 (inf) time: 0.6249 [2021-03-26 12:08:08 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 340/1251] eta: 0:09:41 lr: 0.000902 loss: 3.6030 (3.6821) grad_norm: 1.0322 (inf) time: 0.6266 [2021-03-26 12:08:14 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 350/1251] eta: 0:09:34 lr: 0.000902 loss: 3.7046 (3.6841) grad_norm: 1.0521 (inf) time: 0.6247 [2021-03-26 12:08:20 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 360/1251] eta: 0:09:27 lr: 0.000902 loss: 3.7093 (3.6831) grad_norm: 1.0521 (inf) time: 0.6226 [2021-03-26 12:08:27 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 370/1251] eta: 0:09:21 lr: 0.000901 loss: 3.8602 (3.6889) grad_norm: 1.0537 (inf) time: 0.6247 [2021-03-26 12:08:33 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 380/1251] eta: 0:09:14 lr: 0.000901 loss: 3.8706 (3.6911) grad_norm: 1.1787 (inf) time: 0.6227 [2021-03-26 12:08:39 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 390/1251] eta: 0:09:07 lr: 0.000901 loss: 3.7709 (3.6874) grad_norm: 1.1500 (inf) time: 0.6211 [2021-03-26 12:08:45 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 400/1251] eta: 0:09:00 lr: 0.000901 loss: 3.6306 (3.6881) grad_norm: 1.1533 (inf) time: 0.6201 [2021-03-26 12:08:52 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 410/1251] eta: 0:08:54 lr: 0.000901 loss: 3.6306 (3.6867) grad_norm: 1.1533 (inf) time: 0.6222 [2021-03-26 12:08:58 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 420/1251] eta: 0:08:47 lr: 0.000901 loss: 3.6064 (3.6888) grad_norm: 1.0837 (inf) time: 0.6248 [2021-03-26 12:09:04 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 430/1251] eta: 0:08:41 lr: 0.000901 loss: 3.7007 (3.6866) grad_norm: 1.0265 (inf) time: 0.6230 [2021-03-26 12:09:10 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 440/1251] eta: 0:08:34 lr: 0.000901 loss: 3.7036 (3.6874) grad_norm: 0.9946 (inf) time: 0.6256 [2021-03-26 12:09:17 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 450/1251] eta: 0:08:28 lr: 0.000901 loss: 3.7036 (3.6869) grad_norm: 1.0876 (inf) time: 0.6305 [2021-03-26 12:09:23 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 460/1251] eta: 0:08:21 lr: 0.000901 loss: 3.7519 (3.6869) grad_norm: 1.0876 (inf) time: 0.6289 [2021-03-26 12:09:29 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 470/1251] eta: 0:08:15 lr: 0.000901 loss: 3.9296 (3.6926) grad_norm: 1.0171 (inf) time: 0.6236 [2021-03-26 12:09:35 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 480/1251] eta: 0:08:08 lr: 0.000901 loss: 3.8310 (3.6881) grad_norm: 1.0394 (inf) time: 0.6226 [2021-03-26 12:09:42 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 490/1251] eta: 0:08:02 lr: 0.000901 loss: 3.6623 (3.6888) grad_norm: 1.0612 (inf) time: 0.6202 [2021-03-26 12:09:48 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 500/1251] eta: 0:07:55 lr: 0.000901 loss: 3.7778 (3.6907) grad_norm: 1.0612 (inf) time: 0.6202 [2021-03-26 12:09:54 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 510/1251] eta: 0:07:49 lr: 0.000901 loss: 3.7099 (3.6904) grad_norm: 1.0119 (inf) time: 0.6273 [2021-03-26 12:10:00 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 520/1251] eta: 0:07:42 lr: 0.000901 loss: 3.8515 (3.6941) grad_norm: 0.9958 (inf) time: 0.6228 [2021-03-26 12:10:06 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 530/1251] eta: 0:07:36 lr: 0.000901 loss: 3.9417 (3.6949) grad_norm: 1.0586 (inf) time: 0.6158 [2021-03-26 12:10:13 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 540/1251] eta: 0:07:29 lr: 0.000901 loss: 3.7087 (3.6938) grad_norm: 1.0906 (inf) time: 0.6215 [2021-03-26 12:10:19 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 550/1251] eta: 0:07:23 lr: 0.000901 loss: 3.7976 (3.6983) grad_norm: 1.0234 (inf) time: 0.6319 [2021-03-26 12:10:25 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 560/1251] eta: 0:07:17 lr: 0.000901 loss: 3.9456 (3.7002) grad_norm: 0.9816 (inf) time: 0.6345 [2021-03-26 12:10:32 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 570/1251] eta: 0:07:10 lr: 0.000901 loss: 3.7758 (3.7019) grad_norm: 1.0456 (inf) time: 0.6304 [2021-03-26 12:10:38 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 580/1251] eta: 0:07:04 lr: 0.000901 loss: 3.9409 (3.7039) grad_norm: 1.0548 (inf) time: 0.6302 [2021-03-26 12:10:44 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 590/1251] eta: 0:06:58 lr: 0.000901 loss: 3.8207 (3.7043) grad_norm: 1.0338 (inf) time: 0.6266 [2021-03-26 12:10:51 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 600/1251] eta: 0:06:51 lr: 0.000901 loss: 3.8033 (3.7027) grad_norm: 1.0623 (inf) time: 0.6291 [2021-03-26 12:10:57 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 610/1251] eta: 0:06:45 lr: 0.000901 loss: 3.7671 (3.7018) grad_norm: 1.0854 (inf) time: 0.6278 [2021-03-26 12:11:03 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 620/1251] eta: 0:06:38 lr: 0.000901 loss: 3.5152 (3.6994) grad_norm: 1.0938 (inf) time: 0.6270 [2021-03-26 12:11:09 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 630/1251] eta: 0:06:32 lr: 0.000901 loss: 3.5152 (3.7003) grad_norm: 1.1011 (inf) time: 0.6287 [2021-03-26 12:11:16 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 640/1251] eta: 0:06:26 lr: 0.000901 loss: 3.6054 (3.6974) grad_norm: 1.0678 (inf) time: 0.6271 [2021-03-26 12:11:22 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 650/1251] eta: 0:06:19 lr: 0.000901 loss: 3.6054 (3.6961) grad_norm: 1.0315 (inf) time: 0.6304 [2021-03-26 12:11:28 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 660/1251] eta: 0:06:13 lr: 0.000901 loss: 3.6858 (3.6955) grad_norm: 1.0315 (inf) time: 0.6242 [2021-03-26 12:11:34 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 670/1251] eta: 0:06:07 lr: 0.000901 loss: 3.5058 (3.6916) grad_norm: 1.0445 (inf) time: 0.6247 [2021-03-26 12:11:41 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 680/1251] eta: 0:06:00 lr: 0.000901 loss: 3.6792 (3.6920) grad_norm: 1.0434 (inf) time: 0.6323 [2021-03-26 12:11:47 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 690/1251] eta: 0:05:54 lr: 0.000901 loss: 3.6823 (3.6898) grad_norm: 1.0600 (inf) time: 0.6366 [2021-03-26 12:11:53 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 700/1251] eta: 0:05:48 lr: 0.000901 loss: 3.6823 (3.6888) grad_norm: 1.0399 (inf) time: 0.6282 [2021-03-26 12:12:00 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 710/1251] eta: 0:05:41 lr: 0.000901 loss: 3.6775 (3.6884) grad_norm: 0.9832 (inf) time: 0.6236 [2021-03-26 12:12:06 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 720/1251] eta: 0:05:35 lr: 0.000901 loss: 3.6647 (3.6875) grad_norm: 1.1261 (inf) time: 0.6291 [2021-03-26 12:12:12 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 730/1251] eta: 0:05:29 lr: 0.000901 loss: 3.6015 (3.6859) grad_norm: 1.1261 (inf) time: 0.6296 [2021-03-26 12:12:19 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 740/1251] eta: 0:05:22 lr: 0.000901 loss: 3.7516 (3.6867) grad_norm: 1.0828 (inf) time: 0.6328 [2021-03-26 12:12:25 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 750/1251] eta: 0:05:16 lr: 0.000901 loss: 3.8487 (3.6842) grad_norm: 1.0155 (inf) time: 0.6316 [2021-03-26 12:12:31 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 760/1251] eta: 0:05:10 lr: 0.000901 loss: 4.0426 (3.6884) grad_norm: 1.0500 (inf) time: 0.6247 [2021-03-26 12:12:37 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 770/1251] eta: 0:05:03 lr: 0.000900 loss: 4.0264 (3.6898) grad_norm: 1.0582 (inf) time: 0.6245 [2021-03-26 12:12:44 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 780/1251] eta: 0:04:57 lr: 0.000900 loss: 3.8366 (3.6903) grad_norm: 1.1079 (inf) time: 0.6262 [2021-03-26 12:12:50 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 790/1251] eta: 0:04:51 lr: 0.000900 loss: 3.8861 (3.6928) grad_norm: 1.1079 (inf) time: 0.6275 [2021-03-26 12:12:56 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 800/1251] eta: 0:04:44 lr: 0.000900 loss: 3.8072 (3.6917) grad_norm: 1.0310 (inf) time: 0.6274 [2021-03-26 12:13:03 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 810/1251] eta: 0:04:38 lr: 0.000900 loss: 3.6631 (3.6919) grad_norm: 1.0172 (inf) time: 0.6275 [2021-03-26 12:13:09 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 820/1251] eta: 0:04:32 lr: 0.000900 loss: 3.6208 (3.6893) grad_norm: 1.0290 (inf) time: 0.6298 [2021-03-26 12:13:15 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 830/1251] eta: 0:04:25 lr: 0.000900 loss: 3.7393 (3.6891) grad_norm: 1.0599 (inf) time: 0.6240 [2021-03-26 12:13:21 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 840/1251] eta: 0:04:19 lr: 0.000900 loss: 3.8390 (3.6894) grad_norm: 1.0883 (inf) time: 0.6220 [2021-03-26 12:13:28 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 850/1251] eta: 0:04:13 lr: 0.000900 loss: 3.8832 (3.6900) grad_norm: 1.0137 (inf) time: 0.6271 [2021-03-26 12:13:34 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 860/1251] eta: 0:04:06 lr: 0.000900 loss: 3.9658 (3.6942) grad_norm: 1.0450 (inf) time: 0.6332 [2021-03-26 12:13:40 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 870/1251] eta: 0:04:00 lr: 0.000900 loss: 3.8878 (3.6950) grad_norm: 1.0361 (inf) time: 0.6312 [2021-03-26 12:13:46 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 880/1251] eta: 0:03:54 lr: 0.000900 loss: 3.8659 (3.6946) grad_norm: 0.9950 (inf) time: 0.6246 [2021-03-26 12:13:53 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 890/1251] eta: 0:03:47 lr: 0.000900 loss: 3.7104 (3.6955) grad_norm: 1.0211 (inf) time: 0.6220 [2021-03-26 12:13:59 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 900/1251] eta: 0:03:41 lr: 0.000900 loss: 3.9938 (3.6987) grad_norm: 1.0675 (inf) time: 0.6236 [2021-03-26 12:14:05 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 910/1251] eta: 0:03:35 lr: 0.000900 loss: 3.7970 (3.6970) grad_norm: 1.1088 (inf) time: 0.6275 [2021-03-26 12:14:11 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 920/1251] eta: 0:03:28 lr: 0.000900 loss: 3.8627 (3.7012) grad_norm: 1.0350 (inf) time: 0.6231 [2021-03-26 12:14:18 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 930/1251] eta: 0:03:22 lr: 0.000900 loss: 3.9527 (3.6999) grad_norm: 1.1046 (inf) time: 0.6208 [2021-03-26 12:14:24 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 940/1251] eta: 0:03:16 lr: 0.000900 loss: 3.8328 (3.7001) grad_norm: 1.1362 (inf) time: 0.6253 [2021-03-26 12:14:30 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 950/1251] eta: 0:03:09 lr: 0.000900 loss: 3.8328 (3.6995) grad_norm: 1.0943 (inf) time: 0.6241 [2021-03-26 12:14:36 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 960/1251] eta: 0:03:03 lr: 0.000900 loss: 3.7694 (3.7011) grad_norm: 1.1792 (inf) time: 0.6246 [2021-03-26 12:14:43 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 970/1251] eta: 0:02:57 lr: 0.000900 loss: 3.8326 (3.7001) grad_norm: 1.1351 (inf) time: 0.6301 [2021-03-26 12:14:49 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 980/1251] eta: 0:02:50 lr: 0.000900 loss: 3.6738 (3.6987) grad_norm: 1.1125 (inf) time: 0.6269 [2021-03-26 12:14:55 swin_base_patch4_window7_224] INFO: Epoch: [61] [ 990/1251] eta: 0:02:44 lr: 0.000900 loss: 3.9237 (3.6996) grad_norm: 1.0037 (inf) time: 0.6226 [2021-03-26 12:15:02 swin_base_patch4_window7_224] INFO: Epoch: [61] [1000/1251] eta: 0:02:38 lr: 0.000900 loss: 3.8356 (3.6979) grad_norm: 1.0163 (inf) time: 0.6309 [2021-03-26 12:15:08 swin_base_patch4_window7_224] INFO: Epoch: [61] [1010/1251] eta: 0:02:31 lr: 0.000900 loss: 3.6321 (3.6990) grad_norm: 1.1008 (inf) time: 0.6354 [2021-03-26 12:15:14 swin_base_patch4_window7_224] INFO: Epoch: [61] [1020/1251] eta: 0:02:25 lr: 0.000900 loss: 3.8963 (3.6998) grad_norm: 1.0543 (inf) time: 0.6340 [2021-03-26 12:15:20 swin_base_patch4_window7_224] INFO: Epoch: [61] [1030/1251] eta: 0:02:19 lr: 0.000900 loss: 3.7534 (3.7006) grad_norm: 1.0628 (inf) time: 0.6265 [2021-03-26 12:15:27 swin_base_patch4_window7_224] INFO: Epoch: [61] [1040/1251] eta: 0:02:12 lr: 0.000900 loss: 3.7534 (3.7018) grad_norm: 1.0310 (inf) time: 0.6209 [2021-03-26 12:15:33 swin_base_patch4_window7_224] INFO: Epoch: [61] [1050/1251] eta: 0:02:06 lr: 0.000900 loss: 3.8215 (3.7030) grad_norm: 1.0381 (inf) time: 0.6271 [2021-03-26 12:15:39 swin_base_patch4_window7_224] INFO: Epoch: [61] [1060/1251] eta: 0:02:00 lr: 0.000900 loss: 3.8026 (3.7014) grad_norm: 1.0760 (inf) time: 0.6340 [2021-03-26 12:15:46 swin_base_patch4_window7_224] INFO: Epoch: [61] [1070/1251] eta: 0:01:54 lr: 0.000900 loss: 3.5595 (3.7014) grad_norm: 1.0809 (inf) time: 0.6298 [2021-03-26 12:15:52 swin_base_patch4_window7_224] INFO: Epoch: [61] [1080/1251] eta: 0:01:47 lr: 0.000900 loss: 3.6445 (3.7027) grad_norm: 1.0821 (inf) time: 0.6259 [2021-03-26 12:15:58 swin_base_patch4_window7_224] INFO: Epoch: [61] [1090/1251] eta: 0:01:41 lr: 0.000900 loss: 3.8282 (3.7040) grad_norm: 1.0865 (inf) time: 0.6248 [2021-03-26 12:16:04 swin_base_patch4_window7_224] INFO: Epoch: [61] [1100/1251] eta: 0:01:35 lr: 0.000900 loss: 3.9526 (3.7053) grad_norm: 1.1124 (inf) time: 0.6221 [2021-03-26 12:16:11 swin_base_patch4_window7_224] INFO: Epoch: [61] [1110/1251] eta: 0:01:28 lr: 0.000900 loss: 3.9691 (3.7071) grad_norm: 1.0963 (inf) time: 0.6249 [2021-03-26 12:16:17 swin_base_patch4_window7_224] INFO: Epoch: [61] [1120/1251] eta: 0:01:22 lr: 0.000900 loss: 3.8942 (3.7055) grad_norm: 1.0963 (inf) time: 0.6229 [2021-03-26 12:16:23 swin_base_patch4_window7_224] INFO: Epoch: [61] [1130/1251] eta: 0:01:16 lr: 0.000900 loss: 3.2660 (3.7016) grad_norm: 1.0974 (inf) time: 0.6266 [2021-03-26 12:16:29 swin_base_patch4_window7_224] INFO: Epoch: [61] [1140/1251] eta: 0:01:09 lr: 0.000900 loss: 3.4046 (3.7016) grad_norm: 1.0944 (inf) time: 0.6331 [2021-03-26 12:16:36 swin_base_patch4_window7_224] INFO: Epoch: [61] [1150/1251] eta: 0:01:03 lr: 0.000900 loss: 3.8016 (3.7012) grad_norm: 1.0060 (inf) time: 0.6277 [2021-03-26 12:16:42 swin_base_patch4_window7_224] INFO: Epoch: [61] [1160/1251] eta: 0:00:57 lr: 0.000900 loss: 3.8016 (3.7021) grad_norm: 1.0257 (inf) time: 0.6215 [2021-03-26 12:16:48 swin_base_patch4_window7_224] INFO: Epoch: [61] [1170/1251] eta: 0:00:51 lr: 0.000899 loss: 3.8401 (3.7035) grad_norm: 1.1301 (inf) time: 0.6273 [2021-03-26 12:16:54 swin_base_patch4_window7_224] INFO: Epoch: [61] [1180/1251] eta: 0:00:44 lr: 0.000899 loss: 3.8238 (3.7029) grad_norm: 1.1152 (inf) time: 0.6320 [2021-03-26 12:17:01 swin_base_patch4_window7_224] INFO: Epoch: [61] [1190/1251] eta: 0:00:38 lr: 0.000899 loss: 3.5195 (3.7017) grad_norm: 1.0455 (inf) time: 0.6277 [2021-03-26 12:17:07 swin_base_patch4_window7_224] INFO: Epoch: [61] [1200/1251] eta: 0:00:32 lr: 0.000899 loss: 3.5195 (3.7000) grad_norm: 1.0939 (inf) time: 0.6283 [2021-03-26 12:17:13 swin_base_patch4_window7_224] INFO: Epoch: [61] [1210/1251] eta: 0:00:25 lr: 0.000899 loss: 3.4876 (3.6985) grad_norm: 1.0228 (inf) time: 0.6256 [2021-03-26 12:17:19 swin_base_patch4_window7_224] INFO: Epoch: [61] [1220/1251] eta: 0:00:19 lr: 0.000899 loss: 3.6302 (3.6991) grad_norm: 0.9942 (inf) time: 0.6215 [2021-03-26 12:17:26 swin_base_patch4_window7_224] INFO: Epoch: [61] [1230/1251] eta: 0:00:13 lr: 0.000899 loss: 3.5435 (3.6985) grad_norm: 1.0385 (inf) time: 0.6233 [2021-03-26 12:17:32 swin_base_patch4_window7_224] INFO: Epoch: [61] [1240/1251] eta: 0:00:06 lr: 0.000899 loss: 3.4616 (3.6974) grad_norm: 1.0538 (inf) time: 0.6230 [2021-03-26 12:17:38 swin_base_patch4_window7_224] INFO: Epoch: [61] [1250/1251] eta: 0:00:00 lr: 0.000899 loss: 3.5722 (3.6963) grad_norm: 1.0430 (inf) time: 0.6244 [2021-03-26 12:17:43 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:56 loss: 1.4857 (1.4857) acc1: 64.0625 (64.0625) acc5: 87.5000 (87.5000) [2021-03-26 12:17:45 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0408 (1.0876) acc1: 73.4375 (73.4375) acc5: 93.7500 (93.1818) [2021-03-26 12:17:48 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0408 (1.0972) acc1: 73.4375 (74.1815) acc5: 93.7500 (92.2619) [2021-03-26 12:17:50 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1535 (1.1225) acc1: 71.8750 (73.2359) acc5: 92.1875 (92.2883) [2021-03-26 12:17:52 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1522 (1.1217) acc1: 71.8750 (73.8567) acc5: 92.1875 (92.0351) [2021-03-26 12:17:53 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1499 (1.1231) acc1: 73.4375 (73.6640) acc5: 92.1875 (92.1600) [2021-03-26 12:17:57 swin_base_patch4_window7_224] INFO: * Acc@1 73.974 Acc@5 92.556 loss 1.097 [2021-03-26 12:17:57 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.0% [2021-03-26 12:17:57 swin_base_patch4_window7_224] INFO: Max accuracy: 74.19% [2021-03-26 12:18:02 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 0/1251] eta: 1:29:58 lr: 0.000899 loss: 3.8995 (3.8995) grad_norm: 1.1032 (1.1032) time: 4.3152 [2021-03-26 12:18:08 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 10/1251] eta: 0:20:01 lr: 0.000899 loss: 3.8995 (3.6962) grad_norm: 1.1032 (1.1566) time: 0.9686 [2021-03-26 12:18:14 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 20/1251] eta: 0:16:38 lr: 0.000899 loss: 3.7751 (3.6374) grad_norm: 1.0884 (1.1274) time: 0.6360 [2021-03-26 12:18:21 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 30/1251] eta: 0:15:16 lr: 0.000899 loss: 4.0210 (3.7161) grad_norm: 1.0815 (1.1057) time: 0.6305 [2021-03-26 12:18:27 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 40/1251] eta: 0:14:30 lr: 0.000899 loss: 3.8133 (3.6935) grad_norm: 1.0054 (1.0821) time: 0.6220 [2021-03-26 12:18:33 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 50/1251] eta: 0:14:01 lr: 0.000899 loss: 3.8133 (3.7234) grad_norm: 1.0159 (1.0840) time: 0.6226 [2021-03-26 12:18:39 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 60/1251] eta: 0:13:39 lr: 0.000899 loss: 3.9237 (3.7243) grad_norm: 1.0633 (1.0801) time: 0.6242 [2021-03-26 12:18:46 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 70/1251] eta: 0:13:24 lr: 0.000899 loss: 3.7015 (3.7052) grad_norm: 1.0673 (1.0871) time: 0.6331 [2021-03-26 12:18:52 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 80/1251] eta: 0:13:08 lr: 0.000899 loss: 3.6491 (3.6581) grad_norm: 1.0673 (1.0854) time: 0.6294 [2021-03-26 12:18:58 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 90/1251] eta: 0:12:56 lr: 0.000899 loss: 3.6491 (3.6482) grad_norm: 1.0233 (1.0820) time: 0.6248 [2021-03-26 12:19:04 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 100/1251] eta: 0:12:43 lr: 0.000899 loss: 3.6795 (3.6278) grad_norm: 1.0135 (1.0808) time: 0.6236 [2021-03-26 12:19:10 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 110/1251] eta: 0:12:32 lr: 0.000899 loss: 3.6033 (3.6140) grad_norm: 1.0261 (1.0841) time: 0.6177 [2021-03-26 12:19:17 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 120/1251] eta: 0:12:22 lr: 0.000899 loss: 3.5689 (3.6199) grad_norm: 1.0455 (1.0848) time: 0.6194 [2021-03-26 12:19:23 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 130/1251] eta: 0:12:12 lr: 0.000899 loss: 3.5638 (3.6119) grad_norm: 1.0402 (1.0843) time: 0.6206 [2021-03-26 12:19:29 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 140/1251] eta: 0:12:03 lr: 0.000899 loss: 3.4524 (3.6057) grad_norm: 1.0242 (1.0797) time: 0.6238 [2021-03-26 12:19:35 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 150/1251] eta: 0:11:55 lr: 0.000899 loss: 3.7361 (3.5985) grad_norm: 1.0339 (1.0840) time: 0.6231 [2021-03-26 12:19:42 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 160/1251] eta: 0:11:47 lr: 0.000899 loss: 3.6186 (3.5911) grad_norm: 1.1154 (1.0860) time: 0.6261 [2021-03-26 12:19:48 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 170/1251] eta: 0:11:39 lr: 0.000899 loss: 3.4654 (3.5763) grad_norm: 1.1007 (1.0874) time: 0.6285 [2021-03-26 12:19:54 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 180/1251] eta: 0:11:32 lr: 0.000899 loss: 3.5717 (3.5874) grad_norm: 1.0901 (1.0876) time: 0.6283 [2021-03-26 12:20:01 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 190/1251] eta: 0:11:24 lr: 0.000899 loss: 3.6895 (3.5839) grad_norm: 1.1052 (1.0915) time: 0.6283 [2021-03-26 12:20:07 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 200/1251] eta: 0:11:17 lr: 0.000899 loss: 3.7876 (3.5952) grad_norm: 1.1620 (1.0926) time: 0.6288 [2021-03-26 12:20:13 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 210/1251] eta: 0:11:09 lr: 0.000899 loss: 3.9833 (3.6119) grad_norm: 1.1620 (1.0966) time: 0.6272 [2021-03-26 12:20:19 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 220/1251] eta: 0:11:02 lr: 0.000899 loss: 3.8388 (3.6063) grad_norm: 1.0634 (1.0939) time: 0.6228 [2021-03-26 12:20:26 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 230/1251] eta: 0:10:55 lr: 0.000899 loss: 3.6882 (3.6093) grad_norm: 1.0237 (1.0928) time: 0.6251 [2021-03-26 12:20:32 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 240/1251] eta: 0:10:47 lr: 0.000899 loss: 3.7638 (3.6181) grad_norm: 1.0005 (1.0895) time: 0.6222 [2021-03-26 12:20:38 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 250/1251] eta: 0:10:40 lr: 0.000899 loss: 3.7625 (3.6151) grad_norm: 1.0012 (1.0905) time: 0.6191 [2021-03-26 12:20:44 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 260/1251] eta: 0:10:33 lr: 0.000899 loss: 3.5699 (3.6136) grad_norm: 1.0241 (1.0885) time: 0.6251 [2021-03-26 12:20:50 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 270/1251] eta: 0:10:27 lr: 0.000899 loss: 3.5923 (3.6067) grad_norm: 1.0241 (1.0879) time: 0.6275 [2021-03-26 12:20:57 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 280/1251] eta: 0:10:20 lr: 0.000899 loss: 3.5884 (3.6071) grad_norm: 1.0976 (1.0901) time: 0.6253 [2021-03-26 12:21:03 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 290/1251] eta: 0:10:13 lr: 0.000899 loss: 3.5906 (3.6104) grad_norm: 1.1030 (1.0897) time: 0.6235 [2021-03-26 12:21:09 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 300/1251] eta: 0:10:06 lr: 0.000899 loss: 3.6373 (3.6119) grad_norm: 1.0826 (1.0911) time: 0.6245 [2021-03-26 12:21:15 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 310/1251] eta: 0:09:59 lr: 0.000899 loss: 3.9369 (3.6216) grad_norm: 1.0537 (1.0892) time: 0.6226 [2021-03-26 12:21:22 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 320/1251] eta: 0:09:53 lr: 0.000898 loss: 3.7588 (3.6201) grad_norm: 1.0625 (1.0907) time: 0.6262 [2021-03-26 12:21:28 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 330/1251] eta: 0:09:46 lr: 0.000898 loss: 3.6667 (3.6194) grad_norm: 1.0785 (1.0903) time: 0.6243 [2021-03-26 12:21:34 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 340/1251] eta: 0:09:39 lr: 0.000898 loss: 3.6365 (3.6148) grad_norm: 0.9880 (1.0881) time: 0.6208 [2021-03-26 12:21:40 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 350/1251] eta: 0:09:32 lr: 0.000898 loss: 3.6957 (3.6159) grad_norm: 1.0573 (1.0890) time: 0.6265 [2021-03-26 12:21:47 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 360/1251] eta: 0:09:26 lr: 0.000898 loss: 3.9167 (3.6217) grad_norm: 1.0476 (1.0881) time: 0.6234 [2021-03-26 12:21:53 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 370/1251] eta: 0:09:19 lr: 0.000898 loss: 3.9810 (3.6313) grad_norm: 1.0476 (1.0883) time: 0.6275 [2021-03-26 12:21:59 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 380/1251] eta: 0:09:12 lr: 0.000898 loss: 4.0298 (3.6362) grad_norm: 1.0264 (1.0866) time: 0.6269 [2021-03-26 12:22:05 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 390/1251] eta: 0:09:06 lr: 0.000898 loss: 3.9581 (3.6376) grad_norm: 0.9977 (1.0866) time: 0.6159 [2021-03-26 12:22:12 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 400/1251] eta: 0:09:00 lr: 0.000898 loss: 3.8339 (3.6375) grad_norm: 1.0780 (1.0872) time: 0.6285 [2021-03-26 12:22:18 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 410/1251] eta: 0:08:53 lr: 0.000898 loss: 3.6862 (3.6360) grad_norm: 1.1532 (1.0895) time: 0.6387 [2021-03-26 12:22:24 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 420/1251] eta: 0:08:47 lr: 0.000898 loss: 3.6976 (3.6381) grad_norm: 1.1370 (1.0902) time: 0.6326 [2021-03-26 12:22:31 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 430/1251] eta: 0:08:40 lr: 0.000898 loss: 3.6976 (3.6321) grad_norm: 1.0718 (1.0916) time: 0.6260 [2021-03-26 12:22:37 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 440/1251] eta: 0:08:33 lr: 0.000898 loss: 3.3326 (3.6285) grad_norm: 1.0293 (1.0905) time: 0.6193 [2021-03-26 12:22:43 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 450/1251] eta: 0:08:27 lr: 0.000898 loss: 3.4952 (3.6252) grad_norm: 1.0562 (1.0902) time: 0.6219 [2021-03-26 12:22:49 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 460/1251] eta: 0:08:21 lr: 0.000898 loss: 3.6909 (3.6225) grad_norm: 1.0621 (1.0914) time: 0.6268 [2021-03-26 12:22:56 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 470/1251] eta: 0:08:14 lr: 0.000898 loss: 3.8067 (3.6238) grad_norm: 1.1419 (1.0932) time: 0.6269 [2021-03-26 12:23:02 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 480/1251] eta: 0:08:08 lr: 0.000898 loss: 3.8673 (3.6262) grad_norm: 1.1597 (1.0946) time: 0.6242 [2021-03-26 12:23:08 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 490/1251] eta: 0:08:01 lr: 0.000898 loss: 3.6462 (3.6257) grad_norm: 1.0744 (1.0952) time: 0.6258 [2021-03-26 12:23:14 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 500/1251] eta: 0:07:55 lr: 0.000898 loss: 3.7354 (3.6301) grad_norm: 1.0198 (1.0943) time: 0.6255 [2021-03-26 12:23:21 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 510/1251] eta: 0:07:48 lr: 0.000898 loss: 3.8636 (3.6305) grad_norm: 1.0488 (1.0942) time: 0.6193 [2021-03-26 12:23:27 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 520/1251] eta: 0:07:42 lr: 0.000898 loss: 3.6916 (3.6297) grad_norm: 1.0634 (1.0937) time: 0.6216 [2021-03-26 12:23:33 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 530/1251] eta: 0:07:35 lr: 0.000898 loss: 3.6916 (3.6328) grad_norm: 1.0576 (1.0939) time: 0.6290 [2021-03-26 12:23:39 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 540/1251] eta: 0:07:29 lr: 0.000898 loss: 3.7242 (3.6348) grad_norm: 1.1503 (1.0971) time: 0.6295 [2021-03-26 12:23:46 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 550/1251] eta: 0:07:23 lr: 0.000898 loss: 3.7242 (3.6364) grad_norm: 1.1417 (1.0964) time: 0.6418 [2021-03-26 12:23:52 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 560/1251] eta: 0:07:17 lr: 0.000898 loss: 3.9111 (3.6375) grad_norm: 1.0449 (1.0966) time: 0.6467 [2021-03-26 12:23:59 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 570/1251] eta: 0:07:10 lr: 0.000898 loss: 3.9148 (3.6419) grad_norm: 1.1426 (1.0984) time: 0.6353 [2021-03-26 12:24:05 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 580/1251] eta: 0:07:04 lr: 0.000898 loss: 3.7676 (3.6415) grad_norm: 1.1218 (1.0989) time: 0.6312 [2021-03-26 12:24:11 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 590/1251] eta: 0:06:58 lr: 0.000898 loss: 3.8016 (3.6437) grad_norm: 1.0772 (1.0993) time: 0.6294 [2021-03-26 12:24:18 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 600/1251] eta: 0:06:51 lr: 0.000898 loss: 3.8016 (3.6463) grad_norm: 1.0772 (1.0986) time: 0.6297 [2021-03-26 12:24:24 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 610/1251] eta: 0:06:45 lr: 0.000898 loss: 3.8444 (3.6500) grad_norm: 1.0905 (1.0990) time: 0.6310 [2021-03-26 12:24:30 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 620/1251] eta: 0:06:39 lr: 0.000898 loss: 3.8203 (3.6507) grad_norm: 1.0973 (1.0992) time: 0.6290 [2021-03-26 12:24:36 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 630/1251] eta: 0:06:32 lr: 0.000898 loss: 3.8203 (3.6547) grad_norm: 1.0672 (1.0986) time: 0.6281 [2021-03-26 12:24:43 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 640/1251] eta: 0:06:26 lr: 0.000898 loss: 3.7439 (3.6499) grad_norm: 1.0672 (1.0993) time: 0.6331 [2021-03-26 12:24:49 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 650/1251] eta: 0:06:20 lr: 0.000898 loss: 3.3144 (3.6468) grad_norm: 1.1154 (1.0999) time: 0.6358 [2021-03-26 12:24:55 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 660/1251] eta: 0:06:13 lr: 0.000898 loss: 3.7975 (3.6503) grad_norm: 1.1125 (1.1013) time: 0.6308 [2021-03-26 12:25:02 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 670/1251] eta: 0:06:07 lr: 0.000898 loss: 3.8364 (3.6502) grad_norm: 1.1265 (1.1025) time: 0.6284 [2021-03-26 12:25:08 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 680/1251] eta: 0:06:01 lr: 0.000898 loss: 3.7877 (3.6523) grad_norm: 1.0810 (1.1020) time: 0.6258 [2021-03-26 12:25:14 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 690/1251] eta: 0:05:54 lr: 0.000898 loss: 3.6846 (3.6496) grad_norm: 1.0264 (1.1018) time: 0.6264 [2021-03-26 12:25:21 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 700/1251] eta: 0:05:48 lr: 0.000898 loss: 3.6426 (3.6497) grad_norm: 1.0254 (1.1013) time: 0.6301 [2021-03-26 12:25:27 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 710/1251] eta: 0:05:41 lr: 0.000897 loss: 3.8690 (3.6485) grad_norm: 1.0891 (1.1024) time: 0.6273 [2021-03-26 12:25:33 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 720/1251] eta: 0:05:35 lr: 0.000897 loss: 3.6574 (3.6476) grad_norm: 1.0897 (1.1022) time: 0.6244 [2021-03-26 12:25:39 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 730/1251] eta: 0:05:29 lr: 0.000897 loss: 3.4846 (3.6453) grad_norm: 1.0897 (1.1025) time: 0.6262 [2021-03-26 12:25:46 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 740/1251] eta: 0:05:23 lr: 0.000897 loss: 3.6893 (3.6465) grad_norm: 1.0808 (1.1031) time: 0.6367 [2021-03-26 12:25:52 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 750/1251] eta: 0:05:16 lr: 0.000897 loss: 3.7568 (3.6453) grad_norm: 1.0753 (1.1031) time: 0.6395 [2021-03-26 12:25:58 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 760/1251] eta: 0:05:10 lr: 0.000897 loss: 3.7568 (3.6468) grad_norm: 1.0451 (1.1027) time: 0.6361 [2021-03-26 12:26:05 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 770/1251] eta: 0:05:04 lr: 0.000897 loss: 3.7915 (3.6479) grad_norm: 1.0652 (1.1023) time: 0.6333 [2021-03-26 12:26:11 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 780/1251] eta: 0:04:57 lr: 0.000897 loss: 3.4519 (3.6456) grad_norm: 1.0864 (1.1025) time: 0.6301 [2021-03-26 12:26:17 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 790/1251] eta: 0:04:51 lr: 0.000897 loss: 3.3518 (3.6454) grad_norm: 1.0864 (1.1022) time: 0.6312 [2021-03-26 12:26:24 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 800/1251] eta: 0:04:45 lr: 0.000897 loss: 3.4209 (3.6428) grad_norm: 1.0539 (1.1024) time: 0.6297 [2021-03-26 12:26:30 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 810/1251] eta: 0:04:38 lr: 0.000897 loss: 3.8092 (3.6449) grad_norm: 1.0539 (1.1015) time: 0.6281 [2021-03-26 12:26:36 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 820/1251] eta: 0:04:32 lr: 0.000897 loss: 3.8092 (3.6467) grad_norm: 0.9811 (1.1005) time: 0.6266 [2021-03-26 12:26:43 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 830/1251] eta: 0:04:26 lr: 0.000897 loss: 3.5789 (3.6455) grad_norm: 1.0014 (1.1001) time: 0.6280 [2021-03-26 12:26:49 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 840/1251] eta: 0:04:19 lr: 0.000897 loss: 3.5148 (3.6435) grad_norm: 1.0486 (1.1006) time: 0.6313 [2021-03-26 12:26:55 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 850/1251] eta: 0:04:13 lr: 0.000897 loss: 3.5771 (3.6442) grad_norm: 1.0911 (1.1008) time: 0.6275 [2021-03-26 12:27:01 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 860/1251] eta: 0:04:06 lr: 0.000897 loss: 3.8158 (3.6445) grad_norm: 1.0732 (1.1009) time: 0.6208 [2021-03-26 12:27:08 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 870/1251] eta: 0:04:00 lr: 0.000897 loss: 3.4807 (3.6378) grad_norm: 1.0732 (1.1006) time: 0.6214 [2021-03-26 12:27:14 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 880/1251] eta: 0:03:54 lr: 0.000897 loss: 3.0996 (3.6372) grad_norm: 1.0939 (1.1011) time: 0.6246 [2021-03-26 12:27:20 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 890/1251] eta: 0:03:47 lr: 0.000897 loss: 3.9063 (3.6379) grad_norm: 1.1200 (1.1013) time: 0.6238 [2021-03-26 12:27:26 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 900/1251] eta: 0:03:41 lr: 0.000897 loss: 3.5798 (3.6356) grad_norm: 1.0782 (1.1016) time: 0.6226 [2021-03-26 12:27:32 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 910/1251] eta: 0:03:35 lr: 0.000897 loss: 3.6077 (3.6364) grad_norm: 1.0303 (1.1004) time: 0.6214 [2021-03-26 12:27:39 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 920/1251] eta: 0:03:28 lr: 0.000897 loss: 3.7630 (3.6374) grad_norm: 1.0434 (1.1004) time: 0.6280 [2021-03-26 12:27:45 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 930/1251] eta: 0:03:22 lr: 0.000897 loss: 3.6794 (3.6347) grad_norm: 1.0605 (1.0999) time: 0.6327 [2021-03-26 12:27:51 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 940/1251] eta: 0:03:16 lr: 0.000897 loss: 3.4682 (3.6339) grad_norm: 1.0070 (1.0988) time: 0.6245 [2021-03-26 12:27:57 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 950/1251] eta: 0:03:09 lr: 0.000897 loss: 3.9528 (3.6367) grad_norm: 1.0336 (1.0994) time: 0.6200 [2021-03-26 12:28:04 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 960/1251] eta: 0:03:03 lr: 0.000897 loss: 3.8802 (3.6360) grad_norm: 1.0844 (1.0995) time: 0.6266 [2021-03-26 12:28:10 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 970/1251] eta: 0:02:57 lr: 0.000897 loss: 3.7539 (3.6376) grad_norm: 1.1131 (1.1001) time: 0.6301 [2021-03-26 12:28:16 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 980/1251] eta: 0:02:50 lr: 0.000897 loss: 3.6862 (3.6372) grad_norm: 1.0519 (1.0994) time: 0.6241 [2021-03-26 12:28:23 swin_base_patch4_window7_224] INFO: Epoch: [62] [ 990/1251] eta: 0:02:44 lr: 0.000897 loss: 3.6825 (3.6374) grad_norm: 1.0666 (1.0995) time: 0.6266 [2021-03-26 12:28:29 swin_base_patch4_window7_224] INFO: Epoch: [62] [1000/1251] eta: 0:02:38 lr: 0.000897 loss: 3.5570 (3.6355) grad_norm: 1.0843 (1.0984) time: 0.6262 [2021-03-26 12:28:35 swin_base_patch4_window7_224] INFO: Epoch: [62] [1010/1251] eta: 0:02:32 lr: 0.000897 loss: 3.5523 (3.6350) grad_norm: 1.0503 (1.0984) time: 0.6250 [2021-03-26 12:28:41 swin_base_patch4_window7_224] INFO: Epoch: [62] [1020/1251] eta: 0:02:25 lr: 0.000897 loss: 3.7899 (3.6373) grad_norm: 1.0902 (1.0984) time: 0.6304 [2021-03-26 12:28:48 swin_base_patch4_window7_224] INFO: Epoch: [62] [1030/1251] eta: 0:02:19 lr: 0.000897 loss: 3.8207 (3.6399) grad_norm: 1.0195 (1.0977) time: 0.6253 [2021-03-26 12:28:54 swin_base_patch4_window7_224] INFO: Epoch: [62] [1040/1251] eta: 0:02:13 lr: 0.000897 loss: 3.7559 (3.6397) grad_norm: 1.0331 (1.0976) time: 0.6241 [2021-03-26 12:29:00 swin_base_patch4_window7_224] INFO: Epoch: [62] [1050/1251] eta: 0:02:06 lr: 0.000897 loss: 3.7097 (3.6388) grad_norm: 1.1075 (1.0976) time: 0.6284 [2021-03-26 12:29:06 swin_base_patch4_window7_224] INFO: Epoch: [62] [1060/1251] eta: 0:02:00 lr: 0.000897 loss: 3.7097 (3.6394) grad_norm: 1.1247 (inf) time: 0.6235 [2021-03-26 12:29:13 swin_base_patch4_window7_224] INFO: Epoch: [62] [1070/1251] eta: 0:01:54 lr: 0.000897 loss: 3.7137 (3.6391) grad_norm: 1.0627 (inf) time: 0.6198 [2021-03-26 12:29:19 swin_base_patch4_window7_224] INFO: Epoch: [62] [1080/1251] eta: 0:01:47 lr: 0.000897 loss: 3.5190 (3.6392) grad_norm: 1.0529 (inf) time: 0.6246 [2021-03-26 12:29:25 swin_base_patch4_window7_224] INFO: Epoch: [62] [1090/1251] eta: 0:01:41 lr: 0.000897 loss: 3.8078 (3.6405) grad_norm: 1.0888 (inf) time: 0.6273 [2021-03-26 12:29:31 swin_base_patch4_window7_224] INFO: Epoch: [62] [1100/1251] eta: 0:01:35 lr: 0.000897 loss: 3.9513 (3.6426) grad_norm: 1.0905 (inf) time: 0.6241 [2021-03-26 12:29:38 swin_base_patch4_window7_224] INFO: Epoch: [62] [1110/1251] eta: 0:01:28 lr: 0.000896 loss: 3.8427 (3.6441) grad_norm: 1.0313 (inf) time: 0.6263 [2021-03-26 12:29:44 swin_base_patch4_window7_224] INFO: Epoch: [62] [1120/1251] eta: 0:01:22 lr: 0.000896 loss: 3.7466 (3.6449) grad_norm: 1.0102 (inf) time: 0.6267 [2021-03-26 12:29:50 swin_base_patch4_window7_224] INFO: Epoch: [62] [1130/1251] eta: 0:01:16 lr: 0.000896 loss: 3.6704 (3.6454) grad_norm: 1.0102 (inf) time: 0.6193 [2021-03-26 12:29:56 swin_base_patch4_window7_224] INFO: Epoch: [62] [1140/1251] eta: 0:01:09 lr: 0.000896 loss: 3.6993 (3.6475) grad_norm: 1.0350 (inf) time: 0.6243 [2021-03-26 12:30:03 swin_base_patch4_window7_224] INFO: Epoch: [62] [1150/1251] eta: 0:01:03 lr: 0.000896 loss: 3.6977 (3.6453) grad_norm: 1.1393 (inf) time: 0.6313 [2021-03-26 12:30:09 swin_base_patch4_window7_224] INFO: Epoch: [62] [1160/1251] eta: 0:00:57 lr: 0.000896 loss: 3.4646 (3.6457) grad_norm: 1.1393 (inf) time: 0.6289 [2021-03-26 12:30:15 swin_base_patch4_window7_224] INFO: Epoch: [62] [1170/1251] eta: 0:00:51 lr: 0.000896 loss: 3.8209 (3.6477) grad_norm: 1.1138 (inf) time: 0.6219 [2021-03-26 12:30:21 swin_base_patch4_window7_224] INFO: Epoch: [62] [1180/1251] eta: 0:00:44 lr: 0.000896 loss: 3.8881 (3.6479) grad_norm: 1.0772 (inf) time: 0.6215 [2021-03-26 12:30:28 swin_base_patch4_window7_224] INFO: Epoch: [62] [1190/1251] eta: 0:00:38 lr: 0.000896 loss: 3.7439 (3.6486) grad_norm: 1.0673 (inf) time: 0.6274 [2021-03-26 12:30:34 swin_base_patch4_window7_224] INFO: Epoch: [62] [1200/1251] eta: 0:00:32 lr: 0.000896 loss: 3.7439 (3.6501) grad_norm: 1.0675 (inf) time: 0.6323 [2021-03-26 12:30:40 swin_base_patch4_window7_224] INFO: Epoch: [62] [1210/1251] eta: 0:00:25 lr: 0.000896 loss: 3.9651 (3.6513) grad_norm: 1.0675 (inf) time: 0.6258 [2021-03-26 12:30:47 swin_base_patch4_window7_224] INFO: Epoch: [62] [1220/1251] eta: 0:00:19 lr: 0.000896 loss: 3.7624 (3.6507) grad_norm: 1.0401 (inf) time: 0.6260 [2021-03-26 12:30:53 swin_base_patch4_window7_224] INFO: Epoch: [62] [1230/1251] eta: 0:00:13 lr: 0.000896 loss: 3.5230 (3.6492) grad_norm: 1.0274 (inf) time: 0.6257 [2021-03-26 12:30:59 swin_base_patch4_window7_224] INFO: Epoch: [62] [1240/1251] eta: 0:00:06 lr: 0.000896 loss: 3.1635 (3.6457) grad_norm: 1.0367 (inf) time: 0.6153 [2021-03-26 12:31:05 swin_base_patch4_window7_224] INFO: Epoch: [62] [1250/1251] eta: 0:00:00 lr: 0.000896 loss: 3.5138 (3.6477) grad_norm: 1.0521 (inf) time: 0.6113 [2021-03-26 12:31:09 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 1.3888 (1.3888) acc1: 70.3125 (70.3125) acc5: 90.6250 (90.6250) [2021-03-26 12:31:13 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.0484 (1.0923) acc1: 76.5625 (74.5739) acc5: 93.7500 (92.6136) [2021-03-26 12:31:15 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0212 (1.0800) acc1: 75.0000 (74.0327) acc5: 93.7500 (93.0804) [2021-03-26 12:31:17 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1129 (1.0968) acc1: 71.8750 (73.4879) acc5: 93.7500 (93.0444) [2021-03-26 12:31:19 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1864 (1.1146) acc1: 71.8750 (73.5899) acc5: 92.1875 (92.4543) [2021-03-26 12:31:20 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1637 (1.1140) acc1: 73.4375 (73.4080) acc5: 92.1875 (92.5760) [2021-03-26 12:31:24 swin_base_patch4_window7_224] INFO: * Acc@1 74.280 Acc@5 92.438 loss 1.105 [2021-03-26 12:31:24 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.3% [2021-03-26 12:31:24 swin_base_patch4_window7_224] INFO: Max accuracy: 74.28% [2021-03-26 12:31:28 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 0/1251] eta: 1:27:33 lr: 0.000896 loss: 3.9401 (3.9401) grad_norm: 0.9232 (0.9232) time: 4.1995 [2021-03-26 12:31:34 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 10/1251] eta: 0:20:01 lr: 0.000896 loss: 3.2714 (3.3274) grad_norm: 1.0847 (1.0988) time: 0.9683 [2021-03-26 12:31:40 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 20/1251] eta: 0:16:29 lr: 0.000896 loss: 3.3712 (3.4811) grad_norm: 1.0739 (1.0517) time: 0.6339 [2021-03-26 12:31:47 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 30/1251] eta: 0:15:12 lr: 0.000896 loss: 3.7500 (3.5588) grad_norm: 1.0774 (1.1092) time: 0.6256 [2021-03-26 12:31:53 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 40/1251] eta: 0:14:29 lr: 0.000896 loss: 3.7977 (3.6215) grad_norm: 1.1412 (1.1258) time: 0.6287 [2021-03-26 12:31:59 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 50/1251] eta: 0:14:02 lr: 0.000896 loss: 3.7321 (3.6467) grad_norm: 1.1536 (1.1368) time: 0.6304 [2021-03-26 12:32:06 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 60/1251] eta: 0:13:40 lr: 0.000896 loss: 3.6457 (3.6436) grad_norm: 1.1711 (1.1466) time: 0.6276 [2021-03-26 12:32:12 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 70/1251] eta: 0:13:23 lr: 0.000896 loss: 3.4614 (3.6204) grad_norm: 1.1750 (1.1640) time: 0.6259 [2021-03-26 12:32:18 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 80/1251] eta: 0:13:09 lr: 0.000896 loss: 3.4561 (3.6021) grad_norm: 1.1176 (1.1545) time: 0.6288 [2021-03-26 12:32:24 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 90/1251] eta: 0:12:55 lr: 0.000896 loss: 3.6556 (3.6388) grad_norm: 1.0441 (1.1436) time: 0.6242 [2021-03-26 12:32:31 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 100/1251] eta: 0:12:42 lr: 0.000896 loss: 3.8405 (3.6412) grad_norm: 1.0219 (1.1375) time: 0.6183 [2021-03-26 12:32:37 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 110/1251] eta: 0:12:32 lr: 0.000896 loss: 3.8788 (3.6652) grad_norm: 1.0934 (1.1474) time: 0.6207 [2021-03-26 12:32:43 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 120/1251] eta: 0:12:22 lr: 0.000896 loss: 3.7723 (3.6511) grad_norm: 1.1155 (1.1405) time: 0.6258 [2021-03-26 12:32:49 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 130/1251] eta: 0:12:13 lr: 0.000896 loss: 3.4223 (3.6383) grad_norm: 1.0663 (1.1377) time: 0.6252 [2021-03-26 12:32:56 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 140/1251] eta: 0:12:05 lr: 0.000896 loss: 3.6580 (3.6563) grad_norm: 1.0809 (1.1369) time: 0.6282 [2021-03-26 12:33:02 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 150/1251] eta: 0:11:56 lr: 0.000896 loss: 3.6580 (3.6489) grad_norm: 1.1283 (1.1366) time: 0.6311 [2021-03-26 12:33:08 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 160/1251] eta: 0:11:48 lr: 0.000896 loss: 3.4818 (3.6272) grad_norm: 1.0860 (1.1316) time: 0.6271 [2021-03-26 12:33:14 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 170/1251] eta: 0:11:39 lr: 0.000896 loss: 3.4528 (3.6228) grad_norm: 1.0269 (1.1233) time: 0.6178 [2021-03-26 12:33:20 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 180/1251] eta: 0:11:31 lr: 0.000896 loss: 3.6361 (3.6256) grad_norm: 1.0389 (1.1193) time: 0.6164 [2021-03-26 12:33:27 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 190/1251] eta: 0:11:23 lr: 0.000896 loss: 3.7409 (3.6245) grad_norm: 1.0837 (1.1176) time: 0.6209 [2021-03-26 12:33:33 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 200/1251] eta: 0:11:17 lr: 0.000896 loss: 3.6233 (3.6230) grad_norm: 1.0939 (1.1182) time: 0.6318 [2021-03-26 12:33:39 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 210/1251] eta: 0:11:10 lr: 0.000896 loss: 3.4287 (3.6179) grad_norm: 1.0966 (1.1183) time: 0.6382 [2021-03-26 12:33:46 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 220/1251] eta: 0:11:02 lr: 0.000896 loss: 3.4410 (3.6188) grad_norm: 1.0966 (1.1182) time: 0.6292 [2021-03-26 12:33:52 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 230/1251] eta: 0:10:56 lr: 0.000896 loss: 3.7185 (3.6229) grad_norm: 1.1369 (1.1193) time: 0.6300 [2021-03-26 12:33:58 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 240/1251] eta: 0:10:49 lr: 0.000896 loss: 3.7185 (3.6227) grad_norm: 1.1052 (1.1168) time: 0.6329 [2021-03-26 12:34:05 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 250/1251] eta: 0:10:42 lr: 0.000895 loss: 3.8628 (3.6286) grad_norm: 1.0434 (1.1149) time: 0.6371 [2021-03-26 12:34:11 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 260/1251] eta: 0:10:35 lr: 0.000895 loss: 3.7930 (3.6281) grad_norm: 1.0439 (1.1145) time: 0.6333 [2021-03-26 12:34:17 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 270/1251] eta: 0:10:29 lr: 0.000895 loss: 3.5681 (3.6238) grad_norm: 1.0850 (1.1142) time: 0.6289 [2021-03-26 12:34:24 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 280/1251] eta: 0:10:21 lr: 0.000895 loss: 3.4609 (3.6180) grad_norm: 1.0850 (1.1136) time: 0.6260 [2021-03-26 12:34:30 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 290/1251] eta: 0:10:15 lr: 0.000895 loss: 3.3536 (3.6096) grad_norm: 1.0648 (1.1112) time: 0.6246 [2021-03-26 12:34:36 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 300/1251] eta: 0:10:07 lr: 0.000895 loss: 3.4224 (3.6122) grad_norm: 1.0157 (1.1096) time: 0.6229 [2021-03-26 12:34:42 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 310/1251] eta: 0:10:01 lr: 0.000895 loss: 3.7352 (3.6111) grad_norm: 1.0204 (1.1067) time: 0.6209 [2021-03-26 12:34:48 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 320/1251] eta: 0:09:54 lr: 0.000895 loss: 3.6385 (3.6106) grad_norm: 1.0204 (1.1054) time: 0.6225 [2021-03-26 12:34:55 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 330/1251] eta: 0:09:47 lr: 0.000895 loss: 3.6385 (3.6044) grad_norm: 1.0130 (1.1036) time: 0.6187 [2021-03-26 12:35:01 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 340/1251] eta: 0:09:40 lr: 0.000895 loss: 3.7635 (3.6088) grad_norm: 1.0260 (1.1023) time: 0.6195 [2021-03-26 12:35:07 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 350/1251] eta: 0:09:33 lr: 0.000895 loss: 3.8323 (3.6137) grad_norm: 1.0781 (1.1034) time: 0.6207 [2021-03-26 12:35:13 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 360/1251] eta: 0:09:26 lr: 0.000895 loss: 3.9146 (3.6205) grad_norm: 1.0798 (1.1026) time: 0.6191 [2021-03-26 12:35:19 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 370/1251] eta: 0:09:20 lr: 0.000895 loss: 3.5859 (3.6213) grad_norm: 1.0320 (1.1011) time: 0.6184 [2021-03-26 12:35:26 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 380/1251] eta: 0:09:13 lr: 0.000895 loss: 3.6848 (3.6258) grad_norm: 1.0051 (1.0988) time: 0.6205 [2021-03-26 12:35:32 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 390/1251] eta: 0:09:06 lr: 0.000895 loss: 3.9496 (3.6296) grad_norm: 1.0554 (1.0986) time: 0.6248 [2021-03-26 12:35:38 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 400/1251] eta: 0:09:00 lr: 0.000895 loss: 3.6785 (3.6303) grad_norm: 1.0976 (1.1002) time: 0.6251 [2021-03-26 12:35:44 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 410/1251] eta: 0:08:53 lr: 0.000895 loss: 3.6874 (3.6350) grad_norm: 1.2187 (1.1049) time: 0.6234 [2021-03-26 12:35:51 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 420/1251] eta: 0:08:47 lr: 0.000895 loss: 3.8401 (3.6405) grad_norm: 1.1721 (1.1043) time: 0.6251 [2021-03-26 12:35:57 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 430/1251] eta: 0:08:40 lr: 0.000895 loss: 4.0542 (3.6465) grad_norm: 1.0239 (1.1050) time: 0.6255 [2021-03-26 12:36:03 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 440/1251] eta: 0:08:34 lr: 0.000895 loss: 4.0701 (3.6534) grad_norm: 1.1685 (1.1083) time: 0.6277 [2021-03-26 12:36:09 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 450/1251] eta: 0:08:27 lr: 0.000895 loss: 3.9088 (3.6515) grad_norm: 1.2537 (1.1109) time: 0.6267 [2021-03-26 12:36:16 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 460/1251] eta: 0:08:21 lr: 0.000895 loss: 3.7475 (3.6493) grad_norm: 1.1496 (1.1104) time: 0.6224 [2021-03-26 12:36:22 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 470/1251] eta: 0:08:14 lr: 0.000895 loss: 3.6015 (3.6459) grad_norm: 1.0668 (1.1098) time: 0.6218 [2021-03-26 12:36:28 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 480/1251] eta: 0:08:08 lr: 0.000895 loss: 3.6015 (3.6452) grad_norm: 1.0367 (1.1089) time: 0.6230 [2021-03-26 12:36:35 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 490/1251] eta: 0:08:01 lr: 0.000895 loss: 3.6805 (3.6455) grad_norm: 1.0469 (1.1100) time: 0.6294 [2021-03-26 12:36:41 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 500/1251] eta: 0:07:55 lr: 0.000895 loss: 3.8778 (3.6491) grad_norm: 1.1291 (1.1114) time: 0.6297 [2021-03-26 12:36:47 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 510/1251] eta: 0:07:48 lr: 0.000895 loss: 3.8778 (3.6479) grad_norm: 1.1520 (1.1118) time: 0.6249 [2021-03-26 12:36:53 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 520/1251] eta: 0:07:42 lr: 0.000895 loss: 3.5948 (3.6494) grad_norm: 1.1266 (1.1125) time: 0.6297 [2021-03-26 12:37:00 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 530/1251] eta: 0:07:36 lr: 0.000895 loss: 3.5948 (3.6520) grad_norm: 1.1090 (1.1130) time: 0.6290 [2021-03-26 12:37:06 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 540/1251] eta: 0:07:29 lr: 0.000895 loss: 3.6951 (3.6539) grad_norm: 1.1352 (1.1134) time: 0.6260 [2021-03-26 12:37:12 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 550/1251] eta: 0:07:23 lr: 0.000895 loss: 3.8860 (3.6601) grad_norm: 1.0426 (1.1121) time: 0.6374 [2021-03-26 12:37:19 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 560/1251] eta: 0:07:17 lr: 0.000895 loss: 3.9184 (3.6634) grad_norm: 1.0309 (1.1121) time: 0.6422 [2021-03-26 12:37:25 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 570/1251] eta: 0:07:10 lr: 0.000895 loss: 3.7167 (3.6592) grad_norm: 1.0442 (1.1118) time: 0.6328 [2021-03-26 12:37:31 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 580/1251] eta: 0:07:04 lr: 0.000895 loss: 3.4433 (3.6602) grad_norm: 1.0558 (1.1109) time: 0.6293 [2021-03-26 12:37:37 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 590/1251] eta: 0:06:58 lr: 0.000895 loss: 3.4375 (3.6559) grad_norm: 1.0756 (1.1112) time: 0.6242 [2021-03-26 12:37:44 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 600/1251] eta: 0:06:51 lr: 0.000895 loss: 3.4375 (3.6525) grad_norm: 1.1083 (1.1109) time: 0.6190 [2021-03-26 12:37:50 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 610/1251] eta: 0:06:45 lr: 0.000895 loss: 3.7253 (3.6544) grad_norm: 1.0971 (1.1108) time: 0.6187 [2021-03-26 12:37:56 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 620/1251] eta: 0:06:38 lr: 0.000895 loss: 3.9115 (3.6597) grad_norm: 1.0326 (1.1096) time: 0.6217 [2021-03-26 12:38:02 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 630/1251] eta: 0:06:32 lr: 0.000895 loss: 3.8978 (3.6598) grad_norm: 1.0268 (1.1083) time: 0.6231 [2021-03-26 12:38:09 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 640/1251] eta: 0:06:25 lr: 0.000894 loss: 3.6725 (3.6608) grad_norm: 1.0605 (1.1079) time: 0.6214 [2021-03-26 12:38:15 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 650/1251] eta: 0:06:19 lr: 0.000894 loss: 3.8039 (3.6631) grad_norm: 1.0025 (1.1062) time: 0.6199 [2021-03-26 12:38:21 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 660/1251] eta: 0:06:13 lr: 0.000894 loss: 3.7247 (3.6604) grad_norm: 0.9917 (1.1055) time: 0.6235 [2021-03-26 12:38:27 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 670/1251] eta: 0:06:06 lr: 0.000894 loss: 3.6625 (3.6648) grad_norm: 1.1102 (1.1063) time: 0.6229 [2021-03-26 12:38:33 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 680/1251] eta: 0:06:00 lr: 0.000894 loss: 3.8982 (3.6631) grad_norm: 1.0619 (1.1060) time: 0.6176 [2021-03-26 12:38:40 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 690/1251] eta: 0:05:53 lr: 0.000894 loss: 3.5287 (3.6598) grad_norm: 0.9834 (1.1048) time: 0.6200 [2021-03-26 12:38:46 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 700/1251] eta: 0:05:47 lr: 0.000894 loss: 3.7466 (3.6638) grad_norm: 1.0160 (1.1044) time: 0.6218 [2021-03-26 12:38:52 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 710/1251] eta: 0:05:41 lr: 0.000894 loss: 3.7466 (3.6639) grad_norm: 1.0892 (1.1043) time: 0.6225 [2021-03-26 12:38:58 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 720/1251] eta: 0:05:34 lr: 0.000894 loss: 3.5889 (3.6603) grad_norm: 1.0465 (1.1031) time: 0.6217 [2021-03-26 12:39:05 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 730/1251] eta: 0:05:28 lr: 0.000894 loss: 3.4969 (3.6570) grad_norm: 1.0168 (1.1023) time: 0.6244 [2021-03-26 12:39:11 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 740/1251] eta: 0:05:22 lr: 0.000894 loss: 3.4651 (3.6541) grad_norm: 1.0506 (1.1027) time: 0.6370 [2021-03-26 12:39:17 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 750/1251] eta: 0:05:16 lr: 0.000894 loss: 3.6401 (3.6576) grad_norm: 1.1632 (1.1043) time: 0.6433 [2021-03-26 12:39:24 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 760/1251] eta: 0:05:09 lr: 0.000894 loss: 3.7999 (3.6579) grad_norm: 1.1079 (1.1042) time: 0.6391 [2021-03-26 12:39:30 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 770/1251] eta: 0:05:03 lr: 0.000894 loss: 3.7999 (3.6581) grad_norm: 1.1080 (1.1055) time: 0.6382 [2021-03-26 12:39:36 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 780/1251] eta: 0:04:57 lr: 0.000894 loss: 3.5037 (3.6536) grad_norm: 1.1445 (1.1053) time: 0.6296 [2021-03-26 12:39:43 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 790/1251] eta: 0:04:50 lr: 0.000894 loss: 3.5037 (3.6538) grad_norm: 1.0727 (1.1051) time: 0.6241 [2021-03-26 12:39:49 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 800/1251] eta: 0:04:44 lr: 0.000894 loss: 3.6490 (3.6512) grad_norm: 1.1152 (1.1057) time: 0.6282 [2021-03-26 12:39:55 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 810/1251] eta: 0:04:38 lr: 0.000894 loss: 3.7868 (3.6524) grad_norm: 1.1153 (1.1058) time: 0.6264 [2021-03-26 12:40:02 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 820/1251] eta: 0:04:31 lr: 0.000894 loss: 3.7603 (3.6514) grad_norm: 1.0508 (1.1057) time: 0.6290 [2021-03-26 12:40:08 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 830/1251] eta: 0:04:25 lr: 0.000894 loss: 3.4600 (3.6485) grad_norm: 1.0736 (1.1059) time: 0.6323 [2021-03-26 12:40:14 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 840/1251] eta: 0:04:19 lr: 0.000894 loss: 3.7643 (3.6508) grad_norm: 1.1528 (1.1068) time: 0.6252 [2021-03-26 12:40:20 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 850/1251] eta: 0:04:12 lr: 0.000894 loss: 3.6428 (3.6477) grad_norm: 1.1420 (1.1067) time: 0.6201 [2021-03-26 12:40:27 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 860/1251] eta: 0:04:06 lr: 0.000894 loss: 3.5876 (3.6470) grad_norm: 1.0480 (1.1055) time: 0.6236 [2021-03-26 12:40:33 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 870/1251] eta: 0:04:00 lr: 0.000894 loss: 3.6479 (3.6477) grad_norm: 1.0170 (1.1049) time: 0.6262 [2021-03-26 12:40:39 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 880/1251] eta: 0:03:53 lr: 0.000894 loss: 3.6479 (3.6473) grad_norm: 1.0435 (1.1044) time: 0.6241 [2021-03-26 12:40:45 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 890/1251] eta: 0:03:47 lr: 0.000894 loss: 3.5285 (3.6451) grad_norm: 1.0424 (1.1041) time: 0.6225 [2021-03-26 12:40:52 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 900/1251] eta: 0:03:41 lr: 0.000894 loss: 3.5318 (3.6458) grad_norm: 1.1352 (1.1055) time: 0.6270 [2021-03-26 12:40:58 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 910/1251] eta: 0:03:34 lr: 0.000894 loss: 3.9164 (3.6455) grad_norm: 1.0729 (1.1042) time: 0.6258 [2021-03-26 12:41:04 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 920/1251] eta: 0:03:28 lr: 0.000894 loss: 3.5366 (3.6433) grad_norm: 1.0199 (1.1043) time: 0.6245 [2021-03-26 12:41:10 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 930/1251] eta: 0:03:22 lr: 0.000894 loss: 3.6005 (3.6465) grad_norm: 1.0430 (1.1039) time: 0.6314 [2021-03-26 12:41:17 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 940/1251] eta: 0:03:15 lr: 0.000894 loss: 3.7486 (3.6471) grad_norm: 1.0224 (1.1035) time: 0.6330 [2021-03-26 12:41:23 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 950/1251] eta: 0:03:09 lr: 0.000894 loss: 3.5466 (3.6468) grad_norm: 1.0487 (1.1037) time: 0.6299 [2021-03-26 12:41:29 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 960/1251] eta: 0:03:03 lr: 0.000894 loss: 3.3801 (3.6444) grad_norm: 1.0441 (1.1033) time: 0.6247 [2021-03-26 12:41:36 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 970/1251] eta: 0:02:57 lr: 0.000894 loss: 3.7573 (3.6458) grad_norm: 1.0407 (1.1033) time: 0.6263 [2021-03-26 12:41:42 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 980/1251] eta: 0:02:50 lr: 0.000894 loss: 3.7851 (3.6426) grad_norm: 1.0658 (1.1031) time: 0.6313 [2021-03-26 12:41:48 swin_base_patch4_window7_224] INFO: Epoch: [63] [ 990/1251] eta: 0:02:44 lr: 0.000894 loss: 3.5174 (3.6440) grad_norm: 1.1086 (1.1032) time: 0.6301 [2021-03-26 12:41:54 swin_base_patch4_window7_224] INFO: Epoch: [63] [1000/1251] eta: 0:02:38 lr: 0.000894 loss: 4.1567 (3.6500) grad_norm: 1.0774 (1.1029) time: 0.6210 [2021-03-26 12:42:00 swin_base_patch4_window7_224] INFO: Epoch: [63] [1010/1251] eta: 0:02:31 lr: 0.000894 loss: 3.9741 (3.6478) grad_norm: 1.0774 (1.1033) time: 0.6181 [2021-03-26 12:42:07 swin_base_patch4_window7_224] INFO: Epoch: [63] [1020/1251] eta: 0:02:25 lr: 0.000894 loss: 3.4062 (3.6477) grad_norm: 1.1566 (1.1036) time: 0.6200 [2021-03-26 12:42:13 swin_base_patch4_window7_224] INFO: Epoch: [63] [1030/1251] eta: 0:02:19 lr: 0.000893 loss: 3.4956 (3.6469) grad_norm: 1.1033 (1.1041) time: 0.6178 [2021-03-26 12:42:19 swin_base_patch4_window7_224] INFO: Epoch: [63] [1040/1251] eta: 0:02:12 lr: 0.000893 loss: 3.8663 (3.6482) grad_norm: 1.0442 (1.1035) time: 0.6184 [2021-03-26 12:42:25 swin_base_patch4_window7_224] INFO: Epoch: [63] [1050/1251] eta: 0:02:06 lr: 0.000893 loss: 3.8917 (3.6473) grad_norm: 1.0442 (1.1033) time: 0.6181 [2021-03-26 12:42:31 swin_base_patch4_window7_224] INFO: Epoch: [63] [1060/1251] eta: 0:02:00 lr: 0.000893 loss: 3.6138 (3.6467) grad_norm: 1.0730 (1.1038) time: 0.6228 [2021-03-26 12:42:38 swin_base_patch4_window7_224] INFO: Epoch: [63] [1070/1251] eta: 0:01:53 lr: 0.000893 loss: 3.5835 (3.6449) grad_norm: 1.0710 (1.1035) time: 0.6260 [2021-03-26 12:42:44 swin_base_patch4_window7_224] INFO: Epoch: [63] [1080/1251] eta: 0:01:47 lr: 0.000893 loss: 3.5855 (3.6454) grad_norm: 1.0648 (1.1037) time: 0.6287 [2021-03-26 12:42:50 swin_base_patch4_window7_224] INFO: Epoch: [63] [1090/1251] eta: 0:01:41 lr: 0.000893 loss: 3.6274 (3.6473) grad_norm: 1.0936 (1.1043) time: 0.6257 [2021-03-26 12:42:56 swin_base_patch4_window7_224] INFO: Epoch: [63] [1100/1251] eta: 0:01:35 lr: 0.000893 loss: 3.5264 (3.6442) grad_norm: 1.0871 (1.1038) time: 0.6208 [2021-03-26 12:43:03 swin_base_patch4_window7_224] INFO: Epoch: [63] [1110/1251] eta: 0:01:28 lr: 0.000893 loss: 3.5839 (3.6446) grad_norm: 1.0871 (1.1042) time: 0.6257 [2021-03-26 12:43:09 swin_base_patch4_window7_224] INFO: Epoch: [63] [1120/1251] eta: 0:01:22 lr: 0.000893 loss: 3.7695 (3.6454) grad_norm: 1.1593 (1.1049) time: 0.6315 [2021-03-26 12:43:15 swin_base_patch4_window7_224] INFO: Epoch: [63] [1130/1251] eta: 0:01:16 lr: 0.000893 loss: 3.7695 (3.6462) grad_norm: 1.1680 (1.1055) time: 0.6347 [2021-03-26 12:43:22 swin_base_patch4_window7_224] INFO: Epoch: [63] [1140/1251] eta: 0:01:09 lr: 0.000893 loss: 4.0065 (3.6488) grad_norm: 1.0626 (1.1049) time: 0.6306 [2021-03-26 12:43:28 swin_base_patch4_window7_224] INFO: Epoch: [63] [1150/1251] eta: 0:01:03 lr: 0.000893 loss: 3.8026 (3.6480) grad_norm: 1.0030 (1.1044) time: 0.6246 [2021-03-26 12:43:34 swin_base_patch4_window7_224] INFO: Epoch: [63] [1160/1251] eta: 0:00:57 lr: 0.000893 loss: 3.7073 (3.6497) grad_norm: 1.0890 (1.1054) time: 0.6289 [2021-03-26 12:43:40 swin_base_patch4_window7_224] INFO: Epoch: [63] [1170/1251] eta: 0:00:50 lr: 0.000893 loss: 3.8673 (3.6504) grad_norm: 1.0964 (1.1055) time: 0.6263 [2021-03-26 12:43:47 swin_base_patch4_window7_224] INFO: Epoch: [63] [1180/1251] eta: 0:00:44 lr: 0.000893 loss: 3.8770 (3.6504) grad_norm: 1.0606 (1.1052) time: 0.6200 [2021-03-26 12:43:53 swin_base_patch4_window7_224] INFO: Epoch: [63] [1190/1251] eta: 0:00:38 lr: 0.000893 loss: 3.8770 (3.6517) grad_norm: 1.0783 (1.1060) time: 0.6252 [2021-03-26 12:43:59 swin_base_patch4_window7_224] INFO: Epoch: [63] [1200/1251] eta: 0:00:32 lr: 0.000893 loss: 3.6430 (3.6504) grad_norm: 1.0855 (1.1066) time: 0.6259 [2021-03-26 12:44:05 swin_base_patch4_window7_224] INFO: Epoch: [63] [1210/1251] eta: 0:00:25 lr: 0.000893 loss: 3.7785 (3.6523) grad_norm: 1.0603 (1.1071) time: 0.6236 [2021-03-26 12:44:12 swin_base_patch4_window7_224] INFO: Epoch: [63] [1220/1251] eta: 0:00:19 lr: 0.000893 loss: 3.6282 (3.6488) grad_norm: 1.0812 (1.1072) time: 0.6209 [2021-03-26 12:44:18 swin_base_patch4_window7_224] INFO: Epoch: [63] [1230/1251] eta: 0:00:13 lr: 0.000893 loss: 3.4383 (3.6492) grad_norm: 1.1463 (1.1076) time: 0.6225 [2021-03-26 12:44:24 swin_base_patch4_window7_224] INFO: Epoch: [63] [1240/1251] eta: 0:00:06 lr: 0.000893 loss: 3.7248 (3.6489) grad_norm: 1.1038 (1.1075) time: 0.6226 [2021-03-26 12:44:30 swin_base_patch4_window7_224] INFO: Epoch: [63] [1250/1251] eta: 0:00:00 lr: 0.000893 loss: 3.5002 (3.6470) grad_norm: 1.1366 (1.1076) time: 0.6139 [2021-03-26 12:44:36 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:07 loss: 0.8769 (0.8769) acc1: 76.5625 (76.5625) acc5: 96.8750 (96.8750) [2021-03-26 12:44:38 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.0330 (1.0835) acc1: 75.0000 (74.8580) acc5: 93.7500 (93.4659) [2021-03-26 12:44:40 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.0796 (1.0996) acc1: 75.0000 (74.3304) acc5: 92.1875 (93.0804) [2021-03-26 12:44:41 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1770 (1.1310) acc1: 73.4375 (73.3871) acc5: 92.1875 (92.5907) [2021-03-26 12:44:43 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1403 (1.1172) acc1: 73.4375 (73.7424) acc5: 93.7500 (92.7973) [2021-03-26 12:44:45 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1287 (1.1291) acc1: 73.4375 (73.6960) acc5: 92.1875 (92.4480) [2021-03-26 12:44:50 swin_base_patch4_window7_224] INFO: * Acc@1 74.280 Acc@5 92.570 loss 1.110 [2021-03-26 12:44:50 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.3% [2021-03-26 12:44:50 swin_base_patch4_window7_224] INFO: Max accuracy: 74.28% [2021-03-26 12:44:54 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 0/1251] eta: 1:28:51 lr: 0.000893 loss: 3.8424 (3.8424) grad_norm: 1.0774 (1.0774) time: 4.2614 [2021-03-26 12:45:01 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 10/1251] eta: 0:20:11 lr: 0.000893 loss: 4.1032 (3.9422) grad_norm: 1.0268 (1.0239) time: 0.9765 [2021-03-26 12:45:07 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 20/1251] eta: 0:16:40 lr: 0.000893 loss: 3.7366 (3.7695) grad_norm: 1.0674 (1.0857) time: 0.6403 [2021-03-26 12:45:13 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 30/1251] eta: 0:15:15 lr: 0.000893 loss: 3.5666 (3.7241) grad_norm: 1.0718 (1.0695) time: 0.6254 [2021-03-26 12:45:19 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 40/1251] eta: 0:14:30 lr: 0.000893 loss: 3.2002 (3.6076) grad_norm: 1.0481 (1.0824) time: 0.6209 [2021-03-26 12:45:26 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 50/1251] eta: 0:14:01 lr: 0.000893 loss: 3.4818 (3.6619) grad_norm: 1.1630 (1.1079) time: 0.6233 [2021-03-26 12:45:32 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 60/1251] eta: 0:13:39 lr: 0.000893 loss: 3.7533 (3.6828) grad_norm: 1.0969 (1.0981) time: 0.6254 [2021-03-26 12:45:38 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 70/1251] eta: 0:13:21 lr: 0.000893 loss: 3.7533 (3.6778) grad_norm: 1.0785 (1.0935) time: 0.6247 [2021-03-26 12:45:44 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 80/1251] eta: 0:13:06 lr: 0.000893 loss: 3.4916 (3.6701) grad_norm: 1.0377 (1.0859) time: 0.6213 [2021-03-26 12:45:51 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 90/1251] eta: 0:12:54 lr: 0.000893 loss: 3.4100 (3.6456) grad_norm: 1.0377 (1.0863) time: 0.6261 [2021-03-26 12:45:57 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 100/1251] eta: 0:12:43 lr: 0.000893 loss: 3.7995 (3.6601) grad_norm: 1.1213 (1.1103) time: 0.6280 [2021-03-26 12:46:03 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 110/1251] eta: 0:12:34 lr: 0.000893 loss: 3.5511 (3.6166) grad_norm: 1.1213 (1.1109) time: 0.6351 [2021-03-26 12:46:10 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 120/1251] eta: 0:12:25 lr: 0.000893 loss: 3.1344 (3.6078) grad_norm: 1.0852 (1.1120) time: 0.6377 [2021-03-26 12:46:16 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 130/1251] eta: 0:12:16 lr: 0.000893 loss: 3.5165 (3.6027) grad_norm: 1.0566 (1.1061) time: 0.6332 [2021-03-26 12:46:22 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 140/1251] eta: 0:12:06 lr: 0.000893 loss: 3.6703 (3.6083) grad_norm: 1.0330 (1.0992) time: 0.6252 [2021-03-26 12:46:28 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 150/1251] eta: 0:11:57 lr: 0.000893 loss: 3.7782 (3.6134) grad_norm: 1.0476 (1.1023) time: 0.6160 [2021-03-26 12:46:35 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 160/1251] eta: 0:11:49 lr: 0.000893 loss: 3.8827 (3.6222) grad_norm: 1.0676 (1.1016) time: 0.6247 [2021-03-26 12:46:41 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 170/1251] eta: 0:11:41 lr: 0.000892 loss: 3.9197 (3.6296) grad_norm: 1.0676 (1.0982) time: 0.6265 [2021-03-26 12:46:47 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 180/1251] eta: 0:11:33 lr: 0.000892 loss: 3.9436 (3.6342) grad_norm: 1.0695 (1.0966) time: 0.6235 [2021-03-26 12:46:53 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 190/1251] eta: 0:11:25 lr: 0.000892 loss: 3.8809 (3.6397) grad_norm: 1.0884 (1.0977) time: 0.6249 [2021-03-26 12:47:00 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 200/1251] eta: 0:11:19 lr: 0.000892 loss: 3.6027 (3.6498) grad_norm: 1.0884 (1.1014) time: 0.6362 [2021-03-26 12:47:06 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 210/1251] eta: 0:11:12 lr: 0.000892 loss: 3.6027 (3.6489) grad_norm: 1.0857 (1.1023) time: 0.6384 [2021-03-26 12:47:12 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 220/1251] eta: 0:11:04 lr: 0.000892 loss: 3.8019 (3.6518) grad_norm: 1.0708 (1.1014) time: 0.6295 [2021-03-26 12:47:19 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 230/1251] eta: 0:10:57 lr: 0.000892 loss: 3.6072 (3.6459) grad_norm: 1.0668 (1.0996) time: 0.6251 [2021-03-26 12:47:25 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 240/1251] eta: 0:10:50 lr: 0.000892 loss: 3.6342 (3.6539) grad_norm: 1.0167 (1.1004) time: 0.6235 [2021-03-26 12:47:31 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 250/1251] eta: 0:10:42 lr: 0.000892 loss: 3.8116 (3.6520) grad_norm: 1.0717 (1.1012) time: 0.6252 [2021-03-26 12:47:37 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 260/1251] eta: 0:10:36 lr: 0.000892 loss: 3.7290 (3.6543) grad_norm: 1.0717 (1.1014) time: 0.6264 [2021-03-26 12:47:44 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 270/1251] eta: 0:10:29 lr: 0.000892 loss: 3.8838 (3.6668) grad_norm: 1.0280 (1.1008) time: 0.6280 [2021-03-26 12:47:50 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 280/1251] eta: 0:10:22 lr: 0.000892 loss: 3.9192 (3.6645) grad_norm: 1.0509 (1.1037) time: 0.6284 [2021-03-26 12:47:56 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 290/1251] eta: 0:10:15 lr: 0.000892 loss: 3.7228 (3.6566) grad_norm: 1.1137 (1.1043) time: 0.6324 [2021-03-26 12:48:03 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 300/1251] eta: 0:10:08 lr: 0.000892 loss: 3.3991 (3.6469) grad_norm: 1.1137 (1.1055) time: 0.6312 [2021-03-26 12:48:09 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 310/1251] eta: 0:10:02 lr: 0.000892 loss: 3.3720 (3.6472) grad_norm: 1.1056 (1.1055) time: 0.6277 [2021-03-26 12:48:15 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 320/1251] eta: 0:09:55 lr: 0.000892 loss: 3.4760 (3.6507) grad_norm: 1.0962 (1.1074) time: 0.6283 [2021-03-26 12:48:21 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 330/1251] eta: 0:09:48 lr: 0.000892 loss: 3.9239 (3.6621) grad_norm: 1.0931 (1.1066) time: 0.6251 [2021-03-26 12:48:28 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 340/1251] eta: 0:09:41 lr: 0.000892 loss: 3.9142 (3.6581) grad_norm: 1.0400 (1.1054) time: 0.6232 [2021-03-26 12:48:34 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 350/1251] eta: 0:09:35 lr: 0.000892 loss: 3.6990 (3.6622) grad_norm: 1.0811 (1.1059) time: 0.6265 [2021-03-26 12:48:40 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 360/1251] eta: 0:09:28 lr: 0.000892 loss: 3.6871 (3.6597) grad_norm: 1.0863 (1.1049) time: 0.6246 [2021-03-26 12:48:46 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 370/1251] eta: 0:09:21 lr: 0.000892 loss: 3.6634 (3.6585) grad_norm: 1.0392 (1.1034) time: 0.6238 [2021-03-26 12:48:53 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 380/1251] eta: 0:09:14 lr: 0.000892 loss: 3.6382 (3.6568) grad_norm: 1.0470 (1.1049) time: 0.6274 [2021-03-26 12:48:59 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 390/1251] eta: 0:09:08 lr: 0.000892 loss: 3.5962 (3.6559) grad_norm: 1.0470 (1.1043) time: 0.6237 [2021-03-26 12:49:05 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 400/1251] eta: 0:09:01 lr: 0.000892 loss: 3.5368 (3.6527) grad_norm: 1.0663 (1.1039) time: 0.6226 [2021-03-26 12:49:11 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 410/1251] eta: 0:08:55 lr: 0.000892 loss: 3.5620 (3.6534) grad_norm: 1.1205 (1.1048) time: 0.6263 [2021-03-26 12:49:18 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 420/1251] eta: 0:08:48 lr: 0.000892 loss: 3.5704 (3.6474) grad_norm: 1.1550 (1.1064) time: 0.6337 [2021-03-26 12:49:24 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 430/1251] eta: 0:08:42 lr: 0.000892 loss: 3.6817 (3.6477) grad_norm: 1.1309 (1.1083) time: 0.6358 [2021-03-26 12:49:30 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 440/1251] eta: 0:08:35 lr: 0.000892 loss: 3.6169 (3.6459) grad_norm: 1.0951 (1.1076) time: 0.6237 [2021-03-26 12:49:37 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 450/1251] eta: 0:08:29 lr: 0.000892 loss: 3.6169 (3.6476) grad_norm: 1.0562 (1.1086) time: 0.6253 [2021-03-26 12:49:43 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 460/1251] eta: 0:08:22 lr: 0.000892 loss: 3.8427 (3.6518) grad_norm: 1.1599 (1.1131) time: 0.6348 [2021-03-26 12:49:49 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 470/1251] eta: 0:08:16 lr: 0.000892 loss: 3.8928 (3.6552) grad_norm: 1.1425 (1.1124) time: 0.6308 [2021-03-26 12:49:55 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 480/1251] eta: 0:08:09 lr: 0.000892 loss: 3.7540 (3.6511) grad_norm: 1.0445 (1.1112) time: 0.6234 [2021-03-26 12:50:02 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 490/1251] eta: 0:08:03 lr: 0.000892 loss: 3.5857 (3.6489) grad_norm: 1.0367 (1.1097) time: 0.6235 [2021-03-26 12:50:08 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 500/1251] eta: 0:07:56 lr: 0.000892 loss: 3.7688 (3.6528) grad_norm: 1.0367 (1.1096) time: 0.6319 [2021-03-26 12:50:14 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 510/1251] eta: 0:07:50 lr: 0.000892 loss: 3.8382 (3.6534) grad_norm: 1.0557 (1.1090) time: 0.6310 [2021-03-26 12:50:21 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 520/1251] eta: 0:07:44 lr: 0.000892 loss: 3.8995 (3.6581) grad_norm: 1.0557 (1.1090) time: 0.6360 [2021-03-26 12:50:27 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 530/1251] eta: 0:07:37 lr: 0.000892 loss: 3.9445 (3.6583) grad_norm: 1.0898 (1.1088) time: 0.6397 [2021-03-26 12:50:33 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 540/1251] eta: 0:07:31 lr: 0.000892 loss: 3.9025 (3.6582) grad_norm: 1.1004 (1.1094) time: 0.6296 [2021-03-26 12:50:40 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 550/1251] eta: 0:07:25 lr: 0.000892 loss: 3.7939 (3.6591) grad_norm: 1.1117 (1.1095) time: 0.6414 [2021-03-26 12:50:46 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 560/1251] eta: 0:07:18 lr: 0.000891 loss: 3.9261 (3.6600) grad_norm: 1.0943 (1.1110) time: 0.6432 [2021-03-26 12:50:52 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 570/1251] eta: 0:07:12 lr: 0.000891 loss: 3.8862 (3.6558) grad_norm: 1.0210 (1.1095) time: 0.6228 [2021-03-26 12:50:59 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 580/1251] eta: 0:07:05 lr: 0.000891 loss: 3.6326 (3.6564) grad_norm: 1.0210 (1.1087) time: 0.6208 [2021-03-26 12:51:05 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 590/1251] eta: 0:06:59 lr: 0.000891 loss: 3.7979 (3.6574) grad_norm: 1.0802 (1.1089) time: 0.6249 [2021-03-26 12:51:11 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 600/1251] eta: 0:06:52 lr: 0.000891 loss: 3.8157 (3.6572) grad_norm: 1.0970 (1.1101) time: 0.6254 [2021-03-26 12:51:17 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 610/1251] eta: 0:06:46 lr: 0.000891 loss: 3.8076 (3.6568) grad_norm: 1.0836 (1.1092) time: 0.6250 [2021-03-26 12:51:24 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 620/1251] eta: 0:06:40 lr: 0.000891 loss: 3.8076 (3.6582) grad_norm: 1.1025 (1.1099) time: 0.6258 [2021-03-26 12:51:30 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 630/1251] eta: 0:06:33 lr: 0.000891 loss: 3.6604 (3.6590) grad_norm: 1.0173 (1.1084) time: 0.6233 [2021-03-26 12:51:36 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 640/1251] eta: 0:06:27 lr: 0.000891 loss: 3.6604 (3.6555) grad_norm: 1.0165 (1.1075) time: 0.6223 [2021-03-26 12:51:43 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 650/1251] eta: 0:06:20 lr: 0.000891 loss: 3.4394 (3.6529) grad_norm: 1.0228 (1.1066) time: 0.6310 [2021-03-26 12:51:49 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 660/1251] eta: 0:06:14 lr: 0.000891 loss: 3.7654 (3.6535) grad_norm: 1.0622 (1.1071) time: 0.6325 [2021-03-26 12:51:55 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 670/1251] eta: 0:06:08 lr: 0.000891 loss: 3.7654 (3.6542) grad_norm: 1.1107 (1.1073) time: 0.6299 [2021-03-26 12:52:01 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 680/1251] eta: 0:06:01 lr: 0.000891 loss: 3.6541 (3.6551) grad_norm: 1.0939 (1.1077) time: 0.6269 [2021-03-26 12:52:08 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 690/1251] eta: 0:05:55 lr: 0.000891 loss: 3.7456 (3.6562) grad_norm: 1.1255 (1.1084) time: 0.6264 [2021-03-26 12:52:14 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 700/1251] eta: 0:05:48 lr: 0.000891 loss: 3.7464 (3.6538) grad_norm: 1.0995 (1.1086) time: 0.6278 [2021-03-26 12:52:20 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 710/1251] eta: 0:05:42 lr: 0.000891 loss: 3.4837 (3.6517) grad_norm: 1.0756 (1.1091) time: 0.6266 [2021-03-26 12:52:26 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 720/1251] eta: 0:05:36 lr: 0.000891 loss: 3.4837 (3.6528) grad_norm: 1.0758 (1.1088) time: 0.6221 [2021-03-26 12:52:33 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 730/1251] eta: 0:05:29 lr: 0.000891 loss: 3.6090 (3.6510) grad_norm: 1.0679 (1.1082) time: 0.6265 [2021-03-26 12:52:39 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 740/1251] eta: 0:05:23 lr: 0.000891 loss: 3.7732 (3.6528) grad_norm: 1.0367 (1.1083) time: 0.6344 [2021-03-26 12:52:45 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 750/1251] eta: 0:05:17 lr: 0.000891 loss: 3.7732 (3.6560) grad_norm: 1.0961 (1.1092) time: 0.6311 [2021-03-26 12:52:52 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 760/1251] eta: 0:05:10 lr: 0.000891 loss: 3.6635 (3.6563) grad_norm: 1.1089 (1.1093) time: 0.6394 [2021-03-26 12:52:58 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 770/1251] eta: 0:05:04 lr: 0.000891 loss: 3.6635 (3.6558) grad_norm: 1.0552 (1.1084) time: 0.6362 [2021-03-26 12:53:04 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 780/1251] eta: 0:04:58 lr: 0.000891 loss: 3.6275 (3.6566) grad_norm: 1.0552 (1.1088) time: 0.6247 [2021-03-26 12:53:11 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 790/1251] eta: 0:04:51 lr: 0.000891 loss: 3.8042 (3.6596) grad_norm: 1.1067 (1.1088) time: 0.6301 [2021-03-26 12:53:17 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 800/1251] eta: 0:04:45 lr: 0.000891 loss: 3.9217 (3.6609) grad_norm: 1.1001 (1.1084) time: 0.6436 [2021-03-26 12:53:23 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 810/1251] eta: 0:04:39 lr: 0.000891 loss: 3.8013 (3.6594) grad_norm: 1.0569 (1.1076) time: 0.6367 [2021-03-26 12:53:30 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 820/1251] eta: 0:04:32 lr: 0.000891 loss: 3.6235 (3.6594) grad_norm: 1.0569 (1.1081) time: 0.6244 [2021-03-26 12:53:36 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 830/1251] eta: 0:04:26 lr: 0.000891 loss: 3.8356 (3.6621) grad_norm: 1.1695 (1.1097) time: 0.6288 [2021-03-26 12:53:42 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 840/1251] eta: 0:04:20 lr: 0.000891 loss: 3.8608 (3.6643) grad_norm: 1.1485 (1.1098) time: 0.6257 [2021-03-26 12:53:48 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 850/1251] eta: 0:04:13 lr: 0.000891 loss: 3.6221 (3.6618) grad_norm: 1.0920 (1.1103) time: 0.6204 [2021-03-26 12:53:55 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 860/1251] eta: 0:04:07 lr: 0.000891 loss: 3.7226 (3.6637) grad_norm: 1.1102 (1.1103) time: 0.6282 [2021-03-26 12:54:01 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 870/1251] eta: 0:04:01 lr: 0.000891 loss: 3.8545 (3.6658) grad_norm: 1.0851 (1.1095) time: 0.6348 [2021-03-26 12:54:07 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 880/1251] eta: 0:03:54 lr: 0.000891 loss: 3.8545 (3.6651) grad_norm: 1.0920 (1.1103) time: 0.6282 [2021-03-26 12:54:14 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 890/1251] eta: 0:03:48 lr: 0.000891 loss: 3.8358 (3.6669) grad_norm: 1.1284 (1.1112) time: 0.6216 [2021-03-26 12:54:20 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 900/1251] eta: 0:03:42 lr: 0.000891 loss: 3.7269 (3.6670) grad_norm: 1.1284 (1.1118) time: 0.6255 [2021-03-26 12:54:26 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 910/1251] eta: 0:03:35 lr: 0.000891 loss: 3.8274 (3.6689) grad_norm: 1.0645 (1.1117) time: 0.6300 [2021-03-26 12:54:32 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 920/1251] eta: 0:03:29 lr: 0.000891 loss: 3.8280 (3.6693) grad_norm: 1.0513 (1.1121) time: 0.6257 [2021-03-26 12:54:39 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 930/1251] eta: 0:03:23 lr: 0.000891 loss: 3.8566 (3.6718) grad_norm: 1.0795 (1.1117) time: 0.6325 [2021-03-26 12:54:45 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 940/1251] eta: 0:03:16 lr: 0.000890 loss: 3.9127 (3.6732) grad_norm: 1.0795 (1.1113) time: 0.6373 [2021-03-26 12:54:51 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 950/1251] eta: 0:03:10 lr: 0.000890 loss: 3.7979 (3.6749) grad_norm: 1.1027 (1.1113) time: 0.6320 [2021-03-26 12:54:58 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 960/1251] eta: 0:03:03 lr: 0.000890 loss: 3.7604 (3.6720) grad_norm: 1.0697 (1.1107) time: 0.6208 [2021-03-26 12:55:04 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 970/1251] eta: 0:02:57 lr: 0.000890 loss: 3.4777 (3.6701) grad_norm: 1.1354 (1.1118) time: 0.6223 [2021-03-26 12:55:10 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 980/1251] eta: 0:02:51 lr: 0.000890 loss: 3.6737 (3.6718) grad_norm: 1.1354 (1.1113) time: 0.6242 [2021-03-26 12:55:16 swin_base_patch4_window7_224] INFO: Epoch: [64] [ 990/1251] eta: 0:02:44 lr: 0.000890 loss: 3.6737 (3.6698) grad_norm: 1.0396 (1.1115) time: 0.6199 [2021-03-26 12:55:23 swin_base_patch4_window7_224] INFO: Epoch: [64] [1000/1251] eta: 0:02:38 lr: 0.000890 loss: 3.5390 (3.6685) grad_norm: 1.0984 (1.1120) time: 0.6291 [2021-03-26 12:55:29 swin_base_patch4_window7_224] INFO: Epoch: [64] [1010/1251] eta: 0:02:32 lr: 0.000890 loss: 3.7886 (3.6697) grad_norm: 1.1088 (1.1119) time: 0.6300 [2021-03-26 12:55:35 swin_base_patch4_window7_224] INFO: Epoch: [64] [1020/1251] eta: 0:02:25 lr: 0.000890 loss: 3.7937 (3.6688) grad_norm: 1.0989 (1.1117) time: 0.6229 [2021-03-26 12:55:41 swin_base_patch4_window7_224] INFO: Epoch: [64] [1030/1251] eta: 0:02:19 lr: 0.000890 loss: 3.6360 (3.6669) grad_norm: 1.0501 (1.1113) time: 0.6259 [2021-03-26 12:55:48 swin_base_patch4_window7_224] INFO: Epoch: [64] [1040/1251] eta: 0:02:13 lr: 0.000890 loss: 3.6360 (3.6662) grad_norm: 1.0456 (1.1109) time: 0.6289 [2021-03-26 12:55:54 swin_base_patch4_window7_224] INFO: Epoch: [64] [1050/1251] eta: 0:02:06 lr: 0.000890 loss: 3.7128 (3.6645) grad_norm: 1.1082 (1.1118) time: 0.6262 [2021-03-26 12:56:00 swin_base_patch4_window7_224] INFO: Epoch: [64] [1060/1251] eta: 0:02:00 lr: 0.000890 loss: 3.7128 (3.6651) grad_norm: 1.1308 (1.1122) time: 0.6238 [2021-03-26 12:56:07 swin_base_patch4_window7_224] INFO: Epoch: [64] [1070/1251] eta: 0:01:54 lr: 0.000890 loss: 3.6606 (3.6640) grad_norm: 1.1308 (1.1135) time: 0.6285 [2021-03-26 12:56:13 swin_base_patch4_window7_224] INFO: Epoch: [64] [1080/1251] eta: 0:01:48 lr: 0.000890 loss: 3.6558 (3.6621) grad_norm: 1.1433 (1.1136) time: 0.6369 [2021-03-26 12:56:19 swin_base_patch4_window7_224] INFO: Epoch: [64] [1090/1251] eta: 0:01:41 lr: 0.000890 loss: 3.7223 (3.6649) grad_norm: 1.1542 (1.1144) time: 0.6305 [2021-03-26 12:56:25 swin_base_patch4_window7_224] INFO: Epoch: [64] [1100/1251] eta: 0:01:35 lr: 0.000890 loss: 3.9341 (3.6642) grad_norm: 1.1465 (1.1149) time: 0.6219 [2021-03-26 12:56:32 swin_base_patch4_window7_224] INFO: Epoch: [64] [1110/1251] eta: 0:01:29 lr: 0.000890 loss: 3.6418 (3.6658) grad_norm: 1.0210 (1.1136) time: 0.6224 [2021-03-26 12:56:38 swin_base_patch4_window7_224] INFO: Epoch: [64] [1120/1251] eta: 0:01:22 lr: 0.000890 loss: 3.7644 (3.6666) grad_norm: 1.0407 (1.1149) time: 0.6259 [2021-03-26 12:56:44 swin_base_patch4_window7_224] INFO: Epoch: [64] [1130/1251] eta: 0:01:16 lr: 0.000890 loss: 3.5928 (3.6661) grad_norm: 1.1436 (1.1149) time: 0.6240 [2021-03-26 12:56:50 swin_base_patch4_window7_224] INFO: Epoch: [64] [1140/1251] eta: 0:01:10 lr: 0.000890 loss: 3.5928 (3.6651) grad_norm: 1.0766 (1.1146) time: 0.6209 [2021-03-26 12:56:57 swin_base_patch4_window7_224] INFO: Epoch: [64] [1150/1251] eta: 0:01:03 lr: 0.000890 loss: 3.7199 (3.6651) grad_norm: 1.0618 (1.1138) time: 0.6266 [2021-03-26 12:57:03 swin_base_patch4_window7_224] INFO: Epoch: [64] [1160/1251] eta: 0:00:57 lr: 0.000890 loss: 3.6418 (3.6619) grad_norm: 1.0618 (1.1138) time: 0.6282 [2021-03-26 12:57:09 swin_base_patch4_window7_224] INFO: Epoch: [64] [1170/1251] eta: 0:00:51 lr: 0.000890 loss: 3.6418 (3.6632) grad_norm: 1.1252 (1.1145) time: 0.6234 [2021-03-26 12:57:15 swin_base_patch4_window7_224] INFO: Epoch: [64] [1180/1251] eta: 0:00:44 lr: 0.000890 loss: 3.6726 (3.6624) grad_norm: 1.1092 (1.1142) time: 0.6202 [2021-03-26 12:57:21 swin_base_patch4_window7_224] INFO: Epoch: [64] [1190/1251] eta: 0:00:38 lr: 0.000890 loss: 3.4698 (3.6607) grad_norm: 1.1172 (inf) time: 0.6191 [2021-03-26 12:57:28 swin_base_patch4_window7_224] INFO: Epoch: [64] [1200/1251] eta: 0:00:32 lr: 0.000890 loss: 3.7257 (3.6617) grad_norm: 1.2429 (inf) time: 0.6247 [2021-03-26 12:57:34 swin_base_patch4_window7_224] INFO: Epoch: [64] [1210/1251] eta: 0:00:25 lr: 0.000890 loss: 3.5765 (3.6590) grad_norm: 1.2288 (inf) time: 0.6307 [2021-03-26 12:57:40 swin_base_patch4_window7_224] INFO: Epoch: [64] [1220/1251] eta: 0:00:19 lr: 0.000890 loss: 3.4970 (3.6581) grad_norm: 1.0608 (inf) time: 0.6280 [2021-03-26 12:57:47 swin_base_patch4_window7_224] INFO: Epoch: [64] [1230/1251] eta: 0:00:13 lr: 0.000890 loss: 3.8537 (3.6604) grad_norm: 1.0498 (inf) time: 0.6262 [2021-03-26 12:57:53 swin_base_patch4_window7_224] INFO: Epoch: [64] [1240/1251] eta: 0:00:06 lr: 0.000890 loss: 3.7758 (3.6574) grad_norm: 1.1129 (inf) time: 0.6238 [2021-03-26 12:57:59 swin_base_patch4_window7_224] INFO: Epoch: [64] [1250/1251] eta: 0:00:00 lr: 0.000890 loss: 3.4489 (3.6568) grad_norm: 1.0894 (inf) time: 0.6185 [2021-03-26 12:58:06 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:19 loss: 0.8451 (0.8451) acc1: 76.5625 (76.5625) acc5: 96.8750 (96.8750) [2021-03-26 12:58:08 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0286 (1.0024) acc1: 73.4375 (74.5739) acc5: 92.1875 (93.3239) [2021-03-26 12:58:10 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0448 (1.0404) acc1: 71.8750 (73.8095) acc5: 92.1875 (93.0060) [2021-03-26 12:58:12 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1506 (1.0676) acc1: 71.8750 (73.4375) acc5: 92.1875 (92.4395) [2021-03-26 12:58:14 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1506 (1.0570) acc1: 73.4375 (73.9710) acc5: 92.1875 (92.9116) [2021-03-26 12:58:15 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0360 (1.0681) acc1: 75.0000 (73.7280) acc5: 93.7500 (92.8960) [2021-03-26 12:58:20 swin_base_patch4_window7_224] INFO: * Acc@1 74.572 Acc@5 92.620 loss 1.070 [2021-03-26 12:58:20 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.6% [2021-03-26 12:58:20 swin_base_patch4_window7_224] INFO: Max accuracy: 74.57% [2021-03-26 12:58:24 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 0/1251] eta: 1:23:59 lr: 0.000890 loss: 3.0599 (3.0599) grad_norm: 0.9851 (0.9851) time: 4.0286 [2021-03-26 12:58:31 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 10/1251] eta: 0:19:37 lr: 0.000890 loss: 3.9220 (3.6221) grad_norm: 1.0673 (1.1515) time: 0.9487 [2021-03-26 12:58:37 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 20/1251] eta: 0:16:20 lr: 0.000890 loss: 3.7721 (3.6023) grad_norm: 1.0909 (1.1200) time: 0.6348 [2021-03-26 12:58:43 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 30/1251] eta: 0:15:06 lr: 0.000890 loss: 3.6928 (3.6478) grad_norm: 1.1249 (1.1558) time: 0.6291 [2021-03-26 12:58:50 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 40/1251] eta: 0:14:24 lr: 0.000890 loss: 3.6943 (3.6435) grad_norm: 1.1590 (1.1568) time: 0.6279 [2021-03-26 12:58:56 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 50/1251] eta: 0:14:00 lr: 0.000890 loss: 3.7390 (3.6680) grad_norm: 1.1183 (1.1540) time: 0.6341 [2021-03-26 12:59:02 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 60/1251] eta: 0:13:37 lr: 0.000890 loss: 3.9769 (3.6815) grad_norm: 1.0649 (1.1496) time: 0.6303 [2021-03-26 12:59:08 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 70/1251] eta: 0:13:21 lr: 0.000890 loss: 3.8964 (3.6854) grad_norm: 1.0914 (1.1461) time: 0.6248 [2021-03-26 12:59:15 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 80/1251] eta: 0:13:07 lr: 0.000889 loss: 3.7453 (3.6556) grad_norm: 1.1158 (1.1461) time: 0.6303 [2021-03-26 12:59:21 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 90/1251] eta: 0:12:56 lr: 0.000889 loss: 3.6328 (3.6331) grad_norm: 1.0677 (1.1443) time: 0.6345 [2021-03-26 12:59:27 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 100/1251] eta: 0:12:45 lr: 0.000889 loss: 3.6328 (3.6171) grad_norm: 1.0709 (1.1440) time: 0.6338 [2021-03-26 12:59:34 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 110/1251] eta: 0:12:34 lr: 0.000889 loss: 3.6137 (3.6062) grad_norm: 1.0709 (1.1403) time: 0.6271 [2021-03-26 12:59:40 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 120/1251] eta: 0:12:24 lr: 0.000889 loss: 3.5017 (3.5948) grad_norm: 1.0481 (1.1331) time: 0.6251 [2021-03-26 12:59:46 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 130/1251] eta: 0:12:15 lr: 0.000889 loss: 3.4960 (3.5954) grad_norm: 1.0704 (1.1342) time: 0.6252 [2021-03-26 12:59:52 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 140/1251] eta: 0:12:05 lr: 0.000889 loss: 3.6662 (3.6136) grad_norm: 1.0992 (1.1339) time: 0.6222 [2021-03-26 12:59:59 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 150/1251] eta: 0:11:57 lr: 0.000889 loss: 3.9255 (3.6287) grad_norm: 1.1356 (1.1323) time: 0.6245 [2021-03-26 13:00:05 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 160/1251] eta: 0:11:49 lr: 0.000889 loss: 3.7727 (3.6294) grad_norm: 1.1132 (1.1318) time: 0.6272 [2021-03-26 13:00:11 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 170/1251] eta: 0:11:41 lr: 0.000889 loss: 3.7727 (3.6363) grad_norm: 1.1132 (1.1311) time: 0.6258 [2021-03-26 13:00:18 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 180/1251] eta: 0:11:33 lr: 0.000889 loss: 3.3292 (3.6133) grad_norm: 1.1202 (1.1291) time: 0.6278 [2021-03-26 13:00:24 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 190/1251] eta: 0:11:26 lr: 0.000889 loss: 3.1835 (3.5982) grad_norm: 1.0791 (1.1263) time: 0.6285 [2021-03-26 13:00:30 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 200/1251] eta: 0:11:18 lr: 0.000889 loss: 3.6931 (3.6127) grad_norm: 1.0704 (1.1237) time: 0.6240 [2021-03-26 13:00:36 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 210/1251] eta: 0:11:11 lr: 0.000889 loss: 3.7083 (3.6159) grad_norm: 1.1157 (1.1291) time: 0.6300 [2021-03-26 13:00:43 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 220/1251] eta: 0:11:04 lr: 0.000889 loss: 3.6412 (3.6168) grad_norm: 1.1157 (1.1281) time: 0.6331 [2021-03-26 13:00:49 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 230/1251] eta: 0:10:56 lr: 0.000889 loss: 3.5698 (3.6095) grad_norm: 1.1089 (1.1301) time: 0.6257 [2021-03-26 13:00:55 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 240/1251] eta: 0:10:49 lr: 0.000889 loss: 3.5698 (3.6119) grad_norm: 1.1525 (1.1313) time: 0.6237 [2021-03-26 13:01:01 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 250/1251] eta: 0:10:42 lr: 0.000889 loss: 3.8190 (3.6140) grad_norm: 1.1328 (1.1316) time: 0.6227 [2021-03-26 13:01:08 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 260/1251] eta: 0:10:35 lr: 0.000889 loss: 4.0362 (3.6203) grad_norm: 1.1006 (1.1314) time: 0.6288 [2021-03-26 13:01:14 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 270/1251] eta: 0:10:28 lr: 0.000889 loss: 3.7774 (3.6225) grad_norm: 1.0727 (1.1314) time: 0.6274 [2021-03-26 13:01:20 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 280/1251] eta: 0:10:21 lr: 0.000889 loss: 3.5755 (3.6190) grad_norm: 1.0727 (1.1297) time: 0.6187 [2021-03-26 13:01:26 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 290/1251] eta: 0:10:14 lr: 0.000889 loss: 3.5755 (3.6200) grad_norm: 1.0381 (1.1265) time: 0.6185 [2021-03-26 13:01:33 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 300/1251] eta: 0:10:07 lr: 0.000889 loss: 3.6275 (3.6206) grad_norm: 1.0222 (1.1249) time: 0.6215 [2021-03-26 13:01:39 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 310/1251] eta: 0:10:00 lr: 0.000889 loss: 3.7614 (3.6261) grad_norm: 1.0277 (1.1237) time: 0.6202 [2021-03-26 13:01:45 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 320/1251] eta: 0:09:53 lr: 0.000889 loss: 3.8189 (3.6370) grad_norm: 1.0746 (1.1224) time: 0.6256 [2021-03-26 13:01:51 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 330/1251] eta: 0:09:47 lr: 0.000889 loss: 3.7064 (3.6301) grad_norm: 1.0557 (1.1202) time: 0.6333 [2021-03-26 13:01:58 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 340/1251] eta: 0:09:40 lr: 0.000889 loss: 3.4620 (3.6295) grad_norm: 0.9735 (1.1169) time: 0.6297 [2021-03-26 13:02:04 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 350/1251] eta: 0:09:33 lr: 0.000889 loss: 3.7800 (3.6374) grad_norm: 0.9884 (1.1165) time: 0.6221 [2021-03-26 13:02:10 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 360/1251] eta: 0:09:27 lr: 0.000889 loss: 3.8787 (3.6377) grad_norm: 1.1254 (1.1176) time: 0.6260 [2021-03-26 13:02:16 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 370/1251] eta: 0:09:20 lr: 0.000889 loss: 3.7787 (3.6366) grad_norm: 1.1254 (1.1169) time: 0.6295 [2021-03-26 13:02:23 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 380/1251] eta: 0:09:14 lr: 0.000889 loss: 3.8496 (3.6388) grad_norm: 1.0821 (1.1173) time: 0.6256 [2021-03-26 13:02:29 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 390/1251] eta: 0:09:07 lr: 0.000889 loss: 3.7131 (3.6375) grad_norm: 1.1089 (1.1173) time: 0.6242 [2021-03-26 13:02:35 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 400/1251] eta: 0:09:00 lr: 0.000889 loss: 3.6743 (3.6364) grad_norm: 1.1089 (1.1173) time: 0.6285 [2021-03-26 13:02:41 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 410/1251] eta: 0:08:54 lr: 0.000889 loss: 3.6369 (3.6359) grad_norm: 1.1163 (1.1194) time: 0.6279 [2021-03-26 13:02:48 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 420/1251] eta: 0:08:47 lr: 0.000889 loss: 3.6085 (3.6386) grad_norm: 1.0884 (1.1199) time: 0.6232 [2021-03-26 13:02:54 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 430/1251] eta: 0:08:41 lr: 0.000889 loss: 3.6245 (3.6394) grad_norm: 1.0365 (1.1185) time: 0.6254 [2021-03-26 13:03:00 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 440/1251] eta: 0:08:34 lr: 0.000889 loss: 3.6653 (3.6347) grad_norm: 1.0582 (1.1182) time: 0.6280 [2021-03-26 13:03:07 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 450/1251] eta: 0:08:28 lr: 0.000889 loss: 3.7504 (3.6348) grad_norm: 1.0907 (1.1190) time: 0.6280 [2021-03-26 13:03:13 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 460/1251] eta: 0:08:21 lr: 0.000888 loss: 3.7504 (3.6347) grad_norm: 1.1435 (1.1200) time: 0.6274 [2021-03-26 13:03:19 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 470/1251] eta: 0:08:15 lr: 0.000888 loss: 3.7511 (3.6388) grad_norm: 1.0835 (1.1181) time: 0.6229 [2021-03-26 13:03:25 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 480/1251] eta: 0:08:08 lr: 0.000888 loss: 3.7412 (3.6369) grad_norm: 1.0440 (1.1179) time: 0.6278 [2021-03-26 13:03:32 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 490/1251] eta: 0:08:02 lr: 0.000888 loss: 3.7412 (3.6408) grad_norm: 1.0378 (1.1159) time: 0.6279 [2021-03-26 13:03:38 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 500/1251] eta: 0:07:55 lr: 0.000888 loss: 3.7814 (3.6413) grad_norm: 1.0093 (1.1146) time: 0.6193 [2021-03-26 13:03:44 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 510/1251] eta: 0:07:49 lr: 0.000888 loss: 3.7497 (3.6425) grad_norm: 1.0749 (1.1148) time: 0.6230 [2021-03-26 13:03:50 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 520/1251] eta: 0:07:42 lr: 0.000888 loss: 3.4926 (3.6402) grad_norm: 1.1069 (1.1141) time: 0.6260 [2021-03-26 13:03:57 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 530/1251] eta: 0:07:36 lr: 0.000888 loss: 3.8379 (3.6439) grad_norm: 1.1229 (1.1149) time: 0.6286 [2021-03-26 13:04:03 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 540/1251] eta: 0:07:30 lr: 0.000888 loss: 3.7600 (3.6451) grad_norm: 1.0747 (1.1133) time: 0.6296 [2021-03-26 13:04:09 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 550/1251] eta: 0:07:23 lr: 0.000888 loss: 3.7209 (3.6443) grad_norm: 1.0581 (1.1131) time: 0.6339 [2021-03-26 13:04:16 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 560/1251] eta: 0:07:17 lr: 0.000888 loss: 3.4738 (3.6432) grad_norm: 1.0626 (1.1121) time: 0.6337 [2021-03-26 13:04:22 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 570/1251] eta: 0:07:11 lr: 0.000888 loss: 3.4296 (3.6398) grad_norm: 1.0523 (1.1109) time: 0.6291 [2021-03-26 13:04:28 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 580/1251] eta: 0:07:04 lr: 0.000888 loss: 3.4846 (3.6405) grad_norm: 1.0134 (1.1097) time: 0.6301 [2021-03-26 13:04:34 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 590/1251] eta: 0:06:58 lr: 0.000888 loss: 3.8304 (3.6436) grad_norm: 1.0072 (1.1101) time: 0.6284 [2021-03-26 13:04:41 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 600/1251] eta: 0:06:52 lr: 0.000888 loss: 3.7437 (3.6423) grad_norm: 1.0210 (1.1092) time: 0.6385 [2021-03-26 13:04:47 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 610/1251] eta: 0:06:45 lr: 0.000888 loss: 3.3054 (3.6363) grad_norm: 1.0246 (1.1094) time: 0.6360 [2021-03-26 13:04:53 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 620/1251] eta: 0:06:39 lr: 0.000888 loss: 3.6582 (3.6394) grad_norm: 1.0418 (1.1083) time: 0.6187 [2021-03-26 13:05:00 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 630/1251] eta: 0:06:32 lr: 0.000888 loss: 3.6582 (3.6363) grad_norm: 1.0458 (1.1083) time: 0.6240 [2021-03-26 13:05:06 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 640/1251] eta: 0:06:26 lr: 0.000888 loss: 3.7616 (3.6402) grad_norm: 1.1399 (1.1100) time: 0.6301 [2021-03-26 13:05:12 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 650/1251] eta: 0:06:20 lr: 0.000888 loss: 3.8371 (3.6411) grad_norm: 1.1393 (1.1114) time: 0.6282 [2021-03-26 13:05:18 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 660/1251] eta: 0:06:13 lr: 0.000888 loss: 3.7643 (3.6443) grad_norm: 1.1008 (1.1124) time: 0.6257 [2021-03-26 13:05:25 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 670/1251] eta: 0:06:07 lr: 0.000888 loss: 3.8043 (3.6467) grad_norm: 1.0589 (1.1118) time: 0.6211 [2021-03-26 13:05:31 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 680/1251] eta: 0:06:01 lr: 0.000888 loss: 3.8043 (3.6492) grad_norm: 1.0361 (1.1119) time: 0.6260 [2021-03-26 13:05:37 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 690/1251] eta: 0:05:54 lr: 0.000888 loss: 3.8540 (3.6509) grad_norm: 1.0717 (1.1119) time: 0.6343 [2021-03-26 13:05:44 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 700/1251] eta: 0:05:48 lr: 0.000888 loss: 3.6877 (3.6511) grad_norm: 1.0717 (1.1110) time: 0.6325 [2021-03-26 13:05:50 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 710/1251] eta: 0:05:42 lr: 0.000888 loss: 3.9058 (3.6533) grad_norm: 1.0398 (1.1108) time: 0.6260 [2021-03-26 13:05:56 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 720/1251] eta: 0:05:35 lr: 0.000888 loss: 3.8050 (3.6552) grad_norm: 1.0388 (1.1110) time: 0.6277 [2021-03-26 13:06:03 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 730/1251] eta: 0:05:29 lr: 0.000888 loss: 3.7219 (3.6542) grad_norm: 1.0388 (1.1111) time: 0.6337 [2021-03-26 13:06:09 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 740/1251] eta: 0:05:23 lr: 0.000888 loss: 3.7866 (3.6568) grad_norm: 1.0845 (1.1111) time: 0.6319 [2021-03-26 13:06:15 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 750/1251] eta: 0:05:16 lr: 0.000888 loss: 3.9128 (3.6580) grad_norm: 1.0850 (1.1116) time: 0.6292 [2021-03-26 13:06:21 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 760/1251] eta: 0:05:10 lr: 0.000888 loss: 3.8119 (3.6597) grad_norm: 1.0790 (1.1114) time: 0.6267 [2021-03-26 13:06:28 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 770/1251] eta: 0:05:04 lr: 0.000888 loss: 3.8575 (3.6620) grad_norm: 1.1273 (1.1123) time: 0.6321 [2021-03-26 13:06:34 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 780/1251] eta: 0:04:57 lr: 0.000888 loss: 3.8217 (3.6609) grad_norm: 1.1598 (1.1129) time: 0.6315 [2021-03-26 13:06:40 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 790/1251] eta: 0:04:51 lr: 0.000888 loss: 3.6547 (3.6620) grad_norm: 1.0890 (1.1124) time: 0.6296 [2021-03-26 13:06:47 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 800/1251] eta: 0:04:45 lr: 0.000888 loss: 3.6547 (3.6595) grad_norm: 1.0371 (1.1115) time: 0.6333 [2021-03-26 13:06:53 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 810/1251] eta: 0:04:38 lr: 0.000888 loss: 3.8325 (3.6625) grad_norm: 1.0424 (1.1110) time: 0.6263 [2021-03-26 13:06:59 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 820/1251] eta: 0:04:32 lr: 0.000888 loss: 3.8325 (3.6596) grad_norm: 1.1586 (1.1130) time: 0.6289 [2021-03-26 13:07:06 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 830/1251] eta: 0:04:26 lr: 0.000888 loss: 3.9361 (3.6618) grad_norm: 1.2270 (1.1134) time: 0.6354 [2021-03-26 13:07:12 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 840/1251] eta: 0:04:19 lr: 0.000887 loss: 3.6949 (3.6588) grad_norm: 1.1542 (1.1139) time: 0.6304 [2021-03-26 13:07:18 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 850/1251] eta: 0:04:13 lr: 0.000887 loss: 3.4967 (3.6565) grad_norm: 1.1299 (1.1138) time: 0.6250 [2021-03-26 13:07:24 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 860/1251] eta: 0:04:07 lr: 0.000887 loss: 3.7623 (3.6578) grad_norm: 1.1119 (1.1136) time: 0.6307 [2021-03-26 13:07:31 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 870/1251] eta: 0:04:00 lr: 0.000887 loss: 3.6611 (3.6554) grad_norm: 1.1150 (1.1152) time: 0.6305 [2021-03-26 13:07:37 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 880/1251] eta: 0:03:54 lr: 0.000887 loss: 3.6349 (3.6566) grad_norm: 1.0522 (1.1146) time: 0.6274 [2021-03-26 13:07:43 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 890/1251] eta: 0:03:48 lr: 0.000887 loss: 3.8869 (3.6582) grad_norm: 1.1169 (1.1159) time: 0.6240 [2021-03-26 13:07:49 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 900/1251] eta: 0:03:41 lr: 0.000887 loss: 3.7856 (3.6553) grad_norm: 1.1443 (1.1160) time: 0.6212 [2021-03-26 13:07:56 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 910/1251] eta: 0:03:35 lr: 0.000887 loss: 3.2047 (3.6551) grad_norm: 1.0556 (1.1156) time: 0.6228 [2021-03-26 13:08:02 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 920/1251] eta: 0:03:29 lr: 0.000887 loss: 3.8150 (3.6569) grad_norm: 1.0556 (1.1151) time: 0.6258 [2021-03-26 13:08:08 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 930/1251] eta: 0:03:22 lr: 0.000887 loss: 3.7059 (3.6543) grad_norm: 1.0914 (1.1147) time: 0.6287 [2021-03-26 13:08:14 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 940/1251] eta: 0:03:16 lr: 0.000887 loss: 3.4870 (3.6527) grad_norm: 1.1011 (1.1145) time: 0.6248 [2021-03-26 13:08:21 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 950/1251] eta: 0:03:10 lr: 0.000887 loss: 3.7682 (3.6544) grad_norm: 1.0724 (1.1145) time: 0.6246 [2021-03-26 13:08:27 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 960/1251] eta: 0:03:03 lr: 0.000887 loss: 3.6345 (3.6517) grad_norm: 1.1319 (1.1157) time: 0.6287 [2021-03-26 13:08:33 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 970/1251] eta: 0:02:57 lr: 0.000887 loss: 3.6206 (3.6519) grad_norm: 1.0551 (1.1149) time: 0.6255 [2021-03-26 13:08:39 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 980/1251] eta: 0:02:51 lr: 0.000887 loss: 3.9202 (3.6541) grad_norm: 1.0369 (1.1143) time: 0.6210 [2021-03-26 13:08:46 swin_base_patch4_window7_224] INFO: Epoch: [65] [ 990/1251] eta: 0:02:44 lr: 0.000887 loss: 3.9202 (3.6540) grad_norm: 1.0236 (1.1143) time: 0.6246 [2021-03-26 13:08:52 swin_base_patch4_window7_224] INFO: Epoch: [65] [1000/1251] eta: 0:02:38 lr: 0.000887 loss: 3.6681 (3.6536) grad_norm: 1.0518 (1.1142) time: 0.6309 [2021-03-26 13:08:58 swin_base_patch4_window7_224] INFO: Epoch: [65] [1010/1251] eta: 0:02:32 lr: 0.000887 loss: 3.6148 (3.6510) grad_norm: 1.0444 (1.1132) time: 0.6338 [2021-03-26 13:09:05 swin_base_patch4_window7_224] INFO: Epoch: [65] [1020/1251] eta: 0:02:25 lr: 0.000887 loss: 3.6917 (3.6511) grad_norm: 1.0117 (1.1126) time: 0.6279 [2021-03-26 13:09:11 swin_base_patch4_window7_224] INFO: Epoch: [65] [1030/1251] eta: 0:02:19 lr: 0.000887 loss: 3.6917 (3.6517) grad_norm: 1.0634 (1.1127) time: 0.6241 [2021-03-26 13:09:17 swin_base_patch4_window7_224] INFO: Epoch: [65] [1040/1251] eta: 0:02:13 lr: 0.000887 loss: 3.7902 (3.6516) grad_norm: 1.0395 (1.1121) time: 0.6258 [2021-03-26 13:09:23 swin_base_patch4_window7_224] INFO: Epoch: [65] [1050/1251] eta: 0:02:06 lr: 0.000887 loss: 3.7799 (3.6508) grad_norm: 1.1063 (1.1136) time: 0.6268 [2021-03-26 13:09:30 swin_base_patch4_window7_224] INFO: Epoch: [65] [1060/1251] eta: 0:02:00 lr: 0.000887 loss: 3.6100 (3.6509) grad_norm: 1.1435 (1.1130) time: 0.6209 [2021-03-26 13:09:36 swin_base_patch4_window7_224] INFO: Epoch: [65] [1070/1251] eta: 0:01:54 lr: 0.000887 loss: 3.6469 (3.6511) grad_norm: 1.0417 (1.1125) time: 0.6216 [2021-03-26 13:09:42 swin_base_patch4_window7_224] INFO: Epoch: [65] [1080/1251] eta: 0:01:47 lr: 0.000887 loss: 3.7301 (3.6488) grad_norm: 1.0455 (1.1128) time: 0.6312 [2021-03-26 13:09:48 swin_base_patch4_window7_224] INFO: Epoch: [65] [1090/1251] eta: 0:01:41 lr: 0.000887 loss: 3.7008 (3.6485) grad_norm: 1.0296 (1.1123) time: 0.6249 [2021-03-26 13:09:55 swin_base_patch4_window7_224] INFO: Epoch: [65] [1100/1251] eta: 0:01:35 lr: 0.000887 loss: 3.9615 (3.6520) grad_norm: 1.0700 (1.1123) time: 0.6175 [2021-03-26 13:10:01 swin_base_patch4_window7_224] INFO: Epoch: [65] [1110/1251] eta: 0:01:28 lr: 0.000887 loss: 3.9891 (3.6521) grad_norm: 1.0369 (1.1112) time: 0.6168 [2021-03-26 13:10:07 swin_base_patch4_window7_224] INFO: Epoch: [65] [1120/1251] eta: 0:01:22 lr: 0.000887 loss: 3.9033 (3.6555) grad_norm: 1.0531 (inf) time: 0.6189 [2021-03-26 13:10:13 swin_base_patch4_window7_224] INFO: Epoch: [65] [1130/1251] eta: 0:01:16 lr: 0.000887 loss: 3.8889 (3.6560) grad_norm: 1.0696 (inf) time: 0.6224 [2021-03-26 13:10:19 swin_base_patch4_window7_224] INFO: Epoch: [65] [1140/1251] eta: 0:01:09 lr: 0.000887 loss: 3.8762 (3.6571) grad_norm: 0.9923 (inf) time: 0.6240 [2021-03-26 13:10:26 swin_base_patch4_window7_224] INFO: Epoch: [65] [1150/1251] eta: 0:01:03 lr: 0.000887 loss: 3.8394 (3.6575) grad_norm: 0.9905 (inf) time: 0.6240 [2021-03-26 13:10:32 swin_base_patch4_window7_224] INFO: Epoch: [65] [1160/1251] eta: 0:00:57 lr: 0.000887 loss: 3.8394 (3.6582) grad_norm: 1.0800 (inf) time: 0.6222 [2021-03-26 13:10:38 swin_base_patch4_window7_224] INFO: Epoch: [65] [1170/1251] eta: 0:00:51 lr: 0.000887 loss: 3.4300 (3.6566) grad_norm: 1.1515 (inf) time: 0.6288 [2021-03-26 13:10:45 swin_base_patch4_window7_224] INFO: Epoch: [65] [1180/1251] eta: 0:00:44 lr: 0.000887 loss: 3.6795 (3.6585) grad_norm: 1.1085 (inf) time: 0.6313 [2021-03-26 13:10:51 swin_base_patch4_window7_224] INFO: Epoch: [65] [1190/1251] eta: 0:00:38 lr: 0.000887 loss: 3.8208 (3.6594) grad_norm: 1.0663 (inf) time: 0.6282 [2021-03-26 13:10:57 swin_base_patch4_window7_224] INFO: Epoch: [65] [1200/1251] eta: 0:00:32 lr: 0.000887 loss: 3.9874 (3.6616) grad_norm: 1.0736 (inf) time: 0.6311 [2021-03-26 13:11:03 swin_base_patch4_window7_224] INFO: Epoch: [65] [1210/1251] eta: 0:00:25 lr: 0.000887 loss: 3.8029 (3.6593) grad_norm: 0.9778 (inf) time: 0.6263 [2021-03-26 13:11:10 swin_base_patch4_window7_224] INFO: Epoch: [65] [1220/1251] eta: 0:00:19 lr: 0.000886 loss: 3.8780 (3.6608) grad_norm: 1.0373 (inf) time: 0.6239 [2021-03-26 13:11:16 swin_base_patch4_window7_224] INFO: Epoch: [65] [1230/1251] eta: 0:00:13 lr: 0.000886 loss: 3.9420 (3.6623) grad_norm: 1.0493 (inf) time: 0.6281 [2021-03-26 13:11:22 swin_base_patch4_window7_224] INFO: Epoch: [65] [1240/1251] eta: 0:00:06 lr: 0.000886 loss: 3.9297 (3.6632) grad_norm: 1.1010 (inf) time: 0.6236 [2021-03-26 13:11:28 swin_base_patch4_window7_224] INFO: Epoch: [65] [1250/1251] eta: 0:00:00 lr: 0.000886 loss: 3.7827 (3.6627) grad_norm: 1.0857 (inf) time: 0.6184 [2021-03-26 13:12:33 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:16 loss: 1.0193 (1.0193) acc1: 75.0000 (75.0000) acc5: 93.7500 (93.7500) [2021-03-26 13:12:35 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 1.0425 (1.0773) acc1: 73.4375 (73.1534) acc5: 93.7500 (92.7557) [2021-03-26 13:12:36 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:06 loss: 1.0544 (1.0826) acc1: 73.4375 (73.8095) acc5: 92.1875 (92.5595) [2021-03-26 13:12:37 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.0883 (1.1041) acc1: 73.4375 (72.9335) acc5: 92.1875 (92.4899) [2021-03-26 13:12:39 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.1596 (1.1091) acc1: 71.8750 (73.2088) acc5: 92.1875 (92.4924) [2021-03-26 13:12:40 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1337 (1.1005) acc1: 71.8750 (73.2800) acc5: 92.1875 (92.6080) [2021-03-26 13:12:43 swin_base_patch4_window7_224] INFO: * Acc@1 74.360 Acc@5 92.702 loss 1.088 [2021-03-26 13:12:43 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.4% [2021-03-26 13:12:43 swin_base_patch4_window7_224] INFO: Max accuracy: 74.57% [2021-03-26 13:12:48 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 0/1251] eta: 1:25:30 lr: 0.000886 loss: 2.8051 (2.8051) grad_norm: 1.0067 (1.0067) time: 4.1011 [2021-03-26 13:12:54 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 10/1251] eta: 0:19:48 lr: 0.000886 loss: 3.9969 (3.8010) grad_norm: 1.0566 (1.1230) time: 0.9573 [2021-03-26 13:13:00 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 20/1251] eta: 0:16:28 lr: 0.000886 loss: 3.8281 (3.6680) grad_norm: 1.1410 (1.1352) time: 0.6381 [2021-03-26 13:13:07 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 30/1251] eta: 0:15:15 lr: 0.000886 loss: 3.8125 (3.6883) grad_norm: 1.0497 (1.0989) time: 0.6362 [2021-03-26 13:13:13 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 40/1251] eta: 0:14:28 lr: 0.000886 loss: 3.8876 (3.7239) grad_norm: 1.0120 (1.0895) time: 0.6275 [2021-03-26 13:13:19 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 50/1251] eta: 0:13:58 lr: 0.000886 loss: 4.0853 (3.7954) grad_norm: 0.9864 (1.0730) time: 0.6178 [2021-03-26 13:13:25 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 60/1251] eta: 0:13:37 lr: 0.000886 loss: 3.8094 (3.7552) grad_norm: 1.0320 (1.0753) time: 0.6223 [2021-03-26 13:13:32 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 70/1251] eta: 0:13:20 lr: 0.000886 loss: 3.6728 (3.7368) grad_norm: 1.0813 (1.0968) time: 0.6255 [2021-03-26 13:13:38 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 80/1251] eta: 0:13:04 lr: 0.000886 loss: 3.6728 (3.7369) grad_norm: 1.0707 (1.0884) time: 0.6215 [2021-03-26 13:13:44 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 90/1251] eta: 0:12:52 lr: 0.000886 loss: 3.5813 (3.7110) grad_norm: 1.0583 (1.0919) time: 0.6222 [2021-03-26 13:13:50 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 100/1251] eta: 0:12:41 lr: 0.000886 loss: 3.4303 (3.6686) grad_norm: 1.0693 (1.0985) time: 0.6284 [2021-03-26 13:13:57 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 110/1251] eta: 0:12:32 lr: 0.000886 loss: 3.7329 (3.6645) grad_norm: 1.1217 (1.0991) time: 0.6308 [2021-03-26 13:14:03 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 120/1251] eta: 0:12:23 lr: 0.000886 loss: 3.9108 (3.6629) grad_norm: 1.0725 (1.0957) time: 0.6338 [2021-03-26 13:14:10 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 130/1251] eta: 0:12:16 lr: 0.000886 loss: 3.9433 (3.6875) grad_norm: 1.0590 (1.0960) time: 0.6425 [2021-03-26 13:14:16 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 140/1251] eta: 0:12:08 lr: 0.000886 loss: 4.0066 (3.6795) grad_norm: 1.0989 (1.0992) time: 0.6480 [2021-03-26 13:14:22 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 150/1251] eta: 0:11:59 lr: 0.000886 loss: 3.7476 (3.6814) grad_norm: 1.1639 (1.1014) time: 0.6335 [2021-03-26 13:14:28 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 160/1251] eta: 0:11:50 lr: 0.000886 loss: 3.5938 (3.6776) grad_norm: 1.1816 (1.1056) time: 0.6193 [2021-03-26 13:14:35 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 170/1251] eta: 0:11:42 lr: 0.000886 loss: 3.5059 (3.6745) grad_norm: 1.1620 (1.1102) time: 0.6224 [2021-03-26 13:14:41 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 180/1251] eta: 0:11:34 lr: 0.000886 loss: 3.3971 (3.6597) grad_norm: 1.1090 (1.1128) time: 0.6267 [2021-03-26 13:14:47 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 190/1251] eta: 0:11:26 lr: 0.000886 loss: 3.5491 (3.6710) grad_norm: 1.0524 (1.1132) time: 0.6250 [2021-03-26 13:14:54 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 200/1251] eta: 0:11:20 lr: 0.000886 loss: 3.9019 (3.6808) grad_norm: 1.0350 (1.1117) time: 0.6319 [2021-03-26 13:15:00 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 210/1251] eta: 0:11:12 lr: 0.000886 loss: 3.7804 (3.6795) grad_norm: 1.0775 (1.1117) time: 0.6350 [2021-03-26 13:15:06 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 220/1251] eta: 0:11:05 lr: 0.000886 loss: 3.7554 (3.6676) grad_norm: 1.0482 (1.1079) time: 0.6267 [2021-03-26 13:15:12 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 230/1251] eta: 0:10:58 lr: 0.000886 loss: 3.6675 (3.6700) grad_norm: 1.0644 (1.1092) time: 0.6269 [2021-03-26 13:15:19 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 240/1251] eta: 0:10:51 lr: 0.000886 loss: 3.8034 (3.6745) grad_norm: 1.1206 (1.1113) time: 0.6342 [2021-03-26 13:15:25 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 250/1251] eta: 0:10:44 lr: 0.000886 loss: 3.8086 (3.6547) grad_norm: 1.1255 (1.1116) time: 0.6305 [2021-03-26 13:15:31 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 260/1251] eta: 0:10:36 lr: 0.000886 loss: 3.6943 (3.6548) grad_norm: 1.1176 (1.1125) time: 0.6226 [2021-03-26 13:15:38 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 270/1251] eta: 0:10:29 lr: 0.000886 loss: 3.7306 (3.6573) grad_norm: 1.1161 (1.1130) time: 0.6262 [2021-03-26 13:15:44 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 280/1251] eta: 0:10:22 lr: 0.000886 loss: 3.7614 (3.6618) grad_norm: 1.0318 (1.1112) time: 0.6240 [2021-03-26 13:15:50 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 290/1251] eta: 0:10:15 lr: 0.000886 loss: 3.8295 (3.6708) grad_norm: 1.0465 (1.1149) time: 0.6204 [2021-03-26 13:15:56 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 300/1251] eta: 0:10:09 lr: 0.000886 loss: 3.7023 (3.6704) grad_norm: 1.1312 (1.1156) time: 0.6319 [2021-03-26 13:16:03 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 310/1251] eta: 0:10:02 lr: 0.000886 loss: 3.4627 (3.6650) grad_norm: 1.1548 (1.1190) time: 0.6389 [2021-03-26 13:16:09 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 320/1251] eta: 0:09:55 lr: 0.000886 loss: 3.7417 (3.6622) grad_norm: 1.1687 (1.1188) time: 0.6284 [2021-03-26 13:16:15 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 330/1251] eta: 0:09:49 lr: 0.000886 loss: 3.8153 (3.6647) grad_norm: 1.0949 (1.1189) time: 0.6248 [2021-03-26 13:16:22 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 340/1251] eta: 0:09:42 lr: 0.000886 loss: 3.8134 (3.6672) grad_norm: 1.0765 (1.1173) time: 0.6282 [2021-03-26 13:16:28 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 350/1251] eta: 0:09:35 lr: 0.000885 loss: 3.4578 (3.6579) grad_norm: 1.0704 (1.1168) time: 0.6261 [2021-03-26 13:16:34 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 360/1251] eta: 0:09:29 lr: 0.000885 loss: 3.7909 (3.6701) grad_norm: 1.0704 (1.1168) time: 0.6299 [2021-03-26 13:16:40 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 370/1251] eta: 0:09:22 lr: 0.000885 loss: 4.0689 (3.6769) grad_norm: 1.0641 (1.1183) time: 0.6285 [2021-03-26 13:16:47 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 380/1251] eta: 0:09:15 lr: 0.000885 loss: 3.7946 (3.6783) grad_norm: 1.0654 (1.1188) time: 0.6248 [2021-03-26 13:16:53 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 390/1251] eta: 0:09:08 lr: 0.000885 loss: 3.6413 (3.6735) grad_norm: 1.0161 (1.1156) time: 0.6227 [2021-03-26 13:16:59 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 400/1251] eta: 0:09:02 lr: 0.000885 loss: 3.6884 (3.6737) grad_norm: 1.0170 (1.1193) time: 0.6328 [2021-03-26 13:17:05 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 410/1251] eta: 0:08:56 lr: 0.000885 loss: 3.6879 (3.6678) grad_norm: 1.1229 (1.1180) time: 0.6351 [2021-03-26 13:17:12 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 420/1251] eta: 0:08:49 lr: 0.000885 loss: 3.4886 (3.6654) grad_norm: 1.0792 (1.1178) time: 0.6254 [2021-03-26 13:17:18 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 430/1251] eta: 0:08:42 lr: 0.000885 loss: 3.5026 (3.6658) grad_norm: 1.0809 (1.1179) time: 0.6247 [2021-03-26 13:17:24 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 440/1251] eta: 0:08:35 lr: 0.000885 loss: 3.6780 (3.6655) grad_norm: 1.0809 (1.1167) time: 0.6172 [2021-03-26 13:17:30 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 450/1251] eta: 0:08:29 lr: 0.000885 loss: 3.6780 (3.6646) grad_norm: 1.0418 (1.1182) time: 0.6217 [2021-03-26 13:17:37 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 460/1251] eta: 0:08:22 lr: 0.000885 loss: 3.6734 (3.6632) grad_norm: 1.0526 (1.1162) time: 0.6288 [2021-03-26 13:17:43 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 470/1251] eta: 0:08:16 lr: 0.000885 loss: 3.6262 (3.6589) grad_norm: 1.0526 (1.1160) time: 0.6249 [2021-03-26 13:17:49 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 480/1251] eta: 0:08:09 lr: 0.000885 loss: 3.6262 (3.6598) grad_norm: 1.0551 (1.1175) time: 0.6211 [2021-03-26 13:17:55 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 490/1251] eta: 0:08:03 lr: 0.000885 loss: 3.6763 (3.6549) grad_norm: 1.0867 (1.1183) time: 0.6211 [2021-03-26 13:18:02 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 500/1251] eta: 0:07:56 lr: 0.000885 loss: 3.7553 (3.6523) grad_norm: 1.0846 (1.1172) time: 0.6289 [2021-03-26 13:18:08 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 510/1251] eta: 0:07:50 lr: 0.000885 loss: 3.7820 (3.6561) grad_norm: 1.0846 (1.1176) time: 0.6304 [2021-03-26 13:18:14 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 520/1251] eta: 0:07:44 lr: 0.000885 loss: 3.8607 (3.6598) grad_norm: 1.1156 (1.1182) time: 0.6281 [2021-03-26 13:18:20 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 530/1251] eta: 0:07:37 lr: 0.000885 loss: 3.9472 (3.6613) grad_norm: 1.1535 (1.1189) time: 0.6215 [2021-03-26 13:18:27 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 540/1251] eta: 0:07:30 lr: 0.000885 loss: 3.8605 (3.6577) grad_norm: 1.1535 (1.1189) time: 0.6185 [2021-03-26 13:18:33 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 550/1251] eta: 0:07:24 lr: 0.000885 loss: 3.8701 (3.6611) grad_norm: 1.1060 (1.1182) time: 0.6309 [2021-03-26 13:18:40 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 560/1251] eta: 0:07:18 lr: 0.000885 loss: 3.8870 (3.6600) grad_norm: 1.0803 (1.1178) time: 0.6444 [2021-03-26 13:18:46 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 570/1251] eta: 0:07:12 lr: 0.000885 loss: 3.7141 (3.6617) grad_norm: 1.1201 (1.1194) time: 0.6384 [2021-03-26 13:18:52 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 580/1251] eta: 0:07:05 lr: 0.000885 loss: 3.7141 (3.6594) grad_norm: 1.1271 (1.1182) time: 0.6308 [2021-03-26 13:18:58 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 590/1251] eta: 0:06:59 lr: 0.000885 loss: 3.7943 (3.6609) grad_norm: 1.0456 (1.1190) time: 0.6297 [2021-03-26 13:19:05 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 600/1251] eta: 0:06:52 lr: 0.000885 loss: 3.8925 (3.6632) grad_norm: 1.1151 (1.1191) time: 0.6238 [2021-03-26 13:19:11 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 610/1251] eta: 0:06:46 lr: 0.000885 loss: 3.8127 (3.6665) grad_norm: 1.0780 (1.1183) time: 0.6253 [2021-03-26 13:19:17 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 620/1251] eta: 0:06:40 lr: 0.000885 loss: 3.7384 (3.6648) grad_norm: 1.0780 (1.1180) time: 0.6302 [2021-03-26 13:19:24 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 630/1251] eta: 0:06:33 lr: 0.000885 loss: 3.7174 (3.6652) grad_norm: 1.0872 (1.1175) time: 0.6391 [2021-03-26 13:19:30 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 640/1251] eta: 0:06:27 lr: 0.000885 loss: 3.8417 (3.6684) grad_norm: 1.0844 (1.1176) time: 0.6300 [2021-03-26 13:19:36 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 650/1251] eta: 0:06:20 lr: 0.000885 loss: 3.9074 (3.6697) grad_norm: 1.0908 (1.1176) time: 0.6244 [2021-03-26 13:19:42 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 660/1251] eta: 0:06:14 lr: 0.000885 loss: 3.8167 (3.6715) grad_norm: 1.0908 (1.1170) time: 0.6277 [2021-03-26 13:19:49 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 670/1251] eta: 0:06:08 lr: 0.000885 loss: 3.7933 (3.6699) grad_norm: 1.0221 (1.1162) time: 0.6294 [2021-03-26 13:19:55 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 680/1251] eta: 0:06:01 lr: 0.000885 loss: 3.7933 (3.6667) grad_norm: 1.0221 (1.1156) time: 0.6395 [2021-03-26 13:20:02 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 690/1251] eta: 0:05:55 lr: 0.000885 loss: 3.6199 (3.6666) grad_norm: 1.0261 (1.1141) time: 0.6391 [2021-03-26 13:20:08 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 700/1251] eta: 0:05:49 lr: 0.000885 loss: 3.7974 (3.6680) grad_norm: 1.0188 (1.1134) time: 0.6335 [2021-03-26 13:20:14 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 710/1251] eta: 0:05:42 lr: 0.000885 loss: 3.8645 (3.6703) grad_norm: 1.0188 (1.1122) time: 0.6280 [2021-03-26 13:20:20 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 720/1251] eta: 0:05:36 lr: 0.000884 loss: 3.8925 (3.6739) grad_norm: 1.0181 (1.1115) time: 0.6289 [2021-03-26 13:20:27 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 730/1251] eta: 0:05:30 lr: 0.000884 loss: 3.8845 (3.6718) grad_norm: 1.0948 (1.1122) time: 0.6334 [2021-03-26 13:20:33 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 740/1251] eta: 0:05:23 lr: 0.000884 loss: 3.7378 (3.6710) grad_norm: 1.0948 (1.1118) time: 0.6364 [2021-03-26 13:20:40 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 750/1251] eta: 0:05:17 lr: 0.000884 loss: 3.7834 (3.6732) grad_norm: 1.0458 (1.1117) time: 0.6410 [2021-03-26 13:20:46 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 760/1251] eta: 0:05:11 lr: 0.000884 loss: 3.7308 (3.6700) grad_norm: 1.0581 (1.1118) time: 0.6331 [2021-03-26 13:20:52 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 770/1251] eta: 0:05:04 lr: 0.000884 loss: 3.6669 (3.6697) grad_norm: 1.0957 (1.1118) time: 0.6317 [2021-03-26 13:20:58 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 780/1251] eta: 0:04:58 lr: 0.000884 loss: 3.7840 (3.6702) grad_norm: 1.0791 (1.1111) time: 0.6278 [2021-03-26 13:21:05 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 790/1251] eta: 0:04:52 lr: 0.000884 loss: 3.6536 (3.6684) grad_norm: 1.0220 (1.1101) time: 0.6249 [2021-03-26 13:21:11 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 800/1251] eta: 0:04:45 lr: 0.000884 loss: 3.4845 (3.6664) grad_norm: 0.9904 (1.1095) time: 0.6310 [2021-03-26 13:21:17 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 810/1251] eta: 0:04:39 lr: 0.000884 loss: 3.5091 (3.6643) grad_norm: 0.9845 (1.1082) time: 0.6208 [2021-03-26 13:21:23 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 820/1251] eta: 0:04:32 lr: 0.000884 loss: 3.6028 (3.6633) grad_norm: 0.9895 (1.1075) time: 0.6161 [2021-03-26 13:21:30 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 830/1251] eta: 0:04:26 lr: 0.000884 loss: 3.6950 (3.6638) grad_norm: 1.0086 (1.1066) time: 0.6170 [2021-03-26 13:21:36 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 840/1251] eta: 0:04:20 lr: 0.000884 loss: 3.6950 (3.6633) grad_norm: 1.0086 (1.1065) time: 0.6209 [2021-03-26 13:21:42 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 850/1251] eta: 0:04:13 lr: 0.000884 loss: 3.6816 (3.6642) grad_norm: 1.0490 (1.1060) time: 0.6336 [2021-03-26 13:21:48 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 860/1251] eta: 0:04:07 lr: 0.000884 loss: 3.7731 (3.6632) grad_norm: 1.0800 (1.1068) time: 0.6324 [2021-03-26 13:21:55 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 870/1251] eta: 0:04:01 lr: 0.000884 loss: 3.4761 (3.6595) grad_norm: 1.1324 (1.1074) time: 0.6320 [2021-03-26 13:22:01 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 880/1251] eta: 0:03:54 lr: 0.000884 loss: 3.2851 (3.6588) grad_norm: 1.1440 (1.1072) time: 0.6308 [2021-03-26 13:22:07 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 890/1251] eta: 0:03:48 lr: 0.000884 loss: 3.6441 (3.6599) grad_norm: 1.1396 (1.1077) time: 0.6292 [2021-03-26 13:22:14 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 900/1251] eta: 0:03:42 lr: 0.000884 loss: 3.7628 (3.6624) grad_norm: 1.1175 (1.1080) time: 0.6324 [2021-03-26 13:22:20 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 910/1251] eta: 0:03:35 lr: 0.000884 loss: 3.8193 (3.6635) grad_norm: 1.1175 (1.1082) time: 0.6278 [2021-03-26 13:22:26 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 920/1251] eta: 0:03:29 lr: 0.000884 loss: 3.8559 (3.6657) grad_norm: 1.1433 (1.1096) time: 0.6273 [2021-03-26 13:22:33 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 930/1251] eta: 0:03:23 lr: 0.000884 loss: 3.7856 (3.6635) grad_norm: 1.0952 (1.1092) time: 0.6267 [2021-03-26 13:22:39 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 940/1251] eta: 0:03:16 lr: 0.000884 loss: 3.5975 (3.6636) grad_norm: 0.9971 (1.1081) time: 0.6227 [2021-03-26 13:22:45 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 950/1251] eta: 0:03:10 lr: 0.000884 loss: 3.5841 (3.6612) grad_norm: 1.0005 (1.1084) time: 0.6270 [2021-03-26 13:22:51 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 960/1251] eta: 0:03:04 lr: 0.000884 loss: 3.4316 (3.6598) grad_norm: 1.0415 (1.1078) time: 0.6346 [2021-03-26 13:22:58 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 970/1251] eta: 0:02:57 lr: 0.000884 loss: 3.6045 (3.6595) grad_norm: 1.0620 (1.1078) time: 0.6321 [2021-03-26 13:23:04 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 980/1251] eta: 0:02:51 lr: 0.000884 loss: 3.6379 (3.6583) grad_norm: 1.0901 (1.1074) time: 0.6301 [2021-03-26 13:23:10 swin_base_patch4_window7_224] INFO: Epoch: [66] [ 990/1251] eta: 0:02:45 lr: 0.000884 loss: 3.4649 (3.6564) grad_norm: 1.0324 (1.1066) time: 0.6266 [2021-03-26 13:23:16 swin_base_patch4_window7_224] INFO: Epoch: [66] [1000/1251] eta: 0:02:38 lr: 0.000884 loss: 3.8342 (3.6597) grad_norm: 1.0324 (1.1060) time: 0.6223 [2021-03-26 13:23:23 swin_base_patch4_window7_224] INFO: Epoch: [66] [1010/1251] eta: 0:02:32 lr: 0.000884 loss: 4.0104 (3.6612) grad_norm: 1.0472 (1.1060) time: 0.6208 [2021-03-26 13:23:29 swin_base_patch4_window7_224] INFO: Epoch: [66] [1020/1251] eta: 0:02:25 lr: 0.000884 loss: 3.7771 (3.6615) grad_norm: 1.1244 (1.1066) time: 0.6192 [2021-03-26 13:23:35 swin_base_patch4_window7_224] INFO: Epoch: [66] [1030/1251] eta: 0:02:19 lr: 0.000884 loss: 3.9523 (3.6639) grad_norm: 1.1289 (1.1068) time: 0.6215 [2021-03-26 13:23:41 swin_base_patch4_window7_224] INFO: Epoch: [66] [1040/1251] eta: 0:02:13 lr: 0.000884 loss: 3.8252 (3.6635) grad_norm: 1.0718 (1.1064) time: 0.6244 [2021-03-26 13:23:48 swin_base_patch4_window7_224] INFO: Epoch: [66] [1050/1251] eta: 0:02:06 lr: 0.000884 loss: 3.8252 (3.6636) grad_norm: 1.0465 (1.1065) time: 0.6258 [2021-03-26 13:23:54 swin_base_patch4_window7_224] INFO: Epoch: [66] [1060/1251] eta: 0:02:00 lr: 0.000884 loss: 3.8545 (3.6655) grad_norm: 1.0454 (1.1057) time: 0.6247 [2021-03-26 13:24:00 swin_base_patch4_window7_224] INFO: Epoch: [66] [1070/1251] eta: 0:01:54 lr: 0.000884 loss: 3.8316 (3.6635) grad_norm: 1.0486 (1.1059) time: 0.6282 [2021-03-26 13:24:06 swin_base_patch4_window7_224] INFO: Epoch: [66] [1080/1251] eta: 0:01:48 lr: 0.000884 loss: 3.3896 (3.6619) grad_norm: 1.0671 (1.1057) time: 0.6316 [2021-03-26 13:24:13 swin_base_patch4_window7_224] INFO: Epoch: [66] [1090/1251] eta: 0:01:41 lr: 0.000884 loss: 3.5684 (3.6618) grad_norm: 1.0685 (1.1060) time: 0.6260 [2021-03-26 13:24:19 swin_base_patch4_window7_224] INFO: Epoch: [66] [1100/1251] eta: 0:01:35 lr: 0.000883 loss: 3.7652 (3.6626) grad_norm: 1.0746 (1.1058) time: 0.6219 [2021-03-26 13:24:25 swin_base_patch4_window7_224] INFO: Epoch: [66] [1110/1251] eta: 0:01:29 lr: 0.000883 loss: 3.8377 (3.6644) grad_norm: 1.0746 (1.1066) time: 0.6248 [2021-03-26 13:24:31 swin_base_patch4_window7_224] INFO: Epoch: [66] [1120/1251] eta: 0:01:22 lr: 0.000883 loss: 3.8377 (3.6651) grad_norm: 1.0337 (1.1062) time: 0.6242 [2021-03-26 13:24:38 swin_base_patch4_window7_224] INFO: Epoch: [66] [1130/1251] eta: 0:01:16 lr: 0.000883 loss: 3.7588 (3.6655) grad_norm: 1.0258 (1.1061) time: 0.6260 [2021-03-26 13:24:44 swin_base_patch4_window7_224] INFO: Epoch: [66] [1140/1251] eta: 0:01:10 lr: 0.000883 loss: 3.7084 (3.6643) grad_norm: 1.0369 (1.1058) time: 0.6259 [2021-03-26 13:24:50 swin_base_patch4_window7_224] INFO: Epoch: [66] [1150/1251] eta: 0:01:03 lr: 0.000883 loss: 3.4662 (3.6632) grad_norm: 1.0369 (1.1055) time: 0.6179 [2021-03-26 13:24:56 swin_base_patch4_window7_224] INFO: Epoch: [66] [1160/1251] eta: 0:00:57 lr: 0.000883 loss: 3.5813 (3.6613) grad_norm: 1.0744 (1.1056) time: 0.6207 [2021-03-26 13:25:03 swin_base_patch4_window7_224] INFO: Epoch: [66] [1170/1251] eta: 0:00:51 lr: 0.000883 loss: 3.6466 (3.6603) grad_norm: 1.0744 (1.1050) time: 0.6234 [2021-03-26 13:25:09 swin_base_patch4_window7_224] INFO: Epoch: [66] [1180/1251] eta: 0:00:44 lr: 0.000883 loss: 3.7449 (3.6609) grad_norm: 1.0388 (1.1045) time: 0.6283 [2021-03-26 13:25:15 swin_base_patch4_window7_224] INFO: Epoch: [66] [1190/1251] eta: 0:00:38 lr: 0.000883 loss: 3.7925 (3.6615) grad_norm: 1.0507 (1.1042) time: 0.6337 [2021-03-26 13:25:21 swin_base_patch4_window7_224] INFO: Epoch: [66] [1200/1251] eta: 0:00:32 lr: 0.000883 loss: 3.7833 (3.6611) grad_norm: 1.0847 (1.1046) time: 0.6285 [2021-03-26 13:25:28 swin_base_patch4_window7_224] INFO: Epoch: [66] [1210/1251] eta: 0:00:25 lr: 0.000883 loss: 3.8420 (3.6626) grad_norm: 1.1293 (1.1056) time: 0.6341 [2021-03-26 13:25:34 swin_base_patch4_window7_224] INFO: Epoch: [66] [1220/1251] eta: 0:00:19 lr: 0.000883 loss: 3.8479 (3.6632) grad_norm: 1.1007 (1.1057) time: 0.6315 [2021-03-26 13:25:40 swin_base_patch4_window7_224] INFO: Epoch: [66] [1230/1251] eta: 0:00:13 lr: 0.000883 loss: 3.7066 (3.6636) grad_norm: 1.0984 (1.1061) time: 0.6204 [2021-03-26 13:25:46 swin_base_patch4_window7_224] INFO: Epoch: [66] [1240/1251] eta: 0:00:06 lr: 0.000883 loss: 3.7078 (3.6638) grad_norm: 1.1537 (1.1071) time: 0.6186 [2021-03-26 13:25:53 swin_base_patch4_window7_224] INFO: Epoch: [66] [1250/1251] eta: 0:00:00 lr: 0.000883 loss: 3.8462 (3.6657) grad_norm: 1.1425 (1.1080) time: 0.6115 [2021-03-26 13:25:58 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:43 loss: 1.0767 (1.0767) acc1: 73.4375 (73.4375) acc5: 90.6250 (90.6250) [2021-03-26 13:26:01 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.0767 (1.1318) acc1: 73.4375 (73.8636) acc5: 92.1875 (91.3352) [2021-03-26 13:26:03 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0720 (1.1362) acc1: 73.4375 (73.5119) acc5: 92.1875 (92.3363) [2021-03-26 13:26:06 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0740 (1.1285) acc1: 73.4375 (73.4879) acc5: 92.1875 (92.1875) [2021-03-26 13:26:08 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0740 (1.1032) acc1: 73.4375 (73.8948) acc5: 92.1875 (92.6067) [2021-03-26 13:26:09 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0484 (1.0862) acc1: 75.0000 (74.3360) acc5: 93.7500 (92.8000) [2021-03-26 13:26:12 swin_base_patch4_window7_224] INFO: * Acc@1 74.376 Acc@5 92.700 loss 1.073 [2021-03-26 13:26:12 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.4% [2021-03-26 13:26:12 swin_base_patch4_window7_224] INFO: Max accuracy: 74.57% [2021-03-26 13:26:17 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 0/1251] eta: 1:29:13 lr: 0.000883 loss: 4.0659 (4.0659) grad_norm: 1.4309 (1.4309) time: 4.2794 [2021-03-26 13:26:23 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 10/1251] eta: 0:20:05 lr: 0.000883 loss: 4.0519 (3.7924) grad_norm: 1.1089 (1.1305) time: 0.9715 [2021-03-26 13:26:29 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 20/1251] eta: 0:16:32 lr: 0.000883 loss: 3.6938 (3.6212) grad_norm: 1.0660 (1.1120) time: 0.6323 [2021-03-26 13:26:36 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 30/1251] eta: 0:15:13 lr: 0.000883 loss: 3.7532 (3.6741) grad_norm: 1.0565 (1.1135) time: 0.6251 [2021-03-26 13:26:42 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 40/1251] eta: 0:14:29 lr: 0.000883 loss: 3.8424 (3.6347) grad_norm: 1.0565 (1.1029) time: 0.6261 [2021-03-26 13:26:48 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 50/1251] eta: 0:14:00 lr: 0.000883 loss: 3.7180 (3.6021) grad_norm: 1.0515 (1.0952) time: 0.6252 [2021-03-26 13:26:54 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 60/1251] eta: 0:13:39 lr: 0.000883 loss: 3.7335 (3.6354) grad_norm: 1.0848 (1.1041) time: 0.6272 [2021-03-26 13:27:01 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 70/1251] eta: 0:13:22 lr: 0.000883 loss: 3.8987 (3.6582) grad_norm: 1.1076 (1.1109) time: 0.6275 [2021-03-26 13:27:07 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 80/1251] eta: 0:13:08 lr: 0.000883 loss: 3.7772 (3.6529) grad_norm: 1.1439 (1.1110) time: 0.6259 [2021-03-26 13:27:13 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 90/1251] eta: 0:12:56 lr: 0.000883 loss: 3.4823 (3.6316) grad_norm: 1.0350 (1.1130) time: 0.6310 [2021-03-26 13:27:19 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 100/1251] eta: 0:12:44 lr: 0.000883 loss: 3.4389 (3.6053) grad_norm: 1.1401 (1.1207) time: 0.6291 [2021-03-26 13:27:26 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 110/1251] eta: 0:12:33 lr: 0.000883 loss: 3.5785 (3.6237) grad_norm: 1.1401 (1.1205) time: 0.6232 [2021-03-26 13:27:32 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 120/1251] eta: 0:12:24 lr: 0.000883 loss: 3.7616 (3.6374) grad_norm: 1.1591 (1.1332) time: 0.6297 [2021-03-26 13:27:38 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 130/1251] eta: 0:12:14 lr: 0.000883 loss: 3.7616 (3.6197) grad_norm: 1.2461 (1.1308) time: 0.6254 [2021-03-26 13:27:45 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 140/1251] eta: 0:12:06 lr: 0.000883 loss: 3.4514 (3.6126) grad_norm: 1.1098 (1.1317) time: 0.6267 [2021-03-26 13:27:51 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 150/1251] eta: 0:11:58 lr: 0.000883 loss: 3.5450 (3.6075) grad_norm: 1.0909 (1.1264) time: 0.6321 [2021-03-26 13:27:57 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 160/1251] eta: 0:11:49 lr: 0.000883 loss: 3.6449 (3.6032) grad_norm: 1.0290 (1.1259) time: 0.6236 [2021-03-26 13:28:03 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 170/1251] eta: 0:11:41 lr: 0.000883 loss: 3.5868 (3.5955) grad_norm: 1.0455 (1.1290) time: 0.6227 [2021-03-26 13:28:10 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 180/1251] eta: 0:11:33 lr: 0.000883 loss: 3.8214 (3.6119) grad_norm: 1.0481 (1.1264) time: 0.6247 [2021-03-26 13:28:16 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 190/1251] eta: 0:11:25 lr: 0.000883 loss: 3.9219 (3.6095) grad_norm: 1.0634 (1.1290) time: 0.6220 [2021-03-26 13:28:22 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 200/1251] eta: 0:11:18 lr: 0.000883 loss: 3.9221 (3.6267) grad_norm: 1.0608 (1.1245) time: 0.6256 [2021-03-26 13:28:28 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 210/1251] eta: 0:11:10 lr: 0.000883 loss: 3.7984 (3.6155) grad_norm: 1.0622 (1.1244) time: 0.6308 [2021-03-26 13:28:35 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 220/1251] eta: 0:11:04 lr: 0.000882 loss: 3.5548 (3.6182) grad_norm: 1.1182 (1.1268) time: 0.6330 [2021-03-26 13:28:41 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 230/1251] eta: 0:10:57 lr: 0.000882 loss: 3.8980 (3.6288) grad_norm: 1.1463 (1.1298) time: 0.6359 [2021-03-26 13:28:47 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 240/1251] eta: 0:10:49 lr: 0.000882 loss: 3.7496 (3.6269) grad_norm: 1.1143 (1.1283) time: 0.6281 [2021-03-26 13:28:54 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 250/1251] eta: 0:10:42 lr: 0.000882 loss: 3.4692 (3.6187) grad_norm: 1.0388 (1.1258) time: 0.6260 [2021-03-26 13:29:00 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 260/1251] eta: 0:10:36 lr: 0.000882 loss: 3.4692 (3.6155) grad_norm: 1.0700 (1.1293) time: 0.6305 [2021-03-26 13:29:06 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 270/1251] eta: 0:10:29 lr: 0.000882 loss: 3.7836 (3.6233) grad_norm: 1.1249 (1.1290) time: 0.6310 [2021-03-26 13:29:13 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 280/1251] eta: 0:10:22 lr: 0.000882 loss: 3.9430 (3.6363) grad_norm: 1.0961 (1.1283) time: 0.6293 [2021-03-26 13:29:19 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 290/1251] eta: 0:10:15 lr: 0.000882 loss: 3.7889 (3.6360) grad_norm: 1.0961 (1.1269) time: 0.6223 [2021-03-26 13:29:25 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 300/1251] eta: 0:10:08 lr: 0.000882 loss: 3.5955 (3.6357) grad_norm: 1.0501 (1.1251) time: 0.6167 [2021-03-26 13:29:31 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 310/1251] eta: 0:10:01 lr: 0.000882 loss: 3.7338 (3.6413) grad_norm: 1.0229 (1.1248) time: 0.6234 [2021-03-26 13:29:37 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 320/1251] eta: 0:09:54 lr: 0.000882 loss: 3.7647 (3.6426) grad_norm: 1.0621 (1.1245) time: 0.6275 [2021-03-26 13:29:44 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 330/1251] eta: 0:09:48 lr: 0.000882 loss: 3.6831 (3.6427) grad_norm: 1.1070 (1.1240) time: 0.6288 [2021-03-26 13:29:50 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 340/1251] eta: 0:09:41 lr: 0.000882 loss: 3.5948 (3.6430) grad_norm: 1.0921 (1.1237) time: 0.6340 [2021-03-26 13:29:56 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 350/1251] eta: 0:09:34 lr: 0.000882 loss: 3.6066 (3.6450) grad_norm: 1.0310 (1.1211) time: 0.6254 [2021-03-26 13:30:03 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 360/1251] eta: 0:09:28 lr: 0.000882 loss: 3.6447 (3.6445) grad_norm: 1.0548 (1.1216) time: 0.6277 [2021-03-26 13:30:09 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 370/1251] eta: 0:09:21 lr: 0.000882 loss: 3.6447 (3.6419) grad_norm: 1.1074 (1.1224) time: 0.6333 [2021-03-26 13:30:15 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 380/1251] eta: 0:09:15 lr: 0.000882 loss: 3.4167 (3.6385) grad_norm: 1.1102 (1.1230) time: 0.6344 [2021-03-26 13:30:22 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 390/1251] eta: 0:09:08 lr: 0.000882 loss: 3.6519 (3.6420) grad_norm: 1.0669 (1.1223) time: 0.6326 [2021-03-26 13:30:28 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 400/1251] eta: 0:09:02 lr: 0.000882 loss: 3.7352 (3.6382) grad_norm: 1.0284 (1.1200) time: 0.6245 [2021-03-26 13:30:34 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 410/1251] eta: 0:08:55 lr: 0.000882 loss: 3.6423 (3.6415) grad_norm: 1.0446 (1.1202) time: 0.6236 [2021-03-26 13:30:40 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 420/1251] eta: 0:08:48 lr: 0.000882 loss: 3.6608 (3.6428) grad_norm: 1.0293 (1.1172) time: 0.6255 [2021-03-26 13:30:47 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 430/1251] eta: 0:08:42 lr: 0.000882 loss: 3.6295 (3.6431) grad_norm: 0.9992 (1.1160) time: 0.6260 [2021-03-26 13:30:53 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 440/1251] eta: 0:08:35 lr: 0.000882 loss: 3.6295 (3.6434) grad_norm: 1.1500 (1.1186) time: 0.6281 [2021-03-26 13:30:59 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 450/1251] eta: 0:08:29 lr: 0.000882 loss: 3.6670 (3.6400) grad_norm: 1.1654 (1.1189) time: 0.6331 [2021-03-26 13:31:06 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 460/1251] eta: 0:08:22 lr: 0.000882 loss: 3.6670 (3.6395) grad_norm: 1.1038 (1.1195) time: 0.6288 [2021-03-26 13:31:12 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 470/1251] eta: 0:08:16 lr: 0.000882 loss: 3.7966 (3.6449) grad_norm: 1.1243 (1.1199) time: 0.6236 [2021-03-26 13:31:18 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 480/1251] eta: 0:08:09 lr: 0.000882 loss: 3.6958 (3.6430) grad_norm: 1.1243 (1.1203) time: 0.6218 [2021-03-26 13:31:24 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 490/1251] eta: 0:08:03 lr: 0.000882 loss: 3.6411 (3.6441) grad_norm: 1.0989 (1.1203) time: 0.6253 [2021-03-26 13:31:31 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 500/1251] eta: 0:07:56 lr: 0.000882 loss: 3.7561 (3.6469) grad_norm: 1.0986 (1.1211) time: 0.6286 [2021-03-26 13:31:37 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 510/1251] eta: 0:07:50 lr: 0.000882 loss: 3.8956 (3.6521) grad_norm: 1.1602 (1.1220) time: 0.6239 [2021-03-26 13:31:43 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 520/1251] eta: 0:07:43 lr: 0.000882 loss: 3.7942 (3.6518) grad_norm: 1.0816 (1.1224) time: 0.6261 [2021-03-26 13:31:49 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 530/1251] eta: 0:07:37 lr: 0.000882 loss: 3.6838 (3.6501) grad_norm: 1.0946 (1.1224) time: 0.6240 [2021-03-26 13:31:55 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 540/1251] eta: 0:07:30 lr: 0.000882 loss: 3.6596 (3.6494) grad_norm: 1.0946 (1.1218) time: 0.6195 [2021-03-26 13:32:02 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 550/1251] eta: 0:07:24 lr: 0.000882 loss: 3.6645 (3.6520) grad_norm: 1.1018 (1.1218) time: 0.6282 [2021-03-26 13:32:08 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 560/1251] eta: 0:07:18 lr: 0.000882 loss: 3.5375 (3.6453) grad_norm: 1.1039 (1.1222) time: 0.6339 [2021-03-26 13:32:14 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 570/1251] eta: 0:07:11 lr: 0.000882 loss: 3.6745 (3.6487) grad_norm: 1.0856 (1.1213) time: 0.6279 [2021-03-26 13:32:21 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 580/1251] eta: 0:07:05 lr: 0.000882 loss: 3.8542 (3.6478) grad_norm: 1.0596 (1.1210) time: 0.6293 [2021-03-26 13:32:27 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 590/1251] eta: 0:06:58 lr: 0.000881 loss: 3.5426 (3.6460) grad_norm: 1.0903 (1.1218) time: 0.6284 [2021-03-26 13:32:33 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 600/1251] eta: 0:06:52 lr: 0.000881 loss: 3.7853 (3.6475) grad_norm: 1.1316 (1.1233) time: 0.6260 [2021-03-26 13:32:40 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 610/1251] eta: 0:06:46 lr: 0.000881 loss: 3.7853 (3.6475) grad_norm: 1.1108 (1.1242) time: 0.6300 [2021-03-26 13:32:46 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 620/1251] eta: 0:06:39 lr: 0.000881 loss: 3.6741 (3.6430) grad_norm: 1.0977 (1.1235) time: 0.6247 [2021-03-26 13:32:52 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 630/1251] eta: 0:06:33 lr: 0.000881 loss: 3.6741 (3.6418) grad_norm: 1.1353 (1.1256) time: 0.6243 [2021-03-26 13:32:58 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 640/1251] eta: 0:06:26 lr: 0.000881 loss: 3.7874 (3.6432) grad_norm: 1.1668 (1.1264) time: 0.6264 [2021-03-26 13:33:05 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 650/1251] eta: 0:06:20 lr: 0.000881 loss: 3.7812 (3.6452) grad_norm: 1.0724 (1.1260) time: 0.6262 [2021-03-26 13:33:11 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 660/1251] eta: 0:06:14 lr: 0.000881 loss: 3.8153 (3.6479) grad_norm: 1.0613 (1.1252) time: 0.6269 [2021-03-26 13:33:17 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 670/1251] eta: 0:06:07 lr: 0.000881 loss: 3.7858 (3.6455) grad_norm: 1.1310 (1.1262) time: 0.6294 [2021-03-26 13:33:23 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 680/1251] eta: 0:06:01 lr: 0.000881 loss: 3.7331 (3.6465) grad_norm: 1.0601 (1.1251) time: 0.6303 [2021-03-26 13:33:30 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 690/1251] eta: 0:05:54 lr: 0.000881 loss: 3.8535 (3.6498) grad_norm: 1.0093 (1.1244) time: 0.6276 [2021-03-26 13:33:36 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 700/1251] eta: 0:05:48 lr: 0.000881 loss: 3.4967 (3.6447) grad_norm: 1.1392 (1.1246) time: 0.6252 [2021-03-26 13:33:42 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 710/1251] eta: 0:05:42 lr: 0.000881 loss: 3.4930 (3.6471) grad_norm: 1.0585 (1.1239) time: 0.6221 [2021-03-26 13:33:48 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 720/1251] eta: 0:05:35 lr: 0.000881 loss: 3.8335 (3.6456) grad_norm: 1.0373 (1.1234) time: 0.6196 [2021-03-26 13:33:55 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 730/1251] eta: 0:05:29 lr: 0.000881 loss: 3.7517 (3.6457) grad_norm: 1.0531 (1.1229) time: 0.6270 [2021-03-26 13:34:01 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 740/1251] eta: 0:05:23 lr: 0.000881 loss: 3.6047 (3.6431) grad_norm: 1.1122 (1.1231) time: 0.6335 [2021-03-26 13:34:07 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 750/1251] eta: 0:05:16 lr: 0.000881 loss: 3.5100 (3.6425) grad_norm: 1.1109 (1.1228) time: 0.6331 [2021-03-26 13:34:14 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 760/1251] eta: 0:05:10 lr: 0.000881 loss: 3.7187 (3.6440) grad_norm: 1.0100 (1.1219) time: 0.6261 [2021-03-26 13:34:20 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 770/1251] eta: 0:05:04 lr: 0.000881 loss: 3.8956 (3.6455) grad_norm: 1.0469 (1.1221) time: 0.6231 [2021-03-26 13:34:26 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 780/1251] eta: 0:04:57 lr: 0.000881 loss: 3.8376 (3.6438) grad_norm: 1.1221 (1.1218) time: 0.6277 [2021-03-26 13:34:32 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 790/1251] eta: 0:04:51 lr: 0.000881 loss: 3.8305 (3.6464) grad_norm: 1.1203 (1.1217) time: 0.6288 [2021-03-26 13:34:39 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 800/1251] eta: 0:04:45 lr: 0.000881 loss: 3.7265 (3.6441) grad_norm: 1.0600 (1.1210) time: 0.6317 [2021-03-26 13:34:45 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 810/1251] eta: 0:04:38 lr: 0.000881 loss: 3.6770 (3.6457) grad_norm: 1.0600 (1.1209) time: 0.6322 [2021-03-26 13:34:51 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 820/1251] eta: 0:04:32 lr: 0.000881 loss: 4.0979 (3.6494) grad_norm: 1.0662 (1.1211) time: 0.6244 [2021-03-26 13:34:58 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 830/1251] eta: 0:04:25 lr: 0.000881 loss: 3.9627 (3.6513) grad_norm: 1.0730 (1.1206) time: 0.6254 [2021-03-26 13:35:04 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 840/1251] eta: 0:04:19 lr: 0.000881 loss: 3.9422 (3.6516) grad_norm: 1.0530 (1.1196) time: 0.6304 [2021-03-26 13:35:10 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 850/1251] eta: 0:04:13 lr: 0.000881 loss: 3.7864 (3.6525) grad_norm: 1.0445 (1.1193) time: 0.6233 [2021-03-26 13:35:16 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 860/1251] eta: 0:04:06 lr: 0.000881 loss: 3.8677 (3.6566) grad_norm: 1.0659 (1.1195) time: 0.6196 [2021-03-26 13:35:22 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 870/1251] eta: 0:04:00 lr: 0.000881 loss: 3.8976 (3.6598) grad_norm: 1.0318 (1.1183) time: 0.6239 [2021-03-26 13:35:29 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 880/1251] eta: 0:03:54 lr: 0.000881 loss: 3.8296 (3.6593) grad_norm: 1.0268 (1.1180) time: 0.6293 [2021-03-26 13:35:35 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 890/1251] eta: 0:03:47 lr: 0.000881 loss: 3.7143 (3.6592) grad_norm: 1.1310 (1.1194) time: 0.6295 [2021-03-26 13:35:41 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 900/1251] eta: 0:03:41 lr: 0.000881 loss: 3.8587 (3.6619) grad_norm: 1.1022 (1.1186) time: 0.6260 [2021-03-26 13:35:48 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 910/1251] eta: 0:03:35 lr: 0.000881 loss: 3.8826 (3.6620) grad_norm: 1.0858 (1.1192) time: 0.6259 [2021-03-26 13:35:54 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 920/1251] eta: 0:03:28 lr: 0.000881 loss: 3.5969 (3.6608) grad_norm: 1.0993 (1.1191) time: 0.6247 [2021-03-26 13:36:00 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 930/1251] eta: 0:03:22 lr: 0.000881 loss: 3.5455 (3.6595) grad_norm: 1.0142 (1.1182) time: 0.6242 [2021-03-26 13:36:06 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 940/1251] eta: 0:03:16 lr: 0.000881 loss: 3.8122 (3.6605) grad_norm: 1.1130 (1.1189) time: 0.6272 [2021-03-26 13:36:13 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 950/1251] eta: 0:03:09 lr: 0.000881 loss: 3.5904 (3.6568) grad_norm: 1.1360 (1.1187) time: 0.6288 [2021-03-26 13:36:19 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 960/1251] eta: 0:03:03 lr: 0.000880 loss: 3.4659 (3.6558) grad_norm: 1.0936 (1.1183) time: 0.6297 [2021-03-26 13:36:25 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 970/1251] eta: 0:02:57 lr: 0.000880 loss: 3.5872 (3.6541) grad_norm: 1.0823 (1.1183) time: 0.6276 [2021-03-26 13:36:32 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 980/1251] eta: 0:02:50 lr: 0.000880 loss: 3.5872 (3.6534) grad_norm: 1.1068 (1.1178) time: 0.6268 [2021-03-26 13:36:38 swin_base_patch4_window7_224] INFO: Epoch: [67] [ 990/1251] eta: 0:02:44 lr: 0.000880 loss: 3.9153 (3.6561) grad_norm: 1.1244 (1.1192) time: 0.6277 [2021-03-26 13:36:44 swin_base_patch4_window7_224] INFO: Epoch: [67] [1000/1251] eta: 0:02:38 lr: 0.000880 loss: 3.8525 (3.6549) grad_norm: 1.1763 (1.1194) time: 0.6335 [2021-03-26 13:36:51 swin_base_patch4_window7_224] INFO: Epoch: [67] [1010/1251] eta: 0:02:32 lr: 0.000880 loss: 3.8307 (3.6562) grad_norm: 1.1093 (1.1197) time: 0.6369 [2021-03-26 13:36:57 swin_base_patch4_window7_224] INFO: Epoch: [67] [1020/1251] eta: 0:02:25 lr: 0.000880 loss: 3.8307 (3.6575) grad_norm: 1.1251 (1.1205) time: 0.6294 [2021-03-26 13:37:03 swin_base_patch4_window7_224] INFO: Epoch: [67] [1030/1251] eta: 0:02:19 lr: 0.000880 loss: 3.9241 (3.6616) grad_norm: 1.1702 (1.1213) time: 0.6234 [2021-03-26 13:37:09 swin_base_patch4_window7_224] INFO: Epoch: [67] [1040/1251] eta: 0:02:13 lr: 0.000880 loss: 3.7689 (3.6621) grad_norm: 1.0893 (1.1208) time: 0.6248 [2021-03-26 13:37:16 swin_base_patch4_window7_224] INFO: Epoch: [67] [1050/1251] eta: 0:02:06 lr: 0.000880 loss: 3.6304 (3.6620) grad_norm: 1.0968 (1.1212) time: 0.6269 [2021-03-26 13:37:22 swin_base_patch4_window7_224] INFO: Epoch: [67] [1060/1251] eta: 0:02:00 lr: 0.000880 loss: 3.5755 (3.6604) grad_norm: 1.1116 (1.1207) time: 0.6248 [2021-03-26 13:37:28 swin_base_patch4_window7_224] INFO: Epoch: [67] [1070/1251] eta: 0:01:54 lr: 0.000880 loss: 3.5186 (3.6604) grad_norm: 1.0170 (1.1202) time: 0.6242 [2021-03-26 13:37:34 swin_base_patch4_window7_224] INFO: Epoch: [67] [1080/1251] eta: 0:01:47 lr: 0.000880 loss: 3.7525 (3.6622) grad_norm: 1.1191 (1.1202) time: 0.6280 [2021-03-26 13:37:41 swin_base_patch4_window7_224] INFO: Epoch: [67] [1090/1251] eta: 0:01:41 lr: 0.000880 loss: 3.7525 (3.6613) grad_norm: 1.1266 (1.1210) time: 0.6294 [2021-03-26 13:37:47 swin_base_patch4_window7_224] INFO: Epoch: [67] [1100/1251] eta: 0:01:35 lr: 0.000880 loss: 3.9273 (3.6649) grad_norm: 1.1252 (1.1207) time: 0.6268 [2021-03-26 13:37:53 swin_base_patch4_window7_224] INFO: Epoch: [67] [1110/1251] eta: 0:01:28 lr: 0.000880 loss: 3.9371 (3.6655) grad_norm: 1.0404 (1.1206) time: 0.6236 [2021-03-26 13:37:59 swin_base_patch4_window7_224] INFO: Epoch: [67] [1120/1251] eta: 0:01:22 lr: 0.000880 loss: 3.7215 (3.6656) grad_norm: 1.1201 (1.1210) time: 0.6258 [2021-03-26 13:38:06 swin_base_patch4_window7_224] INFO: Epoch: [67] [1130/1251] eta: 0:01:16 lr: 0.000880 loss: 3.7353 (3.6664) grad_norm: 1.1296 (1.1212) time: 0.6293 [2021-03-26 13:38:12 swin_base_patch4_window7_224] INFO: Epoch: [67] [1140/1251] eta: 0:01:09 lr: 0.000880 loss: 3.8496 (3.6673) grad_norm: 1.1073 (1.1217) time: 0.6289 [2021-03-26 13:38:18 swin_base_patch4_window7_224] INFO: Epoch: [67] [1150/1251] eta: 0:01:03 lr: 0.000880 loss: 3.7338 (3.6655) grad_norm: 1.0904 (1.1212) time: 0.6260 [2021-03-26 13:38:25 swin_base_patch4_window7_224] INFO: Epoch: [67] [1160/1251] eta: 0:00:57 lr: 0.000880 loss: 3.5853 (3.6658) grad_norm: 1.0674 (1.1208) time: 0.6284 [2021-03-26 13:38:31 swin_base_patch4_window7_224] INFO: Epoch: [67] [1170/1251] eta: 0:00:51 lr: 0.000880 loss: 3.5589 (3.6626) grad_norm: 1.0547 (1.1207) time: 0.6350 [2021-03-26 13:38:37 swin_base_patch4_window7_224] INFO: Epoch: [67] [1180/1251] eta: 0:00:44 lr: 0.000880 loss: 3.6069 (3.6634) grad_norm: 1.0547 (1.1204) time: 0.6286 [2021-03-26 13:38:43 swin_base_patch4_window7_224] INFO: Epoch: [67] [1190/1251] eta: 0:00:38 lr: 0.000880 loss: 3.8801 (3.6659) grad_norm: 1.0520 (1.1204) time: 0.6229 [2021-03-26 13:38:50 swin_base_patch4_window7_224] INFO: Epoch: [67] [1200/1251] eta: 0:00:32 lr: 0.000880 loss: 3.7882 (3.6635) grad_norm: 1.1271 (1.1213) time: 0.6261 [2021-03-26 13:38:56 swin_base_patch4_window7_224] INFO: Epoch: [67] [1210/1251] eta: 0:00:25 lr: 0.000880 loss: 3.4862 (3.6617) grad_norm: 1.1598 (1.1216) time: 0.6254 [2021-03-26 13:39:02 swin_base_patch4_window7_224] INFO: Epoch: [67] [1220/1251] eta: 0:00:19 lr: 0.000880 loss: 3.8038 (3.6633) grad_norm: 1.1381 (1.1217) time: 0.6242 [2021-03-26 13:39:08 swin_base_patch4_window7_224] INFO: Epoch: [67] [1230/1251] eta: 0:00:13 lr: 0.000880 loss: 3.8020 (3.6633) grad_norm: 1.1207 (1.1216) time: 0.6232 [2021-03-26 13:39:14 swin_base_patch4_window7_224] INFO: Epoch: [67] [1240/1251] eta: 0:00:06 lr: 0.000880 loss: 3.5496 (3.6611) grad_norm: 1.1048 (1.1218) time: 0.6176 [2021-03-26 13:39:21 swin_base_patch4_window7_224] INFO: Epoch: [67] [1250/1251] eta: 0:00:00 lr: 0.000880 loss: 3.4234 (3.6589) grad_norm: 1.1385 (1.1220) time: 0.6223 [2021-03-26 13:39:26 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:41 loss: 1.0631 (1.0631) acc1: 71.8750 (71.8750) acc5: 93.7500 (93.7500) [2021-03-26 13:39:30 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.1010 (1.0942) acc1: 73.4375 (73.4375) acc5: 92.1875 (93.3239) [2021-03-26 13:39:32 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.1002 (1.0811) acc1: 73.4375 (74.1815) acc5: 93.7500 (93.6756) [2021-03-26 13:39:33 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1002 (1.0933) acc1: 73.4375 (73.9415) acc5: 93.7500 (93.3468) [2021-03-26 13:39:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0883 (1.0872) acc1: 75.0000 (74.6570) acc5: 92.1875 (92.8354) [2021-03-26 13:39:37 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0883 (1.1098) acc1: 75.0000 (74.1760) acc5: 92.1875 (92.8960) [2021-03-26 13:39:41 swin_base_patch4_window7_224] INFO: * Acc@1 74.674 Acc@5 92.790 loss 1.093 [2021-03-26 13:39:41 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.7% [2021-03-26 13:39:41 swin_base_patch4_window7_224] INFO: Max accuracy: 74.67% [2021-03-26 13:39:45 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 0/1251] eta: 1:23:44 lr: 0.000880 loss: 3.9919 (3.9919) grad_norm: 1.1198 (1.1198) time: 4.0165 [2021-03-26 13:39:52 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 10/1251] eta: 0:19:51 lr: 0.000880 loss: 3.7682 (3.6855) grad_norm: 1.0721 (1.1073) time: 0.9601 [2021-03-26 13:39:58 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 20/1251] eta: 0:16:25 lr: 0.000880 loss: 3.7139 (3.5108) grad_norm: 1.0703 (1.0782) time: 0.6394 [2021-03-26 13:40:04 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 30/1251] eta: 0:15:08 lr: 0.000880 loss: 3.5138 (3.5847) grad_norm: 1.0278 (1.0876) time: 0.6252 [2021-03-26 13:40:11 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 40/1251] eta: 0:14:27 lr: 0.000880 loss: 3.9559 (3.6570) grad_norm: 1.0152 (1.0900) time: 0.6275 [2021-03-26 13:40:17 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 50/1251] eta: 0:13:58 lr: 0.000880 loss: 3.7575 (3.6029) grad_norm: 1.0396 (1.0902) time: 0.6275 [2021-03-26 13:40:23 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 60/1251] eta: 0:13:40 lr: 0.000880 loss: 3.6324 (3.5917) grad_norm: 1.0644 (1.0922) time: 0.6330 [2021-03-26 13:40:30 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 70/1251] eta: 0:13:23 lr: 0.000880 loss: 3.6739 (3.6099) grad_norm: 1.0654 (1.0908) time: 0.6345 [2021-03-26 13:40:36 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 80/1251] eta: 0:13:10 lr: 0.000879 loss: 3.7010 (3.6427) grad_norm: 1.0654 (1.0919) time: 0.6322 [2021-03-26 13:40:42 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 90/1251] eta: 0:12:57 lr: 0.000879 loss: 3.8878 (3.6509) grad_norm: 1.0509 (1.0922) time: 0.6307 [2021-03-26 13:40:48 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 100/1251] eta: 0:12:45 lr: 0.000879 loss: 3.8342 (3.6595) grad_norm: 1.1329 (1.1046) time: 0.6265 [2021-03-26 13:40:55 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 110/1251] eta: 0:12:34 lr: 0.000879 loss: 3.8503 (3.6740) grad_norm: 1.1569 (1.1038) time: 0.6257 [2021-03-26 13:41:01 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 120/1251] eta: 0:12:26 lr: 0.000879 loss: 3.7514 (3.6752) grad_norm: 1.0686 (1.1074) time: 0.6312 [2021-03-26 13:41:07 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 130/1251] eta: 0:12:17 lr: 0.000879 loss: 3.5129 (3.6546) grad_norm: 1.0686 (1.1067) time: 0.6367 [2021-03-26 13:41:14 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 140/1251] eta: 0:12:08 lr: 0.000879 loss: 3.5542 (3.6492) grad_norm: 1.1244 (1.1125) time: 0.6334 [2021-03-26 13:41:20 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 150/1251] eta: 0:12:01 lr: 0.000879 loss: 3.7238 (3.6550) grad_norm: 1.1759 (1.1260) time: 0.6366 [2021-03-26 13:41:26 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 160/1251] eta: 0:11:52 lr: 0.000879 loss: 3.7379 (3.6630) grad_norm: 1.1716 (1.1258) time: 0.6359 [2021-03-26 13:41:33 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 170/1251] eta: 0:11:44 lr: 0.000879 loss: 3.7402 (3.6681) grad_norm: 1.0894 (1.1329) time: 0.6304 [2021-03-26 13:41:39 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 180/1251] eta: 0:11:36 lr: 0.000879 loss: 3.7383 (3.6589) grad_norm: 1.1068 (1.1313) time: 0.6282 [2021-03-26 13:41:45 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 190/1251] eta: 0:11:28 lr: 0.000879 loss: 3.6386 (3.6529) grad_norm: 1.0442 (1.1256) time: 0.6209 [2021-03-26 13:41:52 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 200/1251] eta: 0:11:21 lr: 0.000879 loss: 3.6386 (3.6391) grad_norm: 1.0527 (1.1245) time: 0.6256 [2021-03-26 13:41:58 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 210/1251] eta: 0:11:13 lr: 0.000879 loss: 3.6621 (3.6400) grad_norm: 1.1029 (1.1284) time: 0.6266 [2021-03-26 13:42:04 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 220/1251] eta: 0:11:05 lr: 0.000879 loss: 3.8525 (3.6336) grad_norm: 1.1195 (1.1282) time: 0.6178 [2021-03-26 13:42:10 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 230/1251] eta: 0:10:58 lr: 0.000879 loss: 3.5273 (3.6305) grad_norm: 1.1204 (1.1314) time: 0.6263 [2021-03-26 13:42:17 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 240/1251] eta: 0:10:51 lr: 0.000879 loss: 3.3905 (3.6133) grad_norm: 1.1342 (1.1307) time: 0.6311 [2021-03-26 13:42:23 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 250/1251] eta: 0:10:43 lr: 0.000879 loss: 3.4961 (3.6249) grad_norm: 1.0176 (1.1277) time: 0.6245 [2021-03-26 13:42:29 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 260/1251] eta: 0:10:36 lr: 0.000879 loss: 3.7087 (3.6232) grad_norm: 1.0369 (1.1267) time: 0.6226 [2021-03-26 13:42:35 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 270/1251] eta: 0:10:29 lr: 0.000879 loss: 3.7087 (3.6281) grad_norm: 1.1095 (1.1272) time: 0.6201 [2021-03-26 13:42:41 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 280/1251] eta: 0:10:22 lr: 0.000879 loss: 3.8409 (3.6246) grad_norm: 1.1318 (1.1303) time: 0.6222 [2021-03-26 13:42:48 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 290/1251] eta: 0:10:15 lr: 0.000879 loss: 3.8409 (3.6285) grad_norm: 1.1612 (1.1315) time: 0.6247 [2021-03-26 13:42:54 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 300/1251] eta: 0:10:08 lr: 0.000879 loss: 3.8311 (3.6284) grad_norm: 1.1957 (1.1332) time: 0.6203 [2021-03-26 13:43:00 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 310/1251] eta: 0:10:01 lr: 0.000879 loss: 3.3579 (3.6212) grad_norm: 1.1949 (1.1332) time: 0.6225 [2021-03-26 13:43:06 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 320/1251] eta: 0:09:54 lr: 0.000879 loss: 3.5532 (3.6255) grad_norm: 1.1055 (1.1332) time: 0.6261 [2021-03-26 13:43:13 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 330/1251] eta: 0:09:48 lr: 0.000879 loss: 3.7100 (3.6221) grad_norm: 1.0654 (1.1313) time: 0.6309 [2021-03-26 13:43:19 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 340/1251] eta: 0:09:41 lr: 0.000879 loss: 3.7100 (3.6249) grad_norm: 1.0851 (1.1324) time: 0.6332 [2021-03-26 13:43:25 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 350/1251] eta: 0:09:35 lr: 0.000879 loss: 3.5947 (3.6176) grad_norm: 1.2041 (1.1350) time: 0.6291 [2021-03-26 13:43:32 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 360/1251] eta: 0:09:28 lr: 0.000879 loss: 3.5792 (3.6154) grad_norm: 1.0924 (1.1335) time: 0.6291 [2021-03-26 13:43:38 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 370/1251] eta: 0:09:22 lr: 0.000879 loss: 3.9617 (3.6252) grad_norm: 1.0170 (1.1316) time: 0.6354 [2021-03-26 13:43:44 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 380/1251] eta: 0:09:15 lr: 0.000879 loss: 4.0376 (3.6311) grad_norm: 1.0613 (1.1316) time: 0.6345 [2021-03-26 13:43:51 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 390/1251] eta: 0:09:08 lr: 0.000879 loss: 3.9685 (3.6334) grad_norm: 1.1898 (1.1342) time: 0.6245 [2021-03-26 13:43:57 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 400/1251] eta: 0:09:02 lr: 0.000879 loss: 3.8829 (3.6365) grad_norm: 1.1087 (1.1327) time: 0.6210 [2021-03-26 13:44:03 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 410/1251] eta: 0:08:55 lr: 0.000879 loss: 3.7181 (3.6369) grad_norm: 1.0496 (1.1329) time: 0.6253 [2021-03-26 13:44:09 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 420/1251] eta: 0:08:48 lr: 0.000879 loss: 3.7097 (3.6381) grad_norm: 1.1282 (1.1322) time: 0.6263 [2021-03-26 13:44:16 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 430/1251] eta: 0:08:42 lr: 0.000879 loss: 3.7963 (3.6345) grad_norm: 1.1282 (1.1322) time: 0.6233 [2021-03-26 13:44:22 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 440/1251] eta: 0:08:35 lr: 0.000879 loss: 3.5154 (3.6295) grad_norm: 1.1023 (1.1325) time: 0.6280 [2021-03-26 13:44:28 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 450/1251] eta: 0:08:29 lr: 0.000878 loss: 3.4731 (3.6286) grad_norm: 1.0502 (1.1314) time: 0.6265 [2021-03-26 13:44:34 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 460/1251] eta: 0:08:22 lr: 0.000878 loss: 3.9377 (3.6344) grad_norm: 0.9885 (1.1297) time: 0.6205 [2021-03-26 13:44:41 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 470/1251] eta: 0:08:16 lr: 0.000878 loss: 3.8449 (3.6344) grad_norm: 1.0500 (1.1278) time: 0.6244 [2021-03-26 13:44:47 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 480/1251] eta: 0:08:09 lr: 0.000878 loss: 3.7249 (3.6387) grad_norm: 1.0592 (1.1281) time: 0.6233 [2021-03-26 13:44:53 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 490/1251] eta: 0:08:02 lr: 0.000878 loss: 3.8264 (3.6427) grad_norm: 1.0420 (1.1262) time: 0.6174 [2021-03-26 13:44:59 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 500/1251] eta: 0:07:56 lr: 0.000878 loss: 3.9644 (3.6490) grad_norm: 1.0615 (1.1260) time: 0.6216 [2021-03-26 13:45:05 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 510/1251] eta: 0:07:49 lr: 0.000878 loss: 3.8804 (3.6483) grad_norm: 1.0719 (1.1256) time: 0.6242 [2021-03-26 13:45:12 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 520/1251] eta: 0:07:43 lr: 0.000878 loss: 3.8484 (3.6484) grad_norm: 1.0719 (1.1266) time: 0.6259 [2021-03-26 13:45:18 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 530/1251] eta: 0:07:37 lr: 0.000878 loss: 3.8527 (3.6519) grad_norm: 1.0787 (1.1268) time: 0.6310 [2021-03-26 13:45:24 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 540/1251] eta: 0:07:30 lr: 0.000878 loss: 3.8303 (3.6500) grad_norm: 1.0792 (1.1262) time: 0.6282 [2021-03-26 13:45:31 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 550/1251] eta: 0:07:24 lr: 0.000878 loss: 3.4139 (3.6447) grad_norm: 1.0675 (1.1252) time: 0.6360 [2021-03-26 13:45:37 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 560/1251] eta: 0:07:18 lr: 0.000878 loss: 3.8015 (3.6477) grad_norm: 1.0659 (1.1268) time: 0.6372 [2021-03-26 13:45:43 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 570/1251] eta: 0:07:11 lr: 0.000878 loss: 3.8268 (3.6471) grad_norm: 1.0493 (1.1258) time: 0.6287 [2021-03-26 13:45:49 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 580/1251] eta: 0:07:05 lr: 0.000878 loss: 3.6597 (3.6471) grad_norm: 1.0477 (1.1250) time: 0.6250 [2021-03-26 13:45:56 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 590/1251] eta: 0:06:58 lr: 0.000878 loss: 3.7234 (3.6469) grad_norm: 1.1385 (1.1269) time: 0.6215 [2021-03-26 13:46:02 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 600/1251] eta: 0:06:52 lr: 0.000878 loss: 3.7647 (3.6448) grad_norm: 1.1587 (1.1266) time: 0.6279 [2021-03-26 13:46:08 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 610/1251] eta: 0:06:45 lr: 0.000878 loss: 3.4859 (3.6409) grad_norm: 1.0666 (1.1270) time: 0.6286 [2021-03-26 13:46:15 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 620/1251] eta: 0:06:39 lr: 0.000878 loss: 3.4859 (3.6427) grad_norm: 1.1018 (1.1265) time: 0.6325 [2021-03-26 13:46:21 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 630/1251] eta: 0:06:33 lr: 0.000878 loss: 3.7882 (3.6430) grad_norm: 1.1083 (1.1265) time: 0.6318 [2021-03-26 13:46:27 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 640/1251] eta: 0:06:26 lr: 0.000878 loss: 3.7940 (3.6433) grad_norm: 1.1083 (1.1265) time: 0.6280 [2021-03-26 13:46:34 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 650/1251] eta: 0:06:20 lr: 0.000878 loss: 3.9564 (3.6473) grad_norm: 1.1224 (1.1278) time: 0.6332 [2021-03-26 13:46:40 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 660/1251] eta: 0:06:14 lr: 0.000878 loss: 3.7331 (3.6463) grad_norm: 1.0697 (1.1273) time: 0.6275 [2021-03-26 13:46:46 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 670/1251] eta: 0:06:07 lr: 0.000878 loss: 3.4757 (3.6446) grad_norm: 1.0541 (1.1269) time: 0.6218 [2021-03-26 13:46:52 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 680/1251] eta: 0:06:01 lr: 0.000878 loss: 3.7271 (3.6463) grad_norm: 1.1051 (1.1289) time: 0.6305 [2021-03-26 13:46:59 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 690/1251] eta: 0:05:55 lr: 0.000878 loss: 3.8943 (3.6493) grad_norm: 1.1156 (1.1285) time: 0.6337 [2021-03-26 13:47:05 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 700/1251] eta: 0:05:48 lr: 0.000878 loss: 3.8119 (3.6503) grad_norm: 1.0473 (1.1286) time: 0.6290 [2021-03-26 13:47:11 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 710/1251] eta: 0:05:42 lr: 0.000878 loss: 3.8117 (3.6513) grad_norm: 1.1063 (1.1283) time: 0.6327 [2021-03-26 13:47:18 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 720/1251] eta: 0:05:36 lr: 0.000878 loss: 3.6927 (3.6504) grad_norm: 1.1057 (1.1286) time: 0.6396 [2021-03-26 13:47:24 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 730/1251] eta: 0:05:29 lr: 0.000878 loss: 3.5312 (3.6487) grad_norm: 1.0045 (1.1268) time: 0.6379 [2021-03-26 13:47:30 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 740/1251] eta: 0:05:23 lr: 0.000878 loss: 3.5312 (3.6461) grad_norm: 1.0616 (1.1273) time: 0.6299 [2021-03-26 13:47:37 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 750/1251] eta: 0:05:17 lr: 0.000878 loss: 3.5700 (3.6474) grad_norm: 1.1390 (1.1278) time: 0.6407 [2021-03-26 13:47:43 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 760/1251] eta: 0:05:10 lr: 0.000878 loss: 3.9865 (3.6483) grad_norm: 1.0733 (1.1280) time: 0.6388 [2021-03-26 13:47:50 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 770/1251] eta: 0:05:04 lr: 0.000878 loss: 3.8736 (3.6491) grad_norm: 1.1106 (1.1285) time: 0.6362 [2021-03-26 13:47:56 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 780/1251] eta: 0:04:58 lr: 0.000878 loss: 3.8309 (3.6525) grad_norm: 1.1106 (1.1282) time: 0.6357 [2021-03-26 13:48:02 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 790/1251] eta: 0:04:51 lr: 0.000878 loss: 3.9641 (3.6547) grad_norm: 1.0580 (1.1278) time: 0.6279 [2021-03-26 13:48:08 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 800/1251] eta: 0:04:45 lr: 0.000878 loss: 3.9057 (3.6551) grad_norm: 1.0579 (1.1272) time: 0.6268 [2021-03-26 13:48:15 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 810/1251] eta: 0:04:39 lr: 0.000878 loss: 3.7870 (3.6550) grad_norm: 1.1241 (1.1273) time: 0.6213 [2021-03-26 13:48:21 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 820/1251] eta: 0:04:32 lr: 0.000877 loss: 3.7409 (3.6523) grad_norm: 1.1473 (1.1269) time: 0.6212 [2021-03-26 13:48:27 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 830/1251] eta: 0:04:26 lr: 0.000877 loss: 3.2373 (3.6489) grad_norm: 1.0514 (1.1268) time: 0.6144 [2021-03-26 13:48:33 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 840/1251] eta: 0:04:19 lr: 0.000877 loss: 3.5319 (3.6484) grad_norm: 1.0640 (1.1279) time: 0.6217 [2021-03-26 13:48:40 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 850/1251] eta: 0:04:13 lr: 0.000877 loss: 3.6210 (3.6480) grad_norm: 1.1327 (1.1277) time: 0.6341 [2021-03-26 13:48:46 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 860/1251] eta: 0:04:07 lr: 0.000877 loss: 3.6492 (3.6472) grad_norm: 1.0927 (1.1277) time: 0.6353 [2021-03-26 13:48:52 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 870/1251] eta: 0:04:01 lr: 0.000877 loss: 3.6492 (3.6457) grad_norm: 1.1410 (1.1287) time: 0.6369 [2021-03-26 13:48:59 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 880/1251] eta: 0:03:54 lr: 0.000877 loss: 3.7544 (3.6463) grad_norm: 1.1323 (1.1284) time: 0.6332 [2021-03-26 13:49:05 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 890/1251] eta: 0:03:48 lr: 0.000877 loss: 3.7814 (3.6475) grad_norm: 1.0870 (1.1285) time: 0.6289 [2021-03-26 13:49:11 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 900/1251] eta: 0:03:42 lr: 0.000877 loss: 3.6049 (3.6463) grad_norm: 1.1053 (1.1279) time: 0.6282 [2021-03-26 13:49:18 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 910/1251] eta: 0:03:35 lr: 0.000877 loss: 3.6256 (3.6476) grad_norm: 1.0551 (1.1273) time: 0.6293 [2021-03-26 13:49:24 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 920/1251] eta: 0:03:29 lr: 0.000877 loss: 3.6888 (3.6471) grad_norm: 1.0520 (1.1268) time: 0.6287 [2021-03-26 13:49:30 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 930/1251] eta: 0:03:23 lr: 0.000877 loss: 3.6285 (3.6471) grad_norm: 1.0946 (1.1271) time: 0.6320 [2021-03-26 13:49:36 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 940/1251] eta: 0:03:16 lr: 0.000877 loss: 3.8179 (3.6485) grad_norm: 1.2003 (1.1281) time: 0.6299 [2021-03-26 13:49:43 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 950/1251] eta: 0:03:10 lr: 0.000877 loss: 3.7309 (3.6481) grad_norm: 1.1867 (1.1277) time: 0.6247 [2021-03-26 13:49:49 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 960/1251] eta: 0:03:03 lr: 0.000877 loss: 3.7300 (3.6486) grad_norm: 1.1059 (1.1277) time: 0.6300 [2021-03-26 13:49:55 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 970/1251] eta: 0:02:57 lr: 0.000877 loss: 3.8451 (3.6467) grad_norm: 1.1018 (1.1278) time: 0.6269 [2021-03-26 13:50:02 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 980/1251] eta: 0:02:51 lr: 0.000877 loss: 3.2904 (3.6413) grad_norm: 1.0630 (1.1275) time: 0.6233 [2021-03-26 13:50:08 swin_base_patch4_window7_224] INFO: Epoch: [68] [ 990/1251] eta: 0:02:44 lr: 0.000877 loss: 3.5286 (3.6422) grad_norm: 1.0396 (1.1269) time: 0.6221 [2021-03-26 13:50:14 swin_base_patch4_window7_224] INFO: Epoch: [68] [1000/1251] eta: 0:02:38 lr: 0.000877 loss: 3.5286 (3.6393) grad_norm: 1.0685 (1.1264) time: 0.6248 [2021-03-26 13:50:20 swin_base_patch4_window7_224] INFO: Epoch: [68] [1010/1251] eta: 0:02:32 lr: 0.000877 loss: 3.4472 (3.6392) grad_norm: 1.1389 (1.1275) time: 0.6339 [2021-03-26 13:50:27 swin_base_patch4_window7_224] INFO: Epoch: [68] [1020/1251] eta: 0:02:25 lr: 0.000877 loss: 3.7038 (3.6390) grad_norm: 1.1620 (1.1272) time: 0.6280 [2021-03-26 13:50:33 swin_base_patch4_window7_224] INFO: Epoch: [68] [1030/1251] eta: 0:02:19 lr: 0.000877 loss: 3.6958 (3.6401) grad_norm: 1.1309 (1.1273) time: 0.6258 [2021-03-26 13:50:39 swin_base_patch4_window7_224] INFO: Epoch: [68] [1040/1251] eta: 0:02:13 lr: 0.000877 loss: 3.6550 (3.6391) grad_norm: 1.0751 (1.1267) time: 0.6268 [2021-03-26 13:50:45 swin_base_patch4_window7_224] INFO: Epoch: [68] [1050/1251] eta: 0:02:06 lr: 0.000877 loss: 3.6048 (3.6370) grad_norm: 1.1013 (1.1276) time: 0.6212 [2021-03-26 13:50:52 swin_base_patch4_window7_224] INFO: Epoch: [68] [1060/1251] eta: 0:02:00 lr: 0.000877 loss: 3.6100 (3.6390) grad_norm: 1.1013 (1.1275) time: 0.6217 [2021-03-26 13:50:58 swin_base_patch4_window7_224] INFO: Epoch: [68] [1070/1251] eta: 0:01:54 lr: 0.000877 loss: 3.5294 (3.6374) grad_norm: 0.9956 (1.1264) time: 0.6181 [2021-03-26 13:51:04 swin_base_patch4_window7_224] INFO: Epoch: [68] [1080/1251] eta: 0:01:47 lr: 0.000877 loss: 3.5214 (3.6363) grad_norm: 1.0043 (1.1265) time: 0.6224 [2021-03-26 13:51:10 swin_base_patch4_window7_224] INFO: Epoch: [68] [1090/1251] eta: 0:01:41 lr: 0.000877 loss: 3.8869 (3.6367) grad_norm: 1.1494 (1.1272) time: 0.6311 [2021-03-26 13:51:17 swin_base_patch4_window7_224] INFO: Epoch: [68] [1100/1251] eta: 0:01:35 lr: 0.000877 loss: 3.6061 (3.6341) grad_norm: 1.1483 (1.1272) time: 0.6281 [2021-03-26 13:51:23 swin_base_patch4_window7_224] INFO: Epoch: [68] [1110/1251] eta: 0:01:29 lr: 0.000877 loss: 3.3597 (3.6346) grad_norm: 1.1486 (1.1282) time: 0.6279 [2021-03-26 13:51:29 swin_base_patch4_window7_224] INFO: Epoch: [68] [1120/1251] eta: 0:01:22 lr: 0.000877 loss: 3.6576 (3.6356) grad_norm: 1.1486 (1.1280) time: 0.6334 [2021-03-26 13:51:35 swin_base_patch4_window7_224] INFO: Epoch: [68] [1130/1251] eta: 0:01:16 lr: 0.000877 loss: 3.6283 (3.6340) grad_norm: 1.1484 (1.1282) time: 0.6308 [2021-03-26 13:51:42 swin_base_patch4_window7_224] INFO: Epoch: [68] [1140/1251] eta: 0:01:10 lr: 0.000877 loss: 3.5841 (3.6343) grad_norm: 1.1423 (1.1285) time: 0.6244 [2021-03-26 13:51:48 swin_base_patch4_window7_224] INFO: Epoch: [68] [1150/1251] eta: 0:01:03 lr: 0.000877 loss: 3.7812 (3.6335) grad_norm: 1.1119 (1.1284) time: 0.6239 [2021-03-26 13:51:54 swin_base_patch4_window7_224] INFO: Epoch: [68] [1160/1251] eta: 0:00:57 lr: 0.000877 loss: 3.6650 (3.6316) grad_norm: 1.0514 (1.1276) time: 0.6267 [2021-03-26 13:52:00 swin_base_patch4_window7_224] INFO: Epoch: [68] [1170/1251] eta: 0:00:51 lr: 0.000877 loss: 3.3944 (3.6304) grad_norm: 1.0384 (inf) time: 0.6199 [2021-03-26 13:52:07 swin_base_patch4_window7_224] INFO: Epoch: [68] [1180/1251] eta: 0:00:44 lr: 0.000876 loss: 3.4227 (3.6302) grad_norm: 1.1244 (inf) time: 0.6152 [2021-03-26 13:52:13 swin_base_patch4_window7_224] INFO: Epoch: [68] [1190/1251] eta: 0:00:38 lr: 0.000876 loss: 3.7235 (3.6312) grad_norm: 1.1137 (inf) time: 0.6200 [2021-03-26 13:52:19 swin_base_patch4_window7_224] INFO: Epoch: [68] [1200/1251] eta: 0:00:32 lr: 0.000876 loss: 3.8318 (3.6297) grad_norm: 1.0319 (inf) time: 0.6250 [2021-03-26 13:52:25 swin_base_patch4_window7_224] INFO: Epoch: [68] [1210/1251] eta: 0:00:25 lr: 0.000876 loss: 3.4513 (3.6282) grad_norm: 1.0546 (inf) time: 0.6283 [2021-03-26 13:52:32 swin_base_patch4_window7_224] INFO: Epoch: [68] [1220/1251] eta: 0:00:19 lr: 0.000876 loss: 3.3380 (3.6253) grad_norm: 1.0800 (inf) time: 0.6236 [2021-03-26 13:52:38 swin_base_patch4_window7_224] INFO: Epoch: [68] [1230/1251] eta: 0:00:13 lr: 0.000876 loss: 3.6712 (3.6276) grad_norm: 1.0556 (inf) time: 0.6250 [2021-03-26 13:52:44 swin_base_patch4_window7_224] INFO: Epoch: [68] [1240/1251] eta: 0:00:06 lr: 0.000876 loss: 3.7977 (3.6284) grad_norm: 1.1434 (inf) time: 0.6249 [2021-03-26 13:52:50 swin_base_patch4_window7_224] INFO: Epoch: [68] [1250/1251] eta: 0:00:00 lr: 0.000876 loss: 3.7977 (3.6295) grad_norm: 1.1771 (inf) time: 0.6123 [2021-03-26 13:52:57 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:09 loss: 0.9265 (0.9265) acc1: 81.2500 (81.2500) acc5: 95.3125 (95.3125) [2021-03-26 13:52:58 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 1.1149 (1.0800) acc1: 73.4375 (74.7159) acc5: 92.1875 (92.7557) [2021-03-26 13:53:01 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0559 (1.0668) acc1: 73.4375 (74.2560) acc5: 92.1875 (92.7083) [2021-03-26 13:53:04 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0559 (1.0793) acc1: 73.4375 (74.1431) acc5: 92.1875 (92.5907) [2021-03-26 13:53:06 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0229 (1.0500) acc1: 75.0000 (75.1524) acc5: 93.7500 (92.9878) [2021-03-26 13:53:07 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0360 (1.0868) acc1: 73.4375 (74.0160) acc5: 93.7500 (92.7360) [2021-03-26 13:53:10 swin_base_patch4_window7_224] INFO: * Acc@1 74.652 Acc@5 92.882 loss 1.073 [2021-03-26 13:53:10 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.7% [2021-03-26 13:53:10 swin_base_patch4_window7_224] INFO: Max accuracy: 74.67% [2021-03-26 13:53:15 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 0/1251] eta: 1:34:51 lr: 0.000876 loss: 3.4328 (3.4328) grad_norm: 1.2311 (1.2311) time: 4.5497 [2021-03-26 13:53:21 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 10/1251] eta: 0:20:45 lr: 0.000876 loss: 3.9119 (3.8396) grad_norm: 1.2311 (1.2271) time: 1.0038 [2021-03-26 13:53:27 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 20/1251] eta: 0:16:56 lr: 0.000876 loss: 3.8146 (3.7951) grad_norm: 1.1461 (1.1647) time: 0.6400 [2021-03-26 13:53:34 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 30/1251] eta: 0:15:32 lr: 0.000876 loss: 3.6798 (3.7173) grad_norm: 1.0441 (1.1515) time: 0.6322 [2021-03-26 13:53:40 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 40/1251] eta: 0:14:44 lr: 0.000876 loss: 3.4942 (3.6260) grad_norm: 1.1669 (1.1711) time: 0.6307 [2021-03-26 13:53:46 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 50/1251] eta: 0:14:13 lr: 0.000876 loss: 3.6799 (3.6359) grad_norm: 1.1345 (1.1601) time: 0.6273 [2021-03-26 13:53:52 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 60/1251] eta: 0:13:49 lr: 0.000876 loss: 3.7459 (3.6540) grad_norm: 1.1113 (1.1596) time: 0.6258 [2021-03-26 13:53:59 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 70/1251] eta: 0:13:32 lr: 0.000876 loss: 3.7447 (3.6534) grad_norm: 1.1245 (1.1651) time: 0.6295 [2021-03-26 13:54:05 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 80/1251] eta: 0:13:17 lr: 0.000876 loss: 3.5366 (3.6371) grad_norm: 1.1014 (1.1583) time: 0.6358 [2021-03-26 13:54:11 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 90/1251] eta: 0:13:04 lr: 0.000876 loss: 3.5361 (3.6219) grad_norm: 1.1240 (1.1619) time: 0.6327 [2021-03-26 13:54:18 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 100/1251] eta: 0:12:52 lr: 0.000876 loss: 3.7586 (3.6456) grad_norm: 1.2010 (1.1626) time: 0.6295 [2021-03-26 13:54:24 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 110/1251] eta: 0:12:40 lr: 0.000876 loss: 3.9177 (3.6594) grad_norm: 1.1378 (1.1583) time: 0.6258 [2021-03-26 13:54:30 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 120/1251] eta: 0:12:30 lr: 0.000876 loss: 3.7149 (3.6577) grad_norm: 1.0940 (1.1535) time: 0.6277 [2021-03-26 13:54:37 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 130/1251] eta: 0:12:21 lr: 0.000876 loss: 3.8109 (3.6797) grad_norm: 1.0014 (1.1396) time: 0.6326 [2021-03-26 13:54:43 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 140/1251] eta: 0:12:11 lr: 0.000876 loss: 3.7571 (3.6635) grad_norm: 1.0014 (1.1469) time: 0.6278 [2021-03-26 13:54:49 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 150/1251] eta: 0:12:03 lr: 0.000876 loss: 3.5075 (3.6539) grad_norm: 1.2123 (1.1541) time: 0.6286 [2021-03-26 13:54:56 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 160/1251] eta: 0:11:55 lr: 0.000876 loss: 3.5574 (3.6493) grad_norm: 1.2092 (1.1555) time: 0.6326 [2021-03-26 13:55:02 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 170/1251] eta: 0:11:46 lr: 0.000876 loss: 3.5928 (3.6444) grad_norm: 1.1076 (1.1513) time: 0.6305 [2021-03-26 13:55:08 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 180/1251] eta: 0:11:39 lr: 0.000876 loss: 3.3232 (3.6208) grad_norm: 1.0645 (1.1457) time: 0.6303 [2021-03-26 13:55:14 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 190/1251] eta: 0:11:31 lr: 0.000876 loss: 3.4461 (3.6094) grad_norm: 1.0532 (1.1422) time: 0.6309 [2021-03-26 13:55:21 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 200/1251] eta: 0:11:23 lr: 0.000876 loss: 3.6601 (3.6128) grad_norm: 1.0924 (1.1417) time: 0.6296 [2021-03-26 13:55:27 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 210/1251] eta: 0:11:16 lr: 0.000876 loss: 3.6893 (3.6184) grad_norm: 1.1212 (1.1388) time: 0.6290 [2021-03-26 13:55:33 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 220/1251] eta: 0:11:08 lr: 0.000876 loss: 3.7353 (3.6109) grad_norm: 1.1212 (1.1404) time: 0.6304 [2021-03-26 13:55:40 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 230/1251] eta: 0:11:01 lr: 0.000876 loss: 3.8876 (3.6170) grad_norm: 1.0953 (1.1379) time: 0.6303 [2021-03-26 13:55:46 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 240/1251] eta: 0:10:53 lr: 0.000876 loss: 3.7437 (3.6033) grad_norm: 1.0531 (1.1364) time: 0.6251 [2021-03-26 13:55:52 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 250/1251] eta: 0:10:47 lr: 0.000876 loss: 3.5658 (3.5955) grad_norm: 1.0815 (1.1420) time: 0.6312 [2021-03-26 13:55:59 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 260/1251] eta: 0:10:39 lr: 0.000876 loss: 3.7184 (3.6032) grad_norm: 1.1170 (1.1437) time: 0.6326 [2021-03-26 13:56:05 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 270/1251] eta: 0:10:32 lr: 0.000876 loss: 3.6048 (3.6002) grad_norm: 1.1652 (1.1454) time: 0.6207 [2021-03-26 13:56:11 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 280/1251] eta: 0:10:25 lr: 0.000876 loss: 3.5665 (3.5952) grad_norm: 1.0613 (1.1427) time: 0.6188 [2021-03-26 13:56:17 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 290/1251] eta: 0:10:18 lr: 0.000876 loss: 3.8570 (3.6031) grad_norm: 1.0238 (1.1415) time: 0.6240 [2021-03-26 13:56:23 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 300/1251] eta: 0:10:10 lr: 0.000875 loss: 3.7699 (3.6030) grad_norm: 1.1709 (1.1467) time: 0.6251 [2021-03-26 13:56:30 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 310/1251] eta: 0:10:03 lr: 0.000875 loss: 3.7167 (3.6003) grad_norm: 1.1709 (1.1478) time: 0.6234 [2021-03-26 13:56:36 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 320/1251] eta: 0:09:57 lr: 0.000875 loss: 3.7161 (3.5999) grad_norm: 1.1348 (1.1492) time: 0.6263 [2021-03-26 13:56:42 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 330/1251] eta: 0:09:50 lr: 0.000875 loss: 3.6552 (3.5933) grad_norm: 1.0696 (1.1495) time: 0.6327 [2021-03-26 13:56:49 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 340/1251] eta: 0:09:43 lr: 0.000875 loss: 3.5814 (3.5945) grad_norm: 1.0504 (1.1473) time: 0.6321 [2021-03-26 13:56:55 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 350/1251] eta: 0:09:37 lr: 0.000875 loss: 3.5814 (3.5920) grad_norm: 1.0934 (1.1465) time: 0.6326 [2021-03-26 13:57:01 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 360/1251] eta: 0:09:30 lr: 0.000875 loss: 3.6259 (3.5891) grad_norm: 1.0635 (1.1451) time: 0.6355 [2021-03-26 13:57:08 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 370/1251] eta: 0:09:23 lr: 0.000875 loss: 3.5589 (3.5829) grad_norm: 1.0254 (1.1416) time: 0.6269 [2021-03-26 13:57:14 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 380/1251] eta: 0:09:17 lr: 0.000875 loss: 3.2431 (3.5761) grad_norm: 1.0655 (1.1420) time: 0.6275 [2021-03-26 13:57:20 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 390/1251] eta: 0:09:10 lr: 0.000875 loss: 3.6188 (3.5820) grad_norm: 1.1429 (1.1436) time: 0.6319 [2021-03-26 13:57:26 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 400/1251] eta: 0:09:03 lr: 0.000875 loss: 3.7359 (3.5851) grad_norm: 1.1195 (1.1428) time: 0.6258 [2021-03-26 13:57:33 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 410/1251] eta: 0:08:57 lr: 0.000875 loss: 3.6637 (3.5852) grad_norm: 1.0705 (1.1441) time: 0.6250 [2021-03-26 13:57:39 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 420/1251] eta: 0:08:50 lr: 0.000875 loss: 3.5390 (3.5815) grad_norm: 1.1535 (1.1443) time: 0.6283 [2021-03-26 13:57:45 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 430/1251] eta: 0:08:44 lr: 0.000875 loss: 3.5779 (3.5846) grad_norm: 1.0957 (1.1442) time: 0.6314 [2021-03-26 13:57:51 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 440/1251] eta: 0:08:37 lr: 0.000875 loss: 3.7283 (3.5844) grad_norm: 1.0437 (1.1417) time: 0.6270 [2021-03-26 13:57:58 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 450/1251] eta: 0:08:30 lr: 0.000875 loss: 3.6243 (3.5808) grad_norm: 1.0479 (1.1415) time: 0.6232 [2021-03-26 13:58:04 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 460/1251] eta: 0:08:24 lr: 0.000875 loss: 3.4890 (3.5768) grad_norm: 1.1193 (1.1420) time: 0.6267 [2021-03-26 13:58:10 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 470/1251] eta: 0:08:17 lr: 0.000875 loss: 3.8128 (3.5846) grad_norm: 1.0629 (1.1405) time: 0.6273 [2021-03-26 13:58:17 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 480/1251] eta: 0:08:11 lr: 0.000875 loss: 3.7869 (3.5821) grad_norm: 1.0633 (1.1407) time: 0.6246 [2021-03-26 13:58:23 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 490/1251] eta: 0:08:04 lr: 0.000875 loss: 3.5234 (3.5796) grad_norm: 1.0763 (1.1394) time: 0.6300 [2021-03-26 13:58:29 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 500/1251] eta: 0:07:58 lr: 0.000875 loss: 3.6059 (3.5804) grad_norm: 1.0820 (1.1398) time: 0.6376 [2021-03-26 13:58:36 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 510/1251] eta: 0:07:52 lr: 0.000875 loss: 3.8467 (3.5861) grad_norm: 1.1849 (1.1413) time: 0.6347 [2021-03-26 13:58:42 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 520/1251] eta: 0:07:45 lr: 0.000875 loss: 3.8129 (3.5870) grad_norm: 1.2082 (1.1427) time: 0.6260 [2021-03-26 13:58:48 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 530/1251] eta: 0:07:38 lr: 0.000875 loss: 3.6587 (3.5874) grad_norm: 1.1459 (1.1423) time: 0.6225 [2021-03-26 13:58:54 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 540/1251] eta: 0:07:32 lr: 0.000875 loss: 3.6587 (3.5873) grad_norm: 1.0567 (1.1406) time: 0.6229 [2021-03-26 13:59:01 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 550/1251] eta: 0:07:26 lr: 0.000875 loss: 3.7449 (3.5900) grad_norm: 1.1234 (1.1410) time: 0.6296 [2021-03-26 13:59:07 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 560/1251] eta: 0:07:19 lr: 0.000875 loss: 3.8635 (3.5909) grad_norm: 1.1234 (1.1401) time: 0.6362 [2021-03-26 13:59:13 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 570/1251] eta: 0:07:13 lr: 0.000875 loss: 3.8605 (3.5938) grad_norm: 1.0567 (1.1416) time: 0.6338 [2021-03-26 13:59:20 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 580/1251] eta: 0:07:06 lr: 0.000875 loss: 3.7091 (3.5948) grad_norm: 1.1179 (1.1422) time: 0.6345 [2021-03-26 13:59:26 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 590/1251] eta: 0:07:00 lr: 0.000875 loss: 3.8995 (3.6034) grad_norm: 1.1714 (1.1439) time: 0.6317 [2021-03-26 13:59:32 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 600/1251] eta: 0:06:54 lr: 0.000875 loss: 3.8814 (3.6040) grad_norm: 1.2008 (1.1454) time: 0.6352 [2021-03-26 13:59:39 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 610/1251] eta: 0:06:47 lr: 0.000875 loss: 3.7755 (3.6100) grad_norm: 1.1220 (1.1446) time: 0.6354 [2021-03-26 13:59:45 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 620/1251] eta: 0:06:41 lr: 0.000875 loss: 3.8835 (3.6138) grad_norm: 1.1050 (1.1457) time: 0.6265 [2021-03-26 13:59:51 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 630/1251] eta: 0:06:34 lr: 0.000875 loss: 3.7979 (3.6123) grad_norm: 1.1086 (1.1459) time: 0.6300 [2021-03-26 13:59:57 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 640/1251] eta: 0:06:28 lr: 0.000875 loss: 3.5164 (3.6094) grad_norm: 1.1086 (1.1478) time: 0.6273 [2021-03-26 14:00:04 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 650/1251] eta: 0:06:21 lr: 0.000875 loss: 3.4327 (3.6070) grad_norm: 1.1031 (1.1467) time: 0.6260 [2021-03-26 14:00:10 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 660/1251] eta: 0:06:15 lr: 0.000874 loss: 3.7178 (3.6114) grad_norm: 1.0330 (1.1461) time: 0.6270 [2021-03-26 14:00:16 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 670/1251] eta: 0:06:09 lr: 0.000874 loss: 3.8148 (3.6164) grad_norm: 1.0577 (1.1452) time: 0.6237 [2021-03-26 14:00:23 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 680/1251] eta: 0:06:02 lr: 0.000874 loss: 3.8148 (3.6160) grad_norm: 1.0690 (1.1444) time: 0.6283 [2021-03-26 14:00:29 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 690/1251] eta: 0:05:56 lr: 0.000874 loss: 3.5646 (3.6123) grad_norm: 1.0698 (1.1437) time: 0.6313 [2021-03-26 14:00:35 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 700/1251] eta: 0:05:49 lr: 0.000874 loss: 3.3987 (3.6058) grad_norm: 1.0741 (1.1428) time: 0.6284 [2021-03-26 14:00:41 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 710/1251] eta: 0:05:43 lr: 0.000874 loss: 3.6444 (3.6091) grad_norm: 1.0597 (1.1419) time: 0.6279 [2021-03-26 14:00:48 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 720/1251] eta: 0:05:36 lr: 0.000874 loss: 3.7937 (3.6108) grad_norm: 1.0766 (1.1416) time: 0.6249 [2021-03-26 14:00:54 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 730/1251] eta: 0:05:30 lr: 0.000874 loss: 3.6757 (3.6115) grad_norm: 1.0856 (1.1414) time: 0.6209 [2021-03-26 14:01:00 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 740/1251] eta: 0:05:24 lr: 0.000874 loss: 3.6295 (3.6106) grad_norm: 1.0853 (1.1410) time: 0.6274 [2021-03-26 14:01:07 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 750/1251] eta: 0:05:17 lr: 0.000874 loss: 3.6003 (3.6116) grad_norm: 1.0613 (1.1404) time: 0.6326 [2021-03-26 14:01:13 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 760/1251] eta: 0:05:11 lr: 0.000874 loss: 3.6244 (3.6107) grad_norm: 1.0700 (1.1405) time: 0.6386 [2021-03-26 14:01:19 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 770/1251] eta: 0:05:05 lr: 0.000874 loss: 3.5847 (3.6087) grad_norm: 1.1532 (1.1411) time: 0.6418 [2021-03-26 14:01:26 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 780/1251] eta: 0:04:58 lr: 0.000874 loss: 3.5847 (3.6089) grad_norm: 1.2505 (1.1429) time: 0.6325 [2021-03-26 14:01:32 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 790/1251] eta: 0:04:52 lr: 0.000874 loss: 3.5658 (3.6068) grad_norm: 1.1942 (1.1432) time: 0.6256 [2021-03-26 14:01:38 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 800/1251] eta: 0:04:46 lr: 0.000874 loss: 3.8100 (3.6105) grad_norm: 1.2138 (1.1445) time: 0.6307 [2021-03-26 14:01:45 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 810/1251] eta: 0:04:39 lr: 0.000874 loss: 3.8819 (3.6091) grad_norm: 1.1648 (1.1443) time: 0.6346 [2021-03-26 14:01:51 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 820/1251] eta: 0:04:33 lr: 0.000874 loss: 3.7341 (3.6076) grad_norm: 1.1079 (1.1441) time: 0.6301 [2021-03-26 14:01:57 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 830/1251] eta: 0:04:26 lr: 0.000874 loss: 3.7282 (3.6099) grad_norm: 1.1079 (1.1433) time: 0.6228 [2021-03-26 14:02:03 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 840/1251] eta: 0:04:20 lr: 0.000874 loss: 3.7433 (3.6113) grad_norm: 1.0268 (1.1420) time: 0.6219 [2021-03-26 14:02:10 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 850/1251] eta: 0:04:14 lr: 0.000874 loss: 3.5419 (3.6081) grad_norm: 1.0268 (1.1411) time: 0.6235 [2021-03-26 14:02:16 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 860/1251] eta: 0:04:07 lr: 0.000874 loss: 3.6687 (3.6124) grad_norm: 1.0668 (1.1411) time: 0.6229 [2021-03-26 14:02:22 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 870/1251] eta: 0:04:01 lr: 0.000874 loss: 3.9571 (3.6171) grad_norm: 1.1192 (1.1415) time: 0.6256 [2021-03-26 14:02:28 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 880/1251] eta: 0:03:55 lr: 0.000874 loss: 3.8612 (3.6164) grad_norm: 1.1351 (1.1415) time: 0.6240 [2021-03-26 14:02:35 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 890/1251] eta: 0:03:48 lr: 0.000874 loss: 3.6482 (3.6153) grad_norm: 1.1545 (1.1419) time: 0.6259 [2021-03-26 14:02:41 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 900/1251] eta: 0:03:42 lr: 0.000874 loss: 3.4755 (3.6160) grad_norm: 1.1242 (1.1416) time: 0.6312 [2021-03-26 14:02:47 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 910/1251] eta: 0:03:35 lr: 0.000874 loss: 3.4755 (3.6156) grad_norm: 1.0663 (1.1409) time: 0.6244 [2021-03-26 14:02:53 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 920/1251] eta: 0:03:29 lr: 0.000874 loss: 3.6949 (3.6172) grad_norm: 1.0805 (1.1410) time: 0.6251 [2021-03-26 14:03:00 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 930/1251] eta: 0:03:23 lr: 0.000874 loss: 3.8387 (3.6173) grad_norm: 1.1179 (1.1404) time: 0.6300 [2021-03-26 14:03:06 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 940/1251] eta: 0:03:16 lr: 0.000874 loss: 3.7959 (3.6198) grad_norm: 1.1228 (1.1406) time: 0.6277 [2021-03-26 14:03:12 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 950/1251] eta: 0:03:10 lr: 0.000874 loss: 3.7944 (3.6213) grad_norm: 1.1598 (1.1408) time: 0.6252 [2021-03-26 14:03:18 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 960/1251] eta: 0:03:04 lr: 0.000874 loss: 3.7944 (3.6198) grad_norm: 1.1027 (1.1402) time: 0.6192 [2021-03-26 14:03:25 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 970/1251] eta: 0:02:57 lr: 0.000874 loss: 3.8154 (3.6218) grad_norm: 1.0981 (1.1400) time: 0.6209 [2021-03-26 14:03:31 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 980/1251] eta: 0:02:51 lr: 0.000874 loss: 3.7478 (3.6217) grad_norm: 1.1544 (1.1412) time: 0.6290 [2021-03-26 14:03:37 swin_base_patch4_window7_224] INFO: Epoch: [69] [ 990/1251] eta: 0:02:45 lr: 0.000874 loss: 3.7293 (3.6235) grad_norm: 1.1210 (1.1406) time: 0.6327 [2021-03-26 14:03:44 swin_base_patch4_window7_224] INFO: Epoch: [69] [1000/1251] eta: 0:02:38 lr: 0.000874 loss: 3.7984 (3.6240) grad_norm: 1.0781 (1.1408) time: 0.6327 [2021-03-26 14:03:50 swin_base_patch4_window7_224] INFO: Epoch: [69] [1010/1251] eta: 0:02:32 lr: 0.000874 loss: 3.6481 (3.6258) grad_norm: 1.0796 (1.1400) time: 0.6335 [2021-03-26 14:03:56 swin_base_patch4_window7_224] INFO: Epoch: [69] [1020/1251] eta: 0:02:26 lr: 0.000873 loss: 3.7482 (3.6271) grad_norm: 1.0316 (1.1389) time: 0.6293 [2021-03-26 14:04:02 swin_base_patch4_window7_224] INFO: Epoch: [69] [1030/1251] eta: 0:02:19 lr: 0.000873 loss: 3.7231 (3.6266) grad_norm: 1.0709 (1.1393) time: 0.6249 [2021-03-26 14:04:09 swin_base_patch4_window7_224] INFO: Epoch: [69] [1040/1251] eta: 0:02:13 lr: 0.000873 loss: 3.7231 (3.6284) grad_norm: 1.1069 (1.1395) time: 0.6274 [2021-03-26 14:04:15 swin_base_patch4_window7_224] INFO: Epoch: [69] [1050/1251] eta: 0:02:07 lr: 0.000873 loss: 3.9468 (3.6314) grad_norm: 1.1215 (1.1405) time: 0.6244 [2021-03-26 14:04:21 swin_base_patch4_window7_224] INFO: Epoch: [69] [1060/1251] eta: 0:02:00 lr: 0.000873 loss: 3.6337 (3.6300) grad_norm: 1.1497 (1.1404) time: 0.6254 [2021-03-26 14:04:27 swin_base_patch4_window7_224] INFO: Epoch: [69] [1070/1251] eta: 0:01:54 lr: 0.000873 loss: 3.6121 (3.6304) grad_norm: 1.1317 (1.1412) time: 0.6288 [2021-03-26 14:04:34 swin_base_patch4_window7_224] INFO: Epoch: [69] [1080/1251] eta: 0:01:48 lr: 0.000873 loss: 3.6634 (3.6289) grad_norm: 1.1272 (1.1410) time: 0.6297 [2021-03-26 14:04:40 swin_base_patch4_window7_224] INFO: Epoch: [69] [1090/1251] eta: 0:01:41 lr: 0.000873 loss: 3.6977 (3.6285) grad_norm: 1.1272 (1.1409) time: 0.6277 [2021-03-26 14:04:46 swin_base_patch4_window7_224] INFO: Epoch: [69] [1100/1251] eta: 0:01:35 lr: 0.000873 loss: 3.6977 (3.6290) grad_norm: 1.1375 (1.1404) time: 0.6230 [2021-03-26 14:04:53 swin_base_patch4_window7_224] INFO: Epoch: [69] [1110/1251] eta: 0:01:29 lr: 0.000873 loss: 3.6950 (3.6288) grad_norm: 1.1409 (1.1406) time: 0.6230 [2021-03-26 14:04:59 swin_base_patch4_window7_224] INFO: Epoch: [69] [1120/1251] eta: 0:01:22 lr: 0.000873 loss: 3.6359 (3.6263) grad_norm: 1.1458 (1.1410) time: 0.6242 [2021-03-26 14:05:05 swin_base_patch4_window7_224] INFO: Epoch: [69] [1130/1251] eta: 0:01:16 lr: 0.000873 loss: 3.7999 (3.6293) grad_norm: 1.1595 (1.1415) time: 0.6292 [2021-03-26 14:05:11 swin_base_patch4_window7_224] INFO: Epoch: [69] [1140/1251] eta: 0:01:10 lr: 0.000873 loss: 3.9747 (3.6303) grad_norm: 1.1050 (1.1409) time: 0.6317 [2021-03-26 14:05:18 swin_base_patch4_window7_224] INFO: Epoch: [69] [1150/1251] eta: 0:01:03 lr: 0.000873 loss: 3.7135 (3.6301) grad_norm: 1.0379 (1.1397) time: 0.6288 [2021-03-26 14:05:24 swin_base_patch4_window7_224] INFO: Epoch: [69] [1160/1251] eta: 0:00:57 lr: 0.000873 loss: 3.3160 (3.6278) grad_norm: 1.0471 (1.1400) time: 0.6302 [2021-03-26 14:05:30 swin_base_patch4_window7_224] INFO: Epoch: [69] [1170/1251] eta: 0:00:51 lr: 0.000873 loss: 3.4109 (3.6282) grad_norm: 1.0701 (1.1397) time: 0.6299 [2021-03-26 14:05:36 swin_base_patch4_window7_224] INFO: Epoch: [69] [1180/1251] eta: 0:00:44 lr: 0.000873 loss: 3.8401 (3.6293) grad_norm: 1.0418 (1.1390) time: 0.6235 [2021-03-26 14:05:43 swin_base_patch4_window7_224] INFO: Epoch: [69] [1190/1251] eta: 0:00:38 lr: 0.000873 loss: 3.4388 (3.6252) grad_norm: 1.0955 (1.1394) time: 0.6277 [2021-03-26 14:05:49 swin_base_patch4_window7_224] INFO: Epoch: [69] [1200/1251] eta: 0:00:32 lr: 0.000873 loss: 3.3559 (3.6266) grad_norm: 1.1439 (1.1394) time: 0.6299 [2021-03-26 14:05:55 swin_base_patch4_window7_224] INFO: Epoch: [69] [1210/1251] eta: 0:00:25 lr: 0.000873 loss: 3.9768 (3.6288) grad_norm: 1.0262 (1.1388) time: 0.6245 [2021-03-26 14:06:02 swin_base_patch4_window7_224] INFO: Epoch: [69] [1220/1251] eta: 0:00:19 lr: 0.000873 loss: 3.8031 (3.6293) grad_norm: 1.0257 (1.1387) time: 0.6233 [2021-03-26 14:06:08 swin_base_patch4_window7_224] INFO: Epoch: [69] [1230/1251] eta: 0:00:13 lr: 0.000873 loss: 3.8090 (3.6303) grad_norm: 1.1108 (1.1390) time: 0.6255 [2021-03-26 14:06:14 swin_base_patch4_window7_224] INFO: Epoch: [69] [1240/1251] eta: 0:00:06 lr: 0.000873 loss: 3.6877 (3.6305) grad_norm: 1.0594 (1.1386) time: 0.6280 [2021-03-26 14:06:20 swin_base_patch4_window7_224] INFO: Epoch: [69] [1250/1251] eta: 0:00:00 lr: 0.000873 loss: 3.6194 (3.6301) grad_norm: 1.0518 (1.1381) time: 0.6237 [2021-03-26 14:06:27 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:16 loss: 1.4886 (1.4886) acc1: 64.0625 (64.0625) acc5: 87.5000 (87.5000) [2021-03-26 14:06:28 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.1066 (1.0909) acc1: 75.0000 (72.4432) acc5: 92.1875 (93.0398) [2021-03-26 14:06:30 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.0365 (1.0747) acc1: 75.0000 (74.4792) acc5: 92.1875 (92.4851) [2021-03-26 14:06:32 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0509 (1.0656) acc1: 75.0000 (74.5968) acc5: 92.1875 (92.6411) [2021-03-26 14:06:35 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0603 (1.0714) acc1: 73.4375 (74.3140) acc5: 93.7500 (92.8735) [2021-03-26 14:06:36 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1011 (1.0696) acc1: 73.4375 (74.4640) acc5: 93.7500 (92.8320) [2021-03-26 14:06:41 swin_base_patch4_window7_224] INFO: * Acc@1 74.920 Acc@5 92.912 loss 1.056 [2021-03-26 14:06:41 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.9% [2021-03-26 14:06:41 swin_base_patch4_window7_224] INFO: Max accuracy: 74.92% [2021-03-26 14:06:45 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 0/1251] eta: 1:27:08 lr: 0.000873 loss: 3.8996 (3.8996) grad_norm: 1.1697 (1.1697) time: 4.1796 [2021-03-26 14:06:52 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 10/1251] eta: 0:19:48 lr: 0.000873 loss: 3.8996 (3.7868) grad_norm: 1.1668 (1.1355) time: 0.9573 [2021-03-26 14:06:58 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 20/1251] eta: 0:16:20 lr: 0.000873 loss: 3.7849 (3.6715) grad_norm: 1.1076 (1.1880) time: 0.6274 [2021-03-26 14:07:04 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 30/1251] eta: 0:15:09 lr: 0.000873 loss: 3.5169 (3.6048) grad_norm: 1.1662 (1.1883) time: 0.6275 [2021-03-26 14:07:11 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 40/1251] eta: 0:14:27 lr: 0.000873 loss: 3.5503 (3.6081) grad_norm: 1.1498 (1.1739) time: 0.6322 [2021-03-26 14:07:17 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 50/1251] eta: 0:14:00 lr: 0.000873 loss: 3.5503 (3.5580) grad_norm: 1.0860 (1.1826) time: 0.6296 [2021-03-26 14:07:23 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 60/1251] eta: 0:13:37 lr: 0.000873 loss: 3.6289 (3.6145) grad_norm: 1.1172 (1.1928) time: 0.6259 [2021-03-26 14:07:29 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 70/1251] eta: 0:13:21 lr: 0.000873 loss: 3.6974 (3.5878) grad_norm: 1.1172 (1.1748) time: 0.6242 [2021-03-26 14:07:36 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 80/1251] eta: 0:13:06 lr: 0.000873 loss: 3.5496 (3.5781) grad_norm: 1.0430 (1.1653) time: 0.6241 [2021-03-26 14:07:42 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 90/1251] eta: 0:12:54 lr: 0.000873 loss: 3.6229 (3.5854) grad_norm: 1.1406 (1.1694) time: 0.6264 [2021-03-26 14:07:48 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 100/1251] eta: 0:12:43 lr: 0.000873 loss: 3.6081 (3.5630) grad_norm: 1.1227 (1.1626) time: 0.6316 [2021-03-26 14:07:55 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 110/1251] eta: 0:12:32 lr: 0.000873 loss: 3.6081 (3.5681) grad_norm: 1.1327 (1.1651) time: 0.6283 [2021-03-26 14:08:01 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 120/1251] eta: 0:12:22 lr: 0.000873 loss: 3.6824 (3.5622) grad_norm: 1.0770 (1.1552) time: 0.6223 [2021-03-26 14:08:07 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 130/1251] eta: 0:12:13 lr: 0.000872 loss: 3.6478 (3.5755) grad_norm: 1.0533 (1.1494) time: 0.6262 [2021-03-26 14:08:13 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 140/1251] eta: 0:12:04 lr: 0.000872 loss: 3.6478 (3.5667) grad_norm: 1.0533 (1.1473) time: 0.6276 [2021-03-26 14:08:20 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 150/1251] eta: 0:11:57 lr: 0.000872 loss: 3.8771 (3.5823) grad_norm: 1.0481 (1.1420) time: 0.6312 [2021-03-26 14:08:26 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 160/1251] eta: 0:11:48 lr: 0.000872 loss: 3.8771 (3.5861) grad_norm: 1.0645 (1.1412) time: 0.6311 [2021-03-26 14:08:32 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 170/1251] eta: 0:11:40 lr: 0.000872 loss: 3.4628 (3.5776) grad_norm: 1.0645 (1.1359) time: 0.6215 [2021-03-26 14:08:38 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 180/1251] eta: 0:11:33 lr: 0.000872 loss: 3.6374 (3.5868) grad_norm: 1.0447 (1.1334) time: 0.6270 [2021-03-26 14:08:45 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 190/1251] eta: 0:11:26 lr: 0.000872 loss: 3.7476 (3.5894) grad_norm: 1.0879 (1.1304) time: 0.6343 [2021-03-26 14:08:51 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 200/1251] eta: 0:11:18 lr: 0.000872 loss: 3.7088 (3.5939) grad_norm: 1.0414 (1.1286) time: 0.6282 [2021-03-26 14:08:57 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 210/1251] eta: 0:11:10 lr: 0.000872 loss: 3.8361 (3.5943) grad_norm: 1.0837 (1.1274) time: 0.6184 [2021-03-26 14:09:03 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 220/1251] eta: 0:11:02 lr: 0.000872 loss: 3.9091 (3.5944) grad_norm: 1.1086 (1.1284) time: 0.6186 [2021-03-26 14:09:10 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 230/1251] eta: 0:10:55 lr: 0.000872 loss: 3.7049 (3.5965) grad_norm: 1.1334 (1.1289) time: 0.6268 [2021-03-26 14:09:16 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 240/1251] eta: 0:10:48 lr: 0.000872 loss: 3.8722 (3.6009) grad_norm: 1.0621 (1.1283) time: 0.6296 [2021-03-26 14:09:22 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 250/1251] eta: 0:10:41 lr: 0.000872 loss: 3.7840 (3.6009) grad_norm: 1.0621 (1.1268) time: 0.6280 [2021-03-26 14:09:29 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 260/1251] eta: 0:10:35 lr: 0.000872 loss: 3.5992 (3.6004) grad_norm: 1.1350 (1.1288) time: 0.6290 [2021-03-26 14:09:35 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 270/1251] eta: 0:10:28 lr: 0.000872 loss: 3.5992 (3.5940) grad_norm: 1.1444 (1.1300) time: 0.6323 [2021-03-26 14:09:41 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 280/1251] eta: 0:10:21 lr: 0.000872 loss: 3.6610 (3.5945) grad_norm: 1.1466 (1.1323) time: 0.6321 [2021-03-26 14:09:48 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 290/1251] eta: 0:10:15 lr: 0.000872 loss: 3.5834 (3.5921) grad_norm: 1.1113 (1.1308) time: 0.6342 [2021-03-26 14:09:54 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 300/1251] eta: 0:10:08 lr: 0.000872 loss: 3.7106 (3.5995) grad_norm: 1.0831 (1.1300) time: 0.6314 [2021-03-26 14:10:00 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 310/1251] eta: 0:10:01 lr: 0.000872 loss: 3.9187 (3.6126) grad_norm: 1.0648 (1.1280) time: 0.6235 [2021-03-26 14:10:06 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 320/1251] eta: 0:09:54 lr: 0.000872 loss: 3.8953 (3.6118) grad_norm: 1.0697 (1.1295) time: 0.6240 [2021-03-26 14:10:13 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 330/1251] eta: 0:09:47 lr: 0.000872 loss: 3.6682 (3.6099) grad_norm: 1.1592 (1.1301) time: 0.6226 [2021-03-26 14:10:19 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 340/1251] eta: 0:09:41 lr: 0.000872 loss: 3.6055 (3.6053) grad_norm: 1.1413 (1.1298) time: 0.6300 [2021-03-26 14:10:25 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 350/1251] eta: 0:09:34 lr: 0.000872 loss: 3.6055 (3.6035) grad_norm: 1.0701 (1.1293) time: 0.6347 [2021-03-26 14:10:32 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 360/1251] eta: 0:09:28 lr: 0.000872 loss: 3.7841 (3.6075) grad_norm: 1.0872 (1.1304) time: 0.6272 [2021-03-26 14:10:38 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 370/1251] eta: 0:09:21 lr: 0.000872 loss: 3.7709 (3.6047) grad_norm: 1.0608 (1.1284) time: 0.6266 [2021-03-26 14:10:44 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 380/1251] eta: 0:09:14 lr: 0.000872 loss: 3.7374 (3.6060) grad_norm: 1.0705 (1.1287) time: 0.6275 [2021-03-26 14:10:50 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 390/1251] eta: 0:09:08 lr: 0.000872 loss: 3.7374 (3.6121) grad_norm: 1.0705 (1.1271) time: 0.6298 [2021-03-26 14:10:57 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 400/1251] eta: 0:09:01 lr: 0.000872 loss: 3.6644 (3.6059) grad_norm: 1.0505 (1.1291) time: 0.6269 [2021-03-26 14:11:03 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 410/1251] eta: 0:08:55 lr: 0.000872 loss: 3.7986 (3.6136) grad_norm: 1.0176 (1.1274) time: 0.6210 [2021-03-26 14:11:09 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 420/1251] eta: 0:08:48 lr: 0.000872 loss: 3.9090 (3.6194) grad_norm: 1.0422 (1.1267) time: 0.6241 [2021-03-26 14:11:16 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 430/1251] eta: 0:08:42 lr: 0.000872 loss: 3.9190 (3.6180) grad_norm: 1.1191 (1.1276) time: 0.6328 [2021-03-26 14:11:22 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 440/1251] eta: 0:08:35 lr: 0.000872 loss: 3.5333 (3.6125) grad_norm: 1.1330 (1.1294) time: 0.6351 [2021-03-26 14:11:28 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 450/1251] eta: 0:08:29 lr: 0.000872 loss: 3.6155 (3.6119) grad_norm: 1.2126 (1.1312) time: 0.6306 [2021-03-26 14:11:34 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 460/1251] eta: 0:08:22 lr: 0.000872 loss: 3.7956 (3.6115) grad_norm: 1.1476 (1.1312) time: 0.6286 [2021-03-26 14:11:41 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 470/1251] eta: 0:08:16 lr: 0.000872 loss: 3.6875 (3.6120) grad_norm: 1.0611 (1.1314) time: 0.6278 [2021-03-26 14:11:47 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 480/1251] eta: 0:08:09 lr: 0.000872 loss: 3.9043 (3.6130) grad_norm: 1.1330 (1.1333) time: 0.6313 [2021-03-26 14:11:53 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 490/1251] eta: 0:08:03 lr: 0.000871 loss: 3.5651 (3.6064) grad_norm: 1.1450 (1.1346) time: 0.6361 [2021-03-26 14:12:00 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 500/1251] eta: 0:07:57 lr: 0.000871 loss: 3.6961 (3.6094) grad_norm: 1.1352 (1.1344) time: 0.6289 [2021-03-26 14:12:06 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 510/1251] eta: 0:07:50 lr: 0.000871 loss: 3.7141 (3.6061) grad_norm: 1.0465 (1.1329) time: 0.6238 [2021-03-26 14:12:12 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 520/1251] eta: 0:07:44 lr: 0.000871 loss: 3.4406 (3.6070) grad_norm: 1.0677 (1.1333) time: 0.6265 [2021-03-26 14:12:18 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 530/1251] eta: 0:07:37 lr: 0.000871 loss: 3.4950 (3.6031) grad_norm: 1.0957 (1.1332) time: 0.6259 [2021-03-26 14:12:25 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 540/1251] eta: 0:07:31 lr: 0.000871 loss: 3.5856 (3.6074) grad_norm: 1.1006 (1.1335) time: 0.6258 [2021-03-26 14:12:31 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 550/1251] eta: 0:07:25 lr: 0.000871 loss: 3.6459 (3.6041) grad_norm: 1.1818 (1.1365) time: 0.6395 [2021-03-26 14:12:37 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 560/1251] eta: 0:07:18 lr: 0.000871 loss: 3.5148 (3.6017) grad_norm: 1.1818 (1.1379) time: 0.6405 [2021-03-26 14:12:44 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 570/1251] eta: 0:07:12 lr: 0.000871 loss: 3.3059 (3.5956) grad_norm: 1.2033 (1.1401) time: 0.6297 [2021-03-26 14:12:50 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 580/1251] eta: 0:07:05 lr: 0.000871 loss: 3.6269 (3.5984) grad_norm: 1.0887 (1.1395) time: 0.6302 [2021-03-26 14:12:56 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 590/1251] eta: 0:06:59 lr: 0.000871 loss: 3.6059 (3.5995) grad_norm: 1.0887 (1.1398) time: 0.6285 [2021-03-26 14:13:03 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 600/1251] eta: 0:06:52 lr: 0.000871 loss: 3.6059 (3.5988) grad_norm: 1.1494 (1.1403) time: 0.6288 [2021-03-26 14:13:09 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 610/1251] eta: 0:06:46 lr: 0.000871 loss: 3.7474 (3.5981) grad_norm: 1.1370 (1.1402) time: 0.6294 [2021-03-26 14:13:15 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 620/1251] eta: 0:06:40 lr: 0.000871 loss: 3.8094 (3.6014) grad_norm: 1.0600 (1.1388) time: 0.6268 [2021-03-26 14:13:21 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 630/1251] eta: 0:06:33 lr: 0.000871 loss: 3.8094 (3.6048) grad_norm: 1.0545 (1.1377) time: 0.6216 [2021-03-26 14:13:28 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 640/1251] eta: 0:06:27 lr: 0.000871 loss: 3.4522 (3.6018) grad_norm: 1.0735 (1.1378) time: 0.6203 [2021-03-26 14:13:34 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 650/1251] eta: 0:06:20 lr: 0.000871 loss: 3.4522 (3.6037) grad_norm: 1.1348 (1.1377) time: 0.6214 [2021-03-26 14:13:40 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 660/1251] eta: 0:06:14 lr: 0.000871 loss: 3.1924 (3.5974) grad_norm: 1.0841 (1.1363) time: 0.6254 [2021-03-26 14:13:46 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 670/1251] eta: 0:06:08 lr: 0.000871 loss: 3.3929 (3.5980) grad_norm: 1.0563 (1.1366) time: 0.6334 [2021-03-26 14:13:53 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 680/1251] eta: 0:06:01 lr: 0.000871 loss: 3.6150 (3.5962) grad_norm: 1.0724 (1.1360) time: 0.6317 [2021-03-26 14:13:59 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 690/1251] eta: 0:05:55 lr: 0.000871 loss: 3.4913 (3.5934) grad_norm: 1.0513 (1.1353) time: 0.6290 [2021-03-26 14:14:05 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 700/1251] eta: 0:05:48 lr: 0.000871 loss: 3.8134 (3.5987) grad_norm: 1.1139 (1.1356) time: 0.6280 [2021-03-26 14:14:12 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 710/1251] eta: 0:05:42 lr: 0.000871 loss: 3.7107 (3.5968) grad_norm: 1.0847 (1.1344) time: 0.6294 [2021-03-26 14:14:18 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 720/1251] eta: 0:05:36 lr: 0.000871 loss: 3.6366 (3.5978) grad_norm: 1.0704 (1.1340) time: 0.6307 [2021-03-26 14:14:24 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 730/1251] eta: 0:05:29 lr: 0.000871 loss: 3.7122 (3.5969) grad_norm: 1.0887 (1.1333) time: 0.6226 [2021-03-26 14:14:31 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 740/1251] eta: 0:05:23 lr: 0.000871 loss: 3.7272 (3.5960) grad_norm: 1.1034 (1.1344) time: 0.6306 [2021-03-26 14:14:37 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 750/1251] eta: 0:05:17 lr: 0.000871 loss: 3.7113 (3.5969) grad_norm: 1.1034 (1.1338) time: 0.6414 [2021-03-26 14:14:43 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 760/1251] eta: 0:05:10 lr: 0.000871 loss: 3.5908 (3.5974) grad_norm: 1.1187 (1.1348) time: 0.6303 [2021-03-26 14:14:49 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 770/1251] eta: 0:05:04 lr: 0.000871 loss: 3.3195 (3.5947) grad_norm: 1.0929 (1.1337) time: 0.6259 [2021-03-26 14:14:56 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 780/1251] eta: 0:04:58 lr: 0.000871 loss: 3.2316 (3.5936) grad_norm: 1.0236 (1.1324) time: 0.6252 [2021-03-26 14:15:02 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 790/1251] eta: 0:04:51 lr: 0.000871 loss: 3.8635 (3.5972) grad_norm: 1.0794 (1.1327) time: 0.6251 [2021-03-26 14:15:08 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 800/1251] eta: 0:04:45 lr: 0.000871 loss: 3.7846 (3.5996) grad_norm: 1.1037 (1.1329) time: 0.6296 [2021-03-26 14:15:15 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 810/1251] eta: 0:04:39 lr: 0.000871 loss: 3.7613 (3.6027) grad_norm: 1.1132 (1.1332) time: 0.6275 [2021-03-26 14:15:21 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 820/1251] eta: 0:04:32 lr: 0.000871 loss: 3.8476 (3.6052) grad_norm: 1.1858 (1.1339) time: 0.6278 [2021-03-26 14:15:27 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 830/1251] eta: 0:04:26 lr: 0.000871 loss: 3.8844 (3.6059) grad_norm: 1.1446 (1.1342) time: 0.6299 [2021-03-26 14:15:33 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 840/1251] eta: 0:04:19 lr: 0.000871 loss: 3.6973 (3.6075) grad_norm: 1.0842 (1.1333) time: 0.6317 [2021-03-26 14:15:40 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 850/1251] eta: 0:04:13 lr: 0.000870 loss: 3.5748 (3.6062) grad_norm: 1.0775 (1.1334) time: 0.6248 [2021-03-26 14:15:46 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 860/1251] eta: 0:04:07 lr: 0.000870 loss: 3.9004 (3.6097) grad_norm: 1.0837 (1.1339) time: 0.6273 [2021-03-26 14:15:52 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 870/1251] eta: 0:04:00 lr: 0.000870 loss: 3.8147 (3.6098) grad_norm: 1.1010 (1.1336) time: 0.6341 [2021-03-26 14:15:59 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 880/1251] eta: 0:03:54 lr: 0.000870 loss: 3.7704 (3.6132) grad_norm: 1.1349 (1.1349) time: 0.6361 [2021-03-26 14:16:05 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 890/1251] eta: 0:03:48 lr: 0.000870 loss: 3.6396 (3.6124) grad_norm: 1.2201 (1.1357) time: 0.6417 [2021-03-26 14:16:11 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 900/1251] eta: 0:03:42 lr: 0.000870 loss: 3.6487 (3.6137) grad_norm: 1.1374 (1.1352) time: 0.6350 [2021-03-26 14:16:18 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 910/1251] eta: 0:03:35 lr: 0.000870 loss: 3.7146 (3.6156) grad_norm: 1.0931 (1.1351) time: 0.6236 [2021-03-26 14:16:24 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 920/1251] eta: 0:03:29 lr: 0.000870 loss: 3.6416 (3.6153) grad_norm: 1.0441 (1.1337) time: 0.6226 [2021-03-26 14:16:30 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 930/1251] eta: 0:03:22 lr: 0.000870 loss: 3.6416 (3.6160) grad_norm: 1.0313 (1.1335) time: 0.6262 [2021-03-26 14:16:37 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 940/1251] eta: 0:03:16 lr: 0.000870 loss: 3.6783 (3.6170) grad_norm: 1.1308 (1.1346) time: 0.6316 [2021-03-26 14:16:43 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 950/1251] eta: 0:03:10 lr: 0.000870 loss: 3.6739 (3.6166) grad_norm: 1.1746 (1.1357) time: 0.6313 [2021-03-26 14:16:49 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 960/1251] eta: 0:03:03 lr: 0.000870 loss: 3.5262 (3.6165) grad_norm: 1.1029 (1.1355) time: 0.6259 [2021-03-26 14:16:55 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 970/1251] eta: 0:02:57 lr: 0.000870 loss: 3.7879 (3.6172) grad_norm: 1.0994 (1.1355) time: 0.6230 [2021-03-26 14:17:01 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 980/1251] eta: 0:02:51 lr: 0.000870 loss: 3.8914 (3.6168) grad_norm: 1.1427 (1.1357) time: 0.6200 [2021-03-26 14:17:08 swin_base_patch4_window7_224] INFO: Epoch: [70] [ 990/1251] eta: 0:02:44 lr: 0.000870 loss: 3.5626 (3.6169) grad_norm: 1.0978 (1.1359) time: 0.6221 [2021-03-26 14:17:14 swin_base_patch4_window7_224] INFO: Epoch: [70] [1000/1251] eta: 0:02:38 lr: 0.000870 loss: 3.5287 (3.6141) grad_norm: 1.1060 (1.1365) time: 0.6265 [2021-03-26 14:17:20 swin_base_patch4_window7_224] INFO: Epoch: [70] [1010/1251] eta: 0:02:32 lr: 0.000870 loss: 3.5252 (3.6126) grad_norm: 1.1795 (1.1384) time: 0.6271 [2021-03-26 14:17:27 swin_base_patch4_window7_224] INFO: Epoch: [70] [1020/1251] eta: 0:02:25 lr: 0.000870 loss: 3.9450 (3.6167) grad_norm: 1.1446 (1.1379) time: 0.6276 [2021-03-26 14:17:33 swin_base_patch4_window7_224] INFO: Epoch: [70] [1030/1251] eta: 0:02:19 lr: 0.000870 loss: 4.0409 (3.6195) grad_norm: 1.0604 (1.1371) time: 0.6302 [2021-03-26 14:17:39 swin_base_patch4_window7_224] INFO: Epoch: [70] [1040/1251] eta: 0:02:13 lr: 0.000870 loss: 3.7046 (3.6175) grad_norm: 1.0878 (1.1374) time: 0.6281 [2021-03-26 14:17:45 swin_base_patch4_window7_224] INFO: Epoch: [70] [1050/1251] eta: 0:02:06 lr: 0.000870 loss: 3.7046 (3.6204) grad_norm: 1.1285 (1.1370) time: 0.6268 [2021-03-26 14:17:52 swin_base_patch4_window7_224] INFO: Epoch: [70] [1060/1251] eta: 0:02:00 lr: 0.000870 loss: 3.8125 (3.6231) grad_norm: 1.0883 (1.1363) time: 0.6285 [2021-03-26 14:17:58 swin_base_patch4_window7_224] INFO: Epoch: [70] [1070/1251] eta: 0:01:54 lr: 0.000870 loss: 3.7823 (3.6218) grad_norm: 1.0810 (1.1356) time: 0.6258 [2021-03-26 14:18:04 swin_base_patch4_window7_224] INFO: Epoch: [70] [1080/1251] eta: 0:01:48 lr: 0.000870 loss: 3.7397 (3.6235) grad_norm: 1.1214 (1.1361) time: 0.6295 [2021-03-26 14:18:11 swin_base_patch4_window7_224] INFO: Epoch: [70] [1090/1251] eta: 0:01:41 lr: 0.000870 loss: 3.7397 (3.6245) grad_norm: 1.1835 (1.1370) time: 0.6336 [2021-03-26 14:18:17 swin_base_patch4_window7_224] INFO: Epoch: [70] [1100/1251] eta: 0:01:35 lr: 0.000870 loss: 3.6737 (3.6245) grad_norm: 1.1137 (1.1370) time: 0.6314 [2021-03-26 14:18:23 swin_base_patch4_window7_224] INFO: Epoch: [70] [1110/1251] eta: 0:01:29 lr: 0.000870 loss: 3.6780 (3.6242) grad_norm: 1.1107 (1.1370) time: 0.6302 [2021-03-26 14:18:29 swin_base_patch4_window7_224] INFO: Epoch: [70] [1120/1251] eta: 0:01:22 lr: 0.000870 loss: 3.8671 (3.6254) grad_norm: 1.0845 (1.1365) time: 0.6263 [2021-03-26 14:18:36 swin_base_patch4_window7_224] INFO: Epoch: [70] [1130/1251] eta: 0:01:16 lr: 0.000870 loss: 3.9088 (3.6269) grad_norm: 1.0723 (1.1363) time: 0.6289 [2021-03-26 14:18:42 swin_base_patch4_window7_224] INFO: Epoch: [70] [1140/1251] eta: 0:01:10 lr: 0.000870 loss: 3.7384 (3.6261) grad_norm: 1.1225 (1.1363) time: 0.6350 [2021-03-26 14:18:48 swin_base_patch4_window7_224] INFO: Epoch: [70] [1150/1251] eta: 0:01:03 lr: 0.000870 loss: 3.7702 (3.6272) grad_norm: 1.0714 (1.1355) time: 0.6293 [2021-03-26 14:18:55 swin_base_patch4_window7_224] INFO: Epoch: [70] [1160/1251] eta: 0:00:57 lr: 0.000870 loss: 3.9167 (3.6274) grad_norm: 1.0733 (1.1360) time: 0.6244 [2021-03-26 14:19:01 swin_base_patch4_window7_224] INFO: Epoch: [70] [1170/1251] eta: 0:00:51 lr: 0.000870 loss: 3.5049 (3.6248) grad_norm: 1.1452 (1.1369) time: 0.6264 [2021-03-26 14:19:07 swin_base_patch4_window7_224] INFO: Epoch: [70] [1180/1251] eta: 0:00:44 lr: 0.000870 loss: 3.3757 (3.6247) grad_norm: 1.0514 (1.1363) time: 0.6253 [2021-03-26 14:19:13 swin_base_patch4_window7_224] INFO: Epoch: [70] [1190/1251] eta: 0:00:38 lr: 0.000870 loss: 3.6137 (3.6247) grad_norm: 1.0973 (1.1361) time: 0.6263 [2021-03-26 14:19:20 swin_base_patch4_window7_224] INFO: Epoch: [70] [1200/1251] eta: 0:00:32 lr: 0.000870 loss: 3.6137 (3.6247) grad_norm: 1.1560 (1.1367) time: 0.6265 [2021-03-26 14:19:26 swin_base_patch4_window7_224] INFO: Epoch: [70] [1210/1251] eta: 0:00:25 lr: 0.000869 loss: 3.6462 (3.6234) grad_norm: 1.1785 (1.1385) time: 0.6242 [2021-03-26 14:19:32 swin_base_patch4_window7_224] INFO: Epoch: [70] [1220/1251] eta: 0:00:19 lr: 0.000869 loss: 3.7075 (3.6225) grad_norm: 1.1420 (1.1382) time: 0.6222 [2021-03-26 14:19:38 swin_base_patch4_window7_224] INFO: Epoch: [70] [1230/1251] eta: 0:00:13 lr: 0.000869 loss: 3.6004 (3.6236) grad_norm: 1.0765 (1.1374) time: 0.6167 [2021-03-26 14:19:44 swin_base_patch4_window7_224] INFO: Epoch: [70] [1240/1251] eta: 0:00:06 lr: 0.000869 loss: 3.6004 (3.6231) grad_norm: 1.0700 (1.1375) time: 0.6169 [2021-03-26 14:19:51 swin_base_patch4_window7_224] INFO: Epoch: [70] [1250/1251] eta: 0:00:00 lr: 0.000869 loss: 3.5136 (3.6220) grad_norm: 1.1111 (1.1378) time: 0.6254 [2021-03-26 14:20:47 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 1.0578 (1.0578) acc1: 73.4375 (73.4375) acc5: 89.0625 (89.0625) [2021-03-26 14:20:48 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 1.1052 (1.1250) acc1: 73.4375 (72.8693) acc5: 92.1875 (92.1875) [2021-03-26 14:20:50 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.1052 (1.1080) acc1: 71.8750 (73.0655) acc5: 93.7500 (92.5595) [2021-03-26 14:20:51 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.0853 (1.1135) acc1: 71.8750 (72.6815) acc5: 93.7500 (92.4899) [2021-03-26 14:20:52 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.0257 (1.0847) acc1: 75.0000 (73.7424) acc5: 93.7500 (92.7591) [2021-03-26 14:20:54 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0192 (1.0849) acc1: 78.1250 (74.0480) acc5: 93.7500 (92.7360) [2021-03-26 14:20:58 swin_base_patch4_window7_224] INFO: * Acc@1 74.604 Acc@5 92.812 loss 1.073 [2021-03-26 14:20:58 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.6% [2021-03-26 14:20:58 swin_base_patch4_window7_224] INFO: Max accuracy: 74.92% [2021-03-26 14:21:02 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 0/1251] eta: 1:27:54 lr: 0.000869 loss: 2.9333 (2.9333) grad_norm: 0.9605 (0.9605) time: 4.2161 [2021-03-26 14:21:08 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 10/1251] eta: 0:20:01 lr: 0.000869 loss: 3.8781 (3.7535) grad_norm: 1.0782 (1.1344) time: 0.9682 [2021-03-26 14:21:14 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 20/1251] eta: 0:16:29 lr: 0.000869 loss: 3.8297 (3.7498) grad_norm: 1.0849 (1.1149) time: 0.6335 [2021-03-26 14:21:21 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 30/1251] eta: 0:15:11 lr: 0.000869 loss: 3.5814 (3.6167) grad_norm: 1.0890 (1.1156) time: 0.6246 [2021-03-26 14:21:27 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 40/1251] eta: 0:14:29 lr: 0.000869 loss: 3.4852 (3.5931) grad_norm: 1.1670 (1.1779) time: 0.6270 [2021-03-26 14:21:33 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 50/1251] eta: 0:14:01 lr: 0.000869 loss: 3.5949 (3.5760) grad_norm: 1.2496 (1.1861) time: 0.6291 [2021-03-26 14:21:40 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 60/1251] eta: 0:13:40 lr: 0.000869 loss: 3.6893 (3.6115) grad_norm: 1.1582 (1.1825) time: 0.6297 [2021-03-26 14:21:46 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 70/1251] eta: 0:13:22 lr: 0.000869 loss: 3.6489 (3.6156) grad_norm: 1.1243 (1.1748) time: 0.6262 [2021-03-26 14:21:52 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 80/1251] eta: 0:13:07 lr: 0.000869 loss: 3.4725 (3.5927) grad_norm: 1.1057 (1.1671) time: 0.6239 [2021-03-26 14:21:58 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 90/1251] eta: 0:12:55 lr: 0.000869 loss: 3.7035 (3.5932) grad_norm: 1.0862 (1.1608) time: 0.6253 [2021-03-26 14:22:05 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 100/1251] eta: 0:12:43 lr: 0.000869 loss: 3.7974 (3.5984) grad_norm: 1.0575 (1.1533) time: 0.6237 [2021-03-26 14:22:11 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 110/1251] eta: 0:12:32 lr: 0.000869 loss: 4.0387 (3.6261) grad_norm: 1.0413 (1.1486) time: 0.6209 [2021-03-26 14:22:17 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 120/1251] eta: 0:12:22 lr: 0.000869 loss: 3.8571 (3.6259) grad_norm: 1.1324 (1.1453) time: 0.6217 [2021-03-26 14:22:23 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 130/1251] eta: 0:12:13 lr: 0.000869 loss: 3.4352 (3.6069) grad_norm: 1.1656 (1.1470) time: 0.6285 [2021-03-26 14:22:30 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 140/1251] eta: 0:12:05 lr: 0.000869 loss: 3.4352 (3.6070) grad_norm: 1.1691 (1.1502) time: 0.6321 [2021-03-26 14:22:36 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 150/1251] eta: 0:11:57 lr: 0.000869 loss: 3.6022 (3.6036) grad_norm: 1.1267 (1.1497) time: 0.6357 [2021-03-26 14:22:42 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 160/1251] eta: 0:11:49 lr: 0.000869 loss: 3.6022 (3.5969) grad_norm: 1.0896 (1.1483) time: 0.6336 [2021-03-26 14:22:49 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 170/1251] eta: 0:11:41 lr: 0.000869 loss: 3.6202 (3.5954) grad_norm: 1.1139 (1.1553) time: 0.6291 [2021-03-26 14:22:55 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 180/1251] eta: 0:11:34 lr: 0.000869 loss: 3.8050 (3.6131) grad_norm: 1.2334 (1.1629) time: 0.6355 [2021-03-26 14:23:01 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 190/1251] eta: 0:11:26 lr: 0.000869 loss: 3.9128 (3.6105) grad_norm: 1.1918 (1.1650) time: 0.6300 [2021-03-26 14:23:08 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 200/1251] eta: 0:11:20 lr: 0.000869 loss: 3.4372 (3.5899) grad_norm: 1.0864 (1.1610) time: 0.6315 [2021-03-26 14:23:14 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 210/1251] eta: 0:11:12 lr: 0.000869 loss: 3.4840 (3.5979) grad_norm: 1.0864 (1.1596) time: 0.6343 [2021-03-26 14:23:20 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 220/1251] eta: 0:11:05 lr: 0.000869 loss: 3.7101 (3.5910) grad_norm: 1.0207 (1.1545) time: 0.6256 [2021-03-26 14:23:26 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 230/1251] eta: 0:10:57 lr: 0.000869 loss: 3.5915 (3.5857) grad_norm: 1.0523 (1.1557) time: 0.6261 [2021-03-26 14:23:33 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 240/1251] eta: 0:10:50 lr: 0.000869 loss: 3.6045 (3.5919) grad_norm: 1.1171 (1.1551) time: 0.6259 [2021-03-26 14:23:39 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 250/1251] eta: 0:10:43 lr: 0.000869 loss: 3.5932 (3.5743) grad_norm: 1.0583 (1.1526) time: 0.6290 [2021-03-26 14:23:45 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 260/1251] eta: 0:10:36 lr: 0.000869 loss: 3.2150 (3.5764) grad_norm: 1.0606 (1.1505) time: 0.6272 [2021-03-26 14:23:52 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 270/1251] eta: 0:10:29 lr: 0.000869 loss: 3.7446 (3.5730) grad_norm: 1.1408 (1.1561) time: 0.6294 [2021-03-26 14:23:58 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 280/1251] eta: 0:10:22 lr: 0.000869 loss: 3.5209 (3.5686) grad_norm: 1.1712 (1.1568) time: 0.6281 [2021-03-26 14:24:04 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 290/1251] eta: 0:10:15 lr: 0.000869 loss: 3.4328 (3.5689) grad_norm: 1.1139 (1.1544) time: 0.6215 [2021-03-26 14:24:10 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 300/1251] eta: 0:10:08 lr: 0.000869 loss: 3.5074 (3.5673) grad_norm: 1.0617 (1.1533) time: 0.6247 [2021-03-26 14:24:17 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 310/1251] eta: 0:10:02 lr: 0.000868 loss: 3.6037 (3.5700) grad_norm: 1.1145 (1.1524) time: 0.6289 [2021-03-26 14:24:23 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 320/1251] eta: 0:09:55 lr: 0.000868 loss: 3.7598 (3.5749) grad_norm: 1.1384 (1.1562) time: 0.6350 [2021-03-26 14:24:29 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 330/1251] eta: 0:09:49 lr: 0.000868 loss: 3.5466 (3.5743) grad_norm: 1.2439 (1.1593) time: 0.6352 [2021-03-26 14:24:36 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 340/1251] eta: 0:09:42 lr: 0.000868 loss: 3.5154 (3.5704) grad_norm: 1.2139 (1.1612) time: 0.6310 [2021-03-26 14:24:42 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 350/1251] eta: 0:09:35 lr: 0.000868 loss: 3.2947 (3.5600) grad_norm: 1.1084 (1.1591) time: 0.6291 [2021-03-26 14:24:48 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 360/1251] eta: 0:09:29 lr: 0.000868 loss: 3.3442 (3.5575) grad_norm: 1.0478 (1.1556) time: 0.6271 [2021-03-26 14:24:54 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 370/1251] eta: 0:09:22 lr: 0.000868 loss: 3.6884 (3.5632) grad_norm: 1.0392 (1.1559) time: 0.6247 [2021-03-26 14:25:01 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 380/1251] eta: 0:09:15 lr: 0.000868 loss: 3.6599 (3.5602) grad_norm: 1.0753 (1.1542) time: 0.6253 [2021-03-26 14:25:07 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 390/1251] eta: 0:09:08 lr: 0.000868 loss: 3.6599 (3.5625) grad_norm: 1.0753 (1.1531) time: 0.6246 [2021-03-26 14:25:13 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 400/1251] eta: 0:09:02 lr: 0.000868 loss: 3.5614 (3.5574) grad_norm: 1.1101 (1.1531) time: 0.6306 [2021-03-26 14:25:20 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 410/1251] eta: 0:08:56 lr: 0.000868 loss: 3.2071 (3.5544) grad_norm: 1.0987 (1.1517) time: 0.6371 [2021-03-26 14:25:26 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 420/1251] eta: 0:08:49 lr: 0.000868 loss: 3.3191 (3.5544) grad_norm: 1.0850 (1.1519) time: 0.6340 [2021-03-26 14:25:32 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 430/1251] eta: 0:08:43 lr: 0.000868 loss: 3.4081 (3.5513) grad_norm: 1.1581 (1.1550) time: 0.6298 [2021-03-26 14:25:38 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 440/1251] eta: 0:08:36 lr: 0.000868 loss: 3.4636 (3.5521) grad_norm: 1.1382 (1.1555) time: 0.6242 [2021-03-26 14:25:45 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 450/1251] eta: 0:08:29 lr: 0.000868 loss: 3.7151 (3.5535) grad_norm: 1.1170 (1.1535) time: 0.6253 [2021-03-26 14:25:51 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 460/1251] eta: 0:08:23 lr: 0.000868 loss: 3.8085 (3.5587) grad_norm: 1.1235 (1.1529) time: 0.6302 [2021-03-26 14:25:57 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 470/1251] eta: 0:08:16 lr: 0.000868 loss: 3.7771 (3.5635) grad_norm: 1.1362 (1.1533) time: 0.6247 [2021-03-26 14:26:04 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 480/1251] eta: 0:08:10 lr: 0.000868 loss: 3.5728 (3.5657) grad_norm: 1.1281 (1.1525) time: 0.6220 [2021-03-26 14:26:10 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 490/1251] eta: 0:08:03 lr: 0.000868 loss: 3.5907 (3.5674) grad_norm: 1.1370 (1.1529) time: 0.6313 [2021-03-26 14:26:16 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 500/1251] eta: 0:07:57 lr: 0.000868 loss: 3.5807 (3.5638) grad_norm: 1.1243 (1.1525) time: 0.6381 [2021-03-26 14:26:23 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 510/1251] eta: 0:07:51 lr: 0.000868 loss: 3.4446 (3.5633) grad_norm: 1.1051 (1.1521) time: 0.6313 [2021-03-26 14:26:29 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 520/1251] eta: 0:07:44 lr: 0.000868 loss: 3.7620 (3.5665) grad_norm: 1.1333 (1.1525) time: 0.6251 [2021-03-26 14:26:35 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 530/1251] eta: 0:07:38 lr: 0.000868 loss: 3.7146 (3.5618) grad_norm: 1.1333 (1.1532) time: 0.6306 [2021-03-26 14:26:41 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 540/1251] eta: 0:07:31 lr: 0.000868 loss: 3.3998 (3.5649) grad_norm: 1.1256 (1.1517) time: 0.6287 [2021-03-26 14:26:48 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 550/1251] eta: 0:07:25 lr: 0.000868 loss: 3.4728 (3.5637) grad_norm: 1.0476 (1.1511) time: 0.6412 [2021-03-26 14:26:54 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 560/1251] eta: 0:07:19 lr: 0.000868 loss: 3.4085 (3.5632) grad_norm: 1.0476 (1.1498) time: 0.6470 [2021-03-26 14:27:01 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 570/1251] eta: 0:07:12 lr: 0.000868 loss: 3.5891 (3.5663) grad_norm: 1.0858 (1.1504) time: 0.6275 [2021-03-26 14:27:07 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 580/1251] eta: 0:07:06 lr: 0.000868 loss: 3.5891 (3.5625) grad_norm: 1.0443 (1.1482) time: 0.6314 [2021-03-26 14:27:13 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 590/1251] eta: 0:07:00 lr: 0.000868 loss: 3.6589 (3.5672) grad_norm: 1.0344 (1.1483) time: 0.6348 [2021-03-26 14:27:20 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 600/1251] eta: 0:06:53 lr: 0.000868 loss: 3.8397 (3.5673) grad_norm: 1.1015 (1.1490) time: 0.6306 [2021-03-26 14:27:26 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 610/1251] eta: 0:06:47 lr: 0.000868 loss: 3.8397 (3.5715) grad_norm: 1.0857 (1.1479) time: 0.6291 [2021-03-26 14:27:32 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 620/1251] eta: 0:06:40 lr: 0.000868 loss: 3.7289 (3.5730) grad_norm: 1.0222 (1.1461) time: 0.6233 [2021-03-26 14:27:38 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 630/1251] eta: 0:06:34 lr: 0.000868 loss: 3.6587 (3.5755) grad_norm: 1.0423 (1.1469) time: 0.6233 [2021-03-26 14:27:45 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 640/1251] eta: 0:06:27 lr: 0.000868 loss: 3.7432 (3.5752) grad_norm: 1.1236 (1.1465) time: 0.6295 [2021-03-26 14:27:51 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 650/1251] eta: 0:06:21 lr: 0.000868 loss: 3.7432 (3.5768) grad_norm: 1.1733 (1.1472) time: 0.6344 [2021-03-26 14:27:57 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 660/1251] eta: 0:06:15 lr: 0.000868 loss: 3.8261 (3.5792) grad_norm: 1.1087 (1.1463) time: 0.6360 [2021-03-26 14:28:04 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 670/1251] eta: 0:06:08 lr: 0.000867 loss: 3.7815 (3.5819) grad_norm: 1.0908 (1.1462) time: 0.6319 [2021-03-26 14:28:10 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 680/1251] eta: 0:06:02 lr: 0.000867 loss: 3.6198 (3.5818) grad_norm: 1.1538 (1.1464) time: 0.6266 [2021-03-26 14:28:16 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 690/1251] eta: 0:05:56 lr: 0.000867 loss: 3.7254 (3.5852) grad_norm: 1.1010 (1.1459) time: 0.6288 [2021-03-26 14:28:23 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 700/1251] eta: 0:05:49 lr: 0.000867 loss: 3.8725 (3.5848) grad_norm: 1.0773 (1.1456) time: 0.6327 [2021-03-26 14:28:29 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 710/1251] eta: 0:05:43 lr: 0.000867 loss: 3.7512 (3.5846) grad_norm: 1.1218 (1.1473) time: 0.6299 [2021-03-26 14:28:35 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 720/1251] eta: 0:05:36 lr: 0.000867 loss: 3.6216 (3.5821) grad_norm: 1.1315 (1.1473) time: 0.6294 [2021-03-26 14:28:41 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 730/1251] eta: 0:05:30 lr: 0.000867 loss: 3.5113 (3.5824) grad_norm: 1.1315 (1.1484) time: 0.6330 [2021-03-26 14:28:48 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 740/1251] eta: 0:05:24 lr: 0.000867 loss: 3.6566 (3.5836) grad_norm: 1.1631 (1.1483) time: 0.6400 [2021-03-26 14:28:54 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 750/1251] eta: 0:05:17 lr: 0.000867 loss: 3.5558 (3.5819) grad_norm: 1.0600 (1.1469) time: 0.6424 [2021-03-26 14:29:01 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 760/1251] eta: 0:05:11 lr: 0.000867 loss: 3.6808 (3.5850) grad_norm: 1.0279 (1.1461) time: 0.6331 [2021-03-26 14:29:07 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 770/1251] eta: 0:05:05 lr: 0.000867 loss: 3.8820 (3.5875) grad_norm: 1.0975 (1.1468) time: 0.6288 [2021-03-26 14:29:13 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 780/1251] eta: 0:04:58 lr: 0.000867 loss: 3.7312 (3.5880) grad_norm: 1.1074 (1.1461) time: 0.6288 [2021-03-26 14:29:19 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 790/1251] eta: 0:04:52 lr: 0.000867 loss: 3.7540 (3.5910) grad_norm: 1.0895 (1.1454) time: 0.6250 [2021-03-26 14:29:26 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 800/1251] eta: 0:04:45 lr: 0.000867 loss: 3.9459 (3.5971) grad_norm: 1.1228 (1.1459) time: 0.6222 [2021-03-26 14:29:32 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 810/1251] eta: 0:04:39 lr: 0.000867 loss: 3.8010 (3.5931) grad_norm: 1.1345 (1.1463) time: 0.6228 [2021-03-26 14:29:38 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 820/1251] eta: 0:04:33 lr: 0.000867 loss: 3.2488 (3.5928) grad_norm: 1.0682 (1.1457) time: 0.6252 [2021-03-26 14:29:44 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 830/1251] eta: 0:04:26 lr: 0.000867 loss: 3.8850 (3.5974) grad_norm: 1.1602 (1.1474) time: 0.6269 [2021-03-26 14:29:51 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 840/1251] eta: 0:04:20 lr: 0.000867 loss: 3.8427 (3.5959) grad_norm: 1.1965 (1.1472) time: 0.6243 [2021-03-26 14:29:57 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 850/1251] eta: 0:04:14 lr: 0.000867 loss: 3.5794 (3.5961) grad_norm: 1.1718 (1.1483) time: 0.6268 [2021-03-26 14:30:03 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 860/1251] eta: 0:04:07 lr: 0.000867 loss: 3.6283 (3.5981) grad_norm: 1.1098 (1.1476) time: 0.6278 [2021-03-26 14:30:10 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 870/1251] eta: 0:04:01 lr: 0.000867 loss: 3.7436 (3.5982) grad_norm: 1.0600 (1.1475) time: 0.6286 [2021-03-26 14:30:16 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 880/1251] eta: 0:03:54 lr: 0.000867 loss: 3.7272 (3.5999) grad_norm: 1.0279 (1.1465) time: 0.6268 [2021-03-26 14:30:22 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 890/1251] eta: 0:03:48 lr: 0.000867 loss: 3.5702 (3.5991) grad_norm: 1.0279 (1.1461) time: 0.6245 [2021-03-26 14:30:28 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 900/1251] eta: 0:03:42 lr: 0.000867 loss: 3.5362 (3.5985) grad_norm: 1.1094 (1.1462) time: 0.6309 [2021-03-26 14:30:35 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 910/1251] eta: 0:03:35 lr: 0.000867 loss: 3.7098 (3.5968) grad_norm: 1.0763 (1.1450) time: 0.6295 [2021-03-26 14:30:41 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 920/1251] eta: 0:03:29 lr: 0.000867 loss: 3.6601 (3.5968) grad_norm: 0.9976 (1.1437) time: 0.6214 [2021-03-26 14:30:47 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 930/1251] eta: 0:03:23 lr: 0.000867 loss: 3.6081 (3.5975) grad_norm: 0.9976 (1.1431) time: 0.6209 [2021-03-26 14:30:53 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 940/1251] eta: 0:03:16 lr: 0.000867 loss: 3.5250 (3.5977) grad_norm: 1.1264 (1.1430) time: 0.6310 [2021-03-26 14:31:00 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 950/1251] eta: 0:03:10 lr: 0.000867 loss: 3.8766 (3.6001) grad_norm: 1.1050 (1.1423) time: 0.6363 [2021-03-26 14:31:06 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 960/1251] eta: 0:03:04 lr: 0.000867 loss: 3.8495 (3.6023) grad_norm: 1.0422 (1.1413) time: 0.6279 [2021-03-26 14:31:12 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 970/1251] eta: 0:02:57 lr: 0.000867 loss: 3.8135 (3.6023) grad_norm: 1.0894 (1.1414) time: 0.6221 [2021-03-26 14:31:18 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 980/1251] eta: 0:02:51 lr: 0.000867 loss: 3.8898 (3.6039) grad_norm: 1.1198 (1.1413) time: 0.6216 [2021-03-26 14:31:25 swin_base_patch4_window7_224] INFO: Epoch: [71] [ 990/1251] eta: 0:02:45 lr: 0.000867 loss: 3.8835 (3.6053) grad_norm: 1.0746 (1.1409) time: 0.6301 [2021-03-26 14:31:31 swin_base_patch4_window7_224] INFO: Epoch: [71] [1000/1251] eta: 0:02:38 lr: 0.000867 loss: 3.8068 (3.6055) grad_norm: 1.0435 (1.1398) time: 0.6327 [2021-03-26 14:31:37 swin_base_patch4_window7_224] INFO: Epoch: [71] [1010/1251] eta: 0:02:32 lr: 0.000867 loss: 3.8095 (3.6075) grad_norm: 1.0608 (1.1400) time: 0.6310 [2021-03-26 14:31:44 swin_base_patch4_window7_224] INFO: Epoch: [71] [1020/1251] eta: 0:02:26 lr: 0.000866 loss: 3.8409 (3.6073) grad_norm: 1.1816 (1.1403) time: 0.6360 [2021-03-26 14:31:50 swin_base_patch4_window7_224] INFO: Epoch: [71] [1030/1251] eta: 0:02:19 lr: 0.000866 loss: 3.3270 (3.6045) grad_norm: 1.1519 (1.1402) time: 0.6336 [2021-03-26 14:31:56 swin_base_patch4_window7_224] INFO: Epoch: [71] [1040/1251] eta: 0:02:13 lr: 0.000866 loss: 3.3808 (3.6029) grad_norm: 1.0759 (1.1403) time: 0.6262 [2021-03-26 14:32:03 swin_base_patch4_window7_224] INFO: Epoch: [71] [1050/1251] eta: 0:02:07 lr: 0.000866 loss: 3.4716 (3.6019) grad_norm: 1.2027 (1.1410) time: 0.6251 [2021-03-26 14:32:09 swin_base_patch4_window7_224] INFO: Epoch: [71] [1060/1251] eta: 0:02:00 lr: 0.000866 loss: 3.5866 (3.6035) grad_norm: 1.1106 (1.1406) time: 0.6279 [2021-03-26 14:32:15 swin_base_patch4_window7_224] INFO: Epoch: [71] [1070/1251] eta: 0:01:54 lr: 0.000866 loss: 3.8377 (3.6044) grad_norm: 1.1375 (1.1421) time: 0.6322 [2021-03-26 14:32:22 swin_base_patch4_window7_224] INFO: Epoch: [71] [1080/1251] eta: 0:01:48 lr: 0.000866 loss: 3.6969 (3.6042) grad_norm: 1.1435 (1.1417) time: 0.6319 [2021-03-26 14:32:28 swin_base_patch4_window7_224] INFO: Epoch: [71] [1090/1251] eta: 0:01:41 lr: 0.000866 loss: 3.7485 (3.6065) grad_norm: 1.1270 (1.1422) time: 0.6282 [2021-03-26 14:32:34 swin_base_patch4_window7_224] INFO: Epoch: [71] [1100/1251] eta: 0:01:35 lr: 0.000866 loss: 3.7399 (3.6054) grad_norm: 1.0985 (1.1418) time: 0.6296 [2021-03-26 14:32:40 swin_base_patch4_window7_224] INFO: Epoch: [71] [1110/1251] eta: 0:01:29 lr: 0.000866 loss: 3.4513 (3.6024) grad_norm: 1.0985 (1.1418) time: 0.6243 [2021-03-26 14:32:47 swin_base_patch4_window7_224] INFO: Epoch: [71] [1120/1251] eta: 0:01:22 lr: 0.000866 loss: 3.6716 (3.6036) grad_norm: 1.1196 (1.1415) time: 0.6214 [2021-03-26 14:32:53 swin_base_patch4_window7_224] INFO: Epoch: [71] [1130/1251] eta: 0:01:16 lr: 0.000866 loss: 3.9484 (3.6059) grad_norm: 1.1069 (1.1413) time: 0.6230 [2021-03-26 14:32:59 swin_base_patch4_window7_224] INFO: Epoch: [71] [1140/1251] eta: 0:01:10 lr: 0.000866 loss: 3.8312 (3.6057) grad_norm: 1.1300 (1.1421) time: 0.6237 [2021-03-26 14:33:05 swin_base_patch4_window7_224] INFO: Epoch: [71] [1150/1251] eta: 0:01:03 lr: 0.000866 loss: 3.6707 (3.6073) grad_norm: 1.2528 (1.1436) time: 0.6271 [2021-03-26 14:33:12 swin_base_patch4_window7_224] INFO: Epoch: [71] [1160/1251] eta: 0:00:57 lr: 0.000866 loss: 3.8515 (3.6063) grad_norm: 1.1577 (1.1436) time: 0.6257 [2021-03-26 14:33:18 swin_base_patch4_window7_224] INFO: Epoch: [71] [1170/1251] eta: 0:00:51 lr: 0.000866 loss: 3.4022 (3.6052) grad_norm: 1.1100 (1.1431) time: 0.6226 [2021-03-26 14:33:24 swin_base_patch4_window7_224] INFO: Epoch: [71] [1180/1251] eta: 0:00:44 lr: 0.000866 loss: 3.2981 (3.6018) grad_norm: 1.0644 (1.1427) time: 0.6242 [2021-03-26 14:33:30 swin_base_patch4_window7_224] INFO: Epoch: [71] [1190/1251] eta: 0:00:38 lr: 0.000866 loss: 3.2283 (3.5990) grad_norm: 1.0843 (1.1428) time: 0.6248 [2021-03-26 14:33:37 swin_base_patch4_window7_224] INFO: Epoch: [71] [1200/1251] eta: 0:00:32 lr: 0.000866 loss: 3.5015 (3.5991) grad_norm: 1.1016 (1.1431) time: 0.6283 [2021-03-26 14:33:43 swin_base_patch4_window7_224] INFO: Epoch: [71] [1210/1251] eta: 0:00:25 lr: 0.000866 loss: 3.6386 (3.5981) grad_norm: 1.1154 (1.1428) time: 0.6272 [2021-03-26 14:33:49 swin_base_patch4_window7_224] INFO: Epoch: [71] [1220/1251] eta: 0:00:19 lr: 0.000866 loss: 3.6386 (3.5978) grad_norm: 1.1765 (1.1431) time: 0.6271 [2021-03-26 14:33:55 swin_base_patch4_window7_224] INFO: Epoch: [71] [1230/1251] eta: 0:00:13 lr: 0.000866 loss: 3.6714 (3.5974) grad_norm: 1.1655 (1.1435) time: 0.6260 [2021-03-26 14:34:02 swin_base_patch4_window7_224] INFO: Epoch: [71] [1240/1251] eta: 0:00:06 lr: 0.000866 loss: 3.6935 (3.5970) grad_norm: 1.1222 (1.1435) time: 0.6222 [2021-03-26 14:34:08 swin_base_patch4_window7_224] INFO: Epoch: [71] [1250/1251] eta: 0:00:00 lr: 0.000866 loss: 3.6935 (3.5970) grad_norm: 1.1531 (1.1438) time: 0.6258 [2021-03-26 14:34:15 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:17 loss: 1.4963 (1.4963) acc1: 71.8750 (71.8750) acc5: 84.3750 (84.3750) [2021-03-26 14:34:17 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.0663 (1.0953) acc1: 76.5625 (75.9943) acc5: 93.7500 (93.0398) [2021-03-26 14:34:20 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.0547 (1.0902) acc1: 75.0000 (75.0000) acc5: 93.7500 (92.7827) [2021-03-26 14:34:22 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9510 (1.0542) acc1: 73.4375 (75.4032) acc5: 93.7500 (93.1956) [2021-03-26 14:34:24 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0453 (1.0722) acc1: 73.4375 (74.8095) acc5: 93.7500 (93.2927) [2021-03-26 14:34:25 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0952 (1.0792) acc1: 73.4375 (74.7200) acc5: 93.7500 (93.3760) [2021-03-26 14:34:29 swin_base_patch4_window7_224] INFO: * Acc@1 74.910 Acc@5 92.956 loss 1.078 [2021-03-26 14:34:29 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.9% [2021-03-26 14:34:29 swin_base_patch4_window7_224] INFO: Max accuracy: 74.92% [2021-03-26 14:34:33 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 0/1251] eta: 1:39:16 lr: 0.000866 loss: 3.6937 (3.6937) grad_norm: 0.9669 (0.9669) time: 4.7611 [2021-03-26 14:34:40 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 10/1251] eta: 0:20:50 lr: 0.000866 loss: 3.7170 (3.6785) grad_norm: 1.0516 (1.0949) time: 1.0073 [2021-03-26 14:34:46 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 20/1251] eta: 0:16:59 lr: 0.000866 loss: 3.6959 (3.5990) grad_norm: 1.1149 (1.1050) time: 0.6314 [2021-03-26 14:34:52 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 30/1251] eta: 0:15:32 lr: 0.000866 loss: 3.5849 (3.6274) grad_norm: 1.1149 (1.1091) time: 0.6295 [2021-03-26 14:34:59 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 40/1251] eta: 0:14:45 lr: 0.000866 loss: 3.7213 (3.6780) grad_norm: 1.1057 (1.1113) time: 0.6297 [2021-03-26 14:35:05 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 50/1251] eta: 0:14:12 lr: 0.000866 loss: 3.7224 (3.6669) grad_norm: 1.0685 (1.1042) time: 0.6276 [2021-03-26 14:35:11 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 60/1251] eta: 0:13:49 lr: 0.000866 loss: 3.8431 (3.6895) grad_norm: 1.0548 (1.1005) time: 0.6243 [2021-03-26 14:35:18 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 70/1251] eta: 0:13:32 lr: 0.000866 loss: 3.8105 (3.6731) grad_norm: 1.0627 (1.1065) time: 0.6309 [2021-03-26 14:35:24 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 80/1251] eta: 0:13:16 lr: 0.000866 loss: 3.5454 (3.6476) grad_norm: 1.1186 (1.1130) time: 0.6328 [2021-03-26 14:35:30 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 90/1251] eta: 0:13:04 lr: 0.000866 loss: 3.3320 (3.6038) grad_norm: 1.1796 (1.1233) time: 0.6311 [2021-03-26 14:35:37 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 100/1251] eta: 0:12:52 lr: 0.000866 loss: 3.5158 (3.6003) grad_norm: 1.2105 (1.1352) time: 0.6347 [2021-03-26 14:35:43 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 110/1251] eta: 0:12:40 lr: 0.000866 loss: 3.8476 (3.6359) grad_norm: 1.1560 (1.1338) time: 0.6278 [2021-03-26 14:35:49 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 120/1251] eta: 0:12:30 lr: 0.000865 loss: 3.7641 (3.6337) grad_norm: 1.1432 (1.1459) time: 0.6241 [2021-03-26 14:35:55 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 130/1251] eta: 0:12:20 lr: 0.000865 loss: 3.5662 (3.6263) grad_norm: 1.1410 (1.1467) time: 0.6263 [2021-03-26 14:36:02 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 140/1251] eta: 0:12:11 lr: 0.000865 loss: 3.6112 (3.6304) grad_norm: 1.1167 (1.1498) time: 0.6264 [2021-03-26 14:36:08 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 150/1251] eta: 0:12:02 lr: 0.000865 loss: 3.5373 (3.6180) grad_norm: 1.0728 (1.1454) time: 0.6255 [2021-03-26 14:36:14 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 160/1251] eta: 0:11:54 lr: 0.000865 loss: 3.5886 (3.6233) grad_norm: 1.0408 (1.1436) time: 0.6283 [2021-03-26 14:36:20 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 170/1251] eta: 0:11:45 lr: 0.000865 loss: 3.7438 (3.6176) grad_norm: 1.0725 (1.1400) time: 0.6268 [2021-03-26 14:36:27 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 180/1251] eta: 0:11:37 lr: 0.000865 loss: 3.6706 (3.6297) grad_norm: 1.0725 (1.1400) time: 0.6233 [2021-03-26 14:36:33 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 190/1251] eta: 0:11:29 lr: 0.000865 loss: 3.8448 (3.6274) grad_norm: 1.1290 (1.1460) time: 0.6268 [2021-03-26 14:36:39 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 200/1251] eta: 0:11:22 lr: 0.000865 loss: 3.8270 (3.6279) grad_norm: 1.1290 (1.1448) time: 0.6305 [2021-03-26 14:36:46 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 210/1251] eta: 0:11:15 lr: 0.000865 loss: 3.7370 (3.6303) grad_norm: 1.1100 (1.1492) time: 0.6371 [2021-03-26 14:36:52 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 220/1251] eta: 0:11:08 lr: 0.000865 loss: 3.6023 (3.6213) grad_norm: 1.1724 (1.1548) time: 0.6366 [2021-03-26 14:36:58 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 230/1251] eta: 0:11:00 lr: 0.000865 loss: 3.3346 (3.6132) grad_norm: 1.1724 (1.1567) time: 0.6295 [2021-03-26 14:37:04 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 240/1251] eta: 0:10:53 lr: 0.000865 loss: 3.6357 (3.6046) grad_norm: 1.0992 (1.1541) time: 0.6251 [2021-03-26 14:37:11 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 250/1251] eta: 0:10:45 lr: 0.000865 loss: 3.6357 (3.6091) grad_norm: 1.0515 (1.1523) time: 0.6217 [2021-03-26 14:37:17 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 260/1251] eta: 0:10:38 lr: 0.000865 loss: 3.6055 (3.6017) grad_norm: 1.0355 (1.1504) time: 0.6217 [2021-03-26 14:37:23 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 270/1251] eta: 0:10:31 lr: 0.000865 loss: 3.4508 (3.5909) grad_norm: 1.0637 (1.1481) time: 0.6288 [2021-03-26 14:37:29 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 280/1251] eta: 0:10:24 lr: 0.000865 loss: 3.6258 (3.6003) grad_norm: 1.0372 (1.1450) time: 0.6237 [2021-03-26 14:37:36 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 290/1251] eta: 0:10:17 lr: 0.000865 loss: 3.5900 (3.5866) grad_norm: 1.0456 (1.1430) time: 0.6205 [2021-03-26 14:37:42 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 300/1251] eta: 0:10:10 lr: 0.000865 loss: 3.7656 (3.5998) grad_norm: 1.0757 (1.1414) time: 0.6268 [2021-03-26 14:37:48 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 310/1251] eta: 0:10:03 lr: 0.000865 loss: 3.7417 (3.5948) grad_norm: 1.0611 (1.1399) time: 0.6293 [2021-03-26 14:37:54 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 320/1251] eta: 0:09:56 lr: 0.000865 loss: 3.5006 (3.5931) grad_norm: 1.1345 (inf) time: 0.6270 [2021-03-26 14:38:01 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 330/1251] eta: 0:09:49 lr: 0.000865 loss: 3.6786 (3.5915) grad_norm: 1.1940 (inf) time: 0.6261 [2021-03-26 14:38:07 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 340/1251] eta: 0:09:43 lr: 0.000865 loss: 3.8611 (3.6027) grad_norm: 1.1503 (inf) time: 0.6303 [2021-03-26 14:38:13 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 350/1251] eta: 0:09:36 lr: 0.000865 loss: 3.8444 (3.6071) grad_norm: 1.1984 (inf) time: 0.6293 [2021-03-26 14:38:20 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 360/1251] eta: 0:09:29 lr: 0.000865 loss: 3.6437 (3.6083) grad_norm: 1.1528 (inf) time: 0.6272 [2021-03-26 14:38:26 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 370/1251] eta: 0:09:23 lr: 0.000865 loss: 3.6914 (3.6099) grad_norm: 1.1349 (inf) time: 0.6260 [2021-03-26 14:38:32 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 380/1251] eta: 0:09:16 lr: 0.000865 loss: 3.7942 (3.6128) grad_norm: 1.1635 (inf) time: 0.6278 [2021-03-26 14:38:39 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 390/1251] eta: 0:09:09 lr: 0.000865 loss: 3.3655 (3.6046) grad_norm: 1.1508 (inf) time: 0.6326 [2021-03-26 14:38:45 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 400/1251] eta: 0:09:03 lr: 0.000865 loss: 3.3655 (3.6069) grad_norm: 1.1631 (inf) time: 0.6377 [2021-03-26 14:38:51 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 410/1251] eta: 0:08:57 lr: 0.000865 loss: 3.6369 (3.6068) grad_norm: 1.1634 (inf) time: 0.6378 [2021-03-26 14:38:58 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 420/1251] eta: 0:08:50 lr: 0.000865 loss: 3.6684 (3.6077) grad_norm: 1.0657 (inf) time: 0.6285 [2021-03-26 14:39:04 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 430/1251] eta: 0:08:43 lr: 0.000865 loss: 3.6684 (3.6069) grad_norm: 1.0657 (inf) time: 0.6236 [2021-03-26 14:39:10 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 440/1251] eta: 0:08:37 lr: 0.000865 loss: 3.6461 (3.6065) grad_norm: 1.1058 (inf) time: 0.6235 [2021-03-26 14:39:16 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 450/1251] eta: 0:08:30 lr: 0.000865 loss: 3.5979 (3.6001) grad_norm: 1.1286 (inf) time: 0.6215 [2021-03-26 14:39:22 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 460/1251] eta: 0:08:23 lr: 0.000865 loss: 3.7676 (3.6060) grad_norm: 1.0652 (inf) time: 0.6239 [2021-03-26 14:39:29 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 470/1251] eta: 0:08:17 lr: 0.000865 loss: 3.8340 (3.6069) grad_norm: 1.0504 (inf) time: 0.6278 [2021-03-26 14:39:35 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 480/1251] eta: 0:08:11 lr: 0.000864 loss: 3.8340 (3.6115) grad_norm: 1.0504 (inf) time: 0.6332 [2021-03-26 14:39:41 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 490/1251] eta: 0:08:04 lr: 0.000864 loss: 3.8151 (3.6102) grad_norm: 1.1013 (inf) time: 0.6327 [2021-03-26 14:39:48 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 500/1251] eta: 0:07:57 lr: 0.000864 loss: 3.1851 (3.6029) grad_norm: 1.0930 (inf) time: 0.6261 [2021-03-26 14:39:54 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 510/1251] eta: 0:07:51 lr: 0.000864 loss: 3.3031 (3.6018) grad_norm: 1.0426 (inf) time: 0.6275 [2021-03-26 14:40:00 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 520/1251] eta: 0:07:44 lr: 0.000864 loss: 3.5814 (3.5987) grad_norm: 1.0657 (inf) time: 0.6275 [2021-03-26 14:40:06 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 530/1251] eta: 0:07:38 lr: 0.000864 loss: 3.5814 (3.5983) grad_norm: 1.1145 (inf) time: 0.6245 [2021-03-26 14:40:13 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 540/1251] eta: 0:07:31 lr: 0.000864 loss: 3.7059 (3.5982) grad_norm: 1.1326 (inf) time: 0.6256 [2021-03-26 14:40:19 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 550/1251] eta: 0:07:25 lr: 0.000864 loss: 3.5204 (3.5934) grad_norm: 1.1126 (inf) time: 0.6390 [2021-03-26 14:40:25 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 560/1251] eta: 0:07:19 lr: 0.000864 loss: 3.5204 (3.5954) grad_norm: 1.0968 (inf) time: 0.6355 [2021-03-26 14:40:32 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 570/1251] eta: 0:07:12 lr: 0.000864 loss: 3.5757 (3.5908) grad_norm: 1.1035 (inf) time: 0.6240 [2021-03-26 14:40:38 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 580/1251] eta: 0:07:06 lr: 0.000864 loss: 3.4759 (3.5903) grad_norm: 1.1110 (inf) time: 0.6238 [2021-03-26 14:40:44 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 590/1251] eta: 0:06:59 lr: 0.000864 loss: 3.6271 (3.5870) grad_norm: 1.1624 (inf) time: 0.6209 [2021-03-26 14:40:50 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 600/1251] eta: 0:06:53 lr: 0.000864 loss: 3.5504 (3.5829) grad_norm: 1.1364 (inf) time: 0.6273 [2021-03-26 14:40:57 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 610/1251] eta: 0:06:47 lr: 0.000864 loss: 3.5732 (3.5838) grad_norm: 1.1387 (inf) time: 0.6316 [2021-03-26 14:41:03 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 620/1251] eta: 0:06:40 lr: 0.000864 loss: 3.7136 (3.5842) grad_norm: 1.1320 (inf) time: 0.6321 [2021-03-26 14:41:10 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 630/1251] eta: 0:06:34 lr: 0.000864 loss: 3.9833 (3.5897) grad_norm: 1.1320 (inf) time: 0.6363 [2021-03-26 14:41:16 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 640/1251] eta: 0:06:27 lr: 0.000864 loss: 3.9850 (3.5947) grad_norm: 1.1187 (inf) time: 0.6312 [2021-03-26 14:41:22 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 650/1251] eta: 0:06:21 lr: 0.000864 loss: 3.7883 (3.5970) grad_norm: 1.1280 (inf) time: 0.6322 [2021-03-26 14:41:28 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 660/1251] eta: 0:06:15 lr: 0.000864 loss: 3.5948 (3.5966) grad_norm: 1.1053 (inf) time: 0.6341 [2021-03-26 14:41:35 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 670/1251] eta: 0:06:08 lr: 0.000864 loss: 3.5862 (3.5950) grad_norm: 1.0869 (inf) time: 0.6267 [2021-03-26 14:41:41 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 680/1251] eta: 0:06:02 lr: 0.000864 loss: 3.4159 (3.5915) grad_norm: 1.1442 (inf) time: 0.6287 [2021-03-26 14:41:47 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 690/1251] eta: 0:05:55 lr: 0.000864 loss: 3.6324 (3.5947) grad_norm: 1.1145 (inf) time: 0.6281 [2021-03-26 14:41:54 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 700/1251] eta: 0:05:49 lr: 0.000864 loss: 3.6973 (3.5941) grad_norm: 1.1294 (inf) time: 0.6268 [2021-03-26 14:42:00 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 710/1251] eta: 0:05:43 lr: 0.000864 loss: 3.6973 (3.5951) grad_norm: 1.1389 (inf) time: 0.6275 [2021-03-26 14:42:06 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 720/1251] eta: 0:05:36 lr: 0.000864 loss: 3.7627 (3.5967) grad_norm: 1.0808 (inf) time: 0.6268 [2021-03-26 14:42:12 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 730/1251] eta: 0:05:30 lr: 0.000864 loss: 3.6161 (3.5938) grad_norm: 1.0794 (inf) time: 0.6287 [2021-03-26 14:42:19 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 740/1251] eta: 0:05:24 lr: 0.000864 loss: 3.6161 (3.5938) grad_norm: 1.0735 (inf) time: 0.6384 [2021-03-26 14:42:25 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 750/1251] eta: 0:05:17 lr: 0.000864 loss: 3.8318 (3.5947) grad_norm: 1.1126 (inf) time: 0.6457 [2021-03-26 14:42:32 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 760/1251] eta: 0:05:11 lr: 0.000864 loss: 3.7829 (3.5964) grad_norm: 1.1145 (inf) time: 0.6352 [2021-03-26 14:42:38 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 770/1251] eta: 0:05:05 lr: 0.000864 loss: 3.6462 (3.5940) grad_norm: 1.1145 (inf) time: 0.6255 [2021-03-26 14:42:44 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 780/1251] eta: 0:04:58 lr: 0.000864 loss: 3.6399 (3.5948) grad_norm: 1.1101 (inf) time: 0.6285 [2021-03-26 14:42:50 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 790/1251] eta: 0:04:52 lr: 0.000864 loss: 3.9275 (3.5994) grad_norm: 1.0738 (inf) time: 0.6310 [2021-03-26 14:42:57 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 800/1251] eta: 0:04:45 lr: 0.000864 loss: 3.9561 (3.6005) grad_norm: 1.0850 (inf) time: 0.6328 [2021-03-26 14:43:03 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 810/1251] eta: 0:04:39 lr: 0.000864 loss: 3.8931 (3.6028) grad_norm: 1.0961 (inf) time: 0.6260 [2021-03-26 14:43:09 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 820/1251] eta: 0:04:33 lr: 0.000864 loss: 3.8628 (3.6038) grad_norm: 1.0316 (inf) time: 0.6255 [2021-03-26 14:43:16 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 830/1251] eta: 0:04:26 lr: 0.000863 loss: 3.5778 (3.6062) grad_norm: 1.1240 (inf) time: 0.6302 [2021-03-26 14:43:22 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 840/1251] eta: 0:04:20 lr: 0.000863 loss: 3.5936 (3.6049) grad_norm: 1.1240 (inf) time: 0.6345 [2021-03-26 14:43:28 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 850/1251] eta: 0:04:14 lr: 0.000863 loss: 3.8866 (3.6075) grad_norm: 1.0947 (inf) time: 0.6288 [2021-03-26 14:43:34 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 860/1251] eta: 0:04:07 lr: 0.000863 loss: 3.9216 (3.6096) grad_norm: 1.1309 (inf) time: 0.6246 [2021-03-26 14:43:41 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 870/1251] eta: 0:04:01 lr: 0.000863 loss: 3.6803 (3.6091) grad_norm: 1.1309 (inf) time: 0.6300 [2021-03-26 14:43:47 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 880/1251] eta: 0:03:55 lr: 0.000863 loss: 3.5650 (3.6095) grad_norm: 1.1094 (inf) time: 0.6277 [2021-03-26 14:43:53 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 890/1251] eta: 0:03:48 lr: 0.000863 loss: 3.8413 (3.6113) grad_norm: 1.1548 (inf) time: 0.6338 [2021-03-26 14:44:00 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 900/1251] eta: 0:03:42 lr: 0.000863 loss: 3.8791 (3.6120) grad_norm: 1.1968 (inf) time: 0.6413 [2021-03-26 14:44:06 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 910/1251] eta: 0:03:36 lr: 0.000863 loss: 3.6748 (3.6125) grad_norm: 1.1506 (inf) time: 0.6351 [2021-03-26 14:44:12 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 920/1251] eta: 0:03:29 lr: 0.000863 loss: 3.8143 (3.6140) grad_norm: 1.1244 (inf) time: 0.6282 [2021-03-26 14:44:19 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 930/1251] eta: 0:03:23 lr: 0.000863 loss: 3.8143 (3.6128) grad_norm: 1.2098 (inf) time: 0.6281 [2021-03-26 14:44:25 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 940/1251] eta: 0:03:17 lr: 0.000863 loss: 3.4797 (3.6100) grad_norm: 1.1374 (inf) time: 0.6311 [2021-03-26 14:44:31 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 950/1251] eta: 0:03:10 lr: 0.000863 loss: 3.2148 (3.6076) grad_norm: 1.0492 (inf) time: 0.6344 [2021-03-26 14:44:38 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 960/1251] eta: 0:03:04 lr: 0.000863 loss: 3.5480 (3.6076) grad_norm: 1.0514 (inf) time: 0.6297 [2021-03-26 14:44:44 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 970/1251] eta: 0:02:57 lr: 0.000863 loss: 3.7337 (3.6086) grad_norm: 1.0514 (inf) time: 0.6261 [2021-03-26 14:44:50 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 980/1251] eta: 0:02:51 lr: 0.000863 loss: 3.8038 (3.6096) grad_norm: 1.0572 (inf) time: 0.6254 [2021-03-26 14:44:56 swin_base_patch4_window7_224] INFO: Epoch: [72] [ 990/1251] eta: 0:02:45 lr: 0.000863 loss: 3.7092 (3.6100) grad_norm: 1.1148 (inf) time: 0.6265 [2021-03-26 14:45:03 swin_base_patch4_window7_224] INFO: Epoch: [72] [1000/1251] eta: 0:02:38 lr: 0.000863 loss: 3.6732 (3.6102) grad_norm: 1.1043 (inf) time: 0.6295 [2021-03-26 14:45:09 swin_base_patch4_window7_224] INFO: Epoch: [72] [1010/1251] eta: 0:02:32 lr: 0.000863 loss: 3.7306 (3.6120) grad_norm: 1.1169 (inf) time: 0.6282 [2021-03-26 14:45:15 swin_base_patch4_window7_224] INFO: Epoch: [72] [1020/1251] eta: 0:02:26 lr: 0.000863 loss: 3.8330 (3.6128) grad_norm: 1.1161 (inf) time: 0.6252 [2021-03-26 14:45:22 swin_base_patch4_window7_224] INFO: Epoch: [72] [1030/1251] eta: 0:02:19 lr: 0.000863 loss: 3.6711 (3.6106) grad_norm: 1.1028 (inf) time: 0.6274 [2021-03-26 14:45:28 swin_base_patch4_window7_224] INFO: Epoch: [72] [1040/1251] eta: 0:02:13 lr: 0.000863 loss: 3.5699 (3.6112) grad_norm: 1.1038 (inf) time: 0.6287 [2021-03-26 14:45:34 swin_base_patch4_window7_224] INFO: Epoch: [72] [1050/1251] eta: 0:02:07 lr: 0.000863 loss: 3.5699 (3.6092) grad_norm: 1.1840 (inf) time: 0.6264 [2021-03-26 14:45:40 swin_base_patch4_window7_224] INFO: Epoch: [72] [1060/1251] eta: 0:02:00 lr: 0.000863 loss: 3.7886 (3.6113) grad_norm: 1.2081 (inf) time: 0.6270 [2021-03-26 14:45:47 swin_base_patch4_window7_224] INFO: Epoch: [72] [1070/1251] eta: 0:01:54 lr: 0.000863 loss: 3.8362 (3.6140) grad_norm: 1.1627 (inf) time: 0.6246 [2021-03-26 14:45:53 swin_base_patch4_window7_224] INFO: Epoch: [72] [1080/1251] eta: 0:01:48 lr: 0.000863 loss: 3.7953 (3.6155) grad_norm: 1.0486 (inf) time: 0.6227 [2021-03-26 14:45:59 swin_base_patch4_window7_224] INFO: Epoch: [72] [1090/1251] eta: 0:01:41 lr: 0.000863 loss: 3.7555 (3.6164) grad_norm: 1.0577 (inf) time: 0.6293 [2021-03-26 14:46:06 swin_base_patch4_window7_224] INFO: Epoch: [72] [1100/1251] eta: 0:01:35 lr: 0.000863 loss: 3.8096 (3.6180) grad_norm: 1.1042 (inf) time: 0.6334 [2021-03-26 14:46:12 swin_base_patch4_window7_224] INFO: Epoch: [72] [1110/1251] eta: 0:01:29 lr: 0.000863 loss: 3.7211 (3.6178) grad_norm: 1.1553 (inf) time: 0.6276 [2021-03-26 14:46:18 swin_base_patch4_window7_224] INFO: Epoch: [72] [1120/1251] eta: 0:01:22 lr: 0.000863 loss: 3.5814 (3.6141) grad_norm: 1.0881 (inf) time: 0.6265 [2021-03-26 14:46:24 swin_base_patch4_window7_224] INFO: Epoch: [72] [1130/1251] eta: 0:01:16 lr: 0.000863 loss: 3.7160 (3.6168) grad_norm: 1.1298 (inf) time: 0.6289 [2021-03-26 14:46:31 swin_base_patch4_window7_224] INFO: Epoch: [72] [1140/1251] eta: 0:01:10 lr: 0.000863 loss: 3.7787 (3.6164) grad_norm: 1.2281 (inf) time: 0.6229 [2021-03-26 14:46:37 swin_base_patch4_window7_224] INFO: Epoch: [72] [1150/1251] eta: 0:01:03 lr: 0.000863 loss: 3.1759 (3.6132) grad_norm: 1.1705 (inf) time: 0.6203 [2021-03-26 14:46:43 swin_base_patch4_window7_224] INFO: Epoch: [72] [1160/1251] eta: 0:00:57 lr: 0.000863 loss: 3.5923 (3.6137) grad_norm: 1.0933 (inf) time: 0.6263 [2021-03-26 14:46:49 swin_base_patch4_window7_224] INFO: Epoch: [72] [1170/1251] eta: 0:00:51 lr: 0.000863 loss: 3.6306 (3.6115) grad_norm: 1.0976 (inf) time: 0.6260 [2021-03-26 14:46:56 swin_base_patch4_window7_224] INFO: Epoch: [72] [1180/1251] eta: 0:00:44 lr: 0.000862 loss: 3.6325 (3.6117) grad_norm: 1.1873 (inf) time: 0.6237 [2021-03-26 14:47:02 swin_base_patch4_window7_224] INFO: Epoch: [72] [1190/1251] eta: 0:00:38 lr: 0.000862 loss: 3.9297 (3.6133) grad_norm: 1.1144 (inf) time: 0.6286 [2021-03-26 14:47:08 swin_base_patch4_window7_224] INFO: Epoch: [72] [1200/1251] eta: 0:00:32 lr: 0.000862 loss: 3.9064 (3.6138) grad_norm: 1.0762 (inf) time: 0.6304 [2021-03-26 14:47:14 swin_base_patch4_window7_224] INFO: Epoch: [72] [1210/1251] eta: 0:00:25 lr: 0.000862 loss: 3.6913 (3.6134) grad_norm: 1.0947 (inf) time: 0.6320 [2021-03-26 14:47:21 swin_base_patch4_window7_224] INFO: Epoch: [72] [1220/1251] eta: 0:00:19 lr: 0.000862 loss: 3.6769 (3.6124) grad_norm: 1.0886 (inf) time: 0.6273 [2021-03-26 14:47:27 swin_base_patch4_window7_224] INFO: Epoch: [72] [1230/1251] eta: 0:00:13 lr: 0.000862 loss: 3.6769 (3.6138) grad_norm: 1.0552 (inf) time: 0.6253 [2021-03-26 14:47:33 swin_base_patch4_window7_224] INFO: Epoch: [72] [1240/1251] eta: 0:00:06 lr: 0.000862 loss: 3.7595 (3.6144) grad_norm: 1.0294 (inf) time: 0.6224 [2021-03-26 14:47:39 swin_base_patch4_window7_224] INFO: Epoch: [72] [1250/1251] eta: 0:00:00 lr: 0.000862 loss: 3.7896 (3.6151) grad_norm: 1.0226 (inf) time: 0.6132 [2021-03-26 14:47:45 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:48 loss: 1.0165 (1.0165) acc1: 76.5625 (76.5625) acc5: 96.8750 (96.8750) [2021-03-26 14:47:46 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 1.0683 (1.1340) acc1: 73.4375 (71.7330) acc5: 90.6250 (92.1875) [2021-03-26 14:47:48 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.9788 (1.0604) acc1: 73.4375 (73.9583) acc5: 92.1875 (93.3036) [2021-03-26 14:47:52 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0221 (1.0809) acc1: 75.0000 (73.9919) acc5: 92.1875 (92.7923) [2021-03-26 14:47:53 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1115 (1.0880) acc1: 73.4375 (73.7805) acc5: 92.1875 (92.8354) [2021-03-26 14:47:54 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0970 (1.0793) acc1: 73.4375 (73.8560) acc5: 93.7500 (92.9920) [2021-03-26 14:47:59 swin_base_patch4_window7_224] INFO: * Acc@1 74.770 Acc@5 92.878 loss 1.069 [2021-03-26 14:47:59 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.8% [2021-03-26 14:47:59 swin_base_patch4_window7_224] INFO: Max accuracy: 74.92% [2021-03-26 14:48:03 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 0/1251] eta: 1:31:38 lr: 0.000862 loss: 3.7551 (3.7551) grad_norm: 0.9005 (0.9005) time: 4.3955 [2021-03-26 14:48:10 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 10/1251] eta: 0:20:07 lr: 0.000862 loss: 3.4999 (3.4152) grad_norm: 1.1215 (1.1100) time: 0.9731 [2021-03-26 14:48:16 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 20/1251] eta: 0:16:33 lr: 0.000862 loss: 3.4999 (3.5368) grad_norm: 1.1130 (1.1130) time: 0.6280 [2021-03-26 14:48:22 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 30/1251] eta: 0:15:14 lr: 0.000862 loss: 3.3287 (3.4311) grad_norm: 1.1037 (1.1100) time: 0.6259 [2021-03-26 14:48:28 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 40/1251] eta: 0:14:32 lr: 0.000862 loss: 3.0724 (3.3944) grad_norm: 1.1480 (1.1223) time: 0.6289 [2021-03-26 14:48:35 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 50/1251] eta: 0:14:04 lr: 0.000862 loss: 3.4216 (3.4298) grad_norm: 1.0907 (1.1206) time: 0.6316 [2021-03-26 14:48:41 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 60/1251] eta: 0:13:40 lr: 0.000862 loss: 3.5481 (3.4501) grad_norm: 1.0907 (1.1274) time: 0.6245 [2021-03-26 14:48:47 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 70/1251] eta: 0:13:22 lr: 0.000862 loss: 3.5260 (3.4629) grad_norm: 1.1795 (1.1357) time: 0.6198 [2021-03-26 14:48:53 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 80/1251] eta: 0:13:08 lr: 0.000862 loss: 3.5303 (3.4728) grad_norm: 1.1708 (1.1373) time: 0.6268 [2021-03-26 14:49:00 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 90/1251] eta: 0:12:56 lr: 0.000862 loss: 3.5670 (3.4617) grad_norm: 1.1461 (1.1356) time: 0.6303 [2021-03-26 14:49:06 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 100/1251] eta: 0:12:44 lr: 0.000862 loss: 3.4718 (3.4603) grad_norm: 1.0772 (1.1371) time: 0.6260 [2021-03-26 14:49:12 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 110/1251] eta: 0:12:34 lr: 0.000862 loss: 3.4718 (3.4651) grad_norm: 1.0772 (1.1311) time: 0.6289 [2021-03-26 14:49:19 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 120/1251] eta: 0:12:25 lr: 0.000862 loss: 3.7012 (3.4880) grad_norm: 1.0638 (1.1218) time: 0.6347 [2021-03-26 14:49:25 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 130/1251] eta: 0:12:17 lr: 0.000862 loss: 3.8425 (3.5180) grad_norm: 1.1044 (1.1303) time: 0.6365 [2021-03-26 14:49:31 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 140/1251] eta: 0:12:09 lr: 0.000862 loss: 3.7614 (3.5144) grad_norm: 1.1913 (1.1388) time: 0.6436 [2021-03-26 14:49:38 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 150/1251] eta: 0:12:01 lr: 0.000862 loss: 3.6806 (3.5320) grad_norm: 1.1913 (1.1400) time: 0.6370 [2021-03-26 14:49:44 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 160/1251] eta: 0:11:52 lr: 0.000862 loss: 3.9149 (3.5407) grad_norm: 1.0778 (1.1381) time: 0.6276 [2021-03-26 14:49:50 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 170/1251] eta: 0:11:44 lr: 0.000862 loss: 3.5503 (3.5300) grad_norm: 1.0755 (1.1351) time: 0.6253 [2021-03-26 14:49:56 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 180/1251] eta: 0:11:35 lr: 0.000862 loss: 3.3610 (3.5220) grad_norm: 1.0633 (1.1333) time: 0.6212 [2021-03-26 14:50:03 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 190/1251] eta: 0:11:29 lr: 0.000862 loss: 3.3165 (3.5072) grad_norm: 1.0513 (1.1350) time: 0.6329 [2021-03-26 14:50:09 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 200/1251] eta: 0:11:21 lr: 0.000862 loss: 3.4948 (3.5179) grad_norm: 1.0339 (1.1346) time: 0.6364 [2021-03-26 14:50:15 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 210/1251] eta: 0:11:13 lr: 0.000862 loss: 3.9409 (3.5328) grad_norm: 1.0994 (1.1364) time: 0.6260 [2021-03-26 14:50:22 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 220/1251] eta: 0:11:06 lr: 0.000862 loss: 3.9602 (3.5455) grad_norm: 1.0994 (1.1373) time: 0.6251 [2021-03-26 14:50:28 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 230/1251] eta: 0:10:59 lr: 0.000862 loss: 3.6874 (3.5464) grad_norm: 1.0688 (1.1354) time: 0.6273 [2021-03-26 14:50:34 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 240/1251] eta: 0:10:51 lr: 0.000862 loss: 3.5275 (3.5450) grad_norm: 1.0860 (1.1355) time: 0.6282 [2021-03-26 14:50:41 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 250/1251] eta: 0:10:44 lr: 0.000862 loss: 3.7647 (3.5592) grad_norm: 1.1167 (1.1355) time: 0.6275 [2021-03-26 14:50:47 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 260/1251] eta: 0:10:37 lr: 0.000862 loss: 3.8775 (3.5593) grad_norm: 1.0819 (1.1332) time: 0.6210 [2021-03-26 14:50:53 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 270/1251] eta: 0:10:30 lr: 0.000861 loss: 3.8223 (3.5660) grad_norm: 1.1314 (1.1355) time: 0.6240 [2021-03-26 14:50:59 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 280/1251] eta: 0:10:23 lr: 0.000861 loss: 3.8522 (3.5724) grad_norm: 1.1540 (1.1360) time: 0.6282 [2021-03-26 14:51:06 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 290/1251] eta: 0:10:16 lr: 0.000861 loss: 3.6844 (3.5690) grad_norm: 1.1374 (1.1376) time: 0.6281 [2021-03-26 14:51:12 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 300/1251] eta: 0:10:09 lr: 0.000861 loss: 3.4255 (3.5684) grad_norm: 1.1547 (1.1379) time: 0.6283 [2021-03-26 14:51:18 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 310/1251] eta: 0:10:02 lr: 0.000861 loss: 3.5047 (3.5724) grad_norm: 1.0015 (1.1340) time: 0.6211 [2021-03-26 14:51:24 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 320/1251] eta: 0:09:56 lr: 0.000861 loss: 3.4381 (3.5648) grad_norm: 1.0414 (1.1345) time: 0.6273 [2021-03-26 14:51:31 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 330/1251] eta: 0:09:49 lr: 0.000861 loss: 3.5209 (3.5701) grad_norm: 1.0777 (1.1328) time: 0.6298 [2021-03-26 14:51:37 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 340/1251] eta: 0:09:42 lr: 0.000861 loss: 3.7694 (3.5743) grad_norm: 1.0830 (1.1326) time: 0.6245 [2021-03-26 14:51:43 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 350/1251] eta: 0:09:35 lr: 0.000861 loss: 3.6132 (3.5665) grad_norm: 1.1342 (1.1354) time: 0.6242 [2021-03-26 14:51:49 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 360/1251] eta: 0:09:29 lr: 0.000861 loss: 3.6132 (3.5723) grad_norm: 1.2214 (1.1388) time: 0.6271 [2021-03-26 14:51:56 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 370/1251] eta: 0:09:22 lr: 0.000861 loss: 3.7661 (3.5717) grad_norm: 1.2155 (1.1406) time: 0.6323 [2021-03-26 14:52:02 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 380/1251] eta: 0:09:15 lr: 0.000861 loss: 3.6911 (3.5738) grad_norm: 1.1466 (1.1397) time: 0.6290 [2021-03-26 14:52:08 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 390/1251] eta: 0:09:09 lr: 0.000861 loss: 3.6046 (3.5781) grad_norm: 1.1275 (1.1389) time: 0.6246 [2021-03-26 14:52:14 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 400/1251] eta: 0:09:02 lr: 0.000861 loss: 3.5776 (3.5761) grad_norm: 1.0760 (1.1376) time: 0.6230 [2021-03-26 14:52:21 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 410/1251] eta: 0:08:55 lr: 0.000861 loss: 3.4345 (3.5763) grad_norm: 1.1354 (1.1408) time: 0.6204 [2021-03-26 14:52:27 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 420/1251] eta: 0:08:48 lr: 0.000861 loss: 3.2564 (3.5654) grad_norm: 1.1727 (1.1413) time: 0.6207 [2021-03-26 14:52:33 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 430/1251] eta: 0:08:42 lr: 0.000861 loss: 3.4421 (3.5674) grad_norm: 1.1489 (1.1420) time: 0.6244 [2021-03-26 14:52:39 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 440/1251] eta: 0:08:35 lr: 0.000861 loss: 3.8672 (3.5717) grad_norm: 1.0982 (1.1408) time: 0.6254 [2021-03-26 14:52:46 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 450/1251] eta: 0:08:29 lr: 0.000861 loss: 3.3509 (3.5622) grad_norm: 1.1280 (1.1443) time: 0.6293 [2021-03-26 14:52:52 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 460/1251] eta: 0:08:23 lr: 0.000861 loss: 3.3211 (3.5657) grad_norm: 1.1142 (1.1428) time: 0.6333 [2021-03-26 14:52:58 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 470/1251] eta: 0:08:16 lr: 0.000861 loss: 3.6769 (3.5658) grad_norm: 1.1016 (1.1431) time: 0.6315 [2021-03-26 14:53:05 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 480/1251] eta: 0:08:09 lr: 0.000861 loss: 3.4711 (3.5613) grad_norm: 1.0648 (1.1419) time: 0.6249 [2021-03-26 14:53:11 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 490/1251] eta: 0:08:03 lr: 0.000861 loss: 3.4296 (3.5652) grad_norm: 1.0648 (1.1429) time: 0.6267 [2021-03-26 14:53:17 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 500/1251] eta: 0:07:56 lr: 0.000861 loss: 3.4296 (3.5588) grad_norm: 1.1333 (1.1430) time: 0.6268 [2021-03-26 14:53:23 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 510/1251] eta: 0:07:50 lr: 0.000861 loss: 3.5797 (3.5596) grad_norm: 1.1034 (1.1435) time: 0.6226 [2021-03-26 14:53:30 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 520/1251] eta: 0:07:44 lr: 0.000861 loss: 3.6055 (3.5583) grad_norm: 1.1112 (1.1441) time: 0.6260 [2021-03-26 14:53:36 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 530/1251] eta: 0:07:37 lr: 0.000861 loss: 3.3668 (3.5542) grad_norm: 1.1550 (1.1454) time: 0.6308 [2021-03-26 14:53:42 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 540/1251] eta: 0:07:31 lr: 0.000861 loss: 3.2485 (3.5499) grad_norm: 1.1439 (1.1453) time: 0.6302 [2021-03-26 14:53:49 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 550/1251] eta: 0:07:25 lr: 0.000861 loss: 3.5589 (3.5519) grad_norm: 1.1400 (1.1449) time: 0.6363 [2021-03-26 14:53:55 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 560/1251] eta: 0:07:18 lr: 0.000861 loss: 3.7017 (3.5504) grad_norm: 1.1316 (1.1442) time: 0.6415 [2021-03-26 14:54:01 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 570/1251] eta: 0:07:12 lr: 0.000861 loss: 3.7017 (3.5547) grad_norm: 1.1059 (1.1444) time: 0.6341 [2021-03-26 14:54:08 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 580/1251] eta: 0:07:05 lr: 0.000861 loss: 3.8553 (3.5601) grad_norm: 1.1342 (1.1443) time: 0.6297 [2021-03-26 14:54:14 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 590/1251] eta: 0:06:59 lr: 0.000861 loss: 3.6640 (3.5563) grad_norm: 1.1244 (1.1431) time: 0.6244 [2021-03-26 14:54:20 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 600/1251] eta: 0:06:52 lr: 0.000861 loss: 3.3818 (3.5543) grad_norm: 1.1239 (1.1449) time: 0.6258 [2021-03-26 14:54:27 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 610/1251] eta: 0:06:46 lr: 0.000861 loss: 3.3537 (3.5511) grad_norm: 1.1005 (1.1439) time: 0.6322 [2021-03-26 14:54:33 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 620/1251] eta: 0:06:40 lr: 0.000860 loss: 3.6526 (3.5559) grad_norm: 1.0799 (1.1427) time: 0.6334 [2021-03-26 14:54:39 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 630/1251] eta: 0:06:33 lr: 0.000860 loss: 3.5020 (3.5544) grad_norm: 1.1015 (1.1429) time: 0.6298 [2021-03-26 14:54:45 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 640/1251] eta: 0:06:27 lr: 0.000860 loss: 3.4157 (3.5536) grad_norm: 1.1520 (1.1430) time: 0.6278 [2021-03-26 14:54:52 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 650/1251] eta: 0:06:21 lr: 0.000860 loss: 3.6112 (3.5564) grad_norm: 1.1310 (1.1428) time: 0.6239 [2021-03-26 14:54:58 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 660/1251] eta: 0:06:14 lr: 0.000860 loss: 3.9317 (3.5606) grad_norm: 1.0979 (1.1418) time: 0.6217 [2021-03-26 14:55:04 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 670/1251] eta: 0:06:08 lr: 0.000860 loss: 3.7470 (3.5591) grad_norm: 1.0926 (1.1418) time: 0.6257 [2021-03-26 14:55:10 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 680/1251] eta: 0:06:01 lr: 0.000860 loss: 3.7267 (3.5611) grad_norm: 1.0766 (1.1420) time: 0.6274 [2021-03-26 14:55:17 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 690/1251] eta: 0:05:55 lr: 0.000860 loss: 3.8295 (3.5650) grad_norm: 1.0691 (1.1412) time: 0.6295 [2021-03-26 14:55:23 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 700/1251] eta: 0:05:49 lr: 0.000860 loss: 3.6156 (3.5629) grad_norm: 1.0701 (1.1406) time: 0.6340 [2021-03-26 14:55:29 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 710/1251] eta: 0:05:42 lr: 0.000860 loss: 3.4788 (3.5616) grad_norm: 1.1156 (1.1407) time: 0.6311 [2021-03-26 14:55:36 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 720/1251] eta: 0:05:36 lr: 0.000860 loss: 3.6996 (3.5628) grad_norm: 1.1289 (1.1399) time: 0.6235 [2021-03-26 14:55:42 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 730/1251] eta: 0:05:29 lr: 0.000860 loss: 3.6309 (3.5604) grad_norm: 1.1416 (1.1401) time: 0.6240 [2021-03-26 14:55:48 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 740/1251] eta: 0:05:23 lr: 0.000860 loss: 3.4236 (3.5623) grad_norm: 1.1638 (1.1408) time: 0.6349 [2021-03-26 14:55:55 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 750/1251] eta: 0:05:17 lr: 0.000860 loss: 3.7774 (3.5650) grad_norm: 1.1233 (1.1403) time: 0.6425 [2021-03-26 14:56:01 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 760/1251] eta: 0:05:10 lr: 0.000860 loss: 3.7011 (3.5660) grad_norm: 1.0773 (1.1389) time: 0.6292 [2021-03-26 14:56:07 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 770/1251] eta: 0:05:04 lr: 0.000860 loss: 3.6577 (3.5639) grad_norm: 1.0269 (1.1386) time: 0.6239 [2021-03-26 14:56:13 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 780/1251] eta: 0:04:58 lr: 0.000860 loss: 3.5782 (3.5647) grad_norm: 1.0938 (1.1387) time: 0.6295 [2021-03-26 14:56:20 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 790/1251] eta: 0:04:51 lr: 0.000860 loss: 3.3964 (3.5623) grad_norm: 1.0938 (1.1392) time: 0.6324 [2021-03-26 14:56:26 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 800/1251] eta: 0:04:45 lr: 0.000860 loss: 3.5469 (3.5647) grad_norm: 1.0871 (1.1387) time: 0.6318 [2021-03-26 14:56:32 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 810/1251] eta: 0:04:39 lr: 0.000860 loss: 3.6442 (3.5640) grad_norm: 1.0757 (1.1385) time: 0.6232 [2021-03-26 14:56:39 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 820/1251] eta: 0:04:32 lr: 0.000860 loss: 3.5505 (3.5631) grad_norm: 1.0941 (1.1384) time: 0.6241 [2021-03-26 14:56:45 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 830/1251] eta: 0:04:26 lr: 0.000860 loss: 3.5505 (3.5653) grad_norm: 1.0941 (1.1376) time: 0.6299 [2021-03-26 14:56:51 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 840/1251] eta: 0:04:20 lr: 0.000860 loss: 3.7898 (3.5687) grad_norm: 1.0966 (1.1373) time: 0.6263 [2021-03-26 14:56:57 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 850/1251] eta: 0:04:13 lr: 0.000860 loss: 3.7874 (3.5710) grad_norm: 1.1420 (1.1371) time: 0.6240 [2021-03-26 14:57:04 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 860/1251] eta: 0:04:07 lr: 0.000860 loss: 3.7761 (3.5719) grad_norm: 1.0681 (1.1362) time: 0.6237 [2021-03-26 14:57:10 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 870/1251] eta: 0:04:00 lr: 0.000860 loss: 3.4339 (3.5707) grad_norm: 1.0755 (1.1358) time: 0.6258 [2021-03-26 14:57:16 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 880/1251] eta: 0:03:54 lr: 0.000860 loss: 3.5797 (3.5724) grad_norm: 1.1316 (1.1366) time: 0.6332 [2021-03-26 14:57:23 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 890/1251] eta: 0:03:48 lr: 0.000860 loss: 3.7067 (3.5742) grad_norm: 1.1442 (1.1367) time: 0.6348 [2021-03-26 14:57:29 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 900/1251] eta: 0:03:42 lr: 0.000860 loss: 3.7686 (3.5770) grad_norm: 1.1350 (1.1369) time: 0.6299 [2021-03-26 14:57:35 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 910/1251] eta: 0:03:35 lr: 0.000860 loss: 3.7327 (3.5763) grad_norm: 1.0719 (1.1367) time: 0.6242 [2021-03-26 14:57:41 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 920/1251] eta: 0:03:29 lr: 0.000860 loss: 3.6498 (3.5759) grad_norm: 1.1363 (1.1380) time: 0.6277 [2021-03-26 14:57:48 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 930/1251] eta: 0:03:23 lr: 0.000860 loss: 3.7778 (3.5769) grad_norm: 1.1149 (1.1383) time: 0.6407 [2021-03-26 14:57:54 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 940/1251] eta: 0:03:16 lr: 0.000860 loss: 3.7778 (3.5777) grad_norm: 1.1105 (1.1383) time: 0.6347 [2021-03-26 14:58:00 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 950/1251] eta: 0:03:10 lr: 0.000860 loss: 3.6840 (3.5790) grad_norm: 1.0723 (1.1377) time: 0.6216 [2021-03-26 14:58:07 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 960/1251] eta: 0:03:04 lr: 0.000860 loss: 3.6059 (3.5778) grad_norm: 1.0723 (1.1379) time: 0.6277 [2021-03-26 14:58:13 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 970/1251] eta: 0:02:57 lr: 0.000859 loss: 3.4764 (3.5745) grad_norm: 1.0997 (1.1378) time: 0.6275 [2021-03-26 14:58:19 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 980/1251] eta: 0:02:51 lr: 0.000859 loss: 3.4764 (3.5739) grad_norm: 1.0803 (1.1377) time: 0.6226 [2021-03-26 14:58:25 swin_base_patch4_window7_224] INFO: Epoch: [73] [ 990/1251] eta: 0:02:44 lr: 0.000859 loss: 3.6618 (3.5744) grad_norm: 1.0760 (1.1381) time: 0.6226 [2021-03-26 14:58:32 swin_base_patch4_window7_224] INFO: Epoch: [73] [1000/1251] eta: 0:02:38 lr: 0.000859 loss: 3.7110 (3.5774) grad_norm: 1.0765 (1.1379) time: 0.6248 [2021-03-26 14:58:38 swin_base_patch4_window7_224] INFO: Epoch: [73] [1010/1251] eta: 0:02:32 lr: 0.000859 loss: 3.6263 (3.5756) grad_norm: 1.1187 (1.1384) time: 0.6321 [2021-03-26 14:58:44 swin_base_patch4_window7_224] INFO: Epoch: [73] [1020/1251] eta: 0:02:26 lr: 0.000859 loss: 3.6056 (3.5767) grad_norm: 1.0492 (1.1372) time: 0.6351 [2021-03-26 14:58:51 swin_base_patch4_window7_224] INFO: Epoch: [73] [1030/1251] eta: 0:02:19 lr: 0.000859 loss: 3.7230 (3.5774) grad_norm: 1.0303 (1.1369) time: 0.6335 [2021-03-26 14:58:57 swin_base_patch4_window7_224] INFO: Epoch: [73] [1040/1251] eta: 0:02:13 lr: 0.000859 loss: 3.5528 (3.5772) grad_norm: 1.0303 (1.1363) time: 0.6253 [2021-03-26 14:59:03 swin_base_patch4_window7_224] INFO: Epoch: [73] [1050/1251] eta: 0:02:06 lr: 0.000859 loss: 3.4233 (3.5756) grad_norm: 1.0483 (1.1364) time: 0.6161 [2021-03-26 14:59:09 swin_base_patch4_window7_224] INFO: Epoch: [73] [1060/1251] eta: 0:02:00 lr: 0.000859 loss: 3.4382 (3.5757) grad_norm: 1.0723 (1.1360) time: 0.6260 [2021-03-26 14:59:16 swin_base_patch4_window7_224] INFO: Epoch: [73] [1070/1251] eta: 0:01:54 lr: 0.000859 loss: 3.5919 (3.5755) grad_norm: 1.0771 (nan) time: 0.6297 [2021-03-26 14:59:22 swin_base_patch4_window7_224] INFO: Epoch: [73] [1080/1251] eta: 0:01:48 lr: 0.000859 loss: 3.6481 (3.5764) grad_norm: 1.1647 (nan) time: 0.6268 [2021-03-26 14:59:28 swin_base_patch4_window7_224] INFO: Epoch: [73] [1090/1251] eta: 0:01:41 lr: 0.000859 loss: 3.7428 (3.5780) grad_norm: 1.1513 (nan) time: 0.6280 [2021-03-26 14:59:34 swin_base_patch4_window7_224] INFO: Epoch: [73] [1100/1251] eta: 0:01:35 lr: 0.000859 loss: 3.3825 (3.5728) grad_norm: 1.1182 (nan) time: 0.6280 [2021-03-26 14:59:41 swin_base_patch4_window7_224] INFO: Epoch: [73] [1110/1251] eta: 0:01:29 lr: 0.000859 loss: 3.1644 (3.5723) grad_norm: 1.0898 (nan) time: 0.6287 [2021-03-26 14:59:47 swin_base_patch4_window7_224] INFO: Epoch: [73] [1120/1251] eta: 0:01:22 lr: 0.000859 loss: 3.6237 (3.5739) grad_norm: 1.0898 (nan) time: 0.6230 [2021-03-26 14:59:53 swin_base_patch4_window7_224] INFO: Epoch: [73] [1130/1251] eta: 0:01:16 lr: 0.000859 loss: 3.6355 (3.5735) grad_norm: 1.1857 (nan) time: 0.6242 [2021-03-26 14:59:59 swin_base_patch4_window7_224] INFO: Epoch: [73] [1140/1251] eta: 0:01:10 lr: 0.000859 loss: 3.7445 (3.5752) grad_norm: 1.1241 (nan) time: 0.6281 [2021-03-26 15:00:06 swin_base_patch4_window7_224] INFO: Epoch: [73] [1150/1251] eta: 0:01:03 lr: 0.000859 loss: 3.7328 (3.5759) grad_norm: 1.1017 (nan) time: 0.6229 [2021-03-26 15:00:12 swin_base_patch4_window7_224] INFO: Epoch: [73] [1160/1251] eta: 0:00:57 lr: 0.000859 loss: 3.6087 (3.5730) grad_norm: 1.0342 (nan) time: 0.6230 [2021-03-26 15:00:18 swin_base_patch4_window7_224] INFO: Epoch: [73] [1170/1251] eta: 0:00:51 lr: 0.000859 loss: 3.4908 (3.5730) grad_norm: 1.0567 (nan) time: 0.6291 [2021-03-26 15:00:25 swin_base_patch4_window7_224] INFO: Epoch: [73] [1180/1251] eta: 0:00:44 lr: 0.000859 loss: 3.5963 (3.5732) grad_norm: 1.1277 (nan) time: 0.6339 [2021-03-26 15:00:31 swin_base_patch4_window7_224] INFO: Epoch: [73] [1190/1251] eta: 0:00:38 lr: 0.000859 loss: 3.5417 (3.5729) grad_norm: 1.1091 (nan) time: 0.6297 [2021-03-26 15:00:37 swin_base_patch4_window7_224] INFO: Epoch: [73] [1200/1251] eta: 0:00:32 lr: 0.000859 loss: 3.7558 (3.5727) grad_norm: 1.1086 (nan) time: 0.6265 [2021-03-26 15:00:43 swin_base_patch4_window7_224] INFO: Epoch: [73] [1210/1251] eta: 0:00:25 lr: 0.000859 loss: 3.6366 (3.5726) grad_norm: 1.1250 (nan) time: 0.6289 [2021-03-26 15:00:50 swin_base_patch4_window7_224] INFO: Epoch: [73] [1220/1251] eta: 0:00:19 lr: 0.000859 loss: 3.4327 (3.5711) grad_norm: 1.1659 (nan) time: 0.6274 [2021-03-26 15:00:56 swin_base_patch4_window7_224] INFO: Epoch: [73] [1230/1251] eta: 0:00:13 lr: 0.000859 loss: 3.4785 (3.5715) grad_norm: 1.0755 (nan) time: 0.6343 [2021-03-26 15:01:02 swin_base_patch4_window7_224] INFO: Epoch: [73] [1240/1251] eta: 0:00:06 lr: 0.000859 loss: 3.7924 (3.5723) grad_norm: 1.0639 (nan) time: 0.6286 [2021-03-26 15:01:09 swin_base_patch4_window7_224] INFO: Epoch: [73] [1250/1251] eta: 0:00:00 lr: 0.000859 loss: 3.6084 (3.5715) grad_norm: 1.0704 (nan) time: 0.6188 [2021-03-26 15:01:16 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:48 loss: 1.1807 (1.1807) acc1: 70.3125 (70.3125) acc5: 90.6250 (90.6250) [2021-03-26 15:01:17 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.1051 (1.1093) acc1: 73.4375 (74.1477) acc5: 93.7500 (92.6136) [2021-03-26 15:01:20 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0577 (1.0891) acc1: 73.4375 (75.0000) acc5: 93.7500 (93.0804) [2021-03-26 15:01:22 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0181 (1.0734) acc1: 73.4375 (75.2520) acc5: 93.7500 (93.3468) [2021-03-26 15:01:24 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0568 (1.0644) acc1: 71.8750 (75.0381) acc5: 93.7500 (93.3308) [2021-03-26 15:01:25 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0940 (1.0964) acc1: 73.4375 (74.6240) acc5: 92.1875 (92.9920) [2021-03-26 15:01:29 swin_base_patch4_window7_224] INFO: * Acc@1 74.798 Acc@5 92.864 loss 1.078 [2021-03-26 15:01:29 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.8% [2021-03-26 15:01:29 swin_base_patch4_window7_224] INFO: Max accuracy: 74.92% [2021-03-26 15:01:33 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 0/1251] eta: 1:29:20 lr: 0.000859 loss: 3.9532 (3.9532) grad_norm: 1.2857 (1.2857) time: 4.2852 [2021-03-26 15:01:39 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 10/1251] eta: 0:20:22 lr: 0.000859 loss: 3.7525 (3.5759) grad_norm: 1.1044 (1.1342) time: 0.9853 [2021-03-26 15:01:46 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 20/1251] eta: 0:16:42 lr: 0.000859 loss: 3.2000 (3.4021) grad_norm: 1.1536 (1.1553) time: 0.6411 [2021-03-26 15:01:52 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 30/1251] eta: 0:15:17 lr: 0.000859 loss: 3.2000 (3.3890) grad_norm: 1.1263 (1.1355) time: 0.6232 [2021-03-26 15:01:58 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 40/1251] eta: 0:14:37 lr: 0.000859 loss: 3.5002 (3.4702) grad_norm: 1.0637 (1.1237) time: 0.6301 [2021-03-26 15:02:05 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 50/1251] eta: 0:14:08 lr: 0.000859 loss: 3.6999 (3.4726) grad_norm: 1.0741 (1.1379) time: 0.6371 [2021-03-26 15:02:11 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 60/1251] eta: 0:13:44 lr: 0.000858 loss: 3.7562 (3.5213) grad_norm: 1.0626 (1.1197) time: 0.6269 [2021-03-26 15:02:17 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 70/1251] eta: 0:13:28 lr: 0.000858 loss: 3.8336 (3.5468) grad_norm: 1.0905 (1.1259) time: 0.6285 [2021-03-26 15:02:24 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 80/1251] eta: 0:13:14 lr: 0.000858 loss: 3.6725 (3.5565) grad_norm: 1.1399 (1.1323) time: 0.6363 [2021-03-26 15:02:30 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 90/1251] eta: 0:13:02 lr: 0.000858 loss: 3.6695 (3.5711) grad_norm: 1.2025 (1.1415) time: 0.6364 [2021-03-26 15:02:36 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 100/1251] eta: 0:12:50 lr: 0.000858 loss: 3.8102 (3.5938) grad_norm: 1.1390 (1.1375) time: 0.6304 [2021-03-26 15:02:42 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 110/1251] eta: 0:12:39 lr: 0.000858 loss: 3.5633 (3.5762) grad_norm: 1.0544 (1.1329) time: 0.6268 [2021-03-26 15:02:49 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 120/1251] eta: 0:12:29 lr: 0.000858 loss: 3.5633 (3.5809) grad_norm: 1.0980 (1.1340) time: 0.6290 [2021-03-26 15:02:55 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 130/1251] eta: 0:12:19 lr: 0.000858 loss: 3.6733 (3.5913) grad_norm: 1.0746 (1.1287) time: 0.6252 [2021-03-26 15:03:02 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 140/1251] eta: 0:12:11 lr: 0.000858 loss: 3.6733 (3.6003) grad_norm: 1.0746 (1.1301) time: 0.6368 [2021-03-26 15:03:08 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 150/1251] eta: 0:12:03 lr: 0.000858 loss: 3.7647 (3.6134) grad_norm: 1.1695 (1.1348) time: 0.6404 [2021-03-26 15:03:14 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 160/1251] eta: 0:11:54 lr: 0.000858 loss: 3.7873 (3.6147) grad_norm: 1.1059 (1.1297) time: 0.6306 [2021-03-26 15:03:20 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 170/1251] eta: 0:11:46 lr: 0.000858 loss: 3.7873 (3.6123) grad_norm: 1.0897 (1.1280) time: 0.6316 [2021-03-26 15:03:27 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 180/1251] eta: 0:11:39 lr: 0.000858 loss: 3.7782 (3.6142) grad_norm: 1.1259 (1.1297) time: 0.6350 [2021-03-26 15:03:33 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 190/1251] eta: 0:11:31 lr: 0.000858 loss: 3.6213 (3.6126) grad_norm: 1.1454 (1.1330) time: 0.6321 [2021-03-26 15:03:39 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 200/1251] eta: 0:11:24 lr: 0.000858 loss: 3.6721 (3.6137) grad_norm: 1.1264 (1.1414) time: 0.6301 [2021-03-26 15:03:46 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 210/1251] eta: 0:11:16 lr: 0.000858 loss: 3.5083 (3.6018) grad_norm: 1.2094 (1.1533) time: 0.6283 [2021-03-26 15:03:52 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 220/1251] eta: 0:11:08 lr: 0.000858 loss: 3.2675 (3.5933) grad_norm: 1.2331 (1.1540) time: 0.6226 [2021-03-26 15:03:58 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 230/1251] eta: 0:11:00 lr: 0.000858 loss: 3.7444 (3.5972) grad_norm: 1.1452 (1.1533) time: 0.6248 [2021-03-26 15:04:05 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 240/1251] eta: 0:10:54 lr: 0.000858 loss: 3.7256 (3.5867) grad_norm: 1.1567 (1.1554) time: 0.6323 [2021-03-26 15:04:11 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 250/1251] eta: 0:10:47 lr: 0.000858 loss: 3.4458 (3.5763) grad_norm: 1.1794 (1.1593) time: 0.6360 [2021-03-26 15:04:17 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 260/1251] eta: 0:10:40 lr: 0.000858 loss: 3.5916 (3.5799) grad_norm: 1.0667 (1.1552) time: 0.6328 [2021-03-26 15:04:23 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 270/1251] eta: 0:10:32 lr: 0.000858 loss: 3.7293 (3.5763) grad_norm: 1.0228 (1.1522) time: 0.6300 [2021-03-26 15:04:30 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 280/1251] eta: 0:10:25 lr: 0.000858 loss: 3.5961 (3.5711) grad_norm: 1.1347 (1.1564) time: 0.6244 [2021-03-26 15:04:36 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 290/1251] eta: 0:10:18 lr: 0.000858 loss: 3.5915 (3.5639) grad_norm: 1.1017 (1.1530) time: 0.6191 [2021-03-26 15:04:42 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 300/1251] eta: 0:10:11 lr: 0.000858 loss: 3.5229 (3.5595) grad_norm: 1.0772 (1.1506) time: 0.6200 [2021-03-26 15:04:48 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 310/1251] eta: 0:10:04 lr: 0.000858 loss: 3.7109 (3.5613) grad_norm: 1.0504 (1.1475) time: 0.6227 [2021-03-26 15:04:55 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 320/1251] eta: 0:09:57 lr: 0.000858 loss: 3.8070 (3.5628) grad_norm: 1.0520 (1.1466) time: 0.6242 [2021-03-26 15:05:01 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 330/1251] eta: 0:09:50 lr: 0.000858 loss: 3.8016 (3.5646) grad_norm: 1.0439 (1.1430) time: 0.6250 [2021-03-26 15:05:07 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 340/1251] eta: 0:09:43 lr: 0.000858 loss: 3.5956 (3.5642) grad_norm: 1.0480 (1.1433) time: 0.6264 [2021-03-26 15:05:13 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 350/1251] eta: 0:09:36 lr: 0.000858 loss: 3.7353 (3.5696) grad_norm: 1.1556 (1.1444) time: 0.6254 [2021-03-26 15:05:20 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 360/1251] eta: 0:09:30 lr: 0.000858 loss: 3.7353 (3.5689) grad_norm: 1.1804 (1.1455) time: 0.6300 [2021-03-26 15:05:26 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 370/1251] eta: 0:09:23 lr: 0.000858 loss: 3.8336 (3.5811) grad_norm: 1.1804 (1.1460) time: 0.6292 [2021-03-26 15:05:32 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 380/1251] eta: 0:09:16 lr: 0.000858 loss: 3.9619 (3.5888) grad_norm: 1.0693 (1.1424) time: 0.6193 [2021-03-26 15:05:38 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 390/1251] eta: 0:09:09 lr: 0.000858 loss: 3.8803 (3.5971) grad_norm: 1.0275 (1.1428) time: 0.6217 [2021-03-26 15:05:45 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 400/1251] eta: 0:09:03 lr: 0.000858 loss: 3.7464 (3.5923) grad_norm: 1.1693 (1.1447) time: 0.6248 [2021-03-26 15:05:51 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 410/1251] eta: 0:08:56 lr: 0.000857 loss: 3.6868 (3.6003) grad_norm: 1.1502 (1.1440) time: 0.6208 [2021-03-26 15:05:57 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 420/1251] eta: 0:08:49 lr: 0.000857 loss: 3.8707 (3.5983) grad_norm: 1.0772 (1.1424) time: 0.6235 [2021-03-26 15:06:03 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 430/1251] eta: 0:08:43 lr: 0.000857 loss: 3.5375 (3.5985) grad_norm: 1.0950 (1.1425) time: 0.6293 [2021-03-26 15:06:10 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 440/1251] eta: 0:08:36 lr: 0.000857 loss: 3.5725 (3.5999) grad_norm: 1.1022 (1.1421) time: 0.6305 [2021-03-26 15:06:16 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 450/1251] eta: 0:08:30 lr: 0.000857 loss: 3.8353 (3.6097) grad_norm: 1.0795 (1.1417) time: 0.6324 [2021-03-26 15:06:22 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 460/1251] eta: 0:08:23 lr: 0.000857 loss: 3.9033 (3.6071) grad_norm: 1.0882 (1.1417) time: 0.6313 [2021-03-26 15:06:29 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 470/1251] eta: 0:08:17 lr: 0.000857 loss: 3.6519 (3.6069) grad_norm: 1.0930 (1.1415) time: 0.6252 [2021-03-26 15:06:35 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 480/1251] eta: 0:08:10 lr: 0.000857 loss: 3.5100 (3.6071) grad_norm: 1.1032 (1.1414) time: 0.6226 [2021-03-26 15:06:41 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 490/1251] eta: 0:08:04 lr: 0.000857 loss: 3.4971 (3.6043) grad_norm: 1.1516 (1.1421) time: 0.6239 [2021-03-26 15:06:47 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 500/1251] eta: 0:07:57 lr: 0.000857 loss: 3.4647 (3.6014) grad_norm: 1.1792 (1.1430) time: 0.6219 [2021-03-26 15:06:53 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 510/1251] eta: 0:07:50 lr: 0.000857 loss: 3.4787 (3.5990) grad_norm: 1.1792 (1.1438) time: 0.6219 [2021-03-26 15:07:00 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 520/1251] eta: 0:07:44 lr: 0.000857 loss: 3.4909 (3.5993) grad_norm: 1.1009 (1.1425) time: 0.6246 [2021-03-26 15:07:06 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 530/1251] eta: 0:07:38 lr: 0.000857 loss: 3.8255 (3.6051) grad_norm: 1.0720 (1.1427) time: 0.6311 [2021-03-26 15:07:12 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 540/1251] eta: 0:07:31 lr: 0.000857 loss: 3.9492 (3.6105) grad_norm: 1.1099 (1.1428) time: 0.6353 [2021-03-26 15:07:19 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 550/1251] eta: 0:07:25 lr: 0.000857 loss: 3.9325 (3.6139) grad_norm: 1.2359 (1.1453) time: 0.6384 [2021-03-26 15:07:25 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 560/1251] eta: 0:07:19 lr: 0.000857 loss: 3.9402 (3.6178) grad_norm: 1.2692 (1.1468) time: 0.6338 [2021-03-26 15:07:31 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 570/1251] eta: 0:07:12 lr: 0.000857 loss: 3.6706 (3.6164) grad_norm: 1.1931 (1.1468) time: 0.6247 [2021-03-26 15:07:38 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 580/1251] eta: 0:07:06 lr: 0.000857 loss: 3.7128 (3.6200) grad_norm: 1.1357 (1.1466) time: 0.6250 [2021-03-26 15:07:44 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 590/1251] eta: 0:06:59 lr: 0.000857 loss: 3.7648 (3.6173) grad_norm: 1.1357 (1.1466) time: 0.6254 [2021-03-26 15:07:50 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 600/1251] eta: 0:06:53 lr: 0.000857 loss: 3.6510 (3.6143) grad_norm: 1.0606 (1.1455) time: 0.6254 [2021-03-26 15:07:56 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 610/1251] eta: 0:06:46 lr: 0.000857 loss: 3.6833 (3.6146) grad_norm: 1.0360 (1.1453) time: 0.6241 [2021-03-26 15:08:03 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 620/1251] eta: 0:06:40 lr: 0.000857 loss: 3.4866 (3.6105) grad_norm: 1.1278 (1.1466) time: 0.6232 [2021-03-26 15:08:09 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 630/1251] eta: 0:06:33 lr: 0.000857 loss: 3.4866 (3.6088) grad_norm: 1.2054 (1.1474) time: 0.6259 [2021-03-26 15:08:15 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 640/1251] eta: 0:06:27 lr: 0.000857 loss: 3.6118 (3.6064) grad_norm: 1.1313 (1.1484) time: 0.6278 [2021-03-26 15:08:22 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 650/1251] eta: 0:06:21 lr: 0.000857 loss: 3.2713 (3.6036) grad_norm: 1.0824 (1.1466) time: 0.6322 [2021-03-26 15:08:28 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 660/1251] eta: 0:06:14 lr: 0.000857 loss: 3.8200 (3.6048) grad_norm: 1.0381 (1.1454) time: 0.6252 [2021-03-26 15:08:34 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 670/1251] eta: 0:06:08 lr: 0.000857 loss: 3.7588 (3.6005) grad_norm: 1.1245 (1.1463) time: 0.6182 [2021-03-26 15:08:40 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 680/1251] eta: 0:06:01 lr: 0.000857 loss: 3.3405 (3.5990) grad_norm: 1.1551 (1.1459) time: 0.6246 [2021-03-26 15:08:46 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 690/1251] eta: 0:05:55 lr: 0.000857 loss: 3.7780 (3.6039) grad_norm: 1.1637 (1.1459) time: 0.6270 [2021-03-26 15:08:53 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 700/1251] eta: 0:05:48 lr: 0.000857 loss: 3.8040 (3.6029) grad_norm: 1.1801 (1.1469) time: 0.6246 [2021-03-26 15:08:59 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 710/1251] eta: 0:05:42 lr: 0.000857 loss: 3.5994 (3.6032) grad_norm: 1.1445 (1.1468) time: 0.6309 [2021-03-26 15:09:05 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 720/1251] eta: 0:05:36 lr: 0.000857 loss: 3.4309 (3.6007) grad_norm: 1.0820 (1.1463) time: 0.6339 [2021-03-26 15:09:12 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 730/1251] eta: 0:05:29 lr: 0.000857 loss: 3.4673 (3.5998) grad_norm: 1.1460 (1.1465) time: 0.6331 [2021-03-26 15:09:18 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 740/1251] eta: 0:05:23 lr: 0.000857 loss: 3.5267 (3.5963) grad_norm: 1.0899 (1.1452) time: 0.6279 [2021-03-26 15:09:24 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 750/1251] eta: 0:05:17 lr: 0.000856 loss: 3.5267 (3.5957) grad_norm: 1.0529 (1.1445) time: 0.6262 [2021-03-26 15:09:31 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 760/1251] eta: 0:05:10 lr: 0.000856 loss: 3.5451 (3.5971) grad_norm: 1.1346 (1.1449) time: 0.6348 [2021-03-26 15:09:37 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 770/1251] eta: 0:05:04 lr: 0.000856 loss: 3.5814 (3.5998) grad_norm: 1.1501 (1.1455) time: 0.6335 [2021-03-26 15:09:43 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 780/1251] eta: 0:04:58 lr: 0.000856 loss: 3.6737 (3.6013) grad_norm: 1.1501 (1.1464) time: 0.6266 [2021-03-26 15:09:49 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 790/1251] eta: 0:04:51 lr: 0.000856 loss: 3.4996 (3.5980) grad_norm: 1.1463 (1.1459) time: 0.6260 [2021-03-26 15:09:56 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 800/1251] eta: 0:04:45 lr: 0.000856 loss: 3.3950 (3.5966) grad_norm: 1.0782 (1.1450) time: 0.6270 [2021-03-26 15:10:02 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 810/1251] eta: 0:04:39 lr: 0.000856 loss: 3.4599 (3.5949) grad_norm: 1.0972 (1.1453) time: 0.6286 [2021-03-26 15:10:08 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 820/1251] eta: 0:04:32 lr: 0.000856 loss: 3.4465 (3.5910) grad_norm: 1.1576 (1.1457) time: 0.6304 [2021-03-26 15:10:15 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 830/1251] eta: 0:04:26 lr: 0.000856 loss: 3.4421 (3.5889) grad_norm: 1.1410 (1.1462) time: 0.6291 [2021-03-26 15:10:21 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 840/1251] eta: 0:04:20 lr: 0.000856 loss: 3.4823 (3.5877) grad_norm: 1.1410 (1.1465) time: 0.6311 [2021-03-26 15:10:27 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 850/1251] eta: 0:04:13 lr: 0.000856 loss: 3.4049 (3.5864) grad_norm: 1.1449 (1.1471) time: 0.6291 [2021-03-26 15:10:34 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 860/1251] eta: 0:04:07 lr: 0.000856 loss: 3.6487 (3.5872) grad_norm: 1.2076 (1.1473) time: 0.6292 [2021-03-26 15:10:40 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 870/1251] eta: 0:04:01 lr: 0.000856 loss: 3.8196 (3.5877) grad_norm: 1.1204 (1.1478) time: 0.6275 [2021-03-26 15:10:46 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 880/1251] eta: 0:03:54 lr: 0.000856 loss: 3.8411 (3.5915) grad_norm: 1.1074 (1.1478) time: 0.6250 [2021-03-26 15:10:52 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 890/1251] eta: 0:03:48 lr: 0.000856 loss: 3.8763 (3.5915) grad_norm: 1.1074 (1.1476) time: 0.6271 [2021-03-26 15:10:59 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 900/1251] eta: 0:03:41 lr: 0.000856 loss: 3.7125 (3.5934) grad_norm: 1.1362 (1.1478) time: 0.6256 [2021-03-26 15:11:05 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 910/1251] eta: 0:03:35 lr: 0.000856 loss: 3.7238 (3.5961) grad_norm: 1.1640 (1.1489) time: 0.6269 [2021-03-26 15:11:11 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 920/1251] eta: 0:03:29 lr: 0.000856 loss: 3.9505 (3.5984) grad_norm: 1.1769 (1.1493) time: 0.6274 [2021-03-26 15:11:18 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 930/1251] eta: 0:03:22 lr: 0.000856 loss: 3.8841 (3.5976) grad_norm: 1.1272 (1.1495) time: 0.6338 [2021-03-26 15:11:24 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 940/1251] eta: 0:03:16 lr: 0.000856 loss: 3.5698 (3.5976) grad_norm: 1.0965 (1.1496) time: 0.6360 [2021-03-26 15:11:30 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 950/1251] eta: 0:03:10 lr: 0.000856 loss: 3.5968 (3.5980) grad_norm: 1.0965 (1.1489) time: 0.6351 [2021-03-26 15:11:36 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 960/1251] eta: 0:03:04 lr: 0.000856 loss: 3.5463 (3.5986) grad_norm: 1.0970 (1.1487) time: 0.6332 [2021-03-26 15:11:43 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 970/1251] eta: 0:02:57 lr: 0.000856 loss: 3.5463 (3.5968) grad_norm: 1.1116 (1.1487) time: 0.6253 [2021-03-26 15:11:49 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 980/1251] eta: 0:02:51 lr: 0.000856 loss: 3.4675 (3.5949) grad_norm: 1.1116 (1.1485) time: 0.6230 [2021-03-26 15:11:55 swin_base_patch4_window7_224] INFO: Epoch: [74] [ 990/1251] eta: 0:02:44 lr: 0.000856 loss: 3.4820 (3.5940) grad_norm: 1.1076 (1.1481) time: 0.6239 [2021-03-26 15:12:02 swin_base_patch4_window7_224] INFO: Epoch: [74] [1000/1251] eta: 0:02:38 lr: 0.000856 loss: 3.5027 (3.5944) grad_norm: 1.1312 (1.1486) time: 0.6334 [2021-03-26 15:12:08 swin_base_patch4_window7_224] INFO: Epoch: [74] [1010/1251] eta: 0:02:32 lr: 0.000856 loss: 3.4398 (3.5924) grad_norm: 1.2219 (1.1493) time: 0.6414 [2021-03-26 15:12:14 swin_base_patch4_window7_224] INFO: Epoch: [74] [1020/1251] eta: 0:02:26 lr: 0.000856 loss: 3.5152 (3.5942) grad_norm: 1.1770 (1.1500) time: 0.6395 [2021-03-26 15:12:21 swin_base_patch4_window7_224] INFO: Epoch: [74] [1030/1251] eta: 0:02:19 lr: 0.000856 loss: 3.5849 (3.5918) grad_norm: 1.1452 (1.1499) time: 0.6281 [2021-03-26 15:12:27 swin_base_patch4_window7_224] INFO: Epoch: [74] [1040/1251] eta: 0:02:13 lr: 0.000856 loss: 3.3384 (3.5899) grad_norm: 1.0934 (1.1499) time: 0.6238 [2021-03-26 15:12:33 swin_base_patch4_window7_224] INFO: Epoch: [74] [1050/1251] eta: 0:02:07 lr: 0.000856 loss: 3.4667 (3.5910) grad_norm: 1.0934 (1.1495) time: 0.6302 [2021-03-26 15:12:39 swin_base_patch4_window7_224] INFO: Epoch: [74] [1060/1251] eta: 0:02:00 lr: 0.000856 loss: 3.8265 (3.5924) grad_norm: 1.0576 (1.1485) time: 0.6288 [2021-03-26 15:12:46 swin_base_patch4_window7_224] INFO: Epoch: [74] [1070/1251] eta: 0:01:54 lr: 0.000856 loss: 3.7537 (3.5929) grad_norm: 1.0923 (1.1488) time: 0.6223 [2021-03-26 15:12:52 swin_base_patch4_window7_224] INFO: Epoch: [74] [1080/1251] eta: 0:01:48 lr: 0.000856 loss: 3.7345 (3.5946) grad_norm: 1.1226 (1.1493) time: 0.6233 [2021-03-26 15:12:58 swin_base_patch4_window7_224] INFO: Epoch: [74] [1090/1251] eta: 0:01:41 lr: 0.000855 loss: 3.7864 (3.5960) grad_norm: 1.0676 (1.1485) time: 0.6227 [2021-03-26 15:13:04 swin_base_patch4_window7_224] INFO: Epoch: [74] [1100/1251] eta: 0:01:35 lr: 0.000855 loss: 3.7873 (3.5981) grad_norm: 1.0377 (1.1478) time: 0.6252 [2021-03-26 15:13:11 swin_base_patch4_window7_224] INFO: Epoch: [74] [1110/1251] eta: 0:01:29 lr: 0.000855 loss: 3.7606 (3.5987) grad_norm: 1.0895 (1.1475) time: 0.6253 [2021-03-26 15:13:17 swin_base_patch4_window7_224] INFO: Epoch: [74] [1120/1251] eta: 0:01:22 lr: 0.000855 loss: 3.5947 (3.5982) grad_norm: 1.1395 (1.1474) time: 0.6221 [2021-03-26 15:13:23 swin_base_patch4_window7_224] INFO: Epoch: [74] [1130/1251] eta: 0:01:16 lr: 0.000855 loss: 3.7091 (3.5999) grad_norm: 1.1395 (1.1477) time: 0.6266 [2021-03-26 15:13:29 swin_base_patch4_window7_224] INFO: Epoch: [74] [1140/1251] eta: 0:01:10 lr: 0.000855 loss: 3.7950 (3.6017) grad_norm: 1.1541 (1.1477) time: 0.6238 [2021-03-26 15:13:36 swin_base_patch4_window7_224] INFO: Epoch: [74] [1150/1251] eta: 0:01:03 lr: 0.000855 loss: 3.6712 (3.6019) grad_norm: 1.1847 (1.1484) time: 0.6244 [2021-03-26 15:13:42 swin_base_patch4_window7_224] INFO: Epoch: [74] [1160/1251] eta: 0:00:57 lr: 0.000855 loss: 3.5508 (3.6008) grad_norm: 1.1152 (1.1480) time: 0.6290 [2021-03-26 15:13:48 swin_base_patch4_window7_224] INFO: Epoch: [74] [1170/1251] eta: 0:00:51 lr: 0.000855 loss: 3.8424 (3.6021) grad_norm: 1.1152 (1.1484) time: 0.6287 [2021-03-26 15:13:55 swin_base_patch4_window7_224] INFO: Epoch: [74] [1180/1251] eta: 0:00:44 lr: 0.000855 loss: 3.7167 (3.6007) grad_norm: 1.1084 (1.1478) time: 0.6294 [2021-03-26 15:14:01 swin_base_patch4_window7_224] INFO: Epoch: [74] [1190/1251] eta: 0:00:38 lr: 0.000855 loss: 3.2809 (3.5997) grad_norm: 1.0880 (1.1475) time: 0.6293 [2021-03-26 15:14:07 swin_base_patch4_window7_224] INFO: Epoch: [74] [1200/1251] eta: 0:00:32 lr: 0.000855 loss: 3.6060 (3.5992) grad_norm: 1.1416 (1.1477) time: 0.6246 [2021-03-26 15:14:13 swin_base_patch4_window7_224] INFO: Epoch: [74] [1210/1251] eta: 0:00:25 lr: 0.000855 loss: 3.6980 (3.6007) grad_norm: 1.1773 (1.1478) time: 0.6279 [2021-03-26 15:14:20 swin_base_patch4_window7_224] INFO: Epoch: [74] [1220/1251] eta: 0:00:19 lr: 0.000855 loss: 3.7818 (3.6027) grad_norm: 1.1245 (1.1481) time: 0.6332 [2021-03-26 15:14:26 swin_base_patch4_window7_224] INFO: Epoch: [74] [1230/1251] eta: 0:00:13 lr: 0.000855 loss: 3.7711 (3.6024) grad_norm: 1.0936 (1.1480) time: 0.6285 [2021-03-26 15:14:32 swin_base_patch4_window7_224] INFO: Epoch: [74] [1240/1251] eta: 0:00:06 lr: 0.000855 loss: 3.8004 (3.6037) grad_norm: 1.0936 (1.1479) time: 0.6254 [2021-03-26 15:14:38 swin_base_patch4_window7_224] INFO: Epoch: [74] [1250/1251] eta: 0:00:00 lr: 0.000855 loss: 3.8113 (3.6044) grad_norm: 1.1117 (1.1494) time: 0.6165 [2021-03-26 15:14:44 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:20 loss: 1.4606 (1.4606) acc1: 64.0625 (64.0625) acc5: 87.5000 (87.5000) [2021-03-26 15:14:46 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.1433 (1.1144) acc1: 71.8750 (74.5739) acc5: 93.7500 (92.7557) [2021-03-26 15:14:48 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.1433 (1.1249) acc1: 71.8750 (73.2887) acc5: 92.1875 (92.2619) [2021-03-26 15:14:50 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0555 (1.1048) acc1: 73.4375 (73.8911) acc5: 93.7500 (92.5403) [2021-03-26 15:14:53 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0125 (1.0972) acc1: 75.0000 (74.1616) acc5: 93.7500 (92.7973) [2021-03-26 15:14:54 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0601 (1.1020) acc1: 73.4375 (73.8880) acc5: 93.7500 (92.8320) [2021-03-26 15:14:57 swin_base_patch4_window7_224] INFO: * Acc@1 75.100 Acc@5 92.894 loss 1.078 [2021-03-26 15:14:57 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.1% [2021-03-26 15:14:57 swin_base_patch4_window7_224] INFO: Max accuracy: 75.10% [2021-03-26 15:15:02 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 0/1251] eta: 1:30:43 lr: 0.000855 loss: 4.0913 (4.0913) grad_norm: 1.1351 (1.1351) time: 4.3511 [2021-03-26 15:15:08 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 10/1251] eta: 0:20:04 lr: 0.000855 loss: 3.9253 (3.6180) grad_norm: 1.2884 (1.2567) time: 0.9702 [2021-03-26 15:15:14 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 20/1251] eta: 0:16:34 lr: 0.000855 loss: 3.5972 (3.4858) grad_norm: 1.2156 (1.2135) time: 0.6307 [2021-03-26 15:15:21 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 30/1251] eta: 0:15:21 lr: 0.000855 loss: 3.5972 (3.5473) grad_norm: 1.1216 (1.1771) time: 0.6364 [2021-03-26 15:15:27 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 40/1251] eta: 0:14:35 lr: 0.000855 loss: 3.8062 (3.5929) grad_norm: 1.1002 (1.1587) time: 0.6343 [2021-03-26 15:15:33 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 50/1251] eta: 0:14:06 lr: 0.000855 loss: 3.8062 (3.6119) grad_norm: 1.1002 (1.1484) time: 0.6278 [2021-03-26 15:15:39 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 60/1251] eta: 0:13:43 lr: 0.000855 loss: 3.8326 (3.6323) grad_norm: 1.1296 (1.1482) time: 0.6258 [2021-03-26 15:15:46 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 70/1251] eta: 0:13:24 lr: 0.000855 loss: 3.6510 (3.5823) grad_norm: 1.1354 (1.1520) time: 0.6214 [2021-03-26 15:15:52 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 80/1251] eta: 0:13:11 lr: 0.000855 loss: 3.2966 (3.5569) grad_norm: 1.1288 (1.1520) time: 0.6275 [2021-03-26 15:15:58 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 90/1251] eta: 0:12:58 lr: 0.000855 loss: 3.4992 (3.5702) grad_norm: 1.1288 (1.1594) time: 0.6319 [2021-03-26 15:16:05 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 100/1251] eta: 0:12:46 lr: 0.000855 loss: 3.6827 (3.5901) grad_norm: 1.1317 (1.1535) time: 0.6286 [2021-03-26 15:16:11 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 110/1251] eta: 0:12:37 lr: 0.000855 loss: 3.6581 (3.5976) grad_norm: 1.1317 (1.1570) time: 0.6359 [2021-03-26 15:16:17 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 120/1251] eta: 0:12:28 lr: 0.000855 loss: 3.6272 (3.5868) grad_norm: 1.1676 (1.1590) time: 0.6371 [2021-03-26 15:16:24 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 130/1251] eta: 0:12:18 lr: 0.000855 loss: 3.5335 (3.5694) grad_norm: 1.1897 (1.1604) time: 0.6309 [2021-03-26 15:16:30 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 140/1251] eta: 0:12:09 lr: 0.000855 loss: 3.6727 (3.5889) grad_norm: 1.1484 (1.1599) time: 0.6266 [2021-03-26 15:16:36 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 150/1251] eta: 0:12:00 lr: 0.000855 loss: 3.7365 (3.5948) grad_norm: 1.0559 (1.1531) time: 0.6250 [2021-03-26 15:16:42 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 160/1251] eta: 0:11:52 lr: 0.000855 loss: 3.6366 (3.6040) grad_norm: 1.0273 (1.1503) time: 0.6310 [2021-03-26 15:16:49 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 170/1251] eta: 0:11:44 lr: 0.000855 loss: 3.7736 (3.6142) grad_norm: 1.0952 (1.1482) time: 0.6300 [2021-03-26 15:16:55 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 180/1251] eta: 0:11:36 lr: 0.000854 loss: 3.4385 (3.6065) grad_norm: 1.1059 (1.1491) time: 0.6275 [2021-03-26 15:17:01 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 190/1251] eta: 0:11:28 lr: 0.000854 loss: 3.5920 (3.6064) grad_norm: 1.1059 (1.1483) time: 0.6251 [2021-03-26 15:17:07 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 200/1251] eta: 0:11:21 lr: 0.000854 loss: 3.7525 (3.6139) grad_norm: 1.0392 (1.1467) time: 0.6258 [2021-03-26 15:17:14 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 210/1251] eta: 0:11:14 lr: 0.000854 loss: 3.8053 (3.6101) grad_norm: 1.1126 (1.1473) time: 0.6364 [2021-03-26 15:17:20 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 220/1251] eta: 0:11:07 lr: 0.000854 loss: 3.5300 (3.6120) grad_norm: 1.1426 (1.1506) time: 0.6370 [2021-03-26 15:17:26 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 230/1251] eta: 0:10:59 lr: 0.000854 loss: 3.5300 (3.6042) grad_norm: 1.1051 (1.1489) time: 0.6266 [2021-03-26 15:17:33 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 240/1251] eta: 0:10:52 lr: 0.000854 loss: 3.5409 (3.6029) grad_norm: 1.1218 (1.1512) time: 0.6271 [2021-03-26 15:17:39 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 250/1251] eta: 0:10:45 lr: 0.000854 loss: 3.6358 (3.6016) grad_norm: 1.0797 (1.1482) time: 0.6298 [2021-03-26 15:17:45 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 260/1251] eta: 0:10:38 lr: 0.000854 loss: 3.7281 (3.6023) grad_norm: 1.0797 (1.1490) time: 0.6310 [2021-03-26 15:17:52 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 270/1251] eta: 0:10:31 lr: 0.000854 loss: 3.6762 (3.5939) grad_norm: 1.1234 (1.1484) time: 0.6287 [2021-03-26 15:17:58 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 280/1251] eta: 0:10:24 lr: 0.000854 loss: 3.6900 (3.6016) grad_norm: 1.1064 (1.1499) time: 0.6249 [2021-03-26 15:18:04 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 290/1251] eta: 0:10:17 lr: 0.000854 loss: 3.9205 (3.6162) grad_norm: 1.1784 (1.1518) time: 0.6313 [2021-03-26 15:18:10 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 300/1251] eta: 0:10:10 lr: 0.000854 loss: 3.8002 (3.6171) grad_norm: 1.1337 (1.1489) time: 0.6292 [2021-03-26 15:18:17 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 310/1251] eta: 0:10:03 lr: 0.000854 loss: 3.3839 (3.6090) grad_norm: 1.0175 (1.1447) time: 0.6259 [2021-03-26 15:18:23 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 320/1251] eta: 0:09:57 lr: 0.000854 loss: 3.3941 (3.6125) grad_norm: 1.0212 (1.1450) time: 0.6336 [2021-03-26 15:18:29 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 330/1251] eta: 0:09:50 lr: 0.000854 loss: 3.6243 (3.6033) grad_norm: 1.1769 (1.1494) time: 0.6346 [2021-03-26 15:18:36 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 340/1251] eta: 0:09:43 lr: 0.000854 loss: 3.6380 (3.6089) grad_norm: 1.1380 (1.1500) time: 0.6330 [2021-03-26 15:18:42 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 350/1251] eta: 0:09:37 lr: 0.000854 loss: 3.7470 (3.6097) grad_norm: 1.1138 (1.1485) time: 0.6300 [2021-03-26 15:18:48 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 360/1251] eta: 0:09:30 lr: 0.000854 loss: 3.6739 (3.6118) grad_norm: 1.1386 (1.1481) time: 0.6206 [2021-03-26 15:18:55 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 370/1251] eta: 0:09:23 lr: 0.000854 loss: 3.6418 (3.6072) grad_norm: 1.1642 (1.1507) time: 0.6206 [2021-03-26 15:19:01 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 380/1251] eta: 0:09:16 lr: 0.000854 loss: 3.3250 (3.6008) grad_norm: 1.1722 (1.1528) time: 0.6279 [2021-03-26 15:19:07 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 390/1251] eta: 0:09:10 lr: 0.000854 loss: 3.6691 (3.6026) grad_norm: 1.1694 (1.1525) time: 0.6334 [2021-03-26 15:19:14 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 400/1251] eta: 0:09:03 lr: 0.000854 loss: 3.7093 (3.6021) grad_norm: 1.0983 (1.1512) time: 0.6382 [2021-03-26 15:19:20 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 410/1251] eta: 0:08:57 lr: 0.000854 loss: 3.7093 (3.6012) grad_norm: 1.0983 (1.1509) time: 0.6339 [2021-03-26 15:19:26 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 420/1251] eta: 0:08:50 lr: 0.000854 loss: 3.6088 (3.5948) grad_norm: 1.1390 (1.1513) time: 0.6300 [2021-03-26 15:19:33 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 430/1251] eta: 0:08:44 lr: 0.000854 loss: 3.5754 (3.5984) grad_norm: 1.1472 (1.1506) time: 0.6321 [2021-03-26 15:19:39 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 440/1251] eta: 0:08:37 lr: 0.000854 loss: 3.6858 (3.5973) grad_norm: 1.1808 (1.1521) time: 0.6281 [2021-03-26 15:19:45 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 450/1251] eta: 0:08:31 lr: 0.000854 loss: 3.6249 (3.5988) grad_norm: 1.2377 (1.1543) time: 0.6288 [2021-03-26 15:19:51 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 460/1251] eta: 0:08:24 lr: 0.000854 loss: 3.7992 (3.6041) grad_norm: 1.1586 (1.1537) time: 0.6308 [2021-03-26 15:19:58 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 470/1251] eta: 0:08:18 lr: 0.000854 loss: 3.8308 (3.6047) grad_norm: 1.1004 (1.1540) time: 0.6276 [2021-03-26 15:20:04 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 480/1251] eta: 0:08:11 lr: 0.000854 loss: 3.7633 (3.6038) grad_norm: 1.0986 (1.1538) time: 0.6337 [2021-03-26 15:20:10 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 490/1251] eta: 0:08:05 lr: 0.000854 loss: 3.7633 (3.6008) grad_norm: 1.0986 (1.1524) time: 0.6339 [2021-03-26 15:20:17 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 500/1251] eta: 0:07:58 lr: 0.000854 loss: 3.7798 (3.6019) grad_norm: 1.0933 (1.1522) time: 0.6257 [2021-03-26 15:20:23 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 510/1251] eta: 0:07:52 lr: 0.000854 loss: 3.5940 (3.5999) grad_norm: 1.2178 (1.1543) time: 0.6241 [2021-03-26 15:20:29 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 520/1251] eta: 0:07:45 lr: 0.000853 loss: 3.5659 (3.6002) grad_norm: 1.1935 (1.1553) time: 0.6293 [2021-03-26 15:20:35 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 530/1251] eta: 0:07:39 lr: 0.000853 loss: 3.8483 (3.6054) grad_norm: 1.1231 (1.1557) time: 0.6314 [2021-03-26 15:20:42 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 540/1251] eta: 0:07:32 lr: 0.000853 loss: 3.7673 (3.6079) grad_norm: 1.0838 (1.1540) time: 0.6230 [2021-03-26 15:20:48 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 550/1251] eta: 0:07:26 lr: 0.000853 loss: 3.5102 (3.6059) grad_norm: 1.0604 (1.1526) time: 0.6280 [2021-03-26 15:20:54 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 560/1251] eta: 0:07:19 lr: 0.000853 loss: 3.4627 (3.6031) grad_norm: 1.0616 (1.1529) time: 0.6326 [2021-03-26 15:21:01 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 570/1251] eta: 0:07:13 lr: 0.000853 loss: 3.7323 (3.6073) grad_norm: 1.1367 (1.1529) time: 0.6252 [2021-03-26 15:21:07 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 580/1251] eta: 0:07:06 lr: 0.000853 loss: 3.8198 (3.6110) grad_norm: 1.1367 (1.1545) time: 0.6300 [2021-03-26 15:21:13 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 590/1251] eta: 0:07:00 lr: 0.000853 loss: 3.9324 (3.6147) grad_norm: 1.1888 (1.1568) time: 0.6388 [2021-03-26 15:21:20 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 600/1251] eta: 0:06:54 lr: 0.000853 loss: 3.9047 (3.6140) grad_norm: 1.2884 (1.1608) time: 0.6372 [2021-03-26 15:21:26 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 610/1251] eta: 0:06:47 lr: 0.000853 loss: 3.7656 (3.6151) grad_norm: 1.1014 (1.1590) time: 0.6315 [2021-03-26 15:21:32 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 620/1251] eta: 0:06:41 lr: 0.000853 loss: 3.7587 (3.6152) grad_norm: 1.0618 (1.1588) time: 0.6288 [2021-03-26 15:21:39 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 630/1251] eta: 0:06:34 lr: 0.000853 loss: 3.7765 (3.6156) grad_norm: 1.1047 (1.1591) time: 0.6364 [2021-03-26 15:21:45 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 640/1251] eta: 0:06:28 lr: 0.000853 loss: 3.7765 (3.6148) grad_norm: 1.1384 (1.1594) time: 0.6390 [2021-03-26 15:21:51 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 650/1251] eta: 0:06:22 lr: 0.000853 loss: 3.7432 (3.6178) grad_norm: 1.1195 (1.1588) time: 0.6316 [2021-03-26 15:21:58 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 660/1251] eta: 0:06:15 lr: 0.000853 loss: 3.7432 (3.6186) grad_norm: 1.0995 (1.1585) time: 0.6289 [2021-03-26 15:22:04 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 670/1251] eta: 0:06:09 lr: 0.000853 loss: 3.6502 (3.6188) grad_norm: 1.0995 (1.1570) time: 0.6287 [2021-03-26 15:22:10 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 680/1251] eta: 0:06:02 lr: 0.000853 loss: 3.6502 (3.6198) grad_norm: 1.1002 (1.1577) time: 0.6306 [2021-03-26 15:22:17 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 690/1251] eta: 0:05:56 lr: 0.000853 loss: 3.6413 (3.6202) grad_norm: 1.1899 (1.1585) time: 0.6362 [2021-03-26 15:22:23 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 700/1251] eta: 0:05:50 lr: 0.000853 loss: 3.6389 (3.6197) grad_norm: 1.1983 (1.1590) time: 0.6361 [2021-03-26 15:22:29 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 710/1251] eta: 0:05:43 lr: 0.000853 loss: 3.5918 (3.6154) grad_norm: 1.1442 (1.1596) time: 0.6290 [2021-03-26 15:22:36 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 720/1251] eta: 0:05:37 lr: 0.000853 loss: 3.4394 (3.6137) grad_norm: 1.1135 (1.1589) time: 0.6327 [2021-03-26 15:22:42 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 730/1251] eta: 0:05:31 lr: 0.000853 loss: 3.5925 (3.6130) grad_norm: 1.1135 (1.1591) time: 0.6360 [2021-03-26 15:22:48 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 740/1251] eta: 0:05:24 lr: 0.000853 loss: 3.6846 (3.6130) grad_norm: 1.0965 (1.1582) time: 0.6300 [2021-03-26 15:22:55 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 750/1251] eta: 0:05:18 lr: 0.000853 loss: 3.4375 (3.6072) grad_norm: 1.0691 (1.1569) time: 0.6308 [2021-03-26 15:23:01 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 760/1251] eta: 0:05:11 lr: 0.000853 loss: 3.0785 (3.6064) grad_norm: 1.0882 (1.1571) time: 0.6343 [2021-03-26 15:23:07 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 770/1251] eta: 0:05:05 lr: 0.000853 loss: 3.8385 (3.6093) grad_norm: 1.1760 (1.1571) time: 0.6369 [2021-03-26 15:23:14 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 780/1251] eta: 0:04:59 lr: 0.000853 loss: 3.8008 (3.6112) grad_norm: 1.1913 (1.1578) time: 0.6403 [2021-03-26 15:23:20 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 790/1251] eta: 0:04:52 lr: 0.000853 loss: 3.8718 (3.6153) grad_norm: 1.1526 (1.1579) time: 0.6390 [2021-03-26 15:23:26 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 800/1251] eta: 0:04:46 lr: 0.000853 loss: 3.9128 (3.6145) grad_norm: 1.1352 (1.1576) time: 0.6329 [2021-03-26 15:23:33 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 810/1251] eta: 0:04:40 lr: 0.000853 loss: 3.6195 (3.6143) grad_norm: 1.1137 (1.1569) time: 0.6275 [2021-03-26 15:23:39 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 820/1251] eta: 0:04:33 lr: 0.000853 loss: 3.6195 (3.6133) grad_norm: 1.1059 (1.1563) time: 0.6283 [2021-03-26 15:23:45 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 830/1251] eta: 0:04:27 lr: 0.000853 loss: 3.7035 (3.6139) grad_norm: 1.1080 (1.1557) time: 0.6324 [2021-03-26 15:23:51 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 840/1251] eta: 0:04:21 lr: 0.000853 loss: 3.8188 (3.6149) grad_norm: 1.1094 (1.1550) time: 0.6300 [2021-03-26 15:23:58 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 850/1251] eta: 0:04:14 lr: 0.000853 loss: 3.6716 (3.6153) grad_norm: 1.1392 (1.1552) time: 0.6251 [2021-03-26 15:24:04 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 860/1251] eta: 0:04:08 lr: 0.000852 loss: 3.6459 (3.6133) grad_norm: 1.1635 (1.1555) time: 0.6256 [2021-03-26 15:24:10 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 870/1251] eta: 0:04:01 lr: 0.000852 loss: 3.5562 (3.6124) grad_norm: 1.1442 (1.1555) time: 0.6281 [2021-03-26 15:24:17 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 880/1251] eta: 0:03:55 lr: 0.000852 loss: 3.7427 (3.6143) grad_norm: 1.0596 (1.1543) time: 0.6357 [2021-03-26 15:24:23 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 890/1251] eta: 0:03:49 lr: 0.000852 loss: 3.8130 (3.6159) grad_norm: 1.0707 (1.1541) time: 0.6348 [2021-03-26 15:24:29 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 900/1251] eta: 0:03:42 lr: 0.000852 loss: 3.6754 (3.6134) grad_norm: 1.1077 (1.1542) time: 0.6288 [2021-03-26 15:24:36 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 910/1251] eta: 0:03:36 lr: 0.000852 loss: 3.3958 (3.6111) grad_norm: 1.1725 (1.1547) time: 0.6325 [2021-03-26 15:24:42 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 920/1251] eta: 0:03:30 lr: 0.000852 loss: 3.5245 (3.6108) grad_norm: 1.1166 (1.1539) time: 0.6361 [2021-03-26 15:24:48 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 930/1251] eta: 0:03:23 lr: 0.000852 loss: 3.6390 (3.6110) grad_norm: 1.1166 (1.1537) time: 0.6313 [2021-03-26 15:24:55 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 940/1251] eta: 0:03:17 lr: 0.000852 loss: 3.6390 (3.6089) grad_norm: 1.1154 (1.1530) time: 0.6288 [2021-03-26 15:25:01 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 950/1251] eta: 0:03:10 lr: 0.000852 loss: 3.6748 (3.6124) grad_norm: 1.0864 (1.1527) time: 0.6251 [2021-03-26 15:25:07 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 960/1251] eta: 0:03:04 lr: 0.000852 loss: 3.9157 (3.6150) grad_norm: 1.1082 (1.1531) time: 0.6297 [2021-03-26 15:25:14 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 970/1251] eta: 0:02:58 lr: 0.000852 loss: 3.6839 (3.6144) grad_norm: 1.1029 (1.1525) time: 0.6350 [2021-03-26 15:25:20 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 980/1251] eta: 0:02:51 lr: 0.000852 loss: 3.5963 (3.6125) grad_norm: 1.1029 (1.1528) time: 0.6300 [2021-03-26 15:25:26 swin_base_patch4_window7_224] INFO: Epoch: [75] [ 990/1251] eta: 0:02:45 lr: 0.000852 loss: 3.4722 (3.6116) grad_norm: 1.0917 (1.1524) time: 0.6259 [2021-03-26 15:25:32 swin_base_patch4_window7_224] INFO: Epoch: [75] [1000/1251] eta: 0:02:39 lr: 0.000852 loss: 3.7111 (3.6132) grad_norm: 1.0987 (1.1524) time: 0.6281 [2021-03-26 15:25:39 swin_base_patch4_window7_224] INFO: Epoch: [75] [1010/1251] eta: 0:02:32 lr: 0.000852 loss: 3.9178 (3.6126) grad_norm: 1.0783 (1.1518) time: 0.6271 [2021-03-26 15:25:45 swin_base_patch4_window7_224] INFO: Epoch: [75] [1020/1251] eta: 0:02:26 lr: 0.000852 loss: 3.9178 (3.6146) grad_norm: 1.0727 (1.1524) time: 0.6264 [2021-03-26 15:25:51 swin_base_patch4_window7_224] INFO: Epoch: [75] [1030/1251] eta: 0:02:20 lr: 0.000852 loss: 3.9273 (3.6163) grad_norm: 1.1233 (1.1523) time: 0.6341 [2021-03-26 15:25:58 swin_base_patch4_window7_224] INFO: Epoch: [75] [1040/1251] eta: 0:02:13 lr: 0.000852 loss: 3.7610 (3.6154) grad_norm: 1.1243 (1.1521) time: 0.6323 [2021-03-26 15:26:04 swin_base_patch4_window7_224] INFO: Epoch: [75] [1050/1251] eta: 0:02:07 lr: 0.000852 loss: 3.6550 (3.6186) grad_norm: 1.1494 (1.1522) time: 0.6305 [2021-03-26 15:26:10 swin_base_patch4_window7_224] INFO: Epoch: [75] [1060/1251] eta: 0:02:01 lr: 0.000852 loss: 3.9156 (3.6190) grad_norm: 1.1494 (1.1522) time: 0.6315 [2021-03-26 15:26:16 swin_base_patch4_window7_224] INFO: Epoch: [75] [1070/1251] eta: 0:01:54 lr: 0.000852 loss: 3.7409 (3.6198) grad_norm: 1.0553 (1.1514) time: 0.6272 [2021-03-26 15:26:23 swin_base_patch4_window7_224] INFO: Epoch: [75] [1080/1251] eta: 0:01:48 lr: 0.000852 loss: 3.3606 (3.6174) grad_norm: 1.0623 (1.1509) time: 0.6250 [2021-03-26 15:26:29 swin_base_patch4_window7_224] INFO: Epoch: [75] [1090/1251] eta: 0:01:42 lr: 0.000852 loss: 3.2178 (3.6154) grad_norm: 1.1443 (1.1518) time: 0.6347 [2021-03-26 15:26:35 swin_base_patch4_window7_224] INFO: Epoch: [75] [1100/1251] eta: 0:01:35 lr: 0.000852 loss: 3.6878 (3.6156) grad_norm: 1.2132 (1.1522) time: 0.6379 [2021-03-26 15:26:42 swin_base_patch4_window7_224] INFO: Epoch: [75] [1110/1251] eta: 0:01:29 lr: 0.000852 loss: 3.7861 (3.6165) grad_norm: 1.1752 (1.1524) time: 0.6359 [2021-03-26 15:26:48 swin_base_patch4_window7_224] INFO: Epoch: [75] [1120/1251] eta: 0:01:23 lr: 0.000852 loss: 3.6351 (3.6151) grad_norm: 1.1693 (1.1525) time: 0.6327 [2021-03-26 15:26:54 swin_base_patch4_window7_224] INFO: Epoch: [75] [1130/1251] eta: 0:01:16 lr: 0.000852 loss: 3.7405 (3.6163) grad_norm: 1.1958 (1.1534) time: 0.6264 [2021-03-26 15:27:01 swin_base_patch4_window7_224] INFO: Epoch: [75] [1140/1251] eta: 0:01:10 lr: 0.000852 loss: 3.7850 (3.6141) grad_norm: 1.1761 (1.1533) time: 0.6233 [2021-03-26 15:27:07 swin_base_patch4_window7_224] INFO: Epoch: [75] [1150/1251] eta: 0:01:04 lr: 0.000852 loss: 3.3752 (3.6129) grad_norm: 1.1289 (1.1528) time: 0.6325 [2021-03-26 15:27:13 swin_base_patch4_window7_224] INFO: Epoch: [75] [1160/1251] eta: 0:00:57 lr: 0.000852 loss: 3.5099 (3.6135) grad_norm: 1.0538 (1.1519) time: 0.6392 [2021-03-26 15:27:20 swin_base_patch4_window7_224] INFO: Epoch: [75] [1170/1251] eta: 0:00:51 lr: 0.000852 loss: 3.7045 (3.6112) grad_norm: 1.0888 (1.1521) time: 0.6353 [2021-03-26 15:27:26 swin_base_patch4_window7_224] INFO: Epoch: [75] [1180/1251] eta: 0:00:45 lr: 0.000852 loss: 3.7197 (3.6123) grad_norm: 1.1108 (1.1518) time: 0.6328 [2021-03-26 15:27:32 swin_base_patch4_window7_224] INFO: Epoch: [75] [1190/1251] eta: 0:00:38 lr: 0.000852 loss: 3.7197 (3.6126) grad_norm: 1.1649 (1.1531) time: 0.6288 [2021-03-26 15:27:39 swin_base_patch4_window7_224] INFO: Epoch: [75] [1200/1251] eta: 0:00:32 lr: 0.000851 loss: 3.4561 (3.6112) grad_norm: 1.2249 (1.1532) time: 0.6337 [2021-03-26 15:27:45 swin_base_patch4_window7_224] INFO: Epoch: [75] [1210/1251] eta: 0:00:25 lr: 0.000851 loss: 3.2657 (3.6093) grad_norm: 1.1397 (1.1539) time: 0.6401 [2021-03-26 15:27:51 swin_base_patch4_window7_224] INFO: Epoch: [75] [1220/1251] eta: 0:00:19 lr: 0.000851 loss: 3.6805 (3.6091) grad_norm: 1.1213 (1.1535) time: 0.6367 [2021-03-26 15:27:58 swin_base_patch4_window7_224] INFO: Epoch: [75] [1230/1251] eta: 0:00:13 lr: 0.000851 loss: 3.8514 (3.6099) grad_norm: 1.1316 (1.1544) time: 0.6287 [2021-03-26 15:28:04 swin_base_patch4_window7_224] INFO: Epoch: [75] [1240/1251] eta: 0:00:06 lr: 0.000851 loss: 3.8891 (3.6103) grad_norm: 1.1849 (1.1546) time: 0.6276 [2021-03-26 15:28:10 swin_base_patch4_window7_224] INFO: Epoch: [75] [1250/1251] eta: 0:00:00 lr: 0.000851 loss: 3.6068 (3.6090) grad_norm: 1.1890 (1.1552) time: 0.6246 [2021-03-26 15:29:14 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.9997 (0.9997) acc1: 71.8750 (71.8750) acc5: 96.8750 (96.8750) [2021-03-26 15:29:16 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 1.1068 (1.0665) acc1: 73.4375 (75.0000) acc5: 93.7500 (94.3182) [2021-03-26 15:29:17 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.0558 (1.0636) acc1: 76.5625 (75.8185) acc5: 93.7500 (93.7500) [2021-03-26 15:29:19 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.0649 (1.1095) acc1: 75.0000 (74.6472) acc5: 93.7500 (93.3468) [2021-03-26 15:29:20 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.0958 (1.0947) acc1: 75.0000 (75.1524) acc5: 93.7500 (93.4451) [2021-03-26 15:29:21 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0744 (1.1119) acc1: 73.4375 (74.5600) acc5: 93.7500 (93.1840) [2021-03-26 15:29:25 swin_base_patch4_window7_224] INFO: * Acc@1 75.216 Acc@5 92.956 loss 1.094 [2021-03-26 15:29:25 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.2% [2021-03-26 15:29:25 swin_base_patch4_window7_224] INFO: Max accuracy: 75.22% [2021-03-26 15:29:30 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 0/1251] eta: 1:27:41 lr: 0.000851 loss: 3.6550 (3.6550) grad_norm: 1.1150 (1.1150) time: 4.2059 [2021-03-26 15:29:36 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 10/1251] eta: 0:20:17 lr: 0.000851 loss: 3.7201 (3.8472) grad_norm: 1.1166 (1.1453) time: 0.9814 [2021-03-26 15:29:43 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 20/1251] eta: 0:16:42 lr: 0.000851 loss: 3.6901 (3.6539) grad_norm: 1.1382 (1.1860) time: 0.6450 [2021-03-26 15:29:49 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 30/1251] eta: 0:15:19 lr: 0.000851 loss: 3.4770 (3.7017) grad_norm: 1.1542 (1.1688) time: 0.6278 [2021-03-26 15:29:55 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 40/1251] eta: 0:14:33 lr: 0.000851 loss: 3.8997 (3.7082) grad_norm: 1.0620 (1.1519) time: 0.6233 [2021-03-26 15:30:01 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 50/1251] eta: 0:14:05 lr: 0.000851 loss: 3.6730 (3.6731) grad_norm: 1.1436 (1.1574) time: 0.6271 [2021-03-26 15:30:08 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 60/1251] eta: 0:13:45 lr: 0.000851 loss: 3.6730 (3.6832) grad_norm: 1.1211 (1.1535) time: 0.6360 [2021-03-26 15:30:14 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 70/1251] eta: 0:13:29 lr: 0.000851 loss: 3.6540 (3.6567) grad_norm: 1.0763 (1.1394) time: 0.6395 [2021-03-26 15:30:20 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 80/1251] eta: 0:13:13 lr: 0.000851 loss: 3.5358 (3.6293) grad_norm: 1.0733 (1.1322) time: 0.6314 [2021-03-26 15:30:27 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 90/1251] eta: 0:13:00 lr: 0.000851 loss: 3.6576 (3.6513) grad_norm: 1.1135 (1.1358) time: 0.6254 [2021-03-26 15:30:33 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 100/1251] eta: 0:12:49 lr: 0.000851 loss: 3.7328 (3.6557) grad_norm: 1.1357 (1.1339) time: 0.6289 [2021-03-26 15:30:39 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 110/1251] eta: 0:12:37 lr: 0.000851 loss: 3.7458 (3.6607) grad_norm: 1.1215 (1.1355) time: 0.6238 [2021-03-26 15:30:46 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 120/1251] eta: 0:12:28 lr: 0.000851 loss: 3.7330 (3.6592) grad_norm: 1.0686 (1.1318) time: 0.6304 [2021-03-26 15:30:52 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 130/1251] eta: 0:12:18 lr: 0.000851 loss: 3.7330 (3.6729) grad_norm: 1.0668 (1.1285) time: 0.6326 [2021-03-26 15:30:58 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 140/1251] eta: 0:12:09 lr: 0.000851 loss: 3.7208 (3.6714) grad_norm: 1.0611 (1.1252) time: 0.6223 [2021-03-26 15:31:04 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 150/1251] eta: 0:12:00 lr: 0.000851 loss: 3.5154 (3.6602) grad_norm: 1.1242 (1.1321) time: 0.6227 [2021-03-26 15:31:11 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 160/1251] eta: 0:11:52 lr: 0.000851 loss: 3.7656 (3.6647) grad_norm: 1.1788 (1.1362) time: 0.6264 [2021-03-26 15:31:17 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 170/1251] eta: 0:11:44 lr: 0.000851 loss: 3.7656 (3.6543) grad_norm: 1.2191 (1.1498) time: 0.6324 [2021-03-26 15:31:23 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 180/1251] eta: 0:11:36 lr: 0.000851 loss: 3.5469 (3.6393) grad_norm: 1.1740 (1.1481) time: 0.6313 [2021-03-26 15:31:29 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 190/1251] eta: 0:11:28 lr: 0.000851 loss: 3.7357 (3.6506) grad_norm: 1.1302 (1.1491) time: 0.6271 [2021-03-26 15:31:36 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 200/1251] eta: 0:11:20 lr: 0.000851 loss: 3.8172 (3.6475) grad_norm: 1.0753 (1.1462) time: 0.6254 [2021-03-26 15:31:42 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 210/1251] eta: 0:11:13 lr: 0.000851 loss: 3.5499 (3.6376) grad_norm: 1.0658 (1.1450) time: 0.6292 [2021-03-26 15:31:48 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 220/1251] eta: 0:11:06 lr: 0.000851 loss: 3.4306 (3.6314) grad_norm: 1.0527 (1.1409) time: 0.6314 [2021-03-26 15:31:55 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 230/1251] eta: 0:10:59 lr: 0.000851 loss: 3.4694 (3.6213) grad_norm: 1.0527 (1.1420) time: 0.6317 [2021-03-26 15:32:01 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 240/1251] eta: 0:10:51 lr: 0.000851 loss: 3.6185 (3.6269) grad_norm: 1.1449 (1.1447) time: 0.6284 [2021-03-26 15:32:07 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 250/1251] eta: 0:10:44 lr: 0.000851 loss: 3.3491 (3.6085) grad_norm: 1.1064 (1.1417) time: 0.6206 [2021-03-26 15:32:13 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 260/1251] eta: 0:10:37 lr: 0.000851 loss: 3.3388 (3.6053) grad_norm: 1.0820 (1.1422) time: 0.6263 [2021-03-26 15:32:20 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 270/1251] eta: 0:10:31 lr: 0.000851 loss: 3.6861 (3.6070) grad_norm: 1.1841 (1.1470) time: 0.6363 [2021-03-26 15:32:26 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 280/1251] eta: 0:10:23 lr: 0.000851 loss: 3.6919 (3.6083) grad_norm: 1.1742 (1.1448) time: 0.6303 [2021-03-26 15:32:32 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 290/1251] eta: 0:10:17 lr: 0.000850 loss: 3.6443 (3.6056) grad_norm: 1.0884 (1.1453) time: 0.6284 [2021-03-26 15:32:39 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 300/1251] eta: 0:10:10 lr: 0.000850 loss: 3.5295 (3.5985) grad_norm: 1.0919 (1.1431) time: 0.6358 [2021-03-26 15:32:45 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 310/1251] eta: 0:10:03 lr: 0.000850 loss: 3.3143 (3.5920) grad_norm: 1.0919 (1.1434) time: 0.6362 [2021-03-26 15:32:51 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 320/1251] eta: 0:09:57 lr: 0.000850 loss: 3.6069 (3.5994) grad_norm: 1.1002 (1.1443) time: 0.6316 [2021-03-26 15:32:58 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 330/1251] eta: 0:09:50 lr: 0.000850 loss: 3.8855 (3.5953) grad_norm: 1.0888 (1.1426) time: 0.6229 [2021-03-26 15:33:04 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 340/1251] eta: 0:09:43 lr: 0.000850 loss: 3.5773 (3.5944) grad_norm: 1.1292 (1.1445) time: 0.6275 [2021-03-26 15:33:10 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 350/1251] eta: 0:09:36 lr: 0.000850 loss: 3.6626 (3.5973) grad_norm: 1.1443 (1.1430) time: 0.6326 [2021-03-26 15:33:17 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 360/1251] eta: 0:09:30 lr: 0.000850 loss: 3.6504 (3.5950) grad_norm: 1.1201 (1.1463) time: 0.6271 [2021-03-26 15:33:23 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 370/1251] eta: 0:09:23 lr: 0.000850 loss: 3.4098 (3.5854) grad_norm: 1.0760 (1.1449) time: 0.6267 [2021-03-26 15:33:29 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 380/1251] eta: 0:09:16 lr: 0.000850 loss: 3.2105 (3.5857) grad_norm: 1.0601 (1.1432) time: 0.6256 [2021-03-26 15:33:35 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 390/1251] eta: 0:09:09 lr: 0.000850 loss: 3.2105 (3.5727) grad_norm: 1.1368 (1.1447) time: 0.6234 [2021-03-26 15:33:42 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 400/1251] eta: 0:09:03 lr: 0.000850 loss: 3.2396 (3.5752) grad_norm: 1.1689 (1.1457) time: 0.6247 [2021-03-26 15:33:48 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 410/1251] eta: 0:08:56 lr: 0.000850 loss: 3.7828 (3.5801) grad_norm: 1.1188 (1.1447) time: 0.6261 [2021-03-26 15:33:54 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 420/1251] eta: 0:08:50 lr: 0.000850 loss: 3.6311 (3.5772) grad_norm: 1.1018 (1.1444) time: 0.6263 [2021-03-26 15:34:00 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 430/1251] eta: 0:08:43 lr: 0.000850 loss: 3.8604 (3.5824) grad_norm: 1.0812 (1.1434) time: 0.6227 [2021-03-26 15:34:06 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 440/1251] eta: 0:08:36 lr: 0.000850 loss: 3.7734 (3.5828) grad_norm: 1.1102 (1.1441) time: 0.6190 [2021-03-26 15:34:13 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 450/1251] eta: 0:08:30 lr: 0.000850 loss: 3.6070 (3.5793) grad_norm: 1.1102 (1.1418) time: 0.6228 [2021-03-26 15:34:19 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 460/1251] eta: 0:08:23 lr: 0.000850 loss: 3.5523 (3.5807) grad_norm: 1.0251 (1.1401) time: 0.6253 [2021-03-26 15:34:25 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 470/1251] eta: 0:08:17 lr: 0.000850 loss: 3.5568 (3.5819) grad_norm: 1.1144 (1.1405) time: 0.6307 [2021-03-26 15:34:32 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 480/1251] eta: 0:08:10 lr: 0.000850 loss: 3.3926 (3.5786) grad_norm: 1.1798 (1.1425) time: 0.6314 [2021-03-26 15:34:38 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 490/1251] eta: 0:08:04 lr: 0.000850 loss: 3.7102 (3.5811) grad_norm: 1.2003 (1.1424) time: 0.6276 [2021-03-26 15:34:44 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 500/1251] eta: 0:07:57 lr: 0.000850 loss: 3.8019 (3.5830) grad_norm: 1.1595 (1.1434) time: 0.6274 [2021-03-26 15:34:50 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 510/1251] eta: 0:07:51 lr: 0.000850 loss: 3.8094 (3.5846) grad_norm: 1.1421 (1.1433) time: 0.6302 [2021-03-26 15:34:57 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 520/1251] eta: 0:07:44 lr: 0.000850 loss: 3.8094 (3.5809) grad_norm: 1.1064 (1.1439) time: 0.6342 [2021-03-26 15:35:03 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 530/1251] eta: 0:07:38 lr: 0.000850 loss: 3.5835 (3.5831) grad_norm: 1.1064 (1.1440) time: 0.6360 [2021-03-26 15:35:09 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 540/1251] eta: 0:07:31 lr: 0.000850 loss: 3.7083 (3.5856) grad_norm: 1.0820 (1.1435) time: 0.6310 [2021-03-26 15:35:16 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 550/1251] eta: 0:07:25 lr: 0.000850 loss: 3.7490 (3.5896) grad_norm: 1.0820 (1.1439) time: 0.6325 [2021-03-26 15:35:22 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 560/1251] eta: 0:07:19 lr: 0.000850 loss: 3.7407 (3.5885) grad_norm: 1.0539 (1.1430) time: 0.6335 [2021-03-26 15:35:28 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 570/1251] eta: 0:07:12 lr: 0.000850 loss: 3.4004 (3.5831) grad_norm: 1.0081 (1.1411) time: 0.6263 [2021-03-26 15:35:35 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 580/1251] eta: 0:07:06 lr: 0.000850 loss: 3.4004 (3.5841) grad_norm: 1.0399 (1.1410) time: 0.6284 [2021-03-26 15:35:41 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 590/1251] eta: 0:07:00 lr: 0.000850 loss: 3.7514 (3.5836) grad_norm: 1.1625 (1.1417) time: 0.6357 [2021-03-26 15:35:47 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 600/1251] eta: 0:06:53 lr: 0.000850 loss: 3.6852 (3.5834) grad_norm: 1.1707 (1.1426) time: 0.6367 [2021-03-26 15:35:54 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 610/1251] eta: 0:06:47 lr: 0.000850 loss: 3.6806 (3.5843) grad_norm: 1.1673 (1.1425) time: 0.6348 [2021-03-26 15:36:00 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 620/1251] eta: 0:06:40 lr: 0.000849 loss: 3.6693 (3.5817) grad_norm: 1.1409 (1.1431) time: 0.6324 [2021-03-26 15:36:06 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 630/1251] eta: 0:06:34 lr: 0.000849 loss: 3.6693 (3.5859) grad_norm: 1.1306 (1.1436) time: 0.6289 [2021-03-26 15:36:13 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 640/1251] eta: 0:06:27 lr: 0.000849 loss: 3.6125 (3.5803) grad_norm: 1.0885 (1.1425) time: 0.6231 [2021-03-26 15:36:19 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 650/1251] eta: 0:06:21 lr: 0.000849 loss: 3.5823 (3.5848) grad_norm: 1.1333 (1.1426) time: 0.6232 [2021-03-26 15:36:25 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 660/1251] eta: 0:06:15 lr: 0.000849 loss: 3.9482 (3.5883) grad_norm: 1.1051 (1.1413) time: 0.6238 [2021-03-26 15:36:31 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 670/1251] eta: 0:06:08 lr: 0.000849 loss: 3.8222 (3.5889) grad_norm: 1.0673 (1.1421) time: 0.6213 [2021-03-26 15:36:38 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 680/1251] eta: 0:06:02 lr: 0.000849 loss: 3.8721 (3.5954) grad_norm: 1.1853 (1.1422) time: 0.6274 [2021-03-26 15:36:44 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 690/1251] eta: 0:05:55 lr: 0.000849 loss: 3.8070 (3.5913) grad_norm: 1.1937 (1.1430) time: 0.6269 [2021-03-26 15:36:50 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 700/1251] eta: 0:05:49 lr: 0.000849 loss: 3.6508 (3.5923) grad_norm: 1.1666 (1.1424) time: 0.6226 [2021-03-26 15:36:56 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 710/1251] eta: 0:05:42 lr: 0.000849 loss: 3.7074 (3.5943) grad_norm: 1.0672 (1.1420) time: 0.6259 [2021-03-26 15:37:03 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 720/1251] eta: 0:05:36 lr: 0.000849 loss: 3.7548 (3.5959) grad_norm: 1.0428 (1.1411) time: 0.6268 [2021-03-26 15:37:09 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 730/1251] eta: 0:05:30 lr: 0.000849 loss: 3.8268 (3.5971) grad_norm: 1.0872 (1.1419) time: 0.6321 [2021-03-26 15:37:15 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 740/1251] eta: 0:05:23 lr: 0.000849 loss: 3.5460 (3.5962) grad_norm: 1.1306 (1.1420) time: 0.6361 [2021-03-26 15:37:22 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 750/1251] eta: 0:05:17 lr: 0.000849 loss: 3.5460 (3.5968) grad_norm: 1.0446 (1.1408) time: 0.6288 [2021-03-26 15:37:28 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 760/1251] eta: 0:05:11 lr: 0.000849 loss: 3.6818 (3.6003) grad_norm: 1.0871 (1.1409) time: 0.6306 [2021-03-26 15:37:34 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 770/1251] eta: 0:05:04 lr: 0.000849 loss: 3.6162 (3.6003) grad_norm: 1.1179 (1.1422) time: 0.6321 [2021-03-26 15:37:41 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 780/1251] eta: 0:04:58 lr: 0.000849 loss: 3.5963 (3.6005) grad_norm: 1.1557 (1.1428) time: 0.6326 [2021-03-26 15:37:47 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 790/1251] eta: 0:04:52 lr: 0.000849 loss: 3.5049 (3.5969) grad_norm: 1.1468 (1.1436) time: 0.6311 [2021-03-26 15:37:53 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 800/1251] eta: 0:04:45 lr: 0.000849 loss: 3.5348 (3.5989) grad_norm: 1.1725 (1.1451) time: 0.6366 [2021-03-26 15:38:00 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 810/1251] eta: 0:04:39 lr: 0.000849 loss: 3.8094 (3.6017) grad_norm: 1.1335 (1.1451) time: 0.6400 [2021-03-26 15:38:06 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 820/1251] eta: 0:04:33 lr: 0.000849 loss: 3.6184 (3.5995) grad_norm: 1.1209 (1.1450) time: 0.6398 [2021-03-26 15:38:12 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 830/1251] eta: 0:04:26 lr: 0.000849 loss: 3.5871 (3.6017) grad_norm: 1.0975 (1.1449) time: 0.6322 [2021-03-26 15:38:19 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 840/1251] eta: 0:04:20 lr: 0.000849 loss: 3.6906 (3.6011) grad_norm: 1.1194 (1.1452) time: 0.6281 [2021-03-26 15:38:25 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 850/1251] eta: 0:04:14 lr: 0.000849 loss: 3.6563 (3.6018) grad_norm: 1.1614 (1.1455) time: 0.6306 [2021-03-26 15:38:31 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 860/1251] eta: 0:04:07 lr: 0.000849 loss: 3.4679 (3.5991) grad_norm: 1.1579 (1.1453) time: 0.6299 [2021-03-26 15:38:38 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 870/1251] eta: 0:04:01 lr: 0.000849 loss: 3.4613 (3.5985) grad_norm: 1.1565 (1.1462) time: 0.6356 [2021-03-26 15:38:44 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 880/1251] eta: 0:03:55 lr: 0.000849 loss: 3.4613 (3.5961) grad_norm: 1.1085 (1.1452) time: 0.6301 [2021-03-26 15:38:50 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 890/1251] eta: 0:03:48 lr: 0.000849 loss: 3.6539 (3.5976) grad_norm: 1.0909 (1.1456) time: 0.6243 [2021-03-26 15:38:56 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 900/1251] eta: 0:03:42 lr: 0.000849 loss: 3.8519 (3.6000) grad_norm: 1.0942 (1.1453) time: 0.6222 [2021-03-26 15:39:03 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 910/1251] eta: 0:03:36 lr: 0.000849 loss: 3.6017 (3.5954) grad_norm: 1.0850 (1.1444) time: 0.6289 [2021-03-26 15:39:09 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 920/1251] eta: 0:03:29 lr: 0.000849 loss: 3.2168 (3.5950) grad_norm: 1.0850 (1.1443) time: 0.6303 [2021-03-26 15:39:15 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 930/1251] eta: 0:03:23 lr: 0.000849 loss: 3.7064 (3.5958) grad_norm: 1.1184 (1.1445) time: 0.6273 [2021-03-26 15:39:21 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 940/1251] eta: 0:03:16 lr: 0.000849 loss: 3.5364 (3.5925) grad_norm: 1.1420 (1.1458) time: 0.6281 [2021-03-26 15:39:28 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 950/1251] eta: 0:03:10 lr: 0.000849 loss: 3.4502 (3.5913) grad_norm: 1.1955 (1.1461) time: 0.6330 [2021-03-26 15:39:34 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 960/1251] eta: 0:03:04 lr: 0.000848 loss: 3.6578 (3.5924) grad_norm: 1.1387 (1.1461) time: 0.6371 [2021-03-26 15:39:41 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 970/1251] eta: 0:02:57 lr: 0.000848 loss: 3.8752 (3.5917) grad_norm: 1.1236 (1.1461) time: 0.6340 [2021-03-26 15:39:47 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 980/1251] eta: 0:02:51 lr: 0.000848 loss: 3.6029 (3.5918) grad_norm: 1.1236 (1.1459) time: 0.6337 [2021-03-26 15:39:53 swin_base_patch4_window7_224] INFO: Epoch: [76] [ 990/1251] eta: 0:02:45 lr: 0.000848 loss: 3.5391 (3.5918) grad_norm: 1.1021 (1.1458) time: 0.6245 [2021-03-26 15:39:59 swin_base_patch4_window7_224] INFO: Epoch: [76] [1000/1251] eta: 0:02:38 lr: 0.000848 loss: 3.7568 (3.5923) grad_norm: 1.1021 (1.1463) time: 0.6218 [2021-03-26 15:40:06 swin_base_patch4_window7_224] INFO: Epoch: [76] [1010/1251] eta: 0:02:32 lr: 0.000848 loss: 3.7568 (3.5926) grad_norm: 1.1380 (1.1461) time: 0.6296 [2021-03-26 15:40:12 swin_base_patch4_window7_224] INFO: Epoch: [76] [1020/1251] eta: 0:02:26 lr: 0.000848 loss: 3.6342 (3.5925) grad_norm: 1.0733 (1.1459) time: 0.6338 [2021-03-26 15:40:18 swin_base_patch4_window7_224] INFO: Epoch: [76] [1030/1251] eta: 0:02:19 lr: 0.000848 loss: 3.7216 (3.5916) grad_norm: 1.1138 (1.1463) time: 0.6307 [2021-03-26 15:40:25 swin_base_patch4_window7_224] INFO: Epoch: [76] [1040/1251] eta: 0:02:13 lr: 0.000848 loss: 3.7724 (3.5931) grad_norm: 1.1138 (1.1458) time: 0.6312 [2021-03-26 15:40:31 swin_base_patch4_window7_224] INFO: Epoch: [76] [1050/1251] eta: 0:02:07 lr: 0.000848 loss: 3.7876 (3.5958) grad_norm: 1.1041 (1.1460) time: 0.6313 [2021-03-26 15:40:37 swin_base_patch4_window7_224] INFO: Epoch: [76] [1060/1251] eta: 0:02:00 lr: 0.000848 loss: 3.7299 (3.5956) grad_norm: 1.1041 (1.1460) time: 0.6232 [2021-03-26 15:40:43 swin_base_patch4_window7_224] INFO: Epoch: [76] [1070/1251] eta: 0:01:54 lr: 0.000848 loss: 3.6901 (3.5969) grad_norm: 1.1056 (1.1459) time: 0.6267 [2021-03-26 15:40:50 swin_base_patch4_window7_224] INFO: Epoch: [76] [1080/1251] eta: 0:01:48 lr: 0.000848 loss: 3.7163 (3.5984) grad_norm: 1.1382 (1.1456) time: 0.6332 [2021-03-26 15:40:56 swin_base_patch4_window7_224] INFO: Epoch: [76] [1090/1251] eta: 0:01:41 lr: 0.000848 loss: 3.7419 (3.5997) grad_norm: 1.1181 (1.1459) time: 0.6331 [2021-03-26 15:41:02 swin_base_patch4_window7_224] INFO: Epoch: [76] [1100/1251] eta: 0:01:35 lr: 0.000848 loss: 3.6875 (3.5986) grad_norm: 1.1256 (1.1461) time: 0.6244 [2021-03-26 15:41:09 swin_base_patch4_window7_224] INFO: Epoch: [76] [1110/1251] eta: 0:01:29 lr: 0.000848 loss: 3.6120 (3.5981) grad_norm: 1.1462 (1.1460) time: 0.6201 [2021-03-26 15:41:15 swin_base_patch4_window7_224] INFO: Epoch: [76] [1120/1251] eta: 0:01:22 lr: 0.000848 loss: 3.8194 (3.6003) grad_norm: 1.0984 (1.1458) time: 0.6227 [2021-03-26 15:41:21 swin_base_patch4_window7_224] INFO: Epoch: [76] [1130/1251] eta: 0:01:16 lr: 0.000848 loss: 3.4723 (3.5965) grad_norm: 1.1326 (1.1462) time: 0.6242 [2021-03-26 15:41:27 swin_base_patch4_window7_224] INFO: Epoch: [76] [1140/1251] eta: 0:01:10 lr: 0.000848 loss: 3.2261 (3.5959) grad_norm: 1.1326 (1.1462) time: 0.6259 [2021-03-26 15:41:34 swin_base_patch4_window7_224] INFO: Epoch: [76] [1150/1251] eta: 0:01:03 lr: 0.000848 loss: 3.4632 (3.5950) grad_norm: 1.1018 (1.1464) time: 0.6277 [2021-03-26 15:41:40 swin_base_patch4_window7_224] INFO: Epoch: [76] [1160/1251] eta: 0:00:57 lr: 0.000848 loss: 3.7609 (3.5964) grad_norm: 1.1216 (1.1465) time: 0.6290 [2021-03-26 15:41:46 swin_base_patch4_window7_224] INFO: Epoch: [76] [1170/1251] eta: 0:00:51 lr: 0.000848 loss: 3.6771 (3.5953) grad_norm: 1.1247 (1.1466) time: 0.6303 [2021-03-26 15:41:52 swin_base_patch4_window7_224] INFO: Epoch: [76] [1180/1251] eta: 0:00:44 lr: 0.000848 loss: 3.4995 (3.5942) grad_norm: 1.1632 (1.1475) time: 0.6305 [2021-03-26 15:41:59 swin_base_patch4_window7_224] INFO: Epoch: [76] [1190/1251] eta: 0:00:38 lr: 0.000848 loss: 3.5947 (3.5946) grad_norm: 1.1453 (1.1471) time: 0.6240 [2021-03-26 15:42:05 swin_base_patch4_window7_224] INFO: Epoch: [76] [1200/1251] eta: 0:00:32 lr: 0.000848 loss: 3.5743 (3.5933) grad_norm: 1.0977 (1.1476) time: 0.6248 [2021-03-26 15:42:11 swin_base_patch4_window7_224] INFO: Epoch: [76] [1210/1251] eta: 0:00:25 lr: 0.000848 loss: 3.5743 (3.5942) grad_norm: 1.1013 (1.1475) time: 0.6315 [2021-03-26 15:42:17 swin_base_patch4_window7_224] INFO: Epoch: [76] [1220/1251] eta: 0:00:19 lr: 0.000848 loss: 3.5047 (3.5934) grad_norm: 1.1081 (1.1472) time: 0.6254 [2021-03-26 15:42:24 swin_base_patch4_window7_224] INFO: Epoch: [76] [1230/1251] eta: 0:00:13 lr: 0.000848 loss: 3.5634 (3.5954) grad_norm: 1.1081 (1.1472) time: 0.6262 [2021-03-26 15:42:30 swin_base_patch4_window7_224] INFO: Epoch: [76] [1240/1251] eta: 0:00:06 lr: 0.000848 loss: 3.5634 (3.5939) grad_norm: 1.1088 (1.1473) time: 0.6295 [2021-03-26 15:42:36 swin_base_patch4_window7_224] INFO: Epoch: [76] [1250/1251] eta: 0:00:00 lr: 0.000848 loss: 3.4187 (3.5929) grad_norm: 1.1664 (1.1475) time: 0.6186 [2021-03-26 15:42:44 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:55 loss: 1.2533 (1.2533) acc1: 71.8750 (71.8750) acc5: 89.0625 (89.0625) [2021-03-26 15:42:46 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.0626 (1.1260) acc1: 76.5625 (74.0057) acc5: 92.1875 (92.4716) [2021-03-26 15:42:47 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0524 (1.0488) acc1: 76.5625 (76.1905) acc5: 93.7500 (93.7500) [2021-03-26 15:42:50 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0804 (1.0753) acc1: 75.0000 (74.8992) acc5: 92.1875 (93.2964) [2021-03-26 15:42:52 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0714 (1.0819) acc1: 73.4375 (74.9238) acc5: 92.1875 (93.3308) [2021-03-26 15:42:53 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1550 (1.1000) acc1: 73.4375 (74.4320) acc5: 92.1875 (93.1200) [2021-03-26 15:42:57 swin_base_patch4_window7_224] INFO: * Acc@1 75.104 Acc@5 93.010 loss 1.074 [2021-03-26 15:42:57 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.1% [2021-03-26 15:42:57 swin_base_patch4_window7_224] INFO: Max accuracy: 75.22% [2021-03-26 15:43:02 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 0/1251] eta: 1:34:05 lr: 0.000848 loss: 2.6978 (2.6978) grad_norm: 1.2544 (1.2544) time: 4.5126 [2021-03-26 15:43:08 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 10/1251] eta: 0:20:31 lr: 0.000848 loss: 3.6342 (3.5237) grad_norm: 1.1465 (1.1668) time: 0.9924 [2021-03-26 15:43:14 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 20/1251] eta: 0:16:47 lr: 0.000848 loss: 3.4958 (3.4181) grad_norm: 1.0884 (1.1462) time: 0.6335 [2021-03-26 15:43:21 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 30/1251] eta: 0:15:25 lr: 0.000848 loss: 3.3275 (3.3962) grad_norm: 1.1011 (1.1626) time: 0.6288 [2021-03-26 15:43:27 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 40/1251] eta: 0:14:42 lr: 0.000847 loss: 3.6391 (3.4785) grad_norm: 1.1011 (1.1752) time: 0.6346 [2021-03-26 15:43:33 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 50/1251] eta: 0:14:12 lr: 0.000847 loss: 3.7129 (3.5004) grad_norm: 1.0810 (1.1599) time: 0.6362 [2021-03-26 15:43:40 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 60/1251] eta: 0:13:51 lr: 0.000847 loss: 3.5546 (3.4853) grad_norm: 1.0529 (1.1552) time: 0.6345 [2021-03-26 15:43:46 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 70/1251] eta: 0:13:33 lr: 0.000847 loss: 3.6865 (3.5326) grad_norm: 1.2188 (1.1693) time: 0.6340 [2021-03-26 15:43:52 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 80/1251] eta: 0:13:17 lr: 0.000847 loss: 3.8247 (3.5633) grad_norm: 1.2103 (1.1655) time: 0.6295 [2021-03-26 15:43:59 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 90/1251] eta: 0:13:03 lr: 0.000847 loss: 3.8725 (3.5998) grad_norm: 1.0700 (1.1619) time: 0.6270 [2021-03-26 15:44:05 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 100/1251] eta: 0:12:51 lr: 0.000847 loss: 3.9402 (3.6190) grad_norm: 1.0700 (1.1603) time: 0.6255 [2021-03-26 15:44:11 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 110/1251] eta: 0:12:39 lr: 0.000847 loss: 3.7986 (3.6198) grad_norm: 1.0705 (1.1524) time: 0.6217 [2021-03-26 15:44:17 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 120/1251] eta: 0:12:29 lr: 0.000847 loss: 3.5609 (3.6060) grad_norm: 1.0766 (1.1462) time: 0.6253 [2021-03-26 15:44:24 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 130/1251] eta: 0:12:19 lr: 0.000847 loss: 3.5609 (3.6179) grad_norm: 1.1361 (1.1539) time: 0.6300 [2021-03-26 15:44:30 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 140/1251] eta: 0:12:11 lr: 0.000847 loss: 3.6582 (3.6346) grad_norm: 1.1819 (1.1540) time: 0.6316 [2021-03-26 15:44:36 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 150/1251] eta: 0:12:02 lr: 0.000847 loss: 3.6342 (3.6293) grad_norm: 1.1535 (1.1569) time: 0.6333 [2021-03-26 15:44:43 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 160/1251] eta: 0:11:54 lr: 0.000847 loss: 3.6850 (3.6208) grad_norm: 1.1633 (1.1589) time: 0.6322 [2021-03-26 15:44:49 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 170/1251] eta: 0:11:46 lr: 0.000847 loss: 3.7577 (3.6287) grad_norm: 1.1097 (1.1551) time: 0.6315 [2021-03-26 15:44:55 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 180/1251] eta: 0:11:38 lr: 0.000847 loss: 3.9553 (3.6328) grad_norm: 1.1096 (1.1543) time: 0.6331 [2021-03-26 15:45:02 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 190/1251] eta: 0:11:32 lr: 0.000847 loss: 3.8631 (3.6375) grad_norm: 1.1317 (1.1577) time: 0.6412 [2021-03-26 15:45:08 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 200/1251] eta: 0:11:25 lr: 0.000847 loss: 3.6801 (3.6309) grad_norm: 1.1897 (1.1600) time: 0.6478 [2021-03-26 15:45:14 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 210/1251] eta: 0:11:17 lr: 0.000847 loss: 3.6587 (3.6304) grad_norm: 1.1666 (1.1562) time: 0.6364 [2021-03-26 15:45:21 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 220/1251] eta: 0:11:10 lr: 0.000847 loss: 3.7066 (3.6224) grad_norm: 1.1226 (1.1573) time: 0.6277 [2021-03-26 15:45:27 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 230/1251] eta: 0:11:02 lr: 0.000847 loss: 3.6260 (3.6193) grad_norm: 1.1369 (1.1563) time: 0.6316 [2021-03-26 15:45:33 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 240/1251] eta: 0:10:55 lr: 0.000847 loss: 3.7337 (3.6255) grad_norm: 1.0920 (1.1552) time: 0.6292 [2021-03-26 15:45:40 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 250/1251] eta: 0:10:48 lr: 0.000847 loss: 3.6347 (3.6213) grad_norm: 1.0804 (1.1549) time: 0.6273 [2021-03-26 15:45:46 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 260/1251] eta: 0:10:40 lr: 0.000847 loss: 3.6132 (3.6286) grad_norm: 1.1190 (1.1563) time: 0.6275 [2021-03-26 15:45:52 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 270/1251] eta: 0:10:33 lr: 0.000847 loss: 3.7392 (3.6264) grad_norm: 1.2290 (1.1601) time: 0.6277 [2021-03-26 15:45:58 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 280/1251] eta: 0:10:26 lr: 0.000847 loss: 3.6287 (3.6295) grad_norm: 1.1808 (1.1599) time: 0.6272 [2021-03-26 15:46:05 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 290/1251] eta: 0:10:19 lr: 0.000847 loss: 3.5433 (3.6185) grad_norm: 1.1502 (1.1602) time: 0.6251 [2021-03-26 15:46:11 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 300/1251] eta: 0:10:12 lr: 0.000847 loss: 3.5433 (3.6225) grad_norm: 1.1502 (1.1605) time: 0.6275 [2021-03-26 15:46:17 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 310/1251] eta: 0:10:05 lr: 0.000847 loss: 3.6940 (3.6193) grad_norm: 1.0977 (1.1618) time: 0.6260 [2021-03-26 15:46:24 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 320/1251] eta: 0:09:58 lr: 0.000847 loss: 3.5534 (3.6209) grad_norm: 1.1218 (1.1633) time: 0.6280 [2021-03-26 15:46:30 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 330/1251] eta: 0:09:51 lr: 0.000847 loss: 3.6778 (3.6166) grad_norm: 1.1644 (1.1637) time: 0.6298 [2021-03-26 15:46:36 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 340/1251] eta: 0:09:44 lr: 0.000847 loss: 3.8344 (3.6261) grad_norm: 1.1915 (1.1645) time: 0.6270 [2021-03-26 15:46:42 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 350/1251] eta: 0:09:38 lr: 0.000847 loss: 3.8724 (3.6226) grad_norm: 1.1461 (1.1636) time: 0.6294 [2021-03-26 15:46:49 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 360/1251] eta: 0:09:31 lr: 0.000847 loss: 3.5760 (3.6187) grad_norm: 1.1728 (1.1642) time: 0.6353 [2021-03-26 15:46:55 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 370/1251] eta: 0:09:25 lr: 0.000847 loss: 3.4946 (3.6154) grad_norm: 1.2045 (inf) time: 0.6371 [2021-03-26 15:47:01 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 380/1251] eta: 0:09:18 lr: 0.000846 loss: 3.6952 (3.6237) grad_norm: 1.1571 (inf) time: 0.6254 [2021-03-26 15:47:08 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 390/1251] eta: 0:09:11 lr: 0.000846 loss: 3.8051 (3.6228) grad_norm: 1.0864 (inf) time: 0.6261 [2021-03-26 15:47:14 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 400/1251] eta: 0:09:05 lr: 0.000846 loss: 3.6338 (3.6194) grad_norm: 1.1441 (inf) time: 0.6339 [2021-03-26 15:47:20 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 410/1251] eta: 0:08:58 lr: 0.000846 loss: 3.6963 (3.6223) grad_norm: 1.1535 (inf) time: 0.6256 [2021-03-26 15:47:27 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 420/1251] eta: 0:08:51 lr: 0.000846 loss: 3.7199 (3.6227) grad_norm: 1.1156 (inf) time: 0.6248 [2021-03-26 15:47:33 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 430/1251] eta: 0:08:45 lr: 0.000846 loss: 3.8171 (3.6282) grad_norm: 1.1132 (inf) time: 0.6307 [2021-03-26 15:47:39 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 440/1251] eta: 0:08:38 lr: 0.000846 loss: 3.6884 (3.6258) grad_norm: 1.1648 (inf) time: 0.6266 [2021-03-26 15:47:45 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 450/1251] eta: 0:08:31 lr: 0.000846 loss: 3.6542 (3.6239) grad_norm: 1.1552 (inf) time: 0.6252 [2021-03-26 15:47:52 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 460/1251] eta: 0:08:25 lr: 0.000846 loss: 3.6542 (3.6246) grad_norm: 1.1012 (inf) time: 0.6316 [2021-03-26 15:47:58 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 470/1251] eta: 0:08:18 lr: 0.000846 loss: 3.6983 (3.6257) grad_norm: 1.1060 (inf) time: 0.6312 [2021-03-26 15:48:04 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 480/1251] eta: 0:08:12 lr: 0.000846 loss: 3.5829 (3.6215) grad_norm: 1.2100 (inf) time: 0.6314 [2021-03-26 15:48:11 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 490/1251] eta: 0:08:05 lr: 0.000846 loss: 3.3564 (3.6210) grad_norm: 1.1080 (inf) time: 0.6279 [2021-03-26 15:48:17 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 500/1251] eta: 0:07:59 lr: 0.000846 loss: 3.5526 (3.6194) grad_norm: 1.0844 (inf) time: 0.6221 [2021-03-26 15:48:23 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 510/1251] eta: 0:07:52 lr: 0.000846 loss: 3.7146 (3.6197) grad_norm: 1.0696 (inf) time: 0.6286 [2021-03-26 15:48:29 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 520/1251] eta: 0:07:46 lr: 0.000846 loss: 3.5850 (3.6141) grad_norm: 1.0929 (inf) time: 0.6301 [2021-03-26 15:48:36 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 530/1251] eta: 0:07:39 lr: 0.000846 loss: 3.3748 (3.6107) grad_norm: 1.1369 (inf) time: 0.6276 [2021-03-26 15:48:42 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 540/1251] eta: 0:07:33 lr: 0.000846 loss: 3.3748 (3.6078) grad_norm: 1.1340 (inf) time: 0.6264 [2021-03-26 15:48:48 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 550/1251] eta: 0:07:26 lr: 0.000846 loss: 3.7666 (3.6110) grad_norm: 1.1249 (inf) time: 0.6309 [2021-03-26 15:48:55 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 560/1251] eta: 0:07:20 lr: 0.000846 loss: 3.7163 (3.6103) grad_norm: 1.0965 (inf) time: 0.6319 [2021-03-26 15:49:01 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 570/1251] eta: 0:07:13 lr: 0.000846 loss: 3.6582 (3.6102) grad_norm: 1.0550 (inf) time: 0.6272 [2021-03-26 15:49:07 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 580/1251] eta: 0:07:07 lr: 0.000846 loss: 3.5916 (3.6104) grad_norm: 1.1025 (inf) time: 0.6321 [2021-03-26 15:49:13 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 590/1251] eta: 0:07:00 lr: 0.000846 loss: 3.5916 (3.6089) grad_norm: 1.1110 (inf) time: 0.6312 [2021-03-26 15:49:20 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 600/1251] eta: 0:06:54 lr: 0.000846 loss: 3.7352 (3.6126) grad_norm: 1.1035 (inf) time: 0.6283 [2021-03-26 15:49:26 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 610/1251] eta: 0:06:47 lr: 0.000846 loss: 3.7079 (3.6112) grad_norm: 1.1358 (inf) time: 0.6266 [2021-03-26 15:49:32 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 620/1251] eta: 0:06:41 lr: 0.000846 loss: 3.6355 (3.6113) grad_norm: 1.0888 (inf) time: 0.6216 [2021-03-26 15:49:38 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 630/1251] eta: 0:06:34 lr: 0.000846 loss: 3.6355 (3.6101) grad_norm: 1.0677 (inf) time: 0.6232 [2021-03-26 15:49:45 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 640/1251] eta: 0:06:28 lr: 0.000846 loss: 3.6097 (3.6066) grad_norm: 1.1030 (inf) time: 0.6296 [2021-03-26 15:49:51 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 650/1251] eta: 0:06:22 lr: 0.000846 loss: 3.6336 (3.6044) grad_norm: 1.1370 (inf) time: 0.6368 [2021-03-26 15:49:58 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 660/1251] eta: 0:06:15 lr: 0.000846 loss: 3.7587 (3.6036) grad_norm: 1.1510 (inf) time: 0.6356 [2021-03-26 15:50:04 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 670/1251] eta: 0:06:09 lr: 0.000846 loss: 3.6012 (3.6024) grad_norm: 1.1024 (inf) time: 0.6281 [2021-03-26 15:50:10 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 680/1251] eta: 0:06:02 lr: 0.000846 loss: 3.5130 (3.6031) grad_norm: 1.0972 (inf) time: 0.6290 [2021-03-26 15:50:16 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 690/1251] eta: 0:05:56 lr: 0.000846 loss: 3.6954 (3.6041) grad_norm: 1.0816 (inf) time: 0.6351 [2021-03-26 15:50:23 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 700/1251] eta: 0:05:50 lr: 0.000846 loss: 3.7741 (3.6056) grad_norm: 1.0897 (inf) time: 0.6340 [2021-03-26 15:50:29 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 710/1251] eta: 0:05:43 lr: 0.000845 loss: 3.7872 (3.6070) grad_norm: 1.0853 (inf) time: 0.6329 [2021-03-26 15:50:35 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 720/1251] eta: 0:05:37 lr: 0.000845 loss: 3.6877 (3.6049) grad_norm: 1.0958 (inf) time: 0.6335 [2021-03-26 15:50:42 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 730/1251] eta: 0:05:31 lr: 0.000845 loss: 3.6877 (3.6061) grad_norm: 1.1174 (inf) time: 0.6302 [2021-03-26 15:50:48 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 740/1251] eta: 0:05:24 lr: 0.000845 loss: 4.0204 (3.6104) grad_norm: 1.0903 (inf) time: 0.6363 [2021-03-26 15:50:55 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 750/1251] eta: 0:05:18 lr: 0.000845 loss: 3.7671 (3.6083) grad_norm: 1.1422 (inf) time: 0.6463 [2021-03-26 15:51:01 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 760/1251] eta: 0:05:12 lr: 0.000845 loss: 3.5356 (3.6072) grad_norm: 1.1251 (inf) time: 0.6420 [2021-03-26 15:51:07 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 770/1251] eta: 0:05:05 lr: 0.000845 loss: 3.6437 (3.6067) grad_norm: 1.1060 (inf) time: 0.6379 [2021-03-26 15:51:14 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 780/1251] eta: 0:04:59 lr: 0.000845 loss: 3.6437 (3.6079) grad_norm: 1.1060 (inf) time: 0.6355 [2021-03-26 15:51:20 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 790/1251] eta: 0:04:53 lr: 0.000845 loss: 3.5623 (3.6077) grad_norm: 1.0908 (inf) time: 0.6280 [2021-03-26 15:51:26 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 800/1251] eta: 0:04:46 lr: 0.000845 loss: 3.5124 (3.6068) grad_norm: 1.0873 (inf) time: 0.6302 [2021-03-26 15:51:33 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 810/1251] eta: 0:04:40 lr: 0.000845 loss: 3.6853 (3.6062) grad_norm: 1.0784 (inf) time: 0.6326 [2021-03-26 15:51:39 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 820/1251] eta: 0:04:33 lr: 0.000845 loss: 3.7703 (3.6076) grad_norm: 1.1348 (inf) time: 0.6321 [2021-03-26 15:51:45 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 830/1251] eta: 0:04:27 lr: 0.000845 loss: 3.6065 (3.6064) grad_norm: 1.1597 (inf) time: 0.6322 [2021-03-26 15:51:52 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 840/1251] eta: 0:04:21 lr: 0.000845 loss: 3.5531 (3.6076) grad_norm: 1.1192 (inf) time: 0.6308 [2021-03-26 15:51:58 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 850/1251] eta: 0:04:14 lr: 0.000845 loss: 3.5644 (3.6067) grad_norm: 1.1134 (inf) time: 0.6275 [2021-03-26 15:52:04 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 860/1251] eta: 0:04:08 lr: 0.000845 loss: 3.7591 (3.6070) grad_norm: 1.1554 (inf) time: 0.6279 [2021-03-26 15:52:11 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 870/1251] eta: 0:04:02 lr: 0.000845 loss: 3.5862 (3.6058) grad_norm: 1.1714 (inf) time: 0.6344 [2021-03-26 15:52:17 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 880/1251] eta: 0:03:55 lr: 0.000845 loss: 3.7037 (3.6051) grad_norm: 1.0988 (inf) time: 0.6333 [2021-03-26 15:52:23 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 890/1251] eta: 0:03:49 lr: 0.000845 loss: 3.7345 (3.6055) grad_norm: 1.1440 (inf) time: 0.6284 [2021-03-26 15:52:29 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 900/1251] eta: 0:03:42 lr: 0.000845 loss: 3.7958 (3.6044) grad_norm: 1.1116 (inf) time: 0.6275 [2021-03-26 15:52:36 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 910/1251] eta: 0:03:36 lr: 0.000845 loss: 3.7951 (3.6051) grad_norm: 1.0799 (inf) time: 0.6248 [2021-03-26 15:52:42 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 920/1251] eta: 0:03:30 lr: 0.000845 loss: 3.6218 (3.6045) grad_norm: 1.0885 (inf) time: 0.6254 [2021-03-26 15:52:48 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 930/1251] eta: 0:03:23 lr: 0.000845 loss: 3.6893 (3.6049) grad_norm: 1.0977 (inf) time: 0.6304 [2021-03-26 15:52:54 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 940/1251] eta: 0:03:17 lr: 0.000845 loss: 3.6231 (3.6019) grad_norm: 1.1552 (inf) time: 0.6294 [2021-03-26 15:53:01 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 950/1251] eta: 0:03:11 lr: 0.000845 loss: 3.7105 (3.6037) grad_norm: 1.1225 (inf) time: 0.6339 [2021-03-26 15:53:07 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 960/1251] eta: 0:03:04 lr: 0.000845 loss: 3.8023 (3.6025) grad_norm: 1.0773 (inf) time: 0.6319 [2021-03-26 15:53:13 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 970/1251] eta: 0:02:58 lr: 0.000845 loss: 3.8025 (3.6052) grad_norm: 1.1054 (inf) time: 0.6229 [2021-03-26 15:53:20 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 980/1251] eta: 0:02:51 lr: 0.000845 loss: 3.8058 (3.6057) grad_norm: 1.0744 (inf) time: 0.6269 [2021-03-26 15:53:26 swin_base_patch4_window7_224] INFO: Epoch: [77] [ 990/1251] eta: 0:02:45 lr: 0.000845 loss: 3.6032 (3.6049) grad_norm: 1.0744 (inf) time: 0.6264 [2021-03-26 15:53:32 swin_base_patch4_window7_224] INFO: Epoch: [77] [1000/1251] eta: 0:02:39 lr: 0.000845 loss: 3.3860 (3.6036) grad_norm: 1.1113 (inf) time: 0.6204 [2021-03-26 15:53:38 swin_base_patch4_window7_224] INFO: Epoch: [77] [1010/1251] eta: 0:02:32 lr: 0.000845 loss: 3.8070 (3.6052) grad_norm: 1.1113 (inf) time: 0.6258 [2021-03-26 15:53:45 swin_base_patch4_window7_224] INFO: Epoch: [77] [1020/1251] eta: 0:02:26 lr: 0.000845 loss: 3.8523 (3.6064) grad_norm: 1.0822 (inf) time: 0.6272 [2021-03-26 15:53:51 swin_base_patch4_window7_224] INFO: Epoch: [77] [1030/1251] eta: 0:02:20 lr: 0.000845 loss: 3.8944 (3.6096) grad_norm: 1.1596 (inf) time: 0.6214 [2021-03-26 15:53:57 swin_base_patch4_window7_224] INFO: Epoch: [77] [1040/1251] eta: 0:02:13 lr: 0.000844 loss: 3.7856 (3.6084) grad_norm: 1.1484 (inf) time: 0.6296 [2021-03-26 15:54:03 swin_base_patch4_window7_224] INFO: Epoch: [77] [1050/1251] eta: 0:02:07 lr: 0.000844 loss: 3.7005 (3.6076) grad_norm: 1.1484 (inf) time: 0.6305 [2021-03-26 15:54:10 swin_base_patch4_window7_224] INFO: Epoch: [77] [1060/1251] eta: 0:02:01 lr: 0.000844 loss: 3.7908 (3.6067) grad_norm: 1.1679 (inf) time: 0.6249 [2021-03-26 15:54:16 swin_base_patch4_window7_224] INFO: Epoch: [77] [1070/1251] eta: 0:01:54 lr: 0.000844 loss: 3.9003 (3.6099) grad_norm: 1.1973 (inf) time: 0.6287 [2021-03-26 15:54:22 swin_base_patch4_window7_224] INFO: Epoch: [77] [1080/1251] eta: 0:01:48 lr: 0.000844 loss: 3.7599 (3.6084) grad_norm: 1.1876 (inf) time: 0.6326 [2021-03-26 15:54:29 swin_base_patch4_window7_224] INFO: Epoch: [77] [1090/1251] eta: 0:01:42 lr: 0.000844 loss: 3.4585 (3.6079) grad_norm: 1.1780 (inf) time: 0.6232 [2021-03-26 15:54:35 swin_base_patch4_window7_224] INFO: Epoch: [77] [1100/1251] eta: 0:01:35 lr: 0.000844 loss: 3.4585 (3.6066) grad_norm: 1.1600 (inf) time: 0.6241 [2021-03-26 15:54:41 swin_base_patch4_window7_224] INFO: Epoch: [77] [1110/1251] eta: 0:01:29 lr: 0.000844 loss: 3.7165 (3.6074) grad_norm: 1.1561 (inf) time: 0.6296 [2021-03-26 15:54:47 swin_base_patch4_window7_224] INFO: Epoch: [77] [1120/1251] eta: 0:01:22 lr: 0.000844 loss: 3.7365 (3.6074) grad_norm: 1.1370 (inf) time: 0.6203 [2021-03-26 15:54:54 swin_base_patch4_window7_224] INFO: Epoch: [77] [1130/1251] eta: 0:01:16 lr: 0.000844 loss: 3.5457 (3.6060) grad_norm: 1.2269 (inf) time: 0.6254 [2021-03-26 15:55:00 swin_base_patch4_window7_224] INFO: Epoch: [77] [1140/1251] eta: 0:01:10 lr: 0.000844 loss: 3.3921 (3.6043) grad_norm: 1.1927 (inf) time: 0.6335 [2021-03-26 15:55:06 swin_base_patch4_window7_224] INFO: Epoch: [77] [1150/1251] eta: 0:01:03 lr: 0.000844 loss: 3.5339 (3.6038) grad_norm: 1.1039 (inf) time: 0.6353 [2021-03-26 15:55:13 swin_base_patch4_window7_224] INFO: Epoch: [77] [1160/1251] eta: 0:00:57 lr: 0.000844 loss: 3.4789 (3.6027) grad_norm: 1.1785 (inf) time: 0.6321 [2021-03-26 15:55:19 swin_base_patch4_window7_224] INFO: Epoch: [77] [1170/1251] eta: 0:00:51 lr: 0.000844 loss: 3.4169 (3.5998) grad_norm: 1.1438 (inf) time: 0.6290 [2021-03-26 15:55:25 swin_base_patch4_window7_224] INFO: Epoch: [77] [1180/1251] eta: 0:00:44 lr: 0.000844 loss: 3.4958 (3.5983) grad_norm: 1.1058 (inf) time: 0.6277 [2021-03-26 15:55:32 swin_base_patch4_window7_224] INFO: Epoch: [77] [1190/1251] eta: 0:00:38 lr: 0.000844 loss: 3.4958 (3.5967) grad_norm: 1.1323 (inf) time: 0.6311 [2021-03-26 15:55:38 swin_base_patch4_window7_224] INFO: Epoch: [77] [1200/1251] eta: 0:00:32 lr: 0.000844 loss: 3.2287 (3.5954) grad_norm: 1.1486 (inf) time: 0.6363 [2021-03-26 15:55:44 swin_base_patch4_window7_224] INFO: Epoch: [77] [1210/1251] eta: 0:00:25 lr: 0.000844 loss: 3.7603 (3.5969) grad_norm: 1.1888 (inf) time: 0.6298 [2021-03-26 15:55:50 swin_base_patch4_window7_224] INFO: Epoch: [77] [1220/1251] eta: 0:00:19 lr: 0.000844 loss: 3.8448 (3.5978) grad_norm: 1.1089 (inf) time: 0.6228 [2021-03-26 15:55:57 swin_base_patch4_window7_224] INFO: Epoch: [77] [1230/1251] eta: 0:00:13 lr: 0.000844 loss: 3.8448 (3.5990) grad_norm: 1.0955 (inf) time: 0.6228 [2021-03-26 15:56:03 swin_base_patch4_window7_224] INFO: Epoch: [77] [1240/1251] eta: 0:00:06 lr: 0.000844 loss: 3.7547 (3.5985) grad_norm: 1.0334 (inf) time: 0.6257 [2021-03-26 15:56:09 swin_base_patch4_window7_224] INFO: Epoch: [77] [1250/1251] eta: 0:00:00 lr: 0.000844 loss: 3.7363 (3.5995) grad_norm: 1.0407 (inf) time: 0.6262 [2021-03-26 15:56:15 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:37 loss: 1.0321 (1.0321) acc1: 75.0000 (75.0000) acc5: 90.6250 (90.6250) [2021-03-26 15:56:17 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.0571 (1.0417) acc1: 73.4375 (73.8636) acc5: 93.7500 (93.1818) [2021-03-26 15:56:20 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0403 (1.0397) acc1: 75.0000 (74.9256) acc5: 93.7500 (92.7827) [2021-03-26 15:56:22 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9671 (1.0192) acc1: 75.0000 (75.1008) acc5: 93.7500 (93.0444) [2021-03-26 15:56:24 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0492 (1.0458) acc1: 73.4375 (74.5427) acc5: 93.7500 (92.9116) [2021-03-26 15:56:25 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0492 (1.0468) acc1: 71.8750 (74.1120) acc5: 93.7500 (93.0880) [2021-03-26 15:56:28 swin_base_patch4_window7_224] INFO: * Acc@1 75.482 Acc@5 93.096 loss 1.029 [2021-03-26 15:56:28 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.5% [2021-03-26 15:56:28 swin_base_patch4_window7_224] INFO: Max accuracy: 75.48% [2021-03-26 15:56:33 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 0/1251] eta: 1:30:40 lr: 0.000844 loss: 3.9973 (3.9973) grad_norm: 1.0786 (1.0786) time: 4.3490 [2021-03-26 15:56:39 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 10/1251] eta: 0:20:05 lr: 0.000844 loss: 3.9973 (3.9094) grad_norm: 1.1084 (1.1653) time: 0.9711 [2021-03-26 15:56:45 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 20/1251] eta: 0:16:30 lr: 0.000844 loss: 3.8722 (3.8677) grad_norm: 1.0981 (1.1111) time: 0.6277 [2021-03-26 15:56:51 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 30/1251] eta: 0:15:13 lr: 0.000844 loss: 3.7420 (3.7555) grad_norm: 1.0888 (1.1130) time: 0.6250 [2021-03-26 15:56:58 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 40/1251] eta: 0:14:31 lr: 0.000844 loss: 3.5890 (3.7494) grad_norm: 1.1085 (1.1315) time: 0.6299 [2021-03-26 15:57:04 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 50/1251] eta: 0:14:05 lr: 0.000844 loss: 3.5890 (3.6724) grad_norm: 1.1363 (1.1512) time: 0.6372 [2021-03-26 15:57:10 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 60/1251] eta: 0:13:44 lr: 0.000844 loss: 3.3504 (3.5898) grad_norm: 1.1617 (1.1547) time: 0.6369 [2021-03-26 15:57:17 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 70/1251] eta: 0:13:28 lr: 0.000844 loss: 3.2727 (3.5483) grad_norm: 1.1389 (1.1507) time: 0.6325 [2021-03-26 15:57:23 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 80/1251] eta: 0:13:13 lr: 0.000844 loss: 3.4727 (3.5503) grad_norm: 1.1156 (1.1491) time: 0.6313 [2021-03-26 15:57:29 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 90/1251] eta: 0:12:59 lr: 0.000844 loss: 3.6655 (3.5652) grad_norm: 1.1342 (1.1542) time: 0.6242 [2021-03-26 15:57:36 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 100/1251] eta: 0:12:47 lr: 0.000844 loss: 3.8511 (3.5973) grad_norm: 1.1665 (1.1587) time: 0.6226 [2021-03-26 15:57:42 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 110/1251] eta: 0:12:36 lr: 0.000844 loss: 3.8511 (3.5821) grad_norm: 1.1202 (1.1685) time: 0.6272 [2021-03-26 15:57:48 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 120/1251] eta: 0:12:28 lr: 0.000843 loss: 3.5197 (3.5790) grad_norm: 1.1186 (1.1667) time: 0.6359 [2021-03-26 15:57:55 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 130/1251] eta: 0:12:18 lr: 0.000843 loss: 3.7101 (3.5972) grad_norm: 1.0965 (1.1627) time: 0.6364 [2021-03-26 15:58:01 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 140/1251] eta: 0:12:10 lr: 0.000843 loss: 3.6763 (3.6000) grad_norm: 1.0965 (1.1609) time: 0.6310 [2021-03-26 15:58:07 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 150/1251] eta: 0:12:01 lr: 0.000843 loss: 3.6448 (3.5966) grad_norm: 1.1541 (1.1583) time: 0.6305 [2021-03-26 15:58:14 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 160/1251] eta: 0:11:54 lr: 0.000843 loss: 3.7528 (3.6115) grad_norm: 1.1744 (1.1611) time: 0.6375 [2021-03-26 15:58:20 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 170/1251] eta: 0:11:45 lr: 0.000843 loss: 3.6168 (3.5940) grad_norm: 1.1459 (1.1589) time: 0.6330 [2021-03-26 15:58:26 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 180/1251] eta: 0:11:36 lr: 0.000843 loss: 3.5500 (3.5906) grad_norm: 1.0988 (1.1581) time: 0.6181 [2021-03-26 15:58:32 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 190/1251] eta: 0:11:29 lr: 0.000843 loss: 3.1434 (3.5481) grad_norm: 1.0988 (1.1560) time: 0.6223 [2021-03-26 15:58:39 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 200/1251] eta: 0:11:21 lr: 0.000843 loss: 3.1755 (3.5573) grad_norm: 1.0991 (1.1553) time: 0.6298 [2021-03-26 15:58:45 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 210/1251] eta: 0:11:14 lr: 0.000843 loss: 3.7080 (3.5504) grad_norm: 1.1077 (1.1533) time: 0.6293 [2021-03-26 15:58:51 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 220/1251] eta: 0:11:06 lr: 0.000843 loss: 3.5980 (3.5519) grad_norm: 1.1459 (1.1536) time: 0.6256 [2021-03-26 15:58:57 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 230/1251] eta: 0:10:58 lr: 0.000843 loss: 3.7021 (3.5569) grad_norm: 1.1365 (1.1518) time: 0.6213 [2021-03-26 15:59:04 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 240/1251] eta: 0:10:51 lr: 0.000843 loss: 3.6053 (3.5550) grad_norm: 1.1186 (1.1510) time: 0.6229 [2021-03-26 15:59:10 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 250/1251] eta: 0:10:45 lr: 0.000843 loss: 3.5008 (3.5494) grad_norm: 1.1454 (1.1508) time: 0.6338 [2021-03-26 15:59:16 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 260/1251] eta: 0:10:37 lr: 0.000843 loss: 3.2832 (3.5382) grad_norm: 1.2036 (1.1562) time: 0.6335 [2021-03-26 15:59:23 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 270/1251] eta: 0:10:31 lr: 0.000843 loss: 3.5726 (3.5488) grad_norm: 1.2036 (1.1580) time: 0.6296 [2021-03-26 15:59:29 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 280/1251] eta: 0:10:24 lr: 0.000843 loss: 3.8676 (3.5531) grad_norm: 1.2107 (1.1623) time: 0.6289 [2021-03-26 15:59:35 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 290/1251] eta: 0:10:17 lr: 0.000843 loss: 3.6278 (3.5552) grad_norm: 1.1952 (1.1635) time: 0.6296 [2021-03-26 15:59:41 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 300/1251] eta: 0:10:10 lr: 0.000843 loss: 3.8034 (3.5594) grad_norm: 1.1062 (1.1630) time: 0.6296 [2021-03-26 15:59:48 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 310/1251] eta: 0:10:03 lr: 0.000843 loss: 3.6128 (3.5596) grad_norm: 1.1242 (1.1616) time: 0.6213 [2021-03-26 15:59:54 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 320/1251] eta: 0:09:56 lr: 0.000843 loss: 3.5371 (3.5593) grad_norm: 1.1449 (1.1613) time: 0.6245 [2021-03-26 16:00:00 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 330/1251] eta: 0:09:49 lr: 0.000843 loss: 3.5184 (3.5515) grad_norm: 1.1613 (1.1622) time: 0.6300 [2021-03-26 16:00:06 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 340/1251] eta: 0:09:42 lr: 0.000843 loss: 3.6060 (3.5523) grad_norm: 1.1065 (1.1593) time: 0.6251 [2021-03-26 16:00:13 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 350/1251] eta: 0:09:36 lr: 0.000843 loss: 3.7627 (3.5569) grad_norm: 1.1126 (1.1615) time: 0.6285 [2021-03-26 16:00:19 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 360/1251] eta: 0:09:29 lr: 0.000843 loss: 3.7760 (3.5602) grad_norm: 1.1591 (1.1603) time: 0.6350 [2021-03-26 16:00:25 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 370/1251] eta: 0:09:22 lr: 0.000843 loss: 3.8007 (3.5705) grad_norm: 1.0813 (1.1598) time: 0.6254 [2021-03-26 16:00:32 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 380/1251] eta: 0:09:16 lr: 0.000843 loss: 3.8007 (3.5717) grad_norm: 1.0813 (1.1592) time: 0.6222 [2021-03-26 16:00:38 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 390/1251] eta: 0:09:09 lr: 0.000843 loss: 3.7252 (3.5693) grad_norm: 1.1216 (1.1591) time: 0.6278 [2021-03-26 16:00:44 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 400/1251] eta: 0:09:02 lr: 0.000843 loss: 3.6051 (3.5696) grad_norm: 1.0973 (1.1583) time: 0.6251 [2021-03-26 16:00:50 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 410/1251] eta: 0:08:56 lr: 0.000843 loss: 3.6051 (3.5704) grad_norm: 1.0813 (1.1565) time: 0.6217 [2021-03-26 16:00:57 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 420/1251] eta: 0:08:49 lr: 0.000843 loss: 3.8298 (3.5792) grad_norm: 1.0625 (1.1548) time: 0.6209 [2021-03-26 16:01:03 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 430/1251] eta: 0:08:42 lr: 0.000843 loss: 3.7102 (3.5726) grad_norm: 1.0850 (1.1533) time: 0.6233 [2021-03-26 16:01:09 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 440/1251] eta: 0:08:36 lr: 0.000843 loss: 3.5514 (3.5736) grad_norm: 1.1240 (1.1565) time: 0.6315 [2021-03-26 16:01:15 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 450/1251] eta: 0:08:30 lr: 0.000842 loss: 3.5677 (3.5677) grad_norm: 1.1741 (1.1551) time: 0.6341 [2021-03-26 16:01:22 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 460/1251] eta: 0:08:23 lr: 0.000842 loss: 3.5275 (3.5717) grad_norm: 1.1467 (1.1583) time: 0.6355 [2021-03-26 16:01:28 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 470/1251] eta: 0:08:17 lr: 0.000842 loss: 3.7084 (3.5701) grad_norm: 1.1467 (1.1573) time: 0.6328 [2021-03-26 16:01:34 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 480/1251] eta: 0:08:10 lr: 0.000842 loss: 3.5735 (3.5707) grad_norm: 1.0963 (1.1560) time: 0.6268 [2021-03-26 16:01:41 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 490/1251] eta: 0:08:04 lr: 0.000842 loss: 3.7205 (3.5753) grad_norm: 1.0634 (1.1549) time: 0.6307 [2021-03-26 16:01:47 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 500/1251] eta: 0:07:57 lr: 0.000842 loss: 3.9351 (3.5800) grad_norm: 1.0634 (1.1542) time: 0.6355 [2021-03-26 16:01:53 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 510/1251] eta: 0:07:51 lr: 0.000842 loss: 3.8010 (3.5803) grad_norm: 1.0653 (1.1523) time: 0.6296 [2021-03-26 16:02:00 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 520/1251] eta: 0:07:44 lr: 0.000842 loss: 3.5450 (3.5808) grad_norm: 1.1077 (1.1540) time: 0.6235 [2021-03-26 16:02:06 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 530/1251] eta: 0:07:38 lr: 0.000842 loss: 3.5017 (3.5790) grad_norm: 1.1824 (1.1544) time: 0.6279 [2021-03-26 16:02:12 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 540/1251] eta: 0:07:31 lr: 0.000842 loss: 3.8446 (3.5834) grad_norm: 1.1527 (1.1542) time: 0.6264 [2021-03-26 16:02:18 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 550/1251] eta: 0:07:25 lr: 0.000842 loss: 3.5108 (3.5765) grad_norm: 1.2145 (1.1574) time: 0.6298 [2021-03-26 16:02:25 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 560/1251] eta: 0:07:19 lr: 0.000842 loss: 3.1915 (3.5737) grad_norm: 1.2145 (1.1575) time: 0.6339 [2021-03-26 16:02:31 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 570/1251] eta: 0:07:12 lr: 0.000842 loss: 3.5112 (3.5708) grad_norm: 1.0858 (1.1573) time: 0.6312 [2021-03-26 16:02:37 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 580/1251] eta: 0:07:06 lr: 0.000842 loss: 3.5606 (3.5736) grad_norm: 1.1056 (1.1566) time: 0.6322 [2021-03-26 16:02:44 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 590/1251] eta: 0:06:59 lr: 0.000842 loss: 3.6645 (3.5725) grad_norm: 1.0740 (1.1565) time: 0.6358 [2021-03-26 16:02:50 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 600/1251] eta: 0:06:53 lr: 0.000842 loss: 3.5955 (3.5671) grad_norm: 1.1095 (1.1570) time: 0.6442 [2021-03-26 16:02:57 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 610/1251] eta: 0:06:47 lr: 0.000842 loss: 3.5156 (3.5664) grad_norm: 1.1095 (1.1557) time: 0.6355 [2021-03-26 16:03:03 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 620/1251] eta: 0:06:40 lr: 0.000842 loss: 3.6918 (3.5685) grad_norm: 1.0852 (1.1564) time: 0.6230 [2021-03-26 16:03:09 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 630/1251] eta: 0:06:34 lr: 0.000842 loss: 3.4486 (3.5660) grad_norm: 1.1338 (1.1563) time: 0.6269 [2021-03-26 16:03:15 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 640/1251] eta: 0:06:27 lr: 0.000842 loss: 3.2354 (3.5603) grad_norm: 1.1028 (1.1554) time: 0.6276 [2021-03-26 16:03:22 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 650/1251] eta: 0:06:21 lr: 0.000842 loss: 3.4051 (3.5614) grad_norm: 1.0826 (1.1547) time: 0.6294 [2021-03-26 16:03:28 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 660/1251] eta: 0:06:15 lr: 0.000842 loss: 3.5578 (3.5575) grad_norm: 1.1064 (1.1561) time: 0.6290 [2021-03-26 16:03:34 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 670/1251] eta: 0:06:08 lr: 0.000842 loss: 3.6823 (3.5609) grad_norm: 1.1324 (1.1554) time: 0.6288 [2021-03-26 16:03:41 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 680/1251] eta: 0:06:02 lr: 0.000842 loss: 3.7912 (3.5651) grad_norm: 1.1324 (1.1554) time: 0.6321 [2021-03-26 16:03:47 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 690/1251] eta: 0:05:56 lr: 0.000842 loss: 3.7886 (3.5662) grad_norm: 1.1261 (1.1550) time: 0.6306 [2021-03-26 16:03:53 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 700/1251] eta: 0:05:49 lr: 0.000842 loss: 3.8064 (3.5673) grad_norm: 1.1261 (1.1552) time: 0.6276 [2021-03-26 16:03:59 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 710/1251] eta: 0:05:43 lr: 0.000842 loss: 4.0167 (3.5689) grad_norm: 1.0893 (1.1549) time: 0.6290 [2021-03-26 16:04:06 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 720/1251] eta: 0:05:36 lr: 0.000842 loss: 3.8256 (3.5703) grad_norm: 1.0797 (1.1542) time: 0.6301 [2021-03-26 16:04:12 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 730/1251] eta: 0:05:30 lr: 0.000842 loss: 3.8122 (3.5737) grad_norm: 1.0810 (1.1544) time: 0.6327 [2021-03-26 16:04:19 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 740/1251] eta: 0:05:24 lr: 0.000842 loss: 3.6972 (3.5726) grad_norm: 1.1414 (1.1544) time: 0.6403 [2021-03-26 16:04:25 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 750/1251] eta: 0:05:17 lr: 0.000842 loss: 3.7602 (3.5772) grad_norm: 1.1601 (1.1548) time: 0.6436 [2021-03-26 16:04:31 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 760/1251] eta: 0:05:11 lr: 0.000842 loss: 3.7559 (3.5769) grad_norm: 1.1426 (1.1542) time: 0.6316 [2021-03-26 16:04:37 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 770/1251] eta: 0:05:05 lr: 0.000842 loss: 3.6262 (3.5772) grad_norm: 1.0981 (1.1545) time: 0.6242 [2021-03-26 16:04:44 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 780/1251] eta: 0:04:58 lr: 0.000841 loss: 3.7453 (3.5794) grad_norm: 1.1941 (1.1560) time: 0.6308 [2021-03-26 16:04:50 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 790/1251] eta: 0:04:52 lr: 0.000841 loss: 3.7609 (3.5800) grad_norm: 1.1751 (1.1554) time: 0.6385 [2021-03-26 16:04:57 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 800/1251] eta: 0:04:46 lr: 0.000841 loss: 3.7928 (3.5825) grad_norm: 1.1306 (1.1566) time: 0.6391 [2021-03-26 16:05:03 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 810/1251] eta: 0:04:39 lr: 0.000841 loss: 3.6554 (3.5805) grad_norm: 1.1894 (1.1575) time: 0.6409 [2021-03-26 16:05:10 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 820/1251] eta: 0:04:33 lr: 0.000841 loss: 3.5449 (3.5808) grad_norm: 1.1264 (1.1577) time: 0.6460 [2021-03-26 16:05:16 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 830/1251] eta: 0:04:27 lr: 0.000841 loss: 3.5640 (3.5812) grad_norm: 1.1075 (1.1571) time: 0.6398 [2021-03-26 16:05:22 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 840/1251] eta: 0:04:20 lr: 0.000841 loss: 3.3143 (3.5768) grad_norm: 1.1265 (1.1568) time: 0.6352 [2021-03-26 16:05:28 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 850/1251] eta: 0:04:14 lr: 0.000841 loss: 3.4671 (3.5765) grad_norm: 1.1337 (1.1570) time: 0.6296 [2021-03-26 16:05:35 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 860/1251] eta: 0:04:08 lr: 0.000841 loss: 3.7919 (3.5802) grad_norm: 1.1313 (1.1566) time: 0.6324 [2021-03-26 16:05:41 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 870/1251] eta: 0:04:01 lr: 0.000841 loss: 3.8825 (3.5824) grad_norm: 1.0884 (1.1560) time: 0.6396 [2021-03-26 16:05:48 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 880/1251] eta: 0:03:55 lr: 0.000841 loss: 3.7515 (3.5822) grad_norm: 1.0804 (1.1552) time: 0.6349 [2021-03-26 16:05:54 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 890/1251] eta: 0:03:49 lr: 0.000841 loss: 3.8318 (3.5841) grad_norm: 1.0819 (1.1555) time: 0.6313 [2021-03-26 16:06:00 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 900/1251] eta: 0:03:42 lr: 0.000841 loss: 3.6148 (3.5832) grad_norm: 1.1051 (1.1552) time: 0.6258 [2021-03-26 16:06:06 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 910/1251] eta: 0:03:36 lr: 0.000841 loss: 3.5632 (3.5825) grad_norm: 1.0904 (1.1549) time: 0.6220 [2021-03-26 16:06:13 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 920/1251] eta: 0:03:29 lr: 0.000841 loss: 3.6343 (3.5832) grad_norm: 1.1643 (1.1565) time: 0.6248 [2021-03-26 16:06:19 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 930/1251] eta: 0:03:23 lr: 0.000841 loss: 3.6018 (3.5830) grad_norm: 1.2463 (1.1573) time: 0.6292 [2021-03-26 16:06:25 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 940/1251] eta: 0:03:17 lr: 0.000841 loss: 3.6689 (3.5846) grad_norm: 1.2004 (1.1576) time: 0.6258 [2021-03-26 16:06:31 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 950/1251] eta: 0:03:10 lr: 0.000841 loss: 3.6778 (3.5848) grad_norm: 1.1217 (1.1567) time: 0.6272 [2021-03-26 16:06:38 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 960/1251] eta: 0:03:04 lr: 0.000841 loss: 3.7278 (3.5861) grad_norm: 1.0628 (1.1567) time: 0.6314 [2021-03-26 16:06:44 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 970/1251] eta: 0:02:58 lr: 0.000841 loss: 3.8705 (3.5881) grad_norm: 1.1030 (1.1568) time: 0.6272 [2021-03-26 16:06:50 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 980/1251] eta: 0:02:51 lr: 0.000841 loss: 3.7628 (3.5886) grad_norm: 1.0710 (1.1562) time: 0.6250 [2021-03-26 16:06:57 swin_base_patch4_window7_224] INFO: Epoch: [78] [ 990/1251] eta: 0:02:45 lr: 0.000841 loss: 3.7406 (3.5897) grad_norm: 1.0643 (1.1556) time: 0.6242 [2021-03-26 16:07:03 swin_base_patch4_window7_224] INFO: Epoch: [78] [1000/1251] eta: 0:02:39 lr: 0.000841 loss: 3.5241 (3.5866) grad_norm: 1.0657 (1.1551) time: 0.6294 [2021-03-26 16:07:09 swin_base_patch4_window7_224] INFO: Epoch: [78] [1010/1251] eta: 0:02:32 lr: 0.000841 loss: 3.3919 (3.5858) grad_norm: 1.0766 (1.1552) time: 0.6325 [2021-03-26 16:07:15 swin_base_patch4_window7_224] INFO: Epoch: [78] [1020/1251] eta: 0:02:26 lr: 0.000841 loss: 3.5552 (3.5845) grad_norm: 1.1662 (1.1560) time: 0.6298 [2021-03-26 16:07:22 swin_base_patch4_window7_224] INFO: Epoch: [78] [1030/1251] eta: 0:02:20 lr: 0.000841 loss: 3.8215 (3.5864) grad_norm: 1.1311 (1.1550) time: 0.6272 [2021-03-26 16:07:28 swin_base_patch4_window7_224] INFO: Epoch: [78] [1040/1251] eta: 0:02:13 lr: 0.000841 loss: 3.8319 (3.5869) grad_norm: 1.1218 (1.1551) time: 0.6265 [2021-03-26 16:07:34 swin_base_patch4_window7_224] INFO: Epoch: [78] [1050/1251] eta: 0:02:07 lr: 0.000841 loss: 3.8639 (3.5896) grad_norm: 1.1218 (1.1547) time: 0.6263 [2021-03-26 16:07:41 swin_base_patch4_window7_224] INFO: Epoch: [78] [1060/1251] eta: 0:02:01 lr: 0.000841 loss: 3.8639 (3.5912) grad_norm: 1.1280 (1.1548) time: 0.6321 [2021-03-26 16:07:47 swin_base_patch4_window7_224] INFO: Epoch: [78] [1070/1251] eta: 0:01:54 lr: 0.000841 loss: 3.6429 (3.5908) grad_norm: 1.1335 (1.1549) time: 0.6330 [2021-03-26 16:07:53 swin_base_patch4_window7_224] INFO: Epoch: [78] [1080/1251] eta: 0:01:48 lr: 0.000841 loss: 3.5109 (3.5882) grad_norm: 1.1462 (1.1552) time: 0.6312 [2021-03-26 16:08:00 swin_base_patch4_window7_224] INFO: Epoch: [78] [1090/1251] eta: 0:01:41 lr: 0.000841 loss: 3.3838 (3.5874) grad_norm: 1.1136 (1.1551) time: 0.6337 [2021-03-26 16:08:06 swin_base_patch4_window7_224] INFO: Epoch: [78] [1100/1251] eta: 0:01:35 lr: 0.000841 loss: 3.3838 (3.5865) grad_norm: 1.0848 (1.1547) time: 0.6369 [2021-03-26 16:08:12 swin_base_patch4_window7_224] INFO: Epoch: [78] [1110/1251] eta: 0:01:29 lr: 0.000840 loss: 3.8491 (3.5897) grad_norm: 1.1063 (1.1556) time: 0.6385 [2021-03-26 16:08:19 swin_base_patch4_window7_224] INFO: Epoch: [78] [1120/1251] eta: 0:01:23 lr: 0.000840 loss: 4.0477 (3.5903) grad_norm: 1.2648 (1.1564) time: 0.6354 [2021-03-26 16:08:25 swin_base_patch4_window7_224] INFO: Epoch: [78] [1130/1251] eta: 0:01:16 lr: 0.000840 loss: 3.7537 (3.5902) grad_norm: 1.2243 (1.1566) time: 0.6316 [2021-03-26 16:08:31 swin_base_patch4_window7_224] INFO: Epoch: [78] [1140/1251] eta: 0:01:10 lr: 0.000840 loss: 3.6815 (3.5890) grad_norm: 1.1325 (1.1564) time: 0.6338 [2021-03-26 16:08:38 swin_base_patch4_window7_224] INFO: Epoch: [78] [1150/1251] eta: 0:01:03 lr: 0.000840 loss: 3.5519 (3.5894) grad_norm: 1.0911 (1.1562) time: 0.6319 [2021-03-26 16:08:44 swin_base_patch4_window7_224] INFO: Epoch: [78] [1160/1251] eta: 0:00:57 lr: 0.000840 loss: 3.5519 (3.5881) grad_norm: 1.1246 (1.1569) time: 0.6313 [2021-03-26 16:08:50 swin_base_patch4_window7_224] INFO: Epoch: [78] [1170/1251] eta: 0:00:51 lr: 0.000840 loss: 3.6739 (3.5894) grad_norm: 1.1949 (1.1570) time: 0.6304 [2021-03-26 16:08:57 swin_base_patch4_window7_224] INFO: Epoch: [78] [1180/1251] eta: 0:00:44 lr: 0.000840 loss: 3.7814 (3.5903) grad_norm: 1.1335 (1.1567) time: 0.6278 [2021-03-26 16:09:03 swin_base_patch4_window7_224] INFO: Epoch: [78] [1190/1251] eta: 0:00:38 lr: 0.000840 loss: 3.7319 (3.5889) grad_norm: 1.1335 (1.1565) time: 0.6305 [2021-03-26 16:09:09 swin_base_patch4_window7_224] INFO: Epoch: [78] [1200/1251] eta: 0:00:32 lr: 0.000840 loss: 3.7319 (3.5895) grad_norm: 1.1337 (nan) time: 0.6219 [2021-03-26 16:09:15 swin_base_patch4_window7_224] INFO: Epoch: [78] [1210/1251] eta: 0:00:25 lr: 0.000840 loss: 3.6709 (3.5905) grad_norm: 1.1842 (nan) time: 0.6179 [2021-03-26 16:09:21 swin_base_patch4_window7_224] INFO: Epoch: [78] [1220/1251] eta: 0:00:19 lr: 0.000840 loss: 3.6442 (3.5910) grad_norm: 1.2775 (nan) time: 0.6231 [2021-03-26 16:09:28 swin_base_patch4_window7_224] INFO: Epoch: [78] [1230/1251] eta: 0:00:13 lr: 0.000840 loss: 3.6971 (3.5921) grad_norm: 1.2159 (nan) time: 0.6276 [2021-03-26 16:09:34 swin_base_patch4_window7_224] INFO: Epoch: [78] [1240/1251] eta: 0:00:06 lr: 0.000840 loss: 3.6727 (3.5918) grad_norm: 1.1419 (nan) time: 0.6288 [2021-03-26 16:09:40 swin_base_patch4_window7_224] INFO: Epoch: [78] [1250/1251] eta: 0:00:00 lr: 0.000840 loss: 3.5944 (3.5924) grad_norm: 1.0954 (nan) time: 0.6268 [2021-03-26 16:09:46 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:59 loss: 0.9961 (0.9961) acc1: 76.5625 (76.5625) acc5: 93.7500 (93.7500) [2021-03-26 16:09:48 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.0178 (1.0614) acc1: 76.5625 (74.7159) acc5: 93.7500 (93.1818) [2021-03-26 16:09:51 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0361 (1.0580) acc1: 76.5625 (75.9673) acc5: 92.1875 (93.2292) [2021-03-26 16:09:53 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1311 (1.0683) acc1: 75.0000 (74.8488) acc5: 93.7500 (93.3972) [2021-03-26 16:09:55 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0235 (1.0704) acc1: 71.8750 (74.6570) acc5: 93.7500 (93.0259) [2021-03-26 16:09:56 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0372 (1.0657) acc1: 73.4375 (74.8480) acc5: 92.1875 (93.2480) [2021-03-26 16:10:01 swin_base_patch4_window7_224] INFO: * Acc@1 75.504 Acc@5 93.110 loss 1.050 [2021-03-26 16:10:01 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.5% [2021-03-26 16:10:01 swin_base_patch4_window7_224] INFO: Max accuracy: 75.50% [2021-03-26 16:10:06 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 0/1251] eta: 1:33:06 lr: 0.000840 loss: 3.0081 (3.0081) grad_norm: 1.0434 (1.0434) time: 4.4657 [2021-03-26 16:10:12 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 10/1251] eta: 0:20:13 lr: 0.000840 loss: 3.7599 (3.6190) grad_norm: 1.0816 (1.0901) time: 0.9780 [2021-03-26 16:10:18 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 20/1251] eta: 0:16:37 lr: 0.000840 loss: 3.7338 (3.6024) grad_norm: 1.1346 (1.1354) time: 0.6272 [2021-03-26 16:10:25 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 30/1251] eta: 0:15:16 lr: 0.000840 loss: 3.6157 (3.6821) grad_norm: 1.1426 (1.1359) time: 0.6256 [2021-03-26 16:10:31 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 40/1251] eta: 0:14:33 lr: 0.000840 loss: 3.8925 (3.6413) grad_norm: 1.1581 (1.1464) time: 0.6277 [2021-03-26 16:10:37 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 50/1251] eta: 0:14:03 lr: 0.000840 loss: 3.5430 (3.5842) grad_norm: 1.1182 (1.1376) time: 0.6285 [2021-03-26 16:10:43 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 60/1251] eta: 0:13:44 lr: 0.000840 loss: 3.4730 (3.5694) grad_norm: 1.0844 (1.1345) time: 0.6329 [2021-03-26 16:10:50 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 70/1251] eta: 0:13:26 lr: 0.000840 loss: 3.5254 (3.5489) grad_norm: 1.0844 (1.1330) time: 0.6320 [2021-03-26 16:10:56 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 80/1251] eta: 0:13:12 lr: 0.000840 loss: 3.6822 (3.5501) grad_norm: 1.1086 (1.1430) time: 0.6288 [2021-03-26 16:11:02 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 90/1251] eta: 0:12:59 lr: 0.000840 loss: 3.4950 (3.5309) grad_norm: 1.1405 (1.1452) time: 0.6294 [2021-03-26 16:11:09 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 100/1251] eta: 0:12:46 lr: 0.000840 loss: 3.4400 (3.5330) grad_norm: 1.1158 (1.1471) time: 0.6243 [2021-03-26 16:11:15 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 110/1251] eta: 0:12:36 lr: 0.000840 loss: 3.6909 (3.5496) grad_norm: 1.1132 (1.1479) time: 0.6267 [2021-03-26 16:11:21 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 120/1251] eta: 0:12:26 lr: 0.000840 loss: 3.6282 (3.5507) grad_norm: 1.1054 (1.1410) time: 0.6293 [2021-03-26 16:11:27 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 130/1251] eta: 0:12:17 lr: 0.000840 loss: 3.6132 (3.5660) grad_norm: 1.0933 (1.1411) time: 0.6289 [2021-03-26 16:11:34 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 140/1251] eta: 0:12:08 lr: 0.000840 loss: 3.5258 (3.5502) grad_norm: 1.1517 (1.1466) time: 0.6271 [2021-03-26 16:11:40 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 150/1251] eta: 0:11:59 lr: 0.000840 loss: 3.5258 (3.5548) grad_norm: 1.2156 (1.1469) time: 0.6276 [2021-03-26 16:11:46 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 160/1251] eta: 0:11:51 lr: 0.000840 loss: 3.9135 (3.5787) grad_norm: 1.1235 (1.1484) time: 0.6300 [2021-03-26 16:11:53 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 170/1251] eta: 0:11:44 lr: 0.000840 loss: 3.9135 (3.5727) grad_norm: 1.1170 (1.1454) time: 0.6385 [2021-03-26 16:11:59 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 180/1251] eta: 0:11:36 lr: 0.000840 loss: 3.6801 (3.5859) grad_norm: 1.0822 (1.1419) time: 0.6361 [2021-03-26 16:12:05 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 190/1251] eta: 0:11:29 lr: 0.000839 loss: 3.6801 (3.5821) grad_norm: 1.1508 (1.1443) time: 0.6330 [2021-03-26 16:12:12 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 200/1251] eta: 0:11:22 lr: 0.000839 loss: 3.5900 (3.5826) grad_norm: 1.1866 (1.1492) time: 0.6395 [2021-03-26 16:12:18 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 210/1251] eta: 0:11:15 lr: 0.000839 loss: 3.5877 (3.5803) grad_norm: 1.1688 (1.1497) time: 0.6349 [2021-03-26 16:12:24 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 220/1251] eta: 0:11:07 lr: 0.000839 loss: 3.7223 (3.5816) grad_norm: 1.1325 (1.1529) time: 0.6315 [2021-03-26 16:12:31 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 230/1251] eta: 0:11:00 lr: 0.000839 loss: 3.5887 (3.5732) grad_norm: 1.1581 (1.1517) time: 0.6299 [2021-03-26 16:12:37 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 240/1251] eta: 0:10:53 lr: 0.000839 loss: 3.4481 (3.5693) grad_norm: 1.1241 (1.1518) time: 0.6345 [2021-03-26 16:12:44 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 250/1251] eta: 0:10:46 lr: 0.000839 loss: 3.3246 (3.5597) grad_norm: 1.1122 (1.1515) time: 0.6382 [2021-03-26 16:12:50 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 260/1251] eta: 0:10:39 lr: 0.000839 loss: 3.2683 (3.5547) grad_norm: 1.1381 (1.1536) time: 0.6323 [2021-03-26 16:12:56 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 270/1251] eta: 0:10:33 lr: 0.000839 loss: 3.7274 (3.5661) grad_norm: 1.0919 (1.1528) time: 0.6347 [2021-03-26 16:13:03 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 280/1251] eta: 0:10:26 lr: 0.000839 loss: 3.7050 (3.5652) grad_norm: 1.1367 (1.1548) time: 0.6427 [2021-03-26 16:13:09 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 290/1251] eta: 0:10:19 lr: 0.000839 loss: 3.6626 (3.5692) grad_norm: 1.1716 (1.1553) time: 0.6369 [2021-03-26 16:13:15 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 300/1251] eta: 0:10:13 lr: 0.000839 loss: 3.7636 (3.5737) grad_norm: 1.0698 (1.1536) time: 0.6345 [2021-03-26 16:13:22 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 310/1251] eta: 0:10:06 lr: 0.000839 loss: 3.7890 (3.5785) grad_norm: 1.1114 (1.1543) time: 0.6316 [2021-03-26 16:13:28 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 320/1251] eta: 0:09:59 lr: 0.000839 loss: 3.7320 (3.5745) grad_norm: 1.1114 (1.1525) time: 0.6317 [2021-03-26 16:13:34 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 330/1251] eta: 0:09:52 lr: 0.000839 loss: 3.6192 (3.5766) grad_norm: 1.1107 (1.1531) time: 0.6344 [2021-03-26 16:13:41 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 340/1251] eta: 0:09:45 lr: 0.000839 loss: 3.6485 (3.5748) grad_norm: 1.1107 (1.1537) time: 0.6287 [2021-03-26 16:13:47 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 350/1251] eta: 0:09:39 lr: 0.000839 loss: 3.6485 (3.5762) grad_norm: 1.0656 (1.1513) time: 0.6301 [2021-03-26 16:13:53 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 360/1251] eta: 0:09:32 lr: 0.000839 loss: 3.8335 (3.5797) grad_norm: 1.0814 (1.1510) time: 0.6326 [2021-03-26 16:14:00 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 370/1251] eta: 0:09:25 lr: 0.000839 loss: 3.6372 (3.5788) grad_norm: 1.1476 (1.1522) time: 0.6315 [2021-03-26 16:14:06 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 380/1251] eta: 0:09:19 lr: 0.000839 loss: 3.5823 (3.5773) grad_norm: 1.1705 (1.1531) time: 0.6321 [2021-03-26 16:14:12 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 390/1251] eta: 0:09:12 lr: 0.000839 loss: 3.6082 (3.5783) grad_norm: 1.1407 (1.1542) time: 0.6306 [2021-03-26 16:14:18 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 400/1251] eta: 0:09:05 lr: 0.000839 loss: 3.3627 (3.5680) grad_norm: 1.1261 (1.1550) time: 0.6290 [2021-03-26 16:14:25 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 410/1251] eta: 0:08:59 lr: 0.000839 loss: 3.7423 (3.5753) grad_norm: 1.1261 (1.1541) time: 0.6333 [2021-03-26 16:14:31 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 420/1251] eta: 0:08:52 lr: 0.000839 loss: 3.9508 (3.5835) grad_norm: 1.0739 (1.1524) time: 0.6303 [2021-03-26 16:14:37 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 430/1251] eta: 0:08:45 lr: 0.000839 loss: 4.0510 (3.5916) grad_norm: 1.1060 (1.1528) time: 0.6303 [2021-03-26 16:14:44 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 440/1251] eta: 0:08:39 lr: 0.000839 loss: 3.9038 (3.5931) grad_norm: 1.1125 (1.1532) time: 0.6335 [2021-03-26 16:14:50 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 450/1251] eta: 0:08:32 lr: 0.000839 loss: 3.7241 (3.5872) grad_norm: 1.1401 (1.1538) time: 0.6296 [2021-03-26 16:14:56 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 460/1251] eta: 0:08:26 lr: 0.000839 loss: 3.6509 (3.5891) grad_norm: 1.2115 (1.1565) time: 0.6294 [2021-03-26 16:15:03 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 470/1251] eta: 0:08:19 lr: 0.000839 loss: 3.6861 (3.5880) grad_norm: 1.1673 (1.1562) time: 0.6342 [2021-03-26 16:15:09 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 480/1251] eta: 0:08:13 lr: 0.000839 loss: 3.6861 (3.5887) grad_norm: 1.1022 (1.1551) time: 0.6365 [2021-03-26 16:15:15 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 490/1251] eta: 0:08:06 lr: 0.000839 loss: 3.6000 (3.5878) grad_norm: 1.1709 (1.1569) time: 0.6320 [2021-03-26 16:15:22 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 500/1251] eta: 0:08:00 lr: 0.000839 loss: 3.5616 (3.5862) grad_norm: 1.2424 (1.1596) time: 0.6270 [2021-03-26 16:15:28 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 510/1251] eta: 0:07:53 lr: 0.000838 loss: 3.3760 (3.5812) grad_norm: 1.1700 (1.1597) time: 0.6305 [2021-03-26 16:15:34 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 520/1251] eta: 0:07:47 lr: 0.000838 loss: 3.3771 (3.5803) grad_norm: 1.1198 (1.1598) time: 0.6343 [2021-03-26 16:15:41 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 530/1251] eta: 0:07:40 lr: 0.000838 loss: 3.6634 (3.5820) grad_norm: 1.1139 (1.1611) time: 0.6297 [2021-03-26 16:15:47 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 540/1251] eta: 0:07:34 lr: 0.000838 loss: 3.7613 (3.5843) grad_norm: 1.1144 (1.1616) time: 0.6305 [2021-03-26 16:15:53 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 550/1251] eta: 0:07:27 lr: 0.000838 loss: 3.7455 (3.5874) grad_norm: 1.1144 (1.1608) time: 0.6408 [2021-03-26 16:16:00 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 560/1251] eta: 0:07:21 lr: 0.000838 loss: 3.8394 (3.5916) grad_norm: 1.0589 (1.1597) time: 0.6413 [2021-03-26 16:16:06 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 570/1251] eta: 0:07:14 lr: 0.000838 loss: 3.6892 (3.5913) grad_norm: 1.0397 (1.1593) time: 0.6320 [2021-03-26 16:16:12 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 580/1251] eta: 0:07:08 lr: 0.000838 loss: 3.5425 (3.5926) grad_norm: 1.1554 (1.1609) time: 0.6321 [2021-03-26 16:16:19 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 590/1251] eta: 0:07:02 lr: 0.000838 loss: 3.7999 (3.5957) grad_norm: 1.1852 (1.1611) time: 0.6381 [2021-03-26 16:16:25 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 600/1251] eta: 0:06:55 lr: 0.000838 loss: 3.8653 (3.5984) grad_norm: 1.1967 (1.1624) time: 0.6380 [2021-03-26 16:16:31 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 610/1251] eta: 0:06:49 lr: 0.000838 loss: 3.8334 (3.6003) grad_norm: 1.1470 (1.1615) time: 0.6293 [2021-03-26 16:16:38 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 620/1251] eta: 0:06:42 lr: 0.000838 loss: 3.7843 (3.6043) grad_norm: 1.1001 (1.1600) time: 0.6226 [2021-03-26 16:16:44 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 630/1251] eta: 0:06:36 lr: 0.000838 loss: 3.9891 (3.6096) grad_norm: 1.0792 (1.1589) time: 0.6230 [2021-03-26 16:16:50 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 640/1251] eta: 0:06:29 lr: 0.000838 loss: 3.8098 (3.6090) grad_norm: 1.0796 (1.1594) time: 0.6327 [2021-03-26 16:16:57 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 650/1251] eta: 0:06:23 lr: 0.000838 loss: 3.3723 (3.6023) grad_norm: 1.1325 (1.1614) time: 0.6391 [2021-03-26 16:17:03 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 660/1251] eta: 0:06:16 lr: 0.000838 loss: 3.1578 (3.5987) grad_norm: 1.1598 (1.1615) time: 0.6275 [2021-03-26 16:17:09 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 670/1251] eta: 0:06:10 lr: 0.000838 loss: 3.6809 (3.6008) grad_norm: 1.1294 (1.1610) time: 0.6267 [2021-03-26 16:17:15 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 680/1251] eta: 0:06:04 lr: 0.000838 loss: 3.7046 (3.6018) grad_norm: 1.1185 (1.1601) time: 0.6358 [2021-03-26 16:17:22 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 690/1251] eta: 0:05:57 lr: 0.000838 loss: 3.7255 (3.6051) grad_norm: 1.1060 (1.1604) time: 0.6353 [2021-03-26 16:17:28 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 700/1251] eta: 0:05:51 lr: 0.000838 loss: 3.5021 (3.6006) grad_norm: 1.0970 (1.1597) time: 0.6295 [2021-03-26 16:17:35 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 710/1251] eta: 0:05:44 lr: 0.000838 loss: 3.3822 (3.5986) grad_norm: 1.0994 (1.1599) time: 0.6328 [2021-03-26 16:17:41 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 720/1251] eta: 0:05:38 lr: 0.000838 loss: 3.6419 (3.5998) grad_norm: 1.1591 (1.1598) time: 0.6377 [2021-03-26 16:17:47 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 730/1251] eta: 0:05:32 lr: 0.000838 loss: 3.7386 (3.5974) grad_norm: 1.1713 (1.1613) time: 0.6341 [2021-03-26 16:17:54 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 740/1251] eta: 0:05:25 lr: 0.000838 loss: 3.7526 (3.5985) grad_norm: 1.1530 (1.1612) time: 0.6439 [2021-03-26 16:18:00 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 750/1251] eta: 0:05:19 lr: 0.000838 loss: 3.5926 (3.5961) grad_norm: 1.1461 (1.1624) time: 0.6475 [2021-03-26 16:18:06 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 760/1251] eta: 0:05:12 lr: 0.000838 loss: 3.7221 (3.5977) grad_norm: 1.1441 (1.1617) time: 0.6343 [2021-03-26 16:18:13 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 770/1251] eta: 0:05:06 lr: 0.000838 loss: 3.6527 (3.5931) grad_norm: 1.0431 (1.1604) time: 0.6283 [2021-03-26 16:18:19 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 780/1251] eta: 0:05:00 lr: 0.000838 loss: 3.2385 (3.5893) grad_norm: 1.1073 (1.1613) time: 0.6325 [2021-03-26 16:18:25 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 790/1251] eta: 0:04:53 lr: 0.000838 loss: 3.6707 (3.5895) grad_norm: 1.1879 (1.1609) time: 0.6337 [2021-03-26 16:18:32 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 800/1251] eta: 0:04:47 lr: 0.000838 loss: 3.5411 (3.5851) grad_norm: 1.0443 (1.1596) time: 0.6290 [2021-03-26 16:18:38 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 810/1251] eta: 0:04:40 lr: 0.000838 loss: 3.5918 (3.5859) grad_norm: 1.0443 (1.1588) time: 0.6265 [2021-03-26 16:18:44 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 820/1251] eta: 0:04:34 lr: 0.000838 loss: 3.7830 (3.5872) grad_norm: 1.0954 (1.1582) time: 0.6309 [2021-03-26 16:18:51 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 830/1251] eta: 0:04:28 lr: 0.000838 loss: 3.6864 (3.5874) grad_norm: 1.0959 (1.1578) time: 0.6300 [2021-03-26 16:18:57 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 840/1251] eta: 0:04:21 lr: 0.000837 loss: 3.7421 (3.5892) grad_norm: 1.1161 (1.1582) time: 0.6242 [2021-03-26 16:19:03 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 850/1251] eta: 0:04:15 lr: 0.000837 loss: 3.7421 (3.5874) grad_norm: 1.1122 (1.1574) time: 0.6272 [2021-03-26 16:19:09 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 860/1251] eta: 0:04:08 lr: 0.000837 loss: 3.6770 (3.5886) grad_norm: 1.0610 (1.1571) time: 0.6296 [2021-03-26 16:19:16 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 870/1251] eta: 0:04:02 lr: 0.000837 loss: 3.5100 (3.5866) grad_norm: 1.0886 (1.1566) time: 0.6286 [2021-03-26 16:19:22 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 880/1251] eta: 0:03:56 lr: 0.000837 loss: 3.2556 (3.5832) grad_norm: 1.1464 (1.1575) time: 0.6337 [2021-03-26 16:19:28 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 890/1251] eta: 0:03:49 lr: 0.000837 loss: 3.2556 (3.5815) grad_norm: 1.2095 (1.1579) time: 0.6327 [2021-03-26 16:19:35 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 900/1251] eta: 0:03:43 lr: 0.000837 loss: 3.5187 (3.5806) grad_norm: 1.2348 (1.1598) time: 0.6278 [2021-03-26 16:19:41 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 910/1251] eta: 0:03:36 lr: 0.000837 loss: 3.6702 (3.5814) grad_norm: 1.1977 (1.1602) time: 0.6257 [2021-03-26 16:19:47 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 920/1251] eta: 0:03:30 lr: 0.000837 loss: 3.6706 (3.5815) grad_norm: 1.1977 (1.1612) time: 0.6301 [2021-03-26 16:19:54 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 930/1251] eta: 0:03:24 lr: 0.000837 loss: 3.4477 (3.5798) grad_norm: 1.1749 (1.1611) time: 0.6359 [2021-03-26 16:20:00 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 940/1251] eta: 0:03:17 lr: 0.000837 loss: 3.4746 (3.5764) grad_norm: 1.0936 (1.1603) time: 0.6331 [2021-03-26 16:20:06 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 950/1251] eta: 0:03:11 lr: 0.000837 loss: 3.5426 (3.5762) grad_norm: 1.0936 (1.1604) time: 0.6286 [2021-03-26 16:20:12 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 960/1251] eta: 0:03:05 lr: 0.000837 loss: 3.6154 (3.5770) grad_norm: 1.0928 (1.1600) time: 0.6273 [2021-03-26 16:20:19 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 970/1251] eta: 0:02:58 lr: 0.000837 loss: 3.5885 (3.5754) grad_norm: 1.0145 (1.1585) time: 0.6291 [2021-03-26 16:20:25 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 980/1251] eta: 0:02:52 lr: 0.000837 loss: 3.6963 (3.5749) grad_norm: 1.0197 (1.1580) time: 0.6253 [2021-03-26 16:20:31 swin_base_patch4_window7_224] INFO: Epoch: [79] [ 990/1251] eta: 0:02:45 lr: 0.000837 loss: 3.7481 (3.5763) grad_norm: 1.1158 (1.1578) time: 0.6339 [2021-03-26 16:20:38 swin_base_patch4_window7_224] INFO: Epoch: [79] [1000/1251] eta: 0:02:39 lr: 0.000837 loss: 3.7481 (3.5767) grad_norm: 1.1158 (1.1578) time: 0.6449 [2021-03-26 16:20:44 swin_base_patch4_window7_224] INFO: Epoch: [79] [1010/1251] eta: 0:02:33 lr: 0.000837 loss: 3.7874 (3.5784) grad_norm: 1.1476 (1.1579) time: 0.6380 [2021-03-26 16:20:51 swin_base_patch4_window7_224] INFO: Epoch: [79] [1020/1251] eta: 0:02:26 lr: 0.000837 loss: 3.5599 (3.5763) grad_norm: 1.1477 (1.1581) time: 0.6333 [2021-03-26 16:20:57 swin_base_patch4_window7_224] INFO: Epoch: [79] [1030/1251] eta: 0:02:20 lr: 0.000837 loss: 3.4804 (3.5761) grad_norm: 1.1427 (1.1584) time: 0.6413 [2021-03-26 16:21:03 swin_base_patch4_window7_224] INFO: Epoch: [79] [1040/1251] eta: 0:02:14 lr: 0.000837 loss: 3.5649 (3.5743) grad_norm: 1.1427 (1.1585) time: 0.6392 [2021-03-26 16:21:10 swin_base_patch4_window7_224] INFO: Epoch: [79] [1050/1251] eta: 0:02:07 lr: 0.000837 loss: 3.7997 (3.5774) grad_norm: 1.0877 (1.1576) time: 0.6283 [2021-03-26 16:21:16 swin_base_patch4_window7_224] INFO: Epoch: [79] [1060/1251] eta: 0:02:01 lr: 0.000837 loss: 3.8093 (3.5795) grad_norm: 1.0866 (1.1573) time: 0.6260 [2021-03-26 16:21:22 swin_base_patch4_window7_224] INFO: Epoch: [79] [1070/1251] eta: 0:01:55 lr: 0.000837 loss: 3.7600 (3.5787) grad_norm: 1.1042 (1.1573) time: 0.6253 [2021-03-26 16:21:28 swin_base_patch4_window7_224] INFO: Epoch: [79] [1080/1251] eta: 0:01:48 lr: 0.000837 loss: 3.6980 (3.5813) grad_norm: 1.1148 (1.1569) time: 0.6287 [2021-03-26 16:21:35 swin_base_patch4_window7_224] INFO: Epoch: [79] [1090/1251] eta: 0:01:42 lr: 0.000837 loss: 3.8697 (3.5809) grad_norm: 1.1148 (1.1572) time: 0.6276 [2021-03-26 16:21:41 swin_base_patch4_window7_224] INFO: Epoch: [79] [1100/1251] eta: 0:01:35 lr: 0.000837 loss: 3.5118 (3.5792) grad_norm: 1.1310 (1.1575) time: 0.6212 [2021-03-26 16:21:47 swin_base_patch4_window7_224] INFO: Epoch: [79] [1110/1251] eta: 0:01:29 lr: 0.000837 loss: 3.4742 (3.5774) grad_norm: 1.2029 (1.1584) time: 0.6238 [2021-03-26 16:21:53 swin_base_patch4_window7_224] INFO: Epoch: [79] [1120/1251] eta: 0:01:23 lr: 0.000837 loss: 3.4742 (3.5773) grad_norm: 1.1531 (1.1585) time: 0.6266 [2021-03-26 16:22:00 swin_base_patch4_window7_224] INFO: Epoch: [79] [1130/1251] eta: 0:01:16 lr: 0.000837 loss: 3.5089 (3.5789) grad_norm: 1.1054 (1.1576) time: 0.6269 [2021-03-26 16:22:06 swin_base_patch4_window7_224] INFO: Epoch: [79] [1140/1251] eta: 0:01:10 lr: 0.000837 loss: 3.7125 (3.5799) grad_norm: 1.0846 (1.1571) time: 0.6278 [2021-03-26 16:22:12 swin_base_patch4_window7_224] INFO: Epoch: [79] [1150/1251] eta: 0:01:04 lr: 0.000837 loss: 3.8101 (3.5822) grad_norm: 1.1241 (1.1575) time: 0.6306 [2021-03-26 16:22:18 swin_base_patch4_window7_224] INFO: Epoch: [79] [1160/1251] eta: 0:00:57 lr: 0.000836 loss: 3.7401 (3.5824) grad_norm: 1.1396 (1.1573) time: 0.6278 [2021-03-26 16:22:25 swin_base_patch4_window7_224] INFO: Epoch: [79] [1170/1251] eta: 0:00:51 lr: 0.000836 loss: 3.5471 (3.5827) grad_norm: 1.1654 (1.1575) time: 0.6263 [2021-03-26 16:22:31 swin_base_patch4_window7_224] INFO: Epoch: [79] [1180/1251] eta: 0:00:45 lr: 0.000836 loss: 3.6763 (3.5812) grad_norm: 1.1944 (1.1579) time: 0.6279 [2021-03-26 16:22:37 swin_base_patch4_window7_224] INFO: Epoch: [79] [1190/1251] eta: 0:00:38 lr: 0.000836 loss: 3.6873 (3.5807) grad_norm: 1.2004 (1.1580) time: 0.6330 [2021-03-26 16:22:44 swin_base_patch4_window7_224] INFO: Epoch: [79] [1200/1251] eta: 0:00:32 lr: 0.000836 loss: 3.6785 (3.5809) grad_norm: 1.1158 (1.1579) time: 0.6351 [2021-03-26 16:22:50 swin_base_patch4_window7_224] INFO: Epoch: [79] [1210/1251] eta: 0:00:26 lr: 0.000836 loss: 3.5821 (3.5800) grad_norm: 1.1233 (1.1583) time: 0.6333 [2021-03-26 16:22:56 swin_base_patch4_window7_224] INFO: Epoch: [79] [1220/1251] eta: 0:00:19 lr: 0.000836 loss: 3.6796 (3.5805) grad_norm: 1.1378 (1.1579) time: 0.6352 [2021-03-26 16:23:03 swin_base_patch4_window7_224] INFO: Epoch: [79] [1230/1251] eta: 0:00:13 lr: 0.000836 loss: 3.4116 (3.5782) grad_norm: 1.0967 (1.1575) time: 0.6290 [2021-03-26 16:23:09 swin_base_patch4_window7_224] INFO: Epoch: [79] [1240/1251] eta: 0:00:06 lr: 0.000836 loss: 3.1877 (3.5781) grad_norm: 1.1271 (1.1577) time: 0.6277 [2021-03-26 16:23:15 swin_base_patch4_window7_224] INFO: Epoch: [79] [1250/1251] eta: 0:00:00 lr: 0.000836 loss: 3.7315 (3.5779) grad_norm: 1.1135 (1.1569) time: 0.6223 [2021-03-26 16:23:21 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:26 loss: 0.9744 (0.9744) acc1: 73.4375 (73.4375) acc5: 96.8750 (96.8750) [2021-03-26 16:23:23 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0239 (1.0555) acc1: 73.4375 (74.8580) acc5: 93.7500 (94.0341) [2021-03-26 16:23:25 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0488 (1.0817) acc1: 73.4375 (74.4048) acc5: 93.7500 (93.4524) [2021-03-26 16:23:27 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0488 (1.0745) acc1: 73.4375 (74.5968) acc5: 93.7500 (93.5988) [2021-03-26 16:23:30 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0905 (1.0819) acc1: 73.4375 (74.1997) acc5: 93.7500 (93.5595) [2021-03-26 16:23:31 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0905 (1.0762) acc1: 75.0000 (74.6560) acc5: 92.1875 (93.4400) [2021-03-26 16:23:35 swin_base_patch4_window7_224] INFO: * Acc@1 75.534 Acc@5 93.078 loss 1.057 [2021-03-26 16:23:35 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.5% [2021-03-26 16:23:35 swin_base_patch4_window7_224] INFO: Max accuracy: 75.53% [2021-03-26 16:23:39 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 0/1251] eta: 1:27:06 lr: 0.000836 loss: 2.7700 (2.7700) grad_norm: 1.2527 (1.2527) time: 4.1776 [2021-03-26 16:23:45 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 10/1251] eta: 0:20:11 lr: 0.000836 loss: 3.3121 (3.4463) grad_norm: 1.0965 (1.1689) time: 0.9766 [2021-03-26 16:23:52 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 20/1251] eta: 0:16:44 lr: 0.000836 loss: 3.2290 (3.4005) grad_norm: 1.0927 (1.1397) time: 0.6476 [2021-03-26 16:23:58 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 30/1251] eta: 0:15:22 lr: 0.000836 loss: 3.6657 (3.4576) grad_norm: 1.1573 (1.1724) time: 0.6343 [2021-03-26 16:24:04 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 40/1251] eta: 0:14:37 lr: 0.000836 loss: 3.7599 (3.5113) grad_norm: 1.1814 (1.1764) time: 0.6286 [2021-03-26 16:24:11 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 50/1251] eta: 0:14:09 lr: 0.000836 loss: 3.6508 (3.4809) grad_norm: 1.1814 (1.1827) time: 0.6315 [2021-03-26 16:24:17 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 60/1251] eta: 0:13:49 lr: 0.000836 loss: 3.4495 (3.4915) grad_norm: 1.1868 (1.1873) time: 0.6384 [2021-03-26 16:24:23 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 70/1251] eta: 0:13:30 lr: 0.000836 loss: 3.3833 (3.4641) grad_norm: 1.1554 (1.1802) time: 0.6334 [2021-03-26 16:24:30 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 80/1251] eta: 0:13:15 lr: 0.000836 loss: 3.4210 (3.4913) grad_norm: 1.1017 (1.1726) time: 0.6282 [2021-03-26 16:24:36 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 90/1251] eta: 0:13:02 lr: 0.000836 loss: 3.8643 (3.5409) grad_norm: 1.0848 (1.1690) time: 0.6293 [2021-03-26 16:24:42 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 100/1251] eta: 0:12:50 lr: 0.000836 loss: 3.8794 (3.5556) grad_norm: 1.0861 (1.1605) time: 0.6309 [2021-03-26 16:24:49 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 110/1251] eta: 0:12:41 lr: 0.000836 loss: 3.7485 (3.5516) grad_norm: 1.0861 (1.1601) time: 0.6388 [2021-03-26 16:24:55 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 120/1251] eta: 0:12:33 lr: 0.000836 loss: 3.6868 (3.5692) grad_norm: 1.1073 (1.1627) time: 0.6485 [2021-03-26 16:25:02 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 130/1251] eta: 0:12:23 lr: 0.000836 loss: 3.7615 (3.5671) grad_norm: 1.1723 (1.1687) time: 0.6406 [2021-03-26 16:25:08 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 140/1251] eta: 0:12:14 lr: 0.000836 loss: 3.6663 (3.5675) grad_norm: 1.1761 (1.1763) time: 0.6315 [2021-03-26 16:25:14 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 150/1251] eta: 0:12:05 lr: 0.000836 loss: 3.2872 (3.5640) grad_norm: 1.2208 (1.1817) time: 0.6312 [2021-03-26 16:25:20 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 160/1251] eta: 0:11:56 lr: 0.000836 loss: 3.5534 (3.5673) grad_norm: 1.2162 (1.1834) time: 0.6257 [2021-03-26 16:25:27 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 170/1251] eta: 0:11:47 lr: 0.000836 loss: 3.8512 (3.5835) grad_norm: 1.1701 (1.1838) time: 0.6224 [2021-03-26 16:25:33 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 180/1251] eta: 0:11:39 lr: 0.000836 loss: 3.8014 (3.5867) grad_norm: 1.0888 (1.1765) time: 0.6241 [2021-03-26 16:25:39 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 190/1251] eta: 0:11:32 lr: 0.000836 loss: 3.5595 (3.5785) grad_norm: 1.0792 (1.1728) time: 0.6361 [2021-03-26 16:25:46 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 200/1251] eta: 0:11:25 lr: 0.000836 loss: 3.7342 (3.5905) grad_norm: 1.0878 (1.1695) time: 0.6381 [2021-03-26 16:25:52 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 210/1251] eta: 0:11:17 lr: 0.000836 loss: 3.7462 (3.5923) grad_norm: 1.1007 (1.1706) time: 0.6297 [2021-03-26 16:25:58 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 220/1251] eta: 0:11:09 lr: 0.000836 loss: 3.4649 (3.5789) grad_norm: 1.1485 (1.1710) time: 0.6277 [2021-03-26 16:26:05 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 230/1251] eta: 0:11:02 lr: 0.000836 loss: 3.6650 (3.5837) grad_norm: 1.1355 (1.1693) time: 0.6274 [2021-03-26 16:26:11 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 240/1251] eta: 0:10:54 lr: 0.000835 loss: 3.9189 (3.6038) grad_norm: 1.1168 (1.1687) time: 0.6273 [2021-03-26 16:26:17 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 250/1251] eta: 0:10:47 lr: 0.000835 loss: 3.8792 (3.6042) grad_norm: 1.1333 (1.1675) time: 0.6271 [2021-03-26 16:26:23 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 260/1251] eta: 0:10:40 lr: 0.000835 loss: 3.4209 (3.5935) grad_norm: 1.1707 (1.1673) time: 0.6325 [2021-03-26 16:26:30 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 270/1251] eta: 0:10:33 lr: 0.000835 loss: 3.4209 (3.5934) grad_norm: 1.1575 (1.1669) time: 0.6354 [2021-03-26 16:26:36 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 280/1251] eta: 0:10:26 lr: 0.000835 loss: 3.8694 (3.6014) grad_norm: 1.1692 (1.1674) time: 0.6328 [2021-03-26 16:26:42 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 290/1251] eta: 0:10:19 lr: 0.000835 loss: 3.7471 (3.5997) grad_norm: 1.1859 (1.1684) time: 0.6302 [2021-03-26 16:26:49 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 300/1251] eta: 0:10:12 lr: 0.000835 loss: 3.5641 (3.5975) grad_norm: 1.1425 (1.1678) time: 0.6259 [2021-03-26 16:26:55 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 310/1251] eta: 0:10:05 lr: 0.000835 loss: 3.5641 (3.5941) grad_norm: 1.1626 (1.1705) time: 0.6242 [2021-03-26 16:27:01 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 320/1251] eta: 0:09:58 lr: 0.000835 loss: 3.6879 (3.5923) grad_norm: 1.1938 (1.1710) time: 0.6253 [2021-03-26 16:27:07 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 330/1251] eta: 0:09:51 lr: 0.000835 loss: 3.6879 (3.5987) grad_norm: 1.0731 (1.1663) time: 0.6238 [2021-03-26 16:27:14 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 340/1251] eta: 0:09:45 lr: 0.000835 loss: 3.4072 (3.5878) grad_norm: 1.0479 (1.1656) time: 0.6328 [2021-03-26 16:27:20 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 350/1251] eta: 0:09:38 lr: 0.000835 loss: 3.3079 (3.5855) grad_norm: 1.0511 (1.1633) time: 0.6416 [2021-03-26 16:27:27 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 360/1251] eta: 0:09:32 lr: 0.000835 loss: 3.5659 (3.5859) grad_norm: 1.0511 (1.1620) time: 0.6347 [2021-03-26 16:27:33 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 370/1251] eta: 0:09:25 lr: 0.000835 loss: 3.3987 (3.5799) grad_norm: 1.0930 (1.1624) time: 0.6296 [2021-03-26 16:27:39 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 380/1251] eta: 0:09:18 lr: 0.000835 loss: 3.4584 (3.5813) grad_norm: 1.0913 (1.1599) time: 0.6272 [2021-03-26 16:27:45 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 390/1251] eta: 0:09:11 lr: 0.000835 loss: 3.5222 (3.5796) grad_norm: 1.0846 (1.1591) time: 0.6288 [2021-03-26 16:27:52 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 400/1251] eta: 0:09:05 lr: 0.000835 loss: 3.5222 (3.5771) grad_norm: 1.1399 (1.1607) time: 0.6316 [2021-03-26 16:27:58 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 410/1251] eta: 0:08:58 lr: 0.000835 loss: 3.5865 (3.5717) grad_norm: 1.1625 (1.1610) time: 0.6300 [2021-03-26 16:28:04 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 420/1251] eta: 0:08:52 lr: 0.000835 loss: 3.5672 (3.5689) grad_norm: 1.1465 (1.1619) time: 0.6281 [2021-03-26 16:28:11 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 430/1251] eta: 0:08:45 lr: 0.000835 loss: 3.3575 (3.5651) grad_norm: 1.1353 (1.1624) time: 0.6294 [2021-03-26 16:28:17 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 440/1251] eta: 0:08:39 lr: 0.000835 loss: 3.4146 (3.5669) grad_norm: 1.1281 (1.1640) time: 0.6362 [2021-03-26 16:28:23 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 450/1251] eta: 0:08:32 lr: 0.000835 loss: 3.7265 (3.5706) grad_norm: 1.2179 (1.1642) time: 0.6308 [2021-03-26 16:28:30 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 460/1251] eta: 0:08:25 lr: 0.000835 loss: 3.6026 (3.5681) grad_norm: 1.1528 (1.1639) time: 0.6295 [2021-03-26 16:28:36 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 470/1251] eta: 0:08:19 lr: 0.000835 loss: 3.2978 (3.5635) grad_norm: 1.1720 (1.1653) time: 0.6355 [2021-03-26 16:28:42 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 480/1251] eta: 0:08:12 lr: 0.000835 loss: 3.3464 (3.5639) grad_norm: 1.1027 (1.1636) time: 0.6287 [2021-03-26 16:28:49 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 490/1251] eta: 0:08:06 lr: 0.000835 loss: 3.4803 (3.5610) grad_norm: 1.0845 (1.1637) time: 0.6294 [2021-03-26 16:28:55 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 500/1251] eta: 0:07:59 lr: 0.000835 loss: 3.6984 (3.5614) grad_norm: 1.0845 (1.1622) time: 0.6318 [2021-03-26 16:29:01 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 510/1251] eta: 0:07:53 lr: 0.000835 loss: 3.6581 (3.5634) grad_norm: 1.1251 (1.1628) time: 0.6312 [2021-03-26 16:29:07 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 520/1251] eta: 0:07:46 lr: 0.000835 loss: 3.6006 (3.5599) grad_norm: 1.1360 (1.1623) time: 0.6322 [2021-03-26 16:29:14 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 530/1251] eta: 0:07:40 lr: 0.000835 loss: 3.6006 (3.5624) grad_norm: 1.1444 (1.1632) time: 0.6273 [2021-03-26 16:29:20 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 540/1251] eta: 0:07:33 lr: 0.000835 loss: 3.4072 (3.5579) grad_norm: 1.1568 (1.1628) time: 0.6320 [2021-03-26 16:29:27 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 550/1251] eta: 0:07:27 lr: 0.000835 loss: 3.3819 (3.5583) grad_norm: 1.1476 (1.1629) time: 0.6409 [2021-03-26 16:29:33 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 560/1251] eta: 0:07:21 lr: 0.000834 loss: 3.5283 (3.5569) grad_norm: 1.1406 (1.1631) time: 0.6403 [2021-03-26 16:29:39 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 570/1251] eta: 0:07:14 lr: 0.000834 loss: 3.7185 (3.5609) grad_norm: 1.1489 (1.1641) time: 0.6395 [2021-03-26 16:29:46 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 580/1251] eta: 0:07:08 lr: 0.000834 loss: 3.6624 (3.5566) grad_norm: 1.1489 (1.1639) time: 0.6355 [2021-03-26 16:29:52 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 590/1251] eta: 0:07:01 lr: 0.000834 loss: 3.7000 (3.5630) grad_norm: 1.0976 (1.1626) time: 0.6295 [2021-03-26 16:29:58 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 600/1251] eta: 0:06:55 lr: 0.000834 loss: 3.6264 (3.5565) grad_norm: 1.1615 (1.1656) time: 0.6389 [2021-03-26 16:30:05 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 610/1251] eta: 0:06:49 lr: 0.000834 loss: 3.5449 (3.5551) grad_norm: 1.1351 (1.1659) time: 0.6411 [2021-03-26 16:30:11 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 620/1251] eta: 0:06:42 lr: 0.000834 loss: 3.6332 (3.5535) grad_norm: 1.1304 (1.1660) time: 0.6334 [2021-03-26 16:30:17 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 630/1251] eta: 0:06:36 lr: 0.000834 loss: 3.5268 (3.5512) grad_norm: 1.1395 (1.1655) time: 0.6304 [2021-03-26 16:30:24 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 640/1251] eta: 0:06:29 lr: 0.000834 loss: 3.5785 (3.5525) grad_norm: 1.0725 (1.1642) time: 0.6248 [2021-03-26 16:30:30 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 650/1251] eta: 0:06:23 lr: 0.000834 loss: 3.7982 (3.5553) grad_norm: 1.0725 (1.1634) time: 0.6233 [2021-03-26 16:30:36 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 660/1251] eta: 0:06:16 lr: 0.000834 loss: 3.7982 (3.5544) grad_norm: 1.1074 (1.1626) time: 0.6226 [2021-03-26 16:30:42 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 670/1251] eta: 0:06:10 lr: 0.000834 loss: 3.3932 (3.5519) grad_norm: 1.1335 (1.1644) time: 0.6272 [2021-03-26 16:30:49 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 680/1251] eta: 0:06:03 lr: 0.000834 loss: 3.4361 (3.5518) grad_norm: 1.1648 (1.1649) time: 0.6291 [2021-03-26 16:30:55 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 690/1251] eta: 0:05:57 lr: 0.000834 loss: 3.5281 (3.5526) grad_norm: 1.1631 (1.1651) time: 0.6313 [2021-03-26 16:31:01 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 700/1251] eta: 0:05:51 lr: 0.000834 loss: 3.5814 (3.5536) grad_norm: 1.1943 (1.1662) time: 0.6434 [2021-03-26 16:31:08 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 710/1251] eta: 0:05:44 lr: 0.000834 loss: 3.8256 (3.5572) grad_norm: 1.1951 (1.1665) time: 0.6415 [2021-03-26 16:31:14 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 720/1251] eta: 0:05:38 lr: 0.000834 loss: 3.7920 (3.5546) grad_norm: 1.1475 (1.1660) time: 0.6269 [2021-03-26 16:31:20 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 730/1251] eta: 0:05:31 lr: 0.000834 loss: 3.7225 (3.5559) grad_norm: 1.0694 (1.1651) time: 0.6309 [2021-03-26 16:31:27 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 740/1251] eta: 0:05:25 lr: 0.000834 loss: 3.8466 (3.5562) grad_norm: 1.1339 (nan) time: 0.6273 [2021-03-26 16:31:33 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 750/1251] eta: 0:05:18 lr: 0.000834 loss: 3.5906 (3.5559) grad_norm: 1.1339 (nan) time: 0.6194 [2021-03-26 16:31:39 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 760/1251] eta: 0:05:12 lr: 0.000834 loss: 3.5906 (3.5582) grad_norm: 1.1585 (nan) time: 0.6292 [2021-03-26 16:31:46 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 770/1251] eta: 0:05:06 lr: 0.000834 loss: 3.6507 (3.5590) grad_norm: 1.1703 (nan) time: 0.6384 [2021-03-26 16:31:52 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 780/1251] eta: 0:04:59 lr: 0.000834 loss: 3.7259 (3.5612) grad_norm: 1.0436 (nan) time: 0.6363 [2021-03-26 16:31:58 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 790/1251] eta: 0:04:53 lr: 0.000834 loss: 3.8414 (3.5593) grad_norm: 1.0939 (nan) time: 0.6366 [2021-03-26 16:32:05 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 800/1251] eta: 0:04:47 lr: 0.000834 loss: 3.3851 (3.5593) grad_norm: 1.1338 (nan) time: 0.6397 [2021-03-26 16:32:11 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 810/1251] eta: 0:04:40 lr: 0.000834 loss: 3.3088 (3.5578) grad_norm: 1.1458 (nan) time: 0.6344 [2021-03-26 16:32:17 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 820/1251] eta: 0:04:34 lr: 0.000834 loss: 3.2625 (3.5547) grad_norm: 1.1458 (nan) time: 0.6279 [2021-03-26 16:32:23 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 830/1251] eta: 0:04:27 lr: 0.000834 loss: 3.2974 (3.5515) grad_norm: 1.1434 (nan) time: 0.6218 [2021-03-26 16:32:30 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 840/1251] eta: 0:04:21 lr: 0.000834 loss: 3.4750 (3.5502) grad_norm: 1.1597 (nan) time: 0.6270 [2021-03-26 16:32:36 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 850/1251] eta: 0:04:15 lr: 0.000834 loss: 3.7752 (3.5518) grad_norm: 1.1314 (nan) time: 0.6288 [2021-03-26 16:32:42 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 860/1251] eta: 0:04:08 lr: 0.000834 loss: 3.3892 (3.5498) grad_norm: 1.0920 (nan) time: 0.6242 [2021-03-26 16:32:49 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 870/1251] eta: 0:04:02 lr: 0.000834 loss: 3.2820 (3.5471) grad_norm: 1.0747 (nan) time: 0.6251 [2021-03-26 16:32:55 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 880/1251] eta: 0:03:55 lr: 0.000834 loss: 3.3495 (3.5471) grad_norm: 1.0340 (nan) time: 0.6267 [2021-03-26 16:33:01 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 890/1251] eta: 0:03:49 lr: 0.000833 loss: 3.8004 (3.5503) grad_norm: 1.1014 (nan) time: 0.6359 [2021-03-26 16:33:08 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 900/1251] eta: 0:03:43 lr: 0.000833 loss: 3.7005 (3.5500) grad_norm: 1.1405 (nan) time: 0.6351 [2021-03-26 16:33:14 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 910/1251] eta: 0:03:36 lr: 0.000833 loss: 3.4007 (3.5500) grad_norm: 1.1508 (nan) time: 0.6271 [2021-03-26 16:33:20 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 920/1251] eta: 0:03:30 lr: 0.000833 loss: 3.5373 (3.5504) grad_norm: 1.1498 (nan) time: 0.6237 [2021-03-26 16:33:26 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 930/1251] eta: 0:03:23 lr: 0.000833 loss: 3.6986 (3.5513) grad_norm: 1.1498 (nan) time: 0.6271 [2021-03-26 16:33:33 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 940/1251] eta: 0:03:17 lr: 0.000833 loss: 3.6986 (3.5515) grad_norm: 1.1122 (nan) time: 0.6364 [2021-03-26 16:33:39 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 950/1251] eta: 0:03:11 lr: 0.000833 loss: 3.4451 (3.5503) grad_norm: 1.0834 (nan) time: 0.6332 [2021-03-26 16:33:45 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 960/1251] eta: 0:03:04 lr: 0.000833 loss: 3.6236 (3.5511) grad_norm: 1.1337 (nan) time: 0.6275 [2021-03-26 16:33:52 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 970/1251] eta: 0:02:58 lr: 0.000833 loss: 3.5255 (3.5486) grad_norm: 1.2329 (nan) time: 0.6307 [2021-03-26 16:33:58 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 980/1251] eta: 0:02:52 lr: 0.000833 loss: 3.6509 (3.5507) grad_norm: 1.2329 (nan) time: 0.6341 [2021-03-26 16:34:04 swin_base_patch4_window7_224] INFO: Epoch: [80] [ 990/1251] eta: 0:02:45 lr: 0.000833 loss: 3.8368 (3.5537) grad_norm: 1.2476 (nan) time: 0.6355 [2021-03-26 16:34:11 swin_base_patch4_window7_224] INFO: Epoch: [80] [1000/1251] eta: 0:02:39 lr: 0.000833 loss: 3.5004 (3.5509) grad_norm: 1.1416 (nan) time: 0.6329 [2021-03-26 16:34:17 swin_base_patch4_window7_224] INFO: Epoch: [80] [1010/1251] eta: 0:02:33 lr: 0.000833 loss: 3.2076 (3.5508) grad_norm: 1.1564 (nan) time: 0.6318 [2021-03-26 16:34:23 swin_base_patch4_window7_224] INFO: Epoch: [80] [1020/1251] eta: 0:02:26 lr: 0.000833 loss: 3.7278 (3.5529) grad_norm: 1.1660 (nan) time: 0.6299 [2021-03-26 16:34:30 swin_base_patch4_window7_224] INFO: Epoch: [80] [1030/1251] eta: 0:02:20 lr: 0.000833 loss: 3.7278 (3.5541) grad_norm: 1.1393 (nan) time: 0.6273 [2021-03-26 16:34:36 swin_base_patch4_window7_224] INFO: Epoch: [80] [1040/1251] eta: 0:02:13 lr: 0.000833 loss: 3.7060 (3.5544) grad_norm: 1.1393 (nan) time: 0.6287 [2021-03-26 16:34:42 swin_base_patch4_window7_224] INFO: Epoch: [80] [1050/1251] eta: 0:02:07 lr: 0.000833 loss: 3.5072 (3.5505) grad_norm: 1.1775 (nan) time: 0.6294 [2021-03-26 16:34:48 swin_base_patch4_window7_224] INFO: Epoch: [80] [1060/1251] eta: 0:02:01 lr: 0.000833 loss: 3.4652 (3.5501) grad_norm: 1.1935 (nan) time: 0.6273 [2021-03-26 16:34:55 swin_base_patch4_window7_224] INFO: Epoch: [80] [1070/1251] eta: 0:01:54 lr: 0.000833 loss: 3.4736 (3.5514) grad_norm: 1.1605 (nan) time: 0.6231 [2021-03-26 16:35:01 swin_base_patch4_window7_224] INFO: Epoch: [80] [1080/1251] eta: 0:01:48 lr: 0.000833 loss: 3.7587 (3.5533) grad_norm: 1.1076 (nan) time: 0.6234 [2021-03-26 16:35:07 swin_base_patch4_window7_224] INFO: Epoch: [80] [1090/1251] eta: 0:01:42 lr: 0.000833 loss: 3.7717 (3.5551) grad_norm: 1.1241 (nan) time: 0.6298 [2021-03-26 16:35:14 swin_base_patch4_window7_224] INFO: Epoch: [80] [1100/1251] eta: 0:01:35 lr: 0.000833 loss: 3.7717 (3.5542) grad_norm: 1.1241 (nan) time: 0.6352 [2021-03-26 16:35:20 swin_base_patch4_window7_224] INFO: Epoch: [80] [1110/1251] eta: 0:01:29 lr: 0.000833 loss: 3.1264 (3.5507) grad_norm: 1.1578 (nan) time: 0.6313 [2021-03-26 16:35:26 swin_base_patch4_window7_224] INFO: Epoch: [80] [1120/1251] eta: 0:01:23 lr: 0.000833 loss: 3.1132 (3.5495) grad_norm: 1.2051 (nan) time: 0.6297 [2021-03-26 16:35:32 swin_base_patch4_window7_224] INFO: Epoch: [80] [1130/1251] eta: 0:01:16 lr: 0.000833 loss: 3.3228 (3.5494) grad_norm: 1.1815 (nan) time: 0.6312 [2021-03-26 16:35:39 swin_base_patch4_window7_224] INFO: Epoch: [80] [1140/1251] eta: 0:01:10 lr: 0.000833 loss: 3.4495 (3.5494) grad_norm: 1.0994 (nan) time: 0.6303 [2021-03-26 16:35:45 swin_base_patch4_window7_224] INFO: Epoch: [80] [1150/1251] eta: 0:01:04 lr: 0.000833 loss: 3.6175 (3.5482) grad_norm: 1.1314 (nan) time: 0.6288 [2021-03-26 16:35:51 swin_base_patch4_window7_224] INFO: Epoch: [80] [1160/1251] eta: 0:00:57 lr: 0.000833 loss: 3.7134 (3.5492) grad_norm: 1.2381 (nan) time: 0.6298 [2021-03-26 16:35:58 swin_base_patch4_window7_224] INFO: Epoch: [80] [1170/1251] eta: 0:00:51 lr: 0.000833 loss: 3.7603 (3.5520) grad_norm: 1.2381 (nan) time: 0.6303 [2021-03-26 16:36:04 swin_base_patch4_window7_224] INFO: Epoch: [80] [1180/1251] eta: 0:00:45 lr: 0.000833 loss: 3.7603 (3.5523) grad_norm: 1.2749 (nan) time: 0.6373 [2021-03-26 16:36:10 swin_base_patch4_window7_224] INFO: Epoch: [80] [1190/1251] eta: 0:00:38 lr: 0.000833 loss: 3.7229 (3.5530) grad_norm: 1.2728 (nan) time: 0.6390 [2021-03-26 16:36:17 swin_base_patch4_window7_224] INFO: Epoch: [80] [1200/1251] eta: 0:00:32 lr: 0.000833 loss: 3.6539 (3.5531) grad_norm: 1.1285 (nan) time: 0.6245 [2021-03-26 16:36:23 swin_base_patch4_window7_224] INFO: Epoch: [80] [1210/1251] eta: 0:00:26 lr: 0.000832 loss: 3.7081 (3.5539) grad_norm: 1.1483 (nan) time: 0.6204 [2021-03-26 16:36:29 swin_base_patch4_window7_224] INFO: Epoch: [80] [1220/1251] eta: 0:00:19 lr: 0.000832 loss: 3.7632 (3.5546) grad_norm: 1.1138 (nan) time: 0.6241 [2021-03-26 16:36:35 swin_base_patch4_window7_224] INFO: Epoch: [80] [1230/1251] eta: 0:00:13 lr: 0.000832 loss: 3.7730 (3.5554) grad_norm: 1.1046 (nan) time: 0.6234 [2021-03-26 16:36:42 swin_base_patch4_window7_224] INFO: Epoch: [80] [1240/1251] eta: 0:00:06 lr: 0.000832 loss: 3.7229 (3.5566) grad_norm: 1.1370 (nan) time: 0.6237 [2021-03-26 16:36:48 swin_base_patch4_window7_224] INFO: Epoch: [80] [1250/1251] eta: 0:00:00 lr: 0.000832 loss: 3.7964 (3.5592) grad_norm: 1.1893 (nan) time: 0.6166 [2021-03-26 16:38:01 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:10 loss: 1.0469 (1.0469) acc1: 78.1250 (78.1250) acc5: 92.1875 (92.1875) [2021-03-26 16:38:03 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 1.0469 (1.0640) acc1: 73.4375 (74.0057) acc5: 93.7500 (93.6080) [2021-03-26 16:38:04 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:06 loss: 1.0644 (1.0803) acc1: 73.4375 (74.1815) acc5: 93.7500 (93.6012) [2021-03-26 16:38:06 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.0649 (1.0702) acc1: 73.4375 (74.4456) acc5: 93.7500 (93.1956) [2021-03-26 16:38:07 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.0476 (1.0469) acc1: 75.0000 (75.0000) acc5: 93.7500 (93.4070) [2021-03-26 16:38:08 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9970 (1.0361) acc1: 76.5625 (75.1680) acc5: 93.7500 (93.5360) [2021-03-26 16:38:14 swin_base_patch4_window7_224] INFO: * Acc@1 75.560 Acc@5 93.290 loss 1.026 [2021-03-26 16:38:14 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.6% [2021-03-26 16:38:14 swin_base_patch4_window7_224] INFO: Max accuracy: 75.56% [2021-03-26 16:38:18 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 0/1251] eta: 1:28:27 lr: 0.000832 loss: 3.1669 (3.1669) grad_norm: 1.1308 (1.1308) time: 4.2424 [2021-03-26 16:38:24 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 10/1251] eta: 0:20:02 lr: 0.000832 loss: 3.7002 (3.4508) grad_norm: 1.0749 (1.0784) time: 0.9694 [2021-03-26 16:38:31 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 20/1251] eta: 0:16:33 lr: 0.000832 loss: 3.7002 (3.5586) grad_norm: 1.0590 (1.1064) time: 0.6354 [2021-03-26 16:38:37 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 30/1251] eta: 0:15:18 lr: 0.000832 loss: 3.5962 (3.5349) grad_norm: 1.1888 (1.1583) time: 0.6329 [2021-03-26 16:38:43 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 40/1251] eta: 0:14:34 lr: 0.000832 loss: 3.4793 (3.4798) grad_norm: 1.2093 (1.1849) time: 0.6331 [2021-03-26 16:38:50 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 50/1251] eta: 0:14:05 lr: 0.000832 loss: 3.4793 (3.5215) grad_norm: 1.2276 (1.1854) time: 0.6282 [2021-03-26 16:38:56 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 60/1251] eta: 0:13:41 lr: 0.000832 loss: 3.6027 (3.5110) grad_norm: 1.1103 (1.1846) time: 0.6232 [2021-03-26 16:39:02 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 70/1251] eta: 0:13:24 lr: 0.000832 loss: 3.6264 (3.5249) grad_norm: 1.1016 (1.1814) time: 0.6252 [2021-03-26 16:39:08 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 80/1251] eta: 0:13:12 lr: 0.000832 loss: 3.8125 (3.5707) grad_norm: 1.1154 (1.1732) time: 0.6356 [2021-03-26 16:39:15 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 90/1251] eta: 0:12:58 lr: 0.000832 loss: 3.8562 (3.5867) grad_norm: 1.1280 (1.1757) time: 0.6311 [2021-03-26 16:39:21 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 100/1251] eta: 0:12:46 lr: 0.000832 loss: 3.7610 (3.5766) grad_norm: 1.1517 (1.1754) time: 0.6250 [2021-03-26 16:39:27 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 110/1251] eta: 0:12:35 lr: 0.000832 loss: 3.3190 (3.5331) grad_norm: 1.1184 (1.1687) time: 0.6263 [2021-03-26 16:39:34 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 120/1251] eta: 0:12:27 lr: 0.000832 loss: 3.5625 (3.5354) grad_norm: 1.1148 (1.1655) time: 0.6327 [2021-03-26 16:39:40 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 130/1251] eta: 0:12:18 lr: 0.000832 loss: 3.6659 (3.5453) grad_norm: 1.1148 (1.1647) time: 0.6378 [2021-03-26 16:39:46 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 140/1251] eta: 0:12:09 lr: 0.000832 loss: 3.5672 (3.5372) grad_norm: 1.0876 (1.1626) time: 0.6348 [2021-03-26 16:39:53 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 150/1251] eta: 0:12:01 lr: 0.000832 loss: 3.6327 (3.5547) grad_norm: 1.1126 (1.1632) time: 0.6310 [2021-03-26 16:39:59 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 160/1251] eta: 0:11:52 lr: 0.000832 loss: 3.6857 (3.5621) grad_norm: 1.2044 (1.1709) time: 0.6258 [2021-03-26 16:40:05 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 170/1251] eta: 0:11:44 lr: 0.000832 loss: 3.9197 (3.5818) grad_norm: 1.2567 (1.1783) time: 0.6267 [2021-03-26 16:40:11 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 180/1251] eta: 0:11:36 lr: 0.000832 loss: 3.9834 (3.5841) grad_norm: 1.2251 (1.1782) time: 0.6245 [2021-03-26 16:40:18 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 190/1251] eta: 0:11:28 lr: 0.000832 loss: 3.6288 (3.5780) grad_norm: 1.1039 (1.1748) time: 0.6273 [2021-03-26 16:40:24 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 200/1251] eta: 0:11:21 lr: 0.000832 loss: 3.5127 (3.5672) grad_norm: 1.0863 (1.1753) time: 0.6329 [2021-03-26 16:40:30 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 210/1251] eta: 0:11:14 lr: 0.000832 loss: 3.5328 (3.5692) grad_norm: 1.1200 (1.1731) time: 0.6326 [2021-03-26 16:40:37 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 220/1251] eta: 0:11:06 lr: 0.000832 loss: 3.6705 (3.5673) grad_norm: 1.1200 (1.1735) time: 0.6285 [2021-03-26 16:40:43 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 230/1251] eta: 0:10:59 lr: 0.000832 loss: 3.6562 (3.5573) grad_norm: 1.1305 (1.1745) time: 0.6249 [2021-03-26 16:40:49 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 240/1251] eta: 0:10:51 lr: 0.000832 loss: 3.5958 (3.5675) grad_norm: 1.1026 (1.1710) time: 0.6265 [2021-03-26 16:40:55 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 250/1251] eta: 0:10:45 lr: 0.000832 loss: 3.5531 (3.5672) grad_norm: 1.1458 (1.1761) time: 0.6307 [2021-03-26 16:41:02 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 260/1251] eta: 0:10:37 lr: 0.000832 loss: 3.5360 (3.5649) grad_norm: 1.2369 (1.1780) time: 0.6308 [2021-03-26 16:41:08 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 270/1251] eta: 0:10:31 lr: 0.000832 loss: 3.7309 (3.5704) grad_norm: 1.1561 (1.1758) time: 0.6280 [2021-03-26 16:41:14 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 280/1251] eta: 0:10:24 lr: 0.000831 loss: 3.6723 (3.5674) grad_norm: 1.1311 (1.1755) time: 0.6317 [2021-03-26 16:41:21 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 290/1251] eta: 0:10:17 lr: 0.000831 loss: 3.5477 (3.5657) grad_norm: 1.1596 (inf) time: 0.6329 [2021-03-26 16:41:27 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 300/1251] eta: 0:10:10 lr: 0.000831 loss: 3.6742 (3.5715) grad_norm: 1.1514 (inf) time: 0.6318 [2021-03-26 16:41:33 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 310/1251] eta: 0:10:03 lr: 0.000831 loss: 3.7419 (3.5742) grad_norm: 1.1057 (inf) time: 0.6317 [2021-03-26 16:41:40 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 320/1251] eta: 0:09:57 lr: 0.000831 loss: 3.6683 (3.5720) grad_norm: 1.1800 (inf) time: 0.6349 [2021-03-26 16:41:46 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 330/1251] eta: 0:09:50 lr: 0.000831 loss: 3.4623 (3.5728) grad_norm: 1.1690 (inf) time: 0.6345 [2021-03-26 16:41:52 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 340/1251] eta: 0:09:43 lr: 0.000831 loss: 3.4289 (3.5635) grad_norm: 1.1521 (inf) time: 0.6298 [2021-03-26 16:41:59 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 350/1251] eta: 0:09:37 lr: 0.000831 loss: 3.6229 (3.5653) grad_norm: 1.1158 (inf) time: 0.6271 [2021-03-26 16:42:05 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 360/1251] eta: 0:09:30 lr: 0.000831 loss: 3.8105 (3.5719) grad_norm: 1.1144 (inf) time: 0.6257 [2021-03-26 16:42:11 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 370/1251] eta: 0:09:23 lr: 0.000831 loss: 3.6910 (3.5730) grad_norm: 1.1290 (inf) time: 0.6268 [2021-03-26 16:42:17 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 380/1251] eta: 0:09:16 lr: 0.000831 loss: 3.6782 (3.5677) grad_norm: 1.1290 (inf) time: 0.6262 [2021-03-26 16:42:24 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 390/1251] eta: 0:09:10 lr: 0.000831 loss: 3.6468 (3.5705) grad_norm: 1.1603 (inf) time: 0.6274 [2021-03-26 16:42:30 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 400/1251] eta: 0:09:03 lr: 0.000831 loss: 3.7475 (3.5775) grad_norm: 1.1773 (inf) time: 0.6330 [2021-03-26 16:42:36 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 410/1251] eta: 0:08:57 lr: 0.000831 loss: 3.6882 (3.5698) grad_norm: 1.2449 (inf) time: 0.6338 [2021-03-26 16:42:43 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 420/1251] eta: 0:08:50 lr: 0.000831 loss: 3.7850 (3.5772) grad_norm: 1.1862 (inf) time: 0.6270 [2021-03-26 16:42:49 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 430/1251] eta: 0:08:44 lr: 0.000831 loss: 3.8144 (3.5749) grad_norm: 1.0778 (inf) time: 0.6258 [2021-03-26 16:42:55 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 440/1251] eta: 0:08:37 lr: 0.000831 loss: 3.4695 (3.5755) grad_norm: 1.0648 (inf) time: 0.6296 [2021-03-26 16:43:01 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 450/1251] eta: 0:08:30 lr: 0.000831 loss: 3.7726 (3.5759) grad_norm: 1.0704 (inf) time: 0.6273 [2021-03-26 16:43:08 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 460/1251] eta: 0:08:24 lr: 0.000831 loss: 3.7891 (3.5800) grad_norm: 1.1552 (inf) time: 0.6255 [2021-03-26 16:43:14 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 470/1251] eta: 0:08:17 lr: 0.000831 loss: 3.8438 (3.5831) grad_norm: 1.1322 (inf) time: 0.6233 [2021-03-26 16:43:20 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 480/1251] eta: 0:08:11 lr: 0.000831 loss: 3.6554 (3.5820) grad_norm: 1.1582 (inf) time: 0.6279 [2021-03-26 16:43:26 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 490/1251] eta: 0:08:04 lr: 0.000831 loss: 3.6281 (3.5816) grad_norm: 1.1238 (inf) time: 0.6256 [2021-03-26 16:43:33 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 500/1251] eta: 0:07:58 lr: 0.000831 loss: 3.7045 (3.5853) grad_norm: 1.0963 (inf) time: 0.6219 [2021-03-26 16:43:39 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 510/1251] eta: 0:07:51 lr: 0.000831 loss: 3.3706 (3.5797) grad_norm: 1.0992 (inf) time: 0.6294 [2021-03-26 16:43:45 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 520/1251] eta: 0:07:45 lr: 0.000831 loss: 3.3488 (3.5769) grad_norm: 1.1245 (inf) time: 0.6297 [2021-03-26 16:43:52 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 530/1251] eta: 0:07:38 lr: 0.000831 loss: 3.5054 (3.5738) grad_norm: 1.0719 (inf) time: 0.6307 [2021-03-26 16:43:58 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 540/1251] eta: 0:07:32 lr: 0.000831 loss: 3.5195 (3.5739) grad_norm: 1.0656 (inf) time: 0.6324 [2021-03-26 16:44:04 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 550/1251] eta: 0:07:26 lr: 0.000831 loss: 3.7014 (3.5760) grad_norm: 1.1419 (inf) time: 0.6364 [2021-03-26 16:44:11 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 560/1251] eta: 0:07:19 lr: 0.000831 loss: 3.8781 (3.5776) grad_norm: 1.1590 (inf) time: 0.6343 [2021-03-26 16:44:17 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 570/1251] eta: 0:07:12 lr: 0.000831 loss: 3.7318 (3.5797) grad_norm: 1.1510 (inf) time: 0.6230 [2021-03-26 16:44:23 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 580/1251] eta: 0:07:06 lr: 0.000831 loss: 3.7033 (3.5836) grad_norm: 1.1374 (inf) time: 0.6238 [2021-03-26 16:44:29 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 590/1251] eta: 0:07:00 lr: 0.000831 loss: 3.7093 (3.5834) grad_norm: 1.1374 (inf) time: 0.6263 [2021-03-26 16:44:36 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 600/1251] eta: 0:06:53 lr: 0.000830 loss: 3.7093 (3.5845) grad_norm: 1.1442 (inf) time: 0.6246 [2021-03-26 16:44:42 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 610/1251] eta: 0:06:47 lr: 0.000830 loss: 3.7021 (3.5845) grad_norm: 1.1553 (inf) time: 0.6253 [2021-03-26 16:44:48 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 620/1251] eta: 0:06:40 lr: 0.000830 loss: 3.7026 (3.5849) grad_norm: 1.1941 (inf) time: 0.6245 [2021-03-26 16:44:54 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 630/1251] eta: 0:06:34 lr: 0.000830 loss: 3.9040 (3.5880) grad_norm: 1.1311 (inf) time: 0.6234 [2021-03-26 16:45:01 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 640/1251] eta: 0:06:27 lr: 0.000830 loss: 3.8582 (3.5915) grad_norm: 1.1255 (inf) time: 0.6264 [2021-03-26 16:45:07 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 650/1251] eta: 0:06:21 lr: 0.000830 loss: 3.5609 (3.5910) grad_norm: 1.1043 (inf) time: 0.6270 [2021-03-26 16:45:13 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 660/1251] eta: 0:06:14 lr: 0.000830 loss: 3.5620 (3.5930) grad_norm: 1.0746 (inf) time: 0.6263 [2021-03-26 16:45:19 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 670/1251] eta: 0:06:08 lr: 0.000830 loss: 3.7344 (3.5923) grad_norm: 1.0177 (inf) time: 0.6252 [2021-03-26 16:45:26 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 680/1251] eta: 0:06:02 lr: 0.000830 loss: 3.8035 (3.5963) grad_norm: 1.0451 (inf) time: 0.6213 [2021-03-26 16:45:32 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 690/1251] eta: 0:05:55 lr: 0.000830 loss: 3.5450 (3.5929) grad_norm: 1.0747 (inf) time: 0.6203 [2021-03-26 16:45:38 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 700/1251] eta: 0:05:49 lr: 0.000830 loss: 3.5260 (3.5928) grad_norm: 1.0714 (inf) time: 0.6291 [2021-03-26 16:45:44 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 710/1251] eta: 0:05:42 lr: 0.000830 loss: 3.6634 (3.5917) grad_norm: 1.1673 (inf) time: 0.6330 [2021-03-26 16:45:51 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 720/1251] eta: 0:05:36 lr: 0.000830 loss: 3.5585 (3.5896) grad_norm: 1.1710 (inf) time: 0.6273 [2021-03-26 16:45:57 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 730/1251] eta: 0:05:30 lr: 0.000830 loss: 3.5585 (3.5895) grad_norm: 1.1710 (inf) time: 0.6255 [2021-03-26 16:46:03 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 740/1251] eta: 0:05:23 lr: 0.000830 loss: 3.4107 (3.5857) grad_norm: 1.1457 (inf) time: 0.6324 [2021-03-26 16:46:10 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 750/1251] eta: 0:05:17 lr: 0.000830 loss: 3.4107 (3.5847) grad_norm: 1.1138 (inf) time: 0.6413 [2021-03-26 16:46:16 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 760/1251] eta: 0:05:11 lr: 0.000830 loss: 3.6783 (3.5852) grad_norm: 1.1032 (inf) time: 0.6321 [2021-03-26 16:46:22 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 770/1251] eta: 0:05:04 lr: 0.000830 loss: 3.5834 (3.5824) grad_norm: 1.1189 (inf) time: 0.6259 [2021-03-26 16:46:29 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 780/1251] eta: 0:04:58 lr: 0.000830 loss: 3.2992 (3.5773) grad_norm: 1.1217 (inf) time: 0.6344 [2021-03-26 16:46:35 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 790/1251] eta: 0:04:52 lr: 0.000830 loss: 3.4354 (3.5781) grad_norm: 1.1130 (inf) time: 0.6353 [2021-03-26 16:46:41 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 800/1251] eta: 0:04:45 lr: 0.000830 loss: 3.6573 (3.5797) grad_norm: 1.1107 (inf) time: 0.6361 [2021-03-26 16:46:48 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 810/1251] eta: 0:04:39 lr: 0.000830 loss: 3.9041 (3.5845) grad_norm: 1.0945 (inf) time: 0.6370 [2021-03-26 16:46:54 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 820/1251] eta: 0:04:33 lr: 0.000830 loss: 3.9333 (3.5866) grad_norm: 1.0929 (inf) time: 0.6335 [2021-03-26 16:47:00 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 830/1251] eta: 0:04:26 lr: 0.000830 loss: 3.7822 (3.5870) grad_norm: 1.2206 (inf) time: 0.6304 [2021-03-26 16:47:07 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 840/1251] eta: 0:04:20 lr: 0.000830 loss: 3.8406 (3.5890) grad_norm: 1.1698 (inf) time: 0.6247 [2021-03-26 16:47:13 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 850/1251] eta: 0:04:13 lr: 0.000830 loss: 3.8625 (3.5892) grad_norm: 1.0762 (inf) time: 0.6221 [2021-03-26 16:47:19 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 860/1251] eta: 0:04:07 lr: 0.000830 loss: 3.8023 (3.5897) grad_norm: 1.1389 (inf) time: 0.6220 [2021-03-26 16:47:25 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 870/1251] eta: 0:04:01 lr: 0.000830 loss: 3.7304 (3.5906) grad_norm: 1.1404 (inf) time: 0.6285 [2021-03-26 16:47:32 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 880/1251] eta: 0:03:54 lr: 0.000830 loss: 3.5594 (3.5883) grad_norm: 1.1790 (inf) time: 0.6297 [2021-03-26 16:47:38 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 890/1251] eta: 0:03:48 lr: 0.000830 loss: 3.7584 (3.5887) grad_norm: 1.1438 (inf) time: 0.6253 [2021-03-26 16:47:44 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 900/1251] eta: 0:03:42 lr: 0.000830 loss: 3.7716 (3.5889) grad_norm: 1.0946 (inf) time: 0.6347 [2021-03-26 16:47:51 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 910/1251] eta: 0:03:35 lr: 0.000830 loss: 3.5683 (3.5865) grad_norm: 1.1279 (inf) time: 0.6383 [2021-03-26 16:47:57 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 920/1251] eta: 0:03:29 lr: 0.000829 loss: 3.4080 (3.5846) grad_norm: 1.1484 (inf) time: 0.6280 [2021-03-26 16:48:03 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 930/1251] eta: 0:03:23 lr: 0.000829 loss: 3.4332 (3.5850) grad_norm: 1.1484 (inf) time: 0.6313 [2021-03-26 16:48:10 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 940/1251] eta: 0:03:16 lr: 0.000829 loss: 3.4332 (3.5827) grad_norm: 1.2146 (inf) time: 0.6378 [2021-03-26 16:48:16 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 950/1251] eta: 0:03:10 lr: 0.000829 loss: 3.5662 (3.5843) grad_norm: 1.1883 (inf) time: 0.6375 [2021-03-26 16:48:22 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 960/1251] eta: 0:03:04 lr: 0.000829 loss: 3.7964 (3.5846) grad_norm: 1.0864 (inf) time: 0.6314 [2021-03-26 16:48:29 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 970/1251] eta: 0:02:57 lr: 0.000829 loss: 3.7964 (3.5855) grad_norm: 1.0923 (inf) time: 0.6266 [2021-03-26 16:48:35 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 980/1251] eta: 0:02:51 lr: 0.000829 loss: 3.6482 (3.5849) grad_norm: 1.2096 (inf) time: 0.6313 [2021-03-26 16:48:41 swin_base_patch4_window7_224] INFO: Epoch: [81] [ 990/1251] eta: 0:02:45 lr: 0.000829 loss: 3.6321 (3.5847) grad_norm: 1.2499 (inf) time: 0.6309 [2021-03-26 16:48:47 swin_base_patch4_window7_224] INFO: Epoch: [81] [1000/1251] eta: 0:02:38 lr: 0.000829 loss: 3.6095 (3.5834) grad_norm: 1.1511 (inf) time: 0.6285 [2021-03-26 16:48:54 swin_base_patch4_window7_224] INFO: Epoch: [81] [1010/1251] eta: 0:02:32 lr: 0.000829 loss: 3.6095 (3.5842) grad_norm: 1.1301 (inf) time: 0.6315 [2021-03-26 16:49:00 swin_base_patch4_window7_224] INFO: Epoch: [81] [1020/1251] eta: 0:02:26 lr: 0.000829 loss: 3.6557 (3.5846) grad_norm: 1.0508 (inf) time: 0.6270 [2021-03-26 16:49:06 swin_base_patch4_window7_224] INFO: Epoch: [81] [1030/1251] eta: 0:02:19 lr: 0.000829 loss: 3.5916 (3.5847) grad_norm: 1.0804 (inf) time: 0.6273 [2021-03-26 16:49:13 swin_base_patch4_window7_224] INFO: Epoch: [81] [1040/1251] eta: 0:02:13 lr: 0.000829 loss: 3.5791 (3.5821) grad_norm: 1.1854 (inf) time: 0.6343 [2021-03-26 16:49:19 swin_base_patch4_window7_224] INFO: Epoch: [81] [1050/1251] eta: 0:02:07 lr: 0.000829 loss: 3.6150 (3.5834) grad_norm: 1.0984 (inf) time: 0.6252 [2021-03-26 16:49:25 swin_base_patch4_window7_224] INFO: Epoch: [81] [1060/1251] eta: 0:02:00 lr: 0.000829 loss: 3.5648 (3.5813) grad_norm: 1.0799 (inf) time: 0.6199 [2021-03-26 16:49:31 swin_base_patch4_window7_224] INFO: Epoch: [81] [1070/1251] eta: 0:01:54 lr: 0.000829 loss: 3.1898 (3.5763) grad_norm: 1.1927 (inf) time: 0.6331 [2021-03-26 16:49:38 swin_base_patch4_window7_224] INFO: Epoch: [81] [1080/1251] eta: 0:01:48 lr: 0.000829 loss: 3.0917 (3.5767) grad_norm: 1.1658 (inf) time: 0.6403 [2021-03-26 16:49:44 swin_base_patch4_window7_224] INFO: Epoch: [81] [1090/1251] eta: 0:01:41 lr: 0.000829 loss: 3.8192 (3.5769) grad_norm: 1.1425 (inf) time: 0.6325 [2021-03-26 16:49:50 swin_base_patch4_window7_224] INFO: Epoch: [81] [1100/1251] eta: 0:01:35 lr: 0.000829 loss: 3.4229 (3.5757) grad_norm: 1.1304 (inf) time: 0.6313 [2021-03-26 16:49:57 swin_base_patch4_window7_224] INFO: Epoch: [81] [1110/1251] eta: 0:01:29 lr: 0.000829 loss: 3.3727 (3.5739) grad_norm: 1.1507 (inf) time: 0.6335 [2021-03-26 16:50:03 swin_base_patch4_window7_224] INFO: Epoch: [81] [1120/1251] eta: 0:01:22 lr: 0.000829 loss: 3.3727 (3.5721) grad_norm: 1.1689 (inf) time: 0.6320 [2021-03-26 16:50:09 swin_base_patch4_window7_224] INFO: Epoch: [81] [1130/1251] eta: 0:01:16 lr: 0.000829 loss: 3.5061 (3.5717) grad_norm: 1.1195 (inf) time: 0.6276 [2021-03-26 16:50:16 swin_base_patch4_window7_224] INFO: Epoch: [81] [1140/1251] eta: 0:01:10 lr: 0.000829 loss: 3.4511 (3.5705) grad_norm: 1.2388 (inf) time: 0.6284 [2021-03-26 16:50:22 swin_base_patch4_window7_224] INFO: Epoch: [81] [1150/1251] eta: 0:01:03 lr: 0.000829 loss: 3.5273 (3.5718) grad_norm: 1.2046 (inf) time: 0.6339 [2021-03-26 16:50:28 swin_base_patch4_window7_224] INFO: Epoch: [81] [1160/1251] eta: 0:00:57 lr: 0.000829 loss: 3.5923 (3.5710) grad_norm: 1.1715 (inf) time: 0.6272 [2021-03-26 16:50:34 swin_base_patch4_window7_224] INFO: Epoch: [81] [1170/1251] eta: 0:00:51 lr: 0.000829 loss: 3.4746 (3.5717) grad_norm: 1.1299 (inf) time: 0.6203 [2021-03-26 16:50:41 swin_base_patch4_window7_224] INFO: Epoch: [81] [1180/1251] eta: 0:00:44 lr: 0.000829 loss: 3.7039 (3.5732) grad_norm: 1.1254 (inf) time: 0.6226 [2021-03-26 16:50:47 swin_base_patch4_window7_224] INFO: Epoch: [81] [1190/1251] eta: 0:00:38 lr: 0.000829 loss: 3.8914 (3.5742) grad_norm: 1.1345 (inf) time: 0.6309 [2021-03-26 16:50:53 swin_base_patch4_window7_224] INFO: Epoch: [81] [1200/1251] eta: 0:00:32 lr: 0.000829 loss: 3.7650 (3.5745) grad_norm: 1.1472 (inf) time: 0.6343 [2021-03-26 16:51:00 swin_base_patch4_window7_224] INFO: Epoch: [81] [1210/1251] eta: 0:00:25 lr: 0.000829 loss: 3.5958 (3.5734) grad_norm: 1.1047 (inf) time: 0.6261 [2021-03-26 16:51:06 swin_base_patch4_window7_224] INFO: Epoch: [81] [1220/1251] eta: 0:00:19 lr: 0.000829 loss: 3.5958 (3.5740) grad_norm: 1.1421 (inf) time: 0.6254 [2021-03-26 16:51:12 swin_base_patch4_window7_224] INFO: Epoch: [81] [1230/1251] eta: 0:00:13 lr: 0.000829 loss: 3.7172 (3.5751) grad_norm: 1.1421 (inf) time: 0.6268 [2021-03-26 16:51:18 swin_base_patch4_window7_224] INFO: Epoch: [81] [1240/1251] eta: 0:00:06 lr: 0.000828 loss: 3.6316 (3.5747) grad_norm: 1.1035 (inf) time: 0.6258 [2021-03-26 16:51:25 swin_base_patch4_window7_224] INFO: Epoch: [81] [1250/1251] eta: 0:00:00 lr: 0.000828 loss: 3.6478 (3.5766) grad_norm: 1.0478 (inf) time: 0.6223 [2021-03-26 16:51:31 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:24 loss: 1.1031 (1.1031) acc1: 81.2500 (81.2500) acc5: 92.1875 (92.1875) [2021-03-26 16:51:33 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.0164 (0.9742) acc1: 78.1250 (77.6989) acc5: 93.7500 (93.8920) [2021-03-26 16:51:35 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9722 (0.9892) acc1: 76.5625 (77.0089) acc5: 93.7500 (93.6756) [2021-03-26 16:51:37 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0608 (1.0538) acc1: 73.4375 (74.8488) acc5: 92.1875 (93.2460) [2021-03-26 16:51:39 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0561 (1.0310) acc1: 75.0000 (75.3811) acc5: 93.7500 (93.7500) [2021-03-26 16:51:41 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0561 (1.0522) acc1: 73.4375 (74.7840) acc5: 92.1875 (93.1840) [2021-03-26 16:51:45 swin_base_patch4_window7_224] INFO: * Acc@1 75.634 Acc@5 93.256 loss 1.038 [2021-03-26 16:51:45 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.6% [2021-03-26 16:51:45 swin_base_patch4_window7_224] INFO: Max accuracy: 75.63% [2021-03-26 16:51:49 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 0/1251] eta: 1:23:54 lr: 0.000828 loss: 2.3636 (2.3636) grad_norm: 1.0553 (1.0553) time: 4.0245 [2021-03-26 16:51:56 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 10/1251] eta: 0:19:47 lr: 0.000828 loss: 3.7589 (3.5396) grad_norm: 1.1908 (1.1776) time: 0.9570 [2021-03-26 16:52:02 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 20/1251] eta: 0:16:21 lr: 0.000828 loss: 3.5915 (3.5247) grad_norm: 1.1417 (1.1677) time: 0.6363 [2021-03-26 16:52:08 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 30/1251] eta: 0:15:06 lr: 0.000828 loss: 3.5231 (3.5273) grad_norm: 1.0968 (1.1429) time: 0.6243 [2021-03-26 16:52:15 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 40/1251] eta: 0:14:26 lr: 0.000828 loss: 3.7263 (3.5844) grad_norm: 1.1271 (1.1695) time: 0.6298 [2021-03-26 16:52:21 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 50/1251] eta: 0:13:57 lr: 0.000828 loss: 3.7191 (3.6062) grad_norm: 1.1318 (1.1770) time: 0.6280 [2021-03-26 16:52:27 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 60/1251] eta: 0:13:37 lr: 0.000828 loss: 3.4975 (3.5679) grad_norm: 1.1157 (1.1616) time: 0.6272 [2021-03-26 16:52:33 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 70/1251] eta: 0:13:21 lr: 0.000828 loss: 3.4547 (3.5717) grad_norm: 1.0869 (1.1527) time: 0.6293 [2021-03-26 16:52:40 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 80/1251] eta: 0:13:06 lr: 0.000828 loss: 3.4070 (3.5362) grad_norm: 1.1538 (1.1684) time: 0.6257 [2021-03-26 16:52:46 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 90/1251] eta: 0:12:53 lr: 0.000828 loss: 3.3686 (3.5452) grad_norm: 1.1857 (1.1702) time: 0.6234 [2021-03-26 16:52:52 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 100/1251] eta: 0:12:43 lr: 0.000828 loss: 3.6451 (3.5473) grad_norm: 1.1676 (1.1689) time: 0.6280 [2021-03-26 16:52:58 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 110/1251] eta: 0:12:33 lr: 0.000828 loss: 3.6600 (3.5570) grad_norm: 1.1046 (1.1626) time: 0.6318 [2021-03-26 16:53:05 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 120/1251] eta: 0:12:23 lr: 0.000828 loss: 3.7453 (3.5577) grad_norm: 1.0848 (1.1597) time: 0.6289 [2021-03-26 16:53:11 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 130/1251] eta: 0:12:14 lr: 0.000828 loss: 3.6968 (3.5523) grad_norm: 1.1372 (1.1610) time: 0.6315 [2021-03-26 16:53:17 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 140/1251] eta: 0:12:06 lr: 0.000828 loss: 3.7238 (3.5652) grad_norm: 1.2196 (1.1611) time: 0.6361 [2021-03-26 16:53:24 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 150/1251] eta: 0:11:58 lr: 0.000828 loss: 3.7601 (3.5733) grad_norm: 1.0883 (1.1566) time: 0.6297 [2021-03-26 16:53:30 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 160/1251] eta: 0:11:49 lr: 0.000828 loss: 3.7613 (3.5836) grad_norm: 1.0761 (1.1551) time: 0.6224 [2021-03-26 16:53:36 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 170/1251] eta: 0:11:41 lr: 0.000828 loss: 3.7098 (3.5736) grad_norm: 1.0678 (1.1497) time: 0.6246 [2021-03-26 16:53:43 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 180/1251] eta: 0:11:34 lr: 0.000828 loss: 3.6329 (3.5820) grad_norm: 1.0884 (1.1507) time: 0.6300 [2021-03-26 16:53:49 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 190/1251] eta: 0:11:26 lr: 0.000828 loss: 3.8353 (3.5929) grad_norm: 1.1211 (1.1525) time: 0.6317 [2021-03-26 16:53:55 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 200/1251] eta: 0:11:19 lr: 0.000828 loss: 3.6992 (3.5865) grad_norm: 1.1242 (1.1535) time: 0.6337 [2021-03-26 16:54:01 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 210/1251] eta: 0:11:12 lr: 0.000828 loss: 3.3987 (3.5808) grad_norm: 1.1546 (1.1575) time: 0.6333 [2021-03-26 16:54:08 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 220/1251] eta: 0:11:04 lr: 0.000828 loss: 3.3217 (3.5698) grad_norm: 1.1622 (1.1603) time: 0.6264 [2021-03-26 16:54:14 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 230/1251] eta: 0:10:57 lr: 0.000828 loss: 3.5888 (3.5742) grad_norm: 1.1582 (1.1612) time: 0.6243 [2021-03-26 16:54:20 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 240/1251] eta: 0:10:50 lr: 0.000828 loss: 3.6955 (3.5734) grad_norm: 1.1339 (1.1617) time: 0.6256 [2021-03-26 16:54:27 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 250/1251] eta: 0:10:43 lr: 0.000828 loss: 3.6435 (3.5709) grad_norm: 1.2081 (1.1652) time: 0.6281 [2021-03-26 16:54:33 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 260/1251] eta: 0:10:36 lr: 0.000828 loss: 3.7874 (3.5773) grad_norm: 1.1913 (1.1650) time: 0.6294 [2021-03-26 16:54:39 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 270/1251] eta: 0:10:29 lr: 0.000828 loss: 3.7571 (3.5774) grad_norm: 1.0858 (1.1632) time: 0.6255 [2021-03-26 16:54:45 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 280/1251] eta: 0:10:22 lr: 0.000828 loss: 3.6481 (3.5787) grad_norm: 1.0697 (1.1613) time: 0.6266 [2021-03-26 16:54:52 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 290/1251] eta: 0:10:15 lr: 0.000828 loss: 3.8097 (3.5856) grad_norm: 1.1530 (1.1629) time: 0.6265 [2021-03-26 16:54:58 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 300/1251] eta: 0:10:08 lr: 0.000828 loss: 3.5465 (3.5755) grad_norm: 1.1530 (1.1613) time: 0.6211 [2021-03-26 16:55:04 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 310/1251] eta: 0:10:01 lr: 0.000827 loss: 3.6996 (3.5768) grad_norm: 1.1180 (1.1618) time: 0.6239 [2021-03-26 16:55:10 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 320/1251] eta: 0:09:55 lr: 0.000827 loss: 3.6805 (3.5698) grad_norm: 1.1546 (1.1615) time: 0.6299 [2021-03-26 16:55:17 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 330/1251] eta: 0:09:48 lr: 0.000827 loss: 3.5839 (3.5732) grad_norm: 1.0832 (1.1595) time: 0.6333 [2021-03-26 16:55:23 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 340/1251] eta: 0:09:41 lr: 0.000827 loss: 3.7808 (3.5758) grad_norm: 1.0484 (1.1595) time: 0.6306 [2021-03-26 16:55:29 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 350/1251] eta: 0:09:34 lr: 0.000827 loss: 3.7704 (3.5737) grad_norm: 1.0656 (1.1580) time: 0.6233 [2021-03-26 16:55:36 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 360/1251] eta: 0:09:28 lr: 0.000827 loss: 3.5764 (3.5785) grad_norm: 1.0793 (1.1558) time: 0.6264 [2021-03-26 16:55:42 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 370/1251] eta: 0:09:21 lr: 0.000827 loss: 3.7442 (3.5775) grad_norm: 1.0964 (1.1555) time: 0.6327 [2021-03-26 16:55:48 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 380/1251] eta: 0:09:15 lr: 0.000827 loss: 3.7044 (3.5776) grad_norm: 1.1210 (1.1559) time: 0.6281 [2021-03-26 16:55:54 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 390/1251] eta: 0:09:08 lr: 0.000827 loss: 3.5283 (3.5775) grad_norm: 1.1265 (1.1568) time: 0.6283 [2021-03-26 16:56:01 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 400/1251] eta: 0:09:02 lr: 0.000827 loss: 3.6211 (3.5795) grad_norm: 1.1265 (1.1565) time: 0.6302 [2021-03-26 16:56:07 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 410/1251] eta: 0:08:55 lr: 0.000827 loss: 3.7079 (3.5831) grad_norm: 1.1455 (1.1573) time: 0.6257 [2021-03-26 16:56:13 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 420/1251] eta: 0:08:48 lr: 0.000827 loss: 3.7079 (3.5804) grad_norm: 1.1411 (1.1570) time: 0.6264 [2021-03-26 16:56:20 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 430/1251] eta: 0:08:42 lr: 0.000827 loss: 3.4468 (3.5760) grad_norm: 1.1418 (1.1573) time: 0.6302 [2021-03-26 16:56:26 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 440/1251] eta: 0:08:36 lr: 0.000827 loss: 3.4980 (3.5747) grad_norm: 1.1418 (1.1580) time: 0.6296 [2021-03-26 16:56:32 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 450/1251] eta: 0:08:29 lr: 0.000827 loss: 3.5643 (3.5764) grad_norm: 1.0730 (1.1557) time: 0.6267 [2021-03-26 16:56:38 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 460/1251] eta: 0:08:23 lr: 0.000827 loss: 3.7304 (3.5757) grad_norm: 1.1277 (1.1574) time: 0.6305 [2021-03-26 16:56:45 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 470/1251] eta: 0:08:16 lr: 0.000827 loss: 3.6561 (3.5711) grad_norm: 1.2099 (1.1591) time: 0.6321 [2021-03-26 16:56:51 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 480/1251] eta: 0:08:10 lr: 0.000827 loss: 3.4463 (3.5672) grad_norm: 1.2099 (1.1600) time: 0.6271 [2021-03-26 16:56:57 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 490/1251] eta: 0:08:03 lr: 0.000827 loss: 3.7032 (3.5697) grad_norm: 1.1551 (1.1594) time: 0.6298 [2021-03-26 16:57:04 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 500/1251] eta: 0:07:57 lr: 0.000827 loss: 3.7032 (3.5686) grad_norm: 1.0696 (1.1576) time: 0.6299 [2021-03-26 16:57:10 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 510/1251] eta: 0:07:50 lr: 0.000827 loss: 3.5332 (3.5670) grad_norm: 1.0734 (1.1571) time: 0.6244 [2021-03-26 16:57:16 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 520/1251] eta: 0:07:44 lr: 0.000827 loss: 3.6653 (3.5657) grad_norm: 1.1070 (1.1570) time: 0.6207 [2021-03-26 16:57:22 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 530/1251] eta: 0:07:37 lr: 0.000827 loss: 3.5650 (3.5677) grad_norm: 1.1434 (1.1561) time: 0.6187 [2021-03-26 16:57:28 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 540/1251] eta: 0:07:31 lr: 0.000827 loss: 3.8417 (3.5702) grad_norm: 1.1180 (1.1557) time: 0.6207 [2021-03-26 16:57:35 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 550/1251] eta: 0:07:24 lr: 0.000827 loss: 3.8417 (3.5705) grad_norm: 1.0900 (1.1541) time: 0.6324 [2021-03-26 16:57:41 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 560/1251] eta: 0:07:18 lr: 0.000827 loss: 3.4394 (3.5678) grad_norm: 1.0900 (1.1541) time: 0.6370 [2021-03-26 16:57:47 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 570/1251] eta: 0:07:12 lr: 0.000827 loss: 3.5249 (3.5675) grad_norm: 1.1421 (1.1536) time: 0.6317 [2021-03-26 16:57:54 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 580/1251] eta: 0:07:05 lr: 0.000827 loss: 3.9109 (3.5730) grad_norm: 1.1656 (1.1541) time: 0.6264 [2021-03-26 16:58:00 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 590/1251] eta: 0:06:59 lr: 0.000827 loss: 3.5443 (3.5688) grad_norm: 1.1037 (1.1533) time: 0.6255 [2021-03-26 16:58:06 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 600/1251] eta: 0:06:52 lr: 0.000827 loss: 3.1863 (3.5650) grad_norm: 1.0738 (1.1532) time: 0.6301 [2021-03-26 16:58:13 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 610/1251] eta: 0:06:46 lr: 0.000827 loss: 3.7469 (3.5678) grad_norm: 1.1435 (1.1537) time: 0.6298 [2021-03-26 16:58:19 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 620/1251] eta: 0:06:39 lr: 0.000826 loss: 3.6821 (3.5686) grad_norm: 1.1435 (1.1538) time: 0.6295 [2021-03-26 16:58:25 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 630/1251] eta: 0:06:33 lr: 0.000826 loss: 3.7656 (3.5723) grad_norm: 1.2083 (1.1554) time: 0.6279 [2021-03-26 16:58:31 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 640/1251] eta: 0:06:27 lr: 0.000826 loss: 3.7656 (3.5708) grad_norm: 1.2592 (1.1580) time: 0.6230 [2021-03-26 16:58:38 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 650/1251] eta: 0:06:20 lr: 0.000826 loss: 3.6580 (3.5732) grad_norm: 1.3056 (1.1610) time: 0.6219 [2021-03-26 16:58:44 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 660/1251] eta: 0:06:14 lr: 0.000826 loss: 3.8860 (3.5758) grad_norm: 1.2105 (1.1621) time: 0.6286 [2021-03-26 16:58:50 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 670/1251] eta: 0:06:08 lr: 0.000826 loss: 3.7499 (3.5708) grad_norm: 1.2086 (1.1634) time: 0.6378 [2021-03-26 16:58:57 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 680/1251] eta: 0:06:01 lr: 0.000826 loss: 3.2871 (3.5689) grad_norm: 1.1984 (1.1636) time: 0.6402 [2021-03-26 16:59:03 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 690/1251] eta: 0:05:55 lr: 0.000826 loss: 3.5929 (3.5702) grad_norm: 1.1631 (1.1643) time: 0.6374 [2021-03-26 16:59:09 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 700/1251] eta: 0:05:49 lr: 0.000826 loss: 3.7409 (3.5721) grad_norm: 1.1631 (1.1646) time: 0.6328 [2021-03-26 16:59:16 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 710/1251] eta: 0:05:42 lr: 0.000826 loss: 3.7500 (3.5722) grad_norm: 1.2120 (1.1647) time: 0.6250 [2021-03-26 16:59:22 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 720/1251] eta: 0:05:36 lr: 0.000826 loss: 3.7448 (3.5720) grad_norm: 1.1462 (1.1645) time: 0.6325 [2021-03-26 16:59:29 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 730/1251] eta: 0:05:30 lr: 0.000826 loss: 3.5687 (3.5712) grad_norm: 1.1560 (1.1651) time: 0.6446 [2021-03-26 16:59:35 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 740/1251] eta: 0:05:23 lr: 0.000826 loss: 3.5452 (3.5710) grad_norm: 1.1090 (1.1641) time: 0.6522 [2021-03-26 16:59:41 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 750/1251] eta: 0:05:17 lr: 0.000826 loss: 3.7116 (3.5733) grad_norm: 1.1295 (1.1658) time: 0.6480 [2021-03-26 16:59:48 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 760/1251] eta: 0:05:11 lr: 0.000826 loss: 3.7116 (3.5741) grad_norm: 1.2281 (1.1666) time: 0.6344 [2021-03-26 16:59:54 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 770/1251] eta: 0:05:04 lr: 0.000826 loss: 3.3346 (3.5697) grad_norm: 1.1468 (1.1659) time: 0.6277 [2021-03-26 17:00:00 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 780/1251] eta: 0:04:58 lr: 0.000826 loss: 3.3346 (3.5687) grad_norm: 1.1080 (1.1653) time: 0.6227 [2021-03-26 17:00:07 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 790/1251] eta: 0:04:52 lr: 0.000826 loss: 3.6968 (3.5716) grad_norm: 1.1057 (1.1643) time: 0.6271 [2021-03-26 17:00:13 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 800/1251] eta: 0:04:45 lr: 0.000826 loss: 3.8045 (3.5722) grad_norm: 1.1064 (1.1653) time: 0.6293 [2021-03-26 17:00:19 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 810/1251] eta: 0:04:39 lr: 0.000826 loss: 3.8114 (3.5752) grad_norm: 1.1123 (1.1644) time: 0.6262 [2021-03-26 17:00:25 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 820/1251] eta: 0:04:33 lr: 0.000826 loss: 3.8369 (3.5776) grad_norm: 1.1101 (1.1650) time: 0.6278 [2021-03-26 17:00:32 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 830/1251] eta: 0:04:26 lr: 0.000826 loss: 3.8480 (3.5806) grad_norm: 1.1374 (1.1653) time: 0.6261 [2021-03-26 17:00:38 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 840/1251] eta: 0:04:20 lr: 0.000826 loss: 3.9700 (3.5838) grad_norm: 1.1618 (1.1652) time: 0.6282 [2021-03-26 17:00:44 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 850/1251] eta: 0:04:13 lr: 0.000826 loss: 3.8215 (3.5846) grad_norm: 1.1290 (1.1668) time: 0.6308 [2021-03-26 17:00:50 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 860/1251] eta: 0:04:07 lr: 0.000826 loss: 3.7117 (3.5819) grad_norm: 1.1290 (1.1662) time: 0.6234 [2021-03-26 17:00:57 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 870/1251] eta: 0:04:01 lr: 0.000826 loss: 3.2632 (3.5777) grad_norm: 1.1464 (1.1663) time: 0.6216 [2021-03-26 17:01:03 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 880/1251] eta: 0:03:54 lr: 0.000826 loss: 3.4804 (3.5771) grad_norm: 1.1709 (1.1665) time: 0.6322 [2021-03-26 17:01:09 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 890/1251] eta: 0:03:48 lr: 0.000826 loss: 3.6498 (3.5769) grad_norm: 1.1331 (1.1653) time: 0.6327 [2021-03-26 17:01:16 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 900/1251] eta: 0:03:42 lr: 0.000826 loss: 3.7451 (3.5779) grad_norm: 1.0825 (1.1647) time: 0.6223 [2021-03-26 17:01:22 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 910/1251] eta: 0:03:35 lr: 0.000826 loss: 3.6737 (3.5764) grad_norm: 1.1438 (1.1654) time: 0.6282 [2021-03-26 17:01:28 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 920/1251] eta: 0:03:29 lr: 0.000826 loss: 3.6010 (3.5770) grad_norm: 1.2133 (1.1667) time: 0.6355 [2021-03-26 17:01:35 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 930/1251] eta: 0:03:23 lr: 0.000826 loss: 3.6506 (3.5782) grad_norm: 1.1986 (1.1673) time: 0.6373 [2021-03-26 17:01:41 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 940/1251] eta: 0:03:16 lr: 0.000825 loss: 3.5634 (3.5777) grad_norm: 1.1967 (1.1673) time: 0.6363 [2021-03-26 17:01:47 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 950/1251] eta: 0:03:10 lr: 0.000825 loss: 3.5634 (3.5778) grad_norm: 1.2276 (1.1676) time: 0.6336 [2021-03-26 17:01:54 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 960/1251] eta: 0:03:04 lr: 0.000825 loss: 3.7348 (3.5800) grad_norm: 1.2032 (1.1681) time: 0.6319 [2021-03-26 17:02:00 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 970/1251] eta: 0:02:57 lr: 0.000825 loss: 3.6287 (3.5747) grad_norm: 1.1601 (1.1683) time: 0.6285 [2021-03-26 17:02:06 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 980/1251] eta: 0:02:51 lr: 0.000825 loss: 3.6287 (3.5768) grad_norm: 1.1418 (1.1680) time: 0.6281 [2021-03-26 17:02:13 swin_base_patch4_window7_224] INFO: Epoch: [82] [ 990/1251] eta: 0:02:45 lr: 0.000825 loss: 3.8370 (3.5789) grad_norm: 1.1869 (1.1693) time: 0.6305 [2021-03-26 17:02:19 swin_base_patch4_window7_224] INFO: Epoch: [82] [1000/1251] eta: 0:02:38 lr: 0.000825 loss: 3.8165 (3.5777) grad_norm: 1.1924 (1.1695) time: 0.6296 [2021-03-26 17:02:25 swin_base_patch4_window7_224] INFO: Epoch: [82] [1010/1251] eta: 0:02:32 lr: 0.000825 loss: 3.4601 (3.5769) grad_norm: 1.1537 (1.1692) time: 0.6242 [2021-03-26 17:02:31 swin_base_patch4_window7_224] INFO: Epoch: [82] [1020/1251] eta: 0:02:26 lr: 0.000825 loss: 3.4774 (3.5757) grad_norm: 1.2149 (1.1700) time: 0.6262 [2021-03-26 17:02:38 swin_base_patch4_window7_224] INFO: Epoch: [82] [1030/1251] eta: 0:02:19 lr: 0.000825 loss: 3.4774 (3.5743) grad_norm: 1.2182 (1.1697) time: 0.6267 [2021-03-26 17:02:44 swin_base_patch4_window7_224] INFO: Epoch: [82] [1040/1251] eta: 0:02:13 lr: 0.000825 loss: 3.6183 (3.5747) grad_norm: 1.1899 (1.1702) time: 0.6275 [2021-03-26 17:02:50 swin_base_patch4_window7_224] INFO: Epoch: [82] [1050/1251] eta: 0:02:07 lr: 0.000825 loss: 3.5939 (3.5739) grad_norm: 1.1586 (1.1699) time: 0.6267 [2021-03-26 17:02:56 swin_base_patch4_window7_224] INFO: Epoch: [82] [1060/1251] eta: 0:02:00 lr: 0.000825 loss: 3.4218 (3.5745) grad_norm: 1.1228 (1.1699) time: 0.6222 [2021-03-26 17:03:03 swin_base_patch4_window7_224] INFO: Epoch: [82] [1070/1251] eta: 0:01:54 lr: 0.000825 loss: 3.6768 (3.5747) grad_norm: 1.1140 (1.1697) time: 0.6322 [2021-03-26 17:03:09 swin_base_patch4_window7_224] INFO: Epoch: [82] [1080/1251] eta: 0:01:48 lr: 0.000825 loss: 3.6768 (3.5733) grad_norm: 1.1313 (1.1699) time: 0.6351 [2021-03-26 17:03:15 swin_base_patch4_window7_224] INFO: Epoch: [82] [1090/1251] eta: 0:01:41 lr: 0.000825 loss: 3.6628 (3.5745) grad_norm: 1.1313 (1.1694) time: 0.6271 [2021-03-26 17:03:21 swin_base_patch4_window7_224] INFO: Epoch: [82] [1100/1251] eta: 0:01:35 lr: 0.000825 loss: 3.7222 (3.5746) grad_norm: 1.0962 (1.1689) time: 0.6241 [2021-03-26 17:03:28 swin_base_patch4_window7_224] INFO: Epoch: [82] [1110/1251] eta: 0:01:29 lr: 0.000825 loss: 3.7222 (3.5743) grad_norm: 1.0962 (1.1687) time: 0.6233 [2021-03-26 17:03:34 swin_base_patch4_window7_224] INFO: Epoch: [82] [1120/1251] eta: 0:01:22 lr: 0.000825 loss: 3.7181 (3.5740) grad_norm: 1.1829 (1.1698) time: 0.6295 [2021-03-26 17:03:40 swin_base_patch4_window7_224] INFO: Epoch: [82] [1130/1251] eta: 0:01:16 lr: 0.000825 loss: 3.4956 (3.5733) grad_norm: 1.2273 (1.1698) time: 0.6277 [2021-03-26 17:03:47 swin_base_patch4_window7_224] INFO: Epoch: [82] [1140/1251] eta: 0:01:10 lr: 0.000825 loss: 3.4678 (3.5726) grad_norm: 1.1661 (1.1699) time: 0.6260 [2021-03-26 17:03:53 swin_base_patch4_window7_224] INFO: Epoch: [82] [1150/1251] eta: 0:01:03 lr: 0.000825 loss: 3.6994 (3.5724) grad_norm: 1.1128 (1.1699) time: 0.6338 [2021-03-26 17:03:59 swin_base_patch4_window7_224] INFO: Epoch: [82] [1160/1251] eta: 0:00:57 lr: 0.000825 loss: 3.5009 (3.5711) grad_norm: 1.1654 (1.1705) time: 0.6374 [2021-03-26 17:04:06 swin_base_patch4_window7_224] INFO: Epoch: [82] [1170/1251] eta: 0:00:51 lr: 0.000825 loss: 3.4337 (3.5700) grad_norm: 1.2300 (1.1710) time: 0.6312 [2021-03-26 17:04:12 swin_base_patch4_window7_224] INFO: Epoch: [82] [1180/1251] eta: 0:00:44 lr: 0.000825 loss: 3.5799 (3.5698) grad_norm: 1.1817 (1.1709) time: 0.6241 [2021-03-26 17:04:18 swin_base_patch4_window7_224] INFO: Epoch: [82] [1190/1251] eta: 0:00:38 lr: 0.000825 loss: 3.5799 (3.5678) grad_norm: 1.1474 (1.1709) time: 0.6258 [2021-03-26 17:04:24 swin_base_patch4_window7_224] INFO: Epoch: [82] [1200/1251] eta: 0:00:32 lr: 0.000825 loss: 3.6305 (3.5689) grad_norm: 1.1484 (1.1722) time: 0.6266 [2021-03-26 17:04:31 swin_base_patch4_window7_224] INFO: Epoch: [82] [1210/1251] eta: 0:00:25 lr: 0.000825 loss: 3.6204 (3.5696) grad_norm: 1.1984 (1.1724) time: 0.6304 [2021-03-26 17:04:37 swin_base_patch4_window7_224] INFO: Epoch: [82] [1220/1251] eta: 0:00:19 lr: 0.000825 loss: 3.5331 (3.5687) grad_norm: 1.1838 (1.1728) time: 0.6272 [2021-03-26 17:04:43 swin_base_patch4_window7_224] INFO: Epoch: [82] [1230/1251] eta: 0:00:13 lr: 0.000825 loss: 3.5800 (3.5694) grad_norm: 1.1440 (1.1734) time: 0.6212 [2021-03-26 17:04:49 swin_base_patch4_window7_224] INFO: Epoch: [82] [1240/1251] eta: 0:00:06 lr: 0.000825 loss: 3.6658 (3.5693) grad_norm: 1.1993 (1.1735) time: 0.6239 [2021-03-26 17:04:56 swin_base_patch4_window7_224] INFO: Epoch: [82] [1250/1251] eta: 0:00:00 lr: 0.000825 loss: 3.6115 (3.5685) grad_norm: 1.1993 (1.1737) time: 0.6184 [2021-03-26 17:05:01 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:25 loss: 1.0369 (1.0369) acc1: 76.5625 (76.5625) acc5: 90.6250 (90.6250) [2021-03-26 17:05:03 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.1149 (1.1712) acc1: 73.4375 (71.8750) acc5: 92.1875 (91.9034) [2021-03-26 17:05:05 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.1149 (1.1219) acc1: 75.0000 (74.0327) acc5: 92.1875 (92.1131) [2021-03-26 17:05:07 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9824 (1.0763) acc1: 78.1250 (75.5544) acc5: 93.7500 (92.9435) [2021-03-26 17:05:08 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9956 (1.0829) acc1: 75.0000 (75.1524) acc5: 93.7500 (92.7973) [2021-03-26 17:05:09 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0437 (1.0718) acc1: 75.0000 (75.2640) acc5: 93.7500 (93.1840) [2021-03-26 17:05:15 swin_base_patch4_window7_224] INFO: * Acc@1 75.776 Acc@5 93.342 loss 1.055 [2021-03-26 17:05:15 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.8% [2021-03-26 17:05:15 swin_base_patch4_window7_224] INFO: Max accuracy: 75.78% [2021-03-26 17:05:19 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 0/1251] eta: 1:28:54 lr: 0.000825 loss: 3.3489 (3.3489) grad_norm: 1.2540 (1.2540) time: 4.2645 [2021-03-26 17:05:26 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 10/1251] eta: 0:20:20 lr: 0.000824 loss: 3.4151 (3.5093) grad_norm: 1.1411 (1.1369) time: 0.9837 [2021-03-26 17:05:32 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 20/1251] eta: 0:16:46 lr: 0.000824 loss: 3.4516 (3.5432) grad_norm: 1.1343 (1.1343) time: 0.6454 [2021-03-26 17:05:38 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 30/1251] eta: 0:15:23 lr: 0.000824 loss: 3.4569 (3.5865) grad_norm: 1.1414 (1.1588) time: 0.6310 [2021-03-26 17:05:45 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 40/1251] eta: 0:14:41 lr: 0.000824 loss: 3.6285 (3.5933) grad_norm: 1.1414 (1.1521) time: 0.6331 [2021-03-26 17:05:51 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 50/1251] eta: 0:14:13 lr: 0.000824 loss: 3.6919 (3.6262) grad_norm: 1.1465 (1.1615) time: 0.6393 [2021-03-26 17:05:57 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 60/1251] eta: 0:13:52 lr: 0.000824 loss: 3.6919 (3.6557) grad_norm: 1.2837 (1.1828) time: 0.6408 [2021-03-26 17:06:04 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 70/1251] eta: 0:13:32 lr: 0.000824 loss: 3.6591 (3.6246) grad_norm: 1.2837 (1.1946) time: 0.6318 [2021-03-26 17:06:10 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 80/1251] eta: 0:13:17 lr: 0.000824 loss: 3.8048 (3.6559) grad_norm: 1.1680 (1.1852) time: 0.6249 [2021-03-26 17:06:16 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 90/1251] eta: 0:13:02 lr: 0.000824 loss: 3.7648 (3.6596) grad_norm: 1.0413 (1.1693) time: 0.6234 [2021-03-26 17:06:22 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 100/1251] eta: 0:12:49 lr: 0.000824 loss: 3.7445 (3.6774) grad_norm: 1.0343 (1.1741) time: 0.6193 [2021-03-26 17:06:29 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 110/1251] eta: 0:12:38 lr: 0.000824 loss: 3.7445 (3.6715) grad_norm: 1.0856 (1.1667) time: 0.6231 [2021-03-26 17:06:35 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 120/1251] eta: 0:12:30 lr: 0.000824 loss: 3.6984 (3.6802) grad_norm: 1.1269 (1.1712) time: 0.6366 [2021-03-26 17:06:41 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 130/1251] eta: 0:12:20 lr: 0.000824 loss: 3.4982 (3.6500) grad_norm: 1.2283 (1.1770) time: 0.6391 [2021-03-26 17:06:48 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 140/1251] eta: 0:12:12 lr: 0.000824 loss: 3.4982 (3.6559) grad_norm: 1.1766 (1.1724) time: 0.6323 [2021-03-26 17:06:54 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 150/1251] eta: 0:12:03 lr: 0.000824 loss: 3.8044 (3.6456) grad_norm: 1.1082 (1.1723) time: 0.6297 [2021-03-26 17:07:00 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 160/1251] eta: 0:11:54 lr: 0.000824 loss: 3.6103 (3.6405) grad_norm: 1.1350 (1.1715) time: 0.6239 [2021-03-26 17:07:07 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 170/1251] eta: 0:11:46 lr: 0.000824 loss: 3.6103 (3.6376) grad_norm: 1.1350 (1.1734) time: 0.6295 [2021-03-26 17:07:13 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 180/1251] eta: 0:11:38 lr: 0.000824 loss: 3.5879 (3.6318) grad_norm: 1.1301 (1.1715) time: 0.6325 [2021-03-26 17:07:19 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 190/1251] eta: 0:11:31 lr: 0.000824 loss: 3.5993 (3.6250) grad_norm: 1.1780 (1.1741) time: 0.6351 [2021-03-26 17:07:26 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 200/1251] eta: 0:11:24 lr: 0.000824 loss: 3.5141 (3.6207) grad_norm: 1.2097 (1.1772) time: 0.6393 [2021-03-26 17:07:32 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 210/1251] eta: 0:11:16 lr: 0.000824 loss: 3.5141 (3.6172) grad_norm: 1.1381 (1.1779) time: 0.6299 [2021-03-26 17:07:38 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 220/1251] eta: 0:11:08 lr: 0.000824 loss: 3.8350 (3.6233) grad_norm: 1.0807 (1.1730) time: 0.6217 [2021-03-26 17:07:44 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 230/1251] eta: 0:11:00 lr: 0.000824 loss: 3.9273 (3.6277) grad_norm: 1.0940 (1.1711) time: 0.6208 [2021-03-26 17:07:51 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 240/1251] eta: 0:10:53 lr: 0.000824 loss: 3.7223 (3.6278) grad_norm: 1.1363 (1.1726) time: 0.6259 [2021-03-26 17:07:57 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 250/1251] eta: 0:10:46 lr: 0.000824 loss: 3.5630 (3.6151) grad_norm: 1.1389 (1.1718) time: 0.6279 [2021-03-26 17:08:03 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 260/1251] eta: 0:10:39 lr: 0.000824 loss: 3.3192 (3.6072) grad_norm: 1.1639 (1.1747) time: 0.6346 [2021-03-26 17:08:10 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 270/1251] eta: 0:10:33 lr: 0.000824 loss: 3.3192 (3.6007) grad_norm: 1.2657 (1.1787) time: 0.6463 [2021-03-26 17:08:16 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 280/1251] eta: 0:10:26 lr: 0.000824 loss: 3.5363 (3.5992) grad_norm: 1.2214 (1.1834) time: 0.6424 [2021-03-26 17:08:22 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 290/1251] eta: 0:10:19 lr: 0.000824 loss: 3.5721 (3.5962) grad_norm: 1.1892 (1.1865) time: 0.6328 [2021-03-26 17:08:29 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 300/1251] eta: 0:10:12 lr: 0.000824 loss: 3.5721 (3.5995) grad_norm: 1.1970 (1.1870) time: 0.6283 [2021-03-26 17:08:35 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 310/1251] eta: 0:10:05 lr: 0.000824 loss: 3.4834 (3.5868) grad_norm: 1.1741 (1.1857) time: 0.6299 [2021-03-26 17:08:41 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 320/1251] eta: 0:09:59 lr: 0.000823 loss: 3.4693 (3.5854) grad_norm: 1.1080 (1.1850) time: 0.6337 [2021-03-26 17:08:48 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 330/1251] eta: 0:09:52 lr: 0.000823 loss: 3.6180 (3.5794) grad_norm: 1.1358 (1.1853) time: 0.6293 [2021-03-26 17:08:54 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 340/1251] eta: 0:09:45 lr: 0.000823 loss: 3.6483 (3.5861) grad_norm: 1.1369 (1.1833) time: 0.6293 [2021-03-26 17:09:00 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 350/1251] eta: 0:09:38 lr: 0.000823 loss: 3.7677 (3.5869) grad_norm: 1.1475 (1.1834) time: 0.6328 [2021-03-26 17:09:07 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 360/1251] eta: 0:09:32 lr: 0.000823 loss: 3.6498 (3.5845) grad_norm: 1.0985 (1.1806) time: 0.6310 [2021-03-26 17:09:13 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 370/1251] eta: 0:09:25 lr: 0.000823 loss: 3.6308 (3.5840) grad_norm: 1.0845 (1.1787) time: 0.6291 [2021-03-26 17:09:19 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 380/1251] eta: 0:09:18 lr: 0.000823 loss: 3.4832 (3.5824) grad_norm: 1.0994 (1.1774) time: 0.6217 [2021-03-26 17:09:25 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 390/1251] eta: 0:09:11 lr: 0.000823 loss: 3.5765 (3.5814) grad_norm: 1.1006 (1.1759) time: 0.6209 [2021-03-26 17:09:31 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 400/1251] eta: 0:09:04 lr: 0.000823 loss: 3.4718 (3.5788) grad_norm: 1.0926 (1.1753) time: 0.6251 [2021-03-26 17:09:38 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 410/1251] eta: 0:08:58 lr: 0.000823 loss: 3.5855 (3.5829) grad_norm: 1.1115 (1.1762) time: 0.6344 [2021-03-26 17:09:44 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 420/1251] eta: 0:08:51 lr: 0.000823 loss: 3.5871 (3.5789) grad_norm: 1.1375 (1.1766) time: 0.6317 [2021-03-26 17:09:50 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 430/1251] eta: 0:08:45 lr: 0.000823 loss: 3.4950 (3.5753) grad_norm: 1.1455 (1.1769) time: 0.6240 [2021-03-26 17:09:57 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 440/1251] eta: 0:08:38 lr: 0.000823 loss: 3.6504 (3.5750) grad_norm: 1.0962 (1.1752) time: 0.6315 [2021-03-26 17:10:03 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 450/1251] eta: 0:08:31 lr: 0.000823 loss: 3.3060 (3.5692) grad_norm: 1.0637 (1.1739) time: 0.6324 [2021-03-26 17:10:09 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 460/1251] eta: 0:08:25 lr: 0.000823 loss: 3.2649 (3.5644) grad_norm: 1.0773 (1.1736) time: 0.6333 [2021-03-26 17:10:16 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 470/1251] eta: 0:08:19 lr: 0.000823 loss: 3.5094 (3.5663) grad_norm: 1.1058 (1.1727) time: 0.6335 [2021-03-26 17:10:22 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 480/1251] eta: 0:08:12 lr: 0.000823 loss: 3.7606 (3.5691) grad_norm: 1.1824 (1.1740) time: 0.6359 [2021-03-26 17:10:28 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 490/1251] eta: 0:08:06 lr: 0.000823 loss: 3.6165 (3.5694) grad_norm: 1.1986 (1.1746) time: 0.6368 [2021-03-26 17:10:35 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 500/1251] eta: 0:07:59 lr: 0.000823 loss: 3.4403 (3.5653) grad_norm: 1.1428 (1.1750) time: 0.6333 [2021-03-26 17:10:41 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 510/1251] eta: 0:07:53 lr: 0.000823 loss: 3.4534 (3.5684) grad_norm: 1.0809 (1.1724) time: 0.6275 [2021-03-26 17:10:47 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 520/1251] eta: 0:07:46 lr: 0.000823 loss: 3.4534 (3.5693) grad_norm: 1.0809 (1.1715) time: 0.6177 [2021-03-26 17:10:54 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 530/1251] eta: 0:07:39 lr: 0.000823 loss: 3.2880 (3.5616) grad_norm: 1.1392 (1.1713) time: 0.6269 [2021-03-26 17:11:00 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 540/1251] eta: 0:07:33 lr: 0.000823 loss: 3.4585 (3.5621) grad_norm: 1.1392 (1.1715) time: 0.6356 [2021-03-26 17:11:06 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 550/1251] eta: 0:07:27 lr: 0.000823 loss: 3.8111 (3.5646) grad_norm: 1.1476 (1.1722) time: 0.6373 [2021-03-26 17:11:13 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 560/1251] eta: 0:07:20 lr: 0.000823 loss: 3.7210 (3.5658) grad_norm: 1.1436 (1.1719) time: 0.6324 [2021-03-26 17:11:19 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 570/1251] eta: 0:07:14 lr: 0.000823 loss: 3.8135 (3.5721) grad_norm: 1.1436 (1.1733) time: 0.6279 [2021-03-26 17:11:25 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 580/1251] eta: 0:07:07 lr: 0.000823 loss: 3.7424 (3.5678) grad_norm: 1.1408 (1.1734) time: 0.6317 [2021-03-26 17:11:32 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 590/1251] eta: 0:07:01 lr: 0.000823 loss: 3.3082 (3.5636) grad_norm: 1.1315 (1.1733) time: 0.6315 [2021-03-26 17:11:38 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 600/1251] eta: 0:06:54 lr: 0.000823 loss: 3.4592 (3.5599) grad_norm: 1.0889 (1.1712) time: 0.6357 [2021-03-26 17:11:44 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 610/1251] eta: 0:06:48 lr: 0.000823 loss: 3.6828 (3.5624) grad_norm: 1.0830 (1.1757) time: 0.6340 [2021-03-26 17:11:50 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 620/1251] eta: 0:06:41 lr: 0.000823 loss: 3.8937 (3.5661) grad_norm: 1.1910 (1.1753) time: 0.6242 [2021-03-26 17:11:57 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 630/1251] eta: 0:06:35 lr: 0.000823 loss: 3.7940 (3.5647) grad_norm: 1.1697 (1.1754) time: 0.6244 [2021-03-26 17:12:03 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 640/1251] eta: 0:06:29 lr: 0.000822 loss: 3.5574 (3.5653) grad_norm: 1.1504 (1.1755) time: 0.6290 [2021-03-26 17:12:09 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 650/1251] eta: 0:06:22 lr: 0.000822 loss: 3.6766 (3.5668) grad_norm: 1.1285 (1.1747) time: 0.6303 [2021-03-26 17:12:16 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 660/1251] eta: 0:06:16 lr: 0.000822 loss: 3.6766 (3.5671) grad_norm: 1.1193 (1.1743) time: 0.6309 [2021-03-26 17:12:22 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 670/1251] eta: 0:06:09 lr: 0.000822 loss: 3.6823 (3.5658) grad_norm: 1.1591 (1.1744) time: 0.6329 [2021-03-26 17:12:28 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 680/1251] eta: 0:06:03 lr: 0.000822 loss: 3.6823 (3.5653) grad_norm: 1.1799 (1.1757) time: 0.6346 [2021-03-26 17:12:35 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 690/1251] eta: 0:05:57 lr: 0.000822 loss: 3.6308 (3.5643) grad_norm: 1.2846 (1.1780) time: 0.6305 [2021-03-26 17:12:41 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 700/1251] eta: 0:05:50 lr: 0.000822 loss: 3.5009 (3.5615) grad_norm: 1.3198 (1.1801) time: 0.6365 [2021-03-26 17:12:47 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 710/1251] eta: 0:05:44 lr: 0.000822 loss: 3.5015 (3.5622) grad_norm: 1.1857 (1.1796) time: 0.6372 [2021-03-26 17:12:54 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 720/1251] eta: 0:05:37 lr: 0.000822 loss: 3.6444 (3.5614) grad_norm: 1.1377 (1.1790) time: 0.6303 [2021-03-26 17:13:00 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 730/1251] eta: 0:05:31 lr: 0.000822 loss: 3.7218 (3.5594) grad_norm: 1.1628 (1.1792) time: 0.6387 [2021-03-26 17:13:06 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 740/1251] eta: 0:05:25 lr: 0.000822 loss: 3.5753 (3.5589) grad_norm: 1.0846 (1.1782) time: 0.6397 [2021-03-26 17:13:13 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 750/1251] eta: 0:05:18 lr: 0.000822 loss: 3.5753 (3.5617) grad_norm: 1.0814 (1.1771) time: 0.6389 [2021-03-26 17:13:19 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 760/1251] eta: 0:05:12 lr: 0.000822 loss: 3.7126 (3.5595) grad_norm: 1.1124 (1.1774) time: 0.6397 [2021-03-26 17:13:25 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 770/1251] eta: 0:05:06 lr: 0.000822 loss: 3.4363 (3.5581) grad_norm: 1.1324 (1.1769) time: 0.6294 [2021-03-26 17:13:32 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 780/1251] eta: 0:04:59 lr: 0.000822 loss: 3.9090 (3.5614) grad_norm: 1.1018 (1.1765) time: 0.6294 [2021-03-26 17:13:38 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 790/1251] eta: 0:04:53 lr: 0.000822 loss: 3.6840 (3.5614) grad_norm: 1.1514 (1.1767) time: 0.6277 [2021-03-26 17:13:44 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 800/1251] eta: 0:04:46 lr: 0.000822 loss: 3.5668 (3.5598) grad_norm: 1.1739 (1.1779) time: 0.6207 [2021-03-26 17:13:51 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 810/1251] eta: 0:04:40 lr: 0.000822 loss: 3.2372 (3.5551) grad_norm: 1.1413 (1.1788) time: 0.6253 [2021-03-26 17:13:57 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 820/1251] eta: 0:04:34 lr: 0.000822 loss: 3.5153 (3.5544) grad_norm: 1.1027 (1.1783) time: 0.6385 [2021-03-26 17:14:03 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 830/1251] eta: 0:04:27 lr: 0.000822 loss: 3.5406 (3.5532) grad_norm: 1.0926 (1.1777) time: 0.6444 [2021-03-26 17:14:10 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 840/1251] eta: 0:04:21 lr: 0.000822 loss: 3.4848 (3.5520) grad_norm: 1.1356 (1.1784) time: 0.6372 [2021-03-26 17:14:16 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 850/1251] eta: 0:04:15 lr: 0.000822 loss: 3.6921 (3.5515) grad_norm: 1.1555 (1.1786) time: 0.6320 [2021-03-26 17:14:22 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 860/1251] eta: 0:04:08 lr: 0.000822 loss: 3.5919 (3.5499) grad_norm: 1.1307 (1.1780) time: 0.6351 [2021-03-26 17:14:29 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 870/1251] eta: 0:04:02 lr: 0.000822 loss: 3.5919 (3.5508) grad_norm: 1.1525 (1.1785) time: 0.6355 [2021-03-26 17:14:35 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 880/1251] eta: 0:03:56 lr: 0.000822 loss: 3.6580 (3.5517) grad_norm: 1.1451 (1.1775) time: 0.6432 [2021-03-26 17:14:42 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 890/1251] eta: 0:03:49 lr: 0.000822 loss: 3.6580 (3.5544) grad_norm: 1.1451 (1.1777) time: 0.6376 [2021-03-26 17:14:48 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 900/1251] eta: 0:03:43 lr: 0.000822 loss: 3.6448 (3.5525) grad_norm: 1.1499 (1.1781) time: 0.6264 [2021-03-26 17:14:54 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 910/1251] eta: 0:03:36 lr: 0.000822 loss: 3.5390 (3.5552) grad_norm: 1.1499 (1.1775) time: 0.6274 [2021-03-26 17:15:00 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 920/1251] eta: 0:03:30 lr: 0.000822 loss: 3.7090 (3.5540) grad_norm: 1.1305 (1.1775) time: 0.6280 [2021-03-26 17:15:07 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 930/1251] eta: 0:03:24 lr: 0.000822 loss: 3.6162 (3.5527) grad_norm: 1.1279 (1.1774) time: 0.6313 [2021-03-26 17:15:13 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 940/1251] eta: 0:03:17 lr: 0.000822 loss: 3.5816 (3.5530) grad_norm: 1.1543 (1.1773) time: 0.6309 [2021-03-26 17:15:19 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 950/1251] eta: 0:03:11 lr: 0.000821 loss: 3.5816 (3.5531) grad_norm: 1.1543 (1.1769) time: 0.6303 [2021-03-26 17:15:26 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 960/1251] eta: 0:03:04 lr: 0.000821 loss: 3.6709 (3.5544) grad_norm: 1.1717 (1.1781) time: 0.6372 [2021-03-26 17:15:32 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 970/1251] eta: 0:02:58 lr: 0.000821 loss: 3.8399 (3.5572) grad_norm: 1.1832 (1.1780) time: 0.6363 [2021-03-26 17:15:38 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 980/1251] eta: 0:02:52 lr: 0.000821 loss: 3.8548 (3.5583) grad_norm: 1.1527 (1.1780) time: 0.6265 [2021-03-26 17:15:45 swin_base_patch4_window7_224] INFO: Epoch: [83] [ 990/1251] eta: 0:02:45 lr: 0.000821 loss: 3.9041 (3.5598) grad_norm: 1.1549 (1.1788) time: 0.6238 [2021-03-26 17:15:51 swin_base_patch4_window7_224] INFO: Epoch: [83] [1000/1251] eta: 0:02:39 lr: 0.000821 loss: 3.6268 (3.5589) grad_norm: 1.1057 (1.1786) time: 0.6235 [2021-03-26 17:15:57 swin_base_patch4_window7_224] INFO: Epoch: [83] [1010/1251] eta: 0:02:33 lr: 0.000821 loss: 3.5101 (3.5565) grad_norm: 1.2127 (1.1793) time: 0.6333 [2021-03-26 17:16:03 swin_base_patch4_window7_224] INFO: Epoch: [83] [1020/1251] eta: 0:02:26 lr: 0.000821 loss: 3.6271 (3.5562) grad_norm: 1.1626 (1.1788) time: 0.6326 [2021-03-26 17:16:10 swin_base_patch4_window7_224] INFO: Epoch: [83] [1030/1251] eta: 0:02:20 lr: 0.000821 loss: 3.5380 (3.5529) grad_norm: 1.1322 (1.1786) time: 0.6264 [2021-03-26 17:16:16 swin_base_patch4_window7_224] INFO: Epoch: [83] [1040/1251] eta: 0:02:13 lr: 0.000821 loss: 3.3271 (3.5509) grad_norm: 1.1504 (1.1786) time: 0.6275 [2021-03-26 17:16:22 swin_base_patch4_window7_224] INFO: Epoch: [83] [1050/1251] eta: 0:02:07 lr: 0.000821 loss: 3.5330 (3.5500) grad_norm: 1.1504 (1.1783) time: 0.6268 [2021-03-26 17:16:29 swin_base_patch4_window7_224] INFO: Epoch: [83] [1060/1251] eta: 0:02:01 lr: 0.000821 loss: 3.6277 (3.5510) grad_norm: 1.1129 (1.1777) time: 0.6310 [2021-03-26 17:16:35 swin_base_patch4_window7_224] INFO: Epoch: [83] [1070/1251] eta: 0:01:54 lr: 0.000821 loss: 3.6613 (3.5526) grad_norm: 1.1287 (1.1783) time: 0.6338 [2021-03-26 17:16:41 swin_base_patch4_window7_224] INFO: Epoch: [83] [1080/1251] eta: 0:01:48 lr: 0.000821 loss: 3.6613 (3.5520) grad_norm: 1.1935 (1.1780) time: 0.6305 [2021-03-26 17:16:48 swin_base_patch4_window7_224] INFO: Epoch: [83] [1090/1251] eta: 0:01:42 lr: 0.000821 loss: 3.4498 (3.5517) grad_norm: 1.1645 (1.1782) time: 0.6271 [2021-03-26 17:16:54 swin_base_patch4_window7_224] INFO: Epoch: [83] [1100/1251] eta: 0:01:35 lr: 0.000821 loss: 3.4498 (3.5516) grad_norm: 1.1706 (1.1781) time: 0.6310 [2021-03-26 17:17:00 swin_base_patch4_window7_224] INFO: Epoch: [83] [1110/1251] eta: 0:01:29 lr: 0.000821 loss: 3.4812 (3.5511) grad_norm: 1.1234 (1.1777) time: 0.6285 [2021-03-26 17:17:06 swin_base_patch4_window7_224] INFO: Epoch: [83] [1120/1251] eta: 0:01:23 lr: 0.000821 loss: 3.5098 (3.5503) grad_norm: 1.1044 (1.1772) time: 0.6237 [2021-03-26 17:17:13 swin_base_patch4_window7_224] INFO: Epoch: [83] [1130/1251] eta: 0:01:16 lr: 0.000821 loss: 3.7626 (3.5520) grad_norm: 1.0936 (1.1767) time: 0.6290 [2021-03-26 17:17:19 swin_base_patch4_window7_224] INFO: Epoch: [83] [1140/1251] eta: 0:01:10 lr: 0.000821 loss: 3.8252 (3.5514) grad_norm: 1.1033 (1.1761) time: 0.6308 [2021-03-26 17:17:25 swin_base_patch4_window7_224] INFO: Epoch: [83] [1150/1251] eta: 0:01:04 lr: 0.000821 loss: 3.8252 (3.5530) grad_norm: 1.1653 (1.1763) time: 0.6355 [2021-03-26 17:17:32 swin_base_patch4_window7_224] INFO: Epoch: [83] [1160/1251] eta: 0:00:57 lr: 0.000821 loss: 3.6570 (3.5530) grad_norm: 1.1893 (1.1767) time: 0.6337 [2021-03-26 17:17:38 swin_base_patch4_window7_224] INFO: Epoch: [83] [1170/1251] eta: 0:00:51 lr: 0.000821 loss: 3.7107 (3.5559) grad_norm: 1.1324 (1.1766) time: 0.6245 [2021-03-26 17:17:44 swin_base_patch4_window7_224] INFO: Epoch: [83] [1180/1251] eta: 0:00:45 lr: 0.000821 loss: 3.6051 (3.5544) grad_norm: 1.1220 (1.1767) time: 0.6247 [2021-03-26 17:17:50 swin_base_patch4_window7_224] INFO: Epoch: [83] [1190/1251] eta: 0:00:38 lr: 0.000821 loss: 3.5291 (3.5543) grad_norm: 1.1852 (1.1770) time: 0.6242 [2021-03-26 17:17:57 swin_base_patch4_window7_224] INFO: Epoch: [83] [1200/1251] eta: 0:00:32 lr: 0.000821 loss: 3.6139 (3.5539) grad_norm: 1.1083 (1.1763) time: 0.6253 [2021-03-26 17:18:03 swin_base_patch4_window7_224] INFO: Epoch: [83] [1210/1251] eta: 0:00:26 lr: 0.000821 loss: 3.5880 (3.5536) grad_norm: 1.1057 (1.1764) time: 0.6303 [2021-03-26 17:18:09 swin_base_patch4_window7_224] INFO: Epoch: [83] [1220/1251] eta: 0:00:19 lr: 0.000821 loss: 3.5880 (3.5530) grad_norm: 1.1764 (1.1771) time: 0.6365 [2021-03-26 17:18:16 swin_base_patch4_window7_224] INFO: Epoch: [83] [1230/1251] eta: 0:00:13 lr: 0.000821 loss: 3.6171 (3.5537) grad_norm: 1.2126 (1.1770) time: 0.6381 [2021-03-26 17:18:22 swin_base_patch4_window7_224] INFO: Epoch: [83] [1240/1251] eta: 0:00:06 lr: 0.000821 loss: 3.5767 (3.5537) grad_norm: 1.1444 (1.1769) time: 0.6361 [2021-03-26 17:18:28 swin_base_patch4_window7_224] INFO: Epoch: [83] [1250/1251] eta: 0:00:00 lr: 0.000821 loss: 3.5766 (3.5528) grad_norm: 1.1594 (1.1772) time: 0.6238 [2021-03-26 17:18:36 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:23 loss: 0.8525 (0.8525) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-26 17:18:38 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.0650 (1.0442) acc1: 76.5625 (75.4261) acc5: 93.7500 (94.0341) [2021-03-26 17:18:41 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0304 (1.0125) acc1: 76.5625 (76.0417) acc5: 93.7500 (94.4196) [2021-03-26 17:18:43 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0831 (1.0597) acc1: 75.0000 (75.4536) acc5: 93.7500 (93.3972) [2021-03-26 17:18:45 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1208 (1.0723) acc1: 73.4375 (74.9238) acc5: 92.1875 (93.3689) [2021-03-26 17:18:46 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0452 (1.0614) acc1: 73.4375 (75.0400) acc5: 93.7500 (93.5360) [2021-03-26 17:18:51 swin_base_patch4_window7_224] INFO: * Acc@1 75.680 Acc@5 93.294 loss 1.050 [2021-03-26 17:18:51 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.7% [2021-03-26 17:18:51 swin_base_patch4_window7_224] INFO: Max accuracy: 75.78% [2021-03-26 17:18:55 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 0/1251] eta: 1:22:31 lr: 0.000821 loss: 3.3764 (3.3764) grad_norm: 1.0598 (1.0598) time: 3.9577 [2021-03-26 17:19:01 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 10/1251] eta: 0:19:54 lr: 0.000820 loss: 3.3764 (3.4158) grad_norm: 1.1390 (1.1493) time: 0.9627 [2021-03-26 17:19:08 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 20/1251] eta: 0:16:29 lr: 0.000820 loss: 3.7693 (3.5200) grad_norm: 1.0918 (1.1210) time: 0.6465 [2021-03-26 17:19:14 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 30/1251] eta: 0:15:11 lr: 0.000820 loss: 3.6235 (3.4431) grad_norm: 1.0918 (1.1335) time: 0.6272 [2021-03-26 17:19:20 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 40/1251] eta: 0:14:30 lr: 0.000820 loss: 3.5050 (3.4807) grad_norm: 1.1869 (1.1538) time: 0.6296 [2021-03-26 17:19:27 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 50/1251] eta: 0:14:04 lr: 0.000820 loss: 3.6995 (3.4889) grad_norm: 1.1424 (1.1483) time: 0.6361 [2021-03-26 17:19:33 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 60/1251] eta: 0:13:41 lr: 0.000820 loss: 3.7454 (3.5246) grad_norm: 1.1049 (1.1447) time: 0.6308 [2021-03-26 17:19:39 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 70/1251] eta: 0:13:26 lr: 0.000820 loss: 3.6992 (3.5120) grad_norm: 1.1049 (1.1432) time: 0.6303 [2021-03-26 17:19:46 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 80/1251] eta: 0:13:13 lr: 0.000820 loss: 3.5868 (3.5135) grad_norm: 1.1585 (1.1520) time: 0.6408 [2021-03-26 17:19:52 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 90/1251] eta: 0:13:01 lr: 0.000820 loss: 3.5868 (3.5283) grad_norm: 1.2043 (1.1645) time: 0.6379 [2021-03-26 17:19:58 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 100/1251] eta: 0:12:49 lr: 0.000820 loss: 3.4268 (3.5064) grad_norm: 1.2898 (1.1736) time: 0.6296 [2021-03-26 17:20:04 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 110/1251] eta: 0:12:38 lr: 0.000820 loss: 3.1287 (3.5133) grad_norm: 1.2626 (1.1745) time: 0.6262 [2021-03-26 17:20:11 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 120/1251] eta: 0:12:27 lr: 0.000820 loss: 3.5594 (3.4987) grad_norm: 1.1863 (1.1807) time: 0.6243 [2021-03-26 17:20:17 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 130/1251] eta: 0:12:18 lr: 0.000820 loss: 3.7091 (3.5226) grad_norm: 1.1715 (1.1802) time: 0.6303 [2021-03-26 17:20:23 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 140/1251] eta: 0:12:09 lr: 0.000820 loss: 3.7772 (3.5235) grad_norm: 1.1715 (1.1819) time: 0.6308 [2021-03-26 17:20:30 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 150/1251] eta: 0:12:00 lr: 0.000820 loss: 3.6526 (3.5254) grad_norm: 1.1521 (1.1781) time: 0.6247 [2021-03-26 17:20:36 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 160/1251] eta: 0:11:51 lr: 0.000820 loss: 3.7107 (3.5303) grad_norm: 1.1131 (1.1786) time: 0.6225 [2021-03-26 17:20:42 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 170/1251] eta: 0:11:43 lr: 0.000820 loss: 3.7107 (3.5241) grad_norm: 1.1250 (1.1759) time: 0.6258 [2021-03-26 17:20:48 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 180/1251] eta: 0:11:36 lr: 0.000820 loss: 3.4106 (3.5322) grad_norm: 1.1597 (1.1796) time: 0.6291 [2021-03-26 17:20:55 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 190/1251] eta: 0:11:28 lr: 0.000820 loss: 3.4667 (3.5365) grad_norm: 1.2624 (1.1842) time: 0.6287 [2021-03-26 17:21:01 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 200/1251] eta: 0:11:20 lr: 0.000820 loss: 3.7197 (3.5415) grad_norm: 1.1745 (1.1818) time: 0.6260 [2021-03-26 17:21:07 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 210/1251] eta: 0:11:13 lr: 0.000820 loss: 3.3910 (3.5271) grad_norm: 1.1433 (1.1858) time: 0.6324 [2021-03-26 17:21:14 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 220/1251] eta: 0:11:06 lr: 0.000820 loss: 3.2294 (3.5235) grad_norm: 1.1868 (1.1874) time: 0.6384 [2021-03-26 17:21:20 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 230/1251] eta: 0:10:59 lr: 0.000820 loss: 3.3192 (3.5108) grad_norm: 1.1610 (1.1899) time: 0.6319 [2021-03-26 17:21:26 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 240/1251] eta: 0:10:52 lr: 0.000820 loss: 3.4832 (3.5196) grad_norm: 1.1321 (1.1880) time: 0.6318 [2021-03-26 17:21:33 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 250/1251] eta: 0:10:45 lr: 0.000820 loss: 3.6816 (3.5122) grad_norm: 1.0992 (1.1860) time: 0.6269 [2021-03-26 17:21:39 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 260/1251] eta: 0:10:38 lr: 0.000820 loss: 3.4647 (3.5151) grad_norm: 1.0992 (1.1846) time: 0.6247 [2021-03-26 17:21:45 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 270/1251] eta: 0:10:30 lr: 0.000820 loss: 3.5944 (3.5211) grad_norm: 1.0823 (1.1820) time: 0.6264 [2021-03-26 17:21:51 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 280/1251] eta: 0:10:23 lr: 0.000820 loss: 3.5512 (3.5142) grad_norm: 1.1413 (1.1833) time: 0.6258 [2021-03-26 17:21:58 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 290/1251] eta: 0:10:17 lr: 0.000820 loss: 3.5882 (3.5198) grad_norm: 1.1314 (1.1814) time: 0.6299 [2021-03-26 17:22:04 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 300/1251] eta: 0:10:10 lr: 0.000820 loss: 3.4638 (3.5154) grad_norm: 1.1638 (1.1834) time: 0.6279 [2021-03-26 17:22:10 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 310/1251] eta: 0:10:03 lr: 0.000820 loss: 3.5727 (3.5232) grad_norm: 1.2907 (1.1862) time: 0.6314 [2021-03-26 17:22:17 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 320/1251] eta: 0:09:56 lr: 0.000820 loss: 3.8052 (3.5252) grad_norm: 1.2292 (1.1854) time: 0.6326 [2021-03-26 17:22:23 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 330/1251] eta: 0:09:50 lr: 0.000819 loss: 3.7348 (3.5295) grad_norm: 1.1601 (1.1897) time: 0.6285 [2021-03-26 17:22:29 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 340/1251] eta: 0:09:43 lr: 0.000819 loss: 3.5892 (3.5261) grad_norm: 1.1724 (1.1900) time: 0.6315 [2021-03-26 17:22:35 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 350/1251] eta: 0:09:36 lr: 0.000819 loss: 3.6459 (3.5285) grad_norm: 1.1724 (1.1913) time: 0.6317 [2021-03-26 17:22:42 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 360/1251] eta: 0:09:30 lr: 0.000819 loss: 3.7202 (3.5335) grad_norm: 1.1019 (1.1886) time: 0.6325 [2021-03-26 17:22:48 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 370/1251] eta: 0:09:23 lr: 0.000819 loss: 3.5726 (3.5318) grad_norm: 1.0863 (1.1884) time: 0.6351 [2021-03-26 17:22:54 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 380/1251] eta: 0:09:17 lr: 0.000819 loss: 3.5115 (3.5344) grad_norm: 1.1532 (1.1885) time: 0.6322 [2021-03-26 17:23:01 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 390/1251] eta: 0:09:10 lr: 0.000819 loss: 3.6693 (3.5374) grad_norm: 1.1532 (1.1890) time: 0.6277 [2021-03-26 17:23:07 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 400/1251] eta: 0:09:03 lr: 0.000819 loss: 3.6693 (3.5369) grad_norm: 1.1520 (1.1898) time: 0.6277 [2021-03-26 17:23:13 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 410/1251] eta: 0:08:57 lr: 0.000819 loss: 3.4904 (3.5324) grad_norm: 1.1520 (1.1896) time: 0.6295 [2021-03-26 17:23:20 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 420/1251] eta: 0:08:50 lr: 0.000819 loss: 3.4898 (3.5369) grad_norm: 1.1392 (1.1884) time: 0.6296 [2021-03-26 17:23:26 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 430/1251] eta: 0:08:44 lr: 0.000819 loss: 3.6997 (3.5406) grad_norm: 1.1420 (1.1883) time: 0.6325 [2021-03-26 17:23:32 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 440/1251] eta: 0:08:37 lr: 0.000819 loss: 3.7466 (3.5412) grad_norm: 1.1201 (1.1865) time: 0.6283 [2021-03-26 17:23:38 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 450/1251] eta: 0:08:30 lr: 0.000819 loss: 3.7647 (3.5439) grad_norm: 1.1201 (1.1869) time: 0.6213 [2021-03-26 17:23:45 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 460/1251] eta: 0:08:24 lr: 0.000819 loss: 3.6849 (3.5460) grad_norm: 1.0982 (1.1851) time: 0.6230 [2021-03-26 17:23:51 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 470/1251] eta: 0:08:17 lr: 0.000819 loss: 3.8082 (3.5522) grad_norm: 1.0982 (1.1837) time: 0.6339 [2021-03-26 17:23:58 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 480/1251] eta: 0:08:11 lr: 0.000819 loss: 3.8448 (3.5559) grad_norm: 1.1230 (1.1829) time: 0.6423 [2021-03-26 17:24:04 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 490/1251] eta: 0:08:05 lr: 0.000819 loss: 3.8070 (3.5548) grad_norm: 1.0977 (1.1817) time: 0.6320 [2021-03-26 17:24:10 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 500/1251] eta: 0:07:58 lr: 0.000819 loss: 3.6660 (3.5530) grad_norm: 1.1215 (1.1821) time: 0.6225 [2021-03-26 17:24:16 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 510/1251] eta: 0:07:51 lr: 0.000819 loss: 3.4743 (3.5516) grad_norm: 1.1215 (1.1811) time: 0.6268 [2021-03-26 17:24:23 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 520/1251] eta: 0:07:45 lr: 0.000819 loss: 3.6147 (3.5540) grad_norm: 1.1597 (1.1817) time: 0.6281 [2021-03-26 17:24:29 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 530/1251] eta: 0:07:39 lr: 0.000819 loss: 3.6548 (3.5543) grad_norm: 1.1597 (1.1804) time: 0.6306 [2021-03-26 17:24:35 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 540/1251] eta: 0:07:32 lr: 0.000819 loss: 3.6168 (3.5563) grad_norm: 1.1086 (1.1797) time: 0.6355 [2021-03-26 17:24:42 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 550/1251] eta: 0:07:26 lr: 0.000819 loss: 3.6168 (3.5547) grad_norm: 1.1192 (1.1807) time: 0.6434 [2021-03-26 17:24:48 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 560/1251] eta: 0:07:20 lr: 0.000819 loss: 3.5279 (3.5541) grad_norm: 1.2261 (1.1826) time: 0.6411 [2021-03-26 17:24:54 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 570/1251] eta: 0:07:13 lr: 0.000819 loss: 3.3322 (3.5482) grad_norm: 1.1192 (1.1811) time: 0.6296 [2021-03-26 17:25:01 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 580/1251] eta: 0:07:07 lr: 0.000819 loss: 3.4843 (3.5478) grad_norm: 1.1091 (1.1832) time: 0.6295 [2021-03-26 17:25:07 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 590/1251] eta: 0:07:00 lr: 0.000819 loss: 3.5464 (3.5457) grad_norm: 1.2415 (1.1845) time: 0.6276 [2021-03-26 17:25:13 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 600/1251] eta: 0:06:54 lr: 0.000819 loss: 3.6053 (3.5458) grad_norm: 1.1939 (inf) time: 0.6328 [2021-03-26 17:25:20 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 610/1251] eta: 0:06:47 lr: 0.000819 loss: 3.6053 (3.5454) grad_norm: 1.1337 (inf) time: 0.6342 [2021-03-26 17:25:26 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 620/1251] eta: 0:06:41 lr: 0.000819 loss: 3.8393 (3.5470) grad_norm: 1.1182 (inf) time: 0.6278 [2021-03-26 17:25:32 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 630/1251] eta: 0:06:35 lr: 0.000819 loss: 3.7304 (3.5467) grad_norm: 1.1478 (inf) time: 0.6313 [2021-03-26 17:25:39 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 640/1251] eta: 0:06:28 lr: 0.000818 loss: 3.6553 (3.5484) grad_norm: 1.1740 (inf) time: 0.6336 [2021-03-26 17:25:45 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 650/1251] eta: 0:06:22 lr: 0.000818 loss: 3.6430 (3.5470) grad_norm: 1.1450 (inf) time: 0.6374 [2021-03-26 17:25:51 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 660/1251] eta: 0:06:16 lr: 0.000818 loss: 3.6689 (3.5494) grad_norm: 1.0495 (inf) time: 0.6398 [2021-03-26 17:25:58 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 670/1251] eta: 0:06:09 lr: 0.000818 loss: 3.7148 (3.5537) grad_norm: 1.1134 (inf) time: 0.6290 [2021-03-26 17:26:04 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 680/1251] eta: 0:06:03 lr: 0.000818 loss: 3.6979 (3.5553) grad_norm: 1.1352 (inf) time: 0.6286 [2021-03-26 17:26:10 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 690/1251] eta: 0:05:56 lr: 0.000818 loss: 3.6170 (3.5550) grad_norm: 1.1205 (inf) time: 0.6367 [2021-03-26 17:26:17 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 700/1251] eta: 0:05:50 lr: 0.000818 loss: 3.6180 (3.5582) grad_norm: 1.1758 (inf) time: 0.6390 [2021-03-26 17:26:23 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 710/1251] eta: 0:05:44 lr: 0.000818 loss: 3.7265 (3.5585) grad_norm: 1.1869 (inf) time: 0.6336 [2021-03-26 17:26:29 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 720/1251] eta: 0:05:37 lr: 0.000818 loss: 3.5958 (3.5571) grad_norm: 1.1533 (inf) time: 0.6265 [2021-03-26 17:26:36 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 730/1251] eta: 0:05:31 lr: 0.000818 loss: 3.6347 (3.5580) grad_norm: 1.1691 (inf) time: 0.6294 [2021-03-26 17:26:42 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 740/1251] eta: 0:05:24 lr: 0.000818 loss: 3.6853 (3.5595) grad_norm: 1.1029 (inf) time: 0.6347 [2021-03-26 17:26:48 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 750/1251] eta: 0:05:18 lr: 0.000818 loss: 3.5834 (3.5592) grad_norm: 1.1029 (inf) time: 0.6398 [2021-03-26 17:26:55 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 760/1251] eta: 0:05:12 lr: 0.000818 loss: 3.4816 (3.5593) grad_norm: 1.1424 (inf) time: 0.6365 [2021-03-26 17:27:01 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 770/1251] eta: 0:05:05 lr: 0.000818 loss: 3.4790 (3.5580) grad_norm: 1.2014 (inf) time: 0.6337 [2021-03-26 17:27:07 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 780/1251] eta: 0:04:59 lr: 0.000818 loss: 3.7008 (3.5584) grad_norm: 1.2248 (inf) time: 0.6371 [2021-03-26 17:27:14 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 790/1251] eta: 0:04:53 lr: 0.000818 loss: 3.8141 (3.5608) grad_norm: 1.1800 (inf) time: 0.6318 [2021-03-26 17:27:20 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 800/1251] eta: 0:04:46 lr: 0.000818 loss: 3.7820 (3.5613) grad_norm: 1.1800 (inf) time: 0.6360 [2021-03-26 17:27:27 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 810/1251] eta: 0:04:40 lr: 0.000818 loss: 3.6670 (3.5615) grad_norm: 1.1226 (inf) time: 0.6478 [2021-03-26 17:27:33 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 820/1251] eta: 0:04:34 lr: 0.000818 loss: 3.7215 (3.5640) grad_norm: 1.1287 (inf) time: 0.6422 [2021-03-26 17:27:39 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 830/1251] eta: 0:04:27 lr: 0.000818 loss: 3.8114 (3.5648) grad_norm: 1.1815 (inf) time: 0.6301 [2021-03-26 17:27:46 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 840/1251] eta: 0:04:21 lr: 0.000818 loss: 3.8114 (3.5652) grad_norm: 1.1334 (inf) time: 0.6339 [2021-03-26 17:27:52 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 850/1251] eta: 0:04:14 lr: 0.000818 loss: 3.8377 (3.5670) grad_norm: 1.1667 (inf) time: 0.6326 [2021-03-26 17:27:58 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 860/1251] eta: 0:04:08 lr: 0.000818 loss: 3.7716 (3.5677) grad_norm: 1.2843 (inf) time: 0.6271 [2021-03-26 17:28:05 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 870/1251] eta: 0:04:02 lr: 0.000818 loss: 3.5044 (3.5673) grad_norm: 1.1502 (inf) time: 0.6315 [2021-03-26 17:28:11 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 880/1251] eta: 0:03:55 lr: 0.000818 loss: 3.4780 (3.5684) grad_norm: 1.1730 (inf) time: 0.6296 [2021-03-26 17:28:17 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 890/1251] eta: 0:03:49 lr: 0.000818 loss: 3.5127 (3.5694) grad_norm: 1.1629 (inf) time: 0.6297 [2021-03-26 17:28:23 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 900/1251] eta: 0:03:43 lr: 0.000818 loss: 3.8394 (3.5702) grad_norm: 1.1672 (inf) time: 0.6322 [2021-03-26 17:28:30 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 910/1251] eta: 0:03:36 lr: 0.000818 loss: 3.8152 (3.5699) grad_norm: 1.2425 (inf) time: 0.6345 [2021-03-26 17:28:36 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 920/1251] eta: 0:03:30 lr: 0.000818 loss: 3.7130 (3.5713) grad_norm: 1.2584 (inf) time: 0.6320 [2021-03-26 17:28:42 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 930/1251] eta: 0:03:23 lr: 0.000818 loss: 3.7130 (3.5718) grad_norm: 1.3204 (inf) time: 0.6306 [2021-03-26 17:28:49 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 940/1251] eta: 0:03:17 lr: 0.000818 loss: 3.7061 (3.5715) grad_norm: 1.2291 (inf) time: 0.6303 [2021-03-26 17:28:55 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 950/1251] eta: 0:03:11 lr: 0.000817 loss: 3.6732 (3.5694) grad_norm: 1.1661 (inf) time: 0.6290 [2021-03-26 17:29:01 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 960/1251] eta: 0:03:04 lr: 0.000817 loss: 3.6692 (3.5707) grad_norm: 1.1661 (inf) time: 0.6321 [2021-03-26 17:29:08 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 970/1251] eta: 0:02:58 lr: 0.000817 loss: 3.5520 (3.5686) grad_norm: 1.1823 (inf) time: 0.6281 [2021-03-26 17:29:14 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 980/1251] eta: 0:02:52 lr: 0.000817 loss: 3.3817 (3.5686) grad_norm: 1.1292 (inf) time: 0.6224 [2021-03-26 17:29:20 swin_base_patch4_window7_224] INFO: Epoch: [84] [ 990/1251] eta: 0:02:45 lr: 0.000817 loss: 3.5029 (3.5690) grad_norm: 1.1814 (inf) time: 0.6277 [2021-03-26 17:29:26 swin_base_patch4_window7_224] INFO: Epoch: [84] [1000/1251] eta: 0:02:39 lr: 0.000817 loss: 3.4812 (3.5675) grad_norm: 1.2104 (inf) time: 0.6343 [2021-03-26 17:29:33 swin_base_patch4_window7_224] INFO: Epoch: [84] [1010/1251] eta: 0:02:33 lr: 0.000817 loss: 3.4340 (3.5642) grad_norm: 1.1871 (inf) time: 0.6336 [2021-03-26 17:29:39 swin_base_patch4_window7_224] INFO: Epoch: [84] [1020/1251] eta: 0:02:26 lr: 0.000817 loss: 3.8017 (3.5674) grad_norm: 1.1737 (inf) time: 0.6294 [2021-03-26 17:29:45 swin_base_patch4_window7_224] INFO: Epoch: [84] [1030/1251] eta: 0:02:20 lr: 0.000817 loss: 3.8708 (3.5681) grad_norm: 1.1439 (inf) time: 0.6240 [2021-03-26 17:29:52 swin_base_patch4_window7_224] INFO: Epoch: [84] [1040/1251] eta: 0:02:13 lr: 0.000817 loss: 3.5848 (3.5675) grad_norm: 1.1452 (inf) time: 0.6260 [2021-03-26 17:29:58 swin_base_patch4_window7_224] INFO: Epoch: [84] [1050/1251] eta: 0:02:07 lr: 0.000817 loss: 3.5405 (3.5654) grad_norm: 1.1787 (inf) time: 0.6329 [2021-03-26 17:30:04 swin_base_patch4_window7_224] INFO: Epoch: [84] [1060/1251] eta: 0:02:01 lr: 0.000817 loss: 3.1804 (3.5632) grad_norm: 1.1666 (inf) time: 0.6309 [2021-03-26 17:30:11 swin_base_patch4_window7_224] INFO: Epoch: [84] [1070/1251] eta: 0:01:54 lr: 0.000817 loss: 3.4834 (3.5632) grad_norm: 1.1264 (inf) time: 0.6300 [2021-03-26 17:30:17 swin_base_patch4_window7_224] INFO: Epoch: [84] [1080/1251] eta: 0:01:48 lr: 0.000817 loss: 3.4834 (3.5616) grad_norm: 1.0965 (inf) time: 0.6286 [2021-03-26 17:30:23 swin_base_patch4_window7_224] INFO: Epoch: [84] [1090/1251] eta: 0:01:42 lr: 0.000817 loss: 3.4671 (3.5612) grad_norm: 1.1645 (inf) time: 0.6286 [2021-03-26 17:30:29 swin_base_patch4_window7_224] INFO: Epoch: [84] [1100/1251] eta: 0:01:35 lr: 0.000817 loss: 3.6153 (3.5611) grad_norm: 1.2365 (inf) time: 0.6281 [2021-03-26 17:30:36 swin_base_patch4_window7_224] INFO: Epoch: [84] [1110/1251] eta: 0:01:29 lr: 0.000817 loss: 3.6130 (3.5615) grad_norm: 1.1968 (inf) time: 0.6267 [2021-03-26 17:30:42 swin_base_patch4_window7_224] INFO: Epoch: [84] [1120/1251] eta: 0:01:23 lr: 0.000817 loss: 3.6130 (3.5611) grad_norm: 1.1277 (inf) time: 0.6277 [2021-03-26 17:30:48 swin_base_patch4_window7_224] INFO: Epoch: [84] [1130/1251] eta: 0:01:16 lr: 0.000817 loss: 3.6055 (3.5611) grad_norm: 1.0702 (inf) time: 0.6254 [2021-03-26 17:30:54 swin_base_patch4_window7_224] INFO: Epoch: [84] [1140/1251] eta: 0:01:10 lr: 0.000817 loss: 3.6055 (3.5617) grad_norm: 1.0702 (inf) time: 0.6277 [2021-03-26 17:31:01 swin_base_patch4_window7_224] INFO: Epoch: [84] [1150/1251] eta: 0:01:04 lr: 0.000817 loss: 3.8368 (3.5618) grad_norm: 1.1701 (inf) time: 0.6327 [2021-03-26 17:31:07 swin_base_patch4_window7_224] INFO: Epoch: [84] [1160/1251] eta: 0:00:57 lr: 0.000817 loss: 3.7889 (3.5629) grad_norm: 1.1769 (inf) time: 0.6306 [2021-03-26 17:31:13 swin_base_patch4_window7_224] INFO: Epoch: [84] [1170/1251] eta: 0:00:51 lr: 0.000817 loss: 3.8143 (3.5658) grad_norm: 1.1468 (inf) time: 0.6221 [2021-03-26 17:31:20 swin_base_patch4_window7_224] INFO: Epoch: [84] [1180/1251] eta: 0:00:45 lr: 0.000817 loss: 3.7968 (3.5667) grad_norm: 1.1427 (inf) time: 0.6236 [2021-03-26 17:31:26 swin_base_patch4_window7_224] INFO: Epoch: [84] [1190/1251] eta: 0:00:38 lr: 0.000817 loss: 3.5649 (3.5655) grad_norm: 1.1427 (inf) time: 0.6295 [2021-03-26 17:31:32 swin_base_patch4_window7_224] INFO: Epoch: [84] [1200/1251] eta: 0:00:32 lr: 0.000817 loss: 3.4676 (3.5645) grad_norm: 1.1504 (inf) time: 0.6286 [2021-03-26 17:31:38 swin_base_patch4_window7_224] INFO: Epoch: [84] [1210/1251] eta: 0:00:25 lr: 0.000817 loss: 3.5435 (3.5635) grad_norm: 1.1251 (inf) time: 0.6276 [2021-03-26 17:31:45 swin_base_patch4_window7_224] INFO: Epoch: [84] [1220/1251] eta: 0:00:19 lr: 0.000817 loss: 3.5435 (3.5628) grad_norm: 1.2217 (inf) time: 0.6337 [2021-03-26 17:31:51 swin_base_patch4_window7_224] INFO: Epoch: [84] [1230/1251] eta: 0:00:13 lr: 0.000817 loss: 3.4780 (3.5617) grad_norm: 1.2674 (inf) time: 0.6345 [2021-03-26 17:31:57 swin_base_patch4_window7_224] INFO: Epoch: [84] [1240/1251] eta: 0:00:06 lr: 0.000817 loss: 3.7076 (3.5638) grad_norm: 1.1808 (inf) time: 0.6242 [2021-03-26 17:32:03 swin_base_patch4_window7_224] INFO: Epoch: [84] [1250/1251] eta: 0:00:00 lr: 0.000817 loss: 3.7262 (3.5634) grad_norm: 1.1188 (inf) time: 0.6156 [2021-03-26 17:32:10 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:16 loss: 0.9774 (0.9774) acc1: 75.0000 (75.0000) acc5: 95.3125 (95.3125) [2021-03-26 17:32:12 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.9786 (0.9409) acc1: 78.1250 (77.9830) acc5: 93.7500 (94.0341) [2021-03-26 17:32:15 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0730 (1.0247) acc1: 75.0000 (75.8929) acc5: 93.7500 (93.7500) [2021-03-26 17:32:17 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1249 (1.0719) acc1: 73.4375 (75.2520) acc5: 92.1875 (93.0444) [2021-03-26 17:32:19 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1177 (1.0915) acc1: 73.4375 (74.8476) acc5: 92.1875 (92.7210) [2021-03-26 17:32:20 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0755 (1.0715) acc1: 75.0000 (75.3280) acc5: 93.7500 (93.1200) [2021-03-26 17:32:25 swin_base_patch4_window7_224] INFO: * Acc@1 75.834 Acc@5 93.362 loss 1.055 [2021-03-26 17:32:25 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.8% [2021-03-26 17:32:25 swin_base_patch4_window7_224] INFO: Max accuracy: 75.83% [2021-03-26 17:32:29 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 0/1251] eta: 1:28:26 lr: 0.000817 loss: 2.3817 (2.3817) grad_norm: 1.0272 (1.0272) time: 4.2415 [2021-03-26 17:32:36 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 10/1251] eta: 0:20:17 lr: 0.000816 loss: 3.3328 (3.3712) grad_norm: 1.1926 (1.2160) time: 0.9814 [2021-03-26 17:32:42 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 20/1251] eta: 0:16:43 lr: 0.000816 loss: 3.6649 (3.5477) grad_norm: 1.1814 (1.2105) time: 0.6437 [2021-03-26 17:32:49 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 30/1251] eta: 0:15:26 lr: 0.000816 loss: 3.9134 (3.6642) grad_norm: 1.1814 (1.2531) time: 0.6358 [2021-03-26 17:32:55 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 40/1251] eta: 0:14:38 lr: 0.000816 loss: 3.7303 (3.6494) grad_norm: 1.1808 (1.2439) time: 0.6321 [2021-03-26 17:33:01 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 50/1251] eta: 0:14:07 lr: 0.000816 loss: 3.6336 (3.6394) grad_norm: 1.1212 (1.2198) time: 0.6242 [2021-03-26 17:33:07 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 60/1251] eta: 0:13:45 lr: 0.000816 loss: 3.5739 (3.6130) grad_norm: 1.1119 (1.2070) time: 0.6250 [2021-03-26 17:33:14 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 70/1251] eta: 0:13:28 lr: 0.000816 loss: 3.6061 (3.6101) grad_norm: 1.1472 (1.1989) time: 0.6313 [2021-03-26 17:33:20 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 80/1251] eta: 0:13:13 lr: 0.000816 loss: 3.5806 (3.6056) grad_norm: 1.1535 (1.1998) time: 0.6305 [2021-03-26 17:33:26 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 90/1251] eta: 0:13:00 lr: 0.000816 loss: 3.4805 (3.5778) grad_norm: 1.1835 (1.1969) time: 0.6274 [2021-03-26 17:33:33 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 100/1251] eta: 0:12:49 lr: 0.000816 loss: 3.5193 (3.5654) grad_norm: 1.0839 (1.1903) time: 0.6325 [2021-03-26 17:33:39 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 110/1251] eta: 0:12:39 lr: 0.000816 loss: 3.7613 (3.5779) grad_norm: 1.1169 (1.1924) time: 0.6339 [2021-03-26 17:33:45 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 120/1251] eta: 0:12:29 lr: 0.000816 loss: 3.7897 (3.5726) grad_norm: 1.1579 (1.1922) time: 0.6357 [2021-03-26 17:33:52 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 130/1251] eta: 0:12:21 lr: 0.000816 loss: 3.5993 (3.5716) grad_norm: 1.1775 (1.1993) time: 0.6411 [2021-03-26 17:33:58 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 140/1251] eta: 0:12:12 lr: 0.000816 loss: 3.4672 (3.5421) grad_norm: 1.1891 (1.1980) time: 0.6377 [2021-03-26 17:34:04 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 150/1251] eta: 0:12:03 lr: 0.000816 loss: 3.3322 (3.5376) grad_norm: 1.1850 (1.1994) time: 0.6302 [2021-03-26 17:34:11 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 160/1251] eta: 0:11:55 lr: 0.000816 loss: 3.3322 (3.5294) grad_norm: 1.1445 (1.1954) time: 0.6312 [2021-03-26 17:34:17 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 170/1251] eta: 0:11:47 lr: 0.000816 loss: 3.5705 (3.5368) grad_norm: 1.1208 (1.1955) time: 0.6350 [2021-03-26 17:34:23 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 180/1251] eta: 0:11:39 lr: 0.000816 loss: 3.6573 (3.5364) grad_norm: 1.1208 (1.1909) time: 0.6320 [2021-03-26 17:34:30 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 190/1251] eta: 0:11:31 lr: 0.000816 loss: 3.6358 (3.5316) grad_norm: 1.1192 (1.1884) time: 0.6286 [2021-03-26 17:34:36 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 200/1251] eta: 0:11:24 lr: 0.000816 loss: 3.7582 (3.5405) grad_norm: 1.1126 (1.1871) time: 0.6339 [2021-03-26 17:34:42 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 210/1251] eta: 0:11:16 lr: 0.000816 loss: 3.7411 (3.5228) grad_norm: 1.0852 (1.1819) time: 0.6311 [2021-03-26 17:34:49 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 220/1251] eta: 0:11:09 lr: 0.000816 loss: 3.3979 (3.5277) grad_norm: 1.1064 (1.1821) time: 0.6323 [2021-03-26 17:34:55 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 230/1251] eta: 0:11:02 lr: 0.000816 loss: 3.5371 (3.5221) grad_norm: 1.1351 (1.1801) time: 0.6326 [2021-03-26 17:35:01 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 240/1251] eta: 0:10:54 lr: 0.000816 loss: 3.4791 (3.5193) grad_norm: 1.1295 (1.1779) time: 0.6227 [2021-03-26 17:35:08 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 250/1251] eta: 0:10:47 lr: 0.000816 loss: 3.5699 (3.5197) grad_norm: 1.1582 (1.1791) time: 0.6264 [2021-03-26 17:35:14 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 260/1251] eta: 0:10:39 lr: 0.000816 loss: 3.4327 (3.5237) grad_norm: 1.1174 (1.1759) time: 0.6252 [2021-03-26 17:35:20 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 270/1251] eta: 0:10:32 lr: 0.000816 loss: 3.6303 (3.5254) grad_norm: 1.1174 (1.1781) time: 0.6199 [2021-03-26 17:35:26 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 280/1251] eta: 0:10:26 lr: 0.000816 loss: 3.6388 (3.5345) grad_norm: 1.1896 (1.1779) time: 0.6329 [2021-03-26 17:35:33 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 290/1251] eta: 0:10:19 lr: 0.000816 loss: 3.7983 (3.5427) grad_norm: 1.1915 (1.1788) time: 0.6407 [2021-03-26 17:35:39 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 300/1251] eta: 0:10:12 lr: 0.000816 loss: 3.7458 (3.5451) grad_norm: 1.2159 (1.1799) time: 0.6406 [2021-03-26 17:35:45 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 310/1251] eta: 0:10:05 lr: 0.000816 loss: 3.5571 (3.5410) grad_norm: 1.2159 (1.1836) time: 0.6349 [2021-03-26 17:35:52 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 320/1251] eta: 0:09:59 lr: 0.000815 loss: 3.6702 (3.5475) grad_norm: 1.1912 (1.1840) time: 0.6304 [2021-03-26 17:35:58 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 330/1251] eta: 0:09:52 lr: 0.000815 loss: 3.8383 (3.5533) grad_norm: 1.1394 (1.1817) time: 0.6310 [2021-03-26 17:36:04 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 340/1251] eta: 0:09:45 lr: 0.000815 loss: 3.8289 (3.5554) grad_norm: 1.1256 (1.1829) time: 0.6252 [2021-03-26 17:36:11 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 350/1251] eta: 0:09:38 lr: 0.000815 loss: 3.5879 (3.5543) grad_norm: 1.1154 (1.1812) time: 0.6229 [2021-03-26 17:36:17 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 360/1251] eta: 0:09:31 lr: 0.000815 loss: 3.4693 (3.5519) grad_norm: 1.1491 (1.1817) time: 0.6265 [2021-03-26 17:36:23 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 370/1251] eta: 0:09:24 lr: 0.000815 loss: 3.4693 (3.5486) grad_norm: 1.1690 (1.1814) time: 0.6245 [2021-03-26 17:36:29 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 380/1251] eta: 0:09:18 lr: 0.000815 loss: 3.7086 (3.5522) grad_norm: 1.1042 (1.1801) time: 0.6250 [2021-03-26 17:36:36 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 390/1251] eta: 0:09:11 lr: 0.000815 loss: 3.6770 (3.5488) grad_norm: 1.1042 (1.1789) time: 0.6305 [2021-03-26 17:36:42 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 400/1251] eta: 0:09:04 lr: 0.000815 loss: 3.3978 (3.5460) grad_norm: 1.1219 (1.1786) time: 0.6327 [2021-03-26 17:36:48 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 410/1251] eta: 0:08:58 lr: 0.000815 loss: 3.5578 (3.5474) grad_norm: 1.1210 (1.1779) time: 0.6318 [2021-03-26 17:36:55 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 420/1251] eta: 0:08:51 lr: 0.000815 loss: 3.5846 (3.5484) grad_norm: 1.1210 (1.1776) time: 0.6297 [2021-03-26 17:37:01 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 430/1251] eta: 0:08:45 lr: 0.000815 loss: 3.5610 (3.5471) grad_norm: 1.1274 (1.1773) time: 0.6277 [2021-03-26 17:37:07 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 440/1251] eta: 0:08:38 lr: 0.000815 loss: 3.4805 (3.5470) grad_norm: 1.1285 (1.1772) time: 0.6240 [2021-03-26 17:37:13 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 450/1251] eta: 0:08:31 lr: 0.000815 loss: 3.5147 (3.5468) grad_norm: 1.1333 (1.1783) time: 0.6246 [2021-03-26 17:37:20 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 460/1251] eta: 0:08:25 lr: 0.000815 loss: 3.4635 (3.5436) grad_norm: 1.1333 (1.1782) time: 0.6300 [2021-03-26 17:37:26 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 470/1251] eta: 0:08:18 lr: 0.000815 loss: 3.3958 (3.5428) grad_norm: 1.1226 (1.1769) time: 0.6334 [2021-03-26 17:37:32 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 480/1251] eta: 0:08:12 lr: 0.000815 loss: 3.3958 (3.5385) grad_norm: 1.1228 (1.1772) time: 0.6310 [2021-03-26 17:37:39 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 490/1251] eta: 0:08:05 lr: 0.000815 loss: 3.5485 (3.5400) grad_norm: 1.1691 (1.1778) time: 0.6312 [2021-03-26 17:37:45 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 500/1251] eta: 0:07:59 lr: 0.000815 loss: 3.5729 (3.5393) grad_norm: 1.2187 (1.1799) time: 0.6296 [2021-03-26 17:37:51 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 510/1251] eta: 0:07:52 lr: 0.000815 loss: 3.5342 (3.5385) grad_norm: 1.2085 (1.1801) time: 0.6273 [2021-03-26 17:37:57 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 520/1251] eta: 0:07:46 lr: 0.000815 loss: 3.5123 (3.5401) grad_norm: 1.1990 (1.1803) time: 0.6262 [2021-03-26 17:38:04 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 530/1251] eta: 0:07:39 lr: 0.000815 loss: 3.7529 (3.5389) grad_norm: 1.1750 (1.1812) time: 0.6253 [2021-03-26 17:38:10 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 540/1251] eta: 0:07:33 lr: 0.000815 loss: 3.5770 (3.5367) grad_norm: 1.1323 (1.1814) time: 0.6273 [2021-03-26 17:38:16 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 550/1251] eta: 0:07:26 lr: 0.000815 loss: 3.5992 (3.5345) grad_norm: 1.1162 (1.1804) time: 0.6368 [2021-03-26 17:38:23 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 560/1251] eta: 0:07:20 lr: 0.000815 loss: 3.6132 (3.5339) grad_norm: 1.1341 (1.1808) time: 0.6318 [2021-03-26 17:38:29 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 570/1251] eta: 0:07:13 lr: 0.000815 loss: 3.7244 (3.5397) grad_norm: 1.1734 (1.1806) time: 0.6262 [2021-03-26 17:38:35 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 580/1251] eta: 0:07:07 lr: 0.000815 loss: 3.8844 (3.5474) grad_norm: 1.1586 (1.1800) time: 0.6360 [2021-03-26 17:38:42 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 590/1251] eta: 0:07:00 lr: 0.000815 loss: 3.8105 (3.5474) grad_norm: 1.1586 (1.1798) time: 0.6315 [2021-03-26 17:38:48 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 600/1251] eta: 0:06:54 lr: 0.000815 loss: 3.2787 (3.5420) grad_norm: 1.1675 (1.1798) time: 0.6281 [2021-03-26 17:38:54 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 610/1251] eta: 0:06:47 lr: 0.000815 loss: 3.2787 (3.5397) grad_norm: 1.1002 (1.1786) time: 0.6264 [2021-03-26 17:39:01 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 620/1251] eta: 0:06:41 lr: 0.000815 loss: 3.6645 (3.5453) grad_norm: 1.0874 (1.1773) time: 0.6289 [2021-03-26 17:39:07 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 630/1251] eta: 0:06:35 lr: 0.000814 loss: 3.6645 (3.5449) grad_norm: 1.1085 (1.1770) time: 0.6324 [2021-03-26 17:39:13 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 640/1251] eta: 0:06:28 lr: 0.000814 loss: 3.8288 (3.5507) grad_norm: 1.1896 (1.1789) time: 0.6319 [2021-03-26 17:39:19 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 650/1251] eta: 0:06:22 lr: 0.000814 loss: 3.6342 (3.5465) grad_norm: 1.2472 (1.1808) time: 0.6342 [2021-03-26 17:39:26 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 660/1251] eta: 0:06:15 lr: 0.000814 loss: 3.2388 (3.5451) grad_norm: 1.1800 (1.1802) time: 0.6292 [2021-03-26 17:39:32 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 670/1251] eta: 0:06:09 lr: 0.000814 loss: 3.3891 (3.5452) grad_norm: 1.1540 (1.1801) time: 0.6225 [2021-03-26 17:39:38 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 680/1251] eta: 0:06:03 lr: 0.000814 loss: 3.6877 (3.5459) grad_norm: 1.1527 (1.1804) time: 0.6304 [2021-03-26 17:39:45 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 690/1251] eta: 0:05:56 lr: 0.000814 loss: 3.6788 (3.5479) grad_norm: 1.0846 (1.1791) time: 0.6461 [2021-03-26 17:39:51 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 700/1251] eta: 0:05:50 lr: 0.000814 loss: 3.5511 (3.5441) grad_norm: 1.0752 (1.1788) time: 0.6416 [2021-03-26 17:39:58 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 710/1251] eta: 0:05:44 lr: 0.000814 loss: 3.4944 (3.5443) grad_norm: 1.1679 (1.1783) time: 0.6320 [2021-03-26 17:40:04 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 720/1251] eta: 0:05:37 lr: 0.000814 loss: 3.6346 (3.5443) grad_norm: 1.1716 (1.1790) time: 0.6244 [2021-03-26 17:40:10 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 730/1251] eta: 0:05:31 lr: 0.000814 loss: 3.5585 (3.5424) grad_norm: 1.1578 (1.1781) time: 0.6224 [2021-03-26 17:40:16 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 740/1251] eta: 0:05:24 lr: 0.000814 loss: 3.4103 (3.5425) grad_norm: 1.1368 (1.1783) time: 0.6328 [2021-03-26 17:40:23 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 750/1251] eta: 0:05:18 lr: 0.000814 loss: 3.5810 (3.5433) grad_norm: 1.1428 (1.1785) time: 0.6426 [2021-03-26 17:40:29 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 760/1251] eta: 0:05:12 lr: 0.000814 loss: 3.6008 (3.5438) grad_norm: 1.1428 (1.1783) time: 0.6385 [2021-03-26 17:40:35 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 770/1251] eta: 0:05:05 lr: 0.000814 loss: 3.5508 (3.5410) grad_norm: 1.1898 (1.1789) time: 0.6327 [2021-03-26 17:40:42 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 780/1251] eta: 0:04:59 lr: 0.000814 loss: 3.5508 (3.5404) grad_norm: 1.2434 (1.1799) time: 0.6353 [2021-03-26 17:40:48 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 790/1251] eta: 0:04:53 lr: 0.000814 loss: 3.4208 (3.5394) grad_norm: 1.1005 (1.1789) time: 0.6324 [2021-03-26 17:40:54 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 800/1251] eta: 0:04:46 lr: 0.000814 loss: 3.4466 (3.5379) grad_norm: 1.1137 (1.1788) time: 0.6273 [2021-03-26 17:41:01 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 810/1251] eta: 0:04:40 lr: 0.000814 loss: 3.4466 (3.5344) grad_norm: 1.1477 (1.1791) time: 0.6285 [2021-03-26 17:41:07 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 820/1251] eta: 0:04:33 lr: 0.000814 loss: 3.4753 (3.5358) grad_norm: 1.1552 (1.1794) time: 0.6304 [2021-03-26 17:41:13 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 830/1251] eta: 0:04:27 lr: 0.000814 loss: 3.6785 (3.5387) grad_norm: 1.1530 (1.1785) time: 0.6262 [2021-03-26 17:41:20 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 840/1251] eta: 0:04:21 lr: 0.000814 loss: 3.6180 (3.5377) grad_norm: 1.1878 (1.1800) time: 0.6308 [2021-03-26 17:41:26 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 850/1251] eta: 0:04:14 lr: 0.000814 loss: 3.3625 (3.5342) grad_norm: 1.2686 (1.1807) time: 0.6302 [2021-03-26 17:41:32 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 860/1251] eta: 0:04:08 lr: 0.000814 loss: 3.2686 (3.5331) grad_norm: 1.1475 (1.1804) time: 0.6249 [2021-03-26 17:41:38 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 870/1251] eta: 0:04:01 lr: 0.000814 loss: 3.4107 (3.5323) grad_norm: 1.0991 (1.1798) time: 0.6283 [2021-03-26 17:41:45 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 880/1251] eta: 0:03:55 lr: 0.000814 loss: 3.3894 (3.5305) grad_norm: 1.1210 (1.1795) time: 0.6318 [2021-03-26 17:41:51 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 890/1251] eta: 0:03:49 lr: 0.000814 loss: 3.4814 (3.5319) grad_norm: 1.1320 (1.1792) time: 0.6276 [2021-03-26 17:41:57 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 900/1251] eta: 0:03:42 lr: 0.000814 loss: 3.7966 (3.5346) grad_norm: 1.1433 (1.1794) time: 0.6257 [2021-03-26 17:42:04 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 910/1251] eta: 0:03:36 lr: 0.000814 loss: 3.8529 (3.5362) grad_norm: 1.1433 (1.1795) time: 0.6283 [2021-03-26 17:42:10 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 920/1251] eta: 0:03:30 lr: 0.000814 loss: 3.9338 (3.5388) grad_norm: 1.1055 (1.1788) time: 0.6293 [2021-03-26 17:42:16 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 930/1251] eta: 0:03:23 lr: 0.000814 loss: 3.7022 (3.5388) grad_norm: 1.0878 (1.1792) time: 0.6322 [2021-03-26 17:42:23 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 940/1251] eta: 0:03:17 lr: 0.000813 loss: 3.5567 (3.5395) grad_norm: 1.1422 (1.1785) time: 0.6335 [2021-03-26 17:42:29 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 950/1251] eta: 0:03:11 lr: 0.000813 loss: 3.6196 (3.5381) grad_norm: 1.1764 (1.1792) time: 0.6352 [2021-03-26 17:42:35 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 960/1251] eta: 0:03:04 lr: 0.000813 loss: 3.2411 (3.5345) grad_norm: 1.1764 (1.1791) time: 0.6323 [2021-03-26 17:42:42 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 970/1251] eta: 0:02:58 lr: 0.000813 loss: 3.6822 (3.5368) grad_norm: 1.1374 (1.1797) time: 0.6342 [2021-03-26 17:42:48 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 980/1251] eta: 0:02:51 lr: 0.000813 loss: 3.7769 (3.5381) grad_norm: 1.1235 (1.1787) time: 0.6300 [2021-03-26 17:42:54 swin_base_patch4_window7_224] INFO: Epoch: [85] [ 990/1251] eta: 0:02:45 lr: 0.000813 loss: 3.7769 (3.5408) grad_norm: 1.1235 (1.1782) time: 0.6190 [2021-03-26 17:43:00 swin_base_patch4_window7_224] INFO: Epoch: [85] [1000/1251] eta: 0:02:39 lr: 0.000813 loss: 3.5074 (3.5378) grad_norm: 1.1840 (1.1793) time: 0.6282 [2021-03-26 17:43:07 swin_base_patch4_window7_224] INFO: Epoch: [85] [1010/1251] eta: 0:02:32 lr: 0.000813 loss: 3.3985 (3.5384) grad_norm: 1.1732 (1.1786) time: 0.6361 [2021-03-26 17:43:13 swin_base_patch4_window7_224] INFO: Epoch: [85] [1020/1251] eta: 0:02:26 lr: 0.000813 loss: 3.6868 (3.5389) grad_norm: 1.1018 (1.1779) time: 0.6332 [2021-03-26 17:43:19 swin_base_patch4_window7_224] INFO: Epoch: [85] [1030/1251] eta: 0:02:20 lr: 0.000813 loss: 3.6868 (3.5392) grad_norm: 1.1214 (1.1778) time: 0.6327 [2021-03-26 17:43:26 swin_base_patch4_window7_224] INFO: Epoch: [85] [1040/1251] eta: 0:02:13 lr: 0.000813 loss: 3.6739 (3.5377) grad_norm: 1.1707 (1.1778) time: 0.6304 [2021-03-26 17:43:32 swin_base_patch4_window7_224] INFO: Epoch: [85] [1050/1251] eta: 0:02:07 lr: 0.000813 loss: 3.5185 (3.5363) grad_norm: 1.1926 (1.1784) time: 0.6268 [2021-03-26 17:43:38 swin_base_patch4_window7_224] INFO: Epoch: [85] [1060/1251] eta: 0:02:01 lr: 0.000813 loss: 3.6257 (3.5395) grad_norm: 1.1452 (1.1782) time: 0.6235 [2021-03-26 17:43:44 swin_base_patch4_window7_224] INFO: Epoch: [85] [1070/1251] eta: 0:01:54 lr: 0.000813 loss: 3.6003 (3.5375) grad_norm: 1.1452 (1.1785) time: 0.6295 [2021-03-26 17:43:51 swin_base_patch4_window7_224] INFO: Epoch: [85] [1080/1251] eta: 0:01:48 lr: 0.000813 loss: 3.4762 (3.5376) grad_norm: 1.1990 (1.1784) time: 0.6333 [2021-03-26 17:43:57 swin_base_patch4_window7_224] INFO: Epoch: [85] [1090/1251] eta: 0:01:42 lr: 0.000813 loss: 3.7551 (3.5373) grad_norm: 1.1608 (1.1783) time: 0.6290 [2021-03-26 17:44:03 swin_base_patch4_window7_224] INFO: Epoch: [85] [1100/1251] eta: 0:01:35 lr: 0.000813 loss: 3.6780 (3.5369) grad_norm: 1.1389 (1.1780) time: 0.6263 [2021-03-26 17:44:10 swin_base_patch4_window7_224] INFO: Epoch: [85] [1110/1251] eta: 0:01:29 lr: 0.000813 loss: 3.4781 (3.5368) grad_norm: 1.1527 (1.1788) time: 0.6233 [2021-03-26 17:44:16 swin_base_patch4_window7_224] INFO: Epoch: [85] [1120/1251] eta: 0:01:23 lr: 0.000813 loss: 3.7162 (3.5388) grad_norm: 1.1729 (1.1786) time: 0.6232 [2021-03-26 17:44:22 swin_base_patch4_window7_224] INFO: Epoch: [85] [1130/1251] eta: 0:01:16 lr: 0.000813 loss: 3.8373 (3.5401) grad_norm: 1.1136 (1.1781) time: 0.6318 [2021-03-26 17:44:28 swin_base_patch4_window7_224] INFO: Epoch: [85] [1140/1251] eta: 0:01:10 lr: 0.000813 loss: 3.7408 (3.5396) grad_norm: 1.1280 (1.1782) time: 0.6324 [2021-03-26 17:44:35 swin_base_patch4_window7_224] INFO: Epoch: [85] [1150/1251] eta: 0:01:04 lr: 0.000813 loss: 3.7408 (3.5425) grad_norm: 1.1510 (1.1783) time: 0.6303 [2021-03-26 17:44:41 swin_base_patch4_window7_224] INFO: Epoch: [85] [1160/1251] eta: 0:00:57 lr: 0.000813 loss: 3.7316 (3.5411) grad_norm: 1.1618 (1.1783) time: 0.6279 [2021-03-26 17:44:47 swin_base_patch4_window7_224] INFO: Epoch: [85] [1170/1251] eta: 0:00:51 lr: 0.000813 loss: 3.4457 (3.5405) grad_norm: 1.1458 (1.1784) time: 0.6263 [2021-03-26 17:44:54 swin_base_patch4_window7_224] INFO: Epoch: [85] [1180/1251] eta: 0:00:44 lr: 0.000813 loss: 3.4457 (3.5399) grad_norm: 1.1667 (1.1788) time: 0.6324 [2021-03-26 17:45:00 swin_base_patch4_window7_224] INFO: Epoch: [85] [1190/1251] eta: 0:00:38 lr: 0.000813 loss: 3.7296 (3.5408) grad_norm: 1.2012 (1.1788) time: 0.6272 [2021-03-26 17:45:06 swin_base_patch4_window7_224] INFO: Epoch: [85] [1200/1251] eta: 0:00:32 lr: 0.000813 loss: 3.5206 (3.5399) grad_norm: 1.1772 (1.1786) time: 0.6274 [2021-03-26 17:45:12 swin_base_patch4_window7_224] INFO: Epoch: [85] [1210/1251] eta: 0:00:25 lr: 0.000813 loss: 3.4842 (3.5395) grad_norm: 1.1679 (1.1787) time: 0.6306 [2021-03-26 17:45:19 swin_base_patch4_window7_224] INFO: Epoch: [85] [1220/1251] eta: 0:00:19 lr: 0.000813 loss: 3.8174 (3.5415) grad_norm: 1.1741 (1.1793) time: 0.6278 [2021-03-26 17:45:25 swin_base_patch4_window7_224] INFO: Epoch: [85] [1230/1251] eta: 0:00:13 lr: 0.000813 loss: 3.7926 (3.5392) grad_norm: 1.1902 (1.1800) time: 0.6285 [2021-03-26 17:45:31 swin_base_patch4_window7_224] INFO: Epoch: [85] [1240/1251] eta: 0:00:06 lr: 0.000813 loss: 3.7312 (3.5406) grad_norm: 1.1738 (1.1797) time: 0.6222 [2021-03-26 17:45:37 swin_base_patch4_window7_224] INFO: Epoch: [85] [1250/1251] eta: 0:00:00 lr: 0.000812 loss: 3.7937 (3.5420) grad_norm: 1.1371 (1.1799) time: 0.6144 [2021-03-26 17:46:34 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:04 loss: 1.0617 (1.0617) acc1: 79.6875 (79.6875) acc5: 93.7500 (93.7500) [2021-03-26 17:46:36 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 1.0273 (1.0019) acc1: 76.5625 (75.7102) acc5: 93.7500 (93.8920) [2021-03-26 17:46:37 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.0273 (1.0383) acc1: 75.0000 (75.2976) acc5: 93.7500 (93.5268) [2021-03-26 17:46:39 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.0466 (1.0583) acc1: 75.0000 (74.8992) acc5: 93.7500 (93.2964) [2021-03-26 17:46:40 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.0547 (1.0625) acc1: 76.5625 (75.4954) acc5: 92.1875 (93.2546) [2021-03-26 17:46:41 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0329 (1.0404) acc1: 78.1250 (76.2880) acc5: 93.7500 (93.3760) [2021-03-26 17:46:46 swin_base_patch4_window7_224] INFO: * Acc@1 76.212 Acc@5 93.460 loss 1.033 [2021-03-26 17:46:46 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.2% [2021-03-26 17:46:46 swin_base_patch4_window7_224] INFO: Max accuracy: 76.21% [2021-03-26 17:46:51 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 0/1251] eta: 1:30:07 lr: 0.000812 loss: 3.8947 (3.8947) grad_norm: 1.1707 (1.1707) time: 4.3229 [2021-03-26 17:46:57 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 10/1251] eta: 0:20:02 lr: 0.000812 loss: 3.8653 (3.7963) grad_norm: 1.1707 (1.1165) time: 0.9687 [2021-03-26 17:47:03 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 20/1251] eta: 0:16:37 lr: 0.000812 loss: 3.7401 (3.7103) grad_norm: 1.1172 (1.1087) time: 0.6344 [2021-03-26 17:47:10 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 30/1251] eta: 0:15:22 lr: 0.000812 loss: 3.8140 (3.7746) grad_norm: 1.1415 (1.1374) time: 0.6386 [2021-03-26 17:47:16 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 40/1251] eta: 0:14:35 lr: 0.000812 loss: 3.7117 (3.6802) grad_norm: 1.2717 (1.2010) time: 0.6310 [2021-03-26 17:47:22 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 50/1251] eta: 0:14:06 lr: 0.000812 loss: 3.7117 (3.6776) grad_norm: 1.2834 (1.2143) time: 0.6254 [2021-03-26 17:47:29 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 60/1251] eta: 0:13:44 lr: 0.000812 loss: 3.6685 (3.5926) grad_norm: 1.1790 (1.2021) time: 0.6305 [2021-03-26 17:47:35 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 70/1251] eta: 0:13:26 lr: 0.000812 loss: 3.5123 (3.6124) grad_norm: 1.2242 (1.2078) time: 0.6286 [2021-03-26 17:47:41 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 80/1251] eta: 0:13:12 lr: 0.000812 loss: 3.6877 (3.6081) grad_norm: 1.2343 (1.2053) time: 0.6299 [2021-03-26 17:47:48 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 90/1251] eta: 0:12:59 lr: 0.000812 loss: 3.5999 (3.6133) grad_norm: 1.2148 (1.2055) time: 0.6313 [2021-03-26 17:47:54 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 100/1251] eta: 0:12:48 lr: 0.000812 loss: 3.5801 (3.6148) grad_norm: 1.1522 (1.1990) time: 0.6314 [2021-03-26 17:48:00 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 110/1251] eta: 0:12:37 lr: 0.000812 loss: 3.6193 (3.6108) grad_norm: 1.1522 (1.2080) time: 0.6296 [2021-03-26 17:48:06 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 120/1251] eta: 0:12:27 lr: 0.000812 loss: 3.5722 (3.5980) grad_norm: 1.2300 (1.2072) time: 0.6252 [2021-03-26 17:48:13 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 130/1251] eta: 0:12:18 lr: 0.000812 loss: 3.5469 (3.5972) grad_norm: 1.1490 (1.2037) time: 0.6300 [2021-03-26 17:48:19 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 140/1251] eta: 0:12:10 lr: 0.000812 loss: 3.7162 (3.6055) grad_norm: 1.0963 (1.1986) time: 0.6360 [2021-03-26 17:48:25 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 150/1251] eta: 0:12:01 lr: 0.000812 loss: 3.5690 (3.5812) grad_norm: 1.1347 (1.2031) time: 0.6320 [2021-03-26 17:48:32 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 160/1251] eta: 0:11:53 lr: 0.000812 loss: 3.3126 (3.5660) grad_norm: 1.3168 (inf) time: 0.6282 [2021-03-26 17:48:38 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 170/1251] eta: 0:11:45 lr: 0.000812 loss: 3.3126 (3.5640) grad_norm: 1.2311 (inf) time: 0.6329 [2021-03-26 17:48:44 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 180/1251] eta: 0:11:38 lr: 0.000812 loss: 3.7919 (3.5832) grad_norm: 1.1691 (inf) time: 0.6354 [2021-03-26 17:48:51 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 190/1251] eta: 0:11:30 lr: 0.000812 loss: 3.7483 (3.5814) grad_norm: 1.2336 (inf) time: 0.6355 [2021-03-26 17:48:57 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 200/1251] eta: 0:11:23 lr: 0.000812 loss: 3.5801 (3.5802) grad_norm: 1.1323 (inf) time: 0.6330 [2021-03-26 17:49:03 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 210/1251] eta: 0:11:15 lr: 0.000812 loss: 3.6438 (3.5890) grad_norm: 1.1554 (inf) time: 0.6280 [2021-03-26 17:49:10 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 220/1251] eta: 0:11:08 lr: 0.000812 loss: 3.7232 (3.5945) grad_norm: 1.2189 (inf) time: 0.6326 [2021-03-26 17:49:16 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 230/1251] eta: 0:11:00 lr: 0.000812 loss: 3.7373 (3.5991) grad_norm: 1.2119 (inf) time: 0.6307 [2021-03-26 17:49:22 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 240/1251] eta: 0:10:53 lr: 0.000812 loss: 3.7332 (3.6024) grad_norm: 1.1985 (inf) time: 0.6270 [2021-03-26 17:49:29 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 250/1251] eta: 0:10:46 lr: 0.000812 loss: 3.7020 (3.6024) grad_norm: 1.1357 (inf) time: 0.6277 [2021-03-26 17:49:35 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 260/1251] eta: 0:10:39 lr: 0.000812 loss: 3.7204 (3.6070) grad_norm: 1.1211 (inf) time: 0.6340 [2021-03-26 17:49:41 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 270/1251] eta: 0:10:33 lr: 0.000812 loss: 3.7301 (3.6130) grad_norm: 1.1156 (inf) time: 0.6405 [2021-03-26 17:49:48 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 280/1251] eta: 0:10:26 lr: 0.000812 loss: 3.8009 (3.6219) grad_norm: 1.1884 (inf) time: 0.6336 [2021-03-26 17:49:54 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 290/1251] eta: 0:10:18 lr: 0.000812 loss: 3.8880 (3.6291) grad_norm: 1.2516 (inf) time: 0.6272 [2021-03-26 17:50:00 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 300/1251] eta: 0:10:11 lr: 0.000811 loss: 3.7376 (3.6268) grad_norm: 1.3149 (inf) time: 0.6262 [2021-03-26 17:50:07 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 310/1251] eta: 0:10:05 lr: 0.000811 loss: 3.5657 (3.6205) grad_norm: 1.1462 (inf) time: 0.6305 [2021-03-26 17:50:13 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 320/1251] eta: 0:09:58 lr: 0.000811 loss: 3.5031 (3.6141) grad_norm: 1.1424 (inf) time: 0.6290 [2021-03-26 17:50:19 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 330/1251] eta: 0:09:51 lr: 0.000811 loss: 3.3809 (3.6043) grad_norm: 1.1363 (inf) time: 0.6250 [2021-03-26 17:50:25 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 340/1251] eta: 0:09:44 lr: 0.000811 loss: 3.5783 (3.6068) grad_norm: 1.1792 (inf) time: 0.6223 [2021-03-26 17:50:31 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 350/1251] eta: 0:09:37 lr: 0.000811 loss: 3.6186 (3.6049) grad_norm: 1.1796 (inf) time: 0.6196 [2021-03-26 17:50:38 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 360/1251] eta: 0:09:30 lr: 0.000811 loss: 3.4346 (3.5933) grad_norm: 1.1753 (inf) time: 0.6247 [2021-03-26 17:50:44 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 370/1251] eta: 0:09:24 lr: 0.000811 loss: 3.4033 (3.5920) grad_norm: 1.1544 (inf) time: 0.6299 [2021-03-26 17:50:50 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 380/1251] eta: 0:09:17 lr: 0.000811 loss: 3.6837 (3.5899) grad_norm: 1.1478 (inf) time: 0.6308 [2021-03-26 17:50:57 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 390/1251] eta: 0:09:10 lr: 0.000811 loss: 3.7855 (3.5955) grad_norm: 1.0963 (inf) time: 0.6291 [2021-03-26 17:51:03 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 400/1251] eta: 0:09:04 lr: 0.000811 loss: 3.7325 (3.5938) grad_norm: 1.0903 (inf) time: 0.6334 [2021-03-26 17:51:09 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 410/1251] eta: 0:08:57 lr: 0.000811 loss: 3.7122 (3.5959) grad_norm: 1.1344 (inf) time: 0.6322 [2021-03-26 17:51:15 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 420/1251] eta: 0:08:50 lr: 0.000811 loss: 3.6758 (3.5912) grad_norm: 1.1092 (inf) time: 0.6225 [2021-03-26 17:51:22 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 430/1251] eta: 0:08:44 lr: 0.000811 loss: 3.4786 (3.5926) grad_norm: 1.0845 (inf) time: 0.6205 [2021-03-26 17:51:28 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 440/1251] eta: 0:08:37 lr: 0.000811 loss: 3.8398 (3.5900) grad_norm: 1.1128 (inf) time: 0.6246 [2021-03-26 17:51:34 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 450/1251] eta: 0:08:31 lr: 0.000811 loss: 3.5506 (3.5896) grad_norm: 1.1535 (inf) time: 0.6284 [2021-03-26 17:51:41 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 460/1251] eta: 0:08:24 lr: 0.000811 loss: 3.3789 (3.5842) grad_norm: 1.2065 (inf) time: 0.6294 [2021-03-26 17:51:47 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 470/1251] eta: 0:08:17 lr: 0.000811 loss: 3.2446 (3.5805) grad_norm: 1.2515 (inf) time: 0.6300 [2021-03-26 17:51:53 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 480/1251] eta: 0:08:11 lr: 0.000811 loss: 3.5141 (3.5816) grad_norm: 1.3121 (inf) time: 0.6239 [2021-03-26 17:51:59 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 490/1251] eta: 0:08:04 lr: 0.000811 loss: 3.5208 (3.5777) grad_norm: 1.1668 (inf) time: 0.6226 [2021-03-26 17:52:06 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 500/1251] eta: 0:07:58 lr: 0.000811 loss: 3.6371 (3.5764) grad_norm: 1.1030 (inf) time: 0.6271 [2021-03-26 17:52:12 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 510/1251] eta: 0:07:51 lr: 0.000811 loss: 3.6649 (3.5785) grad_norm: 1.0700 (inf) time: 0.6251 [2021-03-26 17:52:18 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 520/1251] eta: 0:07:45 lr: 0.000811 loss: 3.5792 (3.5764) grad_norm: 1.0813 (inf) time: 0.6288 [2021-03-26 17:52:25 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 530/1251] eta: 0:07:38 lr: 0.000811 loss: 3.4969 (3.5757) grad_norm: 1.1416 (inf) time: 0.6330 [2021-03-26 17:52:31 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 540/1251] eta: 0:07:32 lr: 0.000811 loss: 3.4969 (3.5726) grad_norm: 1.1416 (inf) time: 0.6267 [2021-03-26 17:52:37 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 550/1251] eta: 0:07:25 lr: 0.000811 loss: 3.5977 (3.5712) grad_norm: 1.1416 (inf) time: 0.6275 [2021-03-26 17:52:43 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 560/1251] eta: 0:07:19 lr: 0.000811 loss: 3.6497 (3.5694) grad_norm: 1.1405 (inf) time: 0.6346 [2021-03-26 17:52:50 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 570/1251] eta: 0:07:13 lr: 0.000811 loss: 3.6554 (3.5725) grad_norm: 1.0666 (inf) time: 0.6332 [2021-03-26 17:52:56 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 580/1251] eta: 0:07:06 lr: 0.000811 loss: 3.6554 (3.5723) grad_norm: 1.1141 (inf) time: 0.6299 [2021-03-26 17:53:02 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 590/1251] eta: 0:07:00 lr: 0.000811 loss: 3.5530 (3.5683) grad_norm: 1.1364 (inf) time: 0.6267 [2021-03-26 17:53:09 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 600/1251] eta: 0:06:53 lr: 0.000811 loss: 3.6033 (3.5684) grad_norm: 1.1425 (inf) time: 0.6265 [2021-03-26 17:53:15 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 610/1251] eta: 0:06:47 lr: 0.000810 loss: 3.8334 (3.5748) grad_norm: 1.1653 (inf) time: 0.6354 [2021-03-26 17:53:21 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 620/1251] eta: 0:06:40 lr: 0.000810 loss: 3.7858 (3.5756) grad_norm: 1.1835 (inf) time: 0.6334 [2021-03-26 17:53:27 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 630/1251] eta: 0:06:34 lr: 0.000810 loss: 3.6862 (3.5749) grad_norm: 1.1251 (inf) time: 0.6221 [2021-03-26 17:53:34 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 640/1251] eta: 0:06:28 lr: 0.000810 loss: 3.7548 (3.5776) grad_norm: 1.1117 (inf) time: 0.6223 [2021-03-26 17:53:40 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 650/1251] eta: 0:06:21 lr: 0.000810 loss: 3.7562 (3.5788) grad_norm: 1.1823 (inf) time: 0.6287 [2021-03-26 17:53:46 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 660/1251] eta: 0:06:15 lr: 0.000810 loss: 3.6492 (3.5754) grad_norm: 1.2218 (inf) time: 0.6278 [2021-03-26 17:53:53 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 670/1251] eta: 0:06:08 lr: 0.000810 loss: 3.5340 (3.5757) grad_norm: 1.2218 (inf) time: 0.6273 [2021-03-26 17:53:59 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 680/1251] eta: 0:06:02 lr: 0.000810 loss: 3.5217 (3.5759) grad_norm: 1.1619 (inf) time: 0.6294 [2021-03-26 17:54:05 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 690/1251] eta: 0:05:56 lr: 0.000810 loss: 3.5217 (3.5750) grad_norm: 1.1622 (inf) time: 0.6328 [2021-03-26 17:54:12 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 700/1251] eta: 0:05:49 lr: 0.000810 loss: 3.6337 (3.5738) grad_norm: 1.1622 (inf) time: 0.6354 [2021-03-26 17:54:18 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 710/1251] eta: 0:05:43 lr: 0.000810 loss: 3.6337 (3.5714) grad_norm: 1.1637 (inf) time: 0.6317 [2021-03-26 17:54:24 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 720/1251] eta: 0:05:36 lr: 0.000810 loss: 3.7347 (3.5746) grad_norm: 1.1617 (inf) time: 0.6295 [2021-03-26 17:54:30 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 730/1251] eta: 0:05:30 lr: 0.000810 loss: 3.7403 (3.5750) grad_norm: 1.1738 (inf) time: 0.6324 [2021-03-26 17:54:37 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 740/1251] eta: 0:05:24 lr: 0.000810 loss: 3.7127 (3.5756) grad_norm: 1.2144 (inf) time: 0.6333 [2021-03-26 17:54:43 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 750/1251] eta: 0:05:17 lr: 0.000810 loss: 3.6510 (3.5740) grad_norm: 1.1945 (inf) time: 0.6381 [2021-03-26 17:54:50 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 760/1251] eta: 0:05:11 lr: 0.000810 loss: 3.5844 (3.5723) grad_norm: 1.2001 (inf) time: 0.6370 [2021-03-26 17:54:56 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 770/1251] eta: 0:05:05 lr: 0.000810 loss: 3.5441 (3.5734) grad_norm: 1.2001 (inf) time: 0.6294 [2021-03-26 17:55:02 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 780/1251] eta: 0:04:58 lr: 0.000810 loss: 3.5441 (3.5713) grad_norm: 1.1886 (inf) time: 0.6268 [2021-03-26 17:55:08 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 790/1251] eta: 0:04:52 lr: 0.000810 loss: 3.5738 (3.5710) grad_norm: 1.2658 (inf) time: 0.6272 [2021-03-26 17:55:15 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 800/1251] eta: 0:04:46 lr: 0.000810 loss: 3.7089 (3.5727) grad_norm: 1.2658 (inf) time: 0.6329 [2021-03-26 17:55:21 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 810/1251] eta: 0:04:39 lr: 0.000810 loss: 3.7089 (3.5733) grad_norm: 1.1874 (inf) time: 0.6306 [2021-03-26 17:55:27 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 820/1251] eta: 0:04:33 lr: 0.000810 loss: 3.8041 (3.5756) grad_norm: 1.1874 (inf) time: 0.6266 [2021-03-26 17:55:34 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 830/1251] eta: 0:04:27 lr: 0.000810 loss: 3.7371 (3.5749) grad_norm: 1.1482 (inf) time: 0.6317 [2021-03-26 17:55:40 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 840/1251] eta: 0:04:20 lr: 0.000810 loss: 3.6946 (3.5748) grad_norm: 1.1470 (inf) time: 0.6351 [2021-03-26 17:55:46 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 850/1251] eta: 0:04:14 lr: 0.000810 loss: 3.5216 (3.5743) grad_norm: 1.1723 (inf) time: 0.6349 [2021-03-26 17:55:53 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 860/1251] eta: 0:04:07 lr: 0.000810 loss: 3.6176 (3.5761) grad_norm: 1.1499 (inf) time: 0.6315 [2021-03-26 17:55:59 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 870/1251] eta: 0:04:01 lr: 0.000810 loss: 3.7763 (3.5763) grad_norm: 1.0846 (inf) time: 0.6343 [2021-03-26 17:56:05 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 880/1251] eta: 0:03:55 lr: 0.000810 loss: 3.6460 (3.5765) grad_norm: 1.0988 (inf) time: 0.6315 [2021-03-26 17:56:12 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 890/1251] eta: 0:03:48 lr: 0.000810 loss: 3.5364 (3.5726) grad_norm: 1.2242 (inf) time: 0.6314 [2021-03-26 17:56:18 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 900/1251] eta: 0:03:42 lr: 0.000810 loss: 3.1296 (3.5717) grad_norm: 1.2301 (inf) time: 0.6340 [2021-03-26 17:56:24 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 910/1251] eta: 0:03:36 lr: 0.000810 loss: 3.5755 (3.5709) grad_norm: 1.2209 (inf) time: 0.6235 [2021-03-26 17:56:30 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 920/1251] eta: 0:03:29 lr: 0.000809 loss: 3.5755 (3.5700) grad_norm: 1.2070 (inf) time: 0.6213 [2021-03-26 17:56:37 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 930/1251] eta: 0:03:23 lr: 0.000809 loss: 3.6681 (3.5702) grad_norm: 1.2070 (inf) time: 0.6228 [2021-03-26 17:56:43 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 940/1251] eta: 0:03:17 lr: 0.000809 loss: 3.5278 (3.5698) grad_norm: 1.2408 (inf) time: 0.6363 [2021-03-26 17:56:49 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 950/1251] eta: 0:03:10 lr: 0.000809 loss: 3.5179 (3.5689) grad_norm: 1.1928 (inf) time: 0.6385 [2021-03-26 17:56:56 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 960/1251] eta: 0:03:04 lr: 0.000809 loss: 3.7433 (3.5703) grad_norm: 1.1928 (inf) time: 0.6275 [2021-03-26 17:57:02 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 970/1251] eta: 0:02:58 lr: 0.000809 loss: 3.7600 (3.5702) grad_norm: 1.1985 (inf) time: 0.6275 [2021-03-26 17:57:08 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 980/1251] eta: 0:02:51 lr: 0.000809 loss: 3.5254 (3.5681) grad_norm: 1.0925 (inf) time: 0.6260 [2021-03-26 17:57:14 swin_base_patch4_window7_224] INFO: Epoch: [86] [ 990/1251] eta: 0:02:45 lr: 0.000809 loss: 3.2955 (3.5660) grad_norm: 1.0834 (inf) time: 0.6269 [2021-03-26 17:57:21 swin_base_patch4_window7_224] INFO: Epoch: [86] [1000/1251] eta: 0:02:38 lr: 0.000809 loss: 3.0694 (3.5624) grad_norm: 1.1444 (inf) time: 0.6260 [2021-03-26 17:57:27 swin_base_patch4_window7_224] INFO: Epoch: [86] [1010/1251] eta: 0:02:32 lr: 0.000809 loss: 3.3634 (3.5612) grad_norm: 1.1758 (inf) time: 0.6315 [2021-03-26 17:57:33 swin_base_patch4_window7_224] INFO: Epoch: [86] [1020/1251] eta: 0:02:26 lr: 0.000809 loss: 3.3634 (3.5592) grad_norm: 1.2246 (inf) time: 0.6376 [2021-03-26 17:57:40 swin_base_patch4_window7_224] INFO: Epoch: [86] [1030/1251] eta: 0:02:19 lr: 0.000809 loss: 3.3846 (3.5577) grad_norm: 1.1907 (inf) time: 0.6264 [2021-03-26 17:57:46 swin_base_patch4_window7_224] INFO: Epoch: [86] [1040/1251] eta: 0:02:13 lr: 0.000809 loss: 3.5101 (3.5579) grad_norm: 1.1306 (inf) time: 0.6200 [2021-03-26 17:57:52 swin_base_patch4_window7_224] INFO: Epoch: [86] [1050/1251] eta: 0:02:07 lr: 0.000809 loss: 3.6202 (3.5585) grad_norm: 1.1656 (inf) time: 0.6257 [2021-03-26 17:57:58 swin_base_patch4_window7_224] INFO: Epoch: [86] [1060/1251] eta: 0:02:00 lr: 0.000809 loss: 3.6035 (3.5590) grad_norm: 1.1738 (inf) time: 0.6291 [2021-03-26 17:58:05 swin_base_patch4_window7_224] INFO: Epoch: [86] [1070/1251] eta: 0:01:54 lr: 0.000809 loss: 3.6117 (3.5597) grad_norm: 1.1215 (inf) time: 0.6313 [2021-03-26 17:58:11 swin_base_patch4_window7_224] INFO: Epoch: [86] [1080/1251] eta: 0:01:48 lr: 0.000809 loss: 3.6117 (3.5591) grad_norm: 1.1165 (inf) time: 0.6337 [2021-03-26 17:58:17 swin_base_patch4_window7_224] INFO: Epoch: [86] [1090/1251] eta: 0:01:41 lr: 0.000809 loss: 3.5260 (3.5571) grad_norm: 1.1166 (inf) time: 0.6317 [2021-03-26 17:58:24 swin_base_patch4_window7_224] INFO: Epoch: [86] [1100/1251] eta: 0:01:35 lr: 0.000809 loss: 3.7312 (3.5594) grad_norm: 1.0754 (inf) time: 0.6274 [2021-03-26 17:58:30 swin_base_patch4_window7_224] INFO: Epoch: [86] [1110/1251] eta: 0:01:29 lr: 0.000809 loss: 3.6836 (3.5586) grad_norm: 1.0780 (inf) time: 0.6284 [2021-03-26 17:58:36 swin_base_patch4_window7_224] INFO: Epoch: [86] [1120/1251] eta: 0:01:22 lr: 0.000809 loss: 3.7356 (3.5624) grad_norm: 1.1881 (inf) time: 0.6298 [2021-03-26 17:58:43 swin_base_patch4_window7_224] INFO: Epoch: [86] [1130/1251] eta: 0:01:16 lr: 0.000809 loss: 3.7837 (3.5625) grad_norm: 1.1438 (inf) time: 0.6327 [2021-03-26 17:58:49 swin_base_patch4_window7_224] INFO: Epoch: [86] [1140/1251] eta: 0:01:10 lr: 0.000809 loss: 3.6726 (3.5623) grad_norm: 1.0836 (inf) time: 0.6308 [2021-03-26 17:58:55 swin_base_patch4_window7_224] INFO: Epoch: [86] [1150/1251] eta: 0:01:03 lr: 0.000809 loss: 3.7415 (3.5644) grad_norm: 1.1801 (inf) time: 0.6262 [2021-03-26 17:59:01 swin_base_patch4_window7_224] INFO: Epoch: [86] [1160/1251] eta: 0:00:57 lr: 0.000809 loss: 3.7153 (3.5643) grad_norm: 1.1388 (inf) time: 0.6285 [2021-03-26 17:59:08 swin_base_patch4_window7_224] INFO: Epoch: [86] [1170/1251] eta: 0:00:51 lr: 0.000809 loss: 3.3289 (3.5631) grad_norm: 1.0946 (inf) time: 0.6299 [2021-03-26 17:59:14 swin_base_patch4_window7_224] INFO: Epoch: [86] [1180/1251] eta: 0:00:44 lr: 0.000809 loss: 3.1066 (3.5594) grad_norm: 1.1532 (inf) time: 0.6324 [2021-03-26 17:59:20 swin_base_patch4_window7_224] INFO: Epoch: [86] [1190/1251] eta: 0:00:38 lr: 0.000809 loss: 3.4105 (3.5611) grad_norm: 1.1882 (inf) time: 0.6295 [2021-03-26 17:59:27 swin_base_patch4_window7_224] INFO: Epoch: [86] [1200/1251] eta: 0:00:32 lr: 0.000809 loss: 3.5435 (3.5595) grad_norm: 1.1522 (inf) time: 0.6255 [2021-03-26 17:59:33 swin_base_patch4_window7_224] INFO: Epoch: [86] [1210/1251] eta: 0:00:25 lr: 0.000809 loss: 3.4644 (3.5594) grad_norm: 1.1403 (inf) time: 0.6258 [2021-03-26 17:59:39 swin_base_patch4_window7_224] INFO: Epoch: [86] [1220/1251] eta: 0:00:19 lr: 0.000808 loss: 3.5529 (3.5611) grad_norm: 1.1295 (inf) time: 0.6265 [2021-03-26 17:59:45 swin_base_patch4_window7_224] INFO: Epoch: [86] [1230/1251] eta: 0:00:13 lr: 0.000808 loss: 3.6861 (3.5631) grad_norm: 1.1167 (inf) time: 0.6286 [2021-03-26 17:59:52 swin_base_patch4_window7_224] INFO: Epoch: [86] [1240/1251] eta: 0:00:06 lr: 0.000808 loss: 3.8801 (3.5651) grad_norm: 1.1625 (inf) time: 0.6276 [2021-03-26 17:59:58 swin_base_patch4_window7_224] INFO: Epoch: [86] [1250/1251] eta: 0:00:00 lr: 0.000808 loss: 3.7340 (3.5644) grad_norm: 1.1547 (inf) time: 0.6240 [2021-03-26 18:00:04 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:17 loss: 1.3369 (1.3369) acc1: 65.6250 (65.6250) acc5: 90.6250 (90.6250) [2021-03-26 18:00:06 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.0364 (1.1253) acc1: 75.0000 (74.8580) acc5: 93.7500 (92.1875) [2021-03-26 18:00:09 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0364 (1.0962) acc1: 75.0000 (75.4464) acc5: 93.7500 (92.7083) [2021-03-26 18:00:12 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0852 (1.0896) acc1: 75.0000 (74.9496) acc5: 93.7500 (92.5403) [2021-03-26 18:00:13 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0852 (1.0935) acc1: 71.8750 (74.5808) acc5: 93.7500 (92.7210) [2021-03-26 18:00:14 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0262 (1.0760) acc1: 71.8750 (75.1680) acc5: 93.7500 (92.9280) [2021-03-26 18:00:17 swin_base_patch4_window7_224] INFO: * Acc@1 75.834 Acc@5 93.248 loss 1.044 [2021-03-26 18:00:17 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.8% [2021-03-26 18:00:17 swin_base_patch4_window7_224] INFO: Max accuracy: 76.21% [2021-03-26 18:00:22 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 0/1251] eta: 1:33:13 lr: 0.000808 loss: 3.5426 (3.5426) grad_norm: 1.0192 (1.0192) time: 4.4710 [2021-03-26 18:00:28 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 10/1251] eta: 0:20:34 lr: 0.000808 loss: 3.5426 (3.4931) grad_norm: 1.1526 (1.1913) time: 0.9947 [2021-03-26 18:00:35 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 20/1251] eta: 0:16:47 lr: 0.000808 loss: 3.5228 (3.5004) grad_norm: 1.1556 (1.2076) time: 0.6359 [2021-03-26 18:00:41 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 30/1251] eta: 0:15:26 lr: 0.000808 loss: 3.5276 (3.5335) grad_norm: 1.1630 (1.1911) time: 0.6289 [2021-03-26 18:00:47 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 40/1251] eta: 0:14:40 lr: 0.000808 loss: 3.6459 (3.5196) grad_norm: 1.1757 (1.1809) time: 0.6318 [2021-03-26 18:00:53 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 50/1251] eta: 0:14:09 lr: 0.000808 loss: 3.7196 (3.5407) grad_norm: 1.1551 (1.1764) time: 0.6272 [2021-03-26 18:01:00 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 60/1251] eta: 0:13:45 lr: 0.000808 loss: 3.7076 (3.5269) grad_norm: 1.0999 (1.1704) time: 0.6236 [2021-03-26 18:01:06 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 70/1251] eta: 0:13:29 lr: 0.000808 loss: 3.7147 (3.5473) grad_norm: 1.1758 (1.1768) time: 0.6309 [2021-03-26 18:01:12 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 80/1251] eta: 0:13:13 lr: 0.000808 loss: 3.7147 (3.5587) grad_norm: 1.1873 (1.1824) time: 0.6311 [2021-03-26 18:01:18 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 90/1251] eta: 0:12:59 lr: 0.000808 loss: 3.5353 (3.5244) grad_norm: 1.1028 (1.1724) time: 0.6211 [2021-03-26 18:01:25 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 100/1251] eta: 0:12:48 lr: 0.000808 loss: 3.6307 (3.5517) grad_norm: 1.1353 (1.1785) time: 0.6253 [2021-03-26 18:01:31 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 110/1251] eta: 0:12:37 lr: 0.000808 loss: 3.5658 (3.5296) grad_norm: 1.2573 (1.1900) time: 0.6305 [2021-03-26 18:01:37 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 120/1251] eta: 0:12:27 lr: 0.000808 loss: 3.1499 (3.4965) grad_norm: 1.1887 (1.1844) time: 0.6300 [2021-03-26 18:01:44 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 130/1251] eta: 0:12:19 lr: 0.000808 loss: 3.0952 (3.4820) grad_norm: 1.1643 (1.1849) time: 0.6362 [2021-03-26 18:01:50 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 140/1251] eta: 0:12:10 lr: 0.000808 loss: 3.3441 (3.4827) grad_norm: 1.1793 (1.1888) time: 0.6326 [2021-03-26 18:01:56 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 150/1251] eta: 0:12:01 lr: 0.000808 loss: 3.3824 (3.4688) grad_norm: 1.1844 (1.1896) time: 0.6270 [2021-03-26 18:02:03 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 160/1251] eta: 0:11:53 lr: 0.000808 loss: 3.3885 (3.4802) grad_norm: 1.2175 (1.2043) time: 0.6314 [2021-03-26 18:02:09 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 170/1251] eta: 0:11:45 lr: 0.000808 loss: 3.5957 (3.4801) grad_norm: 1.3181 (1.2061) time: 0.6310 [2021-03-26 18:02:15 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 180/1251] eta: 0:11:37 lr: 0.000808 loss: 3.5351 (3.4656) grad_norm: 1.2221 (1.2062) time: 0.6313 [2021-03-26 18:02:22 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 190/1251] eta: 0:11:30 lr: 0.000808 loss: 3.3979 (3.4578) grad_norm: 1.1733 (1.2044) time: 0.6320 [2021-03-26 18:02:28 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 200/1251] eta: 0:11:22 lr: 0.000808 loss: 3.3717 (3.4524) grad_norm: 1.1787 (1.2088) time: 0.6276 [2021-03-26 18:02:34 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 210/1251] eta: 0:11:14 lr: 0.000808 loss: 3.4268 (3.4532) grad_norm: 1.1879 (1.2072) time: 0.6276 [2021-03-26 18:02:40 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 220/1251] eta: 0:11:07 lr: 0.000808 loss: 3.6524 (3.4606) grad_norm: 1.1574 (1.2035) time: 0.6283 [2021-03-26 18:02:47 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 230/1251] eta: 0:11:00 lr: 0.000808 loss: 3.5325 (3.4636) grad_norm: 1.1773 (1.2044) time: 0.6297 [2021-03-26 18:02:53 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 240/1251] eta: 0:10:52 lr: 0.000808 loss: 3.5734 (3.4683) grad_norm: 1.1464 (1.2028) time: 0.6292 [2021-03-26 18:02:59 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 250/1251] eta: 0:10:46 lr: 0.000808 loss: 3.6445 (3.4679) grad_norm: 1.1464 (1.2051) time: 0.6319 [2021-03-26 18:03:06 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 260/1251] eta: 0:10:39 lr: 0.000808 loss: 3.3420 (3.4589) grad_norm: 1.1719 (1.2087) time: 0.6373 [2021-03-26 18:03:12 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 270/1251] eta: 0:10:32 lr: 0.000808 loss: 3.6365 (3.4648) grad_norm: 1.1757 (1.2085) time: 0.6345 [2021-03-26 18:03:18 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 280/1251] eta: 0:10:25 lr: 0.000807 loss: 3.8794 (3.4750) grad_norm: 1.1757 (1.2072) time: 0.6319 [2021-03-26 18:03:25 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 290/1251] eta: 0:10:18 lr: 0.000807 loss: 3.7725 (3.4838) grad_norm: 1.1419 (1.2068) time: 0.6303 [2021-03-26 18:03:31 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 300/1251] eta: 0:10:11 lr: 0.000807 loss: 3.5664 (3.4763) grad_norm: 1.1374 (1.2041) time: 0.6301 [2021-03-26 18:03:37 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 310/1251] eta: 0:10:04 lr: 0.000807 loss: 3.3728 (3.4724) grad_norm: 1.1315 (1.2013) time: 0.6268 [2021-03-26 18:03:44 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 320/1251] eta: 0:09:57 lr: 0.000807 loss: 3.6780 (3.4786) grad_norm: 1.1428 (1.1994) time: 0.6282 [2021-03-26 18:03:50 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 330/1251] eta: 0:09:51 lr: 0.000807 loss: 3.7557 (3.4771) grad_norm: 1.1466 (1.1992) time: 0.6309 [2021-03-26 18:03:56 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 340/1251] eta: 0:09:44 lr: 0.000807 loss: 3.6107 (3.4798) grad_norm: 1.1313 (1.1995) time: 0.6327 [2021-03-26 18:04:03 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 350/1251] eta: 0:09:37 lr: 0.000807 loss: 3.4615 (3.4769) grad_norm: 1.1851 (1.2006) time: 0.6325 [2021-03-26 18:04:09 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 360/1251] eta: 0:09:31 lr: 0.000807 loss: 3.5322 (3.4806) grad_norm: 1.1943 (1.2005) time: 0.6288 [2021-03-26 18:04:15 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 370/1251] eta: 0:09:24 lr: 0.000807 loss: 3.7157 (3.4843) grad_norm: 1.1246 (1.1990) time: 0.6314 [2021-03-26 18:04:21 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 380/1251] eta: 0:09:17 lr: 0.000807 loss: 3.5579 (3.4881) grad_norm: 1.0959 (1.1974) time: 0.6311 [2021-03-26 18:04:28 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 390/1251] eta: 0:09:11 lr: 0.000807 loss: 3.6005 (3.4896) grad_norm: 1.1059 (1.1958) time: 0.6266 [2021-03-26 18:04:34 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 400/1251] eta: 0:09:04 lr: 0.000807 loss: 3.5659 (3.4833) grad_norm: 1.1200 (1.1940) time: 0.6268 [2021-03-26 18:04:40 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 410/1251] eta: 0:08:57 lr: 0.000807 loss: 3.1725 (3.4790) grad_norm: 1.1587 (1.1943) time: 0.6264 [2021-03-26 18:04:47 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 420/1251] eta: 0:08:51 lr: 0.000807 loss: 3.5917 (3.4795) grad_norm: 1.1579 (1.1943) time: 0.6250 [2021-03-26 18:04:53 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 430/1251] eta: 0:08:44 lr: 0.000807 loss: 3.7375 (3.4824) grad_norm: 1.0914 (1.1924) time: 0.6268 [2021-03-26 18:04:59 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 440/1251] eta: 0:08:37 lr: 0.000807 loss: 3.4002 (3.4775) grad_norm: 1.0612 (1.1907) time: 0.6224 [2021-03-26 18:05:05 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 450/1251] eta: 0:08:31 lr: 0.000807 loss: 3.6650 (3.4819) grad_norm: 1.1059 (1.1908) time: 0.6233 [2021-03-26 18:05:12 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 460/1251] eta: 0:08:24 lr: 0.000807 loss: 3.7244 (3.4805) grad_norm: 1.1752 (1.1907) time: 0.6317 [2021-03-26 18:05:18 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 470/1251] eta: 0:08:18 lr: 0.000807 loss: 3.7359 (3.4863) grad_norm: 1.2100 (1.1925) time: 0.6310 [2021-03-26 18:05:24 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 480/1251] eta: 0:08:11 lr: 0.000807 loss: 3.8927 (3.4939) grad_norm: 1.1850 (1.1912) time: 0.6296 [2021-03-26 18:05:30 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 490/1251] eta: 0:08:04 lr: 0.000807 loss: 3.6671 (3.4937) grad_norm: 1.1949 (inf) time: 0.6229 [2021-03-26 18:05:37 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 500/1251] eta: 0:07:58 lr: 0.000807 loss: 3.6129 (3.4972) grad_norm: 1.2461 (inf) time: 0.6256 [2021-03-26 18:05:43 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 510/1251] eta: 0:07:52 lr: 0.000807 loss: 3.7793 (3.4998) grad_norm: 1.1312 (inf) time: 0.6349 [2021-03-26 18:05:49 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 520/1251] eta: 0:07:45 lr: 0.000807 loss: 3.7030 (3.4985) grad_norm: 1.1365 (inf) time: 0.6347 [2021-03-26 18:05:56 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 530/1251] eta: 0:07:39 lr: 0.000807 loss: 3.6437 (3.5007) grad_norm: 1.1474 (inf) time: 0.6296 [2021-03-26 18:06:02 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 540/1251] eta: 0:07:32 lr: 0.000807 loss: 3.6983 (3.5036) grad_norm: 1.1822 (inf) time: 0.6268 [2021-03-26 18:06:09 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 550/1251] eta: 0:07:26 lr: 0.000807 loss: 3.4083 (3.4985) grad_norm: 1.2206 (inf) time: 0.6439 [2021-03-26 18:06:15 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 560/1251] eta: 0:07:20 lr: 0.000807 loss: 3.5146 (3.5018) grad_norm: 1.1541 (inf) time: 0.6494 [2021-03-26 18:06:21 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 570/1251] eta: 0:07:13 lr: 0.000807 loss: 3.7695 (3.5030) grad_norm: 1.1615 (inf) time: 0.6368 [2021-03-26 18:06:28 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 580/1251] eta: 0:07:07 lr: 0.000806 loss: 3.6350 (3.5061) grad_norm: 1.2095 (inf) time: 0.6291 [2021-03-26 18:06:34 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 590/1251] eta: 0:07:01 lr: 0.000806 loss: 3.6350 (3.5072) grad_norm: 1.1403 (inf) time: 0.6366 [2021-03-26 18:06:40 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 600/1251] eta: 0:06:54 lr: 0.000806 loss: 3.4346 (3.5081) grad_norm: 1.0767 (inf) time: 0.6354 [2021-03-26 18:06:47 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 610/1251] eta: 0:06:48 lr: 0.000806 loss: 3.4346 (3.5080) grad_norm: 1.0767 (inf) time: 0.6300 [2021-03-26 18:06:53 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 620/1251] eta: 0:06:41 lr: 0.000806 loss: 3.6406 (3.5088) grad_norm: 1.1439 (inf) time: 0.6324 [2021-03-26 18:06:59 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 630/1251] eta: 0:06:35 lr: 0.000806 loss: 3.7361 (3.5096) grad_norm: 1.1528 (inf) time: 0.6255 [2021-03-26 18:07:05 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 640/1251] eta: 0:06:28 lr: 0.000806 loss: 3.7361 (3.5118) grad_norm: 1.1269 (inf) time: 0.6276 [2021-03-26 18:07:12 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 650/1251] eta: 0:06:22 lr: 0.000806 loss: 3.8964 (3.5173) grad_norm: 1.1146 (inf) time: 0.6323 [2021-03-26 18:07:18 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 660/1251] eta: 0:06:16 lr: 0.000806 loss: 3.7634 (3.5159) grad_norm: 1.1287 (inf) time: 0.6335 [2021-03-26 18:07:24 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 670/1251] eta: 0:06:09 lr: 0.000806 loss: 3.3694 (3.5146) grad_norm: 1.0857 (inf) time: 0.6300 [2021-03-26 18:07:31 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 680/1251] eta: 0:06:03 lr: 0.000806 loss: 3.5665 (3.5144) grad_norm: 1.0598 (inf) time: 0.6260 [2021-03-26 18:07:37 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 690/1251] eta: 0:05:56 lr: 0.000806 loss: 3.4668 (3.5112) grad_norm: 1.2032 (inf) time: 0.6275 [2021-03-26 18:07:43 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 700/1251] eta: 0:05:50 lr: 0.000806 loss: 3.5258 (3.5138) grad_norm: 1.2380 (inf) time: 0.6332 [2021-03-26 18:07:50 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 710/1251] eta: 0:05:44 lr: 0.000806 loss: 3.7955 (3.5155) grad_norm: 1.1806 (inf) time: 0.6370 [2021-03-26 18:07:56 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 720/1251] eta: 0:05:37 lr: 0.000806 loss: 3.8251 (3.5179) grad_norm: 1.1572 (inf) time: 0.6317 [2021-03-26 18:08:02 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 730/1251] eta: 0:05:31 lr: 0.000806 loss: 3.7176 (3.5188) grad_norm: 1.1382 (inf) time: 0.6305 [2021-03-26 18:08:09 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 740/1251] eta: 0:05:24 lr: 0.000806 loss: 3.4273 (3.5160) grad_norm: 1.0907 (inf) time: 0.6366 [2021-03-26 18:08:15 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 750/1251] eta: 0:05:18 lr: 0.000806 loss: 3.3663 (3.5141) grad_norm: 1.0907 (inf) time: 0.6344 [2021-03-26 18:08:21 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 760/1251] eta: 0:05:12 lr: 0.000806 loss: 3.6711 (3.5155) grad_norm: 1.0918 (inf) time: 0.6304 [2021-03-26 18:08:28 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 770/1251] eta: 0:05:05 lr: 0.000806 loss: 3.6923 (3.5155) grad_norm: 1.1233 (inf) time: 0.6308 [2021-03-26 18:08:34 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 780/1251] eta: 0:04:59 lr: 0.000806 loss: 3.7653 (3.5179) grad_norm: 1.1427 (inf) time: 0.6238 [2021-03-26 18:08:40 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 790/1251] eta: 0:04:52 lr: 0.000806 loss: 3.3731 (3.5129) grad_norm: 1.1223 (inf) time: 0.6226 [2021-03-26 18:08:46 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 800/1251] eta: 0:04:46 lr: 0.000806 loss: 3.2929 (3.5139) grad_norm: 1.1399 (inf) time: 0.6284 [2021-03-26 18:08:53 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 810/1251] eta: 0:04:40 lr: 0.000806 loss: 3.3534 (3.5094) grad_norm: 1.2205 (inf) time: 0.6397 [2021-03-26 18:08:59 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 820/1251] eta: 0:04:33 lr: 0.000806 loss: 3.2874 (3.5073) grad_norm: 1.1126 (inf) time: 0.6372 [2021-03-26 18:09:05 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 830/1251] eta: 0:04:27 lr: 0.000806 loss: 3.4916 (3.5068) grad_norm: 1.0884 (inf) time: 0.6239 [2021-03-26 18:09:12 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 840/1251] eta: 0:04:20 lr: 0.000806 loss: 3.5802 (3.5076) grad_norm: 1.0772 (inf) time: 0.6237 [2021-03-26 18:09:18 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 850/1251] eta: 0:04:14 lr: 0.000806 loss: 3.5072 (3.5056) grad_norm: 1.1049 (inf) time: 0.6291 [2021-03-26 18:09:24 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 860/1251] eta: 0:04:08 lr: 0.000806 loss: 3.4661 (3.5054) grad_norm: 1.2110 (inf) time: 0.6274 [2021-03-26 18:09:30 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 870/1251] eta: 0:04:01 lr: 0.000806 loss: 3.6733 (3.5076) grad_norm: 1.1747 (inf) time: 0.6243 [2021-03-26 18:09:37 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 880/1251] eta: 0:03:55 lr: 0.000805 loss: 3.7121 (3.5068) grad_norm: 1.1351 (inf) time: 0.6304 [2021-03-26 18:09:43 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 890/1251] eta: 0:03:49 lr: 0.000805 loss: 3.4755 (3.5049) grad_norm: 1.1793 (inf) time: 0.6353 [2021-03-26 18:09:49 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 900/1251] eta: 0:03:42 lr: 0.000805 loss: 3.6454 (3.5076) grad_norm: 1.2177 (inf) time: 0.6317 [2021-03-26 18:09:56 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 910/1251] eta: 0:03:36 lr: 0.000805 loss: 3.7558 (3.5089) grad_norm: 1.2054 (inf) time: 0.6264 [2021-03-26 18:10:02 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 920/1251] eta: 0:03:30 lr: 0.000805 loss: 3.5575 (3.5065) grad_norm: 1.1995 (inf) time: 0.6271 [2021-03-26 18:10:08 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 930/1251] eta: 0:03:23 lr: 0.000805 loss: 3.3065 (3.5039) grad_norm: 1.1880 (inf) time: 0.6269 [2021-03-26 18:10:15 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 940/1251] eta: 0:03:17 lr: 0.000805 loss: 3.6141 (3.5070) grad_norm: 1.1452 (inf) time: 0.6295 [2021-03-26 18:10:21 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 950/1251] eta: 0:03:10 lr: 0.000805 loss: 3.8453 (3.5099) grad_norm: 1.1160 (inf) time: 0.6275 [2021-03-26 18:10:27 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 960/1251] eta: 0:03:04 lr: 0.000805 loss: 3.8904 (3.5121) grad_norm: 1.0819 (inf) time: 0.6215 [2021-03-26 18:10:33 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 970/1251] eta: 0:02:58 lr: 0.000805 loss: 3.7062 (3.5106) grad_norm: 1.0748 (inf) time: 0.6255 [2021-03-26 18:10:40 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 980/1251] eta: 0:02:51 lr: 0.000805 loss: 3.6456 (3.5124) grad_norm: 1.1150 (inf) time: 0.6323 [2021-03-26 18:10:46 swin_base_patch4_window7_224] INFO: Epoch: [87] [ 990/1251] eta: 0:02:45 lr: 0.000805 loss: 3.6906 (3.5118) grad_norm: 1.1252 (inf) time: 0.6359 [2021-03-26 18:10:52 swin_base_patch4_window7_224] INFO: Epoch: [87] [1000/1251] eta: 0:02:39 lr: 0.000805 loss: 3.4718 (3.5107) grad_norm: 1.1034 (inf) time: 0.6320 [2021-03-26 18:10:59 swin_base_patch4_window7_224] INFO: Epoch: [87] [1010/1251] eta: 0:02:32 lr: 0.000805 loss: 3.7017 (3.5140) grad_norm: 1.1882 (inf) time: 0.6283 [2021-03-26 18:11:05 swin_base_patch4_window7_224] INFO: Epoch: [87] [1020/1251] eta: 0:02:26 lr: 0.000805 loss: 3.7548 (3.5155) grad_norm: 1.1992 (inf) time: 0.6315 [2021-03-26 18:11:11 swin_base_patch4_window7_224] INFO: Epoch: [87] [1030/1251] eta: 0:02:20 lr: 0.000805 loss: 3.4239 (3.5154) grad_norm: 1.1873 (inf) time: 0.6320 [2021-03-26 18:11:17 swin_base_patch4_window7_224] INFO: Epoch: [87] [1040/1251] eta: 0:02:13 lr: 0.000805 loss: 3.6055 (3.5164) grad_norm: 1.1122 (inf) time: 0.6306 [2021-03-26 18:11:24 swin_base_patch4_window7_224] INFO: Epoch: [87] [1050/1251] eta: 0:02:07 lr: 0.000805 loss: 3.6055 (3.5178) grad_norm: 1.1061 (inf) time: 0.6283 [2021-03-26 18:11:30 swin_base_patch4_window7_224] INFO: Epoch: [87] [1060/1251] eta: 0:02:01 lr: 0.000805 loss: 3.5976 (3.5183) grad_norm: 1.1156 (inf) time: 0.6233 [2021-03-26 18:11:36 swin_base_patch4_window7_224] INFO: Epoch: [87] [1070/1251] eta: 0:01:54 lr: 0.000805 loss: 3.5912 (3.5177) grad_norm: 1.1544 (inf) time: 0.6251 [2021-03-26 18:11:43 swin_base_patch4_window7_224] INFO: Epoch: [87] [1080/1251] eta: 0:01:48 lr: 0.000805 loss: 3.5145 (3.5183) grad_norm: 1.1395 (inf) time: 0.6398 [2021-03-26 18:11:49 swin_base_patch4_window7_224] INFO: Epoch: [87] [1090/1251] eta: 0:01:42 lr: 0.000805 loss: 3.6154 (3.5183) grad_norm: 1.0937 (inf) time: 0.6358 [2021-03-26 18:11:55 swin_base_patch4_window7_224] INFO: Epoch: [87] [1100/1251] eta: 0:01:35 lr: 0.000805 loss: 3.6329 (3.5203) grad_norm: 1.0996 (inf) time: 0.6274 [2021-03-26 18:12:02 swin_base_patch4_window7_224] INFO: Epoch: [87] [1110/1251] eta: 0:01:29 lr: 0.000805 loss: 3.7292 (3.5201) grad_norm: 1.1692 (inf) time: 0.6285 [2021-03-26 18:12:08 swin_base_patch4_window7_224] INFO: Epoch: [87] [1120/1251] eta: 0:01:22 lr: 0.000805 loss: 3.6143 (3.5220) grad_norm: 1.1652 (inf) time: 0.6248 [2021-03-26 18:12:14 swin_base_patch4_window7_224] INFO: Epoch: [87] [1130/1251] eta: 0:01:16 lr: 0.000805 loss: 3.8050 (3.5227) grad_norm: 1.1809 (inf) time: 0.6325 [2021-03-26 18:12:20 swin_base_patch4_window7_224] INFO: Epoch: [87] [1140/1251] eta: 0:01:10 lr: 0.000805 loss: 3.7459 (3.5228) grad_norm: 1.2593 (inf) time: 0.6309 [2021-03-26 18:12:27 swin_base_patch4_window7_224] INFO: Epoch: [87] [1150/1251] eta: 0:01:03 lr: 0.000805 loss: 3.6966 (3.5239) grad_norm: 1.2323 (inf) time: 0.6227 [2021-03-26 18:12:33 swin_base_patch4_window7_224] INFO: Epoch: [87] [1160/1251] eta: 0:00:57 lr: 0.000805 loss: 3.5704 (3.5234) grad_norm: 1.1519 (inf) time: 0.6237 [2021-03-26 18:12:39 swin_base_patch4_window7_224] INFO: Epoch: [87] [1170/1251] eta: 0:00:51 lr: 0.000805 loss: 3.6338 (3.5263) grad_norm: 1.1966 (inf) time: 0.6302 [2021-03-26 18:12:46 swin_base_patch4_window7_224] INFO: Epoch: [87] [1180/1251] eta: 0:00:44 lr: 0.000805 loss: 3.6945 (3.5242) grad_norm: 1.2046 (inf) time: 0.6333 [2021-03-26 18:12:52 swin_base_patch4_window7_224] INFO: Epoch: [87] [1190/1251] eta: 0:00:38 lr: 0.000804 loss: 3.5126 (3.5239) grad_norm: 1.2481 (inf) time: 0.6344 [2021-03-26 18:12:58 swin_base_patch4_window7_224] INFO: Epoch: [87] [1200/1251] eta: 0:00:32 lr: 0.000804 loss: 3.5237 (3.5244) grad_norm: 1.2089 (inf) time: 0.6326 [2021-03-26 18:13:05 swin_base_patch4_window7_224] INFO: Epoch: [87] [1210/1251] eta: 0:00:25 lr: 0.000804 loss: 3.4345 (3.5241) grad_norm: 1.2520 (inf) time: 0.6328 [2021-03-26 18:13:11 swin_base_patch4_window7_224] INFO: Epoch: [87] [1220/1251] eta: 0:00:19 lr: 0.000804 loss: 3.4345 (3.5252) grad_norm: 1.2684 (inf) time: 0.6350 [2021-03-26 18:13:17 swin_base_patch4_window7_224] INFO: Epoch: [87] [1230/1251] eta: 0:00:13 lr: 0.000804 loss: 3.5781 (3.5246) grad_norm: 1.2495 (inf) time: 0.6397 [2021-03-26 18:13:24 swin_base_patch4_window7_224] INFO: Epoch: [87] [1240/1251] eta: 0:00:06 lr: 0.000804 loss: 3.4682 (3.5245) grad_norm: 1.1613 (inf) time: 0.6318 [2021-03-26 18:13:30 swin_base_patch4_window7_224] INFO: Epoch: [87] [1250/1251] eta: 0:00:00 lr: 0.000804 loss: 3.7438 (3.5252) grad_norm: 1.1418 (inf) time: 0.6132 [2021-03-26 18:13:36 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:38 loss: 1.0716 (1.0716) acc1: 79.6875 (79.6875) acc5: 92.1875 (92.1875) [2021-03-26 18:13:38 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.0716 (1.0508) acc1: 75.0000 (76.7045) acc5: 93.7500 (93.7500) [2021-03-26 18:13:41 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.1690 (1.1333) acc1: 70.3125 (73.4375) acc5: 92.1875 (92.8571) [2021-03-26 18:13:43 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0507 (1.0782) acc1: 75.0000 (75.2520) acc5: 92.1875 (92.9940) [2021-03-26 18:13:45 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0262 (1.0654) acc1: 78.1250 (75.9909) acc5: 93.7500 (93.2165) [2021-03-26 18:13:46 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9827 (1.0719) acc1: 76.5625 (75.9040) acc5: 93.7500 (93.2160) [2021-03-26 18:13:50 swin_base_patch4_window7_224] INFO: * Acc@1 76.234 Acc@5 93.496 loss 1.045 [2021-03-26 18:13:50 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.2% [2021-03-26 18:13:50 swin_base_patch4_window7_224] INFO: Max accuracy: 76.23% [2021-03-26 18:13:54 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 0/1251] eta: 1:29:20 lr: 0.000804 loss: 3.7292 (3.7292) grad_norm: 1.1108 (1.1108) time: 4.2847 [2021-03-26 18:14:00 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 10/1251] eta: 0:20:06 lr: 0.000804 loss: 2.9916 (3.1834) grad_norm: 1.1251 (1.3191) time: 0.9721 [2021-03-26 18:14:07 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 20/1251] eta: 0:16:38 lr: 0.000804 loss: 3.1678 (3.3070) grad_norm: 1.1872 (1.2681) time: 0.6372 [2021-03-26 18:14:13 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 30/1251] eta: 0:15:21 lr: 0.000804 loss: 3.2512 (3.3164) grad_norm: 1.1951 (1.2676) time: 0.6351 [2021-03-26 18:14:19 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 40/1251] eta: 0:14:37 lr: 0.000804 loss: 3.7047 (3.4500) grad_norm: 1.2001 (1.2548) time: 0.6337 [2021-03-26 18:14:26 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 50/1251] eta: 0:14:09 lr: 0.000804 loss: 3.8448 (3.5132) grad_norm: 1.1254 (1.2345) time: 0.6338 [2021-03-26 18:14:32 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 60/1251] eta: 0:13:48 lr: 0.000804 loss: 3.7626 (3.5175) grad_norm: 1.1296 (1.2386) time: 0.6365 [2021-03-26 18:14:38 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 70/1251] eta: 0:13:31 lr: 0.000804 loss: 3.4484 (3.4795) grad_norm: 1.1672 (1.2334) time: 0.6366 [2021-03-26 18:14:45 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 80/1251] eta: 0:13:17 lr: 0.000804 loss: 3.1353 (3.4526) grad_norm: 1.2237 (1.2299) time: 0.6366 [2021-03-26 18:14:51 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 90/1251] eta: 0:13:03 lr: 0.000804 loss: 3.5365 (3.4919) grad_norm: 1.1123 (1.2205) time: 0.6317 [2021-03-26 18:14:57 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 100/1251] eta: 0:12:51 lr: 0.000804 loss: 3.7133 (3.4934) grad_norm: 1.0977 (1.2117) time: 0.6257 [2021-03-26 18:15:04 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 110/1251] eta: 0:12:41 lr: 0.000804 loss: 3.6347 (3.5048) grad_norm: 1.1451 (1.2094) time: 0.6301 [2021-03-26 18:15:10 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 120/1251] eta: 0:12:30 lr: 0.000804 loss: 3.6516 (3.5136) grad_norm: 1.1970 (1.2100) time: 0.6285 [2021-03-26 18:15:16 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 130/1251] eta: 0:12:21 lr: 0.000804 loss: 3.5609 (3.4960) grad_norm: 1.2085 (1.2192) time: 0.6325 [2021-03-26 18:15:23 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 140/1251] eta: 0:12:13 lr: 0.000804 loss: 3.5968 (3.5046) grad_norm: 1.2978 (1.2275) time: 0.6447 [2021-03-26 18:15:29 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 150/1251] eta: 0:12:04 lr: 0.000804 loss: 3.7658 (3.5180) grad_norm: 1.2719 (1.2284) time: 0.6352 [2021-03-26 18:15:35 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 160/1251] eta: 0:11:57 lr: 0.000804 loss: 3.6944 (3.5151) grad_norm: 1.1639 (1.2269) time: 0.6357 [2021-03-26 18:15:42 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 170/1251] eta: 0:11:48 lr: 0.000804 loss: 3.1034 (3.4898) grad_norm: 1.1254 (1.2205) time: 0.6369 [2021-03-26 18:15:48 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 180/1251] eta: 0:11:40 lr: 0.000804 loss: 3.3965 (3.4934) grad_norm: 1.1541 (1.2176) time: 0.6288 [2021-03-26 18:15:54 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 190/1251] eta: 0:11:32 lr: 0.000804 loss: 3.5943 (3.4996) grad_norm: 1.1827 (1.2178) time: 0.6293 [2021-03-26 18:16:01 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 200/1251] eta: 0:11:24 lr: 0.000804 loss: 3.6565 (3.5064) grad_norm: 1.2100 (1.2223) time: 0.6283 [2021-03-26 18:16:07 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 210/1251] eta: 0:11:17 lr: 0.000804 loss: 3.6565 (3.5088) grad_norm: 1.1517 (1.2227) time: 0.6274 [2021-03-26 18:16:13 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 220/1251] eta: 0:11:09 lr: 0.000804 loss: 3.6444 (3.5096) grad_norm: 1.2229 (1.2241) time: 0.6290 [2021-03-26 18:16:20 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 230/1251] eta: 0:11:02 lr: 0.000804 loss: 3.5754 (3.5106) grad_norm: 1.2411 (1.2261) time: 0.6325 [2021-03-26 18:16:26 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 240/1251] eta: 0:10:55 lr: 0.000803 loss: 3.5110 (3.5004) grad_norm: 1.2665 (1.2298) time: 0.6334 [2021-03-26 18:16:32 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 250/1251] eta: 0:10:48 lr: 0.000803 loss: 3.5415 (3.5079) grad_norm: 1.3541 (1.2374) time: 0.6300 [2021-03-26 18:16:38 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 260/1251] eta: 0:10:40 lr: 0.000803 loss: 3.6280 (3.5119) grad_norm: 1.2630 (1.2354) time: 0.6238 [2021-03-26 18:16:45 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 270/1251] eta: 0:10:33 lr: 0.000803 loss: 3.6701 (3.5169) grad_norm: 1.1830 (1.2352) time: 0.6241 [2021-03-26 18:16:51 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 280/1251] eta: 0:10:26 lr: 0.000803 loss: 3.6309 (3.5222) grad_norm: 1.1728 (1.2348) time: 0.6266 [2021-03-26 18:16:57 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 290/1251] eta: 0:10:19 lr: 0.000803 loss: 3.5215 (3.5146) grad_norm: 1.1697 (1.2328) time: 0.6294 [2021-03-26 18:17:03 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 300/1251] eta: 0:10:12 lr: 0.000803 loss: 3.3689 (3.5118) grad_norm: 1.1472 (1.2302) time: 0.6318 [2021-03-26 18:17:10 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 310/1251] eta: 0:10:05 lr: 0.000803 loss: 3.3689 (3.5065) grad_norm: 1.0862 (1.2277) time: 0.6307 [2021-03-26 18:17:16 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 320/1251] eta: 0:09:58 lr: 0.000803 loss: 3.3015 (3.4990) grad_norm: 1.1475 (1.2270) time: 0.6280 [2021-03-26 18:17:22 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 330/1251] eta: 0:09:52 lr: 0.000803 loss: 3.3972 (3.5013) grad_norm: 1.1888 (1.2273) time: 0.6302 [2021-03-26 18:17:29 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 340/1251] eta: 0:09:45 lr: 0.000803 loss: 3.6890 (3.4987) grad_norm: 1.1187 (1.2244) time: 0.6337 [2021-03-26 18:17:35 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 350/1251] eta: 0:09:38 lr: 0.000803 loss: 3.4940 (3.4974) grad_norm: 1.0981 (1.2225) time: 0.6267 [2021-03-26 18:17:41 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 360/1251] eta: 0:09:31 lr: 0.000803 loss: 3.5938 (3.4995) grad_norm: 1.0981 (1.2211) time: 0.6276 [2021-03-26 18:17:47 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 370/1251] eta: 0:09:24 lr: 0.000803 loss: 3.6371 (3.5049) grad_norm: 1.0931 (1.2186) time: 0.6264 [2021-03-26 18:17:54 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 380/1251] eta: 0:09:18 lr: 0.000803 loss: 3.7521 (3.5094) grad_norm: 1.1039 (1.2158) time: 0.6224 [2021-03-26 18:18:00 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 390/1251] eta: 0:09:11 lr: 0.000803 loss: 3.7521 (3.5031) grad_norm: 1.1001 (1.2134) time: 0.6247 [2021-03-26 18:18:06 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 400/1251] eta: 0:09:04 lr: 0.000803 loss: 3.2212 (3.4983) grad_norm: 1.1385 (1.2121) time: 0.6259 [2021-03-26 18:18:13 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 410/1251] eta: 0:08:57 lr: 0.000803 loss: 3.3967 (3.5017) grad_norm: 1.1489 (1.2115) time: 0.6270 [2021-03-26 18:18:19 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 420/1251] eta: 0:08:51 lr: 0.000803 loss: 3.6081 (3.5034) grad_norm: 1.1741 (1.2098) time: 0.6248 [2021-03-26 18:18:25 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 430/1251] eta: 0:08:44 lr: 0.000803 loss: 3.6081 (3.5072) grad_norm: 1.1341 (1.2074) time: 0.6288 [2021-03-26 18:18:31 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 440/1251] eta: 0:08:38 lr: 0.000803 loss: 3.6038 (3.5092) grad_norm: 1.1143 (1.2067) time: 0.6311 [2021-03-26 18:18:38 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 450/1251] eta: 0:08:31 lr: 0.000803 loss: 3.8218 (3.5157) grad_norm: 1.1184 (1.2094) time: 0.6375 [2021-03-26 18:18:44 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 460/1251] eta: 0:08:25 lr: 0.000803 loss: 3.7358 (3.5099) grad_norm: 1.1184 (1.2085) time: 0.6381 [2021-03-26 18:18:50 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 470/1251] eta: 0:08:18 lr: 0.000803 loss: 3.3197 (3.5128) grad_norm: 1.1205 (1.2077) time: 0.6273 [2021-03-26 18:18:57 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 480/1251] eta: 0:08:12 lr: 0.000803 loss: 3.4367 (3.5145) grad_norm: 1.1205 (1.2067) time: 0.6264 [2021-03-26 18:19:03 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 490/1251] eta: 0:08:05 lr: 0.000803 loss: 3.6416 (3.5168) grad_norm: 1.1234 (1.2049) time: 0.6283 [2021-03-26 18:19:09 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 500/1251] eta: 0:07:59 lr: 0.000803 loss: 3.6331 (3.5180) grad_norm: 1.1353 (1.2044) time: 0.6324 [2021-03-26 18:19:16 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 510/1251] eta: 0:07:52 lr: 0.000803 loss: 3.4835 (3.5152) grad_norm: 1.0891 (1.2024) time: 0.6291 [2021-03-26 18:19:22 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 520/1251] eta: 0:07:46 lr: 0.000803 loss: 3.4771 (3.5143) grad_norm: 1.0982 (1.2026) time: 0.6260 [2021-03-26 18:19:28 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 530/1251] eta: 0:07:39 lr: 0.000803 loss: 3.4674 (3.5147) grad_norm: 1.0982 (1.2000) time: 0.6264 [2021-03-26 18:19:34 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 540/1251] eta: 0:07:33 lr: 0.000802 loss: 3.4560 (3.5156) grad_norm: 1.0872 (1.1988) time: 0.6273 [2021-03-26 18:19:41 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 550/1251] eta: 0:07:27 lr: 0.000802 loss: 3.6254 (3.5162) grad_norm: 1.1074 (1.1992) time: 0.6482 [2021-03-26 18:19:47 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 560/1251] eta: 0:07:20 lr: 0.000802 loss: 3.6254 (3.5157) grad_norm: 1.1996 (1.2001) time: 0.6480 [2021-03-26 18:19:54 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 570/1251] eta: 0:07:14 lr: 0.000802 loss: 3.4029 (3.5131) grad_norm: 1.1624 (1.1996) time: 0.6274 [2021-03-26 18:20:00 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 580/1251] eta: 0:07:07 lr: 0.000802 loss: 3.7432 (3.5180) grad_norm: 1.1547 (1.1998) time: 0.6330 [2021-03-26 18:20:06 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 590/1251] eta: 0:07:01 lr: 0.000802 loss: 3.8330 (3.5237) grad_norm: 1.1620 (1.1999) time: 0.6430 [2021-03-26 18:20:13 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 600/1251] eta: 0:06:55 lr: 0.000802 loss: 3.8157 (3.5232) grad_norm: 1.1561 (1.2001) time: 0.6410 [2021-03-26 18:20:19 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 610/1251] eta: 0:06:48 lr: 0.000802 loss: 3.6098 (3.5217) grad_norm: 1.1124 (1.1984) time: 0.6309 [2021-03-26 18:20:25 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 620/1251] eta: 0:06:42 lr: 0.000802 loss: 3.5001 (3.5191) grad_norm: 1.1468 (1.1987) time: 0.6248 [2021-03-26 18:20:32 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 630/1251] eta: 0:06:35 lr: 0.000802 loss: 3.4415 (3.5163) grad_norm: 1.1896 (1.1987) time: 0.6237 [2021-03-26 18:20:38 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 640/1251] eta: 0:06:29 lr: 0.000802 loss: 3.2960 (3.5135) grad_norm: 1.1836 (1.1989) time: 0.6260 [2021-03-26 18:20:44 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 650/1251] eta: 0:06:22 lr: 0.000802 loss: 3.5693 (3.5120) grad_norm: 1.1247 (1.1973) time: 0.6298 [2021-03-26 18:20:50 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 660/1251] eta: 0:06:16 lr: 0.000802 loss: 3.4264 (3.5086) grad_norm: 1.1395 (1.1965) time: 0.6247 [2021-03-26 18:20:57 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 670/1251] eta: 0:06:09 lr: 0.000802 loss: 3.5973 (3.5109) grad_norm: 1.1550 (1.1962) time: 0.6296 [2021-03-26 18:21:03 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 680/1251] eta: 0:06:03 lr: 0.000802 loss: 3.6347 (3.5119) grad_norm: 1.1484 (1.1948) time: 0.6293 [2021-03-26 18:21:09 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 690/1251] eta: 0:05:56 lr: 0.000802 loss: 3.6325 (3.5127) grad_norm: 1.1257 (1.1961) time: 0.6257 [2021-03-26 18:21:16 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 700/1251] eta: 0:05:50 lr: 0.000802 loss: 3.6889 (3.5156) grad_norm: 1.1717 (1.1961) time: 0.6344 [2021-03-26 18:21:22 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 710/1251] eta: 0:05:44 lr: 0.000802 loss: 3.6059 (3.5150) grad_norm: 1.1943 (1.1959) time: 0.6340 [2021-03-26 18:21:28 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 720/1251] eta: 0:05:37 lr: 0.000802 loss: 3.3103 (3.5145) grad_norm: 1.1541 (1.1963) time: 0.6411 [2021-03-26 18:21:35 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 730/1251] eta: 0:05:31 lr: 0.000802 loss: 3.6794 (3.5166) grad_norm: 1.1266 (1.1947) time: 0.6411 [2021-03-26 18:21:41 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 740/1251] eta: 0:05:25 lr: 0.000802 loss: 3.5349 (3.5128) grad_norm: 1.0607 (1.1943) time: 0.6420 [2021-03-26 18:21:48 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 750/1251] eta: 0:05:18 lr: 0.000802 loss: 3.2096 (3.5109) grad_norm: 1.1490 (1.1943) time: 0.6464 [2021-03-26 18:21:54 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 760/1251] eta: 0:05:12 lr: 0.000802 loss: 3.3216 (3.5103) grad_norm: 1.0992 (1.1928) time: 0.6366 [2021-03-26 18:22:00 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 770/1251] eta: 0:05:06 lr: 0.000802 loss: 3.4868 (3.5115) grad_norm: 1.1073 (1.1925) time: 0.6329 [2021-03-26 18:22:07 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 780/1251] eta: 0:04:59 lr: 0.000802 loss: 3.7851 (3.5166) grad_norm: 1.1858 (1.1931) time: 0.6351 [2021-03-26 18:22:13 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 790/1251] eta: 0:04:53 lr: 0.000802 loss: 3.7851 (3.5158) grad_norm: 1.2436 (1.1943) time: 0.6365 [2021-03-26 18:22:19 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 800/1251] eta: 0:04:47 lr: 0.000802 loss: 3.4380 (3.5144) grad_norm: 1.2369 (1.1943) time: 0.6336 [2021-03-26 18:22:26 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 810/1251] eta: 0:04:40 lr: 0.000802 loss: 3.4603 (3.5168) grad_norm: 1.1549 (1.1934) time: 0.6289 [2021-03-26 18:22:32 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 820/1251] eta: 0:04:34 lr: 0.000802 loss: 3.7124 (3.5189) grad_norm: 1.1512 (1.1938) time: 0.6294 [2021-03-26 18:22:38 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 830/1251] eta: 0:04:27 lr: 0.000802 loss: 3.6475 (3.5198) grad_norm: 1.1554 (1.1935) time: 0.6296 [2021-03-26 18:22:45 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 840/1251] eta: 0:04:21 lr: 0.000801 loss: 3.6213 (3.5178) grad_norm: 1.1554 (1.1934) time: 0.6304 [2021-03-26 18:22:51 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 850/1251] eta: 0:04:15 lr: 0.000801 loss: 3.4511 (3.5168) grad_norm: 1.1050 (1.1922) time: 0.6298 [2021-03-26 18:22:57 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 860/1251] eta: 0:04:08 lr: 0.000801 loss: 3.5911 (3.5177) grad_norm: 1.1054 (1.1918) time: 0.6325 [2021-03-26 18:23:04 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 870/1251] eta: 0:04:02 lr: 0.000801 loss: 3.6444 (3.5183) grad_norm: 1.1728 (1.1924) time: 0.6340 [2021-03-26 18:23:10 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 880/1251] eta: 0:03:55 lr: 0.000801 loss: 3.7351 (3.5220) grad_norm: 1.1677 (1.1922) time: 0.6284 [2021-03-26 18:23:16 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 890/1251] eta: 0:03:49 lr: 0.000801 loss: 3.7351 (3.5219) grad_norm: 1.2026 (1.1940) time: 0.6316 [2021-03-26 18:23:22 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 900/1251] eta: 0:03:43 lr: 0.000801 loss: 3.7112 (3.5238) grad_norm: 1.2016 (1.1933) time: 0.6268 [2021-03-26 18:23:29 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 910/1251] eta: 0:03:36 lr: 0.000801 loss: 3.8436 (3.5272) grad_norm: 1.1244 (1.1939) time: 0.6253 [2021-03-26 18:23:35 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 920/1251] eta: 0:03:30 lr: 0.000801 loss: 3.7593 (3.5265) grad_norm: 1.1442 (1.1940) time: 0.6341 [2021-03-26 18:23:41 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 930/1251] eta: 0:03:24 lr: 0.000801 loss: 3.4204 (3.5277) grad_norm: 1.1377 (1.1936) time: 0.6336 [2021-03-26 18:23:48 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 940/1251] eta: 0:03:17 lr: 0.000801 loss: 3.5496 (3.5272) grad_norm: 1.1203 (1.1931) time: 0.6268 [2021-03-26 18:23:54 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 950/1251] eta: 0:03:11 lr: 0.000801 loss: 3.8372 (3.5292) grad_norm: 1.0975 (1.1922) time: 0.6297 [2021-03-26 18:24:00 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 960/1251] eta: 0:03:04 lr: 0.000801 loss: 3.8114 (3.5296) grad_norm: 1.1418 (1.1931) time: 0.6333 [2021-03-26 18:24:07 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 970/1251] eta: 0:02:58 lr: 0.000801 loss: 3.5906 (3.5313) grad_norm: 1.1740 (1.1928) time: 0.6310 [2021-03-26 18:24:13 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 980/1251] eta: 0:02:52 lr: 0.000801 loss: 3.7167 (3.5338) grad_norm: 1.0887 (1.1914) time: 0.6294 [2021-03-26 18:24:19 swin_base_patch4_window7_224] INFO: Epoch: [88] [ 990/1251] eta: 0:02:45 lr: 0.000801 loss: 3.8277 (3.5363) grad_norm: 1.0872 (1.1911) time: 0.6293 [2021-03-26 18:24:25 swin_base_patch4_window7_224] INFO: Epoch: [88] [1000/1251] eta: 0:02:39 lr: 0.000801 loss: 3.7726 (3.5366) grad_norm: 1.1403 (1.1912) time: 0.6284 [2021-03-26 18:24:32 swin_base_patch4_window7_224] INFO: Epoch: [88] [1010/1251] eta: 0:02:33 lr: 0.000801 loss: 3.7243 (3.5370) grad_norm: 1.1781 (1.1909) time: 0.6305 [2021-03-26 18:24:38 swin_base_patch4_window7_224] INFO: Epoch: [88] [1020/1251] eta: 0:02:26 lr: 0.000801 loss: 3.5980 (3.5363) grad_norm: 1.1489 (1.1905) time: 0.6352 [2021-03-26 18:24:44 swin_base_patch4_window7_224] INFO: Epoch: [88] [1030/1251] eta: 0:02:20 lr: 0.000801 loss: 3.6081 (3.5388) grad_norm: 1.1514 (1.1904) time: 0.6320 [2021-03-26 18:24:51 swin_base_patch4_window7_224] INFO: Epoch: [88] [1040/1251] eta: 0:02:14 lr: 0.000801 loss: 3.6081 (3.5388) grad_norm: 1.1545 (1.1912) time: 0.6418 [2021-03-26 18:24:57 swin_base_patch4_window7_224] INFO: Epoch: [88] [1050/1251] eta: 0:02:07 lr: 0.000801 loss: 3.5871 (3.5392) grad_norm: 1.2053 (1.1916) time: 0.6397 [2021-03-26 18:25:04 swin_base_patch4_window7_224] INFO: Epoch: [88] [1060/1251] eta: 0:02:01 lr: 0.000801 loss: 3.6723 (3.5417) grad_norm: 1.2221 (1.1930) time: 0.6278 [2021-03-26 18:25:10 swin_base_patch4_window7_224] INFO: Epoch: [88] [1070/1251] eta: 0:01:54 lr: 0.000801 loss: 3.6625 (3.5403) grad_norm: 1.1935 (1.1925) time: 0.6273 [2021-03-26 18:25:16 swin_base_patch4_window7_224] INFO: Epoch: [88] [1080/1251] eta: 0:01:48 lr: 0.000801 loss: 3.5026 (3.5415) grad_norm: 1.1499 (1.1929) time: 0.6292 [2021-03-26 18:25:22 swin_base_patch4_window7_224] INFO: Epoch: [88] [1090/1251] eta: 0:01:42 lr: 0.000801 loss: 3.6869 (3.5432) grad_norm: 1.1318 (1.1924) time: 0.6339 [2021-03-26 18:25:29 swin_base_patch4_window7_224] INFO: Epoch: [88] [1100/1251] eta: 0:01:35 lr: 0.000801 loss: 3.6122 (3.5427) grad_norm: 1.1318 (1.1925) time: 0.6361 [2021-03-26 18:25:35 swin_base_patch4_window7_224] INFO: Epoch: [88] [1110/1251] eta: 0:01:29 lr: 0.000801 loss: 3.5736 (3.5425) grad_norm: 1.1925 (1.1929) time: 0.6329 [2021-03-26 18:25:41 swin_base_patch4_window7_224] INFO: Epoch: [88] [1120/1251] eta: 0:01:23 lr: 0.000801 loss: 3.1268 (3.5396) grad_norm: 1.1600 (1.1927) time: 0.6290 [2021-03-26 18:25:48 swin_base_patch4_window7_224] INFO: Epoch: [88] [1130/1251] eta: 0:01:16 lr: 0.000801 loss: 3.5211 (3.5405) grad_norm: 1.1383 (1.1934) time: 0.6307 [2021-03-26 18:25:54 swin_base_patch4_window7_224] INFO: Epoch: [88] [1140/1251] eta: 0:01:10 lr: 0.000801 loss: 3.6315 (3.5413) grad_norm: 1.1383 (1.1932) time: 0.6285 [2021-03-26 18:26:00 swin_base_patch4_window7_224] INFO: Epoch: [88] [1150/1251] eta: 0:01:04 lr: 0.000800 loss: 3.7806 (3.5440) grad_norm: 1.1232 (1.1928) time: 0.6293 [2021-03-26 18:26:07 swin_base_patch4_window7_224] INFO: Epoch: [88] [1160/1251] eta: 0:00:57 lr: 0.000800 loss: 3.7806 (3.5446) grad_norm: 1.1752 (1.1927) time: 0.6258 [2021-03-26 18:26:13 swin_base_patch4_window7_224] INFO: Epoch: [88] [1170/1251] eta: 0:00:51 lr: 0.000800 loss: 3.5693 (3.5433) grad_norm: 1.1590 (1.1926) time: 0.6250 [2021-03-26 18:26:19 swin_base_patch4_window7_224] INFO: Epoch: [88] [1180/1251] eta: 0:00:45 lr: 0.000800 loss: 3.4037 (3.5418) grad_norm: 1.1229 (1.1921) time: 0.6288 [2021-03-26 18:26:26 swin_base_patch4_window7_224] INFO: Epoch: [88] [1190/1251] eta: 0:00:38 lr: 0.000800 loss: 3.3516 (3.5393) grad_norm: 1.1386 (1.1922) time: 0.6328 [2021-03-26 18:26:32 swin_base_patch4_window7_224] INFO: Epoch: [88] [1200/1251] eta: 0:00:32 lr: 0.000800 loss: 3.5205 (3.5396) grad_norm: 1.1528 (1.1920) time: 0.6322 [2021-03-26 18:26:38 swin_base_patch4_window7_224] INFO: Epoch: [88] [1210/1251] eta: 0:00:26 lr: 0.000800 loss: 3.1739 (3.5370) grad_norm: 1.1505 (1.1921) time: 0.6244 [2021-03-26 18:26:44 swin_base_patch4_window7_224] INFO: Epoch: [88] [1220/1251] eta: 0:00:19 lr: 0.000800 loss: 3.5326 (3.5378) grad_norm: 1.1394 (1.1916) time: 0.6231 [2021-03-26 18:26:51 swin_base_patch4_window7_224] INFO: Epoch: [88] [1230/1251] eta: 0:00:13 lr: 0.000800 loss: 3.5468 (3.5359) grad_norm: 1.0683 (1.1909) time: 0.6279 [2021-03-26 18:26:57 swin_base_patch4_window7_224] INFO: Epoch: [88] [1240/1251] eta: 0:00:06 lr: 0.000800 loss: 3.3771 (3.5353) grad_norm: 1.0953 (1.1910) time: 0.6325 [2021-03-26 18:27:03 swin_base_patch4_window7_224] INFO: Epoch: [88] [1250/1251] eta: 0:00:00 lr: 0.000800 loss: 3.5260 (3.5351) grad_norm: 1.1569 (1.1908) time: 0.6291 [2021-03-26 18:27:09 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:28 loss: 0.7217 (0.7217) acc1: 84.3750 (84.3750) acc5: 95.3125 (95.3125) [2021-03-26 18:27:12 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9992 (1.0658) acc1: 76.5625 (76.5625) acc5: 92.1875 (92.4716) [2021-03-26 18:27:15 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9891 (1.0429) acc1: 75.0000 (75.3720) acc5: 93.7500 (93.3036) [2021-03-26 18:27:18 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9680 (0.9998) acc1: 75.0000 (76.2601) acc5: 95.3125 (93.4980) [2021-03-26 18:27:20 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9495 (0.9968) acc1: 76.5625 (76.1052) acc5: 93.7500 (93.7119) [2021-03-26 18:27:21 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9909 (1.0042) acc1: 76.5625 (75.9360) acc5: 92.4528 (93.5360) [2021-03-26 18:27:24 swin_base_patch4_window7_224] INFO: * Acc@1 76.176 Acc@5 93.466 loss 0.989 [2021-03-26 18:27:24 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.2% [2021-03-26 18:27:24 swin_base_patch4_window7_224] INFO: Max accuracy: 76.23% [2021-03-26 18:27:28 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 0/1251] eta: 1:26:02 lr: 0.000800 loss: 3.8198 (3.8198) grad_norm: 1.1040 (1.1040) time: 4.1266 [2021-03-26 18:27:34 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 10/1251] eta: 0:19:53 lr: 0.000800 loss: 3.3053 (3.3013) grad_norm: 1.1040 (1.0964) time: 0.9616 [2021-03-26 18:27:41 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 20/1251] eta: 0:16:28 lr: 0.000800 loss: 3.3576 (3.4240) grad_norm: 1.1517 (1.1659) time: 0.6365 [2021-03-26 18:27:47 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 30/1251] eta: 0:15:09 lr: 0.000800 loss: 3.6257 (3.4569) grad_norm: 1.2073 (inf) time: 0.6260 [2021-03-26 18:27:53 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 40/1251] eta: 0:14:27 lr: 0.000800 loss: 3.6257 (3.4645) grad_norm: 1.2328 (inf) time: 0.6261 [2021-03-26 18:28:00 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 50/1251] eta: 0:13:59 lr: 0.000800 loss: 3.7104 (3.5014) grad_norm: 1.2328 (inf) time: 0.6282 [2021-03-26 18:28:06 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 60/1251] eta: 0:13:38 lr: 0.000800 loss: 3.4708 (3.4733) grad_norm: 1.1300 (inf) time: 0.6279 [2021-03-26 18:28:12 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 70/1251] eta: 0:13:23 lr: 0.000800 loss: 3.3955 (3.4599) grad_norm: 1.0671 (inf) time: 0.6330 [2021-03-26 18:28:18 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 80/1251] eta: 0:13:08 lr: 0.000800 loss: 3.3955 (3.4377) grad_norm: 1.1007 (inf) time: 0.6303 [2021-03-26 18:28:25 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 90/1251] eta: 0:12:55 lr: 0.000800 loss: 3.4858 (3.4431) grad_norm: 1.1917 (inf) time: 0.6222 [2021-03-26 18:28:31 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 100/1251] eta: 0:12:44 lr: 0.000800 loss: 3.2948 (3.4339) grad_norm: 1.1316 (inf) time: 0.6282 [2021-03-26 18:28:37 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 110/1251] eta: 0:12:35 lr: 0.000800 loss: 3.7339 (3.4518) grad_norm: 1.1460 (inf) time: 0.6378 [2021-03-26 18:28:44 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 120/1251] eta: 0:12:26 lr: 0.000800 loss: 3.7183 (3.4485) grad_norm: 1.1728 (inf) time: 0.6390 [2021-03-26 18:28:50 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 130/1251] eta: 0:12:18 lr: 0.000800 loss: 3.4411 (3.4648) grad_norm: 1.1316 (inf) time: 0.6375 [2021-03-26 18:28:56 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 140/1251] eta: 0:12:09 lr: 0.000800 loss: 3.5743 (3.4629) grad_norm: 1.1316 (inf) time: 0.6326 [2021-03-26 18:29:03 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 150/1251] eta: 0:12:00 lr: 0.000800 loss: 3.5849 (3.4786) grad_norm: 1.2094 (inf) time: 0.6246 [2021-03-26 18:29:09 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 160/1251] eta: 0:11:51 lr: 0.000800 loss: 3.7270 (3.4977) grad_norm: 1.2094 (inf) time: 0.6246 [2021-03-26 18:29:15 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 170/1251] eta: 0:11:42 lr: 0.000800 loss: 3.7701 (3.4915) grad_norm: 1.1905 (inf) time: 0.6216 [2021-03-26 18:29:21 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 180/1251] eta: 0:11:35 lr: 0.000800 loss: 3.6016 (3.4943) grad_norm: 1.1655 (inf) time: 0.6223 [2021-03-26 18:29:28 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 190/1251] eta: 0:11:27 lr: 0.000799 loss: 3.6433 (3.5050) grad_norm: 1.1969 (inf) time: 0.6268 [2021-03-26 18:29:34 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 200/1251] eta: 0:11:20 lr: 0.000799 loss: 3.6522 (3.5060) grad_norm: 1.1969 (inf) time: 0.6306 [2021-03-26 18:29:40 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 210/1251] eta: 0:11:13 lr: 0.000799 loss: 3.6748 (3.5162) grad_norm: 1.1279 (inf) time: 0.6357 [2021-03-26 18:29:47 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 220/1251] eta: 0:11:05 lr: 0.000799 loss: 3.7586 (3.5240) grad_norm: 1.1279 (inf) time: 0.6323 [2021-03-26 18:29:53 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 230/1251] eta: 0:10:58 lr: 0.000799 loss: 3.7586 (3.5255) grad_norm: 1.1708 (inf) time: 0.6273 [2021-03-26 18:29:59 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 240/1251] eta: 0:10:51 lr: 0.000799 loss: 3.7309 (3.5240) grad_norm: 1.1188 (inf) time: 0.6301 [2021-03-26 18:30:06 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 250/1251] eta: 0:10:44 lr: 0.000799 loss: 3.8058 (3.5282) grad_norm: 1.0931 (inf) time: 0.6296 [2021-03-26 18:30:12 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 260/1251] eta: 0:10:37 lr: 0.000799 loss: 3.7706 (3.5345) grad_norm: 1.1111 (inf) time: 0.6267 [2021-03-26 18:30:18 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 270/1251] eta: 0:10:30 lr: 0.000799 loss: 3.5989 (3.5256) grad_norm: 1.1125 (inf) time: 0.6298 [2021-03-26 18:30:24 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 280/1251] eta: 0:10:23 lr: 0.000799 loss: 3.4801 (3.5246) grad_norm: 1.2373 (inf) time: 0.6305 [2021-03-26 18:30:31 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 290/1251] eta: 0:10:16 lr: 0.000799 loss: 3.5260 (3.5297) grad_norm: 1.2984 (inf) time: 0.6258 [2021-03-26 18:30:37 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 300/1251] eta: 0:10:09 lr: 0.000799 loss: 3.9158 (3.5386) grad_norm: 1.1723 (inf) time: 0.6266 [2021-03-26 18:30:43 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 310/1251] eta: 0:10:03 lr: 0.000799 loss: 3.8340 (3.5423) grad_norm: 1.2039 (inf) time: 0.6304 [2021-03-26 18:30:50 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 320/1251] eta: 0:09:56 lr: 0.000799 loss: 3.7338 (3.5401) grad_norm: 1.1825 (inf) time: 0.6271 [2021-03-26 18:30:56 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 330/1251] eta: 0:09:49 lr: 0.000799 loss: 3.3835 (3.5391) grad_norm: 1.1825 (inf) time: 0.6327 [2021-03-26 18:31:02 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 340/1251] eta: 0:09:43 lr: 0.000799 loss: 3.3835 (3.5336) grad_norm: 1.1857 (inf) time: 0.6362 [2021-03-26 18:31:08 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 350/1251] eta: 0:09:36 lr: 0.000799 loss: 3.5921 (3.5390) grad_norm: 1.1966 (inf) time: 0.6287 [2021-03-26 18:31:15 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 360/1251] eta: 0:09:29 lr: 0.000799 loss: 3.7577 (3.5394) grad_norm: 1.2085 (inf) time: 0.6254 [2021-03-26 18:31:21 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 370/1251] eta: 0:09:23 lr: 0.000799 loss: 3.5105 (3.5334) grad_norm: 1.1605 (inf) time: 0.6315 [2021-03-26 18:31:27 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 380/1251] eta: 0:09:16 lr: 0.000799 loss: 3.4389 (3.5278) grad_norm: 1.1605 (inf) time: 0.6300 [2021-03-26 18:31:34 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 390/1251] eta: 0:09:09 lr: 0.000799 loss: 3.3667 (3.5218) grad_norm: 1.2173 (inf) time: 0.6277 [2021-03-26 18:31:40 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 400/1251] eta: 0:09:03 lr: 0.000799 loss: 3.4783 (3.5276) grad_norm: 1.1780 (inf) time: 0.6322 [2021-03-26 18:31:46 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 410/1251] eta: 0:08:56 lr: 0.000799 loss: 3.7498 (3.5262) grad_norm: 1.1338 (inf) time: 0.6286 [2021-03-26 18:31:53 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 420/1251] eta: 0:08:50 lr: 0.000799 loss: 3.6436 (3.5282) grad_norm: 1.1561 (inf) time: 0.6289 [2021-03-26 18:31:59 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 430/1251] eta: 0:08:43 lr: 0.000799 loss: 3.6049 (3.5245) grad_norm: 1.1612 (inf) time: 0.6322 [2021-03-26 18:32:05 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 440/1251] eta: 0:08:37 lr: 0.000799 loss: 3.4537 (3.5243) grad_norm: 1.1382 (inf) time: 0.6326 [2021-03-26 18:32:12 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 450/1251] eta: 0:08:30 lr: 0.000799 loss: 3.3606 (3.5245) grad_norm: 1.1382 (inf) time: 0.6301 [2021-03-26 18:32:18 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 460/1251] eta: 0:08:24 lr: 0.000799 loss: 3.6006 (3.5285) grad_norm: 1.1200 (inf) time: 0.6281 [2021-03-26 18:32:24 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 470/1251] eta: 0:08:17 lr: 0.000799 loss: 3.7510 (3.5333) grad_norm: 1.1641 (inf) time: 0.6281 [2021-03-26 18:32:30 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 480/1251] eta: 0:08:11 lr: 0.000799 loss: 3.7210 (3.5276) grad_norm: 1.1753 (inf) time: 0.6281 [2021-03-26 18:32:37 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 490/1251] eta: 0:08:04 lr: 0.000798 loss: 3.6396 (3.5309) grad_norm: 1.1414 (inf) time: 0.6287 [2021-03-26 18:32:43 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 500/1251] eta: 0:07:58 lr: 0.000798 loss: 3.6396 (3.5279) grad_norm: 1.1053 (inf) time: 0.6265 [2021-03-26 18:32:49 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 510/1251] eta: 0:07:51 lr: 0.000798 loss: 3.3445 (3.5241) grad_norm: 1.1525 (inf) time: 0.6272 [2021-03-26 18:32:56 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 520/1251] eta: 0:07:45 lr: 0.000798 loss: 3.3445 (3.5235) grad_norm: 1.1194 (inf) time: 0.6330 [2021-03-26 18:33:02 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 530/1251] eta: 0:07:38 lr: 0.000798 loss: 3.7200 (3.5263) grad_norm: 1.1395 (inf) time: 0.6336 [2021-03-26 18:33:08 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 540/1251] eta: 0:07:32 lr: 0.000798 loss: 3.8758 (3.5318) grad_norm: 1.2343 (inf) time: 0.6268 [2021-03-26 18:33:15 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 550/1251] eta: 0:07:25 lr: 0.000798 loss: 3.6203 (3.5249) grad_norm: 1.1263 (inf) time: 0.6322 [2021-03-26 18:33:21 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 560/1251] eta: 0:07:19 lr: 0.000798 loss: 3.2333 (3.5263) grad_norm: 1.1369 (inf) time: 0.6357 [2021-03-26 18:33:27 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 570/1251] eta: 0:07:13 lr: 0.000798 loss: 3.4529 (3.5245) grad_norm: 1.1807 (inf) time: 0.6330 [2021-03-26 18:33:33 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 580/1251] eta: 0:07:06 lr: 0.000798 loss: 3.4498 (3.5228) grad_norm: 1.1807 (inf) time: 0.6340 [2021-03-26 18:33:40 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 590/1251] eta: 0:07:00 lr: 0.000798 loss: 3.4978 (3.5232) grad_norm: 1.1547 (inf) time: 0.6357 [2021-03-26 18:33:46 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 600/1251] eta: 0:06:53 lr: 0.000798 loss: 3.5781 (3.5265) grad_norm: 1.1537 (inf) time: 0.6318 [2021-03-26 18:33:52 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 610/1251] eta: 0:06:47 lr: 0.000798 loss: 3.5681 (3.5253) grad_norm: 1.0927 (inf) time: 0.6267 [2021-03-26 18:33:59 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 620/1251] eta: 0:06:41 lr: 0.000798 loss: 3.3586 (3.5254) grad_norm: 1.1121 (inf) time: 0.6307 [2021-03-26 18:34:05 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 630/1251] eta: 0:06:34 lr: 0.000798 loss: 3.4200 (3.5218) grad_norm: 1.1342 (inf) time: 0.6279 [2021-03-26 18:34:11 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 640/1251] eta: 0:06:28 lr: 0.000798 loss: 3.2059 (3.5181) grad_norm: 1.0998 (inf) time: 0.6301 [2021-03-26 18:34:18 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 650/1251] eta: 0:06:21 lr: 0.000798 loss: 3.3079 (3.5190) grad_norm: 1.0734 (inf) time: 0.6286 [2021-03-26 18:34:24 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 660/1251] eta: 0:06:15 lr: 0.000798 loss: 3.5883 (3.5176) grad_norm: 1.1096 (inf) time: 0.6265 [2021-03-26 18:34:30 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 670/1251] eta: 0:06:08 lr: 0.000798 loss: 3.7059 (3.5195) grad_norm: 1.1302 (inf) time: 0.6289 [2021-03-26 18:34:36 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 680/1251] eta: 0:06:02 lr: 0.000798 loss: 3.7837 (3.5232) grad_norm: 1.1302 (inf) time: 0.6260 [2021-03-26 18:34:43 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 690/1251] eta: 0:05:56 lr: 0.000798 loss: 3.7761 (3.5256) grad_norm: 1.1792 (inf) time: 0.6299 [2021-03-26 18:34:49 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 700/1251] eta: 0:05:49 lr: 0.000798 loss: 3.8524 (3.5294) grad_norm: 1.2068 (inf) time: 0.6302 [2021-03-26 18:34:55 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 710/1251] eta: 0:05:43 lr: 0.000798 loss: 3.8442 (3.5332) grad_norm: 1.1772 (inf) time: 0.6284 [2021-03-26 18:35:02 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 720/1251] eta: 0:05:37 lr: 0.000798 loss: 3.7258 (3.5346) grad_norm: 1.1261 (inf) time: 0.6341 [2021-03-26 18:35:08 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 730/1251] eta: 0:05:30 lr: 0.000798 loss: 3.6241 (3.5366) grad_norm: 1.1204 (inf) time: 0.6389 [2021-03-26 18:35:15 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 740/1251] eta: 0:05:24 lr: 0.000798 loss: 3.6272 (3.5354) grad_norm: 1.1286 (inf) time: 0.6407 [2021-03-26 18:35:21 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 750/1251] eta: 0:05:18 lr: 0.000798 loss: 3.2746 (3.5294) grad_norm: 1.1444 (inf) time: 0.6455 [2021-03-26 18:35:27 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 760/1251] eta: 0:05:11 lr: 0.000798 loss: 3.5201 (3.5336) grad_norm: 1.1583 (inf) time: 0.6370 [2021-03-26 18:35:34 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 770/1251] eta: 0:05:05 lr: 0.000798 loss: 3.8020 (3.5370) grad_norm: 1.1348 (inf) time: 0.6266 [2021-03-26 18:35:40 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 780/1251] eta: 0:04:59 lr: 0.000798 loss: 3.7291 (3.5390) grad_norm: 1.1084 (inf) time: 0.6312 [2021-03-26 18:35:46 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 790/1251] eta: 0:04:52 lr: 0.000797 loss: 3.7098 (3.5390) grad_norm: 1.1531 (inf) time: 0.6286 [2021-03-26 18:35:52 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 800/1251] eta: 0:04:46 lr: 0.000797 loss: 3.4977 (3.5368) grad_norm: 1.1568 (inf) time: 0.6269 [2021-03-26 18:35:59 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 810/1251] eta: 0:04:39 lr: 0.000797 loss: 3.7222 (3.5396) grad_norm: 1.1918 (inf) time: 0.6323 [2021-03-26 18:36:05 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 820/1251] eta: 0:04:33 lr: 0.000797 loss: 3.7222 (3.5397) grad_norm: 1.2284 (inf) time: 0.6356 [2021-03-26 18:36:11 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 830/1251] eta: 0:04:27 lr: 0.000797 loss: 3.5888 (3.5397) grad_norm: 1.1858 (inf) time: 0.6313 [2021-03-26 18:36:18 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 840/1251] eta: 0:04:20 lr: 0.000797 loss: 3.5039 (3.5366) grad_norm: 1.1858 (inf) time: 0.6261 [2021-03-26 18:36:24 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 850/1251] eta: 0:04:14 lr: 0.000797 loss: 3.5886 (3.5402) grad_norm: 1.2107 (inf) time: 0.6298 [2021-03-26 18:36:30 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 860/1251] eta: 0:04:08 lr: 0.000797 loss: 3.7610 (3.5382) grad_norm: 1.1420 (inf) time: 0.6326 [2021-03-26 18:36:37 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 870/1251] eta: 0:04:01 lr: 0.000797 loss: 3.6053 (3.5405) grad_norm: 1.1844 (inf) time: 0.6322 [2021-03-26 18:36:43 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 880/1251] eta: 0:03:55 lr: 0.000797 loss: 3.5006 (3.5383) grad_norm: 1.1541 (inf) time: 0.6324 [2021-03-26 18:36:49 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 890/1251] eta: 0:03:48 lr: 0.000797 loss: 3.4561 (3.5389) grad_norm: 1.1541 (inf) time: 0.6274 [2021-03-26 18:36:56 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 900/1251] eta: 0:03:42 lr: 0.000797 loss: 3.6256 (3.5412) grad_norm: 1.1545 (inf) time: 0.6321 [2021-03-26 18:37:02 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 910/1251] eta: 0:03:36 lr: 0.000797 loss: 3.7200 (3.5424) grad_norm: 1.0959 (inf) time: 0.6340 [2021-03-26 18:37:08 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 920/1251] eta: 0:03:29 lr: 0.000797 loss: 3.7127 (3.5452) grad_norm: 1.0959 (inf) time: 0.6258 [2021-03-26 18:37:14 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 930/1251] eta: 0:03:23 lr: 0.000797 loss: 3.6880 (3.5453) grad_norm: 1.2147 (inf) time: 0.6283 [2021-03-26 18:37:21 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 940/1251] eta: 0:03:17 lr: 0.000797 loss: 3.6880 (3.5482) grad_norm: 1.1954 (inf) time: 0.6375 [2021-03-26 18:37:27 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 950/1251] eta: 0:03:10 lr: 0.000797 loss: 3.6739 (3.5483) grad_norm: 1.1922 (inf) time: 0.6365 [2021-03-26 18:37:34 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 960/1251] eta: 0:03:04 lr: 0.000797 loss: 3.6304 (3.5467) grad_norm: 1.1982 (inf) time: 0.6348 [2021-03-26 18:37:40 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 970/1251] eta: 0:02:58 lr: 0.000797 loss: 3.4735 (3.5458) grad_norm: 1.1514 (inf) time: 0.6333 [2021-03-26 18:37:46 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 980/1251] eta: 0:02:51 lr: 0.000797 loss: 3.5324 (3.5465) grad_norm: 1.1372 (inf) time: 0.6295 [2021-03-26 18:37:52 swin_base_patch4_window7_224] INFO: Epoch: [89] [ 990/1251] eta: 0:02:45 lr: 0.000797 loss: 3.6199 (3.5469) grad_norm: 1.1723 (inf) time: 0.6303 [2021-03-26 18:37:59 swin_base_patch4_window7_224] INFO: Epoch: [89] [1000/1251] eta: 0:02:39 lr: 0.000797 loss: 3.5843 (3.5433) grad_norm: 1.2017 (inf) time: 0.6349 [2021-03-26 18:38:05 swin_base_patch4_window7_224] INFO: Epoch: [89] [1010/1251] eta: 0:02:32 lr: 0.000797 loss: 3.5843 (3.5444) grad_norm: 1.1981 (inf) time: 0.6392 [2021-03-26 18:38:11 swin_base_patch4_window7_224] INFO: Epoch: [89] [1020/1251] eta: 0:02:26 lr: 0.000797 loss: 3.8727 (3.5459) grad_norm: 1.0781 (inf) time: 0.6287 [2021-03-26 18:38:18 swin_base_patch4_window7_224] INFO: Epoch: [89] [1030/1251] eta: 0:02:20 lr: 0.000797 loss: 3.6393 (3.5454) grad_norm: 1.0637 (inf) time: 0.6295 [2021-03-26 18:38:24 swin_base_patch4_window7_224] INFO: Epoch: [89] [1040/1251] eta: 0:02:13 lr: 0.000797 loss: 3.3578 (3.5445) grad_norm: 1.1909 (inf) time: 0.6339 [2021-03-26 18:38:30 swin_base_patch4_window7_224] INFO: Epoch: [89] [1050/1251] eta: 0:02:07 lr: 0.000797 loss: 3.4637 (3.5447) grad_norm: 1.1791 (inf) time: 0.6275 [2021-03-26 18:38:37 swin_base_patch4_window7_224] INFO: Epoch: [89] [1060/1251] eta: 0:02:01 lr: 0.000797 loss: 3.5584 (3.5451) grad_norm: 1.0671 (inf) time: 0.6268 [2021-03-26 18:38:43 swin_base_patch4_window7_224] INFO: Epoch: [89] [1070/1251] eta: 0:01:54 lr: 0.000797 loss: 3.5853 (3.5465) grad_norm: 1.1419 (inf) time: 0.6321 [2021-03-26 18:38:49 swin_base_patch4_window7_224] INFO: Epoch: [89] [1080/1251] eta: 0:01:48 lr: 0.000797 loss: 3.5455 (3.5454) grad_norm: 1.1780 (inf) time: 0.6322 [2021-03-26 18:38:56 swin_base_patch4_window7_224] INFO: Epoch: [89] [1090/1251] eta: 0:01:42 lr: 0.000796 loss: 3.5160 (3.5460) grad_norm: 1.2194 (inf) time: 0.6238 [2021-03-26 18:39:02 swin_base_patch4_window7_224] INFO: Epoch: [89] [1100/1251] eta: 0:01:35 lr: 0.000796 loss: 3.7766 (3.5484) grad_norm: 1.1386 (inf) time: 0.6209 [2021-03-26 18:39:08 swin_base_patch4_window7_224] INFO: Epoch: [89] [1110/1251] eta: 0:01:29 lr: 0.000796 loss: 3.8300 (3.5490) grad_norm: 1.1386 (inf) time: 0.6239 [2021-03-26 18:39:14 swin_base_patch4_window7_224] INFO: Epoch: [89] [1120/1251] eta: 0:01:22 lr: 0.000796 loss: 3.4392 (3.5481) grad_norm: 1.0426 (inf) time: 0.6211 [2021-03-26 18:39:21 swin_base_patch4_window7_224] INFO: Epoch: [89] [1130/1251] eta: 0:01:16 lr: 0.000796 loss: 3.3989 (3.5474) grad_norm: 1.0865 (inf) time: 0.6255 [2021-03-26 18:39:27 swin_base_patch4_window7_224] INFO: Epoch: [89] [1140/1251] eta: 0:01:10 lr: 0.000796 loss: 3.4521 (3.5468) grad_norm: 1.1354 (inf) time: 0.6340 [2021-03-26 18:39:33 swin_base_patch4_window7_224] INFO: Epoch: [89] [1150/1251] eta: 0:01:03 lr: 0.000796 loss: 3.3998 (3.5436) grad_norm: 1.2078 (inf) time: 0.6313 [2021-03-26 18:39:39 swin_base_patch4_window7_224] INFO: Epoch: [89] [1160/1251] eta: 0:00:57 lr: 0.000796 loss: 3.4181 (3.5441) grad_norm: 1.2004 (inf) time: 0.6251 [2021-03-26 18:39:46 swin_base_patch4_window7_224] INFO: Epoch: [89] [1170/1251] eta: 0:00:51 lr: 0.000796 loss: 3.7315 (3.5445) grad_norm: 1.2199 (inf) time: 0.6292 [2021-03-26 18:39:52 swin_base_patch4_window7_224] INFO: Epoch: [89] [1180/1251] eta: 0:00:44 lr: 0.000796 loss: 3.7336 (3.5449) grad_norm: 1.2199 (inf) time: 0.6300 [2021-03-26 18:39:58 swin_base_patch4_window7_224] INFO: Epoch: [89] [1190/1251] eta: 0:00:38 lr: 0.000796 loss: 3.6533 (3.5434) grad_norm: 1.2064 (inf) time: 0.6264 [2021-03-26 18:40:05 swin_base_patch4_window7_224] INFO: Epoch: [89] [1200/1251] eta: 0:00:32 lr: 0.000796 loss: 3.4880 (3.5421) grad_norm: 1.1649 (inf) time: 0.6295 [2021-03-26 18:40:11 swin_base_patch4_window7_224] INFO: Epoch: [89] [1210/1251] eta: 0:00:25 lr: 0.000796 loss: 3.3589 (3.5429) grad_norm: 1.1500 (inf) time: 0.6290 [2021-03-26 18:40:17 swin_base_patch4_window7_224] INFO: Epoch: [89] [1220/1251] eta: 0:00:19 lr: 0.000796 loss: 3.5302 (3.5419) grad_norm: 1.1395 (inf) time: 0.6229 [2021-03-26 18:40:23 swin_base_patch4_window7_224] INFO: Epoch: [89] [1230/1251] eta: 0:00:13 lr: 0.000796 loss: 3.4790 (3.5404) grad_norm: 1.1168 (inf) time: 0.6249 [2021-03-26 18:40:30 swin_base_patch4_window7_224] INFO: Epoch: [89] [1240/1251] eta: 0:00:06 lr: 0.000796 loss: 3.4434 (3.5395) grad_norm: 1.1400 (inf) time: 0.6245 [2021-03-26 18:40:36 swin_base_patch4_window7_224] INFO: Epoch: [89] [1250/1251] eta: 0:00:00 lr: 0.000796 loss: 3.5096 (3.5391) grad_norm: 1.1656 (inf) time: 0.6194 [2021-03-26 18:40:42 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:34 loss: 1.2340 (1.2340) acc1: 70.3125 (70.3125) acc5: 95.3125 (95.3125) [2021-03-26 18:40:44 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:13 loss: 1.0398 (1.0292) acc1: 73.4375 (75.1420) acc5: 95.3125 (94.6023) [2021-03-26 18:40:46 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.0398 (1.0404) acc1: 73.4375 (75.9673) acc5: 93.7500 (94.1220) [2021-03-26 18:40:48 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.9929 (1.0530) acc1: 75.0000 (76.4113) acc5: 93.7500 (94.0020) [2021-03-26 18:40:51 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0323 (1.0749) acc1: 75.0000 (75.6098) acc5: 92.1875 (93.5213) [2021-03-26 18:40:52 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0800 (1.0761) acc1: 73.4375 (75.5520) acc5: 92.1875 (93.4400) [2021-03-26 18:40:58 swin_base_patch4_window7_224] INFO: * Acc@1 75.960 Acc@5 93.508 loss 1.053 [2021-03-26 18:40:58 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.0% [2021-03-26 18:40:58 swin_base_patch4_window7_224] INFO: Max accuracy: 76.23% [2021-03-26 18:41:02 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 0/1251] eta: 1:31:06 lr: 0.000796 loss: 4.2498 (4.2498) grad_norm: 1.1271 (1.1271) time: 4.3696 [2021-03-26 18:41:08 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 10/1251] eta: 0:20:08 lr: 0.000796 loss: 3.8145 (3.6600) grad_norm: 1.1877 (1.2424) time: 0.9738 [2021-03-26 18:41:15 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 20/1251] eta: 0:16:40 lr: 0.000796 loss: 3.7803 (3.6960) grad_norm: 1.1877 (1.2037) time: 0.6353 [2021-03-26 18:41:21 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 30/1251] eta: 0:15:21 lr: 0.000796 loss: 3.7803 (3.6279) grad_norm: 1.1549 (1.1885) time: 0.6338 [2021-03-26 18:41:27 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 40/1251] eta: 0:14:37 lr: 0.000796 loss: 3.7080 (3.6152) grad_norm: 1.1686 (1.1921) time: 0.6309 [2021-03-26 18:41:34 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 50/1251] eta: 0:14:08 lr: 0.000796 loss: 3.7080 (3.6024) grad_norm: 1.1156 (1.1942) time: 0.6320 [2021-03-26 18:41:40 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 60/1251] eta: 0:13:47 lr: 0.000796 loss: 3.6080 (3.5904) grad_norm: 1.1449 (1.1904) time: 0.6334 [2021-03-26 18:41:46 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 70/1251] eta: 0:13:28 lr: 0.000796 loss: 3.6924 (3.6174) grad_norm: 1.1449 (1.1793) time: 0.6293 [2021-03-26 18:41:53 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 80/1251] eta: 0:13:14 lr: 0.000796 loss: 3.5803 (3.5973) grad_norm: 1.0969 (1.1749) time: 0.6282 [2021-03-26 18:41:59 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 90/1251] eta: 0:13:04 lr: 0.000796 loss: 3.4360 (3.5787) grad_norm: 1.1605 (1.1828) time: 0.6429 [2021-03-26 18:42:06 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 100/1251] eta: 0:12:52 lr: 0.000796 loss: 3.4857 (3.5895) grad_norm: 1.1903 (1.1844) time: 0.6438 [2021-03-26 18:42:12 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 110/1251] eta: 0:12:42 lr: 0.000796 loss: 3.4614 (3.5569) grad_norm: 1.0996 (1.1760) time: 0.6334 [2021-03-26 18:42:18 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 120/1251] eta: 0:12:31 lr: 0.000796 loss: 3.4608 (3.5673) grad_norm: 1.1079 (1.1761) time: 0.6300 [2021-03-26 18:42:25 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 130/1251] eta: 0:12:22 lr: 0.000796 loss: 3.5262 (3.5522) grad_norm: 1.1387 (1.1779) time: 0.6326 [2021-03-26 18:42:31 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 140/1251] eta: 0:12:14 lr: 0.000795 loss: 3.4678 (3.5388) grad_norm: 1.1777 (1.1817) time: 0.6379 [2021-03-26 18:42:37 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 150/1251] eta: 0:12:05 lr: 0.000795 loss: 3.3291 (3.5191) grad_norm: 1.1418 (1.1775) time: 0.6357 [2021-03-26 18:42:44 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 160/1251] eta: 0:11:56 lr: 0.000795 loss: 3.5149 (3.5286) grad_norm: 1.1960 (1.1822) time: 0.6291 [2021-03-26 18:42:50 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 170/1251] eta: 0:11:47 lr: 0.000795 loss: 3.6754 (3.5484) grad_norm: 1.2352 (1.1815) time: 0.6206 [2021-03-26 18:42:56 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 180/1251] eta: 0:11:39 lr: 0.000795 loss: 3.5815 (3.5343) grad_norm: 1.1856 (1.1833) time: 0.6216 [2021-03-26 18:43:02 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 190/1251] eta: 0:11:32 lr: 0.000795 loss: 3.2826 (3.5192) grad_norm: 1.2026 (1.1899) time: 0.6337 [2021-03-26 18:43:09 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 200/1251] eta: 0:11:24 lr: 0.000795 loss: 3.2826 (3.5200) grad_norm: 1.2015 (1.1887) time: 0.6380 [2021-03-26 18:43:15 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 210/1251] eta: 0:11:17 lr: 0.000795 loss: 3.5590 (3.5115) grad_norm: 1.1718 (1.1887) time: 0.6358 [2021-03-26 18:43:21 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 220/1251] eta: 0:11:09 lr: 0.000795 loss: 3.5590 (3.5159) grad_norm: 1.2018 (1.1927) time: 0.6302 [2021-03-26 18:43:28 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 230/1251] eta: 0:11:01 lr: 0.000795 loss: 3.5569 (3.5109) grad_norm: 1.1951 (1.1943) time: 0.6210 [2021-03-26 18:43:34 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 240/1251] eta: 0:10:54 lr: 0.000795 loss: 3.4993 (3.5111) grad_norm: 1.1406 (1.1940) time: 0.6288 [2021-03-26 18:43:40 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 250/1251] eta: 0:10:47 lr: 0.000795 loss: 3.5594 (3.5147) grad_norm: 1.0829 (1.1900) time: 0.6321 [2021-03-26 18:43:46 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 260/1251] eta: 0:10:40 lr: 0.000795 loss: 3.6342 (3.5184) grad_norm: 1.0767 (1.1872) time: 0.6285 [2021-03-26 18:43:53 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 270/1251] eta: 0:10:33 lr: 0.000795 loss: 3.8599 (3.5198) grad_norm: 1.1324 (1.1862) time: 0.6335 [2021-03-26 18:43:59 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 280/1251] eta: 0:10:26 lr: 0.000795 loss: 3.5417 (3.5191) grad_norm: 1.1366 (1.1845) time: 0.6342 [2021-03-26 18:44:05 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 290/1251] eta: 0:10:19 lr: 0.000795 loss: 3.7897 (3.5320) grad_norm: 1.0894 (1.1818) time: 0.6291 [2021-03-26 18:44:12 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 300/1251] eta: 0:10:12 lr: 0.000795 loss: 3.8193 (3.5339) grad_norm: 1.0886 (1.1810) time: 0.6314 [2021-03-26 18:44:18 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 310/1251] eta: 0:10:05 lr: 0.000795 loss: 3.7384 (3.5409) grad_norm: 1.1772 (1.1820) time: 0.6301 [2021-03-26 18:44:24 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 320/1251] eta: 0:09:59 lr: 0.000795 loss: 3.8079 (3.5466) grad_norm: 1.2023 (1.1836) time: 0.6292 [2021-03-26 18:44:31 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 330/1251] eta: 0:09:52 lr: 0.000795 loss: 3.7724 (3.5542) grad_norm: 1.1672 (1.1843) time: 0.6350 [2021-03-26 18:44:37 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 340/1251] eta: 0:09:45 lr: 0.000795 loss: 3.6861 (3.5520) grad_norm: 1.1609 (1.1838) time: 0.6316 [2021-03-26 18:44:43 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 350/1251] eta: 0:09:39 lr: 0.000795 loss: 3.5490 (3.5467) grad_norm: 1.1265 (1.1843) time: 0.6349 [2021-03-26 18:44:50 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 360/1251] eta: 0:09:32 lr: 0.000795 loss: 3.5490 (3.5475) grad_norm: 1.1490 (1.1859) time: 0.6341 [2021-03-26 18:44:56 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 370/1251] eta: 0:09:25 lr: 0.000795 loss: 3.5208 (3.5434) grad_norm: 1.1386 (1.1846) time: 0.6271 [2021-03-26 18:45:02 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 380/1251] eta: 0:09:18 lr: 0.000795 loss: 3.5208 (3.5454) grad_norm: 1.1007 (1.1835) time: 0.6288 [2021-03-26 18:45:09 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 390/1251] eta: 0:09:12 lr: 0.000795 loss: 3.4736 (3.5451) grad_norm: 1.1772 (1.1838) time: 0.6318 [2021-03-26 18:45:15 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 400/1251] eta: 0:09:05 lr: 0.000795 loss: 3.5274 (3.5459) grad_norm: 1.1772 (1.1838) time: 0.6307 [2021-03-26 18:45:21 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 410/1251] eta: 0:08:58 lr: 0.000795 loss: 3.8935 (3.5499) grad_norm: 1.1685 (1.1844) time: 0.6271 [2021-03-26 18:45:27 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 420/1251] eta: 0:08:52 lr: 0.000795 loss: 3.6517 (3.5486) grad_norm: 1.1687 (1.1836) time: 0.6279 [2021-03-26 18:45:34 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 430/1251] eta: 0:08:45 lr: 0.000795 loss: 3.4145 (3.5442) grad_norm: 1.1591 (1.1851) time: 0.6335 [2021-03-26 18:45:40 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 440/1251] eta: 0:08:39 lr: 0.000794 loss: 3.5443 (3.5484) grad_norm: 1.1847 (1.1849) time: 0.6317 [2021-03-26 18:45:46 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 450/1251] eta: 0:08:32 lr: 0.000794 loss: 3.8723 (3.5544) grad_norm: 1.2231 (1.1863) time: 0.6249 [2021-03-26 18:45:53 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 460/1251] eta: 0:08:26 lr: 0.000794 loss: 3.8021 (3.5584) grad_norm: 1.2269 (1.1872) time: 0.6329 [2021-03-26 18:45:59 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 470/1251] eta: 0:08:19 lr: 0.000794 loss: 3.5344 (3.5571) grad_norm: 1.2412 (1.1890) time: 0.6415 [2021-03-26 18:46:05 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 480/1251] eta: 0:08:13 lr: 0.000794 loss: 3.5299 (3.5567) grad_norm: 1.2461 (1.1911) time: 0.6354 [2021-03-26 18:46:12 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 490/1251] eta: 0:08:06 lr: 0.000794 loss: 3.4485 (3.5568) grad_norm: 1.2008 (1.1919) time: 0.6265 [2021-03-26 18:46:18 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 500/1251] eta: 0:07:59 lr: 0.000794 loss: 3.3215 (3.5514) grad_norm: 1.2008 (1.1932) time: 0.6247 [2021-03-26 18:46:24 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 510/1251] eta: 0:07:53 lr: 0.000794 loss: 3.3847 (3.5522) grad_norm: 1.1600 (1.1931) time: 0.6268 [2021-03-26 18:46:31 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 520/1251] eta: 0:07:46 lr: 0.000794 loss: 3.4996 (3.5506) grad_norm: 1.1453 (1.1924) time: 0.6321 [2021-03-26 18:46:37 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 530/1251] eta: 0:07:40 lr: 0.000794 loss: 3.5792 (3.5485) grad_norm: 1.1542 (1.1929) time: 0.6311 [2021-03-26 18:46:43 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 540/1251] eta: 0:07:33 lr: 0.000794 loss: 3.5555 (3.5458) grad_norm: 1.1974 (1.1926) time: 0.6295 [2021-03-26 18:46:50 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 550/1251] eta: 0:07:27 lr: 0.000794 loss: 3.3885 (3.5396) grad_norm: 1.1723 (1.1918) time: 0.6383 [2021-03-26 18:46:56 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 560/1251] eta: 0:07:21 lr: 0.000794 loss: 3.2083 (3.5341) grad_norm: 1.1723 (1.1914) time: 0.6406 [2021-03-26 18:47:02 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 570/1251] eta: 0:07:14 lr: 0.000794 loss: 3.3040 (3.5326) grad_norm: 1.1802 (1.1918) time: 0.6311 [2021-03-26 18:47:09 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 580/1251] eta: 0:07:08 lr: 0.000794 loss: 3.3615 (3.5310) grad_norm: 1.2119 (1.1923) time: 0.6284 [2021-03-26 18:47:15 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 590/1251] eta: 0:07:01 lr: 0.000794 loss: 3.4052 (3.5314) grad_norm: 1.2050 (1.1925) time: 0.6299 [2021-03-26 18:47:21 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 600/1251] eta: 0:06:55 lr: 0.000794 loss: 3.6973 (3.5342) grad_norm: 1.1725 (1.1922) time: 0.6326 [2021-03-26 18:47:27 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 610/1251] eta: 0:06:48 lr: 0.000794 loss: 3.5162 (3.5324) grad_norm: 1.1861 (1.1926) time: 0.6295 [2021-03-26 18:47:34 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 620/1251] eta: 0:06:42 lr: 0.000794 loss: 3.6755 (3.5374) grad_norm: 1.1104 (1.1913) time: 0.6208 [2021-03-26 18:47:40 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 630/1251] eta: 0:06:35 lr: 0.000794 loss: 3.6256 (3.5355) grad_norm: 1.1228 (1.1905) time: 0.6253 [2021-03-26 18:47:46 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 640/1251] eta: 0:06:29 lr: 0.000794 loss: 3.4505 (3.5326) grad_norm: 1.1542 (1.1901) time: 0.6326 [2021-03-26 18:47:53 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 650/1251] eta: 0:06:22 lr: 0.000794 loss: 3.5442 (3.5331) grad_norm: 1.1328 (1.1897) time: 0.6300 [2021-03-26 18:47:59 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 660/1251] eta: 0:06:16 lr: 0.000794 loss: 3.6201 (3.5352) grad_norm: 1.0925 (1.1897) time: 0.6310 [2021-03-26 18:48:05 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 670/1251] eta: 0:06:09 lr: 0.000794 loss: 3.7978 (3.5373) grad_norm: 1.1208 (1.1892) time: 0.6287 [2021-03-26 18:48:11 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 680/1251] eta: 0:06:03 lr: 0.000794 loss: 3.5917 (3.5355) grad_norm: 1.1106 (1.1884) time: 0.6222 [2021-03-26 18:48:18 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 690/1251] eta: 0:05:57 lr: 0.000794 loss: 3.4765 (3.5340) grad_norm: 1.1517 (1.1889) time: 0.6255 [2021-03-26 18:48:24 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 700/1251] eta: 0:05:50 lr: 0.000794 loss: 3.5170 (3.5330) grad_norm: 1.2470 (1.1893) time: 0.6248 [2021-03-26 18:48:30 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 710/1251] eta: 0:05:44 lr: 0.000794 loss: 3.7036 (3.5348) grad_norm: 1.1618 (1.1904) time: 0.6250 [2021-03-26 18:48:37 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 720/1251] eta: 0:05:37 lr: 0.000794 loss: 3.7036 (3.5337) grad_norm: 1.1485 (1.1899) time: 0.6301 [2021-03-26 18:48:43 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 730/1251] eta: 0:05:31 lr: 0.000794 loss: 3.5537 (3.5325) grad_norm: 1.2091 (1.1913) time: 0.6364 [2021-03-26 18:48:49 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 740/1251] eta: 0:05:25 lr: 0.000793 loss: 3.7240 (3.5349) grad_norm: 1.2278 (1.1921) time: 0.6399 [2021-03-26 18:48:56 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 750/1251] eta: 0:05:18 lr: 0.000793 loss: 3.7240 (3.5349) grad_norm: 1.1393 (1.1916) time: 0.6415 [2021-03-26 18:49:02 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 760/1251] eta: 0:05:12 lr: 0.000793 loss: 3.2049 (3.5305) grad_norm: 1.0931 (1.1911) time: 0.6362 [2021-03-26 18:49:08 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 770/1251] eta: 0:05:05 lr: 0.000793 loss: 3.4048 (3.5302) grad_norm: 1.1532 (1.1922) time: 0.6303 [2021-03-26 18:49:15 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 780/1251] eta: 0:04:59 lr: 0.000793 loss: 3.4555 (3.5291) grad_norm: 1.2251 (1.1935) time: 0.6289 [2021-03-26 18:49:21 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 790/1251] eta: 0:04:53 lr: 0.000793 loss: 3.3289 (3.5260) grad_norm: 1.1868 (1.1934) time: 0.6291 [2021-03-26 18:49:27 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 800/1251] eta: 0:04:46 lr: 0.000793 loss: 3.5874 (3.5274) grad_norm: 1.1485 (1.1934) time: 0.6332 [2021-03-26 18:49:34 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 810/1251] eta: 0:04:40 lr: 0.000793 loss: 3.8114 (3.5276) grad_norm: 1.1220 (1.1918) time: 0.6337 [2021-03-26 18:49:40 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 820/1251] eta: 0:04:34 lr: 0.000793 loss: 3.6673 (3.5289) grad_norm: 1.1130 (1.1921) time: 0.6271 [2021-03-26 18:49:46 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 830/1251] eta: 0:04:27 lr: 0.000793 loss: 3.6673 (3.5297) grad_norm: 1.2023 (1.1922) time: 0.6259 [2021-03-26 18:49:52 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 840/1251] eta: 0:04:21 lr: 0.000793 loss: 3.6993 (3.5316) grad_norm: 1.1846 (1.1935) time: 0.6278 [2021-03-26 18:49:59 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 850/1251] eta: 0:04:14 lr: 0.000793 loss: 3.4776 (3.5309) grad_norm: 1.1846 (1.1943) time: 0.6321 [2021-03-26 18:50:05 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 860/1251] eta: 0:04:08 lr: 0.000793 loss: 3.3686 (3.5270) grad_norm: 1.2191 (1.1949) time: 0.6362 [2021-03-26 18:50:12 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 870/1251] eta: 0:04:02 lr: 0.000793 loss: 3.3128 (3.5271) grad_norm: 1.2225 (1.1957) time: 0.6387 [2021-03-26 18:50:18 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 880/1251] eta: 0:03:55 lr: 0.000793 loss: 3.7127 (3.5298) grad_norm: 1.2225 (1.1957) time: 0.6362 [2021-03-26 18:50:24 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 890/1251] eta: 0:03:49 lr: 0.000793 loss: 3.6267 (3.5293) grad_norm: 1.2087 (1.1961) time: 0.6288 [2021-03-26 18:50:30 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 900/1251] eta: 0:03:43 lr: 0.000793 loss: 3.5250 (3.5296) grad_norm: 1.1640 (1.1957) time: 0.6275 [2021-03-26 18:50:37 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 910/1251] eta: 0:03:36 lr: 0.000793 loss: 3.5798 (3.5300) grad_norm: 1.1282 (1.1952) time: 0.6259 [2021-03-26 18:50:43 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 920/1251] eta: 0:03:30 lr: 0.000793 loss: 3.5323 (3.5287) grad_norm: 1.1638 (1.1954) time: 0.6264 [2021-03-26 18:50:49 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 930/1251] eta: 0:03:23 lr: 0.000793 loss: 3.5323 (3.5287) grad_norm: 1.1887 (1.1963) time: 0.6278 [2021-03-26 18:50:55 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 940/1251] eta: 0:03:17 lr: 0.000793 loss: 3.6843 (3.5301) grad_norm: 1.2029 (1.1962) time: 0.6262 [2021-03-26 18:51:02 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 950/1251] eta: 0:03:11 lr: 0.000793 loss: 3.6843 (3.5304) grad_norm: 1.1656 (1.1969) time: 0.6330 [2021-03-26 18:51:08 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 960/1251] eta: 0:03:04 lr: 0.000793 loss: 3.4716 (3.5278) grad_norm: 1.1637 (1.1959) time: 0.6321 [2021-03-26 18:51:14 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 970/1251] eta: 0:02:58 lr: 0.000793 loss: 3.6474 (3.5290) grad_norm: 1.0820 (1.1952) time: 0.6231 [2021-03-26 18:51:21 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 980/1251] eta: 0:02:52 lr: 0.000793 loss: 3.5400 (3.5280) grad_norm: 1.1300 (1.1950) time: 0.6256 [2021-03-26 18:51:27 swin_base_patch4_window7_224] INFO: Epoch: [90] [ 990/1251] eta: 0:02:45 lr: 0.000793 loss: 3.5283 (3.5291) grad_norm: 1.1386 (1.1947) time: 0.6308 [2021-03-26 18:51:33 swin_base_patch4_window7_224] INFO: Epoch: [90] [1000/1251] eta: 0:02:39 lr: 0.000793 loss: 3.7065 (3.5302) grad_norm: 1.1279 (1.1945) time: 0.6297 [2021-03-26 18:51:39 swin_base_patch4_window7_224] INFO: Epoch: [90] [1010/1251] eta: 0:02:32 lr: 0.000793 loss: 3.5132 (3.5291) grad_norm: 1.1237 (1.1944) time: 0.6248 [2021-03-26 18:51:46 swin_base_patch4_window7_224] INFO: Epoch: [90] [1020/1251] eta: 0:02:26 lr: 0.000793 loss: 3.4986 (3.5288) grad_norm: 1.1858 (1.1943) time: 0.6273 [2021-03-26 18:51:52 swin_base_patch4_window7_224] INFO: Epoch: [90] [1030/1251] eta: 0:02:20 lr: 0.000792 loss: 3.4701 (3.5251) grad_norm: 1.2127 (1.1951) time: 0.6331 [2021-03-26 18:51:58 swin_base_patch4_window7_224] INFO: Epoch: [90] [1040/1251] eta: 0:02:13 lr: 0.000792 loss: 3.4981 (3.5275) grad_norm: 1.2127 (1.1945) time: 0.6348 [2021-03-26 18:52:05 swin_base_patch4_window7_224] INFO: Epoch: [90] [1050/1251] eta: 0:02:07 lr: 0.000792 loss: 3.8510 (3.5288) grad_norm: 1.1541 (1.1949) time: 0.6322 [2021-03-26 18:52:11 swin_base_patch4_window7_224] INFO: Epoch: [90] [1060/1251] eta: 0:02:01 lr: 0.000792 loss: 3.7167 (3.5296) grad_norm: 1.1901 (1.1945) time: 0.6291 [2021-03-26 18:52:17 swin_base_patch4_window7_224] INFO: Epoch: [90] [1070/1251] eta: 0:01:54 lr: 0.000792 loss: 3.7167 (3.5303) grad_norm: 1.0982 (1.1936) time: 0.6276 [2021-03-26 18:52:24 swin_base_patch4_window7_224] INFO: Epoch: [90] [1080/1251] eta: 0:01:48 lr: 0.000792 loss: 3.6639 (3.5297) grad_norm: 1.0760 (1.1925) time: 0.6369 [2021-03-26 18:52:30 swin_base_patch4_window7_224] INFO: Epoch: [90] [1090/1251] eta: 0:01:42 lr: 0.000792 loss: 3.7199 (3.5323) grad_norm: 1.0886 (1.1921) time: 0.6349 [2021-03-26 18:52:36 swin_base_patch4_window7_224] INFO: Epoch: [90] [1100/1251] eta: 0:01:35 lr: 0.000792 loss: 3.6020 (3.5305) grad_norm: 1.1634 (1.1930) time: 0.6263 [2021-03-26 18:52:43 swin_base_patch4_window7_224] INFO: Epoch: [90] [1110/1251] eta: 0:01:29 lr: 0.000792 loss: 3.3919 (3.5300) grad_norm: 1.1634 (1.1930) time: 0.6323 [2021-03-26 18:52:49 swin_base_patch4_window7_224] INFO: Epoch: [90] [1120/1251] eta: 0:01:23 lr: 0.000792 loss: 3.3919 (3.5286) grad_norm: 1.1202 (1.1929) time: 0.6294 [2021-03-26 18:52:55 swin_base_patch4_window7_224] INFO: Epoch: [90] [1130/1251] eta: 0:01:16 lr: 0.000792 loss: 3.1786 (3.5237) grad_norm: 1.1679 (1.1937) time: 0.6243 [2021-03-26 18:53:01 swin_base_patch4_window7_224] INFO: Epoch: [90] [1140/1251] eta: 0:01:10 lr: 0.000792 loss: 3.1781 (3.5221) grad_norm: 1.2632 (1.1939) time: 0.6247 [2021-03-26 18:53:08 swin_base_patch4_window7_224] INFO: Epoch: [90] [1150/1251] eta: 0:01:04 lr: 0.000792 loss: 3.5361 (3.5230) grad_norm: 1.2018 (1.1938) time: 0.6244 [2021-03-26 18:53:14 swin_base_patch4_window7_224] INFO: Epoch: [90] [1160/1251] eta: 0:00:57 lr: 0.000792 loss: 3.7112 (3.5238) grad_norm: 1.1747 (1.1936) time: 0.6242 [2021-03-26 18:53:20 swin_base_patch4_window7_224] INFO: Epoch: [90] [1170/1251] eta: 0:00:51 lr: 0.000792 loss: 3.7112 (3.5240) grad_norm: 1.1027 (1.1927) time: 0.6265 [2021-03-26 18:53:26 swin_base_patch4_window7_224] INFO: Epoch: [90] [1180/1251] eta: 0:00:44 lr: 0.000792 loss: 3.5051 (3.5237) grad_norm: 1.0982 (1.1925) time: 0.6261 [2021-03-26 18:53:33 swin_base_patch4_window7_224] INFO: Epoch: [90] [1190/1251] eta: 0:00:38 lr: 0.000792 loss: 3.5051 (3.5239) grad_norm: 1.0938 (1.1918) time: 0.6214 [2021-03-26 18:53:39 swin_base_patch4_window7_224] INFO: Epoch: [90] [1200/1251] eta: 0:00:32 lr: 0.000792 loss: 3.7129 (3.5234) grad_norm: 1.0579 (1.1908) time: 0.6218 [2021-03-26 18:53:45 swin_base_patch4_window7_224] INFO: Epoch: [90] [1210/1251] eta: 0:00:25 lr: 0.000792 loss: 3.8458 (3.5259) grad_norm: 1.0670 (1.1901) time: 0.6271 [2021-03-26 18:53:52 swin_base_patch4_window7_224] INFO: Epoch: [90] [1220/1251] eta: 0:00:19 lr: 0.000792 loss: 3.8111 (3.5249) grad_norm: 1.0743 (1.1896) time: 0.6311 [2021-03-26 18:53:58 swin_base_patch4_window7_224] INFO: Epoch: [90] [1230/1251] eta: 0:00:13 lr: 0.000792 loss: 3.2625 (3.5224) grad_norm: 1.1887 (1.1902) time: 0.6271 [2021-03-26 18:54:04 swin_base_patch4_window7_224] INFO: Epoch: [90] [1240/1251] eta: 0:00:06 lr: 0.000792 loss: 3.5359 (3.5238) grad_norm: 1.1887 (1.1902) time: 0.6280 [2021-03-26 18:54:10 swin_base_patch4_window7_224] INFO: Epoch: [90] [1250/1251] eta: 0:00:00 lr: 0.000792 loss: 3.7704 (3.5253) grad_norm: 1.1444 (1.1898) time: 0.6292 [2021-03-26 18:55:21 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:14 loss: 0.9019 (0.9019) acc1: 79.6875 (79.6875) acc5: 95.3125 (95.3125) [2021-03-26 18:55:23 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.9897 (1.0096) acc1: 78.1250 (77.6989) acc5: 93.7500 (93.8920) [2021-03-26 18:55:24 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9750 (0.9982) acc1: 76.5625 (76.2649) acc5: 93.7500 (93.7500) [2021-03-26 18:55:26 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.9657 (0.9957) acc1: 75.0000 (76.0585) acc5: 93.7500 (94.1028) [2021-03-26 18:55:27 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.0695 (1.0347) acc1: 73.4375 (75.2668) acc5: 93.7500 (93.3689) [2021-03-26 18:55:28 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0695 (1.0322) acc1: 75.0000 (75.1680) acc5: 92.1875 (93.3120) [2021-03-26 18:55:33 swin_base_patch4_window7_224] INFO: * Acc@1 76.102 Acc@5 93.550 loss 1.015 [2021-03-26 18:55:33 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.1% [2021-03-26 18:55:33 swin_base_patch4_window7_224] INFO: Max accuracy: 76.23% [2021-03-26 18:55:37 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 0/1251] eta: 1:26:23 lr: 0.000792 loss: 3.0826 (3.0826) grad_norm: 1.6596 (1.6596) time: 4.1438 [2021-03-26 18:55:44 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 10/1251] eta: 0:20:07 lr: 0.000792 loss: 3.3205 (3.2453) grad_norm: 1.1105 (1.2055) time: 0.9727 [2021-03-26 18:55:50 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 20/1251] eta: 0:16:37 lr: 0.000792 loss: 3.4775 (3.3705) grad_norm: 1.1554 (1.2070) time: 0.6432 [2021-03-26 18:55:56 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 30/1251] eta: 0:15:17 lr: 0.000792 loss: 3.5690 (3.4538) grad_norm: 1.2300 (1.2654) time: 0.6298 [2021-03-26 18:56:02 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 40/1251] eta: 0:14:33 lr: 0.000792 loss: 3.5588 (3.4309) grad_norm: 1.2906 (1.2920) time: 0.6284 [2021-03-26 18:56:09 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 50/1251] eta: 0:14:02 lr: 0.000792 loss: 3.6792 (3.4779) grad_norm: 1.2344 (1.2716) time: 0.6246 [2021-03-26 18:56:15 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 60/1251] eta: 0:13:41 lr: 0.000792 loss: 3.7738 (3.5329) grad_norm: 1.1913 (1.2645) time: 0.6240 [2021-03-26 18:56:21 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 70/1251] eta: 0:13:24 lr: 0.000792 loss: 3.7694 (3.5279) grad_norm: 1.1913 (1.2548) time: 0.6302 [2021-03-26 18:56:28 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 80/1251] eta: 0:13:10 lr: 0.000791 loss: 3.8191 (3.5551) grad_norm: 1.1395 (1.2473) time: 0.6317 [2021-03-26 18:56:34 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 90/1251] eta: 0:12:58 lr: 0.000791 loss: 3.4549 (3.5160) grad_norm: 1.1537 (1.2407) time: 0.6322 [2021-03-26 18:56:40 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 100/1251] eta: 0:12:46 lr: 0.000791 loss: 3.2002 (3.5117) grad_norm: 1.1752 (1.2313) time: 0.6299 [2021-03-26 18:56:46 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 110/1251] eta: 0:12:36 lr: 0.000791 loss: 3.6513 (3.5085) grad_norm: 1.1905 (1.2289) time: 0.6260 [2021-03-26 18:56:53 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 120/1251] eta: 0:12:26 lr: 0.000791 loss: 3.3949 (3.5034) grad_norm: 1.2202 (1.2319) time: 0.6289 [2021-03-26 18:56:59 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 130/1251] eta: 0:12:17 lr: 0.000791 loss: 3.4355 (3.5085) grad_norm: 1.2090 (1.2306) time: 0.6307 [2021-03-26 18:57:05 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 140/1251] eta: 0:12:08 lr: 0.000791 loss: 3.5862 (3.5109) grad_norm: 1.1644 (1.2249) time: 0.6301 [2021-03-26 18:57:12 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 150/1251] eta: 0:12:00 lr: 0.000791 loss: 3.5115 (3.4971) grad_norm: 1.1644 (1.2212) time: 0.6300 [2021-03-26 18:57:18 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 160/1251] eta: 0:11:52 lr: 0.000791 loss: 3.3464 (3.4925) grad_norm: 1.1394 (1.2157) time: 0.6306 [2021-03-26 18:57:24 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 170/1251] eta: 0:11:43 lr: 0.000791 loss: 3.4746 (3.5058) grad_norm: 1.1394 (1.2159) time: 0.6276 [2021-03-26 18:57:30 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 180/1251] eta: 0:11:35 lr: 0.000791 loss: 3.7168 (3.5163) grad_norm: 1.1247 (1.2115) time: 0.6249 [2021-03-26 18:57:37 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 190/1251] eta: 0:11:28 lr: 0.000791 loss: 3.6224 (3.4992) grad_norm: 1.1300 (1.2081) time: 0.6295 [2021-03-26 18:57:43 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 200/1251] eta: 0:11:20 lr: 0.000791 loss: 3.7068 (3.5127) grad_norm: 1.1583 (1.2069) time: 0.6330 [2021-03-26 18:57:50 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 210/1251] eta: 0:11:14 lr: 0.000791 loss: 3.8664 (3.5196) grad_norm: 1.1888 (1.2101) time: 0.6371 [2021-03-26 18:57:56 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 220/1251] eta: 0:11:06 lr: 0.000791 loss: 3.3332 (3.5034) grad_norm: 1.1665 (1.2078) time: 0.6319 [2021-03-26 18:58:02 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 230/1251] eta: 0:10:59 lr: 0.000791 loss: 3.1256 (3.4956) grad_norm: 1.1130 (1.2038) time: 0.6236 [2021-03-26 18:58:08 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 240/1251] eta: 0:10:52 lr: 0.000791 loss: 3.5788 (3.5041) grad_norm: 1.1155 (1.2041) time: 0.6274 [2021-03-26 18:58:15 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 250/1251] eta: 0:10:45 lr: 0.000791 loss: 3.7132 (3.5044) grad_norm: 1.2090 (1.2079) time: 0.6347 [2021-03-26 18:58:21 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 260/1251] eta: 0:10:38 lr: 0.000791 loss: 3.5201 (3.5086) grad_norm: 1.3153 (1.2135) time: 0.6320 [2021-03-26 18:58:27 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 270/1251] eta: 0:10:31 lr: 0.000791 loss: 3.6404 (3.5117) grad_norm: 1.1829 (1.2140) time: 0.6255 [2021-03-26 18:58:33 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 280/1251] eta: 0:10:24 lr: 0.000791 loss: 3.7050 (3.5130) grad_norm: 1.1399 (1.2109) time: 0.6264 [2021-03-26 18:58:40 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 290/1251] eta: 0:10:17 lr: 0.000791 loss: 3.7050 (3.5147) grad_norm: 1.1346 (1.2140) time: 0.6288 [2021-03-26 18:58:46 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 300/1251] eta: 0:10:10 lr: 0.000791 loss: 3.7141 (3.5159) grad_norm: 1.1417 (1.2123) time: 0.6294 [2021-03-26 18:58:52 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 310/1251] eta: 0:10:03 lr: 0.000791 loss: 3.7796 (3.5257) grad_norm: 1.1215 (1.2083) time: 0.6239 [2021-03-26 18:58:59 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 320/1251] eta: 0:09:56 lr: 0.000791 loss: 3.7020 (3.5309) grad_norm: 1.1151 (1.2082) time: 0.6211 [2021-03-26 18:59:05 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 330/1251] eta: 0:09:49 lr: 0.000791 loss: 3.5870 (3.5360) grad_norm: 1.1151 (1.2058) time: 0.6282 [2021-03-26 18:59:11 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 340/1251] eta: 0:09:43 lr: 0.000791 loss: 3.4519 (3.5348) grad_norm: 1.1401 (1.2083) time: 0.6352 [2021-03-26 18:59:18 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 350/1251] eta: 0:09:36 lr: 0.000791 loss: 3.4925 (3.5386) grad_norm: 1.1420 (1.2049) time: 0.6344 [2021-03-26 18:59:24 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 360/1251] eta: 0:09:29 lr: 0.000791 loss: 3.4943 (3.5365) grad_norm: 1.1091 (1.2041) time: 0.6313 [2021-03-26 18:59:30 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 370/1251] eta: 0:09:23 lr: 0.000790 loss: 3.4943 (3.5337) grad_norm: 1.1633 (1.2038) time: 0.6302 [2021-03-26 18:59:36 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 380/1251] eta: 0:09:16 lr: 0.000790 loss: 3.6167 (3.5395) grad_norm: 1.1426 (1.2031) time: 0.6299 [2021-03-26 18:59:43 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 390/1251] eta: 0:09:10 lr: 0.000790 loss: 3.7502 (3.5420) grad_norm: 1.1103 (1.2035) time: 0.6274 [2021-03-26 18:59:49 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 400/1251] eta: 0:09:03 lr: 0.000790 loss: 3.7547 (3.5455) grad_norm: 1.0671 (1.2013) time: 0.6255 [2021-03-26 18:59:55 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 410/1251] eta: 0:08:56 lr: 0.000790 loss: 3.7547 (3.5428) grad_norm: 1.1730 (1.2023) time: 0.6237 [2021-03-26 19:00:01 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 420/1251] eta: 0:08:49 lr: 0.000790 loss: 3.7552 (3.5399) grad_norm: 1.2550 (1.2032) time: 0.6228 [2021-03-26 19:00:08 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 430/1251] eta: 0:08:43 lr: 0.000790 loss: 3.3812 (3.5390) grad_norm: 1.1650 (1.2021) time: 0.6247 [2021-03-26 19:00:14 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 440/1251] eta: 0:08:36 lr: 0.000790 loss: 3.3812 (3.5388) grad_norm: 1.1567 (1.2014) time: 0.6311 [2021-03-26 19:00:20 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 450/1251] eta: 0:08:30 lr: 0.000790 loss: 3.3682 (3.5320) grad_norm: 1.1655 (1.2012) time: 0.6332 [2021-03-26 19:00:27 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 460/1251] eta: 0:08:23 lr: 0.000790 loss: 3.3982 (3.5358) grad_norm: 1.1610 (1.2016) time: 0.6297 [2021-03-26 19:00:33 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 470/1251] eta: 0:08:17 lr: 0.000790 loss: 3.7614 (3.5372) grad_norm: 1.1508 (1.2006) time: 0.6270 [2021-03-26 19:00:39 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 480/1251] eta: 0:08:10 lr: 0.000790 loss: 3.6706 (3.5392) grad_norm: 1.1436 (1.1997) time: 0.6267 [2021-03-26 19:00:45 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 490/1251] eta: 0:08:04 lr: 0.000790 loss: 3.6049 (3.5368) grad_norm: 1.1857 (1.2008) time: 0.6279 [2021-03-26 19:00:52 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 500/1251] eta: 0:07:57 lr: 0.000790 loss: 3.6049 (3.5399) grad_norm: 1.2445 (1.2015) time: 0.6270 [2021-03-26 19:00:58 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 510/1251] eta: 0:07:51 lr: 0.000790 loss: 3.7221 (3.5408) grad_norm: 1.1913 (1.2026) time: 0.6254 [2021-03-26 19:01:04 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 520/1251] eta: 0:07:44 lr: 0.000790 loss: 3.6253 (3.5444) grad_norm: 1.1825 (1.2014) time: 0.6241 [2021-03-26 19:01:11 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 530/1251] eta: 0:07:38 lr: 0.000790 loss: 3.5421 (3.5411) grad_norm: 1.0984 (1.2006) time: 0.6285 [2021-03-26 19:01:17 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 540/1251] eta: 0:07:31 lr: 0.000790 loss: 3.5852 (3.5455) grad_norm: 1.1754 (1.2018) time: 0.6322 [2021-03-26 19:01:23 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 550/1251] eta: 0:07:25 lr: 0.000790 loss: 3.7635 (3.5470) grad_norm: 1.2055 (1.2022) time: 0.6407 [2021-03-26 19:01:30 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 560/1251] eta: 0:07:19 lr: 0.000790 loss: 3.4805 (3.5466) grad_norm: 1.1409 (1.2009) time: 0.6435 [2021-03-26 19:01:36 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 570/1251] eta: 0:07:13 lr: 0.000790 loss: 3.3136 (3.5420) grad_norm: 1.1425 (1.2034) time: 0.6391 [2021-03-26 19:01:42 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 580/1251] eta: 0:07:06 lr: 0.000790 loss: 3.5228 (3.5416) grad_norm: 1.2576 (1.2041) time: 0.6335 [2021-03-26 19:01:49 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 590/1251] eta: 0:07:00 lr: 0.000790 loss: 3.6475 (3.5432) grad_norm: 1.2413 (1.2060) time: 0.6289 [2021-03-26 19:01:55 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 600/1251] eta: 0:06:53 lr: 0.000790 loss: 3.6089 (3.5439) grad_norm: 1.2413 (1.2061) time: 0.6290 [2021-03-26 19:02:01 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 610/1251] eta: 0:06:47 lr: 0.000790 loss: 3.7043 (3.5458) grad_norm: 1.1655 (1.2068) time: 0.6241 [2021-03-26 19:02:07 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 620/1251] eta: 0:06:40 lr: 0.000790 loss: 3.7638 (3.5415) grad_norm: 1.2516 (1.2092) time: 0.6205 [2021-03-26 19:02:14 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 630/1251] eta: 0:06:34 lr: 0.000790 loss: 3.4097 (3.5415) grad_norm: 1.2925 (1.2113) time: 0.6260 [2021-03-26 19:02:20 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 640/1251] eta: 0:06:28 lr: 0.000790 loss: 3.5992 (3.5453) grad_norm: 1.3109 (1.2127) time: 0.6322 [2021-03-26 19:02:26 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 650/1251] eta: 0:06:21 lr: 0.000790 loss: 3.6436 (3.5461) grad_norm: 1.2416 (1.2126) time: 0.6378 [2021-03-26 19:02:33 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 660/1251] eta: 0:06:15 lr: 0.000790 loss: 3.6842 (3.5464) grad_norm: 1.2351 (1.2135) time: 0.6349 [2021-03-26 19:02:39 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 670/1251] eta: 0:06:08 lr: 0.000789 loss: 3.7573 (3.5496) grad_norm: 1.2141 (1.2133) time: 0.6288 [2021-03-26 19:02:45 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 680/1251] eta: 0:06:02 lr: 0.000789 loss: 3.7170 (3.5479) grad_norm: 1.1635 (1.2122) time: 0.6322 [2021-03-26 19:02:52 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 690/1251] eta: 0:05:56 lr: 0.000789 loss: 3.6712 (3.5500) grad_norm: 1.1474 (1.2118) time: 0.6336 [2021-03-26 19:02:58 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 700/1251] eta: 0:05:49 lr: 0.000789 loss: 3.6992 (3.5532) grad_norm: 1.1760 (1.2111) time: 0.6267 [2021-03-26 19:03:04 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 710/1251] eta: 0:05:43 lr: 0.000789 loss: 3.7381 (3.5550) grad_norm: 1.1313 (1.2098) time: 0.6235 [2021-03-26 19:03:10 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 720/1251] eta: 0:05:36 lr: 0.000789 loss: 3.7381 (3.5535) grad_norm: 1.1552 (1.2103) time: 0.6275 [2021-03-26 19:03:17 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 730/1251] eta: 0:05:30 lr: 0.000789 loss: 3.6752 (3.5512) grad_norm: 1.1760 (1.2099) time: 0.6356 [2021-03-26 19:03:23 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 740/1251] eta: 0:05:24 lr: 0.000789 loss: 3.7104 (3.5533) grad_norm: 1.1881 (1.2110) time: 0.6430 [2021-03-26 19:03:30 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 750/1251] eta: 0:05:17 lr: 0.000789 loss: 3.6625 (3.5523) grad_norm: 1.2084 (1.2111) time: 0.6331 [2021-03-26 19:03:36 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 760/1251] eta: 0:05:11 lr: 0.000789 loss: 3.6537 (3.5536) grad_norm: 1.1943 (1.2113) time: 0.6291 [2021-03-26 19:03:42 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 770/1251] eta: 0:05:05 lr: 0.000789 loss: 3.7514 (3.5574) grad_norm: 1.1943 (1.2113) time: 0.6281 [2021-03-26 19:03:48 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 780/1251] eta: 0:04:58 lr: 0.000789 loss: 3.9317 (3.5599) grad_norm: 1.1572 (1.2115) time: 0.6236 [2021-03-26 19:03:55 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 790/1251] eta: 0:04:52 lr: 0.000789 loss: 3.6252 (3.5570) grad_norm: 1.1491 (1.2114) time: 0.6252 [2021-03-26 19:04:01 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 800/1251] eta: 0:04:46 lr: 0.000789 loss: 3.6488 (3.5590) grad_norm: 1.1491 (1.2117) time: 0.6307 [2021-03-26 19:04:07 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 810/1251] eta: 0:04:39 lr: 0.000789 loss: 3.6016 (3.5595) grad_norm: 1.1315 (1.2118) time: 0.6288 [2021-03-26 19:04:14 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 820/1251] eta: 0:04:33 lr: 0.000789 loss: 3.4368 (3.5583) grad_norm: 1.1833 (1.2121) time: 0.6258 [2021-03-26 19:04:20 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 830/1251] eta: 0:04:26 lr: 0.000789 loss: 3.4415 (3.5601) grad_norm: 1.1734 (1.2117) time: 0.6256 [2021-03-26 19:04:26 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 840/1251] eta: 0:04:20 lr: 0.000789 loss: 3.5823 (3.5596) grad_norm: 1.1718 (1.2118) time: 0.6257 [2021-03-26 19:04:32 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 850/1251] eta: 0:04:14 lr: 0.000789 loss: 3.6568 (3.5627) grad_norm: 1.1386 (1.2109) time: 0.6330 [2021-03-26 19:04:39 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 860/1251] eta: 0:04:07 lr: 0.000789 loss: 3.6861 (3.5627) grad_norm: 1.1590 (1.2115) time: 0.6316 [2021-03-26 19:04:45 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 870/1251] eta: 0:04:01 lr: 0.000789 loss: 3.4552 (3.5603) grad_norm: 1.1891 (1.2115) time: 0.6272 [2021-03-26 19:04:51 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 880/1251] eta: 0:03:55 lr: 0.000789 loss: 3.4552 (3.5586) grad_norm: 1.1669 (1.2111) time: 0.6249 [2021-03-26 19:04:57 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 890/1251] eta: 0:03:48 lr: 0.000789 loss: 3.4786 (3.5592) grad_norm: 1.1366 (1.2105) time: 0.6261 [2021-03-26 19:05:04 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 900/1251] eta: 0:03:42 lr: 0.000789 loss: 3.6181 (3.5592) grad_norm: 1.1708 (1.2106) time: 0.6269 [2021-03-26 19:05:10 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 910/1251] eta: 0:03:35 lr: 0.000789 loss: 3.5809 (3.5578) grad_norm: 1.1708 (1.2104) time: 0.6221 [2021-03-26 19:05:16 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 920/1251] eta: 0:03:29 lr: 0.000789 loss: 3.4440 (3.5575) grad_norm: 1.1915 (1.2115) time: 0.6229 [2021-03-26 19:05:23 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 930/1251] eta: 0:03:23 lr: 0.000789 loss: 3.4586 (3.5569) grad_norm: 1.2546 (1.2119) time: 0.6283 [2021-03-26 19:05:29 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 940/1251] eta: 0:03:16 lr: 0.000789 loss: 3.4586 (3.5544) grad_norm: 1.1771 (1.2113) time: 0.6272 [2021-03-26 19:05:35 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 950/1251] eta: 0:03:10 lr: 0.000789 loss: 3.7034 (3.5557) grad_norm: 1.1675 (1.2118) time: 0.6287 [2021-03-26 19:05:41 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 960/1251] eta: 0:03:04 lr: 0.000788 loss: 3.7120 (3.5572) grad_norm: 1.1512 (1.2110) time: 0.6312 [2021-03-26 19:05:48 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 970/1251] eta: 0:02:57 lr: 0.000788 loss: 3.6908 (3.5586) grad_norm: 1.1295 (1.2111) time: 0.6297 [2021-03-26 19:05:54 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 980/1251] eta: 0:02:51 lr: 0.000788 loss: 3.5829 (3.5573) grad_norm: 1.1205 (1.2103) time: 0.6293 [2021-03-26 19:06:00 swin_base_patch4_window7_224] INFO: Epoch: [91] [ 990/1251] eta: 0:02:45 lr: 0.000788 loss: 3.8458 (3.5602) grad_norm: 1.1742 (1.2108) time: 0.6339 [2021-03-26 19:06:07 swin_base_patch4_window7_224] INFO: Epoch: [91] [1000/1251] eta: 0:02:38 lr: 0.000788 loss: 3.7671 (3.5598) grad_norm: 1.1974 (1.2107) time: 0.6314 [2021-03-26 19:06:13 swin_base_patch4_window7_224] INFO: Epoch: [91] [1010/1251] eta: 0:02:32 lr: 0.000788 loss: 3.6492 (3.5606) grad_norm: 1.1771 (1.2118) time: 0.6259 [2021-03-26 19:06:19 swin_base_patch4_window7_224] INFO: Epoch: [91] [1020/1251] eta: 0:02:26 lr: 0.000788 loss: 3.6095 (3.5605) grad_norm: 1.1701 (1.2115) time: 0.6266 [2021-03-26 19:06:25 swin_base_patch4_window7_224] INFO: Epoch: [91] [1030/1251] eta: 0:02:19 lr: 0.000788 loss: 3.5881 (3.5617) grad_norm: 1.1411 (1.2117) time: 0.6271 [2021-03-26 19:06:32 swin_base_patch4_window7_224] INFO: Epoch: [91] [1040/1251] eta: 0:02:13 lr: 0.000788 loss: 3.3030 (3.5586) grad_norm: 1.1450 (1.2115) time: 0.6305 [2021-03-26 19:06:38 swin_base_patch4_window7_224] INFO: Epoch: [91] [1050/1251] eta: 0:02:07 lr: 0.000788 loss: 3.4136 (3.5583) grad_norm: 1.2373 (1.2118) time: 0.6308 [2021-03-26 19:06:44 swin_base_patch4_window7_224] INFO: Epoch: [91] [1060/1251] eta: 0:02:00 lr: 0.000788 loss: 3.7477 (3.5595) grad_norm: 1.3147 (1.2127) time: 0.6275 [2021-03-26 19:06:51 swin_base_patch4_window7_224] INFO: Epoch: [91] [1070/1251] eta: 0:01:54 lr: 0.000788 loss: 3.7477 (3.5608) grad_norm: 1.2728 (1.2130) time: 0.6241 [2021-03-26 19:06:57 swin_base_patch4_window7_224] INFO: Epoch: [91] [1080/1251] eta: 0:01:48 lr: 0.000788 loss: 3.5035 (3.5597) grad_norm: 1.1950 (1.2126) time: 0.6336 [2021-03-26 19:07:03 swin_base_patch4_window7_224] INFO: Epoch: [91] [1090/1251] eta: 0:01:41 lr: 0.000788 loss: 3.3705 (3.5580) grad_norm: 1.1582 (1.2122) time: 0.6365 [2021-03-26 19:07:10 swin_base_patch4_window7_224] INFO: Epoch: [91] [1100/1251] eta: 0:01:35 lr: 0.000788 loss: 3.5833 (3.5589) grad_norm: 1.1302 (1.2114) time: 0.6294 [2021-03-26 19:07:16 swin_base_patch4_window7_224] INFO: Epoch: [91] [1110/1251] eta: 0:01:29 lr: 0.000788 loss: 3.7390 (3.5595) grad_norm: 1.1679 (1.2124) time: 0.6324 [2021-03-26 19:07:22 swin_base_patch4_window7_224] INFO: Epoch: [91] [1120/1251] eta: 0:01:22 lr: 0.000788 loss: 3.6037 (3.5595) grad_norm: 1.2345 (1.2121) time: 0.6385 [2021-03-26 19:07:29 swin_base_patch4_window7_224] INFO: Epoch: [91] [1130/1251] eta: 0:01:16 lr: 0.000788 loss: 3.3295 (3.5578) grad_norm: 1.1618 (1.2120) time: 0.6340 [2021-03-26 19:07:35 swin_base_patch4_window7_224] INFO: Epoch: [91] [1140/1251] eta: 0:01:10 lr: 0.000788 loss: 3.5887 (3.5581) grad_norm: 1.1503 (1.2119) time: 0.6262 [2021-03-26 19:07:41 swin_base_patch4_window7_224] INFO: Epoch: [91] [1150/1251] eta: 0:01:03 lr: 0.000788 loss: 3.4630 (3.5570) grad_norm: 1.1503 (1.2116) time: 0.6248 [2021-03-26 19:07:47 swin_base_patch4_window7_224] INFO: Epoch: [91] [1160/1251] eta: 0:00:57 lr: 0.000788 loss: 3.2391 (3.5552) grad_norm: 1.1362 (1.2110) time: 0.6244 [2021-03-26 19:07:54 swin_base_patch4_window7_224] INFO: Epoch: [91] [1170/1251] eta: 0:00:51 lr: 0.000788 loss: 3.6176 (3.5570) grad_norm: 1.1923 (1.2113) time: 0.6295 [2021-03-26 19:08:00 swin_base_patch4_window7_224] INFO: Epoch: [91] [1180/1251] eta: 0:00:44 lr: 0.000788 loss: 3.7096 (3.5556) grad_norm: 1.2393 (1.2121) time: 0.6335 [2021-03-26 19:08:06 swin_base_patch4_window7_224] INFO: Epoch: [91] [1190/1251] eta: 0:00:38 lr: 0.000788 loss: 3.6029 (3.5547) grad_norm: 1.1942 (1.2123) time: 0.6315 [2021-03-26 19:08:13 swin_base_patch4_window7_224] INFO: Epoch: [91] [1200/1251] eta: 0:00:32 lr: 0.000788 loss: 3.4065 (3.5516) grad_norm: 1.2055 (1.2130) time: 0.6355 [2021-03-26 19:08:19 swin_base_patch4_window7_224] INFO: Epoch: [91] [1210/1251] eta: 0:00:25 lr: 0.000788 loss: 3.4625 (3.5518) grad_norm: 1.1132 (1.2123) time: 0.6350 [2021-03-26 19:08:25 swin_base_patch4_window7_224] INFO: Epoch: [91] [1220/1251] eta: 0:00:19 lr: 0.000788 loss: 3.5389 (3.5524) grad_norm: 1.0784 (1.2116) time: 0.6317 [2021-03-26 19:08:32 swin_base_patch4_window7_224] INFO: Epoch: [91] [1230/1251] eta: 0:00:13 lr: 0.000788 loss: 3.6028 (3.5537) grad_norm: 1.1450 (1.2120) time: 0.6320 [2021-03-26 19:08:38 swin_base_patch4_window7_224] INFO: Epoch: [91] [1240/1251] eta: 0:00:06 lr: 0.000788 loss: 3.6028 (3.5515) grad_norm: 1.2172 (1.2121) time: 0.6290 [2021-03-26 19:08:44 swin_base_patch4_window7_224] INFO: Epoch: [91] [1250/1251] eta: 0:00:00 lr: 0.000788 loss: 3.2402 (3.5506) grad_norm: 1.2161 (1.2121) time: 0.6222 [2021-03-26 19:08:52 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:11 loss: 0.9540 (0.9540) acc1: 78.1250 (78.1250) acc5: 92.1875 (92.1875) [2021-03-26 19:08:54 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9827 (0.9994) acc1: 78.1250 (76.9886) acc5: 93.7500 (94.1761) [2021-03-26 19:08:56 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9332 (0.9818) acc1: 76.5625 (76.7113) acc5: 93.7500 (94.1220) [2021-03-26 19:08:58 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9610 (0.9828) acc1: 76.5625 (76.7641) acc5: 93.7500 (94.0524) [2021-03-26 19:09:00 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9770 (1.0058) acc1: 75.0000 (76.0290) acc5: 93.7500 (93.9787) [2021-03-26 19:09:01 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0751 (1.0193) acc1: 75.0000 (75.7440) acc5: 92.1875 (93.6320) [2021-03-26 19:09:08 swin_base_patch4_window7_224] INFO: * Acc@1 76.176 Acc@5 93.562 loss 1.012 [2021-03-26 19:09:08 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.2% [2021-03-26 19:09:08 swin_base_patch4_window7_224] INFO: Max accuracy: 76.23% [2021-03-26 19:09:13 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 0/1251] eta: 1:28:56 lr: 0.000788 loss: 3.3689 (3.3689) grad_norm: 1.1815 (1.1815) time: 4.2654 [2021-03-26 19:09:19 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 10/1251] eta: 0:20:17 lr: 0.000787 loss: 3.4506 (3.3762) grad_norm: 1.1815 (1.2576) time: 0.9809 [2021-03-26 19:09:25 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 20/1251] eta: 0:16:40 lr: 0.000787 loss: 3.5347 (3.4773) grad_norm: 1.1915 (1.2398) time: 0.6401 [2021-03-26 19:09:32 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 30/1251] eta: 0:15:23 lr: 0.000787 loss: 3.5701 (3.4246) grad_norm: 1.2168 (1.2424) time: 0.6326 [2021-03-26 19:09:38 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 40/1251] eta: 0:14:44 lr: 0.000787 loss: 3.5504 (3.4902) grad_norm: 1.1683 (1.2320) time: 0.6443 [2021-03-26 19:09:45 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 50/1251] eta: 0:14:13 lr: 0.000787 loss: 3.4954 (3.4801) grad_norm: 1.1618 (1.2197) time: 0.6393 [2021-03-26 19:09:51 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 60/1251] eta: 0:13:51 lr: 0.000787 loss: 3.4954 (3.4323) grad_norm: 1.1875 (1.2142) time: 0.6307 [2021-03-26 19:09:57 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 70/1251] eta: 0:13:32 lr: 0.000787 loss: 3.5208 (3.4552) grad_norm: 1.1875 (1.2176) time: 0.6301 [2021-03-26 19:10:04 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 80/1251] eta: 0:13:18 lr: 0.000787 loss: 3.5208 (3.4667) grad_norm: 1.2209 (1.2239) time: 0.6327 [2021-03-26 19:10:10 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 90/1251] eta: 0:13:05 lr: 0.000787 loss: 3.6360 (3.4576) grad_norm: 1.2140 (1.2193) time: 0.6365 [2021-03-26 19:10:16 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 100/1251] eta: 0:12:52 lr: 0.000787 loss: 3.4601 (3.4503) grad_norm: 1.2099 (1.2245) time: 0.6287 [2021-03-26 19:10:22 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 110/1251] eta: 0:12:41 lr: 0.000787 loss: 3.5025 (3.4706) grad_norm: 1.2369 (1.2270) time: 0.6245 [2021-03-26 19:10:29 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 120/1251] eta: 0:12:30 lr: 0.000787 loss: 3.8115 (3.4918) grad_norm: 1.1779 (1.2229) time: 0.6267 [2021-03-26 19:10:35 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 130/1251] eta: 0:12:22 lr: 0.000787 loss: 3.7735 (3.5085) grad_norm: 1.1600 (1.2202) time: 0.6346 [2021-03-26 19:10:41 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 140/1251] eta: 0:12:13 lr: 0.000787 loss: 3.7671 (3.5211) grad_norm: 1.1422 (1.2148) time: 0.6390 [2021-03-26 19:10:48 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 150/1251] eta: 0:12:04 lr: 0.000787 loss: 3.5530 (3.5103) grad_norm: 1.1699 (1.2126) time: 0.6329 [2021-03-26 19:10:54 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 160/1251] eta: 0:11:56 lr: 0.000787 loss: 3.7168 (3.5232) grad_norm: 1.1799 (1.2112) time: 0.6305 [2021-03-26 19:11:00 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 170/1251] eta: 0:11:47 lr: 0.000787 loss: 3.7985 (3.5304) grad_norm: 1.1525 (1.2095) time: 0.6279 [2021-03-26 19:11:07 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 180/1251] eta: 0:11:39 lr: 0.000787 loss: 3.6000 (3.5325) grad_norm: 1.1758 (1.2123) time: 0.6262 [2021-03-26 19:11:13 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 190/1251] eta: 0:11:32 lr: 0.000787 loss: 3.6204 (3.5346) grad_norm: 1.2480 (1.2133) time: 0.6309 [2021-03-26 19:11:19 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 200/1251] eta: 0:11:24 lr: 0.000787 loss: 3.5299 (3.5208) grad_norm: 1.1896 (1.2143) time: 0.6322 [2021-03-26 19:11:25 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 210/1251] eta: 0:11:16 lr: 0.000787 loss: 3.4684 (3.5216) grad_norm: 1.1896 (1.2133) time: 0.6286 [2021-03-26 19:11:32 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 220/1251] eta: 0:11:09 lr: 0.000787 loss: 3.4926 (3.5157) grad_norm: 1.1083 (1.2078) time: 0.6264 [2021-03-26 19:11:38 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 230/1251] eta: 0:11:02 lr: 0.000787 loss: 3.5577 (3.5244) grad_norm: 1.1322 (1.2126) time: 0.6326 [2021-03-26 19:11:44 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 240/1251] eta: 0:10:54 lr: 0.000787 loss: 3.6940 (3.5262) grad_norm: 1.2544 (1.2135) time: 0.6344 [2021-03-26 19:11:51 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 250/1251] eta: 0:10:47 lr: 0.000787 loss: 3.7204 (3.5355) grad_norm: 1.1661 (1.2123) time: 0.6340 [2021-03-26 19:11:57 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 260/1251] eta: 0:10:40 lr: 0.000787 loss: 3.7712 (3.5392) grad_norm: 1.1661 (1.2143) time: 0.6342 [2021-03-26 19:12:04 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 270/1251] eta: 0:10:34 lr: 0.000787 loss: 3.6666 (3.5422) grad_norm: 1.1953 (1.2156) time: 0.6366 [2021-03-26 19:12:10 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 280/1251] eta: 0:10:27 lr: 0.000787 loss: 3.5883 (3.5344) grad_norm: 1.1608 (1.2143) time: 0.6347 [2021-03-26 19:12:16 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 290/1251] eta: 0:10:20 lr: 0.000787 loss: 3.2946 (3.5319) grad_norm: 1.1793 (1.2133) time: 0.6266 [2021-03-26 19:12:22 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 300/1251] eta: 0:10:12 lr: 0.000786 loss: 3.2946 (3.5312) grad_norm: 1.1849 (1.2113) time: 0.6241 [2021-03-26 19:12:29 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 310/1251] eta: 0:10:05 lr: 0.000786 loss: 3.7196 (3.5339) grad_norm: 1.1728 (1.2108) time: 0.6259 [2021-03-26 19:12:35 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 320/1251] eta: 0:09:59 lr: 0.000786 loss: 3.7196 (3.5357) grad_norm: 1.1665 (1.2091) time: 0.6325 [2021-03-26 19:12:41 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 330/1251] eta: 0:09:52 lr: 0.000786 loss: 3.5896 (3.5357) grad_norm: 1.1763 (1.2095) time: 0.6295 [2021-03-26 19:12:47 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 340/1251] eta: 0:09:45 lr: 0.000786 loss: 3.3889 (3.5332) grad_norm: 1.1816 (inf) time: 0.6256 [2021-03-26 19:12:54 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 350/1251] eta: 0:09:38 lr: 0.000786 loss: 3.4272 (3.5353) grad_norm: 1.1517 (inf) time: 0.6297 [2021-03-26 19:13:00 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 360/1251] eta: 0:09:32 lr: 0.000786 loss: 3.7671 (3.5378) grad_norm: 1.1547 (inf) time: 0.6356 [2021-03-26 19:13:07 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 370/1251] eta: 0:09:25 lr: 0.000786 loss: 3.7673 (3.5434) grad_norm: 1.1594 (inf) time: 0.6377 [2021-03-26 19:13:13 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 380/1251] eta: 0:09:18 lr: 0.000786 loss: 3.2423 (3.5340) grad_norm: 1.1558 (inf) time: 0.6336 [2021-03-26 19:13:19 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 390/1251] eta: 0:09:12 lr: 0.000786 loss: 3.2269 (3.5316) grad_norm: 1.1561 (inf) time: 0.6305 [2021-03-26 19:13:25 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 400/1251] eta: 0:09:05 lr: 0.000786 loss: 3.6870 (3.5355) grad_norm: 1.2217 (inf) time: 0.6299 [2021-03-26 19:13:32 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 410/1251] eta: 0:08:58 lr: 0.000786 loss: 3.5476 (3.5323) grad_norm: 1.2460 (inf) time: 0.6279 [2021-03-26 19:13:38 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 420/1251] eta: 0:08:52 lr: 0.000786 loss: 3.4513 (3.5353) grad_norm: 1.1937 (inf) time: 0.6273 [2021-03-26 19:13:44 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 430/1251] eta: 0:08:45 lr: 0.000786 loss: 3.6869 (3.5378) grad_norm: 1.2108 (inf) time: 0.6267 [2021-03-26 19:13:51 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 440/1251] eta: 0:08:38 lr: 0.000786 loss: 3.6500 (3.5362) grad_norm: 1.1442 (inf) time: 0.6255 [2021-03-26 19:13:57 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 450/1251] eta: 0:08:32 lr: 0.000786 loss: 3.6500 (3.5404) grad_norm: 1.2197 (inf) time: 0.6259 [2021-03-26 19:14:03 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 460/1251] eta: 0:08:25 lr: 0.000786 loss: 3.3854 (3.5359) grad_norm: 1.2127 (inf) time: 0.6315 [2021-03-26 19:14:09 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 470/1251] eta: 0:08:19 lr: 0.000786 loss: 3.8388 (3.5432) grad_norm: 1.1948 (inf) time: 0.6312 [2021-03-26 19:14:16 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 480/1251] eta: 0:08:12 lr: 0.000786 loss: 3.8469 (3.5455) grad_norm: 1.1744 (inf) time: 0.6266 [2021-03-26 19:14:22 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 490/1251] eta: 0:08:06 lr: 0.000786 loss: 3.6390 (3.5500) grad_norm: 1.1744 (inf) time: 0.6306 [2021-03-26 19:14:28 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 500/1251] eta: 0:07:59 lr: 0.000786 loss: 3.6390 (3.5502) grad_norm: 1.1936 (inf) time: 0.6261 [2021-03-26 19:14:35 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 510/1251] eta: 0:07:53 lr: 0.000786 loss: 3.6428 (3.5477) grad_norm: 1.1843 (inf) time: 0.6301 [2021-03-26 19:14:41 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 520/1251] eta: 0:07:46 lr: 0.000786 loss: 3.6588 (3.5467) grad_norm: 1.1797 (inf) time: 0.6391 [2021-03-26 19:14:47 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 530/1251] eta: 0:07:40 lr: 0.000786 loss: 3.7331 (3.5477) grad_norm: 1.1753 (inf) time: 0.6280 [2021-03-26 19:14:54 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 540/1251] eta: 0:07:33 lr: 0.000786 loss: 3.7926 (3.5521) grad_norm: 1.2692 (inf) time: 0.6291 [2021-03-26 19:15:00 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 550/1251] eta: 0:07:27 lr: 0.000786 loss: 3.7197 (3.5507) grad_norm: 1.2284 (inf) time: 0.6375 [2021-03-26 19:15:06 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 560/1251] eta: 0:07:20 lr: 0.000786 loss: 3.7197 (3.5548) grad_norm: 1.1389 (inf) time: 0.6405 [2021-03-26 19:15:13 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 570/1251] eta: 0:07:14 lr: 0.000786 loss: 3.6770 (3.5465) grad_norm: 1.1040 (inf) time: 0.6386 [2021-03-26 19:15:19 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 580/1251] eta: 0:07:08 lr: 0.000786 loss: 3.4231 (3.5446) grad_norm: 1.1470 (inf) time: 0.6298 [2021-03-26 19:15:25 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 590/1251] eta: 0:07:01 lr: 0.000785 loss: 3.5761 (3.5470) grad_norm: 1.1568 (inf) time: 0.6282 [2021-03-26 19:15:32 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 600/1251] eta: 0:06:55 lr: 0.000785 loss: 3.8186 (3.5505) grad_norm: 1.1228 (inf) time: 0.6302 [2021-03-26 19:15:38 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 610/1251] eta: 0:06:48 lr: 0.000785 loss: 3.7829 (3.5519) grad_norm: 1.1430 (inf) time: 0.6277 [2021-03-26 19:15:44 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 620/1251] eta: 0:06:42 lr: 0.000785 loss: 3.7708 (3.5496) grad_norm: 1.1314 (inf) time: 0.6298 [2021-03-26 19:15:51 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 630/1251] eta: 0:06:35 lr: 0.000785 loss: 3.5379 (3.5480) grad_norm: 1.0937 (inf) time: 0.6333 [2021-03-26 19:15:57 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 640/1251] eta: 0:06:29 lr: 0.000785 loss: 3.6593 (3.5499) grad_norm: 1.1462 (inf) time: 0.6293 [2021-03-26 19:16:03 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 650/1251] eta: 0:06:22 lr: 0.000785 loss: 3.6830 (3.5508) grad_norm: 1.1789 (inf) time: 0.6305 [2021-03-26 19:16:09 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 660/1251] eta: 0:06:16 lr: 0.000785 loss: 3.6830 (3.5533) grad_norm: 1.2253 (inf) time: 0.6293 [2021-03-26 19:16:16 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 670/1251] eta: 0:06:10 lr: 0.000785 loss: 3.7347 (3.5526) grad_norm: 1.2433 (inf) time: 0.6310 [2021-03-26 19:16:22 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 680/1251] eta: 0:06:03 lr: 0.000785 loss: 3.7347 (3.5552) grad_norm: 1.2012 (inf) time: 0.6366 [2021-03-26 19:16:28 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 690/1251] eta: 0:05:57 lr: 0.000785 loss: 3.6709 (3.5525) grad_norm: 1.1628 (inf) time: 0.6343 [2021-03-26 19:16:35 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 700/1251] eta: 0:05:50 lr: 0.000785 loss: 3.2529 (3.5474) grad_norm: 1.1120 (inf) time: 0.6357 [2021-03-26 19:16:41 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 710/1251] eta: 0:05:44 lr: 0.000785 loss: 3.5924 (3.5512) grad_norm: 1.1307 (inf) time: 0.6367 [2021-03-26 19:16:48 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 720/1251] eta: 0:05:38 lr: 0.000785 loss: 3.7520 (3.5517) grad_norm: 1.1885 (inf) time: 0.6344 [2021-03-26 19:16:54 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 730/1251] eta: 0:05:31 lr: 0.000785 loss: 3.4863 (3.5492) grad_norm: 1.1920 (inf) time: 0.6334 [2021-03-26 19:17:00 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 740/1251] eta: 0:05:25 lr: 0.000785 loss: 3.5088 (3.5508) grad_norm: 1.1645 (inf) time: 0.6369 [2021-03-26 19:17:07 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 750/1251] eta: 0:05:19 lr: 0.000785 loss: 3.7120 (3.5532) grad_norm: 1.1558 (inf) time: 0.6398 [2021-03-26 19:17:13 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 760/1251] eta: 0:05:12 lr: 0.000785 loss: 3.4913 (3.5505) grad_norm: 1.1311 (inf) time: 0.6335 [2021-03-26 19:17:19 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 770/1251] eta: 0:05:06 lr: 0.000785 loss: 3.3284 (3.5485) grad_norm: 1.1469 (inf) time: 0.6288 [2021-03-26 19:17:26 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 780/1251] eta: 0:04:59 lr: 0.000785 loss: 3.2735 (3.5471) grad_norm: 1.1697 (inf) time: 0.6279 [2021-03-26 19:17:32 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 790/1251] eta: 0:04:53 lr: 0.000785 loss: 3.5799 (3.5490) grad_norm: 1.1425 (inf) time: 0.6315 [2021-03-26 19:17:38 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 800/1251] eta: 0:04:46 lr: 0.000785 loss: 3.5913 (3.5486) grad_norm: 1.1425 (inf) time: 0.6312 [2021-03-26 19:17:44 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 810/1251] eta: 0:04:40 lr: 0.000785 loss: 3.5390 (3.5477) grad_norm: 1.2178 (inf) time: 0.6277 [2021-03-26 19:17:51 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 820/1251] eta: 0:04:34 lr: 0.000785 loss: 3.7199 (3.5501) grad_norm: 1.2777 (inf) time: 0.6284 [2021-03-26 19:17:57 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 830/1251] eta: 0:04:27 lr: 0.000785 loss: 3.7199 (3.5487) grad_norm: 1.2545 (inf) time: 0.6302 [2021-03-26 19:18:03 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 840/1251] eta: 0:04:21 lr: 0.000785 loss: 3.4412 (3.5465) grad_norm: 1.2216 (inf) time: 0.6291 [2021-03-26 19:18:10 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 850/1251] eta: 0:04:15 lr: 0.000785 loss: 3.4412 (3.5456) grad_norm: 1.2184 (inf) time: 0.6280 [2021-03-26 19:18:16 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 860/1251] eta: 0:04:08 lr: 0.000785 loss: 3.4593 (3.5445) grad_norm: 1.1288 (inf) time: 0.6281 [2021-03-26 19:18:22 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 870/1251] eta: 0:04:02 lr: 0.000785 loss: 3.4593 (3.5463) grad_norm: 1.1689 (inf) time: 0.6315 [2021-03-26 19:18:29 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 880/1251] eta: 0:03:55 lr: 0.000785 loss: 3.5790 (3.5443) grad_norm: 1.1729 (inf) time: 0.6348 [2021-03-26 19:18:35 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 890/1251] eta: 0:03:49 lr: 0.000784 loss: 3.6008 (3.5461) grad_norm: 1.2062 (inf) time: 0.6315 [2021-03-26 19:18:41 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 900/1251] eta: 0:03:43 lr: 0.000784 loss: 3.6844 (3.5461) grad_norm: 1.2062 (inf) time: 0.6307 [2021-03-26 19:18:48 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 910/1251] eta: 0:03:36 lr: 0.000784 loss: 3.6422 (3.5450) grad_norm: 1.1514 (inf) time: 0.6351 [2021-03-26 19:18:54 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 920/1251] eta: 0:03:30 lr: 0.000784 loss: 3.5420 (3.5449) grad_norm: 1.1394 (inf) time: 0.6371 [2021-03-26 19:19:00 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 930/1251] eta: 0:03:24 lr: 0.000784 loss: 3.5420 (3.5449) grad_norm: 1.1479 (inf) time: 0.6391 [2021-03-26 19:19:07 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 940/1251] eta: 0:03:17 lr: 0.000784 loss: 3.5393 (3.5439) grad_norm: 1.2057 (inf) time: 0.6425 [2021-03-26 19:19:13 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 950/1251] eta: 0:03:11 lr: 0.000784 loss: 3.5599 (3.5431) grad_norm: 1.1834 (inf) time: 0.6366 [2021-03-26 19:19:19 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 960/1251] eta: 0:03:05 lr: 0.000784 loss: 3.6126 (3.5403) grad_norm: 1.1934 (inf) time: 0.6353 [2021-03-26 19:19:26 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 970/1251] eta: 0:02:58 lr: 0.000784 loss: 3.5679 (3.5393) grad_norm: 1.2575 (inf) time: 0.6361 [2021-03-26 19:19:32 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 980/1251] eta: 0:02:52 lr: 0.000784 loss: 3.5679 (3.5391) grad_norm: 1.2534 (inf) time: 0.6363 [2021-03-26 19:19:39 swin_base_patch4_window7_224] INFO: Epoch: [92] [ 990/1251] eta: 0:02:45 lr: 0.000784 loss: 3.5314 (3.5391) grad_norm: 1.2121 (inf) time: 0.6382 [2021-03-26 19:19:45 swin_base_patch4_window7_224] INFO: Epoch: [92] [1000/1251] eta: 0:02:39 lr: 0.000784 loss: 3.5314 (3.5395) grad_norm: 1.1299 (inf) time: 0.6341 [2021-03-26 19:19:51 swin_base_patch4_window7_224] INFO: Epoch: [92] [1010/1251] eta: 0:02:33 lr: 0.000784 loss: 3.6184 (3.5392) grad_norm: 1.1349 (inf) time: 0.6318 [2021-03-26 19:19:58 swin_base_patch4_window7_224] INFO: Epoch: [92] [1020/1251] eta: 0:02:26 lr: 0.000784 loss: 3.4830 (3.5383) grad_norm: 1.1527 (inf) time: 0.6353 [2021-03-26 19:20:04 swin_base_patch4_window7_224] INFO: Epoch: [92] [1030/1251] eta: 0:02:20 lr: 0.000784 loss: 3.3751 (3.5372) grad_norm: 1.1566 (inf) time: 0.6313 [2021-03-26 19:20:10 swin_base_patch4_window7_224] INFO: Epoch: [92] [1040/1251] eta: 0:02:14 lr: 0.000784 loss: 3.5702 (3.5382) grad_norm: 1.0948 (inf) time: 0.6225 [2021-03-26 19:20:16 swin_base_patch4_window7_224] INFO: Epoch: [92] [1050/1251] eta: 0:02:07 lr: 0.000784 loss: 3.6818 (3.5382) grad_norm: 1.1389 (inf) time: 0.6289 [2021-03-26 19:20:23 swin_base_patch4_window7_224] INFO: Epoch: [92] [1060/1251] eta: 0:02:01 lr: 0.000784 loss: 3.3200 (3.5340) grad_norm: 1.1535 (inf) time: 0.6305 [2021-03-26 19:20:29 swin_base_patch4_window7_224] INFO: Epoch: [92] [1070/1251] eta: 0:01:55 lr: 0.000784 loss: 3.5363 (3.5356) grad_norm: 1.0911 (inf) time: 0.6278 [2021-03-26 19:20:35 swin_base_patch4_window7_224] INFO: Epoch: [92] [1080/1251] eta: 0:01:48 lr: 0.000784 loss: 3.7142 (3.5354) grad_norm: 1.1024 (inf) time: 0.6304 [2021-03-26 19:20:42 swin_base_patch4_window7_224] INFO: Epoch: [92] [1090/1251] eta: 0:01:42 lr: 0.000784 loss: 3.4879 (3.5366) grad_norm: 1.1024 (inf) time: 0.6322 [2021-03-26 19:20:48 swin_base_patch4_window7_224] INFO: Epoch: [92] [1100/1251] eta: 0:01:35 lr: 0.000784 loss: 3.6816 (3.5378) grad_norm: 1.1412 (inf) time: 0.6298 [2021-03-26 19:20:54 swin_base_patch4_window7_224] INFO: Epoch: [92] [1110/1251] eta: 0:01:29 lr: 0.000784 loss: 3.7509 (3.5386) grad_norm: 1.1630 (inf) time: 0.6252 [2021-03-26 19:21:00 swin_base_patch4_window7_224] INFO: Epoch: [92] [1120/1251] eta: 0:01:23 lr: 0.000784 loss: 3.6458 (3.5369) grad_norm: 1.1588 (inf) time: 0.6288 [2021-03-26 19:21:07 swin_base_patch4_window7_224] INFO: Epoch: [92] [1130/1251] eta: 0:01:16 lr: 0.000784 loss: 3.5174 (3.5373) grad_norm: 1.1588 (inf) time: 0.6313 [2021-03-26 19:21:13 swin_base_patch4_window7_224] INFO: Epoch: [92] [1140/1251] eta: 0:01:10 lr: 0.000784 loss: 3.6422 (3.5401) grad_norm: 1.1272 (inf) time: 0.6362 [2021-03-26 19:21:19 swin_base_patch4_window7_224] INFO: Epoch: [92] [1150/1251] eta: 0:01:04 lr: 0.000784 loss: 3.5812 (3.5394) grad_norm: 1.2055 (inf) time: 0.6344 [2021-03-26 19:21:26 swin_base_patch4_window7_224] INFO: Epoch: [92] [1160/1251] eta: 0:00:57 lr: 0.000784 loss: 3.7331 (3.5417) grad_norm: 1.2346 (inf) time: 0.6333 [2021-03-26 19:21:32 swin_base_patch4_window7_224] INFO: Epoch: [92] [1170/1251] eta: 0:00:51 lr: 0.000784 loss: 3.6137 (3.5408) grad_norm: 1.1936 (inf) time: 0.6333 [2021-03-26 19:21:38 swin_base_patch4_window7_224] INFO: Epoch: [92] [1180/1251] eta: 0:00:45 lr: 0.000783 loss: 3.5365 (3.5401) grad_norm: 1.1936 (inf) time: 0.6267 [2021-03-26 19:21:45 swin_base_patch4_window7_224] INFO: Epoch: [92] [1190/1251] eta: 0:00:38 lr: 0.000783 loss: 3.4891 (3.5384) grad_norm: 1.2071 (inf) time: 0.6268 [2021-03-26 19:21:51 swin_base_patch4_window7_224] INFO: Epoch: [92] [1200/1251] eta: 0:00:32 lr: 0.000783 loss: 3.3185 (3.5370) grad_norm: 1.1324 (inf) time: 0.6324 [2021-03-26 19:21:57 swin_base_patch4_window7_224] INFO: Epoch: [92] [1210/1251] eta: 0:00:26 lr: 0.000783 loss: 3.8146 (3.5392) grad_norm: 1.1238 (inf) time: 0.6339 [2021-03-26 19:22:04 swin_base_patch4_window7_224] INFO: Epoch: [92] [1220/1251] eta: 0:00:19 lr: 0.000783 loss: 3.8146 (3.5394) grad_norm: 1.1900 (inf) time: 0.6309 [2021-03-26 19:22:10 swin_base_patch4_window7_224] INFO: Epoch: [92] [1230/1251] eta: 0:00:13 lr: 0.000783 loss: 3.6829 (3.5393) grad_norm: 1.2521 (inf) time: 0.6364 [2021-03-26 19:22:16 swin_base_patch4_window7_224] INFO: Epoch: [92] [1240/1251] eta: 0:00:06 lr: 0.000783 loss: 3.4697 (3.5396) grad_norm: 1.2214 (inf) time: 0.6309 [2021-03-26 19:22:23 swin_base_patch4_window7_224] INFO: Epoch: [92] [1250/1251] eta: 0:00:00 lr: 0.000783 loss: 3.3809 (3.5400) grad_norm: 1.1305 (inf) time: 0.6226 [2021-03-26 19:22:27 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:24 loss: 0.9984 (0.9984) acc1: 76.5625 (76.5625) acc5: 96.8750 (96.8750) [2021-03-26 19:22:31 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.9984 (0.9915) acc1: 78.1250 (77.4148) acc5: 93.7500 (93.8920) [2021-03-26 19:22:33 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0313 (1.0192) acc1: 75.0000 (75.8185) acc5: 93.7500 (94.1964) [2021-03-26 19:22:34 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0313 (1.0294) acc1: 75.0000 (75.7560) acc5: 93.7500 (93.8508) [2021-03-26 19:22:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1023 (1.0464) acc1: 73.4375 (75.2287) acc5: 93.7500 (93.7500) [2021-03-26 19:22:37 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0187 (1.0503) acc1: 73.4375 (75.1680) acc5: 92.4528 (93.7280) [2021-03-26 19:22:42 swin_base_patch4_window7_224] INFO: * Acc@1 76.200 Acc@5 93.544 loss 1.029 [2021-03-26 19:22:42 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.2% [2021-03-26 19:22:42 swin_base_patch4_window7_224] INFO: Max accuracy: 76.23% [2021-03-26 19:22:47 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 0/1251] eta: 1:30:56 lr: 0.000783 loss: 4.1081 (4.1081) grad_norm: 1.1036 (1.1036) time: 4.3614 [2021-03-26 19:22:53 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 10/1251] eta: 0:20:04 lr: 0.000783 loss: 3.8730 (3.5777) grad_norm: 1.1073 (1.1695) time: 0.9704 [2021-03-26 19:22:59 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 20/1251] eta: 0:16:33 lr: 0.000783 loss: 3.6237 (3.6745) grad_norm: 1.1506 (1.1808) time: 0.6296 [2021-03-26 19:23:05 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 30/1251] eta: 0:15:14 lr: 0.000783 loss: 3.6237 (3.6099) grad_norm: 1.1506 (1.1822) time: 0.6266 [2021-03-26 19:23:12 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 40/1251] eta: 0:14:32 lr: 0.000783 loss: 3.7252 (3.6174) grad_norm: 1.1786 (1.2041) time: 0.6295 [2021-03-26 19:23:18 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 50/1251] eta: 0:14:05 lr: 0.000783 loss: 3.5736 (3.5707) grad_norm: 1.1885 (1.1956) time: 0.6357 [2021-03-26 19:23:25 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 60/1251] eta: 0:13:46 lr: 0.000783 loss: 3.4812 (3.5513) grad_norm: 1.2300 (1.2067) time: 0.6405 [2021-03-26 19:23:31 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 70/1251] eta: 0:13:29 lr: 0.000783 loss: 3.5679 (3.5526) grad_norm: 1.1722 (1.2048) time: 0.6380 [2021-03-26 19:23:37 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 80/1251] eta: 0:13:14 lr: 0.000783 loss: 3.6424 (3.5603) grad_norm: 1.1722 (1.2123) time: 0.6316 [2021-03-26 19:23:44 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 90/1251] eta: 0:13:02 lr: 0.000783 loss: 3.7224 (3.5703) grad_norm: 1.1185 (1.1977) time: 0.6306 [2021-03-26 19:23:50 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 100/1251] eta: 0:12:51 lr: 0.000783 loss: 3.7976 (3.5902) grad_norm: 1.1164 (1.1992) time: 0.6343 [2021-03-26 19:23:56 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 110/1251] eta: 0:12:39 lr: 0.000783 loss: 3.7686 (3.5925) grad_norm: 1.2608 (1.2091) time: 0.6306 [2021-03-26 19:24:03 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 120/1251] eta: 0:12:30 lr: 0.000783 loss: 3.7301 (3.5943) grad_norm: 1.2591 (1.2155) time: 0.6337 [2021-03-26 19:24:09 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 130/1251] eta: 0:12:21 lr: 0.000783 loss: 3.6892 (3.5916) grad_norm: 1.2213 (1.2202) time: 0.6398 [2021-03-26 19:24:15 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 140/1251] eta: 0:12:13 lr: 0.000783 loss: 3.5831 (3.5728) grad_norm: 1.2483 (1.2230) time: 0.6371 [2021-03-26 19:24:22 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 150/1251] eta: 0:12:03 lr: 0.000783 loss: 3.5831 (3.5819) grad_norm: 1.1948 (1.2203) time: 0.6295 [2021-03-26 19:24:28 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 160/1251] eta: 0:11:55 lr: 0.000783 loss: 3.6954 (3.5820) grad_norm: 1.1624 (1.2163) time: 0.6257 [2021-03-26 19:24:34 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 170/1251] eta: 0:11:47 lr: 0.000783 loss: 3.6045 (3.5762) grad_norm: 1.1624 (1.2143) time: 0.6348 [2021-03-26 19:24:41 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 180/1251] eta: 0:11:40 lr: 0.000783 loss: 3.7466 (3.5932) grad_norm: 1.2143 (1.2189) time: 0.6423 [2021-03-26 19:24:47 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 190/1251] eta: 0:11:32 lr: 0.000783 loss: 3.8296 (3.5867) grad_norm: 1.1927 (1.2172) time: 0.6361 [2021-03-26 19:24:53 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 200/1251] eta: 0:11:25 lr: 0.000783 loss: 3.2263 (3.5710) grad_norm: 1.1503 (1.2146) time: 0.6284 [2021-03-26 19:25:00 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 210/1251] eta: 0:11:17 lr: 0.000783 loss: 3.6159 (3.5695) grad_norm: 1.1273 (1.2111) time: 0.6311 [2021-03-26 19:25:06 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 220/1251] eta: 0:11:10 lr: 0.000782 loss: 3.6159 (3.5586) grad_norm: 1.1367 (1.2090) time: 0.6312 [2021-03-26 19:25:12 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 230/1251] eta: 0:11:02 lr: 0.000782 loss: 3.6876 (3.5628) grad_norm: 1.1417 (1.2062) time: 0.6285 [2021-03-26 19:25:18 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 240/1251] eta: 0:10:54 lr: 0.000782 loss: 3.6876 (3.5511) grad_norm: 1.1519 (1.2057) time: 0.6241 [2021-03-26 19:25:25 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 250/1251] eta: 0:10:47 lr: 0.000782 loss: 3.5154 (3.5545) grad_norm: 1.1953 (1.2066) time: 0.6252 [2021-03-26 19:25:31 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 260/1251] eta: 0:10:40 lr: 0.000782 loss: 3.6290 (3.5568) grad_norm: 1.2152 (1.2063) time: 0.6302 [2021-03-26 19:25:37 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 270/1251] eta: 0:10:33 lr: 0.000782 loss: 3.4353 (3.5547) grad_norm: 1.2024 (1.2062) time: 0.6319 [2021-03-26 19:25:44 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 280/1251] eta: 0:10:26 lr: 0.000782 loss: 3.6698 (3.5616) grad_norm: 1.1680 (1.2049) time: 0.6280 [2021-03-26 19:25:50 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 290/1251] eta: 0:10:19 lr: 0.000782 loss: 3.6475 (3.5587) grad_norm: 1.1047 (1.2030) time: 0.6273 [2021-03-26 19:25:56 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 300/1251] eta: 0:10:12 lr: 0.000782 loss: 3.6051 (3.5599) grad_norm: 1.1039 (1.2061) time: 0.6285 [2021-03-26 19:26:02 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 310/1251] eta: 0:10:05 lr: 0.000782 loss: 3.6992 (3.5654) grad_norm: 1.2590 (1.2083) time: 0.6310 [2021-03-26 19:26:09 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 320/1251] eta: 0:09:59 lr: 0.000782 loss: 3.6992 (3.5604) grad_norm: 1.2283 (1.2101) time: 0.6383 [2021-03-26 19:26:15 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 330/1251] eta: 0:09:52 lr: 0.000782 loss: 3.5008 (3.5518) grad_norm: 1.1861 (1.2098) time: 0.6340 [2021-03-26 19:26:21 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 340/1251] eta: 0:09:45 lr: 0.000782 loss: 3.5008 (3.5495) grad_norm: 1.0839 (1.2078) time: 0.6224 [2021-03-26 19:26:28 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 350/1251] eta: 0:09:38 lr: 0.000782 loss: 3.5834 (3.5512) grad_norm: 1.1484 (1.2073) time: 0.6255 [2021-03-26 19:26:34 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 360/1251] eta: 0:09:31 lr: 0.000782 loss: 3.6989 (3.5595) grad_norm: 1.2000 (1.2090) time: 0.6330 [2021-03-26 19:26:40 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 370/1251] eta: 0:09:25 lr: 0.000782 loss: 3.6382 (3.5518) grad_norm: 1.2341 (1.2096) time: 0.6288 [2021-03-26 19:26:47 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 380/1251] eta: 0:09:18 lr: 0.000782 loss: 3.2172 (3.5429) grad_norm: 1.2341 (1.2104) time: 0.6327 [2021-03-26 19:26:53 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 390/1251] eta: 0:09:11 lr: 0.000782 loss: 3.3333 (3.5407) grad_norm: 1.2580 (1.2125) time: 0.6326 [2021-03-26 19:26:59 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 400/1251] eta: 0:09:05 lr: 0.000782 loss: 3.6413 (3.5427) grad_norm: 1.1948 (1.2115) time: 0.6307 [2021-03-26 19:27:06 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 410/1251] eta: 0:08:58 lr: 0.000782 loss: 3.7562 (3.5492) grad_norm: 1.1823 (1.2103) time: 0.6319 [2021-03-26 19:27:12 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 420/1251] eta: 0:08:51 lr: 0.000782 loss: 3.6771 (3.5451) grad_norm: 1.2400 (1.2126) time: 0.6241 [2021-03-26 19:27:18 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 430/1251] eta: 0:08:45 lr: 0.000782 loss: 3.4554 (3.5448) grad_norm: 1.2204 (1.2135) time: 0.6219 [2021-03-26 19:27:24 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 440/1251] eta: 0:08:38 lr: 0.000782 loss: 3.4324 (3.5416) grad_norm: 1.1958 (1.2143) time: 0.6232 [2021-03-26 19:27:30 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 450/1251] eta: 0:08:31 lr: 0.000782 loss: 3.4566 (3.5441) grad_norm: 1.1934 (1.2150) time: 0.6233 [2021-03-26 19:27:37 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 460/1251] eta: 0:08:25 lr: 0.000782 loss: 3.7803 (3.5485) grad_norm: 1.2141 (1.2165) time: 0.6286 [2021-03-26 19:27:43 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 470/1251] eta: 0:08:18 lr: 0.000782 loss: 3.7287 (3.5469) grad_norm: 1.2063 (1.2153) time: 0.6312 [2021-03-26 19:27:49 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 480/1251] eta: 0:08:12 lr: 0.000782 loss: 3.7287 (3.5502) grad_norm: 1.1249 (1.2150) time: 0.6285 [2021-03-26 19:27:56 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 490/1251] eta: 0:08:05 lr: 0.000782 loss: 3.7146 (3.5507) grad_norm: 1.1964 (1.2140) time: 0.6301 [2021-03-26 19:28:02 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 500/1251] eta: 0:07:59 lr: 0.000782 loss: 3.5963 (3.5528) grad_norm: 1.2163 (1.2162) time: 0.6291 [2021-03-26 19:28:08 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 510/1251] eta: 0:07:52 lr: 0.000781 loss: 3.6725 (3.5510) grad_norm: 1.2093 (1.2152) time: 0.6356 [2021-03-26 19:28:15 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 520/1251] eta: 0:07:46 lr: 0.000781 loss: 3.4999 (3.5490) grad_norm: 1.1093 (1.2132) time: 0.6404 [2021-03-26 19:28:21 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 530/1251] eta: 0:07:40 lr: 0.000781 loss: 3.4122 (3.5407) grad_norm: 1.1093 (1.2121) time: 0.6348 [2021-03-26 19:28:27 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 540/1251] eta: 0:07:33 lr: 0.000781 loss: 3.2318 (3.5366) grad_norm: 1.1285 (1.2123) time: 0.6345 [2021-03-26 19:28:34 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 550/1251] eta: 0:07:27 lr: 0.000781 loss: 3.4256 (3.5359) grad_norm: 1.2342 (1.2147) time: 0.6424 [2021-03-26 19:28:40 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 560/1251] eta: 0:07:20 lr: 0.000781 loss: 3.5983 (3.5357) grad_norm: 1.2282 (1.2146) time: 0.6359 [2021-03-26 19:28:47 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 570/1251] eta: 0:07:14 lr: 0.000781 loss: 3.5455 (3.5333) grad_norm: 1.2312 (1.2172) time: 0.6307 [2021-03-26 19:28:53 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 580/1251] eta: 0:07:07 lr: 0.000781 loss: 3.4161 (3.5336) grad_norm: 1.1978 (1.2171) time: 0.6321 [2021-03-26 19:28:59 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 590/1251] eta: 0:07:01 lr: 0.000781 loss: 3.7597 (3.5342) grad_norm: 1.1420 (1.2163) time: 0.6301 [2021-03-26 19:29:06 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 600/1251] eta: 0:06:55 lr: 0.000781 loss: 3.7597 (3.5372) grad_norm: 1.1373 (1.2154) time: 0.6397 [2021-03-26 19:29:12 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 610/1251] eta: 0:06:48 lr: 0.000781 loss: 3.6520 (3.5355) grad_norm: 1.2155 (1.2172) time: 0.6372 [2021-03-26 19:29:18 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 620/1251] eta: 0:06:42 lr: 0.000781 loss: 3.3829 (3.5325) grad_norm: 1.2129 (1.2154) time: 0.6278 [2021-03-26 19:29:24 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 630/1251] eta: 0:06:35 lr: 0.000781 loss: 3.5827 (3.5354) grad_norm: 1.2289 (1.2170) time: 0.6256 [2021-03-26 19:29:31 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 640/1251] eta: 0:06:29 lr: 0.000781 loss: 3.7571 (3.5351) grad_norm: 1.2672 (1.2172) time: 0.6255 [2021-03-26 19:29:37 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 650/1251] eta: 0:06:22 lr: 0.000781 loss: 3.6692 (3.5357) grad_norm: 1.1992 (1.2165) time: 0.6291 [2021-03-26 19:29:43 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 660/1251] eta: 0:06:16 lr: 0.000781 loss: 3.5705 (3.5338) grad_norm: 1.1548 (1.2169) time: 0.6310 [2021-03-26 19:29:50 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 670/1251] eta: 0:06:10 lr: 0.000781 loss: 3.4602 (3.5359) grad_norm: 1.1419 (1.2156) time: 0.6306 [2021-03-26 19:29:56 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 680/1251] eta: 0:06:03 lr: 0.000781 loss: 3.6921 (3.5363) grad_norm: 1.1236 (1.2153) time: 0.6350 [2021-03-26 19:30:02 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 690/1251] eta: 0:05:57 lr: 0.000781 loss: 3.7291 (3.5371) grad_norm: 1.1805 (1.2151) time: 0.6362 [2021-03-26 19:30:09 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 700/1251] eta: 0:05:50 lr: 0.000781 loss: 3.6159 (3.5345) grad_norm: 1.2180 (1.2167) time: 0.6371 [2021-03-26 19:30:15 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 710/1251] eta: 0:05:44 lr: 0.000781 loss: 3.6159 (3.5361) grad_norm: 1.2281 (1.2176) time: 0.6373 [2021-03-26 19:30:21 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 720/1251] eta: 0:05:38 lr: 0.000781 loss: 3.3320 (3.5342) grad_norm: 1.2281 (1.2195) time: 0.6281 [2021-03-26 19:30:28 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 730/1251] eta: 0:05:31 lr: 0.000781 loss: 3.7151 (3.5379) grad_norm: 1.2210 (1.2192) time: 0.6324 [2021-03-26 19:30:34 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 740/1251] eta: 0:05:25 lr: 0.000781 loss: 3.7737 (3.5363) grad_norm: 1.1001 (1.2169) time: 0.6361 [2021-03-26 19:30:40 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 750/1251] eta: 0:05:18 lr: 0.000781 loss: 3.7043 (3.5374) grad_norm: 1.0907 (1.2163) time: 0.6287 [2021-03-26 19:30:47 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 760/1251] eta: 0:05:12 lr: 0.000781 loss: 3.7043 (3.5388) grad_norm: 1.1547 (1.2159) time: 0.6280 [2021-03-26 19:30:53 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 770/1251] eta: 0:05:06 lr: 0.000781 loss: 3.7151 (3.5397) grad_norm: 1.1916 (1.2157) time: 0.6291 [2021-03-26 19:30:59 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 780/1251] eta: 0:04:59 lr: 0.000781 loss: 3.7630 (3.5395) grad_norm: 1.2177 (1.2175) time: 0.6274 [2021-03-26 19:31:05 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 790/1251] eta: 0:04:53 lr: 0.000781 loss: 3.6578 (3.5386) grad_norm: 1.2849 (1.2182) time: 0.6261 [2021-03-26 19:31:12 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 800/1251] eta: 0:04:46 lr: 0.000780 loss: 3.6578 (3.5386) grad_norm: 1.2029 (1.2186) time: 0.6289 [2021-03-26 19:31:18 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 810/1251] eta: 0:04:40 lr: 0.000780 loss: 3.5350 (3.5373) grad_norm: 1.1745 (1.2179) time: 0.6309 [2021-03-26 19:31:24 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 820/1251] eta: 0:04:34 lr: 0.000780 loss: 3.4437 (3.5368) grad_norm: 1.1692 (1.2177) time: 0.6354 [2021-03-26 19:31:31 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 830/1251] eta: 0:04:27 lr: 0.000780 loss: 3.6147 (3.5370) grad_norm: 1.2099 (1.2181) time: 0.6340 [2021-03-26 19:31:37 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 840/1251] eta: 0:04:21 lr: 0.000780 loss: 3.5975 (3.5366) grad_norm: 1.1500 (1.2170) time: 0.6324 [2021-03-26 19:31:43 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 850/1251] eta: 0:04:14 lr: 0.000780 loss: 3.4898 (3.5363) grad_norm: 1.1262 (1.2174) time: 0.6331 [2021-03-26 19:31:50 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 860/1251] eta: 0:04:08 lr: 0.000780 loss: 3.6499 (3.5388) grad_norm: 1.1971 (1.2170) time: 0.6298 [2021-03-26 19:31:56 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 870/1251] eta: 0:04:02 lr: 0.000780 loss: 3.7018 (3.5413) grad_norm: 1.1636 (1.2162) time: 0.6403 [2021-03-26 19:32:03 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 880/1251] eta: 0:03:55 lr: 0.000780 loss: 3.5553 (3.5383) grad_norm: 1.1659 (1.2167) time: 0.6439 [2021-03-26 19:32:09 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 890/1251] eta: 0:03:49 lr: 0.000780 loss: 3.5369 (3.5395) grad_norm: 1.2232 (1.2170) time: 0.6328 [2021-03-26 19:32:15 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 900/1251] eta: 0:03:43 lr: 0.000780 loss: 3.7191 (3.5399) grad_norm: 1.2232 (1.2182) time: 0.6283 [2021-03-26 19:32:22 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 910/1251] eta: 0:03:36 lr: 0.000780 loss: 3.5863 (3.5389) grad_norm: 1.2540 (1.2188) time: 0.6308 [2021-03-26 19:32:28 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 920/1251] eta: 0:03:30 lr: 0.000780 loss: 3.5355 (3.5392) grad_norm: 1.1809 (1.2182) time: 0.6364 [2021-03-26 19:32:34 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 930/1251] eta: 0:03:24 lr: 0.000780 loss: 3.5355 (3.5398) grad_norm: 1.1372 (1.2172) time: 0.6413 [2021-03-26 19:32:41 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 940/1251] eta: 0:03:17 lr: 0.000780 loss: 3.5774 (3.5410) grad_norm: 1.1469 (1.2174) time: 0.6408 [2021-03-26 19:32:47 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 950/1251] eta: 0:03:11 lr: 0.000780 loss: 3.4762 (3.5410) grad_norm: 1.1735 (1.2172) time: 0.6355 [2021-03-26 19:32:53 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 960/1251] eta: 0:03:04 lr: 0.000780 loss: 3.3139 (3.5379) grad_norm: 1.1914 (1.2174) time: 0.6260 [2021-03-26 19:33:00 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 970/1251] eta: 0:02:58 lr: 0.000780 loss: 3.4150 (3.5378) grad_norm: 1.2314 (1.2173) time: 0.6279 [2021-03-26 19:33:06 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 980/1251] eta: 0:02:52 lr: 0.000780 loss: 3.7466 (3.5390) grad_norm: 1.1827 (1.2172) time: 0.6345 [2021-03-26 19:33:12 swin_base_patch4_window7_224] INFO: Epoch: [93] [ 990/1251] eta: 0:02:45 lr: 0.000780 loss: 3.6381 (3.5381) grad_norm: 1.1493 (1.2162) time: 0.6329 [2021-03-26 19:33:19 swin_base_patch4_window7_224] INFO: Epoch: [93] [1000/1251] eta: 0:02:39 lr: 0.000780 loss: 3.5741 (3.5372) grad_norm: 1.0797 (1.2155) time: 0.6329 [2021-03-26 19:33:25 swin_base_patch4_window7_224] INFO: Epoch: [93] [1010/1251] eta: 0:02:33 lr: 0.000780 loss: 3.4597 (3.5350) grad_norm: 1.1597 (1.2151) time: 0.6302 [2021-03-26 19:33:31 swin_base_patch4_window7_224] INFO: Epoch: [93] [1020/1251] eta: 0:02:26 lr: 0.000780 loss: 3.5179 (3.5348) grad_norm: 1.2017 (1.2159) time: 0.6318 [2021-03-26 19:33:38 swin_base_patch4_window7_224] INFO: Epoch: [93] [1030/1251] eta: 0:02:20 lr: 0.000780 loss: 3.6172 (3.5328) grad_norm: 1.2537 (1.2168) time: 0.6333 [2021-03-26 19:33:44 swin_base_patch4_window7_224] INFO: Epoch: [93] [1040/1251] eta: 0:02:14 lr: 0.000780 loss: 3.6454 (3.5358) grad_norm: 1.2492 (1.2172) time: 0.6325 [2021-03-26 19:33:50 swin_base_patch4_window7_224] INFO: Epoch: [93] [1050/1251] eta: 0:02:07 lr: 0.000780 loss: 3.6747 (3.5343) grad_norm: 1.2415 (1.2175) time: 0.6291 [2021-03-26 19:33:56 swin_base_patch4_window7_224] INFO: Epoch: [93] [1060/1251] eta: 0:02:01 lr: 0.000780 loss: 3.6652 (3.5357) grad_norm: 1.2354 (1.2180) time: 0.6287 [2021-03-26 19:34:03 swin_base_patch4_window7_224] INFO: Epoch: [93] [1070/1251] eta: 0:01:54 lr: 0.000780 loss: 3.6652 (3.5349) grad_norm: 1.2465 (1.2184) time: 0.6298 [2021-03-26 19:34:09 swin_base_patch4_window7_224] INFO: Epoch: [93] [1080/1251] eta: 0:01:48 lr: 0.000780 loss: 3.6407 (3.5350) grad_norm: 1.2106 (1.2188) time: 0.6215 [2021-03-26 19:34:15 swin_base_patch4_window7_224] INFO: Epoch: [93] [1090/1251] eta: 0:01:42 lr: 0.000779 loss: 3.5633 (3.5345) grad_norm: 1.1782 (1.2183) time: 0.6234 [2021-03-26 19:34:22 swin_base_patch4_window7_224] INFO: Epoch: [93] [1100/1251] eta: 0:01:35 lr: 0.000779 loss: 3.5315 (3.5364) grad_norm: 1.1782 (1.2191) time: 0.6298 [2021-03-26 19:34:28 swin_base_patch4_window7_224] INFO: Epoch: [93] [1110/1251] eta: 0:01:29 lr: 0.000779 loss: 3.5970 (3.5353) grad_norm: 1.1370 (1.2184) time: 0.6249 [2021-03-26 19:34:34 swin_base_patch4_window7_224] INFO: Epoch: [93] [1120/1251] eta: 0:01:23 lr: 0.000779 loss: 3.4138 (3.5330) grad_norm: 1.1630 (1.2194) time: 0.6265 [2021-03-26 19:34:40 swin_base_patch4_window7_224] INFO: Epoch: [93] [1130/1251] eta: 0:01:16 lr: 0.000779 loss: 3.6350 (3.5344) grad_norm: 1.2132 (1.2197) time: 0.6302 [2021-03-26 19:34:47 swin_base_patch4_window7_224] INFO: Epoch: [93] [1140/1251] eta: 0:01:10 lr: 0.000779 loss: 3.5100 (3.5312) grad_norm: 1.1701 (1.2190) time: 0.6281 [2021-03-26 19:34:53 swin_base_patch4_window7_224] INFO: Epoch: [93] [1150/1251] eta: 0:01:04 lr: 0.000779 loss: 3.4019 (3.5310) grad_norm: 1.1302 (1.2188) time: 0.6308 [2021-03-26 19:34:59 swin_base_patch4_window7_224] INFO: Epoch: [93] [1160/1251] eta: 0:00:57 lr: 0.000779 loss: 3.5659 (3.5326) grad_norm: 1.2076 (1.2200) time: 0.6343 [2021-03-26 19:35:06 swin_base_patch4_window7_224] INFO: Epoch: [93] [1170/1251] eta: 0:00:51 lr: 0.000779 loss: 3.7837 (3.5354) grad_norm: 1.2469 (1.2202) time: 0.6351 [2021-03-26 19:35:12 swin_base_patch4_window7_224] INFO: Epoch: [93] [1180/1251] eta: 0:00:45 lr: 0.000779 loss: 3.7922 (3.5349) grad_norm: 1.1559 (1.2195) time: 0.6252 [2021-03-26 19:35:18 swin_base_patch4_window7_224] INFO: Epoch: [93] [1190/1251] eta: 0:00:38 lr: 0.000779 loss: 3.3346 (3.5341) grad_norm: 1.1372 (1.2189) time: 0.6272 [2021-03-26 19:35:24 swin_base_patch4_window7_224] INFO: Epoch: [93] [1200/1251] eta: 0:00:32 lr: 0.000779 loss: 3.3604 (3.5329) grad_norm: 1.1479 (1.2189) time: 0.6320 [2021-03-26 19:35:31 swin_base_patch4_window7_224] INFO: Epoch: [93] [1210/1251] eta: 0:00:26 lr: 0.000779 loss: 3.4987 (3.5335) grad_norm: 1.2545 (1.2189) time: 0.6296 [2021-03-26 19:35:37 swin_base_patch4_window7_224] INFO: Epoch: [93] [1220/1251] eta: 0:00:19 lr: 0.000779 loss: 3.7645 (3.5346) grad_norm: 1.2498 (1.2191) time: 0.6322 [2021-03-26 19:35:43 swin_base_patch4_window7_224] INFO: Epoch: [93] [1230/1251] eta: 0:00:13 lr: 0.000779 loss: 3.6632 (3.5348) grad_norm: 1.2598 (1.2198) time: 0.6283 [2021-03-26 19:35:50 swin_base_patch4_window7_224] INFO: Epoch: [93] [1240/1251] eta: 0:00:06 lr: 0.000779 loss: 3.4695 (3.5358) grad_norm: 1.2411 (1.2200) time: 0.6228 [2021-03-26 19:35:56 swin_base_patch4_window7_224] INFO: Epoch: [93] [1250/1251] eta: 0:00:00 lr: 0.000779 loss: 3.5687 (3.5358) grad_norm: 1.2411 (1.2206) time: 0.6190 [2021-03-26 19:36:03 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:57 loss: 1.0602 (1.0602) acc1: 79.6875 (79.6875) acc5: 90.6250 (90.6250) [2021-03-26 19:36:06 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9778 (1.0379) acc1: 78.1250 (76.2784) acc5: 95.3125 (94.0341) [2021-03-26 19:36:08 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0685 (1.0667) acc1: 73.4375 (74.6280) acc5: 95.3125 (94.1220) [2021-03-26 19:36:11 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0680 (1.0307) acc1: 76.5625 (75.6552) acc5: 93.7500 (94.1028) [2021-03-26 19:36:12 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9416 (1.0164) acc1: 76.5625 (76.0671) acc5: 93.7500 (94.0549) [2021-03-26 19:36:14 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9901 (1.0281) acc1: 76.5625 (75.7440) acc5: 93.7500 (94.0160) [2021-03-26 19:36:19 swin_base_patch4_window7_224] INFO: * Acc@1 76.208 Acc@5 93.602 loss 1.014 [2021-03-26 19:36:19 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.2% [2021-03-26 19:36:19 swin_base_patch4_window7_224] INFO: Max accuracy: 76.23% [2021-03-26 19:36:24 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 0/1251] eta: 1:37:14 lr: 0.000779 loss: 3.4218 (3.4218) grad_norm: 1.7524 (1.7524) time: 4.6640 [2021-03-26 19:36:30 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 10/1251] eta: 0:20:39 lr: 0.000779 loss: 3.6395 (3.6522) grad_norm: 1.1786 (1.2559) time: 0.9988 [2021-03-26 19:36:36 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 20/1251] eta: 0:16:55 lr: 0.000779 loss: 3.6137 (3.5112) grad_norm: 1.1786 (1.2339) time: 0.6327 [2021-03-26 19:36:43 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 30/1251] eta: 0:15:38 lr: 0.000779 loss: 3.4587 (3.5130) grad_norm: 1.2055 (1.2369) time: 0.6421 [2021-03-26 19:36:49 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 40/1251] eta: 0:14:51 lr: 0.000779 loss: 3.3213 (3.4858) grad_norm: 1.1399 (1.2120) time: 0.6438 [2021-03-26 19:36:56 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 50/1251] eta: 0:14:19 lr: 0.000779 loss: 3.5957 (3.5032) grad_norm: 1.1392 (1.2033) time: 0.6332 [2021-03-26 19:37:02 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 60/1251] eta: 0:13:57 lr: 0.000779 loss: 3.6069 (3.4739) grad_norm: 1.2201 (1.2310) time: 0.6356 [2021-03-26 19:37:08 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 70/1251] eta: 0:13:41 lr: 0.000779 loss: 3.4247 (3.4633) grad_norm: 1.2858 (1.2298) time: 0.6446 [2021-03-26 19:37:15 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 80/1251] eta: 0:13:24 lr: 0.000779 loss: 3.5900 (3.4722) grad_norm: 1.1594 (1.2313) time: 0.6359 [2021-03-26 19:37:21 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 90/1251] eta: 0:13:09 lr: 0.000779 loss: 3.7229 (3.4839) grad_norm: 1.2232 (1.2398) time: 0.6261 [2021-03-26 19:37:27 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 100/1251] eta: 0:12:58 lr: 0.000779 loss: 3.7253 (3.4816) grad_norm: 1.2527 (1.2442) time: 0.6322 [2021-03-26 19:37:34 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 110/1251] eta: 0:12:46 lr: 0.000779 loss: 3.4920 (3.4670) grad_norm: 1.1645 (1.2408) time: 0.6351 [2021-03-26 19:37:40 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 120/1251] eta: 0:12:36 lr: 0.000779 loss: 3.2890 (3.4579) grad_norm: 1.1979 (1.2410) time: 0.6315 [2021-03-26 19:37:46 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 130/1251] eta: 0:12:26 lr: 0.000778 loss: 3.7813 (3.4938) grad_norm: 1.1943 (1.2372) time: 0.6332 [2021-03-26 19:37:53 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 140/1251] eta: 0:12:16 lr: 0.000778 loss: 3.9068 (3.5101) grad_norm: 1.1566 (1.2309) time: 0.6315 [2021-03-26 19:37:59 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 150/1251] eta: 0:12:07 lr: 0.000778 loss: 3.7556 (3.5151) grad_norm: 1.1516 (1.2304) time: 0.6256 [2021-03-26 19:38:05 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 160/1251] eta: 0:11:59 lr: 0.000778 loss: 3.6580 (3.5188) grad_norm: 1.1516 (1.2283) time: 0.6330 [2021-03-26 19:38:11 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 170/1251] eta: 0:11:50 lr: 0.000778 loss: 3.6021 (3.5277) grad_norm: 1.1655 (1.2317) time: 0.6305 [2021-03-26 19:38:18 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 180/1251] eta: 0:11:42 lr: 0.000778 loss: 3.5312 (3.5209) grad_norm: 1.2031 (1.2274) time: 0.6249 [2021-03-26 19:38:24 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 190/1251] eta: 0:11:34 lr: 0.000778 loss: 3.5463 (3.5229) grad_norm: 1.2178 (1.2301) time: 0.6288 [2021-03-26 19:38:30 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 200/1251] eta: 0:11:26 lr: 0.000778 loss: 3.5463 (3.5110) grad_norm: 1.1730 (1.2256) time: 0.6273 [2021-03-26 19:38:37 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 210/1251] eta: 0:11:18 lr: 0.000778 loss: 3.5999 (3.5174) grad_norm: 1.1730 (1.2298) time: 0.6236 [2021-03-26 19:38:43 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 220/1251] eta: 0:11:10 lr: 0.000778 loss: 3.6743 (3.5286) grad_norm: 1.1921 (1.2283) time: 0.6238 [2021-03-26 19:38:49 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 230/1251] eta: 0:11:03 lr: 0.000778 loss: 3.4511 (3.5100) grad_norm: 1.1921 (1.2353) time: 0.6305 [2021-03-26 19:38:55 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 240/1251] eta: 0:10:55 lr: 0.000778 loss: 3.2544 (3.5059) grad_norm: 1.2425 (1.2359) time: 0.6332 [2021-03-26 19:39:02 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 250/1251] eta: 0:10:48 lr: 0.000778 loss: 3.4867 (3.5060) grad_norm: 1.1170 (inf) time: 0.6334 [2021-03-26 19:39:08 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 260/1251] eta: 0:10:42 lr: 0.000778 loss: 3.6275 (3.5092) grad_norm: 1.1500 (inf) time: 0.6395 [2021-03-26 19:39:15 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 270/1251] eta: 0:10:35 lr: 0.000778 loss: 3.5821 (3.4952) grad_norm: 1.2038 (inf) time: 0.6360 [2021-03-26 19:39:21 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 280/1251] eta: 0:10:28 lr: 0.000778 loss: 3.7790 (3.5130) grad_norm: 1.2289 (inf) time: 0.6310 [2021-03-26 19:39:27 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 290/1251] eta: 0:10:21 lr: 0.000778 loss: 3.8591 (3.5098) grad_norm: 1.1625 (inf) time: 0.6304 [2021-03-26 19:39:33 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 300/1251] eta: 0:10:14 lr: 0.000778 loss: 3.7876 (3.5182) grad_norm: 1.1524 (inf) time: 0.6288 [2021-03-26 19:39:40 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 310/1251] eta: 0:10:07 lr: 0.000778 loss: 3.6446 (3.5155) grad_norm: 1.2155 (inf) time: 0.6303 [2021-03-26 19:39:46 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 320/1251] eta: 0:10:00 lr: 0.000778 loss: 3.4772 (3.5191) grad_norm: 1.1774 (inf) time: 0.6334 [2021-03-26 19:39:52 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 330/1251] eta: 0:09:53 lr: 0.000778 loss: 3.8744 (3.5260) grad_norm: 1.1381 (inf) time: 0.6342 [2021-03-26 19:39:59 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 340/1251] eta: 0:09:46 lr: 0.000778 loss: 3.6565 (3.5279) grad_norm: 1.1317 (inf) time: 0.6278 [2021-03-26 19:40:05 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 350/1251] eta: 0:09:39 lr: 0.000778 loss: 3.6565 (3.5282) grad_norm: 1.1317 (inf) time: 0.6304 [2021-03-26 19:40:11 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 360/1251] eta: 0:09:33 lr: 0.000778 loss: 3.7404 (3.5301) grad_norm: 1.1646 (inf) time: 0.6296 [2021-03-26 19:40:18 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 370/1251] eta: 0:09:26 lr: 0.000778 loss: 3.7404 (3.5331) grad_norm: 1.2187 (inf) time: 0.6267 [2021-03-26 19:40:24 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 380/1251] eta: 0:09:19 lr: 0.000778 loss: 3.7813 (3.5397) grad_norm: 1.1692 (inf) time: 0.6293 [2021-03-26 19:40:30 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 390/1251] eta: 0:09:12 lr: 0.000778 loss: 3.5770 (3.5378) grad_norm: 1.2004 (inf) time: 0.6264 [2021-03-26 19:40:36 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 400/1251] eta: 0:09:06 lr: 0.000778 loss: 3.5875 (3.5435) grad_norm: 1.1792 (inf) time: 0.6287 [2021-03-26 19:40:43 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 410/1251] eta: 0:08:59 lr: 0.000778 loss: 3.4972 (3.5339) grad_norm: 1.2111 (inf) time: 0.6293 [2021-03-26 19:40:49 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 420/1251] eta: 0:08:52 lr: 0.000777 loss: 3.1270 (3.5273) grad_norm: 1.2152 (inf) time: 0.6257 [2021-03-26 19:40:55 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 430/1251] eta: 0:08:46 lr: 0.000777 loss: 3.3075 (3.5292) grad_norm: 1.2019 (inf) time: 0.6274 [2021-03-26 19:41:02 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 440/1251] eta: 0:08:39 lr: 0.000777 loss: 3.7663 (3.5346) grad_norm: 1.1781 (inf) time: 0.6353 [2021-03-26 19:41:08 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 450/1251] eta: 0:08:32 lr: 0.000777 loss: 3.7191 (3.5324) grad_norm: 1.1955 (inf) time: 0.6341 [2021-03-26 19:41:14 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 460/1251] eta: 0:08:26 lr: 0.000777 loss: 3.5452 (3.5287) grad_norm: 1.2912 (inf) time: 0.6272 [2021-03-26 19:41:21 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 470/1251] eta: 0:08:19 lr: 0.000777 loss: 3.4419 (3.5236) grad_norm: 1.1796 (inf) time: 0.6296 [2021-03-26 19:41:27 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 480/1251] eta: 0:08:13 lr: 0.000777 loss: 3.1346 (3.5170) grad_norm: 1.1796 (inf) time: 0.6295 [2021-03-26 19:41:33 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 490/1251] eta: 0:08:06 lr: 0.000777 loss: 3.1384 (3.5096) grad_norm: 1.2520 (inf) time: 0.6264 [2021-03-26 19:41:39 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 500/1251] eta: 0:07:59 lr: 0.000777 loss: 3.4583 (3.5136) grad_norm: 1.1823 (inf) time: 0.6241 [2021-03-26 19:41:46 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 510/1251] eta: 0:07:53 lr: 0.000777 loss: 3.8474 (3.5177) grad_norm: 1.1201 (inf) time: 0.6300 [2021-03-26 19:41:52 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 520/1251] eta: 0:07:46 lr: 0.000777 loss: 3.7628 (3.5203) grad_norm: 1.1653 (inf) time: 0.6314 [2021-03-26 19:41:58 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 530/1251] eta: 0:07:40 lr: 0.000777 loss: 3.6198 (3.5183) grad_norm: 1.1289 (inf) time: 0.6290 [2021-03-26 19:42:04 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 540/1251] eta: 0:07:33 lr: 0.000777 loss: 3.7396 (3.5225) grad_norm: 1.0988 (inf) time: 0.6277 [2021-03-26 19:42:11 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 550/1251] eta: 0:07:27 lr: 0.000777 loss: 3.4545 (3.5181) grad_norm: 1.1838 (inf) time: 0.6385 [2021-03-26 19:42:17 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 560/1251] eta: 0:07:21 lr: 0.000777 loss: 3.4487 (3.5197) grad_norm: 1.2064 (inf) time: 0.6450 [2021-03-26 19:42:24 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 570/1251] eta: 0:07:14 lr: 0.000777 loss: 3.5619 (3.5169) grad_norm: 1.2000 (inf) time: 0.6355 [2021-03-26 19:42:30 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 580/1251] eta: 0:07:08 lr: 0.000777 loss: 3.5382 (3.5165) grad_norm: 1.1703 (inf) time: 0.6293 [2021-03-26 19:42:36 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 590/1251] eta: 0:07:01 lr: 0.000777 loss: 3.4928 (3.5130) grad_norm: 1.2536 (inf) time: 0.6344 [2021-03-26 19:42:43 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 600/1251] eta: 0:06:55 lr: 0.000777 loss: 3.4928 (3.5139) grad_norm: 1.2385 (inf) time: 0.6391 [2021-03-26 19:42:49 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 610/1251] eta: 0:06:49 lr: 0.000777 loss: 3.7625 (3.5156) grad_norm: 1.1864 (inf) time: 0.6309 [2021-03-26 19:42:55 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 620/1251] eta: 0:06:42 lr: 0.000777 loss: 3.6569 (3.5162) grad_norm: 1.1631 (inf) time: 0.6266 [2021-03-26 19:43:02 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 630/1251] eta: 0:06:36 lr: 0.000777 loss: 3.5677 (3.5138) grad_norm: 1.1831 (inf) time: 0.6260 [2021-03-26 19:43:08 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 640/1251] eta: 0:06:29 lr: 0.000777 loss: 3.2025 (3.5114) grad_norm: 1.1831 (inf) time: 0.6327 [2021-03-26 19:43:14 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 650/1251] eta: 0:06:23 lr: 0.000777 loss: 3.7045 (3.5121) grad_norm: 1.2173 (inf) time: 0.6278 [2021-03-26 19:43:21 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 660/1251] eta: 0:06:16 lr: 0.000777 loss: 3.7139 (3.5131) grad_norm: 1.2423 (inf) time: 0.6278 [2021-03-26 19:43:27 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 670/1251] eta: 0:06:10 lr: 0.000777 loss: 3.7215 (3.5176) grad_norm: 1.2012 (inf) time: 0.6343 [2021-03-26 19:43:33 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 680/1251] eta: 0:06:03 lr: 0.000777 loss: 3.6596 (3.5156) grad_norm: 1.1623 (inf) time: 0.6364 [2021-03-26 19:43:40 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 690/1251] eta: 0:05:57 lr: 0.000777 loss: 3.5321 (3.5224) grad_norm: 1.2182 (inf) time: 0.6364 [2021-03-26 19:43:46 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 700/1251] eta: 0:05:51 lr: 0.000777 loss: 3.8185 (3.5253) grad_norm: 1.2352 (inf) time: 0.6312 [2021-03-26 19:43:52 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 710/1251] eta: 0:05:44 lr: 0.000776 loss: 3.8252 (3.5275) grad_norm: 1.3227 (inf) time: 0.6301 [2021-03-26 19:43:58 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 720/1251] eta: 0:05:38 lr: 0.000776 loss: 3.8208 (3.5300) grad_norm: 1.2647 (inf) time: 0.6277 [2021-03-26 19:44:05 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 730/1251] eta: 0:05:31 lr: 0.000776 loss: 3.6698 (3.5330) grad_norm: 1.1703 (inf) time: 0.6327 [2021-03-26 19:44:11 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 740/1251] eta: 0:05:25 lr: 0.000776 loss: 3.6523 (3.5316) grad_norm: 1.1617 (inf) time: 0.6378 [2021-03-26 19:44:18 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 750/1251] eta: 0:05:19 lr: 0.000776 loss: 3.7021 (3.5336) grad_norm: 1.2396 (inf) time: 0.6374 [2021-03-26 19:44:24 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 760/1251] eta: 0:05:12 lr: 0.000776 loss: 3.7525 (3.5339) grad_norm: 1.3376 (inf) time: 0.6397 [2021-03-26 19:44:30 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 770/1251] eta: 0:05:06 lr: 0.000776 loss: 3.5499 (3.5335) grad_norm: 1.2270 (inf) time: 0.6414 [2021-03-26 19:44:37 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 780/1251] eta: 0:05:00 lr: 0.000776 loss: 3.6052 (3.5345) grad_norm: 1.2153 (inf) time: 0.6395 [2021-03-26 19:44:43 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 790/1251] eta: 0:04:53 lr: 0.000776 loss: 3.7631 (3.5345) grad_norm: 1.2285 (inf) time: 0.6345 [2021-03-26 19:44:49 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 800/1251] eta: 0:04:47 lr: 0.000776 loss: 3.7140 (3.5338) grad_norm: 1.2285 (inf) time: 0.6310 [2021-03-26 19:44:56 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 810/1251] eta: 0:04:40 lr: 0.000776 loss: 3.6946 (3.5331) grad_norm: 1.1303 (inf) time: 0.6286 [2021-03-26 19:45:02 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 820/1251] eta: 0:04:34 lr: 0.000776 loss: 3.6036 (3.5342) grad_norm: 1.1287 (inf) time: 0.6255 [2021-03-26 19:45:08 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 830/1251] eta: 0:04:27 lr: 0.000776 loss: 3.5975 (3.5320) grad_norm: 1.1812 (inf) time: 0.6247 [2021-03-26 19:45:15 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 840/1251] eta: 0:04:21 lr: 0.000776 loss: 3.3030 (3.5293) grad_norm: 1.1551 (inf) time: 0.6296 [2021-03-26 19:45:21 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 850/1251] eta: 0:04:15 lr: 0.000776 loss: 3.4820 (3.5270) grad_norm: 1.1019 (inf) time: 0.6330 [2021-03-26 19:45:27 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 860/1251] eta: 0:04:08 lr: 0.000776 loss: 3.6200 (3.5293) grad_norm: 1.2084 (inf) time: 0.6336 [2021-03-26 19:45:33 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 870/1251] eta: 0:04:02 lr: 0.000776 loss: 3.6920 (3.5289) grad_norm: 1.1614 (inf) time: 0.6322 [2021-03-26 19:45:40 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 880/1251] eta: 0:03:56 lr: 0.000776 loss: 3.7023 (3.5318) grad_norm: 1.1428 (inf) time: 0.6266 [2021-03-26 19:45:46 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 890/1251] eta: 0:03:49 lr: 0.000776 loss: 3.5608 (3.5286) grad_norm: 1.2251 (inf) time: 0.6268 [2021-03-26 19:45:52 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 900/1251] eta: 0:03:43 lr: 0.000776 loss: 3.3663 (3.5313) grad_norm: 1.2255 (inf) time: 0.6366 [2021-03-26 19:45:59 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 910/1251] eta: 0:03:36 lr: 0.000776 loss: 3.7601 (3.5296) grad_norm: 1.1815 (inf) time: 0.6356 [2021-03-26 19:46:05 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 920/1251] eta: 0:03:30 lr: 0.000776 loss: 3.3359 (3.5283) grad_norm: 1.1927 (inf) time: 0.6296 [2021-03-26 19:46:11 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 930/1251] eta: 0:03:24 lr: 0.000776 loss: 3.3359 (3.5266) grad_norm: 1.2206 (inf) time: 0.6310 [2021-03-26 19:46:18 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 940/1251] eta: 0:03:17 lr: 0.000776 loss: 3.5051 (3.5272) grad_norm: 1.2343 (inf) time: 0.6309 [2021-03-26 19:46:24 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 950/1251] eta: 0:03:11 lr: 0.000776 loss: 3.7092 (3.5262) grad_norm: 1.1708 (inf) time: 0.6320 [2021-03-26 19:46:30 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 960/1251] eta: 0:03:05 lr: 0.000776 loss: 3.7092 (3.5278) grad_norm: 1.1594 (inf) time: 0.6267 [2021-03-26 19:46:37 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 970/1251] eta: 0:02:58 lr: 0.000776 loss: 3.3796 (3.5258) grad_norm: 1.2459 (inf) time: 0.6313 [2021-03-26 19:46:43 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 980/1251] eta: 0:02:52 lr: 0.000776 loss: 3.4238 (3.5273) grad_norm: 1.2714 (inf) time: 0.6351 [2021-03-26 19:46:49 swin_base_patch4_window7_224] INFO: Epoch: [94] [ 990/1251] eta: 0:02:45 lr: 0.000776 loss: 3.5854 (3.5274) grad_norm: 1.2018 (inf) time: 0.6290 [2021-03-26 19:46:56 swin_base_patch4_window7_224] INFO: Epoch: [94] [1000/1251] eta: 0:02:39 lr: 0.000775 loss: 3.7403 (3.5289) grad_norm: 1.1900 (inf) time: 0.6355 [2021-03-26 19:47:02 swin_base_patch4_window7_224] INFO: Epoch: [94] [1010/1251] eta: 0:02:33 lr: 0.000775 loss: 3.5864 (3.5287) grad_norm: 1.1540 (inf) time: 0.6395 [2021-03-26 19:47:08 swin_base_patch4_window7_224] INFO: Epoch: [94] [1020/1251] eta: 0:02:26 lr: 0.000775 loss: 3.2975 (3.5264) grad_norm: 1.1358 (inf) time: 0.6389 [2021-03-26 19:47:15 swin_base_patch4_window7_224] INFO: Epoch: [94] [1030/1251] eta: 0:02:20 lr: 0.000775 loss: 3.1067 (3.5254) grad_norm: 1.1358 (inf) time: 0.6332 [2021-03-26 19:47:21 swin_base_patch4_window7_224] INFO: Epoch: [94] [1040/1251] eta: 0:02:14 lr: 0.000775 loss: 3.6037 (3.5249) grad_norm: 1.1622 (inf) time: 0.6269 [2021-03-26 19:47:27 swin_base_patch4_window7_224] INFO: Epoch: [94] [1050/1251] eta: 0:02:07 lr: 0.000775 loss: 3.7580 (3.5276) grad_norm: 1.1228 (inf) time: 0.6313 [2021-03-26 19:47:34 swin_base_patch4_window7_224] INFO: Epoch: [94] [1060/1251] eta: 0:02:01 lr: 0.000775 loss: 3.8035 (3.5290) grad_norm: 1.1881 (inf) time: 0.6358 [2021-03-26 19:47:40 swin_base_patch4_window7_224] INFO: Epoch: [94] [1070/1251] eta: 0:01:55 lr: 0.000775 loss: 3.4848 (3.5277) grad_norm: 1.2455 (inf) time: 0.6305 [2021-03-26 19:47:46 swin_base_patch4_window7_224] INFO: Epoch: [94] [1080/1251] eta: 0:01:48 lr: 0.000775 loss: 3.4506 (3.5279) grad_norm: 1.1945 (inf) time: 0.6238 [2021-03-26 19:47:53 swin_base_patch4_window7_224] INFO: Epoch: [94] [1090/1251] eta: 0:01:42 lr: 0.000775 loss: 3.4781 (3.5263) grad_norm: 1.2060 (inf) time: 0.6304 [2021-03-26 19:47:59 swin_base_patch4_window7_224] INFO: Epoch: [94] [1100/1251] eta: 0:01:35 lr: 0.000775 loss: 3.4781 (3.5263) grad_norm: 1.1859 (inf) time: 0.6307 [2021-03-26 19:48:05 swin_base_patch4_window7_224] INFO: Epoch: [94] [1110/1251] eta: 0:01:29 lr: 0.000775 loss: 3.6016 (3.5263) grad_norm: 1.1863 (inf) time: 0.6302 [2021-03-26 19:48:11 swin_base_patch4_window7_224] INFO: Epoch: [94] [1120/1251] eta: 0:01:23 lr: 0.000775 loss: 3.5834 (3.5249) grad_norm: 1.1891 (inf) time: 0.6291 [2021-03-26 19:48:18 swin_base_patch4_window7_224] INFO: Epoch: [94] [1130/1251] eta: 0:01:16 lr: 0.000775 loss: 3.6486 (3.5258) grad_norm: 1.1056 (inf) time: 0.6266 [2021-03-26 19:48:24 swin_base_patch4_window7_224] INFO: Epoch: [94] [1140/1251] eta: 0:01:10 lr: 0.000775 loss: 3.6359 (3.5264) grad_norm: 1.1536 (inf) time: 0.6292 [2021-03-26 19:48:30 swin_base_patch4_window7_224] INFO: Epoch: [94] [1150/1251] eta: 0:01:04 lr: 0.000775 loss: 3.4006 (3.5246) grad_norm: 1.1710 (inf) time: 0.6308 [2021-03-26 19:48:37 swin_base_patch4_window7_224] INFO: Epoch: [94] [1160/1251] eta: 0:00:57 lr: 0.000775 loss: 3.4353 (3.5253) grad_norm: 1.1674 (inf) time: 0.6354 [2021-03-26 19:48:43 swin_base_patch4_window7_224] INFO: Epoch: [94] [1170/1251] eta: 0:00:51 lr: 0.000775 loss: 3.3130 (3.5227) grad_norm: 1.2715 (inf) time: 0.6332 [2021-03-26 19:48:49 swin_base_patch4_window7_224] INFO: Epoch: [94] [1180/1251] eta: 0:00:45 lr: 0.000775 loss: 3.3130 (3.5226) grad_norm: 1.2839 (inf) time: 0.6288 [2021-03-26 19:48:56 swin_base_patch4_window7_224] INFO: Epoch: [94] [1190/1251] eta: 0:00:38 lr: 0.000775 loss: 3.4271 (3.5200) grad_norm: 1.1757 (inf) time: 0.6334 [2021-03-26 19:49:02 swin_base_patch4_window7_224] INFO: Epoch: [94] [1200/1251] eta: 0:00:32 lr: 0.000775 loss: 3.2548 (3.5204) grad_norm: 1.1995 (inf) time: 0.6355 [2021-03-26 19:49:08 swin_base_patch4_window7_224] INFO: Epoch: [94] [1210/1251] eta: 0:00:26 lr: 0.000775 loss: 3.7123 (3.5215) grad_norm: 1.1995 (inf) time: 0.6320 [2021-03-26 19:49:15 swin_base_patch4_window7_224] INFO: Epoch: [94] [1220/1251] eta: 0:00:19 lr: 0.000775 loss: 3.7043 (3.5194) grad_norm: 1.1638 (inf) time: 0.6388 [2021-03-26 19:49:21 swin_base_patch4_window7_224] INFO: Epoch: [94] [1230/1251] eta: 0:00:13 lr: 0.000775 loss: 3.5225 (3.5185) grad_norm: 1.1400 (inf) time: 0.6354 [2021-03-26 19:49:27 swin_base_patch4_window7_224] INFO: Epoch: [94] [1240/1251] eta: 0:00:06 lr: 0.000775 loss: 3.5256 (3.5188) grad_norm: 1.1339 (inf) time: 0.6327 [2021-03-26 19:49:34 swin_base_patch4_window7_224] INFO: Epoch: [94] [1250/1251] eta: 0:00:00 lr: 0.000775 loss: 3.5867 (3.5193) grad_norm: 1.1339 (inf) time: 0.6269 [2021-03-26 19:49:39 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:52 loss: 1.3136 (1.3136) acc1: 71.8750 (71.8750) acc5: 85.9375 (85.9375) [2021-03-26 19:49:42 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.9040 (0.9736) acc1: 78.1250 (78.2670) acc5: 93.7500 (93.3239) [2021-03-26 19:49:45 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.9260 (0.9826) acc1: 78.1250 (77.4554) acc5: 93.7500 (93.5268) [2021-03-26 19:49:47 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9927 (1.0313) acc1: 76.5625 (75.6048) acc5: 93.7500 (93.1452) [2021-03-26 19:49:49 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1144 (1.0388) acc1: 73.4375 (75.6098) acc5: 92.1875 (93.2927) [2021-03-26 19:49:50 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0120 (1.0214) acc1: 76.5625 (75.8400) acc5: 95.3125 (93.3760) [2021-03-26 19:49:55 swin_base_patch4_window7_224] INFO: * Acc@1 76.330 Acc@5 93.540 loss 1.009 [2021-03-26 19:49:55 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.3% [2021-03-26 19:49:55 swin_base_patch4_window7_224] INFO: Max accuracy: 76.33% [2021-03-26 19:49:59 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 0/1251] eta: 1:29:20 lr: 0.000775 loss: 3.6493 (3.6493) grad_norm: 0.9262 (0.9262) time: 4.2850 [2021-03-26 19:50:05 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 10/1251] eta: 0:19:59 lr: 0.000775 loss: 3.2474 (3.2475) grad_norm: 1.1072 (1.1292) time: 0.9665 [2021-03-26 19:50:12 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 20/1251] eta: 0:16:28 lr: 0.000775 loss: 3.2474 (3.3414) grad_norm: 1.1204 (1.1355) time: 0.6288 [2021-03-26 19:50:18 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 30/1251] eta: 0:15:10 lr: 0.000774 loss: 3.3690 (3.3509) grad_norm: 1.1553 (1.1490) time: 0.6244 [2021-03-26 19:50:24 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 40/1251] eta: 0:14:28 lr: 0.000774 loss: 3.5862 (3.3990) grad_norm: 1.1553 (1.1461) time: 0.6268 [2021-03-26 19:50:30 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 50/1251] eta: 0:14:01 lr: 0.000774 loss: 3.6331 (3.4476) grad_norm: 1.1512 (1.1551) time: 0.6309 [2021-03-26 19:50:37 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 60/1251] eta: 0:13:39 lr: 0.000774 loss: 3.7088 (3.4689) grad_norm: 1.1742 (1.1565) time: 0.6292 [2021-03-26 19:50:43 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 70/1251] eta: 0:13:23 lr: 0.000774 loss: 3.6001 (3.4646) grad_norm: 1.1742 (1.1581) time: 0.6271 [2021-03-26 19:50:49 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 80/1251] eta: 0:13:07 lr: 0.000774 loss: 3.5308 (3.4665) grad_norm: 1.0813 (1.1488) time: 0.6258 [2021-03-26 19:50:56 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 90/1251] eta: 0:12:55 lr: 0.000774 loss: 3.8361 (3.5168) grad_norm: 1.0926 (1.1579) time: 0.6262 [2021-03-26 19:51:02 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 100/1251] eta: 0:12:44 lr: 0.000774 loss: 3.8583 (3.5244) grad_norm: 1.1732 (1.1667) time: 0.6299 [2021-03-26 19:51:08 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 110/1251] eta: 0:12:33 lr: 0.000774 loss: 3.8101 (3.5435) grad_norm: 1.1428 (1.1673) time: 0.6271 [2021-03-26 19:51:14 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 120/1251] eta: 0:12:23 lr: 0.000774 loss: 3.8645 (3.5447) grad_norm: 1.1450 (1.1732) time: 0.6236 [2021-03-26 19:51:21 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 130/1251] eta: 0:12:15 lr: 0.000774 loss: 3.5042 (3.5270) grad_norm: 1.1098 (1.1717) time: 0.6275 [2021-03-26 19:51:27 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 140/1251] eta: 0:12:06 lr: 0.000774 loss: 3.4604 (3.5158) grad_norm: 1.1027 (1.1691) time: 0.6346 [2021-03-26 19:51:33 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 150/1251] eta: 0:11:58 lr: 0.000774 loss: 3.4769 (3.5290) grad_norm: 1.1496 (1.1750) time: 0.6314 [2021-03-26 19:51:40 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 160/1251] eta: 0:11:51 lr: 0.000774 loss: 3.4615 (3.5146) grad_norm: 1.2298 (1.1880) time: 0.6392 [2021-03-26 19:51:46 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 170/1251] eta: 0:11:43 lr: 0.000774 loss: 3.4456 (3.5110) grad_norm: 1.2289 (1.1865) time: 0.6378 [2021-03-26 19:51:52 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 180/1251] eta: 0:11:35 lr: 0.000774 loss: 3.5400 (3.5200) grad_norm: 1.1999 (1.1950) time: 0.6281 [2021-03-26 19:51:59 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 190/1251] eta: 0:11:28 lr: 0.000774 loss: 3.5689 (3.5213) grad_norm: 1.2816 (1.2054) time: 0.6347 [2021-03-26 19:52:05 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 200/1251] eta: 0:11:20 lr: 0.000774 loss: 3.5689 (3.5179) grad_norm: 1.2305 (1.2042) time: 0.6293 [2021-03-26 19:52:11 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 210/1251] eta: 0:11:13 lr: 0.000774 loss: 3.3919 (3.5206) grad_norm: 1.1633 (1.2042) time: 0.6296 [2021-03-26 19:52:18 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 220/1251] eta: 0:11:06 lr: 0.000774 loss: 3.5683 (3.5306) grad_norm: 1.1550 (1.2067) time: 0.6364 [2021-03-26 19:52:24 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 230/1251] eta: 0:10:59 lr: 0.000774 loss: 3.5683 (3.5286) grad_norm: 1.1957 (1.2076) time: 0.6339 [2021-03-26 19:52:30 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 240/1251] eta: 0:10:52 lr: 0.000774 loss: 3.5868 (3.5348) grad_norm: 1.2423 (1.2093) time: 0.6370 [2021-03-26 19:52:37 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 250/1251] eta: 0:10:45 lr: 0.000774 loss: 3.6180 (3.5382) grad_norm: 1.1463 (1.2054) time: 0.6344 [2021-03-26 19:52:43 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 260/1251] eta: 0:10:38 lr: 0.000774 loss: 3.4211 (3.5281) grad_norm: 1.1218 (1.2085) time: 0.6292 [2021-03-26 19:52:49 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 270/1251] eta: 0:10:31 lr: 0.000774 loss: 3.3905 (3.5322) grad_norm: 1.2611 (1.2120) time: 0.6300 [2021-03-26 19:52:56 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 280/1251] eta: 0:10:24 lr: 0.000774 loss: 3.8187 (3.5356) grad_norm: 1.2434 (1.2135) time: 0.6280 [2021-03-26 19:53:02 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 290/1251] eta: 0:10:17 lr: 0.000774 loss: 3.6476 (3.5335) grad_norm: 1.1906 (1.2143) time: 0.6267 [2021-03-26 19:53:08 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 300/1251] eta: 0:10:10 lr: 0.000774 loss: 3.6451 (3.5439) grad_norm: 1.2167 (1.2166) time: 0.6260 [2021-03-26 19:53:14 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 310/1251] eta: 0:10:04 lr: 0.000774 loss: 3.8394 (3.5448) grad_norm: 1.2680 (1.2162) time: 0.6289 [2021-03-26 19:53:21 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 320/1251] eta: 0:09:57 lr: 0.000773 loss: 3.6500 (3.5439) grad_norm: 1.1573 (1.2168) time: 0.6308 [2021-03-26 19:53:27 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 330/1251] eta: 0:09:50 lr: 0.000773 loss: 3.6500 (3.5396) grad_norm: 1.1487 (1.2165) time: 0.6302 [2021-03-26 19:53:33 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 340/1251] eta: 0:09:43 lr: 0.000773 loss: 3.8070 (3.5508) grad_norm: 1.1487 (1.2155) time: 0.6320 [2021-03-26 19:53:40 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 350/1251] eta: 0:09:37 lr: 0.000773 loss: 3.7765 (3.5471) grad_norm: 1.2250 (1.2165) time: 0.6331 [2021-03-26 19:53:46 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 360/1251] eta: 0:09:30 lr: 0.000773 loss: 3.5149 (3.5458) grad_norm: 1.2250 (1.2169) time: 0.6321 [2021-03-26 19:53:52 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 370/1251] eta: 0:09:24 lr: 0.000773 loss: 3.5918 (3.5461) grad_norm: 1.2015 (1.2156) time: 0.6317 [2021-03-26 19:53:59 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 380/1251] eta: 0:09:17 lr: 0.000773 loss: 3.5205 (3.5382) grad_norm: 1.1723 (1.2163) time: 0.6304 [2021-03-26 19:54:05 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 390/1251] eta: 0:09:10 lr: 0.000773 loss: 3.5663 (3.5393) grad_norm: 1.1909 (1.2169) time: 0.6275 [2021-03-26 19:54:11 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 400/1251] eta: 0:09:04 lr: 0.000773 loss: 3.5663 (3.5346) grad_norm: 1.2357 (1.2194) time: 0.6296 [2021-03-26 19:54:17 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 410/1251] eta: 0:08:57 lr: 0.000773 loss: 3.4298 (3.5370) grad_norm: 1.2600 (1.2209) time: 0.6295 [2021-03-26 19:54:24 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 420/1251] eta: 0:08:50 lr: 0.000773 loss: 3.2503 (3.5257) grad_norm: 1.1776 (1.2209) time: 0.6270 [2021-03-26 19:54:30 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 430/1251] eta: 0:08:44 lr: 0.000773 loss: 3.3544 (3.5251) grad_norm: 1.1776 (1.2197) time: 0.6329 [2021-03-26 19:54:36 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 440/1251] eta: 0:08:37 lr: 0.000773 loss: 3.6137 (3.5278) grad_norm: 1.1969 (1.2209) time: 0.6319 [2021-03-26 19:54:43 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 450/1251] eta: 0:08:31 lr: 0.000773 loss: 3.5395 (3.5202) grad_norm: 1.2058 (1.2194) time: 0.6304 [2021-03-26 19:54:49 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 460/1251] eta: 0:08:24 lr: 0.000773 loss: 3.6136 (3.5239) grad_norm: 1.1434 (1.2181) time: 0.6276 [2021-03-26 19:54:55 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 470/1251] eta: 0:08:18 lr: 0.000773 loss: 3.6737 (3.5233) grad_norm: 1.1434 (1.2174) time: 0.6278 [2021-03-26 19:55:02 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 480/1251] eta: 0:08:11 lr: 0.000773 loss: 3.6473 (3.5227) grad_norm: 1.1983 (1.2194) time: 0.6333 [2021-03-26 19:55:08 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 490/1251] eta: 0:08:05 lr: 0.000773 loss: 3.4822 (3.5210) grad_norm: 1.2432 (1.2201) time: 0.6339 [2021-03-26 19:55:14 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 500/1251] eta: 0:07:58 lr: 0.000773 loss: 3.4822 (3.5198) grad_norm: 1.2217 (1.2207) time: 0.6321 [2021-03-26 19:55:21 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 510/1251] eta: 0:07:52 lr: 0.000773 loss: 3.4289 (3.5176) grad_norm: 1.1512 (1.2211) time: 0.6266 [2021-03-26 19:55:27 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 520/1251] eta: 0:07:45 lr: 0.000773 loss: 3.4782 (3.5225) grad_norm: 1.1439 (1.2201) time: 0.6254 [2021-03-26 19:55:33 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 530/1251] eta: 0:07:39 lr: 0.000773 loss: 3.9720 (3.5223) grad_norm: 1.1582 (1.2204) time: 0.6278 [2021-03-26 19:55:39 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 540/1251] eta: 0:07:32 lr: 0.000773 loss: 3.6511 (3.5250) grad_norm: 1.1873 (1.2200) time: 0.6264 [2021-03-26 19:55:46 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 550/1251] eta: 0:07:26 lr: 0.000773 loss: 3.6800 (3.5285) grad_norm: 1.1213 (1.2184) time: 0.6345 [2021-03-26 19:55:52 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 560/1251] eta: 0:07:19 lr: 0.000773 loss: 3.5907 (3.5267) grad_norm: 1.1242 (1.2187) time: 0.6360 [2021-03-26 19:55:58 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 570/1251] eta: 0:07:13 lr: 0.000773 loss: 3.5957 (3.5279) grad_norm: 1.1242 (1.2170) time: 0.6309 [2021-03-26 19:56:05 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 580/1251] eta: 0:07:07 lr: 0.000773 loss: 3.6461 (3.5296) grad_norm: 1.1242 (1.2170) time: 0.6324 [2021-03-26 19:56:11 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 590/1251] eta: 0:07:00 lr: 0.000773 loss: 3.6461 (3.5294) grad_norm: 1.1753 (1.2172) time: 0.6327 [2021-03-26 19:56:17 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 600/1251] eta: 0:06:54 lr: 0.000773 loss: 3.2655 (3.5231) grad_norm: 1.1708 (1.2172) time: 0.6391 [2021-03-26 19:56:24 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 610/1251] eta: 0:06:48 lr: 0.000772 loss: 3.2332 (3.5201) grad_norm: 1.1629 (1.2172) time: 0.6415 [2021-03-26 19:56:30 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 620/1251] eta: 0:06:41 lr: 0.000772 loss: 3.6230 (3.5205) grad_norm: 1.1629 (1.2171) time: 0.6341 [2021-03-26 19:56:36 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 630/1251] eta: 0:06:35 lr: 0.000772 loss: 3.6646 (3.5212) grad_norm: 1.2027 (1.2182) time: 0.6273 [2021-03-26 19:56:43 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 640/1251] eta: 0:06:28 lr: 0.000772 loss: 3.6445 (3.5240) grad_norm: 1.1958 (1.2175) time: 0.6286 [2021-03-26 19:56:49 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 650/1251] eta: 0:06:22 lr: 0.000772 loss: 3.5806 (3.5224) grad_norm: 1.1502 (1.2170) time: 0.6250 [2021-03-26 19:56:55 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 660/1251] eta: 0:06:15 lr: 0.000772 loss: 3.7952 (3.5278) grad_norm: 1.1885 (1.2177) time: 0.6253 [2021-03-26 19:57:01 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 670/1251] eta: 0:06:09 lr: 0.000772 loss: 3.7438 (3.5264) grad_norm: 1.1991 (1.2179) time: 0.6278 [2021-03-26 19:57:08 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 680/1251] eta: 0:06:03 lr: 0.000772 loss: 3.3235 (3.5191) grad_norm: 1.2421 (1.2192) time: 0.6278 [2021-03-26 19:57:14 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 690/1251] eta: 0:05:56 lr: 0.000772 loss: 3.0910 (3.5164) grad_norm: 1.1851 (1.2187) time: 0.6345 [2021-03-26 19:57:20 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 700/1251] eta: 0:05:50 lr: 0.000772 loss: 3.4533 (3.5174) grad_norm: 1.1484 (1.2180) time: 0.6339 [2021-03-26 19:57:27 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 710/1251] eta: 0:05:43 lr: 0.000772 loss: 3.5884 (3.5161) grad_norm: 1.1484 (1.2178) time: 0.6285 [2021-03-26 19:57:33 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 720/1251] eta: 0:05:37 lr: 0.000772 loss: 3.4329 (3.5142) grad_norm: 1.1557 (1.2173) time: 0.6250 [2021-03-26 19:57:39 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 730/1251] eta: 0:05:30 lr: 0.000772 loss: 3.2123 (3.5101) grad_norm: 1.1199 (1.2157) time: 0.6242 [2021-03-26 19:57:46 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 740/1251] eta: 0:05:24 lr: 0.000772 loss: 3.4742 (3.5081) grad_norm: 1.1199 (1.2159) time: 0.6308 [2021-03-26 19:57:52 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 750/1251] eta: 0:05:18 lr: 0.000772 loss: 3.5992 (3.5080) grad_norm: 1.2721 (1.2167) time: 0.6356 [2021-03-26 19:57:58 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 760/1251] eta: 0:05:11 lr: 0.000772 loss: 3.5677 (3.5057) grad_norm: 1.1792 (1.2158) time: 0.6257 [2021-03-26 19:58:04 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 770/1251] eta: 0:05:05 lr: 0.000772 loss: 3.5012 (3.5067) grad_norm: 1.1854 (1.2167) time: 0.6229 [2021-03-26 19:58:11 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 780/1251] eta: 0:04:59 lr: 0.000772 loss: 3.7035 (3.5087) grad_norm: 1.2860 (1.2178) time: 0.6325 [2021-03-26 19:58:17 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 790/1251] eta: 0:04:52 lr: 0.000772 loss: 3.7057 (3.5088) grad_norm: 1.2672 (1.2184) time: 0.6322 [2021-03-26 19:58:23 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 800/1251] eta: 0:04:46 lr: 0.000772 loss: 3.5547 (3.5108) grad_norm: 1.1695 (1.2177) time: 0.6311 [2021-03-26 19:58:30 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 810/1251] eta: 0:04:39 lr: 0.000772 loss: 3.5547 (3.5109) grad_norm: 1.1514 (1.2178) time: 0.6325 [2021-03-26 19:58:36 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 820/1251] eta: 0:04:33 lr: 0.000772 loss: 3.4384 (3.5090) grad_norm: 1.2301 (1.2184) time: 0.6269 [2021-03-26 19:58:42 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 830/1251] eta: 0:04:27 lr: 0.000772 loss: 3.5247 (3.5098) grad_norm: 1.2475 (1.2191) time: 0.6258 [2021-03-26 19:58:48 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 840/1251] eta: 0:04:20 lr: 0.000772 loss: 3.6492 (3.5110) grad_norm: 1.1646 (1.2181) time: 0.6271 [2021-03-26 19:58:55 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 850/1251] eta: 0:04:14 lr: 0.000772 loss: 3.7129 (3.5118) grad_norm: 1.1355 (1.2186) time: 0.6234 [2021-03-26 19:59:01 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 860/1251] eta: 0:04:07 lr: 0.000772 loss: 3.7287 (3.5141) grad_norm: 1.1786 (1.2176) time: 0.6206 [2021-03-26 19:59:07 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 870/1251] eta: 0:04:01 lr: 0.000772 loss: 3.6654 (3.5131) grad_norm: 1.1223 (1.2172) time: 0.6226 [2021-03-26 19:59:14 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 880/1251] eta: 0:03:55 lr: 0.000772 loss: 3.3995 (3.5137) grad_norm: 1.1606 (1.2174) time: 0.6317 [2021-03-26 19:59:20 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 890/1251] eta: 0:03:48 lr: 0.000771 loss: 3.3995 (3.5110) grad_norm: 1.1606 (1.2168) time: 0.6355 [2021-03-26 19:59:26 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 900/1251] eta: 0:03:42 lr: 0.000771 loss: 3.5976 (3.5132) grad_norm: 1.1462 (1.2159) time: 0.6303 [2021-03-26 19:59:33 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 910/1251] eta: 0:03:36 lr: 0.000771 loss: 3.7396 (3.5140) grad_norm: 1.2131 (1.2169) time: 0.6311 [2021-03-26 19:59:39 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 920/1251] eta: 0:03:29 lr: 0.000771 loss: 3.6705 (3.5144) grad_norm: 1.3138 (1.2177) time: 0.6320 [2021-03-26 19:59:45 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 930/1251] eta: 0:03:23 lr: 0.000771 loss: 3.7453 (3.5174) grad_norm: 1.2465 (1.2174) time: 0.6282 [2021-03-26 19:59:51 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 940/1251] eta: 0:03:17 lr: 0.000771 loss: 3.8838 (3.5197) grad_norm: 1.2278 (1.2186) time: 0.6301 [2021-03-26 19:59:58 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 950/1251] eta: 0:03:10 lr: 0.000771 loss: 3.5958 (3.5187) grad_norm: 1.1619 (1.2179) time: 0.6291 [2021-03-26 20:00:04 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 960/1251] eta: 0:03:04 lr: 0.000771 loss: 3.3659 (3.5180) grad_norm: 1.1417 (1.2177) time: 0.6284 [2021-03-26 20:00:10 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 970/1251] eta: 0:02:58 lr: 0.000771 loss: 3.4010 (3.5171) grad_norm: 1.1438 (1.2169) time: 0.6289 [2021-03-26 20:00:17 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 980/1251] eta: 0:02:51 lr: 0.000771 loss: 3.3848 (3.5150) grad_norm: 1.1438 (1.2165) time: 0.6273 [2021-03-26 20:00:23 swin_base_patch4_window7_224] INFO: Epoch: [95] [ 990/1251] eta: 0:02:45 lr: 0.000771 loss: 3.3848 (3.5135) grad_norm: 1.1675 (1.2163) time: 0.6354 [2021-03-26 20:00:29 swin_base_patch4_window7_224] INFO: Epoch: [95] [1000/1251] eta: 0:02:39 lr: 0.000771 loss: 2.8746 (3.5104) grad_norm: 1.1598 (1.2161) time: 0.6340 [2021-03-26 20:00:35 swin_base_patch4_window7_224] INFO: Epoch: [95] [1010/1251] eta: 0:02:32 lr: 0.000771 loss: 3.5191 (3.5116) grad_norm: 1.2143 (1.2164) time: 0.6273 [2021-03-26 20:00:42 swin_base_patch4_window7_224] INFO: Epoch: [95] [1020/1251] eta: 0:02:26 lr: 0.000771 loss: 3.5071 (3.5103) grad_norm: 1.2721 (1.2167) time: 0.6261 [2021-03-26 20:00:48 swin_base_patch4_window7_224] INFO: Epoch: [95] [1030/1251] eta: 0:02:20 lr: 0.000771 loss: 3.4367 (3.5108) grad_norm: 1.2748 (1.2170) time: 0.6307 [2021-03-26 20:00:54 swin_base_patch4_window7_224] INFO: Epoch: [95] [1040/1251] eta: 0:02:13 lr: 0.000771 loss: 3.6195 (3.5114) grad_norm: 1.2290 (1.2176) time: 0.6348 [2021-03-26 20:01:01 swin_base_patch4_window7_224] INFO: Epoch: [95] [1050/1251] eta: 0:02:07 lr: 0.000771 loss: 3.5750 (3.5113) grad_norm: 1.2355 (1.2182) time: 0.6307 [2021-03-26 20:01:07 swin_base_patch4_window7_224] INFO: Epoch: [95] [1060/1251] eta: 0:02:01 lr: 0.000771 loss: 3.6654 (3.5127) grad_norm: 1.2138 (1.2182) time: 0.6322 [2021-03-26 20:01:13 swin_base_patch4_window7_224] INFO: Epoch: [95] [1070/1251] eta: 0:01:54 lr: 0.000771 loss: 3.7106 (3.5118) grad_norm: 1.1310 (1.2179) time: 0.6269 [2021-03-26 20:01:20 swin_base_patch4_window7_224] INFO: Epoch: [95] [1080/1251] eta: 0:01:48 lr: 0.000771 loss: 3.4884 (3.5115) grad_norm: 1.2015 (1.2180) time: 0.6268 [2021-03-26 20:01:26 swin_base_patch4_window7_224] INFO: Epoch: [95] [1090/1251] eta: 0:01:41 lr: 0.000771 loss: 3.5494 (3.5115) grad_norm: 1.2015 (1.2177) time: 0.6263 [2021-03-26 20:01:32 swin_base_patch4_window7_224] INFO: Epoch: [95] [1100/1251] eta: 0:01:35 lr: 0.000771 loss: 3.5494 (3.5125) grad_norm: 1.2150 (1.2184) time: 0.6251 [2021-03-26 20:01:39 swin_base_patch4_window7_224] INFO: Epoch: [95] [1110/1251] eta: 0:01:29 lr: 0.000771 loss: 3.5137 (3.5115) grad_norm: 1.2150 (1.2181) time: 0.6358 [2021-03-26 20:01:45 swin_base_patch4_window7_224] INFO: Epoch: [95] [1120/1251] eta: 0:01:22 lr: 0.000771 loss: 3.2863 (3.5100) grad_norm: 1.1905 (1.2177) time: 0.6362 [2021-03-26 20:01:51 swin_base_patch4_window7_224] INFO: Epoch: [95] [1130/1251] eta: 0:01:16 lr: 0.000771 loss: 3.5030 (3.5108) grad_norm: 1.1994 (1.2190) time: 0.6356 [2021-03-26 20:01:58 swin_base_patch4_window7_224] INFO: Epoch: [95] [1140/1251] eta: 0:01:10 lr: 0.000771 loss: 3.8168 (3.5141) grad_norm: 1.2171 (1.2185) time: 0.6339 [2021-03-26 20:02:04 swin_base_patch4_window7_224] INFO: Epoch: [95] [1150/1251] eta: 0:01:03 lr: 0.000771 loss: 3.7151 (3.5119) grad_norm: 1.1359 (1.2181) time: 0.6326 [2021-03-26 20:02:10 swin_base_patch4_window7_224] INFO: Epoch: [95] [1160/1251] eta: 0:00:57 lr: 0.000771 loss: 3.3216 (3.5099) grad_norm: 1.1599 (1.2181) time: 0.6329 [2021-03-26 20:02:17 swin_base_patch4_window7_224] INFO: Epoch: [95] [1170/1251] eta: 0:00:51 lr: 0.000771 loss: 3.3061 (3.5100) grad_norm: 1.2273 (1.2181) time: 0.6371 [2021-03-26 20:02:23 swin_base_patch4_window7_224] INFO: Epoch: [95] [1180/1251] eta: 0:00:44 lr: 0.000770 loss: 3.4746 (3.5094) grad_norm: 1.2273 (1.2184) time: 0.6373 [2021-03-26 20:02:29 swin_base_patch4_window7_224] INFO: Epoch: [95] [1190/1251] eta: 0:00:38 lr: 0.000770 loss: 3.5096 (3.5086) grad_norm: 1.2164 (1.2185) time: 0.6286 [2021-03-26 20:02:35 swin_base_patch4_window7_224] INFO: Epoch: [95] [1200/1251] eta: 0:00:32 lr: 0.000770 loss: 3.7085 (3.5105) grad_norm: 1.1737 (1.2187) time: 0.6254 [2021-03-26 20:02:42 swin_base_patch4_window7_224] INFO: Epoch: [95] [1210/1251] eta: 0:00:25 lr: 0.000770 loss: 3.7063 (3.5109) grad_norm: 1.1853 (1.2185) time: 0.6294 [2021-03-26 20:02:48 swin_base_patch4_window7_224] INFO: Epoch: [95] [1220/1251] eta: 0:00:19 lr: 0.000770 loss: 3.6338 (3.5107) grad_norm: 1.2227 (1.2187) time: 0.6293 [2021-03-26 20:02:54 swin_base_patch4_window7_224] INFO: Epoch: [95] [1230/1251] eta: 0:00:13 lr: 0.000770 loss: 3.5439 (3.5111) grad_norm: 1.2276 (1.2186) time: 0.6269 [2021-03-26 20:03:01 swin_base_patch4_window7_224] INFO: Epoch: [95] [1240/1251] eta: 0:00:06 lr: 0.000770 loss: 3.5825 (3.5119) grad_norm: 1.2267 (1.2184) time: 0.6284 [2021-03-26 20:03:07 swin_base_patch4_window7_224] INFO: Epoch: [95] [1250/1251] eta: 0:00:00 lr: 0.000770 loss: 3.4865 (3.5110) grad_norm: 1.1470 (1.2181) time: 0.6279 [2021-03-26 20:04:12 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:04 loss: 1.2988 (1.2988) acc1: 70.3125 (70.3125) acc5: 92.1875 (92.1875) [2021-03-26 20:04:14 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.9722 (1.0167) acc1: 76.5625 (76.2784) acc5: 92.1875 (93.8920) [2021-03-26 20:04:15 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.0237 (1.0360) acc1: 76.5625 (75.8929) acc5: 93.7500 (93.8244) [2021-03-26 20:04:17 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.0423 (1.0413) acc1: 75.0000 (75.6048) acc5: 93.7500 (93.5988) [2021-03-26 20:04:18 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9605 (1.0204) acc1: 75.0000 (76.1433) acc5: 93.7500 (93.8643) [2021-03-26 20:04:19 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9154 (1.0247) acc1: 77.3585 (75.9040) acc5: 93.7500 (93.8880) [2021-03-26 20:04:24 swin_base_patch4_window7_224] INFO: * Acc@1 76.624 Acc@5 93.728 loss 1.001 [2021-03-26 20:04:24 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.6% [2021-03-26 20:04:24 swin_base_patch4_window7_224] INFO: Max accuracy: 76.62% [2021-03-26 20:04:29 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 0/1251] eta: 1:34:18 lr: 0.000770 loss: 4.0836 (4.0836) grad_norm: 1.3607 (1.3607) time: 4.5228 [2021-03-26 20:04:35 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 10/1251] eta: 0:20:23 lr: 0.000770 loss: 3.6550 (3.4452) grad_norm: 1.2118 (1.1674) time: 0.9858 [2021-03-26 20:04:41 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 20/1251] eta: 0:16:41 lr: 0.000770 loss: 3.5403 (3.4277) grad_norm: 1.1849 (1.2092) time: 0.6285 [2021-03-26 20:04:48 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 30/1251] eta: 0:15:24 lr: 0.000770 loss: 3.6802 (3.5281) grad_norm: 1.1849 (1.1869) time: 0.6313 [2021-03-26 20:04:54 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 40/1251] eta: 0:14:41 lr: 0.000770 loss: 3.3116 (3.4121) grad_norm: 1.1847 (1.1966) time: 0.6381 [2021-03-26 20:05:00 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 50/1251] eta: 0:14:13 lr: 0.000770 loss: 3.0896 (3.3570) grad_norm: 1.1847 (1.1978) time: 0.6388 [2021-03-26 20:05:07 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 60/1251] eta: 0:13:49 lr: 0.000770 loss: 3.4566 (3.4041) grad_norm: 1.1482 (1.1878) time: 0.6322 [2021-03-26 20:05:13 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 70/1251] eta: 0:13:34 lr: 0.000770 loss: 3.6104 (3.3941) grad_norm: 1.1662 (1.2001) time: 0.6346 [2021-03-26 20:05:20 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 80/1251] eta: 0:13:20 lr: 0.000770 loss: 3.6327 (3.3965) grad_norm: 1.1866 (1.1992) time: 0.6436 [2021-03-26 20:05:26 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 90/1251] eta: 0:13:07 lr: 0.000770 loss: 3.5593 (3.4201) grad_norm: 1.1537 (1.2024) time: 0.6387 [2021-03-26 20:05:32 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 100/1251] eta: 0:12:54 lr: 0.000770 loss: 3.5593 (3.4111) grad_norm: 1.1790 (1.1973) time: 0.6278 [2021-03-26 20:05:38 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 110/1251] eta: 0:12:43 lr: 0.000770 loss: 3.5093 (3.4246) grad_norm: 1.1725 (1.2021) time: 0.6296 [2021-03-26 20:05:45 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 120/1251] eta: 0:12:34 lr: 0.000770 loss: 3.6292 (3.4501) grad_norm: 1.1498 (1.2016) time: 0.6375 [2021-03-26 20:05:51 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 130/1251] eta: 0:12:24 lr: 0.000770 loss: 3.7151 (3.4600) grad_norm: 1.1881 (1.2107) time: 0.6356 [2021-03-26 20:05:58 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 140/1251] eta: 0:12:15 lr: 0.000770 loss: 3.6238 (3.4618) grad_norm: 1.2447 (1.2134) time: 0.6340 [2021-03-26 20:06:04 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 150/1251] eta: 0:12:06 lr: 0.000770 loss: 3.6238 (3.4725) grad_norm: 1.2546 (1.2163) time: 0.6312 [2021-03-26 20:06:10 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 160/1251] eta: 0:11:58 lr: 0.000770 loss: 3.5426 (3.4624) grad_norm: 1.2187 (1.2181) time: 0.6312 [2021-03-26 20:06:16 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 170/1251] eta: 0:11:49 lr: 0.000770 loss: 3.5866 (3.4762) grad_norm: 1.2458 (1.2235) time: 0.6316 [2021-03-26 20:06:23 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 180/1251] eta: 0:11:41 lr: 0.000770 loss: 3.8662 (3.4929) grad_norm: 1.2390 (1.2263) time: 0.6324 [2021-03-26 20:06:29 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 190/1251] eta: 0:11:34 lr: 0.000770 loss: 3.8546 (3.4903) grad_norm: 1.2097 (1.2248) time: 0.6331 [2021-03-26 20:06:36 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 200/1251] eta: 0:11:26 lr: 0.000770 loss: 3.5369 (3.4855) grad_norm: 1.2280 (1.2275) time: 0.6359 [2021-03-26 20:06:42 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 210/1251] eta: 0:11:18 lr: 0.000769 loss: 3.6410 (3.5024) grad_norm: 1.2124 (1.2260) time: 0.6345 [2021-03-26 20:06:48 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 220/1251] eta: 0:11:11 lr: 0.000769 loss: 3.5908 (3.4816) grad_norm: 1.2124 (1.2269) time: 0.6325 [2021-03-26 20:06:54 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 230/1251] eta: 0:11:04 lr: 0.000769 loss: 2.9883 (3.4762) grad_norm: 1.2761 (1.2292) time: 0.6325 [2021-03-26 20:07:01 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 240/1251] eta: 0:10:56 lr: 0.000769 loss: 3.3126 (3.4765) grad_norm: 1.2353 (1.2295) time: 0.6287 [2021-03-26 20:07:07 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 250/1251] eta: 0:10:49 lr: 0.000769 loss: 3.4214 (3.4751) grad_norm: 1.1938 (1.2272) time: 0.6342 [2021-03-26 20:07:14 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 260/1251] eta: 0:10:43 lr: 0.000769 loss: 3.5636 (3.4794) grad_norm: 1.1832 (1.2259) time: 0.6407 [2021-03-26 20:07:20 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 270/1251] eta: 0:10:35 lr: 0.000769 loss: 3.6081 (3.4830) grad_norm: 1.1327 (1.2227) time: 0.6330 [2021-03-26 20:07:26 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 280/1251] eta: 0:10:28 lr: 0.000769 loss: 3.3687 (3.4734) grad_norm: 1.1285 (1.2237) time: 0.6232 [2021-03-26 20:07:32 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 290/1251] eta: 0:10:21 lr: 0.000769 loss: 3.4719 (3.4805) grad_norm: 1.2601 (1.2249) time: 0.6248 [2021-03-26 20:07:39 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 300/1251] eta: 0:10:14 lr: 0.000769 loss: 3.6467 (3.4789) grad_norm: 1.2658 (1.2268) time: 0.6296 [2021-03-26 20:07:45 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 310/1251] eta: 0:10:07 lr: 0.000769 loss: 3.4724 (3.4800) grad_norm: 1.1781 (1.2266) time: 0.6306 [2021-03-26 20:07:51 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 320/1251] eta: 0:10:00 lr: 0.000769 loss: 3.6358 (3.4831) grad_norm: 1.2125 (1.2271) time: 0.6308 [2021-03-26 20:07:58 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 330/1251] eta: 0:09:53 lr: 0.000769 loss: 3.6358 (3.4857) grad_norm: 1.1845 (1.2248) time: 0.6346 [2021-03-26 20:08:04 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 340/1251] eta: 0:09:47 lr: 0.000769 loss: 3.5495 (3.4847) grad_norm: 1.1557 (1.2236) time: 0.6352 [2021-03-26 20:08:10 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 350/1251] eta: 0:09:40 lr: 0.000769 loss: 3.5495 (3.4865) grad_norm: 1.1526 (1.2226) time: 0.6325 [2021-03-26 20:08:17 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 360/1251] eta: 0:09:33 lr: 0.000769 loss: 3.6034 (3.4912) grad_norm: 1.1565 (1.2254) time: 0.6330 [2021-03-26 20:08:23 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 370/1251] eta: 0:09:27 lr: 0.000769 loss: 3.7334 (3.4968) grad_norm: 1.1681 (1.2232) time: 0.6384 [2021-03-26 20:08:29 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 380/1251] eta: 0:09:20 lr: 0.000769 loss: 3.6570 (3.5003) grad_norm: 1.1790 (1.2244) time: 0.6370 [2021-03-26 20:08:36 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 390/1251] eta: 0:09:13 lr: 0.000769 loss: 3.5400 (3.4990) grad_norm: 1.2139 (1.2229) time: 0.6303 [2021-03-26 20:08:42 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 400/1251] eta: 0:09:06 lr: 0.000769 loss: 3.5311 (3.4954) grad_norm: 1.1584 (1.2216) time: 0.6277 [2021-03-26 20:08:48 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 410/1251] eta: 0:09:00 lr: 0.000769 loss: 3.4239 (3.4970) grad_norm: 1.1584 (1.2213) time: 0.6271 [2021-03-26 20:08:55 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 420/1251] eta: 0:08:53 lr: 0.000769 loss: 3.3603 (3.4955) grad_norm: 1.1437 (1.2226) time: 0.6311 [2021-03-26 20:09:01 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 430/1251] eta: 0:08:46 lr: 0.000769 loss: 3.3496 (3.4966) grad_norm: 1.1891 (1.2248) time: 0.6318 [2021-03-26 20:09:07 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 440/1251] eta: 0:08:40 lr: 0.000769 loss: 3.4255 (3.4960) grad_norm: 1.1731 (1.2237) time: 0.6253 [2021-03-26 20:09:14 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 450/1251] eta: 0:08:33 lr: 0.000769 loss: 3.6042 (3.4989) grad_norm: 1.1617 (1.2239) time: 0.6356 [2021-03-26 20:09:20 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 460/1251] eta: 0:08:27 lr: 0.000769 loss: 3.6853 (3.4944) grad_norm: 1.1982 (1.2251) time: 0.6404 [2021-03-26 20:09:26 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 470/1251] eta: 0:08:20 lr: 0.000769 loss: 3.4051 (3.4899) grad_norm: 1.1982 (1.2257) time: 0.6323 [2021-03-26 20:09:33 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 480/1251] eta: 0:08:14 lr: 0.000769 loss: 3.4309 (3.4896) grad_norm: 1.2147 (1.2256) time: 0.6360 [2021-03-26 20:09:39 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 490/1251] eta: 0:08:07 lr: 0.000769 loss: 3.4580 (3.4878) grad_norm: 1.2024 (1.2261) time: 0.6378 [2021-03-26 20:09:45 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 500/1251] eta: 0:08:01 lr: 0.000768 loss: 3.5468 (3.4875) grad_norm: 1.1917 (1.2259) time: 0.6340 [2021-03-26 20:09:52 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 510/1251] eta: 0:07:54 lr: 0.000768 loss: 3.6230 (3.4907) grad_norm: 1.1397 (1.2245) time: 0.6320 [2021-03-26 20:09:58 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 520/1251] eta: 0:07:48 lr: 0.000768 loss: 3.5949 (3.4879) grad_norm: 1.1312 (1.2229) time: 0.6263 [2021-03-26 20:10:04 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 530/1251] eta: 0:07:41 lr: 0.000768 loss: 3.5949 (3.4918) grad_norm: 1.1473 (1.2221) time: 0.6262 [2021-03-26 20:10:10 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 540/1251] eta: 0:07:34 lr: 0.000768 loss: 3.6116 (3.4925) grad_norm: 1.1969 (1.2241) time: 0.6302 [2021-03-26 20:10:17 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 550/1251] eta: 0:07:28 lr: 0.000768 loss: 3.6557 (3.4993) grad_norm: 1.1921 (1.2236) time: 0.6437 [2021-03-26 20:10:23 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 560/1251] eta: 0:07:22 lr: 0.000768 loss: 3.8049 (3.5041) grad_norm: 1.1583 (1.2226) time: 0.6413 [2021-03-26 20:10:30 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 570/1251] eta: 0:07:15 lr: 0.000768 loss: 3.5742 (3.5053) grad_norm: 1.1503 (1.2211) time: 0.6286 [2021-03-26 20:10:36 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 580/1251] eta: 0:07:09 lr: 0.000768 loss: 3.5495 (3.5033) grad_norm: 1.1891 (1.2216) time: 0.6310 [2021-03-26 20:10:42 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 590/1251] eta: 0:07:02 lr: 0.000768 loss: 3.5750 (3.5069) grad_norm: 1.2150 (1.2220) time: 0.6355 [2021-03-26 20:10:49 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 600/1251] eta: 0:06:56 lr: 0.000768 loss: 3.7438 (3.5090) grad_norm: 1.2766 (1.2239) time: 0.6353 [2021-03-26 20:10:55 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 610/1251] eta: 0:06:49 lr: 0.000768 loss: 3.8078 (3.5103) grad_norm: 1.2559 (1.2241) time: 0.6285 [2021-03-26 20:11:01 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 620/1251] eta: 0:06:43 lr: 0.000768 loss: 3.6376 (3.5119) grad_norm: 1.1867 (1.2235) time: 0.6287 [2021-03-26 20:11:07 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 630/1251] eta: 0:06:36 lr: 0.000768 loss: 3.6289 (3.5132) grad_norm: 1.2297 (1.2240) time: 0.6265 [2021-03-26 20:11:14 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 640/1251] eta: 0:06:30 lr: 0.000768 loss: 3.6845 (3.5134) grad_norm: 1.2119 (1.2237) time: 0.6319 [2021-03-26 20:11:20 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 650/1251] eta: 0:06:23 lr: 0.000768 loss: 3.5931 (3.5164) grad_norm: 1.2054 (1.2239) time: 0.6350 [2021-03-26 20:11:26 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 660/1251] eta: 0:06:17 lr: 0.000768 loss: 3.4536 (3.5155) grad_norm: 1.1995 (1.2231) time: 0.6328 [2021-03-26 20:11:33 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 670/1251] eta: 0:06:11 lr: 0.000768 loss: 3.4536 (3.5170) grad_norm: 1.1553 (1.2218) time: 0.6363 [2021-03-26 20:11:39 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 680/1251] eta: 0:06:04 lr: 0.000768 loss: 3.3396 (3.5159) grad_norm: 1.1513 (1.2216) time: 0.6454 [2021-03-26 20:11:46 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 690/1251] eta: 0:05:58 lr: 0.000768 loss: 3.2147 (3.5137) grad_norm: 1.1561 (1.2211) time: 0.6448 [2021-03-26 20:11:52 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 700/1251] eta: 0:05:51 lr: 0.000768 loss: 3.4786 (3.5142) grad_norm: 1.1723 (1.2210) time: 0.6337 [2021-03-26 20:11:58 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 710/1251] eta: 0:05:45 lr: 0.000768 loss: 3.7239 (3.5145) grad_norm: 1.1483 (1.2199) time: 0.6340 [2021-03-26 20:12:05 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 720/1251] eta: 0:05:39 lr: 0.000768 loss: 3.6652 (3.5161) grad_norm: 1.1533 (1.2195) time: 0.6301 [2021-03-26 20:12:11 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 730/1251] eta: 0:05:32 lr: 0.000768 loss: 3.5310 (3.5154) grad_norm: 1.2224 (1.2208) time: 0.6281 [2021-03-26 20:12:17 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 740/1251] eta: 0:05:26 lr: 0.000768 loss: 3.4928 (3.5142) grad_norm: 1.2224 (1.2198) time: 0.6384 [2021-03-26 20:12:24 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 750/1251] eta: 0:05:19 lr: 0.000768 loss: 3.6107 (3.5159) grad_norm: 1.1978 (1.2202) time: 0.6402 [2021-03-26 20:12:30 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 760/1251] eta: 0:05:13 lr: 0.000768 loss: 3.7411 (3.5184) grad_norm: 1.1978 (1.2190) time: 0.6418 [2021-03-26 20:12:37 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 770/1251] eta: 0:05:07 lr: 0.000768 loss: 3.6691 (3.5193) grad_norm: 1.1849 (1.2192) time: 0.6362 [2021-03-26 20:12:43 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 780/1251] eta: 0:05:00 lr: 0.000767 loss: 3.6340 (3.5193) grad_norm: 1.2261 (1.2191) time: 0.6390 [2021-03-26 20:12:49 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 790/1251] eta: 0:04:54 lr: 0.000767 loss: 3.6340 (3.5204) grad_norm: 1.2261 (1.2197) time: 0.6461 [2021-03-26 20:12:56 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 800/1251] eta: 0:04:47 lr: 0.000767 loss: 3.7448 (3.5222) grad_norm: 1.2453 (1.2198) time: 0.6360 [2021-03-26 20:13:02 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 810/1251] eta: 0:04:41 lr: 0.000767 loss: 3.6420 (3.5214) grad_norm: 1.2071 (1.2202) time: 0.6304 [2021-03-26 20:13:08 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 820/1251] eta: 0:04:35 lr: 0.000767 loss: 3.5180 (3.5198) grad_norm: 1.2219 (1.2208) time: 0.6369 [2021-03-26 20:13:15 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 830/1251] eta: 0:04:28 lr: 0.000767 loss: 3.5180 (3.5193) grad_norm: 1.2471 (1.2213) time: 0.6346 [2021-03-26 20:13:21 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 840/1251] eta: 0:04:22 lr: 0.000767 loss: 3.6929 (3.5224) grad_norm: 1.1562 (1.2202) time: 0.6249 [2021-03-26 20:13:27 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 850/1251] eta: 0:04:15 lr: 0.000767 loss: 3.8322 (3.5211) grad_norm: 1.1002 (1.2192) time: 0.6288 [2021-03-26 20:13:34 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 860/1251] eta: 0:04:09 lr: 0.000767 loss: 3.7029 (3.5228) grad_norm: 1.2149 (1.2217) time: 0.6366 [2021-03-26 20:13:40 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 870/1251] eta: 0:04:03 lr: 0.000767 loss: 3.5252 (3.5207) grad_norm: 1.2259 (1.2213) time: 0.6352 [2021-03-26 20:13:46 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 880/1251] eta: 0:03:56 lr: 0.000767 loss: 3.3526 (3.5195) grad_norm: 1.1713 (1.2210) time: 0.6273 [2021-03-26 20:13:53 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 890/1251] eta: 0:03:50 lr: 0.000767 loss: 3.6366 (3.5198) grad_norm: 1.2216 (1.2215) time: 0.6245 [2021-03-26 20:13:59 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 900/1251] eta: 0:03:43 lr: 0.000767 loss: 3.7912 (3.5237) grad_norm: 1.2613 (1.2217) time: 0.6292 [2021-03-26 20:14:05 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 910/1251] eta: 0:03:37 lr: 0.000767 loss: 3.6094 (3.5190) grad_norm: 1.2194 (1.2216) time: 0.6327 [2021-03-26 20:14:11 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 920/1251] eta: 0:03:31 lr: 0.000767 loss: 3.2538 (3.5182) grad_norm: 1.1350 (1.2206) time: 0.6263 [2021-03-26 20:14:18 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 930/1251] eta: 0:03:24 lr: 0.000767 loss: 3.2538 (3.5167) grad_norm: 1.1586 (1.2202) time: 0.6271 [2021-03-26 20:14:24 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 940/1251] eta: 0:03:18 lr: 0.000767 loss: 3.4710 (3.5176) grad_norm: 1.1586 (1.2197) time: 0.6316 [2021-03-26 20:14:30 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 950/1251] eta: 0:03:11 lr: 0.000767 loss: 3.4378 (3.5153) grad_norm: 1.2163 (1.2210) time: 0.6273 [2021-03-26 20:14:37 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 960/1251] eta: 0:03:05 lr: 0.000767 loss: 3.6362 (3.5163) grad_norm: 1.2691 (1.2212) time: 0.6325 [2021-03-26 20:14:43 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 970/1251] eta: 0:02:59 lr: 0.000767 loss: 3.6386 (3.5161) grad_norm: 1.1790 (1.2212) time: 0.6472 [2021-03-26 20:14:49 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 980/1251] eta: 0:02:52 lr: 0.000767 loss: 3.6496 (3.5180) grad_norm: 1.1790 (1.2217) time: 0.6385 [2021-03-26 20:14:56 swin_base_patch4_window7_224] INFO: Epoch: [96] [ 990/1251] eta: 0:02:46 lr: 0.000767 loss: 3.6734 (3.5167) grad_norm: 1.2542 (1.2218) time: 0.6226 [2021-03-26 20:15:02 swin_base_patch4_window7_224] INFO: Epoch: [96] [1000/1251] eta: 0:02:39 lr: 0.000767 loss: 3.4159 (3.5160) grad_norm: 1.1132 (1.2210) time: 0.6224 [2021-03-26 20:15:08 swin_base_patch4_window7_224] INFO: Epoch: [96] [1010/1251] eta: 0:02:33 lr: 0.000767 loss: 3.6197 (3.5167) grad_norm: 1.1288 (1.2203) time: 0.6297 [2021-03-26 20:15:14 swin_base_patch4_window7_224] INFO: Epoch: [96] [1020/1251] eta: 0:02:27 lr: 0.000767 loss: 3.7664 (3.5184) grad_norm: 1.1318 (1.2197) time: 0.6277 [2021-03-26 20:15:21 swin_base_patch4_window7_224] INFO: Epoch: [96] [1030/1251] eta: 0:02:20 lr: 0.000767 loss: 3.7681 (3.5189) grad_norm: 1.2033 (1.2200) time: 0.6257 [2021-03-26 20:15:27 swin_base_patch4_window7_224] INFO: Epoch: [96] [1040/1251] eta: 0:02:14 lr: 0.000767 loss: 3.3828 (3.5168) grad_norm: 1.2230 (1.2212) time: 0.6320 [2021-03-26 20:15:33 swin_base_patch4_window7_224] INFO: Epoch: [96] [1050/1251] eta: 0:02:07 lr: 0.000767 loss: 3.3727 (3.5139) grad_norm: 1.1952 (1.2207) time: 0.6314 [2021-03-26 20:15:40 swin_base_patch4_window7_224] INFO: Epoch: [96] [1060/1251] eta: 0:02:01 lr: 0.000767 loss: 3.4981 (3.5157) grad_norm: 1.1473 (1.2209) time: 0.6371 [2021-03-26 20:15:46 swin_base_patch4_window7_224] INFO: Epoch: [96] [1070/1251] eta: 0:01:55 lr: 0.000766 loss: 3.8287 (3.5181) grad_norm: 1.2796 (1.2219) time: 0.6373 [2021-03-26 20:15:53 swin_base_patch4_window7_224] INFO: Epoch: [96] [1080/1251] eta: 0:01:48 lr: 0.000766 loss: 3.6936 (3.5207) grad_norm: 1.3247 (1.2226) time: 0.6345 [2021-03-26 20:15:59 swin_base_patch4_window7_224] INFO: Epoch: [96] [1090/1251] eta: 0:01:42 lr: 0.000766 loss: 3.6068 (3.5203) grad_norm: 1.2824 (1.2233) time: 0.6318 [2021-03-26 20:16:05 swin_base_patch4_window7_224] INFO: Epoch: [96] [1100/1251] eta: 0:01:36 lr: 0.000766 loss: 3.4351 (3.5202) grad_norm: 1.2347 (1.2233) time: 0.6270 [2021-03-26 20:16:11 swin_base_patch4_window7_224] INFO: Epoch: [96] [1110/1251] eta: 0:01:29 lr: 0.000766 loss: 3.5785 (3.5208) grad_norm: 1.1829 (1.2228) time: 0.6299 [2021-03-26 20:16:18 swin_base_patch4_window7_224] INFO: Epoch: [96] [1120/1251] eta: 0:01:23 lr: 0.000766 loss: 3.5359 (3.5205) grad_norm: 1.1887 (1.2228) time: 0.6296 [2021-03-26 20:16:24 swin_base_patch4_window7_224] INFO: Epoch: [96] [1130/1251] eta: 0:01:16 lr: 0.000766 loss: 3.5210 (3.5202) grad_norm: 1.2052 (1.2229) time: 0.6280 [2021-03-26 20:16:30 swin_base_patch4_window7_224] INFO: Epoch: [96] [1140/1251] eta: 0:01:10 lr: 0.000766 loss: 3.6918 (3.5218) grad_norm: 1.2107 (1.2233) time: 0.6267 [2021-03-26 20:16:37 swin_base_patch4_window7_224] INFO: Epoch: [96] [1150/1251] eta: 0:01:04 lr: 0.000766 loss: 3.7139 (3.5215) grad_norm: 1.1670 (1.2226) time: 0.6295 [2021-03-26 20:16:43 swin_base_patch4_window7_224] INFO: Epoch: [96] [1160/1251] eta: 0:00:57 lr: 0.000766 loss: 3.4413 (3.5206) grad_norm: 1.1273 (1.2222) time: 0.6301 [2021-03-26 20:16:49 swin_base_patch4_window7_224] INFO: Epoch: [96] [1170/1251] eta: 0:00:51 lr: 0.000766 loss: 3.4339 (3.5179) grad_norm: 1.1910 (1.2225) time: 0.6245 [2021-03-26 20:16:55 swin_base_patch4_window7_224] INFO: Epoch: [96] [1180/1251] eta: 0:00:45 lr: 0.000766 loss: 3.4949 (3.5189) grad_norm: 1.1835 (1.2214) time: 0.6260 [2021-03-26 20:17:02 swin_base_patch4_window7_224] INFO: Epoch: [96] [1190/1251] eta: 0:00:38 lr: 0.000766 loss: 3.6125 (3.5195) grad_norm: 1.0939 (1.2209) time: 0.6303 [2021-03-26 20:17:08 swin_base_patch4_window7_224] INFO: Epoch: [96] [1200/1251] eta: 0:00:32 lr: 0.000766 loss: 3.7989 (3.5215) grad_norm: 1.1832 (1.2210) time: 0.6305 [2021-03-26 20:17:14 swin_base_patch4_window7_224] INFO: Epoch: [96] [1210/1251] eta: 0:00:26 lr: 0.000766 loss: 3.8321 (3.5238) grad_norm: 1.1698 (1.2203) time: 0.6309 [2021-03-26 20:17:21 swin_base_patch4_window7_224] INFO: Epoch: [96] [1220/1251] eta: 0:00:19 lr: 0.000766 loss: 3.7071 (3.5220) grad_norm: 1.1698 (1.2212) time: 0.6291 [2021-03-26 20:17:27 swin_base_patch4_window7_224] INFO: Epoch: [96] [1230/1251] eta: 0:00:13 lr: 0.000766 loss: 3.5430 (3.5225) grad_norm: 1.2147 (1.2217) time: 0.6245 [2021-03-26 20:17:33 swin_base_patch4_window7_224] INFO: Epoch: [96] [1240/1251] eta: 0:00:06 lr: 0.000766 loss: 3.3591 (3.5208) grad_norm: 1.2886 (1.2226) time: 0.6211 [2021-03-26 20:17:39 swin_base_patch4_window7_224] INFO: Epoch: [96] [1250/1251] eta: 0:00:00 lr: 0.000766 loss: 3.4271 (3.5219) grad_norm: 1.1859 (1.2224) time: 0.6144 [2021-03-26 20:17:45 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:39 loss: 1.1822 (1.1822) acc1: 73.4375 (73.4375) acc5: 92.1875 (92.1875) [2021-03-26 20:17:48 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8657 (0.9320) acc1: 79.6875 (78.4091) acc5: 93.7500 (94.4602) [2021-03-26 20:17:51 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.9361 (0.9807) acc1: 75.0000 (76.9345) acc5: 93.7500 (94.4940) [2021-03-26 20:17:53 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0645 (1.0155) acc1: 75.0000 (76.1089) acc5: 93.7500 (94.0020) [2021-03-26 20:17:55 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9938 (1.0000) acc1: 76.5625 (76.8293) acc5: 93.7500 (94.0549) [2021-03-26 20:17:56 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0042 (1.0156) acc1: 75.4717 (76.4480) acc5: 93.7500 (93.8880) [2021-03-26 20:18:00 swin_base_patch4_window7_224] INFO: * Acc@1 76.644 Acc@5 93.704 loss 1.005 [2021-03-26 20:18:00 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.6% [2021-03-26 20:18:00 swin_base_patch4_window7_224] INFO: Max accuracy: 76.64% [2021-03-26 20:18:05 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 0/1251] eta: 1:29:14 lr: 0.000766 loss: 3.3338 (3.3338) grad_norm: 1.2310 (1.2310) time: 4.2800 [2021-03-26 20:18:11 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 10/1251] eta: 0:20:03 lr: 0.000766 loss: 3.5763 (3.5347) grad_norm: 1.1978 (1.1936) time: 0.9697 [2021-03-26 20:18:18 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 20/1251] eta: 0:16:39 lr: 0.000766 loss: 3.7775 (3.7003) grad_norm: 1.1825 (1.2248) time: 0.6386 [2021-03-26 20:18:24 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 30/1251] eta: 0:15:21 lr: 0.000766 loss: 3.7701 (3.6606) grad_norm: 1.1809 (1.2169) time: 0.6367 [2021-03-26 20:18:30 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 40/1251] eta: 0:14:39 lr: 0.000766 loss: 3.5228 (3.5861) grad_norm: 1.1725 (1.2198) time: 0.6365 [2021-03-26 20:18:37 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 50/1251] eta: 0:14:09 lr: 0.000766 loss: 3.3291 (3.5579) grad_norm: 1.1668 (1.2111) time: 0.6332 [2021-03-26 20:18:43 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 60/1251] eta: 0:13:46 lr: 0.000766 loss: 3.4727 (3.5393) grad_norm: 1.1947 (1.2100) time: 0.6269 [2021-03-26 20:18:49 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 70/1251] eta: 0:13:28 lr: 0.000766 loss: 3.4700 (3.5235) grad_norm: 1.1969 (1.2170) time: 0.6270 [2021-03-26 20:18:55 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 80/1251] eta: 0:13:13 lr: 0.000766 loss: 3.4252 (3.5157) grad_norm: 1.1921 (1.2160) time: 0.6277 [2021-03-26 20:19:02 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 90/1251] eta: 0:13:01 lr: 0.000766 loss: 3.4252 (3.5094) grad_norm: 1.2427 (1.2240) time: 0.6318 [2021-03-26 20:19:08 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 100/1251] eta: 0:12:49 lr: 0.000765 loss: 3.3759 (3.4845) grad_norm: 1.2650 (1.2250) time: 0.6333 [2021-03-26 20:19:14 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 110/1251] eta: 0:12:39 lr: 0.000765 loss: 3.6614 (3.5000) grad_norm: 1.2362 (1.2306) time: 0.6314 [2021-03-26 20:19:21 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 120/1251] eta: 0:12:30 lr: 0.000765 loss: 3.6957 (3.5143) grad_norm: 1.1276 (1.2298) time: 0.6360 [2021-03-26 20:19:27 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 130/1251] eta: 0:12:20 lr: 0.000765 loss: 3.8080 (3.5322) grad_norm: 1.1539 (1.2282) time: 0.6353 [2021-03-26 20:19:33 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 140/1251] eta: 0:12:12 lr: 0.000765 loss: 3.6135 (3.5276) grad_norm: 1.1797 (1.2237) time: 0.6351 [2021-03-26 20:19:40 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 150/1251] eta: 0:12:03 lr: 0.000765 loss: 3.5954 (3.5401) grad_norm: 1.1479 (1.2196) time: 0.6332 [2021-03-26 20:19:46 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 160/1251] eta: 0:11:54 lr: 0.000765 loss: 3.5854 (3.5303) grad_norm: 1.1460 (1.2166) time: 0.6264 [2021-03-26 20:19:52 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 170/1251] eta: 0:11:46 lr: 0.000765 loss: 3.3343 (3.5260) grad_norm: 1.1363 (1.2129) time: 0.6262 [2021-03-26 20:19:59 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 180/1251] eta: 0:11:38 lr: 0.000765 loss: 3.6981 (3.5476) grad_norm: 1.1858 (1.2139) time: 0.6306 [2021-03-26 20:20:05 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 190/1251] eta: 0:11:31 lr: 0.000765 loss: 3.8194 (3.5414) grad_norm: 1.1993 (1.2158) time: 0.6346 [2021-03-26 20:20:11 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 200/1251] eta: 0:11:23 lr: 0.000765 loss: 3.7227 (3.5434) grad_norm: 1.1906 (1.2131) time: 0.6312 [2021-03-26 20:20:18 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 210/1251] eta: 0:11:16 lr: 0.000765 loss: 3.5330 (3.5381) grad_norm: 1.1182 (1.2099) time: 0.6380 [2021-03-26 20:20:24 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 220/1251] eta: 0:11:09 lr: 0.000765 loss: 3.2938 (3.5194) grad_norm: 1.1045 (1.2090) time: 0.6389 [2021-03-26 20:20:30 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 230/1251] eta: 0:11:02 lr: 0.000765 loss: 3.3153 (3.5218) grad_norm: 1.1112 (1.2072) time: 0.6304 [2021-03-26 20:20:37 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 240/1251] eta: 0:10:54 lr: 0.000765 loss: 3.6506 (3.5332) grad_norm: 1.1522 (1.2089) time: 0.6297 [2021-03-26 20:20:43 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 250/1251] eta: 0:10:47 lr: 0.000765 loss: 3.7611 (3.5354) grad_norm: 1.1844 (1.2111) time: 0.6283 [2021-03-26 20:20:49 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 260/1251] eta: 0:10:40 lr: 0.000765 loss: 3.5256 (3.5274) grad_norm: 1.2146 (1.2119) time: 0.6295 [2021-03-26 20:20:55 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 270/1251] eta: 0:10:33 lr: 0.000765 loss: 3.5501 (3.5327) grad_norm: 1.1836 (1.2105) time: 0.6287 [2021-03-26 20:21:02 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 280/1251] eta: 0:10:26 lr: 0.000765 loss: 3.7614 (3.5366) grad_norm: 1.1724 (1.2109) time: 0.6270 [2021-03-26 20:21:08 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 290/1251] eta: 0:10:19 lr: 0.000765 loss: 3.6953 (3.5337) grad_norm: 1.1465 (1.2095) time: 0.6340 [2021-03-26 20:21:14 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 300/1251] eta: 0:10:12 lr: 0.000765 loss: 3.6373 (3.5344) grad_norm: 1.1521 (1.2072) time: 0.6364 [2021-03-26 20:21:21 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 310/1251] eta: 0:10:05 lr: 0.000765 loss: 3.6181 (3.5372) grad_norm: 1.1817 (1.2108) time: 0.6277 [2021-03-26 20:21:27 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 320/1251] eta: 0:09:58 lr: 0.000765 loss: 3.6311 (3.5357) grad_norm: 1.2590 (1.2119) time: 0.6258 [2021-03-26 20:21:33 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 330/1251] eta: 0:09:52 lr: 0.000765 loss: 3.6746 (3.5390) grad_norm: 1.1939 (1.2120) time: 0.6327 [2021-03-26 20:21:40 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 340/1251] eta: 0:09:45 lr: 0.000765 loss: 3.7001 (3.5404) grad_norm: 1.2343 (1.2152) time: 0.6381 [2021-03-26 20:21:46 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 350/1251] eta: 0:09:38 lr: 0.000765 loss: 3.4947 (3.5313) grad_norm: 1.2270 (1.2138) time: 0.6340 [2021-03-26 20:21:52 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 360/1251] eta: 0:09:32 lr: 0.000765 loss: 3.2880 (3.5305) grad_norm: 1.1575 (1.2136) time: 0.6292 [2021-03-26 20:21:59 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 370/1251] eta: 0:09:25 lr: 0.000765 loss: 3.4856 (3.5251) grad_norm: 1.1621 (1.2128) time: 0.6276 [2021-03-26 20:22:05 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 380/1251] eta: 0:09:18 lr: 0.000765 loss: 3.5562 (3.5297) grad_norm: 1.2107 (1.2140) time: 0.6262 [2021-03-26 20:22:11 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 390/1251] eta: 0:09:11 lr: 0.000764 loss: 3.5785 (3.5315) grad_norm: 1.2461 (1.2141) time: 0.6245 [2021-03-26 20:22:17 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 400/1251] eta: 0:09:05 lr: 0.000764 loss: 3.6130 (3.5358) grad_norm: 1.2171 (1.2146) time: 0.6304 [2021-03-26 20:22:24 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 410/1251] eta: 0:08:58 lr: 0.000764 loss: 3.6130 (3.5317) grad_norm: 1.1724 (1.2131) time: 0.6302 [2021-03-26 20:22:30 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 420/1251] eta: 0:08:51 lr: 0.000764 loss: 3.4092 (3.5279) grad_norm: 1.1337 (1.2110) time: 0.6272 [2021-03-26 20:22:36 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 430/1251] eta: 0:08:45 lr: 0.000764 loss: 3.4092 (3.5240) grad_norm: 1.1452 (1.2115) time: 0.6286 [2021-03-26 20:22:43 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 440/1251] eta: 0:08:38 lr: 0.000764 loss: 3.5717 (3.5225) grad_norm: 1.2283 (1.2133) time: 0.6282 [2021-03-26 20:22:49 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 450/1251] eta: 0:08:32 lr: 0.000764 loss: 3.6822 (3.5232) grad_norm: 1.2201 (1.2130) time: 0.6290 [2021-03-26 20:22:55 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 460/1251] eta: 0:08:25 lr: 0.000764 loss: 3.4897 (3.5247) grad_norm: 1.1715 (1.2150) time: 0.6231 [2021-03-26 20:23:01 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 470/1251] eta: 0:08:18 lr: 0.000764 loss: 3.6008 (3.5249) grad_norm: 1.1715 (1.2143) time: 0.6254 [2021-03-26 20:23:08 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 480/1251] eta: 0:08:12 lr: 0.000764 loss: 3.5532 (3.5223) grad_norm: 1.1804 (1.2149) time: 0.6319 [2021-03-26 20:23:14 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 490/1251] eta: 0:08:05 lr: 0.000764 loss: 3.3973 (3.5216) grad_norm: 1.2127 (1.2154) time: 0.6331 [2021-03-26 20:23:20 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 500/1251] eta: 0:07:59 lr: 0.000764 loss: 3.6937 (3.5226) grad_norm: 1.1813 (inf) time: 0.6327 [2021-03-26 20:23:27 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 510/1251] eta: 0:07:52 lr: 0.000764 loss: 3.5670 (3.5192) grad_norm: 1.2134 (inf) time: 0.6274 [2021-03-26 20:23:33 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 520/1251] eta: 0:07:46 lr: 0.000764 loss: 3.3121 (3.5162) grad_norm: 1.2501 (inf) time: 0.6300 [2021-03-26 20:23:39 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 530/1251] eta: 0:07:39 lr: 0.000764 loss: 3.6717 (3.5184) grad_norm: 1.2114 (inf) time: 0.6351 [2021-03-26 20:23:46 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 540/1251] eta: 0:07:33 lr: 0.000764 loss: 3.7071 (3.5121) grad_norm: 1.1919 (inf) time: 0.6327 [2021-03-26 20:23:52 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 550/1251] eta: 0:07:27 lr: 0.000764 loss: 3.4449 (3.5098) grad_norm: 1.2132 (inf) time: 0.6492 [2021-03-26 20:23:59 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 560/1251] eta: 0:07:21 lr: 0.000764 loss: 3.4791 (3.5136) grad_norm: 1.2399 (inf) time: 0.6503 [2021-03-26 20:24:05 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 570/1251] eta: 0:07:14 lr: 0.000764 loss: 3.6003 (3.5108) grad_norm: 1.1389 (inf) time: 0.6302 [2021-03-26 20:24:11 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 580/1251] eta: 0:07:08 lr: 0.000764 loss: 3.6003 (3.5122) grad_norm: 1.1216 (inf) time: 0.6306 [2021-03-26 20:24:18 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 590/1251] eta: 0:07:01 lr: 0.000764 loss: 3.3881 (3.5080) grad_norm: 1.1599 (inf) time: 0.6348 [2021-03-26 20:24:24 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 600/1251] eta: 0:06:55 lr: 0.000764 loss: 3.6110 (3.5126) grad_norm: 1.1599 (inf) time: 0.6357 [2021-03-26 20:24:30 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 610/1251] eta: 0:06:48 lr: 0.000764 loss: 3.8309 (3.5159) grad_norm: 1.2009 (inf) time: 0.6339 [2021-03-26 20:24:37 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 620/1251] eta: 0:06:42 lr: 0.000764 loss: 3.8309 (3.5198) grad_norm: 1.2253 (inf) time: 0.6317 [2021-03-26 20:24:43 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 630/1251] eta: 0:06:35 lr: 0.000764 loss: 3.5991 (3.5185) grad_norm: 1.2253 (inf) time: 0.6285 [2021-03-26 20:24:49 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 640/1251] eta: 0:06:29 lr: 0.000764 loss: 3.4564 (3.5212) grad_norm: 1.2365 (inf) time: 0.6311 [2021-03-26 20:24:56 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 650/1251] eta: 0:06:23 lr: 0.000764 loss: 3.4249 (3.5183) grad_norm: 1.2239 (inf) time: 0.6335 [2021-03-26 20:25:02 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 660/1251] eta: 0:06:16 lr: 0.000764 loss: 3.2633 (3.5182) grad_norm: 1.1424 (inf) time: 0.6300 [2021-03-26 20:25:08 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 670/1251] eta: 0:06:10 lr: 0.000763 loss: 3.6239 (3.5228) grad_norm: 1.1192 (inf) time: 0.6278 [2021-03-26 20:25:14 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 680/1251] eta: 0:06:03 lr: 0.000763 loss: 3.5755 (3.5210) grad_norm: 1.2075 (inf) time: 0.6226 [2021-03-26 20:25:21 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 690/1251] eta: 0:05:57 lr: 0.000763 loss: 3.5359 (3.5216) grad_norm: 1.2129 (inf) time: 0.6245 [2021-03-26 20:25:27 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 700/1251] eta: 0:05:50 lr: 0.000763 loss: 3.4359 (3.5177) grad_norm: 1.1948 (inf) time: 0.6262 [2021-03-26 20:25:33 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 710/1251] eta: 0:05:44 lr: 0.000763 loss: 2.9298 (3.5119) grad_norm: 1.1948 (inf) time: 0.6241 [2021-03-26 20:25:39 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 720/1251] eta: 0:05:37 lr: 0.000763 loss: 3.2359 (3.5117) grad_norm: 1.2128 (inf) time: 0.6273 [2021-03-26 20:25:46 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 730/1251] eta: 0:05:31 lr: 0.000763 loss: 3.5260 (3.5096) grad_norm: 1.2004 (inf) time: 0.6345 [2021-03-26 20:25:52 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 740/1251] eta: 0:05:25 lr: 0.000763 loss: 3.3513 (3.5118) grad_norm: 1.1328 (inf) time: 0.6443 [2021-03-26 20:25:59 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 750/1251] eta: 0:05:18 lr: 0.000763 loss: 3.3513 (3.5084) grad_norm: 1.1612 (inf) time: 0.6428 [2021-03-26 20:26:05 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 760/1251] eta: 0:05:12 lr: 0.000763 loss: 3.5564 (3.5099) grad_norm: 1.1633 (inf) time: 0.6342 [2021-03-26 20:26:11 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 770/1251] eta: 0:05:06 lr: 0.000763 loss: 3.8206 (3.5118) grad_norm: 1.1845 (inf) time: 0.6342 [2021-03-26 20:26:18 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 780/1251] eta: 0:04:59 lr: 0.000763 loss: 3.7835 (3.5127) grad_norm: 1.2176 (inf) time: 0.6335 [2021-03-26 20:26:24 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 790/1251] eta: 0:04:53 lr: 0.000763 loss: 3.5446 (3.5107) grad_norm: 1.1519 (inf) time: 0.6356 [2021-03-26 20:26:30 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 800/1251] eta: 0:04:47 lr: 0.000763 loss: 3.5060 (3.5111) grad_norm: 1.1454 (inf) time: 0.6398 [2021-03-26 20:26:37 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 810/1251] eta: 0:04:40 lr: 0.000763 loss: 3.5834 (3.5129) grad_norm: 1.2104 (inf) time: 0.6326 [2021-03-26 20:26:43 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 820/1251] eta: 0:04:34 lr: 0.000763 loss: 3.5205 (3.5133) grad_norm: 1.2104 (inf) time: 0.6282 [2021-03-26 20:26:49 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 830/1251] eta: 0:04:27 lr: 0.000763 loss: 3.5205 (3.5128) grad_norm: 1.2532 (inf) time: 0.6304 [2021-03-26 20:26:56 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 840/1251] eta: 0:04:21 lr: 0.000763 loss: 3.7075 (3.5139) grad_norm: 1.3629 (inf) time: 0.6292 [2021-03-26 20:27:02 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 850/1251] eta: 0:04:15 lr: 0.000763 loss: 3.7269 (3.5144) grad_norm: 1.2375 (inf) time: 0.6241 [2021-03-26 20:27:08 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 860/1251] eta: 0:04:08 lr: 0.000763 loss: 3.4712 (3.5140) grad_norm: 1.2028 (inf) time: 0.6282 [2021-03-26 20:27:14 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 870/1251] eta: 0:04:02 lr: 0.000763 loss: 3.7050 (3.5171) grad_norm: 1.1511 (inf) time: 0.6297 [2021-03-26 20:27:21 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 880/1251] eta: 0:03:55 lr: 0.000763 loss: 3.7316 (3.5167) grad_norm: 1.0759 (inf) time: 0.6238 [2021-03-26 20:27:27 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 890/1251] eta: 0:03:49 lr: 0.000763 loss: 3.5694 (3.5166) grad_norm: 1.1401 (inf) time: 0.6342 [2021-03-26 20:27:33 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 900/1251] eta: 0:03:43 lr: 0.000763 loss: 3.6634 (3.5182) grad_norm: 1.2180 (inf) time: 0.6389 [2021-03-26 20:27:40 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 910/1251] eta: 0:03:36 lr: 0.000763 loss: 3.7278 (3.5210) grad_norm: 1.1230 (inf) time: 0.6336 [2021-03-26 20:27:46 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 920/1251] eta: 0:03:30 lr: 0.000763 loss: 3.4845 (3.5163) grad_norm: 1.2220 (inf) time: 0.6324 [2021-03-26 20:27:52 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 930/1251] eta: 0:03:24 lr: 0.000763 loss: 3.1945 (3.5162) grad_norm: 1.1995 (inf) time: 0.6324 [2021-03-26 20:27:59 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 940/1251] eta: 0:03:17 lr: 0.000763 loss: 3.1981 (3.5115) grad_norm: 1.1978 (inf) time: 0.6293 [2021-03-26 20:28:05 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 950/1251] eta: 0:03:11 lr: 0.000762 loss: 3.1981 (3.5111) grad_norm: 1.2830 (inf) time: 0.6273 [2021-03-26 20:28:11 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 960/1251] eta: 0:03:04 lr: 0.000762 loss: 3.5804 (3.5120) grad_norm: 1.2658 (inf) time: 0.6288 [2021-03-26 20:28:17 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 970/1251] eta: 0:02:58 lr: 0.000762 loss: 3.4764 (3.5102) grad_norm: 1.1570 (inf) time: 0.6276 [2021-03-26 20:28:24 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 980/1251] eta: 0:02:52 lr: 0.000762 loss: 3.5089 (3.5114) grad_norm: 1.1508 (inf) time: 0.6294 [2021-03-26 20:28:30 swin_base_patch4_window7_224] INFO: Epoch: [97] [ 990/1251] eta: 0:02:45 lr: 0.000762 loss: 3.6591 (3.5110) grad_norm: 1.1652 (inf) time: 0.6317 [2021-03-26 20:28:37 swin_base_patch4_window7_224] INFO: Epoch: [97] [1000/1251] eta: 0:02:39 lr: 0.000762 loss: 3.2996 (3.5091) grad_norm: 1.1752 (inf) time: 0.6365 [2021-03-26 20:28:43 swin_base_patch4_window7_224] INFO: Epoch: [97] [1010/1251] eta: 0:02:33 lr: 0.000762 loss: 3.5790 (3.5097) grad_norm: 1.1782 (inf) time: 0.6312 [2021-03-26 20:28:49 swin_base_patch4_window7_224] INFO: Epoch: [97] [1020/1251] eta: 0:02:26 lr: 0.000762 loss: 3.6828 (3.5117) grad_norm: 1.2287 (inf) time: 0.6267 [2021-03-26 20:28:55 swin_base_patch4_window7_224] INFO: Epoch: [97] [1030/1251] eta: 0:02:20 lr: 0.000762 loss: 3.6125 (3.5121) grad_norm: 1.2355 (inf) time: 0.6249 [2021-03-26 20:29:02 swin_base_patch4_window7_224] INFO: Epoch: [97] [1040/1251] eta: 0:02:13 lr: 0.000762 loss: 3.3109 (3.5094) grad_norm: 1.1062 (inf) time: 0.6211 [2021-03-26 20:29:08 swin_base_patch4_window7_224] INFO: Epoch: [97] [1050/1251] eta: 0:02:07 lr: 0.000762 loss: 3.3047 (3.5111) grad_norm: 1.1505 (inf) time: 0.6269 [2021-03-26 20:29:14 swin_base_patch4_window7_224] INFO: Epoch: [97] [1060/1251] eta: 0:02:01 lr: 0.000762 loss: 3.5462 (3.5097) grad_norm: 1.1876 (inf) time: 0.6300 [2021-03-26 20:29:20 swin_base_patch4_window7_224] INFO: Epoch: [97] [1070/1251] eta: 0:01:54 lr: 0.000762 loss: 3.3873 (3.5084) grad_norm: 1.2196 (inf) time: 0.6271 [2021-03-26 20:29:27 swin_base_patch4_window7_224] INFO: Epoch: [97] [1080/1251] eta: 0:01:48 lr: 0.000762 loss: 3.6012 (3.5083) grad_norm: 1.1490 (inf) time: 0.6230 [2021-03-26 20:29:33 swin_base_patch4_window7_224] INFO: Epoch: [97] [1090/1251] eta: 0:01:42 lr: 0.000762 loss: 3.5328 (3.5072) grad_norm: 1.2249 (inf) time: 0.6255 [2021-03-26 20:29:39 swin_base_patch4_window7_224] INFO: Epoch: [97] [1100/1251] eta: 0:01:35 lr: 0.000762 loss: 3.5174 (3.5068) grad_norm: 1.2681 (inf) time: 0.6285 [2021-03-26 20:29:45 swin_base_patch4_window7_224] INFO: Epoch: [97] [1110/1251] eta: 0:01:29 lr: 0.000762 loss: 3.3804 (3.5044) grad_norm: 1.1896 (inf) time: 0.6249 [2021-03-26 20:29:52 swin_base_patch4_window7_224] INFO: Epoch: [97] [1120/1251] eta: 0:01:23 lr: 0.000762 loss: 3.5405 (3.5055) grad_norm: 1.1323 (inf) time: 0.6278 [2021-03-26 20:29:58 swin_base_patch4_window7_224] INFO: Epoch: [97] [1130/1251] eta: 0:01:16 lr: 0.000762 loss: 3.8016 (3.5073) grad_norm: 1.1630 (inf) time: 0.6324 [2021-03-26 20:30:04 swin_base_patch4_window7_224] INFO: Epoch: [97] [1140/1251] eta: 0:01:10 lr: 0.000762 loss: 3.8270 (3.5082) grad_norm: 1.1954 (inf) time: 0.6316 [2021-03-26 20:30:11 swin_base_patch4_window7_224] INFO: Epoch: [97] [1150/1251] eta: 0:01:04 lr: 0.000762 loss: 3.6531 (3.5086) grad_norm: 1.1314 (inf) time: 0.6264 [2021-03-26 20:30:17 swin_base_patch4_window7_224] INFO: Epoch: [97] [1160/1251] eta: 0:00:57 lr: 0.000762 loss: 3.6531 (3.5090) grad_norm: 1.1293 (inf) time: 0.6293 [2021-03-26 20:30:23 swin_base_patch4_window7_224] INFO: Epoch: [97] [1170/1251] eta: 0:00:51 lr: 0.000762 loss: 3.5906 (3.5106) grad_norm: 1.1677 (inf) time: 0.6340 [2021-03-26 20:30:29 swin_base_patch4_window7_224] INFO: Epoch: [97] [1180/1251] eta: 0:00:45 lr: 0.000762 loss: 3.7358 (3.5127) grad_norm: 1.1635 (inf) time: 0.6255 [2021-03-26 20:30:36 swin_base_patch4_window7_224] INFO: Epoch: [97] [1190/1251] eta: 0:00:38 lr: 0.000762 loss: 3.8712 (3.5148) grad_norm: 1.1259 (inf) time: 0.6288 [2021-03-26 20:30:42 swin_base_patch4_window7_224] INFO: Epoch: [97] [1200/1251] eta: 0:00:32 lr: 0.000762 loss: 3.6705 (3.5145) grad_norm: 1.1445 (inf) time: 0.6283 [2021-03-26 20:30:48 swin_base_patch4_window7_224] INFO: Epoch: [97] [1210/1251] eta: 0:00:25 lr: 0.000762 loss: 3.5289 (3.5134) grad_norm: 1.1663 (inf) time: 0.6302 [2021-03-26 20:30:55 swin_base_patch4_window7_224] INFO: Epoch: [97] [1220/1251] eta: 0:00:19 lr: 0.000762 loss: 3.5288 (3.5135) grad_norm: 1.1604 (inf) time: 0.6360 [2021-03-26 20:31:01 swin_base_patch4_window7_224] INFO: Epoch: [97] [1230/1251] eta: 0:00:13 lr: 0.000761 loss: 3.5288 (3.5130) grad_norm: 1.2560 (inf) time: 0.6335 [2021-03-26 20:31:07 swin_base_patch4_window7_224] INFO: Epoch: [97] [1240/1251] eta: 0:00:06 lr: 0.000761 loss: 3.3574 (3.5106) grad_norm: 1.2506 (inf) time: 0.6335 [2021-03-26 20:31:14 swin_base_patch4_window7_224] INFO: Epoch: [97] [1250/1251] eta: 0:00:00 lr: 0.000761 loss: 3.3574 (3.5105) grad_norm: 1.1921 (inf) time: 0.6246 [2021-03-26 20:31:20 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:54 loss: 1.0892 (1.0892) acc1: 73.4375 (73.4375) acc5: 90.6250 (90.6250) [2021-03-26 20:31:22 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.9887 (0.9914) acc1: 76.5625 (77.5568) acc5: 95.3125 (94.1761) [2021-03-26 20:31:24 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9887 (0.9931) acc1: 78.1250 (77.2321) acc5: 93.7500 (93.6756) [2021-03-26 20:31:26 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9945 (0.9939) acc1: 78.1250 (77.2681) acc5: 93.7500 (93.9012) [2021-03-26 20:31:28 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0484 (1.0212) acc1: 71.8750 (75.8765) acc5: 93.7500 (94.0168) [2021-03-26 20:31:29 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0311 (1.0263) acc1: 71.8750 (75.9040) acc5: 93.7500 (93.9520) [2021-03-26 20:31:35 swin_base_patch4_window7_224] INFO: * Acc@1 76.650 Acc@5 93.710 loss 1.014 [2021-03-26 20:31:35 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.7% [2021-03-26 20:31:35 swin_base_patch4_window7_224] INFO: Max accuracy: 76.65% [2021-03-26 20:31:40 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 0/1251] eta: 1:26:31 lr: 0.000761 loss: 3.8508 (3.8508) grad_norm: 1.1991 (1.1991) time: 4.1502 [2021-03-26 20:31:46 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 10/1251] eta: 0:19:50 lr: 0.000761 loss: 2.8023 (3.2104) grad_norm: 1.0997 (1.1473) time: 0.9595 [2021-03-26 20:31:52 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 20/1251] eta: 0:16:27 lr: 0.000761 loss: 3.5109 (3.4213) grad_norm: 1.1443 (1.1951) time: 0.6347 [2021-03-26 20:31:58 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 30/1251] eta: 0:15:08 lr: 0.000761 loss: 3.7003 (3.5142) grad_norm: 1.1443 (1.2030) time: 0.6261 [2021-03-26 20:32:05 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 40/1251] eta: 0:14:27 lr: 0.000761 loss: 3.8434 (3.5594) grad_norm: 1.1412 (1.1977) time: 0.6272 [2021-03-26 20:32:11 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 50/1251] eta: 0:13:59 lr: 0.000761 loss: 3.5734 (3.5576) grad_norm: 1.1671 (1.2210) time: 0.6294 [2021-03-26 20:32:17 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 60/1251] eta: 0:13:39 lr: 0.000761 loss: 3.5561 (3.5367) grad_norm: 1.2914 (1.2324) time: 0.6304 [2021-03-26 20:32:24 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 70/1251] eta: 0:13:24 lr: 0.000761 loss: 3.3819 (3.5158) grad_norm: 1.2971 (1.2450) time: 0.6362 [2021-03-26 20:32:30 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 80/1251] eta: 0:13:12 lr: 0.000761 loss: 3.4898 (3.5074) grad_norm: 1.2672 (1.2468) time: 0.6423 [2021-03-26 20:32:37 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 90/1251] eta: 0:13:00 lr: 0.000761 loss: 3.6710 (3.5350) grad_norm: 1.2043 (1.2374) time: 0.6406 [2021-03-26 20:32:43 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 100/1251] eta: 0:12:49 lr: 0.000761 loss: 3.7054 (3.5419) grad_norm: 1.2013 (1.2374) time: 0.6341 [2021-03-26 20:32:49 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 110/1251] eta: 0:12:38 lr: 0.000761 loss: 3.5320 (3.5288) grad_norm: 1.2404 (1.2379) time: 0.6281 [2021-03-26 20:32:56 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 120/1251] eta: 0:12:29 lr: 0.000761 loss: 3.3099 (3.5078) grad_norm: 1.1923 (1.2400) time: 0.6319 [2021-03-26 20:33:02 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 130/1251] eta: 0:12:19 lr: 0.000761 loss: 3.4714 (3.5235) grad_norm: 1.1766 (1.2382) time: 0.6331 [2021-03-26 20:33:08 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 140/1251] eta: 0:12:10 lr: 0.000761 loss: 3.4988 (3.5167) grad_norm: 1.1872 (1.2393) time: 0.6282 [2021-03-26 20:33:14 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 150/1251] eta: 0:12:01 lr: 0.000761 loss: 3.2517 (3.5085) grad_norm: 1.2293 (1.2387) time: 0.6263 [2021-03-26 20:33:21 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 160/1251] eta: 0:11:53 lr: 0.000761 loss: 3.3681 (3.5019) grad_norm: 1.2293 (1.2395) time: 0.6306 [2021-03-26 20:33:27 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 170/1251] eta: 0:11:45 lr: 0.000761 loss: 3.4636 (3.4988) grad_norm: 1.2675 (1.2466) time: 0.6341 [2021-03-26 20:33:33 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 180/1251] eta: 0:11:38 lr: 0.000761 loss: 3.7531 (3.5006) grad_norm: 1.2673 (1.2453) time: 0.6366 [2021-03-26 20:33:40 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 190/1251] eta: 0:11:30 lr: 0.000761 loss: 3.7799 (3.5069) grad_norm: 1.2673 (nan) time: 0.6371 [2021-03-26 20:33:46 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 200/1251] eta: 0:11:23 lr: 0.000761 loss: 3.7257 (3.5005) grad_norm: 1.2992 (nan) time: 0.6326 [2021-03-26 20:33:52 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 210/1251] eta: 0:11:15 lr: 0.000761 loss: 3.5720 (3.5025) grad_norm: 1.2820 (nan) time: 0.6309 [2021-03-26 20:33:59 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 220/1251] eta: 0:11:07 lr: 0.000761 loss: 3.5964 (3.5094) grad_norm: 1.1717 (nan) time: 0.6233 [2021-03-26 20:34:05 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 230/1251] eta: 0:11:00 lr: 0.000761 loss: 3.6884 (3.5185) grad_norm: 1.2438 (nan) time: 0.6244 [2021-03-26 20:34:11 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 240/1251] eta: 0:10:53 lr: 0.000761 loss: 3.6332 (3.5178) grad_norm: 1.2438 (nan) time: 0.6280 [2021-03-26 20:34:18 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 250/1251] eta: 0:10:46 lr: 0.000761 loss: 3.5452 (3.5193) grad_norm: 1.2092 (nan) time: 0.6330 [2021-03-26 20:34:24 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 260/1251] eta: 0:10:40 lr: 0.000761 loss: 3.5452 (3.5074) grad_norm: 1.2133 (nan) time: 0.6411 [2021-03-26 20:34:30 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 270/1251] eta: 0:10:33 lr: 0.000760 loss: 3.3912 (3.5004) grad_norm: 1.2133 (nan) time: 0.6368 [2021-03-26 20:34:37 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 280/1251] eta: 0:10:26 lr: 0.000760 loss: 3.2701 (3.4950) grad_norm: 1.2384 (nan) time: 0.6299 [2021-03-26 20:34:43 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 290/1251] eta: 0:10:19 lr: 0.000760 loss: 3.5006 (3.4997) grad_norm: 1.2716 (nan) time: 0.6282 [2021-03-26 20:34:49 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 300/1251] eta: 0:10:12 lr: 0.000760 loss: 3.5796 (3.5064) grad_norm: 1.2070 (nan) time: 0.6296 [2021-03-26 20:34:56 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 310/1251] eta: 0:10:05 lr: 0.000760 loss: 3.4560 (3.5037) grad_norm: 1.1694 (nan) time: 0.6318 [2021-03-26 20:35:02 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 320/1251] eta: 0:09:58 lr: 0.000760 loss: 3.3806 (3.4987) grad_norm: 1.2154 (nan) time: 0.6281 [2021-03-26 20:35:08 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 330/1251] eta: 0:09:51 lr: 0.000760 loss: 3.3806 (3.4976) grad_norm: 1.2354 (nan) time: 0.6280 [2021-03-26 20:35:14 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 340/1251] eta: 0:09:45 lr: 0.000760 loss: 3.5348 (3.4937) grad_norm: 1.1821 (nan) time: 0.6346 [2021-03-26 20:35:21 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 350/1251] eta: 0:09:38 lr: 0.000760 loss: 3.7095 (3.5027) grad_norm: 1.1309 (nan) time: 0.6360 [2021-03-26 20:35:27 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 360/1251] eta: 0:09:31 lr: 0.000760 loss: 3.7095 (3.5016) grad_norm: 1.1316 (nan) time: 0.6329 [2021-03-26 20:35:33 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 370/1251] eta: 0:09:25 lr: 0.000760 loss: 3.3794 (3.4944) grad_norm: 1.1836 (nan) time: 0.6312 [2021-03-26 20:35:40 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 380/1251] eta: 0:09:18 lr: 0.000760 loss: 3.6303 (3.5002) grad_norm: 1.1502 (nan) time: 0.6328 [2021-03-26 20:35:46 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 390/1251] eta: 0:09:12 lr: 0.000760 loss: 3.6303 (3.5008) grad_norm: 1.1939 (nan) time: 0.6358 [2021-03-26 20:35:53 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 400/1251] eta: 0:09:05 lr: 0.000760 loss: 3.6207 (3.5065) grad_norm: 1.2683 (nan) time: 0.6368 [2021-03-26 20:35:59 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 410/1251] eta: 0:08:58 lr: 0.000760 loss: 3.7693 (3.5122) grad_norm: 1.2683 (nan) time: 0.6301 [2021-03-26 20:36:05 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 420/1251] eta: 0:08:52 lr: 0.000760 loss: 3.8025 (3.5151) grad_norm: 1.1646 (nan) time: 0.6326 [2021-03-26 20:36:12 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 430/1251] eta: 0:08:45 lr: 0.000760 loss: 3.7427 (3.5115) grad_norm: 1.1544 (nan) time: 0.6387 [2021-03-26 20:36:18 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 440/1251] eta: 0:08:39 lr: 0.000760 loss: 3.6734 (3.5156) grad_norm: 1.1961 (nan) time: 0.6360 [2021-03-26 20:36:24 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 450/1251] eta: 0:08:32 lr: 0.000760 loss: 3.6734 (3.5187) grad_norm: 1.2462 (nan) time: 0.6351 [2021-03-26 20:36:30 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 460/1251] eta: 0:08:26 lr: 0.000760 loss: 3.6295 (3.5167) grad_norm: 1.2462 (nan) time: 0.6270 [2021-03-26 20:36:37 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 470/1251] eta: 0:08:19 lr: 0.000760 loss: 3.3778 (3.5133) grad_norm: 1.2077 (nan) time: 0.6245 [2021-03-26 20:36:43 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 480/1251] eta: 0:08:12 lr: 0.000760 loss: 3.3778 (3.5141) grad_norm: 1.2263 (nan) time: 0.6282 [2021-03-26 20:36:49 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 490/1251] eta: 0:08:06 lr: 0.000760 loss: 3.2229 (3.5073) grad_norm: 1.2311 (nan) time: 0.6234 [2021-03-26 20:36:55 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 500/1251] eta: 0:07:59 lr: 0.000760 loss: 3.4399 (3.5069) grad_norm: 1.1766 (nan) time: 0.6229 [2021-03-26 20:37:02 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 510/1251] eta: 0:07:53 lr: 0.000760 loss: 3.4863 (3.5072) grad_norm: 1.1805 (nan) time: 0.6282 [2021-03-26 20:37:08 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 520/1251] eta: 0:07:46 lr: 0.000760 loss: 3.4228 (3.5078) grad_norm: 1.1500 (nan) time: 0.6330 [2021-03-26 20:37:14 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 530/1251] eta: 0:07:40 lr: 0.000760 loss: 3.5490 (3.5106) grad_norm: 1.1668 (nan) time: 0.6346 [2021-03-26 20:37:21 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 540/1251] eta: 0:07:33 lr: 0.000760 loss: 3.5227 (3.5070) grad_norm: 1.1972 (nan) time: 0.6357 [2021-03-26 20:37:27 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 550/1251] eta: 0:07:27 lr: 0.000759 loss: 3.1961 (3.5012) grad_norm: 1.1844 (nan) time: 0.6440 [2021-03-26 20:37:34 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 560/1251] eta: 0:07:21 lr: 0.000759 loss: 3.3305 (3.5008) grad_norm: 1.2288 (nan) time: 0.6500 [2021-03-26 20:37:40 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 570/1251] eta: 0:07:14 lr: 0.000759 loss: 3.6297 (3.5023) grad_norm: 1.2588 (nan) time: 0.6395 [2021-03-26 20:37:46 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 580/1251] eta: 0:07:08 lr: 0.000759 loss: 3.7351 (3.5001) grad_norm: 1.2598 (nan) time: 0.6265 [2021-03-26 20:37:53 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 590/1251] eta: 0:07:01 lr: 0.000759 loss: 3.5872 (3.4970) grad_norm: 1.2343 (nan) time: 0.6253 [2021-03-26 20:37:59 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 600/1251] eta: 0:06:55 lr: 0.000759 loss: 3.5872 (3.4988) grad_norm: 1.1584 (nan) time: 0.6270 [2021-03-26 20:38:05 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 610/1251] eta: 0:06:48 lr: 0.000759 loss: 3.4793 (3.4939) grad_norm: 1.0986 (nan) time: 0.6288 [2021-03-26 20:38:12 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 620/1251] eta: 0:06:42 lr: 0.000759 loss: 3.2731 (3.4898) grad_norm: 1.0931 (nan) time: 0.6298 [2021-03-26 20:38:18 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 630/1251] eta: 0:06:36 lr: 0.000759 loss: 3.4316 (3.4898) grad_norm: 1.2087 (nan) time: 0.6325 [2021-03-26 20:38:24 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 640/1251] eta: 0:06:29 lr: 0.000759 loss: 3.5131 (3.4884) grad_norm: 1.2087 (nan) time: 0.6273 [2021-03-26 20:38:30 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 650/1251] eta: 0:06:23 lr: 0.000759 loss: 3.3168 (3.4854) grad_norm: 1.1822 (nan) time: 0.6242 [2021-03-26 20:38:37 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 660/1251] eta: 0:06:16 lr: 0.000759 loss: 3.5289 (3.4885) grad_norm: 1.1759 (nan) time: 0.6289 [2021-03-26 20:38:43 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 670/1251] eta: 0:06:10 lr: 0.000759 loss: 3.7199 (3.4888) grad_norm: 1.1746 (nan) time: 0.6265 [2021-03-26 20:38:49 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 680/1251] eta: 0:06:03 lr: 0.000759 loss: 3.5312 (3.4905) grad_norm: 1.1412 (nan) time: 0.6300 [2021-03-26 20:38:55 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 690/1251] eta: 0:05:57 lr: 0.000759 loss: 3.3972 (3.4903) grad_norm: 1.1712 (nan) time: 0.6298 [2021-03-26 20:39:02 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 700/1251] eta: 0:05:50 lr: 0.000759 loss: 3.6727 (3.4922) grad_norm: 1.1866 (nan) time: 0.6266 [2021-03-26 20:39:08 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 710/1251] eta: 0:05:44 lr: 0.000759 loss: 3.7175 (3.4900) grad_norm: 1.1587 (nan) time: 0.6307 [2021-03-26 20:39:14 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 720/1251] eta: 0:05:37 lr: 0.000759 loss: 3.3755 (3.4901) grad_norm: 1.2662 (nan) time: 0.6268 [2021-03-26 20:39:21 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 730/1251] eta: 0:05:31 lr: 0.000759 loss: 3.5842 (3.4900) grad_norm: 1.2781 (nan) time: 0.6311 [2021-03-26 20:39:27 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 740/1251] eta: 0:05:25 lr: 0.000759 loss: 3.6500 (3.4923) grad_norm: 1.2635 (nan) time: 0.6388 [2021-03-26 20:39:33 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 750/1251] eta: 0:05:18 lr: 0.000759 loss: 3.4166 (3.4894) grad_norm: 1.2222 (nan) time: 0.6353 [2021-03-26 20:39:40 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 760/1251] eta: 0:05:12 lr: 0.000759 loss: 3.3701 (3.4849) grad_norm: 1.2222 (nan) time: 0.6359 [2021-03-26 20:39:46 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 770/1251] eta: 0:05:06 lr: 0.000759 loss: 3.4513 (3.4850) grad_norm: 1.1896 (nan) time: 0.6382 [2021-03-26 20:39:52 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 780/1251] eta: 0:04:59 lr: 0.000759 loss: 3.6282 (3.4861) grad_norm: 1.1946 (nan) time: 0.6331 [2021-03-26 20:39:59 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 790/1251] eta: 0:04:53 lr: 0.000759 loss: 3.8588 (3.4900) grad_norm: 1.1813 (nan) time: 0.6271 [2021-03-26 20:40:05 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 800/1251] eta: 0:04:46 lr: 0.000759 loss: 3.6972 (3.4893) grad_norm: 1.1798 (nan) time: 0.6234 [2021-03-26 20:40:11 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 810/1251] eta: 0:04:40 lr: 0.000759 loss: 3.3586 (3.4851) grad_norm: 1.2453 (nan) time: 0.6262 [2021-03-26 20:40:18 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 820/1251] eta: 0:04:34 lr: 0.000759 loss: 2.8826 (3.4833) grad_norm: 1.2606 (nan) time: 0.6290 [2021-03-26 20:40:24 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 830/1251] eta: 0:04:27 lr: 0.000758 loss: 2.8826 (3.4794) grad_norm: 1.2455 (nan) time: 0.6200 [2021-03-26 20:40:30 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 840/1251] eta: 0:04:21 lr: 0.000758 loss: 3.3853 (3.4778) grad_norm: 1.2199 (nan) time: 0.6302 [2021-03-26 20:40:36 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 850/1251] eta: 0:04:14 lr: 0.000758 loss: 3.5153 (3.4788) grad_norm: 1.2389 (nan) time: 0.6363 [2021-03-26 20:40:43 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 860/1251] eta: 0:04:08 lr: 0.000758 loss: 3.7359 (3.4796) grad_norm: 1.2023 (nan) time: 0.6276 [2021-03-26 20:40:49 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 870/1251] eta: 0:04:02 lr: 0.000758 loss: 3.6766 (3.4813) grad_norm: 1.1802 (nan) time: 0.6327 [2021-03-26 20:40:55 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 880/1251] eta: 0:03:55 lr: 0.000758 loss: 3.5963 (3.4841) grad_norm: 1.1942 (nan) time: 0.6319 [2021-03-26 20:41:02 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 890/1251] eta: 0:03:49 lr: 0.000758 loss: 3.5583 (3.4837) grad_norm: 1.1942 (nan) time: 0.6351 [2021-03-26 20:41:08 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 900/1251] eta: 0:03:43 lr: 0.000758 loss: 3.4734 (3.4835) grad_norm: 1.2662 (nan) time: 0.6336 [2021-03-26 20:41:14 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 910/1251] eta: 0:03:36 lr: 0.000758 loss: 3.6198 (3.4843) grad_norm: 1.2070 (nan) time: 0.6294 [2021-03-26 20:41:21 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 920/1251] eta: 0:03:30 lr: 0.000758 loss: 3.6198 (3.4855) grad_norm: 1.1780 (nan) time: 0.6272 [2021-03-26 20:41:27 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 930/1251] eta: 0:03:23 lr: 0.000758 loss: 3.6191 (3.4874) grad_norm: 1.2022 (nan) time: 0.6270 [2021-03-26 20:41:33 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 940/1251] eta: 0:03:17 lr: 0.000758 loss: 3.6338 (3.4895) grad_norm: 1.1863 (nan) time: 0.6382 [2021-03-26 20:41:40 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 950/1251] eta: 0:03:11 lr: 0.000758 loss: 3.8197 (3.4941) grad_norm: 1.2141 (nan) time: 0.6394 [2021-03-26 20:41:46 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 960/1251] eta: 0:03:04 lr: 0.000758 loss: 3.7996 (3.4954) grad_norm: 1.2062 (nan) time: 0.6329 [2021-03-26 20:41:52 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 970/1251] eta: 0:02:58 lr: 0.000758 loss: 3.5388 (3.4942) grad_norm: 1.1462 (nan) time: 0.6296 [2021-03-26 20:41:59 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 980/1251] eta: 0:02:52 lr: 0.000758 loss: 3.5720 (3.4951) grad_norm: 1.1792 (nan) time: 0.6333 [2021-03-26 20:42:05 swin_base_patch4_window7_224] INFO: Epoch: [98] [ 990/1251] eta: 0:02:45 lr: 0.000758 loss: 3.6007 (3.4952) grad_norm: 1.1792 (nan) time: 0.6314 [2021-03-26 20:42:11 swin_base_patch4_window7_224] INFO: Epoch: [98] [1000/1251] eta: 0:02:39 lr: 0.000758 loss: 3.7392 (3.4965) grad_norm: 1.1483 (nan) time: 0.6272 [2021-03-26 20:42:18 swin_base_patch4_window7_224] INFO: Epoch: [98] [1010/1251] eta: 0:02:33 lr: 0.000758 loss: 3.6913 (3.4970) grad_norm: 1.1912 (nan) time: 0.6320 [2021-03-26 20:42:24 swin_base_patch4_window7_224] INFO: Epoch: [98] [1020/1251] eta: 0:02:26 lr: 0.000758 loss: 3.6259 (3.4977) grad_norm: 1.2376 (nan) time: 0.6311 [2021-03-26 20:42:30 swin_base_patch4_window7_224] INFO: Epoch: [98] [1030/1251] eta: 0:02:20 lr: 0.000758 loss: 3.4682 (3.4971) grad_norm: 1.2381 (nan) time: 0.6255 [2021-03-26 20:42:36 swin_base_patch4_window7_224] INFO: Epoch: [98] [1040/1251] eta: 0:02:13 lr: 0.000758 loss: 3.4587 (3.4982) grad_norm: 1.2025 (nan) time: 0.6278 [2021-03-26 20:42:43 swin_base_patch4_window7_224] INFO: Epoch: [98] [1050/1251] eta: 0:02:07 lr: 0.000758 loss: 3.4893 (3.4988) grad_norm: 1.1552 (nan) time: 0.6305 [2021-03-26 20:42:49 swin_base_patch4_window7_224] INFO: Epoch: [98] [1060/1251] eta: 0:02:01 lr: 0.000758 loss: 3.6717 (3.4993) grad_norm: 1.1784 (nan) time: 0.6299 [2021-03-26 20:42:55 swin_base_patch4_window7_224] INFO: Epoch: [98] [1070/1251] eta: 0:01:54 lr: 0.000758 loss: 3.6717 (3.4982) grad_norm: 1.1581 (nan) time: 0.6272 [2021-03-26 20:43:01 swin_base_patch4_window7_224] INFO: Epoch: [98] [1080/1251] eta: 0:01:48 lr: 0.000758 loss: 3.7346 (3.5011) grad_norm: 1.1450 (nan) time: 0.6237 [2021-03-26 20:43:08 swin_base_patch4_window7_224] INFO: Epoch: [98] [1090/1251] eta: 0:01:42 lr: 0.000758 loss: 3.5211 (3.4996) grad_norm: 1.2299 (nan) time: 0.6266 [2021-03-26 20:43:14 swin_base_patch4_window7_224] INFO: Epoch: [98] [1100/1251] eta: 0:01:35 lr: 0.000758 loss: 3.5022 (3.4996) grad_norm: 1.2330 (nan) time: 0.6293 [2021-03-26 20:43:20 swin_base_patch4_window7_224] INFO: Epoch: [98] [1110/1251] eta: 0:01:29 lr: 0.000757 loss: 3.5695 (3.4987) grad_norm: 1.2145 (nan) time: 0.6310 [2021-03-26 20:43:27 swin_base_patch4_window7_224] INFO: Epoch: [98] [1120/1251] eta: 0:01:23 lr: 0.000757 loss: 3.6443 (3.4987) grad_norm: 1.2253 (nan) time: 0.6319 [2021-03-26 20:43:33 swin_base_patch4_window7_224] INFO: Epoch: [98] [1130/1251] eta: 0:01:16 lr: 0.000757 loss: 3.6467 (3.4992) grad_norm: 1.2244 (nan) time: 0.6309 [2021-03-26 20:43:39 swin_base_patch4_window7_224] INFO: Epoch: [98] [1140/1251] eta: 0:01:10 lr: 0.000757 loss: 3.5082 (3.4986) grad_norm: 1.1725 (nan) time: 0.6302 [2021-03-26 20:43:46 swin_base_patch4_window7_224] INFO: Epoch: [98] [1150/1251] eta: 0:01:04 lr: 0.000757 loss: 3.8043 (3.5006) grad_norm: 1.1333 (nan) time: 0.6277 [2021-03-26 20:43:52 swin_base_patch4_window7_224] INFO: Epoch: [98] [1160/1251] eta: 0:00:57 lr: 0.000757 loss: 3.7742 (3.4996) grad_norm: 1.1292 (nan) time: 0.6282 [2021-03-26 20:43:58 swin_base_patch4_window7_224] INFO: Epoch: [98] [1170/1251] eta: 0:00:51 lr: 0.000757 loss: 3.6764 (3.5013) grad_norm: 1.1249 (nan) time: 0.6306 [2021-03-26 20:44:04 swin_base_patch4_window7_224] INFO: Epoch: [98] [1180/1251] eta: 0:00:45 lr: 0.000757 loss: 3.7438 (3.5027) grad_norm: 1.1461 (nan) time: 0.6282 [2021-03-26 20:44:11 swin_base_patch4_window7_224] INFO: Epoch: [98] [1190/1251] eta: 0:00:38 lr: 0.000757 loss: 3.6527 (3.5017) grad_norm: 1.2092 (nan) time: 0.6267 [2021-03-26 20:44:17 swin_base_patch4_window7_224] INFO: Epoch: [98] [1200/1251] eta: 0:00:32 lr: 0.000757 loss: 3.5681 (3.5028) grad_norm: 1.1944 (nan) time: 0.6251 [2021-03-26 20:44:23 swin_base_patch4_window7_224] INFO: Epoch: [98] [1210/1251] eta: 0:00:25 lr: 0.000757 loss: 3.5381 (3.5017) grad_norm: 1.1740 (nan) time: 0.6270 [2021-03-26 20:44:30 swin_base_patch4_window7_224] INFO: Epoch: [98] [1220/1251] eta: 0:00:19 lr: 0.000757 loss: 3.4987 (3.5010) grad_norm: 1.1193 (nan) time: 0.6347 [2021-03-26 20:44:36 swin_base_patch4_window7_224] INFO: Epoch: [98] [1230/1251] eta: 0:00:13 lr: 0.000757 loss: 3.4821 (3.5003) grad_norm: 1.1191 (nan) time: 0.6373 [2021-03-26 20:44:42 swin_base_patch4_window7_224] INFO: Epoch: [98] [1240/1251] eta: 0:00:06 lr: 0.000757 loss: 3.3535 (3.4981) grad_norm: 1.1468 (nan) time: 0.6266 [2021-03-26 20:44:48 swin_base_patch4_window7_224] INFO: Epoch: [98] [1250/1251] eta: 0:00:00 lr: 0.000757 loss: 3.5225 (3.5001) grad_norm: 1.2089 (nan) time: 0.6132 [2021-03-26 20:44:54 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:52 loss: 0.9468 (0.9468) acc1: 79.6875 (79.6875) acc5: 93.7500 (93.7500) [2021-03-26 20:44:57 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.0040 (1.0446) acc1: 76.5625 (76.4205) acc5: 93.7500 (94.1761) [2021-03-26 20:45:00 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.0462 (1.0767) acc1: 76.5625 (74.9256) acc5: 93.7500 (94.1964) [2021-03-26 20:45:02 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0372 (1.0501) acc1: 75.0000 (75.3528) acc5: 93.7500 (94.1028) [2021-03-26 20:45:04 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9541 (1.0322) acc1: 75.0000 (75.8003) acc5: 93.7500 (94.1692) [2021-03-26 20:45:05 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9478 (1.0139) acc1: 77.3585 (76.3200) acc5: 94.3396 (94.2080) [2021-03-26 20:45:09 swin_base_patch4_window7_224] INFO: * Acc@1 76.454 Acc@5 93.780 loss 1.008 [2021-03-26 20:45:09 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.5% [2021-03-26 20:45:09 swin_base_patch4_window7_224] INFO: Max accuracy: 76.65% [2021-03-26 20:45:13 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 0/1251] eta: 1:23:55 lr: 0.000757 loss: 2.8744 (2.8744) grad_norm: 1.0832 (1.0832) time: 4.0250 [2021-03-26 20:45:20 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 10/1251] eta: 0:20:11 lr: 0.000757 loss: 3.1207 (3.0636) grad_norm: 1.2088 (1.2708) time: 0.9761 [2021-03-26 20:45:26 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 20/1251] eta: 0:16:36 lr: 0.000757 loss: 3.2632 (3.4011) grad_norm: 1.2088 (1.2980) time: 0.6490 [2021-03-26 20:45:32 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 30/1251] eta: 0:15:20 lr: 0.000757 loss: 3.8044 (3.4812) grad_norm: 1.2245 (1.2853) time: 0.6317 [2021-03-26 20:45:39 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 40/1251] eta: 0:14:39 lr: 0.000757 loss: 3.6632 (3.5001) grad_norm: 1.2245 (1.2834) time: 0.6385 [2021-03-26 20:45:45 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 50/1251] eta: 0:14:10 lr: 0.000757 loss: 3.5957 (3.5163) grad_norm: 1.1823 (1.2706) time: 0.6367 [2021-03-26 20:45:51 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 60/1251] eta: 0:13:46 lr: 0.000757 loss: 3.4904 (3.4646) grad_norm: 1.1365 (1.2468) time: 0.6270 [2021-03-26 20:45:58 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 70/1251] eta: 0:13:30 lr: 0.000757 loss: 3.4443 (3.4613) grad_norm: 1.1212 (1.2336) time: 0.6297 [2021-03-26 20:46:04 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 80/1251] eta: 0:13:15 lr: 0.000757 loss: 3.4443 (3.4671) grad_norm: 1.1746 (1.2396) time: 0.6342 [2021-03-26 20:46:10 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 90/1251] eta: 0:13:01 lr: 0.000757 loss: 3.6342 (3.4794) grad_norm: 1.2065 (1.2348) time: 0.6292 [2021-03-26 20:46:17 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 100/1251] eta: 0:12:48 lr: 0.000757 loss: 3.2314 (3.4349) grad_norm: 1.1553 (1.2228) time: 0.6233 [2021-03-26 20:46:23 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 110/1251] eta: 0:12:39 lr: 0.000757 loss: 3.1564 (3.4407) grad_norm: 1.1631 (1.2226) time: 0.6299 [2021-03-26 20:46:29 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 120/1251] eta: 0:12:28 lr: 0.000757 loss: 3.5166 (3.4462) grad_norm: 1.1757 (1.2218) time: 0.6334 [2021-03-26 20:46:36 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 130/1251] eta: 0:12:19 lr: 0.000757 loss: 3.2165 (3.4128) grad_norm: 1.2818 (1.2310) time: 0.6284 [2021-03-26 20:46:42 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 140/1251] eta: 0:12:10 lr: 0.000756 loss: 3.2315 (3.4170) grad_norm: 1.2818 (1.2340) time: 0.6275 [2021-03-26 20:46:48 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 150/1251] eta: 0:12:01 lr: 0.000756 loss: 3.3240 (3.4066) grad_norm: 1.2069 (1.2311) time: 0.6255 [2021-03-26 20:46:54 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 160/1251] eta: 0:11:52 lr: 0.000756 loss: 3.5636 (3.4265) grad_norm: 1.2069 (1.2346) time: 0.6250 [2021-03-26 20:47:01 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 170/1251] eta: 0:11:44 lr: 0.000756 loss: 3.7934 (3.4361) grad_norm: 1.2143 (1.2352) time: 0.6270 [2021-03-26 20:47:07 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 180/1251] eta: 0:11:37 lr: 0.000756 loss: 3.6163 (3.4295) grad_norm: 1.1783 (1.2334) time: 0.6346 [2021-03-26 20:47:13 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 190/1251] eta: 0:11:29 lr: 0.000756 loss: 3.6163 (3.4463) grad_norm: 1.1756 (1.2321) time: 0.6338 [2021-03-26 20:47:20 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 200/1251] eta: 0:11:21 lr: 0.000756 loss: 3.5123 (3.4368) grad_norm: 1.1682 (1.2352) time: 0.6278 [2021-03-26 20:47:26 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 210/1251] eta: 0:11:14 lr: 0.000756 loss: 3.3810 (3.4373) grad_norm: 1.1014 (1.2308) time: 0.6274 [2021-03-26 20:47:32 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 220/1251] eta: 0:11:07 lr: 0.000756 loss: 3.4226 (3.4290) grad_norm: 1.1064 (1.2312) time: 0.6308 [2021-03-26 20:47:38 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 230/1251] eta: 0:10:59 lr: 0.000756 loss: 3.3517 (3.4250) grad_norm: 1.2122 (1.2314) time: 0.6293 [2021-03-26 20:47:45 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 240/1251] eta: 0:10:52 lr: 0.000756 loss: 3.6200 (3.4420) grad_norm: 1.1620 (1.2288) time: 0.6259 [2021-03-26 20:47:51 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 250/1251] eta: 0:10:45 lr: 0.000756 loss: 3.6796 (3.4448) grad_norm: 1.1531 (1.2260) time: 0.6301 [2021-03-26 20:47:57 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 260/1251] eta: 0:10:38 lr: 0.000756 loss: 3.7241 (3.4607) grad_norm: 1.1702 (1.2253) time: 0.6342 [2021-03-26 20:48:04 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 270/1251] eta: 0:10:31 lr: 0.000756 loss: 3.7178 (3.4575) grad_norm: 1.1896 (1.2239) time: 0.6328 [2021-03-26 20:48:10 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 280/1251] eta: 0:10:24 lr: 0.000756 loss: 3.5954 (3.4571) grad_norm: 1.1855 (1.2247) time: 0.6280 [2021-03-26 20:48:16 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 290/1251] eta: 0:10:17 lr: 0.000756 loss: 3.5317 (3.4540) grad_norm: 1.2328 (1.2276) time: 0.6262 [2021-03-26 20:48:23 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 300/1251] eta: 0:10:11 lr: 0.000756 loss: 3.3262 (3.4467) grad_norm: 1.2029 (1.2253) time: 0.6292 [2021-03-26 20:48:29 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 310/1251] eta: 0:10:04 lr: 0.000756 loss: 3.3322 (3.4520) grad_norm: 1.1970 (1.2266) time: 0.6302 [2021-03-26 20:48:35 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 320/1251] eta: 0:09:57 lr: 0.000756 loss: 3.5861 (3.4508) grad_norm: 1.2099 (1.2257) time: 0.6284 [2021-03-26 20:48:42 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 330/1251] eta: 0:09:50 lr: 0.000756 loss: 3.5015 (3.4552) grad_norm: 1.1990 (1.2276) time: 0.6314 [2021-03-26 20:48:48 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 340/1251] eta: 0:09:44 lr: 0.000756 loss: 3.6139 (3.4627) grad_norm: 1.2991 (1.2289) time: 0.6346 [2021-03-26 20:48:54 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 350/1251] eta: 0:09:37 lr: 0.000756 loss: 3.6569 (3.4656) grad_norm: 1.2123 (1.2295) time: 0.6317 [2021-03-26 20:49:01 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 360/1251] eta: 0:09:30 lr: 0.000756 loss: 3.4102 (3.4597) grad_norm: 1.2064 (1.2303) time: 0.6335 [2021-03-26 20:49:07 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 370/1251] eta: 0:09:24 lr: 0.000756 loss: 3.6912 (3.4717) grad_norm: 1.2106 (1.2310) time: 0.6358 [2021-03-26 20:49:13 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 380/1251] eta: 0:09:17 lr: 0.000756 loss: 3.8520 (3.4763) grad_norm: 1.2133 (1.2318) time: 0.6299 [2021-03-26 20:49:19 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 390/1251] eta: 0:09:11 lr: 0.000756 loss: 3.7216 (3.4826) grad_norm: 1.1911 (1.2293) time: 0.6301 [2021-03-26 20:49:26 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 400/1251] eta: 0:09:04 lr: 0.000756 loss: 3.6918 (3.4826) grad_norm: 1.1733 (1.2284) time: 0.6308 [2021-03-26 20:49:32 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 410/1251] eta: 0:08:57 lr: 0.000756 loss: 3.4586 (3.4838) grad_norm: 1.1468 (1.2277) time: 0.6252 [2021-03-26 20:49:38 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 420/1251] eta: 0:08:51 lr: 0.000755 loss: 3.3660 (3.4840) grad_norm: 1.1418 (1.2269) time: 0.6242 [2021-03-26 20:49:44 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 430/1251] eta: 0:08:44 lr: 0.000755 loss: 3.5172 (3.4844) grad_norm: 1.1377 (1.2259) time: 0.6224 [2021-03-26 20:49:51 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 440/1251] eta: 0:08:37 lr: 0.000755 loss: 3.5977 (3.4824) grad_norm: 1.1546 (1.2259) time: 0.6238 [2021-03-26 20:49:57 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 450/1251] eta: 0:08:31 lr: 0.000755 loss: 3.6102 (3.4869) grad_norm: 1.2066 (1.2259) time: 0.6269 [2021-03-26 20:50:03 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 460/1251] eta: 0:08:24 lr: 0.000755 loss: 3.7297 (3.4919) grad_norm: 1.2451 (1.2291) time: 0.6295 [2021-03-26 20:50:10 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 470/1251] eta: 0:08:18 lr: 0.000755 loss: 3.6317 (3.4848) grad_norm: 1.2418 (1.2276) time: 0.6306 [2021-03-26 20:50:16 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 480/1251] eta: 0:08:11 lr: 0.000755 loss: 3.2409 (3.4807) grad_norm: 1.2336 (1.2293) time: 0.6289 [2021-03-26 20:50:22 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 490/1251] eta: 0:08:05 lr: 0.000755 loss: 3.5817 (3.4827) grad_norm: 1.2767 (1.2311) time: 0.6280 [2021-03-26 20:50:28 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 500/1251] eta: 0:07:58 lr: 0.000755 loss: 3.6161 (3.4809) grad_norm: 1.2850 (1.2328) time: 0.6286 [2021-03-26 20:50:35 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 510/1251] eta: 0:07:52 lr: 0.000755 loss: 3.4469 (3.4770) grad_norm: 1.3123 (1.2346) time: 0.6325 [2021-03-26 20:50:41 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 520/1251] eta: 0:07:45 lr: 0.000755 loss: 3.4366 (3.4764) grad_norm: 1.3144 (1.2368) time: 0.6347 [2021-03-26 20:50:47 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 530/1251] eta: 0:07:39 lr: 0.000755 loss: 3.4298 (3.4702) grad_norm: 1.2228 (1.2353) time: 0.6323 [2021-03-26 20:50:54 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 540/1251] eta: 0:07:32 lr: 0.000755 loss: 3.4073 (3.4684) grad_norm: 1.1756 (1.2365) time: 0.6266 [2021-03-26 20:51:00 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 550/1251] eta: 0:07:26 lr: 0.000755 loss: 3.7285 (3.4704) grad_norm: 1.2493 (1.2379) time: 0.6348 [2021-03-26 20:51:06 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 560/1251] eta: 0:07:20 lr: 0.000755 loss: 3.6805 (3.4696) grad_norm: 1.2831 (1.2387) time: 0.6404 [2021-03-26 20:51:13 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 570/1251] eta: 0:07:13 lr: 0.000755 loss: 3.6949 (3.4755) grad_norm: 1.1891 (1.2382) time: 0.6314 [2021-03-26 20:51:19 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 580/1251] eta: 0:07:07 lr: 0.000755 loss: 3.7388 (3.4752) grad_norm: 1.1891 (1.2377) time: 0.6283 [2021-03-26 20:51:25 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 590/1251] eta: 0:07:00 lr: 0.000755 loss: 3.6741 (3.4744) grad_norm: 1.1592 (1.2357) time: 0.6351 [2021-03-26 20:51:32 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 600/1251] eta: 0:06:54 lr: 0.000755 loss: 3.5759 (3.4746) grad_norm: 1.1028 (1.2349) time: 0.6378 [2021-03-26 20:51:38 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 610/1251] eta: 0:06:48 lr: 0.000755 loss: 3.5087 (3.4742) grad_norm: 1.1524 (1.2342) time: 0.6366 [2021-03-26 20:51:44 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 620/1251] eta: 0:06:41 lr: 0.000755 loss: 3.3844 (3.4699) grad_norm: 1.1849 (1.2345) time: 0.6300 [2021-03-26 20:51:51 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 630/1251] eta: 0:06:35 lr: 0.000755 loss: 3.3631 (3.4671) grad_norm: 1.2181 (1.2344) time: 0.6204 [2021-03-26 20:51:57 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 640/1251] eta: 0:06:28 lr: 0.000755 loss: 3.6870 (3.4720) grad_norm: 1.2016 (1.2349) time: 0.6237 [2021-03-26 20:52:03 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 650/1251] eta: 0:06:22 lr: 0.000755 loss: 3.7345 (3.4764) grad_norm: 1.2153 (1.2344) time: 0.6255 [2021-03-26 20:52:10 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 660/1251] eta: 0:06:15 lr: 0.000755 loss: 3.6884 (3.4754) grad_norm: 1.2704 (1.2369) time: 0.6330 [2021-03-26 20:52:16 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 670/1251] eta: 0:06:09 lr: 0.000755 loss: 3.5138 (3.4734) grad_norm: 1.2873 (1.2372) time: 0.6378 [2021-03-26 20:52:22 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 680/1251] eta: 0:06:03 lr: 0.000755 loss: 3.5138 (3.4715) grad_norm: 1.2862 (1.2390) time: 0.6356 [2021-03-26 20:52:29 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 690/1251] eta: 0:05:56 lr: 0.000755 loss: 3.1532 (3.4694) grad_norm: 1.2928 (1.2402) time: 0.6304 [2021-03-26 20:52:35 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 700/1251] eta: 0:05:50 lr: 0.000754 loss: 3.4532 (3.4721) grad_norm: 1.2296 (1.2408) time: 0.6250 [2021-03-26 20:52:41 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 710/1251] eta: 0:05:43 lr: 0.000754 loss: 3.5246 (3.4702) grad_norm: 1.2296 (1.2425) time: 0.6290 [2021-03-26 20:52:47 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 720/1251] eta: 0:05:37 lr: 0.000754 loss: 3.5246 (3.4698) grad_norm: 1.2069 (1.2426) time: 0.6353 [2021-03-26 20:52:54 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 730/1251] eta: 0:05:31 lr: 0.000754 loss: 3.5127 (3.4683) grad_norm: 1.1596 (1.2417) time: 0.6421 [2021-03-26 20:53:00 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 740/1251] eta: 0:05:24 lr: 0.000754 loss: 3.4104 (3.4697) grad_norm: 1.2364 (1.2426) time: 0.6403 [2021-03-26 20:53:07 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 750/1251] eta: 0:05:18 lr: 0.000754 loss: 3.6171 (3.4732) grad_norm: 1.2760 (1.2425) time: 0.6366 [2021-03-26 20:53:13 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 760/1251] eta: 0:05:12 lr: 0.000754 loss: 3.6718 (3.4725) grad_norm: 1.2196 (1.2419) time: 0.6323 [2021-03-26 20:53:19 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 770/1251] eta: 0:05:05 lr: 0.000754 loss: 3.6639 (3.4708) grad_norm: 1.2024 (1.2419) time: 0.6275 [2021-03-26 20:53:26 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 780/1251] eta: 0:04:59 lr: 0.000754 loss: 3.5757 (3.4722) grad_norm: 1.2531 (1.2421) time: 0.6326 [2021-03-26 20:53:32 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 790/1251] eta: 0:04:53 lr: 0.000754 loss: 3.7356 (3.4748) grad_norm: 1.2660 (1.2426) time: 0.6405 [2021-03-26 20:53:38 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 800/1251] eta: 0:04:46 lr: 0.000754 loss: 3.5877 (3.4733) grad_norm: 1.2299 (1.2422) time: 0.6422 [2021-03-26 20:53:45 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 810/1251] eta: 0:04:40 lr: 0.000754 loss: 3.5489 (3.4777) grad_norm: 1.1679 (1.2419) time: 0.6337 [2021-03-26 20:53:51 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 820/1251] eta: 0:04:33 lr: 0.000754 loss: 3.6025 (3.4784) grad_norm: 1.1509 (1.2411) time: 0.6304 [2021-03-26 20:53:57 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 830/1251] eta: 0:04:27 lr: 0.000754 loss: 3.6330 (3.4802) grad_norm: 1.1509 (1.2418) time: 0.6355 [2021-03-26 20:54:04 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 840/1251] eta: 0:04:21 lr: 0.000754 loss: 3.5207 (3.4774) grad_norm: 1.2257 (1.2429) time: 0.6300 [2021-03-26 20:54:10 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 850/1251] eta: 0:04:14 lr: 0.000754 loss: 3.2899 (3.4778) grad_norm: 1.2646 (1.2432) time: 0.6260 [2021-03-26 20:54:16 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 860/1251] eta: 0:04:08 lr: 0.000754 loss: 3.5624 (3.4802) grad_norm: 1.2044 (1.2425) time: 0.6340 [2021-03-26 20:54:23 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 870/1251] eta: 0:04:02 lr: 0.000754 loss: 3.5793 (3.4803) grad_norm: 1.2064 (1.2422) time: 0.6296 [2021-03-26 20:54:29 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 880/1251] eta: 0:03:55 lr: 0.000754 loss: 3.5793 (3.4810) grad_norm: 1.2100 (1.2420) time: 0.6282 [2021-03-26 20:54:35 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 890/1251] eta: 0:03:49 lr: 0.000754 loss: 3.6066 (3.4802) grad_norm: 1.2161 (1.2417) time: 0.6284 [2021-03-26 20:54:41 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 900/1251] eta: 0:03:42 lr: 0.000754 loss: 3.6066 (3.4809) grad_norm: 1.1712 (1.2414) time: 0.6249 [2021-03-26 20:54:48 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 910/1251] eta: 0:03:36 lr: 0.000754 loss: 3.4591 (3.4787) grad_norm: 1.1636 (1.2408) time: 0.6260 [2021-03-26 20:54:54 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 920/1251] eta: 0:03:30 lr: 0.000754 loss: 3.5743 (3.4806) grad_norm: 1.1848 (1.2403) time: 0.6245 [2021-03-26 20:55:00 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 930/1251] eta: 0:03:23 lr: 0.000754 loss: 3.5274 (3.4779) grad_norm: 1.2055 (1.2407) time: 0.6265 [2021-03-26 20:55:07 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 940/1251] eta: 0:03:17 lr: 0.000754 loss: 3.4580 (3.4807) grad_norm: 1.1944 (1.2404) time: 0.6338 [2021-03-26 20:55:13 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 950/1251] eta: 0:03:11 lr: 0.000754 loss: 3.9337 (3.4855) grad_norm: 1.1944 (1.2408) time: 0.6372 [2021-03-26 20:55:19 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 960/1251] eta: 0:03:04 lr: 0.000754 loss: 3.6051 (3.4821) grad_norm: 1.2316 (1.2401) time: 0.6292 [2021-03-26 20:55:25 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 970/1251] eta: 0:02:58 lr: 0.000754 loss: 3.4592 (3.4849) grad_norm: 1.2949 (1.2413) time: 0.6237 [2021-03-26 20:55:32 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 980/1251] eta: 0:02:51 lr: 0.000753 loss: 3.6487 (3.4856) grad_norm: 1.2246 (1.2401) time: 0.6237 [2021-03-26 20:55:38 swin_base_patch4_window7_224] INFO: Epoch: [99] [ 990/1251] eta: 0:02:45 lr: 0.000753 loss: 3.6389 (3.4869) grad_norm: 1.1675 (1.2403) time: 0.6290 [2021-03-26 20:55:44 swin_base_patch4_window7_224] INFO: Epoch: [99] [1000/1251] eta: 0:02:39 lr: 0.000753 loss: 3.6730 (3.4890) grad_norm: 1.2000 (1.2401) time: 0.6274 [2021-03-26 20:55:51 swin_base_patch4_window7_224] INFO: Epoch: [99] [1010/1251] eta: 0:02:32 lr: 0.000753 loss: 3.7579 (3.4913) grad_norm: 1.2009 (1.2408) time: 0.6272 [2021-03-26 20:55:57 swin_base_patch4_window7_224] INFO: Epoch: [99] [1020/1251] eta: 0:02:26 lr: 0.000753 loss: 3.6274 (3.4914) grad_norm: 1.2111 (1.2401) time: 0.6337 [2021-03-26 20:56:03 swin_base_patch4_window7_224] INFO: Epoch: [99] [1030/1251] eta: 0:02:20 lr: 0.000753 loss: 3.6274 (3.4911) grad_norm: 1.1866 (1.2404) time: 0.6359 [2021-03-26 20:56:10 swin_base_patch4_window7_224] INFO: Epoch: [99] [1040/1251] eta: 0:02:13 lr: 0.000753 loss: 3.6771 (3.4905) grad_norm: 1.2058 (1.2408) time: 0.6339 [2021-03-26 20:56:16 swin_base_patch4_window7_224] INFO: Epoch: [99] [1050/1251] eta: 0:02:07 lr: 0.000753 loss: 3.5003 (3.4889) grad_norm: 1.2073 (1.2407) time: 0.6321 [2021-03-26 20:56:22 swin_base_patch4_window7_224] INFO: Epoch: [99] [1060/1251] eta: 0:02:01 lr: 0.000753 loss: 3.4791 (3.4886) grad_norm: 1.2185 (1.2406) time: 0.6282 [2021-03-26 20:56:28 swin_base_patch4_window7_224] INFO: Epoch: [99] [1070/1251] eta: 0:01:54 lr: 0.000753 loss: 3.5046 (3.4885) grad_norm: 1.1780 (1.2399) time: 0.6224 [2021-03-26 20:56:35 swin_base_patch4_window7_224] INFO: Epoch: [99] [1080/1251] eta: 0:01:48 lr: 0.000753 loss: 3.7081 (3.4904) grad_norm: 1.1605 (1.2390) time: 0.6233 [2021-03-26 20:56:41 swin_base_patch4_window7_224] INFO: Epoch: [99] [1090/1251] eta: 0:01:42 lr: 0.000753 loss: 3.7999 (3.4919) grad_norm: 1.1496 (1.2388) time: 0.6255 [2021-03-26 20:56:47 swin_base_patch4_window7_224] INFO: Epoch: [99] [1100/1251] eta: 0:01:35 lr: 0.000753 loss: 3.7067 (3.4933) grad_norm: 1.2088 (1.2393) time: 0.6357 [2021-03-26 20:56:54 swin_base_patch4_window7_224] INFO: Epoch: [99] [1110/1251] eta: 0:01:29 lr: 0.000753 loss: 3.5511 (3.4917) grad_norm: 1.2210 (1.2390) time: 0.6353 [2021-03-26 20:57:00 swin_base_patch4_window7_224] INFO: Epoch: [99] [1120/1251] eta: 0:01:23 lr: 0.000753 loss: 3.3538 (3.4916) grad_norm: 1.2246 (1.2391) time: 0.6275 [2021-03-26 20:57:06 swin_base_patch4_window7_224] INFO: Epoch: [99] [1130/1251] eta: 0:01:16 lr: 0.000753 loss: 3.7352 (3.4945) grad_norm: 1.2228 (1.2391) time: 0.6308 [2021-03-26 20:57:12 swin_base_patch4_window7_224] INFO: Epoch: [99] [1140/1251] eta: 0:01:10 lr: 0.000753 loss: 3.7096 (3.4950) grad_norm: 1.2952 (1.2397) time: 0.6302 [2021-03-26 20:57:19 swin_base_patch4_window7_224] INFO: Epoch: [99] [1150/1251] eta: 0:01:04 lr: 0.000753 loss: 3.4917 (3.4946) grad_norm: 1.2154 (1.2394) time: 0.6265 [2021-03-26 20:57:25 swin_base_patch4_window7_224] INFO: Epoch: [99] [1160/1251] eta: 0:00:57 lr: 0.000753 loss: 3.3849 (3.4943) grad_norm: 1.1575 (1.2386) time: 0.6278 [2021-03-26 20:57:31 swin_base_patch4_window7_224] INFO: Epoch: [99] [1170/1251] eta: 0:00:51 lr: 0.000753 loss: 3.4948 (3.4939) grad_norm: 1.1585 (1.2383) time: 0.6321 [2021-03-26 20:57:38 swin_base_patch4_window7_224] INFO: Epoch: [99] [1180/1251] eta: 0:00:44 lr: 0.000753 loss: 3.5424 (3.4950) grad_norm: 1.2360 (1.2386) time: 0.6311 [2021-03-26 20:57:44 swin_base_patch4_window7_224] INFO: Epoch: [99] [1190/1251] eta: 0:00:38 lr: 0.000753 loss: 3.7240 (3.4960) grad_norm: 1.2360 (1.2384) time: 0.6279 [2021-03-26 20:57:50 swin_base_patch4_window7_224] INFO: Epoch: [99] [1200/1251] eta: 0:00:32 lr: 0.000753 loss: 3.7240 (3.4978) grad_norm: 1.1333 (1.2377) time: 0.6273 [2021-03-26 20:57:56 swin_base_patch4_window7_224] INFO: Epoch: [99] [1210/1251] eta: 0:00:25 lr: 0.000753 loss: 3.7665 (3.4996) grad_norm: 1.1695 (1.2371) time: 0.6256 [2021-03-26 20:58:03 swin_base_patch4_window7_224] INFO: Epoch: [99] [1220/1251] eta: 0:00:19 lr: 0.000753 loss: 3.7014 (3.4992) grad_norm: 1.1642 (1.2362) time: 0.6350 [2021-03-26 20:58:09 swin_base_patch4_window7_224] INFO: Epoch: [99] [1230/1251] eta: 0:00:13 lr: 0.000753 loss: 3.7014 (3.5023) grad_norm: 1.1516 (1.2367) time: 0.6381 [2021-03-26 20:58:16 swin_base_patch4_window7_224] INFO: Epoch: [99] [1240/1251] eta: 0:00:06 lr: 0.000753 loss: 3.9146 (3.5037) grad_norm: 1.2509 (1.2371) time: 0.6307 [2021-03-26 20:58:22 swin_base_patch4_window7_224] INFO: Epoch: [99] [1250/1251] eta: 0:00:00 lr: 0.000753 loss: 3.6862 (3.5028) grad_norm: 1.2344 (1.2366) time: 0.6250 [2021-03-26 20:58:28 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:49 loss: 1.0099 (1.0099) acc1: 73.4375 (73.4375) acc5: 95.3125 (95.3125) [2021-03-26 20:58:30 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.9861 (1.0244) acc1: 79.6875 (78.6932) acc5: 93.7500 (93.4659) [2021-03-26 20:58:32 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.9861 (1.0521) acc1: 76.5625 (77.0089) acc5: 93.7500 (93.3036) [2021-03-26 20:58:34 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0286 (1.0588) acc1: 75.0000 (76.7137) acc5: 92.1875 (93.0444) [2021-03-26 20:58:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0165 (1.0431) acc1: 75.0000 (76.7149) acc5: 93.7500 (93.2927) [2021-03-26 20:58:38 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9698 (1.0188) acc1: 79.6875 (77.1200) acc5: 93.7500 (93.6320) [2021-03-26 20:58:44 swin_base_patch4_window7_224] INFO: * Acc@1 76.762 Acc@5 93.698 loss 1.016 [2021-03-26 20:58:44 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.8% [2021-03-26 20:58:44 swin_base_patch4_window7_224] INFO: Max accuracy: 76.76% [2021-03-26 20:58:49 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 0/1251] eta: 1:32:52 lr: 0.000753 loss: 2.8405 (2.8405) grad_norm: 1.1305 (1.1305) time: 4.4548 [2021-03-26 20:58:55 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 10/1251] eta: 0:20:21 lr: 0.000752 loss: 3.5227 (3.4643) grad_norm: 1.1305 (1.2012) time: 0.9847 [2021-03-26 20:59:02 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 20/1251] eta: 0:16:45 lr: 0.000752 loss: 3.5119 (3.5228) grad_norm: 1.1631 (1.1937) time: 0.6346 [2021-03-26 20:59:08 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 30/1251] eta: 0:15:23 lr: 0.000752 loss: 3.5558 (3.5528) grad_norm: 1.1779 (1.1960) time: 0.6313 [2021-03-26 20:59:14 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 40/1251] eta: 0:14:39 lr: 0.000752 loss: 3.5558 (3.5216) grad_norm: 1.1898 (1.2180) time: 0.6313 [2021-03-26 20:59:21 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 50/1251] eta: 0:14:12 lr: 0.000752 loss: 3.4846 (3.5272) grad_norm: 1.2880 (1.2334) time: 0.6365 [2021-03-26 20:59:27 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 60/1251] eta: 0:13:50 lr: 0.000752 loss: 3.3608 (3.4848) grad_norm: 1.2698 (1.2338) time: 0.6376 [2021-03-26 20:59:33 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 70/1251] eta: 0:13:32 lr: 0.000752 loss: 3.3438 (3.4770) grad_norm: 1.2231 (1.2311) time: 0.6329 [2021-03-26 20:59:40 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 80/1251] eta: 0:13:16 lr: 0.000752 loss: 3.4042 (3.4544) grad_norm: 1.2053 (1.2410) time: 0.6297 [2021-03-26 20:59:46 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 90/1251] eta: 0:13:03 lr: 0.000752 loss: 3.7784 (3.4906) grad_norm: 1.2259 (1.2433) time: 0.6296 [2021-03-26 20:59:52 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 100/1251] eta: 0:12:52 lr: 0.000752 loss: 3.8259 (3.4841) grad_norm: 1.2259 (1.2381) time: 0.6339 [2021-03-26 20:59:59 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 110/1251] eta: 0:12:42 lr: 0.000752 loss: 3.2732 (3.4544) grad_norm: 1.1606 (1.2293) time: 0.6394 [2021-03-26 21:00:05 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 120/1251] eta: 0:12:32 lr: 0.000752 loss: 3.0469 (3.4395) grad_norm: 1.1869 (1.2378) time: 0.6356 [2021-03-26 21:00:11 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 130/1251] eta: 0:12:24 lr: 0.000752 loss: 3.2492 (3.4211) grad_norm: 1.2305 (1.2347) time: 0.6407 [2021-03-26 21:00:18 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 140/1251] eta: 0:12:15 lr: 0.000752 loss: 3.0435 (3.4013) grad_norm: 1.1768 (1.2354) time: 0.6419 [2021-03-26 21:00:24 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 150/1251] eta: 0:12:06 lr: 0.000752 loss: 3.3978 (3.4121) grad_norm: 1.1957 (1.2377) time: 0.6316 [2021-03-26 21:00:30 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 160/1251] eta: 0:11:58 lr: 0.000752 loss: 3.4181 (3.3993) grad_norm: 1.1644 (1.2313) time: 0.6342 [2021-03-26 21:00:37 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 170/1251] eta: 0:11:49 lr: 0.000752 loss: 3.3199 (3.3991) grad_norm: 1.1659 (1.2301) time: 0.6303 [2021-03-26 21:00:43 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 180/1251] eta: 0:11:41 lr: 0.000752 loss: 3.5434 (3.4006) grad_norm: 1.1835 (1.2282) time: 0.6272 [2021-03-26 21:00:49 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 190/1251] eta: 0:11:33 lr: 0.000752 loss: 3.5434 (3.4117) grad_norm: 1.2194 (1.2293) time: 0.6294 [2021-03-26 21:00:56 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 200/1251] eta: 0:11:25 lr: 0.000752 loss: 3.5089 (3.4051) grad_norm: 1.1788 (1.2266) time: 0.6287 [2021-03-26 21:01:02 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 210/1251] eta: 0:11:18 lr: 0.000752 loss: 3.5404 (3.4164) grad_norm: 1.1596 (1.2256) time: 0.6312 [2021-03-26 21:01:08 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 220/1251] eta: 0:11:10 lr: 0.000752 loss: 3.7931 (3.4293) grad_norm: 1.1605 (1.2261) time: 0.6296 [2021-03-26 21:01:15 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 230/1251] eta: 0:11:03 lr: 0.000752 loss: 3.7865 (3.4306) grad_norm: 1.1818 (1.2277) time: 0.6295 [2021-03-26 21:01:21 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 240/1251] eta: 0:10:56 lr: 0.000752 loss: 3.8247 (3.4432) grad_norm: 1.1818 (1.2256) time: 0.6353 [2021-03-26 21:01:27 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 250/1251] eta: 0:10:48 lr: 0.000752 loss: 3.6989 (3.4366) grad_norm: 1.1377 (1.2250) time: 0.6293 [2021-03-26 21:01:33 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 260/1251] eta: 0:10:41 lr: 0.000752 loss: 3.3461 (3.4357) grad_norm: 1.1361 (1.2218) time: 0.6245 [2021-03-26 21:01:40 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 270/1251] eta: 0:10:34 lr: 0.000752 loss: 3.4993 (3.4326) grad_norm: 1.1853 (1.2236) time: 0.6338 [2021-03-26 21:01:46 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 280/1251] eta: 0:10:27 lr: 0.000751 loss: 3.4988 (3.4333) grad_norm: 1.2166 (1.2236) time: 0.6343 [2021-03-26 21:01:52 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 290/1251] eta: 0:10:20 lr: 0.000751 loss: 3.4905 (3.4336) grad_norm: 1.1792 (1.2216) time: 0.6284 [2021-03-26 21:01:59 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 300/1251] eta: 0:10:13 lr: 0.000751 loss: 3.4905 (3.4314) grad_norm: 1.1310 (1.2197) time: 0.6321 [2021-03-26 21:02:05 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 310/1251] eta: 0:10:07 lr: 0.000751 loss: 3.4530 (3.4319) grad_norm: 1.1911 (1.2222) time: 0.6358 [2021-03-26 21:02:11 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 320/1251] eta: 0:10:00 lr: 0.000751 loss: 3.4572 (3.4369) grad_norm: 1.2193 (1.2235) time: 0.6331 [2021-03-26 21:02:18 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 330/1251] eta: 0:09:53 lr: 0.000751 loss: 3.6139 (3.4387) grad_norm: 1.2529 (1.2261) time: 0.6311 [2021-03-26 21:02:24 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 340/1251] eta: 0:09:46 lr: 0.000751 loss: 3.6139 (3.4434) grad_norm: 1.2963 (1.2267) time: 0.6288 [2021-03-26 21:02:30 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 350/1251] eta: 0:09:39 lr: 0.000751 loss: 3.6264 (3.4462) grad_norm: 1.1819 (1.2255) time: 0.6237 [2021-03-26 21:02:36 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 360/1251] eta: 0:09:32 lr: 0.000751 loss: 3.6264 (3.4464) grad_norm: 1.1371 (1.2243) time: 0.6240 [2021-03-26 21:02:43 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 370/1251] eta: 0:09:25 lr: 0.000751 loss: 3.5587 (3.4455) grad_norm: 1.1132 (1.2223) time: 0.6262 [2021-03-26 21:02:49 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 380/1251] eta: 0:09:19 lr: 0.000751 loss: 3.5283 (3.4437) grad_norm: 1.1759 (1.2228) time: 0.6276 [2021-03-26 21:02:55 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 390/1251] eta: 0:09:12 lr: 0.000751 loss: 3.3223 (3.4426) grad_norm: 1.2519 (1.2242) time: 0.6284 [2021-03-26 21:03:02 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 400/1251] eta: 0:09:05 lr: 0.000751 loss: 3.3991 (3.4451) grad_norm: 1.3005 (1.2283) time: 0.6247 [2021-03-26 21:03:08 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 410/1251] eta: 0:08:58 lr: 0.000751 loss: 3.4493 (3.4469) grad_norm: 1.2514 (1.2278) time: 0.6243 [2021-03-26 21:03:14 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 420/1251] eta: 0:08:52 lr: 0.000751 loss: 3.4729 (3.4483) grad_norm: 1.1540 (1.2285) time: 0.6253 [2021-03-26 21:03:20 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 430/1251] eta: 0:08:45 lr: 0.000751 loss: 3.5280 (3.4499) grad_norm: 1.1894 (1.2287) time: 0.6231 [2021-03-26 21:03:26 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 440/1251] eta: 0:08:38 lr: 0.000751 loss: 3.4399 (3.4477) grad_norm: 1.2605 (1.2300) time: 0.6207 [2021-03-26 21:03:33 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 450/1251] eta: 0:08:31 lr: 0.000751 loss: 3.2272 (3.4460) grad_norm: 1.2600 (1.2312) time: 0.6229 [2021-03-26 21:03:39 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 460/1251] eta: 0:08:25 lr: 0.000751 loss: 3.5879 (3.4505) grad_norm: 1.2135 (1.2322) time: 0.6295 [2021-03-26 21:03:45 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 470/1251] eta: 0:08:18 lr: 0.000751 loss: 3.6418 (3.4560) grad_norm: 1.2040 (1.2311) time: 0.6290 [2021-03-26 21:03:52 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 480/1251] eta: 0:08:12 lr: 0.000751 loss: 3.4976 (3.4532) grad_norm: 1.1362 (1.2298) time: 0.6266 [2021-03-26 21:03:58 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 490/1251] eta: 0:08:05 lr: 0.000751 loss: 3.6171 (3.4632) grad_norm: 1.1812 (1.2296) time: 0.6271 [2021-03-26 21:04:04 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 500/1251] eta: 0:07:59 lr: 0.000751 loss: 3.7479 (3.4659) grad_norm: 1.1907 (1.2299) time: 0.6270 [2021-03-26 21:04:10 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 510/1251] eta: 0:07:52 lr: 0.000751 loss: 3.7377 (3.4654) grad_norm: 1.1964 (1.2292) time: 0.6255 [2021-03-26 21:04:17 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 520/1251] eta: 0:07:46 lr: 0.000751 loss: 3.6156 (3.4684) grad_norm: 1.2059 (1.2288) time: 0.6272 [2021-03-26 21:04:23 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 530/1251] eta: 0:07:39 lr: 0.000751 loss: 3.6075 (3.4715) grad_norm: 1.2139 (1.2284) time: 0.6271 [2021-03-26 21:04:29 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 540/1251] eta: 0:07:33 lr: 0.000751 loss: 3.6075 (3.4745) grad_norm: 1.1784 (1.2278) time: 0.6275 [2021-03-26 21:04:36 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 550/1251] eta: 0:07:26 lr: 0.000751 loss: 3.5540 (3.4755) grad_norm: 1.1767 (1.2268) time: 0.6384 [2021-03-26 21:04:42 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 560/1251] eta: 0:07:20 lr: 0.000750 loss: 3.5464 (3.4753) grad_norm: 1.1705 (1.2269) time: 0.6400 [2021-03-26 21:04:48 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 570/1251] eta: 0:07:13 lr: 0.000750 loss: 3.5639 (3.4758) grad_norm: 1.2339 (1.2294) time: 0.6284 [2021-03-26 21:04:55 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 580/1251] eta: 0:07:07 lr: 0.000750 loss: 3.6732 (3.4808) grad_norm: 1.2339 (1.2300) time: 0.6260 [2021-03-26 21:05:01 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 590/1251] eta: 0:07:01 lr: 0.000750 loss: 3.7722 (3.4825) grad_norm: 1.1965 (1.2294) time: 0.6351 [2021-03-26 21:05:07 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 600/1251] eta: 0:06:54 lr: 0.000750 loss: 3.5327 (3.4831) grad_norm: 1.1593 (1.2291) time: 0.6368 [2021-03-26 21:05:14 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 610/1251] eta: 0:06:48 lr: 0.000750 loss: 3.1186 (3.4785) grad_norm: 1.1593 (1.2293) time: 0.6319 [2021-03-26 21:05:20 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 620/1251] eta: 0:06:41 lr: 0.000750 loss: 3.1541 (3.4784) grad_norm: 1.1879 (1.2289) time: 0.6315 [2021-03-26 21:05:26 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 630/1251] eta: 0:06:35 lr: 0.000750 loss: 3.4920 (3.4773) grad_norm: 1.1654 (1.2286) time: 0.6275 [2021-03-26 21:05:32 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 640/1251] eta: 0:06:28 lr: 0.000750 loss: 3.3819 (3.4786) grad_norm: 1.1045 (1.2274) time: 0.6266 [2021-03-26 21:05:39 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 650/1251] eta: 0:06:22 lr: 0.000750 loss: 3.5664 (3.4793) grad_norm: 1.1907 (1.2280) time: 0.6276 [2021-03-26 21:05:45 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 660/1251] eta: 0:06:15 lr: 0.000750 loss: 3.8611 (3.4849) grad_norm: 1.1839 (1.2272) time: 0.6263 [2021-03-26 21:05:51 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 670/1251] eta: 0:06:09 lr: 0.000750 loss: 3.8583 (3.4886) grad_norm: 1.1566 (1.2269) time: 0.6253 [2021-03-26 21:05:58 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 680/1251] eta: 0:06:03 lr: 0.000750 loss: 3.6817 (3.4903) grad_norm: 1.1695 (1.2265) time: 0.6273 [2021-03-26 21:06:04 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 690/1251] eta: 0:05:56 lr: 0.000750 loss: 3.7732 (3.4921) grad_norm: 1.1695 (1.2260) time: 0.6316 [2021-03-26 21:06:10 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 700/1251] eta: 0:05:50 lr: 0.000750 loss: 3.8305 (3.4952) grad_norm: 1.1625 (1.2254) time: 0.6275 [2021-03-26 21:06:16 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 710/1251] eta: 0:05:43 lr: 0.000750 loss: 3.8305 (3.4955) grad_norm: 1.2821 (1.2275) time: 0.6274 [2021-03-26 21:06:23 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 720/1251] eta: 0:05:37 lr: 0.000750 loss: 3.4255 (3.4909) grad_norm: 1.3344 (1.2289) time: 0.6291 [2021-03-26 21:06:29 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 730/1251] eta: 0:05:31 lr: 0.000750 loss: 3.3201 (3.4911) grad_norm: 1.2774 (1.2287) time: 0.6308 [2021-03-26 21:06:36 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 740/1251] eta: 0:05:24 lr: 0.000750 loss: 3.4888 (3.4897) grad_norm: 1.1806 (1.2281) time: 0.6444 [2021-03-26 21:06:42 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 750/1251] eta: 0:05:18 lr: 0.000750 loss: 3.3471 (3.4890) grad_norm: 1.1387 (1.2271) time: 0.6422 [2021-03-26 21:06:48 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 760/1251] eta: 0:05:12 lr: 0.000750 loss: 3.4958 (3.4883) grad_norm: 1.1704 (1.2267) time: 0.6348 [2021-03-26 21:06:55 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 770/1251] eta: 0:05:05 lr: 0.000750 loss: 3.5369 (3.4898) grad_norm: 1.1715 (1.2263) time: 0.6380 [2021-03-26 21:07:01 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 780/1251] eta: 0:04:59 lr: 0.000750 loss: 3.4785 (3.4875) grad_norm: 1.2294 (1.2281) time: 0.6298 [2021-03-26 21:07:07 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 790/1251] eta: 0:04:53 lr: 0.000750 loss: 3.4086 (3.4884) grad_norm: 1.2838 (1.2294) time: 0.6341 [2021-03-26 21:07:14 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 800/1251] eta: 0:04:46 lr: 0.000750 loss: 3.6057 (3.4891) grad_norm: 1.3057 (1.2306) time: 0.6362 [2021-03-26 21:07:20 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 810/1251] eta: 0:04:40 lr: 0.000750 loss: 3.4565 (3.4858) grad_norm: 1.1868 (1.2291) time: 0.6286 [2021-03-26 21:07:26 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 820/1251] eta: 0:04:33 lr: 0.000750 loss: 3.2865 (3.4847) grad_norm: 1.1555 (1.2280) time: 0.6267 [2021-03-26 21:07:32 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 830/1251] eta: 0:04:27 lr: 0.000750 loss: 3.1983 (3.4813) grad_norm: 1.1555 (1.2280) time: 0.6260 [2021-03-26 21:07:39 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 840/1251] eta: 0:04:21 lr: 0.000749 loss: 3.5578 (3.4831) grad_norm: 1.1695 (1.2278) time: 0.6277 [2021-03-26 21:07:45 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 850/1251] eta: 0:04:14 lr: 0.000749 loss: 3.6720 (3.4839) grad_norm: 1.1828 (1.2274) time: 0.6279 [2021-03-26 21:07:51 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 860/1251] eta: 0:04:08 lr: 0.000749 loss: 3.5074 (3.4837) grad_norm: 1.2065 (1.2282) time: 0.6341 [2021-03-26 21:07:58 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 870/1251] eta: 0:04:01 lr: 0.000749 loss: 3.3926 (3.4827) grad_norm: 1.1656 (1.2279) time: 0.6330 [2021-03-26 21:08:04 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 880/1251] eta: 0:03:55 lr: 0.000749 loss: 3.4909 (3.4824) grad_norm: 1.2029 (1.2284) time: 0.6315 [2021-03-26 21:08:10 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 890/1251] eta: 0:03:49 lr: 0.000749 loss: 3.4590 (3.4827) grad_norm: 1.2256 (1.2287) time: 0.6355 [2021-03-26 21:08:17 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 900/1251] eta: 0:03:42 lr: 0.000749 loss: 3.6001 (3.4849) grad_norm: 1.2131 (1.2286) time: 0.6320 [2021-03-26 21:08:23 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 910/1251] eta: 0:03:36 lr: 0.000749 loss: 3.4979 (3.4817) grad_norm: 1.1937 (1.2280) time: 0.6342 [2021-03-26 21:08:29 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 920/1251] eta: 0:03:30 lr: 0.000749 loss: 3.3788 (3.4808) grad_norm: 1.2047 (1.2291) time: 0.6338 [2021-03-26 21:08:36 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 930/1251] eta: 0:03:23 lr: 0.000749 loss: 3.4940 (3.4826) grad_norm: 1.2369 (1.2290) time: 0.6407 [2021-03-26 21:08:42 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 940/1251] eta: 0:03:17 lr: 0.000749 loss: 3.8178 (3.4864) grad_norm: 1.2571 (1.2301) time: 0.6472 [2021-03-26 21:08:49 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 950/1251] eta: 0:03:11 lr: 0.000749 loss: 3.7799 (3.4861) grad_norm: 1.2571 (1.2300) time: 0.6380 [2021-03-26 21:08:55 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 960/1251] eta: 0:03:04 lr: 0.000749 loss: 3.4285 (3.4856) grad_norm: 1.1700 (1.2300) time: 0.6284 [2021-03-26 21:09:01 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 970/1251] eta: 0:02:58 lr: 0.000749 loss: 3.5186 (3.4866) grad_norm: 1.1736 (1.2297) time: 0.6231 [2021-03-26 21:09:07 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 980/1251] eta: 0:02:52 lr: 0.000749 loss: 3.4017 (3.4849) grad_norm: 1.2453 (1.2308) time: 0.6249 [2021-03-26 21:09:14 swin_base_patch4_window7_224] INFO: Epoch: [100] [ 990/1251] eta: 0:02:45 lr: 0.000749 loss: 3.3081 (3.4820) grad_norm: 1.2453 (1.2311) time: 0.6282 [2021-03-26 21:09:20 swin_base_patch4_window7_224] INFO: Epoch: [100] [1000/1251] eta: 0:02:39 lr: 0.000749 loss: 3.4518 (3.4817) grad_norm: 1.1606 (1.2302) time: 0.6248 [2021-03-26 21:09:26 swin_base_patch4_window7_224] INFO: Epoch: [100] [1010/1251] eta: 0:02:32 lr: 0.000749 loss: 3.5162 (3.4804) grad_norm: 1.1817 (1.2302) time: 0.6262 [2021-03-26 21:09:33 swin_base_patch4_window7_224] INFO: Epoch: [100] [1020/1251] eta: 0:02:26 lr: 0.000749 loss: 3.5660 (3.4800) grad_norm: 1.2004 (1.2298) time: 0.6347 [2021-03-26 21:09:39 swin_base_patch4_window7_224] INFO: Epoch: [100] [1030/1251] eta: 0:02:20 lr: 0.000749 loss: 3.5410 (3.4789) grad_norm: 1.1441 (1.2294) time: 0.6325 [2021-03-26 21:09:45 swin_base_patch4_window7_224] INFO: Epoch: [100] [1040/1251] eta: 0:02:13 lr: 0.000749 loss: 3.5689 (3.4805) grad_norm: 1.1251 (1.2287) time: 0.6291 [2021-03-26 21:09:51 swin_base_patch4_window7_224] INFO: Epoch: [100] [1050/1251] eta: 0:02:07 lr: 0.000749 loss: 3.5689 (3.4774) grad_norm: 1.1251 (1.2283) time: 0.6264 [2021-03-26 21:09:58 swin_base_patch4_window7_224] INFO: Epoch: [100] [1060/1251] eta: 0:02:01 lr: 0.000749 loss: 3.5139 (3.4805) grad_norm: 1.1776 (1.2283) time: 0.6236 [2021-03-26 21:10:04 swin_base_patch4_window7_224] INFO: Epoch: [100] [1070/1251] eta: 0:01:54 lr: 0.000749 loss: 3.6764 (3.4836) grad_norm: 1.1750 (1.2281) time: 0.6254 [2021-03-26 21:10:10 swin_base_patch4_window7_224] INFO: Epoch: [100] [1080/1251] eta: 0:01:48 lr: 0.000749 loss: 3.6630 (3.4856) grad_norm: 1.1554 (1.2276) time: 0.6248 [2021-03-26 21:10:16 swin_base_patch4_window7_224] INFO: Epoch: [100] [1090/1251] eta: 0:01:42 lr: 0.000749 loss: 3.8745 (3.4889) grad_norm: 1.1086 (1.2266) time: 0.6239 [2021-03-26 21:10:23 swin_base_patch4_window7_224] INFO: Epoch: [100] [1100/1251] eta: 0:01:35 lr: 0.000749 loss: 3.6555 (3.4875) grad_norm: 1.1086 (1.2255) time: 0.6265 [2021-03-26 21:10:29 swin_base_patch4_window7_224] INFO: Epoch: [100] [1110/1251] eta: 0:01:29 lr: 0.000749 loss: 3.4060 (3.4876) grad_norm: 1.1699 (1.2255) time: 0.6316 [2021-03-26 21:10:35 swin_base_patch4_window7_224] INFO: Epoch: [100] [1120/1251] eta: 0:01:23 lr: 0.000748 loss: 3.4060 (3.4869) grad_norm: 1.2454 (1.2258) time: 0.6366 [2021-03-26 21:10:42 swin_base_patch4_window7_224] INFO: Epoch: [100] [1130/1251] eta: 0:01:16 lr: 0.000748 loss: 3.6535 (3.4895) grad_norm: 1.2365 (1.2257) time: 0.6312 [2021-03-26 21:10:48 swin_base_patch4_window7_224] INFO: Epoch: [100] [1140/1251] eta: 0:01:10 lr: 0.000748 loss: 3.6687 (3.4908) grad_norm: 1.2181 (1.2260) time: 0.6257 [2021-03-26 21:10:54 swin_base_patch4_window7_224] INFO: Epoch: [100] [1150/1251] eta: 0:01:04 lr: 0.000748 loss: 3.3667 (3.4892) grad_norm: 1.2210 (1.2262) time: 0.6247 [2021-03-26 21:11:00 swin_base_patch4_window7_224] INFO: Epoch: [100] [1160/1251] eta: 0:00:57 lr: 0.000748 loss: 3.2267 (3.4877) grad_norm: 1.2156 (1.2262) time: 0.6235 [2021-03-26 21:11:07 swin_base_patch4_window7_224] INFO: Epoch: [100] [1170/1251] eta: 0:00:51 lr: 0.000748 loss: 3.4827 (3.4873) grad_norm: 1.1926 (1.2266) time: 0.6270 [2021-03-26 21:11:13 swin_base_patch4_window7_224] INFO: Epoch: [100] [1180/1251] eta: 0:00:44 lr: 0.000748 loss: 3.6411 (3.4880) grad_norm: 1.2179 (1.2265) time: 0.6306 [2021-03-26 21:11:19 swin_base_patch4_window7_224] INFO: Epoch: [100] [1190/1251] eta: 0:00:38 lr: 0.000748 loss: 3.6411 (3.4871) grad_norm: 1.2179 (1.2266) time: 0.6304 [2021-03-26 21:11:26 swin_base_patch4_window7_224] INFO: Epoch: [100] [1200/1251] eta: 0:00:32 lr: 0.000748 loss: 3.4309 (3.4866) grad_norm: 1.1814 (1.2269) time: 0.6305 [2021-03-26 21:11:32 swin_base_patch4_window7_224] INFO: Epoch: [100] [1210/1251] eta: 0:00:25 lr: 0.000748 loss: 3.5853 (3.4890) grad_norm: 1.1669 (1.2267) time: 0.6298 [2021-03-26 21:11:38 swin_base_patch4_window7_224] INFO: Epoch: [100] [1220/1251] eta: 0:00:19 lr: 0.000748 loss: 3.5853 (3.4868) grad_norm: 1.1937 (1.2267) time: 0.6294 [2021-03-26 21:11:44 swin_base_patch4_window7_224] INFO: Epoch: [100] [1230/1251] eta: 0:00:13 lr: 0.000748 loss: 3.2517 (3.4862) grad_norm: 1.2272 (1.2276) time: 0.6317 [2021-03-26 21:11:51 swin_base_patch4_window7_224] INFO: Epoch: [100] [1240/1251] eta: 0:00:06 lr: 0.000748 loss: 3.5150 (3.4874) grad_norm: 1.2415 (1.2273) time: 0.6304 [2021-03-26 21:11:57 swin_base_patch4_window7_224] INFO: Epoch: [100] [1250/1251] eta: 0:00:00 lr: 0.000748 loss: 3.6420 (3.4876) grad_norm: 1.2238 (1.2283) time: 0.6288 [2021-03-26 21:13:06 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:02 loss: 1.0226 (1.0226) acc1: 78.1250 (78.1250) acc5: 95.3125 (95.3125) [2021-03-26 21:13:07 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 1.0817 (1.0661) acc1: 76.5625 (75.8523) acc5: 93.7500 (94.0341) [2021-03-26 21:13:08 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.0817 (1.0825) acc1: 76.5625 (75.5208) acc5: 93.7500 (93.6012) [2021-03-26 21:13:10 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.0477 (1.0749) acc1: 76.5625 (75.9577) acc5: 93.7500 (93.2964) [2021-03-26 21:13:11 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.0160 (1.0767) acc1: 76.5625 (75.7622) acc5: 93.7500 (93.3689) [2021-03-26 21:13:12 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0160 (1.0573) acc1: 75.0000 (75.9680) acc5: 95.3125 (93.5040) [2021-03-26 21:13:19 swin_base_patch4_window7_224] INFO: * Acc@1 76.618 Acc@5 93.728 loss 1.023 [2021-03-26 21:13:19 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.6% [2021-03-26 21:13:19 swin_base_patch4_window7_224] INFO: Max accuracy: 76.76% [2021-03-26 21:13:23 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 0/1251] eta: 1:27:04 lr: 0.000748 loss: 3.1990 (3.1990) grad_norm: 1.3895 (1.3895) time: 4.1762 [2021-03-26 21:13:30 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 10/1251] eta: 0:19:55 lr: 0.000748 loss: 3.3464 (3.3115) grad_norm: 1.1585 (1.1989) time: 0.9632 [2021-03-26 21:13:36 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 20/1251] eta: 0:16:29 lr: 0.000748 loss: 3.3464 (3.3094) grad_norm: 1.1852 (1.2742) time: 0.6349 [2021-03-26 21:13:42 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 30/1251] eta: 0:15:12 lr: 0.000748 loss: 3.2629 (3.3016) grad_norm: 1.3363 (1.2673) time: 0.6283 [2021-03-26 21:13:49 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 40/1251] eta: 0:14:30 lr: 0.000748 loss: 3.4343 (3.3903) grad_norm: 1.2456 (1.2650) time: 0.6290 [2021-03-26 21:13:55 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 50/1251] eta: 0:14:04 lr: 0.000748 loss: 3.7078 (3.4226) grad_norm: 1.2004 (1.2641) time: 0.6350 [2021-03-26 21:14:02 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 60/1251] eta: 0:13:46 lr: 0.000748 loss: 3.7078 (3.4483) grad_norm: 1.2074 (1.2803) time: 0.6435 [2021-03-26 21:14:08 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 70/1251] eta: 0:13:29 lr: 0.000748 loss: 3.5261 (3.4543) grad_norm: 1.3050 (1.2985) time: 0.6399 [2021-03-26 21:14:14 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 80/1251] eta: 0:13:14 lr: 0.000748 loss: 3.6549 (3.4813) grad_norm: 1.3191 (1.3074) time: 0.6329 [2021-03-26 21:14:21 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 90/1251] eta: 0:13:04 lr: 0.000748 loss: 3.7751 (3.4869) grad_norm: 1.1882 (1.2955) time: 0.6399 [2021-03-26 21:14:27 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 100/1251] eta: 0:12:52 lr: 0.000748 loss: 3.5023 (3.4946) grad_norm: 1.1440 (1.2801) time: 0.6381 [2021-03-26 21:14:33 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 110/1251] eta: 0:12:40 lr: 0.000748 loss: 3.5023 (3.4998) grad_norm: 1.1950 (1.2731) time: 0.6274 [2021-03-26 21:14:40 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 120/1251] eta: 0:12:30 lr: 0.000748 loss: 3.5011 (3.5020) grad_norm: 1.2135 (1.2695) time: 0.6294 [2021-03-26 21:14:46 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 130/1251] eta: 0:12:22 lr: 0.000748 loss: 3.5011 (3.5088) grad_norm: 1.2267 (1.2725) time: 0.6381 [2021-03-26 21:14:52 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 140/1251] eta: 0:12:13 lr: 0.000747 loss: 3.5767 (3.5140) grad_norm: 1.2932 (1.2773) time: 0.6354 [2021-03-26 21:14:59 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 150/1251] eta: 0:12:03 lr: 0.000747 loss: 3.5489 (3.5128) grad_norm: 1.2892 (1.2777) time: 0.6255 [2021-03-26 21:15:05 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 160/1251] eta: 0:11:55 lr: 0.000747 loss: 3.5682 (3.5218) grad_norm: 1.1984 (1.2696) time: 0.6244 [2021-03-26 21:15:11 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 170/1251] eta: 0:11:47 lr: 0.000747 loss: 3.6975 (3.5212) grad_norm: 1.1790 (1.2636) time: 0.6298 [2021-03-26 21:15:18 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 180/1251] eta: 0:11:39 lr: 0.000747 loss: 3.5437 (3.5235) grad_norm: 1.1972 (1.2653) time: 0.6336 [2021-03-26 21:15:24 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 190/1251] eta: 0:11:31 lr: 0.000747 loss: 3.5289 (3.5229) grad_norm: 1.1725 (1.2598) time: 0.6319 [2021-03-26 21:15:30 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 200/1251] eta: 0:11:24 lr: 0.000747 loss: 3.5021 (3.5215) grad_norm: 1.1883 (1.2580) time: 0.6371 [2021-03-26 21:15:37 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 210/1251] eta: 0:11:16 lr: 0.000747 loss: 3.3890 (3.5091) grad_norm: 1.2095 (1.2533) time: 0.6342 [2021-03-26 21:15:43 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 220/1251] eta: 0:11:09 lr: 0.000747 loss: 3.3890 (3.5067) grad_norm: 1.1773 (1.2557) time: 0.6246 [2021-03-26 21:15:49 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 230/1251] eta: 0:11:01 lr: 0.000747 loss: 3.7599 (3.5157) grad_norm: 1.1920 (1.2539) time: 0.6223 [2021-03-26 21:15:55 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 240/1251] eta: 0:10:54 lr: 0.000747 loss: 3.7123 (3.5042) grad_norm: 1.1472 (1.2527) time: 0.6267 [2021-03-26 21:16:02 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 250/1251] eta: 0:10:46 lr: 0.000747 loss: 3.2705 (3.4960) grad_norm: 1.1962 (inf) time: 0.6297 [2021-03-26 21:16:08 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 260/1251] eta: 0:10:39 lr: 0.000747 loss: 3.4648 (3.4939) grad_norm: 1.1759 (inf) time: 0.6296 [2021-03-26 21:16:14 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 270/1251] eta: 0:10:32 lr: 0.000747 loss: 3.3870 (3.4889) grad_norm: 1.1334 (inf) time: 0.6304 [2021-03-26 21:16:21 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 280/1251] eta: 0:10:26 lr: 0.000747 loss: 3.5014 (3.4919) grad_norm: 1.1407 (inf) time: 0.6357 [2021-03-26 21:16:27 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 290/1251] eta: 0:10:19 lr: 0.000747 loss: 3.5014 (3.4900) grad_norm: 1.1593 (inf) time: 0.6326 [2021-03-26 21:16:33 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 300/1251] eta: 0:10:12 lr: 0.000747 loss: 3.4155 (3.4855) grad_norm: 1.2699 (inf) time: 0.6333 [2021-03-26 21:16:40 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 310/1251] eta: 0:10:05 lr: 0.000747 loss: 3.5076 (3.4845) grad_norm: 1.3658 (inf) time: 0.6371 [2021-03-26 21:16:46 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 320/1251] eta: 0:09:59 lr: 0.000747 loss: 3.7032 (3.4833) grad_norm: 1.2717 (inf) time: 0.6315 [2021-03-26 21:16:52 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 330/1251] eta: 0:09:52 lr: 0.000747 loss: 3.5159 (3.4833) grad_norm: 1.1548 (inf) time: 0.6281 [2021-03-26 21:16:58 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 340/1251] eta: 0:09:45 lr: 0.000747 loss: 3.5159 (3.4843) grad_norm: 1.2313 (inf) time: 0.6241 [2021-03-26 21:17:05 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 350/1251] eta: 0:09:38 lr: 0.000747 loss: 3.4527 (3.4814) grad_norm: 1.1849 (inf) time: 0.6295 [2021-03-26 21:17:11 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 360/1251] eta: 0:09:31 lr: 0.000747 loss: 3.4499 (3.4772) grad_norm: 1.1882 (inf) time: 0.6313 [2021-03-26 21:17:17 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 370/1251] eta: 0:09:25 lr: 0.000747 loss: 3.4856 (3.4771) grad_norm: 1.1798 (inf) time: 0.6289 [2021-03-26 21:17:24 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 380/1251] eta: 0:09:18 lr: 0.000747 loss: 3.5823 (3.4769) grad_norm: 1.1586 (inf) time: 0.6263 [2021-03-26 21:17:30 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 390/1251] eta: 0:09:11 lr: 0.000747 loss: 3.5580 (3.4702) grad_norm: 1.1639 (inf) time: 0.6228 [2021-03-26 21:17:36 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 400/1251] eta: 0:09:04 lr: 0.000747 loss: 3.3838 (3.4703) grad_norm: 1.1986 (inf) time: 0.6290 [2021-03-26 21:17:43 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 410/1251] eta: 0:08:58 lr: 0.000747 loss: 3.5117 (3.4726) grad_norm: 1.2115 (inf) time: 0.6386 [2021-03-26 21:17:49 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 420/1251] eta: 0:08:51 lr: 0.000746 loss: 3.4834 (3.4682) grad_norm: 1.2328 (inf) time: 0.6323 [2021-03-26 21:17:55 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 430/1251] eta: 0:08:45 lr: 0.000746 loss: 3.4119 (3.4706) grad_norm: 1.1963 (inf) time: 0.6280 [2021-03-26 21:18:01 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 440/1251] eta: 0:08:38 lr: 0.000746 loss: 3.6624 (3.4749) grad_norm: 1.1428 (inf) time: 0.6316 [2021-03-26 21:18:08 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 450/1251] eta: 0:08:32 lr: 0.000746 loss: 3.6110 (3.4739) grad_norm: 1.1675 (inf) time: 0.6301 [2021-03-26 21:18:14 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 460/1251] eta: 0:08:25 lr: 0.000746 loss: 3.4598 (3.4781) grad_norm: 1.2642 (inf) time: 0.6287 [2021-03-26 21:18:20 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 470/1251] eta: 0:08:19 lr: 0.000746 loss: 3.4845 (3.4743) grad_norm: 1.2642 (inf) time: 0.6299 [2021-03-26 21:18:27 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 480/1251] eta: 0:08:12 lr: 0.000746 loss: 3.5565 (3.4755) grad_norm: 1.2062 (inf) time: 0.6264 [2021-03-26 21:18:33 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 490/1251] eta: 0:08:05 lr: 0.000746 loss: 3.6568 (3.4764) grad_norm: 1.1704 (inf) time: 0.6271 [2021-03-26 21:18:39 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 500/1251] eta: 0:07:59 lr: 0.000746 loss: 3.4665 (3.4746) grad_norm: 1.1769 (inf) time: 0.6304 [2021-03-26 21:18:45 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 510/1251] eta: 0:07:52 lr: 0.000746 loss: 3.5660 (3.4788) grad_norm: 1.2389 (inf) time: 0.6312 [2021-03-26 21:18:52 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 520/1251] eta: 0:07:46 lr: 0.000746 loss: 3.5660 (3.4762) grad_norm: 1.2114 (inf) time: 0.6365 [2021-03-26 21:18:58 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 530/1251] eta: 0:07:40 lr: 0.000746 loss: 3.5066 (3.4754) grad_norm: 1.1471 (inf) time: 0.6371 [2021-03-26 21:19:04 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 540/1251] eta: 0:07:33 lr: 0.000746 loss: 3.6947 (3.4768) grad_norm: 1.1890 (inf) time: 0.6301 [2021-03-26 21:19:11 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 550/1251] eta: 0:07:27 lr: 0.000746 loss: 3.6516 (3.4796) grad_norm: 1.1846 (inf) time: 0.6351 [2021-03-26 21:19:17 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 560/1251] eta: 0:07:21 lr: 0.000746 loss: 3.6516 (3.4829) grad_norm: 1.1759 (inf) time: 0.6467 [2021-03-26 21:19:24 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 570/1251] eta: 0:07:14 lr: 0.000746 loss: 3.7055 (3.4862) grad_norm: 1.1667 (inf) time: 0.6358 [2021-03-26 21:19:30 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 580/1251] eta: 0:07:07 lr: 0.000746 loss: 3.4830 (3.4836) grad_norm: 1.1821 (inf) time: 0.6222 [2021-03-26 21:19:36 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 590/1251] eta: 0:07:01 lr: 0.000746 loss: 3.4378 (3.4870) grad_norm: 1.2191 (inf) time: 0.6216 [2021-03-26 21:19:42 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 600/1251] eta: 0:06:54 lr: 0.000746 loss: 3.5632 (3.4850) grad_norm: 1.2071 (inf) time: 0.6239 [2021-03-26 21:19:49 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 610/1251] eta: 0:06:48 lr: 0.000746 loss: 3.4294 (3.4847) grad_norm: 1.1980 (inf) time: 0.6269 [2021-03-26 21:19:55 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 620/1251] eta: 0:06:41 lr: 0.000746 loss: 3.5914 (3.4863) grad_norm: 1.1980 (inf) time: 0.6321 [2021-03-26 21:20:01 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 630/1251] eta: 0:06:35 lr: 0.000746 loss: 3.5748 (3.4843) grad_norm: 1.2634 (inf) time: 0.6311 [2021-03-26 21:20:08 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 640/1251] eta: 0:06:29 lr: 0.000746 loss: 3.5748 (3.4850) grad_norm: 1.3374 (inf) time: 0.6285 [2021-03-26 21:20:14 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 650/1251] eta: 0:06:22 lr: 0.000746 loss: 3.6028 (3.4844) grad_norm: 1.1967 (inf) time: 0.6331 [2021-03-26 21:20:20 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 660/1251] eta: 0:06:16 lr: 0.000746 loss: 3.4760 (3.4851) grad_norm: 1.1376 (inf) time: 0.6330 [2021-03-26 21:20:27 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 670/1251] eta: 0:06:09 lr: 0.000746 loss: 3.3153 (3.4790) grad_norm: 1.2238 (inf) time: 0.6285 [2021-03-26 21:20:33 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 680/1251] eta: 0:06:03 lr: 0.000746 loss: 3.2583 (3.4771) grad_norm: 1.2176 (inf) time: 0.6378 [2021-03-26 21:20:39 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 690/1251] eta: 0:05:57 lr: 0.000746 loss: 3.4080 (3.4784) grad_norm: 1.1375 (inf) time: 0.6445 [2021-03-26 21:20:46 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 700/1251] eta: 0:05:50 lr: 0.000745 loss: 3.6485 (3.4824) grad_norm: 1.1343 (inf) time: 0.6366 [2021-03-26 21:20:52 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 710/1251] eta: 0:05:44 lr: 0.000745 loss: 3.7804 (3.4846) grad_norm: 1.1959 (inf) time: 0.6349 [2021-03-26 21:20:58 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 720/1251] eta: 0:05:38 lr: 0.000745 loss: 3.7586 (3.4859) grad_norm: 1.2414 (inf) time: 0.6352 [2021-03-26 21:21:05 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 730/1251] eta: 0:05:31 lr: 0.000745 loss: 3.6716 (3.4879) grad_norm: 1.2037 (inf) time: 0.6356 [2021-03-26 21:21:11 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 740/1251] eta: 0:05:25 lr: 0.000745 loss: 3.6716 (3.4868) grad_norm: 1.2079 (inf) time: 0.6398 [2021-03-26 21:21:18 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 750/1251] eta: 0:05:19 lr: 0.000745 loss: 3.4365 (3.4872) grad_norm: 1.2079 (inf) time: 0.6394 [2021-03-26 21:21:24 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 760/1251] eta: 0:05:12 lr: 0.000745 loss: 3.4365 (3.4893) grad_norm: 1.2785 (inf) time: 0.6347 [2021-03-26 21:21:30 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 770/1251] eta: 0:05:06 lr: 0.000745 loss: 3.4639 (3.4901) grad_norm: 1.2763 (inf) time: 0.6289 [2021-03-26 21:21:36 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 780/1251] eta: 0:04:59 lr: 0.000745 loss: 3.7192 (3.4928) grad_norm: 1.2973 (inf) time: 0.6254 [2021-03-26 21:21:43 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 790/1251] eta: 0:04:53 lr: 0.000745 loss: 3.7192 (3.4943) grad_norm: 1.2341 (inf) time: 0.6276 [2021-03-26 21:21:49 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 800/1251] eta: 0:04:47 lr: 0.000745 loss: 3.4214 (3.4901) grad_norm: 1.2333 (inf) time: 0.6355 [2021-03-26 21:21:56 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 810/1251] eta: 0:04:40 lr: 0.000745 loss: 3.2936 (3.4891) grad_norm: 1.2476 (inf) time: 0.6383 [2021-03-26 21:22:02 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 820/1251] eta: 0:04:34 lr: 0.000745 loss: 3.4309 (3.4888) grad_norm: 1.2213 (inf) time: 0.6306 [2021-03-26 21:22:08 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 830/1251] eta: 0:04:27 lr: 0.000745 loss: 3.5070 (3.4876) grad_norm: 1.1963 (inf) time: 0.6274 [2021-03-26 21:22:14 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 840/1251] eta: 0:04:21 lr: 0.000745 loss: 3.5253 (3.4880) grad_norm: 1.2129 (inf) time: 0.6313 [2021-03-26 21:22:21 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 850/1251] eta: 0:04:15 lr: 0.000745 loss: 3.5209 (3.4901) grad_norm: 1.2100 (inf) time: 0.6300 [2021-03-26 21:22:27 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 860/1251] eta: 0:04:08 lr: 0.000745 loss: 3.6272 (3.4914) grad_norm: 1.2100 (inf) time: 0.6241 [2021-03-26 21:22:33 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 870/1251] eta: 0:04:02 lr: 0.000745 loss: 3.6272 (3.4895) grad_norm: 1.2231 (inf) time: 0.6312 [2021-03-26 21:22:40 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 880/1251] eta: 0:03:55 lr: 0.000745 loss: 3.4935 (3.4869) grad_norm: 1.2074 (inf) time: 0.6398 [2021-03-26 21:22:46 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 890/1251] eta: 0:03:49 lr: 0.000745 loss: 3.5200 (3.4874) grad_norm: 1.2010 (inf) time: 0.6339 [2021-03-26 21:22:52 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 900/1251] eta: 0:03:43 lr: 0.000745 loss: 3.4819 (3.4869) grad_norm: 1.2360 (inf) time: 0.6294 [2021-03-26 21:22:59 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 910/1251] eta: 0:03:36 lr: 0.000745 loss: 3.4817 (3.4853) grad_norm: 1.2360 (inf) time: 0.6274 [2021-03-26 21:23:05 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 920/1251] eta: 0:03:30 lr: 0.000745 loss: 3.3953 (3.4849) grad_norm: 1.2380 (inf) time: 0.6299 [2021-03-26 21:23:11 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 930/1251] eta: 0:03:24 lr: 0.000745 loss: 3.3953 (3.4812) grad_norm: 1.1912 (inf) time: 0.6333 [2021-03-26 21:23:18 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 940/1251] eta: 0:03:17 lr: 0.000745 loss: 3.6141 (3.4859) grad_norm: 1.1725 (inf) time: 0.6333 [2021-03-26 21:23:24 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 950/1251] eta: 0:03:11 lr: 0.000745 loss: 3.7144 (3.4865) grad_norm: 1.2082 (inf) time: 0.6405 [2021-03-26 21:23:30 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 960/1251] eta: 0:03:04 lr: 0.000745 loss: 3.6241 (3.4863) grad_norm: 1.1728 (inf) time: 0.6350 [2021-03-26 21:23:36 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 970/1251] eta: 0:02:58 lr: 0.000744 loss: 3.6811 (3.4864) grad_norm: 1.1330 (inf) time: 0.6212 [2021-03-26 21:23:43 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 980/1251] eta: 0:02:52 lr: 0.000744 loss: 3.4704 (3.4871) grad_norm: 1.1529 (inf) time: 0.6223 [2021-03-26 21:23:49 swin_base_patch4_window7_224] INFO: Epoch: [101] [ 990/1251] eta: 0:02:45 lr: 0.000744 loss: 3.4433 (3.4858) grad_norm: 1.1495 (inf) time: 0.6247 [2021-03-26 21:23:55 swin_base_patch4_window7_224] INFO: Epoch: [101] [1000/1251] eta: 0:02:39 lr: 0.000744 loss: 3.4210 (3.4857) grad_norm: 1.2063 (inf) time: 0.6275 [2021-03-26 21:24:02 swin_base_patch4_window7_224] INFO: Epoch: [101] [1010/1251] eta: 0:02:33 lr: 0.000744 loss: 3.4962 (3.4851) grad_norm: 1.2566 (inf) time: 0.6316 [2021-03-26 21:24:08 swin_base_patch4_window7_224] INFO: Epoch: [101] [1020/1251] eta: 0:02:26 lr: 0.000744 loss: 3.5728 (3.4859) grad_norm: 1.1783 (inf) time: 0.6306 [2021-03-26 21:24:14 swin_base_patch4_window7_224] INFO: Epoch: [101] [1030/1251] eta: 0:02:20 lr: 0.000744 loss: 3.4476 (3.4840) grad_norm: 1.1409 (inf) time: 0.6275 [2021-03-26 21:24:20 swin_base_patch4_window7_224] INFO: Epoch: [101] [1040/1251] eta: 0:02:13 lr: 0.000744 loss: 3.3590 (3.4822) grad_norm: 1.2672 (inf) time: 0.6291 [2021-03-26 21:24:27 swin_base_patch4_window7_224] INFO: Epoch: [101] [1050/1251] eta: 0:02:07 lr: 0.000744 loss: 3.5971 (3.4846) grad_norm: 1.2087 (inf) time: 0.6291 [2021-03-26 21:24:33 swin_base_patch4_window7_224] INFO: Epoch: [101] [1060/1251] eta: 0:02:01 lr: 0.000744 loss: 3.7112 (3.4855) grad_norm: 1.2445 (inf) time: 0.6349 [2021-03-26 21:24:39 swin_base_patch4_window7_224] INFO: Epoch: [101] [1070/1251] eta: 0:01:54 lr: 0.000744 loss: 3.5183 (3.4845) grad_norm: 1.2557 (inf) time: 0.6385 [2021-03-26 21:24:46 swin_base_patch4_window7_224] INFO: Epoch: [101] [1080/1251] eta: 0:01:48 lr: 0.000744 loss: 3.6304 (3.4865) grad_norm: 1.2174 (inf) time: 0.6314 [2021-03-26 21:24:52 swin_base_patch4_window7_224] INFO: Epoch: [101] [1090/1251] eta: 0:01:42 lr: 0.000744 loss: 3.6304 (3.4864) grad_norm: 1.2439 (inf) time: 0.6289 [2021-03-26 21:24:58 swin_base_patch4_window7_224] INFO: Epoch: [101] [1100/1251] eta: 0:01:35 lr: 0.000744 loss: 3.5500 (3.4881) grad_norm: 1.2439 (inf) time: 0.6314 [2021-03-26 21:25:05 swin_base_patch4_window7_224] INFO: Epoch: [101] [1110/1251] eta: 0:01:29 lr: 0.000744 loss: 3.6567 (3.4883) grad_norm: 1.2436 (inf) time: 0.6296 [2021-03-26 21:25:11 swin_base_patch4_window7_224] INFO: Epoch: [101] [1120/1251] eta: 0:01:23 lr: 0.000744 loss: 3.7920 (3.4907) grad_norm: 1.2973 (inf) time: 0.6237 [2021-03-26 21:25:17 swin_base_patch4_window7_224] INFO: Epoch: [101] [1130/1251] eta: 0:01:16 lr: 0.000744 loss: 3.7920 (3.4918) grad_norm: 1.3194 (inf) time: 0.6242 [2021-03-26 21:25:23 swin_base_patch4_window7_224] INFO: Epoch: [101] [1140/1251] eta: 0:01:10 lr: 0.000744 loss: 3.6594 (3.4913) grad_norm: 1.1697 (inf) time: 0.6239 [2021-03-26 21:25:30 swin_base_patch4_window7_224] INFO: Epoch: [101] [1150/1251] eta: 0:01:04 lr: 0.000744 loss: 3.4913 (3.4901) grad_norm: 1.1860 (inf) time: 0.6261 [2021-03-26 21:25:36 swin_base_patch4_window7_224] INFO: Epoch: [101] [1160/1251] eta: 0:00:57 lr: 0.000744 loss: 3.5946 (3.4897) grad_norm: 1.1806 (inf) time: 0.6261 [2021-03-26 21:25:42 swin_base_patch4_window7_224] INFO: Epoch: [101] [1170/1251] eta: 0:00:51 lr: 0.000744 loss: 3.7833 (3.4912) grad_norm: 1.1768 (inf) time: 0.6250 [2021-03-26 21:25:48 swin_base_patch4_window7_224] INFO: Epoch: [101] [1180/1251] eta: 0:00:45 lr: 0.000744 loss: 3.5688 (3.4894) grad_norm: 1.2075 (inf) time: 0.6291 [2021-03-26 21:25:55 swin_base_patch4_window7_224] INFO: Epoch: [101] [1190/1251] eta: 0:00:38 lr: 0.000744 loss: 3.4877 (3.4900) grad_norm: 1.2015 (inf) time: 0.6275 [2021-03-26 21:26:01 swin_base_patch4_window7_224] INFO: Epoch: [101] [1200/1251] eta: 0:00:32 lr: 0.000744 loss: 3.6615 (3.4920) grad_norm: 1.1758 (inf) time: 0.6283 [2021-03-26 21:26:07 swin_base_patch4_window7_224] INFO: Epoch: [101] [1210/1251] eta: 0:00:25 lr: 0.000744 loss: 3.8165 (3.4935) grad_norm: 1.1854 (inf) time: 0.6302 [2021-03-26 21:26:14 swin_base_patch4_window7_224] INFO: Epoch: [101] [1220/1251] eta: 0:00:19 lr: 0.000744 loss: 3.4176 (3.4927) grad_norm: 1.2027 (inf) time: 0.6270 [2021-03-26 21:26:20 swin_base_patch4_window7_224] INFO: Epoch: [101] [1230/1251] eta: 0:00:13 lr: 0.000744 loss: 3.5081 (3.4936) grad_norm: 1.2502 (inf) time: 0.6274 [2021-03-26 21:26:26 swin_base_patch4_window7_224] INFO: Epoch: [101] [1240/1251] eta: 0:00:06 lr: 0.000744 loss: 3.5081 (3.4936) grad_norm: 1.2108 (inf) time: 0.6246 [2021-03-26 21:26:32 swin_base_patch4_window7_224] INFO: Epoch: [101] [1250/1251] eta: 0:00:00 lr: 0.000743 loss: 3.4645 (3.4945) grad_norm: 1.1973 (inf) time: 0.6166 [2021-03-26 21:26:38 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:10 loss: 1.0679 (1.0679) acc1: 75.0000 (75.0000) acc5: 96.8750 (96.8750) [2021-03-26 21:26:41 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.0553 (1.0780) acc1: 76.5625 (75.0000) acc5: 93.7500 (93.3239) [2021-03-26 21:26:43 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0283 (1.0483) acc1: 76.5625 (75.9673) acc5: 93.7500 (93.5268) [2021-03-26 21:26:45 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0606 (1.0687) acc1: 75.0000 (75.4536) acc5: 92.1875 (93.3972) [2021-03-26 21:26:46 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0143 (1.0474) acc1: 75.0000 (75.6479) acc5: 93.7500 (93.5976) [2021-03-26 21:26:48 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9523 (1.0332) acc1: 76.5625 (76.0320) acc5: 93.7500 (93.7280) [2021-03-26 21:26:54 swin_base_patch4_window7_224] INFO: * Acc@1 76.708 Acc@5 93.736 loss 1.014 [2021-03-26 21:26:54 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.7% [2021-03-26 21:26:54 swin_base_patch4_window7_224] INFO: Max accuracy: 76.76% [2021-03-26 21:26:58 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 0/1251] eta: 1:28:20 lr: 0.000743 loss: 3.6546 (3.6546) grad_norm: 1.2160 (1.2160) time: 4.2373 [2021-03-26 21:27:04 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 10/1251] eta: 0:19:57 lr: 0.000743 loss: 3.6546 (3.3747) grad_norm: 1.2249 (1.2301) time: 0.9651 [2021-03-26 21:27:11 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 20/1251] eta: 0:16:31 lr: 0.000743 loss: 3.3673 (3.4032) grad_norm: 1.2425 (1.2539) time: 0.6338 [2021-03-26 21:27:17 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 30/1251] eta: 0:15:21 lr: 0.000743 loss: 3.3673 (3.3756) grad_norm: 1.2050 (1.2296) time: 0.6396 [2021-03-26 21:27:24 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 40/1251] eta: 0:14:38 lr: 0.000743 loss: 3.5933 (3.4370) grad_norm: 1.1772 (1.2238) time: 0.6412 [2021-03-26 21:27:30 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 50/1251] eta: 0:14:08 lr: 0.000743 loss: 3.6948 (3.4525) grad_norm: 1.1645 (1.2157) time: 0.6318 [2021-03-26 21:27:36 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 60/1251] eta: 0:13:48 lr: 0.000743 loss: 3.4395 (3.4328) grad_norm: 1.1510 (1.2098) time: 0.6344 [2021-03-26 21:27:43 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 70/1251] eta: 0:13:31 lr: 0.000743 loss: 2.9603 (3.3639) grad_norm: 1.1597 (1.1997) time: 0.6363 [2021-03-26 21:27:49 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 80/1251] eta: 0:13:15 lr: 0.000743 loss: 3.1331 (3.3929) grad_norm: 1.2057 (1.2140) time: 0.6308 [2021-03-26 21:27:55 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 90/1251] eta: 0:13:01 lr: 0.000743 loss: 3.6033 (3.3886) grad_norm: 1.2374 (1.2232) time: 0.6258 [2021-03-26 21:28:01 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 100/1251] eta: 0:12:50 lr: 0.000743 loss: 3.4337 (3.4094) grad_norm: 1.1872 (1.2210) time: 0.6293 [2021-03-26 21:28:08 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 110/1251] eta: 0:12:40 lr: 0.000743 loss: 3.4551 (3.4074) grad_norm: 1.1803 (1.2273) time: 0.6358 [2021-03-26 21:28:14 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 120/1251] eta: 0:12:30 lr: 0.000743 loss: 3.1572 (3.3854) grad_norm: 1.2121 (1.2258) time: 0.6345 [2021-03-26 21:28:20 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 130/1251] eta: 0:12:21 lr: 0.000743 loss: 3.3597 (3.3966) grad_norm: 1.2215 (1.2325) time: 0.6304 [2021-03-26 21:28:27 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 140/1251] eta: 0:12:11 lr: 0.000743 loss: 3.4502 (3.3953) grad_norm: 1.1660 (1.2288) time: 0.6257 [2021-03-26 21:28:33 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 150/1251] eta: 0:12:02 lr: 0.000743 loss: 3.4502 (3.3897) grad_norm: 1.1660 (1.2306) time: 0.6257 [2021-03-26 21:28:39 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 160/1251] eta: 0:11:54 lr: 0.000743 loss: 3.5636 (3.3906) grad_norm: 1.2553 (1.2296) time: 0.6334 [2021-03-26 21:28:46 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 170/1251] eta: 0:11:46 lr: 0.000743 loss: 3.6145 (3.3894) grad_norm: 1.2003 (1.2331) time: 0.6315 [2021-03-26 21:28:52 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 180/1251] eta: 0:11:38 lr: 0.000743 loss: 3.7148 (3.3976) grad_norm: 1.2003 (1.2305) time: 0.6300 [2021-03-26 21:28:58 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 190/1251] eta: 0:11:30 lr: 0.000743 loss: 3.2783 (3.3840) grad_norm: 1.1646 (1.2335) time: 0.6307 [2021-03-26 21:29:04 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 200/1251] eta: 0:11:23 lr: 0.000743 loss: 3.3680 (3.3930) grad_norm: 1.1926 (1.2341) time: 0.6273 [2021-03-26 21:29:11 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 210/1251] eta: 0:11:15 lr: 0.000743 loss: 3.5721 (3.3918) grad_norm: 1.2671 (1.2370) time: 0.6267 [2021-03-26 21:29:17 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 220/1251] eta: 0:11:08 lr: 0.000743 loss: 3.5164 (3.3953) grad_norm: 1.2751 (1.2396) time: 0.6297 [2021-03-26 21:29:23 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 230/1251] eta: 0:11:01 lr: 0.000743 loss: 3.5164 (3.4029) grad_norm: 1.1798 (1.2364) time: 0.6327 [2021-03-26 21:29:30 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 240/1251] eta: 0:10:53 lr: 0.000743 loss: 3.4760 (3.4104) grad_norm: 1.1578 (1.2326) time: 0.6270 [2021-03-26 21:29:36 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 250/1251] eta: 0:10:47 lr: 0.000743 loss: 3.6634 (3.4128) grad_norm: 1.1496 (1.2307) time: 0.6339 [2021-03-26 21:29:42 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 260/1251] eta: 0:10:40 lr: 0.000743 loss: 3.6634 (3.4169) grad_norm: 1.1228 (1.2266) time: 0.6419 [2021-03-26 21:29:49 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 270/1251] eta: 0:10:33 lr: 0.000742 loss: 3.4434 (3.4246) grad_norm: 1.1283 (1.2266) time: 0.6347 [2021-03-26 21:29:55 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 280/1251] eta: 0:10:26 lr: 0.000742 loss: 3.7131 (3.4334) grad_norm: 1.2206 (1.2303) time: 0.6311 [2021-03-26 21:30:01 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 290/1251] eta: 0:10:19 lr: 0.000742 loss: 3.7728 (3.4435) grad_norm: 1.3071 (1.2320) time: 0.6307 [2021-03-26 21:30:08 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 300/1251] eta: 0:10:12 lr: 0.000742 loss: 3.8729 (3.4559) grad_norm: 1.2612 (1.2324) time: 0.6304 [2021-03-26 21:30:14 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 310/1251] eta: 0:10:05 lr: 0.000742 loss: 3.6837 (3.4662) grad_norm: 1.1385 (1.2304) time: 0.6277 [2021-03-26 21:30:20 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 320/1251] eta: 0:09:58 lr: 0.000742 loss: 3.6486 (3.4674) grad_norm: 1.1445 (1.2307) time: 0.6304 [2021-03-26 21:30:27 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 330/1251] eta: 0:09:52 lr: 0.000742 loss: 3.7013 (3.4778) grad_norm: 1.1626 (1.2336) time: 0.6334 [2021-03-26 21:30:33 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 340/1251] eta: 0:09:45 lr: 0.000742 loss: 3.6788 (3.4794) grad_norm: 1.2486 (1.2343) time: 0.6298 [2021-03-26 21:30:39 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 350/1251] eta: 0:09:38 lr: 0.000742 loss: 3.6735 (3.4808) grad_norm: 1.2278 (1.2355) time: 0.6270 [2021-03-26 21:30:45 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 360/1251] eta: 0:09:31 lr: 0.000742 loss: 3.6890 (3.4809) grad_norm: 1.2706 (1.2392) time: 0.6267 [2021-03-26 21:30:52 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 370/1251] eta: 0:09:25 lr: 0.000742 loss: 3.4456 (3.4749) grad_norm: 1.2706 (1.2384) time: 0.6337 [2021-03-26 21:30:58 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 380/1251] eta: 0:09:18 lr: 0.000742 loss: 3.4129 (3.4762) grad_norm: 1.1588 (1.2367) time: 0.6337 [2021-03-26 21:31:04 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 390/1251] eta: 0:09:11 lr: 0.000742 loss: 3.5021 (3.4742) grad_norm: 1.1893 (1.2386) time: 0.6315 [2021-03-26 21:31:11 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 400/1251] eta: 0:09:05 lr: 0.000742 loss: 3.7548 (3.4830) grad_norm: 1.1908 (1.2380) time: 0.6351 [2021-03-26 21:31:17 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 410/1251] eta: 0:08:58 lr: 0.000742 loss: 3.7485 (3.4805) grad_norm: 1.1837 (1.2367) time: 0.6363 [2021-03-26 21:31:23 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 420/1251] eta: 0:08:52 lr: 0.000742 loss: 3.5528 (3.4825) grad_norm: 1.1837 (1.2362) time: 0.6322 [2021-03-26 21:31:30 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 430/1251] eta: 0:08:45 lr: 0.000742 loss: 3.6740 (3.4879) grad_norm: 1.1860 (1.2361) time: 0.6248 [2021-03-26 21:31:36 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 440/1251] eta: 0:08:38 lr: 0.000742 loss: 3.6257 (3.4848) grad_norm: 1.1930 (1.2406) time: 0.6278 [2021-03-26 21:31:42 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 450/1251] eta: 0:08:32 lr: 0.000742 loss: 3.4918 (3.4868) grad_norm: 1.2645 (1.2412) time: 0.6353 [2021-03-26 21:31:49 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 460/1251] eta: 0:08:25 lr: 0.000742 loss: 3.6947 (3.4905) grad_norm: 1.2467 (1.2407) time: 0.6316 [2021-03-26 21:31:55 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 470/1251] eta: 0:08:19 lr: 0.000742 loss: 3.5121 (3.4845) grad_norm: 1.2184 (1.2409) time: 0.6278 [2021-03-26 21:32:01 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 480/1251] eta: 0:08:12 lr: 0.000742 loss: 3.2417 (3.4820) grad_norm: 1.2051 (1.2410) time: 0.6318 [2021-03-26 21:32:08 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 490/1251] eta: 0:08:06 lr: 0.000742 loss: 3.2641 (3.4783) grad_norm: 1.1719 (1.2404) time: 0.6275 [2021-03-26 21:32:14 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 500/1251] eta: 0:07:59 lr: 0.000742 loss: 3.3170 (3.4780) grad_norm: 1.2030 (1.2401) time: 0.6230 [2021-03-26 21:32:20 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 510/1251] eta: 0:07:53 lr: 0.000742 loss: 3.3170 (3.4739) grad_norm: 1.2177 (1.2406) time: 0.6289 [2021-03-26 21:32:27 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 520/1251] eta: 0:07:46 lr: 0.000742 loss: 3.3347 (3.4778) grad_norm: 1.2768 (1.2430) time: 0.6358 [2021-03-26 21:32:33 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 530/1251] eta: 0:07:40 lr: 0.000742 loss: 3.6546 (3.4732) grad_norm: 1.3398 (1.2463) time: 0.6415 [2021-03-26 21:32:39 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 540/1251] eta: 0:07:33 lr: 0.000742 loss: 3.3901 (3.4736) grad_norm: 1.2242 (1.2456) time: 0.6404 [2021-03-26 21:32:46 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 550/1251] eta: 0:07:27 lr: 0.000741 loss: 3.4326 (3.4725) grad_norm: 1.1741 (1.2442) time: 0.6360 [2021-03-26 21:32:52 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 560/1251] eta: 0:07:21 lr: 0.000741 loss: 3.4032 (3.4697) grad_norm: 1.1682 (1.2426) time: 0.6319 [2021-03-26 21:32:58 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 570/1251] eta: 0:07:14 lr: 0.000741 loss: 3.4736 (3.4720) grad_norm: 1.1819 (1.2420) time: 0.6366 [2021-03-26 21:33:05 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 580/1251] eta: 0:07:08 lr: 0.000741 loss: 3.6417 (3.4747) grad_norm: 1.1819 (1.2407) time: 0.6382 [2021-03-26 21:33:11 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 590/1251] eta: 0:07:01 lr: 0.000741 loss: 3.4149 (3.4735) grad_norm: 1.1368 (1.2397) time: 0.6325 [2021-03-26 21:33:17 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 600/1251] eta: 0:06:55 lr: 0.000741 loss: 3.3932 (3.4746) grad_norm: 1.1546 (1.2390) time: 0.6376 [2021-03-26 21:33:24 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 610/1251] eta: 0:06:49 lr: 0.000741 loss: 3.5842 (3.4766) grad_norm: 1.1762 (1.2386) time: 0.6365 [2021-03-26 21:33:30 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 620/1251] eta: 0:06:42 lr: 0.000741 loss: 3.7025 (3.4819) grad_norm: 1.1809 (1.2383) time: 0.6242 [2021-03-26 21:33:36 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 630/1251] eta: 0:06:36 lr: 0.000741 loss: 3.7028 (3.4820) grad_norm: 1.2211 (1.2392) time: 0.6271 [2021-03-26 21:33:43 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 640/1251] eta: 0:06:29 lr: 0.000741 loss: 3.3127 (3.4767) grad_norm: 1.2060 (1.2392) time: 0.6303 [2021-03-26 21:33:49 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 650/1251] eta: 0:06:23 lr: 0.000741 loss: 3.2240 (3.4731) grad_norm: 1.2060 (1.2390) time: 0.6240 [2021-03-26 21:33:55 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 660/1251] eta: 0:06:16 lr: 0.000741 loss: 3.5956 (3.4764) grad_norm: 1.2179 (1.2394) time: 0.6254 [2021-03-26 21:34:01 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 670/1251] eta: 0:06:10 lr: 0.000741 loss: 3.7021 (3.4771) grad_norm: 1.2175 (1.2398) time: 0.6275 [2021-03-26 21:34:08 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 680/1251] eta: 0:06:03 lr: 0.000741 loss: 3.5278 (3.4773) grad_norm: 1.2140 (1.2410) time: 0.6301 [2021-03-26 21:34:14 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 690/1251] eta: 0:05:57 lr: 0.000741 loss: 3.4023 (3.4754) grad_norm: 1.2837 (1.2414) time: 0.6275 [2021-03-26 21:34:20 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 700/1251] eta: 0:05:50 lr: 0.000741 loss: 3.4465 (3.4749) grad_norm: 1.2310 (1.2412) time: 0.6257 [2021-03-26 21:34:27 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 710/1251] eta: 0:05:44 lr: 0.000741 loss: 3.4075 (3.4739) grad_norm: 1.1726 (1.2410) time: 0.6289 [2021-03-26 21:34:33 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 720/1251] eta: 0:05:37 lr: 0.000741 loss: 3.3567 (3.4692) grad_norm: 1.2445 (1.2413) time: 0.6290 [2021-03-26 21:34:39 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 730/1251] eta: 0:05:31 lr: 0.000741 loss: 3.4517 (3.4725) grad_norm: 1.2211 (1.2408) time: 0.6258 [2021-03-26 21:34:45 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 740/1251] eta: 0:05:25 lr: 0.000741 loss: 3.6536 (3.4719) grad_norm: 1.1952 (1.2413) time: 0.6311 [2021-03-26 21:34:52 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 750/1251] eta: 0:05:18 lr: 0.000741 loss: 3.4962 (3.4737) grad_norm: 1.2759 (1.2424) time: 0.6336 [2021-03-26 21:34:58 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 760/1251] eta: 0:05:12 lr: 0.000741 loss: 3.5928 (3.4750) grad_norm: 1.2759 (1.2425) time: 0.6329 [2021-03-26 21:35:04 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 770/1251] eta: 0:05:06 lr: 0.000741 loss: 3.7361 (3.4787) grad_norm: 1.2638 (1.2437) time: 0.6377 [2021-03-26 21:35:11 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 780/1251] eta: 0:04:59 lr: 0.000741 loss: 3.7678 (3.4805) grad_norm: 1.1873 (1.2439) time: 0.6378 [2021-03-26 21:35:17 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 790/1251] eta: 0:04:53 lr: 0.000741 loss: 3.6924 (3.4818) grad_norm: 1.2071 (1.2447) time: 0.6301 [2021-03-26 21:35:23 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 800/1251] eta: 0:04:46 lr: 0.000741 loss: 3.7113 (3.4832) grad_norm: 1.2746 (1.2453) time: 0.6241 [2021-03-26 21:35:30 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 810/1251] eta: 0:04:40 lr: 0.000741 loss: 3.7113 (3.4826) grad_norm: 1.2746 (1.2452) time: 0.6273 [2021-03-26 21:35:36 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 820/1251] eta: 0:04:34 lr: 0.000740 loss: 3.7361 (3.4839) grad_norm: 1.1408 (1.2442) time: 0.6328 [2021-03-26 21:35:42 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 830/1251] eta: 0:04:27 lr: 0.000740 loss: 3.7647 (3.4859) grad_norm: 1.1933 (1.2442) time: 0.6377 [2021-03-26 21:35:49 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 840/1251] eta: 0:04:21 lr: 0.000740 loss: 3.7934 (3.4883) grad_norm: 1.2046 (1.2438) time: 0.6332 [2021-03-26 21:35:55 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 850/1251] eta: 0:04:14 lr: 0.000740 loss: 3.7934 (3.4894) grad_norm: 1.1487 (1.2436) time: 0.6285 [2021-03-26 21:36:01 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 860/1251] eta: 0:04:08 lr: 0.000740 loss: 3.3351 (3.4856) grad_norm: 1.1313 (1.2430) time: 0.6299 [2021-03-26 21:36:08 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 870/1251] eta: 0:04:02 lr: 0.000740 loss: 3.1784 (3.4838) grad_norm: 1.2931 (1.2444) time: 0.6311 [2021-03-26 21:36:14 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 880/1251] eta: 0:03:55 lr: 0.000740 loss: 3.4238 (3.4849) grad_norm: 1.3264 (1.2449) time: 0.6350 [2021-03-26 21:36:20 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 890/1251] eta: 0:03:49 lr: 0.000740 loss: 3.5735 (3.4872) grad_norm: 1.2083 (1.2446) time: 0.6379 [2021-03-26 21:36:27 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 900/1251] eta: 0:03:43 lr: 0.000740 loss: 3.6662 (3.4902) grad_norm: 1.2574 (1.2461) time: 0.6383 [2021-03-26 21:36:33 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 910/1251] eta: 0:03:36 lr: 0.000740 loss: 3.6332 (3.4906) grad_norm: 1.2600 (1.2452) time: 0.6350 [2021-03-26 21:36:39 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 920/1251] eta: 0:03:30 lr: 0.000740 loss: 3.6944 (3.4939) grad_norm: 1.1295 (1.2437) time: 0.6255 [2021-03-26 21:36:46 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 930/1251] eta: 0:03:23 lr: 0.000740 loss: 3.5569 (3.4918) grad_norm: 1.1295 (1.2430) time: 0.6238 [2021-03-26 21:36:52 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 940/1251] eta: 0:03:17 lr: 0.000740 loss: 3.5482 (3.4954) grad_norm: 1.1702 (1.2427) time: 0.6260 [2021-03-26 21:36:58 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 950/1251] eta: 0:03:11 lr: 0.000740 loss: 3.7084 (3.4973) grad_norm: 1.2073 (1.2426) time: 0.6291 [2021-03-26 21:37:04 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 960/1251] eta: 0:03:04 lr: 0.000740 loss: 3.6515 (3.4968) grad_norm: 1.2073 (1.2422) time: 0.6305 [2021-03-26 21:37:11 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 970/1251] eta: 0:02:58 lr: 0.000740 loss: 3.7359 (3.4973) grad_norm: 1.2020 (1.2419) time: 0.6355 [2021-03-26 21:37:17 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 980/1251] eta: 0:02:52 lr: 0.000740 loss: 3.6310 (3.4960) grad_norm: 1.2020 (1.2419) time: 0.6329 [2021-03-26 21:37:23 swin_base_patch4_window7_224] INFO: Epoch: [102] [ 990/1251] eta: 0:02:45 lr: 0.000740 loss: 3.4061 (3.4948) grad_norm: 1.2110 (1.2420) time: 0.6238 [2021-03-26 21:37:30 swin_base_patch4_window7_224] INFO: Epoch: [102] [1000/1251] eta: 0:02:39 lr: 0.000740 loss: 3.3460 (3.4937) grad_norm: 1.2312 (1.2419) time: 0.6308 [2021-03-26 21:37:36 swin_base_patch4_window7_224] INFO: Epoch: [102] [1010/1251] eta: 0:02:33 lr: 0.000740 loss: 3.4629 (3.4935) grad_norm: 1.1904 (1.2416) time: 0.6287 [2021-03-26 21:37:42 swin_base_patch4_window7_224] INFO: Epoch: [102] [1020/1251] eta: 0:02:26 lr: 0.000740 loss: 3.5812 (3.4956) grad_norm: 1.1796 (1.2414) time: 0.6243 [2021-03-26 21:37:48 swin_base_patch4_window7_224] INFO: Epoch: [102] [1030/1251] eta: 0:02:20 lr: 0.000740 loss: 3.5606 (3.4957) grad_norm: 1.2480 (1.2417) time: 0.6290 [2021-03-26 21:37:55 swin_base_patch4_window7_224] INFO: Epoch: [102] [1040/1251] eta: 0:02:13 lr: 0.000740 loss: 3.5335 (3.4953) grad_norm: 1.2683 (1.2420) time: 0.6281 [2021-03-26 21:38:01 swin_base_patch4_window7_224] INFO: Epoch: [102] [1050/1251] eta: 0:02:07 lr: 0.000740 loss: 3.5972 (3.4944) grad_norm: 1.2403 (1.2428) time: 0.6265 [2021-03-26 21:38:07 swin_base_patch4_window7_224] INFO: Epoch: [102] [1060/1251] eta: 0:02:01 lr: 0.000740 loss: 3.5047 (3.4937) grad_norm: 1.3001 (1.2438) time: 0.6319 [2021-03-26 21:38:14 swin_base_patch4_window7_224] INFO: Epoch: [102] [1070/1251] eta: 0:01:54 lr: 0.000740 loss: 3.5777 (3.4947) grad_norm: 1.2267 (1.2430) time: 0.6337 [2021-03-26 21:38:20 swin_base_patch4_window7_224] INFO: Epoch: [102] [1080/1251] eta: 0:01:48 lr: 0.000740 loss: 3.7424 (3.4943) grad_norm: 1.2087 (1.2431) time: 0.6350 [2021-03-26 21:38:26 swin_base_patch4_window7_224] INFO: Epoch: [102] [1090/1251] eta: 0:01:42 lr: 0.000740 loss: 3.5221 (3.4929) grad_norm: 1.2087 (1.2430) time: 0.6373 [2021-03-26 21:38:33 swin_base_patch4_window7_224] INFO: Epoch: [102] [1100/1251] eta: 0:01:35 lr: 0.000739 loss: 3.5463 (3.4933) grad_norm: 1.1971 (1.2436) time: 0.6345 [2021-03-26 21:38:39 swin_base_patch4_window7_224] INFO: Epoch: [102] [1110/1251] eta: 0:01:29 lr: 0.000739 loss: 3.6542 (3.4942) grad_norm: 1.2093 (1.2439) time: 0.6296 [2021-03-26 21:38:45 swin_base_patch4_window7_224] INFO: Epoch: [102] [1120/1251] eta: 0:01:23 lr: 0.000739 loss: 3.4394 (3.4934) grad_norm: 1.2102 (1.2439) time: 0.6234 [2021-03-26 21:38:51 swin_base_patch4_window7_224] INFO: Epoch: [102] [1130/1251] eta: 0:01:16 lr: 0.000739 loss: 3.4394 (3.4924) grad_norm: 1.1842 (1.2432) time: 0.6232 [2021-03-26 21:38:58 swin_base_patch4_window7_224] INFO: Epoch: [102] [1140/1251] eta: 0:01:10 lr: 0.000739 loss: 3.4167 (3.4901) grad_norm: 1.1773 (1.2432) time: 0.6266 [2021-03-26 21:39:04 swin_base_patch4_window7_224] INFO: Epoch: [102] [1150/1251] eta: 0:01:04 lr: 0.000739 loss: 3.2888 (3.4875) grad_norm: 1.2312 (1.2435) time: 0.6278 [2021-03-26 21:39:10 swin_base_patch4_window7_224] INFO: Epoch: [102] [1160/1251] eta: 0:00:57 lr: 0.000739 loss: 3.2888 (3.4871) grad_norm: 1.1902 (1.2431) time: 0.6246 [2021-03-26 21:39:17 swin_base_patch4_window7_224] INFO: Epoch: [102] [1170/1251] eta: 0:00:51 lr: 0.000739 loss: 3.6083 (3.4892) grad_norm: 1.1900 (1.2434) time: 0.6264 [2021-03-26 21:39:23 swin_base_patch4_window7_224] INFO: Epoch: [102] [1180/1251] eta: 0:00:45 lr: 0.000739 loss: 3.9321 (3.4903) grad_norm: 1.3149 (1.2440) time: 0.6295 [2021-03-26 21:39:29 swin_base_patch4_window7_224] INFO: Epoch: [102] [1190/1251] eta: 0:00:38 lr: 0.000739 loss: 3.3196 (3.4892) grad_norm: 1.2577 (1.2438) time: 0.6288 [2021-03-26 21:39:35 swin_base_patch4_window7_224] INFO: Epoch: [102] [1200/1251] eta: 0:00:32 lr: 0.000739 loss: 3.3196 (3.4886) grad_norm: 1.2612 (1.2451) time: 0.6323 [2021-03-26 21:39:42 swin_base_patch4_window7_224] INFO: Epoch: [102] [1210/1251] eta: 0:00:25 lr: 0.000739 loss: 3.1301 (3.4851) grad_norm: 1.2757 (1.2450) time: 0.6310 [2021-03-26 21:39:48 swin_base_patch4_window7_224] INFO: Epoch: [102] [1220/1251] eta: 0:00:19 lr: 0.000739 loss: 3.3903 (3.4866) grad_norm: 1.2200 (1.2449) time: 0.6345 [2021-03-26 21:39:54 swin_base_patch4_window7_224] INFO: Epoch: [102] [1230/1251] eta: 0:00:13 lr: 0.000739 loss: 3.4836 (3.4852) grad_norm: 1.1995 (1.2443) time: 0.6340 [2021-03-26 21:40:01 swin_base_patch4_window7_224] INFO: Epoch: [102] [1240/1251] eta: 0:00:06 lr: 0.000739 loss: 3.4836 (3.4845) grad_norm: 1.1770 (1.2445) time: 0.6229 [2021-03-26 21:40:07 swin_base_patch4_window7_224] INFO: Epoch: [102] [1250/1251] eta: 0:00:00 lr: 0.000739 loss: 3.8211 (3.4869) grad_norm: 1.1770 (1.2438) time: 0.6222 [2021-03-26 21:40:13 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:50 loss: 1.1967 (1.1967) acc1: 75.0000 (75.0000) acc5: 89.0625 (89.0625) [2021-03-26 21:40:16 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.9680 (0.9845) acc1: 76.5625 (76.7045) acc5: 95.3125 (94.6023) [2021-03-26 21:40:18 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0099 (1.0418) acc1: 75.0000 (75.4464) acc5: 95.3125 (93.8988) [2021-03-26 21:40:20 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9872 (1.0106) acc1: 75.0000 (76.3105) acc5: 93.7500 (93.9012) [2021-03-26 21:40:23 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9655 (1.0176) acc1: 76.5625 (75.9909) acc5: 95.3125 (94.2835) [2021-03-26 21:40:24 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9771 (1.0060) acc1: 75.4717 (75.9360) acc5: 95.3125 (94.2720) [2021-03-26 21:40:30 swin_base_patch4_window7_224] INFO: * Acc@1 76.920 Acc@5 93.888 loss 0.999 [2021-03-26 21:40:30 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.9% [2021-03-26 21:40:30 swin_base_patch4_window7_224] INFO: Max accuracy: 76.92% [2021-03-26 21:40:34 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 0/1251] eta: 1:31:16 lr: 0.000739 loss: 3.7690 (3.7690) grad_norm: 1.2504 (1.2504) time: 4.3778 [2021-03-26 21:40:40 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 10/1251] eta: 0:20:15 lr: 0.000739 loss: 3.4517 (3.2113) grad_norm: 1.2043 (1.2539) time: 0.9793 [2021-03-26 21:40:47 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 20/1251] eta: 0:16:34 lr: 0.000739 loss: 3.4517 (3.3886) grad_norm: 1.2152 (1.2820) time: 0.6298 [2021-03-26 21:40:53 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 30/1251] eta: 0:15:12 lr: 0.000739 loss: 3.4330 (3.4149) grad_norm: 1.2686 (1.3051) time: 0.6200 [2021-03-26 21:40:59 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 40/1251] eta: 0:14:29 lr: 0.000739 loss: 3.3718 (3.3755) grad_norm: 1.2789 (1.2936) time: 0.6230 [2021-03-26 21:41:05 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 50/1251] eta: 0:14:01 lr: 0.000739 loss: 3.3124 (3.3548) grad_norm: 1.2127 (1.2728) time: 0.6275 [2021-03-26 21:41:12 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 60/1251] eta: 0:13:43 lr: 0.000739 loss: 3.6619 (3.4071) grad_norm: 1.2406 (1.2813) time: 0.6360 [2021-03-26 21:41:18 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 70/1251] eta: 0:13:27 lr: 0.000739 loss: 3.6716 (3.4409) grad_norm: 1.2446 (1.2837) time: 0.6398 [2021-03-26 21:41:24 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 80/1251] eta: 0:13:13 lr: 0.000739 loss: 3.6355 (3.4470) grad_norm: 1.2595 (1.2858) time: 0.6360 [2021-03-26 21:41:31 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 90/1251] eta: 0:13:01 lr: 0.000739 loss: 3.6376 (3.4645) grad_norm: 1.2503 (1.2785) time: 0.6352 [2021-03-26 21:41:37 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 100/1251] eta: 0:12:48 lr: 0.000739 loss: 3.6129 (3.4491) grad_norm: 1.2503 (1.2791) time: 0.6293 [2021-03-26 21:41:43 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 110/1251] eta: 0:12:38 lr: 0.000739 loss: 3.1293 (3.4265) grad_norm: 1.2242 (1.2732) time: 0.6260 [2021-03-26 21:41:50 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 120/1251] eta: 0:12:28 lr: 0.000738 loss: 3.1584 (3.4323) grad_norm: 1.1884 (1.2730) time: 0.6333 [2021-03-26 21:41:56 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 130/1251] eta: 0:12:19 lr: 0.000738 loss: 3.6597 (3.4378) grad_norm: 1.1884 (1.2680) time: 0.6360 [2021-03-26 21:42:02 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 140/1251] eta: 0:12:10 lr: 0.000738 loss: 3.5414 (3.4411) grad_norm: 1.2335 (1.2680) time: 0.6304 [2021-03-26 21:42:09 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 150/1251] eta: 0:12:01 lr: 0.000738 loss: 3.5414 (3.4465) grad_norm: 1.2963 (1.2684) time: 0.6277 [2021-03-26 21:42:15 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 160/1251] eta: 0:11:54 lr: 0.000738 loss: 3.6870 (3.4564) grad_norm: 1.2890 (1.2662) time: 0.6349 [2021-03-26 21:42:21 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 170/1251] eta: 0:11:46 lr: 0.000738 loss: 3.6065 (3.4607) grad_norm: 1.2890 (1.2697) time: 0.6371 [2021-03-26 21:42:28 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 180/1251] eta: 0:11:38 lr: 0.000738 loss: 3.5111 (3.4542) grad_norm: 1.2898 (1.2710) time: 0.6328 [2021-03-26 21:42:34 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 190/1251] eta: 0:11:31 lr: 0.000738 loss: 3.3808 (3.4479) grad_norm: 1.2898 (1.2736) time: 0.6357 [2021-03-26 21:42:40 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 200/1251] eta: 0:11:24 lr: 0.000738 loss: 3.5297 (3.4612) grad_norm: 1.2760 (1.2719) time: 0.6413 [2021-03-26 21:42:47 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 210/1251] eta: 0:11:16 lr: 0.000738 loss: 3.6070 (3.4649) grad_norm: 1.1236 (1.2660) time: 0.6363 [2021-03-26 21:42:53 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 220/1251] eta: 0:11:09 lr: 0.000738 loss: 3.5557 (3.4638) grad_norm: 1.1345 (1.2677) time: 0.6269 [2021-03-26 21:42:59 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 230/1251] eta: 0:11:01 lr: 0.000738 loss: 3.4130 (3.4639) grad_norm: 1.1457 (1.2646) time: 0.6219 [2021-03-26 21:43:06 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 240/1251] eta: 0:10:54 lr: 0.000738 loss: 3.3117 (3.4669) grad_norm: 1.2382 (1.2756) time: 0.6301 [2021-03-26 21:43:12 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 250/1251] eta: 0:10:47 lr: 0.000738 loss: 3.6318 (3.4710) grad_norm: 1.2322 (1.2697) time: 0.6362 [2021-03-26 21:43:18 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 260/1251] eta: 0:10:40 lr: 0.000738 loss: 3.5929 (3.4670) grad_norm: 1.1432 (1.2687) time: 0.6293 [2021-03-26 21:43:24 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 270/1251] eta: 0:10:33 lr: 0.000738 loss: 3.4507 (3.4660) grad_norm: 1.1771 (1.2691) time: 0.6272 [2021-03-26 21:43:31 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 280/1251] eta: 0:10:26 lr: 0.000738 loss: 3.4507 (3.4595) grad_norm: 1.2180 (1.2661) time: 0.6287 [2021-03-26 21:43:37 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 290/1251] eta: 0:10:19 lr: 0.000738 loss: 3.3132 (3.4528) grad_norm: 1.1061 (1.2623) time: 0.6274 [2021-03-26 21:43:43 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 300/1251] eta: 0:10:12 lr: 0.000738 loss: 3.3802 (3.4503) grad_norm: 1.1591 (1.2606) time: 0.6254 [2021-03-26 21:43:50 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 310/1251] eta: 0:10:05 lr: 0.000738 loss: 3.3802 (3.4542) grad_norm: 1.2061 (1.2596) time: 0.6358 [2021-03-26 21:43:56 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 320/1251] eta: 0:09:58 lr: 0.000738 loss: 3.2925 (3.4483) grad_norm: 1.2690 (1.2617) time: 0.6343 [2021-03-26 21:44:02 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 330/1251] eta: 0:09:51 lr: 0.000738 loss: 3.3116 (3.4525) grad_norm: 1.2822 (1.2631) time: 0.6285 [2021-03-26 21:44:09 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 340/1251] eta: 0:09:45 lr: 0.000738 loss: 3.4436 (3.4478) grad_norm: 1.1791 (1.2618) time: 0.6327 [2021-03-26 21:44:15 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 350/1251] eta: 0:09:38 lr: 0.000738 loss: 3.2685 (3.4486) grad_norm: 1.1921 (1.2627) time: 0.6295 [2021-03-26 21:44:21 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 360/1251] eta: 0:09:31 lr: 0.000738 loss: 3.4774 (3.4514) grad_norm: 1.2187 (1.2634) time: 0.6292 [2021-03-26 21:44:28 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 370/1251] eta: 0:09:25 lr: 0.000738 loss: 3.4649 (3.4515) grad_norm: 1.2062 (1.2628) time: 0.6318 [2021-03-26 21:44:34 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 380/1251] eta: 0:09:18 lr: 0.000738 loss: 3.6102 (3.4597) grad_norm: 1.2948 (1.2652) time: 0.6337 [2021-03-26 21:44:40 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 390/1251] eta: 0:09:11 lr: 0.000737 loss: 3.6721 (3.4617) grad_norm: 1.3285 (1.2653) time: 0.6299 [2021-03-26 21:44:46 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 400/1251] eta: 0:09:05 lr: 0.000737 loss: 3.6225 (3.4633) grad_norm: 1.2180 (1.2639) time: 0.6268 [2021-03-26 21:44:53 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 410/1251] eta: 0:08:58 lr: 0.000737 loss: 3.6533 (3.4718) grad_norm: 1.1850 (1.2627) time: 0.6274 [2021-03-26 21:44:59 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 420/1251] eta: 0:08:51 lr: 0.000737 loss: 3.6616 (3.4722) grad_norm: 1.1859 (1.2612) time: 0.6256 [2021-03-26 21:45:05 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 430/1251] eta: 0:08:44 lr: 0.000737 loss: 3.4553 (3.4721) grad_norm: 1.1974 (1.2618) time: 0.6226 [2021-03-26 21:45:11 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 440/1251] eta: 0:08:38 lr: 0.000737 loss: 3.6473 (3.4800) grad_norm: 1.2264 (1.2622) time: 0.6259 [2021-03-26 21:45:18 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 450/1251] eta: 0:08:31 lr: 0.000737 loss: 3.6297 (3.4716) grad_norm: 1.2220 (1.2617) time: 0.6273 [2021-03-26 21:45:24 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 460/1251] eta: 0:08:25 lr: 0.000737 loss: 3.3501 (3.4674) grad_norm: 1.1736 (1.2609) time: 0.6303 [2021-03-26 21:45:30 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 470/1251] eta: 0:08:18 lr: 0.000737 loss: 3.3991 (3.4691) grad_norm: 1.1782 (1.2607) time: 0.6379 [2021-03-26 21:45:37 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 480/1251] eta: 0:08:12 lr: 0.000737 loss: 3.6460 (3.4689) grad_norm: 1.1841 (1.2593) time: 0.6311 [2021-03-26 21:45:43 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 490/1251] eta: 0:08:05 lr: 0.000737 loss: 3.7009 (3.4699) grad_norm: 1.1982 (1.2597) time: 0.6273 [2021-03-26 21:45:49 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 500/1251] eta: 0:07:59 lr: 0.000737 loss: 3.7103 (3.4696) grad_norm: 1.2616 (1.2608) time: 0.6289 [2021-03-26 21:45:56 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 510/1251] eta: 0:07:52 lr: 0.000737 loss: 3.7011 (3.4723) grad_norm: 1.2616 (1.2610) time: 0.6254 [2021-03-26 21:46:02 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 520/1251] eta: 0:07:46 lr: 0.000737 loss: 3.6331 (3.4723) grad_norm: 1.1855 (1.2599) time: 0.6259 [2021-03-26 21:46:08 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 530/1251] eta: 0:07:39 lr: 0.000737 loss: 3.4364 (3.4692) grad_norm: 1.1523 (1.2578) time: 0.6287 [2021-03-26 21:46:14 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 540/1251] eta: 0:07:33 lr: 0.000737 loss: 3.2134 (3.4657) grad_norm: 1.1697 (1.2582) time: 0.6296 [2021-03-26 21:46:21 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 550/1251] eta: 0:07:26 lr: 0.000737 loss: 3.3693 (3.4639) grad_norm: 1.2070 (1.2578) time: 0.6341 [2021-03-26 21:46:27 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 560/1251] eta: 0:07:20 lr: 0.000737 loss: 3.4673 (3.4633) grad_norm: 1.2113 (1.2590) time: 0.6325 [2021-03-26 21:46:33 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 570/1251] eta: 0:07:13 lr: 0.000737 loss: 3.5685 (3.4680) grad_norm: 1.2309 (1.2587) time: 0.6315 [2021-03-26 21:46:40 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 580/1251] eta: 0:07:07 lr: 0.000737 loss: 3.6443 (3.4721) grad_norm: 1.2133 (1.2583) time: 0.6333 [2021-03-26 21:46:46 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 590/1251] eta: 0:07:00 lr: 0.000737 loss: 3.6443 (3.4714) grad_norm: 1.2179 (1.2597) time: 0.6282 [2021-03-26 21:46:52 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 600/1251] eta: 0:06:54 lr: 0.000737 loss: 3.4058 (3.4665) grad_norm: 1.2740 (1.2609) time: 0.6252 [2021-03-26 21:46:59 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 610/1251] eta: 0:06:47 lr: 0.000737 loss: 3.5484 (3.4709) grad_norm: 1.1834 (1.2599) time: 0.6262 [2021-03-26 21:47:05 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 620/1251] eta: 0:06:41 lr: 0.000737 loss: 3.5700 (3.4690) grad_norm: 1.1795 (1.2595) time: 0.6323 [2021-03-26 21:47:11 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 630/1251] eta: 0:06:35 lr: 0.000737 loss: 3.5163 (3.4702) grad_norm: 1.2042 (1.2588) time: 0.6297 [2021-03-26 21:47:17 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 640/1251] eta: 0:06:28 lr: 0.000737 loss: 3.5762 (3.4737) grad_norm: 1.1961 (1.2580) time: 0.6272 [2021-03-26 21:47:24 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 650/1251] eta: 0:06:22 lr: 0.000737 loss: 3.8454 (3.4764) grad_norm: 1.2079 (1.2579) time: 0.6281 [2021-03-26 21:47:30 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 660/1251] eta: 0:06:15 lr: 0.000736 loss: 3.6642 (3.4764) grad_norm: 1.1750 (1.2573) time: 0.6240 [2021-03-26 21:47:36 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 670/1251] eta: 0:06:09 lr: 0.000736 loss: 3.3307 (3.4737) grad_norm: 1.2085 (1.2578) time: 0.6318 [2021-03-26 21:47:43 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 680/1251] eta: 0:06:03 lr: 0.000736 loss: 3.3307 (3.4731) grad_norm: 1.2300 (1.2573) time: 0.6367 [2021-03-26 21:47:49 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 690/1251] eta: 0:05:56 lr: 0.000736 loss: 3.5947 (3.4742) grad_norm: 1.2007 (1.2571) time: 0.6345 [2021-03-26 21:47:55 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 700/1251] eta: 0:05:50 lr: 0.000736 loss: 3.5074 (3.4726) grad_norm: 1.2276 (1.2573) time: 0.6292 [2021-03-26 21:48:02 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 710/1251] eta: 0:05:43 lr: 0.000736 loss: 3.4779 (3.4719) grad_norm: 1.2123 (1.2569) time: 0.6265 [2021-03-26 21:48:08 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 720/1251] eta: 0:05:37 lr: 0.000736 loss: 3.4993 (3.4737) grad_norm: 1.2123 (1.2572) time: 0.6277 [2021-03-26 21:48:14 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 730/1251] eta: 0:05:31 lr: 0.000736 loss: 3.5951 (3.4734) grad_norm: 1.2660 (1.2569) time: 0.6321 [2021-03-26 21:48:21 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 740/1251] eta: 0:05:24 lr: 0.000736 loss: 3.5451 (3.4734) grad_norm: 1.2561 (1.2565) time: 0.6433 [2021-03-26 21:48:27 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 750/1251] eta: 0:05:18 lr: 0.000736 loss: 3.5990 (3.4748) grad_norm: 1.2277 (1.2561) time: 0.6481 [2021-03-26 21:48:33 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 760/1251] eta: 0:05:12 lr: 0.000736 loss: 3.3617 (3.4697) grad_norm: 1.2078 (1.2558) time: 0.6394 [2021-03-26 21:48:40 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 770/1251] eta: 0:05:05 lr: 0.000736 loss: 3.3552 (3.4714) grad_norm: 1.1939 (1.2554) time: 0.6274 [2021-03-26 21:48:46 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 780/1251] eta: 0:04:59 lr: 0.000736 loss: 3.6761 (3.4726) grad_norm: 1.1956 (1.2552) time: 0.6227 [2021-03-26 21:48:52 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 790/1251] eta: 0:04:52 lr: 0.000736 loss: 3.6188 (3.4727) grad_norm: 1.2429 (1.2568) time: 0.6297 [2021-03-26 21:48:59 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 800/1251] eta: 0:04:46 lr: 0.000736 loss: 3.2364 (3.4660) grad_norm: 1.2709 (1.2576) time: 0.6321 [2021-03-26 21:49:05 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 810/1251] eta: 0:04:40 lr: 0.000736 loss: 3.3268 (3.4661) grad_norm: 1.2759 (1.2584) time: 0.6243 [2021-03-26 21:49:11 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 820/1251] eta: 0:04:33 lr: 0.000736 loss: 3.4339 (3.4676) grad_norm: 1.2329 (1.2573) time: 0.6290 [2021-03-26 21:49:17 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 830/1251] eta: 0:04:27 lr: 0.000736 loss: 3.5681 (3.4697) grad_norm: 1.2700 (1.2579) time: 0.6322 [2021-03-26 21:49:24 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 840/1251] eta: 0:04:21 lr: 0.000736 loss: 3.7333 (3.4718) grad_norm: 1.2315 (1.2573) time: 0.6299 [2021-03-26 21:49:30 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 850/1251] eta: 0:04:14 lr: 0.000736 loss: 3.6684 (3.4710) grad_norm: 1.2130 (1.2578) time: 0.6319 [2021-03-26 21:49:36 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 860/1251] eta: 0:04:08 lr: 0.000736 loss: 3.3376 (3.4694) grad_norm: 1.2353 (1.2574) time: 0.6319 [2021-03-26 21:49:43 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 870/1251] eta: 0:04:01 lr: 0.000736 loss: 3.6354 (3.4694) grad_norm: 1.2303 (1.2576) time: 0.6293 [2021-03-26 21:49:49 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 880/1251] eta: 0:03:55 lr: 0.000736 loss: 3.6497 (3.4689) grad_norm: 1.2456 (1.2585) time: 0.6280 [2021-03-26 21:49:55 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 890/1251] eta: 0:03:49 lr: 0.000736 loss: 3.3130 (3.4672) grad_norm: 1.2631 (1.2582) time: 0.6278 [2021-03-26 21:50:02 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 900/1251] eta: 0:03:42 lr: 0.000736 loss: 3.2245 (3.4656) grad_norm: 1.2074 (1.2582) time: 0.6325 [2021-03-26 21:50:08 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 910/1251] eta: 0:03:36 lr: 0.000736 loss: 3.4885 (3.4656) grad_norm: 1.2545 (1.2585) time: 0.6309 [2021-03-26 21:50:14 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 920/1251] eta: 0:03:30 lr: 0.000736 loss: 3.5569 (3.4658) grad_norm: 1.2403 (1.2581) time: 0.6249 [2021-03-26 21:50:20 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 930/1251] eta: 0:03:23 lr: 0.000736 loss: 3.5961 (3.4684) grad_norm: 1.2636 (1.2587) time: 0.6312 [2021-03-26 21:50:27 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 940/1251] eta: 0:03:17 lr: 0.000735 loss: 3.6045 (3.4689) grad_norm: 1.2433 (1.2581) time: 0.6311 [2021-03-26 21:50:33 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 950/1251] eta: 0:03:11 lr: 0.000735 loss: 3.8157 (3.4737) grad_norm: 1.2281 (1.2579) time: 0.6342 [2021-03-26 21:50:40 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 960/1251] eta: 0:03:04 lr: 0.000735 loss: 3.8437 (3.4759) grad_norm: 1.2226 (1.2571) time: 0.6431 [2021-03-26 21:50:46 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 970/1251] eta: 0:02:58 lr: 0.000735 loss: 3.7090 (3.4766) grad_norm: 1.1841 (1.2581) time: 0.6374 [2021-03-26 21:50:52 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 980/1251] eta: 0:02:51 lr: 0.000735 loss: 3.5594 (3.4768) grad_norm: 1.3164 (1.2586) time: 0.6268 [2021-03-26 21:50:58 swin_base_patch4_window7_224] INFO: Epoch: [103] [ 990/1251] eta: 0:02:45 lr: 0.000735 loss: 3.6155 (3.4801) grad_norm: 1.2936 (1.2588) time: 0.6219 [2021-03-26 21:51:05 swin_base_patch4_window7_224] INFO: Epoch: [103] [1000/1251] eta: 0:02:39 lr: 0.000735 loss: 3.6450 (3.4800) grad_norm: 1.2363 (1.2585) time: 0.6246 [2021-03-26 21:51:11 swin_base_patch4_window7_224] INFO: Epoch: [103] [1010/1251] eta: 0:02:32 lr: 0.000735 loss: 3.5675 (3.4806) grad_norm: 1.2234 (1.2590) time: 0.6302 [2021-03-26 21:51:17 swin_base_patch4_window7_224] INFO: Epoch: [103] [1020/1251] eta: 0:02:26 lr: 0.000735 loss: 3.5439 (3.4806) grad_norm: 1.2671 (1.2602) time: 0.6272 [2021-03-26 21:51:24 swin_base_patch4_window7_224] INFO: Epoch: [103] [1030/1251] eta: 0:02:20 lr: 0.000735 loss: 3.4350 (3.4791) grad_norm: 1.2545 (1.2598) time: 0.6260 [2021-03-26 21:51:30 swin_base_patch4_window7_224] INFO: Epoch: [103] [1040/1251] eta: 0:02:13 lr: 0.000735 loss: 3.6923 (3.4807) grad_norm: 1.1740 (1.2596) time: 0.6333 [2021-03-26 21:51:36 swin_base_patch4_window7_224] INFO: Epoch: [103] [1050/1251] eta: 0:02:07 lr: 0.000735 loss: 3.6288 (3.4805) grad_norm: 1.2566 (1.2600) time: 0.6330 [2021-03-26 21:51:42 swin_base_patch4_window7_224] INFO: Epoch: [103] [1060/1251] eta: 0:02:01 lr: 0.000735 loss: 3.3851 (3.4796) grad_norm: 1.3087 (1.2608) time: 0.6269 [2021-03-26 21:51:49 swin_base_patch4_window7_224] INFO: Epoch: [103] [1070/1251] eta: 0:01:54 lr: 0.000735 loss: 3.2693 (3.4781) grad_norm: 1.3148 (1.2612) time: 0.6255 [2021-03-26 21:51:55 swin_base_patch4_window7_224] INFO: Epoch: [103] [1080/1251] eta: 0:01:48 lr: 0.000735 loss: 3.2693 (3.4774) grad_norm: 1.2430 (1.2609) time: 0.6246 [2021-03-26 21:52:01 swin_base_patch4_window7_224] INFO: Epoch: [103] [1090/1251] eta: 0:01:42 lr: 0.000735 loss: 3.3915 (3.4786) grad_norm: 1.1706 (1.2614) time: 0.6267 [2021-03-26 21:52:08 swin_base_patch4_window7_224] INFO: Epoch: [103] [1100/1251] eta: 0:01:35 lr: 0.000735 loss: 3.5212 (3.4793) grad_norm: 1.1835 (1.2614) time: 0.6300 [2021-03-26 21:52:14 swin_base_patch4_window7_224] INFO: Epoch: [103] [1110/1251] eta: 0:01:29 lr: 0.000735 loss: 3.5573 (3.4803) grad_norm: 1.2506 (1.2620) time: 0.6270 [2021-03-26 21:52:20 swin_base_patch4_window7_224] INFO: Epoch: [103] [1120/1251] eta: 0:01:23 lr: 0.000735 loss: 3.5573 (3.4809) grad_norm: 1.2591 (1.2623) time: 0.6258 [2021-03-26 21:52:26 swin_base_patch4_window7_224] INFO: Epoch: [103] [1130/1251] eta: 0:01:16 lr: 0.000735 loss: 3.6299 (3.4824) grad_norm: 1.2668 (1.2629) time: 0.6241 [2021-03-26 21:52:33 swin_base_patch4_window7_224] INFO: Epoch: [103] [1140/1251] eta: 0:01:10 lr: 0.000735 loss: 3.5230 (3.4819) grad_norm: 1.2525 (1.2630) time: 0.6274 [2021-03-26 21:52:39 swin_base_patch4_window7_224] INFO: Epoch: [103] [1150/1251] eta: 0:01:03 lr: 0.000735 loss: 3.4586 (3.4829) grad_norm: 1.2010 (1.2641) time: 0.6309 [2021-03-26 21:52:45 swin_base_patch4_window7_224] INFO: Epoch: [103] [1160/1251] eta: 0:00:57 lr: 0.000735 loss: 3.6964 (3.4846) grad_norm: 1.2667 (1.2645) time: 0.6296 [2021-03-26 21:52:51 swin_base_patch4_window7_224] INFO: Epoch: [103] [1170/1251] eta: 0:00:51 lr: 0.000735 loss: 3.6410 (3.4861) grad_norm: 1.1600 (1.2639) time: 0.6282 [2021-03-26 21:52:58 swin_base_patch4_window7_224] INFO: Epoch: [103] [1180/1251] eta: 0:00:44 lr: 0.000735 loss: 3.5515 (3.4841) grad_norm: 1.1565 (1.2634) time: 0.6226 [2021-03-26 21:53:04 swin_base_patch4_window7_224] INFO: Epoch: [103] [1190/1251] eta: 0:00:38 lr: 0.000735 loss: 3.4966 (3.4830) grad_norm: 1.1778 (1.2633) time: 0.6251 [2021-03-26 21:53:10 swin_base_patch4_window7_224] INFO: Epoch: [103] [1200/1251] eta: 0:00:32 lr: 0.000735 loss: 3.5421 (3.4829) grad_norm: 1.2211 (1.2632) time: 0.6275 [2021-03-26 21:53:16 swin_base_patch4_window7_224] INFO: Epoch: [103] [1210/1251] eta: 0:00:25 lr: 0.000734 loss: 3.5699 (3.4836) grad_norm: 1.2224 (1.2634) time: 0.6224 [2021-03-26 21:53:23 swin_base_patch4_window7_224] INFO: Epoch: [103] [1220/1251] eta: 0:00:19 lr: 0.000734 loss: 3.5446 (3.4829) grad_norm: 1.2334 (1.2632) time: 0.6264 [2021-03-26 21:53:29 swin_base_patch4_window7_224] INFO: Epoch: [103] [1230/1251] eta: 0:00:13 lr: 0.000734 loss: 3.6153 (3.4836) grad_norm: 1.2701 (1.2633) time: 0.6303 [2021-03-26 21:53:35 swin_base_patch4_window7_224] INFO: Epoch: [103] [1240/1251] eta: 0:00:06 lr: 0.000734 loss: 3.7126 (3.4843) grad_norm: 1.2631 (1.2629) time: 0.6246 [2021-03-26 21:53:42 swin_base_patch4_window7_224] INFO: Epoch: [103] [1250/1251] eta: 0:00:00 lr: 0.000734 loss: 3.6301 (3.4833) grad_norm: 1.1650 (1.2622) time: 0.6249 [2021-03-26 21:53:50 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:59 loss: 0.6181 (0.6181) acc1: 85.9375 (85.9375) acc5: 95.3125 (95.3125) [2021-03-26 21:53:52 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0331 (0.9800) acc1: 75.0000 (76.5625) acc5: 93.7500 (93.7500) [2021-03-26 21:53:54 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0331 (1.0113) acc1: 75.0000 (75.8185) acc5: 93.7500 (93.8244) [2021-03-26 21:53:56 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9769 (0.9810) acc1: 76.5625 (76.7137) acc5: 93.7500 (93.6996) [2021-03-26 21:53:59 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0223 (0.9879) acc1: 76.5625 (76.4101) acc5: 93.7500 (93.7500) [2021-03-26 21:54:00 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0295 (0.9965) acc1: 75.0000 (75.8720) acc5: 93.7500 (93.8240) [2021-03-26 21:54:08 swin_base_patch4_window7_224] INFO: * Acc@1 76.760 Acc@5 93.786 loss 0.971 [2021-03-26 21:54:08 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.8% [2021-03-26 21:54:08 swin_base_patch4_window7_224] INFO: Max accuracy: 76.92% [2021-03-26 21:54:13 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 0/1251] eta: 1:31:58 lr: 0.000734 loss: 3.3308 (3.3308) grad_norm: 1.3370 (1.3370) time: 4.4112 [2021-03-26 21:54:19 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 10/1251] eta: 0:20:15 lr: 0.000734 loss: 3.3308 (3.4274) grad_norm: 1.2371 (1.2437) time: 0.9797 [2021-03-26 21:54:26 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 20/1251] eta: 0:16:47 lr: 0.000734 loss: 3.2211 (3.3374) grad_norm: 1.1898 (1.2327) time: 0.6386 [2021-03-26 21:54:32 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 30/1251] eta: 0:15:32 lr: 0.000734 loss: 3.2864 (3.3740) grad_norm: 1.1824 (1.2354) time: 0.6450 [2021-03-26 21:54:38 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 40/1251] eta: 0:14:46 lr: 0.000734 loss: 3.4881 (3.3845) grad_norm: 1.2285 (1.2691) time: 0.6407 [2021-03-26 21:54:45 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 50/1251] eta: 0:14:16 lr: 0.000734 loss: 3.3695 (3.3512) grad_norm: 1.2770 (1.2655) time: 0.6356 [2021-03-26 21:54:51 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 60/1251] eta: 0:13:52 lr: 0.000734 loss: 3.5251 (3.4049) grad_norm: 1.2278 (1.2644) time: 0.6312 [2021-03-26 21:54:57 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 70/1251] eta: 0:13:35 lr: 0.000734 loss: 3.4733 (3.3874) grad_norm: 1.2278 (1.2657) time: 0.6305 [2021-03-26 21:55:04 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 80/1251] eta: 0:13:18 lr: 0.000734 loss: 3.4659 (3.4059) grad_norm: 1.2784 (1.2672) time: 0.6318 [2021-03-26 21:55:10 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 90/1251] eta: 0:13:05 lr: 0.000734 loss: 3.6193 (3.4106) grad_norm: 1.2348 (1.2674) time: 0.6276 [2021-03-26 21:55:16 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 100/1251] eta: 0:12:53 lr: 0.000734 loss: 3.7231 (3.4476) grad_norm: 1.2113 (1.2687) time: 0.6302 [2021-03-26 21:55:23 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 110/1251] eta: 0:12:41 lr: 0.000734 loss: 3.7460 (3.4435) grad_norm: 1.2225 (1.2672) time: 0.6288 [2021-03-26 21:55:29 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 120/1251] eta: 0:12:34 lr: 0.000734 loss: 3.3783 (3.4496) grad_norm: 1.2541 (1.2701) time: 0.6404 [2021-03-26 21:55:35 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 130/1251] eta: 0:12:25 lr: 0.000734 loss: 3.6396 (3.4679) grad_norm: 1.2541 (1.2721) time: 0.6484 [2021-03-26 21:55:42 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 140/1251] eta: 0:12:16 lr: 0.000734 loss: 3.6525 (3.4564) grad_norm: 1.1860 (1.2640) time: 0.6376 [2021-03-26 21:55:48 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 150/1251] eta: 0:12:06 lr: 0.000734 loss: 3.4093 (3.4549) grad_norm: 1.1966 (1.2648) time: 0.6298 [2021-03-26 21:55:54 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 160/1251] eta: 0:11:57 lr: 0.000734 loss: 3.6122 (3.4745) grad_norm: 1.2359 (1.2632) time: 0.6263 [2021-03-26 21:56:01 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 170/1251] eta: 0:11:50 lr: 0.000734 loss: 3.6821 (3.4871) grad_norm: 1.2359 (1.2664) time: 0.6315 [2021-03-26 21:56:07 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 180/1251] eta: 0:11:42 lr: 0.000734 loss: 3.6226 (3.4829) grad_norm: 1.3180 (1.2670) time: 0.6386 [2021-03-26 21:56:13 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 190/1251] eta: 0:11:34 lr: 0.000734 loss: 3.3495 (3.4823) grad_norm: 1.2254 (1.2684) time: 0.6384 [2021-03-26 21:56:20 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 200/1251] eta: 0:11:27 lr: 0.000734 loss: 3.6133 (3.4797) grad_norm: 1.2317 (1.2734) time: 0.6349 [2021-03-26 21:56:26 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 210/1251] eta: 0:11:20 lr: 0.000734 loss: 3.6133 (3.4788) grad_norm: 1.2147 (1.2715) time: 0.6380 [2021-03-26 21:56:33 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 220/1251] eta: 0:11:13 lr: 0.000734 loss: 3.5762 (3.4773) grad_norm: 1.2543 (1.2749) time: 0.6437 [2021-03-26 21:56:39 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 230/1251] eta: 0:11:05 lr: 0.000733 loss: 3.4720 (3.4819) grad_norm: 1.2675 (1.2742) time: 0.6354 [2021-03-26 21:56:45 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 240/1251] eta: 0:10:57 lr: 0.000733 loss: 3.4720 (3.4707) grad_norm: 1.2729 (1.2756) time: 0.6271 [2021-03-26 21:56:52 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 250/1251] eta: 0:10:50 lr: 0.000733 loss: 3.5581 (3.4723) grad_norm: 1.2147 (1.2727) time: 0.6266 [2021-03-26 21:56:58 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 260/1251] eta: 0:10:42 lr: 0.000733 loss: 3.5581 (3.4643) grad_norm: 1.1842 (1.2699) time: 0.6255 [2021-03-26 21:57:04 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 270/1251] eta: 0:10:35 lr: 0.000733 loss: 3.5711 (3.4699) grad_norm: 1.1580 (1.2653) time: 0.6264 [2021-03-26 21:57:10 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 280/1251] eta: 0:10:28 lr: 0.000733 loss: 3.7353 (3.4723) grad_norm: 1.1580 (1.2690) time: 0.6322 [2021-03-26 21:57:17 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 290/1251] eta: 0:10:22 lr: 0.000733 loss: 3.6580 (3.4766) grad_norm: 1.2798 (1.2692) time: 0.6378 [2021-03-26 21:57:23 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 300/1251] eta: 0:10:15 lr: 0.000733 loss: 3.7299 (3.4816) grad_norm: 1.2734 (1.2707) time: 0.6408 [2021-03-26 21:57:29 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 310/1251] eta: 0:10:08 lr: 0.000733 loss: 3.6204 (3.4829) grad_norm: 1.2616 (1.2698) time: 0.6348 [2021-03-26 21:57:36 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 320/1251] eta: 0:10:01 lr: 0.000733 loss: 3.3109 (3.4731) grad_norm: 1.1459 (1.2664) time: 0.6371 [2021-03-26 21:57:42 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 330/1251] eta: 0:09:55 lr: 0.000733 loss: 3.2655 (3.4708) grad_norm: 1.1459 (1.2634) time: 0.6418 [2021-03-26 21:57:49 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 340/1251] eta: 0:09:48 lr: 0.000733 loss: 3.5065 (3.4710) grad_norm: 1.1951 (1.2653) time: 0.6313 [2021-03-26 21:57:55 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 350/1251] eta: 0:09:41 lr: 0.000733 loss: 3.4252 (3.4619) grad_norm: 1.2576 (1.2664) time: 0.6316 [2021-03-26 21:58:01 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 360/1251] eta: 0:09:34 lr: 0.000733 loss: 3.2647 (3.4589) grad_norm: 1.2576 (1.2665) time: 0.6318 [2021-03-26 21:58:08 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 370/1251] eta: 0:09:27 lr: 0.000733 loss: 3.7270 (3.4688) grad_norm: 1.1397 (1.2666) time: 0.6269 [2021-03-26 21:58:14 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 380/1251] eta: 0:09:21 lr: 0.000733 loss: 3.8845 (3.4767) grad_norm: 1.2057 (1.2680) time: 0.6294 [2021-03-26 21:58:20 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 390/1251] eta: 0:09:14 lr: 0.000733 loss: 3.6482 (3.4765) grad_norm: 1.2973 (1.2676) time: 0.6328 [2021-03-26 21:58:27 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 400/1251] eta: 0:09:07 lr: 0.000733 loss: 3.4913 (3.4728) grad_norm: 1.2251 (1.2674) time: 0.6353 [2021-03-26 21:58:33 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 410/1251] eta: 0:09:01 lr: 0.000733 loss: 3.3570 (3.4671) grad_norm: 1.2506 (1.2667) time: 0.6357 [2021-03-26 21:58:39 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 420/1251] eta: 0:08:54 lr: 0.000733 loss: 3.3570 (3.4631) grad_norm: 1.2444 (1.2661) time: 0.6320 [2021-03-26 21:58:46 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 430/1251] eta: 0:08:47 lr: 0.000733 loss: 3.4080 (3.4624) grad_norm: 1.2444 (1.2683) time: 0.6324 [2021-03-26 21:58:52 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 440/1251] eta: 0:08:41 lr: 0.000733 loss: 3.4347 (3.4559) grad_norm: 1.2688 (1.2690) time: 0.6392 [2021-03-26 21:58:58 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 450/1251] eta: 0:08:34 lr: 0.000733 loss: 3.3879 (3.4542) grad_norm: 1.1718 (1.2662) time: 0.6345 [2021-03-26 21:59:04 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 460/1251] eta: 0:08:27 lr: 0.000733 loss: 3.3879 (3.4510) grad_norm: 1.1741 (1.2673) time: 0.6249 [2021-03-26 21:59:11 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 470/1251] eta: 0:08:21 lr: 0.000733 loss: 3.3878 (3.4465) grad_norm: 1.2520 (1.2678) time: 0.6271 [2021-03-26 21:59:17 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 480/1251] eta: 0:08:14 lr: 0.000733 loss: 3.5599 (3.4511) grad_norm: 1.3613 (1.2691) time: 0.6277 [2021-03-26 21:59:23 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 490/1251] eta: 0:08:08 lr: 0.000733 loss: 3.7273 (3.4545) grad_norm: 1.3009 (1.2707) time: 0.6320 [2021-03-26 21:59:30 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 500/1251] eta: 0:08:01 lr: 0.000732 loss: 3.7482 (3.4591) grad_norm: 1.2106 (1.2705) time: 0.6344 [2021-03-26 21:59:36 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 510/1251] eta: 0:07:55 lr: 0.000732 loss: 3.7482 (3.4635) grad_norm: 1.2042 (1.2702) time: 0.6369 [2021-03-26 21:59:42 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 520/1251] eta: 0:07:48 lr: 0.000732 loss: 3.5162 (3.4659) grad_norm: 1.1958 (inf) time: 0.6325 [2021-03-26 21:59:49 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 530/1251] eta: 0:07:41 lr: 0.000732 loss: 3.5241 (3.4686) grad_norm: 1.1875 (inf) time: 0.6262 [2021-03-26 21:59:55 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 540/1251] eta: 0:07:35 lr: 0.000732 loss: 3.5241 (3.4676) grad_norm: 1.1673 (inf) time: 0.6322 [2021-03-26 22:00:02 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 550/1251] eta: 0:07:29 lr: 0.000732 loss: 3.6280 (3.4723) grad_norm: 1.2036 (inf) time: 0.6472 [2021-03-26 22:00:08 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 560/1251] eta: 0:07:22 lr: 0.000732 loss: 3.6945 (3.4698) grad_norm: 1.3038 (inf) time: 0.6419 [2021-03-26 22:00:14 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 570/1251] eta: 0:07:16 lr: 0.000732 loss: 3.5359 (3.4673) grad_norm: 1.2983 (inf) time: 0.6245 [2021-03-26 22:00:20 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 580/1251] eta: 0:07:09 lr: 0.000732 loss: 3.5320 (3.4643) grad_norm: 1.2778 (inf) time: 0.6241 [2021-03-26 22:00:27 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 590/1251] eta: 0:07:03 lr: 0.000732 loss: 3.1033 (3.4607) grad_norm: 1.2559 (inf) time: 0.6284 [2021-03-26 22:00:33 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 600/1251] eta: 0:06:56 lr: 0.000732 loss: 3.2527 (3.4598) grad_norm: 1.2154 (inf) time: 0.6300 [2021-03-26 22:00:39 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 610/1251] eta: 0:06:50 lr: 0.000732 loss: 3.7706 (3.4664) grad_norm: 1.2463 (inf) time: 0.6336 [2021-03-26 22:00:46 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 620/1251] eta: 0:06:43 lr: 0.000732 loss: 3.7609 (3.4683) grad_norm: 1.2995 (inf) time: 0.6348 [2021-03-26 22:00:52 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 630/1251] eta: 0:06:37 lr: 0.000732 loss: 3.6010 (3.4693) grad_norm: 1.1042 (inf) time: 0.6302 [2021-03-26 22:00:58 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 640/1251] eta: 0:06:30 lr: 0.000732 loss: 3.4027 (3.4651) grad_norm: 1.1237 (inf) time: 0.6291 [2021-03-26 22:01:05 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 650/1251] eta: 0:06:24 lr: 0.000732 loss: 3.1163 (3.4608) grad_norm: 1.2607 (inf) time: 0.6285 [2021-03-26 22:01:11 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 660/1251] eta: 0:06:17 lr: 0.000732 loss: 3.1163 (3.4589) grad_norm: 1.2628 (inf) time: 0.6272 [2021-03-26 22:01:17 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 670/1251] eta: 0:06:11 lr: 0.000732 loss: 3.4013 (3.4579) grad_norm: 1.1588 (inf) time: 0.6255 [2021-03-26 22:01:23 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 680/1251] eta: 0:06:04 lr: 0.000732 loss: 3.5247 (3.4620) grad_norm: 1.1375 (inf) time: 0.6296 [2021-03-26 22:01:30 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 690/1251] eta: 0:05:58 lr: 0.000732 loss: 3.6247 (3.4626) grad_norm: 1.2026 (inf) time: 0.6385 [2021-03-26 22:01:36 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 700/1251] eta: 0:05:51 lr: 0.000732 loss: 3.5609 (3.4595) grad_norm: 1.3137 (inf) time: 0.6395 [2021-03-26 22:01:43 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 710/1251] eta: 0:05:45 lr: 0.000732 loss: 3.4038 (3.4584) grad_norm: 1.3502 (inf) time: 0.6401 [2021-03-26 22:01:49 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 720/1251] eta: 0:05:39 lr: 0.000732 loss: 3.4122 (3.4572) grad_norm: 1.2388 (inf) time: 0.6371 [2021-03-26 22:01:55 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 730/1251] eta: 0:05:32 lr: 0.000732 loss: 3.5430 (3.4612) grad_norm: 1.2788 (inf) time: 0.6294 [2021-03-26 22:02:02 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 740/1251] eta: 0:05:26 lr: 0.000732 loss: 3.7386 (3.4613) grad_norm: 1.3507 (inf) time: 0.6343 [2021-03-26 22:02:08 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 750/1251] eta: 0:05:19 lr: 0.000732 loss: 3.7150 (3.4648) grad_norm: 1.2469 (inf) time: 0.6375 [2021-03-26 22:02:14 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 760/1251] eta: 0:05:13 lr: 0.000732 loss: 3.5864 (3.4638) grad_norm: 1.2134 (inf) time: 0.6319 [2021-03-26 22:02:21 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 770/1251] eta: 0:05:06 lr: 0.000731 loss: 3.4299 (3.4637) grad_norm: 1.3198 (inf) time: 0.6291 [2021-03-26 22:02:27 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 780/1251] eta: 0:05:00 lr: 0.000731 loss: 3.6474 (3.4653) grad_norm: 1.2764 (inf) time: 0.6301 [2021-03-26 22:02:33 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 790/1251] eta: 0:04:54 lr: 0.000731 loss: 3.5557 (3.4658) grad_norm: 1.2599 (inf) time: 0.6254 [2021-03-26 22:02:39 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 800/1251] eta: 0:04:47 lr: 0.000731 loss: 3.5700 (3.4691) grad_norm: 1.2000 (inf) time: 0.6264 [2021-03-26 22:02:46 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 810/1251] eta: 0:04:41 lr: 0.000731 loss: 3.7246 (3.4688) grad_norm: 1.2348 (inf) time: 0.6271 [2021-03-26 22:02:52 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 820/1251] eta: 0:04:34 lr: 0.000731 loss: 3.3982 (3.4679) grad_norm: 1.2462 (inf) time: 0.6345 [2021-03-26 22:02:58 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 830/1251] eta: 0:04:28 lr: 0.000731 loss: 3.5020 (3.4680) grad_norm: 1.2144 (inf) time: 0.6395 [2021-03-26 22:03:05 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 840/1251] eta: 0:04:22 lr: 0.000731 loss: 3.5020 (3.4684) grad_norm: 1.2425 (inf) time: 0.6285 [2021-03-26 22:03:11 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 850/1251] eta: 0:04:15 lr: 0.000731 loss: 3.5988 (3.4707) grad_norm: 1.2222 (inf) time: 0.6237 [2021-03-26 22:03:17 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 860/1251] eta: 0:04:09 lr: 0.000731 loss: 3.3057 (3.4688) grad_norm: 1.2222 (inf) time: 0.6253 [2021-03-26 22:03:24 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 870/1251] eta: 0:04:02 lr: 0.000731 loss: 3.3057 (3.4685) grad_norm: 1.2280 (inf) time: 0.6321 [2021-03-26 22:03:30 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 880/1251] eta: 0:03:56 lr: 0.000731 loss: 3.5651 (3.4701) grad_norm: 1.1707 (nan) time: 0.6299 [2021-03-26 22:03:36 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 890/1251] eta: 0:03:49 lr: 0.000731 loss: 3.5651 (3.4698) grad_norm: 1.1707 (nan) time: 0.6208 [2021-03-26 22:03:42 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 900/1251] eta: 0:03:43 lr: 0.000731 loss: 3.6826 (3.4698) grad_norm: 1.1529 (nan) time: 0.6307 [2021-03-26 22:03:49 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 910/1251] eta: 0:03:37 lr: 0.000731 loss: 3.8283 (3.4714) grad_norm: 1.2085 (nan) time: 0.6317 [2021-03-26 22:03:55 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 920/1251] eta: 0:03:30 lr: 0.000731 loss: 3.5704 (3.4704) grad_norm: 1.2134 (nan) time: 0.6280 [2021-03-26 22:04:01 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 930/1251] eta: 0:03:24 lr: 0.000731 loss: 3.2762 (3.4677) grad_norm: 1.1780 (nan) time: 0.6412 [2021-03-26 22:04:08 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 940/1251] eta: 0:03:18 lr: 0.000731 loss: 3.2762 (3.4674) grad_norm: 1.1954 (nan) time: 0.6409 [2021-03-26 22:04:14 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 950/1251] eta: 0:03:11 lr: 0.000731 loss: 3.6592 (3.4674) grad_norm: 1.2465 (nan) time: 0.6300 [2021-03-26 22:04:20 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 960/1251] eta: 0:03:05 lr: 0.000731 loss: 3.6928 (3.4673) grad_norm: 1.2465 (nan) time: 0.6292 [2021-03-26 22:04:27 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 970/1251] eta: 0:02:58 lr: 0.000731 loss: 3.4764 (3.4648) grad_norm: 1.2653 (nan) time: 0.6329 [2021-03-26 22:04:33 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 980/1251] eta: 0:02:52 lr: 0.000731 loss: 3.5886 (3.4664) grad_norm: 1.2653 (nan) time: 0.6294 [2021-03-26 22:04:39 swin_base_patch4_window7_224] INFO: Epoch: [104] [ 990/1251] eta: 0:02:46 lr: 0.000731 loss: 3.5886 (3.4667) grad_norm: 1.1990 (nan) time: 0.6300 [2021-03-26 22:04:46 swin_base_patch4_window7_224] INFO: Epoch: [104] [1000/1251] eta: 0:02:39 lr: 0.000731 loss: 3.4730 (3.4667) grad_norm: 1.2151 (nan) time: 0.6303 [2021-03-26 22:04:52 swin_base_patch4_window7_224] INFO: Epoch: [104] [1010/1251] eta: 0:02:33 lr: 0.000731 loss: 3.4859 (3.4673) grad_norm: 1.2448 (nan) time: 0.6257 [2021-03-26 22:04:58 swin_base_patch4_window7_224] INFO: Epoch: [104] [1020/1251] eta: 0:02:26 lr: 0.000731 loss: 3.5497 (3.4659) grad_norm: 1.2345 (nan) time: 0.6264 [2021-03-26 22:05:04 swin_base_patch4_window7_224] INFO: Epoch: [104] [1030/1251] eta: 0:02:20 lr: 0.000731 loss: 3.7362 (3.4680) grad_norm: 1.2020 (nan) time: 0.6319 [2021-03-26 22:05:11 swin_base_patch4_window7_224] INFO: Epoch: [104] [1040/1251] eta: 0:02:14 lr: 0.000731 loss: 3.7502 (3.4716) grad_norm: 1.2020 (nan) time: 0.6319 [2021-03-26 22:05:17 swin_base_patch4_window7_224] INFO: Epoch: [104] [1050/1251] eta: 0:02:07 lr: 0.000730 loss: 3.7025 (3.4712) grad_norm: 1.1936 (nan) time: 0.6281 [2021-03-26 22:05:23 swin_base_patch4_window7_224] INFO: Epoch: [104] [1060/1251] eta: 0:02:01 lr: 0.000730 loss: 3.4603 (3.4718) grad_norm: 1.1936 (nan) time: 0.6358 [2021-03-26 22:05:30 swin_base_patch4_window7_224] INFO: Epoch: [104] [1070/1251] eta: 0:01:55 lr: 0.000730 loss: 3.4522 (3.4726) grad_norm: 1.1946 (nan) time: 0.6349 [2021-03-26 22:05:36 swin_base_patch4_window7_224] INFO: Epoch: [104] [1080/1251] eta: 0:01:48 lr: 0.000730 loss: 3.4490 (3.4712) grad_norm: 1.2053 (nan) time: 0.6360 [2021-03-26 22:05:43 swin_base_patch4_window7_224] INFO: Epoch: [104] [1090/1251] eta: 0:01:42 lr: 0.000730 loss: 3.4799 (3.4707) grad_norm: 1.2053 (nan) time: 0.6440 [2021-03-26 22:05:49 swin_base_patch4_window7_224] INFO: Epoch: [104] [1100/1251] eta: 0:01:36 lr: 0.000730 loss: 3.5409 (3.4689) grad_norm: 1.1740 (nan) time: 0.6391 [2021-03-26 22:05:55 swin_base_patch4_window7_224] INFO: Epoch: [104] [1110/1251] eta: 0:01:29 lr: 0.000730 loss: 3.4753 (3.4663) grad_norm: 1.2082 (nan) time: 0.6354 [2021-03-26 22:06:02 swin_base_patch4_window7_224] INFO: Epoch: [104] [1120/1251] eta: 0:01:23 lr: 0.000730 loss: 3.3688 (3.4669) grad_norm: 1.3324 (nan) time: 0.6319 [2021-03-26 22:06:08 swin_base_patch4_window7_224] INFO: Epoch: [104] [1130/1251] eta: 0:01:16 lr: 0.000730 loss: 3.3688 (3.4674) grad_norm: 1.3324 (nan) time: 0.6259 [2021-03-26 22:06:14 swin_base_patch4_window7_224] INFO: Epoch: [104] [1140/1251] eta: 0:01:10 lr: 0.000730 loss: 3.7207 (3.4683) grad_norm: 1.2974 (nan) time: 0.6248 [2021-03-26 22:06:20 swin_base_patch4_window7_224] INFO: Epoch: [104] [1150/1251] eta: 0:01:04 lr: 0.000730 loss: 3.7612 (3.4710) grad_norm: 1.2123 (nan) time: 0.6317 [2021-03-26 22:06:27 swin_base_patch4_window7_224] INFO: Epoch: [104] [1160/1251] eta: 0:00:57 lr: 0.000730 loss: 3.5908 (3.4697) grad_norm: 1.2540 (nan) time: 0.6318 [2021-03-26 22:06:33 swin_base_patch4_window7_224] INFO: Epoch: [104] [1170/1251] eta: 0:00:51 lr: 0.000730 loss: 3.4085 (3.4708) grad_norm: 1.2943 (nan) time: 0.6231 [2021-03-26 22:06:39 swin_base_patch4_window7_224] INFO: Epoch: [104] [1180/1251] eta: 0:00:45 lr: 0.000730 loss: 3.4241 (3.4688) grad_norm: 1.2769 (nan) time: 0.6245 [2021-03-26 22:06:46 swin_base_patch4_window7_224] INFO: Epoch: [104] [1190/1251] eta: 0:00:38 lr: 0.000730 loss: 3.5397 (3.4705) grad_norm: 1.3164 (nan) time: 0.6329 [2021-03-26 22:06:52 swin_base_patch4_window7_224] INFO: Epoch: [104] [1200/1251] eta: 0:00:32 lr: 0.000730 loss: 3.6348 (3.4705) grad_norm: 1.2863 (nan) time: 0.6322 [2021-03-26 22:06:58 swin_base_patch4_window7_224] INFO: Epoch: [104] [1210/1251] eta: 0:00:26 lr: 0.000730 loss: 3.7043 (3.4727) grad_norm: 1.2379 (nan) time: 0.6273 [2021-03-26 22:07:04 swin_base_patch4_window7_224] INFO: Epoch: [104] [1220/1251] eta: 0:00:19 lr: 0.000730 loss: 3.7626 (3.4734) grad_norm: 1.2258 (nan) time: 0.6302 [2021-03-26 22:07:11 swin_base_patch4_window7_224] INFO: Epoch: [104] [1230/1251] eta: 0:00:13 lr: 0.000730 loss: 3.4320 (3.4719) grad_norm: 1.2026 (nan) time: 0.6317 [2021-03-26 22:07:17 swin_base_patch4_window7_224] INFO: Epoch: [104] [1240/1251] eta: 0:00:06 lr: 0.000730 loss: 3.4123 (3.4716) grad_norm: 1.2842 (nan) time: 0.6250 [2021-03-26 22:07:23 swin_base_patch4_window7_224] INFO: Epoch: [104] [1250/1251] eta: 0:00:00 lr: 0.000730 loss: 3.4123 (3.4702) grad_norm: 1.2880 (nan) time: 0.6214 [2021-03-26 22:07:29 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:17 loss: 0.9308 (0.9308) acc1: 71.8750 (71.8750) acc5: 95.3125 (95.3125) [2021-03-26 22:07:31 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.0913 (1.0456) acc1: 71.8750 (73.8636) acc5: 93.7500 (93.7500) [2021-03-26 22:07:33 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0436 (1.0197) acc1: 73.4375 (75.5208) acc5: 93.7500 (93.6756) [2021-03-26 22:07:35 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9953 (1.0043) acc1: 78.1250 (76.0585) acc5: 93.7500 (94.0020) [2021-03-26 22:07:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9909 (0.9994) acc1: 75.0000 (75.9146) acc5: 95.3125 (94.1692) [2021-03-26 22:07:38 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9909 (1.0098) acc1: 75.0000 (76.0000) acc5: 95.3125 (94.0160) [2021-03-26 22:07:45 swin_base_patch4_window7_224] INFO: * Acc@1 76.890 Acc@5 93.824 loss 0.996 [2021-03-26 22:07:45 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.9% [2021-03-26 22:07:45 swin_base_patch4_window7_224] INFO: Max accuracy: 76.92% [2021-03-26 22:07:49 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 0/1251] eta: 1:28:35 lr: 0.000730 loss: 3.7265 (3.7265) grad_norm: 1.3559 (1.3559) time: 4.2493 [2021-03-26 22:07:55 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 10/1251] eta: 0:20:02 lr: 0.000730 loss: 3.8481 (3.6741) grad_norm: 1.3559 (1.3271) time: 0.9687 [2021-03-26 22:08:02 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 20/1251] eta: 0:16:36 lr: 0.000730 loss: 3.7444 (3.6514) grad_norm: 1.3188 (1.3259) time: 0.6377 [2021-03-26 22:08:08 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 30/1251] eta: 0:15:22 lr: 0.000730 loss: 3.4325 (3.5621) grad_norm: 1.2528 (1.3096) time: 0.6378 [2021-03-26 22:08:14 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 40/1251] eta: 0:14:38 lr: 0.000730 loss: 3.4198 (3.5754) grad_norm: 1.2491 (1.2983) time: 0.6376 [2021-03-26 22:08:21 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 50/1251] eta: 0:14:10 lr: 0.000730 loss: 3.3491 (3.5136) grad_norm: 1.2243 (1.2806) time: 0.6346 [2021-03-26 22:08:27 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 60/1251] eta: 0:13:47 lr: 0.000730 loss: 3.1665 (3.4758) grad_norm: 1.1996 (1.2715) time: 0.6309 [2021-03-26 22:08:33 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 70/1251] eta: 0:13:29 lr: 0.000729 loss: 3.3337 (3.4832) grad_norm: 1.2109 (1.2675) time: 0.6274 [2021-03-26 22:08:39 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 80/1251] eta: 0:13:13 lr: 0.000729 loss: 3.3457 (3.4354) grad_norm: 1.2200 (1.2697) time: 0.6260 [2021-03-26 22:08:46 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 90/1251] eta: 0:13:00 lr: 0.000729 loss: 3.2951 (3.3950) grad_norm: 1.1204 (1.2536) time: 0.6251 [2021-03-26 22:08:52 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 100/1251] eta: 0:12:49 lr: 0.000729 loss: 3.5191 (3.3989) grad_norm: 1.1248 (1.2525) time: 0.6327 [2021-03-26 22:08:58 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 110/1251] eta: 0:12:38 lr: 0.000729 loss: 3.3317 (3.3931) grad_norm: 1.2339 (1.2504) time: 0.6305 [2021-03-26 22:09:05 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 120/1251] eta: 0:12:29 lr: 0.000729 loss: 3.3282 (3.3908) grad_norm: 1.2344 (1.2518) time: 0.6313 [2021-03-26 22:09:11 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 130/1251] eta: 0:12:20 lr: 0.000729 loss: 3.5539 (3.4073) grad_norm: 1.2342 (1.2542) time: 0.6402 [2021-03-26 22:09:18 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 140/1251] eta: 0:12:12 lr: 0.000729 loss: 3.6729 (3.4123) grad_norm: 1.2342 (1.2545) time: 0.6382 [2021-03-26 22:09:24 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 150/1251] eta: 0:12:04 lr: 0.000729 loss: 3.6057 (3.4144) grad_norm: 1.2113 (1.2540) time: 0.6377 [2021-03-26 22:09:30 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 160/1251] eta: 0:11:55 lr: 0.000729 loss: 3.4824 (3.4080) grad_norm: 1.2113 (1.2617) time: 0.6316 [2021-03-26 22:09:36 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 170/1251] eta: 0:11:46 lr: 0.000729 loss: 3.4527 (3.4160) grad_norm: 1.2353 (1.2592) time: 0.6243 [2021-03-26 22:09:43 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 180/1251] eta: 0:11:39 lr: 0.000729 loss: 3.4369 (3.4147) grad_norm: 1.2234 (1.2586) time: 0.6284 [2021-03-26 22:09:49 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 190/1251] eta: 0:11:31 lr: 0.000729 loss: 3.2080 (3.4060) grad_norm: 1.2234 (1.2598) time: 0.6301 [2021-03-26 22:09:55 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 200/1251] eta: 0:11:23 lr: 0.000729 loss: 3.2080 (3.4018) grad_norm: 1.2389 (1.2616) time: 0.6284 [2021-03-26 22:10:02 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 210/1251] eta: 0:11:16 lr: 0.000729 loss: 3.6605 (3.4150) grad_norm: 1.2389 (1.2607) time: 0.6336 [2021-03-26 22:10:08 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 220/1251] eta: 0:11:08 lr: 0.000729 loss: 3.6128 (3.4153) grad_norm: 1.2084 (1.2606) time: 0.6319 [2021-03-26 22:10:14 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 230/1251] eta: 0:11:01 lr: 0.000729 loss: 3.4613 (3.4095) grad_norm: 1.3092 (1.2667) time: 0.6273 [2021-03-26 22:10:21 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 240/1251] eta: 0:10:54 lr: 0.000729 loss: 3.5131 (3.4189) grad_norm: 1.3024 (1.2637) time: 0.6286 [2021-03-26 22:10:27 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 250/1251] eta: 0:10:47 lr: 0.000729 loss: 3.5364 (3.4160) grad_norm: 1.2113 (1.2634) time: 0.6339 [2021-03-26 22:10:33 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 260/1251] eta: 0:10:40 lr: 0.000729 loss: 3.2798 (3.4087) grad_norm: 1.2290 (1.2631) time: 0.6323 [2021-03-26 22:10:39 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 270/1251] eta: 0:10:32 lr: 0.000729 loss: 3.4631 (3.4208) grad_norm: 1.2195 (1.2636) time: 0.6243 [2021-03-26 22:10:46 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 280/1251] eta: 0:10:25 lr: 0.000729 loss: 3.6717 (3.4209) grad_norm: 1.2488 (1.2669) time: 0.6257 [2021-03-26 22:10:52 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 290/1251] eta: 0:10:18 lr: 0.000729 loss: 3.4187 (3.4241) grad_norm: 1.3410 (1.2700) time: 0.6286 [2021-03-26 22:10:58 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 300/1251] eta: 0:10:11 lr: 0.000729 loss: 3.6208 (3.4315) grad_norm: 1.2332 (1.2681) time: 0.6291 [2021-03-26 22:11:05 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 310/1251] eta: 0:10:05 lr: 0.000729 loss: 3.6913 (3.4384) grad_norm: 1.2208 (1.2670) time: 0.6337 [2021-03-26 22:11:11 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 320/1251] eta: 0:09:58 lr: 0.000729 loss: 3.5695 (3.4381) grad_norm: 1.1737 (1.2646) time: 0.6291 [2021-03-26 22:11:17 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 330/1251] eta: 0:09:51 lr: 0.000729 loss: 3.5695 (3.4381) grad_norm: 1.1983 (1.2652) time: 0.6278 [2021-03-26 22:11:23 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 340/1251] eta: 0:09:44 lr: 0.000728 loss: 3.5500 (3.4378) grad_norm: 1.2931 (1.2689) time: 0.6304 [2021-03-26 22:11:30 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 350/1251] eta: 0:09:37 lr: 0.000728 loss: 3.5037 (3.4305) grad_norm: 1.3212 (1.2713) time: 0.6224 [2021-03-26 22:11:36 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 360/1251] eta: 0:09:31 lr: 0.000728 loss: 3.1490 (3.4278) grad_norm: 1.2266 (1.2686) time: 0.6269 [2021-03-26 22:11:42 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 370/1251] eta: 0:09:24 lr: 0.000728 loss: 3.2990 (3.4265) grad_norm: 1.1951 (1.2701) time: 0.6354 [2021-03-26 22:11:49 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 380/1251] eta: 0:09:17 lr: 0.000728 loss: 3.4924 (3.4277) grad_norm: 1.1845 (1.2669) time: 0.6290 [2021-03-26 22:11:55 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 390/1251] eta: 0:09:11 lr: 0.000728 loss: 3.6330 (3.4334) grad_norm: 1.2488 (1.2675) time: 0.6249 [2021-03-26 22:12:01 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 400/1251] eta: 0:09:04 lr: 0.000728 loss: 3.4330 (3.4276) grad_norm: 1.2425 (1.2660) time: 0.6339 [2021-03-26 22:12:07 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 410/1251] eta: 0:08:57 lr: 0.000728 loss: 3.5402 (3.4372) grad_norm: 1.2017 (1.2639) time: 0.6294 [2021-03-26 22:12:14 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 420/1251] eta: 0:08:51 lr: 0.000728 loss: 3.6231 (3.4370) grad_norm: 1.2160 (1.2624) time: 0.6222 [2021-03-26 22:12:20 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 430/1251] eta: 0:08:44 lr: 0.000728 loss: 3.7372 (3.4369) grad_norm: 1.2016 (1.2620) time: 0.6212 [2021-03-26 22:12:26 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 440/1251] eta: 0:08:37 lr: 0.000728 loss: 3.7623 (3.4431) grad_norm: 1.1665 (1.2604) time: 0.6223 [2021-03-26 22:12:33 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 450/1251] eta: 0:08:31 lr: 0.000728 loss: 3.7444 (3.4396) grad_norm: 1.1929 (1.2601) time: 0.6300 [2021-03-26 22:12:39 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 460/1251] eta: 0:08:24 lr: 0.000728 loss: 3.4498 (3.4374) grad_norm: 1.1929 (1.2596) time: 0.6283 [2021-03-26 22:12:45 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 470/1251] eta: 0:08:18 lr: 0.000728 loss: 3.4547 (3.4385) grad_norm: 1.1664 (1.2582) time: 0.6262 [2021-03-26 22:12:51 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 480/1251] eta: 0:08:11 lr: 0.000728 loss: 3.5968 (3.4424) grad_norm: 1.1827 (1.2578) time: 0.6289 [2021-03-26 22:12:58 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 490/1251] eta: 0:08:05 lr: 0.000728 loss: 3.7172 (3.4441) grad_norm: 1.2016 (1.2585) time: 0.6303 [2021-03-26 22:13:04 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 500/1251] eta: 0:07:58 lr: 0.000728 loss: 3.7478 (3.4461) grad_norm: 1.2509 (1.2593) time: 0.6345 [2021-03-26 22:13:10 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 510/1251] eta: 0:07:52 lr: 0.000728 loss: 3.3036 (3.4417) grad_norm: 1.1566 (1.2566) time: 0.6328 [2021-03-26 22:13:17 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 520/1251] eta: 0:07:45 lr: 0.000728 loss: 3.3807 (3.4454) grad_norm: 1.1368 (1.2553) time: 0.6313 [2021-03-26 22:13:23 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 530/1251] eta: 0:07:39 lr: 0.000728 loss: 3.5712 (3.4458) grad_norm: 1.1918 (1.2553) time: 0.6321 [2021-03-26 22:13:29 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 540/1251] eta: 0:07:32 lr: 0.000728 loss: 3.5394 (3.4435) grad_norm: 1.2127 (1.2566) time: 0.6309 [2021-03-26 22:13:36 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 550/1251] eta: 0:07:26 lr: 0.000728 loss: 3.3507 (3.4436) grad_norm: 1.2162 (1.2561) time: 0.6416 [2021-03-26 22:13:42 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 560/1251] eta: 0:07:20 lr: 0.000728 loss: 3.5507 (3.4426) grad_norm: 1.2363 (1.2595) time: 0.6422 [2021-03-26 22:13:48 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 570/1251] eta: 0:07:13 lr: 0.000728 loss: 3.5473 (3.4438) grad_norm: 1.2482 (1.2590) time: 0.6328 [2021-03-26 22:13:55 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 580/1251] eta: 0:07:07 lr: 0.000728 loss: 3.4970 (3.4445) grad_norm: 1.2444 (1.2587) time: 0.6310 [2021-03-26 22:14:01 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 590/1251] eta: 0:07:01 lr: 0.000728 loss: 3.4635 (3.4404) grad_norm: 1.2205 (1.2593) time: 0.6410 [2021-03-26 22:14:08 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 600/1251] eta: 0:06:54 lr: 0.000728 loss: 3.4189 (3.4401) grad_norm: 1.2019 (inf) time: 0.6386 [2021-03-26 22:14:14 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 610/1251] eta: 0:06:48 lr: 0.000727 loss: 3.4594 (3.4422) grad_norm: 1.2125 (inf) time: 0.6245 [2021-03-26 22:14:20 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 620/1251] eta: 0:06:41 lr: 0.000727 loss: 3.4594 (3.4415) grad_norm: 1.2425 (inf) time: 0.6270 [2021-03-26 22:14:26 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 630/1251] eta: 0:06:35 lr: 0.000727 loss: 3.4250 (3.4427) grad_norm: 1.2425 (inf) time: 0.6282 [2021-03-26 22:14:33 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 640/1251] eta: 0:06:28 lr: 0.000727 loss: 3.3276 (3.4419) grad_norm: 1.2445 (inf) time: 0.6238 [2021-03-26 22:14:39 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 650/1251] eta: 0:06:22 lr: 0.000727 loss: 3.4605 (3.4431) grad_norm: 1.3388 (inf) time: 0.6245 [2021-03-26 22:14:45 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 660/1251] eta: 0:06:15 lr: 0.000727 loss: 3.6186 (3.4448) grad_norm: 1.2297 (inf) time: 0.6227 [2021-03-26 22:14:51 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 670/1251] eta: 0:06:09 lr: 0.000727 loss: 3.4043 (3.4438) grad_norm: 1.2280 (inf) time: 0.6226 [2021-03-26 22:14:57 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 680/1251] eta: 0:06:02 lr: 0.000727 loss: 3.4043 (3.4449) grad_norm: 1.1813 (inf) time: 0.6244 [2021-03-26 22:15:04 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 690/1251] eta: 0:05:56 lr: 0.000727 loss: 3.5689 (3.4455) grad_norm: 1.1898 (inf) time: 0.6261 [2021-03-26 22:15:10 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 700/1251] eta: 0:05:50 lr: 0.000727 loss: 3.5241 (3.4463) grad_norm: 1.2762 (inf) time: 0.6296 [2021-03-26 22:15:16 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 710/1251] eta: 0:05:43 lr: 0.000727 loss: 3.3102 (3.4443) grad_norm: 1.3106 (inf) time: 0.6298 [2021-03-26 22:15:23 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 720/1251] eta: 0:05:37 lr: 0.000727 loss: 3.6167 (3.4473) grad_norm: 1.2456 (inf) time: 0.6284 [2021-03-26 22:15:29 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 730/1251] eta: 0:05:30 lr: 0.000727 loss: 3.6914 (3.4504) grad_norm: 1.2232 (inf) time: 0.6302 [2021-03-26 22:15:35 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 740/1251] eta: 0:05:24 lr: 0.000727 loss: 3.6983 (3.4517) grad_norm: 1.2542 (inf) time: 0.6369 [2021-03-26 22:15:42 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 750/1251] eta: 0:05:18 lr: 0.000727 loss: 3.6983 (3.4543) grad_norm: 1.2644 (inf) time: 0.6321 [2021-03-26 22:15:48 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 760/1251] eta: 0:05:11 lr: 0.000727 loss: 3.7729 (3.4545) grad_norm: 1.2418 (inf) time: 0.6225 [2021-03-26 22:15:54 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 770/1251] eta: 0:05:05 lr: 0.000727 loss: 3.3963 (3.4524) grad_norm: 1.2575 (inf) time: 0.6254 [2021-03-26 22:16:00 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 780/1251] eta: 0:04:58 lr: 0.000727 loss: 3.3731 (3.4497) grad_norm: 1.2539 (inf) time: 0.6306 [2021-03-26 22:16:07 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 790/1251] eta: 0:04:52 lr: 0.000727 loss: 3.2045 (3.4477) grad_norm: 1.2388 (inf) time: 0.6330 [2021-03-26 22:16:13 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 800/1251] eta: 0:04:46 lr: 0.000727 loss: 3.6140 (3.4509) grad_norm: 1.2232 (inf) time: 0.6292 [2021-03-26 22:16:19 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 810/1251] eta: 0:04:39 lr: 0.000727 loss: 3.6554 (3.4528) grad_norm: 1.2449 (inf) time: 0.6296 [2021-03-26 22:16:26 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 820/1251] eta: 0:04:33 lr: 0.000727 loss: 3.5973 (3.4560) grad_norm: 1.2512 (inf) time: 0.6345 [2021-03-26 22:16:32 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 830/1251] eta: 0:04:27 lr: 0.000727 loss: 3.6314 (3.4568) grad_norm: 1.3416 (inf) time: 0.6326 [2021-03-26 22:16:38 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 840/1251] eta: 0:04:20 lr: 0.000727 loss: 3.6037 (3.4556) grad_norm: 1.3575 (inf) time: 0.6331 [2021-03-26 22:16:45 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 850/1251] eta: 0:04:14 lr: 0.000727 loss: 3.4213 (3.4548) grad_norm: 1.3269 (inf) time: 0.6269 [2021-03-26 22:16:51 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 860/1251] eta: 0:04:08 lr: 0.000727 loss: 3.4213 (3.4556) grad_norm: 1.2978 (inf) time: 0.6229 [2021-03-26 22:16:57 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 870/1251] eta: 0:04:01 lr: 0.000727 loss: 3.4716 (3.4526) grad_norm: 1.2978 (inf) time: 0.6280 [2021-03-26 22:17:04 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 880/1251] eta: 0:03:55 lr: 0.000726 loss: 3.5145 (3.4541) grad_norm: 1.2416 (inf) time: 0.6316 [2021-03-26 22:17:10 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 890/1251] eta: 0:03:48 lr: 0.000726 loss: 3.7072 (3.4569) grad_norm: 1.2000 (inf) time: 0.6336 [2021-03-26 22:17:16 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 900/1251] eta: 0:03:42 lr: 0.000726 loss: 3.4151 (3.4540) grad_norm: 1.1975 (inf) time: 0.6292 [2021-03-26 22:17:22 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 910/1251] eta: 0:03:36 lr: 0.000726 loss: 3.4151 (3.4571) grad_norm: 1.2291 (inf) time: 0.6250 [2021-03-26 22:17:29 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 920/1251] eta: 0:03:29 lr: 0.000726 loss: 3.8317 (3.4595) grad_norm: 1.2475 (inf) time: 0.6258 [2021-03-26 22:17:35 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 930/1251] eta: 0:03:23 lr: 0.000726 loss: 3.6893 (3.4586) grad_norm: 1.2623 (inf) time: 0.6363 [2021-03-26 22:17:41 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 940/1251] eta: 0:03:17 lr: 0.000726 loss: 3.3051 (3.4571) grad_norm: 1.2623 (inf) time: 0.6377 [2021-03-26 22:17:48 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 950/1251] eta: 0:03:10 lr: 0.000726 loss: 3.6968 (3.4599) grad_norm: 1.2303 (inf) time: 0.6302 [2021-03-26 22:17:54 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 960/1251] eta: 0:03:04 lr: 0.000726 loss: 3.7295 (3.4601) grad_norm: 1.2518 (inf) time: 0.6303 [2021-03-26 22:18:00 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 970/1251] eta: 0:02:58 lr: 0.000726 loss: 3.3592 (3.4570) grad_norm: 1.3177 (inf) time: 0.6301 [2021-03-26 22:18:07 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 980/1251] eta: 0:02:51 lr: 0.000726 loss: 3.3833 (3.4575) grad_norm: 1.3200 (inf) time: 0.6306 [2021-03-26 22:18:13 swin_base_patch4_window7_224] INFO: Epoch: [105] [ 990/1251] eta: 0:02:45 lr: 0.000726 loss: 3.5846 (3.4577) grad_norm: 1.2987 (inf) time: 0.6304 [2021-03-26 22:18:19 swin_base_patch4_window7_224] INFO: Epoch: [105] [1000/1251] eta: 0:02:39 lr: 0.000726 loss: 3.4232 (3.4557) grad_norm: 1.2750 (inf) time: 0.6324 [2021-03-26 22:18:25 swin_base_patch4_window7_224] INFO: Epoch: [105] [1010/1251] eta: 0:02:32 lr: 0.000726 loss: 3.3651 (3.4563) grad_norm: 1.2270 (inf) time: 0.6260 [2021-03-26 22:18:32 swin_base_patch4_window7_224] INFO: Epoch: [105] [1020/1251] eta: 0:02:26 lr: 0.000726 loss: 3.4926 (3.4564) grad_norm: 1.1560 (inf) time: 0.6231 [2021-03-26 22:18:38 swin_base_patch4_window7_224] INFO: Epoch: [105] [1030/1251] eta: 0:02:20 lr: 0.000726 loss: 3.4926 (3.4566) grad_norm: 1.2056 (inf) time: 0.6284 [2021-03-26 22:18:44 swin_base_patch4_window7_224] INFO: Epoch: [105] [1040/1251] eta: 0:02:13 lr: 0.000726 loss: 3.5805 (3.4569) grad_norm: 1.2768 (inf) time: 0.6270 [2021-03-26 22:18:51 swin_base_patch4_window7_224] INFO: Epoch: [105] [1050/1251] eta: 0:02:07 lr: 0.000726 loss: 3.5701 (3.4578) grad_norm: 1.2592 (inf) time: 0.6248 [2021-03-26 22:18:57 swin_base_patch4_window7_224] INFO: Epoch: [105] [1060/1251] eta: 0:02:00 lr: 0.000726 loss: 3.4247 (3.4562) grad_norm: 1.1943 (inf) time: 0.6283 [2021-03-26 22:19:03 swin_base_patch4_window7_224] INFO: Epoch: [105] [1070/1251] eta: 0:01:54 lr: 0.000726 loss: 3.4445 (3.4576) grad_norm: 1.2005 (inf) time: 0.6330 [2021-03-26 22:19:09 swin_base_patch4_window7_224] INFO: Epoch: [105] [1080/1251] eta: 0:01:48 lr: 0.000726 loss: 3.5330 (3.4586) grad_norm: 1.2179 (inf) time: 0.6305 [2021-03-26 22:19:16 swin_base_patch4_window7_224] INFO: Epoch: [105] [1090/1251] eta: 0:01:41 lr: 0.000726 loss: 3.5514 (3.4587) grad_norm: 1.1961 (inf) time: 0.6285 [2021-03-26 22:19:22 swin_base_patch4_window7_224] INFO: Epoch: [105] [1100/1251] eta: 0:01:35 lr: 0.000726 loss: 3.5712 (3.4576) grad_norm: 1.1682 (inf) time: 0.6296 [2021-03-26 22:19:28 swin_base_patch4_window7_224] INFO: Epoch: [105] [1110/1251] eta: 0:01:29 lr: 0.000726 loss: 3.7532 (3.4589) grad_norm: 1.2709 (inf) time: 0.6316 [2021-03-26 22:19:35 swin_base_patch4_window7_224] INFO: Epoch: [105] [1120/1251] eta: 0:01:22 lr: 0.000726 loss: 3.7386 (3.4586) grad_norm: 1.2294 (inf) time: 0.6336 [2021-03-26 22:19:41 swin_base_patch4_window7_224] INFO: Epoch: [105] [1130/1251] eta: 0:01:16 lr: 0.000726 loss: 3.5077 (3.4584) grad_norm: 1.2075 (inf) time: 0.6302 [2021-03-26 22:19:47 swin_base_patch4_window7_224] INFO: Epoch: [105] [1140/1251] eta: 0:01:10 lr: 0.000726 loss: 3.7453 (3.4608) grad_norm: 1.2379 (inf) time: 0.6307 [2021-03-26 22:19:54 swin_base_patch4_window7_224] INFO: Epoch: [105] [1150/1251] eta: 0:01:03 lr: 0.000725 loss: 3.7635 (3.4630) grad_norm: 1.1753 (inf) time: 0.6275 [2021-03-26 22:20:00 swin_base_patch4_window7_224] INFO: Epoch: [105] [1160/1251] eta: 0:00:57 lr: 0.000725 loss: 3.6450 (3.4634) grad_norm: 1.2409 (inf) time: 0.6232 [2021-03-26 22:20:06 swin_base_patch4_window7_224] INFO: Epoch: [105] [1170/1251] eta: 0:00:51 lr: 0.000725 loss: 3.6659 (3.4656) grad_norm: 1.2409 (inf) time: 0.6264 [2021-03-26 22:20:13 swin_base_patch4_window7_224] INFO: Epoch: [105] [1180/1251] eta: 0:00:44 lr: 0.000725 loss: 3.7529 (3.4664) grad_norm: 1.1752 (inf) time: 0.6354 [2021-03-26 22:20:19 swin_base_patch4_window7_224] INFO: Epoch: [105] [1190/1251] eta: 0:00:38 lr: 0.000725 loss: 3.7377 (3.4670) grad_norm: 1.2460 (inf) time: 0.6421 [2021-03-26 22:20:25 swin_base_patch4_window7_224] INFO: Epoch: [105] [1200/1251] eta: 0:00:32 lr: 0.000725 loss: 3.5829 (3.4677) grad_norm: 1.2857 (inf) time: 0.6345 [2021-03-26 22:20:32 swin_base_patch4_window7_224] INFO: Epoch: [105] [1210/1251] eta: 0:00:25 lr: 0.000725 loss: 3.6847 (3.4703) grad_norm: 1.2798 (inf) time: 0.6292 [2021-03-26 22:20:38 swin_base_patch4_window7_224] INFO: Epoch: [105] [1220/1251] eta: 0:00:19 lr: 0.000725 loss: 3.5556 (3.4697) grad_norm: 1.2636 (inf) time: 0.6308 [2021-03-26 22:20:44 swin_base_patch4_window7_224] INFO: Epoch: [105] [1230/1251] eta: 0:00:13 lr: 0.000725 loss: 3.5176 (3.4711) grad_norm: 1.2699 (inf) time: 0.6299 [2021-03-26 22:20:50 swin_base_patch4_window7_224] INFO: Epoch: [105] [1240/1251] eta: 0:00:06 lr: 0.000725 loss: 3.5176 (3.4715) grad_norm: 1.2485 (inf) time: 0.6270 [2021-03-26 22:20:57 swin_base_patch4_window7_224] INFO: Epoch: [105] [1250/1251] eta: 0:00:00 lr: 0.000725 loss: 3.2346 (3.4684) grad_norm: 1.2485 (inf) time: 0.6283 [2021-03-26 22:22:07 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.8944 (0.8944) acc1: 81.2500 (81.2500) acc5: 95.3125 (95.3125) [2021-03-26 22:22:09 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 1.0627 (1.1206) acc1: 75.0000 (74.2898) acc5: 93.7500 (93.4659) [2021-03-26 22:22:10 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.0627 (1.0843) acc1: 75.0000 (75.8929) acc5: 93.7500 (93.6756) [2021-03-26 22:22:11 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.9613 (1.0464) acc1: 76.5625 (76.4113) acc5: 93.7500 (94.0020) [2021-03-26 22:22:13 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9749 (1.0381) acc1: 78.1250 (76.7912) acc5: 93.7500 (93.9787) [2021-03-26 22:22:14 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9899 (1.0285) acc1: 78.1250 (76.9280) acc5: 93.7500 (94.0480) [2021-03-26 22:22:21 swin_base_patch4_window7_224] INFO: * Acc@1 76.886 Acc@5 93.826 loss 1.024 [2021-03-26 22:22:21 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.9% [2021-03-26 22:22:21 swin_base_patch4_window7_224] INFO: Max accuracy: 76.92% [2021-03-26 22:22:25 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 0/1251] eta: 1:25:11 lr: 0.000725 loss: 3.6200 (3.6200) grad_norm: 0.9580 (0.9580) time: 4.0860 [2021-03-26 22:22:31 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 10/1251] eta: 0:19:40 lr: 0.000725 loss: 3.5080 (3.4011) grad_norm: 1.2679 (1.2465) time: 0.9511 [2021-03-26 22:22:38 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 20/1251] eta: 0:16:24 lr: 0.000725 loss: 3.4762 (3.3565) grad_norm: 1.2527 (1.2292) time: 0.6351 [2021-03-26 22:22:44 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 30/1251] eta: 0:15:09 lr: 0.000725 loss: 3.4762 (3.3905) grad_norm: 1.2449 (1.2513) time: 0.6314 [2021-03-26 22:22:50 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 40/1251] eta: 0:14:27 lr: 0.000725 loss: 3.6196 (3.4437) grad_norm: 1.2449 (1.2616) time: 0.6296 [2021-03-26 22:22:56 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 50/1251] eta: 0:13:57 lr: 0.000725 loss: 3.6196 (3.4616) grad_norm: 1.2447 (1.2615) time: 0.6245 [2021-03-26 22:23:03 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 60/1251] eta: 0:13:37 lr: 0.000725 loss: 3.7407 (3.4924) grad_norm: 1.2578 (1.2757) time: 0.6247 [2021-03-26 22:23:09 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 70/1251] eta: 0:13:20 lr: 0.000725 loss: 3.7407 (3.4766) grad_norm: 1.2759 (1.2699) time: 0.6258 [2021-03-26 22:23:15 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 80/1251] eta: 0:13:09 lr: 0.000725 loss: 3.2643 (3.4245) grad_norm: 1.1461 (1.2586) time: 0.6357 [2021-03-26 22:23:22 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 90/1251] eta: 0:12:58 lr: 0.000725 loss: 3.2534 (3.4248) grad_norm: 1.1631 (1.2532) time: 0.6466 [2021-03-26 22:23:28 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 100/1251] eta: 0:12:47 lr: 0.000725 loss: 3.4587 (3.4341) grad_norm: 1.2056 (1.2463) time: 0.6396 [2021-03-26 22:23:34 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 110/1251] eta: 0:12:36 lr: 0.000725 loss: 3.4044 (3.4222) grad_norm: 1.2056 (1.2413) time: 0.6285 [2021-03-26 22:23:41 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 120/1251] eta: 0:12:29 lr: 0.000725 loss: 3.3401 (3.4318) grad_norm: 1.1348 (1.2404) time: 0.6391 [2021-03-26 22:23:47 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 130/1251] eta: 0:12:20 lr: 0.000725 loss: 3.4195 (3.4238) grad_norm: 1.1526 (1.2375) time: 0.6444 [2021-03-26 22:23:54 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 140/1251] eta: 0:12:10 lr: 0.000725 loss: 3.1917 (3.4153) grad_norm: 1.2325 (1.2401) time: 0.6270 [2021-03-26 22:24:00 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 150/1251] eta: 0:12:02 lr: 0.000725 loss: 3.1355 (3.3793) grad_norm: 1.2559 (1.2442) time: 0.6272 [2021-03-26 22:24:06 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 160/1251] eta: 0:11:53 lr: 0.000725 loss: 3.3419 (3.3904) grad_norm: 1.2239 (1.2395) time: 0.6289 [2021-03-26 22:24:12 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 170/1251] eta: 0:11:45 lr: 0.000724 loss: 3.8507 (3.4066) grad_norm: 1.1532 (1.2375) time: 0.6298 [2021-03-26 22:24:19 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 180/1251] eta: 0:11:37 lr: 0.000724 loss: 3.6495 (3.4039) grad_norm: 1.1717 (1.2376) time: 0.6290 [2021-03-26 22:24:25 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 190/1251] eta: 0:11:29 lr: 0.000724 loss: 3.5592 (3.4209) grad_norm: 1.1717 (1.2402) time: 0.6287 [2021-03-26 22:24:31 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 200/1251] eta: 0:11:22 lr: 0.000724 loss: 3.5387 (3.4204) grad_norm: 1.2175 (1.2392) time: 0.6380 [2021-03-26 22:24:38 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 210/1251] eta: 0:11:15 lr: 0.000724 loss: 3.7226 (3.4281) grad_norm: 1.2459 (1.2433) time: 0.6375 [2021-03-26 22:24:44 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 220/1251] eta: 0:11:08 lr: 0.000724 loss: 3.6609 (3.4303) grad_norm: 1.2120 (1.2393) time: 0.6351 [2021-03-26 22:24:50 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 230/1251] eta: 0:11:01 lr: 0.000724 loss: 3.6345 (3.4396) grad_norm: 1.1471 (1.2376) time: 0.6328 [2021-03-26 22:24:57 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 240/1251] eta: 0:10:53 lr: 0.000724 loss: 3.7217 (3.4478) grad_norm: 1.2218 (1.2393) time: 0.6258 [2021-03-26 22:25:03 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 250/1251] eta: 0:10:46 lr: 0.000724 loss: 3.6055 (3.4524) grad_norm: 1.2321 (1.2383) time: 0.6289 [2021-03-26 22:25:09 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 260/1251] eta: 0:10:39 lr: 0.000724 loss: 3.6915 (3.4615) grad_norm: 1.2321 (1.2428) time: 0.6273 [2021-03-26 22:25:16 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 270/1251] eta: 0:10:32 lr: 0.000724 loss: 3.7365 (3.4607) grad_norm: 1.2101 (1.2435) time: 0.6235 [2021-03-26 22:25:22 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 280/1251] eta: 0:10:25 lr: 0.000724 loss: 3.7356 (3.4703) grad_norm: 1.2375 (1.2461) time: 0.6290 [2021-03-26 22:25:28 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 290/1251] eta: 0:10:18 lr: 0.000724 loss: 3.6200 (3.4697) grad_norm: 1.2936 (1.2492) time: 0.6279 [2021-03-26 22:25:35 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 300/1251] eta: 0:10:11 lr: 0.000724 loss: 3.4160 (3.4649) grad_norm: 1.2479 (1.2470) time: 0.6338 [2021-03-26 22:25:41 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 310/1251] eta: 0:10:04 lr: 0.000724 loss: 3.5432 (3.4728) grad_norm: 1.2479 (1.2485) time: 0.6365 [2021-03-26 22:25:47 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 320/1251] eta: 0:09:58 lr: 0.000724 loss: 3.8136 (3.4818) grad_norm: 1.3373 (1.2540) time: 0.6273 [2021-03-26 22:25:53 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 330/1251] eta: 0:09:51 lr: 0.000724 loss: 3.5167 (3.4743) grad_norm: 1.2963 (1.2542) time: 0.6294 [2021-03-26 22:26:00 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 340/1251] eta: 0:09:44 lr: 0.000724 loss: 3.6786 (3.4800) grad_norm: 1.2541 (1.2557) time: 0.6352 [2021-03-26 22:26:06 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 350/1251] eta: 0:09:37 lr: 0.000724 loss: 3.6626 (3.4797) grad_norm: 1.2541 (1.2580) time: 0.6320 [2021-03-26 22:26:12 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 360/1251] eta: 0:09:31 lr: 0.000724 loss: 3.5384 (3.4789) grad_norm: 1.3030 (1.2602) time: 0.6297 [2021-03-26 22:26:19 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 370/1251] eta: 0:09:24 lr: 0.000724 loss: 3.5413 (3.4812) grad_norm: 1.1889 (1.2586) time: 0.6288 [2021-03-26 22:26:25 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 380/1251] eta: 0:09:17 lr: 0.000724 loss: 3.5413 (3.4794) grad_norm: 1.1702 (1.2587) time: 0.6266 [2021-03-26 22:26:31 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 390/1251] eta: 0:09:11 lr: 0.000724 loss: 3.5171 (3.4781) grad_norm: 1.2248 (1.2568) time: 0.6265 [2021-03-26 22:26:37 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 400/1251] eta: 0:09:04 lr: 0.000724 loss: 3.6350 (3.4803) grad_norm: 1.1816 (1.2556) time: 0.6286 [2021-03-26 22:26:44 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 410/1251] eta: 0:08:57 lr: 0.000724 loss: 3.4555 (3.4747) grad_norm: 1.1727 (1.2548) time: 0.6310 [2021-03-26 22:26:50 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 420/1251] eta: 0:08:51 lr: 0.000724 loss: 3.4555 (3.4759) grad_norm: 1.2097 (1.2554) time: 0.6308 [2021-03-26 22:26:56 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 430/1251] eta: 0:08:44 lr: 0.000723 loss: 3.6341 (3.4793) grad_norm: 1.2146 (1.2559) time: 0.6309 [2021-03-26 22:27:03 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 440/1251] eta: 0:08:38 lr: 0.000723 loss: 3.6341 (3.4765) grad_norm: 1.2028 (1.2556) time: 0.6259 [2021-03-26 22:27:09 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 450/1251] eta: 0:08:31 lr: 0.000723 loss: 3.6180 (3.4806) grad_norm: 1.3042 (1.2600) time: 0.6269 [2021-03-26 22:27:15 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 460/1251] eta: 0:08:24 lr: 0.000723 loss: 3.7231 (3.4845) grad_norm: 1.2596 (1.2605) time: 0.6278 [2021-03-26 22:27:22 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 470/1251] eta: 0:08:18 lr: 0.000723 loss: 3.6471 (3.4801) grad_norm: 1.1996 (1.2597) time: 0.6351 [2021-03-26 22:27:28 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 480/1251] eta: 0:08:12 lr: 0.000723 loss: 3.4216 (3.4824) grad_norm: 1.2641 (1.2606) time: 0.6349 [2021-03-26 22:27:34 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 490/1251] eta: 0:08:05 lr: 0.000723 loss: 3.5095 (3.4837) grad_norm: 1.2883 (1.2616) time: 0.6269 [2021-03-26 22:27:41 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 500/1251] eta: 0:07:59 lr: 0.000723 loss: 3.8469 (3.4911) grad_norm: 1.2393 (1.2611) time: 0.6392 [2021-03-26 22:27:47 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 510/1251] eta: 0:07:52 lr: 0.000723 loss: 3.8801 (3.4965) grad_norm: 1.1715 (1.2591) time: 0.6374 [2021-03-26 22:27:53 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 520/1251] eta: 0:07:46 lr: 0.000723 loss: 3.6199 (3.4917) grad_norm: 1.1840 (1.2593) time: 0.6236 [2021-03-26 22:27:59 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 530/1251] eta: 0:07:39 lr: 0.000723 loss: 3.5040 (3.4933) grad_norm: 1.2787 (1.2591) time: 0.6197 [2021-03-26 22:28:06 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 540/1251] eta: 0:07:33 lr: 0.000723 loss: 3.5898 (3.4944) grad_norm: 1.1544 (1.2572) time: 0.6234 [2021-03-26 22:28:12 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 550/1251] eta: 0:07:26 lr: 0.000723 loss: 3.4232 (3.4884) grad_norm: 1.1531 (1.2564) time: 0.6300 [2021-03-26 22:28:18 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 560/1251] eta: 0:07:20 lr: 0.000723 loss: 3.4623 (3.4883) grad_norm: 1.1698 (1.2561) time: 0.6353 [2021-03-26 22:28:25 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 570/1251] eta: 0:07:13 lr: 0.000723 loss: 3.5902 (3.4813) grad_norm: 1.1698 (1.2546) time: 0.6297 [2021-03-26 22:28:31 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 580/1251] eta: 0:07:07 lr: 0.000723 loss: 3.4150 (3.4802) grad_norm: 1.1487 (1.2533) time: 0.6219 [2021-03-26 22:28:37 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 590/1251] eta: 0:07:00 lr: 0.000723 loss: 3.5061 (3.4808) grad_norm: 1.1534 (1.2530) time: 0.6265 [2021-03-26 22:28:43 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 600/1251] eta: 0:06:54 lr: 0.000723 loss: 3.5482 (3.4796) grad_norm: 1.2485 (1.2539) time: 0.6323 [2021-03-26 22:28:50 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 610/1251] eta: 0:06:47 lr: 0.000723 loss: 3.5784 (3.4809) grad_norm: 1.3008 (1.2550) time: 0.6328 [2021-03-26 22:28:56 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 620/1251] eta: 0:06:41 lr: 0.000723 loss: 3.5784 (3.4832) grad_norm: 1.3024 (1.2567) time: 0.6344 [2021-03-26 22:29:02 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 630/1251] eta: 0:06:35 lr: 0.000723 loss: 3.6263 (3.4849) grad_norm: 1.3085 (1.2569) time: 0.6320 [2021-03-26 22:29:09 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 640/1251] eta: 0:06:28 lr: 0.000723 loss: 3.4709 (3.4859) grad_norm: 1.1915 (1.2561) time: 0.6308 [2021-03-26 22:29:15 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 650/1251] eta: 0:06:22 lr: 0.000723 loss: 3.4430 (3.4873) grad_norm: 1.1771 (1.2563) time: 0.6340 [2021-03-26 22:29:21 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 660/1251] eta: 0:06:15 lr: 0.000723 loss: 3.4654 (3.4847) grad_norm: 1.2443 (1.2565) time: 0.6353 [2021-03-26 22:29:28 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 670/1251] eta: 0:06:09 lr: 0.000723 loss: 3.4077 (3.4843) grad_norm: 1.2208 (1.2574) time: 0.6383 [2021-03-26 22:29:34 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 680/1251] eta: 0:06:03 lr: 0.000723 loss: 3.5133 (3.4870) grad_norm: 1.2208 (1.2570) time: 0.6376 [2021-03-26 22:29:41 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 690/1251] eta: 0:05:56 lr: 0.000723 loss: 3.7095 (3.4890) grad_norm: 1.1913 (1.2574) time: 0.6344 [2021-03-26 22:29:47 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 700/1251] eta: 0:05:50 lr: 0.000722 loss: 3.3527 (3.4845) grad_norm: 1.1913 (1.2571) time: 0.6284 [2021-03-26 22:29:53 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 710/1251] eta: 0:05:44 lr: 0.000722 loss: 3.0747 (3.4820) grad_norm: 1.2905 (1.2580) time: 0.6298 [2021-03-26 22:29:59 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 720/1251] eta: 0:05:37 lr: 0.000722 loss: 3.4931 (3.4808) grad_norm: 1.2192 (1.2570) time: 0.6349 [2021-03-26 22:30:06 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 730/1251] eta: 0:05:31 lr: 0.000722 loss: 3.6650 (3.4828) grad_norm: 1.1374 (1.2561) time: 0.6287 [2021-03-26 22:30:12 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 740/1251] eta: 0:05:24 lr: 0.000722 loss: 3.7496 (3.4853) grad_norm: 1.1481 (1.2560) time: 0.6260 [2021-03-26 22:30:18 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 750/1251] eta: 0:05:18 lr: 0.000722 loss: 3.6948 (3.4889) grad_norm: 1.1737 (1.2550) time: 0.6344 [2021-03-26 22:30:25 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 760/1251] eta: 0:05:12 lr: 0.000722 loss: 3.5485 (3.4865) grad_norm: 1.1620 (1.2546) time: 0.6309 [2021-03-26 22:30:31 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 770/1251] eta: 0:05:05 lr: 0.000722 loss: 3.3672 (3.4848) grad_norm: 1.2783 (1.2566) time: 0.6230 [2021-03-26 22:30:37 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 780/1251] eta: 0:04:59 lr: 0.000722 loss: 3.5329 (3.4863) grad_norm: 1.2730 (1.2563) time: 0.6262 [2021-03-26 22:30:43 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 790/1251] eta: 0:04:52 lr: 0.000722 loss: 3.5147 (3.4853) grad_norm: 1.1754 (1.2546) time: 0.6305 [2021-03-26 22:30:50 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 800/1251] eta: 0:04:46 lr: 0.000722 loss: 3.4551 (3.4851) grad_norm: 1.1929 (1.2559) time: 0.6315 [2021-03-26 22:30:56 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 810/1251] eta: 0:04:40 lr: 0.000722 loss: 3.5689 (3.4857) grad_norm: 1.2475 (1.2558) time: 0.6286 [2021-03-26 22:31:02 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 820/1251] eta: 0:04:33 lr: 0.000722 loss: 3.6331 (3.4857) grad_norm: 1.2332 (1.2562) time: 0.6338 [2021-03-26 22:31:09 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 830/1251] eta: 0:04:27 lr: 0.000722 loss: 3.4948 (3.4876) grad_norm: 1.2853 (1.2567) time: 0.6298 [2021-03-26 22:31:15 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 840/1251] eta: 0:04:20 lr: 0.000722 loss: 3.5777 (3.4884) grad_norm: 1.3045 (1.2572) time: 0.6255 [2021-03-26 22:31:21 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 850/1251] eta: 0:04:14 lr: 0.000722 loss: 3.5271 (3.4861) grad_norm: 1.2614 (1.2569) time: 0.6313 [2021-03-26 22:31:28 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 860/1251] eta: 0:04:08 lr: 0.000722 loss: 3.3891 (3.4853) grad_norm: 1.1425 (1.2565) time: 0.6268 [2021-03-26 22:31:34 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 870/1251] eta: 0:04:01 lr: 0.000722 loss: 3.4920 (3.4864) grad_norm: 1.2131 (1.2561) time: 0.6289 [2021-03-26 22:31:40 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 880/1251] eta: 0:03:55 lr: 0.000722 loss: 3.4359 (3.4873) grad_norm: 1.2204 (1.2560) time: 0.6329 [2021-03-26 22:31:46 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 890/1251] eta: 0:03:49 lr: 0.000722 loss: 3.6485 (3.4878) grad_norm: 1.3429 (1.2582) time: 0.6269 [2021-03-26 22:31:53 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 900/1251] eta: 0:03:42 lr: 0.000722 loss: 3.6485 (3.4876) grad_norm: 1.3021 (1.2577) time: 0.6221 [2021-03-26 22:31:59 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 910/1251] eta: 0:03:36 lr: 0.000722 loss: 3.7905 (3.4923) grad_norm: 1.1813 (1.2576) time: 0.6210 [2021-03-26 22:32:05 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 920/1251] eta: 0:03:29 lr: 0.000722 loss: 3.8114 (3.4892) grad_norm: 1.1948 (1.2566) time: 0.6218 [2021-03-26 22:32:11 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 930/1251] eta: 0:03:23 lr: 0.000722 loss: 3.2230 (3.4877) grad_norm: 1.1707 (1.2565) time: 0.6265 [2021-03-26 22:32:18 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 940/1251] eta: 0:03:17 lr: 0.000722 loss: 3.5703 (3.4877) grad_norm: 1.2176 (1.2568) time: 0.6303 [2021-03-26 22:32:24 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 950/1251] eta: 0:03:10 lr: 0.000722 loss: 3.4333 (3.4850) grad_norm: 1.2929 (1.2578) time: 0.6324 [2021-03-26 22:32:30 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 960/1251] eta: 0:03:04 lr: 0.000722 loss: 3.5060 (3.4855) grad_norm: 1.2149 (1.2576) time: 0.6309 [2021-03-26 22:32:37 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 970/1251] eta: 0:02:58 lr: 0.000721 loss: 3.5918 (3.4842) grad_norm: 1.1878 (1.2576) time: 0.6247 [2021-03-26 22:32:43 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 980/1251] eta: 0:02:51 lr: 0.000721 loss: 3.4317 (3.4858) grad_norm: 1.1848 (1.2571) time: 0.6236 [2021-03-26 22:32:49 swin_base_patch4_window7_224] INFO: Epoch: [106] [ 990/1251] eta: 0:02:45 lr: 0.000721 loss: 3.7092 (3.4871) grad_norm: 1.1742 (1.2578) time: 0.6286 [2021-03-26 22:32:55 swin_base_patch4_window7_224] INFO: Epoch: [106] [1000/1251] eta: 0:02:39 lr: 0.000721 loss: 3.6573 (3.4880) grad_norm: 1.2769 (1.2575) time: 0.6290 [2021-03-26 22:33:02 swin_base_patch4_window7_224] INFO: Epoch: [106] [1010/1251] eta: 0:02:32 lr: 0.000721 loss: 3.5376 (3.4879) grad_norm: 1.3049 (1.2585) time: 0.6376 [2021-03-26 22:33:08 swin_base_patch4_window7_224] INFO: Epoch: [106] [1020/1251] eta: 0:02:26 lr: 0.000721 loss: 3.4669 (3.4873) grad_norm: 1.2884 (1.2584) time: 0.6387 [2021-03-26 22:33:14 swin_base_patch4_window7_224] INFO: Epoch: [106] [1030/1251] eta: 0:02:20 lr: 0.000721 loss: 3.3687 (3.4880) grad_norm: 1.2745 (1.2592) time: 0.6278 [2021-03-26 22:33:21 swin_base_patch4_window7_224] INFO: Epoch: [106] [1040/1251] eta: 0:02:13 lr: 0.000721 loss: 3.5597 (3.4892) grad_norm: 1.2185 (1.2586) time: 0.6274 [2021-03-26 22:33:27 swin_base_patch4_window7_224] INFO: Epoch: [106] [1050/1251] eta: 0:02:07 lr: 0.000721 loss: 3.6812 (3.4872) grad_norm: 1.1752 (1.2578) time: 0.6272 [2021-03-26 22:33:33 swin_base_patch4_window7_224] INFO: Epoch: [106] [1060/1251] eta: 0:02:01 lr: 0.000721 loss: 3.6222 (3.4874) grad_norm: 1.2188 (1.2578) time: 0.6305 [2021-03-26 22:33:40 swin_base_patch4_window7_224] INFO: Epoch: [106] [1070/1251] eta: 0:01:54 lr: 0.000721 loss: 3.6222 (3.4870) grad_norm: 1.2263 (1.2578) time: 0.6291 [2021-03-26 22:33:46 swin_base_patch4_window7_224] INFO: Epoch: [106] [1080/1251] eta: 0:01:48 lr: 0.000721 loss: 3.5694 (3.4880) grad_norm: 1.2353 (1.2576) time: 0.6294 [2021-03-26 22:33:52 swin_base_patch4_window7_224] INFO: Epoch: [106] [1090/1251] eta: 0:01:42 lr: 0.000721 loss: 3.5414 (3.4873) grad_norm: 1.2169 (1.2575) time: 0.6352 [2021-03-26 22:33:59 swin_base_patch4_window7_224] INFO: Epoch: [106] [1100/1251] eta: 0:01:35 lr: 0.000721 loss: 3.5006 (3.4872) grad_norm: 1.1760 (1.2571) time: 0.6372 [2021-03-26 22:34:05 swin_base_patch4_window7_224] INFO: Epoch: [106] [1110/1251] eta: 0:01:29 lr: 0.000721 loss: 3.4214 (3.4865) grad_norm: 1.2236 (1.2577) time: 0.6312 [2021-03-26 22:34:11 swin_base_patch4_window7_224] INFO: Epoch: [106] [1120/1251] eta: 0:01:22 lr: 0.000721 loss: 3.2710 (3.4832) grad_norm: 1.3675 (1.2599) time: 0.6238 [2021-03-26 22:34:17 swin_base_patch4_window7_224] INFO: Epoch: [106] [1130/1251] eta: 0:01:16 lr: 0.000721 loss: 3.4318 (3.4846) grad_norm: 1.2786 (1.2595) time: 0.6214 [2021-03-26 22:34:24 swin_base_patch4_window7_224] INFO: Epoch: [106] [1140/1251] eta: 0:01:10 lr: 0.000721 loss: 3.6372 (3.4829) grad_norm: 1.2481 (1.2598) time: 0.6273 [2021-03-26 22:34:30 swin_base_patch4_window7_224] INFO: Epoch: [106] [1150/1251] eta: 0:01:03 lr: 0.000721 loss: 3.5361 (3.4823) grad_norm: 1.2224 (1.2591) time: 0.6297 [2021-03-26 22:34:36 swin_base_patch4_window7_224] INFO: Epoch: [106] [1160/1251] eta: 0:00:57 lr: 0.000721 loss: 3.4553 (3.4815) grad_norm: 1.2038 (1.2589) time: 0.6250 [2021-03-26 22:34:42 swin_base_patch4_window7_224] INFO: Epoch: [106] [1170/1251] eta: 0:00:51 lr: 0.000721 loss: 3.4175 (3.4816) grad_norm: 1.2596 (1.2599) time: 0.6262 [2021-03-26 22:34:49 swin_base_patch4_window7_224] INFO: Epoch: [106] [1180/1251] eta: 0:00:44 lr: 0.000721 loss: 3.4175 (3.4811) grad_norm: 1.3020 (1.2605) time: 0.6300 [2021-03-26 22:34:55 swin_base_patch4_window7_224] INFO: Epoch: [106] [1190/1251] eta: 0:00:38 lr: 0.000721 loss: 3.6461 (3.4805) grad_norm: 1.2508 (1.2613) time: 0.6268 [2021-03-26 22:35:01 swin_base_patch4_window7_224] INFO: Epoch: [106] [1200/1251] eta: 0:00:32 lr: 0.000721 loss: 3.3680 (3.4785) grad_norm: 1.2830 (1.2620) time: 0.6203 [2021-03-26 22:35:08 swin_base_patch4_window7_224] INFO: Epoch: [106] [1210/1251] eta: 0:00:25 lr: 0.000721 loss: 3.2958 (3.4790) grad_norm: 1.2862 (1.2624) time: 0.6293 [2021-03-26 22:35:14 swin_base_patch4_window7_224] INFO: Epoch: [106] [1220/1251] eta: 0:00:19 lr: 0.000721 loss: 3.5681 (3.4812) grad_norm: 1.3118 (1.2627) time: 0.6317 [2021-03-26 22:35:20 swin_base_patch4_window7_224] INFO: Epoch: [106] [1230/1251] eta: 0:00:13 lr: 0.000721 loss: 3.5332 (3.4800) grad_norm: 1.3196 (1.2634) time: 0.6217 [2021-03-26 22:35:26 swin_base_patch4_window7_224] INFO: Epoch: [106] [1240/1251] eta: 0:00:06 lr: 0.000720 loss: 3.3595 (3.4785) grad_norm: 1.1767 (1.2629) time: 0.6267 [2021-03-26 22:35:33 swin_base_patch4_window7_224] INFO: Epoch: [106] [1250/1251] eta: 0:00:00 lr: 0.000720 loss: 3.6276 (3.4783) grad_norm: 1.1510 (1.2625) time: 0.6370 [2021-03-26 22:35:41 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:56 loss: 0.9314 (0.9314) acc1: 79.6875 (79.6875) acc5: 95.3125 (95.3125) [2021-03-26 22:35:43 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 1.0967 (1.0518) acc1: 73.4375 (76.2784) acc5: 93.7500 (94.0341) [2021-03-26 22:35:45 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.0785 (1.0374) acc1: 73.4375 (76.3393) acc5: 93.7500 (94.1220) [2021-03-26 22:35:47 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0604 (1.0284) acc1: 73.4375 (75.7056) acc5: 93.7500 (94.0524) [2021-03-26 22:35:48 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9539 (1.0156) acc1: 78.1250 (76.2957) acc5: 93.7500 (94.2835) [2021-03-26 22:35:50 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9679 (1.0201) acc1: 78.1250 (76.2560) acc5: 93.7500 (94.1120) [2021-03-26 22:35:57 swin_base_patch4_window7_224] INFO: * Acc@1 76.766 Acc@5 93.838 loss 1.008 [2021-03-26 22:35:57 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.8% [2021-03-26 22:35:57 swin_base_patch4_window7_224] INFO: Max accuracy: 76.92% [2021-03-26 22:36:01 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 0/1251] eta: 1:24:13 lr: 0.000720 loss: 2.6760 (2.6760) grad_norm: 1.2717 (1.2717) time: 4.0392 [2021-03-26 22:36:08 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 10/1251] eta: 0:20:11 lr: 0.000720 loss: 3.3933 (3.3701) grad_norm: 1.2757 (1.3183) time: 0.9766 [2021-03-26 22:36:14 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 20/1251] eta: 0:16:47 lr: 0.000720 loss: 3.3933 (3.3505) grad_norm: 1.2757 (1.3283) time: 0.6576 [2021-03-26 22:36:21 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 30/1251] eta: 0:15:27 lr: 0.000720 loss: 3.3249 (3.3232) grad_norm: 1.2638 (1.3322) time: 0.6407 [2021-03-26 22:36:27 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 40/1251] eta: 0:14:41 lr: 0.000720 loss: 3.3962 (3.3708) grad_norm: 1.3531 (1.3798) time: 0.6325 [2021-03-26 22:36:33 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 50/1251] eta: 0:14:15 lr: 0.000720 loss: 3.5435 (3.3859) grad_norm: 1.3313 (1.3519) time: 0.6381 [2021-03-26 22:36:40 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 60/1251] eta: 0:13:53 lr: 0.000720 loss: 3.4886 (3.3870) grad_norm: 1.2673 (1.3420) time: 0.6421 [2021-03-26 22:36:46 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 70/1251] eta: 0:13:34 lr: 0.000720 loss: 3.4900 (3.3953) grad_norm: 1.1786 (1.3251) time: 0.6338 [2021-03-26 22:36:53 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 80/1251] eta: 0:13:20 lr: 0.000720 loss: 3.5272 (3.4009) grad_norm: 1.1786 (1.3151) time: 0.6361 [2021-03-26 22:36:59 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 90/1251] eta: 0:13:06 lr: 0.000720 loss: 3.2521 (3.3804) grad_norm: 1.2809 (1.3158) time: 0.6309 [2021-03-26 22:37:05 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 100/1251] eta: 0:12:54 lr: 0.000720 loss: 3.4179 (3.4057) grad_norm: 1.2698 (1.3139) time: 0.6257 [2021-03-26 22:37:11 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 110/1251] eta: 0:12:42 lr: 0.000720 loss: 3.4840 (3.3989) grad_norm: 1.2014 (1.3060) time: 0.6259 [2021-03-26 22:37:18 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 120/1251] eta: 0:12:31 lr: 0.000720 loss: 3.1100 (3.4005) grad_norm: 1.1818 (1.3028) time: 0.6221 [2021-03-26 22:37:24 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 130/1251] eta: 0:12:21 lr: 0.000720 loss: 3.3846 (3.4057) grad_norm: 1.1969 (1.2965) time: 0.6254 [2021-03-26 22:37:30 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 140/1251] eta: 0:12:11 lr: 0.000720 loss: 3.2623 (3.3979) grad_norm: 1.1654 (1.2905) time: 0.6238 [2021-03-26 22:37:36 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 150/1251] eta: 0:12:02 lr: 0.000720 loss: 3.2937 (3.4062) grad_norm: 1.2756 (1.2946) time: 0.6223 [2021-03-26 22:37:43 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 160/1251] eta: 0:11:54 lr: 0.000720 loss: 3.5936 (3.4093) grad_norm: 1.2946 (1.2960) time: 0.6267 [2021-03-26 22:37:49 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 170/1251] eta: 0:11:45 lr: 0.000720 loss: 3.5204 (3.4151) grad_norm: 1.2946 (1.2956) time: 0.6270 [2021-03-26 22:37:55 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 180/1251] eta: 0:11:37 lr: 0.000720 loss: 3.7954 (3.4312) grad_norm: 1.2805 (1.2945) time: 0.6256 [2021-03-26 22:38:02 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 190/1251] eta: 0:11:30 lr: 0.000720 loss: 3.7922 (3.4194) grad_norm: 1.2805 (1.2951) time: 0.6351 [2021-03-26 22:38:08 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 200/1251] eta: 0:11:23 lr: 0.000720 loss: 3.2695 (3.4087) grad_norm: 1.2644 (1.3024) time: 0.6391 [2021-03-26 22:38:14 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 210/1251] eta: 0:11:16 lr: 0.000720 loss: 3.5015 (3.4160) grad_norm: 1.2596 (1.3012) time: 0.6355 [2021-03-26 22:38:21 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 220/1251] eta: 0:11:08 lr: 0.000720 loss: 3.5633 (3.4115) grad_norm: 1.1698 (1.2953) time: 0.6344 [2021-03-26 22:38:27 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 230/1251] eta: 0:11:01 lr: 0.000720 loss: 3.1952 (3.4033) grad_norm: 1.1936 (1.2995) time: 0.6312 [2021-03-26 22:38:33 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 240/1251] eta: 0:10:53 lr: 0.000720 loss: 3.4281 (3.4151) grad_norm: 1.1672 (1.2935) time: 0.6263 [2021-03-26 22:38:39 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 250/1251] eta: 0:10:46 lr: 0.000720 loss: 3.5494 (3.4195) grad_norm: 1.2054 (1.2928) time: 0.6278 [2021-03-26 22:38:46 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 260/1251] eta: 0:10:39 lr: 0.000719 loss: 3.5149 (3.4186) grad_norm: 1.2528 (1.2929) time: 0.6297 [2021-03-26 22:38:52 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 270/1251] eta: 0:10:32 lr: 0.000719 loss: 3.4863 (3.4229) grad_norm: 1.2412 (1.2916) time: 0.6254 [2021-03-26 22:38:58 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 280/1251] eta: 0:10:25 lr: 0.000719 loss: 3.4863 (3.4208) grad_norm: 1.2412 (1.2959) time: 0.6323 [2021-03-26 22:39:05 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 290/1251] eta: 0:10:19 lr: 0.000719 loss: 3.7629 (3.4371) grad_norm: 1.2310 (1.2919) time: 0.6380 [2021-03-26 22:39:11 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 300/1251] eta: 0:10:12 lr: 0.000719 loss: 3.7626 (3.4377) grad_norm: 1.1800 (1.2923) time: 0.6334 [2021-03-26 22:39:17 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 310/1251] eta: 0:10:05 lr: 0.000719 loss: 3.6221 (3.4439) grad_norm: 1.2646 (1.2916) time: 0.6266 [2021-03-26 22:39:23 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 320/1251] eta: 0:09:58 lr: 0.000719 loss: 3.6931 (3.4440) grad_norm: 1.2526 (1.2921) time: 0.6228 [2021-03-26 22:39:30 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 330/1251] eta: 0:09:51 lr: 0.000719 loss: 3.7371 (3.4545) grad_norm: 1.2351 (1.2919) time: 0.6298 [2021-03-26 22:39:36 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 340/1251] eta: 0:09:44 lr: 0.000719 loss: 3.7940 (3.4546) grad_norm: 1.2295 (1.2902) time: 0.6331 [2021-03-26 22:39:42 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 350/1251] eta: 0:09:38 lr: 0.000719 loss: 3.5853 (3.4540) grad_norm: 1.2668 (1.2909) time: 0.6332 [2021-03-26 22:39:49 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 360/1251] eta: 0:09:31 lr: 0.000719 loss: 3.4765 (3.4518) grad_norm: 1.2920 (1.2914) time: 0.6338 [2021-03-26 22:39:55 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 370/1251] eta: 0:09:24 lr: 0.000719 loss: 3.4765 (3.4529) grad_norm: 1.2805 (1.2914) time: 0.6269 [2021-03-26 22:40:01 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 380/1251] eta: 0:09:18 lr: 0.000719 loss: 3.5913 (3.4568) grad_norm: 1.2639 (1.2914) time: 0.6261 [2021-03-26 22:40:08 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 390/1251] eta: 0:09:11 lr: 0.000719 loss: 3.5913 (3.4529) grad_norm: 1.2021 (1.2886) time: 0.6271 [2021-03-26 22:40:14 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 400/1251] eta: 0:09:04 lr: 0.000719 loss: 3.6164 (3.4540) grad_norm: 1.1805 (1.2866) time: 0.6263 [2021-03-26 22:40:20 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 410/1251] eta: 0:08:58 lr: 0.000719 loss: 3.5680 (3.4519) grad_norm: 1.1737 (1.2881) time: 0.6301 [2021-03-26 22:40:27 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 420/1251] eta: 0:08:51 lr: 0.000719 loss: 3.6272 (3.4584) grad_norm: 1.1827 (1.2868) time: 0.6328 [2021-03-26 22:40:33 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 430/1251] eta: 0:08:44 lr: 0.000719 loss: 3.6282 (3.4582) grad_norm: 1.1792 (1.2844) time: 0.6301 [2021-03-26 22:40:39 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 440/1251] eta: 0:08:38 lr: 0.000719 loss: 3.5721 (3.4601) grad_norm: 1.2594 (1.2853) time: 0.6300 [2021-03-26 22:40:45 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 450/1251] eta: 0:08:31 lr: 0.000719 loss: 3.3754 (3.4594) grad_norm: 1.3010 (1.2851) time: 0.6315 [2021-03-26 22:40:52 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 460/1251] eta: 0:08:25 lr: 0.000719 loss: 3.3106 (3.4593) grad_norm: 1.2255 (1.2845) time: 0.6329 [2021-03-26 22:40:58 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 470/1251] eta: 0:08:18 lr: 0.000719 loss: 3.3575 (3.4551) grad_norm: 1.3262 (1.2868) time: 0.6303 [2021-03-26 22:41:04 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 480/1251] eta: 0:08:12 lr: 0.000719 loss: 3.4478 (3.4581) grad_norm: 1.3589 (1.2862) time: 0.6243 [2021-03-26 22:41:11 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 490/1251] eta: 0:08:05 lr: 0.000719 loss: 3.5955 (3.4563) grad_norm: 1.2663 (1.2860) time: 0.6246 [2021-03-26 22:41:17 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 500/1251] eta: 0:07:58 lr: 0.000719 loss: 3.3513 (3.4571) grad_norm: 1.2665 (1.2864) time: 0.6241 [2021-03-26 22:41:23 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 510/1251] eta: 0:07:52 lr: 0.000719 loss: 3.4674 (3.4590) grad_norm: 1.2665 (1.2863) time: 0.6320 [2021-03-26 22:41:30 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 520/1251] eta: 0:07:46 lr: 0.000718 loss: 3.4674 (3.4560) grad_norm: 1.2665 (1.2863) time: 0.6445 [2021-03-26 22:41:36 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 530/1251] eta: 0:07:39 lr: 0.000718 loss: 3.3618 (3.4521) grad_norm: 1.3202 (1.2882) time: 0.6388 [2021-03-26 22:41:42 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 540/1251] eta: 0:07:33 lr: 0.000718 loss: 3.4496 (3.4546) grad_norm: 1.3202 (1.2888) time: 0.6286 [2021-03-26 22:41:49 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 550/1251] eta: 0:07:27 lr: 0.000718 loss: 3.6322 (3.4534) grad_norm: 1.2842 (1.2891) time: 0.6415 [2021-03-26 22:41:55 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 560/1251] eta: 0:07:20 lr: 0.000718 loss: 3.5091 (3.4544) grad_norm: 1.2842 (1.2882) time: 0.6433 [2021-03-26 22:42:01 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 570/1251] eta: 0:07:14 lr: 0.000718 loss: 3.7264 (3.4576) grad_norm: 1.2429 (1.2887) time: 0.6297 [2021-03-26 22:42:08 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 580/1251] eta: 0:07:07 lr: 0.000718 loss: 3.7264 (3.4573) grad_norm: 1.2398 (1.2890) time: 0.6344 [2021-03-26 22:42:14 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 590/1251] eta: 0:07:01 lr: 0.000718 loss: 3.5555 (3.4577) grad_norm: 1.3205 (1.2908) time: 0.6312 [2021-03-26 22:42:20 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 600/1251] eta: 0:06:55 lr: 0.000718 loss: 3.4190 (3.4507) grad_norm: 1.3783 (1.2919) time: 0.6300 [2021-03-26 22:42:27 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 610/1251] eta: 0:06:48 lr: 0.000718 loss: 3.2871 (3.4501) grad_norm: 1.2807 (1.2924) time: 0.6356 [2021-03-26 22:42:33 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 620/1251] eta: 0:06:42 lr: 0.000718 loss: 3.3228 (3.4497) grad_norm: 1.2807 (1.2930) time: 0.6332 [2021-03-26 22:42:39 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 630/1251] eta: 0:06:35 lr: 0.000718 loss: 3.6657 (3.4538) grad_norm: 1.2465 (1.2929) time: 0.6333 [2021-03-26 22:42:46 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 640/1251] eta: 0:06:29 lr: 0.000718 loss: 3.8133 (3.4586) grad_norm: 1.2094 (1.2913) time: 0.6310 [2021-03-26 22:42:52 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 650/1251] eta: 0:06:22 lr: 0.000718 loss: 3.6732 (3.4632) grad_norm: 1.1876 (1.2899) time: 0.6342 [2021-03-26 22:42:58 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 660/1251] eta: 0:06:16 lr: 0.000718 loss: 3.6332 (3.4626) grad_norm: 1.2118 (1.2915) time: 0.6312 [2021-03-26 22:43:05 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 670/1251] eta: 0:06:09 lr: 0.000718 loss: 3.5024 (3.4626) grad_norm: 1.2149 (1.2903) time: 0.6228 [2021-03-26 22:43:11 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 680/1251] eta: 0:06:03 lr: 0.000718 loss: 3.5024 (3.4628) grad_norm: 1.2729 (1.2920) time: 0.6247 [2021-03-26 22:43:17 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 690/1251] eta: 0:05:56 lr: 0.000718 loss: 3.2352 (3.4593) grad_norm: 1.2236 (1.2901) time: 0.6224 [2021-03-26 22:43:23 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 700/1251] eta: 0:05:50 lr: 0.000718 loss: 3.2015 (3.4604) grad_norm: 1.1969 (1.2895) time: 0.6268 [2021-03-26 22:43:30 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 710/1251] eta: 0:05:44 lr: 0.000718 loss: 3.4928 (3.4601) grad_norm: 1.2397 (1.2896) time: 0.6322 [2021-03-26 22:43:36 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 720/1251] eta: 0:05:37 lr: 0.000718 loss: 3.4437 (3.4582) grad_norm: 1.1770 (1.2879) time: 0.6339 [2021-03-26 22:43:42 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 730/1251] eta: 0:05:31 lr: 0.000718 loss: 3.3381 (3.4563) grad_norm: 1.1669 (1.2865) time: 0.6333 [2021-03-26 22:43:49 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 740/1251] eta: 0:05:25 lr: 0.000718 loss: 3.5267 (3.4575) grad_norm: 1.1829 (1.2859) time: 0.6301 [2021-03-26 22:43:55 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 750/1251] eta: 0:05:18 lr: 0.000718 loss: 3.3773 (3.4540) grad_norm: 1.2380 (1.2870) time: 0.6358 [2021-03-26 22:44:01 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 760/1251] eta: 0:05:12 lr: 0.000718 loss: 3.3773 (3.4534) grad_norm: 1.2742 (1.2863) time: 0.6329 [2021-03-26 22:44:08 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 770/1251] eta: 0:05:05 lr: 0.000718 loss: 3.5440 (3.4519) grad_norm: 1.1548 (1.2870) time: 0.6338 [2021-03-26 22:44:14 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 780/1251] eta: 0:04:59 lr: 0.000718 loss: 3.5019 (3.4514) grad_norm: 1.2692 (1.2873) time: 0.6361 [2021-03-26 22:44:20 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 790/1251] eta: 0:04:53 lr: 0.000717 loss: 3.5975 (3.4542) grad_norm: 1.2692 (1.2869) time: 0.6273 [2021-03-26 22:44:27 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 800/1251] eta: 0:04:46 lr: 0.000717 loss: 3.6534 (3.4553) grad_norm: 1.2738 (1.2880) time: 0.6307 [2021-03-26 22:44:33 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 810/1251] eta: 0:04:40 lr: 0.000717 loss: 3.7053 (3.4555) grad_norm: 1.2986 (1.2871) time: 0.6284 [2021-03-26 22:44:39 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 820/1251] eta: 0:04:33 lr: 0.000717 loss: 3.7705 (3.4606) grad_norm: 1.1732 (1.2862) time: 0.6262 [2021-03-26 22:44:46 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 830/1251] eta: 0:04:27 lr: 0.000717 loss: 3.8031 (3.4622) grad_norm: 1.2384 (1.2863) time: 0.6371 [2021-03-26 22:44:52 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 840/1251] eta: 0:04:21 lr: 0.000717 loss: 3.6714 (3.4618) grad_norm: 1.2711 (1.2867) time: 0.6353 [2021-03-26 22:44:58 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 850/1251] eta: 0:04:14 lr: 0.000717 loss: 3.4121 (3.4617) grad_norm: 1.2843 (1.2868) time: 0.6308 [2021-03-26 22:45:05 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 860/1251] eta: 0:04:08 lr: 0.000717 loss: 3.5107 (3.4619) grad_norm: 1.1742 (1.2854) time: 0.6327 [2021-03-26 22:45:11 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 870/1251] eta: 0:04:02 lr: 0.000717 loss: 3.5107 (3.4625) grad_norm: 1.1157 (1.2841) time: 0.6334 [2021-03-26 22:45:17 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 880/1251] eta: 0:03:55 lr: 0.000717 loss: 3.6715 (3.4645) grad_norm: 1.1782 (1.2842) time: 0.6306 [2021-03-26 22:45:23 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 890/1251] eta: 0:03:49 lr: 0.000717 loss: 3.5847 (3.4667) grad_norm: 1.3057 (1.2854) time: 0.6289 [2021-03-26 22:45:30 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 900/1251] eta: 0:03:42 lr: 0.000717 loss: 3.4828 (3.4637) grad_norm: 1.3669 (1.2861) time: 0.6269 [2021-03-26 22:45:36 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 910/1251] eta: 0:03:36 lr: 0.000717 loss: 3.5044 (3.4660) grad_norm: 1.2380 (1.2859) time: 0.6309 [2021-03-26 22:45:42 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 920/1251] eta: 0:03:30 lr: 0.000717 loss: 3.5874 (3.4685) grad_norm: 1.2026 (1.2854) time: 0.6321 [2021-03-26 22:45:49 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 930/1251] eta: 0:03:23 lr: 0.000717 loss: 3.5274 (3.4684) grad_norm: 1.2220 (1.2852) time: 0.6254 [2021-03-26 22:45:55 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 940/1251] eta: 0:03:17 lr: 0.000717 loss: 3.4390 (3.4693) grad_norm: 1.2311 (1.2859) time: 0.6312 [2021-03-26 22:46:01 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 950/1251] eta: 0:03:11 lr: 0.000717 loss: 3.4727 (3.4687) grad_norm: 1.3036 (1.2865) time: 0.6341 [2021-03-26 22:46:08 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 960/1251] eta: 0:03:04 lr: 0.000717 loss: 3.6070 (3.4707) grad_norm: 1.2846 (1.2866) time: 0.6338 [2021-03-26 22:46:14 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 970/1251] eta: 0:02:58 lr: 0.000717 loss: 3.6070 (3.4720) grad_norm: 1.2131 (1.2866) time: 0.6311 [2021-03-26 22:46:20 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 980/1251] eta: 0:02:52 lr: 0.000717 loss: 3.4571 (3.4716) grad_norm: 1.2235 (1.2869) time: 0.6266 [2021-03-26 22:46:27 swin_base_patch4_window7_224] INFO: Epoch: [107] [ 990/1251] eta: 0:02:45 lr: 0.000717 loss: 3.4705 (3.4683) grad_norm: 1.3405 (1.2893) time: 0.6348 [2021-03-26 22:46:33 swin_base_patch4_window7_224] INFO: Epoch: [107] [1000/1251] eta: 0:02:39 lr: 0.000717 loss: 3.4705 (3.4683) grad_norm: 1.3735 (1.2903) time: 0.6362 [2021-03-26 22:46:39 swin_base_patch4_window7_224] INFO: Epoch: [107] [1010/1251] eta: 0:02:33 lr: 0.000717 loss: 3.5969 (3.4687) grad_norm: 1.2742 (1.2891) time: 0.6313 [2021-03-26 22:46:45 swin_base_patch4_window7_224] INFO: Epoch: [107] [1020/1251] eta: 0:02:26 lr: 0.000717 loss: 3.6192 (3.4712) grad_norm: 1.1896 (1.2886) time: 0.6260 [2021-03-26 22:46:52 swin_base_patch4_window7_224] INFO: Epoch: [107] [1030/1251] eta: 0:02:20 lr: 0.000717 loss: 3.7600 (3.4718) grad_norm: 1.2402 (1.2889) time: 0.6221 [2021-03-26 22:46:58 swin_base_patch4_window7_224] INFO: Epoch: [107] [1040/1251] eta: 0:02:13 lr: 0.000717 loss: 3.5333 (3.4718) grad_norm: 1.2793 (1.2885) time: 0.6291 [2021-03-26 22:47:04 swin_base_patch4_window7_224] INFO: Epoch: [107] [1050/1251] eta: 0:02:07 lr: 0.000717 loss: 3.5035 (3.4702) grad_norm: 1.2381 (1.2887) time: 0.6279 [2021-03-26 22:47:10 swin_base_patch4_window7_224] INFO: Epoch: [107] [1060/1251] eta: 0:02:01 lr: 0.000716 loss: 3.3575 (3.4708) grad_norm: 1.2381 (1.2884) time: 0.6233 [2021-03-26 22:47:17 swin_base_patch4_window7_224] INFO: Epoch: [107] [1070/1251] eta: 0:01:54 lr: 0.000716 loss: 3.4393 (3.4698) grad_norm: 1.2294 (1.2889) time: 0.6279 [2021-03-26 22:47:23 swin_base_patch4_window7_224] INFO: Epoch: [107] [1080/1251] eta: 0:01:48 lr: 0.000716 loss: 3.5733 (3.4723) grad_norm: 1.2294 (1.2894) time: 0.6300 [2021-03-26 22:47:29 swin_base_patch4_window7_224] INFO: Epoch: [107] [1090/1251] eta: 0:01:42 lr: 0.000716 loss: 3.7196 (3.4729) grad_norm: 1.1980 (1.2892) time: 0.6248 [2021-03-26 22:47:36 swin_base_patch4_window7_224] INFO: Epoch: [107] [1100/1251] eta: 0:01:35 lr: 0.000716 loss: 3.1856 (3.4708) grad_norm: 1.2643 (1.2892) time: 0.6235 [2021-03-26 22:47:42 swin_base_patch4_window7_224] INFO: Epoch: [107] [1110/1251] eta: 0:01:29 lr: 0.000716 loss: 3.2017 (3.4702) grad_norm: 1.2643 (1.2891) time: 0.6255 [2021-03-26 22:47:48 swin_base_patch4_window7_224] INFO: Epoch: [107] [1120/1251] eta: 0:01:23 lr: 0.000716 loss: 3.3720 (3.4693) grad_norm: 1.2697 (1.2892) time: 0.6211 [2021-03-26 22:47:54 swin_base_patch4_window7_224] INFO: Epoch: [107] [1130/1251] eta: 0:01:16 lr: 0.000716 loss: 3.3720 (3.4688) grad_norm: 1.2697 (1.2888) time: 0.6212 [2021-03-26 22:48:01 swin_base_patch4_window7_224] INFO: Epoch: [107] [1140/1251] eta: 0:01:10 lr: 0.000716 loss: 3.6508 (3.4704) grad_norm: 1.2359 (1.2896) time: 0.6263 [2021-03-26 22:48:07 swin_base_patch4_window7_224] INFO: Epoch: [107] [1150/1251] eta: 0:01:04 lr: 0.000716 loss: 3.5404 (3.4687) grad_norm: 1.2153 (1.2890) time: 0.6261 [2021-03-26 22:48:13 swin_base_patch4_window7_224] INFO: Epoch: [107] [1160/1251] eta: 0:00:57 lr: 0.000716 loss: 3.4432 (3.4689) grad_norm: 1.1699 (1.2886) time: 0.6273 [2021-03-26 22:48:19 swin_base_patch4_window7_224] INFO: Epoch: [107] [1170/1251] eta: 0:00:51 lr: 0.000716 loss: 3.6346 (3.4691) grad_norm: 1.1641 (1.2879) time: 0.6310 [2021-03-26 22:48:26 swin_base_patch4_window7_224] INFO: Epoch: [107] [1180/1251] eta: 0:00:44 lr: 0.000716 loss: 3.5990 (3.4696) grad_norm: 1.2204 (1.2878) time: 0.6328 [2021-03-26 22:48:32 swin_base_patch4_window7_224] INFO: Epoch: [107] [1190/1251] eta: 0:00:38 lr: 0.000716 loss: 3.4098 (3.4676) grad_norm: 1.2357 (1.2874) time: 0.6323 [2021-03-26 22:48:38 swin_base_patch4_window7_224] INFO: Epoch: [107] [1200/1251] eta: 0:00:32 lr: 0.000716 loss: 3.3775 (3.4678) grad_norm: 1.2252 (1.2874) time: 0.6295 [2021-03-26 22:48:45 swin_base_patch4_window7_224] INFO: Epoch: [107] [1210/1251] eta: 0:00:25 lr: 0.000716 loss: 3.3319 (3.4652) grad_norm: 1.2016 (1.2870) time: 0.6242 [2021-03-26 22:48:51 swin_base_patch4_window7_224] INFO: Epoch: [107] [1220/1251] eta: 0:00:19 lr: 0.000716 loss: 3.2239 (3.4645) grad_norm: 1.2622 (1.2868) time: 0.6206 [2021-03-26 22:48:57 swin_base_patch4_window7_224] INFO: Epoch: [107] [1230/1251] eta: 0:00:13 lr: 0.000716 loss: 3.3514 (3.4642) grad_norm: 1.2850 (1.2873) time: 0.6228 [2021-03-26 22:49:03 swin_base_patch4_window7_224] INFO: Epoch: [107] [1240/1251] eta: 0:00:06 lr: 0.000716 loss: 3.6733 (3.4645) grad_norm: 1.2886 (1.2873) time: 0.6270 [2021-03-26 22:49:09 swin_base_patch4_window7_224] INFO: Epoch: [107] [1250/1251] eta: 0:00:00 lr: 0.000716 loss: 3.4718 (3.4629) grad_norm: 1.3190 (1.2877) time: 0.6208 [2021-03-26 22:49:16 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:05 loss: 0.9445 (0.9445) acc1: 81.2500 (81.2500) acc5: 95.3125 (95.3125) [2021-03-26 22:49:18 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9595 (0.9337) acc1: 78.1250 (77.9830) acc5: 95.3125 (94.6023) [2021-03-26 22:49:21 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8959 (0.9675) acc1: 76.5625 (77.0833) acc5: 95.3125 (94.1220) [2021-03-26 22:49:23 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0318 (1.0029) acc1: 76.5625 (76.6129) acc5: 92.1875 (93.7500) [2021-03-26 22:49:25 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0318 (1.0023) acc1: 76.5625 (76.5625) acc5: 93.7500 (94.0930) [2021-03-26 22:49:27 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9536 (1.0076) acc1: 75.0000 (76.0640) acc5: 93.7500 (94.1760) [2021-03-26 22:49:32 swin_base_patch4_window7_224] INFO: * Acc@1 77.034 Acc@5 93.946 loss 0.995 [2021-03-26 22:49:32 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.0% [2021-03-26 22:49:32 swin_base_patch4_window7_224] INFO: Max accuracy: 77.03% [2021-03-26 22:49:36 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 0/1251] eta: 1:29:16 lr: 0.000716 loss: 3.7147 (3.7147) grad_norm: 1.1226 (1.1226) time: 4.2819 [2021-03-26 22:49:42 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 10/1251] eta: 0:20:10 lr: 0.000716 loss: 3.4133 (3.4106) grad_norm: 1.2679 (1.2536) time: 0.9755 [2021-03-26 22:49:49 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 20/1251] eta: 0:16:37 lr: 0.000716 loss: 3.5157 (3.5288) grad_norm: 1.1802 (1.1949) time: 0.6370 [2021-03-26 22:49:55 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 30/1251] eta: 0:15:15 lr: 0.000716 loss: 3.8288 (3.5604) grad_norm: 1.1802 (1.2313) time: 0.6256 [2021-03-26 22:50:01 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 40/1251] eta: 0:14:34 lr: 0.000716 loss: 3.5540 (3.5409) grad_norm: 1.2693 (1.2352) time: 0.6288 [2021-03-26 22:50:08 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 50/1251] eta: 0:14:06 lr: 0.000716 loss: 3.5540 (3.5442) grad_norm: 1.1837 (1.2290) time: 0.6348 [2021-03-26 22:50:14 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 60/1251] eta: 0:13:42 lr: 0.000716 loss: 3.6132 (3.5515) grad_norm: 1.3090 (1.2816) time: 0.6265 [2021-03-26 22:50:20 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 70/1251] eta: 0:13:24 lr: 0.000715 loss: 3.6100 (3.5513) grad_norm: 1.4083 (1.2943) time: 0.6228 [2021-03-26 22:50:26 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 80/1251] eta: 0:13:11 lr: 0.000715 loss: 3.5914 (3.5449) grad_norm: 1.2005 (1.2809) time: 0.6320 [2021-03-26 22:50:33 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 90/1251] eta: 0:12:58 lr: 0.000715 loss: 3.5380 (3.5175) grad_norm: 1.2245 (1.2783) time: 0.6307 [2021-03-26 22:50:39 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 100/1251] eta: 0:12:46 lr: 0.000715 loss: 3.4425 (3.5251) grad_norm: 1.2278 (1.2758) time: 0.6252 [2021-03-26 22:50:45 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 110/1251] eta: 0:12:35 lr: 0.000715 loss: 3.6562 (3.5357) grad_norm: 1.2034 (1.2686) time: 0.6269 [2021-03-26 22:50:51 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 120/1251] eta: 0:12:25 lr: 0.000715 loss: 3.5518 (3.5180) grad_norm: 1.2446 (1.2692) time: 0.6237 [2021-03-26 22:50:58 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 130/1251] eta: 0:12:17 lr: 0.000715 loss: 3.6201 (3.5376) grad_norm: 1.2381 (1.2637) time: 0.6319 [2021-03-26 22:51:04 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 140/1251] eta: 0:12:07 lr: 0.000715 loss: 3.6370 (3.5245) grad_norm: 1.1913 (1.2631) time: 0.6316 [2021-03-26 22:51:10 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 150/1251] eta: 0:11:59 lr: 0.000715 loss: 3.4119 (3.5267) grad_norm: 1.2477 (1.2646) time: 0.6233 [2021-03-26 22:51:17 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 160/1251] eta: 0:11:50 lr: 0.000715 loss: 3.3756 (3.5092) grad_norm: 1.2981 (1.2674) time: 0.6271 [2021-03-26 22:51:23 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 170/1251] eta: 0:11:43 lr: 0.000715 loss: 3.5458 (3.5120) grad_norm: 1.2838 (1.2672) time: 0.6308 [2021-03-26 22:51:29 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 180/1251] eta: 0:11:35 lr: 0.000715 loss: 3.6055 (3.5091) grad_norm: 1.2071 (1.2642) time: 0.6349 [2021-03-26 22:51:36 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 190/1251] eta: 0:11:28 lr: 0.000715 loss: 3.4560 (3.5043) grad_norm: 1.1865 (1.2654) time: 0.6303 [2021-03-26 22:51:42 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 200/1251] eta: 0:11:21 lr: 0.000715 loss: 3.6255 (3.5054) grad_norm: 1.2184 (1.2671) time: 0.6329 [2021-03-26 22:51:48 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 210/1251] eta: 0:11:13 lr: 0.000715 loss: 3.6255 (3.4973) grad_norm: 1.2220 (1.2645) time: 0.6299 [2021-03-26 22:51:54 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 220/1251] eta: 0:11:05 lr: 0.000715 loss: 3.5924 (3.5012) grad_norm: 1.1981 (1.2639) time: 0.6237 [2021-03-26 22:52:01 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 230/1251] eta: 0:10:58 lr: 0.000715 loss: 3.6999 (3.5047) grad_norm: 1.1981 (1.2604) time: 0.6260 [2021-03-26 22:52:07 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 240/1251] eta: 0:10:51 lr: 0.000715 loss: 3.6328 (3.5014) grad_norm: 1.2000 (1.2600) time: 0.6227 [2021-03-26 22:52:13 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 250/1251] eta: 0:10:44 lr: 0.000715 loss: 3.6075 (3.5062) grad_norm: 1.2647 (1.2620) time: 0.6251 [2021-03-26 22:52:20 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 260/1251] eta: 0:10:37 lr: 0.000715 loss: 3.6646 (3.5079) grad_norm: 1.2751 (1.2609) time: 0.6299 [2021-03-26 22:52:26 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 270/1251] eta: 0:10:30 lr: 0.000715 loss: 3.5954 (3.5122) grad_norm: 1.2612 (1.2640) time: 0.6359 [2021-03-26 22:52:32 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 280/1251] eta: 0:10:23 lr: 0.000715 loss: 3.4028 (3.5053) grad_norm: 1.2900 (1.2686) time: 0.6342 [2021-03-26 22:52:39 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 290/1251] eta: 0:10:16 lr: 0.000715 loss: 3.3983 (3.5085) grad_norm: 1.3115 (1.2712) time: 0.6277 [2021-03-26 22:52:45 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 300/1251] eta: 0:10:09 lr: 0.000715 loss: 3.5567 (3.5092) grad_norm: 1.3075 (1.2715) time: 0.6224 [2021-03-26 22:52:51 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 310/1251] eta: 0:10:02 lr: 0.000715 loss: 3.5294 (3.5045) grad_norm: 1.2727 (1.2737) time: 0.6208 [2021-03-26 22:52:57 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 320/1251] eta: 0:09:55 lr: 0.000715 loss: 3.5481 (3.5051) grad_norm: 1.2460 (1.2738) time: 0.6236 [2021-03-26 22:53:03 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 330/1251] eta: 0:09:49 lr: 0.000715 loss: 3.7923 (3.5127) grad_norm: 1.2234 (1.2717) time: 0.6260 [2021-03-26 22:53:10 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 340/1251] eta: 0:09:42 lr: 0.000714 loss: 3.7290 (3.5099) grad_norm: 1.2665 (1.2717) time: 0.6362 [2021-03-26 22:53:16 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 350/1251] eta: 0:09:36 lr: 0.000714 loss: 3.6223 (3.5152) grad_norm: 1.2665 (1.2714) time: 0.6379 [2021-03-26 22:53:22 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 360/1251] eta: 0:09:29 lr: 0.000714 loss: 3.6509 (3.5136) grad_norm: 1.1674 (1.2699) time: 0.6290 [2021-03-26 22:53:29 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 370/1251] eta: 0:09:22 lr: 0.000714 loss: 3.0737 (3.4970) grad_norm: 1.2274 (1.2712) time: 0.6209 [2021-03-26 22:53:35 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 380/1251] eta: 0:09:16 lr: 0.000714 loss: 3.0737 (3.4952) grad_norm: 1.2728 (1.2741) time: 0.6306 [2021-03-26 22:53:41 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 390/1251] eta: 0:09:09 lr: 0.000714 loss: 3.1664 (3.4848) grad_norm: 1.2816 (1.2749) time: 0.6350 [2021-03-26 22:53:48 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 400/1251] eta: 0:09:03 lr: 0.000714 loss: 3.0929 (3.4822) grad_norm: 1.2112 (1.2739) time: 0.6275 [2021-03-26 22:53:54 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 410/1251] eta: 0:08:56 lr: 0.000714 loss: 3.5644 (3.4882) grad_norm: 1.1804 (1.2727) time: 0.6313 [2021-03-26 22:54:00 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 420/1251] eta: 0:08:49 lr: 0.000714 loss: 3.5433 (3.4837) grad_norm: 1.2081 (1.2731) time: 0.6280 [2021-03-26 22:54:06 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 430/1251] eta: 0:08:43 lr: 0.000714 loss: 3.4951 (3.4858) grad_norm: 1.2190 (1.2734) time: 0.6225 [2021-03-26 22:54:13 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 440/1251] eta: 0:08:36 lr: 0.000714 loss: 3.7358 (3.4938) grad_norm: 1.2099 (1.2720) time: 0.6293 [2021-03-26 22:54:19 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 450/1251] eta: 0:08:30 lr: 0.000714 loss: 3.7713 (3.4970) grad_norm: 1.1990 (1.2707) time: 0.6378 [2021-03-26 22:54:25 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 460/1251] eta: 0:08:23 lr: 0.000714 loss: 3.7185 (3.4976) grad_norm: 1.2165 (1.2701) time: 0.6304 [2021-03-26 22:54:32 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 470/1251] eta: 0:08:17 lr: 0.000714 loss: 3.4679 (3.4918) grad_norm: 1.2204 (1.2699) time: 0.6215 [2021-03-26 22:54:38 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 480/1251] eta: 0:08:10 lr: 0.000714 loss: 3.2657 (3.4914) grad_norm: 1.2270 (1.2689) time: 0.6239 [2021-03-26 22:54:44 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 490/1251] eta: 0:08:04 lr: 0.000714 loss: 3.6463 (3.4936) grad_norm: 1.2580 (1.2693) time: 0.6255 [2021-03-26 22:54:50 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 500/1251] eta: 0:07:57 lr: 0.000714 loss: 3.5815 (3.4928) grad_norm: 1.2554 (1.2693) time: 0.6290 [2021-03-26 22:54:57 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 510/1251] eta: 0:07:51 lr: 0.000714 loss: 3.5665 (3.4919) grad_norm: 1.2554 (1.2699) time: 0.6322 [2021-03-26 22:55:03 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 520/1251] eta: 0:07:44 lr: 0.000714 loss: 3.6094 (3.4928) grad_norm: 1.3598 (1.2724) time: 0.6259 [2021-03-26 22:55:09 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 530/1251] eta: 0:07:38 lr: 0.000714 loss: 3.6679 (3.4955) grad_norm: 1.3632 (1.2740) time: 0.6224 [2021-03-26 22:55:16 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 540/1251] eta: 0:07:31 lr: 0.000714 loss: 3.6679 (3.4965) grad_norm: 1.3716 (1.2772) time: 0.6259 [2021-03-26 22:55:22 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 550/1251] eta: 0:07:25 lr: 0.000714 loss: 3.5764 (3.4960) grad_norm: 1.4050 (1.2797) time: 0.6352 [2021-03-26 22:55:28 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 560/1251] eta: 0:07:19 lr: 0.000714 loss: 3.5669 (3.4957) grad_norm: 1.3358 (1.2803) time: 0.6393 [2021-03-26 22:55:35 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 570/1251] eta: 0:07:12 lr: 0.000714 loss: 3.7089 (3.5015) grad_norm: 1.2392 (1.2806) time: 0.6293 [2021-03-26 22:55:41 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 580/1251] eta: 0:07:06 lr: 0.000714 loss: 3.7112 (3.5010) grad_norm: 1.1928 (1.2794) time: 0.6244 [2021-03-26 22:55:47 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 590/1251] eta: 0:06:59 lr: 0.000714 loss: 3.5319 (3.4977) grad_norm: 1.2445 (1.2802) time: 0.6336 [2021-03-26 22:55:54 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 600/1251] eta: 0:06:53 lr: 0.000714 loss: 3.5768 (3.4991) grad_norm: 1.2790 (1.2797) time: 0.6382 [2021-03-26 22:56:00 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 610/1251] eta: 0:06:47 lr: 0.000713 loss: 3.6901 (3.5031) grad_norm: 1.2003 (1.2786) time: 0.6379 [2021-03-26 22:56:06 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 620/1251] eta: 0:06:40 lr: 0.000713 loss: 3.6419 (3.5034) grad_norm: 1.2729 (1.2781) time: 0.6300 [2021-03-26 22:56:12 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 630/1251] eta: 0:06:34 lr: 0.000713 loss: 3.3796 (3.4980) grad_norm: 1.2749 (1.2776) time: 0.6228 [2021-03-26 22:56:19 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 640/1251] eta: 0:06:27 lr: 0.000713 loss: 3.3796 (3.4988) grad_norm: 1.2533 (1.2788) time: 0.6314 [2021-03-26 22:56:25 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 650/1251] eta: 0:06:21 lr: 0.000713 loss: 3.7208 (3.5019) grad_norm: 1.2533 (1.2788) time: 0.6309 [2021-03-26 22:56:31 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 660/1251] eta: 0:06:15 lr: 0.000713 loss: 3.7676 (3.5050) grad_norm: 1.2702 (1.2788) time: 0.6216 [2021-03-26 22:56:37 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 670/1251] eta: 0:06:08 lr: 0.000713 loss: 3.7457 (3.5071) grad_norm: 1.2261 (1.2781) time: 0.6215 [2021-03-26 22:56:44 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 680/1251] eta: 0:06:02 lr: 0.000713 loss: 3.6395 (3.5025) grad_norm: 1.2234 (1.2787) time: 0.6282 [2021-03-26 22:56:50 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 690/1251] eta: 0:05:55 lr: 0.000713 loss: 3.3081 (3.4983) grad_norm: 1.2061 (1.2779) time: 0.6282 [2021-03-26 22:56:56 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 700/1251] eta: 0:05:49 lr: 0.000713 loss: 3.4907 (3.4977) grad_norm: 1.1850 (1.2779) time: 0.6254 [2021-03-26 22:57:03 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 710/1251] eta: 0:05:43 lr: 0.000713 loss: 3.6447 (3.4972) grad_norm: 1.2885 (1.2790) time: 0.6309 [2021-03-26 22:57:09 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 720/1251] eta: 0:05:36 lr: 0.000713 loss: 3.4853 (3.4965) grad_norm: 1.3262 (1.2796) time: 0.6355 [2021-03-26 22:57:15 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 730/1251] eta: 0:05:30 lr: 0.000713 loss: 3.3921 (3.4962) grad_norm: 1.2122 (1.2788) time: 0.6335 [2021-03-26 22:57:22 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 740/1251] eta: 0:05:23 lr: 0.000713 loss: 3.5729 (3.4978) grad_norm: 1.2122 (1.2796) time: 0.6297 [2021-03-26 22:57:28 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 750/1251] eta: 0:05:17 lr: 0.000713 loss: 3.2616 (3.4936) grad_norm: 1.1523 (1.2784) time: 0.6349 [2021-03-26 22:57:34 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 760/1251] eta: 0:05:11 lr: 0.000713 loss: 3.1363 (3.4932) grad_norm: 1.1523 (1.2781) time: 0.6364 [2021-03-26 22:57:41 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 770/1251] eta: 0:05:04 lr: 0.000713 loss: 3.4741 (3.4918) grad_norm: 1.2108 (1.2775) time: 0.6280 [2021-03-26 22:57:47 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 780/1251] eta: 0:04:58 lr: 0.000713 loss: 3.4689 (3.4905) grad_norm: 1.2108 (1.2770) time: 0.6236 [2021-03-26 22:57:53 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 790/1251] eta: 0:04:52 lr: 0.000713 loss: 3.5304 (3.4917) grad_norm: 1.2389 (1.2776) time: 0.6283 [2021-03-26 22:58:00 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 800/1251] eta: 0:04:45 lr: 0.000713 loss: 3.8601 (3.4965) grad_norm: 1.2673 (1.2769) time: 0.6369 [2021-03-26 22:58:06 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 810/1251] eta: 0:04:39 lr: 0.000713 loss: 3.8634 (3.4964) grad_norm: 1.1880 (1.2770) time: 0.6409 [2021-03-26 22:58:12 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 820/1251] eta: 0:04:33 lr: 0.000713 loss: 3.6226 (3.4972) grad_norm: 1.2396 (1.2767) time: 0.6344 [2021-03-26 22:58:19 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 830/1251] eta: 0:04:26 lr: 0.000713 loss: 3.6466 (3.4986) grad_norm: 1.2404 (1.2764) time: 0.6306 [2021-03-26 22:58:25 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 840/1251] eta: 0:04:20 lr: 0.000713 loss: 3.7782 (3.5014) grad_norm: 1.2966 (1.2779) time: 0.6353 [2021-03-26 22:58:31 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 850/1251] eta: 0:04:14 lr: 0.000713 loss: 3.8242 (3.5039) grad_norm: 1.3503 (1.2791) time: 0.6280 [2021-03-26 22:58:37 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 860/1251] eta: 0:04:07 lr: 0.000713 loss: 3.7682 (3.5053) grad_norm: 1.2931 (1.2790) time: 0.6222 [2021-03-26 22:58:44 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 870/1251] eta: 0:04:01 lr: 0.000712 loss: 3.5398 (3.5054) grad_norm: 1.2806 (1.2797) time: 0.6294 [2021-03-26 22:58:50 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 880/1251] eta: 0:03:55 lr: 0.000712 loss: 3.3741 (3.5047) grad_norm: 1.3332 (1.2804) time: 0.6365 [2021-03-26 22:58:56 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 890/1251] eta: 0:03:48 lr: 0.000712 loss: 3.4566 (3.5044) grad_norm: 1.2956 (1.2810) time: 0.6291 [2021-03-26 22:59:03 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 900/1251] eta: 0:03:42 lr: 0.000712 loss: 3.2713 (3.5002) grad_norm: 1.2853 (1.2814) time: 0.6232 [2021-03-26 22:59:09 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 910/1251] eta: 0:03:36 lr: 0.000712 loss: 3.4253 (3.5003) grad_norm: 1.2027 (1.2807) time: 0.6306 [2021-03-26 22:59:15 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 920/1251] eta: 0:03:29 lr: 0.000712 loss: 3.4812 (3.4980) grad_norm: 1.1909 (1.2805) time: 0.6374 [2021-03-26 22:59:22 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 930/1251] eta: 0:03:23 lr: 0.000712 loss: 3.2448 (3.4967) grad_norm: 1.2787 (1.2809) time: 0.6408 [2021-03-26 22:59:28 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 940/1251] eta: 0:03:17 lr: 0.000712 loss: 3.4952 (3.4979) grad_norm: 1.2918 (1.2816) time: 0.6359 [2021-03-26 22:59:34 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 950/1251] eta: 0:03:10 lr: 0.000712 loss: 3.6325 (3.4987) grad_norm: 1.2669 (1.2812) time: 0.6350 [2021-03-26 22:59:41 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 960/1251] eta: 0:03:04 lr: 0.000712 loss: 3.6135 (3.4960) grad_norm: 1.2656 (1.2815) time: 0.6307 [2021-03-26 22:59:47 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 970/1251] eta: 0:02:58 lr: 0.000712 loss: 3.3928 (3.4965) grad_norm: 1.2669 (1.2818) time: 0.6238 [2021-03-26 22:59:53 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 980/1251] eta: 0:02:51 lr: 0.000712 loss: 3.3731 (3.4949) grad_norm: 1.1971 (1.2811) time: 0.6253 [2021-03-26 22:59:59 swin_base_patch4_window7_224] INFO: Epoch: [108] [ 990/1251] eta: 0:02:45 lr: 0.000712 loss: 3.5617 (3.4975) grad_norm: 1.1971 (1.2827) time: 0.6232 [2021-03-26 23:00:06 swin_base_patch4_window7_224] INFO: Epoch: [108] [1000/1251] eta: 0:02:38 lr: 0.000712 loss: 3.6761 (3.4996) grad_norm: 1.4269 (1.2834) time: 0.6245 [2021-03-26 23:00:12 swin_base_patch4_window7_224] INFO: Epoch: [108] [1010/1251] eta: 0:02:32 lr: 0.000712 loss: 3.6110 (3.4991) grad_norm: 1.3718 (1.2841) time: 0.6278 [2021-03-26 23:00:18 swin_base_patch4_window7_224] INFO: Epoch: [108] [1020/1251] eta: 0:02:26 lr: 0.000712 loss: 3.5330 (3.5001) grad_norm: 1.2861 (1.2841) time: 0.6257 [2021-03-26 23:00:24 swin_base_patch4_window7_224] INFO: Epoch: [108] [1030/1251] eta: 0:02:19 lr: 0.000712 loss: 3.4673 (3.4990) grad_norm: 1.1373 (1.2830) time: 0.6213 [2021-03-26 23:00:31 swin_base_patch4_window7_224] INFO: Epoch: [108] [1040/1251] eta: 0:02:13 lr: 0.000712 loss: 3.2268 (3.4973) grad_norm: 1.1847 (1.2831) time: 0.6240 [2021-03-26 23:00:37 swin_base_patch4_window7_224] INFO: Epoch: [108] [1050/1251] eta: 0:02:07 lr: 0.000712 loss: 3.4724 (3.4968) grad_norm: 1.2108 (1.2822) time: 0.6353 [2021-03-26 23:00:43 swin_base_patch4_window7_224] INFO: Epoch: [108] [1060/1251] eta: 0:02:00 lr: 0.000712 loss: 3.0051 (3.4922) grad_norm: 1.1902 (1.2821) time: 0.6324 [2021-03-26 23:00:50 swin_base_patch4_window7_224] INFO: Epoch: [108] [1070/1251] eta: 0:01:54 lr: 0.000712 loss: 3.1928 (3.4932) grad_norm: 1.2137 (1.2818) time: 0.6278 [2021-03-26 23:00:56 swin_base_patch4_window7_224] INFO: Epoch: [108] [1080/1251] eta: 0:01:48 lr: 0.000712 loss: 3.6864 (3.4945) grad_norm: 1.2452 (1.2819) time: 0.6303 [2021-03-26 23:01:02 swin_base_patch4_window7_224] INFO: Epoch: [108] [1090/1251] eta: 0:01:41 lr: 0.000712 loss: 3.6983 (3.4951) grad_norm: 1.2167 (1.2814) time: 0.6275 [2021-03-26 23:01:08 swin_base_patch4_window7_224] INFO: Epoch: [108] [1100/1251] eta: 0:01:35 lr: 0.000712 loss: 3.6983 (3.4961) grad_norm: 1.2769 (1.2829) time: 0.6258 [2021-03-26 23:01:15 swin_base_patch4_window7_224] INFO: Epoch: [108] [1110/1251] eta: 0:01:29 lr: 0.000712 loss: 3.5085 (3.4957) grad_norm: 1.2795 (1.2827) time: 0.6223 [2021-03-26 23:01:21 swin_base_patch4_window7_224] INFO: Epoch: [108] [1120/1251] eta: 0:01:22 lr: 0.000712 loss: 3.5085 (3.4957) grad_norm: 1.1960 (1.2829) time: 0.6231 [2021-03-26 23:01:27 swin_base_patch4_window7_224] INFO: Epoch: [108] [1130/1251] eta: 0:01:16 lr: 0.000712 loss: 3.3949 (3.4920) grad_norm: 1.1875 (1.2821) time: 0.6254 [2021-03-26 23:01:33 swin_base_patch4_window7_224] INFO: Epoch: [108] [1140/1251] eta: 0:01:10 lr: 0.000711 loss: 3.3428 (3.4918) grad_norm: 1.1868 (1.2823) time: 0.6242 [2021-03-26 23:01:40 swin_base_patch4_window7_224] INFO: Epoch: [108] [1150/1251] eta: 0:01:03 lr: 0.000711 loss: 3.6528 (3.4936) grad_norm: 1.2108 (1.2822) time: 0.6223 [2021-03-26 23:01:46 swin_base_patch4_window7_224] INFO: Epoch: [108] [1160/1251] eta: 0:00:57 lr: 0.000711 loss: 3.8029 (3.4960) grad_norm: 1.2463 (1.2826) time: 0.6219 [2021-03-26 23:01:52 swin_base_patch4_window7_224] INFO: Epoch: [108] [1170/1251] eta: 0:00:51 lr: 0.000711 loss: 3.7647 (3.4970) grad_norm: 1.2272 (1.2820) time: 0.6296 [2021-03-26 23:01:59 swin_base_patch4_window7_224] INFO: Epoch: [108] [1180/1251] eta: 0:00:44 lr: 0.000711 loss: 3.6369 (3.4979) grad_norm: 1.2593 (1.2820) time: 0.6341 [2021-03-26 23:02:05 swin_base_patch4_window7_224] INFO: Epoch: [108] [1190/1251] eta: 0:00:38 lr: 0.000711 loss: 3.6369 (3.4989) grad_norm: 1.3143 (1.2823) time: 0.6377 [2021-03-26 23:02:11 swin_base_patch4_window7_224] INFO: Epoch: [108] [1200/1251] eta: 0:00:32 lr: 0.000711 loss: 3.6182 (3.4994) grad_norm: 1.3410 (1.2837) time: 0.6380 [2021-03-26 23:02:18 swin_base_patch4_window7_224] INFO: Epoch: [108] [1210/1251] eta: 0:00:25 lr: 0.000711 loss: 3.4702 (3.4975) grad_norm: 1.3593 (1.2843) time: 0.6307 [2021-03-26 23:02:24 swin_base_patch4_window7_224] INFO: Epoch: [108] [1220/1251] eta: 0:00:19 lr: 0.000711 loss: 3.4664 (3.4981) grad_norm: 1.2417 (1.2839) time: 0.6303 [2021-03-26 23:02:30 swin_base_patch4_window7_224] INFO: Epoch: [108] [1230/1251] eta: 0:00:13 lr: 0.000711 loss: 3.7171 (3.4997) grad_norm: 1.2144 (1.2834) time: 0.6306 [2021-03-26 23:02:36 swin_base_patch4_window7_224] INFO: Epoch: [108] [1240/1251] eta: 0:00:06 lr: 0.000711 loss: 3.5741 (3.4990) grad_norm: 1.2034 (1.2827) time: 0.6228 [2021-03-26 23:02:43 swin_base_patch4_window7_224] INFO: Epoch: [108] [1250/1251] eta: 0:00:00 lr: 0.000711 loss: 3.6235 (3.5020) grad_norm: 1.1554 (1.2816) time: 0.6206 [2021-03-26 23:02:49 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 1.2121 (1.2121) acc1: 78.1250 (78.1250) acc5: 89.0625 (89.0625) [2021-03-26 23:02:52 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 1.0077 (1.0309) acc1: 76.5625 (75.7102) acc5: 93.7500 (94.3182) [2021-03-26 23:02:55 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9672 (0.9728) acc1: 76.5625 (77.5298) acc5: 95.3125 (94.9405) [2021-03-26 23:02:57 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8862 (0.9678) acc1: 78.1250 (78.0242) acc5: 95.3125 (94.3548) [2021-03-26 23:02:58 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9861 (1.0078) acc1: 76.5625 (76.7530) acc5: 93.7500 (93.8262) [2021-03-26 23:02:59 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9861 (1.0020) acc1: 76.5625 (77.0240) acc5: 93.7500 (93.8560) [2021-03-26 23:03:05 swin_base_patch4_window7_224] INFO: * Acc@1 77.186 Acc@5 93.930 loss 0.980 [2021-03-26 23:03:05 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.2% [2021-03-26 23:03:05 swin_base_patch4_window7_224] INFO: Max accuracy: 77.19% [2021-03-26 23:03:10 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 0/1251] eta: 1:32:32 lr: 0.000711 loss: 3.4185 (3.4185) grad_norm: 1.1819 (1.1819) time: 4.4386 [2021-03-26 23:03:16 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 10/1251] eta: 0:20:07 lr: 0.000711 loss: 3.1623 (3.3684) grad_norm: 1.2367 (1.2309) time: 0.9727 [2021-03-26 23:03:22 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 20/1251] eta: 0:16:37 lr: 0.000711 loss: 3.1319 (3.3915) grad_norm: 1.2388 (1.2677) time: 0.6288 [2021-03-26 23:03:28 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 30/1251] eta: 0:15:14 lr: 0.000711 loss: 3.4653 (3.3538) grad_norm: 1.2947 (1.2981) time: 0.6260 [2021-03-26 23:03:35 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 40/1251] eta: 0:14:30 lr: 0.000711 loss: 3.5596 (3.3911) grad_norm: 1.2813 (1.2730) time: 0.6221 [2021-03-26 23:03:41 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 50/1251] eta: 0:14:03 lr: 0.000711 loss: 3.6678 (3.4315) grad_norm: 1.2350 (1.2673) time: 0.6308 [2021-03-26 23:03:47 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 60/1251] eta: 0:13:39 lr: 0.000711 loss: 3.7145 (3.4919) grad_norm: 1.2480 (1.2639) time: 0.6270 [2021-03-26 23:03:54 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 70/1251] eta: 0:13:26 lr: 0.000711 loss: 3.6922 (3.4659) grad_norm: 1.2138 (1.2601) time: 0.6339 [2021-03-26 23:04:00 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 80/1251] eta: 0:13:11 lr: 0.000711 loss: 3.5249 (3.4450) grad_norm: 1.2245 (1.2638) time: 0.6366 [2021-03-26 23:04:06 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 90/1251] eta: 0:12:57 lr: 0.000711 loss: 3.3746 (3.4219) grad_norm: 1.2855 (1.2627) time: 0.6218 [2021-03-26 23:04:12 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 100/1251] eta: 0:12:46 lr: 0.000711 loss: 3.4531 (3.4139) grad_norm: 1.2034 (1.2613) time: 0.6255 [2021-03-26 23:04:19 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 110/1251] eta: 0:12:36 lr: 0.000711 loss: 3.5024 (3.4003) grad_norm: 1.1768 (1.2612) time: 0.6322 [2021-03-26 23:04:25 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 120/1251] eta: 0:12:27 lr: 0.000711 loss: 3.5723 (3.4171) grad_norm: 1.2308 (1.2599) time: 0.6384 [2021-03-26 23:04:32 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 130/1251] eta: 0:12:18 lr: 0.000711 loss: 3.7147 (3.4087) grad_norm: 1.2379 (1.2604) time: 0.6367 [2021-03-26 23:04:38 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 140/1251] eta: 0:12:11 lr: 0.000711 loss: 3.1075 (3.3918) grad_norm: 1.2364 (1.2625) time: 0.6386 [2021-03-26 23:04:44 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 150/1251] eta: 0:12:01 lr: 0.000710 loss: 3.2586 (3.3951) grad_norm: 1.2690 (inf) time: 0.6319 [2021-03-26 23:04:50 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 160/1251] eta: 0:11:53 lr: 0.000710 loss: 3.2586 (3.3762) grad_norm: 1.3011 (inf) time: 0.6231 [2021-03-26 23:04:57 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 170/1251] eta: 0:11:44 lr: 0.000710 loss: 3.5838 (3.3894) grad_norm: 1.3011 (inf) time: 0.6233 [2021-03-26 23:05:03 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 180/1251] eta: 0:11:36 lr: 0.000710 loss: 3.5838 (3.3907) grad_norm: 1.2772 (inf) time: 0.6216 [2021-03-26 23:05:09 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 190/1251] eta: 0:11:28 lr: 0.000710 loss: 3.2435 (3.3885) grad_norm: 1.2593 (inf) time: 0.6272 [2021-03-26 23:05:15 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 200/1251] eta: 0:11:20 lr: 0.000710 loss: 3.5693 (3.3985) grad_norm: 1.2787 (inf) time: 0.6250 [2021-03-26 23:05:22 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 210/1251] eta: 0:11:13 lr: 0.000710 loss: 3.7952 (3.4223) grad_norm: 1.2974 (inf) time: 0.6223 [2021-03-26 23:05:28 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 220/1251] eta: 0:11:05 lr: 0.000710 loss: 3.8322 (3.4389) grad_norm: 1.2681 (inf) time: 0.6245 [2021-03-26 23:05:34 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 230/1251] eta: 0:10:57 lr: 0.000710 loss: 3.8311 (3.4414) grad_norm: 1.2831 (inf) time: 0.6221 [2021-03-26 23:05:40 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 240/1251] eta: 0:10:50 lr: 0.000710 loss: 3.5942 (3.4416) grad_norm: 1.2140 (inf) time: 0.6238 [2021-03-26 23:05:47 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 250/1251] eta: 0:10:43 lr: 0.000710 loss: 3.2793 (3.4354) grad_norm: 1.2268 (inf) time: 0.6257 [2021-03-26 23:05:53 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 260/1251] eta: 0:10:37 lr: 0.000710 loss: 3.2924 (3.4333) grad_norm: 1.2520 (inf) time: 0.6346 [2021-03-26 23:05:59 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 270/1251] eta: 0:10:30 lr: 0.000710 loss: 3.2924 (3.4245) grad_norm: 1.2520 (inf) time: 0.6338 [2021-03-26 23:06:06 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 280/1251] eta: 0:10:23 lr: 0.000710 loss: 3.3332 (3.4296) grad_norm: 1.2535 (inf) time: 0.6269 [2021-03-26 23:06:12 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 290/1251] eta: 0:10:16 lr: 0.000710 loss: 3.5068 (3.4341) grad_norm: 1.1986 (inf) time: 0.6320 [2021-03-26 23:06:18 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 300/1251] eta: 0:10:09 lr: 0.000710 loss: 3.3823 (3.4226) grad_norm: 1.1934 (inf) time: 0.6295 [2021-03-26 23:06:24 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 310/1251] eta: 0:10:02 lr: 0.000710 loss: 3.1308 (3.4228) grad_norm: 1.2028 (inf) time: 0.6286 [2021-03-26 23:06:31 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 320/1251] eta: 0:09:56 lr: 0.000710 loss: 3.4588 (3.4194) grad_norm: 1.2547 (inf) time: 0.6337 [2021-03-26 23:06:37 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 330/1251] eta: 0:09:49 lr: 0.000710 loss: 3.4688 (3.4192) grad_norm: 1.2069 (inf) time: 0.6318 [2021-03-26 23:06:43 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 340/1251] eta: 0:09:42 lr: 0.000710 loss: 3.6434 (3.4259) grad_norm: 1.1969 (inf) time: 0.6276 [2021-03-26 23:06:50 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 350/1251] eta: 0:09:36 lr: 0.000710 loss: 3.6160 (3.4218) grad_norm: 1.2460 (inf) time: 0.6248 [2021-03-26 23:06:56 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 360/1251] eta: 0:09:29 lr: 0.000710 loss: 3.6094 (3.4256) grad_norm: 1.2435 (inf) time: 0.6200 [2021-03-26 23:07:02 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 370/1251] eta: 0:09:22 lr: 0.000710 loss: 3.6271 (3.4298) grad_norm: 1.2183 (inf) time: 0.6201 [2021-03-26 23:07:08 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 380/1251] eta: 0:09:15 lr: 0.000710 loss: 3.5198 (3.4309) grad_norm: 1.2171 (inf) time: 0.6206 [2021-03-26 23:07:15 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 390/1251] eta: 0:09:08 lr: 0.000710 loss: 3.3894 (3.4297) grad_norm: 1.2743 (inf) time: 0.6253 [2021-03-26 23:07:21 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 400/1251] eta: 0:09:02 lr: 0.000710 loss: 3.3473 (3.4309) grad_norm: 1.2782 (inf) time: 0.6337 [2021-03-26 23:07:27 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 410/1251] eta: 0:08:55 lr: 0.000710 loss: 3.5579 (3.4339) grad_norm: 1.2724 (inf) time: 0.6283 [2021-03-26 23:07:33 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 420/1251] eta: 0:08:49 lr: 0.000709 loss: 3.6594 (3.4354) grad_norm: 1.2751 (inf) time: 0.6245 [2021-03-26 23:07:40 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 430/1251] eta: 0:08:42 lr: 0.000709 loss: 3.6190 (3.4313) grad_norm: 1.2999 (inf) time: 0.6277 [2021-03-26 23:07:46 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 440/1251] eta: 0:08:36 lr: 0.000709 loss: 3.3855 (3.4293) grad_norm: 1.2975 (inf) time: 0.6281 [2021-03-26 23:07:52 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 450/1251] eta: 0:08:29 lr: 0.000709 loss: 3.4557 (3.4310) grad_norm: 1.2684 (inf) time: 0.6278 [2021-03-26 23:07:59 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 460/1251] eta: 0:08:23 lr: 0.000709 loss: 3.5534 (3.4291) grad_norm: 1.2455 (inf) time: 0.6294 [2021-03-26 23:08:05 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 470/1251] eta: 0:08:16 lr: 0.000709 loss: 3.5053 (3.4293) grad_norm: 1.1921 (inf) time: 0.6314 [2021-03-26 23:08:11 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 480/1251] eta: 0:08:10 lr: 0.000709 loss: 3.4806 (3.4329) grad_norm: 1.1654 (inf) time: 0.6313 [2021-03-26 23:08:17 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 490/1251] eta: 0:08:03 lr: 0.000709 loss: 3.4485 (3.4334) grad_norm: 1.1712 (inf) time: 0.6290 [2021-03-26 23:08:24 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 500/1251] eta: 0:07:57 lr: 0.000709 loss: 3.4376 (3.4366) grad_norm: 1.2299 (inf) time: 0.6296 [2021-03-26 23:08:30 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 510/1251] eta: 0:07:51 lr: 0.000709 loss: 3.7044 (3.4404) grad_norm: 1.2848 (inf) time: 0.6322 [2021-03-26 23:08:36 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 520/1251] eta: 0:07:44 lr: 0.000709 loss: 3.7044 (3.4446) grad_norm: 1.3550 (inf) time: 0.6338 [2021-03-26 23:08:43 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 530/1251] eta: 0:07:38 lr: 0.000709 loss: 3.5764 (3.4437) grad_norm: 1.3412 (inf) time: 0.6288 [2021-03-26 23:08:49 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 540/1251] eta: 0:07:31 lr: 0.000709 loss: 3.4178 (3.4426) grad_norm: 1.2254 (inf) time: 0.6255 [2021-03-26 23:08:55 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 550/1251] eta: 0:07:25 lr: 0.000709 loss: 3.4443 (3.4447) grad_norm: 1.2484 (inf) time: 0.6390 [2021-03-26 23:09:02 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 560/1251] eta: 0:07:19 lr: 0.000709 loss: 3.5418 (3.4435) grad_norm: 1.3474 (inf) time: 0.6383 [2021-03-26 23:09:08 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 570/1251] eta: 0:07:12 lr: 0.000709 loss: 3.3530 (3.4419) grad_norm: 1.2197 (inf) time: 0.6289 [2021-03-26 23:09:14 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 580/1251] eta: 0:07:06 lr: 0.000709 loss: 3.3810 (3.4433) grad_norm: 1.2173 (inf) time: 0.6309 [2021-03-26 23:09:21 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 590/1251] eta: 0:06:59 lr: 0.000709 loss: 3.5092 (3.4456) grad_norm: 1.2242 (inf) time: 0.6346 [2021-03-26 23:09:27 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 600/1251] eta: 0:06:53 lr: 0.000709 loss: 3.5074 (3.4437) grad_norm: 1.2796 (inf) time: 0.6302 [2021-03-26 23:09:33 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 610/1251] eta: 0:06:47 lr: 0.000709 loss: 3.5730 (3.4483) grad_norm: 1.3104 (inf) time: 0.6332 [2021-03-26 23:09:40 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 620/1251] eta: 0:06:40 lr: 0.000709 loss: 3.5913 (3.4501) grad_norm: 1.3104 (inf) time: 0.6346 [2021-03-26 23:09:46 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 630/1251] eta: 0:06:34 lr: 0.000709 loss: 3.5154 (3.4500) grad_norm: 1.2790 (inf) time: 0.6295 [2021-03-26 23:09:52 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 640/1251] eta: 0:06:27 lr: 0.000709 loss: 3.4564 (3.4501) grad_norm: 1.1753 (inf) time: 0.6246 [2021-03-26 23:09:58 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 650/1251] eta: 0:06:21 lr: 0.000709 loss: 3.6045 (3.4529) grad_norm: 1.2354 (inf) time: 0.6217 [2021-03-26 23:10:05 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 660/1251] eta: 0:06:15 lr: 0.000709 loss: 3.6045 (3.4504) grad_norm: 1.2860 (inf) time: 0.6290 [2021-03-26 23:10:11 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 670/1251] eta: 0:06:08 lr: 0.000709 loss: 3.7579 (3.4576) grad_norm: 1.2860 (inf) time: 0.6314 [2021-03-26 23:10:17 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 680/1251] eta: 0:06:02 lr: 0.000708 loss: 3.7118 (3.4556) grad_norm: 1.2536 (inf) time: 0.6298 [2021-03-26 23:10:24 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 690/1251] eta: 0:05:55 lr: 0.000708 loss: 3.3952 (3.4589) grad_norm: 1.2536 (inf) time: 0.6268 [2021-03-26 23:10:30 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 700/1251] eta: 0:05:49 lr: 0.000708 loss: 3.6133 (3.4603) grad_norm: 1.2704 (inf) time: 0.6338 [2021-03-26 23:10:36 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 710/1251] eta: 0:05:43 lr: 0.000708 loss: 3.3849 (3.4604) grad_norm: 1.2537 (inf) time: 0.6360 [2021-03-26 23:10:43 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 720/1251] eta: 0:05:36 lr: 0.000708 loss: 3.3849 (3.4588) grad_norm: 1.2537 (inf) time: 0.6286 [2021-03-26 23:10:49 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 730/1251] eta: 0:05:30 lr: 0.000708 loss: 3.4758 (3.4592) grad_norm: 1.2933 (inf) time: 0.6246 [2021-03-26 23:10:55 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 740/1251] eta: 0:05:24 lr: 0.000708 loss: 3.4949 (3.4574) grad_norm: 1.1866 (inf) time: 0.6281 [2021-03-26 23:11:02 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 750/1251] eta: 0:05:17 lr: 0.000708 loss: 3.6694 (3.4603) grad_norm: 1.2109 (inf) time: 0.6370 [2021-03-26 23:11:08 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 760/1251] eta: 0:05:11 lr: 0.000708 loss: 3.6616 (3.4579) grad_norm: 1.2313 (inf) time: 0.6359 [2021-03-26 23:11:14 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 770/1251] eta: 0:05:05 lr: 0.000708 loss: 3.4296 (3.4582) grad_norm: 1.2313 (inf) time: 0.6327 [2021-03-26 23:11:21 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 780/1251] eta: 0:04:58 lr: 0.000708 loss: 3.4296 (3.4566) grad_norm: 1.2874 (inf) time: 0.6315 [2021-03-26 23:11:27 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 790/1251] eta: 0:04:52 lr: 0.000708 loss: 3.4051 (3.4557) grad_norm: 1.2717 (inf) time: 0.6292 [2021-03-26 23:11:33 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 800/1251] eta: 0:04:46 lr: 0.000708 loss: 3.5638 (3.4574) grad_norm: 1.2106 (inf) time: 0.6397 [2021-03-26 23:11:40 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 810/1251] eta: 0:04:39 lr: 0.000708 loss: 3.7069 (3.4598) grad_norm: 1.2159 (inf) time: 0.6411 [2021-03-26 23:11:46 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 820/1251] eta: 0:04:33 lr: 0.000708 loss: 3.3475 (3.4590) grad_norm: 1.3029 (inf) time: 0.6301 [2021-03-26 23:11:52 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 830/1251] eta: 0:04:26 lr: 0.000708 loss: 3.3475 (3.4573) grad_norm: 1.3029 (inf) time: 0.6288 [2021-03-26 23:11:59 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 840/1251] eta: 0:04:20 lr: 0.000708 loss: 3.4869 (3.4560) grad_norm: 1.2018 (inf) time: 0.6324 [2021-03-26 23:12:05 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 850/1251] eta: 0:04:14 lr: 0.000708 loss: 3.3157 (3.4534) grad_norm: 1.2152 (inf) time: 0.6321 [2021-03-26 23:12:11 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 860/1251] eta: 0:04:07 lr: 0.000708 loss: 3.3811 (3.4547) grad_norm: 1.1770 (inf) time: 0.6231 [2021-03-26 23:12:18 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 870/1251] eta: 0:04:01 lr: 0.000708 loss: 3.7116 (3.4548) grad_norm: 1.2464 (inf) time: 0.6328 [2021-03-26 23:12:24 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 880/1251] eta: 0:03:55 lr: 0.000708 loss: 3.6053 (3.4549) grad_norm: 1.2562 (inf) time: 0.6374 [2021-03-26 23:12:30 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 890/1251] eta: 0:03:48 lr: 0.000708 loss: 3.4308 (3.4561) grad_norm: 1.2992 (inf) time: 0.6283 [2021-03-26 23:12:36 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 900/1251] eta: 0:03:42 lr: 0.000708 loss: 3.3529 (3.4550) grad_norm: 1.3171 (inf) time: 0.6279 [2021-03-26 23:12:43 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 910/1251] eta: 0:03:36 lr: 0.000708 loss: 3.5891 (3.4570) grad_norm: 1.2326 (inf) time: 0.6267 [2021-03-26 23:12:49 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 920/1251] eta: 0:03:29 lr: 0.000708 loss: 3.7619 (3.4596) grad_norm: 1.2550 (inf) time: 0.6290 [2021-03-26 23:12:55 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 930/1251] eta: 0:03:23 lr: 0.000708 loss: 3.8482 (3.4631) grad_norm: 1.2550 (inf) time: 0.6290 [2021-03-26 23:13:01 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 940/1251] eta: 0:03:17 lr: 0.000708 loss: 3.6386 (3.4639) grad_norm: 1.2639 (inf) time: 0.6270 [2021-03-26 23:13:08 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 950/1251] eta: 0:03:10 lr: 0.000707 loss: 3.5377 (3.4610) grad_norm: 1.2363 (inf) time: 0.6258 [2021-03-26 23:13:14 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 960/1251] eta: 0:03:04 lr: 0.000707 loss: 3.4367 (3.4590) grad_norm: 1.2851 (inf) time: 0.6243 [2021-03-26 23:13:20 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 970/1251] eta: 0:02:57 lr: 0.000707 loss: 3.4717 (3.4579) grad_norm: 1.3047 (inf) time: 0.6237 [2021-03-26 23:13:26 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 980/1251] eta: 0:02:51 lr: 0.000707 loss: 3.4742 (3.4587) grad_norm: 1.3121 (inf) time: 0.6246 [2021-03-26 23:13:33 swin_base_patch4_window7_224] INFO: Epoch: [109] [ 990/1251] eta: 0:02:45 lr: 0.000707 loss: 3.6883 (3.4605) grad_norm: 1.1993 (inf) time: 0.6260 [2021-03-26 23:13:39 swin_base_patch4_window7_224] INFO: Epoch: [109] [1000/1251] eta: 0:02:38 lr: 0.000707 loss: 3.5757 (3.4595) grad_norm: 1.1803 (inf) time: 0.6262 [2021-03-26 23:13:45 swin_base_patch4_window7_224] INFO: Epoch: [109] [1010/1251] eta: 0:02:32 lr: 0.000707 loss: 3.3564 (3.4578) grad_norm: 1.1722 (inf) time: 0.6282 [2021-03-26 23:13:52 swin_base_patch4_window7_224] INFO: Epoch: [109] [1020/1251] eta: 0:02:26 lr: 0.000707 loss: 3.3568 (3.4568) grad_norm: 1.1618 (inf) time: 0.6336 [2021-03-26 23:13:58 swin_base_patch4_window7_224] INFO: Epoch: [109] [1030/1251] eta: 0:02:19 lr: 0.000707 loss: 3.3568 (3.4540) grad_norm: 1.1879 (inf) time: 0.6292 [2021-03-26 23:14:04 swin_base_patch4_window7_224] INFO: Epoch: [109] [1040/1251] eta: 0:02:13 lr: 0.000707 loss: 3.4372 (3.4543) grad_norm: 1.1883 (inf) time: 0.6301 [2021-03-26 23:14:11 swin_base_patch4_window7_224] INFO: Epoch: [109] [1050/1251] eta: 0:02:07 lr: 0.000707 loss: 3.4372 (3.4540) grad_norm: 1.1886 (inf) time: 0.6333 [2021-03-26 23:14:17 swin_base_patch4_window7_224] INFO: Epoch: [109] [1060/1251] eta: 0:02:00 lr: 0.000707 loss: 3.3868 (3.4524) grad_norm: 1.2230 (inf) time: 0.6321 [2021-03-26 23:14:23 swin_base_patch4_window7_224] INFO: Epoch: [109] [1070/1251] eta: 0:01:54 lr: 0.000707 loss: 3.5063 (3.4539) grad_norm: 1.3636 (inf) time: 0.6375 [2021-03-26 23:14:30 swin_base_patch4_window7_224] INFO: Epoch: [109] [1080/1251] eta: 0:01:48 lr: 0.000707 loss: 3.6199 (3.4539) grad_norm: 1.3636 (inf) time: 0.6340 [2021-03-26 23:14:36 swin_base_patch4_window7_224] INFO: Epoch: [109] [1090/1251] eta: 0:01:41 lr: 0.000707 loss: 3.5453 (3.4551) grad_norm: 1.2543 (inf) time: 0.6262 [2021-03-26 23:14:42 swin_base_patch4_window7_224] INFO: Epoch: [109] [1100/1251] eta: 0:01:35 lr: 0.000707 loss: 3.5453 (3.4541) grad_norm: 1.2504 (inf) time: 0.6267 [2021-03-26 23:14:48 swin_base_patch4_window7_224] INFO: Epoch: [109] [1110/1251] eta: 0:01:29 lr: 0.000707 loss: 3.6967 (3.4562) grad_norm: 1.2504 (inf) time: 0.6250 [2021-03-26 23:14:55 swin_base_patch4_window7_224] INFO: Epoch: [109] [1120/1251] eta: 0:01:22 lr: 0.000707 loss: 3.7258 (3.4566) grad_norm: 1.2101 (inf) time: 0.6243 [2021-03-26 23:15:01 swin_base_patch4_window7_224] INFO: Epoch: [109] [1130/1251] eta: 0:01:16 lr: 0.000707 loss: 3.7258 (3.4573) grad_norm: 1.2310 (inf) time: 0.6255 [2021-03-26 23:15:07 swin_base_patch4_window7_224] INFO: Epoch: [109] [1140/1251] eta: 0:01:10 lr: 0.000707 loss: 3.6102 (3.4562) grad_norm: 1.3040 (inf) time: 0.6238 [2021-03-26 23:15:13 swin_base_patch4_window7_224] INFO: Epoch: [109] [1150/1251] eta: 0:01:03 lr: 0.000707 loss: 3.4238 (3.4559) grad_norm: 1.3235 (inf) time: 0.6271 [2021-03-26 23:15:20 swin_base_patch4_window7_224] INFO: Epoch: [109] [1160/1251] eta: 0:00:57 lr: 0.000707 loss: 3.6403 (3.4563) grad_norm: 1.2038 (inf) time: 0.6271 [2021-03-26 23:15:26 swin_base_patch4_window7_224] INFO: Epoch: [109] [1170/1251] eta: 0:00:51 lr: 0.000707 loss: 3.4656 (3.4551) grad_norm: 1.1846 (inf) time: 0.6316 [2021-03-26 23:15:32 swin_base_patch4_window7_224] INFO: Epoch: [109] [1180/1251] eta: 0:00:44 lr: 0.000707 loss: 3.3341 (3.4552) grad_norm: 1.1949 (inf) time: 0.6395 [2021-03-26 23:15:39 swin_base_patch4_window7_224] INFO: Epoch: [109] [1190/1251] eta: 0:00:38 lr: 0.000707 loss: 3.3573 (3.4533) grad_norm: 1.2133 (inf) time: 0.6355 [2021-03-26 23:15:45 swin_base_patch4_window7_224] INFO: Epoch: [109] [1200/1251] eta: 0:00:32 lr: 0.000707 loss: 3.3721 (3.4541) grad_norm: 1.1890 (inf) time: 0.6335 [2021-03-26 23:15:51 swin_base_patch4_window7_224] INFO: Epoch: [109] [1210/1251] eta: 0:00:25 lr: 0.000706 loss: 3.4410 (3.4544) grad_norm: 1.1594 (inf) time: 0.6342 [2021-03-26 23:15:58 swin_base_patch4_window7_224] INFO: Epoch: [109] [1220/1251] eta: 0:00:19 lr: 0.000706 loss: 3.3327 (3.4537) grad_norm: 1.1899 (inf) time: 0.6272 [2021-03-26 23:16:04 swin_base_patch4_window7_224] INFO: Epoch: [109] [1230/1251] eta: 0:00:13 lr: 0.000706 loss: 3.2656 (3.4522) grad_norm: 1.2052 (inf) time: 0.6274 [2021-03-26 23:16:10 swin_base_patch4_window7_224] INFO: Epoch: [109] [1240/1251] eta: 0:00:06 lr: 0.000706 loss: 3.6093 (3.4538) grad_norm: 1.2052 (inf) time: 0.6306 [2021-03-26 23:16:17 swin_base_patch4_window7_224] INFO: Epoch: [109] [1250/1251] eta: 0:00:00 lr: 0.000706 loss: 3.6162 (3.4540) grad_norm: 1.2118 (inf) time: 0.6289 [2021-03-26 23:16:23 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:57 loss: 1.2450 (1.2450) acc1: 73.4375 (73.4375) acc5: 90.6250 (90.6250) [2021-03-26 23:16:25 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0207 (1.0080) acc1: 78.1250 (76.9886) acc5: 95.3125 (95.0284) [2021-03-26 23:16:28 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9484 (0.9877) acc1: 79.6875 (77.8274) acc5: 93.7500 (94.2708) [2021-03-26 23:16:30 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9631 (1.0129) acc1: 78.1250 (77.2681) acc5: 92.1875 (93.8004) [2021-03-26 23:16:32 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9779 (1.0072) acc1: 78.1250 (77.3247) acc5: 92.1875 (93.7881) [2021-03-26 23:16:33 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9779 (1.0127) acc1: 76.5625 (77.0880) acc5: 93.7500 (93.7600) [2021-03-26 23:16:38 swin_base_patch4_window7_224] INFO: * Acc@1 77.032 Acc@5 93.812 loss 1.001 [2021-03-26 23:16:38 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.0% [2021-03-26 23:16:38 swin_base_patch4_window7_224] INFO: Max accuracy: 77.19% [2021-03-26 23:16:42 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 0/1251] eta: 1:32:33 lr: 0.000706 loss: 3.9340 (3.9340) grad_norm: 1.2894 (1.2894) time: 4.4390 [2021-03-26 23:16:49 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 10/1251] eta: 0:20:14 lr: 0.000706 loss: 3.6138 (3.5184) grad_norm: 1.2300 (1.3147) time: 0.9785 [2021-03-26 23:16:55 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 20/1251] eta: 0:16:38 lr: 0.000706 loss: 3.6138 (3.5229) grad_norm: 1.2286 (1.2996) time: 0.6300 [2021-03-26 23:17:01 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 30/1251] eta: 0:15:17 lr: 0.000706 loss: 3.5994 (3.5227) grad_norm: 1.3141 (1.3154) time: 0.6270 [2021-03-26 23:17:08 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 40/1251] eta: 0:14:38 lr: 0.000706 loss: 3.5352 (3.4718) grad_norm: 1.3141 (1.3212) time: 0.6345 [2021-03-26 23:17:14 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 50/1251] eta: 0:14:08 lr: 0.000706 loss: 3.2786 (3.4804) grad_norm: 1.2909 (1.3183) time: 0.6361 [2021-03-26 23:17:20 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 60/1251] eta: 0:13:45 lr: 0.000706 loss: 3.4263 (3.4984) grad_norm: 1.2608 (1.3026) time: 0.6277 [2021-03-26 23:17:27 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 70/1251] eta: 0:13:29 lr: 0.000706 loss: 3.4020 (3.4715) grad_norm: 1.2285 (1.3017) time: 0.6331 [2021-03-26 23:17:33 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 80/1251] eta: 0:13:12 lr: 0.000706 loss: 3.4144 (3.4744) grad_norm: 1.2551 (1.3033) time: 0.6284 [2021-03-26 23:17:39 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 90/1251] eta: 0:13:01 lr: 0.000706 loss: 3.4882 (3.4622) grad_norm: 1.2131 (1.2953) time: 0.6303 [2021-03-26 23:17:46 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 100/1251] eta: 0:12:50 lr: 0.000706 loss: 3.4882 (3.4697) grad_norm: 1.3040 (1.3082) time: 0.6389 [2021-03-26 23:17:52 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 110/1251] eta: 0:12:40 lr: 0.000706 loss: 3.5491 (3.4643) grad_norm: 1.3098 (1.3087) time: 0.6325 [2021-03-26 23:17:58 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 120/1251] eta: 0:12:29 lr: 0.000706 loss: 3.5492 (3.4752) grad_norm: 1.2689 (1.3077) time: 0.6278 [2021-03-26 23:18:05 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 130/1251] eta: 0:12:19 lr: 0.000706 loss: 3.6854 (3.4894) grad_norm: 1.2968 (1.3091) time: 0.6255 [2021-03-26 23:18:11 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 140/1251] eta: 0:12:11 lr: 0.000706 loss: 3.7342 (3.5024) grad_norm: 1.2864 (1.3078) time: 0.6321 [2021-03-26 23:18:17 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 150/1251] eta: 0:12:02 lr: 0.000706 loss: 3.5593 (3.4805) grad_norm: 1.3219 (1.3168) time: 0.6332 [2021-03-26 23:18:23 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 160/1251] eta: 0:11:53 lr: 0.000706 loss: 3.4410 (3.4760) grad_norm: 1.4343 (1.3242) time: 0.6252 [2021-03-26 23:18:30 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 170/1251] eta: 0:11:45 lr: 0.000706 loss: 3.6202 (3.4739) grad_norm: 1.2699 (1.3192) time: 0.6246 [2021-03-26 23:18:36 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 180/1251] eta: 0:11:37 lr: 0.000706 loss: 3.6445 (3.4909) grad_norm: 1.2392 (1.3171) time: 0.6259 [2021-03-26 23:18:42 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 190/1251] eta: 0:11:29 lr: 0.000706 loss: 3.5283 (3.4795) grad_norm: 1.1891 (1.3083) time: 0.6274 [2021-03-26 23:18:48 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 200/1251] eta: 0:11:21 lr: 0.000706 loss: 3.3378 (3.4797) grad_norm: 1.1822 (1.3048) time: 0.6286 [2021-03-26 23:18:55 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 210/1251] eta: 0:11:14 lr: 0.000706 loss: 3.5258 (3.4868) grad_norm: 1.2144 (1.3041) time: 0.6264 [2021-03-26 23:19:01 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 220/1251] eta: 0:11:06 lr: 0.000706 loss: 3.5258 (3.4864) grad_norm: 1.2746 (1.3023) time: 0.6277 [2021-03-26 23:19:07 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 230/1251] eta: 0:11:00 lr: 0.000705 loss: 3.4195 (3.4802) grad_norm: 1.2920 (1.3030) time: 0.6353 [2021-03-26 23:19:14 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 240/1251] eta: 0:10:53 lr: 0.000705 loss: 3.3801 (3.4826) grad_norm: 1.1827 (1.2969) time: 0.6376 [2021-03-26 23:19:20 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 250/1251] eta: 0:10:46 lr: 0.000705 loss: 3.3819 (3.4713) grad_norm: 1.2100 (1.2954) time: 0.6309 [2021-03-26 23:19:26 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 260/1251] eta: 0:10:38 lr: 0.000705 loss: 3.4343 (3.4721) grad_norm: 1.2447 (1.2949) time: 0.6263 [2021-03-26 23:19:33 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 270/1251] eta: 0:10:31 lr: 0.000705 loss: 3.5219 (3.4727) grad_norm: 1.2391 (1.2930) time: 0.6284 [2021-03-26 23:19:39 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 280/1251] eta: 0:10:24 lr: 0.000705 loss: 3.5703 (3.4717) grad_norm: 1.3089 (1.2973) time: 0.6279 [2021-03-26 23:19:45 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 290/1251] eta: 0:10:17 lr: 0.000705 loss: 3.4999 (3.4732) grad_norm: 1.2169 (1.2964) time: 0.6265 [2021-03-26 23:19:52 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 300/1251] eta: 0:10:11 lr: 0.000705 loss: 3.4882 (3.4712) grad_norm: 1.2444 (1.2966) time: 0.6338 [2021-03-26 23:19:58 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 310/1251] eta: 0:10:04 lr: 0.000705 loss: 3.4987 (3.4701) grad_norm: 1.3143 (1.2955) time: 0.6286 [2021-03-26 23:20:04 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 320/1251] eta: 0:09:57 lr: 0.000705 loss: 3.4939 (3.4627) grad_norm: 1.2646 (1.2943) time: 0.6308 [2021-03-26 23:20:11 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 330/1251] eta: 0:09:51 lr: 0.000705 loss: 3.4103 (3.4646) grad_norm: 1.1886 (1.2904) time: 0.6431 [2021-03-26 23:20:17 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 340/1251] eta: 0:09:44 lr: 0.000705 loss: 3.5707 (3.4602) grad_norm: 1.1890 (1.2895) time: 0.6327 [2021-03-26 23:20:23 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 350/1251] eta: 0:09:37 lr: 0.000705 loss: 3.5001 (3.4578) grad_norm: 1.2356 (1.2887) time: 0.6268 [2021-03-26 23:20:29 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 360/1251] eta: 0:09:30 lr: 0.000705 loss: 3.4620 (3.4548) grad_norm: 1.2852 (1.2884) time: 0.6282 [2021-03-26 23:20:36 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 370/1251] eta: 0:09:24 lr: 0.000705 loss: 3.4620 (3.4533) grad_norm: 1.2049 (1.2850) time: 0.6249 [2021-03-26 23:20:42 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 380/1251] eta: 0:09:17 lr: 0.000705 loss: 3.4114 (3.4513) grad_norm: 1.2103 (1.2855) time: 0.6265 [2021-03-26 23:20:48 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 390/1251] eta: 0:09:10 lr: 0.000705 loss: 3.6895 (3.4616) grad_norm: 1.2265 (1.2838) time: 0.6284 [2021-03-26 23:20:54 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 400/1251] eta: 0:09:04 lr: 0.000705 loss: 3.8270 (3.4674) grad_norm: 1.2041 (1.2830) time: 0.6258 [2021-03-26 23:21:01 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 410/1251] eta: 0:08:57 lr: 0.000705 loss: 3.5536 (3.4669) grad_norm: 1.2953 (1.2861) time: 0.6229 [2021-03-26 23:21:07 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 420/1251] eta: 0:08:50 lr: 0.000705 loss: 3.5089 (3.4680) grad_norm: 1.3436 (1.2877) time: 0.6226 [2021-03-26 23:21:13 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 430/1251] eta: 0:08:43 lr: 0.000705 loss: 3.5915 (3.4713) grad_norm: 1.3259 (1.2875) time: 0.6216 [2021-03-26 23:21:19 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 440/1251] eta: 0:08:37 lr: 0.000705 loss: 3.4991 (3.4681) grad_norm: 1.2257 (1.2874) time: 0.6223 [2021-03-26 23:21:26 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 450/1251] eta: 0:08:30 lr: 0.000705 loss: 3.4238 (3.4647) grad_norm: 1.2254 (1.2867) time: 0.6260 [2021-03-26 23:21:32 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 460/1251] eta: 0:08:24 lr: 0.000705 loss: 3.5069 (3.4676) grad_norm: 1.1627 (1.2838) time: 0.6261 [2021-03-26 23:21:38 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 470/1251] eta: 0:08:17 lr: 0.000705 loss: 3.5504 (3.4649) grad_norm: 1.2034 (1.2844) time: 0.6260 [2021-03-26 23:21:44 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 480/1251] eta: 0:08:11 lr: 0.000705 loss: 3.5504 (3.4669) grad_norm: 1.3083 (1.2861) time: 0.6283 [2021-03-26 23:21:51 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 490/1251] eta: 0:08:04 lr: 0.000704 loss: 3.5982 (3.4664) grad_norm: 1.2683 (1.2864) time: 0.6242 [2021-03-26 23:21:57 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 500/1251] eta: 0:07:57 lr: 0.000704 loss: 3.6350 (3.4685) grad_norm: 1.2437 (1.2860) time: 0.6244 [2021-03-26 23:22:03 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 510/1251] eta: 0:07:51 lr: 0.000704 loss: 3.6350 (3.4703) grad_norm: 1.2499 (1.2859) time: 0.6298 [2021-03-26 23:22:10 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 520/1251] eta: 0:07:45 lr: 0.000704 loss: 3.5321 (3.4698) grad_norm: 1.2402 (1.2859) time: 0.6416 [2021-03-26 23:22:16 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 530/1251] eta: 0:07:38 lr: 0.000704 loss: 3.5530 (3.4740) grad_norm: 1.2607 (1.2858) time: 0.6389 [2021-03-26 23:22:22 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 540/1251] eta: 0:07:32 lr: 0.000704 loss: 3.5530 (3.4758) grad_norm: 1.2607 (1.2848) time: 0.6347 [2021-03-26 23:22:29 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 550/1251] eta: 0:07:26 lr: 0.000704 loss: 3.3934 (3.4749) grad_norm: 1.2621 (1.2865) time: 0.6472 [2021-03-26 23:22:36 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 560/1251] eta: 0:07:20 lr: 0.000704 loss: 3.3794 (3.4736) grad_norm: 1.3159 (1.2864) time: 0.6509 [2021-03-26 23:22:42 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 570/1251] eta: 0:07:13 lr: 0.000704 loss: 3.3794 (3.4724) grad_norm: 1.2799 (1.2874) time: 0.6375 [2021-03-26 23:22:48 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 580/1251] eta: 0:07:07 lr: 0.000704 loss: 3.3593 (3.4715) grad_norm: 1.3218 (1.2885) time: 0.6258 [2021-03-26 23:22:54 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 590/1251] eta: 0:07:00 lr: 0.000704 loss: 3.4666 (3.4705) grad_norm: 1.2925 (1.2893) time: 0.6246 [2021-03-26 23:23:00 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 600/1251] eta: 0:06:54 lr: 0.000704 loss: 3.4897 (3.4726) grad_norm: 1.2925 (1.2897) time: 0.6215 [2021-03-26 23:23:07 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 610/1251] eta: 0:06:47 lr: 0.000704 loss: 3.5399 (3.4726) grad_norm: 1.2072 (1.2887) time: 0.6224 [2021-03-26 23:23:13 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 620/1251] eta: 0:06:41 lr: 0.000704 loss: 3.6825 (3.4740) grad_norm: 1.2139 (1.2889) time: 0.6261 [2021-03-26 23:23:19 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 630/1251] eta: 0:06:34 lr: 0.000704 loss: 3.6238 (3.4765) grad_norm: 1.3419 (1.2899) time: 0.6325 [2021-03-26 23:23:26 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 640/1251] eta: 0:06:28 lr: 0.000704 loss: 3.5503 (3.4767) grad_norm: 1.2948 (1.2894) time: 0.6326 [2021-03-26 23:23:32 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 650/1251] eta: 0:06:22 lr: 0.000704 loss: 3.4385 (3.4771) grad_norm: 1.2144 (1.2887) time: 0.6348 [2021-03-26 23:23:38 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 660/1251] eta: 0:06:15 lr: 0.000704 loss: 3.4567 (3.4740) grad_norm: 1.2028 (1.2881) time: 0.6351 [2021-03-26 23:23:45 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 670/1251] eta: 0:06:09 lr: 0.000704 loss: 3.4761 (3.4758) grad_norm: 1.2856 (1.2888) time: 0.6267 [2021-03-26 23:23:51 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 680/1251] eta: 0:06:02 lr: 0.000704 loss: 3.3954 (3.4712) grad_norm: 1.2856 (1.2886) time: 0.6268 [2021-03-26 23:23:57 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 690/1251] eta: 0:05:56 lr: 0.000704 loss: 3.1712 (3.4718) grad_norm: 1.2405 (1.2878) time: 0.6343 [2021-03-26 23:24:04 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 700/1251] eta: 0:05:50 lr: 0.000704 loss: 3.4749 (3.4689) grad_norm: 1.2217 (1.2866) time: 0.6344 [2021-03-26 23:24:10 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 710/1251] eta: 0:05:43 lr: 0.000704 loss: 3.4749 (3.4696) grad_norm: 1.1700 (1.2852) time: 0.6315 [2021-03-26 23:24:16 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 720/1251] eta: 0:05:37 lr: 0.000704 loss: 3.5700 (3.4710) grad_norm: 1.1505 (1.2839) time: 0.6301 [2021-03-26 23:24:23 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 730/1251] eta: 0:05:30 lr: 0.000704 loss: 3.3784 (3.4683) grad_norm: 1.1541 (1.2826) time: 0.6310 [2021-03-26 23:24:29 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 740/1251] eta: 0:05:24 lr: 0.000704 loss: 3.1724 (3.4644) grad_norm: 1.1594 (1.2813) time: 0.6329 [2021-03-26 23:24:35 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 750/1251] eta: 0:05:18 lr: 0.000703 loss: 3.2869 (3.4649) grad_norm: 1.2223 (1.2808) time: 0.6345 [2021-03-26 23:24:42 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 760/1251] eta: 0:05:11 lr: 0.000703 loss: 3.2106 (3.4608) grad_norm: 1.2375 (1.2808) time: 0.6373 [2021-03-26 23:24:48 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 770/1251] eta: 0:05:05 lr: 0.000703 loss: 3.5140 (3.4631) grad_norm: 1.2375 (1.2806) time: 0.6290 [2021-03-26 23:24:54 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 780/1251] eta: 0:04:59 lr: 0.000703 loss: 3.5406 (3.4610) grad_norm: 1.2428 (1.2807) time: 0.6255 [2021-03-26 23:25:00 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 790/1251] eta: 0:04:52 lr: 0.000703 loss: 3.5422 (3.4640) grad_norm: 1.2319 (1.2794) time: 0.6263 [2021-03-26 23:25:07 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 800/1251] eta: 0:04:46 lr: 0.000703 loss: 3.6075 (3.4611) grad_norm: 1.2339 (1.2804) time: 0.6265 [2021-03-26 23:25:13 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 810/1251] eta: 0:04:39 lr: 0.000703 loss: 3.4093 (3.4589) grad_norm: 1.3459 (1.2815) time: 0.6242 [2021-03-26 23:25:19 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 820/1251] eta: 0:04:33 lr: 0.000703 loss: 3.4093 (3.4588) grad_norm: 1.2944 (1.2816) time: 0.6259 [2021-03-26 23:25:25 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 830/1251] eta: 0:04:27 lr: 0.000703 loss: 3.4879 (3.4594) grad_norm: 1.2740 (1.2814) time: 0.6313 [2021-03-26 23:25:32 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 840/1251] eta: 0:04:20 lr: 0.000703 loss: 3.3902 (3.4598) grad_norm: 1.2767 (1.2811) time: 0.6322 [2021-03-26 23:25:38 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 850/1251] eta: 0:04:14 lr: 0.000703 loss: 3.4310 (3.4602) grad_norm: 1.2302 (1.2801) time: 0.6284 [2021-03-26 23:25:44 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 860/1251] eta: 0:04:08 lr: 0.000703 loss: 3.6138 (3.4608) grad_norm: 1.2123 (1.2794) time: 0.6304 [2021-03-26 23:25:51 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 870/1251] eta: 0:04:01 lr: 0.000703 loss: 3.6369 (3.4600) grad_norm: 1.2123 (1.2786) time: 0.6341 [2021-03-26 23:25:57 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 880/1251] eta: 0:03:55 lr: 0.000703 loss: 3.6250 (3.4589) grad_norm: 1.1485 (1.2774) time: 0.6259 [2021-03-26 23:26:03 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 890/1251] eta: 0:03:48 lr: 0.000703 loss: 3.4880 (3.4576) grad_norm: 1.1498 (1.2769) time: 0.6234 [2021-03-26 23:26:09 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 900/1251] eta: 0:03:42 lr: 0.000703 loss: 3.4683 (3.4570) grad_norm: 1.2401 (1.2778) time: 0.6262 [2021-03-26 23:26:16 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 910/1251] eta: 0:03:36 lr: 0.000703 loss: 3.4683 (3.4550) grad_norm: 1.2446 (1.2769) time: 0.6265 [2021-03-26 23:26:22 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 920/1251] eta: 0:03:29 lr: 0.000703 loss: 3.5581 (3.4557) grad_norm: 1.2019 (1.2764) time: 0.6228 [2021-03-26 23:26:28 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 930/1251] eta: 0:03:23 lr: 0.000703 loss: 3.6367 (3.4555) grad_norm: 1.2693 (1.2777) time: 0.6289 [2021-03-26 23:26:35 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 940/1251] eta: 0:03:17 lr: 0.000703 loss: 3.5162 (3.4540) grad_norm: 1.3033 (1.2781) time: 0.6344 [2021-03-26 23:26:41 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 950/1251] eta: 0:03:10 lr: 0.000703 loss: 3.5506 (3.4548) grad_norm: 1.2091 (1.2768) time: 0.6329 [2021-03-26 23:26:47 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 960/1251] eta: 0:03:04 lr: 0.000703 loss: 3.5506 (3.4528) grad_norm: 1.1732 (1.2766) time: 0.6371 [2021-03-26 23:26:54 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 970/1251] eta: 0:02:58 lr: 0.000703 loss: 3.5991 (3.4561) grad_norm: 1.2051 (1.2761) time: 0.6351 [2021-03-26 23:27:00 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 980/1251] eta: 0:02:51 lr: 0.000703 loss: 3.5657 (3.4551) grad_norm: 1.1976 (1.2756) time: 0.6301 [2021-03-26 23:27:06 swin_base_patch4_window7_224] INFO: Epoch: [110] [ 990/1251] eta: 0:02:45 lr: 0.000703 loss: 3.2254 (3.4533) grad_norm: 1.2552 (1.2759) time: 0.6241 [2021-03-26 23:27:12 swin_base_patch4_window7_224] INFO: Epoch: [110] [1000/1251] eta: 0:02:39 lr: 0.000703 loss: 3.1480 (3.4501) grad_norm: 1.2286 (1.2752) time: 0.6244 [2021-03-26 23:27:19 swin_base_patch4_window7_224] INFO: Epoch: [110] [1010/1251] eta: 0:02:32 lr: 0.000703 loss: 3.3678 (3.4474) grad_norm: 1.1822 (1.2749) time: 0.6267 [2021-03-26 23:27:25 swin_base_patch4_window7_224] INFO: Epoch: [110] [1020/1251] eta: 0:02:26 lr: 0.000702 loss: 3.3678 (3.4465) grad_norm: 1.2013 (1.2747) time: 0.6259 [2021-03-26 23:27:31 swin_base_patch4_window7_224] INFO: Epoch: [110] [1030/1251] eta: 0:02:19 lr: 0.000702 loss: 3.6101 (3.4467) grad_norm: 1.2602 (1.2754) time: 0.6292 [2021-03-26 23:27:38 swin_base_patch4_window7_224] INFO: Epoch: [110] [1040/1251] eta: 0:02:13 lr: 0.000702 loss: 3.5402 (3.4456) grad_norm: 1.3114 (1.2753) time: 0.6254 [2021-03-26 23:27:44 swin_base_patch4_window7_224] INFO: Epoch: [110] [1050/1251] eta: 0:02:07 lr: 0.000702 loss: 3.5458 (3.4473) grad_norm: 1.2247 (1.2757) time: 0.6235 [2021-03-26 23:27:50 swin_base_patch4_window7_224] INFO: Epoch: [110] [1060/1251] eta: 0:02:00 lr: 0.000702 loss: 3.5466 (3.4475) grad_norm: 1.2989 (1.2763) time: 0.6248 [2021-03-26 23:27:56 swin_base_patch4_window7_224] INFO: Epoch: [110] [1070/1251] eta: 0:01:54 lr: 0.000702 loss: 3.5675 (3.4475) grad_norm: 1.2989 (1.2764) time: 0.6247 [2021-03-26 23:28:02 swin_base_patch4_window7_224] INFO: Epoch: [110] [1080/1251] eta: 0:01:48 lr: 0.000702 loss: 3.4562 (3.4464) grad_norm: 1.2321 (1.2763) time: 0.6236 [2021-03-26 23:28:09 swin_base_patch4_window7_224] INFO: Epoch: [110] [1090/1251] eta: 0:01:41 lr: 0.000702 loss: 3.4429 (3.4474) grad_norm: 1.2321 (1.2760) time: 0.6247 [2021-03-26 23:28:15 swin_base_patch4_window7_224] INFO: Epoch: [110] [1100/1251] eta: 0:01:35 lr: 0.000702 loss: 3.2578 (3.4445) grad_norm: 1.2249 (1.2753) time: 0.6270 [2021-03-26 23:28:21 swin_base_patch4_window7_224] INFO: Epoch: [110] [1110/1251] eta: 0:01:29 lr: 0.000702 loss: 3.1686 (3.4438) grad_norm: 1.1982 (1.2753) time: 0.6276 [2021-03-26 23:28:28 swin_base_patch4_window7_224] INFO: Epoch: [110] [1120/1251] eta: 0:01:22 lr: 0.000702 loss: 3.6432 (3.4455) grad_norm: 1.2141 (1.2750) time: 0.6357 [2021-03-26 23:28:34 swin_base_patch4_window7_224] INFO: Epoch: [110] [1130/1251] eta: 0:01:16 lr: 0.000702 loss: 3.6944 (3.4462) grad_norm: 1.2204 (1.2747) time: 0.6330 [2021-03-26 23:28:40 swin_base_patch4_window7_224] INFO: Epoch: [110] [1140/1251] eta: 0:01:10 lr: 0.000702 loss: 3.6433 (3.4478) grad_norm: 1.2491 (1.2760) time: 0.6223 [2021-03-26 23:28:47 swin_base_patch4_window7_224] INFO: Epoch: [110] [1150/1251] eta: 0:01:03 lr: 0.000702 loss: 3.5501 (3.4466) grad_norm: 1.3020 (1.2773) time: 0.6275 [2021-03-26 23:28:53 swin_base_patch4_window7_224] INFO: Epoch: [110] [1160/1251] eta: 0:00:57 lr: 0.000702 loss: 3.0622 (3.4445) grad_norm: 1.3020 (1.2779) time: 0.6318 [2021-03-26 23:28:59 swin_base_patch4_window7_224] INFO: Epoch: [110] [1170/1251] eta: 0:00:51 lr: 0.000702 loss: 3.0230 (3.4424) grad_norm: 1.3017 (1.2780) time: 0.6241 [2021-03-26 23:29:05 swin_base_patch4_window7_224] INFO: Epoch: [110] [1180/1251] eta: 0:00:44 lr: 0.000702 loss: 3.4333 (3.4435) grad_norm: 1.2096 (1.2776) time: 0.6236 [2021-03-26 23:29:12 swin_base_patch4_window7_224] INFO: Epoch: [110] [1190/1251] eta: 0:00:38 lr: 0.000702 loss: 3.4805 (3.4420) grad_norm: 1.2322 (1.2775) time: 0.6256 [2021-03-26 23:29:18 swin_base_patch4_window7_224] INFO: Epoch: [110] [1200/1251] eta: 0:00:32 lr: 0.000702 loss: 3.4229 (3.4407) grad_norm: 1.2248 (1.2773) time: 0.6225 [2021-03-26 23:29:24 swin_base_patch4_window7_224] INFO: Epoch: [110] [1210/1251] eta: 0:00:25 lr: 0.000702 loss: 3.5547 (3.4430) grad_norm: 1.2205 (1.2777) time: 0.6261 [2021-03-26 23:29:30 swin_base_patch4_window7_224] INFO: Epoch: [110] [1220/1251] eta: 0:00:19 lr: 0.000702 loss: 3.4629 (3.4417) grad_norm: 1.2899 (1.2783) time: 0.6340 [2021-03-26 23:29:37 swin_base_patch4_window7_224] INFO: Epoch: [110] [1230/1251] eta: 0:00:13 lr: 0.000702 loss: 3.4757 (3.4440) grad_norm: 1.3153 (1.2785) time: 0.6324 [2021-03-26 23:29:43 swin_base_patch4_window7_224] INFO: Epoch: [110] [1240/1251] eta: 0:00:06 lr: 0.000702 loss: 3.5384 (3.4434) grad_norm: 1.2270 (1.2781) time: 0.6260 [2021-03-26 23:29:49 swin_base_patch4_window7_224] INFO: Epoch: [110] [1250/1251] eta: 0:00:00 lr: 0.000702 loss: 3.5384 (3.4434) grad_norm: 1.2265 (1.2782) time: 0.6203 [2021-03-26 23:30:56 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:27 loss: 1.0674 (1.0674) acc1: 75.0000 (75.0000) acc5: 98.4375 (98.4375) [2021-03-26 23:30:57 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:11 loss: 0.8623 (0.9070) acc1: 76.5625 (78.1250) acc5: 95.3125 (95.7386) [2021-03-26 23:30:59 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:06 loss: 0.9219 (0.9650) acc1: 76.5625 (77.1577) acc5: 93.7500 (93.9732) [2021-03-26 23:31:00 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.0571 (0.9891) acc1: 76.5625 (76.8145) acc5: 92.1875 (93.5484) [2021-03-26 23:31:01 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.0017 (0.9937) acc1: 75.0000 (76.7912) acc5: 93.7500 (93.5595) [2021-03-26 23:31:02 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0157 (0.9899) acc1: 75.0000 (76.5760) acc5: 93.7500 (93.4400) [2021-03-26 23:31:08 swin_base_patch4_window7_224] INFO: * Acc@1 77.240 Acc@5 93.978 loss 0.964 [2021-03-26 23:31:08 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.2% [2021-03-26 23:31:08 swin_base_patch4_window7_224] INFO: Max accuracy: 77.24% [2021-03-26 23:31:12 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 0/1251] eta: 1:29:39 lr: 0.000702 loss: 3.6199 (3.6199) grad_norm: 1.3809 (1.3809) time: 4.2999 [2021-03-26 23:31:19 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 10/1251] eta: 0:20:14 lr: 0.000702 loss: 3.5187 (3.4452) grad_norm: 1.3095 (1.3389) time: 0.9787 [2021-03-26 23:31:25 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 20/1251] eta: 0:16:39 lr: 0.000702 loss: 3.5187 (3.3986) grad_norm: 1.2517 (1.3057) time: 0.6372 [2021-03-26 23:31:31 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 30/1251] eta: 0:15:20 lr: 0.000701 loss: 3.5075 (3.3669) grad_norm: 1.2560 (1.3131) time: 0.6304 [2021-03-26 23:31:38 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 40/1251] eta: 0:14:40 lr: 0.000701 loss: 3.3897 (3.3578) grad_norm: 1.2614 (1.2989) time: 0.6375 [2021-03-26 23:31:44 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 50/1251] eta: 0:14:09 lr: 0.000701 loss: 3.3897 (3.3938) grad_norm: 1.1738 (1.2841) time: 0.6355 [2021-03-26 23:31:50 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 60/1251] eta: 0:13:46 lr: 0.000701 loss: 3.7818 (3.4525) grad_norm: 1.1738 (1.2685) time: 0.6272 [2021-03-26 23:31:56 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 70/1251] eta: 0:13:27 lr: 0.000701 loss: 3.7362 (3.4566) grad_norm: 1.1825 (1.2720) time: 0.6241 [2021-03-26 23:32:03 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 80/1251] eta: 0:13:12 lr: 0.000701 loss: 3.5626 (3.4442) grad_norm: 1.2182 (1.2753) time: 0.6255 [2021-03-26 23:32:09 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 90/1251] eta: 0:12:59 lr: 0.000701 loss: 3.3163 (3.4278) grad_norm: 1.2979 (1.2784) time: 0.6270 [2021-03-26 23:32:15 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 100/1251] eta: 0:12:47 lr: 0.000701 loss: 3.3163 (3.4417) grad_norm: 1.2979 (1.2759) time: 0.6258 [2021-03-26 23:32:22 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 110/1251] eta: 0:12:38 lr: 0.000701 loss: 3.5177 (3.4413) grad_norm: 1.2339 (1.2698) time: 0.6319 [2021-03-26 23:32:28 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 120/1251] eta: 0:12:27 lr: 0.000701 loss: 3.4947 (3.4451) grad_norm: 1.2138 (1.2715) time: 0.6296 [2021-03-26 23:32:34 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 130/1251] eta: 0:12:17 lr: 0.000701 loss: 3.2626 (3.4230) grad_norm: 1.2596 (1.2739) time: 0.6233 [2021-03-26 23:32:40 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 140/1251] eta: 0:12:08 lr: 0.000701 loss: 3.2626 (3.4100) grad_norm: 1.2884 (1.2768) time: 0.6255 [2021-03-26 23:32:47 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 150/1251] eta: 0:11:59 lr: 0.000701 loss: 3.3221 (3.4084) grad_norm: 1.2920 (1.2745) time: 0.6257 [2021-03-26 23:32:53 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 160/1251] eta: 0:11:52 lr: 0.000701 loss: 3.3000 (3.4075) grad_norm: 1.2417 (1.2790) time: 0.6351 [2021-03-26 23:32:59 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 170/1251] eta: 0:11:44 lr: 0.000701 loss: 3.4583 (3.4120) grad_norm: 1.3008 (1.2833) time: 0.6397 [2021-03-26 23:33:06 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 180/1251] eta: 0:11:37 lr: 0.000701 loss: 3.6795 (3.4246) grad_norm: 1.1713 (1.2774) time: 0.6332 [2021-03-26 23:33:12 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 190/1251] eta: 0:11:29 lr: 0.000701 loss: 3.6036 (3.4206) grad_norm: 1.1780 (1.2751) time: 0.6308 [2021-03-26 23:33:18 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 200/1251] eta: 0:11:21 lr: 0.000701 loss: 3.5066 (3.4242) grad_norm: 1.3136 (1.2840) time: 0.6289 [2021-03-26 23:33:25 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 210/1251] eta: 0:11:14 lr: 0.000701 loss: 3.4855 (3.4269) grad_norm: 1.4233 (1.2889) time: 0.6261 [2021-03-26 23:33:31 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 220/1251] eta: 0:11:06 lr: 0.000701 loss: 3.4855 (3.4251) grad_norm: 1.2530 (1.2866) time: 0.6263 [2021-03-26 23:33:37 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 230/1251] eta: 0:10:59 lr: 0.000701 loss: 3.3885 (3.4196) grad_norm: 1.2325 (1.2889) time: 0.6241 [2021-03-26 23:33:43 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 240/1251] eta: 0:10:51 lr: 0.000701 loss: 3.3501 (3.4201) grad_norm: 1.3368 (1.2952) time: 0.6216 [2021-03-26 23:33:50 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 250/1251] eta: 0:10:44 lr: 0.000701 loss: 3.8086 (3.4335) grad_norm: 1.3647 (1.2957) time: 0.6236 [2021-03-26 23:33:56 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 260/1251] eta: 0:10:37 lr: 0.000701 loss: 3.9584 (3.4459) grad_norm: 1.2630 (1.2994) time: 0.6301 [2021-03-26 23:34:02 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 270/1251] eta: 0:10:30 lr: 0.000701 loss: 3.4428 (3.4417) grad_norm: 1.2550 (1.2966) time: 0.6307 [2021-03-26 23:34:08 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 280/1251] eta: 0:10:23 lr: 0.000701 loss: 3.2100 (3.4380) grad_norm: 1.2010 (1.2934) time: 0.6273 [2021-03-26 23:34:15 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 290/1251] eta: 0:10:16 lr: 0.000700 loss: 3.3887 (3.4419) grad_norm: 1.2383 (1.2941) time: 0.6266 [2021-03-26 23:34:21 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 300/1251] eta: 0:10:09 lr: 0.000700 loss: 3.4105 (3.4326) grad_norm: 1.2341 (1.2908) time: 0.6246 [2021-03-26 23:34:27 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 310/1251] eta: 0:10:03 lr: 0.000700 loss: 3.4872 (3.4373) grad_norm: 1.1796 (1.2880) time: 0.6278 [2021-03-26 23:34:34 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 320/1251] eta: 0:09:56 lr: 0.000700 loss: 3.7388 (3.4414) grad_norm: 1.2122 (1.2868) time: 0.6313 [2021-03-26 23:34:40 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 330/1251] eta: 0:09:49 lr: 0.000700 loss: 3.7112 (3.4448) grad_norm: 1.2080 (1.2854) time: 0.6269 [2021-03-26 23:34:46 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 340/1251] eta: 0:09:42 lr: 0.000700 loss: 3.5136 (3.4352) grad_norm: 1.1524 (1.2840) time: 0.6242 [2021-03-26 23:34:52 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 350/1251] eta: 0:09:36 lr: 0.000700 loss: 3.1882 (3.4305) grad_norm: 1.2063 (1.2834) time: 0.6332 [2021-03-26 23:34:59 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 360/1251] eta: 0:09:29 lr: 0.000700 loss: 3.1882 (3.4216) grad_norm: 1.2063 (1.2813) time: 0.6400 [2021-03-26 23:35:05 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 370/1251] eta: 0:09:23 lr: 0.000700 loss: 3.3176 (3.4187) grad_norm: 1.1658 (1.2777) time: 0.6324 [2021-03-26 23:35:11 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 380/1251] eta: 0:09:16 lr: 0.000700 loss: 3.4156 (3.4190) grad_norm: 1.2053 (1.2775) time: 0.6303 [2021-03-26 23:35:18 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 390/1251] eta: 0:09:09 lr: 0.000700 loss: 3.6874 (3.4276) grad_norm: 1.2914 (1.2784) time: 0.6301 [2021-03-26 23:35:24 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 400/1251] eta: 0:09:03 lr: 0.000700 loss: 3.6528 (3.4319) grad_norm: 1.2352 (1.2795) time: 0.6277 [2021-03-26 23:35:30 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 410/1251] eta: 0:08:56 lr: 0.000700 loss: 3.7455 (3.4449) grad_norm: 1.2218 (1.2795) time: 0.6287 [2021-03-26 23:35:37 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 420/1251] eta: 0:08:50 lr: 0.000700 loss: 3.9031 (3.4507) grad_norm: 1.2374 (1.2797) time: 0.6319 [2021-03-26 23:35:43 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 430/1251] eta: 0:08:43 lr: 0.000700 loss: 3.6488 (3.4428) grad_norm: 1.2702 (1.2799) time: 0.6321 [2021-03-26 23:35:49 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 440/1251] eta: 0:08:37 lr: 0.000700 loss: 3.5965 (3.4472) grad_norm: 1.2702 (1.2813) time: 0.6229 [2021-03-26 23:35:55 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 450/1251] eta: 0:08:30 lr: 0.000700 loss: 3.6494 (3.4440) grad_norm: 1.2642 (1.2818) time: 0.6223 [2021-03-26 23:36:02 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 460/1251] eta: 0:08:24 lr: 0.000700 loss: 3.4820 (3.4456) grad_norm: 1.2605 (1.2823) time: 0.6347 [2021-03-26 23:36:08 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 470/1251] eta: 0:08:17 lr: 0.000700 loss: 3.5355 (3.4459) grad_norm: 1.2816 (1.2821) time: 0.6365 [2021-03-26 23:36:14 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 480/1251] eta: 0:08:11 lr: 0.000700 loss: 3.5355 (3.4473) grad_norm: 1.2937 (1.2836) time: 0.6271 [2021-03-26 23:36:21 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 490/1251] eta: 0:08:04 lr: 0.000700 loss: 3.6463 (3.4500) grad_norm: 1.2163 (1.2836) time: 0.6286 [2021-03-26 23:36:27 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 500/1251] eta: 0:07:58 lr: 0.000700 loss: 3.5429 (3.4504) grad_norm: 1.2376 (1.2829) time: 0.6256 [2021-03-26 23:36:33 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 510/1251] eta: 0:07:51 lr: 0.000700 loss: 3.3941 (3.4483) grad_norm: 1.2338 (1.2818) time: 0.6252 [2021-03-26 23:36:39 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 520/1251] eta: 0:07:45 lr: 0.000700 loss: 3.5163 (3.4491) grad_norm: 1.2338 (1.2816) time: 0.6280 [2021-03-26 23:36:46 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 530/1251] eta: 0:07:38 lr: 0.000700 loss: 3.4957 (3.4475) grad_norm: 1.2663 (1.2806) time: 0.6267 [2021-03-26 23:36:52 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 540/1251] eta: 0:07:32 lr: 0.000700 loss: 3.5134 (3.4513) grad_norm: 1.2189 (1.2796) time: 0.6278 [2021-03-26 23:36:58 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 550/1251] eta: 0:07:25 lr: 0.000699 loss: 3.5499 (3.4507) grad_norm: 1.2325 (1.2810) time: 0.6342 [2021-03-26 23:37:05 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 560/1251] eta: 0:07:19 lr: 0.000699 loss: 3.6227 (3.4492) grad_norm: 1.3103 (nan) time: 0.6329 [2021-03-26 23:37:11 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 570/1251] eta: 0:07:13 lr: 0.000699 loss: 3.6398 (3.4517) grad_norm: 1.2232 (nan) time: 0.6338 [2021-03-26 23:37:18 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 580/1251] eta: 0:07:06 lr: 0.000699 loss: 3.6398 (3.4512) grad_norm: 1.2232 (nan) time: 0.6433 [2021-03-26 23:37:24 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 590/1251] eta: 0:07:00 lr: 0.000699 loss: 3.5797 (3.4508) grad_norm: 1.2080 (nan) time: 0.6409 [2021-03-26 23:37:30 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 600/1251] eta: 0:06:53 lr: 0.000699 loss: 3.5699 (3.4521) grad_norm: 1.2125 (nan) time: 0.6316 [2021-03-26 23:37:36 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 610/1251] eta: 0:06:47 lr: 0.000699 loss: 3.6201 (3.4556) grad_norm: 1.2507 (nan) time: 0.6267 [2021-03-26 23:37:43 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 620/1251] eta: 0:06:41 lr: 0.000699 loss: 3.5513 (3.4554) grad_norm: 1.2533 (nan) time: 0.6249 [2021-03-26 23:37:49 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 630/1251] eta: 0:06:34 lr: 0.000699 loss: 3.4281 (3.4519) grad_norm: 1.2239 (nan) time: 0.6226 [2021-03-26 23:37:55 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 640/1251] eta: 0:06:28 lr: 0.000699 loss: 3.5196 (3.4556) grad_norm: 1.1814 (nan) time: 0.6242 [2021-03-26 23:38:01 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 650/1251] eta: 0:06:21 lr: 0.000699 loss: 3.5266 (3.4552) grad_norm: 1.2110 (nan) time: 0.6274 [2021-03-26 23:38:08 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 660/1251] eta: 0:06:15 lr: 0.000699 loss: 3.3434 (3.4541) grad_norm: 1.2241 (nan) time: 0.6317 [2021-03-26 23:38:14 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 670/1251] eta: 0:06:08 lr: 0.000699 loss: 3.6677 (3.4578) grad_norm: 1.1116 (nan) time: 0.6290 [2021-03-26 23:38:20 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 680/1251] eta: 0:06:02 lr: 0.000699 loss: 3.7067 (3.4605) grad_norm: 1.1425 (nan) time: 0.6235 [2021-03-26 23:38:27 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 690/1251] eta: 0:05:56 lr: 0.000699 loss: 3.5807 (3.4579) grad_norm: 1.2159 (nan) time: 0.6237 [2021-03-26 23:38:33 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 700/1251] eta: 0:05:49 lr: 0.000699 loss: 3.4763 (3.4584) grad_norm: 1.2397 (nan) time: 0.6232 [2021-03-26 23:38:39 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 710/1251] eta: 0:05:43 lr: 0.000699 loss: 3.4634 (3.4560) grad_norm: 1.1868 (nan) time: 0.6207 [2021-03-26 23:38:45 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 720/1251] eta: 0:05:36 lr: 0.000699 loss: 3.4227 (3.4553) grad_norm: 1.2220 (nan) time: 0.6287 [2021-03-26 23:38:52 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 730/1251] eta: 0:05:30 lr: 0.000699 loss: 3.4694 (3.4508) grad_norm: 1.3040 (nan) time: 0.6355 [2021-03-26 23:38:58 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 740/1251] eta: 0:05:24 lr: 0.000699 loss: 3.4694 (3.4506) grad_norm: 1.1861 (nan) time: 0.6374 [2021-03-26 23:39:04 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 750/1251] eta: 0:05:17 lr: 0.000699 loss: 3.7876 (3.4537) grad_norm: 1.1787 (nan) time: 0.6393 [2021-03-26 23:39:11 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 760/1251] eta: 0:05:11 lr: 0.000699 loss: 3.7937 (3.4585) grad_norm: 1.2542 (nan) time: 0.6427 [2021-03-26 23:39:17 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 770/1251] eta: 0:05:05 lr: 0.000699 loss: 3.6280 (3.4576) grad_norm: 1.3390 (nan) time: 0.6359 [2021-03-26 23:39:24 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 780/1251] eta: 0:04:58 lr: 0.000699 loss: 3.4644 (3.4579) grad_norm: 1.3390 (nan) time: 0.6356 [2021-03-26 23:39:30 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 790/1251] eta: 0:04:52 lr: 0.000699 loss: 3.4282 (3.4545) grad_norm: 1.3173 (nan) time: 0.6364 [2021-03-26 23:39:36 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 800/1251] eta: 0:04:46 lr: 0.000699 loss: 3.0963 (3.4525) grad_norm: 1.2582 (nan) time: 0.6234 [2021-03-26 23:39:43 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 810/1251] eta: 0:04:39 lr: 0.000699 loss: 3.4901 (3.4535) grad_norm: 1.2775 (nan) time: 0.6323 [2021-03-26 23:39:49 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 820/1251] eta: 0:04:33 lr: 0.000698 loss: 3.6097 (3.4531) grad_norm: 1.2790 (nan) time: 0.6313 [2021-03-26 23:39:55 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 830/1251] eta: 0:04:26 lr: 0.000698 loss: 3.6957 (3.4559) grad_norm: 1.1946 (nan) time: 0.6205 [2021-03-26 23:40:01 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 840/1251] eta: 0:04:20 lr: 0.000698 loss: 3.6925 (3.4554) grad_norm: 1.1885 (nan) time: 0.6215 [2021-03-26 23:40:07 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 850/1251] eta: 0:04:14 lr: 0.000698 loss: 3.3643 (3.4555) grad_norm: 1.1869 (nan) time: 0.6258 [2021-03-26 23:40:14 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 860/1251] eta: 0:04:07 lr: 0.000698 loss: 3.4633 (3.4539) grad_norm: 1.2190 (nan) time: 0.6335 [2021-03-26 23:40:20 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 870/1251] eta: 0:04:01 lr: 0.000698 loss: 3.6002 (3.4545) grad_norm: 1.2130 (nan) time: 0.6303 [2021-03-26 23:40:26 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 880/1251] eta: 0:03:55 lr: 0.000698 loss: 3.5292 (3.4544) grad_norm: 1.3004 (nan) time: 0.6269 [2021-03-26 23:40:33 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 890/1251] eta: 0:03:48 lr: 0.000698 loss: 3.5108 (3.4537) grad_norm: 1.3072 (nan) time: 0.6305 [2021-03-26 23:40:39 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 900/1251] eta: 0:03:42 lr: 0.000698 loss: 3.4955 (3.4528) grad_norm: 1.2144 (nan) time: 0.6272 [2021-03-26 23:40:45 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 910/1251] eta: 0:03:36 lr: 0.000698 loss: 3.5087 (3.4534) grad_norm: 1.2144 (nan) time: 0.6310 [2021-03-26 23:40:52 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 920/1251] eta: 0:03:29 lr: 0.000698 loss: 3.6578 (3.4570) grad_norm: 1.2851 (nan) time: 0.6381 [2021-03-26 23:40:58 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 930/1251] eta: 0:03:23 lr: 0.000698 loss: 3.6251 (3.4559) grad_norm: 1.3234 (nan) time: 0.6365 [2021-03-26 23:41:04 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 940/1251] eta: 0:03:17 lr: 0.000698 loss: 3.5212 (3.4553) grad_norm: 1.2281 (nan) time: 0.6317 [2021-03-26 23:41:11 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 950/1251] eta: 0:03:10 lr: 0.000698 loss: 3.4422 (3.4545) grad_norm: 1.3032 (nan) time: 0.6254 [2021-03-26 23:41:17 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 960/1251] eta: 0:03:04 lr: 0.000698 loss: 3.4422 (3.4548) grad_norm: 1.3399 (nan) time: 0.6222 [2021-03-26 23:41:23 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 970/1251] eta: 0:02:57 lr: 0.000698 loss: 3.5985 (3.4572) grad_norm: 1.2223 (nan) time: 0.6239 [2021-03-26 23:41:29 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 980/1251] eta: 0:02:51 lr: 0.000698 loss: 3.7232 (3.4598) grad_norm: 1.1612 (nan) time: 0.6289 [2021-03-26 23:41:36 swin_base_patch4_window7_224] INFO: Epoch: [111] [ 990/1251] eta: 0:02:45 lr: 0.000698 loss: 3.4631 (3.4584) grad_norm: 1.1919 (nan) time: 0.6277 [2021-03-26 23:41:42 swin_base_patch4_window7_224] INFO: Epoch: [111] [1000/1251] eta: 0:02:38 lr: 0.000698 loss: 3.4631 (3.4610) grad_norm: 1.2535 (nan) time: 0.6243 [2021-03-26 23:41:48 swin_base_patch4_window7_224] INFO: Epoch: [111] [1010/1251] eta: 0:02:32 lr: 0.000698 loss: 3.6281 (3.4613) grad_norm: 1.2657 (nan) time: 0.6264 [2021-03-26 23:41:54 swin_base_patch4_window7_224] INFO: Epoch: [111] [1020/1251] eta: 0:02:26 lr: 0.000698 loss: 3.6738 (3.4637) grad_norm: 1.2418 (nan) time: 0.6244 [2021-03-26 23:42:01 swin_base_patch4_window7_224] INFO: Epoch: [111] [1030/1251] eta: 0:02:19 lr: 0.000698 loss: 3.6810 (3.4634) grad_norm: 1.2280 (nan) time: 0.6254 [2021-03-26 23:42:07 swin_base_patch4_window7_224] INFO: Epoch: [111] [1040/1251] eta: 0:02:13 lr: 0.000698 loss: 3.6577 (3.4650) grad_norm: 1.1937 (nan) time: 0.6271 [2021-03-26 23:42:13 swin_base_patch4_window7_224] INFO: Epoch: [111] [1050/1251] eta: 0:02:07 lr: 0.000698 loss: 3.6627 (3.4659) grad_norm: 1.2446 (nan) time: 0.6277 [2021-03-26 23:42:19 swin_base_patch4_window7_224] INFO: Epoch: [111] [1060/1251] eta: 0:02:00 lr: 0.000698 loss: 3.6627 (3.4672) grad_norm: 1.2531 (nan) time: 0.6270 [2021-03-26 23:42:26 swin_base_patch4_window7_224] INFO: Epoch: [111] [1070/1251] eta: 0:01:54 lr: 0.000698 loss: 3.3593 (3.4633) grad_norm: 1.2050 (nan) time: 0.6226 [2021-03-26 23:42:32 swin_base_patch4_window7_224] INFO: Epoch: [111] [1080/1251] eta: 0:01:48 lr: 0.000697 loss: 3.6968 (3.4650) grad_norm: 1.1764 (nan) time: 0.6237 [2021-03-26 23:42:38 swin_base_patch4_window7_224] INFO: Epoch: [111] [1090/1251] eta: 0:01:41 lr: 0.000697 loss: 3.7885 (3.4659) grad_norm: 1.2207 (nan) time: 0.6233 [2021-03-26 23:42:44 swin_base_patch4_window7_224] INFO: Epoch: [111] [1100/1251] eta: 0:01:35 lr: 0.000697 loss: 3.2477 (3.4623) grad_norm: 1.2207 (nan) time: 0.6277 [2021-03-26 23:42:51 swin_base_patch4_window7_224] INFO: Epoch: [111] [1110/1251] eta: 0:01:29 lr: 0.000697 loss: 3.0827 (3.4600) grad_norm: 1.2441 (nan) time: 0.6316 [2021-03-26 23:42:57 swin_base_patch4_window7_224] INFO: Epoch: [111] [1120/1251] eta: 0:01:22 lr: 0.000697 loss: 3.2314 (3.4593) grad_norm: 1.2337 (nan) time: 0.6294 [2021-03-26 23:43:03 swin_base_patch4_window7_224] INFO: Epoch: [111] [1130/1251] eta: 0:01:16 lr: 0.000697 loss: 3.6345 (3.4609) grad_norm: 1.2125 (nan) time: 0.6278 [2021-03-26 23:43:10 swin_base_patch4_window7_224] INFO: Epoch: [111] [1140/1251] eta: 0:01:10 lr: 0.000697 loss: 3.5680 (3.4601) grad_norm: 1.2125 (nan) time: 0.6292 [2021-03-26 23:43:16 swin_base_patch4_window7_224] INFO: Epoch: [111] [1150/1251] eta: 0:01:03 lr: 0.000697 loss: 3.4098 (3.4598) grad_norm: 1.1270 (nan) time: 0.6274 [2021-03-26 23:43:22 swin_base_patch4_window7_224] INFO: Epoch: [111] [1160/1251] eta: 0:00:57 lr: 0.000697 loss: 3.4972 (3.4596) grad_norm: 1.1674 (nan) time: 0.6277 [2021-03-26 23:43:28 swin_base_patch4_window7_224] INFO: Epoch: [111] [1170/1251] eta: 0:00:51 lr: 0.000697 loss: 3.6604 (3.4609) grad_norm: 1.3532 (nan) time: 0.6301 [2021-03-26 23:43:35 swin_base_patch4_window7_224] INFO: Epoch: [111] [1180/1251] eta: 0:00:44 lr: 0.000697 loss: 3.6353 (3.4621) grad_norm: 1.2187 (nan) time: 0.6308 [2021-03-26 23:43:41 swin_base_patch4_window7_224] INFO: Epoch: [111] [1190/1251] eta: 0:00:38 lr: 0.000697 loss: 3.5128 (3.4630) grad_norm: 1.2177 (nan) time: 0.6340 [2021-03-26 23:43:47 swin_base_patch4_window7_224] INFO: Epoch: [111] [1200/1251] eta: 0:00:32 lr: 0.000697 loss: 3.7611 (3.4667) grad_norm: 1.2603 (nan) time: 0.6291 [2021-03-26 23:43:54 swin_base_patch4_window7_224] INFO: Epoch: [111] [1210/1251] eta: 0:00:25 lr: 0.000697 loss: 3.8131 (3.4659) grad_norm: 1.3781 (nan) time: 0.6256 [2021-03-26 23:44:00 swin_base_patch4_window7_224] INFO: Epoch: [111] [1220/1251] eta: 0:00:19 lr: 0.000697 loss: 3.5872 (3.4672) grad_norm: 1.3970 (nan) time: 0.6253 [2021-03-26 23:44:06 swin_base_patch4_window7_224] INFO: Epoch: [111] [1230/1251] eta: 0:00:13 lr: 0.000697 loss: 3.5872 (3.4674) grad_norm: 1.3702 (nan) time: 0.6232 [2021-03-26 23:44:13 swin_base_patch4_window7_224] INFO: Epoch: [111] [1240/1251] eta: 0:00:06 lr: 0.000697 loss: 3.3345 (3.4649) grad_norm: 1.2844 (nan) time: 0.6315 [2021-03-26 23:44:19 swin_base_patch4_window7_224] INFO: Epoch: [111] [1250/1251] eta: 0:00:00 lr: 0.000697 loss: 3.0880 (3.4637) grad_norm: 1.2192 (nan) time: 0.6359 [2021-03-26 23:44:26 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:12 loss: 1.0909 (1.0909) acc1: 68.7500 (68.7500) acc5: 95.3125 (95.3125) [2021-03-26 23:44:29 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8364 (0.8663) acc1: 79.6875 (79.1193) acc5: 96.8750 (95.5966) [2021-03-26 23:44:31 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8774 (0.9249) acc1: 78.1250 (78.2738) acc5: 95.3125 (94.8661) [2021-03-26 23:44:34 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0270 (0.9884) acc1: 75.0000 (76.5625) acc5: 92.1875 (94.2036) [2021-03-26 23:44:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9401 (0.9723) acc1: 75.0000 (76.7530) acc5: 95.3125 (94.5884) [2021-03-26 23:44:37 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9211 (0.9856) acc1: 76.5625 (76.4800) acc5: 95.3125 (94.3680) [2021-03-26 23:44:43 swin_base_patch4_window7_224] INFO: * Acc@1 77.342 Acc@5 94.074 loss 0.965 [2021-03-26 23:44:43 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.3% [2021-03-26 23:44:43 swin_base_patch4_window7_224] INFO: Max accuracy: 77.34% [2021-03-26 23:44:47 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 0/1251] eta: 1:30:58 lr: 0.000697 loss: 3.5295 (3.5295) grad_norm: 1.3817 (1.3817) time: 4.3632 [2021-03-26 23:44:54 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 10/1251] eta: 0:20:06 lr: 0.000697 loss: 3.5295 (3.4270) grad_norm: 1.2551 (1.2773) time: 0.9724 [2021-03-26 23:45:00 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 20/1251] eta: 0:16:33 lr: 0.000697 loss: 3.6946 (3.4675) grad_norm: 1.2338 (1.2811) time: 0.6296 [2021-03-26 23:45:06 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 30/1251] eta: 0:15:17 lr: 0.000697 loss: 3.4381 (3.4140) grad_norm: 1.2343 (1.2738) time: 0.6294 [2021-03-26 23:45:13 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 40/1251] eta: 0:14:33 lr: 0.000697 loss: 3.2867 (3.4235) grad_norm: 1.2438 (1.2736) time: 0.6302 [2021-03-26 23:45:19 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 50/1251] eta: 0:14:06 lr: 0.000697 loss: 3.4495 (3.3922) grad_norm: 1.2195 (1.2639) time: 0.6329 [2021-03-26 23:45:25 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 60/1251] eta: 0:13:45 lr: 0.000697 loss: 3.4520 (3.4046) grad_norm: 1.2832 (1.2701) time: 0.6359 [2021-03-26 23:45:32 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 70/1251] eta: 0:13:28 lr: 0.000697 loss: 3.4612 (3.4149) grad_norm: 1.2832 (1.2716) time: 0.6329 [2021-03-26 23:45:38 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 80/1251] eta: 0:13:14 lr: 0.000697 loss: 3.6179 (3.4372) grad_norm: 1.2312 (1.2721) time: 0.6335 [2021-03-26 23:45:44 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 90/1251] eta: 0:13:02 lr: 0.000696 loss: 3.6827 (3.4337) grad_norm: 1.2265 (1.2681) time: 0.6356 [2021-03-26 23:45:51 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 100/1251] eta: 0:12:49 lr: 0.000696 loss: 3.6994 (3.4531) grad_norm: 1.2552 (1.2842) time: 0.6306 [2021-03-26 23:45:57 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 110/1251] eta: 0:12:38 lr: 0.000696 loss: 3.4324 (3.4461) grad_norm: 1.3672 (1.2974) time: 0.6251 [2021-03-26 23:46:03 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 120/1251] eta: 0:12:28 lr: 0.000696 loss: 3.2681 (3.4266) grad_norm: 1.2188 (1.2876) time: 0.6264 [2021-03-26 23:46:09 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 130/1251] eta: 0:12:20 lr: 0.000696 loss: 3.4024 (3.4225) grad_norm: 1.1789 (1.2844) time: 0.6339 [2021-03-26 23:46:16 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 140/1251] eta: 0:12:11 lr: 0.000696 loss: 3.6006 (3.4388) grad_norm: 1.1996 (1.2811) time: 0.6397 [2021-03-26 23:46:22 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 150/1251] eta: 0:12:02 lr: 0.000696 loss: 3.6569 (3.4535) grad_norm: 1.2653 (1.2861) time: 0.6332 [2021-03-26 23:46:29 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 160/1251] eta: 0:11:55 lr: 0.000696 loss: 3.5763 (3.4524) grad_norm: 1.2639 (1.2798) time: 0.6341 [2021-03-26 23:46:35 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 170/1251] eta: 0:11:47 lr: 0.000696 loss: 3.5780 (3.4594) grad_norm: 1.2045 (1.2789) time: 0.6349 [2021-03-26 23:46:41 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 180/1251] eta: 0:11:39 lr: 0.000696 loss: 3.4089 (3.4435) grad_norm: 1.3135 (1.2823) time: 0.6303 [2021-03-26 23:46:47 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 190/1251] eta: 0:11:31 lr: 0.000696 loss: 3.2358 (3.4443) grad_norm: 1.3130 (1.2882) time: 0.6273 [2021-03-26 23:46:54 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 200/1251] eta: 0:11:23 lr: 0.000696 loss: 3.5553 (3.4459) grad_norm: 1.2544 (1.2840) time: 0.6229 [2021-03-26 23:47:00 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 210/1251] eta: 0:11:15 lr: 0.000696 loss: 3.4913 (3.4411) grad_norm: 1.2720 (1.2882) time: 0.6215 [2021-03-26 23:47:06 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 220/1251] eta: 0:11:07 lr: 0.000696 loss: 3.3726 (3.4424) grad_norm: 1.3667 (1.2934) time: 0.6253 [2021-03-26 23:47:12 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 230/1251] eta: 0:11:00 lr: 0.000696 loss: 3.3622 (3.4318) grad_norm: 1.3640 (1.2974) time: 0.6298 [2021-03-26 23:47:19 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 240/1251] eta: 0:10:52 lr: 0.000696 loss: 3.1055 (3.4288) grad_norm: 1.2957 (1.2965) time: 0.6262 [2021-03-26 23:47:25 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 250/1251] eta: 0:10:45 lr: 0.000696 loss: 3.4260 (3.4223) grad_norm: 1.2141 (1.2944) time: 0.6242 [2021-03-26 23:47:31 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 260/1251] eta: 0:10:38 lr: 0.000696 loss: 3.1811 (3.4162) grad_norm: 1.2211 (1.2917) time: 0.6301 [2021-03-26 23:47:38 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 270/1251] eta: 0:10:31 lr: 0.000696 loss: 3.4549 (3.4223) grad_norm: 1.2146 (1.2897) time: 0.6303 [2021-03-26 23:47:44 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 280/1251] eta: 0:10:24 lr: 0.000696 loss: 3.5036 (3.4140) grad_norm: 1.1689 (1.2857) time: 0.6273 [2021-03-26 23:47:50 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 290/1251] eta: 0:10:18 lr: 0.000696 loss: 3.5992 (3.4194) grad_norm: 1.1800 (1.2879) time: 0.6311 [2021-03-26 23:47:56 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 300/1251] eta: 0:10:11 lr: 0.000696 loss: 3.6689 (3.4187) grad_norm: 1.2854 (1.2897) time: 0.6294 [2021-03-26 23:48:03 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 310/1251] eta: 0:10:04 lr: 0.000696 loss: 3.6490 (3.4286) grad_norm: 1.3238 (1.2916) time: 0.6259 [2021-03-26 23:48:09 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 320/1251] eta: 0:09:57 lr: 0.000696 loss: 3.3909 (3.4215) grad_norm: 1.3525 (1.2936) time: 0.6286 [2021-03-26 23:48:15 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 330/1251] eta: 0:09:50 lr: 0.000696 loss: 3.3200 (3.4260) grad_norm: 1.3630 (1.2958) time: 0.6265 [2021-03-26 23:48:22 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 340/1251] eta: 0:09:43 lr: 0.000696 loss: 3.6374 (3.4211) grad_norm: 1.3630 (1.2979) time: 0.6278 [2021-03-26 23:48:28 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 350/1251] eta: 0:09:37 lr: 0.000695 loss: 3.5488 (3.4198) grad_norm: 1.2375 (1.2959) time: 0.6382 [2021-03-26 23:48:34 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 360/1251] eta: 0:09:30 lr: 0.000695 loss: 3.5488 (3.4225) grad_norm: 1.1895 (1.2939) time: 0.6374 [2021-03-26 23:48:41 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 370/1251] eta: 0:09:24 lr: 0.000695 loss: 3.4887 (3.4251) grad_norm: 1.2419 (1.2943) time: 0.6301 [2021-03-26 23:48:47 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 380/1251] eta: 0:09:17 lr: 0.000695 loss: 3.6291 (3.4282) grad_norm: 1.2815 (1.2949) time: 0.6301 [2021-03-26 23:48:53 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 390/1251] eta: 0:09:10 lr: 0.000695 loss: 3.6291 (3.4299) grad_norm: 1.2479 (1.2940) time: 0.6291 [2021-03-26 23:48:59 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 400/1251] eta: 0:09:04 lr: 0.000695 loss: 3.7017 (3.4363) grad_norm: 1.2674 (1.2955) time: 0.6275 [2021-03-26 23:49:06 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 410/1251] eta: 0:08:57 lr: 0.000695 loss: 3.4838 (3.4301) grad_norm: 1.2674 (1.2940) time: 0.6257 [2021-03-26 23:49:12 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 420/1251] eta: 0:08:51 lr: 0.000695 loss: 3.4785 (3.4325) grad_norm: 1.2665 (1.2946) time: 0.6309 [2021-03-26 23:49:18 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 430/1251] eta: 0:08:44 lr: 0.000695 loss: 3.6255 (3.4340) grad_norm: 1.2380 (1.2958) time: 0.6311 [2021-03-26 23:49:25 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 440/1251] eta: 0:08:37 lr: 0.000695 loss: 3.6541 (3.4360) grad_norm: 1.2584 (inf) time: 0.6233 [2021-03-26 23:49:31 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 450/1251] eta: 0:08:31 lr: 0.000695 loss: 3.6541 (3.4354) grad_norm: 1.2337 (inf) time: 0.6281 [2021-03-26 23:49:37 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 460/1251] eta: 0:08:24 lr: 0.000695 loss: 3.2182 (3.4325) grad_norm: 1.2227 (inf) time: 0.6304 [2021-03-26 23:49:44 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 470/1251] eta: 0:08:18 lr: 0.000695 loss: 3.5941 (3.4349) grad_norm: 1.2474 (inf) time: 0.6311 [2021-03-26 23:49:50 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 480/1251] eta: 0:08:11 lr: 0.000695 loss: 3.3235 (3.4301) grad_norm: 1.2421 (inf) time: 0.6351 [2021-03-26 23:49:56 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 490/1251] eta: 0:08:05 lr: 0.000695 loss: 3.5046 (3.4327) grad_norm: 1.2284 (inf) time: 0.6280 [2021-03-26 23:50:02 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 500/1251] eta: 0:07:58 lr: 0.000695 loss: 3.5851 (3.4351) grad_norm: 1.2684 (inf) time: 0.6190 [2021-03-26 23:50:09 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 510/1251] eta: 0:07:52 lr: 0.000695 loss: 3.5851 (3.4395) grad_norm: 1.2586 (inf) time: 0.6252 [2021-03-26 23:50:15 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 520/1251] eta: 0:07:45 lr: 0.000695 loss: 3.5575 (3.4377) grad_norm: 1.1934 (inf) time: 0.6268 [2021-03-26 23:50:21 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 530/1251] eta: 0:07:38 lr: 0.000695 loss: 3.5391 (3.4410) grad_norm: 1.1830 (inf) time: 0.6206 [2021-03-26 23:50:27 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 540/1251] eta: 0:07:32 lr: 0.000695 loss: 3.4766 (3.4403) grad_norm: 1.2461 (inf) time: 0.6225 [2021-03-26 23:50:34 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 550/1251] eta: 0:07:26 lr: 0.000695 loss: 3.4725 (3.4409) grad_norm: 1.2073 (inf) time: 0.6440 [2021-03-26 23:50:40 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 560/1251] eta: 0:07:19 lr: 0.000695 loss: 3.3587 (3.4368) grad_norm: 1.1502 (inf) time: 0.6503 [2021-03-26 23:50:46 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 570/1251] eta: 0:07:13 lr: 0.000695 loss: 3.4443 (3.4399) grad_norm: 1.2470 (inf) time: 0.6296 [2021-03-26 23:50:53 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 580/1251] eta: 0:07:06 lr: 0.000695 loss: 3.4443 (3.4368) grad_norm: 1.2426 (inf) time: 0.6242 [2021-03-26 23:50:59 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 590/1251] eta: 0:07:00 lr: 0.000695 loss: 3.3703 (3.4327) grad_norm: 1.2136 (inf) time: 0.6294 [2021-03-26 23:51:05 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 600/1251] eta: 0:06:54 lr: 0.000695 loss: 3.3112 (3.4336) grad_norm: 1.1686 (inf) time: 0.6308 [2021-03-26 23:51:12 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 610/1251] eta: 0:06:47 lr: 0.000694 loss: 3.4469 (3.4366) grad_norm: 1.2300 (inf) time: 0.6322 [2021-03-26 23:51:18 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 620/1251] eta: 0:06:41 lr: 0.000694 loss: 3.4058 (3.4306) grad_norm: 1.4497 (inf) time: 0.6297 [2021-03-26 23:51:24 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 630/1251] eta: 0:06:34 lr: 0.000694 loss: 3.1243 (3.4291) grad_norm: 1.3122 (inf) time: 0.6241 [2021-03-26 23:51:30 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 640/1251] eta: 0:06:28 lr: 0.000694 loss: 3.4568 (3.4299) grad_norm: 1.2172 (inf) time: 0.6274 [2021-03-26 23:51:37 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 650/1251] eta: 0:06:21 lr: 0.000694 loss: 3.3977 (3.4285) grad_norm: 1.2473 (inf) time: 0.6286 [2021-03-26 23:51:43 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 660/1251] eta: 0:06:15 lr: 0.000694 loss: 3.4044 (3.4307) grad_norm: 1.2563 (inf) time: 0.6233 [2021-03-26 23:51:49 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 670/1251] eta: 0:06:08 lr: 0.000694 loss: 3.4044 (3.4273) grad_norm: 1.2833 (inf) time: 0.6206 [2021-03-26 23:51:55 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 680/1251] eta: 0:06:02 lr: 0.000694 loss: 3.3620 (3.4277) grad_norm: 1.2013 (inf) time: 0.6263 [2021-03-26 23:52:02 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 690/1251] eta: 0:05:56 lr: 0.000694 loss: 3.6529 (3.4303) grad_norm: 1.2343 (inf) time: 0.6296 [2021-03-26 23:52:08 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 700/1251] eta: 0:05:49 lr: 0.000694 loss: 3.6356 (3.4324) grad_norm: 1.2497 (inf) time: 0.6365 [2021-03-26 23:52:15 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 710/1251] eta: 0:05:43 lr: 0.000694 loss: 3.6356 (3.4344) grad_norm: 1.2098 (inf) time: 0.6427 [2021-03-26 23:52:21 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 720/1251] eta: 0:05:37 lr: 0.000694 loss: 3.7204 (3.4350) grad_norm: 1.2130 (inf) time: 0.6336 [2021-03-26 23:52:27 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 730/1251] eta: 0:05:30 lr: 0.000694 loss: 3.5842 (3.4369) grad_norm: 1.2662 (inf) time: 0.6285 [2021-03-26 23:52:34 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 740/1251] eta: 0:05:24 lr: 0.000694 loss: 3.4599 (3.4357) grad_norm: 1.2824 (inf) time: 0.6334 [2021-03-26 23:52:40 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 750/1251] eta: 0:05:18 lr: 0.000694 loss: 3.4599 (3.4329) grad_norm: 1.2463 (inf) time: 0.6399 [2021-03-26 23:52:46 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 760/1251] eta: 0:05:11 lr: 0.000694 loss: 3.5218 (3.4356) grad_norm: 1.2661 (inf) time: 0.6333 [2021-03-26 23:52:52 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 770/1251] eta: 0:05:05 lr: 0.000694 loss: 3.5218 (3.4379) grad_norm: 1.2843 (inf) time: 0.6219 [2021-03-26 23:52:59 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 780/1251] eta: 0:04:58 lr: 0.000694 loss: 3.4905 (3.4364) grad_norm: 1.2590 (inf) time: 0.6266 [2021-03-26 23:53:05 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 790/1251] eta: 0:04:52 lr: 0.000694 loss: 3.2596 (3.4364) grad_norm: 1.2606 (inf) time: 0.6290 [2021-03-26 23:53:11 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 800/1251] eta: 0:04:46 lr: 0.000694 loss: 3.2634 (3.4359) grad_norm: 1.2865 (inf) time: 0.6255 [2021-03-26 23:53:18 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 810/1251] eta: 0:04:39 lr: 0.000694 loss: 3.7523 (3.4389) grad_norm: 1.2845 (inf) time: 0.6266 [2021-03-26 23:53:24 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 820/1251] eta: 0:04:33 lr: 0.000694 loss: 3.7545 (3.4398) grad_norm: 1.3733 (inf) time: 0.6279 [2021-03-26 23:53:30 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 830/1251] eta: 0:04:27 lr: 0.000694 loss: 3.4703 (3.4403) grad_norm: 1.2700 (inf) time: 0.6371 [2021-03-26 23:53:37 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 840/1251] eta: 0:04:20 lr: 0.000694 loss: 3.3793 (3.4408) grad_norm: 1.2366 (inf) time: 0.6418 [2021-03-26 23:53:43 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 850/1251] eta: 0:04:14 lr: 0.000694 loss: 3.3615 (3.4398) grad_norm: 1.2341 (inf) time: 0.6338 [2021-03-26 23:53:49 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 860/1251] eta: 0:04:07 lr: 0.000694 loss: 3.4271 (3.4392) grad_norm: 1.1432 (inf) time: 0.6235 [2021-03-26 23:53:55 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 870/1251] eta: 0:04:01 lr: 0.000693 loss: 3.4979 (3.4401) grad_norm: 1.2197 (inf) time: 0.6229 [2021-03-26 23:54:02 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 880/1251] eta: 0:03:55 lr: 0.000693 loss: 3.4106 (3.4381) grad_norm: 1.2197 (inf) time: 0.6313 [2021-03-26 23:54:08 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 890/1251] eta: 0:03:48 lr: 0.000693 loss: 3.3832 (3.4380) grad_norm: 1.2253 (inf) time: 0.6328 [2021-03-26 23:54:14 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 900/1251] eta: 0:03:42 lr: 0.000693 loss: 3.4703 (3.4375) grad_norm: 1.2330 (inf) time: 0.6270 [2021-03-26 23:54:21 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 910/1251] eta: 0:03:36 lr: 0.000693 loss: 3.4494 (3.4387) grad_norm: 1.2271 (inf) time: 0.6284 [2021-03-26 23:54:27 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 920/1251] eta: 0:03:29 lr: 0.000693 loss: 3.4494 (3.4398) grad_norm: 1.2271 (inf) time: 0.6303 [2021-03-26 23:54:33 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 930/1251] eta: 0:03:23 lr: 0.000693 loss: 3.5071 (3.4401) grad_norm: 1.2425 (inf) time: 0.6276 [2021-03-26 23:54:39 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 940/1251] eta: 0:03:17 lr: 0.000693 loss: 3.5071 (3.4385) grad_norm: 1.1811 (inf) time: 0.6254 [2021-03-26 23:54:46 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 950/1251] eta: 0:03:10 lr: 0.000693 loss: 3.3302 (3.4366) grad_norm: 1.1958 (inf) time: 0.6261 [2021-03-26 23:54:52 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 960/1251] eta: 0:03:04 lr: 0.000693 loss: 3.5820 (3.4374) grad_norm: 1.3073 (inf) time: 0.6303 [2021-03-26 23:54:58 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 970/1251] eta: 0:02:58 lr: 0.000693 loss: 3.5953 (3.4378) grad_norm: 1.3073 (inf) time: 0.6252 [2021-03-26 23:55:05 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 980/1251] eta: 0:02:51 lr: 0.000693 loss: 3.4447 (3.4375) grad_norm: 1.4034 (inf) time: 0.6235 [2021-03-26 23:55:11 swin_base_patch4_window7_224] INFO: Epoch: [112] [ 990/1251] eta: 0:02:45 lr: 0.000693 loss: 3.5326 (3.4405) grad_norm: 1.3023 (inf) time: 0.6264 [2021-03-26 23:55:17 swin_base_patch4_window7_224] INFO: Epoch: [112] [1000/1251] eta: 0:02:38 lr: 0.000693 loss: 3.6693 (3.4421) grad_norm: 1.2356 (inf) time: 0.6242 [2021-03-26 23:55:23 swin_base_patch4_window7_224] INFO: Epoch: [112] [1010/1251] eta: 0:02:32 lr: 0.000693 loss: 3.4336 (3.4381) grad_norm: 1.2450 (inf) time: 0.6279 [2021-03-26 23:55:30 swin_base_patch4_window7_224] INFO: Epoch: [112] [1020/1251] eta: 0:02:26 lr: 0.000693 loss: 3.5836 (3.4419) grad_norm: 1.2465 (inf) time: 0.6295 [2021-03-26 23:55:36 swin_base_patch4_window7_224] INFO: Epoch: [112] [1030/1251] eta: 0:02:19 lr: 0.000693 loss: 3.7572 (3.4409) grad_norm: 1.2565 (inf) time: 0.6283 [2021-03-26 23:55:42 swin_base_patch4_window7_224] INFO: Epoch: [112] [1040/1251] eta: 0:02:13 lr: 0.000693 loss: 3.1806 (3.4390) grad_norm: 1.2848 (inf) time: 0.6264 [2021-03-26 23:55:48 swin_base_patch4_window7_224] INFO: Epoch: [112] [1050/1251] eta: 0:02:07 lr: 0.000693 loss: 3.2343 (3.4362) grad_norm: 1.2164 (inf) time: 0.6214 [2021-03-26 23:55:55 swin_base_patch4_window7_224] INFO: Epoch: [112] [1060/1251] eta: 0:02:00 lr: 0.000693 loss: 3.4415 (3.4371) grad_norm: 1.2149 (inf) time: 0.6225 [2021-03-26 23:56:01 swin_base_patch4_window7_224] INFO: Epoch: [112] [1070/1251] eta: 0:01:54 lr: 0.000693 loss: 3.6678 (3.4382) grad_norm: 1.2586 (inf) time: 0.6259 [2021-03-26 23:56:07 swin_base_patch4_window7_224] INFO: Epoch: [112] [1080/1251] eta: 0:01:48 lr: 0.000693 loss: 3.6678 (3.4396) grad_norm: 1.2750 (inf) time: 0.6274 [2021-03-26 23:56:13 swin_base_patch4_window7_224] INFO: Epoch: [112] [1090/1251] eta: 0:01:41 lr: 0.000693 loss: 3.5970 (3.4376) grad_norm: 1.2987 (inf) time: 0.6265 [2021-03-26 23:56:20 swin_base_patch4_window7_224] INFO: Epoch: [112] [1100/1251] eta: 0:01:35 lr: 0.000693 loss: 3.1852 (3.4349) grad_norm: 1.2123 (inf) time: 0.6244 [2021-03-26 23:56:26 swin_base_patch4_window7_224] INFO: Epoch: [112] [1110/1251] eta: 0:01:29 lr: 0.000693 loss: 3.1781 (3.4330) grad_norm: 1.2478 (inf) time: 0.6282 [2021-03-26 23:56:32 swin_base_patch4_window7_224] INFO: Epoch: [112] [1120/1251] eta: 0:01:22 lr: 0.000693 loss: 3.3055 (3.4322) grad_norm: 1.2069 (inf) time: 0.6304 [2021-03-26 23:56:39 swin_base_patch4_window7_224] INFO: Epoch: [112] [1130/1251] eta: 0:01:16 lr: 0.000692 loss: 3.5211 (3.4336) grad_norm: 1.2218 (inf) time: 0.6354 [2021-03-26 23:56:45 swin_base_patch4_window7_224] INFO: Epoch: [112] [1140/1251] eta: 0:01:10 lr: 0.000692 loss: 3.6141 (3.4324) grad_norm: 1.2943 (inf) time: 0.6307 [2021-03-26 23:56:51 swin_base_patch4_window7_224] INFO: Epoch: [112] [1150/1251] eta: 0:01:03 lr: 0.000692 loss: 3.0087 (3.4295) grad_norm: 1.1569 (inf) time: 0.6228 [2021-03-26 23:56:57 swin_base_patch4_window7_224] INFO: Epoch: [112] [1160/1251] eta: 0:00:57 lr: 0.000692 loss: 3.2667 (3.4294) grad_norm: 1.1459 (inf) time: 0.6237 [2021-03-26 23:57:04 swin_base_patch4_window7_224] INFO: Epoch: [112] [1170/1251] eta: 0:00:51 lr: 0.000692 loss: 3.6675 (3.4292) grad_norm: 1.1512 (inf) time: 0.6304 [2021-03-26 23:57:10 swin_base_patch4_window7_224] INFO: Epoch: [112] [1180/1251] eta: 0:00:44 lr: 0.000692 loss: 3.6300 (3.4295) grad_norm: 1.1516 (inf) time: 0.6311 [2021-03-26 23:57:16 swin_base_patch4_window7_224] INFO: Epoch: [112] [1190/1251] eta: 0:00:38 lr: 0.000692 loss: 3.4917 (3.4295) grad_norm: 1.1984 (inf) time: 0.6264 [2021-03-26 23:57:23 swin_base_patch4_window7_224] INFO: Epoch: [112] [1200/1251] eta: 0:00:32 lr: 0.000692 loss: 3.5481 (3.4312) grad_norm: 1.2420 (inf) time: 0.6315 [2021-03-26 23:57:29 swin_base_patch4_window7_224] INFO: Epoch: [112] [1210/1251] eta: 0:00:25 lr: 0.000692 loss: 3.6840 (3.4318) grad_norm: 1.1915 (inf) time: 0.6237 [2021-03-26 23:57:35 swin_base_patch4_window7_224] INFO: Epoch: [112] [1220/1251] eta: 0:00:19 lr: 0.000692 loss: 3.3501 (3.4293) grad_norm: 1.2423 (inf) time: 0.6237 [2021-03-26 23:57:41 swin_base_patch4_window7_224] INFO: Epoch: [112] [1230/1251] eta: 0:00:13 lr: 0.000692 loss: 3.3729 (3.4312) grad_norm: 1.2933 (inf) time: 0.6275 [2021-03-26 23:57:48 swin_base_patch4_window7_224] INFO: Epoch: [112] [1240/1251] eta: 0:00:06 lr: 0.000692 loss: 3.7938 (3.4312) grad_norm: 1.2702 (inf) time: 0.6205 [2021-03-26 23:57:54 swin_base_patch4_window7_224] INFO: Epoch: [112] [1250/1251] eta: 0:00:00 lr: 0.000692 loss: 3.5681 (3.4313) grad_norm: 1.2283 (inf) time: 0.6179 [2021-03-26 23:58:01 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:16 loss: 0.8191 (0.8191) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-26 23:58:03 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9924 (1.0128) acc1: 75.0000 (75.5682) acc5: 92.1875 (93.1818) [2021-03-26 23:58:05 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9924 (1.0144) acc1: 75.0000 (76.1905) acc5: 92.1875 (93.6012) [2021-03-26 23:58:08 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9856 (1.0008) acc1: 78.1250 (77.0161) acc5: 93.7500 (93.5988) [2021-03-26 23:58:10 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9856 (1.0094) acc1: 75.0000 (76.6006) acc5: 93.7500 (93.6738) [2021-03-26 23:58:11 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9503 (0.9983) acc1: 76.5625 (76.8640) acc5: 95.3125 (93.9520) [2021-03-26 23:58:17 swin_base_patch4_window7_224] INFO: * Acc@1 77.252 Acc@5 93.918 loss 0.989 [2021-03-26 23:58:17 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.3% [2021-03-26 23:58:17 swin_base_patch4_window7_224] INFO: Max accuracy: 77.34% [2021-03-26 23:58:22 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 0/1251] eta: 1:29:29 lr: 0.000692 loss: 2.8176 (2.8176) grad_norm: 1.1951 (1.1951) time: 4.2922 [2021-03-26 23:58:28 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 10/1251] eta: 0:19:59 lr: 0.000692 loss: 3.5253 (3.5061) grad_norm: 1.3011 (1.2734) time: 0.9670 [2021-03-26 23:58:34 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 20/1251] eta: 0:16:36 lr: 0.000692 loss: 3.4855 (3.3251) grad_norm: 1.3011 (1.2956) time: 0.6354 [2021-03-26 23:58:41 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 30/1251] eta: 0:15:15 lr: 0.000692 loss: 3.4154 (3.3201) grad_norm: 1.3045 (1.3010) time: 0.6304 [2021-03-26 23:58:47 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 40/1251] eta: 0:14:33 lr: 0.000692 loss: 3.4154 (3.3301) grad_norm: 1.2500 (1.2847) time: 0.6287 [2021-03-26 23:58:53 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 50/1251] eta: 0:14:03 lr: 0.000692 loss: 3.3770 (3.3325) grad_norm: 1.2718 (1.3100) time: 0.6289 [2021-03-26 23:59:00 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 60/1251] eta: 0:13:44 lr: 0.000692 loss: 3.4225 (3.3617) grad_norm: 1.3018 (1.2971) time: 0.6315 [2021-03-26 23:59:06 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 70/1251] eta: 0:13:25 lr: 0.000692 loss: 3.6640 (3.3885) grad_norm: 1.2320 (1.2905) time: 0.6298 [2021-03-26 23:59:12 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 80/1251] eta: 0:13:10 lr: 0.000692 loss: 3.5815 (3.3864) grad_norm: 1.2320 (1.2834) time: 0.6245 [2021-03-26 23:59:18 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 90/1251] eta: 0:12:57 lr: 0.000692 loss: 3.5441 (3.4083) grad_norm: 1.2140 (1.2800) time: 0.6273 [2021-03-26 23:59:25 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 100/1251] eta: 0:12:46 lr: 0.000692 loss: 3.4768 (3.3971) grad_norm: 1.2490 (1.2821) time: 0.6299 [2021-03-26 23:59:31 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 110/1251] eta: 0:12:35 lr: 0.000692 loss: 3.4043 (3.3922) grad_norm: 1.2303 (1.2797) time: 0.6277 [2021-03-26 23:59:37 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 120/1251] eta: 0:12:26 lr: 0.000692 loss: 3.5803 (3.3941) grad_norm: 1.2803 (1.2964) time: 0.6303 [2021-03-26 23:59:44 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 130/1251] eta: 0:12:17 lr: 0.000692 loss: 3.5871 (3.4186) grad_norm: 1.3884 (1.3040) time: 0.6352 [2021-03-26 23:59:50 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 140/1251] eta: 0:12:09 lr: 0.000691 loss: 3.5299 (3.4089) grad_norm: 1.2863 (1.3023) time: 0.6332 [2021-03-26 23:59:56 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 150/1251] eta: 0:12:01 lr: 0.000691 loss: 3.5488 (3.4148) grad_norm: 1.2841 (1.3099) time: 0.6342 [2021-03-27 00:00:03 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 160/1251] eta: 0:11:53 lr: 0.000691 loss: 3.2414 (3.4059) grad_norm: 1.3031 (1.3083) time: 0.6374 [2021-03-27 00:00:09 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 170/1251] eta: 0:11:45 lr: 0.000691 loss: 3.2414 (3.4065) grad_norm: 1.2503 (1.3039) time: 0.6337 [2021-03-27 00:00:15 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 180/1251] eta: 0:11:37 lr: 0.000691 loss: 3.6567 (3.4108) grad_norm: 1.2138 (1.3013) time: 0.6307 [2021-03-27 00:00:22 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 190/1251] eta: 0:11:29 lr: 0.000691 loss: 3.5979 (3.4119) grad_norm: 1.2238 (1.2966) time: 0.6301 [2021-03-27 00:00:28 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 200/1251] eta: 0:11:22 lr: 0.000691 loss: 3.5869 (3.4159) grad_norm: 1.2095 (1.2935) time: 0.6258 [2021-03-27 00:00:34 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 210/1251] eta: 0:11:14 lr: 0.000691 loss: 3.5869 (3.4192) grad_norm: 1.1825 (1.2863) time: 0.6286 [2021-03-27 00:00:41 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 220/1251] eta: 0:11:07 lr: 0.000691 loss: 3.5342 (3.4190) grad_norm: 1.1865 (1.2854) time: 0.6336 [2021-03-27 00:00:47 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 230/1251] eta: 0:11:00 lr: 0.000691 loss: 3.6037 (3.4174) grad_norm: 1.2360 (1.2862) time: 0.6346 [2021-03-27 00:00:53 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 240/1251] eta: 0:10:53 lr: 0.000691 loss: 3.5309 (3.4206) grad_norm: 1.2256 (1.2834) time: 0.6309 [2021-03-27 00:00:59 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 250/1251] eta: 0:10:46 lr: 0.000691 loss: 3.4863 (3.4177) grad_norm: 1.1990 (1.2810) time: 0.6282 [2021-03-27 00:01:06 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 260/1251] eta: 0:10:39 lr: 0.000691 loss: 3.4034 (3.4214) grad_norm: 1.3080 (1.2875) time: 0.6365 [2021-03-27 00:01:12 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 270/1251] eta: 0:10:32 lr: 0.000691 loss: 3.3398 (3.4159) grad_norm: 1.3904 (1.2908) time: 0.6351 [2021-03-27 00:01:18 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 280/1251] eta: 0:10:25 lr: 0.000691 loss: 3.2677 (3.4150) grad_norm: 1.3297 (1.2920) time: 0.6274 [2021-03-27 00:01:25 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 290/1251] eta: 0:10:19 lr: 0.000691 loss: 3.4592 (3.4166) grad_norm: 1.3297 (1.2944) time: 0.6397 [2021-03-27 00:01:31 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 300/1251] eta: 0:10:12 lr: 0.000691 loss: 3.6722 (3.4259) grad_norm: 1.3133 (1.2953) time: 0.6420 [2021-03-27 00:01:38 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 310/1251] eta: 0:10:05 lr: 0.000691 loss: 3.6722 (3.4247) grad_norm: 1.3004 (1.2951) time: 0.6291 [2021-03-27 00:01:44 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 320/1251] eta: 0:09:58 lr: 0.000691 loss: 3.4058 (3.4227) grad_norm: 1.2514 (1.2945) time: 0.6283 [2021-03-27 00:01:50 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 330/1251] eta: 0:09:51 lr: 0.000691 loss: 3.6593 (3.4293) grad_norm: 1.2489 (1.2933) time: 0.6308 [2021-03-27 00:01:56 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 340/1251] eta: 0:09:45 lr: 0.000691 loss: 3.6122 (3.4317) grad_norm: 1.2274 (1.2951) time: 0.6284 [2021-03-27 00:02:03 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 350/1251] eta: 0:09:38 lr: 0.000691 loss: 3.5003 (3.4363) grad_norm: 1.2466 (1.2948) time: 0.6305 [2021-03-27 00:02:09 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 360/1251] eta: 0:09:31 lr: 0.000691 loss: 3.7531 (3.4438) grad_norm: 1.2466 (1.2939) time: 0.6284 [2021-03-27 00:02:15 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 370/1251] eta: 0:09:24 lr: 0.000691 loss: 3.6400 (3.4428) grad_norm: 1.2930 (1.2938) time: 0.6224 [2021-03-27 00:02:22 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 380/1251] eta: 0:09:17 lr: 0.000691 loss: 3.6020 (3.4447) grad_norm: 1.1774 (1.2914) time: 0.6238 [2021-03-27 00:02:28 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 390/1251] eta: 0:09:11 lr: 0.000691 loss: 3.6615 (3.4506) grad_norm: 1.2383 (1.2927) time: 0.6257 [2021-03-27 00:02:34 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 400/1251] eta: 0:09:04 lr: 0.000690 loss: 3.6615 (3.4515) grad_norm: 1.2959 (1.2925) time: 0.6291 [2021-03-27 00:02:40 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 410/1251] eta: 0:08:58 lr: 0.000690 loss: 3.5639 (3.4491) grad_norm: 1.2688 (1.2917) time: 0.6330 [2021-03-27 00:02:47 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 420/1251] eta: 0:08:51 lr: 0.000690 loss: 3.3469 (3.4466) grad_norm: 1.2489 (1.2907) time: 0.6253 [2021-03-27 00:02:53 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 430/1251] eta: 0:08:44 lr: 0.000690 loss: 3.3430 (3.4470) grad_norm: 1.2344 (1.2895) time: 0.6228 [2021-03-27 00:02:59 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 440/1251] eta: 0:08:38 lr: 0.000690 loss: 3.3551 (3.4469) grad_norm: 1.2600 (1.2900) time: 0.6291 [2021-03-27 00:03:05 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 450/1251] eta: 0:08:31 lr: 0.000690 loss: 3.3551 (3.4479) grad_norm: 1.3701 (1.2923) time: 0.6265 [2021-03-27 00:03:12 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 460/1251] eta: 0:08:24 lr: 0.000690 loss: 3.4588 (3.4479) grad_norm: 1.3105 (1.2907) time: 0.6246 [2021-03-27 00:03:18 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 470/1251] eta: 0:08:18 lr: 0.000690 loss: 3.4734 (3.4488) grad_norm: 1.2698 (1.2901) time: 0.6283 [2021-03-27 00:03:24 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 480/1251] eta: 0:08:11 lr: 0.000690 loss: 3.3132 (3.4467) grad_norm: 1.2377 (1.2885) time: 0.6330 [2021-03-27 00:03:31 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 490/1251] eta: 0:08:05 lr: 0.000690 loss: 3.3733 (3.4473) grad_norm: 1.1407 (1.2866) time: 0.6359 [2021-03-27 00:03:37 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 500/1251] eta: 0:07:58 lr: 0.000690 loss: 3.4903 (3.4474) grad_norm: 1.1787 (1.2852) time: 0.6288 [2021-03-27 00:03:43 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 510/1251] eta: 0:07:52 lr: 0.000690 loss: 3.3131 (3.4391) grad_norm: 1.2368 (1.2857) time: 0.6274 [2021-03-27 00:03:50 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 520/1251] eta: 0:07:46 lr: 0.000690 loss: 3.4722 (3.4429) grad_norm: 1.3185 (1.2868) time: 0.6370 [2021-03-27 00:03:56 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 530/1251] eta: 0:07:39 lr: 0.000690 loss: 3.5440 (3.4444) grad_norm: 1.3185 (1.2868) time: 0.6314 [2021-03-27 00:04:02 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 540/1251] eta: 0:07:33 lr: 0.000690 loss: 3.5440 (3.4442) grad_norm: 1.2988 (1.2879) time: 0.6283 [2021-03-27 00:04:09 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 550/1251] eta: 0:07:26 lr: 0.000690 loss: 3.5275 (3.4454) grad_norm: 1.2988 (1.2894) time: 0.6423 [2021-03-27 00:04:15 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 560/1251] eta: 0:07:20 lr: 0.000690 loss: 3.5275 (3.4458) grad_norm: 1.3036 (1.2910) time: 0.6407 [2021-03-27 00:04:21 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 570/1251] eta: 0:07:14 lr: 0.000690 loss: 3.3057 (3.4420) grad_norm: 1.3424 (1.2920) time: 0.6347 [2021-03-27 00:04:28 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 580/1251] eta: 0:07:07 lr: 0.000690 loss: 3.2664 (3.4396) grad_norm: 1.2630 (1.2912) time: 0.6328 [2021-03-27 00:04:34 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 590/1251] eta: 0:07:01 lr: 0.000690 loss: 3.4238 (3.4424) grad_norm: 1.1820 (1.2904) time: 0.6335 [2021-03-27 00:04:40 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 600/1251] eta: 0:06:54 lr: 0.000690 loss: 3.5051 (3.4402) grad_norm: 1.2323 (1.2914) time: 0.6328 [2021-03-27 00:04:47 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 610/1251] eta: 0:06:48 lr: 0.000690 loss: 3.3012 (3.4374) grad_norm: 1.2446 (1.2914) time: 0.6245 [2021-03-27 00:04:53 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 620/1251] eta: 0:06:41 lr: 0.000690 loss: 3.3497 (3.4375) grad_norm: 1.2745 (1.2918) time: 0.6234 [2021-03-27 00:04:59 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 630/1251] eta: 0:06:35 lr: 0.000690 loss: 3.4185 (3.4355) grad_norm: 1.2211 (1.2906) time: 0.6238 [2021-03-27 00:05:05 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 640/1251] eta: 0:06:28 lr: 0.000690 loss: 3.4589 (3.4349) grad_norm: 1.2147 (1.2896) time: 0.6231 [2021-03-27 00:05:12 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 650/1251] eta: 0:06:22 lr: 0.000690 loss: 3.4774 (3.4334) grad_norm: 1.1638 (1.2874) time: 0.6377 [2021-03-27 00:05:18 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 660/1251] eta: 0:06:16 lr: 0.000689 loss: 3.3340 (3.4318) grad_norm: 1.1928 (1.2865) time: 0.6379 [2021-03-27 00:05:24 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 670/1251] eta: 0:06:09 lr: 0.000689 loss: 3.3849 (3.4320) grad_norm: 1.2156 (1.2858) time: 0.6231 [2021-03-27 00:05:31 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 680/1251] eta: 0:06:03 lr: 0.000689 loss: 3.3849 (3.4311) grad_norm: 1.1950 (1.2858) time: 0.6251 [2021-03-27 00:05:37 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 690/1251] eta: 0:05:56 lr: 0.000689 loss: 3.4417 (3.4325) grad_norm: 1.2290 (1.2863) time: 0.6354 [2021-03-27 00:05:43 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 700/1251] eta: 0:05:50 lr: 0.000689 loss: 3.5896 (3.4332) grad_norm: 1.2508 (1.2857) time: 0.6390 [2021-03-27 00:05:50 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 710/1251] eta: 0:05:44 lr: 0.000689 loss: 3.5672 (3.4337) grad_norm: 1.2616 (1.2855) time: 0.6354 [2021-03-27 00:05:56 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 720/1251] eta: 0:05:37 lr: 0.000689 loss: 3.5526 (3.4322) grad_norm: 1.2556 (1.2847) time: 0.6287 [2021-03-27 00:06:02 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 730/1251] eta: 0:05:31 lr: 0.000689 loss: 3.4079 (3.4341) grad_norm: 1.2503 (1.2841) time: 0.6293 [2021-03-27 00:06:09 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 740/1251] eta: 0:05:24 lr: 0.000689 loss: 3.5726 (3.4353) grad_norm: 1.2162 (1.2838) time: 0.6425 [2021-03-27 00:06:15 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 750/1251] eta: 0:05:18 lr: 0.000689 loss: 3.6069 (3.4355) grad_norm: 1.2099 (1.2829) time: 0.6387 [2021-03-27 00:06:21 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 760/1251] eta: 0:05:12 lr: 0.000689 loss: 3.4247 (3.4344) grad_norm: 1.2152 (1.2826) time: 0.6302 [2021-03-27 00:06:28 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 770/1251] eta: 0:05:05 lr: 0.000689 loss: 3.5583 (3.4392) grad_norm: 1.2395 (1.2822) time: 0.6314 [2021-03-27 00:06:34 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 780/1251] eta: 0:04:59 lr: 0.000689 loss: 3.5802 (3.4369) grad_norm: 1.2560 (1.2824) time: 0.6287 [2021-03-27 00:06:40 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 790/1251] eta: 0:04:52 lr: 0.000689 loss: 3.3693 (3.4366) grad_norm: 1.2560 (1.2818) time: 0.6268 [2021-03-27 00:06:46 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 800/1251] eta: 0:04:46 lr: 0.000689 loss: 3.3984 (3.4375) grad_norm: 1.2243 (1.2818) time: 0.6258 [2021-03-27 00:06:53 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 810/1251] eta: 0:04:40 lr: 0.000689 loss: 3.3772 (3.4377) grad_norm: 1.2943 (1.2832) time: 0.6295 [2021-03-27 00:06:59 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 820/1251] eta: 0:04:33 lr: 0.000689 loss: 3.4546 (3.4388) grad_norm: 1.2411 (1.2826) time: 0.6271 [2021-03-27 00:07:05 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 830/1251] eta: 0:04:27 lr: 0.000689 loss: 3.6949 (3.4397) grad_norm: 1.1857 (1.2830) time: 0.6214 [2021-03-27 00:07:12 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 840/1251] eta: 0:04:21 lr: 0.000689 loss: 3.5902 (3.4395) grad_norm: 1.2366 (1.2828) time: 0.6312 [2021-03-27 00:07:18 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 850/1251] eta: 0:04:14 lr: 0.000689 loss: 3.1948 (3.4371) grad_norm: 1.1910 (1.2819) time: 0.6335 [2021-03-27 00:07:24 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 860/1251] eta: 0:04:08 lr: 0.000689 loss: 3.2358 (3.4379) grad_norm: 1.1977 (1.2814) time: 0.6312 [2021-03-27 00:07:31 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 870/1251] eta: 0:04:01 lr: 0.000689 loss: 3.6406 (3.4394) grad_norm: 1.2725 (1.2817) time: 0.6325 [2021-03-27 00:07:37 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 880/1251] eta: 0:03:55 lr: 0.000689 loss: 3.4656 (3.4362) grad_norm: 1.2866 (1.2815) time: 0.6281 [2021-03-27 00:07:43 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 890/1251] eta: 0:03:49 lr: 0.000689 loss: 3.1650 (3.4335) grad_norm: 1.2568 (1.2816) time: 0.6294 [2021-03-27 00:07:49 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 900/1251] eta: 0:03:42 lr: 0.000689 loss: 3.3298 (3.4349) grad_norm: 1.2841 (1.2814) time: 0.6315 [2021-03-27 00:07:56 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 910/1251] eta: 0:03:36 lr: 0.000689 loss: 3.5357 (3.4342) grad_norm: 1.2841 (1.2816) time: 0.6310 [2021-03-27 00:08:02 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 920/1251] eta: 0:03:30 lr: 0.000688 loss: 3.4516 (3.4353) grad_norm: 1.3629 (1.2826) time: 0.6290 [2021-03-27 00:08:08 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 930/1251] eta: 0:03:23 lr: 0.000688 loss: 3.5044 (3.4346) grad_norm: 1.3124 (1.2829) time: 0.6282 [2021-03-27 00:08:15 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 940/1251] eta: 0:03:17 lr: 0.000688 loss: 3.4950 (3.4329) grad_norm: 1.2183 (1.2832) time: 0.6300 [2021-03-27 00:08:21 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 950/1251] eta: 0:03:10 lr: 0.000688 loss: 3.6413 (3.4347) grad_norm: 1.1997 (1.2829) time: 0.6261 [2021-03-27 00:08:27 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 960/1251] eta: 0:03:04 lr: 0.000688 loss: 3.5439 (3.4339) grad_norm: 1.1780 (1.2819) time: 0.6233 [2021-03-27 00:08:33 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 970/1251] eta: 0:02:58 lr: 0.000688 loss: 3.4915 (3.4317) grad_norm: 1.2157 (1.2814) time: 0.6255 [2021-03-27 00:08:40 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 980/1251] eta: 0:02:51 lr: 0.000688 loss: 3.0269 (3.4305) grad_norm: 1.2157 (1.2809) time: 0.6240 [2021-03-27 00:08:46 swin_base_patch4_window7_224] INFO: Epoch: [113] [ 990/1251] eta: 0:02:45 lr: 0.000688 loss: 3.6590 (3.4316) grad_norm: 1.2732 (1.2830) time: 0.6256 [2021-03-27 00:08:52 swin_base_patch4_window7_224] INFO: Epoch: [113] [1000/1251] eta: 0:02:39 lr: 0.000688 loss: 3.5556 (3.4292) grad_norm: 1.2945 (1.2834) time: 0.6348 [2021-03-27 00:08:59 swin_base_patch4_window7_224] INFO: Epoch: [113] [1010/1251] eta: 0:02:32 lr: 0.000688 loss: 3.5031 (3.4304) grad_norm: 1.2794 (1.2837) time: 0.6335 [2021-03-27 00:09:05 swin_base_patch4_window7_224] INFO: Epoch: [113] [1020/1251] eta: 0:02:26 lr: 0.000688 loss: 3.5216 (3.4302) grad_norm: 1.2794 (1.2837) time: 0.6242 [2021-03-27 00:09:11 swin_base_patch4_window7_224] INFO: Epoch: [113] [1030/1251] eta: 0:02:20 lr: 0.000688 loss: 3.3410 (3.4314) grad_norm: 1.3041 (1.2842) time: 0.6237 [2021-03-27 00:09:17 swin_base_patch4_window7_224] INFO: Epoch: [113] [1040/1251] eta: 0:02:13 lr: 0.000688 loss: 3.3428 (3.4293) grad_norm: 1.2991 (1.2847) time: 0.6335 [2021-03-27 00:09:24 swin_base_patch4_window7_224] INFO: Epoch: [113] [1050/1251] eta: 0:02:07 lr: 0.000688 loss: 3.2370 (3.4271) grad_norm: 1.2357 (1.2844) time: 0.6323 [2021-03-27 00:09:30 swin_base_patch4_window7_224] INFO: Epoch: [113] [1060/1251] eta: 0:02:01 lr: 0.000688 loss: 3.3648 (3.4265) grad_norm: 1.2360 (1.2857) time: 0.6326 [2021-03-27 00:09:36 swin_base_patch4_window7_224] INFO: Epoch: [113] [1070/1251] eta: 0:01:54 lr: 0.000688 loss: 3.5352 (3.4263) grad_norm: 1.3128 (1.2867) time: 0.6350 [2021-03-27 00:09:43 swin_base_patch4_window7_224] INFO: Epoch: [113] [1080/1251] eta: 0:01:48 lr: 0.000688 loss: 3.5352 (3.4280) grad_norm: 1.3345 (1.2881) time: 0.6297 [2021-03-27 00:09:49 swin_base_patch4_window7_224] INFO: Epoch: [113] [1090/1251] eta: 0:01:42 lr: 0.000688 loss: 3.5606 (3.4295) grad_norm: 1.3626 (1.2899) time: 0.6301 [2021-03-27 00:09:55 swin_base_patch4_window7_224] INFO: Epoch: [113] [1100/1251] eta: 0:01:35 lr: 0.000688 loss: 3.5112 (3.4302) grad_norm: 1.3606 (1.2910) time: 0.6292 [2021-03-27 00:10:02 swin_base_patch4_window7_224] INFO: Epoch: [113] [1110/1251] eta: 0:01:29 lr: 0.000688 loss: 3.2437 (3.4279) grad_norm: 1.3077 (1.2906) time: 0.6277 [2021-03-27 00:10:08 swin_base_patch4_window7_224] INFO: Epoch: [113] [1120/1251] eta: 0:01:23 lr: 0.000688 loss: 3.2437 (3.4286) grad_norm: 1.2626 (1.2905) time: 0.6283 [2021-03-27 00:10:14 swin_base_patch4_window7_224] INFO: Epoch: [113] [1130/1251] eta: 0:01:16 lr: 0.000688 loss: 3.3009 (3.4267) grad_norm: 1.2733 (1.2916) time: 0.6249 [2021-03-27 00:10:20 swin_base_patch4_window7_224] INFO: Epoch: [113] [1140/1251] eta: 0:01:10 lr: 0.000688 loss: 3.3691 (3.4282) grad_norm: 1.2663 (1.2913) time: 0.6265 [2021-03-27 00:10:27 swin_base_patch4_window7_224] INFO: Epoch: [113] [1150/1251] eta: 0:01:03 lr: 0.000688 loss: 3.4448 (3.4278) grad_norm: 1.2057 (1.2910) time: 0.6263 [2021-03-27 00:10:33 swin_base_patch4_window7_224] INFO: Epoch: [113] [1160/1251] eta: 0:00:57 lr: 0.000688 loss: 3.4414 (3.4288) grad_norm: 1.2513 (1.2907) time: 0.6207 [2021-03-27 00:10:39 swin_base_patch4_window7_224] INFO: Epoch: [113] [1170/1251] eta: 0:00:51 lr: 0.000688 loss: 3.4335 (3.4287) grad_norm: 1.2454 (1.2903) time: 0.6271 [2021-03-27 00:10:45 swin_base_patch4_window7_224] INFO: Epoch: [113] [1180/1251] eta: 0:00:44 lr: 0.000687 loss: 3.3884 (3.4284) grad_norm: 1.2439 (1.2901) time: 0.6293 [2021-03-27 00:10:52 swin_base_patch4_window7_224] INFO: Epoch: [113] [1190/1251] eta: 0:00:38 lr: 0.000687 loss: 3.3884 (3.4284) grad_norm: 1.2439 (1.2900) time: 0.6246 [2021-03-27 00:10:58 swin_base_patch4_window7_224] INFO: Epoch: [113] [1200/1251] eta: 0:00:32 lr: 0.000687 loss: 3.6710 (3.4311) grad_norm: 1.2786 (1.2904) time: 0.6270 [2021-03-27 00:11:04 swin_base_patch4_window7_224] INFO: Epoch: [113] [1210/1251] eta: 0:00:25 lr: 0.000687 loss: 3.7231 (3.4309) grad_norm: 1.2786 (1.2904) time: 0.6284 [2021-03-27 00:11:11 swin_base_patch4_window7_224] INFO: Epoch: [113] [1220/1251] eta: 0:00:19 lr: 0.000687 loss: 3.3568 (3.4302) grad_norm: 1.2799 (1.2909) time: 0.6331 [2021-03-27 00:11:17 swin_base_patch4_window7_224] INFO: Epoch: [113] [1230/1251] eta: 0:00:13 lr: 0.000687 loss: 3.3054 (3.4294) grad_norm: 1.2326 (1.2902) time: 0.6320 [2021-03-27 00:11:23 swin_base_patch4_window7_224] INFO: Epoch: [113] [1240/1251] eta: 0:00:06 lr: 0.000687 loss: 3.3357 (3.4297) grad_norm: 1.2165 (1.2901) time: 0.6200 [2021-03-27 00:11:29 swin_base_patch4_window7_224] INFO: Epoch: [113] [1250/1251] eta: 0:00:00 lr: 0.000687 loss: 3.4220 (3.4291) grad_norm: 1.2570 (1.2908) time: 0.6199 [2021-03-27 00:11:37 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:23 loss: 0.6735 (0.6735) acc1: 85.9375 (85.9375) acc5: 98.4375 (98.4375) [2021-03-27 00:11:38 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.1035 (1.1176) acc1: 78.1250 (76.2784) acc5: 93.7500 (92.8977) [2021-03-27 00:11:41 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0906 (1.0928) acc1: 76.5625 (76.3393) acc5: 93.7500 (93.1548) [2021-03-27 00:11:43 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0906 (1.0747) acc1: 76.5625 (75.7560) acc5: 93.7500 (93.2964) [2021-03-27 00:11:45 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9511 (1.0375) acc1: 76.5625 (76.4863) acc5: 95.3125 (93.8262) [2021-03-27 00:11:46 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9299 (1.0207) acc1: 76.5625 (76.6720) acc5: 95.3125 (93.9520) [2021-03-27 00:11:53 swin_base_patch4_window7_224] INFO: * Acc@1 77.244 Acc@5 94.052 loss 0.998 [2021-03-27 00:11:53 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.2% [2021-03-27 00:11:53 swin_base_patch4_window7_224] INFO: Max accuracy: 77.34% [2021-03-27 00:11:57 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 0/1251] eta: 1:28:05 lr: 0.000687 loss: 3.8873 (3.8873) grad_norm: 1.3038 (1.3038) time: 4.2248 [2021-03-27 00:12:04 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 10/1251] eta: 0:20:09 lr: 0.000687 loss: 3.5595 (3.4583) grad_norm: 1.3038 (1.3354) time: 0.9743 [2021-03-27 00:12:10 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 20/1251] eta: 0:16:46 lr: 0.000687 loss: 3.5204 (3.5051) grad_norm: 1.2600 (1.3473) time: 0.6474 [2021-03-27 00:12:17 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 30/1251] eta: 0:15:25 lr: 0.000687 loss: 3.3055 (3.3887) grad_norm: 1.2600 (1.3224) time: 0.6385 [2021-03-27 00:12:23 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 40/1251] eta: 0:14:38 lr: 0.000687 loss: 3.0755 (3.3423) grad_norm: 1.2784 (1.3176) time: 0.6290 [2021-03-27 00:12:29 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 50/1251] eta: 0:14:08 lr: 0.000687 loss: 3.1503 (3.3520) grad_norm: 1.2784 (1.3064) time: 0.6262 [2021-03-27 00:12:35 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 60/1251] eta: 0:13:46 lr: 0.000687 loss: 3.5029 (3.3721) grad_norm: 1.2549 (1.3156) time: 0.6281 [2021-03-27 00:12:42 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 70/1251] eta: 0:13:30 lr: 0.000687 loss: 3.4764 (3.3654) grad_norm: 1.2983 (1.3086) time: 0.6367 [2021-03-27 00:12:48 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 80/1251] eta: 0:13:16 lr: 0.000687 loss: 3.4638 (3.3675) grad_norm: 1.2666 (1.3128) time: 0.6383 [2021-03-27 00:12:54 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 90/1251] eta: 0:13:01 lr: 0.000687 loss: 3.4638 (3.3733) grad_norm: 1.2666 (1.3131) time: 0.6268 [2021-03-27 00:13:01 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 100/1251] eta: 0:12:50 lr: 0.000687 loss: 3.4852 (3.3835) grad_norm: 1.2745 (1.3101) time: 0.6264 [2021-03-27 00:13:07 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 110/1251] eta: 0:12:39 lr: 0.000687 loss: 3.5856 (3.3921) grad_norm: 1.2856 (1.3099) time: 0.6279 [2021-03-27 00:13:13 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 120/1251] eta: 0:12:29 lr: 0.000687 loss: 3.6600 (3.4061) grad_norm: 1.3315 (1.3119) time: 0.6295 [2021-03-27 00:13:20 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 130/1251] eta: 0:12:20 lr: 0.000687 loss: 3.6633 (3.4220) grad_norm: 1.3023 (1.3133) time: 0.6319 [2021-03-27 00:13:26 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 140/1251] eta: 0:12:11 lr: 0.000687 loss: 3.6122 (3.4318) grad_norm: 1.2574 (1.3101) time: 0.6293 [2021-03-27 00:13:32 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 150/1251] eta: 0:12:02 lr: 0.000687 loss: 3.5612 (3.4400) grad_norm: 1.2574 (1.3145) time: 0.6307 [2021-03-27 00:13:39 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 160/1251] eta: 0:11:53 lr: 0.000687 loss: 3.6522 (3.4453) grad_norm: 1.3616 (1.3167) time: 0.6283 [2021-03-27 00:13:45 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 170/1251] eta: 0:11:46 lr: 0.000687 loss: 3.5782 (3.4376) grad_norm: 1.2950 (1.3155) time: 0.6360 [2021-03-27 00:13:51 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 180/1251] eta: 0:11:38 lr: 0.000687 loss: 3.4208 (3.4317) grad_norm: 1.1664 (1.3087) time: 0.6366 [2021-03-27 00:13:58 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 190/1251] eta: 0:11:30 lr: 0.000686 loss: 3.4208 (3.4330) grad_norm: 1.1429 (1.3017) time: 0.6260 [2021-03-27 00:14:04 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 200/1251] eta: 0:11:23 lr: 0.000686 loss: 3.4485 (3.4311) grad_norm: 1.2367 (1.3048) time: 0.6330 [2021-03-27 00:14:10 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 210/1251] eta: 0:11:16 lr: 0.000686 loss: 3.5027 (3.4203) grad_norm: 1.3746 (1.3115) time: 0.6372 [2021-03-27 00:14:16 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 220/1251] eta: 0:11:08 lr: 0.000686 loss: 3.5027 (3.4191) grad_norm: 1.2876 (1.3069) time: 0.6272 [2021-03-27 00:14:23 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 230/1251] eta: 0:11:01 lr: 0.000686 loss: 3.4972 (3.4221) grad_norm: 1.2505 (1.3084) time: 0.6260 [2021-03-27 00:14:29 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 240/1251] eta: 0:10:53 lr: 0.000686 loss: 3.4972 (3.4222) grad_norm: 1.2739 (1.3104) time: 0.6272 [2021-03-27 00:14:35 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 250/1251] eta: 0:10:46 lr: 0.000686 loss: 3.5729 (3.4270) grad_norm: 1.3405 (1.3120) time: 0.6236 [2021-03-27 00:14:42 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 260/1251] eta: 0:10:39 lr: 0.000686 loss: 3.4267 (3.4276) grad_norm: 1.3398 (1.3127) time: 0.6253 [2021-03-27 00:14:48 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 270/1251] eta: 0:10:32 lr: 0.000686 loss: 3.5765 (3.4336) grad_norm: 1.3016 (1.3146) time: 0.6369 [2021-03-27 00:14:54 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 280/1251] eta: 0:10:26 lr: 0.000686 loss: 3.5765 (3.4339) grad_norm: 1.2440 (1.3142) time: 0.6418 [2021-03-27 00:15:01 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 290/1251] eta: 0:10:19 lr: 0.000686 loss: 3.4397 (3.4374) grad_norm: 1.2490 (1.3138) time: 0.6319 [2021-03-27 00:15:07 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 300/1251] eta: 0:10:12 lr: 0.000686 loss: 3.4397 (3.4328) grad_norm: 1.2605 (1.3134) time: 0.6307 [2021-03-27 00:15:13 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 310/1251] eta: 0:10:05 lr: 0.000686 loss: 3.4503 (3.4300) grad_norm: 1.2488 (1.3140) time: 0.6354 [2021-03-27 00:15:20 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 320/1251] eta: 0:09:58 lr: 0.000686 loss: 3.4859 (3.4314) grad_norm: 1.3868 (1.3183) time: 0.6298 [2021-03-27 00:15:26 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 330/1251] eta: 0:09:51 lr: 0.000686 loss: 3.5088 (3.4341) grad_norm: 1.3855 (1.3192) time: 0.6301 [2021-03-27 00:15:32 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 340/1251] eta: 0:09:45 lr: 0.000686 loss: 3.2063 (3.4260) grad_norm: 1.3132 (1.3199) time: 0.6394 [2021-03-27 00:15:39 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 350/1251] eta: 0:09:38 lr: 0.000686 loss: 3.2518 (3.4311) grad_norm: 1.2745 (1.3162) time: 0.6346 [2021-03-27 00:15:45 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 360/1251] eta: 0:09:31 lr: 0.000686 loss: 3.6338 (3.4334) grad_norm: 1.1771 (1.3135) time: 0.6259 [2021-03-27 00:15:51 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 370/1251] eta: 0:09:25 lr: 0.000686 loss: 3.6338 (3.4328) grad_norm: 1.2137 (1.3146) time: 0.6245 [2021-03-27 00:15:57 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 380/1251] eta: 0:09:18 lr: 0.000686 loss: 3.6783 (3.4332) grad_norm: 1.2059 (1.3119) time: 0.6236 [2021-03-27 00:16:04 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 390/1251] eta: 0:09:11 lr: 0.000686 loss: 3.6474 (3.4338) grad_norm: 1.2341 (1.3116) time: 0.6260 [2021-03-27 00:16:10 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 400/1251] eta: 0:09:04 lr: 0.000686 loss: 3.6474 (3.4393) grad_norm: 1.2341 (1.3102) time: 0.6301 [2021-03-27 00:16:16 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 410/1251] eta: 0:08:58 lr: 0.000686 loss: 3.6729 (3.4352) grad_norm: 1.2197 (1.3083) time: 0.6293 [2021-03-27 00:16:23 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 420/1251] eta: 0:08:51 lr: 0.000686 loss: 3.2433 (3.4293) grad_norm: 1.2303 (1.3090) time: 0.6253 [2021-03-27 00:16:29 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 430/1251] eta: 0:08:45 lr: 0.000686 loss: 3.4576 (3.4316) grad_norm: 1.2525 (1.3083) time: 0.6307 [2021-03-27 00:16:35 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 440/1251] eta: 0:08:38 lr: 0.000686 loss: 3.5017 (3.4288) grad_norm: 1.2600 (1.3082) time: 0.6370 [2021-03-27 00:16:42 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 450/1251] eta: 0:08:32 lr: 0.000685 loss: 3.5868 (3.4306) grad_norm: 1.3246 (1.3099) time: 0.6326 [2021-03-27 00:16:48 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 460/1251] eta: 0:08:25 lr: 0.000685 loss: 3.5464 (3.4336) grad_norm: 1.3119 (1.3086) time: 0.6292 [2021-03-27 00:16:54 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 470/1251] eta: 0:08:18 lr: 0.000685 loss: 3.5551 (3.4394) grad_norm: 1.2203 (1.3072) time: 0.6247 [2021-03-27 00:17:00 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 480/1251] eta: 0:08:12 lr: 0.000685 loss: 3.5503 (3.4290) grad_norm: 1.1948 (1.3052) time: 0.6241 [2021-03-27 00:17:07 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 490/1251] eta: 0:08:05 lr: 0.000685 loss: 3.1234 (3.4294) grad_norm: 1.1948 (1.3045) time: 0.6288 [2021-03-27 00:17:13 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 500/1251] eta: 0:07:59 lr: 0.000685 loss: 3.0862 (3.4241) grad_norm: 1.2340 (1.3037) time: 0.6313 [2021-03-27 00:17:19 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 510/1251] eta: 0:07:52 lr: 0.000685 loss: 3.1004 (3.4234) grad_norm: 1.2340 (1.3023) time: 0.6270 [2021-03-27 00:17:26 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 520/1251] eta: 0:07:46 lr: 0.000685 loss: 3.3612 (3.4226) grad_norm: 1.2850 (1.3048) time: 0.6268 [2021-03-27 00:17:32 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 530/1251] eta: 0:07:39 lr: 0.000685 loss: 3.3166 (3.4223) grad_norm: 1.4032 (1.3075) time: 0.6357 [2021-03-27 00:17:38 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 540/1251] eta: 0:07:33 lr: 0.000685 loss: 3.2456 (3.4160) grad_norm: 1.3646 (1.3076) time: 0.6356 [2021-03-27 00:17:45 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 550/1251] eta: 0:07:27 lr: 0.000685 loss: 3.2225 (3.4128) grad_norm: 1.2710 (1.3077) time: 0.6384 [2021-03-27 00:17:51 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 560/1251] eta: 0:07:20 lr: 0.000685 loss: 3.4687 (3.4143) grad_norm: 1.2710 (1.3066) time: 0.6349 [2021-03-27 00:17:57 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 570/1251] eta: 0:07:14 lr: 0.000685 loss: 3.4582 (3.4066) grad_norm: 1.2528 (1.3055) time: 0.6278 [2021-03-27 00:18:03 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 580/1251] eta: 0:07:07 lr: 0.000685 loss: 3.4153 (3.4078) grad_norm: 1.2528 (1.3066) time: 0.6278 [2021-03-27 00:18:10 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 590/1251] eta: 0:07:01 lr: 0.000685 loss: 3.4153 (3.4029) grad_norm: 1.3833 (1.3097) time: 0.6297 [2021-03-27 00:18:16 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 600/1251] eta: 0:06:54 lr: 0.000685 loss: 3.5122 (3.4062) grad_norm: 1.2515 (1.3095) time: 0.6311 [2021-03-27 00:18:23 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 610/1251] eta: 0:06:48 lr: 0.000685 loss: 3.6221 (3.4050) grad_norm: 1.1898 (1.3084) time: 0.6356 [2021-03-27 00:18:29 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 620/1251] eta: 0:06:42 lr: 0.000685 loss: 3.7521 (3.4124) grad_norm: 1.2120 (1.3074) time: 0.6414 [2021-03-27 00:18:35 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 630/1251] eta: 0:06:35 lr: 0.000685 loss: 3.8433 (3.4170) grad_norm: 1.2330 (1.3067) time: 0.6435 [2021-03-27 00:18:42 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 640/1251] eta: 0:06:29 lr: 0.000685 loss: 3.7720 (3.4226) grad_norm: 1.3166 (1.3078) time: 0.6392 [2021-03-27 00:18:48 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 650/1251] eta: 0:06:22 lr: 0.000685 loss: 3.4744 (3.4191) grad_norm: 1.2868 (1.3068) time: 0.6302 [2021-03-27 00:18:54 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 660/1251] eta: 0:06:16 lr: 0.000685 loss: 3.3917 (3.4191) grad_norm: 1.2858 (1.3071) time: 0.6290 [2021-03-27 00:19:01 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 670/1251] eta: 0:06:09 lr: 0.000685 loss: 3.5735 (3.4195) grad_norm: 1.2858 (1.3061) time: 0.6267 [2021-03-27 00:19:07 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 680/1251] eta: 0:06:03 lr: 0.000685 loss: 3.5735 (3.4223) grad_norm: 1.2926 (1.3073) time: 0.6297 [2021-03-27 00:19:13 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 690/1251] eta: 0:05:57 lr: 0.000685 loss: 3.6516 (3.4235) grad_norm: 1.3167 (1.3075) time: 0.6316 [2021-03-27 00:19:20 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 700/1251] eta: 0:05:50 lr: 0.000685 loss: 3.5450 (3.4235) grad_norm: 1.2628 (1.3074) time: 0.6318 [2021-03-27 00:19:26 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 710/1251] eta: 0:05:44 lr: 0.000684 loss: 3.6295 (3.4252) grad_norm: 1.2502 (1.3063) time: 0.6297 [2021-03-27 00:19:32 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 720/1251] eta: 0:05:37 lr: 0.000684 loss: 3.5873 (3.4229) grad_norm: 1.2658 (1.3076) time: 0.6268 [2021-03-27 00:19:38 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 730/1251] eta: 0:05:31 lr: 0.000684 loss: 3.2088 (3.4219) grad_norm: 1.3324 (1.3092) time: 0.6324 [2021-03-27 00:19:45 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 740/1251] eta: 0:05:25 lr: 0.000684 loss: 3.2088 (3.4196) grad_norm: 1.2806 (1.3090) time: 0.6354 [2021-03-27 00:19:51 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 750/1251] eta: 0:05:18 lr: 0.000684 loss: 3.4771 (3.4234) grad_norm: 1.1989 (1.3074) time: 0.6386 [2021-03-27 00:19:58 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 760/1251] eta: 0:05:12 lr: 0.000684 loss: 3.6589 (3.4225) grad_norm: 1.1651 (1.3068) time: 0.6358 [2021-03-27 00:20:04 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 770/1251] eta: 0:05:06 lr: 0.000684 loss: 3.6510 (3.4248) grad_norm: 1.1751 (1.3056) time: 0.6294 [2021-03-27 00:20:10 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 780/1251] eta: 0:04:59 lr: 0.000684 loss: 3.1216 (3.4184) grad_norm: 1.2181 (1.3047) time: 0.6277 [2021-03-27 00:20:16 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 790/1251] eta: 0:04:53 lr: 0.000684 loss: 3.1216 (3.4194) grad_norm: 1.2286 (1.3044) time: 0.6255 [2021-03-27 00:20:23 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 800/1251] eta: 0:04:46 lr: 0.000684 loss: 3.6619 (3.4223) grad_norm: 1.2766 (1.3039) time: 0.6288 [2021-03-27 00:20:29 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 810/1251] eta: 0:04:40 lr: 0.000684 loss: 3.5568 (3.4213) grad_norm: 1.2651 (1.3031) time: 0.6327 [2021-03-27 00:20:35 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 820/1251] eta: 0:04:34 lr: 0.000684 loss: 3.0921 (3.4177) grad_norm: 1.2867 (1.3036) time: 0.6404 [2021-03-27 00:20:42 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 830/1251] eta: 0:04:27 lr: 0.000684 loss: 3.4576 (3.4203) grad_norm: 1.3392 (1.3038) time: 0.6405 [2021-03-27 00:20:48 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 840/1251] eta: 0:04:21 lr: 0.000684 loss: 3.7275 (3.4231) grad_norm: 1.3451 (1.3044) time: 0.6277 [2021-03-27 00:20:54 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 850/1251] eta: 0:04:14 lr: 0.000684 loss: 3.6883 (3.4242) grad_norm: 1.3623 (1.3063) time: 0.6254 [2021-03-27 00:21:01 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 860/1251] eta: 0:04:08 lr: 0.000684 loss: 3.6914 (3.4283) grad_norm: 1.3729 (1.3074) time: 0.6318 [2021-03-27 00:21:07 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 870/1251] eta: 0:04:02 lr: 0.000684 loss: 3.6637 (3.4282) grad_norm: 1.3408 (1.3076) time: 0.6311 [2021-03-27 00:21:13 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 880/1251] eta: 0:03:55 lr: 0.000684 loss: 3.4184 (3.4279) grad_norm: 1.1902 (1.3065) time: 0.6257 [2021-03-27 00:21:20 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 890/1251] eta: 0:03:49 lr: 0.000684 loss: 3.4591 (3.4279) grad_norm: 1.2147 (1.3059) time: 0.6334 [2021-03-27 00:21:26 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 900/1251] eta: 0:03:43 lr: 0.000684 loss: 3.5910 (3.4305) grad_norm: 1.2147 (1.3045) time: 0.6383 [2021-03-27 00:21:32 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 910/1251] eta: 0:03:36 lr: 0.000684 loss: 3.5389 (3.4293) grad_norm: 1.1733 (1.3039) time: 0.6286 [2021-03-27 00:21:38 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 920/1251] eta: 0:03:30 lr: 0.000684 loss: 3.5389 (3.4304) grad_norm: 1.2509 (1.3035) time: 0.6247 [2021-03-27 00:21:45 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 930/1251] eta: 0:03:23 lr: 0.000684 loss: 3.6094 (3.4322) grad_norm: 1.3054 (1.3039) time: 0.6277 [2021-03-27 00:21:51 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 940/1251] eta: 0:03:17 lr: 0.000684 loss: 3.5256 (3.4324) grad_norm: 1.3089 (1.3035) time: 0.6300 [2021-03-27 00:21:57 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 950/1251] eta: 0:03:11 lr: 0.000684 loss: 3.5228 (3.4331) grad_norm: 1.2660 (1.3035) time: 0.6293 [2021-03-27 00:22:04 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 960/1251] eta: 0:03:04 lr: 0.000684 loss: 3.4292 (3.4331) grad_norm: 1.2476 (1.3032) time: 0.6324 [2021-03-27 00:22:10 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 970/1251] eta: 0:02:58 lr: 0.000683 loss: 3.4292 (3.4312) grad_norm: 1.2453 (1.3031) time: 0.6334 [2021-03-27 00:22:16 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 980/1251] eta: 0:02:52 lr: 0.000683 loss: 3.4315 (3.4314) grad_norm: 1.1787 (1.3018) time: 0.6319 [2021-03-27 00:22:23 swin_base_patch4_window7_224] INFO: Epoch: [114] [ 990/1251] eta: 0:02:45 lr: 0.000683 loss: 3.5414 (3.4313) grad_norm: 1.1375 (1.3011) time: 0.6374 [2021-03-27 00:22:29 swin_base_patch4_window7_224] INFO: Epoch: [114] [1000/1251] eta: 0:02:39 lr: 0.000683 loss: 3.3017 (3.4281) grad_norm: 1.2033 (1.3005) time: 0.6344 [2021-03-27 00:22:35 swin_base_patch4_window7_224] INFO: Epoch: [114] [1010/1251] eta: 0:02:33 lr: 0.000683 loss: 3.2832 (3.4259) grad_norm: 1.2617 (1.3008) time: 0.6287 [2021-03-27 00:22:42 swin_base_patch4_window7_224] INFO: Epoch: [114] [1020/1251] eta: 0:02:26 lr: 0.000683 loss: 3.3551 (3.4239) grad_norm: 1.2617 (1.2999) time: 0.6273 [2021-03-27 00:22:48 swin_base_patch4_window7_224] INFO: Epoch: [114] [1030/1251] eta: 0:02:20 lr: 0.000683 loss: 3.3898 (3.4230) grad_norm: 1.2327 (1.2997) time: 0.6313 [2021-03-27 00:22:54 swin_base_patch4_window7_224] INFO: Epoch: [114] [1040/1251] eta: 0:02:13 lr: 0.000683 loss: 3.4604 (3.4218) grad_norm: 1.2670 (1.3000) time: 0.6356 [2021-03-27 00:23:01 swin_base_patch4_window7_224] INFO: Epoch: [114] [1050/1251] eta: 0:02:07 lr: 0.000683 loss: 3.4669 (3.4232) grad_norm: 1.2670 (1.3002) time: 0.6307 [2021-03-27 00:23:07 swin_base_patch4_window7_224] INFO: Epoch: [114] [1060/1251] eta: 0:02:01 lr: 0.000683 loss: 3.6081 (3.4240) grad_norm: 1.2981 (1.3005) time: 0.6313 [2021-03-27 00:23:13 swin_base_patch4_window7_224] INFO: Epoch: [114] [1070/1251] eta: 0:01:54 lr: 0.000683 loss: 3.5485 (3.4235) grad_norm: 1.2945 (1.3000) time: 0.6304 [2021-03-27 00:23:20 swin_base_patch4_window7_224] INFO: Epoch: [114] [1080/1251] eta: 0:01:48 lr: 0.000683 loss: 3.4765 (3.4226) grad_norm: 1.2355 (1.3004) time: 0.6327 [2021-03-27 00:23:26 swin_base_patch4_window7_224] INFO: Epoch: [114] [1090/1251] eta: 0:01:42 lr: 0.000683 loss: 3.1340 (3.4202) grad_norm: 1.2996 (1.3005) time: 0.6379 [2021-03-27 00:23:32 swin_base_patch4_window7_224] INFO: Epoch: [114] [1100/1251] eta: 0:01:35 lr: 0.000683 loss: 3.4569 (3.4230) grad_norm: 1.2249 (1.3002) time: 0.6337 [2021-03-27 00:23:39 swin_base_patch4_window7_224] INFO: Epoch: [114] [1110/1251] eta: 0:01:29 lr: 0.000683 loss: 3.6737 (3.4243) grad_norm: 1.2761 (1.3008) time: 0.6321 [2021-03-27 00:23:45 swin_base_patch4_window7_224] INFO: Epoch: [114] [1120/1251] eta: 0:01:23 lr: 0.000683 loss: 3.6157 (3.4251) grad_norm: 1.3837 (1.3013) time: 0.6276 [2021-03-27 00:23:51 swin_base_patch4_window7_224] INFO: Epoch: [114] [1130/1251] eta: 0:01:16 lr: 0.000683 loss: 3.3892 (3.4233) grad_norm: 1.2537 (1.3010) time: 0.6264 [2021-03-27 00:23:57 swin_base_patch4_window7_224] INFO: Epoch: [114] [1140/1251] eta: 0:01:10 lr: 0.000683 loss: 3.2763 (3.4212) grad_norm: 1.2392 (1.3009) time: 0.6299 [2021-03-27 00:24:04 swin_base_patch4_window7_224] INFO: Epoch: [114] [1150/1251] eta: 0:01:04 lr: 0.000683 loss: 3.6555 (3.4243) grad_norm: 1.2480 (1.3002) time: 0.6285 [2021-03-27 00:24:10 swin_base_patch4_window7_224] INFO: Epoch: [114] [1160/1251] eta: 0:00:57 lr: 0.000683 loss: 3.8294 (3.4243) grad_norm: 1.2658 (1.3003) time: 0.6316 [2021-03-27 00:24:16 swin_base_patch4_window7_224] INFO: Epoch: [114] [1170/1251] eta: 0:00:51 lr: 0.000683 loss: 3.3858 (3.4231) grad_norm: 1.3128 (1.3003) time: 0.6312 [2021-03-27 00:24:23 swin_base_patch4_window7_224] INFO: Epoch: [114] [1180/1251] eta: 0:00:45 lr: 0.000683 loss: 3.3422 (3.4223) grad_norm: 1.2347 (1.3000) time: 0.6320 [2021-03-27 00:24:29 swin_base_patch4_window7_224] INFO: Epoch: [114] [1190/1251] eta: 0:00:38 lr: 0.000683 loss: 3.3248 (3.4204) grad_norm: 1.1868 (1.2997) time: 0.6347 [2021-03-27 00:24:35 swin_base_patch4_window7_224] INFO: Epoch: [114] [1200/1251] eta: 0:00:32 lr: 0.000683 loss: 3.5751 (3.4224) grad_norm: 1.2008 (1.2995) time: 0.6278 [2021-03-27 00:24:42 swin_base_patch4_window7_224] INFO: Epoch: [114] [1210/1251] eta: 0:00:26 lr: 0.000683 loss: 3.2903 (3.4189) grad_norm: 1.2630 (1.3001) time: 0.6249 [2021-03-27 00:24:48 swin_base_patch4_window7_224] INFO: Epoch: [114] [1220/1251] eta: 0:00:19 lr: 0.000683 loss: 2.9028 (3.4176) grad_norm: 1.2959 (1.3000) time: 0.6256 [2021-03-27 00:24:54 swin_base_patch4_window7_224] INFO: Epoch: [114] [1230/1251] eta: 0:00:13 lr: 0.000682 loss: 3.4099 (3.4176) grad_norm: 1.2959 (1.3002) time: 0.6238 [2021-03-27 00:25:00 swin_base_patch4_window7_224] INFO: Epoch: [114] [1240/1251] eta: 0:00:06 lr: 0.000682 loss: 3.4614 (3.4185) grad_norm: 1.2227 (1.2993) time: 0.6281 [2021-03-27 00:25:06 swin_base_patch4_window7_224] INFO: Epoch: [114] [1250/1251] eta: 0:00:00 lr: 0.000682 loss: 3.4047 (3.4167) grad_norm: 1.2094 (1.2986) time: 0.6217 [2021-03-27 00:25:13 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:12 loss: 0.8108 (0.8108) acc1: 78.1250 (78.1250) acc5: 98.4375 (98.4375) [2021-03-27 00:25:14 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.0558 (0.9905) acc1: 76.5625 (77.4148) acc5: 93.7500 (94.4602) [2021-03-27 00:25:16 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.9214 (0.9848) acc1: 76.5625 (76.9345) acc5: 93.7500 (94.4196) [2021-03-27 00:25:18 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0480 (1.0256) acc1: 75.0000 (75.7560) acc5: 93.7500 (94.0524) [2021-03-27 00:25:20 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0420 (1.0091) acc1: 75.0000 (76.3720) acc5: 93.7500 (94.1311) [2021-03-27 00:25:22 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9227 (1.0031) acc1: 76.5625 (76.5120) acc5: 93.7500 (94.1120) [2021-03-27 00:25:28 swin_base_patch4_window7_224] INFO: * Acc@1 77.172 Acc@5 94.096 loss 0.984 [2021-03-27 00:25:28 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.2% [2021-03-27 00:25:28 swin_base_patch4_window7_224] INFO: Max accuracy: 77.34% [2021-03-27 00:25:33 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 0/1251] eta: 1:32:25 lr: 0.000682 loss: 4.0592 (4.0592) grad_norm: 1.2967 (1.2967) time: 4.4328 [2021-03-27 00:25:39 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 10/1251] eta: 0:20:21 lr: 0.000682 loss: 3.6990 (3.6267) grad_norm: 1.3173 (1.3354) time: 0.9840 [2021-03-27 00:25:46 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 20/1251] eta: 0:16:47 lr: 0.000682 loss: 3.5969 (3.5342) grad_norm: 1.3884 (1.4355) time: 0.6376 [2021-03-27 00:25:52 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 30/1251] eta: 0:15:28 lr: 0.000682 loss: 3.3320 (3.4165) grad_norm: 1.3298 (1.3823) time: 0.6371 [2021-03-27 00:25:58 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 40/1251] eta: 0:14:42 lr: 0.000682 loss: 3.3225 (3.3799) grad_norm: 1.2793 (1.3540) time: 0.6345 [2021-03-27 00:26:05 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 50/1251] eta: 0:14:12 lr: 0.000682 loss: 3.3893 (3.3841) grad_norm: 1.2472 (1.3240) time: 0.6311 [2021-03-27 00:26:11 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 60/1251] eta: 0:13:48 lr: 0.000682 loss: 3.6835 (3.4188) grad_norm: 1.2779 (1.3295) time: 0.6277 [2021-03-27 00:26:17 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 70/1251] eta: 0:13:29 lr: 0.000682 loss: 3.7783 (3.4633) grad_norm: 1.2869 (1.3135) time: 0.6246 [2021-03-27 00:26:23 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 80/1251] eta: 0:13:15 lr: 0.000682 loss: 3.3925 (3.4046) grad_norm: 1.1771 (1.3040) time: 0.6290 [2021-03-27 00:26:30 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 90/1251] eta: 0:13:03 lr: 0.000682 loss: 3.0300 (3.3728) grad_norm: 1.2977 (1.3076) time: 0.6349 [2021-03-27 00:26:36 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 100/1251] eta: 0:12:51 lr: 0.000682 loss: 3.2881 (3.3919) grad_norm: 1.3262 (1.3065) time: 0.6345 [2021-03-27 00:26:42 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 110/1251] eta: 0:12:39 lr: 0.000682 loss: 3.4411 (3.4008) grad_norm: 1.3220 (1.3133) time: 0.6257 [2021-03-27 00:26:49 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 120/1251] eta: 0:12:30 lr: 0.000682 loss: 3.4278 (3.3909) grad_norm: 1.2225 (1.3077) time: 0.6294 [2021-03-27 00:26:55 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 130/1251] eta: 0:12:20 lr: 0.000682 loss: 3.4506 (3.4043) grad_norm: 1.2640 (1.3121) time: 0.6307 [2021-03-27 00:27:01 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 140/1251] eta: 0:12:12 lr: 0.000682 loss: 3.2914 (3.3832) grad_norm: 1.3134 (1.3094) time: 0.6352 [2021-03-27 00:27:08 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 150/1251] eta: 0:12:03 lr: 0.000682 loss: 3.3580 (3.3811) grad_norm: 1.2517 (1.3031) time: 0.6378 [2021-03-27 00:27:14 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 160/1251] eta: 0:11:55 lr: 0.000682 loss: 3.3580 (3.3827) grad_norm: 1.2207 (1.2994) time: 0.6277 [2021-03-27 00:27:20 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 170/1251] eta: 0:11:47 lr: 0.000682 loss: 3.3394 (3.3849) grad_norm: 1.2671 (1.3035) time: 0.6324 [2021-03-27 00:27:27 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 180/1251] eta: 0:11:39 lr: 0.000682 loss: 3.4157 (3.3916) grad_norm: 1.3451 (1.3083) time: 0.6312 [2021-03-27 00:27:33 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 190/1251] eta: 0:11:31 lr: 0.000682 loss: 3.3892 (3.3766) grad_norm: 1.3927 (1.3155) time: 0.6293 [2021-03-27 00:27:39 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 200/1251] eta: 0:11:24 lr: 0.000682 loss: 3.0612 (3.3705) grad_norm: 1.4036 (1.3184) time: 0.6379 [2021-03-27 00:27:46 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 210/1251] eta: 0:11:16 lr: 0.000682 loss: 3.4900 (3.3899) grad_norm: 1.2774 (1.3162) time: 0.6352 [2021-03-27 00:27:52 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 220/1251] eta: 0:11:09 lr: 0.000682 loss: 3.7264 (3.3992) grad_norm: 1.2254 (1.3134) time: 0.6280 [2021-03-27 00:27:58 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 230/1251] eta: 0:11:01 lr: 0.000682 loss: 3.6471 (3.4148) grad_norm: 1.2988 (1.3163) time: 0.6252 [2021-03-27 00:28:04 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 240/1251] eta: 0:10:54 lr: 0.000681 loss: 3.5582 (3.4183) grad_norm: 1.3666 (1.3203) time: 0.6239 [2021-03-27 00:28:11 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 250/1251] eta: 0:10:47 lr: 0.000681 loss: 3.4092 (3.4136) grad_norm: 1.2976 (1.3191) time: 0.6328 [2021-03-27 00:28:17 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 260/1251] eta: 0:10:40 lr: 0.000681 loss: 3.4701 (3.4168) grad_norm: 1.2562 (1.3186) time: 0.6412 [2021-03-27 00:28:24 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 270/1251] eta: 0:10:34 lr: 0.000681 loss: 3.4713 (3.4109) grad_norm: 1.2939 (1.3190) time: 0.6395 [2021-03-27 00:28:30 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 280/1251] eta: 0:10:26 lr: 0.000681 loss: 3.1855 (3.4006) grad_norm: 1.2824 (1.3182) time: 0.6318 [2021-03-27 00:28:36 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 290/1251] eta: 0:10:19 lr: 0.000681 loss: 3.3457 (3.4050) grad_norm: 1.2656 (1.3182) time: 0.6259 [2021-03-27 00:28:43 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 300/1251] eta: 0:10:12 lr: 0.000681 loss: 3.3397 (3.4007) grad_norm: 1.2731 (1.3181) time: 0.6292 [2021-03-27 00:28:49 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 310/1251] eta: 0:10:06 lr: 0.000681 loss: 3.2489 (3.4004) grad_norm: 1.2060 (1.3144) time: 0.6312 [2021-03-27 00:28:55 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 320/1251] eta: 0:09:59 lr: 0.000681 loss: 3.0863 (3.3979) grad_norm: 1.2072 (1.3147) time: 0.6307 [2021-03-27 00:29:02 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 330/1251] eta: 0:09:52 lr: 0.000681 loss: 3.5936 (3.4060) grad_norm: 1.2878 (1.3159) time: 0.6381 [2021-03-27 00:29:08 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 340/1251] eta: 0:09:45 lr: 0.000681 loss: 3.6370 (3.4100) grad_norm: 1.2955 (1.3167) time: 0.6345 [2021-03-27 00:29:14 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 350/1251] eta: 0:09:38 lr: 0.000681 loss: 3.3157 (3.4071) grad_norm: 1.3514 (1.3182) time: 0.6237 [2021-03-27 00:29:20 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 360/1251] eta: 0:09:32 lr: 0.000681 loss: 3.5170 (3.4118) grad_norm: 1.2959 (1.3152) time: 0.6230 [2021-03-27 00:29:27 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 370/1251] eta: 0:09:25 lr: 0.000681 loss: 3.4733 (3.4093) grad_norm: 1.2511 (1.3142) time: 0.6273 [2021-03-27 00:29:33 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 380/1251] eta: 0:09:18 lr: 0.000681 loss: 3.0998 (3.3995) grad_norm: 1.2756 (1.3128) time: 0.6354 [2021-03-27 00:29:39 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 390/1251] eta: 0:09:12 lr: 0.000681 loss: 3.2266 (3.4011) grad_norm: 1.2560 (1.3121) time: 0.6372 [2021-03-27 00:29:46 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 400/1251] eta: 0:09:05 lr: 0.000681 loss: 3.4006 (3.3975) grad_norm: 1.2210 (1.3103) time: 0.6293 [2021-03-27 00:29:52 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 410/1251] eta: 0:08:59 lr: 0.000681 loss: 3.4006 (3.3960) grad_norm: 1.2551 (1.3105) time: 0.6312 [2021-03-27 00:29:58 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 420/1251] eta: 0:08:52 lr: 0.000681 loss: 3.4979 (3.3934) grad_norm: 1.2740 (1.3092) time: 0.6331 [2021-03-27 00:30:05 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 430/1251] eta: 0:08:45 lr: 0.000681 loss: 3.4695 (3.3912) grad_norm: 1.2347 (1.3086) time: 0.6299 [2021-03-27 00:30:11 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 440/1251] eta: 0:08:39 lr: 0.000681 loss: 3.5568 (3.3958) grad_norm: 1.1760 (1.3059) time: 0.6315 [2021-03-27 00:30:17 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 450/1251] eta: 0:08:32 lr: 0.000681 loss: 3.6912 (3.3986) grad_norm: 1.2247 (1.3073) time: 0.6321 [2021-03-27 00:30:24 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 460/1251] eta: 0:08:26 lr: 0.000681 loss: 3.3186 (3.3945) grad_norm: 1.2466 (1.3067) time: 0.6313 [2021-03-27 00:30:30 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 470/1251] eta: 0:08:19 lr: 0.000681 loss: 3.3493 (3.3951) grad_norm: 1.2190 (1.3051) time: 0.6251 [2021-03-27 00:30:36 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 480/1251] eta: 0:08:12 lr: 0.000681 loss: 3.4797 (3.3957) grad_norm: 1.2413 (1.3046) time: 0.6211 [2021-03-27 00:30:42 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 490/1251] eta: 0:08:06 lr: 0.000680 loss: 3.3655 (3.3976) grad_norm: 1.2610 (1.3057) time: 0.6300 [2021-03-27 00:30:49 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 500/1251] eta: 0:07:59 lr: 0.000680 loss: 3.4815 (3.3998) grad_norm: 1.2911 (1.3067) time: 0.6347 [2021-03-27 00:30:55 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 510/1251] eta: 0:07:53 lr: 0.000680 loss: 3.5514 (3.4012) grad_norm: 1.3237 (1.3094) time: 0.6299 [2021-03-27 00:31:01 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 520/1251] eta: 0:07:46 lr: 0.000680 loss: 3.5979 (3.4068) grad_norm: 1.2597 (1.3094) time: 0.6293 [2021-03-27 00:31:08 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 530/1251] eta: 0:07:40 lr: 0.000680 loss: 3.4048 (3.4040) grad_norm: 1.2515 (1.3072) time: 0.6288 [2021-03-27 00:31:14 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 540/1251] eta: 0:07:33 lr: 0.000680 loss: 3.3309 (3.4056) grad_norm: 1.2515 (1.3073) time: 0.6286 [2021-03-27 00:31:20 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 550/1251] eta: 0:07:27 lr: 0.000680 loss: 3.5381 (3.4061) grad_norm: 1.3253 (1.3073) time: 0.6370 [2021-03-27 00:31:27 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 560/1251] eta: 0:07:21 lr: 0.000680 loss: 3.4073 (3.4073) grad_norm: 1.3584 (1.3099) time: 0.6452 [2021-03-27 00:31:33 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 570/1251] eta: 0:07:14 lr: 0.000680 loss: 3.6020 (3.4100) grad_norm: 1.3362 (1.3105) time: 0.6403 [2021-03-27 00:31:39 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 580/1251] eta: 0:07:08 lr: 0.000680 loss: 3.5783 (3.4089) grad_norm: 1.2393 (1.3095) time: 0.6323 [2021-03-27 00:31:46 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 590/1251] eta: 0:07:02 lr: 0.000680 loss: 3.3732 (3.4085) grad_norm: 1.2268 (1.3110) time: 0.6412 [2021-03-27 00:31:52 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 600/1251] eta: 0:06:55 lr: 0.000680 loss: 3.3794 (3.4065) grad_norm: 1.3418 (1.3124) time: 0.6404 [2021-03-27 00:31:58 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 610/1251] eta: 0:06:48 lr: 0.000680 loss: 3.3237 (3.4027) grad_norm: 1.3122 (1.3121) time: 0.6264 [2021-03-27 00:32:05 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 620/1251] eta: 0:06:42 lr: 0.000680 loss: 3.3957 (3.4021) grad_norm: 1.2480 (1.3105) time: 0.6235 [2021-03-27 00:32:11 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 630/1251] eta: 0:06:35 lr: 0.000680 loss: 3.4180 (3.4018) grad_norm: 1.2575 (1.3113) time: 0.6243 [2021-03-27 00:32:17 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 640/1251] eta: 0:06:29 lr: 0.000680 loss: 3.4986 (3.4022) grad_norm: 1.2373 (1.3103) time: 0.6285 [2021-03-27 00:32:24 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 650/1251] eta: 0:06:23 lr: 0.000680 loss: 3.2006 (3.3996) grad_norm: 1.1711 (1.3095) time: 0.6295 [2021-03-27 00:32:30 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 660/1251] eta: 0:06:16 lr: 0.000680 loss: 3.2039 (3.3996) grad_norm: 1.2299 (1.3091) time: 0.6268 [2021-03-27 00:32:36 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 670/1251] eta: 0:06:10 lr: 0.000680 loss: 3.5883 (3.4000) grad_norm: 1.2299 (1.3090) time: 0.6298 [2021-03-27 00:32:42 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 680/1251] eta: 0:06:03 lr: 0.000680 loss: 3.6294 (3.4043) grad_norm: 1.2678 (1.3092) time: 0.6336 [2021-03-27 00:32:49 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 690/1251] eta: 0:05:57 lr: 0.000680 loss: 3.7466 (3.4076) grad_norm: 1.2508 (1.3085) time: 0.6369 [2021-03-27 00:32:55 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 700/1251] eta: 0:05:50 lr: 0.000680 loss: 3.7093 (3.4112) grad_norm: 1.2748 (1.3084) time: 0.6300 [2021-03-27 00:33:01 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 710/1251] eta: 0:05:44 lr: 0.000680 loss: 3.5326 (3.4121) grad_norm: 1.3153 (1.3086) time: 0.6263 [2021-03-27 00:33:08 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 720/1251] eta: 0:05:38 lr: 0.000680 loss: 3.4997 (3.4107) grad_norm: 1.3293 (1.3091) time: 0.6350 [2021-03-27 00:33:14 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 730/1251] eta: 0:05:31 lr: 0.000680 loss: 3.3603 (3.4110) grad_norm: 1.3346 (1.3097) time: 0.6343 [2021-03-27 00:33:21 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 740/1251] eta: 0:05:25 lr: 0.000680 loss: 3.5181 (3.4137) grad_norm: 1.3346 (1.3098) time: 0.6403 [2021-03-27 00:33:27 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 750/1251] eta: 0:05:19 lr: 0.000679 loss: 3.6432 (3.4154) grad_norm: 1.2749 (1.3095) time: 0.6485 [2021-03-27 00:33:33 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 760/1251] eta: 0:05:12 lr: 0.000679 loss: 3.5150 (3.4170) grad_norm: 1.2599 (1.3093) time: 0.6356 [2021-03-27 00:33:40 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 770/1251] eta: 0:05:06 lr: 0.000679 loss: 3.4905 (3.4178) grad_norm: 1.3081 (1.3091) time: 0.6293 [2021-03-27 00:33:46 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 780/1251] eta: 0:04:59 lr: 0.000679 loss: 3.4905 (3.4182) grad_norm: 1.2356 (1.3077) time: 0.6286 [2021-03-27 00:33:52 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 790/1251] eta: 0:04:53 lr: 0.000679 loss: 3.5339 (3.4197) grad_norm: 1.2127 (1.3074) time: 0.6343 [2021-03-27 00:33:59 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 800/1251] eta: 0:04:47 lr: 0.000679 loss: 3.5783 (3.4192) grad_norm: 1.2862 (1.3084) time: 0.6355 [2021-03-27 00:34:05 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 810/1251] eta: 0:04:40 lr: 0.000679 loss: 3.2907 (3.4165) grad_norm: 1.2527 (1.3072) time: 0.6303 [2021-03-27 00:34:11 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 820/1251] eta: 0:04:34 lr: 0.000679 loss: 3.1598 (3.4154) grad_norm: 1.2584 (1.3073) time: 0.6312 [2021-03-27 00:34:18 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 830/1251] eta: 0:04:28 lr: 0.000679 loss: 3.4645 (3.4158) grad_norm: 1.2795 (1.3070) time: 0.6340 [2021-03-27 00:34:24 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 840/1251] eta: 0:04:21 lr: 0.000679 loss: 3.2001 (3.4121) grad_norm: 1.2461 (1.3065) time: 0.6370 [2021-03-27 00:34:30 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 850/1251] eta: 0:04:15 lr: 0.000679 loss: 3.0904 (3.4096) grad_norm: 1.2300 (1.3059) time: 0.6315 [2021-03-27 00:34:36 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 860/1251] eta: 0:04:08 lr: 0.000679 loss: 3.2810 (3.4095) grad_norm: 1.2240 (1.3051) time: 0.6251 [2021-03-27 00:34:43 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 870/1251] eta: 0:04:02 lr: 0.000679 loss: 3.4124 (3.4070) grad_norm: 1.2096 (1.3043) time: 0.6233 [2021-03-27 00:34:49 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 880/1251] eta: 0:03:56 lr: 0.000679 loss: 3.4124 (3.4065) grad_norm: 1.2123 (1.3047) time: 0.6332 [2021-03-27 00:34:55 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 890/1251] eta: 0:03:49 lr: 0.000679 loss: 3.4302 (3.4067) grad_norm: 1.2926 (1.3051) time: 0.6364 [2021-03-27 00:35:02 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 900/1251] eta: 0:03:43 lr: 0.000679 loss: 3.4302 (3.4058) grad_norm: 1.2476 (1.3040) time: 0.6401 [2021-03-27 00:35:08 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 910/1251] eta: 0:03:36 lr: 0.000679 loss: 3.6115 (3.4082) grad_norm: 1.2400 (1.3034) time: 0.6429 [2021-03-27 00:35:15 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 920/1251] eta: 0:03:30 lr: 0.000679 loss: 3.4749 (3.4080) grad_norm: 1.1904 (1.3020) time: 0.6298 [2021-03-27 00:35:21 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 930/1251] eta: 0:03:24 lr: 0.000679 loss: 3.4493 (3.4070) grad_norm: 1.1881 (1.3023) time: 0.6282 [2021-03-27 00:35:27 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 940/1251] eta: 0:03:17 lr: 0.000679 loss: 3.7013 (3.4092) grad_norm: 1.2637 (1.3024) time: 0.6316 [2021-03-27 00:35:33 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 950/1251] eta: 0:03:11 lr: 0.000679 loss: 3.7139 (3.4109) grad_norm: 1.2944 (1.3032) time: 0.6303 [2021-03-27 00:35:40 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 960/1251] eta: 0:03:05 lr: 0.000679 loss: 3.3161 (3.4095) grad_norm: 1.3521 (1.3037) time: 0.6306 [2021-03-27 00:35:46 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 970/1251] eta: 0:02:58 lr: 0.000679 loss: 3.2819 (3.4104) grad_norm: 1.3353 (1.3046) time: 0.6309 [2021-03-27 00:35:52 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 980/1251] eta: 0:02:52 lr: 0.000679 loss: 3.5133 (3.4104) grad_norm: 1.4002 (1.3071) time: 0.6363 [2021-03-27 00:35:59 swin_base_patch4_window7_224] INFO: Epoch: [115] [ 990/1251] eta: 0:02:45 lr: 0.000679 loss: 3.5111 (3.4095) grad_norm: 1.4256 (1.3072) time: 0.6310 [2021-03-27 00:36:05 swin_base_patch4_window7_224] INFO: Epoch: [115] [1000/1251] eta: 0:02:39 lr: 0.000679 loss: 3.3933 (3.4080) grad_norm: 1.3251 (1.3078) time: 0.6244 [2021-03-27 00:36:11 swin_base_patch4_window7_224] INFO: Epoch: [115] [1010/1251] eta: 0:02:33 lr: 0.000678 loss: 3.4800 (3.4098) grad_norm: 1.3581 (1.3092) time: 0.6253 [2021-03-27 00:36:18 swin_base_patch4_window7_224] INFO: Epoch: [115] [1020/1251] eta: 0:02:26 lr: 0.000678 loss: 3.6031 (3.4104) grad_norm: 1.2944 (1.3091) time: 0.6272 [2021-03-27 00:36:24 swin_base_patch4_window7_224] INFO: Epoch: [115] [1030/1251] eta: 0:02:20 lr: 0.000678 loss: 3.5767 (3.4093) grad_norm: 1.2590 (1.3087) time: 0.6286 [2021-03-27 00:36:30 swin_base_patch4_window7_224] INFO: Epoch: [115] [1040/1251] eta: 0:02:14 lr: 0.000678 loss: 3.5534 (3.4106) grad_norm: 1.2304 (1.3082) time: 0.6274 [2021-03-27 00:36:36 swin_base_patch4_window7_224] INFO: Epoch: [115] [1050/1251] eta: 0:02:07 lr: 0.000678 loss: 3.4991 (3.4093) grad_norm: 1.2773 (1.3077) time: 0.6322 [2021-03-27 00:36:43 swin_base_patch4_window7_224] INFO: Epoch: [115] [1060/1251] eta: 0:02:01 lr: 0.000678 loss: 3.3415 (3.4098) grad_norm: 1.2995 (1.3084) time: 0.6343 [2021-03-27 00:36:49 swin_base_patch4_window7_224] INFO: Epoch: [115] [1070/1251] eta: 0:01:54 lr: 0.000678 loss: 3.3275 (3.4088) grad_norm: 1.2935 (1.3081) time: 0.6315 [2021-03-27 00:36:55 swin_base_patch4_window7_224] INFO: Epoch: [115] [1080/1251] eta: 0:01:48 lr: 0.000678 loss: 3.2968 (3.4088) grad_norm: 1.2483 (1.3083) time: 0.6325 [2021-03-27 00:37:02 swin_base_patch4_window7_224] INFO: Epoch: [115] [1090/1251] eta: 0:01:42 lr: 0.000678 loss: 3.3979 (3.4083) grad_norm: 1.2372 (1.3080) time: 0.6330 [2021-03-27 00:37:08 swin_base_patch4_window7_224] INFO: Epoch: [115] [1100/1251] eta: 0:01:35 lr: 0.000678 loss: 3.2700 (3.4074) grad_norm: 1.2755 (1.3082) time: 0.6270 [2021-03-27 00:37:14 swin_base_patch4_window7_224] INFO: Epoch: [115] [1110/1251] eta: 0:01:29 lr: 0.000678 loss: 3.0890 (3.4068) grad_norm: 1.2832 (1.3084) time: 0.6204 [2021-03-27 00:37:21 swin_base_patch4_window7_224] INFO: Epoch: [115] [1120/1251] eta: 0:01:23 lr: 0.000678 loss: 3.0890 (3.4067) grad_norm: 1.2991 (1.3084) time: 0.6280 [2021-03-27 00:37:27 swin_base_patch4_window7_224] INFO: Epoch: [115] [1130/1251] eta: 0:01:16 lr: 0.000678 loss: 3.6814 (3.4104) grad_norm: 1.3055 (1.3084) time: 0.6354 [2021-03-27 00:37:33 swin_base_patch4_window7_224] INFO: Epoch: [115] [1140/1251] eta: 0:01:10 lr: 0.000678 loss: 3.6131 (3.4100) grad_norm: 1.2304 (1.3077) time: 0.6304 [2021-03-27 00:37:40 swin_base_patch4_window7_224] INFO: Epoch: [115] [1150/1251] eta: 0:01:04 lr: 0.000678 loss: 3.4659 (3.4090) grad_norm: 1.2304 (1.3080) time: 0.6329 [2021-03-27 00:37:46 swin_base_patch4_window7_224] INFO: Epoch: [115] [1160/1251] eta: 0:00:57 lr: 0.000678 loss: 3.3161 (3.4090) grad_norm: 1.2461 (1.3076) time: 0.6388 [2021-03-27 00:37:52 swin_base_patch4_window7_224] INFO: Epoch: [115] [1170/1251] eta: 0:00:51 lr: 0.000678 loss: 3.3161 (3.4085) grad_norm: 1.2536 (1.3075) time: 0.6323 [2021-03-27 00:37:58 swin_base_patch4_window7_224] INFO: Epoch: [115] [1180/1251] eta: 0:00:45 lr: 0.000678 loss: 3.4320 (3.4092) grad_norm: 1.2236 (inf) time: 0.6221 [2021-03-27 00:38:05 swin_base_patch4_window7_224] INFO: Epoch: [115] [1190/1251] eta: 0:00:38 lr: 0.000678 loss: 3.4002 (3.4079) grad_norm: 1.2247 (inf) time: 0.6256 [2021-03-27 00:38:11 swin_base_patch4_window7_224] INFO: Epoch: [115] [1200/1251] eta: 0:00:32 lr: 0.000678 loss: 3.0947 (3.4052) grad_norm: 1.2026 (inf) time: 0.6365 [2021-03-27 00:38:18 swin_base_patch4_window7_224] INFO: Epoch: [115] [1210/1251] eta: 0:00:26 lr: 0.000678 loss: 3.0947 (3.4035) grad_norm: 1.1817 (inf) time: 0.6406 [2021-03-27 00:38:24 swin_base_patch4_window7_224] INFO: Epoch: [115] [1220/1251] eta: 0:00:19 lr: 0.000678 loss: 3.5365 (3.4062) grad_norm: 1.2264 (inf) time: 0.6353 [2021-03-27 00:38:30 swin_base_patch4_window7_224] INFO: Epoch: [115] [1230/1251] eta: 0:00:13 lr: 0.000678 loss: 3.7020 (3.4067) grad_norm: 1.2633 (inf) time: 0.6262 [2021-03-27 00:38:36 swin_base_patch4_window7_224] INFO: Epoch: [115] [1240/1251] eta: 0:00:06 lr: 0.000678 loss: 3.4064 (3.4050) grad_norm: 1.3038 (inf) time: 0.6310 [2021-03-27 00:38:43 swin_base_patch4_window7_224] INFO: Epoch: [115] [1250/1251] eta: 0:00:00 lr: 0.000678 loss: 3.4064 (3.4051) grad_norm: 1.3014 (inf) time: 0.6367 [2021-03-27 00:39:49 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 0.9812 (0.9812) acc1: 78.1250 (78.1250) acc5: 93.7500 (93.7500) [2021-03-27 00:39:51 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.9593 (0.9257) acc1: 79.6875 (79.2614) acc5: 93.7500 (93.6080) [2021-03-27 00:39:52 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9832 (0.9975) acc1: 76.5625 (76.4137) acc5: 93.7500 (94.1220) [2021-03-27 00:39:54 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 1.0301 (0.9916) acc1: 75.0000 (76.7641) acc5: 93.7500 (94.1028) [2021-03-27 00:39:55 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9474 (0.9953) acc1: 76.5625 (76.9436) acc5: 93.7500 (93.8643) [2021-03-27 00:39:56 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9474 (1.0005) acc1: 75.0000 (76.7040) acc5: 93.7500 (93.7920) [2021-03-27 00:40:02 swin_base_patch4_window7_224] INFO: * Acc@1 77.526 Acc@5 94.216 loss 0.971 [2021-03-27 00:40:02 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.5% [2021-03-27 00:40:02 swin_base_patch4_window7_224] INFO: Max accuracy: 77.53% [2021-03-27 00:40:06 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 0/1251] eta: 1:28:54 lr: 0.000678 loss: 3.5556 (3.5556) grad_norm: 1.1545 (1.1545) time: 4.2642 [2021-03-27 00:40:12 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 10/1251] eta: 0:19:54 lr: 0.000678 loss: 3.4921 (3.4088) grad_norm: 1.2249 (1.2692) time: 0.9628 [2021-03-27 00:40:18 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 20/1251] eta: 0:16:29 lr: 0.000677 loss: 3.4800 (3.4293) grad_norm: 1.2979 (1.3088) time: 0.6306 [2021-03-27 00:40:25 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 30/1251] eta: 0:15:14 lr: 0.000677 loss: 3.5592 (3.5022) grad_norm: 1.3404 (1.3075) time: 0.6311 [2021-03-27 00:40:31 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 40/1251] eta: 0:14:33 lr: 0.000677 loss: 3.4374 (3.4791) grad_norm: 1.2207 (1.3003) time: 0.6342 [2021-03-27 00:40:37 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 50/1251] eta: 0:14:03 lr: 0.000677 loss: 3.3785 (3.4885) grad_norm: 1.2408 (1.3127) time: 0.6308 [2021-03-27 00:40:44 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 60/1251] eta: 0:13:42 lr: 0.000677 loss: 3.4282 (3.4674) grad_norm: 1.2422 (1.3027) time: 0.6272 [2021-03-27 00:40:50 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 70/1251] eta: 0:13:24 lr: 0.000677 loss: 3.6128 (3.4971) grad_norm: 1.2422 (1.3089) time: 0.6256 [2021-03-27 00:40:56 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 80/1251] eta: 0:13:12 lr: 0.000677 loss: 3.6128 (3.4524) grad_norm: 1.3005 (1.3166) time: 0.6360 [2021-03-27 00:41:03 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 90/1251] eta: 0:12:59 lr: 0.000677 loss: 3.4165 (3.4512) grad_norm: 1.2878 (1.3130) time: 0.6388 [2021-03-27 00:41:09 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 100/1251] eta: 0:12:49 lr: 0.000677 loss: 3.5595 (3.4669) grad_norm: 1.3060 (1.3391) time: 0.6342 [2021-03-27 00:41:16 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 110/1251] eta: 0:12:39 lr: 0.000677 loss: 3.3999 (3.4276) grad_norm: 1.3043 (1.3327) time: 0.6380 [2021-03-27 00:41:22 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 120/1251] eta: 0:12:29 lr: 0.000677 loss: 3.1260 (3.4318) grad_norm: 1.2042 (1.3205) time: 0.6329 [2021-03-27 00:41:28 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 130/1251] eta: 0:12:20 lr: 0.000677 loss: 3.5427 (3.4362) grad_norm: 1.1868 (1.3166) time: 0.6317 [2021-03-27 00:41:35 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 140/1251] eta: 0:12:12 lr: 0.000677 loss: 3.5119 (3.4408) grad_norm: 1.2084 (1.3093) time: 0.6429 [2021-03-27 00:41:41 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 150/1251] eta: 0:12:04 lr: 0.000677 loss: 3.3820 (3.4185) grad_norm: 1.2622 (1.3148) time: 0.6432 [2021-03-27 00:41:47 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 160/1251] eta: 0:11:56 lr: 0.000677 loss: 3.3958 (3.4229) grad_norm: 1.2994 (1.3138) time: 0.6352 [2021-03-27 00:41:54 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 170/1251] eta: 0:11:48 lr: 0.000677 loss: 3.4243 (3.4249) grad_norm: 1.2453 (1.3130) time: 0.6318 [2021-03-27 00:42:00 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 180/1251] eta: 0:11:40 lr: 0.000677 loss: 3.6010 (3.4331) grad_norm: 1.2683 (1.3136) time: 0.6319 [2021-03-27 00:42:06 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 190/1251] eta: 0:11:32 lr: 0.000677 loss: 3.5105 (3.4256) grad_norm: 1.3531 (1.3166) time: 0.6368 [2021-03-27 00:42:13 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 200/1251] eta: 0:11:24 lr: 0.000677 loss: 3.3521 (3.4135) grad_norm: 1.3676 (1.3182) time: 0.6315 [2021-03-27 00:42:19 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 210/1251] eta: 0:11:17 lr: 0.000677 loss: 3.4255 (3.4093) grad_norm: 1.3157 (1.3185) time: 0.6249 [2021-03-27 00:42:25 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 220/1251] eta: 0:11:10 lr: 0.000677 loss: 3.4926 (3.4128) grad_norm: 1.3157 (1.3187) time: 0.6345 [2021-03-27 00:42:32 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 230/1251] eta: 0:11:03 lr: 0.000677 loss: 3.3606 (3.4006) grad_norm: 1.2636 (1.3192) time: 0.6442 [2021-03-27 00:42:38 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 240/1251] eta: 0:10:55 lr: 0.000677 loss: 3.1894 (3.4001) grad_norm: 1.2893 (1.3184) time: 0.6331 [2021-03-27 00:42:44 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 250/1251] eta: 0:10:48 lr: 0.000677 loss: 3.2796 (3.3977) grad_norm: 1.2985 (1.3164) time: 0.6259 [2021-03-27 00:42:51 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 260/1251] eta: 0:10:41 lr: 0.000677 loss: 3.2996 (3.3919) grad_norm: 1.1850 (1.3129) time: 0.6286 [2021-03-27 00:42:57 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 270/1251] eta: 0:10:34 lr: 0.000676 loss: 3.4762 (3.3938) grad_norm: 1.2223 (1.3119) time: 0.6306 [2021-03-27 00:43:03 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 280/1251] eta: 0:10:27 lr: 0.000676 loss: 3.4762 (3.3961) grad_norm: 1.2317 (1.3116) time: 0.6312 [2021-03-27 00:43:10 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 290/1251] eta: 0:10:20 lr: 0.000676 loss: 3.3782 (3.3980) grad_norm: 1.2922 (1.3123) time: 0.6346 [2021-03-27 00:43:16 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 300/1251] eta: 0:10:13 lr: 0.000676 loss: 3.3782 (3.3943) grad_norm: 1.2641 (1.3093) time: 0.6335 [2021-03-27 00:43:22 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 310/1251] eta: 0:10:06 lr: 0.000676 loss: 3.4333 (3.3910) grad_norm: 1.2587 (1.3083) time: 0.6267 [2021-03-27 00:43:28 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 320/1251] eta: 0:09:59 lr: 0.000676 loss: 3.5705 (3.3996) grad_norm: 1.2402 (1.3048) time: 0.6242 [2021-03-27 00:43:35 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 330/1251] eta: 0:09:52 lr: 0.000676 loss: 3.7519 (3.4145) grad_norm: 1.1974 (1.3047) time: 0.6248 [2021-03-27 00:43:41 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 340/1251] eta: 0:09:45 lr: 0.000676 loss: 3.7979 (3.4252) grad_norm: 1.2661 (1.3037) time: 0.6302 [2021-03-27 00:43:47 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 350/1251] eta: 0:09:39 lr: 0.000676 loss: 3.6124 (3.4175) grad_norm: 1.3130 (1.3054) time: 0.6333 [2021-03-27 00:43:54 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 360/1251] eta: 0:09:32 lr: 0.000676 loss: 3.2676 (3.4139) grad_norm: 1.3415 (1.3070) time: 0.6286 [2021-03-27 00:44:00 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 370/1251] eta: 0:09:25 lr: 0.000676 loss: 3.5676 (3.4160) grad_norm: 1.4059 (1.3122) time: 0.6274 [2021-03-27 00:44:06 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 380/1251] eta: 0:09:19 lr: 0.000676 loss: 3.6099 (3.4132) grad_norm: 1.3304 (1.3107) time: 0.6350 [2021-03-27 00:44:13 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 390/1251] eta: 0:09:12 lr: 0.000676 loss: 3.6066 (3.4139) grad_norm: 1.2484 (1.3103) time: 0.6356 [2021-03-27 00:44:19 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 400/1251] eta: 0:09:05 lr: 0.000676 loss: 2.9466 (3.4062) grad_norm: 1.3195 (1.3131) time: 0.6304 [2021-03-27 00:44:25 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 410/1251] eta: 0:08:59 lr: 0.000676 loss: 2.9955 (3.4060) grad_norm: 1.3540 (1.3118) time: 0.6269 [2021-03-27 00:44:31 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 420/1251] eta: 0:08:52 lr: 0.000676 loss: 3.5454 (3.4062) grad_norm: 1.1593 (1.3082) time: 0.6293 [2021-03-27 00:44:38 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 430/1251] eta: 0:08:45 lr: 0.000676 loss: 3.5896 (3.4092) grad_norm: 1.1535 (1.3080) time: 0.6298 [2021-03-27 00:44:44 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 440/1251] eta: 0:08:39 lr: 0.000676 loss: 3.6568 (3.4117) grad_norm: 1.2496 (1.3084) time: 0.6339 [2021-03-27 00:44:50 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 450/1251] eta: 0:08:32 lr: 0.000676 loss: 3.4232 (3.4097) grad_norm: 1.2922 (1.3086) time: 0.6338 [2021-03-27 00:44:57 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 460/1251] eta: 0:08:26 lr: 0.000676 loss: 3.5848 (3.4157) grad_norm: 1.2922 (1.3099) time: 0.6332 [2021-03-27 00:45:03 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 470/1251] eta: 0:08:20 lr: 0.000676 loss: 3.5848 (3.4171) grad_norm: 1.3102 (1.3111) time: 0.6412 [2021-03-27 00:45:09 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 480/1251] eta: 0:08:13 lr: 0.000676 loss: 3.5414 (3.4212) grad_norm: 1.2742 (1.3107) time: 0.6331 [2021-03-27 00:45:16 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 490/1251] eta: 0:08:06 lr: 0.000676 loss: 3.5181 (3.4181) grad_norm: 1.2718 (1.3095) time: 0.6241 [2021-03-27 00:45:22 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 500/1251] eta: 0:08:00 lr: 0.000676 loss: 3.5368 (3.4213) grad_norm: 1.2441 (1.3086) time: 0.6277 [2021-03-27 00:45:28 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 510/1251] eta: 0:07:53 lr: 0.000676 loss: 3.5169 (3.4186) grad_norm: 1.2596 (1.3104) time: 0.6267 [2021-03-27 00:45:34 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 520/1251] eta: 0:07:46 lr: 0.000676 loss: 3.3340 (3.4198) grad_norm: 1.2802 (1.3099) time: 0.6230 [2021-03-27 00:45:41 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 530/1251] eta: 0:07:40 lr: 0.000675 loss: 3.4923 (3.4168) grad_norm: 1.2858 (1.3093) time: 0.6291 [2021-03-27 00:45:47 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 540/1251] eta: 0:07:34 lr: 0.000675 loss: 3.3656 (3.4144) grad_norm: 1.2858 (1.3093) time: 0.6414 [2021-03-27 00:45:54 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 550/1251] eta: 0:07:27 lr: 0.000675 loss: 3.3656 (3.4132) grad_norm: 1.3002 (1.3102) time: 0.6482 [2021-03-27 00:46:00 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 560/1251] eta: 0:07:21 lr: 0.000675 loss: 3.4675 (3.4134) grad_norm: 1.3109 (1.3101) time: 0.6389 [2021-03-27 00:46:06 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 570/1251] eta: 0:07:14 lr: 0.000675 loss: 3.5870 (3.4143) grad_norm: 1.2820 (1.3096) time: 0.6264 [2021-03-27 00:46:13 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 580/1251] eta: 0:07:08 lr: 0.000675 loss: 3.8079 (3.4193) grad_norm: 1.2692 (1.3102) time: 0.6266 [2021-03-27 00:46:19 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 590/1251] eta: 0:07:01 lr: 0.000675 loss: 3.7392 (3.4207) grad_norm: 1.2832 (1.3105) time: 0.6273 [2021-03-27 00:46:25 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 600/1251] eta: 0:06:55 lr: 0.000675 loss: 3.5618 (3.4242) grad_norm: 1.2923 (1.3100) time: 0.6294 [2021-03-27 00:46:32 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 610/1251] eta: 0:06:48 lr: 0.000675 loss: 3.5618 (3.4240) grad_norm: 1.2707 (1.3097) time: 0.6328 [2021-03-27 00:46:38 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 620/1251] eta: 0:06:42 lr: 0.000675 loss: 3.4891 (3.4245) grad_norm: 1.2353 (1.3096) time: 0.6308 [2021-03-27 00:46:44 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 630/1251] eta: 0:06:35 lr: 0.000675 loss: 3.4891 (3.4237) grad_norm: 1.3371 (1.3107) time: 0.6254 [2021-03-27 00:46:50 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 640/1251] eta: 0:06:29 lr: 0.000675 loss: 3.4266 (3.4230) grad_norm: 1.3371 (1.3121) time: 0.6230 [2021-03-27 00:46:57 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 650/1251] eta: 0:06:23 lr: 0.000675 loss: 3.4573 (3.4237) grad_norm: 1.3140 (1.3126) time: 0.6266 [2021-03-27 00:47:03 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 660/1251] eta: 0:06:16 lr: 0.000675 loss: 3.4830 (3.4234) grad_norm: 1.3140 (1.3141) time: 0.6303 [2021-03-27 00:47:09 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 670/1251] eta: 0:06:10 lr: 0.000675 loss: 3.3658 (3.4227) grad_norm: 1.3095 (1.3148) time: 0.6326 [2021-03-27 00:47:15 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 680/1251] eta: 0:06:03 lr: 0.000675 loss: 3.6060 (3.4264) grad_norm: 1.3158 (1.3143) time: 0.6278 [2021-03-27 00:47:22 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 690/1251] eta: 0:05:57 lr: 0.000675 loss: 3.4346 (3.4224) grad_norm: 1.3158 (1.3136) time: 0.6342 [2021-03-27 00:47:28 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 700/1251] eta: 0:05:50 lr: 0.000675 loss: 3.4346 (3.4250) grad_norm: 1.2599 (1.3127) time: 0.6319 [2021-03-27 00:47:34 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 710/1251] eta: 0:05:44 lr: 0.000675 loss: 3.7841 (3.4274) grad_norm: 1.2599 (1.3132) time: 0.6243 [2021-03-27 00:47:41 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 720/1251] eta: 0:05:38 lr: 0.000675 loss: 3.4328 (3.4278) grad_norm: 1.2581 (1.3119) time: 0.6328 [2021-03-27 00:47:47 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 730/1251] eta: 0:05:31 lr: 0.000675 loss: 3.6211 (3.4288) grad_norm: 1.2575 (1.3117) time: 0.6360 [2021-03-27 00:47:54 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 740/1251] eta: 0:05:25 lr: 0.000675 loss: 3.6714 (3.4342) grad_norm: 1.3021 (1.3128) time: 0.6392 [2021-03-27 00:48:00 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 750/1251] eta: 0:05:18 lr: 0.000675 loss: 3.5619 (3.4318) grad_norm: 1.3441 (1.3123) time: 0.6354 [2021-03-27 00:48:06 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 760/1251] eta: 0:05:12 lr: 0.000675 loss: 3.4339 (3.4298) grad_norm: 1.3617 (1.3143) time: 0.6289 [2021-03-27 00:48:12 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 770/1251] eta: 0:05:06 lr: 0.000675 loss: 3.4476 (3.4283) grad_norm: 1.3145 (1.3141) time: 0.6286 [2021-03-27 00:48:19 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 780/1251] eta: 0:04:59 lr: 0.000675 loss: 3.4476 (3.4270) grad_norm: 1.2823 (1.3148) time: 0.6332 [2021-03-27 00:48:25 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 790/1251] eta: 0:04:53 lr: 0.000674 loss: 3.6107 (3.4282) grad_norm: 1.4091 (1.3166) time: 0.6361 [2021-03-27 00:48:31 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 800/1251] eta: 0:04:46 lr: 0.000674 loss: 3.4953 (3.4257) grad_norm: 1.3434 (1.3167) time: 0.6306 [2021-03-27 00:48:38 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 810/1251] eta: 0:04:40 lr: 0.000674 loss: 3.5233 (3.4281) grad_norm: 1.2695 (1.3155) time: 0.6272 [2021-03-27 00:48:44 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 820/1251] eta: 0:04:34 lr: 0.000674 loss: 3.5122 (3.4261) grad_norm: 1.2355 (1.3156) time: 0.6269 [2021-03-27 00:48:50 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 830/1251] eta: 0:04:27 lr: 0.000674 loss: 3.2727 (3.4248) grad_norm: 1.2355 (1.3152) time: 0.6333 [2021-03-27 00:48:57 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 840/1251] eta: 0:04:21 lr: 0.000674 loss: 3.4939 (3.4242) grad_norm: 1.2352 (1.3140) time: 0.6361 [2021-03-27 00:49:03 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 850/1251] eta: 0:04:15 lr: 0.000674 loss: 3.5114 (3.4253) grad_norm: 1.2361 (1.3140) time: 0.6311 [2021-03-27 00:49:09 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 860/1251] eta: 0:04:08 lr: 0.000674 loss: 3.4495 (3.4243) grad_norm: 1.2906 (1.3150) time: 0.6304 [2021-03-27 00:49:16 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 870/1251] eta: 0:04:02 lr: 0.000674 loss: 3.3409 (3.4240) grad_norm: 1.3287 (1.3154) time: 0.6356 [2021-03-27 00:49:22 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 880/1251] eta: 0:03:56 lr: 0.000674 loss: 3.5679 (3.4260) grad_norm: 1.2824 (1.3144) time: 0.6440 [2021-03-27 00:49:28 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 890/1251] eta: 0:03:49 lr: 0.000674 loss: 3.6461 (3.4308) grad_norm: 1.2775 (1.3140) time: 0.6359 [2021-03-27 00:49:35 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 900/1251] eta: 0:03:43 lr: 0.000674 loss: 3.6180 (3.4312) grad_norm: 1.2558 (1.3132) time: 0.6273 [2021-03-27 00:49:41 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 910/1251] eta: 0:03:36 lr: 0.000674 loss: 3.3074 (3.4305) grad_norm: 1.2008 (1.3115) time: 0.6286 [2021-03-27 00:49:47 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 920/1251] eta: 0:03:30 lr: 0.000674 loss: 3.3764 (3.4316) grad_norm: 1.1884 (1.3108) time: 0.6245 [2021-03-27 00:49:54 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 930/1251] eta: 0:03:24 lr: 0.000674 loss: 3.4056 (3.4310) grad_norm: 1.2338 (1.3103) time: 0.6270 [2021-03-27 00:50:00 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 940/1251] eta: 0:03:17 lr: 0.000674 loss: 3.5382 (3.4332) grad_norm: 1.2338 (1.3098) time: 0.6302 [2021-03-27 00:50:06 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 950/1251] eta: 0:03:11 lr: 0.000674 loss: 3.5890 (3.4315) grad_norm: 1.2383 (1.3094) time: 0.6271 [2021-03-27 00:50:12 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 960/1251] eta: 0:03:04 lr: 0.000674 loss: 3.5723 (3.4321) grad_norm: 1.2558 (1.3093) time: 0.6260 [2021-03-27 00:50:19 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 970/1251] eta: 0:02:58 lr: 0.000674 loss: 3.4372 (3.4330) grad_norm: 1.3051 (1.3090) time: 0.6287 [2021-03-27 00:50:25 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 980/1251] eta: 0:02:52 lr: 0.000674 loss: 3.3751 (3.4310) grad_norm: 1.2981 (1.3083) time: 0.6255 [2021-03-27 00:50:31 swin_base_patch4_window7_224] INFO: Epoch: [116] [ 990/1251] eta: 0:02:45 lr: 0.000674 loss: 3.3488 (3.4311) grad_norm: 1.2135 (1.3076) time: 0.6261 [2021-03-27 00:50:38 swin_base_patch4_window7_224] INFO: Epoch: [116] [1000/1251] eta: 0:02:39 lr: 0.000674 loss: 3.4759 (3.4314) grad_norm: 1.2588 (1.3081) time: 0.6332 [2021-03-27 00:50:44 swin_base_patch4_window7_224] INFO: Epoch: [116] [1010/1251] eta: 0:02:33 lr: 0.000674 loss: 3.5142 (3.4316) grad_norm: 1.2506 (1.3077) time: 0.6290 [2021-03-27 00:50:50 swin_base_patch4_window7_224] INFO: Epoch: [116] [1020/1251] eta: 0:02:26 lr: 0.000674 loss: 3.4814 (3.4310) grad_norm: 1.2203 (1.3073) time: 0.6268 [2021-03-27 00:50:56 swin_base_patch4_window7_224] INFO: Epoch: [116] [1030/1251] eta: 0:02:20 lr: 0.000674 loss: 3.3867 (3.4308) grad_norm: 1.2690 (1.3070) time: 0.6276 [2021-03-27 00:51:03 swin_base_patch4_window7_224] INFO: Epoch: [116] [1040/1251] eta: 0:02:13 lr: 0.000673 loss: 3.4509 (3.4304) grad_norm: 1.2731 (1.3064) time: 0.6280 [2021-03-27 00:51:09 swin_base_patch4_window7_224] INFO: Epoch: [116] [1050/1251] eta: 0:02:07 lr: 0.000673 loss: 3.4604 (3.4316) grad_norm: 1.2682 (1.3064) time: 0.6302 [2021-03-27 00:51:15 swin_base_patch4_window7_224] INFO: Epoch: [116] [1060/1251] eta: 0:02:01 lr: 0.000673 loss: 3.4671 (3.4333) grad_norm: 1.2884 (1.3073) time: 0.6247 [2021-03-27 00:51:22 swin_base_patch4_window7_224] INFO: Epoch: [116] [1070/1251] eta: 0:01:54 lr: 0.000673 loss: 3.3964 (3.4320) grad_norm: 1.3349 (1.3078) time: 0.6284 [2021-03-27 00:51:28 swin_base_patch4_window7_224] INFO: Epoch: [116] [1080/1251] eta: 0:01:48 lr: 0.000673 loss: 3.6722 (3.4345) grad_norm: 1.2618 (1.3074) time: 0.6367 [2021-03-27 00:51:34 swin_base_patch4_window7_224] INFO: Epoch: [116] [1090/1251] eta: 0:01:42 lr: 0.000673 loss: 3.6783 (3.4339) grad_norm: 1.2583 (1.3076) time: 0.6318 [2021-03-27 00:51:40 swin_base_patch4_window7_224] INFO: Epoch: [116] [1100/1251] eta: 0:01:35 lr: 0.000673 loss: 3.5096 (3.4368) grad_norm: 1.2429 (1.3069) time: 0.6245 [2021-03-27 00:51:47 swin_base_patch4_window7_224] INFO: Epoch: [116] [1110/1251] eta: 0:01:29 lr: 0.000673 loss: 3.5278 (3.4373) grad_norm: 1.2323 (1.3072) time: 0.6208 [2021-03-27 00:51:53 swin_base_patch4_window7_224] INFO: Epoch: [116] [1120/1251] eta: 0:01:23 lr: 0.000673 loss: 3.3983 (3.4373) grad_norm: 1.2390 (1.3072) time: 0.6337 [2021-03-27 00:51:59 swin_base_patch4_window7_224] INFO: Epoch: [116] [1130/1251] eta: 0:01:16 lr: 0.000673 loss: 3.3529 (3.4370) grad_norm: 1.2425 (1.3071) time: 0.6373 [2021-03-27 00:52:06 swin_base_patch4_window7_224] INFO: Epoch: [116] [1140/1251] eta: 0:01:10 lr: 0.000673 loss: 3.5003 (3.4367) grad_norm: 1.2671 (1.3066) time: 0.6287 [2021-03-27 00:52:12 swin_base_patch4_window7_224] INFO: Epoch: [116] [1150/1251] eta: 0:01:04 lr: 0.000673 loss: 3.4604 (3.4349) grad_norm: 1.2898 (1.3071) time: 0.6251 [2021-03-27 00:52:18 swin_base_patch4_window7_224] INFO: Epoch: [116] [1160/1251] eta: 0:00:57 lr: 0.000673 loss: 3.4582 (3.4343) grad_norm: 1.3787 (1.3080) time: 0.6295 [2021-03-27 00:52:24 swin_base_patch4_window7_224] INFO: Epoch: [116] [1170/1251] eta: 0:00:51 lr: 0.000673 loss: 3.4338 (3.4329) grad_norm: 1.2768 (1.3082) time: 0.6314 [2021-03-27 00:52:31 swin_base_patch4_window7_224] INFO: Epoch: [116] [1180/1251] eta: 0:00:45 lr: 0.000673 loss: 3.1242 (3.4309) grad_norm: 1.2663 (1.3082) time: 0.6235 [2021-03-27 00:52:37 swin_base_patch4_window7_224] INFO: Epoch: [116] [1190/1251] eta: 0:00:38 lr: 0.000673 loss: 3.5372 (3.4311) grad_norm: 1.2992 (1.3088) time: 0.6235 [2021-03-27 00:52:43 swin_base_patch4_window7_224] INFO: Epoch: [116] [1200/1251] eta: 0:00:32 lr: 0.000673 loss: 3.5372 (3.4309) grad_norm: 1.3479 (1.3092) time: 0.6263 [2021-03-27 00:52:50 swin_base_patch4_window7_224] INFO: Epoch: [116] [1210/1251] eta: 0:00:25 lr: 0.000673 loss: 3.4223 (3.4296) grad_norm: 1.2948 (1.3098) time: 0.6285 [2021-03-27 00:52:56 swin_base_patch4_window7_224] INFO: Epoch: [116] [1220/1251] eta: 0:00:19 lr: 0.000673 loss: 3.4441 (3.4302) grad_norm: 1.2958 (1.3099) time: 0.6251 [2021-03-27 00:53:02 swin_base_patch4_window7_224] INFO: Epoch: [116] [1230/1251] eta: 0:00:13 lr: 0.000673 loss: 3.4441 (3.4299) grad_norm: 1.2768 (1.3094) time: 0.6248 [2021-03-27 00:53:08 swin_base_patch4_window7_224] INFO: Epoch: [116] [1240/1251] eta: 0:00:06 lr: 0.000673 loss: 3.2714 (3.4287) grad_norm: 1.2811 (1.3098) time: 0.6306 [2021-03-27 00:53:15 swin_base_patch4_window7_224] INFO: Epoch: [116] [1250/1251] eta: 0:00:00 lr: 0.000673 loss: 3.2873 (3.4288) grad_norm: 1.3209 (1.3103) time: 0.6292 [2021-03-27 00:53:23 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:27 loss: 0.9756 (0.9756) acc1: 76.5625 (76.5625) acc5: 93.7500 (93.7500) [2021-03-27 00:53:25 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9542 (0.9566) acc1: 78.1250 (78.4091) acc5: 93.7500 (93.8920) [2021-03-27 00:53:27 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8892 (0.9436) acc1: 79.6875 (78.6458) acc5: 93.7500 (94.3452) [2021-03-27 00:53:29 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0014 (0.9784) acc1: 79.6875 (77.9234) acc5: 93.7500 (94.3044) [2021-03-27 00:53:31 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0396 (0.9933) acc1: 75.0000 (77.4771) acc5: 93.7500 (94.2454) [2021-03-27 00:53:33 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0333 (0.9942) acc1: 75.0000 (77.1520) acc5: 93.7500 (94.1120) [2021-03-27 00:53:39 swin_base_patch4_window7_224] INFO: * Acc@1 77.504 Acc@5 94.148 loss 0.977 [2021-03-27 00:53:39 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.5% [2021-03-27 00:53:39 swin_base_patch4_window7_224] INFO: Max accuracy: 77.53% [2021-03-27 00:53:43 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 0/1251] eta: 1:31:12 lr: 0.000673 loss: 3.5538 (3.5538) grad_norm: 1.1553 (1.1553) time: 4.3746 [2021-03-27 00:53:50 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 10/1251] eta: 0:20:01 lr: 0.000673 loss: 3.4384 (3.2963) grad_norm: 1.3387 (1.3513) time: 0.9679 [2021-03-27 00:53:56 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 20/1251] eta: 0:16:26 lr: 0.000673 loss: 3.4384 (3.4213) grad_norm: 1.3387 (1.3556) time: 0.6229 [2021-03-27 00:54:02 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 30/1251] eta: 0:15:10 lr: 0.000673 loss: 3.6570 (3.5274) grad_norm: 1.2819 (1.3246) time: 0.6235 [2021-03-27 00:54:08 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 40/1251] eta: 0:14:28 lr: 0.000673 loss: 3.5552 (3.4391) grad_norm: 1.2429 (1.3171) time: 0.6292 [2021-03-27 00:54:15 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 50/1251] eta: 0:14:02 lr: 0.000672 loss: 3.4377 (3.4799) grad_norm: 1.2730 (1.3169) time: 0.6328 [2021-03-27 00:54:21 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 60/1251] eta: 0:13:41 lr: 0.000672 loss: 3.4377 (3.4230) grad_norm: 1.2754 (1.3150) time: 0.6327 [2021-03-27 00:54:27 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 70/1251] eta: 0:13:27 lr: 0.000672 loss: 3.4348 (3.4295) grad_norm: 1.2644 (1.3069) time: 0.6384 [2021-03-27 00:54:34 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 80/1251] eta: 0:13:15 lr: 0.000672 loss: 3.5155 (3.4349) grad_norm: 1.3126 (1.3212) time: 0.6467 [2021-03-27 00:54:40 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 90/1251] eta: 0:13:03 lr: 0.000672 loss: 3.5678 (3.4498) grad_norm: 1.3142 (1.3181) time: 0.6432 [2021-03-27 00:54:47 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 100/1251] eta: 0:12:51 lr: 0.000672 loss: 3.5678 (3.4515) grad_norm: 1.3129 (1.3233) time: 0.6354 [2021-03-27 00:54:53 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 110/1251] eta: 0:12:39 lr: 0.000672 loss: 3.4693 (3.4491) grad_norm: 1.3080 (1.3216) time: 0.6254 [2021-03-27 00:54:59 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 120/1251] eta: 0:12:30 lr: 0.000672 loss: 3.3828 (3.4365) grad_norm: 1.2465 (1.3184) time: 0.6271 [2021-03-27 00:55:05 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 130/1251] eta: 0:12:20 lr: 0.000672 loss: 3.3425 (3.4326) grad_norm: 1.2389 (1.3165) time: 0.6302 [2021-03-27 00:55:12 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 140/1251] eta: 0:12:11 lr: 0.000672 loss: 3.3478 (3.4319) grad_norm: 1.2389 (1.3213) time: 0.6308 [2021-03-27 00:55:18 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 150/1251] eta: 0:12:03 lr: 0.000672 loss: 3.4954 (3.4430) grad_norm: 1.3494 (1.3262) time: 0.6347 [2021-03-27 00:55:25 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 160/1251] eta: 0:11:55 lr: 0.000672 loss: 3.6248 (3.4378) grad_norm: 1.3382 (1.3333) time: 0.6347 [2021-03-27 00:55:31 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 170/1251] eta: 0:11:46 lr: 0.000672 loss: 3.6418 (3.4506) grad_norm: 1.3057 (1.3326) time: 0.6275 [2021-03-27 00:55:37 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 180/1251] eta: 0:11:38 lr: 0.000672 loss: 3.7320 (3.4456) grad_norm: 1.2656 (1.3314) time: 0.6234 [2021-03-27 00:55:43 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 190/1251] eta: 0:11:30 lr: 0.000672 loss: 3.6584 (3.4527) grad_norm: 1.1958 (1.3252) time: 0.6241 [2021-03-27 00:55:49 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 200/1251] eta: 0:11:22 lr: 0.000672 loss: 3.5504 (3.4443) grad_norm: 1.1860 (1.3195) time: 0.6227 [2021-03-27 00:55:56 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 210/1251] eta: 0:11:15 lr: 0.000672 loss: 3.3244 (3.4348) grad_norm: 1.1669 (1.3154) time: 0.6290 [2021-03-27 00:56:02 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 220/1251] eta: 0:11:07 lr: 0.000672 loss: 3.4623 (3.4341) grad_norm: 1.2448 (1.3178) time: 0.6306 [2021-03-27 00:56:08 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 230/1251] eta: 0:11:00 lr: 0.000672 loss: 3.4440 (3.4298) grad_norm: 1.3009 (1.3154) time: 0.6275 [2021-03-27 00:56:15 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 240/1251] eta: 0:10:52 lr: 0.000672 loss: 3.3165 (3.4196) grad_norm: 1.2658 (1.3163) time: 0.6272 [2021-03-27 00:56:21 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 250/1251] eta: 0:10:45 lr: 0.000672 loss: 3.4324 (3.4264) grad_norm: 1.2902 (1.3162) time: 0.6296 [2021-03-27 00:56:27 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 260/1251] eta: 0:10:39 lr: 0.000672 loss: 3.4851 (3.4203) grad_norm: 1.3521 (1.3265) time: 0.6345 [2021-03-27 00:56:34 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 270/1251] eta: 0:10:32 lr: 0.000672 loss: 3.4990 (3.4195) grad_norm: 1.4730 (1.3332) time: 0.6357 [2021-03-27 00:56:40 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 280/1251] eta: 0:10:25 lr: 0.000672 loss: 3.3010 (3.4119) grad_norm: 1.3248 (1.3361) time: 0.6330 [2021-03-27 00:56:46 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 290/1251] eta: 0:10:18 lr: 0.000672 loss: 3.3242 (3.4129) grad_norm: 1.2849 (1.3334) time: 0.6299 [2021-03-27 00:56:52 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 300/1251] eta: 0:10:11 lr: 0.000672 loss: 3.4590 (3.4082) grad_norm: 1.2543 (1.3309) time: 0.6247 [2021-03-27 00:56:59 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 310/1251] eta: 0:10:04 lr: 0.000671 loss: 3.5211 (3.4149) grad_norm: 1.2705 (1.3306) time: 0.6229 [2021-03-27 00:57:05 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 320/1251] eta: 0:09:57 lr: 0.000671 loss: 3.7515 (3.4146) grad_norm: 1.4122 (1.3356) time: 0.6238 [2021-03-27 00:57:11 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 330/1251] eta: 0:09:50 lr: 0.000671 loss: 3.6832 (3.4179) grad_norm: 1.3513 (1.3334) time: 0.6276 [2021-03-27 00:57:18 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 340/1251] eta: 0:09:43 lr: 0.000671 loss: 3.4865 (3.4204) grad_norm: 1.3264 (1.3337) time: 0.6308 [2021-03-27 00:57:24 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 350/1251] eta: 0:09:37 lr: 0.000671 loss: 3.3822 (3.4169) grad_norm: 1.3294 (1.3317) time: 0.6249 [2021-03-27 00:57:30 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 360/1251] eta: 0:09:30 lr: 0.000671 loss: 3.3032 (3.4139) grad_norm: 1.3413 (1.3326) time: 0.6255 [2021-03-27 00:57:36 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 370/1251] eta: 0:09:23 lr: 0.000671 loss: 3.5443 (3.4185) grad_norm: 1.3010 (1.3332) time: 0.6291 [2021-03-27 00:57:43 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 380/1251] eta: 0:09:16 lr: 0.000671 loss: 3.5194 (3.4145) grad_norm: 1.2517 (1.3320) time: 0.6247 [2021-03-27 00:57:49 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 390/1251] eta: 0:09:10 lr: 0.000671 loss: 3.2612 (3.4132) grad_norm: 1.2562 (1.3334) time: 0.6307 [2021-03-27 00:57:55 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 400/1251] eta: 0:09:04 lr: 0.000671 loss: 3.4158 (3.4126) grad_norm: 1.3174 (1.3329) time: 0.6396 [2021-03-27 00:58:02 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 410/1251] eta: 0:08:57 lr: 0.000671 loss: 3.4752 (3.4111) grad_norm: 1.2626 (1.3313) time: 0.6436 [2021-03-27 00:58:08 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 420/1251] eta: 0:08:51 lr: 0.000671 loss: 3.5776 (3.4133) grad_norm: 1.2088 (1.3289) time: 0.6457 [2021-03-27 00:58:15 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 430/1251] eta: 0:08:44 lr: 0.000671 loss: 3.6339 (3.4139) grad_norm: 1.2229 (1.3282) time: 0.6359 [2021-03-27 00:58:21 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 440/1251] eta: 0:08:38 lr: 0.000671 loss: 3.5971 (3.4181) grad_norm: 1.3870 (1.3335) time: 0.6280 [2021-03-27 00:58:27 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 450/1251] eta: 0:08:31 lr: 0.000671 loss: 3.4996 (3.4206) grad_norm: 1.3280 (1.3304) time: 0.6248 [2021-03-27 00:58:33 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 460/1251] eta: 0:08:25 lr: 0.000671 loss: 3.4104 (3.4208) grad_norm: 1.1924 (1.3292) time: 0.6237 [2021-03-27 00:58:40 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 470/1251] eta: 0:08:18 lr: 0.000671 loss: 3.5754 (3.4265) grad_norm: 1.2921 (1.3293) time: 0.6287 [2021-03-27 00:58:46 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 480/1251] eta: 0:08:11 lr: 0.000671 loss: 3.7369 (3.4301) grad_norm: 1.3056 (1.3291) time: 0.6286 [2021-03-27 00:58:52 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 490/1251] eta: 0:08:05 lr: 0.000671 loss: 3.3858 (3.4268) grad_norm: 1.2809 (1.3291) time: 0.6242 [2021-03-27 00:58:59 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 500/1251] eta: 0:07:59 lr: 0.000671 loss: 3.2276 (3.4259) grad_norm: 1.2418 (1.3285) time: 0.6351 [2021-03-27 00:59:05 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 510/1251] eta: 0:07:52 lr: 0.000671 loss: 3.0491 (3.4192) grad_norm: 1.2109 (1.3283) time: 0.6421 [2021-03-27 00:59:11 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 520/1251] eta: 0:07:46 lr: 0.000671 loss: 3.3986 (3.4193) grad_norm: 1.2191 (1.3286) time: 0.6370 [2021-03-27 00:59:18 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 530/1251] eta: 0:07:39 lr: 0.000671 loss: 3.6569 (3.4236) grad_norm: 1.2639 (1.3291) time: 0.6326 [2021-03-27 00:59:24 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 540/1251] eta: 0:07:33 lr: 0.000671 loss: 3.6569 (3.4260) grad_norm: 1.3209 (1.3308) time: 0.6281 [2021-03-27 00:59:30 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 550/1251] eta: 0:07:26 lr: 0.000671 loss: 3.4512 (3.4205) grad_norm: 1.3289 (1.3298) time: 0.6361 [2021-03-27 00:59:37 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 560/1251] eta: 0:07:20 lr: 0.000670 loss: 3.3824 (3.4205) grad_norm: 1.3289 (1.3297) time: 0.6361 [2021-03-27 00:59:43 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 570/1251] eta: 0:07:14 lr: 0.000670 loss: 3.5324 (3.4209) grad_norm: 1.3358 (1.3296) time: 0.6282 [2021-03-27 00:59:49 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 580/1251] eta: 0:07:07 lr: 0.000670 loss: 3.3823 (3.4192) grad_norm: 1.2291 (1.3295) time: 0.6277 [2021-03-27 00:59:55 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 590/1251] eta: 0:07:01 lr: 0.000670 loss: 3.4075 (3.4195) grad_norm: 1.2291 (1.3287) time: 0.6279 [2021-03-27 01:00:02 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 600/1251] eta: 0:06:54 lr: 0.000670 loss: 3.5921 (3.4218) grad_norm: 1.2574 (1.3287) time: 0.6404 [2021-03-27 01:00:08 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 610/1251] eta: 0:06:48 lr: 0.000670 loss: 3.5327 (3.4198) grad_norm: 1.2700 (1.3287) time: 0.6458 [2021-03-27 01:00:15 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 620/1251] eta: 0:06:42 lr: 0.000670 loss: 3.4372 (3.4199) grad_norm: 1.2891 (1.3279) time: 0.6338 [2021-03-27 01:00:21 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 630/1251] eta: 0:06:35 lr: 0.000670 loss: 3.4711 (3.4209) grad_norm: 1.2213 (1.3261) time: 0.6342 [2021-03-27 01:00:27 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 640/1251] eta: 0:06:29 lr: 0.000670 loss: 3.5456 (3.4217) grad_norm: 1.2186 (1.3257) time: 0.6388 [2021-03-27 01:00:34 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 650/1251] eta: 0:06:22 lr: 0.000670 loss: 3.4518 (3.4234) grad_norm: 1.2811 (1.3259) time: 0.6325 [2021-03-27 01:00:40 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 660/1251] eta: 0:06:16 lr: 0.000670 loss: 3.3124 (3.4198) grad_norm: 1.2811 (1.3259) time: 0.6250 [2021-03-27 01:00:46 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 670/1251] eta: 0:06:09 lr: 0.000670 loss: 3.3111 (3.4208) grad_norm: 1.2763 (1.3261) time: 0.6242 [2021-03-27 01:00:53 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 680/1251] eta: 0:06:03 lr: 0.000670 loss: 3.3111 (3.4173) grad_norm: 1.3279 (1.3269) time: 0.6369 [2021-03-27 01:00:59 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 690/1251] eta: 0:05:57 lr: 0.000670 loss: 3.3879 (3.4187) grad_norm: 1.3175 (1.3259) time: 0.6361 [2021-03-27 01:01:05 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 700/1251] eta: 0:05:50 lr: 0.000670 loss: 3.6365 (3.4188) grad_norm: 1.2263 (1.3252) time: 0.6282 [2021-03-27 01:01:12 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 710/1251] eta: 0:05:44 lr: 0.000670 loss: 3.5564 (3.4188) grad_norm: 1.2263 (1.3249) time: 0.6284 [2021-03-27 01:01:18 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 720/1251] eta: 0:05:37 lr: 0.000670 loss: 3.6891 (3.4223) grad_norm: 1.2746 (1.3248) time: 0.6275 [2021-03-27 01:01:24 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 730/1251] eta: 0:05:31 lr: 0.000670 loss: 3.5362 (3.4186) grad_norm: 1.2778 (1.3243) time: 0.6309 [2021-03-27 01:01:31 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 740/1251] eta: 0:05:25 lr: 0.000670 loss: 3.3493 (3.4183) grad_norm: 1.2664 (1.3230) time: 0.6361 [2021-03-27 01:01:37 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 750/1251] eta: 0:05:18 lr: 0.000670 loss: 3.4332 (3.4159) grad_norm: 1.2455 (1.3224) time: 0.6321 [2021-03-27 01:01:43 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 760/1251] eta: 0:05:12 lr: 0.000670 loss: 3.5138 (3.4172) grad_norm: 1.2836 (1.3225) time: 0.6227 [2021-03-27 01:01:49 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 770/1251] eta: 0:05:05 lr: 0.000670 loss: 3.5822 (3.4201) grad_norm: 1.2935 (1.3228) time: 0.6228 [2021-03-27 01:01:56 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 780/1251] eta: 0:04:59 lr: 0.000670 loss: 3.5817 (3.4204) grad_norm: 1.3049 (1.3233) time: 0.6268 [2021-03-27 01:02:02 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 790/1251] eta: 0:04:52 lr: 0.000670 loss: 3.4719 (3.4211) grad_norm: 1.2634 (1.3224) time: 0.6261 [2021-03-27 01:02:08 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 800/1251] eta: 0:04:46 lr: 0.000670 loss: 3.5424 (3.4216) grad_norm: 1.2592 (1.3230) time: 0.6214 [2021-03-27 01:02:14 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 810/1251] eta: 0:04:40 lr: 0.000670 loss: 3.3211 (3.4198) grad_norm: 1.2223 (1.3223) time: 0.6254 [2021-03-27 01:02:21 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 820/1251] eta: 0:04:33 lr: 0.000669 loss: 3.3589 (3.4199) grad_norm: 1.2586 (1.3225) time: 0.6308 [2021-03-27 01:02:27 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 830/1251] eta: 0:04:27 lr: 0.000669 loss: 3.4905 (3.4199) grad_norm: 1.3391 (1.3236) time: 0.6366 [2021-03-27 01:02:33 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 840/1251] eta: 0:04:21 lr: 0.000669 loss: 3.5154 (3.4209) grad_norm: 1.2654 (1.3222) time: 0.6338 [2021-03-27 01:02:40 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 850/1251] eta: 0:04:14 lr: 0.000669 loss: 3.7454 (3.4232) grad_norm: 1.2212 (1.3213) time: 0.6281 [2021-03-27 01:02:46 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 860/1251] eta: 0:04:08 lr: 0.000669 loss: 3.7454 (3.4279) grad_norm: 1.2264 (1.3201) time: 0.6326 [2021-03-27 01:02:52 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 870/1251] eta: 0:04:01 lr: 0.000669 loss: 3.7306 (3.4285) grad_norm: 1.2595 (1.3198) time: 0.6315 [2021-03-27 01:02:58 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 880/1251] eta: 0:03:55 lr: 0.000669 loss: 3.3772 (3.4255) grad_norm: 1.2941 (1.3190) time: 0.6248 [2021-03-27 01:03:05 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 890/1251] eta: 0:03:49 lr: 0.000669 loss: 3.2603 (3.4233) grad_norm: 1.2481 (1.3178) time: 0.6307 [2021-03-27 01:03:11 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 900/1251] eta: 0:03:42 lr: 0.000669 loss: 3.2603 (3.4217) grad_norm: 1.2570 (1.3186) time: 0.6363 [2021-03-27 01:03:17 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 910/1251] eta: 0:03:36 lr: 0.000669 loss: 3.2777 (3.4215) grad_norm: 1.2852 (inf) time: 0.6286 [2021-03-27 01:03:24 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 920/1251] eta: 0:03:30 lr: 0.000669 loss: 3.6266 (3.4236) grad_norm: 1.2852 (inf) time: 0.6262 [2021-03-27 01:03:30 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 930/1251] eta: 0:03:23 lr: 0.000669 loss: 3.6362 (3.4219) grad_norm: 1.2813 (inf) time: 0.6353 [2021-03-27 01:03:37 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 940/1251] eta: 0:03:17 lr: 0.000669 loss: 3.3012 (3.4199) grad_norm: 1.2525 (inf) time: 0.6404 [2021-03-27 01:03:43 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 950/1251] eta: 0:03:11 lr: 0.000669 loss: 3.6550 (3.4217) grad_norm: 1.2655 (inf) time: 0.6321 [2021-03-27 01:03:49 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 960/1251] eta: 0:03:04 lr: 0.000669 loss: 3.7261 (3.4224) grad_norm: 1.2839 (inf) time: 0.6260 [2021-03-27 01:03:55 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 970/1251] eta: 0:02:58 lr: 0.000669 loss: 3.5990 (3.4243) grad_norm: 1.2513 (inf) time: 0.6341 [2021-03-27 01:04:02 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 980/1251] eta: 0:02:52 lr: 0.000669 loss: 3.5990 (3.4258) grad_norm: 1.2476 (inf) time: 0.6347 [2021-03-27 01:04:08 swin_base_patch4_window7_224] INFO: Epoch: [117] [ 990/1251] eta: 0:02:45 lr: 0.000669 loss: 3.5663 (3.4273) grad_norm: 1.2564 (inf) time: 0.6267 [2021-03-27 01:04:14 swin_base_patch4_window7_224] INFO: Epoch: [117] [1000/1251] eta: 0:02:39 lr: 0.000669 loss: 3.5467 (3.4286) grad_norm: 1.2564 (inf) time: 0.6251 [2021-03-27 01:04:21 swin_base_patch4_window7_224] INFO: Epoch: [117] [1010/1251] eta: 0:02:32 lr: 0.000669 loss: 3.5467 (3.4275) grad_norm: 1.3514 (inf) time: 0.6296 [2021-03-27 01:04:27 swin_base_patch4_window7_224] INFO: Epoch: [117] [1020/1251] eta: 0:02:26 lr: 0.000669 loss: 3.5160 (3.4273) grad_norm: 1.2880 (inf) time: 0.6392 [2021-03-27 01:04:33 swin_base_patch4_window7_224] INFO: Epoch: [117] [1030/1251] eta: 0:02:20 lr: 0.000669 loss: 3.5242 (3.4285) grad_norm: 1.3038 (inf) time: 0.6317 [2021-03-27 01:04:39 swin_base_patch4_window7_224] INFO: Epoch: [117] [1040/1251] eta: 0:02:13 lr: 0.000669 loss: 3.4448 (3.4272) grad_norm: 1.3207 (inf) time: 0.6208 [2021-03-27 01:04:46 swin_base_patch4_window7_224] INFO: Epoch: [117] [1050/1251] eta: 0:02:07 lr: 0.000669 loss: 3.3769 (3.4274) grad_norm: 1.3073 (inf) time: 0.6293 [2021-03-27 01:04:52 swin_base_patch4_window7_224] INFO: Epoch: [117] [1060/1251] eta: 0:02:01 lr: 0.000669 loss: 3.3433 (3.4247) grad_norm: 1.2642 (inf) time: 0.6321 [2021-03-27 01:04:58 swin_base_patch4_window7_224] INFO: Epoch: [117] [1070/1251] eta: 0:01:54 lr: 0.000668 loss: 3.1254 (3.4235) grad_norm: 1.2085 (inf) time: 0.6273 [2021-03-27 01:05:05 swin_base_patch4_window7_224] INFO: Epoch: [117] [1080/1251] eta: 0:01:48 lr: 0.000668 loss: 3.4441 (3.4241) grad_norm: 1.2929 (inf) time: 0.6242 [2021-03-27 01:05:11 swin_base_patch4_window7_224] INFO: Epoch: [117] [1090/1251] eta: 0:01:42 lr: 0.000668 loss: 3.5944 (3.4258) grad_norm: 1.2523 (inf) time: 0.6210 [2021-03-27 01:05:17 swin_base_patch4_window7_224] INFO: Epoch: [117] [1100/1251] eta: 0:01:35 lr: 0.000668 loss: 3.6421 (3.4271) grad_norm: 1.2791 (inf) time: 0.6284 [2021-03-27 01:05:23 swin_base_patch4_window7_224] INFO: Epoch: [117] [1110/1251] eta: 0:01:29 lr: 0.000668 loss: 3.7863 (3.4289) grad_norm: 1.3869 (inf) time: 0.6302 [2021-03-27 01:05:30 swin_base_patch4_window7_224] INFO: Epoch: [117] [1120/1251] eta: 0:01:23 lr: 0.000668 loss: 3.7863 (3.4303) grad_norm: 1.2433 (inf) time: 0.6270 [2021-03-27 01:05:36 swin_base_patch4_window7_224] INFO: Epoch: [117] [1130/1251] eta: 0:01:16 lr: 0.000668 loss: 3.2496 (3.4286) grad_norm: 1.2298 (inf) time: 0.6257 [2021-03-27 01:05:42 swin_base_patch4_window7_224] INFO: Epoch: [117] [1140/1251] eta: 0:01:10 lr: 0.000668 loss: 3.2559 (3.4288) grad_norm: 1.3288 (inf) time: 0.6239 [2021-03-27 01:05:48 swin_base_patch4_window7_224] INFO: Epoch: [117] [1150/1251] eta: 0:01:04 lr: 0.000668 loss: 3.4547 (3.4286) grad_norm: 1.4003 (inf) time: 0.6268 [2021-03-27 01:05:55 swin_base_patch4_window7_224] INFO: Epoch: [117] [1160/1251] eta: 0:00:57 lr: 0.000668 loss: 3.4963 (3.4286) grad_norm: 1.3696 (inf) time: 0.6285 [2021-03-27 01:06:01 swin_base_patch4_window7_224] INFO: Epoch: [117] [1170/1251] eta: 0:00:51 lr: 0.000668 loss: 3.4698 (3.4291) grad_norm: 1.2794 (inf) time: 0.6231 [2021-03-27 01:06:07 swin_base_patch4_window7_224] INFO: Epoch: [117] [1180/1251] eta: 0:00:44 lr: 0.000668 loss: 3.3525 (3.4272) grad_norm: 1.2957 (inf) time: 0.6213 [2021-03-27 01:06:13 swin_base_patch4_window7_224] INFO: Epoch: [117] [1190/1251] eta: 0:00:38 lr: 0.000668 loss: 3.4789 (3.4283) grad_norm: 1.3333 (inf) time: 0.6262 [2021-03-27 01:06:20 swin_base_patch4_window7_224] INFO: Epoch: [117] [1200/1251] eta: 0:00:32 lr: 0.000668 loss: 3.4789 (3.4279) grad_norm: 1.2865 (inf) time: 0.6303 [2021-03-27 01:06:26 swin_base_patch4_window7_224] INFO: Epoch: [117] [1210/1251] eta: 0:00:25 lr: 0.000668 loss: 3.5134 (3.4293) grad_norm: 1.2048 (inf) time: 0.6289 [2021-03-27 01:06:32 swin_base_patch4_window7_224] INFO: Epoch: [117] [1220/1251] eta: 0:00:19 lr: 0.000668 loss: 3.7866 (3.4323) grad_norm: 1.1990 (inf) time: 0.6263 [2021-03-27 01:06:39 swin_base_patch4_window7_224] INFO: Epoch: [117] [1230/1251] eta: 0:00:13 lr: 0.000668 loss: 3.6551 (3.4334) grad_norm: 1.2204 (inf) time: 0.6268 [2021-03-27 01:06:45 swin_base_patch4_window7_224] INFO: Epoch: [117] [1240/1251] eta: 0:00:06 lr: 0.000668 loss: 3.5096 (3.4327) grad_norm: 1.2473 (inf) time: 0.6300 [2021-03-27 01:06:51 swin_base_patch4_window7_224] INFO: Epoch: [117] [1250/1251] eta: 0:00:00 lr: 0.000668 loss: 3.5568 (3.4342) grad_norm: 1.3238 (inf) time: 0.6367 [2021-03-27 01:06:58 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:13 loss: 1.0700 (1.0700) acc1: 76.5625 (76.5625) acc5: 95.3125 (95.3125) [2021-03-27 01:07:01 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9144 (0.9232) acc1: 78.1250 (79.6875) acc5: 95.3125 (94.3182) [2021-03-27 01:07:02 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9144 (0.9620) acc1: 78.1250 (78.7946) acc5: 95.3125 (94.3452) [2021-03-27 01:07:04 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9815 (0.9753) acc1: 75.0000 (77.6714) acc5: 95.3125 (94.3548) [2021-03-27 01:07:06 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9815 (0.9785) acc1: 75.0000 (77.5152) acc5: 93.7500 (94.3216) [2021-03-27 01:07:07 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9810 (0.9742) acc1: 76.5625 (77.2160) acc5: 93.7500 (94.4000) [2021-03-27 01:07:15 swin_base_patch4_window7_224] INFO: * Acc@1 77.436 Acc@5 94.144 loss 0.968 [2021-03-27 01:07:15 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.4% [2021-03-27 01:07:15 swin_base_patch4_window7_224] INFO: Max accuracy: 77.53% [2021-03-27 01:07:19 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 0/1251] eta: 1:27:11 lr: 0.000668 loss: 2.5045 (2.5045) grad_norm: 1.5332 (1.5332) time: 4.1818 [2021-03-27 01:07:26 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 10/1251] eta: 0:20:16 lr: 0.000668 loss: 3.3593 (3.3995) grad_norm: 1.4190 (1.3633) time: 0.9804 [2021-03-27 01:07:32 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 20/1251] eta: 0:16:44 lr: 0.000668 loss: 3.4487 (3.4491) grad_norm: 1.2893 (1.3420) time: 0.6477 [2021-03-27 01:07:39 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 30/1251] eta: 0:15:24 lr: 0.000668 loss: 3.5401 (3.4723) grad_norm: 1.2865 (1.3264) time: 0.6340 [2021-03-27 01:07:45 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 40/1251] eta: 0:14:44 lr: 0.000668 loss: 3.3975 (3.4245) grad_norm: 1.3015 (1.3345) time: 0.6402 [2021-03-27 01:07:51 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 50/1251] eta: 0:14:13 lr: 0.000668 loss: 3.5058 (3.4900) grad_norm: 1.3015 (1.3298) time: 0.6396 [2021-03-27 01:07:58 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 60/1251] eta: 0:13:51 lr: 0.000668 loss: 3.6971 (3.5063) grad_norm: 1.2939 (1.3325) time: 0.6316 [2021-03-27 01:08:04 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 70/1251] eta: 0:13:33 lr: 0.000668 loss: 3.2926 (3.4263) grad_norm: 1.3287 (1.3379) time: 0.6338 [2021-03-27 01:08:10 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 80/1251] eta: 0:13:19 lr: 0.000667 loss: 3.2926 (3.4370) grad_norm: 1.2958 (1.3292) time: 0.6352 [2021-03-27 01:08:17 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 90/1251] eta: 0:13:05 lr: 0.000667 loss: 3.5608 (3.4288) grad_norm: 1.2542 (1.3251) time: 0.6316 [2021-03-27 01:08:23 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 100/1251] eta: 0:12:53 lr: 0.000667 loss: 3.4080 (3.4238) grad_norm: 1.2566 (1.3281) time: 0.6285 [2021-03-27 01:08:29 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 110/1251] eta: 0:12:41 lr: 0.000667 loss: 3.5547 (3.4424) grad_norm: 1.2491 (1.3229) time: 0.6253 [2021-03-27 01:08:35 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 120/1251] eta: 0:12:31 lr: 0.000667 loss: 3.5547 (3.4355) grad_norm: 1.2878 (1.3261) time: 0.6285 [2021-03-27 01:08:42 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 130/1251] eta: 0:12:22 lr: 0.000667 loss: 3.3517 (3.4144) grad_norm: 1.3223 (1.3296) time: 0.6356 [2021-03-27 01:08:48 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 140/1251] eta: 0:12:12 lr: 0.000667 loss: 3.2749 (3.4137) grad_norm: 1.2569 (1.3256) time: 0.6296 [2021-03-27 01:08:54 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 150/1251] eta: 0:12:04 lr: 0.000667 loss: 3.5340 (3.4239) grad_norm: 1.2737 (1.3265) time: 0.6286 [2021-03-27 01:09:01 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 160/1251] eta: 0:11:56 lr: 0.000667 loss: 3.6415 (3.4318) grad_norm: 1.2981 (1.3246) time: 0.6328 [2021-03-27 01:09:07 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 170/1251] eta: 0:11:47 lr: 0.000667 loss: 3.6131 (3.4445) grad_norm: 1.2981 (1.3281) time: 0.6302 [2021-03-27 01:09:13 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 180/1251] eta: 0:11:40 lr: 0.000667 loss: 3.6861 (3.4539) grad_norm: 1.2798 (1.3301) time: 0.6324 [2021-03-27 01:09:20 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 190/1251] eta: 0:11:31 lr: 0.000667 loss: 3.5056 (3.4523) grad_norm: 1.2430 (1.3280) time: 0.6305 [2021-03-27 01:09:26 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 200/1251] eta: 0:11:24 lr: 0.000667 loss: 3.3580 (3.4485) grad_norm: 1.2962 (1.3290) time: 0.6299 [2021-03-27 01:09:32 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 210/1251] eta: 0:11:16 lr: 0.000667 loss: 3.2812 (3.4373) grad_norm: 1.3244 (1.3289) time: 0.6315 [2021-03-27 01:09:39 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 220/1251] eta: 0:11:09 lr: 0.000667 loss: 3.2812 (3.4335) grad_norm: 1.2568 (1.3270) time: 0.6321 [2021-03-27 01:09:45 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 230/1251] eta: 0:11:02 lr: 0.000667 loss: 3.3852 (3.4308) grad_norm: 1.2493 (1.3256) time: 0.6320 [2021-03-27 01:09:51 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 240/1251] eta: 0:10:55 lr: 0.000667 loss: 3.3947 (3.4219) grad_norm: 1.2976 (1.3239) time: 0.6298 [2021-03-27 01:09:57 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 250/1251] eta: 0:10:47 lr: 0.000667 loss: 3.2242 (3.4181) grad_norm: 1.3252 (1.3273) time: 0.6273 [2021-03-27 01:10:04 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 260/1251] eta: 0:10:40 lr: 0.000667 loss: 3.2723 (3.4100) grad_norm: 1.2636 (1.3243) time: 0.6259 [2021-03-27 01:10:10 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 270/1251] eta: 0:10:33 lr: 0.000667 loss: 3.2723 (3.3998) grad_norm: 1.2705 (1.3275) time: 0.6274 [2021-03-27 01:10:16 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 280/1251] eta: 0:10:26 lr: 0.000667 loss: 3.4376 (3.4081) grad_norm: 1.3358 (1.3316) time: 0.6273 [2021-03-27 01:10:23 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 290/1251] eta: 0:10:19 lr: 0.000667 loss: 3.4376 (3.4041) grad_norm: 1.3551 (1.3316) time: 0.6314 [2021-03-27 01:10:29 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 300/1251] eta: 0:10:12 lr: 0.000667 loss: 3.4067 (3.4027) grad_norm: 1.3548 (1.3345) time: 0.6340 [2021-03-27 01:10:35 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 310/1251] eta: 0:10:05 lr: 0.000667 loss: 3.3614 (3.3981) grad_norm: 1.3729 (1.3358) time: 0.6304 [2021-03-27 01:10:42 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 320/1251] eta: 0:09:58 lr: 0.000667 loss: 3.2723 (3.3903) grad_norm: 1.3356 (1.3350) time: 0.6301 [2021-03-27 01:10:48 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 330/1251] eta: 0:09:52 lr: 0.000666 loss: 3.6147 (3.4011) grad_norm: 1.3116 (1.3365) time: 0.6306 [2021-03-27 01:10:54 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 340/1251] eta: 0:09:45 lr: 0.000666 loss: 3.7849 (3.4016) grad_norm: 1.2839 (1.3388) time: 0.6281 [2021-03-27 01:11:00 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 350/1251] eta: 0:09:38 lr: 0.000666 loss: 3.5262 (3.4089) grad_norm: 1.3236 (1.3397) time: 0.6242 [2021-03-27 01:11:07 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 360/1251] eta: 0:09:31 lr: 0.000666 loss: 3.5262 (3.4098) grad_norm: 1.3236 (1.3417) time: 0.6237 [2021-03-27 01:11:13 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 370/1251] eta: 0:09:24 lr: 0.000666 loss: 3.3474 (3.4135) grad_norm: 1.2642 (1.3393) time: 0.6305 [2021-03-27 01:11:19 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 380/1251] eta: 0:09:18 lr: 0.000666 loss: 3.4239 (3.4113) grad_norm: 1.2442 (1.3377) time: 0.6297 [2021-03-27 01:11:26 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 390/1251] eta: 0:09:11 lr: 0.000666 loss: 3.4551 (3.4124) grad_norm: 1.2535 (1.3364) time: 0.6269 [2021-03-27 01:11:32 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 400/1251] eta: 0:09:05 lr: 0.000666 loss: 3.6438 (3.4196) grad_norm: 1.2919 (1.3389) time: 0.6350 [2021-03-27 01:11:38 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 410/1251] eta: 0:08:58 lr: 0.000666 loss: 3.5712 (3.4096) grad_norm: 1.3224 (1.3391) time: 0.6320 [2021-03-27 01:11:45 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 420/1251] eta: 0:08:51 lr: 0.000666 loss: 3.2962 (3.4109) grad_norm: 1.3619 (1.3412) time: 0.6330 [2021-03-27 01:11:51 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 430/1251] eta: 0:08:45 lr: 0.000666 loss: 3.6948 (3.4150) grad_norm: 1.4061 (1.3427) time: 0.6360 [2021-03-27 01:11:57 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 440/1251] eta: 0:08:38 lr: 0.000666 loss: 3.6948 (3.4176) grad_norm: 1.4319 (1.3465) time: 0.6249 [2021-03-27 01:12:03 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 450/1251] eta: 0:08:31 lr: 0.000666 loss: 3.4249 (3.4172) grad_norm: 1.3441 (1.3452) time: 0.6246 [2021-03-27 01:12:10 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 460/1251] eta: 0:08:25 lr: 0.000666 loss: 3.1584 (3.4112) grad_norm: 1.3688 (1.3478) time: 0.6287 [2021-03-27 01:12:16 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 470/1251] eta: 0:08:18 lr: 0.000666 loss: 3.1861 (3.4106) grad_norm: 1.3724 (1.3476) time: 0.6273 [2021-03-27 01:12:22 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 480/1251] eta: 0:08:12 lr: 0.000666 loss: 3.6328 (3.4134) grad_norm: 1.2832 (1.3462) time: 0.6224 [2021-03-27 01:12:28 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 490/1251] eta: 0:08:05 lr: 0.000666 loss: 3.6398 (3.4168) grad_norm: 1.2835 (1.3459) time: 0.6211 [2021-03-27 01:12:35 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 500/1251] eta: 0:07:58 lr: 0.000666 loss: 3.4618 (3.4170) grad_norm: 1.2965 (1.3470) time: 0.6248 [2021-03-27 01:12:41 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 510/1251] eta: 0:07:52 lr: 0.000666 loss: 3.2354 (3.4118) grad_norm: 1.3003 (1.3473) time: 0.6281 [2021-03-27 01:12:47 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 520/1251] eta: 0:07:46 lr: 0.000666 loss: 3.4869 (3.4168) grad_norm: 1.3394 (1.3475) time: 0.6320 [2021-03-27 01:12:54 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 530/1251] eta: 0:07:39 lr: 0.000666 loss: 3.5634 (3.4158) grad_norm: 1.3605 (1.3483) time: 0.6316 [2021-03-27 01:13:00 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 540/1251] eta: 0:07:33 lr: 0.000666 loss: 3.4814 (3.4175) grad_norm: 1.2881 (1.3475) time: 0.6307 [2021-03-27 01:13:06 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 550/1251] eta: 0:07:26 lr: 0.000666 loss: 3.3686 (3.4137) grad_norm: 1.2723 (1.3484) time: 0.6349 [2021-03-27 01:13:13 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 560/1251] eta: 0:07:20 lr: 0.000666 loss: 3.4546 (3.4144) grad_norm: 1.3279 (1.3477) time: 0.6306 [2021-03-27 01:13:19 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 570/1251] eta: 0:07:13 lr: 0.000666 loss: 3.6403 (3.4179) grad_norm: 1.2431 (1.3463) time: 0.6317 [2021-03-27 01:13:25 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 580/1251] eta: 0:07:07 lr: 0.000666 loss: 3.5316 (3.4197) grad_norm: 1.2898 (1.3478) time: 0.6355 [2021-03-27 01:13:32 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 590/1251] eta: 0:07:00 lr: 0.000665 loss: 3.7303 (3.4217) grad_norm: 1.4032 (1.3487) time: 0.6312 [2021-03-27 01:13:38 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 600/1251] eta: 0:06:54 lr: 0.000665 loss: 3.7303 (3.4232) grad_norm: 1.3436 (1.3494) time: 0.6295 [2021-03-27 01:13:44 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 610/1251] eta: 0:06:48 lr: 0.000665 loss: 3.2885 (3.4180) grad_norm: 1.2708 (1.3489) time: 0.6284 [2021-03-27 01:13:50 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 620/1251] eta: 0:06:41 lr: 0.000665 loss: 3.5546 (3.4248) grad_norm: 1.2633 (1.3478) time: 0.6329 [2021-03-27 01:13:57 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 630/1251] eta: 0:06:35 lr: 0.000665 loss: 3.6780 (3.4248) grad_norm: 1.2731 (1.3475) time: 0.6353 [2021-03-27 01:14:03 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 640/1251] eta: 0:06:28 lr: 0.000665 loss: 3.6489 (3.4310) grad_norm: 1.3120 (1.3471) time: 0.6301 [2021-03-27 01:14:09 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 650/1251] eta: 0:06:22 lr: 0.000665 loss: 3.7407 (3.4296) grad_norm: 1.3543 (1.3474) time: 0.6276 [2021-03-27 01:14:16 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 660/1251] eta: 0:06:15 lr: 0.000665 loss: 3.4087 (3.4303) grad_norm: 1.3819 (1.3488) time: 0.6267 [2021-03-27 01:14:22 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 670/1251] eta: 0:06:09 lr: 0.000665 loss: 3.4211 (3.4280) grad_norm: 1.3700 (1.3487) time: 0.6305 [2021-03-27 01:14:28 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 680/1251] eta: 0:06:03 lr: 0.000665 loss: 3.3662 (3.4263) grad_norm: 1.3368 (1.3486) time: 0.6290 [2021-03-27 01:14:34 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 690/1251] eta: 0:05:56 lr: 0.000665 loss: 3.3805 (3.4231) grad_norm: 1.3125 (1.3476) time: 0.6245 [2021-03-27 01:14:41 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 700/1251] eta: 0:05:50 lr: 0.000665 loss: 3.3985 (3.4236) grad_norm: 1.2290 (1.3462) time: 0.6244 [2021-03-27 01:14:47 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 710/1251] eta: 0:05:43 lr: 0.000665 loss: 3.5540 (3.4240) grad_norm: 1.2089 (1.3444) time: 0.6289 [2021-03-27 01:14:53 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 720/1251] eta: 0:05:37 lr: 0.000665 loss: 3.3776 (3.4238) grad_norm: 1.2558 (1.3443) time: 0.6344 [2021-03-27 01:15:00 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 730/1251] eta: 0:05:31 lr: 0.000665 loss: 3.3776 (3.4249) grad_norm: 1.3055 (1.3454) time: 0.6323 [2021-03-27 01:15:06 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 740/1251] eta: 0:05:24 lr: 0.000665 loss: 3.5548 (3.4248) grad_norm: 1.3134 (1.3458) time: 0.6344 [2021-03-27 01:15:12 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 750/1251] eta: 0:05:18 lr: 0.000665 loss: 3.3849 (3.4222) grad_norm: 1.3134 (1.3453) time: 0.6372 [2021-03-27 01:15:19 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 760/1251] eta: 0:05:12 lr: 0.000665 loss: 3.4543 (3.4244) grad_norm: 1.3612 (1.3454) time: 0.6358 [2021-03-27 01:15:25 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 770/1251] eta: 0:05:05 lr: 0.000665 loss: 3.5304 (3.4258) grad_norm: 1.3521 (1.3452) time: 0.6327 [2021-03-27 01:15:32 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 780/1251] eta: 0:04:59 lr: 0.000665 loss: 3.6556 (3.4291) grad_norm: 1.3342 (1.3447) time: 0.6396 [2021-03-27 01:15:38 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 790/1251] eta: 0:04:53 lr: 0.000665 loss: 3.6566 (3.4325) grad_norm: 1.2455 (1.3442) time: 0.6408 [2021-03-27 01:15:44 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 800/1251] eta: 0:04:46 lr: 0.000665 loss: 3.6461 (3.4336) grad_norm: 1.2879 (1.3461) time: 0.6303 [2021-03-27 01:15:51 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 810/1251] eta: 0:04:40 lr: 0.000665 loss: 3.5569 (3.4340) grad_norm: 1.3372 (1.3452) time: 0.6299 [2021-03-27 01:15:57 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 820/1251] eta: 0:04:33 lr: 0.000665 loss: 3.2961 (3.4310) grad_norm: 1.3148 (1.3451) time: 0.6320 [2021-03-27 01:16:03 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 830/1251] eta: 0:04:27 lr: 0.000665 loss: 3.3117 (3.4307) grad_norm: 1.2826 (1.3446) time: 0.6387 [2021-03-27 01:16:10 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 840/1251] eta: 0:04:21 lr: 0.000664 loss: 3.5508 (3.4326) grad_norm: 1.2768 (1.3447) time: 0.6376 [2021-03-27 01:16:16 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 850/1251] eta: 0:04:14 lr: 0.000664 loss: 3.4357 (3.4324) grad_norm: 1.3451 (1.3452) time: 0.6313 [2021-03-27 01:16:22 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 860/1251] eta: 0:04:08 lr: 0.000664 loss: 3.4307 (3.4327) grad_norm: 1.2855 (1.3442) time: 0.6353 [2021-03-27 01:16:29 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 870/1251] eta: 0:04:02 lr: 0.000664 loss: 3.5459 (3.4341) grad_norm: 1.2771 (1.3440) time: 0.6379 [2021-03-27 01:16:35 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 880/1251] eta: 0:03:55 lr: 0.000664 loss: 3.5063 (3.4297) grad_norm: 1.2837 (1.3439) time: 0.6361 [2021-03-27 01:16:41 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 890/1251] eta: 0:03:49 lr: 0.000664 loss: 3.0682 (3.4275) grad_norm: 1.2278 (1.3434) time: 0.6320 [2021-03-27 01:16:48 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 900/1251] eta: 0:03:43 lr: 0.000664 loss: 3.4199 (3.4283) grad_norm: 1.2264 (1.3432) time: 0.6302 [2021-03-27 01:16:54 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 910/1251] eta: 0:03:36 lr: 0.000664 loss: 3.6133 (3.4325) grad_norm: 1.2264 (1.3418) time: 0.6317 [2021-03-27 01:17:00 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 920/1251] eta: 0:03:30 lr: 0.000664 loss: 3.5437 (3.4292) grad_norm: 1.2239 (1.3406) time: 0.6280 [2021-03-27 01:17:06 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 930/1251] eta: 0:03:23 lr: 0.000664 loss: 3.2464 (3.4292) grad_norm: 1.1944 (1.3389) time: 0.6248 [2021-03-27 01:17:13 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 940/1251] eta: 0:03:17 lr: 0.000664 loss: 3.4911 (3.4290) grad_norm: 1.1902 (1.3377) time: 0.6310 [2021-03-27 01:17:19 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 950/1251] eta: 0:03:11 lr: 0.000664 loss: 3.4911 (3.4283) grad_norm: 1.2055 (1.3365) time: 0.6366 [2021-03-27 01:17:25 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 960/1251] eta: 0:03:04 lr: 0.000664 loss: 3.4782 (3.4261) grad_norm: 1.3111 (1.3371) time: 0.6318 [2021-03-27 01:17:32 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 970/1251] eta: 0:02:58 lr: 0.000664 loss: 3.4782 (3.4293) grad_norm: 1.3111 (1.3364) time: 0.6260 [2021-03-27 01:17:38 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 980/1251] eta: 0:02:52 lr: 0.000664 loss: 3.4895 (3.4281) grad_norm: 1.2834 (1.3366) time: 0.6267 [2021-03-27 01:17:44 swin_base_patch4_window7_224] INFO: Epoch: [118] [ 990/1251] eta: 0:02:45 lr: 0.000664 loss: 3.3973 (3.4276) grad_norm: 1.3123 (1.3376) time: 0.6289 [2021-03-27 01:17:51 swin_base_patch4_window7_224] INFO: Epoch: [118] [1000/1251] eta: 0:02:39 lr: 0.000664 loss: 3.3973 (3.4264) grad_norm: 1.2286 (1.3363) time: 0.6292 [2021-03-27 01:17:57 swin_base_patch4_window7_224] INFO: Epoch: [118] [1010/1251] eta: 0:02:32 lr: 0.000664 loss: 3.4536 (3.4262) grad_norm: 1.2112 (1.3367) time: 0.6299 [2021-03-27 01:18:03 swin_base_patch4_window7_224] INFO: Epoch: [118] [1020/1251] eta: 0:02:26 lr: 0.000664 loss: 3.7251 (3.4275) grad_norm: 1.2306 (1.3358) time: 0.6274 [2021-03-27 01:18:10 swin_base_patch4_window7_224] INFO: Epoch: [118] [1030/1251] eta: 0:02:20 lr: 0.000664 loss: 3.5948 (3.4295) grad_norm: 1.2291 (1.3361) time: 0.6312 [2021-03-27 01:18:16 swin_base_patch4_window7_224] INFO: Epoch: [118] [1040/1251] eta: 0:02:13 lr: 0.000664 loss: 3.4556 (3.4288) grad_norm: 1.2907 (1.3360) time: 0.6355 [2021-03-27 01:18:22 swin_base_patch4_window7_224] INFO: Epoch: [118] [1050/1251] eta: 0:02:07 lr: 0.000664 loss: 3.3713 (3.4294) grad_norm: 1.2907 (1.3353) time: 0.6314 [2021-03-27 01:18:28 swin_base_patch4_window7_224] INFO: Epoch: [118] [1060/1251] eta: 0:02:01 lr: 0.000664 loss: 3.4474 (3.4295) grad_norm: 1.2934 (1.3361) time: 0.6291 [2021-03-27 01:18:35 swin_base_patch4_window7_224] INFO: Epoch: [118] [1070/1251] eta: 0:01:54 lr: 0.000664 loss: 3.3878 (3.4299) grad_norm: 1.2567 (1.3353) time: 0.6278 [2021-03-27 01:18:41 swin_base_patch4_window7_224] INFO: Epoch: [118] [1080/1251] eta: 0:01:48 lr: 0.000664 loss: 3.4484 (3.4314) grad_norm: 1.2410 (1.3349) time: 0.6318 [2021-03-27 01:18:47 swin_base_patch4_window7_224] INFO: Epoch: [118] [1090/1251] eta: 0:01:42 lr: 0.000664 loss: 3.4207 (3.4288) grad_norm: 1.2679 (1.3346) time: 0.6292 [2021-03-27 01:18:54 swin_base_patch4_window7_224] INFO: Epoch: [118] [1100/1251] eta: 0:01:35 lr: 0.000663 loss: 3.0775 (3.4264) grad_norm: 1.3054 (1.3347) time: 0.6294 [2021-03-27 01:19:00 swin_base_patch4_window7_224] INFO: Epoch: [118] [1110/1251] eta: 0:01:29 lr: 0.000663 loss: 3.3936 (3.4281) grad_norm: 1.2682 (1.3339) time: 0.6291 [2021-03-27 01:19:06 swin_base_patch4_window7_224] INFO: Epoch: [118] [1120/1251] eta: 0:01:23 lr: 0.000663 loss: 3.5640 (3.4301) grad_norm: 1.2682 (1.3342) time: 0.6290 [2021-03-27 01:19:12 swin_base_patch4_window7_224] INFO: Epoch: [118] [1130/1251] eta: 0:01:16 lr: 0.000663 loss: 3.5640 (3.4316) grad_norm: 1.2837 (1.3343) time: 0.6277 [2021-03-27 01:19:19 swin_base_patch4_window7_224] INFO: Epoch: [118] [1140/1251] eta: 0:01:10 lr: 0.000663 loss: 3.5010 (3.4303) grad_norm: 1.3725 (1.3350) time: 0.6198 [2021-03-27 01:19:25 swin_base_patch4_window7_224] INFO: Epoch: [118] [1150/1251] eta: 0:01:04 lr: 0.000663 loss: 3.6001 (3.4322) grad_norm: 1.4091 (1.3355) time: 0.6277 [2021-03-27 01:19:31 swin_base_patch4_window7_224] INFO: Epoch: [118] [1160/1251] eta: 0:00:57 lr: 0.000663 loss: 3.8030 (3.4334) grad_norm: 1.4091 (1.3363) time: 0.6319 [2021-03-27 01:19:38 swin_base_patch4_window7_224] INFO: Epoch: [118] [1170/1251] eta: 0:00:51 lr: 0.000663 loss: 3.3674 (3.4311) grad_norm: 1.4044 (1.3377) time: 0.6289 [2021-03-27 01:19:44 swin_base_patch4_window7_224] INFO: Epoch: [118] [1180/1251] eta: 0:00:45 lr: 0.000663 loss: 3.3674 (3.4311) grad_norm: 1.3601 (1.3372) time: 0.6328 [2021-03-27 01:19:50 swin_base_patch4_window7_224] INFO: Epoch: [118] [1190/1251] eta: 0:00:38 lr: 0.000663 loss: 3.4090 (3.4294) grad_norm: 1.2728 (1.3368) time: 0.6383 [2021-03-27 01:19:57 swin_base_patch4_window7_224] INFO: Epoch: [118] [1200/1251] eta: 0:00:32 lr: 0.000663 loss: 3.2777 (3.4291) grad_norm: 1.2558 (1.3372) time: 0.6411 [2021-03-27 01:20:03 swin_base_patch4_window7_224] INFO: Epoch: [118] [1210/1251] eta: 0:00:25 lr: 0.000663 loss: 3.4844 (3.4316) grad_norm: 1.3382 (1.3380) time: 0.6340 [2021-03-27 01:20:09 swin_base_patch4_window7_224] INFO: Epoch: [118] [1220/1251] eta: 0:00:19 lr: 0.000663 loss: 3.4547 (3.4304) grad_norm: 1.3494 (1.3380) time: 0.6236 [2021-03-27 01:20:16 swin_base_patch4_window7_224] INFO: Epoch: [118] [1230/1251] eta: 0:00:13 lr: 0.000663 loss: 3.3985 (3.4287) grad_norm: 1.2848 (1.3378) time: 0.6261 [2021-03-27 01:20:22 swin_base_patch4_window7_224] INFO: Epoch: [118] [1240/1251] eta: 0:00:06 lr: 0.000663 loss: 3.5451 (3.4299) grad_norm: 1.2554 (1.3373) time: 0.6285 [2021-03-27 01:20:28 swin_base_patch4_window7_224] INFO: Epoch: [118] [1250/1251] eta: 0:00:00 lr: 0.000663 loss: 3.4220 (3.4287) grad_norm: 1.2646 (1.3376) time: 0.6225 [2021-03-27 01:20:36 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:33 loss: 0.8278 (0.8278) acc1: 79.6875 (79.6875) acc5: 95.3125 (95.3125) [2021-03-27 01:20:38 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9644 (0.9690) acc1: 78.1250 (77.5568) acc5: 93.7500 (94.6023) [2021-03-27 01:20:41 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0021 (0.9835) acc1: 76.5625 (77.1577) acc5: 93.7500 (94.3452) [2021-03-27 01:20:43 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0208 (1.0224) acc1: 75.0000 (75.7056) acc5: 93.7500 (94.0524) [2021-03-27 01:20:46 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0052 (1.0237) acc1: 73.4375 (75.9146) acc5: 92.1875 (93.9024) [2021-03-27 01:20:47 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9800 (1.0159) acc1: 76.5625 (76.0640) acc5: 93.7500 (94.1440) [2021-03-27 01:20:54 swin_base_patch4_window7_224] INFO: * Acc@1 77.028 Acc@5 94.068 loss 1.000 [2021-03-27 01:20:54 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.0% [2021-03-27 01:20:54 swin_base_patch4_window7_224] INFO: Max accuracy: 77.53% [2021-03-27 01:20:59 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 0/1251] eta: 1:26:42 lr: 0.000663 loss: 3.8513 (3.8513) grad_norm: 1.3435 (1.3435) time: 4.1587 [2021-03-27 01:21:05 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 10/1251] eta: 0:19:51 lr: 0.000663 loss: 3.4728 (3.2972) grad_norm: 1.2717 (1.2747) time: 0.9602 [2021-03-27 01:21:11 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 20/1251] eta: 0:16:35 lr: 0.000663 loss: 3.4801 (3.4083) grad_norm: 1.2406 (1.2828) time: 0.6410 [2021-03-27 01:21:18 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 30/1251] eta: 0:15:19 lr: 0.000663 loss: 3.5619 (3.3686) grad_norm: 1.3854 (1.3315) time: 0.6386 [2021-03-27 01:21:24 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 40/1251] eta: 0:14:43 lr: 0.000663 loss: 3.5764 (3.4035) grad_norm: 1.3605 (1.3709) time: 0.6458 [2021-03-27 01:21:31 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 50/1251] eta: 0:14:13 lr: 0.000663 loss: 3.6306 (3.4277) grad_norm: 1.3211 (1.3687) time: 0.6458 [2021-03-27 01:21:37 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 60/1251] eta: 0:13:51 lr: 0.000663 loss: 3.3271 (3.3619) grad_norm: 1.3211 (1.3744) time: 0.6352 [2021-03-27 01:21:43 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 70/1251] eta: 0:13:33 lr: 0.000663 loss: 2.9885 (3.3313) grad_norm: 1.3366 (1.3636) time: 0.6320 [2021-03-27 01:21:50 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 80/1251] eta: 0:13:19 lr: 0.000663 loss: 3.4264 (3.3281) grad_norm: 1.3221 (1.3605) time: 0.6349 [2021-03-27 01:21:56 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 90/1251] eta: 0:13:05 lr: 0.000663 loss: 3.4645 (3.3451) grad_norm: 1.2802 (1.3482) time: 0.6354 [2021-03-27 01:22:02 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 100/1251] eta: 0:12:52 lr: 0.000662 loss: 3.5161 (3.3374) grad_norm: 1.2583 (1.3491) time: 0.6248 [2021-03-27 01:22:09 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 110/1251] eta: 0:12:41 lr: 0.000662 loss: 3.5161 (3.3484) grad_norm: 1.3082 (1.3513) time: 0.6234 [2021-03-27 01:22:15 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 120/1251] eta: 0:12:31 lr: 0.000662 loss: 3.3796 (3.3433) grad_norm: 1.3271 (1.3471) time: 0.6307 [2021-03-27 01:22:21 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 130/1251] eta: 0:12:22 lr: 0.000662 loss: 3.2962 (3.3290) grad_norm: 1.2186 (1.3407) time: 0.6333 [2021-03-27 01:22:28 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 140/1251] eta: 0:12:14 lr: 0.000662 loss: 3.2933 (3.3359) grad_norm: 1.3407 (1.3502) time: 0.6373 [2021-03-27 01:22:34 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 150/1251] eta: 0:12:05 lr: 0.000662 loss: 3.3208 (3.3343) grad_norm: 1.3733 (1.3501) time: 0.6405 [2021-03-27 01:22:40 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 160/1251] eta: 0:11:57 lr: 0.000662 loss: 3.3208 (3.3298) grad_norm: 1.2609 (1.3460) time: 0.6338 [2021-03-27 01:22:47 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 170/1251] eta: 0:11:48 lr: 0.000662 loss: 3.3578 (3.3373) grad_norm: 1.3598 (1.3541) time: 0.6294 [2021-03-27 01:22:53 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 180/1251] eta: 0:11:40 lr: 0.000662 loss: 3.3578 (3.3388) grad_norm: 1.4216 (1.3547) time: 0.6257 [2021-03-27 01:22:59 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 190/1251] eta: 0:11:31 lr: 0.000662 loss: 2.9385 (3.3327) grad_norm: 1.3104 (1.3554) time: 0.6211 [2021-03-27 01:23:05 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 200/1251] eta: 0:11:23 lr: 0.000662 loss: 3.3563 (3.3386) grad_norm: 1.3085 (1.3525) time: 0.6228 [2021-03-27 01:23:12 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 210/1251] eta: 0:11:16 lr: 0.000662 loss: 3.4840 (3.3481) grad_norm: 1.2408 (1.3502) time: 0.6264 [2021-03-27 01:23:18 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 220/1251] eta: 0:11:08 lr: 0.000662 loss: 3.6371 (3.3602) grad_norm: 1.3160 (1.3552) time: 0.6286 [2021-03-27 01:23:24 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 230/1251] eta: 0:11:01 lr: 0.000662 loss: 3.7181 (3.3668) grad_norm: 1.3003 (1.3557) time: 0.6285 [2021-03-27 01:23:30 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 240/1251] eta: 0:10:54 lr: 0.000662 loss: 3.5347 (3.3666) grad_norm: 1.2743 (1.3596) time: 0.6270 [2021-03-27 01:23:37 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 250/1251] eta: 0:10:46 lr: 0.000662 loss: 3.5842 (3.3701) grad_norm: 1.3359 (1.3586) time: 0.6240 [2021-03-27 01:23:43 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 260/1251] eta: 0:10:39 lr: 0.000662 loss: 3.2075 (3.3658) grad_norm: 1.4081 (1.3599) time: 0.6251 [2021-03-27 01:23:49 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 270/1251] eta: 0:10:32 lr: 0.000662 loss: 3.2691 (3.3668) grad_norm: 1.3024 (1.3575) time: 0.6266 [2021-03-27 01:23:56 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 280/1251] eta: 0:10:25 lr: 0.000662 loss: 3.1191 (3.3530) grad_norm: 1.2868 (1.3576) time: 0.6309 [2021-03-27 01:24:02 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 290/1251] eta: 0:10:18 lr: 0.000662 loss: 2.9862 (3.3499) grad_norm: 1.2815 (1.3559) time: 0.6355 [2021-03-27 01:24:08 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 300/1251] eta: 0:10:11 lr: 0.000662 loss: 3.2789 (3.3501) grad_norm: 1.3011 (1.3569) time: 0.6326 [2021-03-27 01:24:14 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 310/1251] eta: 0:10:05 lr: 0.000662 loss: 3.4790 (3.3565) grad_norm: 1.3142 (1.3560) time: 0.6313 [2021-03-27 01:24:21 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 320/1251] eta: 0:09:58 lr: 0.000662 loss: 3.6102 (3.3589) grad_norm: 1.3142 (1.3563) time: 0.6284 [2021-03-27 01:24:27 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 330/1251] eta: 0:09:51 lr: 0.000662 loss: 3.1928 (3.3537) grad_norm: 1.3468 (1.3560) time: 0.6332 [2021-03-27 01:24:34 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 340/1251] eta: 0:09:45 lr: 0.000662 loss: 3.4589 (3.3577) grad_norm: 1.3283 (1.3547) time: 0.6440 [2021-03-27 01:24:40 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 350/1251] eta: 0:09:38 lr: 0.000662 loss: 3.4589 (3.3546) grad_norm: 1.2912 (1.3533) time: 0.6384 [2021-03-27 01:24:46 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 360/1251] eta: 0:09:31 lr: 0.000661 loss: 3.4324 (3.3548) grad_norm: 1.2947 (1.3537) time: 0.6294 [2021-03-27 01:24:53 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 370/1251] eta: 0:09:25 lr: 0.000661 loss: 3.5907 (3.3611) grad_norm: 1.2882 (1.3518) time: 0.6374 [2021-03-27 01:24:59 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 380/1251] eta: 0:09:18 lr: 0.000661 loss: 3.6302 (3.3674) grad_norm: 1.2878 (1.3504) time: 0.6387 [2021-03-27 01:25:05 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 390/1251] eta: 0:09:12 lr: 0.000661 loss: 3.7050 (3.3758) grad_norm: 1.3011 (1.3486) time: 0.6294 [2021-03-27 01:25:12 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 400/1251] eta: 0:09:05 lr: 0.000661 loss: 3.4283 (3.3689) grad_norm: 1.3195 (1.3480) time: 0.6285 [2021-03-27 01:25:18 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 410/1251] eta: 0:08:58 lr: 0.000661 loss: 3.3397 (3.3662) grad_norm: 1.2674 (1.3444) time: 0.6264 [2021-03-27 01:25:24 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 420/1251] eta: 0:08:51 lr: 0.000661 loss: 3.5606 (3.3660) grad_norm: 1.2431 (1.3437) time: 0.6228 [2021-03-27 01:25:30 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 430/1251] eta: 0:08:45 lr: 0.000661 loss: 3.1572 (3.3585) grad_norm: 1.2555 (1.3428) time: 0.6272 [2021-03-27 01:25:37 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 440/1251] eta: 0:08:38 lr: 0.000661 loss: 3.3085 (3.3599) grad_norm: 1.3017 (1.3429) time: 0.6348 [2021-03-27 01:25:43 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 450/1251] eta: 0:08:32 lr: 0.000661 loss: 3.5886 (3.3607) grad_norm: 1.3163 (1.3433) time: 0.6313 [2021-03-27 01:25:49 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 460/1251] eta: 0:08:25 lr: 0.000661 loss: 3.6365 (3.3631) grad_norm: 1.2967 (1.3426) time: 0.6293 [2021-03-27 01:25:56 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 470/1251] eta: 0:08:19 lr: 0.000661 loss: 3.5801 (3.3678) grad_norm: 1.2852 (1.3434) time: 0.6311 [2021-03-27 01:26:02 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 480/1251] eta: 0:08:12 lr: 0.000661 loss: 3.4999 (3.3680) grad_norm: 1.3161 (1.3451) time: 0.6283 [2021-03-27 01:26:08 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 490/1251] eta: 0:08:06 lr: 0.000661 loss: 3.5325 (3.3739) grad_norm: 1.2549 (1.3423) time: 0.6275 [2021-03-27 01:26:14 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 500/1251] eta: 0:07:59 lr: 0.000661 loss: 3.6956 (3.3777) grad_norm: 1.2595 (1.3413) time: 0.6277 [2021-03-27 01:26:21 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 510/1251] eta: 0:07:52 lr: 0.000661 loss: 3.5759 (3.3763) grad_norm: 1.2723 (1.3399) time: 0.6239 [2021-03-27 01:26:27 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 520/1251] eta: 0:07:46 lr: 0.000661 loss: 3.4456 (3.3787) grad_norm: 1.2777 (1.3395) time: 0.6264 [2021-03-27 01:26:33 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 530/1251] eta: 0:07:40 lr: 0.000661 loss: 3.4105 (3.3756) grad_norm: 1.3340 (1.3420) time: 0.6373 [2021-03-27 01:26:40 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 540/1251] eta: 0:07:33 lr: 0.000661 loss: 3.4105 (3.3746) grad_norm: 1.3340 (1.3429) time: 0.6360 [2021-03-27 01:26:46 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 550/1251] eta: 0:07:27 lr: 0.000661 loss: 3.6266 (3.3804) grad_norm: 1.3073 (1.3423) time: 0.6402 [2021-03-27 01:26:52 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 560/1251] eta: 0:07:20 lr: 0.000661 loss: 3.5682 (3.3792) grad_norm: 1.3832 (1.3446) time: 0.6380 [2021-03-27 01:26:59 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 570/1251] eta: 0:07:14 lr: 0.000661 loss: 3.5682 (3.3825) grad_norm: 1.3963 (inf) time: 0.6235 [2021-03-27 01:27:05 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 580/1251] eta: 0:07:07 lr: 0.000661 loss: 3.5730 (3.3848) grad_norm: 1.3118 (inf) time: 0.6217 [2021-03-27 01:27:11 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 590/1251] eta: 0:07:01 lr: 0.000661 loss: 3.4839 (3.3876) grad_norm: 1.2851 (inf) time: 0.6255 [2021-03-27 01:27:18 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 600/1251] eta: 0:06:54 lr: 0.000661 loss: 3.6568 (3.3891) grad_norm: 1.2054 (inf) time: 0.6342 [2021-03-27 01:27:24 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 610/1251] eta: 0:06:48 lr: 0.000660 loss: 3.7877 (3.3910) grad_norm: 1.1821 (inf) time: 0.6427 [2021-03-27 01:27:30 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 620/1251] eta: 0:06:42 lr: 0.000660 loss: 3.6153 (3.3947) grad_norm: 1.2656 (inf) time: 0.6407 [2021-03-27 01:27:37 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 630/1251] eta: 0:06:35 lr: 0.000660 loss: 3.5768 (3.3957) grad_norm: 1.3075 (inf) time: 0.6355 [2021-03-27 01:27:43 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 640/1251] eta: 0:06:29 lr: 0.000660 loss: 3.5045 (3.3946) grad_norm: 1.3172 (inf) time: 0.6287 [2021-03-27 01:27:49 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 650/1251] eta: 0:06:22 lr: 0.000660 loss: 3.5152 (3.3973) grad_norm: 1.2667 (inf) time: 0.6258 [2021-03-27 01:27:56 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 660/1251] eta: 0:06:16 lr: 0.000660 loss: 3.4748 (3.4000) grad_norm: 1.2139 (inf) time: 0.6258 [2021-03-27 01:28:02 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 670/1251] eta: 0:06:09 lr: 0.000660 loss: 3.4966 (3.4036) grad_norm: 1.2868 (inf) time: 0.6221 [2021-03-27 01:28:08 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 680/1251] eta: 0:06:03 lr: 0.000660 loss: 3.5502 (3.4040) grad_norm: 1.3349 (inf) time: 0.6227 [2021-03-27 01:28:14 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 690/1251] eta: 0:05:56 lr: 0.000660 loss: 3.3434 (3.4051) grad_norm: 1.2735 (inf) time: 0.6279 [2021-03-27 01:28:21 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 700/1251] eta: 0:05:50 lr: 0.000660 loss: 3.4642 (3.4051) grad_norm: 1.2142 (inf) time: 0.6274 [2021-03-27 01:28:27 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 710/1251] eta: 0:05:44 lr: 0.000660 loss: 3.5260 (3.4050) grad_norm: 1.2823 (inf) time: 0.6282 [2021-03-27 01:28:33 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 720/1251] eta: 0:05:37 lr: 0.000660 loss: 3.3876 (3.4027) grad_norm: 1.3329 (inf) time: 0.6338 [2021-03-27 01:28:40 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 730/1251] eta: 0:05:31 lr: 0.000660 loss: 3.2530 (3.4014) grad_norm: 1.2997 (inf) time: 0.6357 [2021-03-27 01:28:46 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 740/1251] eta: 0:05:25 lr: 0.000660 loss: 3.2629 (3.3993) grad_norm: 1.2248 (inf) time: 0.6342 [2021-03-27 01:28:52 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 750/1251] eta: 0:05:18 lr: 0.000660 loss: 3.1686 (3.3964) grad_norm: 1.2661 (inf) time: 0.6288 [2021-03-27 01:28:58 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 760/1251] eta: 0:05:12 lr: 0.000660 loss: 3.3378 (3.3984) grad_norm: 1.3180 (inf) time: 0.6258 [2021-03-27 01:29:05 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 770/1251] eta: 0:05:05 lr: 0.000660 loss: 3.4192 (3.3970) grad_norm: 1.2717 (inf) time: 0.6287 [2021-03-27 01:29:11 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 780/1251] eta: 0:04:59 lr: 0.000660 loss: 3.4083 (3.3975) grad_norm: 1.2524 (inf) time: 0.6282 [2021-03-27 01:29:17 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 790/1251] eta: 0:04:52 lr: 0.000660 loss: 3.4782 (3.3992) grad_norm: 1.2857 (inf) time: 0.6266 [2021-03-27 01:29:24 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 800/1251] eta: 0:04:46 lr: 0.000660 loss: 3.4782 (3.3990) grad_norm: 1.4154 (inf) time: 0.6275 [2021-03-27 01:29:30 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 810/1251] eta: 0:04:40 lr: 0.000660 loss: 3.4265 (3.4011) grad_norm: 1.4188 (inf) time: 0.6303 [2021-03-27 01:29:36 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 820/1251] eta: 0:04:33 lr: 0.000660 loss: 3.4265 (3.4013) grad_norm: 1.2927 (inf) time: 0.6279 [2021-03-27 01:29:42 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 830/1251] eta: 0:04:27 lr: 0.000660 loss: 3.4867 (3.4023) grad_norm: 1.3688 (inf) time: 0.6215 [2021-03-27 01:29:49 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 840/1251] eta: 0:04:20 lr: 0.000660 loss: 3.3629 (3.4006) grad_norm: 1.2950 (inf) time: 0.6254 [2021-03-27 01:29:55 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 850/1251] eta: 0:04:14 lr: 0.000660 loss: 3.2947 (3.3986) grad_norm: 1.2617 (inf) time: 0.6386 [2021-03-27 01:30:01 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 860/1251] eta: 0:04:08 lr: 0.000660 loss: 3.4792 (3.3992) grad_norm: 1.2615 (inf) time: 0.6412 [2021-03-27 01:30:08 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 870/1251] eta: 0:04:01 lr: 0.000659 loss: 3.5984 (3.4006) grad_norm: 1.2442 (inf) time: 0.6365 [2021-03-27 01:30:14 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 880/1251] eta: 0:03:55 lr: 0.000659 loss: 3.6686 (3.3995) grad_norm: 1.2357 (inf) time: 0.6299 [2021-03-27 01:30:20 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 890/1251] eta: 0:03:49 lr: 0.000659 loss: 3.6527 (3.4021) grad_norm: 1.2711 (inf) time: 0.6290 [2021-03-27 01:30:27 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 900/1251] eta: 0:03:42 lr: 0.000659 loss: 3.4806 (3.4012) grad_norm: 1.2711 (inf) time: 0.6327 [2021-03-27 01:30:33 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 910/1251] eta: 0:03:36 lr: 0.000659 loss: 3.3181 (3.3991) grad_norm: 1.3232 (inf) time: 0.6291 [2021-03-27 01:30:39 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 920/1251] eta: 0:03:30 lr: 0.000659 loss: 3.4921 (3.4015) grad_norm: 1.3035 (inf) time: 0.6307 [2021-03-27 01:30:46 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 930/1251] eta: 0:03:23 lr: 0.000659 loss: 3.5241 (3.4034) grad_norm: 1.2962 (inf) time: 0.6280 [2021-03-27 01:30:52 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 940/1251] eta: 0:03:17 lr: 0.000659 loss: 3.4172 (3.4025) grad_norm: 1.3301 (inf) time: 0.6253 [2021-03-27 01:30:58 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 950/1251] eta: 0:03:10 lr: 0.000659 loss: 3.1480 (3.4003) grad_norm: 1.2177 (inf) time: 0.6253 [2021-03-27 01:31:04 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 960/1251] eta: 0:03:04 lr: 0.000659 loss: 3.0723 (3.3991) grad_norm: 1.2042 (inf) time: 0.6311 [2021-03-27 01:31:11 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 970/1251] eta: 0:02:58 lr: 0.000659 loss: 3.0880 (3.3984) grad_norm: 1.2892 (inf) time: 0.6309 [2021-03-27 01:31:17 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 980/1251] eta: 0:02:51 lr: 0.000659 loss: 3.5433 (3.4002) grad_norm: 1.3160 (inf) time: 0.6347 [2021-03-27 01:31:23 swin_base_patch4_window7_224] INFO: Epoch: [119] [ 990/1251] eta: 0:02:45 lr: 0.000659 loss: 3.7191 (3.4019) grad_norm: 1.2935 (inf) time: 0.6408 [2021-03-27 01:31:30 swin_base_patch4_window7_224] INFO: Epoch: [119] [1000/1251] eta: 0:02:39 lr: 0.000659 loss: 3.6688 (3.4029) grad_norm: 1.2312 (inf) time: 0.6291 [2021-03-27 01:31:36 swin_base_patch4_window7_224] INFO: Epoch: [119] [1010/1251] eta: 0:02:32 lr: 0.000659 loss: 3.5553 (3.4036) grad_norm: 1.2975 (inf) time: 0.6276 [2021-03-27 01:31:42 swin_base_patch4_window7_224] INFO: Epoch: [119] [1020/1251] eta: 0:02:26 lr: 0.000659 loss: 3.5877 (3.4047) grad_norm: 1.2772 (inf) time: 0.6314 [2021-03-27 01:31:49 swin_base_patch4_window7_224] INFO: Epoch: [119] [1030/1251] eta: 0:02:20 lr: 0.000659 loss: 3.4658 (3.4051) grad_norm: 1.2604 (inf) time: 0.6296 [2021-03-27 01:31:55 swin_base_patch4_window7_224] INFO: Epoch: [119] [1040/1251] eta: 0:02:13 lr: 0.000659 loss: 3.4460 (3.4057) grad_norm: 1.2542 (inf) time: 0.6271 [2021-03-27 01:32:01 swin_base_patch4_window7_224] INFO: Epoch: [119] [1050/1251] eta: 0:02:07 lr: 0.000659 loss: 3.6727 (3.4088) grad_norm: 1.2865 (inf) time: 0.6240 [2021-03-27 01:32:08 swin_base_patch4_window7_224] INFO: Epoch: [119] [1060/1251] eta: 0:02:01 lr: 0.000659 loss: 3.7165 (3.4089) grad_norm: 1.3132 (inf) time: 0.6316 [2021-03-27 01:32:14 swin_base_patch4_window7_224] INFO: Epoch: [119] [1070/1251] eta: 0:01:54 lr: 0.000659 loss: 3.3647 (3.4066) grad_norm: 1.2496 (inf) time: 0.6353 [2021-03-27 01:32:20 swin_base_patch4_window7_224] INFO: Epoch: [119] [1080/1251] eta: 0:01:48 lr: 0.000659 loss: 3.4916 (3.4075) grad_norm: 1.2476 (inf) time: 0.6343 [2021-03-27 01:32:27 swin_base_patch4_window7_224] INFO: Epoch: [119] [1090/1251] eta: 0:01:42 lr: 0.000659 loss: 3.6443 (3.4101) grad_norm: 1.2828 (inf) time: 0.6404 [2021-03-27 01:32:33 swin_base_patch4_window7_224] INFO: Epoch: [119] [1100/1251] eta: 0:01:35 lr: 0.000659 loss: 3.7873 (3.4112) grad_norm: 1.2330 (inf) time: 0.6361 [2021-03-27 01:32:39 swin_base_patch4_window7_224] INFO: Epoch: [119] [1110/1251] eta: 0:01:29 lr: 0.000659 loss: 3.7823 (3.4133) grad_norm: 1.2330 (inf) time: 0.6271 [2021-03-27 01:32:45 swin_base_patch4_window7_224] INFO: Epoch: [119] [1120/1251] eta: 0:01:23 lr: 0.000658 loss: 3.7403 (3.4145) grad_norm: 1.2760 (inf) time: 0.6264 [2021-03-27 01:32:52 swin_base_patch4_window7_224] INFO: Epoch: [119] [1130/1251] eta: 0:01:16 lr: 0.000658 loss: 3.6430 (3.4156) grad_norm: 1.2682 (inf) time: 0.6259 [2021-03-27 01:32:58 swin_base_patch4_window7_224] INFO: Epoch: [119] [1140/1251] eta: 0:01:10 lr: 0.000658 loss: 3.5361 (3.4153) grad_norm: 1.2762 (inf) time: 0.6238 [2021-03-27 01:33:04 swin_base_patch4_window7_224] INFO: Epoch: [119] [1150/1251] eta: 0:01:04 lr: 0.000658 loss: 3.5159 (3.4163) grad_norm: 1.2762 (inf) time: 0.6282 [2021-03-27 01:33:11 swin_base_patch4_window7_224] INFO: Epoch: [119] [1160/1251] eta: 0:00:57 lr: 0.000658 loss: 3.6890 (3.4177) grad_norm: 1.2632 (inf) time: 0.6309 [2021-03-27 01:33:17 swin_base_patch4_window7_224] INFO: Epoch: [119] [1170/1251] eta: 0:00:51 lr: 0.000658 loss: 3.6890 (3.4193) grad_norm: 1.2944 (inf) time: 0.6274 [2021-03-27 01:33:23 swin_base_patch4_window7_224] INFO: Epoch: [119] [1180/1251] eta: 0:00:44 lr: 0.000658 loss: 3.6230 (3.4191) grad_norm: 1.3148 (inf) time: 0.6217 [2021-03-27 01:33:29 swin_base_patch4_window7_224] INFO: Epoch: [119] [1190/1251] eta: 0:00:38 lr: 0.000658 loss: 3.6230 (3.4198) grad_norm: 1.2722 (inf) time: 0.6196 [2021-03-27 01:33:35 swin_base_patch4_window7_224] INFO: Epoch: [119] [1200/1251] eta: 0:00:32 lr: 0.000658 loss: 3.3946 (3.4192) grad_norm: 1.2653 (inf) time: 0.6229 [2021-03-27 01:33:42 swin_base_patch4_window7_224] INFO: Epoch: [119] [1210/1251] eta: 0:00:25 lr: 0.000658 loss: 3.6065 (3.4220) grad_norm: 1.3869 (inf) time: 0.6227 [2021-03-27 01:33:48 swin_base_patch4_window7_224] INFO: Epoch: [119] [1220/1251] eta: 0:00:19 lr: 0.000658 loss: 3.5639 (3.4198) grad_norm: 1.3567 (inf) time: 0.6205 [2021-03-27 01:33:54 swin_base_patch4_window7_224] INFO: Epoch: [119] [1230/1251] eta: 0:00:13 lr: 0.000658 loss: 3.2820 (3.4189) grad_norm: 1.2918 (inf) time: 0.6206 [2021-03-27 01:34:00 swin_base_patch4_window7_224] INFO: Epoch: [119] [1240/1251] eta: 0:00:06 lr: 0.000658 loss: 3.6169 (3.4193) grad_norm: 1.2918 (inf) time: 0.6216 [2021-03-27 01:34:07 swin_base_patch4_window7_224] INFO: Epoch: [119] [1250/1251] eta: 0:00:00 lr: 0.000658 loss: 3.6169 (3.4198) grad_norm: 1.2681 (inf) time: 0.6265 [2021-03-27 01:34:13 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:35 loss: 0.8219 (0.8219) acc1: 87.5000 (87.5000) acc5: 98.4375 (98.4375) [2021-03-27 01:34:15 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.9669 (0.9881) acc1: 76.5625 (77.5568) acc5: 93.7500 (93.1818) [2021-03-27 01:34:18 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9271 (0.9668) acc1: 78.1250 (77.3810) acc5: 93.7500 (93.8988) [2021-03-27 01:34:20 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9183 (0.9576) acc1: 79.6875 (77.6714) acc5: 95.3125 (94.3044) [2021-03-27 01:34:23 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9141 (0.9397) acc1: 78.1250 (78.0488) acc5: 95.3125 (94.3979) [2021-03-27 01:34:24 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9419 (0.9723) acc1: 78.1250 (77.3440) acc5: 95.3125 (94.2400) [2021-03-27 01:34:30 swin_base_patch4_window7_224] INFO: * Acc@1 77.662 Acc@5 94.248 loss 0.958 [2021-03-27 01:34:30 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.7% [2021-03-27 01:34:30 swin_base_patch4_window7_224] INFO: Max accuracy: 77.66% [2021-03-27 01:34:34 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 0/1251] eta: 1:28:37 lr: 0.000658 loss: 3.1261 (3.1261) grad_norm: 1.1670 (1.1670) time: 4.2502 [2021-03-27 01:34:41 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 10/1251] eta: 0:19:59 lr: 0.000658 loss: 3.3618 (3.2522) grad_norm: 1.2121 (1.2489) time: 0.9665 [2021-03-27 01:34:47 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 20/1251] eta: 0:16:30 lr: 0.000658 loss: 3.4061 (3.3313) grad_norm: 1.2591 (1.3210) time: 0.6324 [2021-03-27 01:34:53 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 30/1251] eta: 0:15:11 lr: 0.000658 loss: 3.5911 (3.4176) grad_norm: 1.2985 (1.3227) time: 0.6257 [2021-03-27 01:35:00 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 40/1251] eta: 0:14:29 lr: 0.000658 loss: 3.5994 (3.4464) grad_norm: 1.2985 (1.3283) time: 0.6264 [2021-03-27 01:35:06 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 50/1251] eta: 0:14:04 lr: 0.000658 loss: 3.5904 (3.4805) grad_norm: 1.3165 (1.3282) time: 0.6351 [2021-03-27 01:35:12 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 60/1251] eta: 0:13:42 lr: 0.000658 loss: 3.5904 (3.4503) grad_norm: 1.3491 (1.3467) time: 0.6345 [2021-03-27 01:35:18 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 70/1251] eta: 0:13:23 lr: 0.000658 loss: 3.1844 (3.4253) grad_norm: 1.4617 (1.3560) time: 0.6240 [2021-03-27 01:35:25 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 80/1251] eta: 0:13:08 lr: 0.000658 loss: 3.1091 (3.3922) grad_norm: 1.3166 (1.3563) time: 0.6224 [2021-03-27 01:35:31 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 90/1251] eta: 0:12:55 lr: 0.000658 loss: 3.1864 (3.4023) grad_norm: 1.3000 (1.3546) time: 0.6210 [2021-03-27 01:35:37 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 100/1251] eta: 0:12:44 lr: 0.000658 loss: 3.5089 (3.4138) grad_norm: 1.2652 (1.3512) time: 0.6261 [2021-03-27 01:35:44 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 110/1251] eta: 0:12:34 lr: 0.000658 loss: 3.5036 (3.4177) grad_norm: 1.2638 (1.3474) time: 0.6325 [2021-03-27 01:35:50 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 120/1251] eta: 0:12:25 lr: 0.000657 loss: 3.2867 (3.3951) grad_norm: 1.3676 (1.3573) time: 0.6322 [2021-03-27 01:35:56 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 130/1251] eta: 0:12:16 lr: 0.000657 loss: 3.4365 (3.4085) grad_norm: 1.4310 (1.3658) time: 0.6346 [2021-03-27 01:36:03 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 140/1251] eta: 0:12:08 lr: 0.000657 loss: 3.2855 (3.3896) grad_norm: 1.3091 (1.3613) time: 0.6367 [2021-03-27 01:36:09 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 150/1251] eta: 0:12:00 lr: 0.000657 loss: 3.2419 (3.3839) grad_norm: 1.3006 (1.3612) time: 0.6329 [2021-03-27 01:36:15 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 160/1251] eta: 0:11:51 lr: 0.000657 loss: 3.4626 (3.3960) grad_norm: 1.3005 (1.3590) time: 0.6293 [2021-03-27 01:36:22 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 170/1251] eta: 0:11:44 lr: 0.000657 loss: 3.5300 (3.3907) grad_norm: 1.2930 (1.3567) time: 0.6313 [2021-03-27 01:36:28 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 180/1251] eta: 0:11:37 lr: 0.000657 loss: 3.4236 (3.3967) grad_norm: 1.2915 (1.3539) time: 0.6436 [2021-03-27 01:36:34 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 190/1251] eta: 0:11:30 lr: 0.000657 loss: 3.4844 (3.3881) grad_norm: 1.2915 (1.3520) time: 0.6468 [2021-03-27 01:36:41 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 200/1251] eta: 0:11:24 lr: 0.000657 loss: 3.5461 (3.3984) grad_norm: 1.2963 (1.3480) time: 0.6479 [2021-03-27 01:36:47 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 210/1251] eta: 0:11:16 lr: 0.000657 loss: 3.5461 (3.3984) grad_norm: 1.3206 (1.3479) time: 0.6403 [2021-03-27 01:36:54 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 220/1251] eta: 0:11:09 lr: 0.000657 loss: 3.4311 (3.3942) grad_norm: 1.2462 (1.3442) time: 0.6330 [2021-03-27 01:37:00 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 230/1251] eta: 0:11:02 lr: 0.000657 loss: 3.5184 (3.4033) grad_norm: 1.2901 (1.3412) time: 0.6437 [2021-03-27 01:37:07 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 240/1251] eta: 0:10:55 lr: 0.000657 loss: 3.4978 (3.3998) grad_norm: 1.2901 (1.3388) time: 0.6410 [2021-03-27 01:37:13 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 250/1251] eta: 0:10:48 lr: 0.000657 loss: 3.2816 (3.3999) grad_norm: 1.2119 (1.3345) time: 0.6369 [2021-03-27 01:37:19 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 260/1251] eta: 0:10:41 lr: 0.000657 loss: 3.5618 (3.4052) grad_norm: 1.2099 (1.3317) time: 0.6297 [2021-03-27 01:37:25 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 270/1251] eta: 0:10:34 lr: 0.000657 loss: 3.6168 (3.4117) grad_norm: 1.2967 (1.3326) time: 0.6290 [2021-03-27 01:37:32 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 280/1251] eta: 0:10:27 lr: 0.000657 loss: 3.6002 (3.4107) grad_norm: 1.2937 (1.3316) time: 0.6348 [2021-03-27 01:37:38 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 290/1251] eta: 0:10:20 lr: 0.000657 loss: 3.5811 (3.4112) grad_norm: 1.2272 (1.3281) time: 0.6355 [2021-03-27 01:37:45 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 300/1251] eta: 0:10:14 lr: 0.000657 loss: 3.5811 (3.4147) grad_norm: 1.2272 (1.3288) time: 0.6375 [2021-03-27 01:37:51 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 310/1251] eta: 0:10:07 lr: 0.000657 loss: 3.6012 (3.4193) grad_norm: 1.2804 (1.3281) time: 0.6413 [2021-03-27 01:37:57 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 320/1251] eta: 0:10:00 lr: 0.000657 loss: 3.5599 (3.4207) grad_norm: 1.3155 (1.3311) time: 0.6383 [2021-03-27 01:38:04 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 330/1251] eta: 0:09:53 lr: 0.000657 loss: 3.6808 (3.4240) grad_norm: 1.2916 (1.3285) time: 0.6293 [2021-03-27 01:38:10 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 340/1251] eta: 0:09:47 lr: 0.000657 loss: 3.5898 (3.4210) grad_norm: 1.2302 (1.3282) time: 0.6311 [2021-03-27 01:38:16 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 350/1251] eta: 0:09:40 lr: 0.000657 loss: 3.5171 (3.4239) grad_norm: 1.3429 (1.3287) time: 0.6322 [2021-03-27 01:38:23 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 360/1251] eta: 0:09:33 lr: 0.000657 loss: 3.5353 (3.4205) grad_norm: 1.2277 (1.3253) time: 0.6304 [2021-03-27 01:38:29 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 370/1251] eta: 0:09:27 lr: 0.000657 loss: 3.2304 (3.4202) grad_norm: 1.2311 (1.3253) time: 0.6393 [2021-03-27 01:38:35 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 380/1251] eta: 0:09:20 lr: 0.000656 loss: 3.7291 (3.4290) grad_norm: 1.2419 (1.3253) time: 0.6394 [2021-03-27 01:38:42 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 390/1251] eta: 0:09:13 lr: 0.000656 loss: 3.7664 (3.4287) grad_norm: 1.2371 (1.3232) time: 0.6354 [2021-03-27 01:38:48 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 400/1251] eta: 0:09:07 lr: 0.000656 loss: 3.6905 (3.4305) grad_norm: 1.2348 (1.3219) time: 0.6332 [2021-03-27 01:38:54 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 410/1251] eta: 0:09:00 lr: 0.000656 loss: 3.4314 (3.4259) grad_norm: 1.2845 (1.3211) time: 0.6300 [2021-03-27 01:39:01 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 420/1251] eta: 0:08:53 lr: 0.000656 loss: 3.4185 (3.4280) grad_norm: 1.2757 (1.3201) time: 0.6297 [2021-03-27 01:39:07 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 430/1251] eta: 0:08:47 lr: 0.000656 loss: 3.5986 (3.4278) grad_norm: 1.2350 (1.3183) time: 0.6290 [2021-03-27 01:39:13 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 440/1251] eta: 0:08:40 lr: 0.000656 loss: 3.5301 (3.4293) grad_norm: 1.2350 (1.3174) time: 0.6300 [2021-03-27 01:39:19 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 450/1251] eta: 0:08:33 lr: 0.000656 loss: 3.5574 (3.4342) grad_norm: 1.2263 (1.3152) time: 0.6253 [2021-03-27 01:39:26 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 460/1251] eta: 0:08:27 lr: 0.000656 loss: 3.5428 (3.4328) grad_norm: 1.2456 (1.3162) time: 0.6281 [2021-03-27 01:39:32 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 470/1251] eta: 0:08:20 lr: 0.000656 loss: 3.4112 (3.4325) grad_norm: 1.3423 (1.3188) time: 0.6313 [2021-03-27 01:39:38 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 480/1251] eta: 0:08:13 lr: 0.000656 loss: 3.4584 (3.4357) grad_norm: 1.3423 (1.3192) time: 0.6290 [2021-03-27 01:39:45 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 490/1251] eta: 0:08:07 lr: 0.000656 loss: 3.4584 (3.4330) grad_norm: 1.2865 (1.3184) time: 0.6273 [2021-03-27 01:39:51 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 500/1251] eta: 0:08:00 lr: 0.000656 loss: 3.4621 (3.4341) grad_norm: 1.2581 (1.3165) time: 0.6254 [2021-03-27 01:39:57 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 510/1251] eta: 0:07:54 lr: 0.000656 loss: 3.4766 (3.4350) grad_norm: 1.2911 (1.3171) time: 0.6267 [2021-03-27 01:40:03 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 520/1251] eta: 0:07:47 lr: 0.000656 loss: 3.3018 (3.4344) grad_norm: 1.3198 (1.3178) time: 0.6252 [2021-03-27 01:40:10 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 530/1251] eta: 0:07:40 lr: 0.000656 loss: 3.4607 (3.4337) grad_norm: 1.2961 (1.3173) time: 0.6259 [2021-03-27 01:40:16 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 540/1251] eta: 0:07:34 lr: 0.000656 loss: 3.5844 (3.4384) grad_norm: 1.3247 (1.3181) time: 0.6301 [2021-03-27 01:40:22 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 550/1251] eta: 0:07:28 lr: 0.000656 loss: 3.5532 (3.4411) grad_norm: 1.2817 (1.3176) time: 0.6384 [2021-03-27 01:40:29 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 560/1251] eta: 0:07:21 lr: 0.000656 loss: 3.4404 (3.4374) grad_norm: 1.2711 (1.3192) time: 0.6374 [2021-03-27 01:40:35 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 570/1251] eta: 0:07:15 lr: 0.000656 loss: 3.4045 (3.4376) grad_norm: 1.3498 (1.3204) time: 0.6352 [2021-03-27 01:40:42 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 580/1251] eta: 0:07:08 lr: 0.000656 loss: 3.5024 (3.4400) grad_norm: 1.3147 (1.3202) time: 0.6393 [2021-03-27 01:40:48 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 590/1251] eta: 0:07:02 lr: 0.000656 loss: 3.5244 (3.4369) grad_norm: 1.3054 (1.3206) time: 0.6328 [2021-03-27 01:40:54 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 600/1251] eta: 0:06:55 lr: 0.000656 loss: 3.5927 (3.4384) grad_norm: 1.3054 (1.3209) time: 0.6252 [2021-03-27 01:41:00 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 610/1251] eta: 0:06:49 lr: 0.000656 loss: 3.4885 (3.4387) grad_norm: 1.3368 (1.3225) time: 0.6289 [2021-03-27 01:41:07 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 620/1251] eta: 0:06:42 lr: 0.000656 loss: 3.4885 (3.4374) grad_norm: 1.3428 (1.3225) time: 0.6359 [2021-03-27 01:41:13 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 630/1251] eta: 0:06:36 lr: 0.000655 loss: 3.5573 (3.4377) grad_norm: 1.3144 (1.3233) time: 0.6354 [2021-03-27 01:41:19 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 640/1251] eta: 0:06:30 lr: 0.000655 loss: 3.4405 (3.4353) grad_norm: 1.3429 (1.3241) time: 0.6305 [2021-03-27 01:41:26 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 650/1251] eta: 0:06:23 lr: 0.000655 loss: 3.2023 (3.4304) grad_norm: 1.3184 (1.3239) time: 0.6264 [2021-03-27 01:41:32 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 660/1251] eta: 0:06:16 lr: 0.000655 loss: 3.2891 (3.4291) grad_norm: 1.3072 (1.3234) time: 0.6244 [2021-03-27 01:41:38 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 670/1251] eta: 0:06:10 lr: 0.000655 loss: 3.4656 (3.4286) grad_norm: 1.3348 (1.3250) time: 0.6307 [2021-03-27 01:41:45 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 680/1251] eta: 0:06:04 lr: 0.000655 loss: 3.7263 (3.4273) grad_norm: 1.3856 (1.3258) time: 0.6321 [2021-03-27 01:41:51 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 690/1251] eta: 0:05:57 lr: 0.000655 loss: 3.7059 (3.4278) grad_norm: 1.3103 (1.3249) time: 0.6318 [2021-03-27 01:41:57 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 700/1251] eta: 0:05:51 lr: 0.000655 loss: 3.7059 (3.4288) grad_norm: 1.2833 (1.3253) time: 0.6318 [2021-03-27 01:42:04 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 710/1251] eta: 0:05:44 lr: 0.000655 loss: 3.4701 (3.4303) grad_norm: 1.2833 (1.3255) time: 0.6344 [2021-03-27 01:42:10 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 720/1251] eta: 0:05:38 lr: 0.000655 loss: 3.5456 (3.4304) grad_norm: 1.2700 (1.3257) time: 0.6336 [2021-03-27 01:42:16 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 730/1251] eta: 0:05:32 lr: 0.000655 loss: 3.6226 (3.4324) grad_norm: 1.2419 (1.3257) time: 0.6285 [2021-03-27 01:42:23 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 740/1251] eta: 0:05:25 lr: 0.000655 loss: 3.3631 (3.4280) grad_norm: 1.3537 (1.3291) time: 0.6383 [2021-03-27 01:42:29 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 750/1251] eta: 0:05:19 lr: 0.000655 loss: 3.3631 (3.4302) grad_norm: 1.3873 (1.3303) time: 0.6465 [2021-03-27 01:42:35 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 760/1251] eta: 0:05:13 lr: 0.000655 loss: 3.4148 (3.4304) grad_norm: 1.2990 (1.3298) time: 0.6433 [2021-03-27 01:42:42 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 770/1251] eta: 0:05:06 lr: 0.000655 loss: 3.6638 (3.4329) grad_norm: 1.2577 (1.3299) time: 0.6359 [2021-03-27 01:42:48 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 780/1251] eta: 0:05:00 lr: 0.000655 loss: 3.6600 (3.4338) grad_norm: 1.3092 (1.3299) time: 0.6283 [2021-03-27 01:42:54 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 790/1251] eta: 0:04:53 lr: 0.000655 loss: 3.4971 (3.4324) grad_norm: 1.2638 (1.3297) time: 0.6219 [2021-03-27 01:43:01 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 800/1251] eta: 0:04:47 lr: 0.000655 loss: 3.2530 (3.4284) grad_norm: 1.2638 (1.3300) time: 0.6267 [2021-03-27 01:43:07 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 810/1251] eta: 0:04:41 lr: 0.000655 loss: 3.2530 (3.4275) grad_norm: 1.3044 (1.3294) time: 0.6375 [2021-03-27 01:43:13 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 820/1251] eta: 0:04:34 lr: 0.000655 loss: 3.6462 (3.4300) grad_norm: 1.3259 (1.3297) time: 0.6403 [2021-03-27 01:43:20 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 830/1251] eta: 0:04:28 lr: 0.000655 loss: 3.7316 (3.4347) grad_norm: 1.3420 (1.3300) time: 0.6343 [2021-03-27 01:43:26 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 840/1251] eta: 0:04:21 lr: 0.000655 loss: 3.5728 (3.4328) grad_norm: 1.3149 (1.3299) time: 0.6328 [2021-03-27 01:43:32 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 850/1251] eta: 0:04:15 lr: 0.000655 loss: 3.5728 (3.4328) grad_norm: 1.3326 (1.3301) time: 0.6292 [2021-03-27 01:43:39 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 860/1251] eta: 0:04:09 lr: 0.000655 loss: 3.6677 (3.4340) grad_norm: 1.3628 (1.3306) time: 0.6262 [2021-03-27 01:43:45 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 870/1251] eta: 0:04:02 lr: 0.000655 loss: 3.4941 (3.4334) grad_norm: 1.3548 (1.3321) time: 0.6265 [2021-03-27 01:43:51 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 880/1251] eta: 0:03:56 lr: 0.000654 loss: 3.4941 (3.4334) grad_norm: 1.3045 (1.3321) time: 0.6294 [2021-03-27 01:43:57 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 890/1251] eta: 0:03:49 lr: 0.000654 loss: 3.4693 (3.4332) grad_norm: 1.2152 (1.3326) time: 0.6331 [2021-03-27 01:44:04 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 900/1251] eta: 0:03:43 lr: 0.000654 loss: 3.4176 (3.4326) grad_norm: 1.2167 (1.3322) time: 0.6256 [2021-03-27 01:44:10 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 910/1251] eta: 0:03:36 lr: 0.000654 loss: 3.6502 (3.4342) grad_norm: 1.3074 (1.3330) time: 0.6234 [2021-03-27 01:44:16 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 920/1251] eta: 0:03:30 lr: 0.000654 loss: 3.4883 (3.4312) grad_norm: 1.3399 (1.3326) time: 0.6279 [2021-03-27 01:44:23 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 930/1251] eta: 0:03:24 lr: 0.000654 loss: 3.3043 (3.4282) grad_norm: 1.3111 (1.3331) time: 0.6302 [2021-03-27 01:44:29 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 940/1251] eta: 0:03:17 lr: 0.000654 loss: 3.4112 (3.4294) grad_norm: 1.3663 (1.3340) time: 0.6325 [2021-03-27 01:44:35 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 950/1251] eta: 0:03:11 lr: 0.000654 loss: 3.5211 (3.4305) grad_norm: 1.2901 (1.3334) time: 0.6330 [2021-03-27 01:44:41 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 960/1251] eta: 0:03:05 lr: 0.000654 loss: 3.7288 (3.4316) grad_norm: 1.3159 (1.3347) time: 0.6289 [2021-03-27 01:44:48 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 970/1251] eta: 0:02:58 lr: 0.000654 loss: 3.5800 (3.4313) grad_norm: 1.2724 (1.3345) time: 0.6279 [2021-03-27 01:44:54 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 980/1251] eta: 0:02:52 lr: 0.000654 loss: 3.5584 (3.4334) grad_norm: 1.2235 (1.3339) time: 0.6275 [2021-03-27 01:45:00 swin_base_patch4_window7_224] INFO: Epoch: [120] [ 990/1251] eta: 0:02:45 lr: 0.000654 loss: 3.5702 (3.4333) grad_norm: 1.3558 (1.3356) time: 0.6241 [2021-03-27 01:45:07 swin_base_patch4_window7_224] INFO: Epoch: [120] [1000/1251] eta: 0:02:39 lr: 0.000654 loss: 3.5584 (3.4348) grad_norm: 1.4186 (1.3374) time: 0.6319 [2021-03-27 01:45:13 swin_base_patch4_window7_224] INFO: Epoch: [120] [1010/1251] eta: 0:02:33 lr: 0.000654 loss: 3.5584 (3.4350) grad_norm: 1.3270 (1.3368) time: 0.6430 [2021-03-27 01:45:19 swin_base_patch4_window7_224] INFO: Epoch: [120] [1020/1251] eta: 0:02:26 lr: 0.000654 loss: 3.2820 (3.4329) grad_norm: 1.2307 (1.3360) time: 0.6353 [2021-03-27 01:45:26 swin_base_patch4_window7_224] INFO: Epoch: [120] [1030/1251] eta: 0:02:20 lr: 0.000654 loss: 3.4586 (3.4356) grad_norm: 1.2948 (1.3366) time: 0.6218 [2021-03-27 01:45:32 swin_base_patch4_window7_224] INFO: Epoch: [120] [1040/1251] eta: 0:02:14 lr: 0.000654 loss: 3.6387 (3.4335) grad_norm: 1.2953 (1.3362) time: 0.6263 [2021-03-27 01:45:38 swin_base_patch4_window7_224] INFO: Epoch: [120] [1050/1251] eta: 0:02:07 lr: 0.000654 loss: 3.4185 (3.4347) grad_norm: 1.2364 (1.3357) time: 0.6292 [2021-03-27 01:45:44 swin_base_patch4_window7_224] INFO: Epoch: [120] [1060/1251] eta: 0:02:01 lr: 0.000654 loss: 3.6036 (3.4359) grad_norm: 1.2937 (1.3357) time: 0.6232 [2021-03-27 01:45:51 swin_base_patch4_window7_224] INFO: Epoch: [120] [1070/1251] eta: 0:01:54 lr: 0.000654 loss: 3.5861 (3.4359) grad_norm: 1.2686 (1.3352) time: 0.6208 [2021-03-27 01:45:57 swin_base_patch4_window7_224] INFO: Epoch: [120] [1080/1251] eta: 0:01:48 lr: 0.000654 loss: 3.5297 (3.4341) grad_norm: 1.2686 (1.3350) time: 0.6254 [2021-03-27 01:46:03 swin_base_patch4_window7_224] INFO: Epoch: [120] [1090/1251] eta: 0:01:42 lr: 0.000654 loss: 3.5292 (3.4343) grad_norm: 1.3088 (1.3354) time: 0.6354 [2021-03-27 01:46:10 swin_base_patch4_window7_224] INFO: Epoch: [120] [1100/1251] eta: 0:01:35 lr: 0.000654 loss: 3.5292 (3.4336) grad_norm: 1.3302 (1.3360) time: 0.6442 [2021-03-27 01:46:16 swin_base_patch4_window7_224] INFO: Epoch: [120] [1110/1251] eta: 0:01:29 lr: 0.000654 loss: 3.3716 (3.4323) grad_norm: 1.3265 (1.3362) time: 0.6395 [2021-03-27 01:46:22 swin_base_patch4_window7_224] INFO: Epoch: [120] [1120/1251] eta: 0:01:23 lr: 0.000654 loss: 3.3657 (3.4300) grad_norm: 1.2736 (1.3355) time: 0.6285 [2021-03-27 01:46:29 swin_base_patch4_window7_224] INFO: Epoch: [120] [1130/1251] eta: 0:01:16 lr: 0.000654 loss: 3.4202 (3.4313) grad_norm: 1.2725 (1.3358) time: 0.6268 [2021-03-27 01:46:35 swin_base_patch4_window7_224] INFO: Epoch: [120] [1140/1251] eta: 0:01:10 lr: 0.000653 loss: 3.5717 (3.4319) grad_norm: 1.3660 (1.3368) time: 0.6255 [2021-03-27 01:46:41 swin_base_patch4_window7_224] INFO: Epoch: [120] [1150/1251] eta: 0:01:04 lr: 0.000653 loss: 3.5584 (3.4315) grad_norm: 1.3493 (1.3368) time: 0.6232 [2021-03-27 01:46:47 swin_base_patch4_window7_224] INFO: Epoch: [120] [1160/1251] eta: 0:00:57 lr: 0.000653 loss: 3.5962 (3.4318) grad_norm: 1.3903 (1.3377) time: 0.6247 [2021-03-27 01:46:54 swin_base_patch4_window7_224] INFO: Epoch: [120] [1170/1251] eta: 0:00:51 lr: 0.000653 loss: 3.6930 (3.4319) grad_norm: 1.4252 (1.3392) time: 0.6293 [2021-03-27 01:47:00 swin_base_patch4_window7_224] INFO: Epoch: [120] [1180/1251] eta: 0:00:45 lr: 0.000653 loss: 3.6985 (3.4328) grad_norm: 1.3163 (1.3394) time: 0.6306 [2021-03-27 01:47:06 swin_base_patch4_window7_224] INFO: Epoch: [120] [1190/1251] eta: 0:00:38 lr: 0.000653 loss: 3.3555 (3.4311) grad_norm: 1.2445 (1.3387) time: 0.6257 [2021-03-27 01:47:13 swin_base_patch4_window7_224] INFO: Epoch: [120] [1200/1251] eta: 0:00:32 lr: 0.000653 loss: 3.3081 (3.4318) grad_norm: 1.2455 (1.3387) time: 0.6278 [2021-03-27 01:47:19 swin_base_patch4_window7_224] INFO: Epoch: [120] [1210/1251] eta: 0:00:26 lr: 0.000653 loss: 3.5683 (3.4330) grad_norm: 1.3523 (1.3392) time: 0.6373 [2021-03-27 01:47:25 swin_base_patch4_window7_224] INFO: Epoch: [120] [1220/1251] eta: 0:00:19 lr: 0.000653 loss: 3.5928 (3.4331) grad_norm: 1.3031 (1.3390) time: 0.6347 [2021-03-27 01:47:32 swin_base_patch4_window7_224] INFO: Epoch: [120] [1230/1251] eta: 0:00:13 lr: 0.000653 loss: 3.5755 (3.4333) grad_norm: 1.2737 (1.3388) time: 0.6282 [2021-03-27 01:47:38 swin_base_patch4_window7_224] INFO: Epoch: [120] [1240/1251] eta: 0:00:06 lr: 0.000653 loss: 3.4851 (3.4321) grad_norm: 1.2062 (1.3377) time: 0.6284 [2021-03-27 01:47:44 swin_base_patch4_window7_224] INFO: Epoch: [120] [1250/1251] eta: 0:00:00 lr: 0.000653 loss: 3.3464 (3.4321) grad_norm: 1.1999 (1.3369) time: 0.6242 [2021-03-27 01:48:55 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:02 loss: 0.8216 (0.8216) acc1: 79.6875 (79.6875) acc5: 98.4375 (98.4375) [2021-03-27 01:48:56 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.9676 (1.0526) acc1: 76.5625 (74.8580) acc5: 95.3125 (93.1818) [2021-03-27 01:48:58 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9248 (0.9550) acc1: 76.5625 (77.5298) acc5: 95.3125 (94.6429) [2021-03-27 01:48:59 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.9118 (0.9786) acc1: 78.1250 (76.8649) acc5: 93.7500 (94.1028) [2021-03-27 01:49:01 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9136 (0.9610) acc1: 75.0000 (77.0960) acc5: 93.7500 (94.5884) [2021-03-27 01:49:02 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8957 (0.9612) acc1: 76.5625 (76.9600) acc5: 95.3125 (94.7200) [2021-03-27 01:49:08 swin_base_patch4_window7_224] INFO: * Acc@1 77.652 Acc@5 94.372 loss 0.955 [2021-03-27 01:49:08 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.7% [2021-03-27 01:49:08 swin_base_patch4_window7_224] INFO: Max accuracy: 77.66% [2021-03-27 01:49:13 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 0/1251] eta: 1:32:17 lr: 0.000653 loss: 2.6898 (2.6898) grad_norm: 1.3351 (1.3351) time: 4.4266 [2021-03-27 01:49:19 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 10/1251] eta: 0:20:27 lr: 0.000653 loss: 3.7248 (3.6320) grad_norm: 1.2401 (1.2544) time: 0.9890 [2021-03-27 01:49:25 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 20/1251] eta: 0:16:48 lr: 0.000653 loss: 3.6420 (3.5976) grad_norm: 1.2401 (1.2689) time: 0.6391 [2021-03-27 01:49:32 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 30/1251] eta: 0:15:28 lr: 0.000653 loss: 3.6336 (3.6206) grad_norm: 1.3386 (1.3190) time: 0.6342 [2021-03-27 01:49:38 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 40/1251] eta: 0:14:45 lr: 0.000653 loss: 3.5422 (3.5329) grad_norm: 1.3232 (1.3121) time: 0.6378 [2021-03-27 01:49:44 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 50/1251] eta: 0:14:14 lr: 0.000653 loss: 3.2618 (3.4990) grad_norm: 1.2329 (1.2926) time: 0.6368 [2021-03-27 01:49:51 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 60/1251] eta: 0:13:52 lr: 0.000653 loss: 3.4357 (3.4650) grad_norm: 1.2545 (1.3038) time: 0.6338 [2021-03-27 01:49:57 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 70/1251] eta: 0:13:34 lr: 0.000653 loss: 3.4357 (3.4516) grad_norm: 1.2856 (1.3080) time: 0.6325 [2021-03-27 01:50:03 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 80/1251] eta: 0:13:18 lr: 0.000653 loss: 3.5534 (3.4405) grad_norm: 1.2954 (1.3070) time: 0.6311 [2021-03-27 01:50:10 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 90/1251] eta: 0:13:08 lr: 0.000653 loss: 3.3828 (3.4143) grad_norm: 1.2954 (1.3075) time: 0.6427 [2021-03-27 01:50:16 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 100/1251] eta: 0:12:55 lr: 0.000653 loss: 3.1971 (3.4008) grad_norm: 1.2870 (1.3084) time: 0.6396 [2021-03-27 01:50:22 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 110/1251] eta: 0:12:44 lr: 0.000653 loss: 3.1971 (3.3818) grad_norm: 1.2831 (1.3151) time: 0.6275 [2021-03-27 01:50:29 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 120/1251] eta: 0:12:33 lr: 0.000653 loss: 3.3346 (3.3789) grad_norm: 1.3584 (inf) time: 0.6291 [2021-03-27 01:50:35 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 130/1251] eta: 0:12:23 lr: 0.000653 loss: 3.4123 (3.3684) grad_norm: 1.3102 (inf) time: 0.6256 [2021-03-27 01:50:41 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 140/1251] eta: 0:12:15 lr: 0.000652 loss: 3.5179 (3.3677) grad_norm: 1.2243 (inf) time: 0.6360 [2021-03-27 01:50:48 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 150/1251] eta: 0:12:06 lr: 0.000652 loss: 3.5179 (3.3745) grad_norm: 1.1888 (inf) time: 0.6368 [2021-03-27 01:50:54 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 160/1251] eta: 0:11:57 lr: 0.000652 loss: 3.4441 (3.3539) grad_norm: 1.2672 (inf) time: 0.6251 [2021-03-27 01:51:00 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 170/1251] eta: 0:11:48 lr: 0.000652 loss: 3.4441 (3.3646) grad_norm: 1.2401 (inf) time: 0.6241 [2021-03-27 01:51:06 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 180/1251] eta: 0:11:40 lr: 0.000652 loss: 3.5156 (3.3625) grad_norm: 1.3080 (inf) time: 0.6265 [2021-03-27 01:51:13 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 190/1251] eta: 0:11:32 lr: 0.000652 loss: 3.3927 (3.3657) grad_norm: 1.3223 (inf) time: 0.6276 [2021-03-27 01:51:19 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 200/1251] eta: 0:11:24 lr: 0.000652 loss: 3.4677 (3.3715) grad_norm: 1.3575 (inf) time: 0.6256 [2021-03-27 01:51:25 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 210/1251] eta: 0:11:16 lr: 0.000652 loss: 3.3400 (3.3634) grad_norm: 1.3729 (inf) time: 0.6271 [2021-03-27 01:51:32 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 220/1251] eta: 0:11:09 lr: 0.000652 loss: 3.2964 (3.3650) grad_norm: 1.2800 (inf) time: 0.6277 [2021-03-27 01:51:38 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 230/1251] eta: 0:11:01 lr: 0.000652 loss: 3.7803 (3.3842) grad_norm: 1.2692 (inf) time: 0.6268 [2021-03-27 01:51:44 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 240/1251] eta: 0:10:55 lr: 0.000652 loss: 3.6924 (3.3889) grad_norm: 1.3088 (inf) time: 0.6364 [2021-03-27 01:51:51 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 250/1251] eta: 0:10:47 lr: 0.000652 loss: 3.5066 (3.3891) grad_norm: 1.2963 (inf) time: 0.6338 [2021-03-27 01:51:57 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 260/1251] eta: 0:10:40 lr: 0.000652 loss: 3.4088 (3.3928) grad_norm: 1.2943 (inf) time: 0.6252 [2021-03-27 01:52:03 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 270/1251] eta: 0:10:33 lr: 0.000652 loss: 3.5756 (3.4005) grad_norm: 1.4081 (inf) time: 0.6288 [2021-03-27 01:52:09 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 280/1251] eta: 0:10:26 lr: 0.000652 loss: 3.5249 (3.3979) grad_norm: 1.4601 (inf) time: 0.6263 [2021-03-27 01:52:16 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 290/1251] eta: 0:10:19 lr: 0.000652 loss: 3.1507 (3.3895) grad_norm: 1.2787 (inf) time: 0.6318 [2021-03-27 01:52:22 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 300/1251] eta: 0:10:12 lr: 0.000652 loss: 3.1309 (3.3936) grad_norm: 1.2601 (inf) time: 0.6315 [2021-03-27 01:52:28 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 310/1251] eta: 0:10:05 lr: 0.000652 loss: 3.3333 (3.3896) grad_norm: 1.4006 (inf) time: 0.6205 [2021-03-27 01:52:34 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 320/1251] eta: 0:09:58 lr: 0.000652 loss: 3.3830 (3.3887) grad_norm: 1.4419 (inf) time: 0.6193 [2021-03-27 01:52:41 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 330/1251] eta: 0:09:51 lr: 0.000652 loss: 3.4098 (3.3863) grad_norm: 1.2897 (inf) time: 0.6297 [2021-03-27 01:52:47 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 340/1251] eta: 0:09:44 lr: 0.000652 loss: 3.5480 (3.3853) grad_norm: 1.2805 (inf) time: 0.6295 [2021-03-27 01:52:53 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 350/1251] eta: 0:09:37 lr: 0.000652 loss: 3.5480 (3.3878) grad_norm: 1.2640 (inf) time: 0.6214 [2021-03-27 01:52:59 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 360/1251] eta: 0:09:30 lr: 0.000652 loss: 3.5675 (3.3873) grad_norm: 1.3004 (inf) time: 0.6248 [2021-03-27 01:53:06 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 370/1251] eta: 0:09:24 lr: 0.000652 loss: 3.5916 (3.3901) grad_norm: 1.3636 (inf) time: 0.6300 [2021-03-27 01:53:12 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 380/1251] eta: 0:09:17 lr: 0.000652 loss: 3.5690 (3.3938) grad_norm: 1.2831 (inf) time: 0.6324 [2021-03-27 01:53:18 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 390/1251] eta: 0:09:11 lr: 0.000651 loss: 3.5026 (3.3927) grad_norm: 1.3478 (inf) time: 0.6312 [2021-03-27 01:53:25 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 400/1251] eta: 0:09:04 lr: 0.000651 loss: 3.4042 (3.3883) grad_norm: 1.2880 (inf) time: 0.6273 [2021-03-27 01:53:31 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 410/1251] eta: 0:08:57 lr: 0.000651 loss: 3.4311 (3.3944) grad_norm: 1.2019 (inf) time: 0.6276 [2021-03-27 01:53:37 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 420/1251] eta: 0:08:51 lr: 0.000651 loss: 3.5928 (3.4007) grad_norm: 1.2114 (inf) time: 0.6268 [2021-03-27 01:53:43 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 430/1251] eta: 0:08:44 lr: 0.000651 loss: 3.5179 (3.4021) grad_norm: 1.2346 (inf) time: 0.6253 [2021-03-27 01:53:50 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 440/1251] eta: 0:08:37 lr: 0.000651 loss: 3.3720 (3.4005) grad_norm: 1.2047 (inf) time: 0.6250 [2021-03-27 01:53:56 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 450/1251] eta: 0:08:31 lr: 0.000651 loss: 3.4362 (3.4022) grad_norm: 1.2742 (inf) time: 0.6238 [2021-03-27 01:54:02 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 460/1251] eta: 0:08:24 lr: 0.000651 loss: 3.4362 (3.4008) grad_norm: 1.3317 (inf) time: 0.6236 [2021-03-27 01:54:09 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 470/1251] eta: 0:08:18 lr: 0.000651 loss: 3.4681 (3.4047) grad_norm: 1.4066 (inf) time: 0.6293 [2021-03-27 01:54:15 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 480/1251] eta: 0:08:11 lr: 0.000651 loss: 3.5427 (3.4071) grad_norm: 1.4613 (inf) time: 0.6343 [2021-03-27 01:54:21 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 490/1251] eta: 0:08:05 lr: 0.000651 loss: 3.5123 (3.4078) grad_norm: 1.4151 (inf) time: 0.6272 [2021-03-27 01:54:27 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 500/1251] eta: 0:07:58 lr: 0.000651 loss: 3.3517 (3.4061) grad_norm: 1.2354 (inf) time: 0.6292 [2021-03-27 01:54:34 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 510/1251] eta: 0:07:52 lr: 0.000651 loss: 3.3378 (3.4064) grad_norm: 1.2986 (inf) time: 0.6302 [2021-03-27 01:54:40 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 520/1251] eta: 0:07:45 lr: 0.000651 loss: 3.3164 (3.4066) grad_norm: 1.3831 (inf) time: 0.6297 [2021-03-27 01:54:46 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 530/1251] eta: 0:07:39 lr: 0.000651 loss: 3.3084 (3.4054) grad_norm: 1.2744 (inf) time: 0.6308 [2021-03-27 01:54:53 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 540/1251] eta: 0:07:32 lr: 0.000651 loss: 3.4407 (3.4059) grad_norm: 1.2675 (inf) time: 0.6284 [2021-03-27 01:54:59 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 550/1251] eta: 0:07:26 lr: 0.000651 loss: 3.6423 (3.4078) grad_norm: 1.2811 (inf) time: 0.6329 [2021-03-27 01:55:05 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 560/1251] eta: 0:07:20 lr: 0.000651 loss: 3.6676 (3.4079) grad_norm: 1.2774 (inf) time: 0.6393 [2021-03-27 01:55:12 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 570/1251] eta: 0:07:13 lr: 0.000651 loss: 3.5175 (3.4074) grad_norm: 1.3513 (inf) time: 0.6331 [2021-03-27 01:55:18 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 580/1251] eta: 0:07:07 lr: 0.000651 loss: 3.4655 (3.4064) grad_norm: 1.3088 (inf) time: 0.6260 [2021-03-27 01:55:24 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 590/1251] eta: 0:07:00 lr: 0.000651 loss: 3.5264 (3.4056) grad_norm: 1.2303 (inf) time: 0.6259 [2021-03-27 01:55:31 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 600/1251] eta: 0:06:54 lr: 0.000651 loss: 3.5417 (3.4067) grad_norm: 1.2639 (inf) time: 0.6330 [2021-03-27 01:55:37 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 610/1251] eta: 0:06:47 lr: 0.000651 loss: 3.5453 (3.4093) grad_norm: 1.2518 (inf) time: 0.6381 [2021-03-27 01:55:43 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 620/1251] eta: 0:06:41 lr: 0.000651 loss: 3.6637 (3.4104) grad_norm: 1.2518 (inf) time: 0.6309 [2021-03-27 01:55:49 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 630/1251] eta: 0:06:34 lr: 0.000651 loss: 3.2924 (3.4078) grad_norm: 1.3030 (inf) time: 0.6250 [2021-03-27 01:55:56 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 640/1251] eta: 0:06:28 lr: 0.000650 loss: 3.2486 (3.4045) grad_norm: 1.3030 (inf) time: 0.6260 [2021-03-27 01:56:02 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 650/1251] eta: 0:06:22 lr: 0.000650 loss: 3.6213 (3.4113) grad_norm: 1.2981 (inf) time: 0.6278 [2021-03-27 01:56:08 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 660/1251] eta: 0:06:15 lr: 0.000650 loss: 3.7192 (3.4120) grad_norm: 1.2436 (inf) time: 0.6228 [2021-03-27 01:56:14 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 670/1251] eta: 0:06:09 lr: 0.000650 loss: 3.4621 (3.4106) grad_norm: 1.2190 (inf) time: 0.6227 [2021-03-27 01:56:21 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 680/1251] eta: 0:06:02 lr: 0.000650 loss: 3.3777 (3.4095) grad_norm: 1.2190 (inf) time: 0.6245 [2021-03-27 01:56:27 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 690/1251] eta: 0:05:56 lr: 0.000650 loss: 3.3777 (3.4090) grad_norm: 1.2364 (inf) time: 0.6291 [2021-03-27 01:56:33 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 700/1251] eta: 0:05:49 lr: 0.000650 loss: 3.3602 (3.4086) grad_norm: 1.3193 (inf) time: 0.6314 [2021-03-27 01:56:40 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 710/1251] eta: 0:05:43 lr: 0.000650 loss: 3.5300 (3.4111) grad_norm: 1.3603 (inf) time: 0.6256 [2021-03-27 01:56:46 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 720/1251] eta: 0:05:36 lr: 0.000650 loss: 3.7167 (3.4135) grad_norm: 1.2747 (inf) time: 0.6209 [2021-03-27 01:56:52 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 730/1251] eta: 0:05:30 lr: 0.000650 loss: 3.6767 (3.4151) grad_norm: 1.2515 (inf) time: 0.6212 [2021-03-27 01:56:58 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 740/1251] eta: 0:05:24 lr: 0.000650 loss: 3.7481 (3.4177) grad_norm: 1.2459 (inf) time: 0.6295 [2021-03-27 01:57:05 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 750/1251] eta: 0:05:17 lr: 0.000650 loss: 3.7218 (3.4196) grad_norm: 1.2498 (inf) time: 0.6385 [2021-03-27 01:57:11 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 760/1251] eta: 0:05:11 lr: 0.000650 loss: 3.4802 (3.4195) grad_norm: 1.2796 (inf) time: 0.6356 [2021-03-27 01:57:17 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 770/1251] eta: 0:05:05 lr: 0.000650 loss: 3.2883 (3.4184) grad_norm: 1.2917 (inf) time: 0.6308 [2021-03-27 01:57:24 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 780/1251] eta: 0:04:58 lr: 0.000650 loss: 3.5592 (3.4217) grad_norm: 1.3394 (inf) time: 0.6295 [2021-03-27 01:57:30 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 790/1251] eta: 0:04:52 lr: 0.000650 loss: 3.6030 (3.4185) grad_norm: 1.3045 (inf) time: 0.6343 [2021-03-27 01:57:37 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 800/1251] eta: 0:04:46 lr: 0.000650 loss: 3.3828 (3.4192) grad_norm: 1.3045 (inf) time: 0.6428 [2021-03-27 01:57:43 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 810/1251] eta: 0:04:39 lr: 0.000650 loss: 3.4357 (3.4183) grad_norm: 1.3307 (inf) time: 0.6406 [2021-03-27 01:57:49 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 820/1251] eta: 0:04:33 lr: 0.000650 loss: 3.3029 (3.4139) grad_norm: 1.3209 (inf) time: 0.6368 [2021-03-27 01:57:56 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 830/1251] eta: 0:04:27 lr: 0.000650 loss: 3.2917 (3.4114) grad_norm: 1.2672 (inf) time: 0.6340 [2021-03-27 01:58:02 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 840/1251] eta: 0:04:20 lr: 0.000650 loss: 3.3295 (3.4112) grad_norm: 1.3101 (inf) time: 0.6351 [2021-03-27 01:58:08 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 850/1251] eta: 0:04:14 lr: 0.000650 loss: 3.5646 (3.4143) grad_norm: 1.2759 (inf) time: 0.6309 [2021-03-27 01:58:14 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 860/1251] eta: 0:04:08 lr: 0.000650 loss: 3.6344 (3.4145) grad_norm: 1.2400 (inf) time: 0.6256 [2021-03-27 01:58:21 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 870/1251] eta: 0:04:01 lr: 0.000650 loss: 3.3182 (3.4128) grad_norm: 1.2992 (inf) time: 0.6272 [2021-03-27 01:58:27 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 880/1251] eta: 0:03:55 lr: 0.000650 loss: 3.5528 (3.4137) grad_norm: 1.3374 (inf) time: 0.6299 [2021-03-27 01:58:33 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 890/1251] eta: 0:03:48 lr: 0.000650 loss: 3.6354 (3.4151) grad_norm: 1.2937 (inf) time: 0.6348 [2021-03-27 01:58:40 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 900/1251] eta: 0:03:42 lr: 0.000649 loss: 3.6519 (3.4153) grad_norm: 1.2419 (inf) time: 0.6317 [2021-03-27 01:58:46 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 910/1251] eta: 0:03:36 lr: 0.000649 loss: 3.5810 (3.4160) grad_norm: 1.2319 (inf) time: 0.6311 [2021-03-27 01:58:52 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 920/1251] eta: 0:03:29 lr: 0.000649 loss: 3.5810 (3.4154) grad_norm: 1.2906 (inf) time: 0.6386 [2021-03-27 01:58:59 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 930/1251] eta: 0:03:23 lr: 0.000649 loss: 3.5868 (3.4163) grad_norm: 1.3017 (inf) time: 0.6359 [2021-03-27 01:59:05 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 940/1251] eta: 0:03:17 lr: 0.000649 loss: 3.2011 (3.4144) grad_norm: 1.3017 (inf) time: 0.6283 [2021-03-27 01:59:11 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 950/1251] eta: 0:03:10 lr: 0.000649 loss: 3.1705 (3.4127) grad_norm: 1.2230 (inf) time: 0.6307 [2021-03-27 01:59:18 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 960/1251] eta: 0:03:04 lr: 0.000649 loss: 3.3237 (3.4134) grad_norm: 1.2797 (inf) time: 0.6305 [2021-03-27 01:59:24 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 970/1251] eta: 0:02:58 lr: 0.000649 loss: 3.5581 (3.4168) grad_norm: 1.3383 (inf) time: 0.6345 [2021-03-27 01:59:30 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 980/1251] eta: 0:02:51 lr: 0.000649 loss: 3.6376 (3.4197) grad_norm: 1.3513 (inf) time: 0.6328 [2021-03-27 01:59:37 swin_base_patch4_window7_224] INFO: Epoch: [121] [ 990/1251] eta: 0:02:45 lr: 0.000649 loss: 3.5533 (3.4186) grad_norm: 1.3755 (inf) time: 0.6269 [2021-03-27 01:59:43 swin_base_patch4_window7_224] INFO: Epoch: [121] [1000/1251] eta: 0:02:39 lr: 0.000649 loss: 3.1899 (3.4161) grad_norm: 1.2386 (inf) time: 0.6318 [2021-03-27 01:59:49 swin_base_patch4_window7_224] INFO: Epoch: [121] [1010/1251] eta: 0:02:32 lr: 0.000649 loss: 3.2947 (3.4160) grad_norm: 1.2344 (inf) time: 0.6290 [2021-03-27 01:59:56 swin_base_patch4_window7_224] INFO: Epoch: [121] [1020/1251] eta: 0:02:26 lr: 0.000649 loss: 3.4672 (3.4152) grad_norm: 1.3387 (inf) time: 0.6283 [2021-03-27 02:00:02 swin_base_patch4_window7_224] INFO: Epoch: [121] [1030/1251] eta: 0:02:20 lr: 0.000649 loss: 3.4474 (3.4170) grad_norm: 1.3619 (inf) time: 0.6326 [2021-03-27 02:00:08 swin_base_patch4_window7_224] INFO: Epoch: [121] [1040/1251] eta: 0:02:13 lr: 0.000649 loss: 3.5806 (3.4182) grad_norm: 1.2699 (inf) time: 0.6404 [2021-03-27 02:00:15 swin_base_patch4_window7_224] INFO: Epoch: [121] [1050/1251] eta: 0:02:07 lr: 0.000649 loss: 3.5242 (3.4166) grad_norm: 1.3223 (inf) time: 0.6426 [2021-03-27 02:00:21 swin_base_patch4_window7_224] INFO: Epoch: [121] [1060/1251] eta: 0:02:01 lr: 0.000649 loss: 3.3565 (3.4159) grad_norm: 1.2844 (inf) time: 0.6337 [2021-03-27 02:00:27 swin_base_patch4_window7_224] INFO: Epoch: [121] [1070/1251] eta: 0:01:54 lr: 0.000649 loss: 3.3730 (3.4162) grad_norm: 1.3086 (inf) time: 0.6267 [2021-03-27 02:00:34 swin_base_patch4_window7_224] INFO: Epoch: [121] [1080/1251] eta: 0:01:48 lr: 0.000649 loss: 3.4507 (3.4137) grad_norm: 1.3463 (inf) time: 0.6279 [2021-03-27 02:00:40 swin_base_patch4_window7_224] INFO: Epoch: [121] [1090/1251] eta: 0:01:42 lr: 0.000649 loss: 3.4507 (3.4137) grad_norm: 1.3463 (inf) time: 0.6277 [2021-03-27 02:00:46 swin_base_patch4_window7_224] INFO: Epoch: [121] [1100/1251] eta: 0:01:35 lr: 0.000649 loss: 3.4922 (3.4127) grad_norm: 1.3720 (inf) time: 0.6307 [2021-03-27 02:00:53 swin_base_patch4_window7_224] INFO: Epoch: [121] [1110/1251] eta: 0:01:29 lr: 0.000649 loss: 3.3202 (3.4108) grad_norm: 1.3321 (inf) time: 0.6364 [2021-03-27 02:00:59 swin_base_patch4_window7_224] INFO: Epoch: [121] [1120/1251] eta: 0:01:23 lr: 0.000649 loss: 3.1917 (3.4085) grad_norm: 1.3247 (inf) time: 0.6290 [2021-03-27 02:01:05 swin_base_patch4_window7_224] INFO: Epoch: [121] [1130/1251] eta: 0:01:16 lr: 0.000649 loss: 3.5078 (3.4095) grad_norm: 1.3191 (inf) time: 0.6260 [2021-03-27 02:01:11 swin_base_patch4_window7_224] INFO: Epoch: [121] [1140/1251] eta: 0:01:10 lr: 0.000649 loss: 3.6020 (3.4099) grad_norm: 1.3191 (inf) time: 0.6316 [2021-03-27 02:01:18 swin_base_patch4_window7_224] INFO: Epoch: [121] [1150/1251] eta: 0:01:04 lr: 0.000648 loss: 3.5737 (3.4082) grad_norm: 1.2806 (inf) time: 0.6318 [2021-03-27 02:01:24 swin_base_patch4_window7_224] INFO: Epoch: [121] [1160/1251] eta: 0:00:57 lr: 0.000648 loss: 3.3927 (3.4082) grad_norm: 1.2674 (inf) time: 0.6270 [2021-03-27 02:01:30 swin_base_patch4_window7_224] INFO: Epoch: [121] [1170/1251] eta: 0:00:51 lr: 0.000648 loss: 3.1552 (3.4055) grad_norm: 1.2851 (inf) time: 0.6262 [2021-03-27 02:01:37 swin_base_patch4_window7_224] INFO: Epoch: [121] [1180/1251] eta: 0:00:44 lr: 0.000648 loss: 3.6456 (3.4090) grad_norm: 1.2851 (inf) time: 0.6321 [2021-03-27 02:01:43 swin_base_patch4_window7_224] INFO: Epoch: [121] [1190/1251] eta: 0:00:38 lr: 0.000648 loss: 3.7066 (3.4085) grad_norm: 1.3207 (inf) time: 0.6365 [2021-03-27 02:01:49 swin_base_patch4_window7_224] INFO: Epoch: [121] [1200/1251] eta: 0:00:32 lr: 0.000648 loss: 3.4133 (3.4089) grad_norm: 1.2811 (inf) time: 0.6361 [2021-03-27 02:01:56 swin_base_patch4_window7_224] INFO: Epoch: [121] [1210/1251] eta: 0:00:25 lr: 0.000648 loss: 3.4623 (3.4088) grad_norm: 1.2811 (inf) time: 0.6318 [2021-03-27 02:02:02 swin_base_patch4_window7_224] INFO: Epoch: [121] [1220/1251] eta: 0:00:19 lr: 0.000648 loss: 3.5734 (3.4100) grad_norm: 1.2801 (inf) time: 0.6276 [2021-03-27 02:02:08 swin_base_patch4_window7_224] INFO: Epoch: [121] [1230/1251] eta: 0:00:13 lr: 0.000648 loss: 3.8459 (3.4130) grad_norm: 1.2801 (inf) time: 0.6308 [2021-03-27 02:02:14 swin_base_patch4_window7_224] INFO: Epoch: [121] [1240/1251] eta: 0:00:06 lr: 0.000648 loss: 3.5714 (3.4128) grad_norm: 1.3377 (inf) time: 0.6290 [2021-03-27 02:02:21 swin_base_patch4_window7_224] INFO: Epoch: [121] [1250/1251] eta: 0:00:00 lr: 0.000648 loss: 3.4118 (3.4111) grad_norm: 1.3377 (inf) time: 0.6231 [2021-03-27 02:02:28 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:45 loss: 0.7699 (0.7699) acc1: 85.9375 (85.9375) acc5: 95.3125 (95.3125) [2021-03-27 02:02:30 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0077 (1.0127) acc1: 76.5625 (77.1307) acc5: 93.7500 (93.1818) [2021-03-27 02:02:32 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.9877 (0.9909) acc1: 76.5625 (77.2321) acc5: 93.7500 (93.9732) [2021-03-27 02:02:34 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 1.0294 (1.0336) acc1: 75.0000 (76.1089) acc5: 93.7500 (93.2964) [2021-03-27 02:02:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0182 (1.0230) acc1: 76.5625 (76.4863) acc5: 93.7500 (93.3308) [2021-03-27 02:02:37 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8865 (1.0047) acc1: 78.1250 (76.6720) acc5: 95.3125 (93.8240) [2021-03-27 02:02:46 swin_base_patch4_window7_224] INFO: * Acc@1 77.802 Acc@5 94.084 loss 0.983 [2021-03-27 02:02:46 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.8% [2021-03-27 02:02:46 swin_base_patch4_window7_224] INFO: Max accuracy: 77.80% [2021-03-27 02:02:50 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 0/1251] eta: 1:34:03 lr: 0.000648 loss: 3.7057 (3.7057) grad_norm: 1.3560 (1.3560) time: 4.5110 [2021-03-27 02:02:57 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 10/1251] eta: 0:20:21 lr: 0.000648 loss: 3.6301 (3.3099) grad_norm: 1.3309 (1.3053) time: 0.9843 [2021-03-27 02:03:03 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 20/1251] eta: 0:16:40 lr: 0.000648 loss: 3.6301 (3.4856) grad_norm: 1.3185 (1.3218) time: 0.6279 [2021-03-27 02:03:09 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 30/1251] eta: 0:15:23 lr: 0.000648 loss: 3.6354 (3.4138) grad_norm: 1.3291 (1.3491) time: 0.6312 [2021-03-27 02:03:15 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 40/1251] eta: 0:14:36 lr: 0.000648 loss: 3.3774 (3.4260) grad_norm: 1.3132 (1.3474) time: 0.6311 [2021-03-27 02:03:22 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 50/1251] eta: 0:14:10 lr: 0.000648 loss: 3.4014 (3.4041) grad_norm: 1.2851 (1.3384) time: 0.6338 [2021-03-27 02:03:28 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 60/1251] eta: 0:13:48 lr: 0.000648 loss: 3.3343 (3.3669) grad_norm: 1.3306 (1.3458) time: 0.6362 [2021-03-27 02:03:35 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 70/1251] eta: 0:13:31 lr: 0.000648 loss: 2.9563 (3.3261) grad_norm: 1.3700 (1.3548) time: 0.6330 [2021-03-27 02:03:41 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 80/1251] eta: 0:13:17 lr: 0.000648 loss: 3.1287 (3.3210) grad_norm: 1.3001 (1.3444) time: 0.6382 [2021-03-27 02:03:47 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 90/1251] eta: 0:13:03 lr: 0.000648 loss: 3.5337 (3.3244) grad_norm: 1.3051 (1.3616) time: 0.6328 [2021-03-27 02:03:54 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 100/1251] eta: 0:12:51 lr: 0.000648 loss: 3.4541 (3.3060) grad_norm: 1.3410 (1.3594) time: 0.6281 [2021-03-27 02:04:00 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 110/1251] eta: 0:12:42 lr: 0.000648 loss: 3.3236 (3.3084) grad_norm: 1.2988 (1.3593) time: 0.6359 [2021-03-27 02:04:06 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 120/1251] eta: 0:12:32 lr: 0.000648 loss: 3.3906 (3.3001) grad_norm: 1.2882 (1.3569) time: 0.6379 [2021-03-27 02:04:13 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 130/1251] eta: 0:12:24 lr: 0.000648 loss: 3.4169 (3.3159) grad_norm: 1.2487 (1.3516) time: 0.6406 [2021-03-27 02:04:19 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 140/1251] eta: 0:12:15 lr: 0.000648 loss: 3.3930 (3.3124) grad_norm: 1.2858 (1.3454) time: 0.6397 [2021-03-27 02:04:25 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 150/1251] eta: 0:12:06 lr: 0.000647 loss: 3.3818 (3.3189) grad_norm: 1.2999 (1.3442) time: 0.6314 [2021-03-27 02:04:32 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 160/1251] eta: 0:11:57 lr: 0.000647 loss: 3.2460 (3.3113) grad_norm: 1.3449 (1.3544) time: 0.6300 [2021-03-27 02:04:38 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 170/1251] eta: 0:11:49 lr: 0.000647 loss: 3.3931 (3.3177) grad_norm: 1.3754 (1.3548) time: 0.6303 [2021-03-27 02:04:44 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 180/1251] eta: 0:11:41 lr: 0.000647 loss: 3.3764 (3.3171) grad_norm: 1.2949 (1.3501) time: 0.6360 [2021-03-27 02:04:51 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 190/1251] eta: 0:11:34 lr: 0.000647 loss: 3.2307 (3.3151) grad_norm: 1.2719 (1.3501) time: 0.6411 [2021-03-27 02:04:57 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 200/1251] eta: 0:11:26 lr: 0.000647 loss: 3.2307 (3.3174) grad_norm: 1.3070 (1.3503) time: 0.6378 [2021-03-27 02:05:03 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 210/1251] eta: 0:11:19 lr: 0.000647 loss: 3.5462 (3.3206) grad_norm: 1.3160 (1.3557) time: 0.6302 [2021-03-27 02:05:10 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 220/1251] eta: 0:11:11 lr: 0.000647 loss: 3.4324 (3.3260) grad_norm: 1.2855 (1.3512) time: 0.6279 [2021-03-27 02:05:16 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 230/1251] eta: 0:11:04 lr: 0.000647 loss: 3.4422 (3.3321) grad_norm: 1.2980 (1.3535) time: 0.6307 [2021-03-27 02:05:22 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 240/1251] eta: 0:10:57 lr: 0.000647 loss: 3.7035 (3.3346) grad_norm: 1.3552 (1.3558) time: 0.6362 [2021-03-27 02:05:29 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 250/1251] eta: 0:10:50 lr: 0.000647 loss: 3.3708 (3.3308) grad_norm: 1.3977 (1.3589) time: 0.6380 [2021-03-27 02:05:35 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 260/1251] eta: 0:10:42 lr: 0.000647 loss: 3.2277 (3.3239) grad_norm: 1.3756 (1.3565) time: 0.6327 [2021-03-27 02:05:42 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 270/1251] eta: 0:10:36 lr: 0.000647 loss: 3.2665 (3.3293) grad_norm: 1.3681 (1.3589) time: 0.6368 [2021-03-27 02:05:48 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 280/1251] eta: 0:10:29 lr: 0.000647 loss: 3.4438 (3.3313) grad_norm: 1.3891 (1.3600) time: 0.6384 [2021-03-27 02:05:54 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 290/1251] eta: 0:10:21 lr: 0.000647 loss: 3.6513 (3.3403) grad_norm: 1.3018 (1.3596) time: 0.6276 [2021-03-27 02:06:00 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 300/1251] eta: 0:10:14 lr: 0.000647 loss: 3.1513 (3.3269) grad_norm: 1.3279 (1.3593) time: 0.6226 [2021-03-27 02:06:07 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 310/1251] eta: 0:10:07 lr: 0.000647 loss: 2.8552 (3.3202) grad_norm: 1.3040 (1.3557) time: 0.6278 [2021-03-27 02:06:13 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 320/1251] eta: 0:10:00 lr: 0.000647 loss: 3.6498 (3.3307) grad_norm: 1.2454 (1.3548) time: 0.6328 [2021-03-27 02:06:20 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 330/1251] eta: 0:09:54 lr: 0.000647 loss: 3.4465 (3.3258) grad_norm: 1.3079 (1.3548) time: 0.6423 [2021-03-27 02:06:26 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 340/1251] eta: 0:09:47 lr: 0.000647 loss: 3.3701 (3.3320) grad_norm: 1.2687 (1.3524) time: 0.6387 [2021-03-27 02:06:32 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 350/1251] eta: 0:09:40 lr: 0.000647 loss: 3.6195 (3.3375) grad_norm: 1.2037 (1.3482) time: 0.6263 [2021-03-27 02:06:39 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 360/1251] eta: 0:09:34 lr: 0.000647 loss: 3.5581 (3.3388) grad_norm: 1.2610 (1.3474) time: 0.6353 [2021-03-27 02:06:45 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 370/1251] eta: 0:09:27 lr: 0.000647 loss: 3.3972 (3.3371) grad_norm: 1.3220 (1.3449) time: 0.6357 [2021-03-27 02:06:51 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 380/1251] eta: 0:09:20 lr: 0.000647 loss: 3.3308 (3.3344) grad_norm: 1.2729 (1.3445) time: 0.6367 [2021-03-27 02:06:58 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 390/1251] eta: 0:09:14 lr: 0.000647 loss: 3.3971 (3.3369) grad_norm: 1.3296 (1.3463) time: 0.6382 [2021-03-27 02:07:04 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 400/1251] eta: 0:09:07 lr: 0.000646 loss: 3.3985 (3.3340) grad_norm: 1.3634 (1.3487) time: 0.6337 [2021-03-27 02:07:10 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 410/1251] eta: 0:09:00 lr: 0.000646 loss: 3.4292 (3.3378) grad_norm: 1.3417 (1.3492) time: 0.6325 [2021-03-27 02:07:17 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 420/1251] eta: 0:08:54 lr: 0.000646 loss: 3.5115 (3.3390) grad_norm: 1.3238 (1.3493) time: 0.6334 [2021-03-27 02:07:23 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 430/1251] eta: 0:08:47 lr: 0.000646 loss: 3.5701 (3.3418) grad_norm: 1.3238 (1.3495) time: 0.6298 [2021-03-27 02:07:29 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 440/1251] eta: 0:08:40 lr: 0.000646 loss: 3.6283 (3.3411) grad_norm: 1.3267 (1.3506) time: 0.6230 [2021-03-27 02:07:35 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 450/1251] eta: 0:08:34 lr: 0.000646 loss: 3.5377 (3.3440) grad_norm: 1.3267 (1.3510) time: 0.6304 [2021-03-27 02:07:42 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 460/1251] eta: 0:08:27 lr: 0.000646 loss: 3.5136 (3.3424) grad_norm: 1.2763 (1.3500) time: 0.6357 [2021-03-27 02:07:48 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 470/1251] eta: 0:08:21 lr: 0.000646 loss: 3.3045 (3.3429) grad_norm: 1.2879 (1.3495) time: 0.6344 [2021-03-27 02:07:54 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 480/1251] eta: 0:08:14 lr: 0.000646 loss: 3.5137 (3.3471) grad_norm: 1.3490 (1.3507) time: 0.6287 [2021-03-27 02:08:01 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 490/1251] eta: 0:08:08 lr: 0.000646 loss: 3.5459 (3.3463) grad_norm: 1.3547 (1.3515) time: 0.6308 [2021-03-27 02:08:07 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 500/1251] eta: 0:08:01 lr: 0.000646 loss: 3.3840 (3.3458) grad_norm: 1.3136 (1.3508) time: 0.6344 [2021-03-27 02:08:13 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 510/1251] eta: 0:07:54 lr: 0.000646 loss: 3.4159 (3.3453) grad_norm: 1.2420 (1.3501) time: 0.6329 [2021-03-27 02:08:20 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 520/1251] eta: 0:07:48 lr: 0.000646 loss: 3.4159 (3.3429) grad_norm: 1.2610 (1.3495) time: 0.6294 [2021-03-27 02:08:26 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 530/1251] eta: 0:07:41 lr: 0.000646 loss: 3.5010 (3.3434) grad_norm: 1.2677 (1.3480) time: 0.6282 [2021-03-27 02:08:32 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 540/1251] eta: 0:07:35 lr: 0.000646 loss: 3.3765 (3.3434) grad_norm: 1.2876 (1.3475) time: 0.6330 [2021-03-27 02:08:39 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 550/1251] eta: 0:07:29 lr: 0.000646 loss: 3.6150 (3.3463) grad_norm: 1.3088 (1.3471) time: 0.6436 [2021-03-27 02:08:45 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 560/1251] eta: 0:07:22 lr: 0.000646 loss: 3.6150 (3.3464) grad_norm: 1.2965 (1.3471) time: 0.6416 [2021-03-27 02:08:51 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 570/1251] eta: 0:07:15 lr: 0.000646 loss: 3.3661 (3.3478) grad_norm: 1.3406 (1.3473) time: 0.6297 [2021-03-27 02:08:58 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 580/1251] eta: 0:07:09 lr: 0.000646 loss: 3.3185 (3.3454) grad_norm: 1.3463 (1.3486) time: 0.6294 [2021-03-27 02:09:04 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 590/1251] eta: 0:07:03 lr: 0.000646 loss: 3.1409 (3.3426) grad_norm: 1.3330 (1.3481) time: 0.6333 [2021-03-27 02:09:10 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 600/1251] eta: 0:06:56 lr: 0.000646 loss: 3.5287 (3.3461) grad_norm: 1.2418 (1.3472) time: 0.6364 [2021-03-27 02:09:17 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 610/1251] eta: 0:06:50 lr: 0.000646 loss: 3.6422 (3.3456) grad_norm: 1.3177 (1.3473) time: 0.6354 [2021-03-27 02:09:23 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 620/1251] eta: 0:06:43 lr: 0.000646 loss: 3.5021 (3.3506) grad_norm: 1.3170 (1.3470) time: 0.6376 [2021-03-27 02:09:30 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 630/1251] eta: 0:06:37 lr: 0.000646 loss: 3.5021 (3.3513) grad_norm: 1.2772 (1.3457) time: 0.6361 [2021-03-27 02:09:36 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 640/1251] eta: 0:06:30 lr: 0.000646 loss: 3.7228 (3.3556) grad_norm: 1.3021 (1.3455) time: 0.6360 [2021-03-27 02:09:42 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 650/1251] eta: 0:06:24 lr: 0.000645 loss: 3.6203 (3.3612) grad_norm: 1.2803 (1.3442) time: 0.6342 [2021-03-27 02:09:49 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 660/1251] eta: 0:06:17 lr: 0.000645 loss: 3.4810 (3.3578) grad_norm: 1.2771 (1.3441) time: 0.6348 [2021-03-27 02:09:55 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 670/1251] eta: 0:06:11 lr: 0.000645 loss: 3.3233 (3.3588) grad_norm: 1.2856 (1.3430) time: 0.6324 [2021-03-27 02:10:01 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 680/1251] eta: 0:06:05 lr: 0.000645 loss: 3.4474 (3.3595) grad_norm: 1.3009 (1.3442) time: 0.6292 [2021-03-27 02:10:08 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 690/1251] eta: 0:05:58 lr: 0.000645 loss: 3.5474 (3.3635) grad_norm: 1.3504 (1.3436) time: 0.6346 [2021-03-27 02:10:14 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 700/1251] eta: 0:05:52 lr: 0.000645 loss: 3.4402 (3.3648) grad_norm: 1.3296 (1.3440) time: 0.6340 [2021-03-27 02:10:20 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 710/1251] eta: 0:05:45 lr: 0.000645 loss: 3.4244 (3.3664) grad_norm: 1.2960 (1.3430) time: 0.6281 [2021-03-27 02:10:27 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 720/1251] eta: 0:05:39 lr: 0.000645 loss: 3.4531 (3.3674) grad_norm: 1.2523 (1.3424) time: 0.6295 [2021-03-27 02:10:33 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 730/1251] eta: 0:05:32 lr: 0.000645 loss: 3.4607 (3.3697) grad_norm: 1.2523 (1.3421) time: 0.6380 [2021-03-27 02:10:39 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 740/1251] eta: 0:05:26 lr: 0.000645 loss: 3.6534 (3.3719) grad_norm: 1.3113 (1.3419) time: 0.6352 [2021-03-27 02:10:46 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 750/1251] eta: 0:05:19 lr: 0.000645 loss: 3.4468 (3.3692) grad_norm: 1.3262 (1.3416) time: 0.6299 [2021-03-27 02:10:52 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 760/1251] eta: 0:05:13 lr: 0.000645 loss: 3.5732 (3.3726) grad_norm: 1.3157 (1.3426) time: 0.6279 [2021-03-27 02:10:58 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 770/1251] eta: 0:05:07 lr: 0.000645 loss: 3.7434 (3.3767) grad_norm: 1.3214 (1.3426) time: 0.6309 [2021-03-27 02:11:04 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 780/1251] eta: 0:05:00 lr: 0.000645 loss: 3.4780 (3.3739) grad_norm: 1.2051 (1.3408) time: 0.6345 [2021-03-27 02:11:11 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 790/1251] eta: 0:04:54 lr: 0.000645 loss: 3.2211 (3.3727) grad_norm: 1.2051 (1.3405) time: 0.6348 [2021-03-27 02:11:17 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 800/1251] eta: 0:04:47 lr: 0.000645 loss: 3.4136 (3.3750) grad_norm: 1.3495 (1.3406) time: 0.6319 [2021-03-27 02:11:23 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 810/1251] eta: 0:04:41 lr: 0.000645 loss: 3.6831 (3.3794) grad_norm: 1.3324 (1.3400) time: 0.6305 [2021-03-27 02:11:30 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 820/1251] eta: 0:04:35 lr: 0.000645 loss: 3.7051 (3.3809) grad_norm: 1.2839 (1.3395) time: 0.6400 [2021-03-27 02:11:36 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 830/1251] eta: 0:04:28 lr: 0.000645 loss: 3.5379 (3.3813) grad_norm: 1.3110 (1.3391) time: 0.6399 [2021-03-27 02:11:43 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 840/1251] eta: 0:04:22 lr: 0.000645 loss: 3.5093 (3.3810) grad_norm: 1.3152 (1.3390) time: 0.6340 [2021-03-27 02:11:49 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 850/1251] eta: 0:04:15 lr: 0.000645 loss: 3.5962 (3.3809) grad_norm: 1.3589 (1.3412) time: 0.6345 [2021-03-27 02:11:55 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 860/1251] eta: 0:04:09 lr: 0.000645 loss: 3.6096 (3.3812) grad_norm: 1.3699 (1.3413) time: 0.6295 [2021-03-27 02:12:02 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 870/1251] eta: 0:04:03 lr: 0.000645 loss: 3.3685 (3.3800) grad_norm: 1.3038 (1.3413) time: 0.6317 [2021-03-27 02:12:08 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 880/1251] eta: 0:03:56 lr: 0.000645 loss: 3.4192 (3.3819) grad_norm: 1.2679 (1.3411) time: 0.6349 [2021-03-27 02:12:14 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 890/1251] eta: 0:03:50 lr: 0.000645 loss: 3.4908 (3.3833) grad_norm: 1.3308 (1.3409) time: 0.6275 [2021-03-27 02:12:20 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 900/1251] eta: 0:03:43 lr: 0.000644 loss: 3.4121 (3.3822) grad_norm: 1.3387 (1.3409) time: 0.6265 [2021-03-27 02:12:27 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 910/1251] eta: 0:03:37 lr: 0.000644 loss: 3.7359 (3.3867) grad_norm: 1.3213 (1.3409) time: 0.6268 [2021-03-27 02:12:33 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 920/1251] eta: 0:03:30 lr: 0.000644 loss: 3.7359 (3.3864) grad_norm: 1.3213 (1.3406) time: 0.6289 [2021-03-27 02:12:39 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 930/1251] eta: 0:03:24 lr: 0.000644 loss: 3.4510 (3.3875) grad_norm: 1.3383 (1.3420) time: 0.6287 [2021-03-27 02:12:45 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 940/1251] eta: 0:03:18 lr: 0.000644 loss: 3.3208 (3.3844) grad_norm: 1.3468 (1.3419) time: 0.6222 [2021-03-27 02:12:52 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 950/1251] eta: 0:03:11 lr: 0.000644 loss: 3.2404 (3.3837) grad_norm: 1.3140 (1.3417) time: 0.6222 [2021-03-27 02:12:58 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 960/1251] eta: 0:03:05 lr: 0.000644 loss: 3.2569 (3.3844) grad_norm: 1.3637 (1.3425) time: 0.6246 [2021-03-27 02:13:04 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 970/1251] eta: 0:02:58 lr: 0.000644 loss: 3.4882 (3.3868) grad_norm: 1.3441 (1.3421) time: 0.6242 [2021-03-27 02:13:10 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 980/1251] eta: 0:02:52 lr: 0.000644 loss: 3.5818 (3.3866) grad_norm: 1.3113 (1.3421) time: 0.6230 [2021-03-27 02:13:17 swin_base_patch4_window7_224] INFO: Epoch: [122] [ 990/1251] eta: 0:02:46 lr: 0.000644 loss: 3.2115 (3.3850) grad_norm: 1.2857 (1.3413) time: 0.6238 [2021-03-27 02:13:23 swin_base_patch4_window7_224] INFO: Epoch: [122] [1000/1251] eta: 0:02:39 lr: 0.000644 loss: 3.2519 (3.3848) grad_norm: 1.2697 (1.3420) time: 0.6263 [2021-03-27 02:13:29 swin_base_patch4_window7_224] INFO: Epoch: [122] [1010/1251] eta: 0:02:33 lr: 0.000644 loss: 3.3924 (3.3849) grad_norm: 1.3103 (1.3421) time: 0.6357 [2021-03-27 02:13:36 swin_base_patch4_window7_224] INFO: Epoch: [122] [1020/1251] eta: 0:02:27 lr: 0.000644 loss: 3.3871 (3.3823) grad_norm: 1.3103 (1.3414) time: 0.6404 [2021-03-27 02:13:42 swin_base_patch4_window7_224] INFO: Epoch: [122] [1030/1251] eta: 0:02:20 lr: 0.000644 loss: 3.3993 (3.3836) grad_norm: 1.2523 (1.3403) time: 0.6382 [2021-03-27 02:13:48 swin_base_patch4_window7_224] INFO: Epoch: [122] [1040/1251] eta: 0:02:14 lr: 0.000644 loss: 3.6269 (3.3842) grad_norm: 1.2919 (1.3407) time: 0.6360 [2021-03-27 02:13:55 swin_base_patch4_window7_224] INFO: Epoch: [122] [1050/1251] eta: 0:02:07 lr: 0.000644 loss: 3.6320 (3.3841) grad_norm: 1.3212 (1.3405) time: 0.6296 [2021-03-27 02:14:01 swin_base_patch4_window7_224] INFO: Epoch: [122] [1060/1251] eta: 0:02:01 lr: 0.000644 loss: 3.5370 (3.3849) grad_norm: 1.3299 (1.3423) time: 0.6227 [2021-03-27 02:14:07 swin_base_patch4_window7_224] INFO: Epoch: [122] [1070/1251] eta: 0:01:55 lr: 0.000644 loss: 3.5248 (3.3864) grad_norm: 1.3299 (1.3418) time: 0.6286 [2021-03-27 02:14:14 swin_base_patch4_window7_224] INFO: Epoch: [122] [1080/1251] eta: 0:01:48 lr: 0.000644 loss: 3.2727 (3.3825) grad_norm: 1.2985 (1.3420) time: 0.6314 [2021-03-27 02:14:20 swin_base_patch4_window7_224] INFO: Epoch: [122] [1090/1251] eta: 0:01:42 lr: 0.000644 loss: 3.1148 (3.3817) grad_norm: 1.2742 (1.3415) time: 0.6290 [2021-03-27 02:14:26 swin_base_patch4_window7_224] INFO: Epoch: [122] [1100/1251] eta: 0:01:36 lr: 0.000644 loss: 3.3447 (3.3826) grad_norm: 1.3681 (1.3436) time: 0.6326 [2021-03-27 02:14:32 swin_base_patch4_window7_224] INFO: Epoch: [122] [1110/1251] eta: 0:01:29 lr: 0.000644 loss: 3.5672 (3.3829) grad_norm: 1.3753 (1.3438) time: 0.6281 [2021-03-27 02:14:39 swin_base_patch4_window7_224] INFO: Epoch: [122] [1120/1251] eta: 0:01:23 lr: 0.000644 loss: 3.5076 (3.3842) grad_norm: 1.3193 (1.3438) time: 0.6231 [2021-03-27 02:14:45 swin_base_patch4_window7_224] INFO: Epoch: [122] [1130/1251] eta: 0:01:16 lr: 0.000644 loss: 3.5076 (3.3854) grad_norm: 1.3072 (1.3438) time: 0.6261 [2021-03-27 02:14:51 swin_base_patch4_window7_224] INFO: Epoch: [122] [1140/1251] eta: 0:01:10 lr: 0.000644 loss: 3.4897 (3.3847) grad_norm: 1.2542 (1.3430) time: 0.6286 [2021-03-27 02:14:58 swin_base_patch4_window7_224] INFO: Epoch: [122] [1150/1251] eta: 0:01:04 lr: 0.000644 loss: 3.5563 (3.3858) grad_norm: 1.2542 (1.3430) time: 0.6325 [2021-03-27 02:15:04 swin_base_patch4_window7_224] INFO: Epoch: [122] [1160/1251] eta: 0:00:57 lr: 0.000643 loss: 3.5632 (3.3865) grad_norm: 1.3539 (1.3431) time: 0.6353 [2021-03-27 02:15:10 swin_base_patch4_window7_224] INFO: Epoch: [122] [1170/1251] eta: 0:00:51 lr: 0.000643 loss: 3.4351 (3.3861) grad_norm: 1.3763 (1.3439) time: 0.6291 [2021-03-27 02:15:16 swin_base_patch4_window7_224] INFO: Epoch: [122] [1180/1251] eta: 0:00:45 lr: 0.000643 loss: 3.2207 (3.3851) grad_norm: 1.3420 (1.3439) time: 0.6254 [2021-03-27 02:15:23 swin_base_patch4_window7_224] INFO: Epoch: [122] [1190/1251] eta: 0:00:38 lr: 0.000643 loss: 3.4220 (3.3865) grad_norm: 1.2815 (1.3441) time: 0.6271 [2021-03-27 02:15:29 swin_base_patch4_window7_224] INFO: Epoch: [122] [1200/1251] eta: 0:00:32 lr: 0.000643 loss: 3.6586 (3.3855) grad_norm: 1.3172 (1.3437) time: 0.6292 [2021-03-27 02:15:35 swin_base_patch4_window7_224] INFO: Epoch: [122] [1210/1251] eta: 0:00:26 lr: 0.000643 loss: 3.5965 (3.3874) grad_norm: 1.3194 (1.3438) time: 0.6359 [2021-03-27 02:15:42 swin_base_patch4_window7_224] INFO: Epoch: [122] [1220/1251] eta: 0:00:19 lr: 0.000643 loss: 3.4696 (3.3851) grad_norm: 1.3005 (1.3439) time: 0.6344 [2021-03-27 02:15:48 swin_base_patch4_window7_224] INFO: Epoch: [122] [1230/1251] eta: 0:00:13 lr: 0.000643 loss: 3.2495 (3.3839) grad_norm: 1.4298 (1.3457) time: 0.6256 [2021-03-27 02:15:54 swin_base_patch4_window7_224] INFO: Epoch: [122] [1240/1251] eta: 0:00:06 lr: 0.000643 loss: 3.3235 (3.3836) grad_norm: 1.4231 (1.3462) time: 0.6251 [2021-03-27 02:16:00 swin_base_patch4_window7_224] INFO: Epoch: [122] [1250/1251] eta: 0:00:00 lr: 0.000643 loss: 3.4815 (3.3841) grad_norm: 1.3873 (1.3463) time: 0.6217 [2021-03-27 02:16:06 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:55 loss: 0.9233 (0.9233) acc1: 79.6875 (79.6875) acc5: 95.3125 (95.3125) [2021-03-27 02:16:09 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.9233 (0.8939) acc1: 81.2500 (80.3977) acc5: 95.3125 (95.5966) [2021-03-27 02:16:11 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9702 (0.9573) acc1: 78.1250 (78.5714) acc5: 93.7500 (94.4940) [2021-03-27 02:16:12 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0234 (0.9916) acc1: 73.4375 (77.1673) acc5: 93.7500 (94.1028) [2021-03-27 02:16:15 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0256 (0.9954) acc1: 76.5625 (77.1723) acc5: 92.1875 (93.7500) [2021-03-27 02:16:16 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9725 (0.9855) acc1: 78.1250 (77.4720) acc5: 93.7500 (93.9520) [2021-03-27 02:16:23 swin_base_patch4_window7_224] INFO: * Acc@1 77.714 Acc@5 94.070 loss 0.971 [2021-03-27 02:16:23 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.7% [2021-03-27 02:16:23 swin_base_patch4_window7_224] INFO: Max accuracy: 77.80% [2021-03-27 02:16:27 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 0/1251] eta: 1:25:53 lr: 0.000643 loss: 3.6378 (3.6378) grad_norm: 1.5591 (1.5591) time: 4.1192 [2021-03-27 02:16:34 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 10/1251] eta: 0:19:51 lr: 0.000643 loss: 3.2258 (3.3312) grad_norm: 1.4768 (1.4604) time: 0.9602 [2021-03-27 02:16:40 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 20/1251] eta: 0:16:22 lr: 0.000643 loss: 3.2417 (3.4116) grad_norm: 1.3802 (1.4243) time: 0.6323 [2021-03-27 02:16:46 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 30/1251] eta: 0:15:13 lr: 0.000643 loss: 3.2417 (3.3418) grad_norm: 1.2692 (1.3617) time: 0.6319 [2021-03-27 02:16:53 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 40/1251] eta: 0:14:33 lr: 0.000643 loss: 3.3321 (3.3506) grad_norm: 1.2954 (1.4162) time: 0.6411 [2021-03-27 02:16:59 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 50/1251] eta: 0:14:04 lr: 0.000643 loss: 3.4144 (3.3582) grad_norm: 1.4519 (1.4218) time: 0.6338 [2021-03-27 02:17:05 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 60/1251] eta: 0:13:42 lr: 0.000643 loss: 3.2142 (3.3212) grad_norm: 1.4145 (1.4182) time: 0.6266 [2021-03-27 02:17:11 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 70/1251] eta: 0:13:24 lr: 0.000643 loss: 3.1794 (3.3088) grad_norm: 1.3109 (1.4101) time: 0.6230 [2021-03-27 02:17:18 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 80/1251] eta: 0:13:10 lr: 0.000643 loss: 3.5710 (3.3487) grad_norm: 1.3014 (1.3946) time: 0.6287 [2021-03-27 02:17:24 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 90/1251] eta: 0:13:00 lr: 0.000643 loss: 3.6698 (3.3625) grad_norm: 1.3259 (1.3899) time: 0.6403 [2021-03-27 02:17:30 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 100/1251] eta: 0:12:48 lr: 0.000643 loss: 3.6126 (3.3537) grad_norm: 1.3160 (1.3841) time: 0.6373 [2021-03-27 02:17:37 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 110/1251] eta: 0:12:37 lr: 0.000643 loss: 3.5663 (3.3619) grad_norm: 1.3314 (1.3926) time: 0.6275 [2021-03-27 02:17:43 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 120/1251] eta: 0:12:27 lr: 0.000643 loss: 3.5387 (3.3594) grad_norm: 1.3581 (1.3886) time: 0.6288 [2021-03-27 02:17:49 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 130/1251] eta: 0:12:18 lr: 0.000643 loss: 3.3340 (3.3626) grad_norm: 1.2632 (1.3813) time: 0.6305 [2021-03-27 02:17:56 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 140/1251] eta: 0:12:10 lr: 0.000643 loss: 3.6363 (3.3679) grad_norm: 1.2563 (1.3732) time: 0.6317 [2021-03-27 02:18:02 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 150/1251] eta: 0:12:01 lr: 0.000643 loss: 3.6633 (3.3766) grad_norm: 1.2257 (1.3691) time: 0.6311 [2021-03-27 02:18:08 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 160/1251] eta: 0:11:52 lr: 0.000642 loss: 3.4770 (3.3739) grad_norm: 1.2513 (1.3624) time: 0.6265 [2021-03-27 02:18:14 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 170/1251] eta: 0:11:44 lr: 0.000642 loss: 3.5897 (3.3913) grad_norm: 1.2776 (1.3614) time: 0.6261 [2021-03-27 02:18:21 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 180/1251] eta: 0:11:37 lr: 0.000642 loss: 3.6079 (3.4026) grad_norm: 1.3216 (1.3636) time: 0.6317 [2021-03-27 02:18:27 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 190/1251] eta: 0:11:29 lr: 0.000642 loss: 3.5664 (3.4053) grad_norm: 1.3794 (1.3663) time: 0.6297 [2021-03-27 02:18:33 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 200/1251] eta: 0:11:21 lr: 0.000642 loss: 3.5286 (3.4041) grad_norm: 1.3943 (1.3665) time: 0.6287 [2021-03-27 02:18:40 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 210/1251] eta: 0:11:14 lr: 0.000642 loss: 3.5286 (3.4071) grad_norm: 1.3495 (1.3683) time: 0.6332 [2021-03-27 02:18:46 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 220/1251] eta: 0:11:07 lr: 0.000642 loss: 3.6418 (3.4176) grad_norm: 1.3328 (1.3668) time: 0.6316 [2021-03-27 02:18:52 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 230/1251] eta: 0:10:59 lr: 0.000642 loss: 3.6786 (3.4116) grad_norm: 1.3313 (1.3645) time: 0.6263 [2021-03-27 02:18:59 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 240/1251] eta: 0:10:52 lr: 0.000642 loss: 3.3067 (3.4056) grad_norm: 1.3105 (1.3639) time: 0.6283 [2021-03-27 02:19:05 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 250/1251] eta: 0:10:45 lr: 0.000642 loss: 3.3628 (3.3953) grad_norm: 1.3105 (1.3605) time: 0.6352 [2021-03-27 02:19:11 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 260/1251] eta: 0:10:39 lr: 0.000642 loss: 3.3628 (3.3921) grad_norm: 1.3077 (1.3606) time: 0.6430 [2021-03-27 02:19:18 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 270/1251] eta: 0:10:32 lr: 0.000642 loss: 3.4260 (3.3936) grad_norm: 1.2699 (1.3581) time: 0.6414 [2021-03-27 02:19:24 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 280/1251] eta: 0:10:25 lr: 0.000642 loss: 3.3364 (3.3836) grad_norm: 1.4119 (1.3651) time: 0.6273 [2021-03-27 02:19:30 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 290/1251] eta: 0:10:18 lr: 0.000642 loss: 3.1618 (3.3807) grad_norm: 1.4850 (1.3686) time: 0.6221 [2021-03-27 02:19:36 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 300/1251] eta: 0:10:11 lr: 0.000642 loss: 3.0996 (3.3706) grad_norm: 1.4280 (1.3684) time: 0.6213 [2021-03-27 02:19:43 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 310/1251] eta: 0:10:04 lr: 0.000642 loss: 3.5298 (3.3829) grad_norm: 1.2949 (1.3675) time: 0.6210 [2021-03-27 02:19:49 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 320/1251] eta: 0:09:57 lr: 0.000642 loss: 3.5941 (3.3796) grad_norm: 1.3345 (1.3676) time: 0.6232 [2021-03-27 02:19:55 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 330/1251] eta: 0:09:50 lr: 0.000642 loss: 3.5616 (3.3863) grad_norm: 1.3434 (1.3669) time: 0.6307 [2021-03-27 02:20:02 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 340/1251] eta: 0:09:43 lr: 0.000642 loss: 3.6054 (3.3950) grad_norm: 1.3939 (1.3697) time: 0.6302 [2021-03-27 02:20:08 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 350/1251] eta: 0:09:36 lr: 0.000642 loss: 3.6404 (3.3961) grad_norm: 1.3987 (1.3692) time: 0.6269 [2021-03-27 02:20:14 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 360/1251] eta: 0:09:30 lr: 0.000642 loss: 3.5339 (3.3947) grad_norm: 1.3413 (1.3701) time: 0.6280 [2021-03-27 02:20:20 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 370/1251] eta: 0:09:23 lr: 0.000642 loss: 3.5109 (3.3983) grad_norm: 1.3413 (1.3693) time: 0.6295 [2021-03-27 02:20:27 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 380/1251] eta: 0:09:17 lr: 0.000642 loss: 3.4519 (3.3973) grad_norm: 1.3567 (1.3720) time: 0.6308 [2021-03-27 02:20:33 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 390/1251] eta: 0:09:10 lr: 0.000642 loss: 3.3613 (3.3895) grad_norm: 1.4033 (1.3717) time: 0.6339 [2021-03-27 02:20:39 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 400/1251] eta: 0:09:04 lr: 0.000642 loss: 3.3967 (3.3974) grad_norm: 1.3678 (1.3714) time: 0.6340 [2021-03-27 02:20:46 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 410/1251] eta: 0:08:57 lr: 0.000641 loss: 3.7034 (3.4016) grad_norm: 1.3167 (1.3701) time: 0.6284 [2021-03-27 02:20:52 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 420/1251] eta: 0:08:50 lr: 0.000641 loss: 3.6369 (3.4067) grad_norm: 1.2916 (1.3676) time: 0.6266 [2021-03-27 02:20:58 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 430/1251] eta: 0:08:44 lr: 0.000641 loss: 3.6062 (3.4003) grad_norm: 1.3299 (1.3697) time: 0.6258 [2021-03-27 02:21:05 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 440/1251] eta: 0:08:37 lr: 0.000641 loss: 3.5761 (3.3993) grad_norm: 1.3555 (1.3688) time: 0.6322 [2021-03-27 02:21:11 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 450/1251] eta: 0:08:31 lr: 0.000641 loss: 3.5445 (3.3997) grad_norm: 1.2952 (1.3682) time: 0.6361 [2021-03-27 02:21:17 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 460/1251] eta: 0:08:24 lr: 0.000641 loss: 3.4932 (3.3993) grad_norm: 1.3364 (1.3702) time: 0.6324 [2021-03-27 02:21:24 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 470/1251] eta: 0:08:18 lr: 0.000641 loss: 3.4932 (3.3995) grad_norm: 1.3424 (1.3697) time: 0.6368 [2021-03-27 02:21:30 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 480/1251] eta: 0:08:11 lr: 0.000641 loss: 3.5814 (3.3936) grad_norm: 1.3343 (1.3711) time: 0.6344 [2021-03-27 02:21:36 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 490/1251] eta: 0:08:05 lr: 0.000641 loss: 3.5235 (3.3921) grad_norm: 1.4208 (1.3736) time: 0.6299 [2021-03-27 02:21:43 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 500/1251] eta: 0:07:58 lr: 0.000641 loss: 3.5977 (3.3973) grad_norm: 1.3729 (1.3730) time: 0.6300 [2021-03-27 02:21:49 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 510/1251] eta: 0:07:52 lr: 0.000641 loss: 3.5809 (3.4002) grad_norm: 1.2996 (1.3736) time: 0.6245 [2021-03-27 02:21:55 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 520/1251] eta: 0:07:45 lr: 0.000641 loss: 3.3518 (3.3958) grad_norm: 1.4287 (1.3747) time: 0.6209 [2021-03-27 02:22:01 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 530/1251] eta: 0:07:39 lr: 0.000641 loss: 3.4553 (3.3989) grad_norm: 1.3852 (1.3761) time: 0.6247 [2021-03-27 02:22:07 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 540/1251] eta: 0:07:32 lr: 0.000641 loss: 3.6823 (3.3994) grad_norm: 1.3852 (1.3763) time: 0.6248 [2021-03-27 02:22:14 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 550/1251] eta: 0:07:26 lr: 0.000641 loss: 3.7259 (3.4037) grad_norm: 1.3581 (1.3757) time: 0.6270 [2021-03-27 02:22:20 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 560/1251] eta: 0:07:19 lr: 0.000641 loss: 3.5199 (3.4039) grad_norm: 1.3279 (1.3761) time: 0.6327 [2021-03-27 02:22:26 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 570/1251] eta: 0:07:13 lr: 0.000641 loss: 3.4550 (3.4061) grad_norm: 1.4087 (1.3766) time: 0.6295 [2021-03-27 02:22:33 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 580/1251] eta: 0:07:06 lr: 0.000641 loss: 3.5444 (3.4083) grad_norm: 1.3885 (1.3773) time: 0.6307 [2021-03-27 02:22:39 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 590/1251] eta: 0:07:00 lr: 0.000641 loss: 3.4256 (3.4068) grad_norm: 1.3357 (1.3772) time: 0.6359 [2021-03-27 02:22:45 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 600/1251] eta: 0:06:54 lr: 0.000641 loss: 3.3957 (3.4100) grad_norm: 1.3705 (1.3777) time: 0.6361 [2021-03-27 02:22:52 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 610/1251] eta: 0:06:47 lr: 0.000641 loss: 3.3649 (3.4067) grad_norm: 1.3705 (1.3782) time: 0.6284 [2021-03-27 02:22:58 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 620/1251] eta: 0:06:41 lr: 0.000641 loss: 3.3649 (3.4103) grad_norm: 1.3392 (1.3787) time: 0.6237 [2021-03-27 02:23:04 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 630/1251] eta: 0:06:34 lr: 0.000641 loss: 3.5124 (3.4087) grad_norm: 1.3785 (1.3791) time: 0.6250 [2021-03-27 02:23:10 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 640/1251] eta: 0:06:28 lr: 0.000641 loss: 3.6272 (3.4117) grad_norm: 1.3181 (1.3775) time: 0.6250 [2021-03-27 02:23:17 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 650/1251] eta: 0:06:21 lr: 0.000641 loss: 3.5844 (3.4143) grad_norm: 1.3181 (1.3777) time: 0.6238 [2021-03-27 02:23:23 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 660/1251] eta: 0:06:15 lr: 0.000640 loss: 3.5263 (3.4155) grad_norm: 1.3335 (1.3774) time: 0.6214 [2021-03-27 02:23:29 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 670/1251] eta: 0:06:08 lr: 0.000640 loss: 3.4545 (3.4142) grad_norm: 1.3335 (1.3776) time: 0.6215 [2021-03-27 02:23:35 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 680/1251] eta: 0:06:02 lr: 0.000640 loss: 3.6058 (3.4155) grad_norm: 1.3570 (1.3763) time: 0.6290 [2021-03-27 02:23:42 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 690/1251] eta: 0:05:56 lr: 0.000640 loss: 3.4813 (3.4132) grad_norm: 1.3395 (1.3762) time: 0.6299 [2021-03-27 02:23:48 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 700/1251] eta: 0:05:49 lr: 0.000640 loss: 3.4108 (3.4135) grad_norm: 1.3085 (1.3760) time: 0.6291 [2021-03-27 02:23:54 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 710/1251] eta: 0:05:43 lr: 0.000640 loss: 3.4990 (3.4130) grad_norm: 1.2344 (1.3747) time: 0.6299 [2021-03-27 02:24:01 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 720/1251] eta: 0:05:36 lr: 0.000640 loss: 3.4990 (3.4135) grad_norm: 1.2618 (1.3737) time: 0.6231 [2021-03-27 02:24:07 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 730/1251] eta: 0:05:30 lr: 0.000640 loss: 3.5323 (3.4142) grad_norm: 1.2719 (1.3730) time: 0.6274 [2021-03-27 02:24:13 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 740/1251] eta: 0:05:24 lr: 0.000640 loss: 3.4921 (3.4120) grad_norm: 1.3607 (1.3734) time: 0.6356 [2021-03-27 02:24:20 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 750/1251] eta: 0:05:17 lr: 0.000640 loss: 3.4114 (3.4137) grad_norm: 1.4569 (1.3745) time: 0.6374 [2021-03-27 02:24:26 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 760/1251] eta: 0:05:11 lr: 0.000640 loss: 3.5382 (3.4152) grad_norm: 1.4569 (1.3742) time: 0.6298 [2021-03-27 02:24:32 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 770/1251] eta: 0:05:05 lr: 0.000640 loss: 3.4825 (3.4142) grad_norm: 1.3825 (1.3756) time: 0.6221 [2021-03-27 02:24:39 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 780/1251] eta: 0:04:58 lr: 0.000640 loss: 3.4825 (3.4147) grad_norm: 1.3815 (1.3752) time: 0.6336 [2021-03-27 02:24:45 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 790/1251] eta: 0:04:52 lr: 0.000640 loss: 3.5107 (3.4147) grad_norm: 1.2724 (1.3747) time: 0.6389 [2021-03-27 02:24:51 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 800/1251] eta: 0:04:46 lr: 0.000640 loss: 3.4854 (3.4145) grad_norm: 1.2316 (1.3730) time: 0.6345 [2021-03-27 02:24:58 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 810/1251] eta: 0:04:39 lr: 0.000640 loss: 3.6277 (3.4158) grad_norm: 1.2429 (1.3718) time: 0.6344 [2021-03-27 02:25:04 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 820/1251] eta: 0:04:33 lr: 0.000640 loss: 3.6277 (3.4161) grad_norm: 1.2446 (1.3708) time: 0.6335 [2021-03-27 02:25:10 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 830/1251] eta: 0:04:26 lr: 0.000640 loss: 3.3790 (3.4148) grad_norm: 1.3293 (1.3716) time: 0.6284 [2021-03-27 02:25:16 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 840/1251] eta: 0:04:20 lr: 0.000640 loss: 3.3790 (3.4155) grad_norm: 1.3997 (1.3735) time: 0.6232 [2021-03-27 02:25:23 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 850/1251] eta: 0:04:14 lr: 0.000640 loss: 3.4781 (3.4158) grad_norm: 1.3777 (1.3729) time: 0.6254 [2021-03-27 02:25:29 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 860/1251] eta: 0:04:07 lr: 0.000640 loss: 3.4241 (3.4150) grad_norm: 1.2085 (1.3711) time: 0.6239 [2021-03-27 02:25:35 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 870/1251] eta: 0:04:01 lr: 0.000640 loss: 3.5310 (3.4153) grad_norm: 1.2085 (1.3697) time: 0.6210 [2021-03-27 02:25:41 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 880/1251] eta: 0:03:55 lr: 0.000640 loss: 3.5256 (3.4140) grad_norm: 1.3281 (1.3704) time: 0.6235 [2021-03-27 02:25:48 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 890/1251] eta: 0:03:48 lr: 0.000640 loss: 3.4817 (3.4137) grad_norm: 1.3371 (1.3709) time: 0.6261 [2021-03-27 02:25:54 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 900/1251] eta: 0:03:42 lr: 0.000640 loss: 3.4691 (3.4115) grad_norm: 1.3371 (1.3711) time: 0.6267 [2021-03-27 02:26:00 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 910/1251] eta: 0:03:35 lr: 0.000639 loss: 3.4691 (3.4120) grad_norm: 1.3963 (1.3713) time: 0.6249 [2021-03-27 02:26:06 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 920/1251] eta: 0:03:29 lr: 0.000639 loss: 3.3904 (3.4088) grad_norm: 1.2874 (1.3706) time: 0.6226 [2021-03-27 02:26:13 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 930/1251] eta: 0:03:23 lr: 0.000639 loss: 3.1347 (3.4079) grad_norm: 1.2918 (1.3699) time: 0.6281 [2021-03-27 02:26:19 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 940/1251] eta: 0:03:16 lr: 0.000639 loss: 3.4940 (3.4090) grad_norm: 1.3320 (1.3703) time: 0.6319 [2021-03-27 02:26:25 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 950/1251] eta: 0:03:10 lr: 0.000639 loss: 3.5104 (3.4112) grad_norm: 1.3244 (1.3704) time: 0.6298 [2021-03-27 02:26:31 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 960/1251] eta: 0:03:04 lr: 0.000639 loss: 3.6208 (3.4124) grad_norm: 1.3401 (1.3707) time: 0.6244 [2021-03-27 02:26:38 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 970/1251] eta: 0:02:57 lr: 0.000639 loss: 3.5325 (3.4132) grad_norm: 1.3537 (1.3705) time: 0.6255 [2021-03-27 02:26:44 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 980/1251] eta: 0:02:51 lr: 0.000639 loss: 3.4700 (3.4140) grad_norm: 1.2727 (1.3692) time: 0.6301 [2021-03-27 02:26:50 swin_base_patch4_window7_224] INFO: Epoch: [123] [ 990/1251] eta: 0:02:45 lr: 0.000639 loss: 3.2358 (3.4131) grad_norm: 1.2368 (1.3687) time: 0.6250 [2021-03-27 02:26:57 swin_base_patch4_window7_224] INFO: Epoch: [123] [1000/1251] eta: 0:02:38 lr: 0.000639 loss: 3.4174 (3.4134) grad_norm: 1.3132 (1.3687) time: 0.6287 [2021-03-27 02:27:03 swin_base_patch4_window7_224] INFO: Epoch: [123] [1010/1251] eta: 0:02:32 lr: 0.000639 loss: 3.4984 (3.4128) grad_norm: 1.2807 (1.3677) time: 0.6308 [2021-03-27 02:27:09 swin_base_patch4_window7_224] INFO: Epoch: [123] [1020/1251] eta: 0:02:26 lr: 0.000639 loss: 3.4805 (3.4119) grad_norm: 1.2807 (1.3678) time: 0.6288 [2021-03-27 02:27:15 swin_base_patch4_window7_224] INFO: Epoch: [123] [1030/1251] eta: 0:02:19 lr: 0.000639 loss: 3.4051 (3.4110) grad_norm: 1.3070 (1.3672) time: 0.6299 [2021-03-27 02:27:22 swin_base_patch4_window7_224] INFO: Epoch: [123] [1040/1251] eta: 0:02:13 lr: 0.000639 loss: 3.4456 (3.4106) grad_norm: 1.3241 (1.3684) time: 0.6235 [2021-03-27 02:27:28 swin_base_patch4_window7_224] INFO: Epoch: [123] [1050/1251] eta: 0:02:07 lr: 0.000639 loss: 3.4507 (3.4113) grad_norm: 1.3806 (1.3687) time: 0.6253 [2021-03-27 02:27:34 swin_base_patch4_window7_224] INFO: Epoch: [123] [1060/1251] eta: 0:02:00 lr: 0.000639 loss: 3.6031 (3.4145) grad_norm: 1.2998 (1.3684) time: 0.6357 [2021-03-27 02:27:41 swin_base_patch4_window7_224] INFO: Epoch: [123] [1070/1251] eta: 0:01:54 lr: 0.000639 loss: 3.5393 (3.4135) grad_norm: 1.3123 (1.3688) time: 0.6355 [2021-03-27 02:27:47 swin_base_patch4_window7_224] INFO: Epoch: [123] [1080/1251] eta: 0:01:48 lr: 0.000639 loss: 3.5393 (3.4160) grad_norm: 1.3218 (1.3683) time: 0.6262 [2021-03-27 02:27:53 swin_base_patch4_window7_224] INFO: Epoch: [123] [1090/1251] eta: 0:01:41 lr: 0.000639 loss: 3.5863 (3.4142) grad_norm: 1.3469 (1.3697) time: 0.6233 [2021-03-27 02:27:59 swin_base_patch4_window7_224] INFO: Epoch: [123] [1100/1251] eta: 0:01:35 lr: 0.000639 loss: 3.4247 (3.4133) grad_norm: 1.3087 (1.3689) time: 0.6237 [2021-03-27 02:28:06 swin_base_patch4_window7_224] INFO: Epoch: [123] [1110/1251] eta: 0:01:29 lr: 0.000639 loss: 3.0747 (3.4107) grad_norm: 1.2356 (1.3687) time: 0.6212 [2021-03-27 02:28:12 swin_base_patch4_window7_224] INFO: Epoch: [123] [1120/1251] eta: 0:01:22 lr: 0.000639 loss: 3.3128 (3.4103) grad_norm: 1.3734 (1.3688) time: 0.6273 [2021-03-27 02:28:18 swin_base_patch4_window7_224] INFO: Epoch: [123] [1130/1251] eta: 0:01:16 lr: 0.000639 loss: 3.3612 (3.4110) grad_norm: 1.3219 (1.3685) time: 0.6316 [2021-03-27 02:28:24 swin_base_patch4_window7_224] INFO: Epoch: [123] [1140/1251] eta: 0:01:10 lr: 0.000639 loss: 3.6024 (3.4105) grad_norm: 1.2863 (1.3678) time: 0.6272 [2021-03-27 02:28:31 swin_base_patch4_window7_224] INFO: Epoch: [123] [1150/1251] eta: 0:01:03 lr: 0.000639 loss: 3.6325 (3.4116) grad_norm: 1.2384 (1.3667) time: 0.6254 [2021-03-27 02:28:37 swin_base_patch4_window7_224] INFO: Epoch: [123] [1160/1251] eta: 0:00:57 lr: 0.000638 loss: 3.6899 (3.4134) grad_norm: 1.2320 (1.3660) time: 0.6296 [2021-03-27 02:28:43 swin_base_patch4_window7_224] INFO: Epoch: [123] [1170/1251] eta: 0:00:51 lr: 0.000638 loss: 3.6104 (3.4132) grad_norm: 1.2732 (1.3662) time: 0.6274 [2021-03-27 02:28:50 swin_base_patch4_window7_224] INFO: Epoch: [123] [1180/1251] eta: 0:00:44 lr: 0.000638 loss: 3.5408 (3.4134) grad_norm: 1.3739 (1.3665) time: 0.6243 [2021-03-27 02:28:56 swin_base_patch4_window7_224] INFO: Epoch: [123] [1190/1251] eta: 0:00:38 lr: 0.000638 loss: 3.5901 (3.4143) grad_norm: 1.3739 (1.3674) time: 0.6302 [2021-03-27 02:29:02 swin_base_patch4_window7_224] INFO: Epoch: [123] [1200/1251] eta: 0:00:32 lr: 0.000638 loss: 3.5759 (3.4137) grad_norm: 1.2841 (1.3667) time: 0.6324 [2021-03-27 02:29:09 swin_base_patch4_window7_224] INFO: Epoch: [123] [1210/1251] eta: 0:00:25 lr: 0.000638 loss: 3.4216 (3.4113) grad_norm: 1.2445 (1.3661) time: 0.6307 [2021-03-27 02:29:15 swin_base_patch4_window7_224] INFO: Epoch: [123] [1220/1251] eta: 0:00:19 lr: 0.000638 loss: 3.4047 (3.4103) grad_norm: 1.2566 (1.3659) time: 0.6317 [2021-03-27 02:29:21 swin_base_patch4_window7_224] INFO: Epoch: [123] [1230/1251] eta: 0:00:13 lr: 0.000638 loss: 3.4047 (3.4100) grad_norm: 1.2820 (1.3656) time: 0.6285 [2021-03-27 02:29:27 swin_base_patch4_window7_224] INFO: Epoch: [123] [1240/1251] eta: 0:00:06 lr: 0.000638 loss: 3.3178 (3.4088) grad_norm: 1.3421 (1.3656) time: 0.6229 [2021-03-27 02:29:33 swin_base_patch4_window7_224] INFO: Epoch: [123] [1250/1251] eta: 0:00:00 lr: 0.000638 loss: 3.3809 (3.4103) grad_norm: 1.2350 (1.3642) time: 0.6161 [2021-03-27 02:29:41 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:54 loss: 0.9354 (0.9354) acc1: 73.4375 (73.4375) acc5: 95.3125 (95.3125) [2021-03-27 02:29:43 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9776 (0.9853) acc1: 78.1250 (77.5568) acc5: 95.3125 (94.0341) [2021-03-27 02:29:46 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9810 (0.9836) acc1: 78.1250 (77.9018) acc5: 93.7500 (93.8988) [2021-03-27 02:29:48 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9803 (0.9582) acc1: 78.1250 (78.4778) acc5: 95.3125 (94.3548) [2021-03-27 02:29:50 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9222 (0.9569) acc1: 79.6875 (78.3537) acc5: 95.3125 (94.2454) [2021-03-27 02:29:51 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9383 (0.9589) acc1: 79.6875 (78.0800) acc5: 93.7500 (94.4000) [2021-03-27 02:29:58 swin_base_patch4_window7_224] INFO: * Acc@1 77.720 Acc@5 94.260 loss 0.954 [2021-03-27 02:29:58 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.7% [2021-03-27 02:29:58 swin_base_patch4_window7_224] INFO: Max accuracy: 77.80% [2021-03-27 02:30:02 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 0/1251] eta: 1:28:38 lr: 0.000638 loss: 3.6431 (3.6431) grad_norm: 1.2224 (1.2224) time: 4.2512 [2021-03-27 02:30:09 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 10/1251] eta: 0:19:55 lr: 0.000638 loss: 3.6060 (3.3186) grad_norm: 1.2556 (1.2350) time: 0.9634 [2021-03-27 02:30:15 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 20/1251] eta: 0:16:28 lr: 0.000638 loss: 3.4648 (3.2991) grad_norm: 1.2624 (1.2859) time: 0.6303 [2021-03-27 02:30:21 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 30/1251] eta: 0:15:13 lr: 0.000638 loss: 3.4935 (3.3921) grad_norm: 1.3342 (1.3138) time: 0.6294 [2021-03-27 02:30:27 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 40/1251] eta: 0:14:31 lr: 0.000638 loss: 3.7572 (3.4139) grad_norm: 1.3505 (1.3227) time: 0.6329 [2021-03-27 02:30:34 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 50/1251] eta: 0:14:03 lr: 0.000638 loss: 3.5869 (3.3946) grad_norm: 1.3166 (1.3236) time: 0.6316 [2021-03-27 02:30:40 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 60/1251] eta: 0:13:45 lr: 0.000638 loss: 3.5654 (3.4286) grad_norm: 1.3111 (1.3246) time: 0.6382 [2021-03-27 02:30:46 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 70/1251] eta: 0:13:26 lr: 0.000638 loss: 3.5174 (3.4087) grad_norm: 1.3103 (1.3268) time: 0.6322 [2021-03-27 02:30:53 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 80/1251] eta: 0:13:13 lr: 0.000638 loss: 3.2587 (3.3906) grad_norm: 1.3479 (1.3300) time: 0.6291 [2021-03-27 02:30:59 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 90/1251] eta: 0:12:59 lr: 0.000638 loss: 3.1915 (3.3453) grad_norm: 1.2381 (1.3240) time: 0.6306 [2021-03-27 02:31:05 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 100/1251] eta: 0:12:48 lr: 0.000638 loss: 3.2693 (3.3549) grad_norm: 1.2355 (1.3172) time: 0.6269 [2021-03-27 02:31:12 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 110/1251] eta: 0:12:38 lr: 0.000638 loss: 3.4391 (3.3622) grad_norm: 1.2131 (1.3131) time: 0.6341 [2021-03-27 02:31:18 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 120/1251] eta: 0:12:28 lr: 0.000638 loss: 3.5597 (3.3699) grad_norm: 1.2131 (1.3088) time: 0.6351 [2021-03-27 02:31:24 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 130/1251] eta: 0:12:19 lr: 0.000638 loss: 3.6200 (3.3860) grad_norm: 1.2357 (1.3102) time: 0.6316 [2021-03-27 02:31:31 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 140/1251] eta: 0:12:10 lr: 0.000638 loss: 3.3151 (3.3612) grad_norm: 1.3189 (1.3088) time: 0.6303 [2021-03-27 02:31:37 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 150/1251] eta: 0:12:02 lr: 0.000638 loss: 3.2399 (3.3563) grad_norm: 1.3206 (1.3167) time: 0.6333 [2021-03-27 02:31:43 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 160/1251] eta: 0:11:53 lr: 0.000637 loss: 3.3703 (3.3471) grad_norm: 1.2912 (1.3116) time: 0.6311 [2021-03-27 02:31:50 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 170/1251] eta: 0:11:45 lr: 0.000637 loss: 3.3703 (3.3448) grad_norm: 1.2434 (1.3171) time: 0.6258 [2021-03-27 02:31:56 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 180/1251] eta: 0:11:37 lr: 0.000637 loss: 3.3856 (3.3440) grad_norm: 1.3319 (1.3205) time: 0.6306 [2021-03-27 02:32:02 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 190/1251] eta: 0:11:29 lr: 0.000637 loss: 3.3909 (3.3485) grad_norm: 1.3219 (1.3216) time: 0.6295 [2021-03-27 02:32:08 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 200/1251] eta: 0:11:21 lr: 0.000637 loss: 3.4496 (3.3521) grad_norm: 1.3090 (1.3221) time: 0.6244 [2021-03-27 02:32:15 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 210/1251] eta: 0:11:14 lr: 0.000637 loss: 3.4903 (3.3557) grad_norm: 1.1717 (1.3161) time: 0.6252 [2021-03-27 02:32:21 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 220/1251] eta: 0:11:06 lr: 0.000637 loss: 3.4903 (3.3589) grad_norm: 1.2979 (1.3293) time: 0.6217 [2021-03-27 02:32:27 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 230/1251] eta: 0:10:59 lr: 0.000637 loss: 3.4125 (3.3599) grad_norm: 1.3149 (1.3325) time: 0.6226 [2021-03-27 02:32:33 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 240/1251] eta: 0:10:51 lr: 0.000637 loss: 3.5648 (3.3783) grad_norm: 1.3131 (1.3356) time: 0.6243 [2021-03-27 02:32:40 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 250/1251] eta: 0:10:44 lr: 0.000637 loss: 3.6894 (3.3803) grad_norm: 1.2304 (1.3312) time: 0.6253 [2021-03-27 02:32:46 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 260/1251] eta: 0:10:37 lr: 0.000637 loss: 3.3208 (3.3737) grad_norm: 1.2725 (1.3330) time: 0.6289 [2021-03-27 02:32:52 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 270/1251] eta: 0:10:31 lr: 0.000637 loss: 3.3691 (3.3786) grad_norm: 1.3938 (1.3372) time: 0.6350 [2021-03-27 02:32:59 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 280/1251] eta: 0:10:24 lr: 0.000637 loss: 3.3168 (3.3705) grad_norm: 1.3938 (1.3377) time: 0.6397 [2021-03-27 02:33:05 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 290/1251] eta: 0:10:17 lr: 0.000637 loss: 3.2092 (3.3729) grad_norm: 1.3552 (1.3402) time: 0.6386 [2021-03-27 02:33:11 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 300/1251] eta: 0:10:11 lr: 0.000637 loss: 3.4090 (3.3722) grad_norm: 1.3177 (1.3398) time: 0.6358 [2021-03-27 02:33:18 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 310/1251] eta: 0:10:04 lr: 0.000637 loss: 3.4167 (3.3747) grad_norm: 1.2683 (1.3405) time: 0.6334 [2021-03-27 02:33:24 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 320/1251] eta: 0:09:57 lr: 0.000637 loss: 3.4567 (3.3738) grad_norm: 1.2450 (1.3371) time: 0.6304 [2021-03-27 02:33:30 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 330/1251] eta: 0:09:50 lr: 0.000637 loss: 3.5181 (3.3796) grad_norm: 1.2450 (1.3360) time: 0.6266 [2021-03-27 02:33:37 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 340/1251] eta: 0:09:43 lr: 0.000637 loss: 3.6522 (3.3842) grad_norm: 1.3168 (1.3365) time: 0.6255 [2021-03-27 02:33:43 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 350/1251] eta: 0:09:37 lr: 0.000637 loss: 3.6522 (3.3903) grad_norm: 1.3139 (1.3371) time: 0.6267 [2021-03-27 02:33:49 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 360/1251] eta: 0:09:30 lr: 0.000637 loss: 3.4155 (3.3902) grad_norm: 1.2895 (1.3359) time: 0.6346 [2021-03-27 02:33:55 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 370/1251] eta: 0:09:23 lr: 0.000637 loss: 3.4414 (3.3952) grad_norm: 1.2595 (1.3343) time: 0.6330 [2021-03-27 02:34:02 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 380/1251] eta: 0:09:17 lr: 0.000637 loss: 3.4894 (3.3958) grad_norm: 1.2754 (1.3350) time: 0.6284 [2021-03-27 02:34:08 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 390/1251] eta: 0:09:10 lr: 0.000637 loss: 3.4196 (3.3979) grad_norm: 1.3368 (1.3390) time: 0.6331 [2021-03-27 02:34:14 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 400/1251] eta: 0:09:04 lr: 0.000637 loss: 3.3949 (3.3930) grad_norm: 1.3368 (1.3408) time: 0.6312 [2021-03-27 02:34:21 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 410/1251] eta: 0:08:57 lr: 0.000636 loss: 3.4431 (3.3922) grad_norm: 1.3564 (1.3427) time: 0.6325 [2021-03-27 02:34:27 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 420/1251] eta: 0:08:50 lr: 0.000636 loss: 3.5046 (3.3953) grad_norm: 1.3146 (1.3421) time: 0.6280 [2021-03-27 02:34:33 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 430/1251] eta: 0:08:44 lr: 0.000636 loss: 3.5485 (3.3977) grad_norm: 1.2985 (1.3423) time: 0.6224 [2021-03-27 02:34:40 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 440/1251] eta: 0:08:37 lr: 0.000636 loss: 3.4751 (3.3995) grad_norm: 1.3285 (1.3425) time: 0.6245 [2021-03-27 02:34:46 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 450/1251] eta: 0:08:31 lr: 0.000636 loss: 3.5642 (3.3988) grad_norm: 1.2955 (1.3421) time: 0.6248 [2021-03-27 02:34:52 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 460/1251] eta: 0:08:24 lr: 0.000636 loss: 3.5342 (3.3999) grad_norm: 1.3250 (1.3447) time: 0.6316 [2021-03-27 02:34:58 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 470/1251] eta: 0:08:18 lr: 0.000636 loss: 3.5321 (3.4023) grad_norm: 1.3483 (1.3443) time: 0.6365 [2021-03-27 02:35:05 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 480/1251] eta: 0:08:11 lr: 0.000636 loss: 3.4313 (3.4009) grad_norm: 1.2854 (1.3424) time: 0.6297 [2021-03-27 02:35:11 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 490/1251] eta: 0:08:05 lr: 0.000636 loss: 3.4075 (3.4053) grad_norm: 1.2611 (1.3416) time: 0.6316 [2021-03-27 02:35:18 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 500/1251] eta: 0:07:59 lr: 0.000636 loss: 3.4075 (3.4053) grad_norm: 1.2611 (1.3416) time: 0.6439 [2021-03-27 02:35:24 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 510/1251] eta: 0:07:52 lr: 0.000636 loss: 3.4664 (3.4046) grad_norm: 1.2721 (1.3411) time: 0.6404 [2021-03-27 02:35:30 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 520/1251] eta: 0:07:46 lr: 0.000636 loss: 3.4848 (3.4061) grad_norm: 1.3232 (1.3430) time: 0.6333 [2021-03-27 02:35:37 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 530/1251] eta: 0:07:39 lr: 0.000636 loss: 3.3804 (3.4069) grad_norm: 1.4479 (1.3454) time: 0.6298 [2021-03-27 02:35:43 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 540/1251] eta: 0:07:33 lr: 0.000636 loss: 3.3804 (3.4080) grad_norm: 1.3382 (1.3452) time: 0.6260 [2021-03-27 02:35:49 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 550/1251] eta: 0:07:26 lr: 0.000636 loss: 3.2264 (3.4051) grad_norm: 1.3227 (1.3469) time: 0.6340 [2021-03-27 02:35:56 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 560/1251] eta: 0:07:20 lr: 0.000636 loss: 3.4344 (3.4081) grad_norm: 1.4005 (nan) time: 0.6396 [2021-03-27 02:36:02 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 570/1251] eta: 0:07:14 lr: 0.000636 loss: 3.7347 (3.4113) grad_norm: 1.4015 (nan) time: 0.6367 [2021-03-27 02:36:08 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 580/1251] eta: 0:07:07 lr: 0.000636 loss: 3.5402 (3.4076) grad_norm: 1.2229 (nan) time: 0.6357 [2021-03-27 02:36:15 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 590/1251] eta: 0:07:01 lr: 0.000636 loss: 3.2581 (3.4065) grad_norm: 1.2929 (nan) time: 0.6404 [2021-03-27 02:36:21 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 600/1251] eta: 0:06:55 lr: 0.000636 loss: 3.5076 (3.4081) grad_norm: 1.3212 (nan) time: 0.6447 [2021-03-27 02:36:27 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 610/1251] eta: 0:06:48 lr: 0.000636 loss: 3.6367 (3.4125) grad_norm: 1.2652 (nan) time: 0.6317 [2021-03-27 02:36:34 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 620/1251] eta: 0:06:42 lr: 0.000636 loss: 3.5019 (3.4134) grad_norm: 1.2546 (nan) time: 0.6330 [2021-03-27 02:36:40 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 630/1251] eta: 0:06:35 lr: 0.000636 loss: 3.5446 (3.4118) grad_norm: 1.3375 (nan) time: 0.6347 [2021-03-27 02:36:46 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 640/1251] eta: 0:06:29 lr: 0.000636 loss: 3.2974 (3.4103) grad_norm: 1.3737 (nan) time: 0.6239 [2021-03-27 02:36:53 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 650/1251] eta: 0:06:22 lr: 0.000636 loss: 3.3905 (3.4124) grad_norm: 1.3093 (nan) time: 0.6234 [2021-03-27 02:36:59 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 660/1251] eta: 0:06:16 lr: 0.000635 loss: 3.4386 (3.4112) grad_norm: 1.3211 (nan) time: 0.6242 [2021-03-27 02:37:05 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 670/1251] eta: 0:06:09 lr: 0.000635 loss: 3.3917 (3.4107) grad_norm: 1.3880 (nan) time: 0.6338 [2021-03-27 02:37:12 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 680/1251] eta: 0:06:03 lr: 0.000635 loss: 3.6293 (3.4150) grad_norm: 1.3567 (nan) time: 0.6374 [2021-03-27 02:37:18 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 690/1251] eta: 0:05:57 lr: 0.000635 loss: 3.5410 (3.4099) grad_norm: 1.2797 (nan) time: 0.6310 [2021-03-27 02:37:24 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 700/1251] eta: 0:05:50 lr: 0.000635 loss: 3.1949 (3.4079) grad_norm: 1.3646 (nan) time: 0.6239 [2021-03-27 02:37:30 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 710/1251] eta: 0:05:44 lr: 0.000635 loss: 3.5685 (3.4110) grad_norm: 1.2994 (nan) time: 0.6288 [2021-03-27 02:37:37 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 720/1251] eta: 0:05:37 lr: 0.000635 loss: 3.4707 (3.4075) grad_norm: 1.3129 (nan) time: 0.6350 [2021-03-27 02:37:43 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 730/1251] eta: 0:05:31 lr: 0.000635 loss: 3.3083 (3.4066) grad_norm: 1.3704 (nan) time: 0.6280 [2021-03-27 02:37:49 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 740/1251] eta: 0:05:24 lr: 0.000635 loss: 3.4202 (3.4080) grad_norm: 1.3341 (nan) time: 0.6240 [2021-03-27 02:37:56 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 750/1251] eta: 0:05:18 lr: 0.000635 loss: 3.6974 (3.4099) grad_norm: 1.3341 (nan) time: 0.6345 [2021-03-27 02:38:02 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 760/1251] eta: 0:05:12 lr: 0.000635 loss: 3.7998 (3.4129) grad_norm: 1.3481 (nan) time: 0.6359 [2021-03-27 02:38:08 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 770/1251] eta: 0:05:05 lr: 0.000635 loss: 3.4899 (3.4110) grad_norm: 1.2961 (nan) time: 0.6295 [2021-03-27 02:38:15 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 780/1251] eta: 0:04:59 lr: 0.000635 loss: 3.2687 (3.4081) grad_norm: 1.2932 (nan) time: 0.6328 [2021-03-27 02:38:21 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 790/1251] eta: 0:04:53 lr: 0.000635 loss: 3.1028 (3.4056) grad_norm: 1.4048 (nan) time: 0.6345 [2021-03-27 02:38:27 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 800/1251] eta: 0:04:46 lr: 0.000635 loss: 3.4442 (3.4059) grad_norm: 1.4024 (nan) time: 0.6360 [2021-03-27 02:38:34 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 810/1251] eta: 0:04:40 lr: 0.000635 loss: 3.5179 (3.4080) grad_norm: 1.3219 (nan) time: 0.6336 [2021-03-27 02:38:40 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 820/1251] eta: 0:04:33 lr: 0.000635 loss: 3.5180 (3.4074) grad_norm: 1.2978 (nan) time: 0.6256 [2021-03-27 02:38:46 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 830/1251] eta: 0:04:27 lr: 0.000635 loss: 3.4350 (3.4053) grad_norm: 1.3618 (nan) time: 0.6229 [2021-03-27 02:38:52 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 840/1251] eta: 0:04:21 lr: 0.000635 loss: 3.3522 (3.4071) grad_norm: 1.2997 (nan) time: 0.6296 [2021-03-27 02:38:59 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 850/1251] eta: 0:04:14 lr: 0.000635 loss: 3.3522 (3.4028) grad_norm: 1.2926 (nan) time: 0.6286 [2021-03-27 02:39:05 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 860/1251] eta: 0:04:08 lr: 0.000635 loss: 3.0970 (3.4003) grad_norm: 1.2918 (nan) time: 0.6312 [2021-03-27 02:39:12 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 870/1251] eta: 0:04:02 lr: 0.000635 loss: 3.2846 (3.3983) grad_norm: 1.2116 (nan) time: 0.6417 [2021-03-27 02:39:18 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 880/1251] eta: 0:03:55 lr: 0.000635 loss: 3.7538 (3.4010) grad_norm: 1.2174 (nan) time: 0.6401 [2021-03-27 02:39:24 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 890/1251] eta: 0:03:49 lr: 0.000635 loss: 3.7270 (3.4034) grad_norm: 1.3239 (nan) time: 0.6313 [2021-03-27 02:39:30 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 900/1251] eta: 0:03:42 lr: 0.000635 loss: 3.5421 (3.4047) grad_norm: 1.3345 (nan) time: 0.6223 [2021-03-27 02:39:37 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 910/1251] eta: 0:03:36 lr: 0.000634 loss: 3.4832 (3.4064) grad_norm: 1.3807 (nan) time: 0.6203 [2021-03-27 02:39:43 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 920/1251] eta: 0:03:30 lr: 0.000634 loss: 3.3000 (3.4062) grad_norm: 1.3807 (nan) time: 0.6233 [2021-03-27 02:39:49 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 930/1251] eta: 0:03:23 lr: 0.000634 loss: 3.2938 (3.4040) grad_norm: 1.3272 (nan) time: 0.6253 [2021-03-27 02:39:55 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 940/1251] eta: 0:03:17 lr: 0.000634 loss: 3.5689 (3.4056) grad_norm: 1.2910 (nan) time: 0.6250 [2021-03-27 02:40:02 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 950/1251] eta: 0:03:11 lr: 0.000634 loss: 3.5274 (3.4060) grad_norm: 1.2637 (nan) time: 0.6235 [2021-03-27 02:40:08 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 960/1251] eta: 0:03:04 lr: 0.000634 loss: 3.4491 (3.4054) grad_norm: 1.2880 (nan) time: 0.6232 [2021-03-27 02:40:14 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 970/1251] eta: 0:02:58 lr: 0.000634 loss: 3.4484 (3.4047) grad_norm: 1.2999 (nan) time: 0.6321 [2021-03-27 02:40:21 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 980/1251] eta: 0:02:51 lr: 0.000634 loss: 3.3912 (3.4051) grad_norm: 1.3053 (nan) time: 0.6409 [2021-03-27 02:40:27 swin_base_patch4_window7_224] INFO: Epoch: [124] [ 990/1251] eta: 0:02:45 lr: 0.000634 loss: 3.5093 (3.4054) grad_norm: 1.3427 (nan) time: 0.6306 [2021-03-27 02:40:33 swin_base_patch4_window7_224] INFO: Epoch: [124] [1000/1251] eta: 0:02:39 lr: 0.000634 loss: 3.5093 (3.4056) grad_norm: 1.2955 (nan) time: 0.6263 [2021-03-27 02:40:40 swin_base_patch4_window7_224] INFO: Epoch: [124] [1010/1251] eta: 0:02:32 lr: 0.000634 loss: 3.4248 (3.4041) grad_norm: 1.3244 (nan) time: 0.6334 [2021-03-27 02:40:46 swin_base_patch4_window7_224] INFO: Epoch: [124] [1020/1251] eta: 0:02:26 lr: 0.000634 loss: 3.3452 (3.4038) grad_norm: 1.3973 (nan) time: 0.6350 [2021-03-27 02:40:52 swin_base_patch4_window7_224] INFO: Epoch: [124] [1030/1251] eta: 0:02:20 lr: 0.000634 loss: 3.4427 (3.4028) grad_norm: 1.4152 (nan) time: 0.6313 [2021-03-27 02:40:58 swin_base_patch4_window7_224] INFO: Epoch: [124] [1040/1251] eta: 0:02:13 lr: 0.000634 loss: 3.5128 (3.4034) grad_norm: 1.3888 (nan) time: 0.6254 [2021-03-27 02:41:05 swin_base_patch4_window7_224] INFO: Epoch: [124] [1050/1251] eta: 0:02:07 lr: 0.000634 loss: 3.5128 (3.4016) grad_norm: 1.3673 (nan) time: 0.6293 [2021-03-27 02:41:11 swin_base_patch4_window7_224] INFO: Epoch: [124] [1060/1251] eta: 0:02:01 lr: 0.000634 loss: 3.5291 (3.4037) grad_norm: 1.3675 (nan) time: 0.6360 [2021-03-27 02:41:17 swin_base_patch4_window7_224] INFO: Epoch: [124] [1070/1251] eta: 0:01:54 lr: 0.000634 loss: 3.6755 (3.4043) grad_norm: 1.3667 (nan) time: 0.6310 [2021-03-27 02:41:24 swin_base_patch4_window7_224] INFO: Epoch: [124] [1080/1251] eta: 0:01:48 lr: 0.000634 loss: 3.6986 (3.4077) grad_norm: 1.3281 (nan) time: 0.6217 [2021-03-27 02:41:30 swin_base_patch4_window7_224] INFO: Epoch: [124] [1090/1251] eta: 0:01:42 lr: 0.000634 loss: 3.4651 (3.4076) grad_norm: 1.3240 (nan) time: 0.6201 [2021-03-27 02:41:36 swin_base_patch4_window7_224] INFO: Epoch: [124] [1100/1251] eta: 0:01:35 lr: 0.000634 loss: 3.4080 (3.4084) grad_norm: 1.2702 (nan) time: 0.6237 [2021-03-27 02:41:42 swin_base_patch4_window7_224] INFO: Epoch: [124] [1110/1251] eta: 0:01:29 lr: 0.000634 loss: 3.4801 (3.4089) grad_norm: 1.2734 (nan) time: 0.6311 [2021-03-27 02:41:49 swin_base_patch4_window7_224] INFO: Epoch: [124] [1120/1251] eta: 0:01:23 lr: 0.000634 loss: 3.5845 (3.4094) grad_norm: 1.3122 (nan) time: 0.6365 [2021-03-27 02:41:55 swin_base_patch4_window7_224] INFO: Epoch: [124] [1130/1251] eta: 0:01:16 lr: 0.000634 loss: 3.5883 (3.4096) grad_norm: 1.3122 (nan) time: 0.6309 [2021-03-27 02:42:01 swin_base_patch4_window7_224] INFO: Epoch: [124] [1140/1251] eta: 0:01:10 lr: 0.000634 loss: 3.5883 (3.4109) grad_norm: 1.3345 (nan) time: 0.6288 [2021-03-27 02:42:08 swin_base_patch4_window7_224] INFO: Epoch: [124] [1150/1251] eta: 0:01:04 lr: 0.000634 loss: 3.6185 (3.4119) grad_norm: 1.3524 (nan) time: 0.6322 [2021-03-27 02:42:14 swin_base_patch4_window7_224] INFO: Epoch: [124] [1160/1251] eta: 0:00:57 lr: 0.000633 loss: 3.4887 (3.4114) grad_norm: 1.3240 (nan) time: 0.6285 [2021-03-27 02:42:20 swin_base_patch4_window7_224] INFO: Epoch: [124] [1170/1251] eta: 0:00:51 lr: 0.000633 loss: 3.5052 (3.4132) grad_norm: 1.3240 (nan) time: 0.6250 [2021-03-27 02:42:26 swin_base_patch4_window7_224] INFO: Epoch: [124] [1180/1251] eta: 0:00:44 lr: 0.000633 loss: 3.7447 (3.4163) grad_norm: 1.3446 (nan) time: 0.6220 [2021-03-27 02:42:33 swin_base_patch4_window7_224] INFO: Epoch: [124] [1190/1251] eta: 0:00:38 lr: 0.000633 loss: 3.6725 (3.4157) grad_norm: 1.3782 (nan) time: 0.6216 [2021-03-27 02:42:39 swin_base_patch4_window7_224] INFO: Epoch: [124] [1200/1251] eta: 0:00:32 lr: 0.000633 loss: 3.4227 (3.4153) grad_norm: 1.3782 (nan) time: 0.6347 [2021-03-27 02:42:45 swin_base_patch4_window7_224] INFO: Epoch: [124] [1210/1251] eta: 0:00:25 lr: 0.000633 loss: 3.6742 (3.4172) grad_norm: 1.3364 (nan) time: 0.6393 [2021-03-27 02:42:52 swin_base_patch4_window7_224] INFO: Epoch: [124] [1220/1251] eta: 0:00:19 lr: 0.000633 loss: 3.6565 (3.4161) grad_norm: 1.3018 (nan) time: 0.6320 [2021-03-27 02:42:58 swin_base_patch4_window7_224] INFO: Epoch: [124] [1230/1251] eta: 0:00:13 lr: 0.000633 loss: 3.2755 (3.4149) grad_norm: 1.2261 (nan) time: 0.6274 [2021-03-27 02:43:04 swin_base_patch4_window7_224] INFO: Epoch: [124] [1240/1251] eta: 0:00:06 lr: 0.000633 loss: 3.0713 (3.4141) grad_norm: 1.3019 (nan) time: 0.6211 [2021-03-27 02:43:10 swin_base_patch4_window7_224] INFO: Epoch: [124] [1250/1251] eta: 0:00:00 lr: 0.000633 loss: 3.0824 (3.4148) grad_norm: 1.3742 (nan) time: 0.6166 [2021-03-27 02:43:16 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:45 loss: 1.0140 (1.0140) acc1: 76.5625 (76.5625) acc5: 93.7500 (93.7500) [2021-03-27 02:43:18 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.0425 (1.0248) acc1: 76.5625 (76.4205) acc5: 93.7500 (93.4659) [2021-03-27 02:43:20 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9232 (0.9416) acc1: 79.6875 (78.0506) acc5: 93.7500 (94.3452) [2021-03-27 02:43:23 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8575 (0.9603) acc1: 79.6875 (77.5202) acc5: 93.7500 (94.1532) [2021-03-27 02:43:25 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9767 (0.9741) acc1: 71.8750 (76.7530) acc5: 93.7500 (93.9787) [2021-03-27 02:43:26 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9636 (0.9655) acc1: 73.4375 (76.9920) acc5: 93.7500 (94.0160) [2021-03-27 02:43:31 swin_base_patch4_window7_224] INFO: * Acc@1 77.828 Acc@5 94.314 loss 0.943 [2021-03-27 02:43:31 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.8% [2021-03-27 02:43:31 swin_base_patch4_window7_224] INFO: Max accuracy: 77.83% [2021-03-27 02:43:35 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 0/1251] eta: 1:29:13 lr: 0.000633 loss: 3.6264 (3.6264) grad_norm: 1.4108 (1.4108) time: 4.2792 [2021-03-27 02:43:42 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 10/1251] eta: 0:20:12 lr: 0.000633 loss: 3.5151 (3.2471) grad_norm: 1.3872 (1.4178) time: 0.9771 [2021-03-27 02:43:48 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 20/1251] eta: 0:16:39 lr: 0.000633 loss: 3.5645 (3.4240) grad_norm: 1.3676 (1.3758) time: 0.6389 [2021-03-27 02:43:54 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 30/1251] eta: 0:15:20 lr: 0.000633 loss: 3.5461 (3.3423) grad_norm: 1.3676 (1.4082) time: 0.6308 [2021-03-27 02:44:01 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 40/1251] eta: 0:14:34 lr: 0.000633 loss: 3.2220 (3.2931) grad_norm: 1.3566 (1.3900) time: 0.6283 [2021-03-27 02:44:07 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 50/1251] eta: 0:14:05 lr: 0.000633 loss: 3.4019 (3.3166) grad_norm: 1.2817 (1.3857) time: 0.6270 [2021-03-27 02:44:13 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 60/1251] eta: 0:13:43 lr: 0.000633 loss: 3.6623 (3.3553) grad_norm: 1.4095 (1.3886) time: 0.6281 [2021-03-27 02:44:19 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 70/1251] eta: 0:13:25 lr: 0.000633 loss: 3.5951 (3.3564) grad_norm: 1.4120 (1.3905) time: 0.6252 [2021-03-27 02:44:26 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 80/1251] eta: 0:13:10 lr: 0.000633 loss: 3.4811 (3.3395) grad_norm: 1.2534 (1.3793) time: 0.6241 [2021-03-27 02:44:32 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 90/1251] eta: 0:12:58 lr: 0.000633 loss: 3.1813 (3.3508) grad_norm: 1.2492 (1.3685) time: 0.6307 [2021-03-27 02:44:38 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 100/1251] eta: 0:12:47 lr: 0.000633 loss: 3.3008 (3.3471) grad_norm: 1.3431 (1.3783) time: 0.6321 [2021-03-27 02:44:45 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 110/1251] eta: 0:12:36 lr: 0.000633 loss: 3.3905 (3.3501) grad_norm: 1.4177 (1.3721) time: 0.6271 [2021-03-27 02:44:51 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 120/1251] eta: 0:12:26 lr: 0.000633 loss: 3.5616 (3.3810) grad_norm: 1.3592 (1.3792) time: 0.6267 [2021-03-27 02:44:57 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 130/1251] eta: 0:12:17 lr: 0.000633 loss: 3.4999 (3.3770) grad_norm: 1.2900 (1.3749) time: 0.6284 [2021-03-27 02:45:03 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 140/1251] eta: 0:12:08 lr: 0.000633 loss: 3.3310 (3.3780) grad_norm: 1.2629 (1.3703) time: 0.6292 [2021-03-27 02:45:10 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 150/1251] eta: 0:12:00 lr: 0.000633 loss: 3.3404 (3.3929) grad_norm: 1.3107 (1.3666) time: 0.6320 [2021-03-27 02:45:16 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 160/1251] eta: 0:11:52 lr: 0.000632 loss: 3.4169 (3.3841) grad_norm: 1.2802 (1.3594) time: 0.6336 [2021-03-27 02:45:22 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 170/1251] eta: 0:11:44 lr: 0.000632 loss: 3.4169 (3.3881) grad_norm: 1.2228 (1.3537) time: 0.6321 [2021-03-27 02:45:29 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 180/1251] eta: 0:11:36 lr: 0.000632 loss: 3.4316 (3.3756) grad_norm: 1.2885 (1.3529) time: 0.6264 [2021-03-27 02:45:35 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 190/1251] eta: 0:11:28 lr: 0.000632 loss: 3.4316 (3.3809) grad_norm: 1.3101 (1.3520) time: 0.6224 [2021-03-27 02:45:41 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 200/1251] eta: 0:11:20 lr: 0.000632 loss: 3.4260 (3.3751) grad_norm: 1.2739 (1.3483) time: 0.6281 [2021-03-27 02:45:48 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 210/1251] eta: 0:11:13 lr: 0.000632 loss: 3.4260 (3.3831) grad_norm: 1.2762 (1.3496) time: 0.6325 [2021-03-27 02:45:54 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 220/1251] eta: 0:11:06 lr: 0.000632 loss: 3.4864 (3.3814) grad_norm: 1.3173 (1.3483) time: 0.6345 [2021-03-27 02:46:00 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 230/1251] eta: 0:10:59 lr: 0.000632 loss: 3.4977 (3.3856) grad_norm: 1.3173 (1.3489) time: 0.6326 [2021-03-27 02:46:07 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 240/1251] eta: 0:10:52 lr: 0.000632 loss: 3.4977 (3.3862) grad_norm: 1.3093 (1.3494) time: 0.6358 [2021-03-27 02:46:13 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 250/1251] eta: 0:10:45 lr: 0.000632 loss: 3.4892 (3.3866) grad_norm: 1.2860 (1.3459) time: 0.6399 [2021-03-27 02:46:19 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 260/1251] eta: 0:10:38 lr: 0.000632 loss: 3.5529 (3.3968) grad_norm: 1.2860 (1.3475) time: 0.6285 [2021-03-27 02:46:26 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 270/1251] eta: 0:10:31 lr: 0.000632 loss: 3.7885 (3.4129) grad_norm: 1.2734 (1.3448) time: 0.6259 [2021-03-27 02:46:32 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 280/1251] eta: 0:10:24 lr: 0.000632 loss: 3.7162 (3.4116) grad_norm: 1.2538 (1.3436) time: 0.6316 [2021-03-27 02:46:38 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 290/1251] eta: 0:10:18 lr: 0.000632 loss: 3.4537 (3.4145) grad_norm: 1.2812 (1.3423) time: 0.6340 [2021-03-27 02:46:45 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 300/1251] eta: 0:10:11 lr: 0.000632 loss: 3.4703 (3.4180) grad_norm: 1.2940 (1.3439) time: 0.6398 [2021-03-27 02:46:51 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 310/1251] eta: 0:10:05 lr: 0.000632 loss: 3.3642 (3.4121) grad_norm: 1.3332 (1.3425) time: 0.6430 [2021-03-27 02:46:57 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 320/1251] eta: 0:09:58 lr: 0.000632 loss: 3.3642 (3.4126) grad_norm: 1.3318 (1.3421) time: 0.6368 [2021-03-27 02:47:04 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 330/1251] eta: 0:09:51 lr: 0.000632 loss: 3.5564 (3.4127) grad_norm: 1.3318 (1.3421) time: 0.6339 [2021-03-27 02:47:10 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 340/1251] eta: 0:09:45 lr: 0.000632 loss: 3.5564 (3.4161) grad_norm: 1.3370 (1.3453) time: 0.6385 [2021-03-27 02:47:17 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 350/1251] eta: 0:09:38 lr: 0.000632 loss: 3.4464 (3.4153) grad_norm: 1.4071 (1.3465) time: 0.6352 [2021-03-27 02:47:23 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 360/1251] eta: 0:09:32 lr: 0.000632 loss: 3.0726 (3.4063) grad_norm: 1.4048 (1.3464) time: 0.6335 [2021-03-27 02:47:29 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 370/1251] eta: 0:09:25 lr: 0.000632 loss: 3.0416 (3.3996) grad_norm: 1.3429 (1.3492) time: 0.6284 [2021-03-27 02:47:35 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 380/1251] eta: 0:09:18 lr: 0.000632 loss: 3.2876 (3.4013) grad_norm: 1.2788 (1.3471) time: 0.6306 [2021-03-27 02:47:42 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 390/1251] eta: 0:09:12 lr: 0.000632 loss: 3.5465 (3.4034) grad_norm: 1.2920 (1.3486) time: 0.6384 [2021-03-27 02:47:48 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 400/1251] eta: 0:09:05 lr: 0.000632 loss: 3.5193 (3.4056) grad_norm: 1.3848 (1.3511) time: 0.6339 [2021-03-27 02:47:54 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 410/1251] eta: 0:08:58 lr: 0.000631 loss: 3.5193 (3.4079) grad_norm: 1.3192 (1.3520) time: 0.6279 [2021-03-27 02:48:01 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 420/1251] eta: 0:08:52 lr: 0.000631 loss: 3.2731 (3.4038) grad_norm: 1.3156 (1.3524) time: 0.6254 [2021-03-27 02:48:07 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 430/1251] eta: 0:08:45 lr: 0.000631 loss: 3.1983 (3.4033) grad_norm: 1.3027 (1.3522) time: 0.6282 [2021-03-27 02:48:13 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 440/1251] eta: 0:08:38 lr: 0.000631 loss: 3.2114 (3.3995) grad_norm: 1.3119 (1.3531) time: 0.6248 [2021-03-27 02:48:19 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 450/1251] eta: 0:08:32 lr: 0.000631 loss: 3.4978 (3.4010) grad_norm: 1.3417 (1.3537) time: 0.6248 [2021-03-27 02:48:26 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 460/1251] eta: 0:08:25 lr: 0.000631 loss: 3.5433 (3.4009) grad_norm: 1.3275 (1.3531) time: 0.6272 [2021-03-27 02:48:32 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 470/1251] eta: 0:08:18 lr: 0.000631 loss: 3.4184 (3.3950) grad_norm: 1.2964 (1.3540) time: 0.6255 [2021-03-27 02:48:38 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 480/1251] eta: 0:08:12 lr: 0.000631 loss: 3.2753 (3.3905) grad_norm: 1.2788 (1.3539) time: 0.6280 [2021-03-27 02:48:45 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 490/1251] eta: 0:08:05 lr: 0.000631 loss: 3.3040 (3.3908) grad_norm: 1.3045 (1.3544) time: 0.6309 [2021-03-27 02:48:51 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 500/1251] eta: 0:07:59 lr: 0.000631 loss: 3.5369 (3.3893) grad_norm: 1.3045 (1.3529) time: 0.6380 [2021-03-27 02:48:57 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 510/1251] eta: 0:07:53 lr: 0.000631 loss: 3.4663 (3.3879) grad_norm: 1.2885 (1.3518) time: 0.6368 [2021-03-27 02:49:04 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 520/1251] eta: 0:07:46 lr: 0.000631 loss: 3.5419 (3.3934) grad_norm: 1.2885 (1.3505) time: 0.6303 [2021-03-27 02:49:10 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 530/1251] eta: 0:07:40 lr: 0.000631 loss: 3.5494 (3.3925) grad_norm: 1.2957 (1.3506) time: 0.6291 [2021-03-27 02:49:16 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 540/1251] eta: 0:07:33 lr: 0.000631 loss: 3.3885 (3.3917) grad_norm: 1.3349 (1.3506) time: 0.6259 [2021-03-27 02:49:23 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 550/1251] eta: 0:07:27 lr: 0.000631 loss: 3.3972 (3.3926) grad_norm: 1.2413 (1.3486) time: 0.6373 [2021-03-27 02:49:29 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 560/1251] eta: 0:07:20 lr: 0.000631 loss: 3.5076 (3.3966) grad_norm: 1.2722 (1.3475) time: 0.6421 [2021-03-27 02:49:35 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 570/1251] eta: 0:07:14 lr: 0.000631 loss: 3.5415 (3.3963) grad_norm: 1.2860 (1.3463) time: 0.6309 [2021-03-27 02:49:42 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 580/1251] eta: 0:07:07 lr: 0.000631 loss: 3.3743 (3.3942) grad_norm: 1.2832 (1.3460) time: 0.6287 [2021-03-27 02:49:48 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 590/1251] eta: 0:07:01 lr: 0.000631 loss: 3.4032 (3.3957) grad_norm: 1.3307 (1.3459) time: 0.6285 [2021-03-27 02:49:54 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 600/1251] eta: 0:06:54 lr: 0.000631 loss: 3.4546 (3.3953) grad_norm: 1.3641 (1.3483) time: 0.6274 [2021-03-27 02:50:00 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 610/1251] eta: 0:06:48 lr: 0.000631 loss: 3.2913 (3.3918) grad_norm: 1.4228 (1.3505) time: 0.6265 [2021-03-27 02:50:07 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 620/1251] eta: 0:06:41 lr: 0.000631 loss: 3.5496 (3.3968) grad_norm: 1.3899 (1.3524) time: 0.6235 [2021-03-27 02:50:13 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 630/1251] eta: 0:06:35 lr: 0.000631 loss: 3.5779 (3.3931) grad_norm: 1.2695 (1.3511) time: 0.6271 [2021-03-27 02:50:19 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 640/1251] eta: 0:06:29 lr: 0.000631 loss: 3.3215 (3.3944) grad_norm: 1.2634 (1.3510) time: 0.6327 [2021-03-27 02:50:26 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 650/1251] eta: 0:06:22 lr: 0.000631 loss: 3.3215 (3.3902) grad_norm: 1.3632 (1.3526) time: 0.6286 [2021-03-27 02:50:32 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 660/1251] eta: 0:06:16 lr: 0.000630 loss: 3.2534 (3.3869) grad_norm: 1.4296 (1.3551) time: 0.6295 [2021-03-27 02:50:38 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 670/1251] eta: 0:06:09 lr: 0.000630 loss: 3.3185 (3.3842) grad_norm: 1.4102 (1.3556) time: 0.6284 [2021-03-27 02:50:44 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 680/1251] eta: 0:06:03 lr: 0.000630 loss: 3.4957 (3.3851) grad_norm: 1.3251 (1.3552) time: 0.6247 [2021-03-27 02:50:51 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 690/1251] eta: 0:05:56 lr: 0.000630 loss: 3.5614 (3.3846) grad_norm: 1.3040 (1.3545) time: 0.6281 [2021-03-27 02:50:57 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 700/1251] eta: 0:05:50 lr: 0.000630 loss: 3.4299 (3.3837) grad_norm: 1.3023 (1.3537) time: 0.6263 [2021-03-27 02:51:03 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 710/1251] eta: 0:05:43 lr: 0.000630 loss: 3.7112 (3.3858) grad_norm: 1.2656 (1.3529) time: 0.6248 [2021-03-27 02:51:09 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 720/1251] eta: 0:05:37 lr: 0.000630 loss: 3.7112 (3.3855) grad_norm: 1.3022 (1.3527) time: 0.6270 [2021-03-27 02:51:16 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 730/1251] eta: 0:05:31 lr: 0.000630 loss: 3.3759 (3.3868) grad_norm: 1.2973 (1.3519) time: 0.6265 [2021-03-27 02:51:22 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 740/1251] eta: 0:05:24 lr: 0.000630 loss: 3.4371 (3.3880) grad_norm: 1.2868 (1.3510) time: 0.6367 [2021-03-27 02:51:29 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 750/1251] eta: 0:05:18 lr: 0.000630 loss: 3.5365 (3.3860) grad_norm: 1.2924 (1.3514) time: 0.6431 [2021-03-27 02:51:35 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 760/1251] eta: 0:05:12 lr: 0.000630 loss: 3.1163 (3.3848) grad_norm: 1.3119 (1.3516) time: 0.6410 [2021-03-27 02:51:41 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 770/1251] eta: 0:05:05 lr: 0.000630 loss: 3.4866 (3.3867) grad_norm: 1.2819 (1.3511) time: 0.6361 [2021-03-27 02:51:47 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 780/1251] eta: 0:04:59 lr: 0.000630 loss: 3.4866 (3.3889) grad_norm: 1.3189 (1.3523) time: 0.6243 [2021-03-27 02:51:54 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 790/1251] eta: 0:04:52 lr: 0.000630 loss: 3.3721 (3.3869) grad_norm: 1.3908 (1.3525) time: 0.6283 [2021-03-27 02:52:00 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 800/1251] eta: 0:04:46 lr: 0.000630 loss: 3.1370 (3.3853) grad_norm: 1.4024 (1.3538) time: 0.6448 [2021-03-27 02:52:07 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 810/1251] eta: 0:04:40 lr: 0.000630 loss: 3.1370 (3.3826) grad_norm: 1.4024 (1.3545) time: 0.6435 [2021-03-27 02:52:13 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 820/1251] eta: 0:04:34 lr: 0.000630 loss: 3.3556 (3.3838) grad_norm: 1.4188 (1.3556) time: 0.6362 [2021-03-27 02:52:19 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 830/1251] eta: 0:04:27 lr: 0.000630 loss: 3.3390 (3.3813) grad_norm: 1.4132 (1.3565) time: 0.6327 [2021-03-27 02:52:26 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 840/1251] eta: 0:04:21 lr: 0.000630 loss: 3.0843 (3.3797) grad_norm: 1.2887 (1.3559) time: 0.6257 [2021-03-27 02:52:32 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 850/1251] eta: 0:04:14 lr: 0.000630 loss: 3.4237 (3.3810) grad_norm: 1.2887 (1.3572) time: 0.6237 [2021-03-27 02:52:38 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 860/1251] eta: 0:04:08 lr: 0.000630 loss: 3.4247 (3.3831) grad_norm: 1.4138 (1.3583) time: 0.6287 [2021-03-27 02:52:44 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 870/1251] eta: 0:04:02 lr: 0.000630 loss: 3.3568 (3.3827) grad_norm: 1.2828 (1.3566) time: 0.6281 [2021-03-27 02:52:51 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 880/1251] eta: 0:03:55 lr: 0.000630 loss: 3.4401 (3.3850) grad_norm: 1.1804 (1.3556) time: 0.6251 [2021-03-27 02:52:57 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 890/1251] eta: 0:03:49 lr: 0.000630 loss: 3.5289 (3.3857) grad_norm: 1.3062 (1.3554) time: 0.6263 [2021-03-27 02:53:03 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 900/1251] eta: 0:03:42 lr: 0.000630 loss: 3.6900 (3.3890) grad_norm: 1.3174 (1.3547) time: 0.6268 [2021-03-27 02:53:10 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 910/1251] eta: 0:03:36 lr: 0.000629 loss: 3.6018 (3.3891) grad_norm: 1.2909 (1.3548) time: 0.6269 [2021-03-27 02:53:16 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 920/1251] eta: 0:03:30 lr: 0.000629 loss: 3.6018 (3.3888) grad_norm: 1.3129 (1.3545) time: 0.6221 [2021-03-27 02:53:22 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 930/1251] eta: 0:03:23 lr: 0.000629 loss: 3.5635 (3.3880) grad_norm: 1.3024 (1.3543) time: 0.6222 [2021-03-27 02:53:28 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 940/1251] eta: 0:03:17 lr: 0.000629 loss: 3.4399 (3.3886) grad_norm: 1.2980 (1.3541) time: 0.6271 [2021-03-27 02:53:35 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 950/1251] eta: 0:03:10 lr: 0.000629 loss: 3.4399 (3.3886) grad_norm: 1.3439 (1.3544) time: 0.6296 [2021-03-27 02:53:41 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 960/1251] eta: 0:03:04 lr: 0.000629 loss: 3.3168 (3.3877) grad_norm: 1.3582 (1.3542) time: 0.6312 [2021-03-27 02:53:47 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 970/1251] eta: 0:02:58 lr: 0.000629 loss: 3.4333 (3.3882) grad_norm: 1.4079 (1.3560) time: 0.6322 [2021-03-27 02:53:54 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 980/1251] eta: 0:02:51 lr: 0.000629 loss: 3.5103 (3.3880) grad_norm: 1.4557 (1.3556) time: 0.6315 [2021-03-27 02:54:00 swin_base_patch4_window7_224] INFO: Epoch: [125] [ 990/1251] eta: 0:02:45 lr: 0.000629 loss: 3.4277 (3.3882) grad_norm: 1.3340 (1.3561) time: 0.6297 [2021-03-27 02:54:06 swin_base_patch4_window7_224] INFO: Epoch: [125] [1000/1251] eta: 0:02:39 lr: 0.000629 loss: 3.5812 (3.3904) grad_norm: 1.2929 (1.3552) time: 0.6262 [2021-03-27 02:54:12 swin_base_patch4_window7_224] INFO: Epoch: [125] [1010/1251] eta: 0:02:32 lr: 0.000629 loss: 3.7628 (3.3934) grad_norm: 1.3164 (1.3554) time: 0.6220 [2021-03-27 02:54:18 swin_base_patch4_window7_224] INFO: Epoch: [125] [1020/1251] eta: 0:02:26 lr: 0.000629 loss: 3.7344 (3.3940) grad_norm: 1.3263 (1.3553) time: 0.6195 [2021-03-27 02:54:25 swin_base_patch4_window7_224] INFO: Epoch: [125] [1030/1251] eta: 0:02:20 lr: 0.000629 loss: 3.3166 (3.3928) grad_norm: 1.2874 (1.3550) time: 0.6259 [2021-03-27 02:54:31 swin_base_patch4_window7_224] INFO: Epoch: [125] [1040/1251] eta: 0:02:13 lr: 0.000629 loss: 3.2859 (3.3923) grad_norm: 1.2787 (1.3543) time: 0.6331 [2021-03-27 02:54:37 swin_base_patch4_window7_224] INFO: Epoch: [125] [1050/1251] eta: 0:02:07 lr: 0.000629 loss: 3.2859 (3.3917) grad_norm: 1.2781 (1.3540) time: 0.6301 [2021-03-27 02:54:44 swin_base_patch4_window7_224] INFO: Epoch: [125] [1060/1251] eta: 0:02:01 lr: 0.000629 loss: 3.2167 (3.3912) grad_norm: 1.2928 (1.3541) time: 0.6282 [2021-03-27 02:54:50 swin_base_patch4_window7_224] INFO: Epoch: [125] [1070/1251] eta: 0:01:54 lr: 0.000629 loss: 3.4344 (3.3919) grad_norm: 1.3821 (1.3551) time: 0.6369 [2021-03-27 02:54:56 swin_base_patch4_window7_224] INFO: Epoch: [125] [1080/1251] eta: 0:01:48 lr: 0.000629 loss: 3.5368 (3.3939) grad_norm: 1.4014 (1.3552) time: 0.6318 [2021-03-27 02:55:03 swin_base_patch4_window7_224] INFO: Epoch: [125] [1090/1251] eta: 0:01:42 lr: 0.000629 loss: 3.4415 (3.3917) grad_norm: 1.4014 (1.3561) time: 0.6272 [2021-03-27 02:55:09 swin_base_patch4_window7_224] INFO: Epoch: [125] [1100/1251] eta: 0:01:35 lr: 0.000629 loss: 3.2533 (3.3902) grad_norm: 1.4175 (1.3566) time: 0.6302 [2021-03-27 02:55:15 swin_base_patch4_window7_224] INFO: Epoch: [125] [1110/1251] eta: 0:01:29 lr: 0.000629 loss: 3.3756 (3.3909) grad_norm: 1.3989 (1.3561) time: 0.6268 [2021-03-27 02:55:21 swin_base_patch4_window7_224] INFO: Epoch: [125] [1120/1251] eta: 0:01:22 lr: 0.000629 loss: 3.6080 (3.3918) grad_norm: 1.2882 (1.3556) time: 0.6261 [2021-03-27 02:55:28 swin_base_patch4_window7_224] INFO: Epoch: [125] [1130/1251] eta: 0:01:16 lr: 0.000629 loss: 3.5984 (3.3930) grad_norm: 1.3083 (1.3552) time: 0.6232 [2021-03-27 02:55:34 swin_base_patch4_window7_224] INFO: Epoch: [125] [1140/1251] eta: 0:01:10 lr: 0.000629 loss: 3.5724 (3.3925) grad_norm: 1.3526 (1.3561) time: 0.6319 [2021-03-27 02:55:40 swin_base_patch4_window7_224] INFO: Epoch: [125] [1150/1251] eta: 0:01:03 lr: 0.000629 loss: 3.5038 (3.3914) grad_norm: 1.3922 (1.3563) time: 0.6355 [2021-03-27 02:55:47 swin_base_patch4_window7_224] INFO: Epoch: [125] [1160/1251] eta: 0:00:57 lr: 0.000628 loss: 3.4711 (3.3920) grad_norm: 1.3326 (1.3564) time: 0.6327 [2021-03-27 02:55:53 swin_base_patch4_window7_224] INFO: Epoch: [125] [1170/1251] eta: 0:00:51 lr: 0.000628 loss: 3.5968 (3.3947) grad_norm: 1.2584 (1.3558) time: 0.6308 [2021-03-27 02:55:59 swin_base_patch4_window7_224] INFO: Epoch: [125] [1180/1251] eta: 0:00:44 lr: 0.000628 loss: 3.5968 (3.3958) grad_norm: 1.2629 (1.3556) time: 0.6275 [2021-03-27 02:56:06 swin_base_patch4_window7_224] INFO: Epoch: [125] [1190/1251] eta: 0:00:38 lr: 0.000628 loss: 3.5764 (3.3956) grad_norm: 1.3893 (1.3572) time: 0.6256 [2021-03-27 02:56:12 swin_base_patch4_window7_224] INFO: Epoch: [125] [1200/1251] eta: 0:00:32 lr: 0.000628 loss: 3.5611 (3.3969) grad_norm: 1.4303 (1.3580) time: 0.6260 [2021-03-27 02:56:18 swin_base_patch4_window7_224] INFO: Epoch: [125] [1210/1251] eta: 0:00:25 lr: 0.000628 loss: 3.5676 (3.3964) grad_norm: 1.3971 (1.3582) time: 0.6265 [2021-03-27 02:56:24 swin_base_patch4_window7_224] INFO: Epoch: [125] [1220/1251] eta: 0:00:19 lr: 0.000628 loss: 3.5676 (3.3971) grad_norm: 1.3227 (1.3580) time: 0.6243 [2021-03-27 02:56:31 swin_base_patch4_window7_224] INFO: Epoch: [125] [1230/1251] eta: 0:00:13 lr: 0.000628 loss: 3.6013 (3.3995) grad_norm: 1.3535 (1.3589) time: 0.6232 [2021-03-27 02:56:37 swin_base_patch4_window7_224] INFO: Epoch: [125] [1240/1251] eta: 0:00:06 lr: 0.000628 loss: 3.6397 (3.4006) grad_norm: 1.3920 (1.3599) time: 0.6261 [2021-03-27 02:56:43 swin_base_patch4_window7_224] INFO: Epoch: [125] [1250/1251] eta: 0:00:00 lr: 0.000628 loss: 3.5895 (3.4005) grad_norm: 1.2917 (1.3599) time: 0.6217 [2021-03-27 02:57:51 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.6879 (0.6879) acc1: 81.2500 (81.2500) acc5: 98.4375 (98.4375) [2021-03-27 02:57:52 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.9777 (0.9939) acc1: 76.5625 (76.1364) acc5: 95.3125 (94.3182) [2021-03-27 02:57:54 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9599 (0.9555) acc1: 78.1250 (77.9018) acc5: 95.3125 (94.4196) [2021-03-27 02:57:55 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8602 (0.9444) acc1: 78.1250 (78.1754) acc5: 95.3125 (94.5060) [2021-03-27 02:57:57 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8850 (0.9498) acc1: 78.1250 (77.9726) acc5: 95.3125 (94.5122) [2021-03-27 02:57:58 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9290 (0.9672) acc1: 76.5625 (77.4720) acc5: 93.7500 (94.4640) [2021-03-27 02:58:04 swin_base_patch4_window7_224] INFO: * Acc@1 77.774 Acc@5 94.306 loss 0.964 [2021-03-27 02:58:04 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.8% [2021-03-27 02:58:04 swin_base_patch4_window7_224] INFO: Max accuracy: 77.83% [2021-03-27 02:58:09 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 0/1251] eta: 1:30:27 lr: 0.000628 loss: 3.7752 (3.7752) grad_norm: 1.5414 (1.5414) time: 4.3383 [2021-03-27 02:58:15 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 10/1251] eta: 0:20:14 lr: 0.000628 loss: 3.4127 (3.3872) grad_norm: 1.2888 (1.3247) time: 0.9786 [2021-03-27 02:58:22 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 20/1251] eta: 0:16:46 lr: 0.000628 loss: 3.4127 (3.4171) grad_norm: 1.3107 (1.3324) time: 0.6420 [2021-03-27 02:58:28 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 30/1251] eta: 0:15:20 lr: 0.000628 loss: 3.3794 (3.3671) grad_norm: 1.3391 (1.3232) time: 0.6307 [2021-03-27 02:58:34 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 40/1251] eta: 0:14:38 lr: 0.000628 loss: 3.4389 (3.3724) grad_norm: 1.2839 (1.3181) time: 0.6279 [2021-03-27 02:58:41 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 50/1251] eta: 0:14:09 lr: 0.000628 loss: 3.5437 (3.3861) grad_norm: 1.2954 (1.3292) time: 0.6358 [2021-03-27 02:58:47 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 60/1251] eta: 0:13:47 lr: 0.000628 loss: 3.5603 (3.3901) grad_norm: 1.2898 (1.3242) time: 0.6319 [2021-03-27 02:58:53 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 70/1251] eta: 0:13:32 lr: 0.000628 loss: 3.5585 (3.3927) grad_norm: 1.3177 (1.3397) time: 0.6375 [2021-03-27 02:58:59 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 80/1251] eta: 0:13:15 lr: 0.000628 loss: 3.2300 (3.3636) grad_norm: 1.3468 (1.3463) time: 0.6335 [2021-03-27 02:59:06 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 90/1251] eta: 0:13:01 lr: 0.000628 loss: 3.2875 (3.3725) grad_norm: 1.3257 (1.3449) time: 0.6221 [2021-03-27 02:59:12 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 100/1251] eta: 0:12:49 lr: 0.000628 loss: 3.6318 (3.4020) grad_norm: 1.3262 (1.3465) time: 0.6251 [2021-03-27 02:59:18 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 110/1251] eta: 0:12:39 lr: 0.000628 loss: 3.7254 (3.4126) grad_norm: 1.3405 (1.3531) time: 0.6317 [2021-03-27 02:59:25 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 120/1251] eta: 0:12:29 lr: 0.000628 loss: 3.4886 (3.4059) grad_norm: 1.3602 (1.3621) time: 0.6321 [2021-03-27 02:59:31 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 130/1251] eta: 0:12:19 lr: 0.000628 loss: 3.3574 (3.4032) grad_norm: 1.4278 (1.3683) time: 0.6249 [2021-03-27 02:59:37 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 140/1251] eta: 0:12:11 lr: 0.000628 loss: 3.2410 (3.4018) grad_norm: 1.3133 (1.3616) time: 0.6304 [2021-03-27 02:59:44 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 150/1251] eta: 0:12:03 lr: 0.000627 loss: 3.4582 (3.4053) grad_norm: 1.2154 (1.3536) time: 0.6428 [2021-03-27 02:59:50 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 160/1251] eta: 0:11:55 lr: 0.000627 loss: 3.5541 (3.4110) grad_norm: 1.2904 (1.3552) time: 0.6375 [2021-03-27 02:59:56 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 170/1251] eta: 0:11:46 lr: 0.000627 loss: 3.5937 (3.4201) grad_norm: 1.3615 (1.3596) time: 0.6250 [2021-03-27 03:00:03 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 180/1251] eta: 0:11:38 lr: 0.000627 loss: 3.6292 (3.4168) grad_norm: 1.2753 (1.3546) time: 0.6274 [2021-03-27 03:00:09 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 190/1251] eta: 0:11:31 lr: 0.000627 loss: 3.5741 (3.4233) grad_norm: 1.3482 (1.3658) time: 0.6365 [2021-03-27 03:00:15 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 200/1251] eta: 0:11:24 lr: 0.000627 loss: 3.6254 (3.4312) grad_norm: 1.3858 (1.3654) time: 0.6372 [2021-03-27 03:00:22 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 210/1251] eta: 0:11:16 lr: 0.000627 loss: 3.4883 (3.4172) grad_norm: 1.2538 (1.3664) time: 0.6295 [2021-03-27 03:00:28 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 220/1251] eta: 0:11:08 lr: 0.000627 loss: 3.4883 (3.4193) grad_norm: 1.3303 (1.3690) time: 0.6231 [2021-03-27 03:00:34 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 230/1251] eta: 0:11:01 lr: 0.000627 loss: 3.3763 (3.4085) grad_norm: 1.3945 (1.3721) time: 0.6260 [2021-03-27 03:00:40 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 240/1251] eta: 0:10:53 lr: 0.000627 loss: 3.2767 (3.4124) grad_norm: 1.3475 (1.3736) time: 0.6280 [2021-03-27 03:00:47 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 250/1251] eta: 0:10:46 lr: 0.000627 loss: 3.6247 (3.4150) grad_norm: 1.3375 (1.3766) time: 0.6303 [2021-03-27 03:00:53 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 260/1251] eta: 0:10:39 lr: 0.000627 loss: 3.5715 (3.4195) grad_norm: 1.4098 (1.3833) time: 0.6314 [2021-03-27 03:00:59 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 270/1251] eta: 0:10:32 lr: 0.000627 loss: 3.4851 (3.4276) grad_norm: 1.4009 (1.3819) time: 0.6267 [2021-03-27 03:01:06 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 280/1251] eta: 0:10:25 lr: 0.000627 loss: 3.8378 (3.4417) grad_norm: 1.3033 (1.3796) time: 0.6316 [2021-03-27 03:01:12 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 290/1251] eta: 0:10:18 lr: 0.000627 loss: 3.5650 (3.4446) grad_norm: 1.3450 (1.3801) time: 0.6303 [2021-03-27 03:01:18 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 300/1251] eta: 0:10:11 lr: 0.000627 loss: 3.3676 (3.4303) grad_norm: 1.3501 (1.3779) time: 0.6278 [2021-03-27 03:01:24 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 310/1251] eta: 0:10:05 lr: 0.000627 loss: 3.1667 (3.4296) grad_norm: 1.3522 (1.3773) time: 0.6304 [2021-03-27 03:01:31 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 320/1251] eta: 0:09:58 lr: 0.000627 loss: 3.5872 (3.4349) grad_norm: 1.3522 (1.3768) time: 0.6287 [2021-03-27 03:01:37 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 330/1251] eta: 0:09:51 lr: 0.000627 loss: 3.3311 (3.4217) grad_norm: 1.3462 (1.3800) time: 0.6345 [2021-03-27 03:01:44 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 340/1251] eta: 0:09:45 lr: 0.000627 loss: 3.2955 (3.4239) grad_norm: 1.3413 (inf) time: 0.6398 [2021-03-27 03:01:50 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 350/1251] eta: 0:09:38 lr: 0.000627 loss: 3.4680 (3.4239) grad_norm: 1.3113 (inf) time: 0.6365 [2021-03-27 03:01:56 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 360/1251] eta: 0:09:32 lr: 0.000627 loss: 3.4731 (3.4233) grad_norm: 1.3631 (inf) time: 0.6377 [2021-03-27 03:02:03 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 370/1251] eta: 0:09:25 lr: 0.000627 loss: 3.4843 (3.4207) grad_norm: 1.3671 (inf) time: 0.6369 [2021-03-27 03:02:09 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 380/1251] eta: 0:09:18 lr: 0.000627 loss: 3.3756 (3.4186) grad_norm: 1.3671 (inf) time: 0.6324 [2021-03-27 03:02:15 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 390/1251] eta: 0:09:12 lr: 0.000627 loss: 3.4231 (3.4216) grad_norm: 1.3407 (inf) time: 0.6334 [2021-03-27 03:02:22 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 400/1251] eta: 0:09:05 lr: 0.000626 loss: 3.4231 (3.4170) grad_norm: 1.3407 (inf) time: 0.6298 [2021-03-27 03:02:28 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 410/1251] eta: 0:08:58 lr: 0.000626 loss: 3.5428 (3.4191) grad_norm: 1.3182 (inf) time: 0.6256 [2021-03-27 03:02:34 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 420/1251] eta: 0:08:52 lr: 0.000626 loss: 3.5828 (3.4197) grad_norm: 1.3114 (inf) time: 0.6304 [2021-03-27 03:02:41 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 430/1251] eta: 0:08:45 lr: 0.000626 loss: 3.5883 (3.4193) grad_norm: 1.3079 (inf) time: 0.6355 [2021-03-27 03:02:47 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 440/1251] eta: 0:08:39 lr: 0.000626 loss: 3.4653 (3.4186) grad_norm: 1.2391 (inf) time: 0.6344 [2021-03-27 03:02:53 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 450/1251] eta: 0:08:32 lr: 0.000626 loss: 3.3496 (3.4147) grad_norm: 1.2391 (inf) time: 0.6295 [2021-03-27 03:02:59 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 460/1251] eta: 0:08:26 lr: 0.000626 loss: 3.2264 (3.4115) grad_norm: 1.3503 (inf) time: 0.6280 [2021-03-27 03:03:06 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 470/1251] eta: 0:08:19 lr: 0.000626 loss: 3.7892 (3.4199) grad_norm: 1.3462 (inf) time: 0.6296 [2021-03-27 03:03:12 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 480/1251] eta: 0:08:12 lr: 0.000626 loss: 3.6859 (3.4171) grad_norm: 1.3213 (inf) time: 0.6308 [2021-03-27 03:03:18 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 490/1251] eta: 0:08:06 lr: 0.000626 loss: 3.4218 (3.4161) grad_norm: 1.3213 (inf) time: 0.6277 [2021-03-27 03:03:25 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 500/1251] eta: 0:07:59 lr: 0.000626 loss: 3.3073 (3.4128) grad_norm: 1.3219 (inf) time: 0.6242 [2021-03-27 03:03:31 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 510/1251] eta: 0:07:53 lr: 0.000626 loss: 3.3073 (3.4109) grad_norm: 1.3585 (inf) time: 0.6303 [2021-03-27 03:03:37 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 520/1251] eta: 0:07:46 lr: 0.000626 loss: 3.4350 (3.4113) grad_norm: 1.3868 (inf) time: 0.6375 [2021-03-27 03:03:44 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 530/1251] eta: 0:07:40 lr: 0.000626 loss: 3.1314 (3.4050) grad_norm: 1.3040 (inf) time: 0.6357 [2021-03-27 03:03:50 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 540/1251] eta: 0:07:33 lr: 0.000626 loss: 3.1337 (3.4043) grad_norm: 1.4393 (inf) time: 0.6324 [2021-03-27 03:03:56 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 550/1251] eta: 0:07:27 lr: 0.000626 loss: 3.5577 (3.4028) grad_norm: 1.4456 (inf) time: 0.6437 [2021-03-27 03:04:03 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 560/1251] eta: 0:07:21 lr: 0.000626 loss: 3.4724 (3.4030) grad_norm: 1.3463 (inf) time: 0.6437 [2021-03-27 03:04:09 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 570/1251] eta: 0:07:14 lr: 0.000626 loss: 3.4334 (3.4028) grad_norm: 1.2518 (inf) time: 0.6299 [2021-03-27 03:04:15 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 580/1251] eta: 0:07:08 lr: 0.000626 loss: 3.4334 (3.4035) grad_norm: 1.2518 (inf) time: 0.6253 [2021-03-27 03:04:22 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 590/1251] eta: 0:07:01 lr: 0.000626 loss: 3.6934 (3.4089) grad_norm: 1.3613 (inf) time: 0.6236 [2021-03-27 03:04:28 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 600/1251] eta: 0:06:55 lr: 0.000626 loss: 3.5266 (3.4076) grad_norm: 1.3613 (inf) time: 0.6213 [2021-03-27 03:04:34 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 610/1251] eta: 0:06:48 lr: 0.000626 loss: 3.3986 (3.4084) grad_norm: 1.4065 (inf) time: 0.6233 [2021-03-27 03:04:40 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 620/1251] eta: 0:06:42 lr: 0.000626 loss: 3.5466 (3.4077) grad_norm: 1.4010 (inf) time: 0.6308 [2021-03-27 03:04:47 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 630/1251] eta: 0:06:35 lr: 0.000626 loss: 3.5124 (3.4093) grad_norm: 1.3228 (inf) time: 0.6291 [2021-03-27 03:04:53 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 640/1251] eta: 0:06:29 lr: 0.000626 loss: 3.6401 (3.4088) grad_norm: 1.3762 (inf) time: 0.6242 [2021-03-27 03:04:59 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 650/1251] eta: 0:06:22 lr: 0.000625 loss: 3.6676 (3.4095) grad_norm: 1.3456 (inf) time: 0.6220 [2021-03-27 03:05:05 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 660/1251] eta: 0:06:16 lr: 0.000625 loss: 3.3074 (3.4048) grad_norm: 1.3222 (inf) time: 0.6230 [2021-03-27 03:05:12 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 670/1251] eta: 0:06:09 lr: 0.000625 loss: 3.2043 (3.4034) grad_norm: 1.3792 (inf) time: 0.6333 [2021-03-27 03:05:18 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 680/1251] eta: 0:06:03 lr: 0.000625 loss: 3.4628 (3.4037) grad_norm: 1.4073 (inf) time: 0.6322 [2021-03-27 03:05:24 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 690/1251] eta: 0:05:56 lr: 0.000625 loss: 3.5352 (3.4071) grad_norm: 1.4113 (inf) time: 0.6261 [2021-03-27 03:05:30 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 700/1251] eta: 0:05:50 lr: 0.000625 loss: 3.6293 (3.4115) grad_norm: 1.3344 (inf) time: 0.6266 [2021-03-27 03:05:37 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 710/1251] eta: 0:05:44 lr: 0.000625 loss: 3.5940 (3.4095) grad_norm: 1.2930 (inf) time: 0.6252 [2021-03-27 03:05:43 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 720/1251] eta: 0:05:37 lr: 0.000625 loss: 3.4096 (3.4104) grad_norm: 1.3436 (inf) time: 0.6266 [2021-03-27 03:05:49 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 730/1251] eta: 0:05:31 lr: 0.000625 loss: 3.4313 (3.4086) grad_norm: 1.2907 (inf) time: 0.6298 [2021-03-27 03:05:56 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 740/1251] eta: 0:05:24 lr: 0.000625 loss: 3.2036 (3.4065) grad_norm: 1.2076 (inf) time: 0.6337 [2021-03-27 03:06:02 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 750/1251] eta: 0:05:18 lr: 0.000625 loss: 3.3354 (3.4069) grad_norm: 1.3142 (inf) time: 0.6389 [2021-03-27 03:06:08 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 760/1251] eta: 0:05:12 lr: 0.000625 loss: 3.3354 (3.4028) grad_norm: 1.3176 (inf) time: 0.6393 [2021-03-27 03:06:15 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 770/1251] eta: 0:05:05 lr: 0.000625 loss: 3.4348 (3.4068) grad_norm: 1.3021 (inf) time: 0.6331 [2021-03-27 03:06:21 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 780/1251] eta: 0:04:59 lr: 0.000625 loss: 3.4428 (3.4047) grad_norm: 1.2676 (inf) time: 0.6277 [2021-03-27 03:06:27 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 790/1251] eta: 0:04:53 lr: 0.000625 loss: 3.3062 (3.4041) grad_norm: 1.2468 (inf) time: 0.6279 [2021-03-27 03:06:34 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 800/1251] eta: 0:04:46 lr: 0.000625 loss: 3.4807 (3.4054) grad_norm: 1.3407 (inf) time: 0.6315 [2021-03-27 03:06:40 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 810/1251] eta: 0:04:40 lr: 0.000625 loss: 3.5387 (3.4064) grad_norm: 1.4665 (inf) time: 0.6340 [2021-03-27 03:06:46 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 820/1251] eta: 0:04:33 lr: 0.000625 loss: 3.5301 (3.4058) grad_norm: 1.3147 (inf) time: 0.6371 [2021-03-27 03:06:53 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 830/1251] eta: 0:04:27 lr: 0.000625 loss: 3.4049 (3.4077) grad_norm: 1.3157 (inf) time: 0.6302 [2021-03-27 03:06:59 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 840/1251] eta: 0:04:21 lr: 0.000625 loss: 3.6426 (3.4094) grad_norm: 1.3446 (inf) time: 0.6243 [2021-03-27 03:07:05 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 850/1251] eta: 0:04:14 lr: 0.000625 loss: 3.6426 (3.4119) grad_norm: 1.3619 (inf) time: 0.6297 [2021-03-27 03:07:12 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 860/1251] eta: 0:04:08 lr: 0.000625 loss: 3.5708 (3.4107) grad_norm: 1.3703 (inf) time: 0.6378 [2021-03-27 03:07:18 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 870/1251] eta: 0:04:02 lr: 0.000625 loss: 3.4286 (3.4124) grad_norm: 1.3443 (inf) time: 0.6342 [2021-03-27 03:07:24 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 880/1251] eta: 0:03:55 lr: 0.000625 loss: 3.5537 (3.4139) grad_norm: 1.3191 (inf) time: 0.6265 [2021-03-27 03:07:31 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 890/1251] eta: 0:03:49 lr: 0.000625 loss: 3.5537 (3.4145) grad_norm: 1.3136 (inf) time: 0.6379 [2021-03-27 03:07:37 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 900/1251] eta: 0:03:42 lr: 0.000624 loss: 3.1608 (3.4114) grad_norm: 1.3367 (inf) time: 0.6371 [2021-03-27 03:07:43 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 910/1251] eta: 0:03:36 lr: 0.000624 loss: 3.0179 (3.4082) grad_norm: 1.4385 (inf) time: 0.6290 [2021-03-27 03:07:50 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 920/1251] eta: 0:03:30 lr: 0.000624 loss: 3.0194 (3.4068) grad_norm: 1.3783 (inf) time: 0.6336 [2021-03-27 03:07:56 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 930/1251] eta: 0:03:23 lr: 0.000624 loss: 3.4858 (3.4067) grad_norm: 1.3616 (inf) time: 0.6329 [2021-03-27 03:08:02 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 940/1251] eta: 0:03:17 lr: 0.000624 loss: 3.6185 (3.4068) grad_norm: 1.3817 (inf) time: 0.6287 [2021-03-27 03:08:09 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 950/1251] eta: 0:03:11 lr: 0.000624 loss: 3.4685 (3.4043) grad_norm: 1.2902 (inf) time: 0.6323 [2021-03-27 03:08:15 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 960/1251] eta: 0:03:04 lr: 0.000624 loss: 3.2910 (3.4029) grad_norm: 1.2922 (inf) time: 0.6330 [2021-03-27 03:08:21 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 970/1251] eta: 0:02:58 lr: 0.000624 loss: 3.4532 (3.4048) grad_norm: 1.3626 (inf) time: 0.6265 [2021-03-27 03:08:27 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 980/1251] eta: 0:02:52 lr: 0.000624 loss: 3.5891 (3.4025) grad_norm: 1.3948 (inf) time: 0.6226 [2021-03-27 03:08:34 swin_base_patch4_window7_224] INFO: Epoch: [126] [ 990/1251] eta: 0:02:45 lr: 0.000624 loss: 3.5891 (3.4045) grad_norm: 1.3493 (inf) time: 0.6259 [2021-03-27 03:08:40 swin_base_patch4_window7_224] INFO: Epoch: [126] [1000/1251] eta: 0:02:39 lr: 0.000624 loss: 3.6825 (3.4050) grad_norm: 1.3493 (inf) time: 0.6276 [2021-03-27 03:08:46 swin_base_patch4_window7_224] INFO: Epoch: [126] [1010/1251] eta: 0:02:32 lr: 0.000624 loss: 3.3593 (3.4056) grad_norm: 1.3438 (inf) time: 0.6249 [2021-03-27 03:08:52 swin_base_patch4_window7_224] INFO: Epoch: [126] [1020/1251] eta: 0:02:26 lr: 0.000624 loss: 3.4050 (3.4059) grad_norm: 1.3392 (inf) time: 0.6277 [2021-03-27 03:08:59 swin_base_patch4_window7_224] INFO: Epoch: [126] [1030/1251] eta: 0:02:20 lr: 0.000624 loss: 3.4770 (3.4065) grad_norm: 1.3128 (inf) time: 0.6248 [2021-03-27 03:09:05 swin_base_patch4_window7_224] INFO: Epoch: [126] [1040/1251] eta: 0:02:13 lr: 0.000624 loss: 3.4533 (3.4033) grad_norm: 1.2565 (inf) time: 0.6243 [2021-03-27 03:09:11 swin_base_patch4_window7_224] INFO: Epoch: [126] [1050/1251] eta: 0:02:07 lr: 0.000624 loss: 3.0818 (3.4030) grad_norm: 1.2565 (inf) time: 0.6317 [2021-03-27 03:09:18 swin_base_patch4_window7_224] INFO: Epoch: [126] [1060/1251] eta: 0:02:01 lr: 0.000624 loss: 3.3049 (3.4027) grad_norm: 1.2878 (inf) time: 0.6327 [2021-03-27 03:09:24 swin_base_patch4_window7_224] INFO: Epoch: [126] [1070/1251] eta: 0:01:54 lr: 0.000624 loss: 3.3338 (3.4023) grad_norm: 1.2708 (inf) time: 0.6294 [2021-03-27 03:09:30 swin_base_patch4_window7_224] INFO: Epoch: [126] [1080/1251] eta: 0:01:48 lr: 0.000624 loss: 3.5155 (3.4031) grad_norm: 1.3525 (inf) time: 0.6290 [2021-03-27 03:09:36 swin_base_patch4_window7_224] INFO: Epoch: [126] [1090/1251] eta: 0:01:42 lr: 0.000624 loss: 3.4823 (3.4022) grad_norm: 1.2660 (inf) time: 0.6313 [2021-03-27 03:09:43 swin_base_patch4_window7_224] INFO: Epoch: [126] [1100/1251] eta: 0:01:35 lr: 0.000624 loss: 3.2716 (3.4014) grad_norm: 1.2843 (inf) time: 0.6269 [2021-03-27 03:09:49 swin_base_patch4_window7_224] INFO: Epoch: [126] [1110/1251] eta: 0:01:29 lr: 0.000624 loss: 3.5422 (3.4022) grad_norm: 1.3506 (inf) time: 0.6265 [2021-03-27 03:09:55 swin_base_patch4_window7_224] INFO: Epoch: [126] [1120/1251] eta: 0:01:23 lr: 0.000624 loss: 3.4041 (3.4014) grad_norm: 1.2799 (inf) time: 0.6309 [2021-03-27 03:10:02 swin_base_patch4_window7_224] INFO: Epoch: [126] [1130/1251] eta: 0:01:16 lr: 0.000624 loss: 3.3756 (3.4027) grad_norm: 1.2778 (inf) time: 0.6270 [2021-03-27 03:10:08 swin_base_patch4_window7_224] INFO: Epoch: [126] [1140/1251] eta: 0:01:10 lr: 0.000624 loss: 3.3756 (3.4027) grad_norm: 1.2943 (inf) time: 0.6250 [2021-03-27 03:10:14 swin_base_patch4_window7_224] INFO: Epoch: [126] [1150/1251] eta: 0:01:04 lr: 0.000623 loss: 3.4131 (3.4028) grad_norm: 1.3312 (inf) time: 0.6317 [2021-03-27 03:10:21 swin_base_patch4_window7_224] INFO: Epoch: [126] [1160/1251] eta: 0:00:57 lr: 0.000623 loss: 3.2853 (3.4024) grad_norm: 1.3449 (inf) time: 0.6411 [2021-03-27 03:10:27 swin_base_patch4_window7_224] INFO: Epoch: [126] [1170/1251] eta: 0:00:51 lr: 0.000623 loss: 3.2667 (3.4021) grad_norm: 1.3341 (inf) time: 0.6351 [2021-03-27 03:10:33 swin_base_patch4_window7_224] INFO: Epoch: [126] [1180/1251] eta: 0:00:45 lr: 0.000623 loss: 3.3677 (3.4006) grad_norm: 1.3051 (inf) time: 0.6282 [2021-03-27 03:10:39 swin_base_patch4_window7_224] INFO: Epoch: [126] [1190/1251] eta: 0:00:38 lr: 0.000623 loss: 3.5174 (3.4002) grad_norm: 1.4005 (inf) time: 0.6291 [2021-03-27 03:10:46 swin_base_patch4_window7_224] INFO: Epoch: [126] [1200/1251] eta: 0:00:32 lr: 0.000623 loss: 3.5853 (3.3996) grad_norm: 1.4137 (inf) time: 0.6313 [2021-03-27 03:10:52 swin_base_patch4_window7_224] INFO: Epoch: [126] [1210/1251] eta: 0:00:25 lr: 0.000623 loss: 3.5853 (3.4016) grad_norm: 1.3024 (inf) time: 0.6333 [2021-03-27 03:10:58 swin_base_patch4_window7_224] INFO: Epoch: [126] [1220/1251] eta: 0:00:19 lr: 0.000623 loss: 3.6458 (3.4025) grad_norm: 1.3454 (inf) time: 0.6282 [2021-03-27 03:11:05 swin_base_patch4_window7_224] INFO: Epoch: [126] [1230/1251] eta: 0:00:13 lr: 0.000623 loss: 3.4476 (3.4029) grad_norm: 1.3533 (inf) time: 0.6268 [2021-03-27 03:11:11 swin_base_patch4_window7_224] INFO: Epoch: [126] [1240/1251] eta: 0:00:06 lr: 0.000623 loss: 3.6894 (3.4037) grad_norm: 1.3533 (inf) time: 0.6244 [2021-03-27 03:11:17 swin_base_patch4_window7_224] INFO: Epoch: [126] [1250/1251] eta: 0:00:00 lr: 0.000623 loss: 3.6424 (3.4053) grad_norm: 1.3728 (inf) time: 0.6166 [2021-03-27 03:11:26 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:19 loss: 1.0479 (1.0479) acc1: 73.4375 (73.4375) acc5: 95.3125 (95.3125) [2021-03-27 03:11:28 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0479 (1.0207) acc1: 75.0000 (75.8523) acc5: 93.7500 (94.1761) [2021-03-27 03:11:31 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9983 (1.0071) acc1: 78.1250 (76.7857) acc5: 93.7500 (93.3780) [2021-03-27 03:11:33 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9476 (0.9663) acc1: 78.1250 (77.5706) acc5: 93.7500 (94.0020) [2021-03-27 03:11:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8898 (0.9553) acc1: 79.6875 (78.1631) acc5: 95.3125 (94.2454) [2021-03-27 03:11:37 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9088 (0.9586) acc1: 79.6875 (78.0160) acc5: 93.7500 (94.2720) [2021-03-27 03:11:44 swin_base_patch4_window7_224] INFO: * Acc@1 77.902 Acc@5 94.350 loss 0.945 [2021-03-27 03:11:44 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.9% [2021-03-27 03:11:44 swin_base_patch4_window7_224] INFO: Max accuracy: 77.90% [2021-03-27 03:11:48 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 0/1251] eta: 1:22:58 lr: 0.000623 loss: 4.1608 (4.1608) grad_norm: 1.5383 (1.5383) time: 3.9793 [2021-03-27 03:11:55 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 10/1251] eta: 0:20:07 lr: 0.000623 loss: 3.7290 (3.5408) grad_norm: 1.2796 (1.3671) time: 0.9734 [2021-03-27 03:12:01 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 20/1251] eta: 0:16:33 lr: 0.000623 loss: 3.4904 (3.4627) grad_norm: 1.3431 (1.4349) time: 0.6485 [2021-03-27 03:12:08 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 30/1251] eta: 0:15:12 lr: 0.000623 loss: 3.3463 (3.4180) grad_norm: 1.4311 (1.4276) time: 0.6235 [2021-03-27 03:12:14 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 40/1251] eta: 0:14:34 lr: 0.000623 loss: 3.3108 (3.3812) grad_norm: 1.3372 (1.4055) time: 0.6325 [2021-03-27 03:12:20 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 50/1251] eta: 0:14:08 lr: 0.000623 loss: 3.2030 (3.3406) grad_norm: 1.2907 (1.3846) time: 0.6426 [2021-03-27 03:12:27 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 60/1251] eta: 0:13:46 lr: 0.000623 loss: 3.2494 (3.3387) grad_norm: 1.2819 (1.3822) time: 0.6354 [2021-03-27 03:12:33 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 70/1251] eta: 0:13:28 lr: 0.000623 loss: 3.2782 (3.3166) grad_norm: 1.3697 (1.3831) time: 0.6281 [2021-03-27 03:12:39 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 80/1251] eta: 0:13:13 lr: 0.000623 loss: 3.2326 (3.2849) grad_norm: 1.3354 (1.3707) time: 0.6282 [2021-03-27 03:12:45 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 90/1251] eta: 0:12:59 lr: 0.000623 loss: 3.0306 (3.2852) grad_norm: 1.2854 (1.3719) time: 0.6245 [2021-03-27 03:12:52 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 100/1251] eta: 0:12:48 lr: 0.000623 loss: 3.3933 (3.2958) grad_norm: 1.3436 (1.3728) time: 0.6268 [2021-03-27 03:12:58 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 110/1251] eta: 0:12:37 lr: 0.000623 loss: 3.4662 (3.3130) grad_norm: 1.3372 (1.3739) time: 0.6304 [2021-03-27 03:13:04 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 120/1251] eta: 0:12:27 lr: 0.000623 loss: 3.5803 (3.3205) grad_norm: 1.3864 (1.3746) time: 0.6260 [2021-03-27 03:13:11 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 130/1251] eta: 0:12:18 lr: 0.000623 loss: 3.3658 (3.3069) grad_norm: 1.4766 (1.3822) time: 0.6296 [2021-03-27 03:13:17 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 140/1251] eta: 0:12:09 lr: 0.000623 loss: 3.2179 (3.3057) grad_norm: 1.3395 (1.3741) time: 0.6303 [2021-03-27 03:13:23 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 150/1251] eta: 0:12:00 lr: 0.000622 loss: 3.3457 (3.3109) grad_norm: 1.2811 (1.3712) time: 0.6295 [2021-03-27 03:13:30 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 160/1251] eta: 0:11:52 lr: 0.000622 loss: 3.1357 (3.3064) grad_norm: 1.2640 (1.3605) time: 0.6303 [2021-03-27 03:13:36 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 170/1251] eta: 0:11:44 lr: 0.000622 loss: 3.5431 (3.3172) grad_norm: 1.2505 (1.3603) time: 0.6280 [2021-03-27 03:13:42 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 180/1251] eta: 0:11:36 lr: 0.000622 loss: 3.5578 (3.3283) grad_norm: 1.3198 (1.3628) time: 0.6299 [2021-03-27 03:13:48 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 190/1251] eta: 0:11:28 lr: 0.000622 loss: 3.6868 (3.3526) grad_norm: 1.2943 (1.3728) time: 0.6247 [2021-03-27 03:13:55 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 200/1251] eta: 0:11:21 lr: 0.000622 loss: 3.6538 (3.3575) grad_norm: 1.2943 (1.3701) time: 0.6298 [2021-03-27 03:14:01 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 210/1251] eta: 0:11:13 lr: 0.000622 loss: 3.4485 (3.3468) grad_norm: 1.2546 (1.3655) time: 0.6332 [2021-03-27 03:14:07 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 220/1251] eta: 0:11:07 lr: 0.000622 loss: 3.3522 (3.3584) grad_norm: 1.2464 (1.3641) time: 0.6341 [2021-03-27 03:14:14 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 230/1251] eta: 0:11:00 lr: 0.000622 loss: 3.4122 (3.3579) grad_norm: 1.3415 (1.3658) time: 0.6379 [2021-03-27 03:14:20 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 240/1251] eta: 0:10:52 lr: 0.000622 loss: 3.5442 (3.3653) grad_norm: 1.3300 (1.3637) time: 0.6284 [2021-03-27 03:14:26 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 250/1251] eta: 0:10:45 lr: 0.000622 loss: 3.5856 (3.3711) grad_norm: 1.2971 (1.3599) time: 0.6230 [2021-03-27 03:14:32 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 260/1251] eta: 0:10:38 lr: 0.000622 loss: 3.3612 (3.3668) grad_norm: 1.3403 (1.3631) time: 0.6232 [2021-03-27 03:14:39 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 270/1251] eta: 0:10:31 lr: 0.000622 loss: 3.2609 (3.3632) grad_norm: 1.3491 (1.3624) time: 0.6286 [2021-03-27 03:14:45 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 280/1251] eta: 0:10:24 lr: 0.000622 loss: 3.4674 (3.3649) grad_norm: 1.3202 (1.3653) time: 0.6303 [2021-03-27 03:14:51 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 290/1251] eta: 0:10:16 lr: 0.000622 loss: 3.4674 (3.3671) grad_norm: 1.3471 (1.3663) time: 0.6221 [2021-03-27 03:14:58 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 300/1251] eta: 0:10:10 lr: 0.000622 loss: 3.4526 (3.3615) grad_norm: 1.3645 (1.3688) time: 0.6237 [2021-03-27 03:15:04 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 310/1251] eta: 0:10:03 lr: 0.000622 loss: 3.3847 (3.3579) grad_norm: 1.3642 (1.3686) time: 0.6280 [2021-03-27 03:15:10 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 320/1251] eta: 0:09:56 lr: 0.000622 loss: 3.4774 (3.3629) grad_norm: 1.3900 (1.3725) time: 0.6246 [2021-03-27 03:15:16 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 330/1251] eta: 0:09:49 lr: 0.000622 loss: 3.5642 (3.3700) grad_norm: 1.4026 (1.3740) time: 0.6250 [2021-03-27 03:15:23 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 340/1251] eta: 0:09:43 lr: 0.000622 loss: 3.5642 (3.3694) grad_norm: 1.3401 (1.3736) time: 0.6319 [2021-03-27 03:15:29 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 350/1251] eta: 0:09:36 lr: 0.000622 loss: 3.3998 (3.3691) grad_norm: 1.3315 (1.3742) time: 0.6330 [2021-03-27 03:15:35 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 360/1251] eta: 0:09:29 lr: 0.000622 loss: 3.3459 (3.3698) grad_norm: 1.3683 (1.3741) time: 0.6327 [2021-03-27 03:15:42 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 370/1251] eta: 0:09:23 lr: 0.000622 loss: 3.3269 (3.3726) grad_norm: 1.3684 (1.3771) time: 0.6332 [2021-03-27 03:15:48 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 380/1251] eta: 0:09:16 lr: 0.000622 loss: 3.4607 (3.3742) grad_norm: 1.4108 (1.3793) time: 0.6255 [2021-03-27 03:15:54 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 390/1251] eta: 0:09:09 lr: 0.000622 loss: 3.5114 (3.3822) grad_norm: 1.4110 (1.3792) time: 0.6235 [2021-03-27 03:16:00 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 400/1251] eta: 0:09:03 lr: 0.000621 loss: 3.4635 (3.3794) grad_norm: 1.3323 (1.3784) time: 0.6315 [2021-03-27 03:16:07 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 410/1251] eta: 0:08:56 lr: 0.000621 loss: 3.2554 (3.3761) grad_norm: 1.3614 (1.3809) time: 0.6340 [2021-03-27 03:16:13 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 420/1251] eta: 0:08:50 lr: 0.000621 loss: 3.4805 (3.3761) grad_norm: 1.3999 (1.3801) time: 0.6399 [2021-03-27 03:16:20 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 430/1251] eta: 0:08:44 lr: 0.000621 loss: 3.4846 (3.3773) grad_norm: 1.4148 (1.3830) time: 0.6380 [2021-03-27 03:16:26 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 440/1251] eta: 0:08:37 lr: 0.000621 loss: 3.4146 (3.3758) grad_norm: 1.4829 (inf) time: 0.6283 [2021-03-27 03:16:32 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 450/1251] eta: 0:08:31 lr: 0.000621 loss: 3.3825 (3.3793) grad_norm: 1.4829 (inf) time: 0.6309 [2021-03-27 03:16:39 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 460/1251] eta: 0:08:24 lr: 0.000621 loss: 3.4956 (3.3791) grad_norm: 1.4583 (inf) time: 0.6364 [2021-03-27 03:16:45 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 470/1251] eta: 0:08:18 lr: 0.000621 loss: 3.4207 (3.3778) grad_norm: 1.4457 (inf) time: 0.6324 [2021-03-27 03:16:51 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 480/1251] eta: 0:08:11 lr: 0.000621 loss: 3.4451 (3.3772) grad_norm: 1.3317 (inf) time: 0.6327 [2021-03-27 03:16:58 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 490/1251] eta: 0:08:05 lr: 0.000621 loss: 3.4741 (3.3766) grad_norm: 1.3398 (inf) time: 0.6410 [2021-03-27 03:17:04 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 500/1251] eta: 0:07:58 lr: 0.000621 loss: 3.3885 (3.3749) grad_norm: 1.3630 (inf) time: 0.6374 [2021-03-27 03:17:10 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 510/1251] eta: 0:07:52 lr: 0.000621 loss: 3.1621 (3.3673) grad_norm: 1.3310 (inf) time: 0.6337 [2021-03-27 03:17:17 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 520/1251] eta: 0:07:46 lr: 0.000621 loss: 2.9980 (3.3655) grad_norm: 1.4156 (inf) time: 0.6349 [2021-03-27 03:17:23 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 530/1251] eta: 0:07:39 lr: 0.000621 loss: 3.2694 (3.3676) grad_norm: 1.3902 (inf) time: 0.6333 [2021-03-27 03:17:29 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 540/1251] eta: 0:07:33 lr: 0.000621 loss: 3.1856 (3.3611) grad_norm: 1.2939 (inf) time: 0.6316 [2021-03-27 03:17:36 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 550/1251] eta: 0:07:27 lr: 0.000621 loss: 3.4347 (3.3659) grad_norm: 1.2922 (inf) time: 0.6409 [2021-03-27 03:17:42 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 560/1251] eta: 0:07:20 lr: 0.000621 loss: 3.7350 (3.3704) grad_norm: 1.3091 (inf) time: 0.6416 [2021-03-27 03:17:49 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 570/1251] eta: 0:07:14 lr: 0.000621 loss: 3.5568 (3.3703) grad_norm: 1.3776 (inf) time: 0.6355 [2021-03-27 03:17:55 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 580/1251] eta: 0:07:07 lr: 0.000621 loss: 3.2560 (3.3660) grad_norm: 1.3771 (inf) time: 0.6340 [2021-03-27 03:18:01 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 590/1251] eta: 0:07:01 lr: 0.000621 loss: 3.3009 (3.3687) grad_norm: 1.2793 (inf) time: 0.6353 [2021-03-27 03:18:08 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 600/1251] eta: 0:06:55 lr: 0.000621 loss: 3.3995 (3.3687) grad_norm: 1.2922 (inf) time: 0.6403 [2021-03-27 03:18:14 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 610/1251] eta: 0:06:48 lr: 0.000621 loss: 3.3397 (3.3671) grad_norm: 1.3060 (inf) time: 0.6363 [2021-03-27 03:18:20 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 620/1251] eta: 0:06:42 lr: 0.000621 loss: 3.5654 (3.3717) grad_norm: 1.2611 (inf) time: 0.6342 [2021-03-27 03:18:27 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 630/1251] eta: 0:06:35 lr: 0.000621 loss: 3.5675 (3.3697) grad_norm: 1.3173 (inf) time: 0.6371 [2021-03-27 03:18:33 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 640/1251] eta: 0:06:29 lr: 0.000620 loss: 3.5150 (3.3711) grad_norm: 1.3868 (inf) time: 0.6422 [2021-03-27 03:18:39 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 650/1251] eta: 0:06:23 lr: 0.000620 loss: 3.5194 (3.3732) grad_norm: 1.3964 (inf) time: 0.6382 [2021-03-27 03:18:46 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 660/1251] eta: 0:06:16 lr: 0.000620 loss: 3.5119 (3.3730) grad_norm: 1.3208 (inf) time: 0.6318 [2021-03-27 03:18:52 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 670/1251] eta: 0:06:10 lr: 0.000620 loss: 3.3181 (3.3721) grad_norm: 1.3219 (inf) time: 0.6286 [2021-03-27 03:18:58 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 680/1251] eta: 0:06:03 lr: 0.000620 loss: 3.2038 (3.3695) grad_norm: 1.3285 (inf) time: 0.6215 [2021-03-27 03:19:05 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 690/1251] eta: 0:05:57 lr: 0.000620 loss: 3.4821 (3.3709) grad_norm: 1.3485 (inf) time: 0.6236 [2021-03-27 03:19:11 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 700/1251] eta: 0:05:50 lr: 0.000620 loss: 3.6757 (3.3751) grad_norm: 1.3949 (inf) time: 0.6267 [2021-03-27 03:19:17 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 710/1251] eta: 0:05:44 lr: 0.000620 loss: 3.5386 (3.3724) grad_norm: 1.4097 (inf) time: 0.6283 [2021-03-27 03:19:23 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 720/1251] eta: 0:05:38 lr: 0.000620 loss: 3.3477 (3.3709) grad_norm: 1.3687 (inf) time: 0.6324 [2021-03-27 03:19:30 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 730/1251] eta: 0:05:31 lr: 0.000620 loss: 3.4706 (3.3712) grad_norm: 1.2852 (inf) time: 0.6406 [2021-03-27 03:19:36 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 740/1251] eta: 0:05:25 lr: 0.000620 loss: 3.6729 (3.3745) grad_norm: 1.2805 (inf) time: 0.6411 [2021-03-27 03:19:43 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 750/1251] eta: 0:05:18 lr: 0.000620 loss: 3.5581 (3.3753) grad_norm: 1.2578 (inf) time: 0.6353 [2021-03-27 03:19:49 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 760/1251] eta: 0:05:12 lr: 0.000620 loss: 3.4869 (3.3751) grad_norm: 1.3358 (inf) time: 0.6358 [2021-03-27 03:19:55 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 770/1251] eta: 0:05:06 lr: 0.000620 loss: 3.5357 (3.3778) grad_norm: 1.3655 (inf) time: 0.6319 [2021-03-27 03:20:02 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 780/1251] eta: 0:04:59 lr: 0.000620 loss: 3.0928 (3.3705) grad_norm: 1.3426 (inf) time: 0.6266 [2021-03-27 03:20:08 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 790/1251] eta: 0:04:53 lr: 0.000620 loss: 2.9761 (3.3685) grad_norm: 1.2780 (inf) time: 0.6280 [2021-03-27 03:20:14 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 800/1251] eta: 0:04:47 lr: 0.000620 loss: 3.2302 (3.3687) grad_norm: 1.2813 (inf) time: 0.6385 [2021-03-27 03:20:21 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 810/1251] eta: 0:04:40 lr: 0.000620 loss: 3.5232 (3.3696) grad_norm: 1.3884 (inf) time: 0.6367 [2021-03-27 03:20:27 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 820/1251] eta: 0:04:34 lr: 0.000620 loss: 3.4757 (3.3701) grad_norm: 1.4000 (inf) time: 0.6320 [2021-03-27 03:20:33 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 830/1251] eta: 0:04:27 lr: 0.000620 loss: 3.3983 (3.3698) grad_norm: 1.3615 (inf) time: 0.6320 [2021-03-27 03:20:39 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 840/1251] eta: 0:04:21 lr: 0.000620 loss: 3.3983 (3.3709) grad_norm: 1.3319 (inf) time: 0.6256 [2021-03-27 03:20:46 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 850/1251] eta: 0:04:15 lr: 0.000620 loss: 3.6039 (3.3723) grad_norm: 1.3722 (inf) time: 0.6226 [2021-03-27 03:20:52 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 860/1251] eta: 0:04:08 lr: 0.000620 loss: 3.4495 (3.3705) grad_norm: 1.3075 (inf) time: 0.6244 [2021-03-27 03:20:58 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 870/1251] eta: 0:04:02 lr: 0.000620 loss: 3.1484 (3.3657) grad_norm: 1.3254 (inf) time: 0.6293 [2021-03-27 03:21:05 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 880/1251] eta: 0:03:55 lr: 0.000620 loss: 3.1484 (3.3640) grad_norm: 1.3888 (inf) time: 0.6291 [2021-03-27 03:21:11 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 890/1251] eta: 0:03:49 lr: 0.000619 loss: 2.9635 (3.3611) grad_norm: 1.4070 (inf) time: 0.6358 [2021-03-27 03:21:17 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 900/1251] eta: 0:03:43 lr: 0.000619 loss: 3.2635 (3.3628) grad_norm: 1.3806 (inf) time: 0.6370 [2021-03-27 03:21:24 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 910/1251] eta: 0:03:36 lr: 0.000619 loss: 3.4957 (3.3643) grad_norm: 1.3690 (inf) time: 0.6281 [2021-03-27 03:21:30 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 920/1251] eta: 0:03:30 lr: 0.000619 loss: 3.6479 (3.3681) grad_norm: 1.3155 (inf) time: 0.6358 [2021-03-27 03:21:36 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 930/1251] eta: 0:03:24 lr: 0.000619 loss: 3.6001 (3.3665) grad_norm: 1.2607 (inf) time: 0.6399 [2021-03-27 03:21:43 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 940/1251] eta: 0:03:17 lr: 0.000619 loss: 3.4395 (3.3665) grad_norm: 1.2657 (inf) time: 0.6301 [2021-03-27 03:21:49 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 950/1251] eta: 0:03:11 lr: 0.000619 loss: 3.5724 (3.3687) grad_norm: 1.3339 (inf) time: 0.6282 [2021-03-27 03:21:55 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 960/1251] eta: 0:03:04 lr: 0.000619 loss: 3.5724 (3.3693) grad_norm: 1.4125 (inf) time: 0.6338 [2021-03-27 03:22:02 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 970/1251] eta: 0:02:58 lr: 0.000619 loss: 3.6505 (3.3711) grad_norm: 1.3816 (inf) time: 0.6392 [2021-03-27 03:22:08 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 980/1251] eta: 0:02:52 lr: 0.000619 loss: 3.6221 (3.3720) grad_norm: 1.3318 (inf) time: 0.6323 [2021-03-27 03:22:14 swin_base_patch4_window7_224] INFO: Epoch: [127] [ 990/1251] eta: 0:02:45 lr: 0.000619 loss: 3.2864 (3.3716) grad_norm: 1.3274 (inf) time: 0.6241 [2021-03-27 03:22:21 swin_base_patch4_window7_224] INFO: Epoch: [127] [1000/1251] eta: 0:02:39 lr: 0.000619 loss: 3.2864 (3.3717) grad_norm: 1.4299 (inf) time: 0.6293 [2021-03-27 03:22:27 swin_base_patch4_window7_224] INFO: Epoch: [127] [1010/1251] eta: 0:02:33 lr: 0.000619 loss: 3.3449 (3.3709) grad_norm: 1.4985 (inf) time: 0.6316 [2021-03-27 03:22:33 swin_base_patch4_window7_224] INFO: Epoch: [127] [1020/1251] eta: 0:02:26 lr: 0.000619 loss: 3.3922 (3.3705) grad_norm: 1.3700 (inf) time: 0.6361 [2021-03-27 03:22:40 swin_base_patch4_window7_224] INFO: Epoch: [127] [1030/1251] eta: 0:02:20 lr: 0.000619 loss: 3.4207 (3.3680) grad_norm: 1.3598 (inf) time: 0.6345 [2021-03-27 03:22:46 swin_base_patch4_window7_224] INFO: Epoch: [127] [1040/1251] eta: 0:02:14 lr: 0.000619 loss: 3.2386 (3.3669) grad_norm: 1.2996 (inf) time: 0.6315 [2021-03-27 03:22:52 swin_base_patch4_window7_224] INFO: Epoch: [127] [1050/1251] eta: 0:02:07 lr: 0.000619 loss: 3.4299 (3.3673) grad_norm: 1.2782 (inf) time: 0.6293 [2021-03-27 03:22:58 swin_base_patch4_window7_224] INFO: Epoch: [127] [1060/1251] eta: 0:02:01 lr: 0.000619 loss: 3.4541 (3.3672) grad_norm: 1.2831 (inf) time: 0.6281 [2021-03-27 03:23:05 swin_base_patch4_window7_224] INFO: Epoch: [127] [1070/1251] eta: 0:01:54 lr: 0.000619 loss: 3.4524 (3.3674) grad_norm: 1.2831 (inf) time: 0.6278 [2021-03-27 03:23:11 swin_base_patch4_window7_224] INFO: Epoch: [127] [1080/1251] eta: 0:01:48 lr: 0.000619 loss: 3.2439 (3.3660) grad_norm: 1.2295 (inf) time: 0.6268 [2021-03-27 03:23:17 swin_base_patch4_window7_224] INFO: Epoch: [127] [1090/1251] eta: 0:01:42 lr: 0.000619 loss: 3.2439 (3.3665) grad_norm: 1.2561 (inf) time: 0.6327 [2021-03-27 03:23:24 swin_base_patch4_window7_224] INFO: Epoch: [127] [1100/1251] eta: 0:01:35 lr: 0.000619 loss: 3.4669 (3.3673) grad_norm: 1.3237 (inf) time: 0.6309 [2021-03-27 03:23:30 swin_base_patch4_window7_224] INFO: Epoch: [127] [1110/1251] eta: 0:01:29 lr: 0.000619 loss: 3.3681 (3.3658) grad_norm: 1.2886 (inf) time: 0.6261 [2021-03-27 03:23:36 swin_base_patch4_window7_224] INFO: Epoch: [127] [1120/1251] eta: 0:01:23 lr: 0.000619 loss: 3.0721 (3.3644) grad_norm: 1.2881 (inf) time: 0.6276 [2021-03-27 03:23:42 swin_base_patch4_window7_224] INFO: Epoch: [127] [1130/1251] eta: 0:01:16 lr: 0.000619 loss: 3.0973 (3.3642) grad_norm: 1.3172 (inf) time: 0.6303 [2021-03-27 03:23:49 swin_base_patch4_window7_224] INFO: Epoch: [127] [1140/1251] eta: 0:01:10 lr: 0.000618 loss: 3.4962 (3.3648) grad_norm: 1.2876 (inf) time: 0.6310 [2021-03-27 03:23:55 swin_base_patch4_window7_224] INFO: Epoch: [127] [1150/1251] eta: 0:01:04 lr: 0.000618 loss: 3.4669 (3.3632) grad_norm: 1.2676 (inf) time: 0.6325 [2021-03-27 03:24:01 swin_base_patch4_window7_224] INFO: Epoch: [127] [1160/1251] eta: 0:00:57 lr: 0.000618 loss: 3.3913 (3.3639) grad_norm: 1.2934 (inf) time: 0.6281 [2021-03-27 03:24:08 swin_base_patch4_window7_224] INFO: Epoch: [127] [1170/1251] eta: 0:00:51 lr: 0.000618 loss: 3.3404 (3.3642) grad_norm: 1.3381 (inf) time: 0.6273 [2021-03-27 03:24:14 swin_base_patch4_window7_224] INFO: Epoch: [127] [1180/1251] eta: 0:00:45 lr: 0.000618 loss: 3.5483 (3.3656) grad_norm: 1.3996 (inf) time: 0.6290 [2021-03-27 03:24:20 swin_base_patch4_window7_224] INFO: Epoch: [127] [1190/1251] eta: 0:00:38 lr: 0.000618 loss: 3.4486 (3.3643) grad_norm: 1.3175 (inf) time: 0.6280 [2021-03-27 03:24:27 swin_base_patch4_window7_224] INFO: Epoch: [127] [1200/1251] eta: 0:00:32 lr: 0.000618 loss: 3.4486 (3.3655) grad_norm: 1.3891 (inf) time: 0.6305 [2021-03-27 03:24:33 swin_base_patch4_window7_224] INFO: Epoch: [127] [1210/1251] eta: 0:00:26 lr: 0.000618 loss: 3.6309 (3.3658) grad_norm: 1.3735 (inf) time: 0.6335 [2021-03-27 03:24:39 swin_base_patch4_window7_224] INFO: Epoch: [127] [1220/1251] eta: 0:00:19 lr: 0.000618 loss: 3.5615 (3.3666) grad_norm: 1.3370 (inf) time: 0.6314 [2021-03-27 03:24:45 swin_base_patch4_window7_224] INFO: Epoch: [127] [1230/1251] eta: 0:00:13 lr: 0.000618 loss: 3.5558 (3.3657) grad_norm: 1.3511 (inf) time: 0.6263 [2021-03-27 03:24:52 swin_base_patch4_window7_224] INFO: Epoch: [127] [1240/1251] eta: 0:00:06 lr: 0.000618 loss: 3.5482 (3.3671) grad_norm: 1.3511 (inf) time: 0.6305 [2021-03-27 03:24:58 swin_base_patch4_window7_224] INFO: Epoch: [127] [1250/1251] eta: 0:00:00 lr: 0.000618 loss: 3.4325 (3.3662) grad_norm: 1.3323 (inf) time: 0.6392 [2021-03-27 03:25:06 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:14 loss: 0.8696 (0.8696) acc1: 79.6875 (79.6875) acc5: 96.8750 (96.8750) [2021-03-27 03:25:08 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8696 (0.8826) acc1: 79.6875 (80.1136) acc5: 95.3125 (95.5966) [2021-03-27 03:25:10 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9496 (0.9632) acc1: 78.1250 (77.4554) acc5: 95.3125 (95.3869) [2021-03-27 03:25:12 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9544 (0.9586) acc1: 78.1250 (78.1250) acc5: 95.3125 (95.0101) [2021-03-27 03:25:14 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9048 (0.9647) acc1: 78.1250 (77.7058) acc5: 95.3125 (94.9695) [2021-03-27 03:25:16 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9619 (0.9704) acc1: 76.5625 (77.6640) acc5: 95.3125 (94.8480) [2021-03-27 03:25:22 swin_base_patch4_window7_224] INFO: * Acc@1 77.784 Acc@5 94.410 loss 0.949 [2021-03-27 03:25:22 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.8% [2021-03-27 03:25:22 swin_base_patch4_window7_224] INFO: Max accuracy: 77.90% [2021-03-27 03:25:27 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 0/1251] eta: 1:35:54 lr: 0.000618 loss: 3.1455 (3.1455) grad_norm: 1.3246 (1.3246) time: 4.6000 [2021-03-27 03:25:33 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 10/1251] eta: 0:20:39 lr: 0.000618 loss: 3.3974 (3.2379) grad_norm: 1.3270 (1.3161) time: 0.9986 [2021-03-27 03:25:40 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 20/1251] eta: 0:16:51 lr: 0.000618 loss: 3.4241 (3.3823) grad_norm: 1.2881 (1.3109) time: 0.6329 [2021-03-27 03:25:46 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 30/1251] eta: 0:15:28 lr: 0.000618 loss: 3.3156 (3.2200) grad_norm: 1.3040 (1.3427) time: 0.6298 [2021-03-27 03:25:52 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 40/1251] eta: 0:14:41 lr: 0.000618 loss: 3.1915 (3.3030) grad_norm: 1.3512 (1.3444) time: 0.6286 [2021-03-27 03:25:59 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 50/1251] eta: 0:14:11 lr: 0.000618 loss: 3.5274 (3.3457) grad_norm: 1.2993 (1.3267) time: 0.6298 [2021-03-27 03:26:05 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 60/1251] eta: 0:13:48 lr: 0.000618 loss: 3.5208 (3.3771) grad_norm: 1.2746 (1.3375) time: 0.6296 [2021-03-27 03:26:11 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 70/1251] eta: 0:13:30 lr: 0.000618 loss: 3.4845 (3.3926) grad_norm: 1.3091 (1.3278) time: 0.6261 [2021-03-27 03:26:17 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 80/1251] eta: 0:13:14 lr: 0.000618 loss: 3.5607 (3.4145) grad_norm: 1.3121 (1.3492) time: 0.6260 [2021-03-27 03:26:24 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 90/1251] eta: 0:13:02 lr: 0.000618 loss: 3.6907 (3.4335) grad_norm: 1.3888 (1.3601) time: 0.6318 [2021-03-27 03:26:30 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 100/1251] eta: 0:12:50 lr: 0.000618 loss: 3.6722 (3.4356) grad_norm: 1.4451 (1.3734) time: 0.6318 [2021-03-27 03:26:36 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 110/1251] eta: 0:12:40 lr: 0.000618 loss: 3.6237 (3.4395) grad_norm: 1.4899 (1.3822) time: 0.6327 [2021-03-27 03:26:43 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 120/1251] eta: 0:12:31 lr: 0.000618 loss: 3.6237 (3.4573) grad_norm: 1.4377 (1.3870) time: 0.6392 [2021-03-27 03:26:49 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 130/1251] eta: 0:12:21 lr: 0.000618 loss: 3.4630 (3.4249) grad_norm: 1.2874 (1.3793) time: 0.6306 [2021-03-27 03:26:55 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 140/1251] eta: 0:12:11 lr: 0.000617 loss: 3.2514 (3.4226) grad_norm: 1.2759 (1.3786) time: 0.6267 [2021-03-27 03:27:02 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 150/1251] eta: 0:12:02 lr: 0.000617 loss: 3.6062 (3.4192) grad_norm: 1.3892 (1.3877) time: 0.6244 [2021-03-27 03:27:08 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 160/1251] eta: 0:11:53 lr: 0.000617 loss: 3.5420 (3.4185) grad_norm: 1.4814 (1.3924) time: 0.6222 [2021-03-27 03:27:14 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 170/1251] eta: 0:11:45 lr: 0.000617 loss: 3.5420 (3.4248) grad_norm: 1.3402 (1.3911) time: 0.6266 [2021-03-27 03:27:20 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 180/1251] eta: 0:11:38 lr: 0.000617 loss: 3.6542 (3.4211) grad_norm: 1.3137 (1.3894) time: 0.6318 [2021-03-27 03:27:27 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 190/1251] eta: 0:11:30 lr: 0.000617 loss: 3.7164 (3.4388) grad_norm: 1.2790 (1.3823) time: 0.6331 [2021-03-27 03:27:33 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 200/1251] eta: 0:11:23 lr: 0.000617 loss: 3.7013 (3.4372) grad_norm: 1.2686 (1.3800) time: 0.6405 [2021-03-27 03:27:40 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 210/1251] eta: 0:11:16 lr: 0.000617 loss: 3.3558 (3.4314) grad_norm: 1.2750 (1.3775) time: 0.6385 [2021-03-27 03:27:46 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 220/1251] eta: 0:11:08 lr: 0.000617 loss: 3.2612 (3.4248) grad_norm: 1.3264 (1.3750) time: 0.6243 [2021-03-27 03:27:52 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 230/1251] eta: 0:11:01 lr: 0.000617 loss: 3.4152 (3.4280) grad_norm: 1.3387 (1.3764) time: 0.6273 [2021-03-27 03:27:58 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 240/1251] eta: 0:10:54 lr: 0.000617 loss: 3.4520 (3.4250) grad_norm: 1.3923 (1.3803) time: 0.6348 [2021-03-27 03:28:05 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 250/1251] eta: 0:10:47 lr: 0.000617 loss: 3.4197 (3.4170) grad_norm: 1.3407 (1.3792) time: 0.6398 [2021-03-27 03:28:11 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 260/1251] eta: 0:10:40 lr: 0.000617 loss: 3.1807 (3.4071) grad_norm: 1.3309 (1.3797) time: 0.6380 [2021-03-27 03:28:18 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 270/1251] eta: 0:10:34 lr: 0.000617 loss: 3.2632 (3.4045) grad_norm: 1.3334 (1.3782) time: 0.6380 [2021-03-27 03:28:24 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 280/1251] eta: 0:10:27 lr: 0.000617 loss: 3.4522 (3.3969) grad_norm: 1.4067 (1.3836) time: 0.6384 [2021-03-27 03:28:30 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 290/1251] eta: 0:10:20 lr: 0.000617 loss: 3.4522 (3.3966) grad_norm: 1.3971 (1.3809) time: 0.6302 [2021-03-27 03:28:36 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 300/1251] eta: 0:10:12 lr: 0.000617 loss: 3.3513 (3.3916) grad_norm: 1.2763 (1.3781) time: 0.6220 [2021-03-27 03:28:43 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 310/1251] eta: 0:10:06 lr: 0.000617 loss: 3.3314 (3.3906) grad_norm: 1.2863 (1.3778) time: 0.6266 [2021-03-27 03:28:49 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 320/1251] eta: 0:09:59 lr: 0.000617 loss: 3.3732 (3.3894) grad_norm: 1.3146 (1.3779) time: 0.6342 [2021-03-27 03:28:55 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 330/1251] eta: 0:09:52 lr: 0.000617 loss: 3.5538 (3.3921) grad_norm: 1.2775 (1.3741) time: 0.6293 [2021-03-27 03:29:02 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 340/1251] eta: 0:09:45 lr: 0.000617 loss: 3.4659 (3.3915) grad_norm: 1.3071 (1.3741) time: 0.6243 [2021-03-27 03:29:08 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 350/1251] eta: 0:09:38 lr: 0.000617 loss: 3.4492 (3.3838) grad_norm: 1.3145 (1.3724) time: 0.6272 [2021-03-27 03:29:14 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 360/1251] eta: 0:09:31 lr: 0.000617 loss: 3.5514 (3.3907) grad_norm: 1.2644 (1.3715) time: 0.6313 [2021-03-27 03:29:21 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 370/1251] eta: 0:09:25 lr: 0.000617 loss: 3.6206 (3.3935) grad_norm: 1.2825 (1.3716) time: 0.6312 [2021-03-27 03:29:27 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 380/1251] eta: 0:09:18 lr: 0.000617 loss: 3.5764 (3.3928) grad_norm: 1.3717 (1.3758) time: 0.6301 [2021-03-27 03:29:33 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 390/1251] eta: 0:09:11 lr: 0.000616 loss: 3.5712 (3.3941) grad_norm: 1.3929 (1.3767) time: 0.6262 [2021-03-27 03:29:39 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 400/1251] eta: 0:09:05 lr: 0.000616 loss: 3.3994 (3.3961) grad_norm: 1.3020 (1.3751) time: 0.6278 [2021-03-27 03:29:46 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 410/1251] eta: 0:08:59 lr: 0.000616 loss: 3.3131 (3.3905) grad_norm: 1.2575 (1.3744) time: 0.6425 [2021-03-27 03:29:52 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 420/1251] eta: 0:08:52 lr: 0.000616 loss: 3.3131 (3.3890) grad_norm: 1.2756 (1.3748) time: 0.6438 [2021-03-27 03:29:59 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 430/1251] eta: 0:08:45 lr: 0.000616 loss: 3.2864 (3.3881) grad_norm: 1.2616 (1.3724) time: 0.6272 [2021-03-27 03:30:05 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 440/1251] eta: 0:08:39 lr: 0.000616 loss: 3.3610 (3.3851) grad_norm: 1.2932 (1.3720) time: 0.6298 [2021-03-27 03:30:11 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 450/1251] eta: 0:08:32 lr: 0.000616 loss: 3.3610 (3.3814) grad_norm: 1.2932 (1.3706) time: 0.6313 [2021-03-27 03:30:17 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 460/1251] eta: 0:08:25 lr: 0.000616 loss: 3.4761 (3.3867) grad_norm: 1.2922 (1.3693) time: 0.6255 [2021-03-27 03:30:24 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 470/1251] eta: 0:08:19 lr: 0.000616 loss: 3.5517 (3.3861) grad_norm: 1.3184 (1.3695) time: 0.6280 [2021-03-27 03:30:30 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 480/1251] eta: 0:08:12 lr: 0.000616 loss: 3.5000 (3.3875) grad_norm: 1.2932 (1.3694) time: 0.6265 [2021-03-27 03:30:36 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 490/1251] eta: 0:08:06 lr: 0.000616 loss: 3.3977 (3.3821) grad_norm: 1.2987 (1.3693) time: 0.6236 [2021-03-27 03:30:42 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 500/1251] eta: 0:07:59 lr: 0.000616 loss: 3.3339 (3.3833) grad_norm: 1.3462 (1.3712) time: 0.6228 [2021-03-27 03:30:49 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 510/1251] eta: 0:07:52 lr: 0.000616 loss: 3.3339 (3.3782) grad_norm: 1.3314 (1.3715) time: 0.6238 [2021-03-27 03:30:55 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 520/1251] eta: 0:07:46 lr: 0.000616 loss: 3.1093 (3.3758) grad_norm: 1.3314 (1.3730) time: 0.6325 [2021-03-27 03:31:01 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 530/1251] eta: 0:07:40 lr: 0.000616 loss: 3.3572 (3.3781) grad_norm: 1.2811 (1.3717) time: 0.6348 [2021-03-27 03:31:08 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 540/1251] eta: 0:07:33 lr: 0.000616 loss: 3.4240 (3.3807) grad_norm: 1.2311 (1.3705) time: 0.6309 [2021-03-27 03:31:14 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 550/1251] eta: 0:07:27 lr: 0.000616 loss: 3.4652 (3.3844) grad_norm: 1.3076 (1.3703) time: 0.6460 [2021-03-27 03:31:21 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 560/1251] eta: 0:07:21 lr: 0.000616 loss: 3.3005 (3.3808) grad_norm: 1.3950 (1.3717) time: 0.6464 [2021-03-27 03:31:27 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 570/1251] eta: 0:07:14 lr: 0.000616 loss: 3.2135 (3.3799) grad_norm: 1.4315 (1.3720) time: 0.6333 [2021-03-27 03:31:33 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 580/1251] eta: 0:07:08 lr: 0.000616 loss: 3.4993 (3.3791) grad_norm: 1.3424 (1.3740) time: 0.6272 [2021-03-27 03:31:40 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 590/1251] eta: 0:07:01 lr: 0.000616 loss: 3.3432 (3.3792) grad_norm: 1.3424 (1.3736) time: 0.6287 [2021-03-27 03:31:46 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 600/1251] eta: 0:06:55 lr: 0.000616 loss: 3.3444 (3.3784) grad_norm: 1.4050 (1.3760) time: 0.6385 [2021-03-27 03:31:52 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 610/1251] eta: 0:06:48 lr: 0.000616 loss: 3.4200 (3.3794) grad_norm: 1.3930 (1.3757) time: 0.6319 [2021-03-27 03:31:58 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 620/1251] eta: 0:06:42 lr: 0.000616 loss: 3.4200 (3.3776) grad_norm: 1.3404 (1.3752) time: 0.6218 [2021-03-27 03:32:05 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 630/1251] eta: 0:06:35 lr: 0.000615 loss: 3.2421 (3.3740) grad_norm: 1.3537 (1.3754) time: 0.6211 [2021-03-27 03:32:11 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 640/1251] eta: 0:06:29 lr: 0.000615 loss: 3.2421 (3.3730) grad_norm: 1.3775 (1.3788) time: 0.6258 [2021-03-27 03:32:17 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 650/1251] eta: 0:06:22 lr: 0.000615 loss: 3.4072 (3.3734) grad_norm: 1.4442 (1.3801) time: 0.6316 [2021-03-27 03:32:24 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 660/1251] eta: 0:06:16 lr: 0.000615 loss: 3.5352 (3.3731) grad_norm: 1.4138 (1.3808) time: 0.6284 [2021-03-27 03:32:30 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 670/1251] eta: 0:06:09 lr: 0.000615 loss: 3.3341 (3.3693) grad_norm: 1.3969 (1.3812) time: 0.6237 [2021-03-27 03:32:36 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 680/1251] eta: 0:06:03 lr: 0.000615 loss: 3.0831 (3.3667) grad_norm: 1.3789 (1.3808) time: 0.6242 [2021-03-27 03:32:42 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 690/1251] eta: 0:05:56 lr: 0.000615 loss: 3.2951 (3.3706) grad_norm: 1.2799 (1.3794) time: 0.6245 [2021-03-27 03:32:49 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 700/1251] eta: 0:05:50 lr: 0.000615 loss: 3.6834 (3.3721) grad_norm: 1.2687 (1.3786) time: 0.6288 [2021-03-27 03:32:55 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 710/1251] eta: 0:05:44 lr: 0.000615 loss: 3.5137 (3.3707) grad_norm: 1.3095 (1.3779) time: 0.6296 [2021-03-27 03:33:01 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 720/1251] eta: 0:05:37 lr: 0.000615 loss: 3.5137 (3.3747) grad_norm: 1.3697 (1.3784) time: 0.6263 [2021-03-27 03:33:08 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 730/1251] eta: 0:05:31 lr: 0.000615 loss: 3.4872 (3.3729) grad_norm: 1.4341 (1.3804) time: 0.6424 [2021-03-27 03:33:14 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 740/1251] eta: 0:05:25 lr: 0.000615 loss: 3.1915 (3.3708) grad_norm: 1.4341 (1.3803) time: 0.6438 [2021-03-27 03:33:20 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 750/1251] eta: 0:05:18 lr: 0.000615 loss: 3.3760 (3.3726) grad_norm: 1.3534 (1.3799) time: 0.6301 [2021-03-27 03:33:27 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 760/1251] eta: 0:05:12 lr: 0.000615 loss: 3.3813 (3.3715) grad_norm: 1.3311 (1.3791) time: 0.6320 [2021-03-27 03:33:33 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 770/1251] eta: 0:05:05 lr: 0.000615 loss: 3.3749 (3.3709) grad_norm: 1.2637 (1.3782) time: 0.6327 [2021-03-27 03:33:39 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 780/1251] eta: 0:04:59 lr: 0.000615 loss: 3.3069 (3.3648) grad_norm: 1.3020 (1.3790) time: 0.6278 [2021-03-27 03:33:45 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 790/1251] eta: 0:04:53 lr: 0.000615 loss: 3.4267 (3.3686) grad_norm: 1.4093 (1.3800) time: 0.6268 [2021-03-27 03:33:52 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 800/1251] eta: 0:04:46 lr: 0.000615 loss: 3.6412 (3.3689) grad_norm: 1.4093 (1.3813) time: 0.6321 [2021-03-27 03:33:58 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 810/1251] eta: 0:04:40 lr: 0.000615 loss: 3.4132 (3.3690) grad_norm: 1.3770 (1.3816) time: 0.6321 [2021-03-27 03:34:04 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 820/1251] eta: 0:04:33 lr: 0.000615 loss: 3.4391 (3.3687) grad_norm: 1.3126 (1.3805) time: 0.6300 [2021-03-27 03:34:11 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 830/1251] eta: 0:04:27 lr: 0.000615 loss: 3.4687 (3.3709) grad_norm: 1.2636 (1.3805) time: 0.6315 [2021-03-27 03:34:17 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 840/1251] eta: 0:04:21 lr: 0.000615 loss: 3.3829 (3.3691) grad_norm: 1.3251 (1.3807) time: 0.6294 [2021-03-27 03:34:23 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 850/1251] eta: 0:04:14 lr: 0.000615 loss: 3.5278 (3.3702) grad_norm: 1.3038 (1.3795) time: 0.6267 [2021-03-27 03:34:30 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 860/1251] eta: 0:04:08 lr: 0.000615 loss: 3.5523 (3.3731) grad_norm: 1.2935 (1.3790) time: 0.6303 [2021-03-27 03:34:36 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 870/1251] eta: 0:04:02 lr: 0.000615 loss: 3.5313 (3.3720) grad_norm: 1.2890 (1.3788) time: 0.6437 [2021-03-27 03:34:42 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 880/1251] eta: 0:03:55 lr: 0.000614 loss: 3.3921 (3.3727) grad_norm: 1.2534 (1.3779) time: 0.6384 [2021-03-27 03:34:49 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 890/1251] eta: 0:03:49 lr: 0.000614 loss: 3.3034 (3.3699) grad_norm: 1.2534 (1.3773) time: 0.6291 [2021-03-27 03:34:55 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 900/1251] eta: 0:03:42 lr: 0.000614 loss: 3.1942 (3.3690) grad_norm: 1.3499 (1.3770) time: 0.6311 [2021-03-27 03:35:01 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 910/1251] eta: 0:03:36 lr: 0.000614 loss: 3.6556 (3.3711) grad_norm: 1.3499 (1.3760) time: 0.6263 [2021-03-27 03:35:08 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 920/1251] eta: 0:03:30 lr: 0.000614 loss: 3.4609 (3.3690) grad_norm: 1.2996 (1.3764) time: 0.6272 [2021-03-27 03:35:14 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 930/1251] eta: 0:03:23 lr: 0.000614 loss: 3.4609 (3.3707) grad_norm: 1.2996 (1.3759) time: 0.6275 [2021-03-27 03:35:20 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 940/1251] eta: 0:03:17 lr: 0.000614 loss: 3.4895 (3.3726) grad_norm: 1.2442 (1.3745) time: 0.6247 [2021-03-27 03:35:26 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 950/1251] eta: 0:03:11 lr: 0.000614 loss: 3.4207 (3.3706) grad_norm: 1.2447 (1.3746) time: 0.6273 [2021-03-27 03:35:33 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 960/1251] eta: 0:03:04 lr: 0.000614 loss: 3.4945 (3.3696) grad_norm: 1.3091 (1.3736) time: 0.6259 [2021-03-27 03:35:39 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 970/1251] eta: 0:02:58 lr: 0.000614 loss: 3.5102 (3.3717) grad_norm: 1.3091 (1.3738) time: 0.6259 [2021-03-27 03:35:45 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 980/1251] eta: 0:02:51 lr: 0.000614 loss: 3.5872 (3.3738) grad_norm: 1.3651 (1.3747) time: 0.6266 [2021-03-27 03:35:51 swin_base_patch4_window7_224] INFO: Epoch: [128] [ 990/1251] eta: 0:02:45 lr: 0.000614 loss: 3.5606 (3.3753) grad_norm: 1.3651 (1.3747) time: 0.6274 [2021-03-27 03:35:58 swin_base_patch4_window7_224] INFO: Epoch: [128] [1000/1251] eta: 0:02:39 lr: 0.000614 loss: 3.4991 (3.3758) grad_norm: 1.3456 (1.3742) time: 0.6329 [2021-03-27 03:36:04 swin_base_patch4_window7_224] INFO: Epoch: [128] [1010/1251] eta: 0:02:32 lr: 0.000614 loss: 3.5182 (3.3784) grad_norm: 1.2459 (1.3734) time: 0.6300 [2021-03-27 03:36:10 swin_base_patch4_window7_224] INFO: Epoch: [128] [1020/1251] eta: 0:02:26 lr: 0.000614 loss: 3.4246 (3.3783) grad_norm: 1.2831 (1.3731) time: 0.6271 [2021-03-27 03:36:17 swin_base_patch4_window7_224] INFO: Epoch: [128] [1030/1251] eta: 0:02:20 lr: 0.000614 loss: 3.3590 (3.3783) grad_norm: 1.3531 (1.3727) time: 0.6325 [2021-03-27 03:36:23 swin_base_patch4_window7_224] INFO: Epoch: [128] [1040/1251] eta: 0:02:13 lr: 0.000614 loss: 3.6981 (3.3797) grad_norm: 1.2912 (1.3728) time: 0.6311 [2021-03-27 03:36:29 swin_base_patch4_window7_224] INFO: Epoch: [128] [1050/1251] eta: 0:02:07 lr: 0.000614 loss: 3.4362 (3.3785) grad_norm: 1.3168 (1.3739) time: 0.6250 [2021-03-27 03:36:36 swin_base_patch4_window7_224] INFO: Epoch: [128] [1060/1251] eta: 0:02:01 lr: 0.000614 loss: 3.2078 (3.3764) grad_norm: 1.3274 (1.3736) time: 0.6291 [2021-03-27 03:36:42 swin_base_patch4_window7_224] INFO: Epoch: [128] [1070/1251] eta: 0:01:54 lr: 0.000614 loss: 3.4991 (3.3793) grad_norm: 1.3437 (1.3733) time: 0.6320 [2021-03-27 03:36:48 swin_base_patch4_window7_224] INFO: Epoch: [128] [1080/1251] eta: 0:01:48 lr: 0.000614 loss: 3.5067 (3.3765) grad_norm: 1.3373 (1.3733) time: 0.6316 [2021-03-27 03:36:54 swin_base_patch4_window7_224] INFO: Epoch: [128] [1090/1251] eta: 0:01:42 lr: 0.000614 loss: 3.3503 (3.3766) grad_norm: 1.3434 (1.3733) time: 0.6296 [2021-03-27 03:37:01 swin_base_patch4_window7_224] INFO: Epoch: [128] [1100/1251] eta: 0:01:35 lr: 0.000614 loss: 3.4015 (3.3781) grad_norm: 1.3437 (1.3732) time: 0.6287 [2021-03-27 03:37:07 swin_base_patch4_window7_224] INFO: Epoch: [128] [1110/1251] eta: 0:01:29 lr: 0.000614 loss: 3.4015 (3.3790) grad_norm: 1.3525 (1.3738) time: 0.6323 [2021-03-27 03:37:13 swin_base_patch4_window7_224] INFO: Epoch: [128] [1120/1251] eta: 0:01:23 lr: 0.000614 loss: 3.3586 (3.3769) grad_norm: 1.3339 (1.3728) time: 0.6293 [2021-03-27 03:37:20 swin_base_patch4_window7_224] INFO: Epoch: [128] [1130/1251] eta: 0:01:16 lr: 0.000613 loss: 3.4666 (3.3780) grad_norm: 1.3432 (1.3733) time: 0.6260 [2021-03-27 03:37:26 swin_base_patch4_window7_224] INFO: Epoch: [128] [1140/1251] eta: 0:01:10 lr: 0.000613 loss: 3.4603 (3.3759) grad_norm: 1.3668 (1.3731) time: 0.6277 [2021-03-27 03:37:32 swin_base_patch4_window7_224] INFO: Epoch: [128] [1150/1251] eta: 0:01:04 lr: 0.000613 loss: 3.4746 (3.3782) grad_norm: 1.3547 (1.3726) time: 0.6286 [2021-03-27 03:37:39 swin_base_patch4_window7_224] INFO: Epoch: [128] [1160/1251] eta: 0:00:57 lr: 0.000613 loss: 3.7270 (3.3810) grad_norm: 1.3253 (1.3724) time: 0.6309 [2021-03-27 03:37:45 swin_base_patch4_window7_224] INFO: Epoch: [128] [1170/1251] eta: 0:00:51 lr: 0.000613 loss: 3.5750 (3.3806) grad_norm: 1.3550 (1.3723) time: 0.6288 [2021-03-27 03:37:51 swin_base_patch4_window7_224] INFO: Epoch: [128] [1180/1251] eta: 0:00:44 lr: 0.000613 loss: 3.2149 (3.3782) grad_norm: 1.3574 (1.3726) time: 0.6269 [2021-03-27 03:37:57 swin_base_patch4_window7_224] INFO: Epoch: [128] [1190/1251] eta: 0:00:38 lr: 0.000613 loss: 3.1614 (3.3770) grad_norm: 1.4391 (1.3733) time: 0.6256 [2021-03-27 03:38:04 swin_base_patch4_window7_224] INFO: Epoch: [128] [1200/1251] eta: 0:00:32 lr: 0.000613 loss: 3.3314 (3.3770) grad_norm: 1.4391 (1.3736) time: 0.6288 [2021-03-27 03:38:10 swin_base_patch4_window7_224] INFO: Epoch: [128] [1210/1251] eta: 0:00:25 lr: 0.000613 loss: 3.4019 (3.3774) grad_norm: 1.3539 (1.3737) time: 0.6308 [2021-03-27 03:38:16 swin_base_patch4_window7_224] INFO: Epoch: [128] [1220/1251] eta: 0:00:19 lr: 0.000613 loss: 3.6160 (3.3784) grad_norm: 1.3816 (1.3750) time: 0.6296 [2021-03-27 03:38:23 swin_base_patch4_window7_224] INFO: Epoch: [128] [1230/1251] eta: 0:00:13 lr: 0.000613 loss: 3.4210 (3.3783) grad_norm: 1.3823 (1.3747) time: 0.6309 [2021-03-27 03:38:29 swin_base_patch4_window7_224] INFO: Epoch: [128] [1240/1251] eta: 0:00:06 lr: 0.000613 loss: 3.1654 (3.3761) grad_norm: 1.3298 (1.3747) time: 0.6336 [2021-03-27 03:38:35 swin_base_patch4_window7_224] INFO: Epoch: [128] [1250/1251] eta: 0:00:00 lr: 0.000613 loss: 3.1079 (3.3764) grad_norm: 1.2887 (1.3741) time: 0.6380 [2021-03-27 03:38:45 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:42 loss: 0.8881 (0.8881) acc1: 81.2500 (81.2500) acc5: 93.7500 (93.7500) [2021-03-27 03:38:47 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0434 (0.9940) acc1: 76.5625 (77.2727) acc5: 93.7500 (93.3239) [2021-03-27 03:38:49 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9980 (0.9951) acc1: 76.5625 (76.4137) acc5: 93.7500 (93.9732) [2021-03-27 03:38:51 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9664 (0.9995) acc1: 75.0000 (76.8145) acc5: 93.7500 (93.6996) [2021-03-27 03:38:53 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9604 (0.9951) acc1: 76.5625 (76.6006) acc5: 93.7500 (93.9024) [2021-03-27 03:38:54 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9159 (0.9706) acc1: 78.1250 (76.8960) acc5: 95.3125 (94.3040) [2021-03-27 03:39:04 swin_base_patch4_window7_224] INFO: * Acc@1 77.866 Acc@5 94.286 loss 0.943 [2021-03-27 03:39:04 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.9% [2021-03-27 03:39:04 swin_base_patch4_window7_224] INFO: Max accuracy: 77.90% [2021-03-27 03:39:08 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 0/1251] eta: 1:29:54 lr: 0.000613 loss: 4.4663 (4.4663) grad_norm: 1.2288 (1.2288) time: 4.3123 [2021-03-27 03:39:15 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 10/1251] eta: 0:20:09 lr: 0.000613 loss: 3.3990 (3.5282) grad_norm: 1.3481 (1.4654) time: 0.9749 [2021-03-27 03:39:21 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 20/1251] eta: 0:16:35 lr: 0.000613 loss: 3.6355 (3.5622) grad_norm: 1.3851 (1.4217) time: 0.6334 [2021-03-27 03:39:27 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 30/1251] eta: 0:15:16 lr: 0.000613 loss: 3.6355 (3.5070) grad_norm: 1.3100 (1.4127) time: 0.6271 [2021-03-27 03:39:34 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 40/1251] eta: 0:14:35 lr: 0.000613 loss: 3.3368 (3.4426) grad_norm: 1.2775 (1.3905) time: 0.6334 [2021-03-27 03:39:40 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 50/1251] eta: 0:14:06 lr: 0.000613 loss: 3.1974 (3.3897) grad_norm: 1.2678 (1.3808) time: 0.6331 [2021-03-27 03:39:46 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 60/1251] eta: 0:13:43 lr: 0.000613 loss: 3.2021 (3.3569) grad_norm: 1.2337 (1.3645) time: 0.6255 [2021-03-27 03:39:52 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 70/1251] eta: 0:13:26 lr: 0.000613 loss: 3.3294 (3.3837) grad_norm: 1.2566 (1.3646) time: 0.6274 [2021-03-27 03:39:59 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 80/1251] eta: 0:13:13 lr: 0.000613 loss: 3.5195 (3.3693) grad_norm: 1.3597 (1.3636) time: 0.6353 [2021-03-27 03:40:05 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 90/1251] eta: 0:13:00 lr: 0.000613 loss: 3.4440 (3.3752) grad_norm: 1.2933 (1.3545) time: 0.6335 [2021-03-27 03:40:11 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 100/1251] eta: 0:12:48 lr: 0.000613 loss: 3.3587 (3.3751) grad_norm: 1.2586 (1.3511) time: 0.6265 [2021-03-27 03:40:18 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 110/1251] eta: 0:12:38 lr: 0.000613 loss: 3.3548 (3.3751) grad_norm: 1.2883 (1.3457) time: 0.6309 [2021-03-27 03:40:24 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 120/1251] eta: 0:12:27 lr: 0.000612 loss: 3.3548 (3.3777) grad_norm: 1.2968 (1.3480) time: 0.6283 [2021-03-27 03:40:30 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 130/1251] eta: 0:12:17 lr: 0.000612 loss: 3.4824 (3.3768) grad_norm: 1.3240 (1.3512) time: 0.6195 [2021-03-27 03:40:37 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 140/1251] eta: 0:12:09 lr: 0.000612 loss: 3.5884 (3.3794) grad_norm: 1.3240 (1.3505) time: 0.6289 [2021-03-27 03:40:43 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 150/1251] eta: 0:12:00 lr: 0.000612 loss: 3.5999 (3.3747) grad_norm: 1.3610 (1.3591) time: 0.6305 [2021-03-27 03:40:49 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 160/1251] eta: 0:11:51 lr: 0.000612 loss: 3.3651 (3.3755) grad_norm: 1.3712 (1.3589) time: 0.6249 [2021-03-27 03:40:55 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 170/1251] eta: 0:11:44 lr: 0.000612 loss: 3.4304 (3.3804) grad_norm: 1.2266 (1.3513) time: 0.6323 [2021-03-27 03:41:02 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 180/1251] eta: 0:11:37 lr: 0.000612 loss: 3.5777 (3.3863) grad_norm: 1.2589 (1.3513) time: 0.6415 [2021-03-27 03:41:08 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 190/1251] eta: 0:11:30 lr: 0.000612 loss: 3.5892 (3.3877) grad_norm: 1.2961 (1.3491) time: 0.6405 [2021-03-27 03:41:15 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 200/1251] eta: 0:11:22 lr: 0.000612 loss: 3.4944 (3.3790) grad_norm: 1.2827 (1.3445) time: 0.6344 [2021-03-27 03:41:21 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 210/1251] eta: 0:11:15 lr: 0.000612 loss: 3.4889 (3.3749) grad_norm: 1.3079 (1.3446) time: 0.6319 [2021-03-27 03:41:27 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 220/1251] eta: 0:11:08 lr: 0.000612 loss: 3.3763 (3.3759) grad_norm: 1.3478 (1.3470) time: 0.6340 [2021-03-27 03:41:34 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 230/1251] eta: 0:11:01 lr: 0.000612 loss: 3.4642 (3.3791) grad_norm: 1.3341 (1.3456) time: 0.6352 [2021-03-27 03:41:40 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 240/1251] eta: 0:10:53 lr: 0.000612 loss: 3.5192 (3.3805) grad_norm: 1.3398 (1.3477) time: 0.6313 [2021-03-27 03:41:46 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 250/1251] eta: 0:10:46 lr: 0.000612 loss: 3.3599 (3.3796) grad_norm: 1.3506 (1.3487) time: 0.6317 [2021-03-27 03:41:52 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 260/1251] eta: 0:10:39 lr: 0.000612 loss: 3.3599 (3.3795) grad_norm: 1.3205 (1.3489) time: 0.6290 [2021-03-27 03:41:59 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 270/1251] eta: 0:10:33 lr: 0.000612 loss: 3.4433 (3.3906) grad_norm: 1.3801 (1.3547) time: 0.6361 [2021-03-27 03:42:05 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 280/1251] eta: 0:10:26 lr: 0.000612 loss: 3.4360 (3.3884) grad_norm: 1.4023 (1.3552) time: 0.6430 [2021-03-27 03:42:12 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 290/1251] eta: 0:10:19 lr: 0.000612 loss: 3.2504 (3.3811) grad_norm: 1.3541 (1.3564) time: 0.6366 [2021-03-27 03:42:18 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 300/1251] eta: 0:10:12 lr: 0.000612 loss: 3.2824 (3.3848) grad_norm: 1.2825 (1.3538) time: 0.6336 [2021-03-27 03:42:24 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 310/1251] eta: 0:10:05 lr: 0.000612 loss: 3.3679 (3.3816) grad_norm: 1.3205 (1.3565) time: 0.6302 [2021-03-27 03:42:30 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 320/1251] eta: 0:09:58 lr: 0.000612 loss: 3.3328 (3.3827) grad_norm: 1.3752 (1.3588) time: 0.6242 [2021-03-27 03:42:37 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 330/1251] eta: 0:09:51 lr: 0.000612 loss: 3.5921 (3.3897) grad_norm: 1.3706 (1.3604) time: 0.6243 [2021-03-27 03:42:43 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 340/1251] eta: 0:09:45 lr: 0.000612 loss: 3.5586 (3.3898) grad_norm: 1.3097 (1.3590) time: 0.6368 [2021-03-27 03:42:50 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 350/1251] eta: 0:09:38 lr: 0.000612 loss: 3.4547 (3.3898) grad_norm: 1.3820 (1.3615) time: 0.6399 [2021-03-27 03:42:56 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 360/1251] eta: 0:09:32 lr: 0.000612 loss: 3.6363 (3.3944) grad_norm: 1.4116 (1.3620) time: 0.6354 [2021-03-27 03:43:02 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 370/1251] eta: 0:09:25 lr: 0.000611 loss: 3.7408 (3.3982) grad_norm: 1.4782 (1.3703) time: 0.6339 [2021-03-27 03:43:09 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 380/1251] eta: 0:09:18 lr: 0.000611 loss: 3.5964 (3.3999) grad_norm: 1.4513 (1.3716) time: 0.6301 [2021-03-27 03:43:15 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 390/1251] eta: 0:09:12 lr: 0.000611 loss: 3.5370 (3.4010) grad_norm: 1.4197 (1.3781) time: 0.6260 [2021-03-27 03:43:21 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 400/1251] eta: 0:09:05 lr: 0.000611 loss: 3.5330 (3.4024) grad_norm: 1.4197 (1.3781) time: 0.6241 [2021-03-27 03:43:27 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 410/1251] eta: 0:08:58 lr: 0.000611 loss: 3.4007 (3.4001) grad_norm: 1.2346 (1.3744) time: 0.6252 [2021-03-27 03:43:34 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 420/1251] eta: 0:08:52 lr: 0.000611 loss: 3.2432 (3.3971) grad_norm: 1.2361 (1.3736) time: 0.6292 [2021-03-27 03:43:40 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 430/1251] eta: 0:08:45 lr: 0.000611 loss: 3.3040 (3.3948) grad_norm: 1.3047 (1.3731) time: 0.6289 [2021-03-27 03:43:46 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 440/1251] eta: 0:08:38 lr: 0.000611 loss: 3.5867 (3.4015) grad_norm: 1.3047 (1.3714) time: 0.6302 [2021-03-27 03:43:53 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 450/1251] eta: 0:08:32 lr: 0.000611 loss: 3.4012 (3.3926) grad_norm: 1.2841 (1.3709) time: 0.6316 [2021-03-27 03:43:59 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 460/1251] eta: 0:08:25 lr: 0.000611 loss: 3.3422 (3.3959) grad_norm: 1.2932 (1.3690) time: 0.6275 [2021-03-27 03:44:05 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 470/1251] eta: 0:08:19 lr: 0.000611 loss: 3.6562 (3.3979) grad_norm: 1.3145 (1.3687) time: 0.6279 [2021-03-27 03:44:11 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 480/1251] eta: 0:08:12 lr: 0.000611 loss: 3.5758 (3.4008) grad_norm: 1.3220 (1.3691) time: 0.6289 [2021-03-27 03:44:18 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 490/1251] eta: 0:08:06 lr: 0.000611 loss: 3.4654 (3.3984) grad_norm: 1.3332 (1.3692) time: 0.6311 [2021-03-27 03:44:24 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 500/1251] eta: 0:07:59 lr: 0.000611 loss: 3.3915 (3.3968) grad_norm: 1.3793 (1.3705) time: 0.6296 [2021-03-27 03:44:30 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 510/1251] eta: 0:07:52 lr: 0.000611 loss: 3.3064 (3.3949) grad_norm: 1.4002 (1.3700) time: 0.6241 [2021-03-27 03:44:36 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 520/1251] eta: 0:07:46 lr: 0.000611 loss: 3.5608 (3.3974) grad_norm: 1.2969 (1.3692) time: 0.6231 [2021-03-27 03:44:43 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 530/1251] eta: 0:07:39 lr: 0.000611 loss: 3.5608 (3.3977) grad_norm: 1.2888 (1.3708) time: 0.6303 [2021-03-27 03:44:49 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 540/1251] eta: 0:07:33 lr: 0.000611 loss: 3.3868 (3.3954) grad_norm: 1.4661 (1.3729) time: 0.6315 [2021-03-27 03:44:55 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 550/1251] eta: 0:07:26 lr: 0.000611 loss: 3.3581 (3.3941) grad_norm: 1.4540 (1.3728) time: 0.6294 [2021-03-27 03:45:02 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 560/1251] eta: 0:07:20 lr: 0.000611 loss: 3.5408 (3.3988) grad_norm: 1.2525 (1.3722) time: 0.6412 [2021-03-27 03:45:08 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 570/1251] eta: 0:07:14 lr: 0.000611 loss: 3.5164 (3.3995) grad_norm: 1.2058 (1.3709) time: 0.6459 [2021-03-27 03:45:15 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 580/1251] eta: 0:07:07 lr: 0.000611 loss: 3.4057 (3.4023) grad_norm: 1.2878 (1.3712) time: 0.6374 [2021-03-27 03:45:21 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 590/1251] eta: 0:07:01 lr: 0.000611 loss: 3.5215 (3.4009) grad_norm: 1.3610 (1.3728) time: 0.6362 [2021-03-27 03:45:27 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 600/1251] eta: 0:06:55 lr: 0.000611 loss: 3.5106 (3.4029) grad_norm: 1.3807 (1.3743) time: 0.6336 [2021-03-27 03:45:34 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 610/1251] eta: 0:06:48 lr: 0.000611 loss: 3.5106 (3.4022) grad_norm: 1.3979 (1.3736) time: 0.6270 [2021-03-27 03:45:40 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 620/1251] eta: 0:06:42 lr: 0.000610 loss: 3.3743 (3.4009) grad_norm: 1.3014 (1.3748) time: 0.6293 [2021-03-27 03:45:46 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 630/1251] eta: 0:06:35 lr: 0.000610 loss: 3.2734 (3.4007) grad_norm: 1.3931 (1.3756) time: 0.6285 [2021-03-27 03:45:52 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 640/1251] eta: 0:06:29 lr: 0.000610 loss: 3.3677 (3.4000) grad_norm: 1.3896 (1.3749) time: 0.6261 [2021-03-27 03:45:59 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 650/1251] eta: 0:06:22 lr: 0.000610 loss: 3.4549 (3.4008) grad_norm: 1.3496 (1.3762) time: 0.6285 [2021-03-27 03:46:05 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 660/1251] eta: 0:06:16 lr: 0.000610 loss: 3.4056 (3.3986) grad_norm: 1.3801 (1.3772) time: 0.6276 [2021-03-27 03:46:11 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 670/1251] eta: 0:06:09 lr: 0.000610 loss: 3.3895 (3.3984) grad_norm: 1.3801 (1.3767) time: 0.6318 [2021-03-27 03:46:18 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 680/1251] eta: 0:06:03 lr: 0.000610 loss: 3.4048 (3.3966) grad_norm: 1.3061 (1.3759) time: 0.6340 [2021-03-27 03:46:24 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 690/1251] eta: 0:05:57 lr: 0.000610 loss: 3.4048 (3.3946) grad_norm: 1.3130 (1.3761) time: 0.6290 [2021-03-27 03:46:30 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 700/1251] eta: 0:05:50 lr: 0.000610 loss: 3.4114 (3.3945) grad_norm: 1.4098 (1.3763) time: 0.6329 [2021-03-27 03:46:37 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 710/1251] eta: 0:05:44 lr: 0.000610 loss: 3.4461 (3.3926) grad_norm: 1.3228 (1.3759) time: 0.6288 [2021-03-27 03:46:43 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 720/1251] eta: 0:05:37 lr: 0.000610 loss: 3.4494 (3.3942) grad_norm: 1.2869 (1.3748) time: 0.6232 [2021-03-27 03:46:49 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 730/1251] eta: 0:05:31 lr: 0.000610 loss: 3.5182 (3.3933) grad_norm: 1.3376 (1.3743) time: 0.6338 [2021-03-27 03:46:56 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 740/1251] eta: 0:05:25 lr: 0.000610 loss: 3.5754 (3.3958) grad_norm: 1.3201 (1.3735) time: 0.6427 [2021-03-27 03:47:02 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 750/1251] eta: 0:05:18 lr: 0.000610 loss: 3.5641 (3.3967) grad_norm: 1.3806 (1.3753) time: 0.6386 [2021-03-27 03:47:08 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 760/1251] eta: 0:05:12 lr: 0.000610 loss: 3.5641 (3.3993) grad_norm: 1.4051 (1.3759) time: 0.6352 [2021-03-27 03:47:15 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 770/1251] eta: 0:05:06 lr: 0.000610 loss: 3.7275 (3.4033) grad_norm: 1.3582 (1.3777) time: 0.6426 [2021-03-27 03:47:21 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 780/1251] eta: 0:04:59 lr: 0.000610 loss: 3.5838 (3.4017) grad_norm: 1.4850 (1.3803) time: 0.6356 [2021-03-27 03:47:27 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 790/1251] eta: 0:04:53 lr: 0.000610 loss: 3.5838 (3.4051) grad_norm: 1.4296 (1.3806) time: 0.6252 [2021-03-27 03:47:34 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 800/1251] eta: 0:04:46 lr: 0.000610 loss: 3.7204 (3.4041) grad_norm: 1.3638 (1.3813) time: 0.6311 [2021-03-27 03:47:40 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 810/1251] eta: 0:04:40 lr: 0.000610 loss: 3.3250 (3.4032) grad_norm: 1.3390 (1.3809) time: 0.6337 [2021-03-27 03:47:46 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 820/1251] eta: 0:04:34 lr: 0.000610 loss: 3.2957 (3.4034) grad_norm: 1.3377 (1.3812) time: 0.6332 [2021-03-27 03:47:53 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 830/1251] eta: 0:04:27 lr: 0.000610 loss: 3.4344 (3.4052) grad_norm: 1.3680 (1.3809) time: 0.6330 [2021-03-27 03:47:59 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 840/1251] eta: 0:04:21 lr: 0.000610 loss: 3.4344 (3.4044) grad_norm: 1.3275 (1.3803) time: 0.6289 [2021-03-27 03:48:05 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 850/1251] eta: 0:04:14 lr: 0.000610 loss: 3.5349 (3.4049) grad_norm: 1.3371 (1.3807) time: 0.6294 [2021-03-27 03:48:12 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 860/1251] eta: 0:04:08 lr: 0.000610 loss: 3.6256 (3.4069) grad_norm: 1.3340 (1.3799) time: 0.6354 [2021-03-27 03:48:18 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 870/1251] eta: 0:04:02 lr: 0.000609 loss: 3.6200 (3.4035) grad_norm: 1.3108 (1.3790) time: 0.6394 [2021-03-27 03:48:24 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 880/1251] eta: 0:03:55 lr: 0.000609 loss: 3.3730 (3.4026) grad_norm: 1.3329 (1.3791) time: 0.6329 [2021-03-27 03:48:31 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 890/1251] eta: 0:03:49 lr: 0.000609 loss: 3.6322 (3.4037) grad_norm: 1.3838 (inf) time: 0.6244 [2021-03-27 03:48:37 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 900/1251] eta: 0:03:43 lr: 0.000609 loss: 3.8155 (3.4084) grad_norm: 1.3847 (inf) time: 0.6256 [2021-03-27 03:48:43 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 910/1251] eta: 0:03:36 lr: 0.000609 loss: 3.8129 (3.4101) grad_norm: 1.4007 (inf) time: 0.6248 [2021-03-27 03:48:49 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 920/1251] eta: 0:03:30 lr: 0.000609 loss: 3.5475 (3.4096) grad_norm: 1.3777 (inf) time: 0.6242 [2021-03-27 03:48:56 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 930/1251] eta: 0:03:24 lr: 0.000609 loss: 3.6024 (3.4120) grad_norm: 1.3640 (inf) time: 0.6388 [2021-03-27 03:49:02 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 940/1251] eta: 0:03:17 lr: 0.000609 loss: 3.5556 (3.4115) grad_norm: 1.4572 (inf) time: 0.6404 [2021-03-27 03:49:08 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 950/1251] eta: 0:03:11 lr: 0.000609 loss: 3.3105 (3.4089) grad_norm: 1.3384 (inf) time: 0.6307 [2021-03-27 03:49:15 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 960/1251] eta: 0:03:04 lr: 0.000609 loss: 3.2436 (3.4092) grad_norm: 1.3595 (inf) time: 0.6301 [2021-03-27 03:49:21 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 970/1251] eta: 0:02:58 lr: 0.000609 loss: 3.6118 (3.4090) grad_norm: 1.3803 (inf) time: 0.6362 [2021-03-27 03:49:27 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 980/1251] eta: 0:02:52 lr: 0.000609 loss: 3.6345 (3.4100) grad_norm: 1.3682 (inf) time: 0.6334 [2021-03-27 03:49:34 swin_base_patch4_window7_224] INFO: Epoch: [129] [ 990/1251] eta: 0:02:45 lr: 0.000609 loss: 3.6345 (3.4101) grad_norm: 1.3439 (inf) time: 0.6253 [2021-03-27 03:49:40 swin_base_patch4_window7_224] INFO: Epoch: [129] [1000/1251] eta: 0:02:39 lr: 0.000609 loss: 3.5079 (3.4087) grad_norm: 1.3439 (inf) time: 0.6281 [2021-03-27 03:49:46 swin_base_patch4_window7_224] INFO: Epoch: [129] [1010/1251] eta: 0:02:33 lr: 0.000609 loss: 3.5210 (3.4091) grad_norm: 1.3988 (inf) time: 0.6300 [2021-03-27 03:49:53 swin_base_patch4_window7_224] INFO: Epoch: [129] [1020/1251] eta: 0:02:26 lr: 0.000609 loss: 3.6759 (3.4117) grad_norm: 1.3818 (inf) time: 0.6299 [2021-03-27 03:49:59 swin_base_patch4_window7_224] INFO: Epoch: [129] [1030/1251] eta: 0:02:20 lr: 0.000609 loss: 3.7258 (3.4145) grad_norm: 1.3818 (inf) time: 0.6289 [2021-03-27 03:50:05 swin_base_patch4_window7_224] INFO: Epoch: [129] [1040/1251] eta: 0:02:14 lr: 0.000609 loss: 3.3854 (3.4126) grad_norm: 1.3301 (inf) time: 0.6371 [2021-03-27 03:50:12 swin_base_patch4_window7_224] INFO: Epoch: [129] [1050/1251] eta: 0:02:07 lr: 0.000609 loss: 3.2596 (3.4127) grad_norm: 1.3056 (inf) time: 0.6419 [2021-03-27 03:50:18 swin_base_patch4_window7_224] INFO: Epoch: [129] [1060/1251] eta: 0:02:01 lr: 0.000609 loss: 3.3361 (3.4133) grad_norm: 1.3203 (inf) time: 0.6312 [2021-03-27 03:50:24 swin_base_patch4_window7_224] INFO: Epoch: [129] [1070/1251] eta: 0:01:54 lr: 0.000609 loss: 3.6335 (3.4160) grad_norm: 1.3048 (inf) time: 0.6267 [2021-03-27 03:50:31 swin_base_patch4_window7_224] INFO: Epoch: [129] [1080/1251] eta: 0:01:48 lr: 0.000609 loss: 3.6034 (3.4137) grad_norm: 1.3408 (inf) time: 0.6335 [2021-03-27 03:50:37 swin_base_patch4_window7_224] INFO: Epoch: [129] [1090/1251] eta: 0:01:42 lr: 0.000609 loss: 3.1201 (3.4119) grad_norm: 1.3408 (inf) time: 0.6287 [2021-03-27 03:50:43 swin_base_patch4_window7_224] INFO: Epoch: [129] [1100/1251] eta: 0:01:35 lr: 0.000609 loss: 3.5252 (3.4142) grad_norm: 1.3475 (inf) time: 0.6226 [2021-03-27 03:50:49 swin_base_patch4_window7_224] INFO: Epoch: [129] [1110/1251] eta: 0:01:29 lr: 0.000608 loss: 3.5252 (3.4130) grad_norm: 1.3801 (inf) time: 0.6259 [2021-03-27 03:50:56 swin_base_patch4_window7_224] INFO: Epoch: [129] [1120/1251] eta: 0:01:23 lr: 0.000608 loss: 3.2821 (3.4121) grad_norm: 1.3778 (inf) time: 0.6245 [2021-03-27 03:51:02 swin_base_patch4_window7_224] INFO: Epoch: [129] [1130/1251] eta: 0:01:16 lr: 0.000608 loss: 3.2514 (3.4107) grad_norm: 1.2998 (inf) time: 0.6260 [2021-03-27 03:51:08 swin_base_patch4_window7_224] INFO: Epoch: [129] [1140/1251] eta: 0:01:10 lr: 0.000608 loss: 3.2244 (3.4074) grad_norm: 1.2998 (inf) time: 0.6243 [2021-03-27 03:51:14 swin_base_patch4_window7_224] INFO: Epoch: [129] [1150/1251] eta: 0:01:04 lr: 0.000608 loss: 3.0138 (3.4049) grad_norm: 1.3571 (inf) time: 0.6260 [2021-03-27 03:51:21 swin_base_patch4_window7_224] INFO: Epoch: [129] [1160/1251] eta: 0:00:57 lr: 0.000608 loss: 3.2359 (3.4060) grad_norm: 1.3614 (inf) time: 0.6351 [2021-03-27 03:51:27 swin_base_patch4_window7_224] INFO: Epoch: [129] [1170/1251] eta: 0:00:51 lr: 0.000608 loss: 3.5337 (3.4072) grad_norm: 1.4028 (inf) time: 0.6337 [2021-03-27 03:51:33 swin_base_patch4_window7_224] INFO: Epoch: [129] [1180/1251] eta: 0:00:45 lr: 0.000608 loss: 3.3967 (3.4058) grad_norm: 1.3810 (inf) time: 0.6315 [2021-03-27 03:51:40 swin_base_patch4_window7_224] INFO: Epoch: [129] [1190/1251] eta: 0:00:38 lr: 0.000608 loss: 3.4869 (3.4087) grad_norm: 1.3648 (inf) time: 0.6300 [2021-03-27 03:51:46 swin_base_patch4_window7_224] INFO: Epoch: [129] [1200/1251] eta: 0:00:32 lr: 0.000608 loss: 3.5474 (3.4090) grad_norm: 1.2994 (inf) time: 0.6308 [2021-03-27 03:51:52 swin_base_patch4_window7_224] INFO: Epoch: [129] [1210/1251] eta: 0:00:26 lr: 0.000608 loss: 3.4957 (3.4073) grad_norm: 1.3335 (inf) time: 0.6346 [2021-03-27 03:51:59 swin_base_patch4_window7_224] INFO: Epoch: [129] [1220/1251] eta: 0:00:19 lr: 0.000608 loss: 3.1811 (3.4054) grad_norm: 1.2975 (inf) time: 0.6268 [2021-03-27 03:52:05 swin_base_patch4_window7_224] INFO: Epoch: [129] [1230/1251] eta: 0:00:13 lr: 0.000608 loss: 3.6074 (3.4061) grad_norm: 1.2852 (inf) time: 0.6211 [2021-03-27 03:52:11 swin_base_patch4_window7_224] INFO: Epoch: [129] [1240/1251] eta: 0:00:06 lr: 0.000608 loss: 3.5432 (3.4059) grad_norm: 1.3891 (inf) time: 0.6242 [2021-03-27 03:52:17 swin_base_patch4_window7_224] INFO: Epoch: [129] [1250/1251] eta: 0:00:00 lr: 0.000608 loss: 3.5265 (3.4075) grad_norm: 1.3358 (inf) time: 0.6196 [2021-03-27 03:52:23 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:15 loss: 1.4356 (1.4356) acc1: 67.1875 (67.1875) acc5: 89.0625 (89.0625) [2021-03-27 03:52:26 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.8868 (0.9673) acc1: 79.6875 (78.1250) acc5: 95.3125 (93.3239) [2021-03-27 03:52:28 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:07 loss: 0.8469 (0.9190) acc1: 79.6875 (78.5714) acc5: 95.3125 (94.2708) [2021-03-27 03:52:30 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.8913 (0.9257) acc1: 79.6875 (78.0746) acc5: 93.7500 (94.3548) [2021-03-27 03:52:31 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9711 (0.9606) acc1: 76.5625 (77.6677) acc5: 93.7500 (93.9787) [2021-03-27 03:52:32 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9423 (0.9411) acc1: 76.5625 (77.9520) acc5: 93.7500 (94.2400) [2021-03-27 03:52:41 swin_base_patch4_window7_224] INFO: * Acc@1 78.162 Acc@5 94.338 loss 0.933 [2021-03-27 03:52:41 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.2% [2021-03-27 03:52:41 swin_base_patch4_window7_224] INFO: Max accuracy: 78.16% [2021-03-27 03:52:46 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 0/1251] eta: 1:31:49 lr: 0.000608 loss: 3.7366 (3.7366) grad_norm: 1.6422 (1.6422) time: 4.4037 [2021-03-27 03:52:52 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 10/1251] eta: 0:20:09 lr: 0.000608 loss: 3.5527 (3.2789) grad_norm: 1.4035 (1.3804) time: 0.9743 [2021-03-27 03:52:58 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 20/1251] eta: 0:16:34 lr: 0.000608 loss: 3.5527 (3.3782) grad_norm: 1.3515 (1.3769) time: 0.6281 [2021-03-27 03:53:05 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 30/1251] eta: 0:15:14 lr: 0.000608 loss: 3.6077 (3.5032) grad_norm: 1.3515 (1.4190) time: 0.6249 [2021-03-27 03:53:11 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 40/1251] eta: 0:14:36 lr: 0.000608 loss: 3.6635 (3.5013) grad_norm: 1.3531 (1.4045) time: 0.6354 [2021-03-27 03:53:18 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 50/1251] eta: 0:14:10 lr: 0.000608 loss: 3.6328 (3.5122) grad_norm: 1.4105 (1.4208) time: 0.6459 [2021-03-27 03:53:24 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 60/1251] eta: 0:13:48 lr: 0.000608 loss: 3.6574 (3.5099) grad_norm: 1.4286 (1.4244) time: 0.6369 [2021-03-27 03:53:30 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 70/1251] eta: 0:13:30 lr: 0.000608 loss: 3.5772 (3.4869) grad_norm: 1.3514 (1.4124) time: 0.6288 [2021-03-27 03:53:36 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 80/1251] eta: 0:13:16 lr: 0.000608 loss: 3.1869 (3.4620) grad_norm: 1.3458 (1.4037) time: 0.6339 [2021-03-27 03:53:43 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 90/1251] eta: 0:13:03 lr: 0.000608 loss: 3.2410 (3.4594) grad_norm: 1.3688 (1.4221) time: 0.6335 [2021-03-27 03:53:49 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 100/1251] eta: 0:12:51 lr: 0.000608 loss: 3.1101 (3.4034) grad_norm: 1.3834 (1.4255) time: 0.6325 [2021-03-27 03:53:56 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 110/1251] eta: 0:12:42 lr: 0.000607 loss: 3.2764 (3.4144) grad_norm: 1.3456 (1.4209) time: 0.6417 [2021-03-27 03:54:02 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 120/1251] eta: 0:12:33 lr: 0.000607 loss: 3.6007 (3.4159) grad_norm: 1.3835 (1.4282) time: 0.6427 [2021-03-27 03:54:08 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 130/1251] eta: 0:12:23 lr: 0.000607 loss: 3.5940 (3.4264) grad_norm: 1.4157 (1.4238) time: 0.6323 [2021-03-27 03:54:14 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 140/1251] eta: 0:12:13 lr: 0.000607 loss: 3.2294 (3.4053) grad_norm: 1.3402 (1.4200) time: 0.6243 [2021-03-27 03:54:21 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 150/1251] eta: 0:12:04 lr: 0.000607 loss: 3.4822 (3.4248) grad_norm: 1.3500 (1.4187) time: 0.6267 [2021-03-27 03:54:27 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 160/1251] eta: 0:11:56 lr: 0.000607 loss: 3.6248 (3.4287) grad_norm: 1.3707 (1.4156) time: 0.6305 [2021-03-27 03:54:33 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 170/1251] eta: 0:11:47 lr: 0.000607 loss: 3.6596 (3.4341) grad_norm: 1.3428 (1.4127) time: 0.6263 [2021-03-27 03:54:40 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 180/1251] eta: 0:11:39 lr: 0.000607 loss: 3.5358 (3.4313) grad_norm: 1.3202 (1.4069) time: 0.6245 [2021-03-27 03:54:46 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 190/1251] eta: 0:11:31 lr: 0.000607 loss: 3.5208 (3.4428) grad_norm: 1.3535 (1.4051) time: 0.6248 [2021-03-27 03:54:52 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 200/1251] eta: 0:11:23 lr: 0.000607 loss: 3.5208 (3.4354) grad_norm: 1.3796 (1.4057) time: 0.6271 [2021-03-27 03:54:58 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 210/1251] eta: 0:11:15 lr: 0.000607 loss: 3.4680 (3.4297) grad_norm: 1.3927 (1.4057) time: 0.6281 [2021-03-27 03:55:05 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 220/1251] eta: 0:11:08 lr: 0.000607 loss: 3.4719 (3.4415) grad_norm: 1.3170 (1.4046) time: 0.6255 [2021-03-27 03:55:11 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 230/1251] eta: 0:11:00 lr: 0.000607 loss: 3.6835 (3.4415) grad_norm: 1.3709 (1.4039) time: 0.6279 [2021-03-27 03:55:17 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 240/1251] eta: 0:10:54 lr: 0.000607 loss: 3.2203 (3.4200) grad_norm: 1.3263 (1.3999) time: 0.6379 [2021-03-27 03:55:24 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 250/1251] eta: 0:10:47 lr: 0.000607 loss: 2.9633 (3.4110) grad_norm: 1.3263 (1.3971) time: 0.6390 [2021-03-27 03:55:30 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 260/1251] eta: 0:10:40 lr: 0.000607 loss: 3.2309 (3.4046) grad_norm: 1.3835 (1.3974) time: 0.6286 [2021-03-27 03:55:36 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 270/1251] eta: 0:10:33 lr: 0.000607 loss: 3.3840 (3.4104) grad_norm: 1.4201 (1.3992) time: 0.6292 [2021-03-27 03:55:43 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 280/1251] eta: 0:10:25 lr: 0.000607 loss: 3.7433 (3.4210) grad_norm: 1.3767 (1.4012) time: 0.6288 [2021-03-27 03:55:49 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 290/1251] eta: 0:10:18 lr: 0.000607 loss: 3.7505 (3.4281) grad_norm: 1.4099 (1.4009) time: 0.6246 [2021-03-27 03:55:55 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 300/1251] eta: 0:10:12 lr: 0.000607 loss: 3.7505 (3.4394) grad_norm: 1.3275 (1.3989) time: 0.6292 [2021-03-27 03:56:01 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 310/1251] eta: 0:10:05 lr: 0.000607 loss: 3.8574 (3.4460) grad_norm: 1.3124 (1.3979) time: 0.6327 [2021-03-27 03:56:08 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 320/1251] eta: 0:09:58 lr: 0.000607 loss: 3.6255 (3.4403) grad_norm: 1.3262 (1.3970) time: 0.6256 [2021-03-27 03:56:14 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 330/1251] eta: 0:09:51 lr: 0.000607 loss: 3.4255 (3.4369) grad_norm: 1.2819 (1.3946) time: 0.6216 [2021-03-27 03:56:20 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 340/1251] eta: 0:09:44 lr: 0.000607 loss: 3.3175 (3.4269) grad_norm: 1.3379 (1.3934) time: 0.6289 [2021-03-27 03:56:26 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 350/1251] eta: 0:09:37 lr: 0.000606 loss: 3.0399 (3.4210) grad_norm: 1.3336 (1.3904) time: 0.6271 [2021-03-27 03:56:33 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 360/1251] eta: 0:09:30 lr: 0.000606 loss: 3.5057 (3.4218) grad_norm: 1.3199 (1.3925) time: 0.6257 [2021-03-27 03:56:39 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 370/1251] eta: 0:09:24 lr: 0.000606 loss: 3.5298 (3.4237) grad_norm: 1.4218 (1.3928) time: 0.6290 [2021-03-27 03:56:45 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 380/1251] eta: 0:09:17 lr: 0.000606 loss: 3.5298 (3.4217) grad_norm: 1.3648 (1.3922) time: 0.6259 [2021-03-27 03:56:52 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 390/1251] eta: 0:09:11 lr: 0.000606 loss: 3.5445 (3.4190) grad_norm: 1.2729 (1.3926) time: 0.6337 [2021-03-27 03:56:58 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 400/1251] eta: 0:09:04 lr: 0.000606 loss: 3.5765 (3.4204) grad_norm: 1.4837 (1.3966) time: 0.6342 [2021-03-27 03:57:04 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 410/1251] eta: 0:08:57 lr: 0.000606 loss: 3.5487 (3.4185) grad_norm: 1.5231 (1.4016) time: 0.6278 [2021-03-27 03:57:11 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 420/1251] eta: 0:08:51 lr: 0.000606 loss: 3.4404 (3.4172) grad_norm: 1.3976 (1.3999) time: 0.6298 [2021-03-27 03:57:17 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 430/1251] eta: 0:08:44 lr: 0.000606 loss: 3.5796 (3.4190) grad_norm: 1.3725 (1.3998) time: 0.6299 [2021-03-27 03:57:23 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 440/1251] eta: 0:08:38 lr: 0.000606 loss: 3.6086 (3.4161) grad_norm: 1.3233 (1.3969) time: 0.6277 [2021-03-27 03:57:29 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 450/1251] eta: 0:08:31 lr: 0.000606 loss: 3.5680 (3.4192) grad_norm: 1.3077 (1.3971) time: 0.6246 [2021-03-27 03:57:36 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 460/1251] eta: 0:08:25 lr: 0.000606 loss: 3.3544 (3.4139) grad_norm: 1.3694 (1.3980) time: 0.6320 [2021-03-27 03:57:42 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 470/1251] eta: 0:08:18 lr: 0.000606 loss: 3.3544 (3.4145) grad_norm: 1.4190 (1.3995) time: 0.6369 [2021-03-27 03:57:48 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 480/1251] eta: 0:08:12 lr: 0.000606 loss: 3.3518 (3.4133) grad_norm: 1.3466 (1.3978) time: 0.6335 [2021-03-27 03:57:55 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 490/1251] eta: 0:08:05 lr: 0.000606 loss: 3.6701 (3.4175) grad_norm: 1.3227 (1.3967) time: 0.6285 [2021-03-27 03:58:01 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 500/1251] eta: 0:07:58 lr: 0.000606 loss: 3.6519 (3.4183) grad_norm: 1.3398 (1.3964) time: 0.6224 [2021-03-27 03:58:07 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 510/1251] eta: 0:07:52 lr: 0.000606 loss: 3.4087 (3.4188) grad_norm: 1.2519 (1.3958) time: 0.6267 [2021-03-27 03:58:13 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 520/1251] eta: 0:07:45 lr: 0.000606 loss: 3.4725 (3.4195) grad_norm: 1.3101 (1.3959) time: 0.6290 [2021-03-27 03:58:20 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 530/1251] eta: 0:07:39 lr: 0.000606 loss: 3.5773 (3.4202) grad_norm: 1.3825 (1.3962) time: 0.6261 [2021-03-27 03:58:26 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 540/1251] eta: 0:07:32 lr: 0.000606 loss: 3.5918 (3.4151) grad_norm: 1.3408 (1.3955) time: 0.6245 [2021-03-27 03:58:33 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 550/1251] eta: 0:07:26 lr: 0.000606 loss: 3.5922 (3.4191) grad_norm: 1.3408 (1.3971) time: 0.6390 [2021-03-27 03:58:39 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 560/1251] eta: 0:07:20 lr: 0.000606 loss: 3.5605 (3.4178) grad_norm: 1.2638 (1.3946) time: 0.6415 [2021-03-27 03:58:45 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 570/1251] eta: 0:07:13 lr: 0.000606 loss: 3.3913 (3.4190) grad_norm: 1.1825 (1.3918) time: 0.6259 [2021-03-27 03:58:51 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 580/1251] eta: 0:07:07 lr: 0.000606 loss: 3.4760 (3.4169) grad_norm: 1.2605 (1.3908) time: 0.6236 [2021-03-27 03:58:58 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 590/1251] eta: 0:07:00 lr: 0.000606 loss: 3.6294 (3.4213) grad_norm: 1.3055 (1.3900) time: 0.6282 [2021-03-27 03:59:04 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 600/1251] eta: 0:06:54 lr: 0.000605 loss: 3.6079 (3.4178) grad_norm: 1.3788 (1.3925) time: 0.6354 [2021-03-27 03:59:10 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 610/1251] eta: 0:06:48 lr: 0.000605 loss: 3.3389 (3.4168) grad_norm: 1.3835 (1.3928) time: 0.6390 [2021-03-27 03:59:17 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 620/1251] eta: 0:06:41 lr: 0.000605 loss: 3.0352 (3.4117) grad_norm: 1.3835 (1.3937) time: 0.6313 [2021-03-27 03:59:23 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 630/1251] eta: 0:06:35 lr: 0.000605 loss: 3.3227 (3.4146) grad_norm: 1.3545 (1.3931) time: 0.6319 [2021-03-27 03:59:29 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 640/1251] eta: 0:06:28 lr: 0.000605 loss: 3.5692 (3.4149) grad_norm: 1.2967 (1.3916) time: 0.6308 [2021-03-27 03:59:36 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 650/1251] eta: 0:06:22 lr: 0.000605 loss: 3.4073 (3.4127) grad_norm: 1.3303 (1.3921) time: 0.6286 [2021-03-27 03:59:42 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 660/1251] eta: 0:06:15 lr: 0.000605 loss: 3.4073 (3.4130) grad_norm: 1.4109 (1.3917) time: 0.6306 [2021-03-27 03:59:48 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 670/1251] eta: 0:06:09 lr: 0.000605 loss: 3.3643 (3.4084) grad_norm: 1.3533 (1.3909) time: 0.6253 [2021-03-27 03:59:54 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 680/1251] eta: 0:06:02 lr: 0.000605 loss: 3.4129 (3.4117) grad_norm: 1.3690 (1.3927) time: 0.6275 [2021-03-27 04:00:01 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 690/1251] eta: 0:05:56 lr: 0.000605 loss: 3.6225 (3.4102) grad_norm: 1.3336 (1.3928) time: 0.6310 [2021-03-27 04:00:07 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 700/1251] eta: 0:05:50 lr: 0.000605 loss: 3.4249 (3.4090) grad_norm: 1.3336 (1.3942) time: 0.6298 [2021-03-27 04:00:13 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 710/1251] eta: 0:05:43 lr: 0.000605 loss: 3.5486 (3.4111) grad_norm: 1.3341 (1.3938) time: 0.6258 [2021-03-27 04:00:20 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 720/1251] eta: 0:05:37 lr: 0.000605 loss: 3.5486 (3.4114) grad_norm: 1.3271 (1.3929) time: 0.6274 [2021-03-27 04:00:26 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 730/1251] eta: 0:05:30 lr: 0.000605 loss: 3.4759 (3.4130) grad_norm: 1.2977 (1.3914) time: 0.6276 [2021-03-27 04:00:32 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 740/1251] eta: 0:05:24 lr: 0.000605 loss: 3.5525 (3.4142) grad_norm: 1.2779 (1.3899) time: 0.6313 [2021-03-27 04:00:39 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 750/1251] eta: 0:05:18 lr: 0.000605 loss: 3.6386 (3.4148) grad_norm: 1.2683 (1.3887) time: 0.6451 [2021-03-27 04:00:45 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 760/1251] eta: 0:05:12 lr: 0.000605 loss: 3.6178 (3.4175) grad_norm: 1.3301 (1.3890) time: 0.6473 [2021-03-27 04:00:51 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 770/1251] eta: 0:05:05 lr: 0.000605 loss: 3.5553 (3.4131) grad_norm: 1.4092 (1.3887) time: 0.6371 [2021-03-27 04:00:58 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 780/1251] eta: 0:04:59 lr: 0.000605 loss: 3.5644 (3.4173) grad_norm: 1.3088 (1.3880) time: 0.6321 [2021-03-27 04:01:04 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 790/1251] eta: 0:04:53 lr: 0.000605 loss: 3.5203 (3.4144) grad_norm: 1.2990 (1.3878) time: 0.6416 [2021-03-27 04:01:11 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 800/1251] eta: 0:04:46 lr: 0.000605 loss: 3.3662 (3.4134) grad_norm: 1.3454 (1.3876) time: 0.6402 [2021-03-27 04:01:17 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 810/1251] eta: 0:04:40 lr: 0.000605 loss: 3.4509 (3.4117) grad_norm: 1.3407 (1.3887) time: 0.6259 [2021-03-27 04:01:23 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 820/1251] eta: 0:04:33 lr: 0.000605 loss: 3.1816 (3.4065) grad_norm: 1.3290 (1.3887) time: 0.6352 [2021-03-27 04:01:30 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 830/1251] eta: 0:04:27 lr: 0.000605 loss: 3.1374 (3.4058) grad_norm: 1.3157 (1.3875) time: 0.6395 [2021-03-27 04:01:36 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 840/1251] eta: 0:04:21 lr: 0.000605 loss: 3.5584 (3.4087) grad_norm: 1.3066 (1.3886) time: 0.6328 [2021-03-27 04:01:42 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 850/1251] eta: 0:04:14 lr: 0.000604 loss: 3.5146 (3.4085) grad_norm: 1.3947 (1.3899) time: 0.6364 [2021-03-27 04:01:49 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 860/1251] eta: 0:04:08 lr: 0.000604 loss: 3.4683 (3.4100) grad_norm: 1.4723 (1.3904) time: 0.6357 [2021-03-27 04:01:55 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 870/1251] eta: 0:04:02 lr: 0.000604 loss: 3.6158 (3.4128) grad_norm: 1.3402 (1.3908) time: 0.6270 [2021-03-27 04:02:01 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 880/1251] eta: 0:03:55 lr: 0.000604 loss: 3.5904 (3.4106) grad_norm: 1.3143 (1.3912) time: 0.6255 [2021-03-27 04:02:08 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 890/1251] eta: 0:03:49 lr: 0.000604 loss: 3.4060 (3.4108) grad_norm: 1.3262 (1.3902) time: 0.6314 [2021-03-27 04:02:14 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 900/1251] eta: 0:03:42 lr: 0.000604 loss: 3.4060 (3.4118) grad_norm: 1.3137 (1.3901) time: 0.6321 [2021-03-27 04:02:20 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 910/1251] eta: 0:03:36 lr: 0.000604 loss: 3.6195 (3.4151) grad_norm: 1.3269 (1.3894) time: 0.6339 [2021-03-27 04:02:26 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 920/1251] eta: 0:03:30 lr: 0.000604 loss: 3.6195 (3.4141) grad_norm: 1.3475 (1.3902) time: 0.6339 [2021-03-27 04:02:33 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 930/1251] eta: 0:03:23 lr: 0.000604 loss: 3.3861 (3.4158) grad_norm: 1.3519 (1.3900) time: 0.6300 [2021-03-27 04:02:39 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 940/1251] eta: 0:03:17 lr: 0.000604 loss: 3.5677 (3.4158) grad_norm: 1.3467 (1.3905) time: 0.6441 [2021-03-27 04:02:46 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 950/1251] eta: 0:03:11 lr: 0.000604 loss: 3.5667 (3.4172) grad_norm: 1.3152 (1.3890) time: 0.6451 [2021-03-27 04:02:52 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 960/1251] eta: 0:03:04 lr: 0.000604 loss: 3.6264 (3.4181) grad_norm: 1.3152 (1.3896) time: 0.6356 [2021-03-27 04:02:58 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 970/1251] eta: 0:02:58 lr: 0.000604 loss: 3.4252 (3.4185) grad_norm: 1.3845 (1.3893) time: 0.6313 [2021-03-27 04:03:05 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 980/1251] eta: 0:02:52 lr: 0.000604 loss: 3.4090 (3.4179) grad_norm: 1.3663 (1.3892) time: 0.6260 [2021-03-27 04:03:11 swin_base_patch4_window7_224] INFO: Epoch: [130] [ 990/1251] eta: 0:02:45 lr: 0.000604 loss: 3.6292 (3.4186) grad_norm: 1.3737 (1.3894) time: 0.6310 [2021-03-27 04:03:17 swin_base_patch4_window7_224] INFO: Epoch: [130] [1000/1251] eta: 0:02:39 lr: 0.000604 loss: 3.6394 (3.4191) grad_norm: 1.4059 (1.3902) time: 0.6285 [2021-03-27 04:03:23 swin_base_patch4_window7_224] INFO: Epoch: [130] [1010/1251] eta: 0:02:33 lr: 0.000604 loss: 3.6394 (3.4217) grad_norm: 1.4268 (1.3913) time: 0.6244 [2021-03-27 04:03:30 swin_base_patch4_window7_224] INFO: Epoch: [130] [1020/1251] eta: 0:02:26 lr: 0.000604 loss: 3.6098 (3.4221) grad_norm: 1.4386 (1.3915) time: 0.6232 [2021-03-27 04:03:36 swin_base_patch4_window7_224] INFO: Epoch: [130] [1030/1251] eta: 0:02:20 lr: 0.000604 loss: 3.4281 (3.4188) grad_norm: 1.3757 (1.3912) time: 0.6228 [2021-03-27 04:03:42 swin_base_patch4_window7_224] INFO: Epoch: [130] [1040/1251] eta: 0:02:13 lr: 0.000604 loss: 3.1461 (3.4187) grad_norm: 1.3536 (1.3904) time: 0.6293 [2021-03-27 04:03:49 swin_base_patch4_window7_224] INFO: Epoch: [130] [1050/1251] eta: 0:02:07 lr: 0.000604 loss: 3.5088 (3.4188) grad_norm: 1.2778 (1.3894) time: 0.6393 [2021-03-27 04:03:55 swin_base_patch4_window7_224] INFO: Epoch: [130] [1060/1251] eta: 0:02:01 lr: 0.000604 loss: 3.3480 (3.4177) grad_norm: 1.3432 (1.3896) time: 0.6333 [2021-03-27 04:04:01 swin_base_patch4_window7_224] INFO: Epoch: [130] [1070/1251] eta: 0:01:54 lr: 0.000604 loss: 3.2822 (3.4155) grad_norm: 1.3946 (1.3894) time: 0.6244 [2021-03-27 04:04:07 swin_base_patch4_window7_224] INFO: Epoch: [130] [1080/1251] eta: 0:01:48 lr: 0.000604 loss: 3.4946 (3.4159) grad_norm: 1.2126 (1.3889) time: 0.6283 [2021-03-27 04:04:14 swin_base_patch4_window7_224] INFO: Epoch: [130] [1090/1251] eta: 0:01:42 lr: 0.000603 loss: 3.5474 (3.4147) grad_norm: 1.2200 (1.3881) time: 0.6270 [2021-03-27 04:04:20 swin_base_patch4_window7_224] INFO: Epoch: [130] [1100/1251] eta: 0:01:35 lr: 0.000603 loss: 3.4471 (3.4147) grad_norm: 1.2732 (1.3874) time: 0.6226 [2021-03-27 04:04:26 swin_base_patch4_window7_224] INFO: Epoch: [130] [1110/1251] eta: 0:01:29 lr: 0.000603 loss: 3.5386 (3.4153) grad_norm: 1.2886 (1.3880) time: 0.6256 [2021-03-27 04:04:32 swin_base_patch4_window7_224] INFO: Epoch: [130] [1120/1251] eta: 0:01:23 lr: 0.000603 loss: 3.5276 (3.4146) grad_norm: 1.3896 (1.3881) time: 0.6276 [2021-03-27 04:04:39 swin_base_patch4_window7_224] INFO: Epoch: [130] [1130/1251] eta: 0:01:16 lr: 0.000603 loss: 3.5588 (3.4166) grad_norm: 1.3257 (1.3880) time: 0.6231 [2021-03-27 04:04:45 swin_base_patch4_window7_224] INFO: Epoch: [130] [1140/1251] eta: 0:01:10 lr: 0.000603 loss: 3.5979 (3.4170) grad_norm: 1.3257 (1.3880) time: 0.6195 [2021-03-27 04:04:51 swin_base_patch4_window7_224] INFO: Epoch: [130] [1150/1251] eta: 0:01:04 lr: 0.000603 loss: 3.4521 (3.4166) grad_norm: 1.4259 (1.3884) time: 0.6207 [2021-03-27 04:04:57 swin_base_patch4_window7_224] INFO: Epoch: [130] [1160/1251] eta: 0:00:57 lr: 0.000603 loss: 3.5757 (3.4169) grad_norm: 1.3600 (1.3877) time: 0.6236 [2021-03-27 04:05:04 swin_base_patch4_window7_224] INFO: Epoch: [130] [1170/1251] eta: 0:00:51 lr: 0.000603 loss: 3.5757 (3.4172) grad_norm: 1.3089 (1.3877) time: 0.6249 [2021-03-27 04:05:10 swin_base_patch4_window7_224] INFO: Epoch: [130] [1180/1251] eta: 0:00:44 lr: 0.000603 loss: 3.4850 (3.4164) grad_norm: 1.3480 (1.3883) time: 0.6248 [2021-03-27 04:05:16 swin_base_patch4_window7_224] INFO: Epoch: [130] [1190/1251] eta: 0:00:38 lr: 0.000603 loss: 3.2624 (3.4150) grad_norm: 1.4274 (1.3894) time: 0.6274 [2021-03-27 04:05:23 swin_base_patch4_window7_224] INFO: Epoch: [130] [1200/1251] eta: 0:00:32 lr: 0.000603 loss: 3.5128 (3.4178) grad_norm: 1.3140 (1.3886) time: 0.6338 [2021-03-27 04:05:29 swin_base_patch4_window7_224] INFO: Epoch: [130] [1210/1251] eta: 0:00:25 lr: 0.000603 loss: 3.6386 (3.4179) grad_norm: 1.2873 (1.3885) time: 0.6375 [2021-03-27 04:05:35 swin_base_patch4_window7_224] INFO: Epoch: [130] [1220/1251] eta: 0:00:19 lr: 0.000603 loss: 3.6265 (3.4186) grad_norm: 1.4297 (1.3895) time: 0.6382 [2021-03-27 04:05:42 swin_base_patch4_window7_224] INFO: Epoch: [130] [1230/1251] eta: 0:00:13 lr: 0.000603 loss: 3.4301 (3.4178) grad_norm: 1.3579 (1.3893) time: 0.6307 [2021-03-27 04:05:48 swin_base_patch4_window7_224] INFO: Epoch: [130] [1240/1251] eta: 0:00:06 lr: 0.000603 loss: 3.4199 (3.4178) grad_norm: 1.2691 (1.3888) time: 0.6237 [2021-03-27 04:05:54 swin_base_patch4_window7_224] INFO: Epoch: [130] [1250/1251] eta: 0:00:00 lr: 0.000603 loss: 3.4949 (3.4197) grad_norm: 1.2826 (1.3884) time: 0.6166 [2021-03-27 04:07:06 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:12 loss: 1.1157 (1.1157) acc1: 75.0000 (75.0000) acc5: 90.6250 (90.6250) [2021-03-27 04:07:07 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.9310 (0.9579) acc1: 76.5625 (76.4205) acc5: 93.7500 (93.8920) [2021-03-27 04:07:09 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:06 loss: 0.9310 (0.9680) acc1: 76.5625 (76.7857) acc5: 93.7500 (94.1964) [2021-03-27 04:07:10 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.9375 (0.9607) acc1: 78.1250 (77.2177) acc5: 93.7500 (94.3548) [2021-03-27 04:07:12 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9375 (0.9754) acc1: 78.1250 (76.7912) acc5: 95.3125 (94.1311) [2021-03-27 04:07:13 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9579 (0.9749) acc1: 76.5625 (76.9280) acc5: 93.7500 (94.2720) [2021-03-27 04:07:20 swin_base_patch4_window7_224] INFO: * Acc@1 77.720 Acc@5 94.204 loss 0.964 [2021-03-27 04:07:20 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.7% [2021-03-27 04:07:20 swin_base_patch4_window7_224] INFO: Max accuracy: 78.16% [2021-03-27 04:07:24 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 0/1251] eta: 1:26:34 lr: 0.000603 loss: 3.6195 (3.6195) grad_norm: 1.2351 (1.2351) time: 4.1522 [2021-03-27 04:07:31 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 10/1251] eta: 0:20:05 lr: 0.000603 loss: 3.5476 (3.4835) grad_norm: 1.3539 (1.3701) time: 0.9713 [2021-03-27 04:07:37 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 20/1251] eta: 0:16:37 lr: 0.000603 loss: 3.3603 (3.3145) grad_norm: 1.3914 (1.3936) time: 0.6436 [2021-03-27 04:07:44 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 30/1251] eta: 0:15:22 lr: 0.000603 loss: 3.1693 (3.3177) grad_norm: 1.3668 (1.3859) time: 0.6369 [2021-03-27 04:07:50 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 40/1251] eta: 0:14:36 lr: 0.000603 loss: 3.3876 (3.3480) grad_norm: 1.3226 (1.3796) time: 0.6332 [2021-03-27 04:07:56 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 50/1251] eta: 0:14:07 lr: 0.000603 loss: 3.5971 (3.3754) grad_norm: 1.3339 (1.3859) time: 0.6277 [2021-03-27 04:08:02 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 60/1251] eta: 0:13:45 lr: 0.000603 loss: 3.4075 (3.3692) grad_norm: 1.3347 (1.3914) time: 0.6296 [2021-03-27 04:08:09 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 70/1251] eta: 0:13:29 lr: 0.000603 loss: 3.1755 (3.3140) grad_norm: 1.3306 (1.3842) time: 0.6347 [2021-03-27 04:08:15 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 80/1251] eta: 0:13:13 lr: 0.000603 loss: 3.1206 (3.3292) grad_norm: 1.3306 (1.3772) time: 0.6310 [2021-03-27 04:08:21 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 90/1251] eta: 0:13:01 lr: 0.000602 loss: 3.4363 (3.3381) grad_norm: 1.3415 (1.3792) time: 0.6311 [2021-03-27 04:08:28 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 100/1251] eta: 0:12:49 lr: 0.000602 loss: 3.4363 (3.3408) grad_norm: 1.2942 (1.3689) time: 0.6318 [2021-03-27 04:08:34 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 110/1251] eta: 0:12:38 lr: 0.000602 loss: 3.5112 (3.3540) grad_norm: 1.2848 (1.3650) time: 0.6247 [2021-03-27 04:08:40 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 120/1251] eta: 0:12:27 lr: 0.000602 loss: 3.5705 (3.3609) grad_norm: 1.2848 (1.3601) time: 0.6220 [2021-03-27 04:08:46 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 130/1251] eta: 0:12:18 lr: 0.000602 loss: 3.3877 (3.3365) grad_norm: 1.2726 (1.3585) time: 0.6238 [2021-03-27 04:08:53 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 140/1251] eta: 0:12:10 lr: 0.000602 loss: 3.3586 (3.3397) grad_norm: 1.3451 (1.3610) time: 0.6335 [2021-03-27 04:08:59 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 150/1251] eta: 0:12:01 lr: 0.000602 loss: 3.4030 (3.3278) grad_norm: 1.4583 (1.3700) time: 0.6358 [2021-03-27 04:09:05 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 160/1251] eta: 0:11:53 lr: 0.000602 loss: 3.3322 (3.3269) grad_norm: 1.5088 (1.3827) time: 0.6313 [2021-03-27 04:09:12 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 170/1251] eta: 0:11:44 lr: 0.000602 loss: 3.3992 (3.3327) grad_norm: 1.4015 (1.3844) time: 0.6261 [2021-03-27 04:09:18 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 180/1251] eta: 0:11:36 lr: 0.000602 loss: 3.5210 (3.3249) grad_norm: 1.3356 (1.3851) time: 0.6248 [2021-03-27 04:09:24 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 190/1251] eta: 0:11:28 lr: 0.000602 loss: 3.5210 (3.3314) grad_norm: 1.3356 (1.3826) time: 0.6232 [2021-03-27 04:09:30 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 200/1251] eta: 0:11:21 lr: 0.000602 loss: 3.4289 (3.3317) grad_norm: 1.3353 (1.3838) time: 0.6278 [2021-03-27 04:09:37 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 210/1251] eta: 0:11:14 lr: 0.000602 loss: 3.2438 (3.3327) grad_norm: 1.3081 (1.3806) time: 0.6398 [2021-03-27 04:09:43 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 220/1251] eta: 0:11:07 lr: 0.000602 loss: 3.2291 (3.3251) grad_norm: 1.3081 (1.3818) time: 0.6405 [2021-03-27 04:09:50 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 230/1251] eta: 0:11:01 lr: 0.000602 loss: 3.1211 (3.3221) grad_norm: 1.2610 (1.3788) time: 0.6437 [2021-03-27 04:09:56 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 240/1251] eta: 0:10:54 lr: 0.000602 loss: 3.3581 (3.3277) grad_norm: 1.3161 (1.3792) time: 0.6393 [2021-03-27 04:10:02 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 250/1251] eta: 0:10:47 lr: 0.000602 loss: 3.3819 (3.3224) grad_norm: 1.4446 (1.3819) time: 0.6303 [2021-03-27 04:10:09 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 260/1251] eta: 0:10:39 lr: 0.000602 loss: 3.3819 (3.3267) grad_norm: 1.2350 (1.3745) time: 0.6301 [2021-03-27 04:10:15 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 270/1251] eta: 0:10:32 lr: 0.000602 loss: 3.5855 (3.3325) grad_norm: 1.2365 (1.3747) time: 0.6276 [2021-03-27 04:10:21 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 280/1251] eta: 0:10:26 lr: 0.000602 loss: 3.6076 (3.3457) grad_norm: 1.3826 (1.3759) time: 0.6319 [2021-03-27 04:10:28 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 290/1251] eta: 0:10:19 lr: 0.000602 loss: 3.6213 (3.3495) grad_norm: 1.3691 (1.3758) time: 0.6344 [2021-03-27 04:10:34 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 300/1251] eta: 0:10:12 lr: 0.000602 loss: 3.5753 (3.3536) grad_norm: 1.4075 (1.3780) time: 0.6297 [2021-03-27 04:10:40 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 310/1251] eta: 0:10:05 lr: 0.000602 loss: 3.6478 (3.3623) grad_norm: 1.4079 (1.3773) time: 0.6291 [2021-03-27 04:10:47 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 320/1251] eta: 0:09:58 lr: 0.000602 loss: 3.5846 (3.3574) grad_norm: 1.3087 (1.3773) time: 0.6326 [2021-03-27 04:10:53 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 330/1251] eta: 0:09:51 lr: 0.000601 loss: 3.4401 (3.3592) grad_norm: 1.3087 (1.3786) time: 0.6335 [2021-03-27 04:10:59 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 340/1251] eta: 0:09:45 lr: 0.000601 loss: 3.4298 (3.3507) grad_norm: 1.2925 (1.3754) time: 0.6317 [2021-03-27 04:11:05 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 350/1251] eta: 0:09:38 lr: 0.000601 loss: 3.4376 (3.3532) grad_norm: 1.2925 (1.3752) time: 0.6283 [2021-03-27 04:11:12 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 360/1251] eta: 0:09:31 lr: 0.000601 loss: 3.4591 (3.3595) grad_norm: 1.3042 (1.3731) time: 0.6247 [2021-03-27 04:11:18 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 370/1251] eta: 0:09:24 lr: 0.000601 loss: 3.4437 (3.3575) grad_norm: 1.3203 (1.3739) time: 0.6276 [2021-03-27 04:11:24 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 380/1251] eta: 0:09:17 lr: 0.000601 loss: 3.1930 (3.3503) grad_norm: 1.3396 (1.3728) time: 0.6257 [2021-03-27 04:11:31 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 390/1251] eta: 0:09:11 lr: 0.000601 loss: 3.2115 (3.3511) grad_norm: 1.2618 (1.3702) time: 0.6256 [2021-03-27 04:11:37 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 400/1251] eta: 0:09:04 lr: 0.000601 loss: 3.3591 (3.3482) grad_norm: 1.3079 (1.3706) time: 0.6348 [2021-03-27 04:11:43 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 410/1251] eta: 0:08:58 lr: 0.000601 loss: 3.3466 (3.3446) grad_norm: 1.2998 (1.3688) time: 0.6341 [2021-03-27 04:11:49 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 420/1251] eta: 0:08:51 lr: 0.000601 loss: 3.3466 (3.3418) grad_norm: 1.2994 (1.3686) time: 0.6283 [2021-03-27 04:11:56 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 430/1251] eta: 0:08:44 lr: 0.000601 loss: 3.4675 (3.3418) grad_norm: 1.3274 (1.3683) time: 0.6249 [2021-03-27 04:12:02 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 440/1251] eta: 0:08:38 lr: 0.000601 loss: 3.4844 (3.3447) grad_norm: 1.3949 (1.3707) time: 0.6257 [2021-03-27 04:12:08 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 450/1251] eta: 0:08:31 lr: 0.000601 loss: 3.3581 (3.3368) grad_norm: 1.3949 (1.3713) time: 0.6267 [2021-03-27 04:12:15 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 460/1251] eta: 0:08:25 lr: 0.000601 loss: 3.1753 (3.3371) grad_norm: 1.3932 (1.3743) time: 0.6309 [2021-03-27 04:12:21 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 470/1251] eta: 0:08:18 lr: 0.000601 loss: 3.4397 (3.3395) grad_norm: 1.4416 (1.3763) time: 0.6351 [2021-03-27 04:12:27 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 480/1251] eta: 0:08:12 lr: 0.000601 loss: 3.2889 (3.3321) grad_norm: 1.3693 (1.3759) time: 0.6315 [2021-03-27 04:12:34 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 490/1251] eta: 0:08:05 lr: 0.000601 loss: 2.9724 (3.3285) grad_norm: 1.3007 (1.3751) time: 0.6322 [2021-03-27 04:12:40 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 500/1251] eta: 0:07:59 lr: 0.000601 loss: 3.3436 (3.3304) grad_norm: 1.2987 (1.3746) time: 0.6282 [2021-03-27 04:12:46 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 510/1251] eta: 0:07:52 lr: 0.000601 loss: 3.5628 (3.3342) grad_norm: 1.3693 (1.3760) time: 0.6202 [2021-03-27 04:12:52 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 520/1251] eta: 0:07:46 lr: 0.000601 loss: 3.3494 (3.3348) grad_norm: 1.4332 (1.3774) time: 0.6265 [2021-03-27 04:12:59 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 530/1251] eta: 0:07:39 lr: 0.000601 loss: 3.3342 (3.3332) grad_norm: 1.4277 (1.3773) time: 0.6304 [2021-03-27 04:13:05 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 540/1251] eta: 0:07:33 lr: 0.000601 loss: 3.5028 (3.3330) grad_norm: 1.3593 (1.3773) time: 0.6286 [2021-03-27 04:13:12 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 550/1251] eta: 0:07:27 lr: 0.000601 loss: 3.5900 (3.3360) grad_norm: 1.2873 (1.3765) time: 0.6502 [2021-03-27 04:13:18 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 560/1251] eta: 0:07:20 lr: 0.000601 loss: 3.3441 (3.3323) grad_norm: 1.3312 (1.3774) time: 0.6511 [2021-03-27 04:13:24 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 570/1251] eta: 0:07:14 lr: 0.000601 loss: 3.3956 (3.3335) grad_norm: 1.4438 (1.3805) time: 0.6358 [2021-03-27 04:13:31 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 580/1251] eta: 0:07:07 lr: 0.000600 loss: 3.7187 (3.3398) grad_norm: 1.5242 (1.3834) time: 0.6350 [2021-03-27 04:13:37 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 590/1251] eta: 0:07:01 lr: 0.000600 loss: 3.4925 (3.3380) grad_norm: 1.3948 (1.3826) time: 0.6312 [2021-03-27 04:13:43 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 600/1251] eta: 0:06:54 lr: 0.000600 loss: 3.4891 (3.3407) grad_norm: 1.3244 (1.3824) time: 0.6330 [2021-03-27 04:13:50 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 610/1251] eta: 0:06:48 lr: 0.000600 loss: 3.5803 (3.3409) grad_norm: 1.3468 (1.3825) time: 0.6327 [2021-03-27 04:13:56 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 620/1251] eta: 0:06:42 lr: 0.000600 loss: 3.4881 (3.3448) grad_norm: 1.4032 (1.3833) time: 0.6330 [2021-03-27 04:14:02 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 630/1251] eta: 0:06:35 lr: 0.000600 loss: 3.4847 (3.3424) grad_norm: 1.4188 (1.3865) time: 0.6327 [2021-03-27 04:14:09 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 640/1251] eta: 0:06:29 lr: 0.000600 loss: 3.1635 (3.3418) grad_norm: 1.4595 (1.3889) time: 0.6314 [2021-03-27 04:14:15 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 650/1251] eta: 0:06:22 lr: 0.000600 loss: 3.1635 (3.3403) grad_norm: 1.3947 (1.3880) time: 0.6326 [2021-03-27 04:14:21 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 660/1251] eta: 0:06:16 lr: 0.000600 loss: 3.2409 (3.3402) grad_norm: 1.3552 (1.3874) time: 0.6327 [2021-03-27 04:14:28 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 670/1251] eta: 0:06:10 lr: 0.000600 loss: 3.4421 (3.3394) grad_norm: 1.4264 (1.3905) time: 0.6292 [2021-03-27 04:14:34 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 680/1251] eta: 0:06:03 lr: 0.000600 loss: 3.3928 (3.3405) grad_norm: 1.5320 (1.3914) time: 0.6306 [2021-03-27 04:14:40 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 690/1251] eta: 0:05:57 lr: 0.000600 loss: 3.5123 (3.3398) grad_norm: 1.4507 (1.3927) time: 0.6343 [2021-03-27 04:14:46 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 700/1251] eta: 0:05:50 lr: 0.000600 loss: 3.5182 (3.3410) grad_norm: 1.3732 (1.3934) time: 0.6301 [2021-03-27 04:14:53 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 710/1251] eta: 0:05:44 lr: 0.000600 loss: 3.5476 (3.3450) grad_norm: 1.3598 (1.3928) time: 0.6301 [2021-03-27 04:14:59 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 720/1251] eta: 0:05:38 lr: 0.000600 loss: 3.6474 (3.3458) grad_norm: 1.3313 (1.3926) time: 0.6355 [2021-03-27 04:15:06 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 730/1251] eta: 0:05:31 lr: 0.000600 loss: 3.3414 (3.3420) grad_norm: 1.3313 (1.3920) time: 0.6360 [2021-03-27 04:15:12 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 740/1251] eta: 0:05:25 lr: 0.000600 loss: 3.2734 (3.3435) grad_norm: 1.2958 (1.3914) time: 0.6406 [2021-03-27 04:15:18 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 750/1251] eta: 0:05:18 lr: 0.000600 loss: 3.3635 (3.3453) grad_norm: 1.3343 (1.3912) time: 0.6412 [2021-03-27 04:15:25 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 760/1251] eta: 0:05:12 lr: 0.000600 loss: 3.4709 (3.3453) grad_norm: 1.4035 (1.3930) time: 0.6349 [2021-03-27 04:15:31 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 770/1251] eta: 0:05:06 lr: 0.000600 loss: 3.1272 (3.3405) grad_norm: 1.4035 (1.3948) time: 0.6318 [2021-03-27 04:15:37 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 780/1251] eta: 0:04:59 lr: 0.000600 loss: 3.1272 (3.3420) grad_norm: 1.3737 (1.3965) time: 0.6259 [2021-03-27 04:15:43 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 790/1251] eta: 0:04:53 lr: 0.000600 loss: 3.4970 (3.3434) grad_norm: 1.4370 (1.3965) time: 0.6242 [2021-03-27 04:15:50 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 800/1251] eta: 0:04:46 lr: 0.000600 loss: 3.4622 (3.3438) grad_norm: 1.3487 (1.3958) time: 0.6341 [2021-03-27 04:15:56 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 810/1251] eta: 0:04:40 lr: 0.000600 loss: 3.4622 (3.3434) grad_norm: 1.3443 (1.3950) time: 0.6338 [2021-03-27 04:16:03 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 820/1251] eta: 0:04:34 lr: 0.000600 loss: 3.4427 (3.3466) grad_norm: 1.3358 (1.3944) time: 0.6318 [2021-03-27 04:16:09 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 830/1251] eta: 0:04:27 lr: 0.000599 loss: 3.4367 (3.3477) grad_norm: 1.3572 (1.3945) time: 0.6356 [2021-03-27 04:16:15 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 840/1251] eta: 0:04:21 lr: 0.000599 loss: 3.3935 (3.3485) grad_norm: 1.3210 (1.3942) time: 0.6267 [2021-03-27 04:16:21 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 850/1251] eta: 0:04:14 lr: 0.000599 loss: 3.5091 (3.3503) grad_norm: 1.3990 (1.3958) time: 0.6230 [2021-03-27 04:16:28 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 860/1251] eta: 0:04:08 lr: 0.000599 loss: 3.4115 (3.3496) grad_norm: 1.5259 (1.3965) time: 0.6273 [2021-03-27 04:16:34 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 870/1251] eta: 0:04:02 lr: 0.000599 loss: 3.3567 (3.3490) grad_norm: 1.3901 (1.3965) time: 0.6290 [2021-03-27 04:16:40 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 880/1251] eta: 0:03:55 lr: 0.000599 loss: 3.3609 (3.3494) grad_norm: 1.3400 (1.3965) time: 0.6333 [2021-03-27 04:16:47 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 890/1251] eta: 0:03:49 lr: 0.000599 loss: 3.3609 (3.3483) grad_norm: 1.4073 (1.3972) time: 0.6349 [2021-03-27 04:16:53 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 900/1251] eta: 0:03:43 lr: 0.000599 loss: 3.3858 (3.3502) grad_norm: 1.3348 (1.3963) time: 0.6290 [2021-03-27 04:16:59 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 910/1251] eta: 0:03:36 lr: 0.000599 loss: 3.4252 (3.3501) grad_norm: 1.3472 (1.3970) time: 0.6332 [2021-03-27 04:17:06 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 920/1251] eta: 0:03:30 lr: 0.000599 loss: 3.4841 (3.3522) grad_norm: 1.4374 (1.3973) time: 0.6467 [2021-03-27 04:17:12 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 930/1251] eta: 0:03:24 lr: 0.000599 loss: 3.5181 (3.3509) grad_norm: 1.2910 (1.3967) time: 0.6413 [2021-03-27 04:17:18 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 940/1251] eta: 0:03:17 lr: 0.000599 loss: 3.3867 (3.3512) grad_norm: 1.3122 (1.3974) time: 0.6287 [2021-03-27 04:17:25 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 950/1251] eta: 0:03:11 lr: 0.000599 loss: 3.2356 (3.3500) grad_norm: 1.4345 (1.3990) time: 0.6291 [2021-03-27 04:17:31 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 960/1251] eta: 0:03:04 lr: 0.000599 loss: 3.3384 (3.3539) grad_norm: 1.4345 (1.3997) time: 0.6317 [2021-03-27 04:17:37 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 970/1251] eta: 0:02:58 lr: 0.000599 loss: 3.3936 (3.3518) grad_norm: 1.3644 (1.3992) time: 0.6313 [2021-03-27 04:17:44 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 980/1251] eta: 0:02:52 lr: 0.000599 loss: 3.2937 (3.3508) grad_norm: 1.3644 (1.3986) time: 0.6315 [2021-03-27 04:17:50 swin_base_patch4_window7_224] INFO: Epoch: [131] [ 990/1251] eta: 0:02:45 lr: 0.000599 loss: 3.2699 (3.3489) grad_norm: 1.3018 (1.3980) time: 0.6313 [2021-03-27 04:17:56 swin_base_patch4_window7_224] INFO: Epoch: [131] [1000/1251] eta: 0:02:39 lr: 0.000599 loss: 3.1738 (3.3486) grad_norm: 1.3159 (1.3981) time: 0.6241 [2021-03-27 04:18:02 swin_base_patch4_window7_224] INFO: Epoch: [131] [1010/1251] eta: 0:02:33 lr: 0.000599 loss: 3.2342 (3.3473) grad_norm: 1.3431 (1.3985) time: 0.6190 [2021-03-27 04:18:09 swin_base_patch4_window7_224] INFO: Epoch: [131] [1020/1251] eta: 0:02:26 lr: 0.000599 loss: 3.3624 (3.3484) grad_norm: 1.4254 (1.3996) time: 0.6222 [2021-03-27 04:18:15 swin_base_patch4_window7_224] INFO: Epoch: [131] [1030/1251] eta: 0:02:20 lr: 0.000599 loss: 3.6247 (3.3508) grad_norm: 1.4643 (1.4001) time: 0.6295 [2021-03-27 04:18:21 swin_base_patch4_window7_224] INFO: Epoch: [131] [1040/1251] eta: 0:02:13 lr: 0.000599 loss: 3.5004 (3.3506) grad_norm: 1.4264 (1.3999) time: 0.6342 [2021-03-27 04:18:28 swin_base_patch4_window7_224] INFO: Epoch: [131] [1050/1251] eta: 0:02:07 lr: 0.000599 loss: 3.5004 (3.3523) grad_norm: 1.3182 (1.3994) time: 0.6345 [2021-03-27 04:18:34 swin_base_patch4_window7_224] INFO: Epoch: [131] [1060/1251] eta: 0:02:01 lr: 0.000599 loss: 3.5413 (3.3535) grad_norm: 1.3087 (1.3990) time: 0.6300 [2021-03-27 04:18:40 swin_base_patch4_window7_224] INFO: Epoch: [131] [1070/1251] eta: 0:01:54 lr: 0.000598 loss: 3.4300 (3.3542) grad_norm: 1.3694 (1.3989) time: 0.6330 [2021-03-27 04:18:47 swin_base_patch4_window7_224] INFO: Epoch: [131] [1080/1251] eta: 0:01:48 lr: 0.000598 loss: 3.4972 (3.3552) grad_norm: 1.3915 (1.3989) time: 0.6360 [2021-03-27 04:18:53 swin_base_patch4_window7_224] INFO: Epoch: [131] [1090/1251] eta: 0:01:42 lr: 0.000598 loss: 3.4884 (3.3550) grad_norm: 1.3824 (1.3989) time: 0.6296 [2021-03-27 04:18:59 swin_base_patch4_window7_224] INFO: Epoch: [131] [1100/1251] eta: 0:01:35 lr: 0.000598 loss: 3.4608 (3.3576) grad_norm: 1.2600 (1.3981) time: 0.6278 [2021-03-27 04:19:05 swin_base_patch4_window7_224] INFO: Epoch: [131] [1110/1251] eta: 0:01:29 lr: 0.000598 loss: 3.6284 (3.3592) grad_norm: 1.2600 (1.3980) time: 0.6267 [2021-03-27 04:19:12 swin_base_patch4_window7_224] INFO: Epoch: [131] [1120/1251] eta: 0:01:23 lr: 0.000598 loss: 3.5589 (3.3608) grad_norm: 1.3628 (1.3976) time: 0.6262 [2021-03-27 04:19:18 swin_base_patch4_window7_224] INFO: Epoch: [131] [1130/1251] eta: 0:01:16 lr: 0.000598 loss: 3.3945 (3.3591) grad_norm: 1.4210 (1.3985) time: 0.6287 [2021-03-27 04:19:24 swin_base_patch4_window7_224] INFO: Epoch: [131] [1140/1251] eta: 0:01:10 lr: 0.000598 loss: 3.3529 (3.3578) grad_norm: 1.4622 (1.3990) time: 0.6305 [2021-03-27 04:19:31 swin_base_patch4_window7_224] INFO: Epoch: [131] [1150/1251] eta: 0:01:04 lr: 0.000598 loss: 3.3654 (3.3562) grad_norm: 1.3941 (1.3988) time: 0.6292 [2021-03-27 04:19:37 swin_base_patch4_window7_224] INFO: Epoch: [131] [1160/1251] eta: 0:00:57 lr: 0.000598 loss: 3.5421 (3.3566) grad_norm: 1.2999 (1.3979) time: 0.6283 [2021-03-27 04:19:43 swin_base_patch4_window7_224] INFO: Epoch: [131] [1170/1251] eta: 0:00:51 lr: 0.000598 loss: 3.5603 (3.3588) grad_norm: 1.2868 (1.3973) time: 0.6326 [2021-03-27 04:19:50 swin_base_patch4_window7_224] INFO: Epoch: [131] [1180/1251] eta: 0:00:45 lr: 0.000598 loss: 3.4772 (3.3604) grad_norm: 1.3417 (1.3977) time: 0.6336 [2021-03-27 04:19:56 swin_base_patch4_window7_224] INFO: Epoch: [131] [1190/1251] eta: 0:00:38 lr: 0.000598 loss: 3.4391 (3.3617) grad_norm: 1.4534 (1.3978) time: 0.6318 [2021-03-27 04:20:02 swin_base_patch4_window7_224] INFO: Epoch: [131] [1200/1251] eta: 0:00:32 lr: 0.000598 loss: 3.3124 (3.3614) grad_norm: 1.3064 (1.3973) time: 0.6301 [2021-03-27 04:20:08 swin_base_patch4_window7_224] INFO: Epoch: [131] [1210/1251] eta: 0:00:26 lr: 0.000598 loss: 3.4540 (3.3626) grad_norm: 1.2957 (1.3975) time: 0.6252 [2021-03-27 04:20:15 swin_base_patch4_window7_224] INFO: Epoch: [131] [1220/1251] eta: 0:00:19 lr: 0.000598 loss: 3.5834 (3.3637) grad_norm: 1.3892 (1.3985) time: 0.6251 [2021-03-27 04:20:21 swin_base_patch4_window7_224] INFO: Epoch: [131] [1230/1251] eta: 0:00:13 lr: 0.000598 loss: 3.5924 (3.3651) grad_norm: 1.3584 (1.3981) time: 0.6250 [2021-03-27 04:20:27 swin_base_patch4_window7_224] INFO: Epoch: [131] [1240/1251] eta: 0:00:06 lr: 0.000598 loss: 3.4072 (3.3644) grad_norm: 1.3494 (1.3981) time: 0.6231 [2021-03-27 04:20:33 swin_base_patch4_window7_224] INFO: Epoch: [131] [1250/1251] eta: 0:00:00 lr: 0.000598 loss: 3.2073 (3.3631) grad_norm: 1.3392 (1.3976) time: 0.6176 [2021-03-27 04:20:45 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:22 loss: 1.0180 (1.0180) acc1: 73.4375 (73.4375) acc5: 96.8750 (96.8750) [2021-03-27 04:20:47 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:13 loss: 1.0180 (0.9699) acc1: 78.1250 (78.1250) acc5: 95.3125 (94.6023) [2021-03-27 04:20:50 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9371 (0.9634) acc1: 78.1250 (77.7530) acc5: 95.3125 (94.3452) [2021-03-27 04:20:52 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9426 (0.9689) acc1: 76.5625 (77.0665) acc5: 95.3125 (94.4556) [2021-03-27 04:20:54 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9389 (0.9545) acc1: 75.0000 (77.0579) acc5: 95.3125 (94.7027) [2021-03-27 04:20:55 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9210 (0.9593) acc1: 75.0000 (77.1200) acc5: 95.3125 (94.7840) [2021-03-27 04:21:04 swin_base_patch4_window7_224] INFO: * Acc@1 78.026 Acc@5 94.378 loss 0.944 [2021-03-27 04:21:04 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.0% [2021-03-27 04:21:04 swin_base_patch4_window7_224] INFO: Max accuracy: 78.16% [2021-03-27 04:21:08 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 0/1251] eta: 1:29:57 lr: 0.000598 loss: 3.5664 (3.5664) grad_norm: 1.3532 (1.3532) time: 4.3147 [2021-03-27 04:21:15 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 10/1251] eta: 0:20:08 lr: 0.000598 loss: 2.7583 (2.9391) grad_norm: 1.4330 (1.4341) time: 0.9738 [2021-03-27 04:21:21 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 20/1251] eta: 0:16:43 lr: 0.000598 loss: 3.1101 (3.1135) grad_norm: 1.3850 (1.4124) time: 0.6404 [2021-03-27 04:21:27 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 30/1251] eta: 0:15:23 lr: 0.000598 loss: 3.4835 (3.2156) grad_norm: 1.3832 (1.4429) time: 0.6364 [2021-03-27 04:21:34 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 40/1251] eta: 0:14:38 lr: 0.000598 loss: 3.4835 (3.2577) grad_norm: 1.3724 (1.4283) time: 0.6306 [2021-03-27 04:21:40 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 50/1251] eta: 0:14:11 lr: 0.000598 loss: 3.4695 (3.2528) grad_norm: 1.3522 (1.4103) time: 0.6355 [2021-03-27 04:21:46 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 60/1251] eta: 0:13:48 lr: 0.000598 loss: 3.4959 (3.2964) grad_norm: 1.3616 (1.3991) time: 0.6342 [2021-03-27 04:21:53 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 70/1251] eta: 0:13:30 lr: 0.000597 loss: 3.4742 (3.2744) grad_norm: 1.3384 (1.3858) time: 0.6279 [2021-03-27 04:21:59 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 80/1251] eta: 0:13:14 lr: 0.000597 loss: 3.4553 (3.3083) grad_norm: 1.3384 (1.3862) time: 0.6253 [2021-03-27 04:22:05 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 90/1251] eta: 0:13:00 lr: 0.000597 loss: 3.4795 (3.2987) grad_norm: 1.3340 (1.3815) time: 0.6232 [2021-03-27 04:22:11 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 100/1251] eta: 0:12:48 lr: 0.000597 loss: 3.3546 (3.2840) grad_norm: 1.3185 (1.3812) time: 0.6267 [2021-03-27 04:22:18 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 110/1251] eta: 0:12:38 lr: 0.000597 loss: 3.3657 (3.2893) grad_norm: 1.3185 (1.3798) time: 0.6311 [2021-03-27 04:22:24 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 120/1251] eta: 0:12:28 lr: 0.000597 loss: 3.3707 (3.2856) grad_norm: 1.3493 (1.3783) time: 0.6303 [2021-03-27 04:22:30 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 130/1251] eta: 0:12:18 lr: 0.000597 loss: 3.4197 (3.3041) grad_norm: 1.3154 (1.3772) time: 0.6257 [2021-03-27 04:22:37 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 140/1251] eta: 0:12:09 lr: 0.000597 loss: 3.4713 (3.2989) grad_norm: 1.3337 (1.3754) time: 0.6258 [2021-03-27 04:22:43 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 150/1251] eta: 0:12:00 lr: 0.000597 loss: 3.4043 (3.2945) grad_norm: 1.4340 (1.3828) time: 0.6280 [2021-03-27 04:22:49 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 160/1251] eta: 0:11:52 lr: 0.000597 loss: 3.3265 (3.2940) grad_norm: 1.4340 (1.3810) time: 0.6271 [2021-03-27 04:22:55 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 170/1251] eta: 0:11:44 lr: 0.000597 loss: 3.4479 (3.3016) grad_norm: 1.3272 (1.3782) time: 0.6287 [2021-03-27 04:23:02 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 180/1251] eta: 0:11:36 lr: 0.000597 loss: 3.4650 (3.3149) grad_norm: 1.2909 (1.3759) time: 0.6301 [2021-03-27 04:23:08 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 190/1251] eta: 0:11:28 lr: 0.000597 loss: 3.4600 (3.3274) grad_norm: 1.3984 (1.3801) time: 0.6289 [2021-03-27 04:23:14 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 200/1251] eta: 0:11:21 lr: 0.000597 loss: 3.4465 (3.3314) grad_norm: 1.4355 (1.3845) time: 0.6309 [2021-03-27 04:23:21 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 210/1251] eta: 0:11:13 lr: 0.000597 loss: 3.2215 (3.3184) grad_norm: 1.3954 (1.3856) time: 0.6275 [2021-03-27 04:23:27 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 220/1251] eta: 0:11:06 lr: 0.000597 loss: 3.4511 (3.3254) grad_norm: 1.3358 (1.3839) time: 0.6265 [2021-03-27 04:23:33 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 230/1251] eta: 0:10:59 lr: 0.000597 loss: 3.5091 (3.3242) grad_norm: 1.3287 (1.3802) time: 0.6277 [2021-03-27 04:23:39 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 240/1251] eta: 0:10:51 lr: 0.000597 loss: 3.4909 (3.3330) grad_norm: 1.3242 (1.3802) time: 0.6265 [2021-03-27 04:23:46 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 250/1251] eta: 0:10:44 lr: 0.000597 loss: 3.4181 (3.3332) grad_norm: 1.4099 (1.3831) time: 0.6281 [2021-03-27 04:23:52 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 260/1251] eta: 0:10:37 lr: 0.000597 loss: 3.3427 (3.3276) grad_norm: 1.4099 (1.3848) time: 0.6294 [2021-03-27 04:23:58 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 270/1251] eta: 0:10:30 lr: 0.000597 loss: 3.3543 (3.3335) grad_norm: 1.3243 (1.3825) time: 0.6290 [2021-03-27 04:24:05 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 280/1251] eta: 0:10:24 lr: 0.000597 loss: 3.5523 (3.3371) grad_norm: 1.3342 (1.3865) time: 0.6300 [2021-03-27 04:24:11 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 290/1251] eta: 0:10:17 lr: 0.000597 loss: 3.5332 (3.3329) grad_norm: 1.3340 (1.3840) time: 0.6299 [2021-03-27 04:24:17 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 300/1251] eta: 0:10:10 lr: 0.000597 loss: 3.1017 (3.3289) grad_norm: 1.3074 (1.3861) time: 0.6241 [2021-03-27 04:24:23 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 310/1251] eta: 0:10:03 lr: 0.000596 loss: 3.1196 (3.3227) grad_norm: 1.3715 (1.3885) time: 0.6242 [2021-03-27 04:24:30 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 320/1251] eta: 0:09:56 lr: 0.000596 loss: 3.3501 (3.3215) grad_norm: 1.3652 (1.3864) time: 0.6308 [2021-03-27 04:24:36 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 330/1251] eta: 0:09:49 lr: 0.000596 loss: 3.5484 (3.3272) grad_norm: 1.3290 (1.3860) time: 0.6308 [2021-03-27 04:24:42 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 340/1251] eta: 0:09:43 lr: 0.000596 loss: 3.5484 (3.3311) grad_norm: 1.3376 (1.3887) time: 0.6289 [2021-03-27 04:24:49 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 350/1251] eta: 0:09:36 lr: 0.000596 loss: 3.4339 (3.3338) grad_norm: 1.3381 (1.3886) time: 0.6333 [2021-03-27 04:24:55 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 360/1251] eta: 0:09:30 lr: 0.000596 loss: 3.2971 (3.3260) grad_norm: 1.3381 (1.3858) time: 0.6353 [2021-03-27 04:25:01 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 370/1251] eta: 0:09:23 lr: 0.000596 loss: 3.2332 (3.3294) grad_norm: 1.3026 (1.3850) time: 0.6303 [2021-03-27 04:25:08 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 380/1251] eta: 0:09:16 lr: 0.000596 loss: 3.4646 (3.3322) grad_norm: 1.3320 (1.3848) time: 0.6285 [2021-03-27 04:25:14 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 390/1251] eta: 0:09:10 lr: 0.000596 loss: 3.5702 (3.3421) grad_norm: 1.3320 (1.3852) time: 0.6300 [2021-03-27 04:25:20 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 400/1251] eta: 0:09:03 lr: 0.000596 loss: 3.5702 (3.3442) grad_norm: 1.3686 (1.3859) time: 0.6301 [2021-03-27 04:25:27 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 410/1251] eta: 0:08:57 lr: 0.000596 loss: 3.2894 (3.3417) grad_norm: 1.3701 (1.3875) time: 0.6335 [2021-03-27 04:25:33 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 420/1251] eta: 0:08:50 lr: 0.000596 loss: 3.3321 (3.3438) grad_norm: 1.4348 (1.3894) time: 0.6339 [2021-03-27 04:25:39 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 430/1251] eta: 0:08:44 lr: 0.000596 loss: 3.4112 (3.3399) grad_norm: 1.4348 (1.3902) time: 0.6386 [2021-03-27 04:25:46 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 440/1251] eta: 0:08:37 lr: 0.000596 loss: 3.4787 (3.3408) grad_norm: 1.3934 (1.3903) time: 0.6394 [2021-03-27 04:25:52 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 450/1251] eta: 0:08:31 lr: 0.000596 loss: 3.5421 (3.3420) grad_norm: 1.3294 (1.3893) time: 0.6300 [2021-03-27 04:25:58 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 460/1251] eta: 0:08:24 lr: 0.000596 loss: 3.5421 (3.3435) grad_norm: 1.3806 (1.3895) time: 0.6329 [2021-03-27 04:26:05 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 470/1251] eta: 0:08:18 lr: 0.000596 loss: 3.5321 (3.3469) grad_norm: 1.3557 (1.3883) time: 0.6339 [2021-03-27 04:26:11 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 480/1251] eta: 0:08:11 lr: 0.000596 loss: 3.5368 (3.3474) grad_norm: 1.3193 (1.3869) time: 0.6309 [2021-03-27 04:26:17 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 490/1251] eta: 0:08:05 lr: 0.000596 loss: 3.2449 (3.3446) grad_norm: 1.3079 (1.3856) time: 0.6310 [2021-03-27 04:26:23 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 500/1251] eta: 0:07:58 lr: 0.000596 loss: 3.2400 (3.3484) grad_norm: 1.3579 (1.3861) time: 0.6244 [2021-03-27 04:26:30 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 510/1251] eta: 0:07:52 lr: 0.000596 loss: 3.5471 (3.3486) grad_norm: 1.3748 (1.3859) time: 0.6222 [2021-03-27 04:26:36 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 520/1251] eta: 0:07:45 lr: 0.000596 loss: 3.6334 (3.3526) grad_norm: 1.3892 (1.3876) time: 0.6313 [2021-03-27 04:26:42 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 530/1251] eta: 0:07:39 lr: 0.000596 loss: 3.6963 (3.3581) grad_norm: 1.4359 (1.3907) time: 0.6365 [2021-03-27 04:26:49 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 540/1251] eta: 0:07:32 lr: 0.000596 loss: 3.7647 (3.3594) grad_norm: 1.4671 (1.3931) time: 0.6305 [2021-03-27 04:26:55 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 550/1251] eta: 0:07:26 lr: 0.000596 loss: 3.4463 (3.3632) grad_norm: 1.4153 (1.3955) time: 0.6369 [2021-03-27 04:27:02 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 560/1251] eta: 0:07:20 lr: 0.000595 loss: 3.6128 (3.3674) grad_norm: 1.3559 (1.3952) time: 0.6448 [2021-03-27 04:27:08 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 570/1251] eta: 0:07:13 lr: 0.000595 loss: 3.6128 (3.3695) grad_norm: 1.3607 (1.3952) time: 0.6338 [2021-03-27 04:27:14 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 580/1251] eta: 0:07:07 lr: 0.000595 loss: 3.3729 (3.3665) grad_norm: 1.3939 (1.3964) time: 0.6339 [2021-03-27 04:27:21 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 590/1251] eta: 0:07:01 lr: 0.000595 loss: 3.3556 (3.3690) grad_norm: 1.3892 (1.3951) time: 0.6333 [2021-03-27 04:27:27 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 600/1251] eta: 0:06:54 lr: 0.000595 loss: 3.3556 (3.3698) grad_norm: 1.2799 (1.3950) time: 0.6288 [2021-03-27 04:27:33 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 610/1251] eta: 0:06:48 lr: 0.000595 loss: 3.4005 (3.3700) grad_norm: 1.3100 (1.3938) time: 0.6315 [2021-03-27 04:27:39 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 620/1251] eta: 0:06:41 lr: 0.000595 loss: 3.3838 (3.3691) grad_norm: 1.3381 (1.3949) time: 0.6272 [2021-03-27 04:27:46 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 630/1251] eta: 0:06:35 lr: 0.000595 loss: 3.1585 (3.3677) grad_norm: 1.3889 (1.3946) time: 0.6307 [2021-03-27 04:27:52 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 640/1251] eta: 0:06:28 lr: 0.000595 loss: 3.5375 (3.3707) grad_norm: 1.3788 (1.3947) time: 0.6308 [2021-03-27 04:27:58 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 650/1251] eta: 0:06:22 lr: 0.000595 loss: 3.4733 (3.3685) grad_norm: 1.3185 (1.3934) time: 0.6291 [2021-03-27 04:28:05 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 660/1251] eta: 0:06:15 lr: 0.000595 loss: 3.4108 (3.3704) grad_norm: 1.3139 (inf) time: 0.6300 [2021-03-27 04:28:11 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 670/1251] eta: 0:06:09 lr: 0.000595 loss: 3.0524 (3.3625) grad_norm: 1.3666 (inf) time: 0.6296 [2021-03-27 04:28:17 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 680/1251] eta: 0:06:03 lr: 0.000595 loss: 3.0524 (3.3620) grad_norm: 1.3576 (inf) time: 0.6320 [2021-03-27 04:28:24 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 690/1251] eta: 0:05:56 lr: 0.000595 loss: 3.5529 (3.3619) grad_norm: 1.3576 (inf) time: 0.6326 [2021-03-27 04:28:30 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 700/1251] eta: 0:05:50 lr: 0.000595 loss: 3.4071 (3.3615) grad_norm: 1.3660 (inf) time: 0.6293 [2021-03-27 04:28:36 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 710/1251] eta: 0:05:44 lr: 0.000595 loss: 3.2415 (3.3628) grad_norm: 1.2830 (inf) time: 0.6302 [2021-03-27 04:28:43 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 720/1251] eta: 0:05:37 lr: 0.000595 loss: 3.2415 (3.3602) grad_norm: 1.2473 (inf) time: 0.6358 [2021-03-27 04:28:49 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 730/1251] eta: 0:05:31 lr: 0.000595 loss: 3.2361 (3.3594) grad_norm: 1.2785 (inf) time: 0.6394 [2021-03-27 04:28:55 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 740/1251] eta: 0:05:24 lr: 0.000595 loss: 3.4158 (3.3617) grad_norm: 1.3720 (inf) time: 0.6380 [2021-03-27 04:29:02 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 750/1251] eta: 0:05:18 lr: 0.000595 loss: 3.5226 (3.3591) grad_norm: 1.4033 (inf) time: 0.6351 [2021-03-27 04:29:08 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 760/1251] eta: 0:05:12 lr: 0.000595 loss: 3.4204 (3.3601) grad_norm: 1.3493 (inf) time: 0.6327 [2021-03-27 04:29:14 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 770/1251] eta: 0:05:05 lr: 0.000595 loss: 3.3143 (3.3596) grad_norm: 1.2779 (inf) time: 0.6334 [2021-03-27 04:29:21 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 780/1251] eta: 0:04:59 lr: 0.000595 loss: 3.4832 (3.3594) grad_norm: 1.2605 (inf) time: 0.6374 [2021-03-27 04:29:27 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 790/1251] eta: 0:04:53 lr: 0.000595 loss: 3.4745 (3.3596) grad_norm: 1.3671 (inf) time: 0.6281 [2021-03-27 04:29:33 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 800/1251] eta: 0:04:46 lr: 0.000594 loss: 3.4600 (3.3597) grad_norm: 1.3671 (inf) time: 0.6256 [2021-03-27 04:29:40 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 810/1251] eta: 0:04:40 lr: 0.000594 loss: 3.5771 (3.3634) grad_norm: 1.3477 (inf) time: 0.6299 [2021-03-27 04:29:46 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 820/1251] eta: 0:04:33 lr: 0.000594 loss: 3.6665 (3.3666) grad_norm: 1.3435 (inf) time: 0.6303 [2021-03-27 04:29:52 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 830/1251] eta: 0:04:27 lr: 0.000594 loss: 3.2061 (3.3640) grad_norm: 1.3776 (inf) time: 0.6338 [2021-03-27 04:29:59 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 840/1251] eta: 0:04:21 lr: 0.000594 loss: 3.2559 (3.3660) grad_norm: 1.3542 (inf) time: 0.6321 [2021-03-27 04:30:05 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 850/1251] eta: 0:04:14 lr: 0.000594 loss: 3.5460 (3.3650) grad_norm: 1.3409 (inf) time: 0.6281 [2021-03-27 04:30:11 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 860/1251] eta: 0:04:08 lr: 0.000594 loss: 3.5283 (3.3644) grad_norm: 1.4128 (inf) time: 0.6306 [2021-03-27 04:30:17 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 870/1251] eta: 0:04:02 lr: 0.000594 loss: 3.4419 (3.3633) grad_norm: 1.3981 (inf) time: 0.6334 [2021-03-27 04:30:24 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 880/1251] eta: 0:03:55 lr: 0.000594 loss: 3.1815 (3.3594) grad_norm: 1.3628 (inf) time: 0.6400 [2021-03-27 04:30:30 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 890/1251] eta: 0:03:49 lr: 0.000594 loss: 3.3084 (3.3619) grad_norm: 1.4372 (inf) time: 0.6399 [2021-03-27 04:30:37 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 900/1251] eta: 0:03:42 lr: 0.000594 loss: 3.5639 (3.3641) grad_norm: 1.4736 (inf) time: 0.6292 [2021-03-27 04:30:43 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 910/1251] eta: 0:03:36 lr: 0.000594 loss: 3.5271 (3.3643) grad_norm: 1.4755 (inf) time: 0.6272 [2021-03-27 04:30:49 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 920/1251] eta: 0:03:30 lr: 0.000594 loss: 3.5564 (3.3668) grad_norm: 1.4037 (inf) time: 0.6285 [2021-03-27 04:30:55 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 930/1251] eta: 0:03:23 lr: 0.000594 loss: 3.3490 (3.3643) grad_norm: 1.3547 (inf) time: 0.6302 [2021-03-27 04:31:02 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 940/1251] eta: 0:03:17 lr: 0.000594 loss: 3.5996 (3.3685) grad_norm: 1.2706 (inf) time: 0.6313 [2021-03-27 04:31:08 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 950/1251] eta: 0:03:11 lr: 0.000594 loss: 3.5996 (3.3697) grad_norm: 1.2838 (inf) time: 0.6347 [2021-03-27 04:31:14 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 960/1251] eta: 0:03:04 lr: 0.000594 loss: 3.4810 (3.3717) grad_norm: 1.3206 (inf) time: 0.6353 [2021-03-27 04:31:21 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 970/1251] eta: 0:02:58 lr: 0.000594 loss: 3.5021 (3.3710) grad_norm: 1.3260 (inf) time: 0.6302 [2021-03-27 04:31:27 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 980/1251] eta: 0:02:52 lr: 0.000594 loss: 3.3044 (3.3676) grad_norm: 1.3360 (inf) time: 0.6300 [2021-03-27 04:31:33 swin_base_patch4_window7_224] INFO: Epoch: [132] [ 990/1251] eta: 0:02:45 lr: 0.000594 loss: 3.3044 (3.3677) grad_norm: 1.3892 (inf) time: 0.6292 [2021-03-27 04:31:40 swin_base_patch4_window7_224] INFO: Epoch: [132] [1000/1251] eta: 0:02:39 lr: 0.000594 loss: 3.4240 (3.3670) grad_norm: 1.3900 (inf) time: 0.6248 [2021-03-27 04:31:46 swin_base_patch4_window7_224] INFO: Epoch: [132] [1010/1251] eta: 0:02:32 lr: 0.000594 loss: 3.3636 (3.3652) grad_norm: 1.3907 (inf) time: 0.6237 [2021-03-27 04:31:52 swin_base_patch4_window7_224] INFO: Epoch: [132] [1020/1251] eta: 0:02:26 lr: 0.000594 loss: 3.3636 (3.3673) grad_norm: 1.3807 (inf) time: 0.6309 [2021-03-27 04:31:58 swin_base_patch4_window7_224] INFO: Epoch: [132] [1030/1251] eta: 0:02:20 lr: 0.000594 loss: 3.6312 (3.3685) grad_norm: 1.3244 (inf) time: 0.6291 [2021-03-27 04:32:05 swin_base_patch4_window7_224] INFO: Epoch: [132] [1040/1251] eta: 0:02:13 lr: 0.000594 loss: 3.2837 (3.3672) grad_norm: 1.3007 (inf) time: 0.6239 [2021-03-27 04:32:11 swin_base_patch4_window7_224] INFO: Epoch: [132] [1050/1251] eta: 0:02:07 lr: 0.000593 loss: 3.2881 (3.3672) grad_norm: 1.3004 (inf) time: 0.6249 [2021-03-27 04:32:17 swin_base_patch4_window7_224] INFO: Epoch: [132] [1060/1251] eta: 0:02:01 lr: 0.000593 loss: 3.5217 (3.3691) grad_norm: 1.3673 (inf) time: 0.6251 [2021-03-27 04:32:23 swin_base_patch4_window7_224] INFO: Epoch: [132] [1070/1251] eta: 0:01:54 lr: 0.000593 loss: 3.6960 (3.3721) grad_norm: 1.3814 (inf) time: 0.6269 [2021-03-27 04:32:30 swin_base_patch4_window7_224] INFO: Epoch: [132] [1080/1251] eta: 0:01:48 lr: 0.000593 loss: 3.5500 (3.3718) grad_norm: 1.3742 (inf) time: 0.6284 [2021-03-27 04:32:36 swin_base_patch4_window7_224] INFO: Epoch: [132] [1090/1251] eta: 0:01:42 lr: 0.000593 loss: 3.3503 (3.3699) grad_norm: 1.3486 (inf) time: 0.6306 [2021-03-27 04:32:42 swin_base_patch4_window7_224] INFO: Epoch: [132] [1100/1251] eta: 0:01:35 lr: 0.000593 loss: 3.1062 (3.3688) grad_norm: 1.4291 (inf) time: 0.6290 [2021-03-27 04:32:49 swin_base_patch4_window7_224] INFO: Epoch: [132] [1110/1251] eta: 0:01:29 lr: 0.000593 loss: 3.3224 (3.3682) grad_norm: 1.4063 (inf) time: 0.6270 [2021-03-27 04:32:55 swin_base_patch4_window7_224] INFO: Epoch: [132] [1120/1251] eta: 0:01:23 lr: 0.000593 loss: 3.3224 (3.3685) grad_norm: 1.3998 (inf) time: 0.6256 [2021-03-27 04:33:01 swin_base_patch4_window7_224] INFO: Epoch: [132] [1130/1251] eta: 0:01:16 lr: 0.000593 loss: 3.2958 (3.3680) grad_norm: 1.4004 (inf) time: 0.6239 [2021-03-27 04:33:07 swin_base_patch4_window7_224] INFO: Epoch: [132] [1140/1251] eta: 0:01:10 lr: 0.000593 loss: 3.2958 (3.3679) grad_norm: 1.4610 (inf) time: 0.6293 [2021-03-27 04:33:14 swin_base_patch4_window7_224] INFO: Epoch: [132] [1150/1251] eta: 0:01:04 lr: 0.000593 loss: 3.5032 (3.3691) grad_norm: 1.3996 (inf) time: 0.6278 [2021-03-27 04:33:20 swin_base_patch4_window7_224] INFO: Epoch: [132] [1160/1251] eta: 0:00:57 lr: 0.000593 loss: 3.6064 (3.3704) grad_norm: 1.3845 (inf) time: 0.6272 [2021-03-27 04:33:26 swin_base_patch4_window7_224] INFO: Epoch: [132] [1170/1251] eta: 0:00:51 lr: 0.000593 loss: 3.5981 (3.3734) grad_norm: 1.5134 (inf) time: 0.6324 [2021-03-27 04:33:33 swin_base_patch4_window7_224] INFO: Epoch: [132] [1180/1251] eta: 0:00:44 lr: 0.000593 loss: 3.5778 (3.3742) grad_norm: 1.4789 (inf) time: 0.6276 [2021-03-27 04:33:39 swin_base_patch4_window7_224] INFO: Epoch: [132] [1190/1251] eta: 0:00:38 lr: 0.000593 loss: 3.2665 (3.3731) grad_norm: 1.3626 (inf) time: 0.6283 [2021-03-27 04:33:45 swin_base_patch4_window7_224] INFO: Epoch: [132] [1200/1251] eta: 0:00:32 lr: 0.000593 loss: 3.2648 (3.3744) grad_norm: 1.3105 (inf) time: 0.6304 [2021-03-27 04:33:52 swin_base_patch4_window7_224] INFO: Epoch: [132] [1210/1251] eta: 0:00:25 lr: 0.000593 loss: 3.4557 (3.3750) grad_norm: 1.3113 (inf) time: 0.6326 [2021-03-27 04:33:58 swin_base_patch4_window7_224] INFO: Epoch: [132] [1220/1251] eta: 0:00:19 lr: 0.000593 loss: 3.2924 (3.3739) grad_norm: 1.3364 (inf) time: 0.6336 [2021-03-27 04:34:04 swin_base_patch4_window7_224] INFO: Epoch: [132] [1230/1251] eta: 0:00:13 lr: 0.000593 loss: 3.1121 (3.3735) grad_norm: 1.3213 (inf) time: 0.6327 [2021-03-27 04:34:10 swin_base_patch4_window7_224] INFO: Epoch: [132] [1240/1251] eta: 0:00:06 lr: 0.000593 loss: 3.3799 (3.3739) grad_norm: 1.3331 (inf) time: 0.6303 [2021-03-27 04:34:17 swin_base_patch4_window7_224] INFO: Epoch: [132] [1250/1251] eta: 0:00:00 lr: 0.000593 loss: 3.5732 (3.3739) grad_norm: 1.3583 (inf) time: 0.6213 [2021-03-27 04:34:26 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:14 loss: 1.0081 (1.0081) acc1: 79.6875 (79.6875) acc5: 96.8750 (96.8750) [2021-03-27 04:34:28 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.9655 (0.9773) acc1: 78.1250 (77.4148) acc5: 95.3125 (93.7500) [2021-03-27 04:34:31 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9165 (0.9689) acc1: 78.1250 (77.3810) acc5: 95.3125 (94.1964) [2021-03-27 04:34:32 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9175 (0.9761) acc1: 78.1250 (77.1673) acc5: 95.3125 (94.3044) [2021-03-27 04:34:34 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8725 (0.9431) acc1: 78.1250 (77.4009) acc5: 95.3125 (94.7027) [2021-03-27 04:34:35 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8863 (0.9595) acc1: 78.1250 (77.2800) acc5: 95.3125 (94.5920) [2021-03-27 04:34:45 swin_base_patch4_window7_224] INFO: * Acc@1 78.010 Acc@5 94.488 loss 0.939 [2021-03-27 04:34:45 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.0% [2021-03-27 04:34:45 swin_base_patch4_window7_224] INFO: Max accuracy: 78.16% [2021-03-27 04:34:50 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 0/1251] eta: 1:32:23 lr: 0.000593 loss: 3.6466 (3.6466) grad_norm: 1.5611 (1.5611) time: 4.4310 [2021-03-27 04:34:56 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 10/1251] eta: 0:20:20 lr: 0.000593 loss: 3.4410 (3.4435) grad_norm: 1.4466 (1.4599) time: 0.9833 [2021-03-27 04:35:02 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 20/1251] eta: 0:16:56 lr: 0.000593 loss: 3.1986 (3.2270) grad_norm: 1.4095 (1.4392) time: 0.6451 [2021-03-27 04:35:09 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 30/1251] eta: 0:15:35 lr: 0.000593 loss: 3.0777 (3.1735) grad_norm: 1.4210 (1.4415) time: 0.6464 [2021-03-27 04:35:15 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 40/1251] eta: 0:14:48 lr: 0.000592 loss: 3.3664 (3.2528) grad_norm: 1.3854 (1.4169) time: 0.6382 [2021-03-27 04:35:21 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 50/1251] eta: 0:14:16 lr: 0.000592 loss: 3.4092 (3.2519) grad_norm: 1.3252 (1.4052) time: 0.6312 [2021-03-27 04:35:28 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 60/1251] eta: 0:13:54 lr: 0.000592 loss: 3.3477 (3.2581) grad_norm: 1.3724 (1.4226) time: 0.6328 [2021-03-27 04:35:34 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 70/1251] eta: 0:13:37 lr: 0.000592 loss: 3.3396 (3.2566) grad_norm: 1.3929 (1.4224) time: 0.6405 [2021-03-27 04:35:41 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 80/1251] eta: 0:13:22 lr: 0.000592 loss: 3.3430 (3.2537) grad_norm: 1.3544 (1.4197) time: 0.6377 [2021-03-27 04:35:47 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 90/1251] eta: 0:13:09 lr: 0.000592 loss: 3.4561 (3.2733) grad_norm: 1.3921 (1.4200) time: 0.6335 [2021-03-27 04:35:53 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 100/1251] eta: 0:12:56 lr: 0.000592 loss: 3.4561 (3.2827) grad_norm: 1.2527 (1.4029) time: 0.6312 [2021-03-27 04:35:59 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 110/1251] eta: 0:12:44 lr: 0.000592 loss: 3.3935 (3.2899) grad_norm: 1.2456 (1.3993) time: 0.6263 [2021-03-27 04:36:06 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 120/1251] eta: 0:12:35 lr: 0.000592 loss: 3.5522 (3.3082) grad_norm: 1.3275 (1.3980) time: 0.6325 [2021-03-27 04:36:12 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 130/1251] eta: 0:12:25 lr: 0.000592 loss: 3.5727 (3.3128) grad_norm: 1.3248 (1.3951) time: 0.6358 [2021-03-27 04:36:19 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 140/1251] eta: 0:12:17 lr: 0.000592 loss: 3.4119 (3.3081) grad_norm: 1.3172 (1.3906) time: 0.6391 [2021-03-27 04:36:25 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 150/1251] eta: 0:12:07 lr: 0.000592 loss: 3.4119 (3.3289) grad_norm: 1.3119 (1.3893) time: 0.6376 [2021-03-27 04:36:31 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 160/1251] eta: 0:11:59 lr: 0.000592 loss: 3.5312 (3.3389) grad_norm: 1.3830 (1.3913) time: 0.6280 [2021-03-27 04:36:38 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 170/1251] eta: 0:11:50 lr: 0.000592 loss: 3.4892 (3.3431) grad_norm: 1.3853 (1.3918) time: 0.6304 [2021-03-27 04:36:44 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 180/1251] eta: 0:11:42 lr: 0.000592 loss: 3.4589 (3.3438) grad_norm: 1.3646 (1.3873) time: 0.6332 [2021-03-27 04:36:50 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 190/1251] eta: 0:11:34 lr: 0.000592 loss: 3.4332 (3.3524) grad_norm: 1.3364 (1.3876) time: 0.6325 [2021-03-27 04:36:57 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 200/1251] eta: 0:11:27 lr: 0.000592 loss: 3.4430 (3.3551) grad_norm: 1.3308 (1.3829) time: 0.6387 [2021-03-27 04:37:03 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 210/1251] eta: 0:11:20 lr: 0.000592 loss: 3.5089 (3.3593) grad_norm: 1.2560 (1.3771) time: 0.6381 [2021-03-27 04:37:09 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 220/1251] eta: 0:11:12 lr: 0.000592 loss: 3.5155 (3.3563) grad_norm: 1.2630 (1.3753) time: 0.6281 [2021-03-27 04:37:15 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 230/1251] eta: 0:11:04 lr: 0.000592 loss: 3.4498 (3.3560) grad_norm: 1.3643 (1.3791) time: 0.6245 [2021-03-27 04:37:22 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 240/1251] eta: 0:10:56 lr: 0.000592 loss: 3.4588 (3.3621) grad_norm: 1.4098 (1.3834) time: 0.6232 [2021-03-27 04:37:28 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 250/1251] eta: 0:10:49 lr: 0.000592 loss: 3.4858 (3.3632) grad_norm: 1.3426 (1.3808) time: 0.6248 [2021-03-27 04:37:34 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 260/1251] eta: 0:10:42 lr: 0.000592 loss: 3.2707 (3.3593) grad_norm: 1.2911 (1.3786) time: 0.6278 [2021-03-27 04:37:41 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 270/1251] eta: 0:10:35 lr: 0.000592 loss: 3.2403 (3.3580) grad_norm: 1.3051 (1.3772) time: 0.6325 [2021-03-27 04:37:47 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 280/1251] eta: 0:10:27 lr: 0.000592 loss: 3.1269 (3.3510) grad_norm: 1.3625 (1.3786) time: 0.6296 [2021-03-27 04:37:53 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 290/1251] eta: 0:10:21 lr: 0.000591 loss: 3.1493 (3.3515) grad_norm: 1.3023 (1.3757) time: 0.6304 [2021-03-27 04:38:00 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 300/1251] eta: 0:10:14 lr: 0.000591 loss: 3.3596 (3.3427) grad_norm: 1.3063 (1.3742) time: 0.6320 [2021-03-27 04:38:06 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 310/1251] eta: 0:10:07 lr: 0.000591 loss: 3.3967 (3.3505) grad_norm: 1.3657 (1.3790) time: 0.6287 [2021-03-27 04:38:12 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 320/1251] eta: 0:10:00 lr: 0.000591 loss: 3.5817 (3.3613) grad_norm: 1.3779 (1.3805) time: 0.6369 [2021-03-27 04:38:19 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 330/1251] eta: 0:09:53 lr: 0.000591 loss: 3.5817 (3.3609) grad_norm: 1.3445 (1.3787) time: 0.6370 [2021-03-27 04:38:25 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 340/1251] eta: 0:09:46 lr: 0.000591 loss: 3.5058 (3.3610) grad_norm: 1.3644 (1.3834) time: 0.6283 [2021-03-27 04:38:31 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 350/1251] eta: 0:09:40 lr: 0.000591 loss: 3.5058 (3.3684) grad_norm: 1.4230 (1.3838) time: 0.6294 [2021-03-27 04:38:37 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 360/1251] eta: 0:09:33 lr: 0.000591 loss: 3.4570 (3.3678) grad_norm: 1.3595 (1.3829) time: 0.6302 [2021-03-27 04:38:44 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 370/1251] eta: 0:09:26 lr: 0.000591 loss: 3.2671 (3.3631) grad_norm: 1.3200 (1.3833) time: 0.6323 [2021-03-27 04:38:50 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 380/1251] eta: 0:09:19 lr: 0.000591 loss: 3.4674 (3.3626) grad_norm: 1.2810 (1.3829) time: 0.6324 [2021-03-27 04:38:56 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 390/1251] eta: 0:09:13 lr: 0.000591 loss: 3.5132 (3.3650) grad_norm: 1.2970 (1.3814) time: 0.6278 [2021-03-27 04:39:03 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 400/1251] eta: 0:09:06 lr: 0.000591 loss: 3.3590 (3.3568) grad_norm: 1.3357 (1.3828) time: 0.6287 [2021-03-27 04:39:09 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 410/1251] eta: 0:09:00 lr: 0.000591 loss: 3.3204 (3.3624) grad_norm: 1.3894 (1.3830) time: 0.6434 [2021-03-27 04:39:16 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 420/1251] eta: 0:08:53 lr: 0.000591 loss: 3.2560 (3.3546) grad_norm: 1.3871 (1.3830) time: 0.6483 [2021-03-27 04:39:22 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 430/1251] eta: 0:08:47 lr: 0.000591 loss: 3.0256 (3.3500) grad_norm: 1.3550 (1.3835) time: 0.6375 [2021-03-27 04:39:28 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 440/1251] eta: 0:08:40 lr: 0.000591 loss: 3.1279 (3.3511) grad_norm: 1.3248 (1.3822) time: 0.6324 [2021-03-27 04:39:34 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 450/1251] eta: 0:08:33 lr: 0.000591 loss: 3.5592 (3.3522) grad_norm: 1.3135 (1.3811) time: 0.6251 [2021-03-27 04:39:41 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 460/1251] eta: 0:08:27 lr: 0.000591 loss: 3.4369 (3.3547) grad_norm: 1.3135 (1.3809) time: 0.6304 [2021-03-27 04:39:47 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 470/1251] eta: 0:08:20 lr: 0.000591 loss: 3.4847 (3.3556) grad_norm: 1.2992 (1.3789) time: 0.6336 [2021-03-27 04:39:53 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 480/1251] eta: 0:08:14 lr: 0.000591 loss: 3.4847 (3.3505) grad_norm: 1.3256 (1.3790) time: 0.6277 [2021-03-27 04:40:00 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 490/1251] eta: 0:08:07 lr: 0.000591 loss: 3.4956 (3.3555) grad_norm: 1.2807 (1.3784) time: 0.6251 [2021-03-27 04:40:06 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 500/1251] eta: 0:08:00 lr: 0.000591 loss: 3.4956 (3.3595) grad_norm: 1.4105 (1.3807) time: 0.6272 [2021-03-27 04:40:12 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 510/1251] eta: 0:07:54 lr: 0.000591 loss: 3.4026 (3.3609) grad_norm: 1.4787 (1.3826) time: 0.6321 [2021-03-27 04:40:19 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 520/1251] eta: 0:07:47 lr: 0.000591 loss: 3.5534 (3.3641) grad_norm: 1.3351 (1.3806) time: 0.6353 [2021-03-27 04:40:25 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 530/1251] eta: 0:07:41 lr: 0.000590 loss: 3.4686 (3.3644) grad_norm: 1.3025 (1.3800) time: 0.6302 [2021-03-27 04:40:31 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 540/1251] eta: 0:07:34 lr: 0.000590 loss: 3.2620 (3.3628) grad_norm: 1.3925 (1.3817) time: 0.6229 [2021-03-27 04:40:38 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 550/1251] eta: 0:07:28 lr: 0.000590 loss: 3.4029 (3.3659) grad_norm: 1.3562 (1.3808) time: 0.6413 [2021-03-27 04:40:44 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 560/1251] eta: 0:07:22 lr: 0.000590 loss: 3.4044 (3.3672) grad_norm: 1.3313 (1.3811) time: 0.6436 [2021-03-27 04:40:50 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 570/1251] eta: 0:07:15 lr: 0.000590 loss: 3.4044 (3.3719) grad_norm: 1.3384 (1.3813) time: 0.6323 [2021-03-27 04:40:57 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 580/1251] eta: 0:07:09 lr: 0.000590 loss: 3.6673 (3.3758) grad_norm: 1.3098 (1.3800) time: 0.6348 [2021-03-27 04:41:03 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 590/1251] eta: 0:07:02 lr: 0.000590 loss: 3.5294 (3.3707) grad_norm: 1.4553 (1.3838) time: 0.6437 [2021-03-27 04:41:10 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 600/1251] eta: 0:06:56 lr: 0.000590 loss: 3.3022 (3.3684) grad_norm: 1.4234 (1.3824) time: 0.6415 [2021-03-27 04:41:16 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 610/1251] eta: 0:06:50 lr: 0.000590 loss: 3.2836 (3.3633) grad_norm: 1.2660 (1.3805) time: 0.6389 [2021-03-27 04:41:22 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 620/1251] eta: 0:06:43 lr: 0.000590 loss: 3.2224 (3.3619) grad_norm: 1.2889 (1.3808) time: 0.6429 [2021-03-27 04:41:29 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 630/1251] eta: 0:06:37 lr: 0.000590 loss: 3.2742 (3.3599) grad_norm: 1.3688 (1.3805) time: 0.6362 [2021-03-27 04:41:35 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 640/1251] eta: 0:06:30 lr: 0.000590 loss: 3.2948 (3.3608) grad_norm: 1.3688 (1.3825) time: 0.6313 [2021-03-27 04:41:41 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 650/1251] eta: 0:06:24 lr: 0.000590 loss: 3.2948 (3.3597) grad_norm: 1.3703 (1.3822) time: 0.6288 [2021-03-27 04:41:48 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 660/1251] eta: 0:06:17 lr: 0.000590 loss: 3.3518 (3.3583) grad_norm: 1.4267 (1.3830) time: 0.6264 [2021-03-27 04:41:54 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 670/1251] eta: 0:06:11 lr: 0.000590 loss: 3.5207 (3.3602) grad_norm: 1.4318 (1.3841) time: 0.6283 [2021-03-27 04:42:00 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 680/1251] eta: 0:06:04 lr: 0.000590 loss: 3.4631 (3.3572) grad_norm: 1.4344 (1.3839) time: 0.6294 [2021-03-27 04:42:07 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 690/1251] eta: 0:05:58 lr: 0.000590 loss: 3.1778 (3.3568) grad_norm: 1.4021 (1.3871) time: 0.6289 [2021-03-27 04:42:13 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 700/1251] eta: 0:05:51 lr: 0.000590 loss: 3.1155 (3.3544) grad_norm: 1.3547 (1.3871) time: 0.6332 [2021-03-27 04:42:19 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 710/1251] eta: 0:05:45 lr: 0.000590 loss: 3.3597 (3.3552) grad_norm: 1.3224 (1.3881) time: 0.6326 [2021-03-27 04:42:25 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 720/1251] eta: 0:05:38 lr: 0.000590 loss: 3.5158 (3.3584) grad_norm: 1.3465 (1.3871) time: 0.6300 [2021-03-27 04:42:32 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 730/1251] eta: 0:05:32 lr: 0.000590 loss: 3.5642 (3.3595) grad_norm: 1.3144 (1.3861) time: 0.6333 [2021-03-27 04:42:38 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 740/1251] eta: 0:05:26 lr: 0.000590 loss: 3.4738 (3.3598) grad_norm: 1.3417 (1.3869) time: 0.6409 [2021-03-27 04:42:45 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 750/1251] eta: 0:05:19 lr: 0.000590 loss: 3.5359 (3.3602) grad_norm: 1.5199 (1.3886) time: 0.6454 [2021-03-27 04:42:51 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 760/1251] eta: 0:05:13 lr: 0.000590 loss: 3.5467 (3.3611) grad_norm: 1.4035 (1.3886) time: 0.6385 [2021-03-27 04:42:57 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 770/1251] eta: 0:05:07 lr: 0.000590 loss: 3.5073 (3.3609) grad_norm: 1.3239 (1.3878) time: 0.6310 [2021-03-27 04:43:04 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 780/1251] eta: 0:05:00 lr: 0.000589 loss: 3.2307 (3.3592) grad_norm: 1.3424 (1.3881) time: 0.6314 [2021-03-27 04:43:10 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 790/1251] eta: 0:04:54 lr: 0.000589 loss: 3.4106 (3.3602) grad_norm: 1.4317 (1.3888) time: 0.6355 [2021-03-27 04:43:16 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 800/1251] eta: 0:04:47 lr: 0.000589 loss: 3.4606 (3.3590) grad_norm: 1.4200 (1.3895) time: 0.6362 [2021-03-27 04:43:23 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 810/1251] eta: 0:04:41 lr: 0.000589 loss: 3.4926 (3.3602) grad_norm: 1.3673 (1.3894) time: 0.6306 [2021-03-27 04:43:29 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 820/1251] eta: 0:04:34 lr: 0.000589 loss: 3.5910 (3.3627) grad_norm: 1.3885 (1.3901) time: 0.6284 [2021-03-27 04:43:35 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 830/1251] eta: 0:04:28 lr: 0.000589 loss: 3.6658 (3.3631) grad_norm: 1.4355 (1.3914) time: 0.6268 [2021-03-27 04:43:42 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 840/1251] eta: 0:04:22 lr: 0.000589 loss: 3.3960 (3.3629) grad_norm: 1.4183 (1.3910) time: 0.6266 [2021-03-27 04:43:48 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 850/1251] eta: 0:04:15 lr: 0.000589 loss: 3.2443 (3.3621) grad_norm: 1.3087 (1.3903) time: 0.6266 [2021-03-27 04:43:54 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 860/1251] eta: 0:04:09 lr: 0.000589 loss: 3.3226 (3.3602) grad_norm: 1.3395 (1.3903) time: 0.6264 [2021-03-27 04:44:00 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 870/1251] eta: 0:04:02 lr: 0.000589 loss: 3.4961 (3.3616) grad_norm: 1.4701 (1.3912) time: 0.6320 [2021-03-27 04:44:07 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 880/1251] eta: 0:03:56 lr: 0.000589 loss: 3.4961 (3.3605) grad_norm: 1.4841 (1.3920) time: 0.6322 [2021-03-27 04:44:13 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 890/1251] eta: 0:03:50 lr: 0.000589 loss: 3.4492 (3.3582) grad_norm: 1.4207 (1.3918) time: 0.6323 [2021-03-27 04:44:19 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 900/1251] eta: 0:03:43 lr: 0.000589 loss: 3.3666 (3.3560) grad_norm: 1.3446 (1.3917) time: 0.6335 [2021-03-27 04:44:26 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 910/1251] eta: 0:03:37 lr: 0.000589 loss: 3.4069 (3.3554) grad_norm: 1.3759 (1.3917) time: 0.6328 [2021-03-27 04:44:32 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 920/1251] eta: 0:03:30 lr: 0.000589 loss: 3.4083 (3.3551) grad_norm: 1.3688 (1.3916) time: 0.6351 [2021-03-27 04:44:39 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 930/1251] eta: 0:03:24 lr: 0.000589 loss: 3.4508 (3.3559) grad_norm: 1.3203 (1.3913) time: 0.6400 [2021-03-27 04:44:45 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 940/1251] eta: 0:03:18 lr: 0.000589 loss: 3.2478 (3.3512) grad_norm: 1.3676 (1.3928) time: 0.6363 [2021-03-27 04:44:51 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 950/1251] eta: 0:03:11 lr: 0.000589 loss: 3.2782 (3.3534) grad_norm: 1.4087 (1.3931) time: 0.6318 [2021-03-27 04:44:57 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 960/1251] eta: 0:03:05 lr: 0.000589 loss: 3.5563 (3.3525) grad_norm: 1.3417 (1.3929) time: 0.6340 [2021-03-27 04:45:04 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 970/1251] eta: 0:02:59 lr: 0.000589 loss: 3.4439 (3.3519) grad_norm: 1.3170 (1.3922) time: 0.6333 [2021-03-27 04:45:10 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 980/1251] eta: 0:02:52 lr: 0.000589 loss: 3.5617 (3.3554) grad_norm: 1.3228 (1.3922) time: 0.6365 [2021-03-27 04:45:16 swin_base_patch4_window7_224] INFO: Epoch: [133] [ 990/1251] eta: 0:02:46 lr: 0.000589 loss: 3.5450 (3.3562) grad_norm: 1.4122 (1.3935) time: 0.6305 [2021-03-27 04:45:23 swin_base_patch4_window7_224] INFO: Epoch: [133] [1000/1251] eta: 0:02:39 lr: 0.000589 loss: 3.4960 (3.3572) grad_norm: 1.4122 (1.3934) time: 0.6291 [2021-03-27 04:45:29 swin_base_patch4_window7_224] INFO: Epoch: [133] [1010/1251] eta: 0:02:33 lr: 0.000589 loss: 3.4960 (3.3560) grad_norm: 1.3671 (1.3930) time: 0.6338 [2021-03-27 04:45:35 swin_base_patch4_window7_224] INFO: Epoch: [133] [1020/1251] eta: 0:02:27 lr: 0.000588 loss: 3.3418 (3.3558) grad_norm: 1.3671 (1.3934) time: 0.6339 [2021-03-27 04:45:42 swin_base_patch4_window7_224] INFO: Epoch: [133] [1030/1251] eta: 0:02:20 lr: 0.000588 loss: 3.3418 (3.3566) grad_norm: 1.3552 (1.3940) time: 0.6338 [2021-03-27 04:45:48 swin_base_patch4_window7_224] INFO: Epoch: [133] [1040/1251] eta: 0:02:14 lr: 0.000588 loss: 3.4626 (3.3581) grad_norm: 1.3780 (1.3946) time: 0.6290 [2021-03-27 04:45:54 swin_base_patch4_window7_224] INFO: Epoch: [133] [1050/1251] eta: 0:02:07 lr: 0.000588 loss: 3.4566 (3.3560) grad_norm: 1.4083 (1.3956) time: 0.6253 [2021-03-27 04:46:01 swin_base_patch4_window7_224] INFO: Epoch: [133] [1060/1251] eta: 0:02:01 lr: 0.000588 loss: 3.3245 (3.3571) grad_norm: 1.3693 (1.3959) time: 0.6290 [2021-03-27 04:46:07 swin_base_patch4_window7_224] INFO: Epoch: [133] [1070/1251] eta: 0:01:55 lr: 0.000588 loss: 3.4065 (3.3581) grad_norm: 1.3675 (1.3956) time: 0.6339 [2021-03-27 04:46:13 swin_base_patch4_window7_224] INFO: Epoch: [133] [1080/1251] eta: 0:01:48 lr: 0.000588 loss: 3.0727 (3.3564) grad_norm: 1.2849 (1.3942) time: 0.6351 [2021-03-27 04:46:20 swin_base_patch4_window7_224] INFO: Epoch: [133] [1090/1251] eta: 0:01:42 lr: 0.000588 loss: 3.0115 (3.3544) grad_norm: 1.2558 (1.3935) time: 0.6345 [2021-03-27 04:46:26 swin_base_patch4_window7_224] INFO: Epoch: [133] [1100/1251] eta: 0:01:36 lr: 0.000588 loss: 3.1114 (3.3547) grad_norm: 1.2966 (1.3939) time: 0.6289 [2021-03-27 04:46:32 swin_base_patch4_window7_224] INFO: Epoch: [133] [1110/1251] eta: 0:01:29 lr: 0.000588 loss: 3.4158 (3.3544) grad_norm: 1.3705 (1.3933) time: 0.6319 [2021-03-27 04:46:39 swin_base_patch4_window7_224] INFO: Epoch: [133] [1120/1251] eta: 0:01:23 lr: 0.000588 loss: 3.4556 (3.3550) grad_norm: 1.4258 (1.3943) time: 0.6377 [2021-03-27 04:46:45 swin_base_patch4_window7_224] INFO: Epoch: [133] [1130/1251] eta: 0:01:17 lr: 0.000588 loss: 3.5760 (3.3552) grad_norm: 1.4502 (1.3950) time: 0.6332 [2021-03-27 04:46:51 swin_base_patch4_window7_224] INFO: Epoch: [133] [1140/1251] eta: 0:01:10 lr: 0.000588 loss: 3.5152 (3.3549) grad_norm: 1.3399 (1.3949) time: 0.6323 [2021-03-27 04:46:58 swin_base_patch4_window7_224] INFO: Epoch: [133] [1150/1251] eta: 0:01:04 lr: 0.000588 loss: 3.5595 (3.3566) grad_norm: 1.3458 (1.3946) time: 0.6372 [2021-03-27 04:47:04 swin_base_patch4_window7_224] INFO: Epoch: [133] [1160/1251] eta: 0:00:57 lr: 0.000588 loss: 3.6591 (3.3580) grad_norm: 1.3481 (1.3945) time: 0.6439 [2021-03-27 04:47:11 swin_base_patch4_window7_224] INFO: Epoch: [133] [1170/1251] eta: 0:00:51 lr: 0.000588 loss: 3.6939 (3.3604) grad_norm: 1.3883 (1.3952) time: 0.6370 [2021-03-27 04:47:17 swin_base_patch4_window7_224] INFO: Epoch: [133] [1180/1251] eta: 0:00:45 lr: 0.000588 loss: 3.5444 (3.3586) grad_norm: 1.3803 (1.3946) time: 0.6271 [2021-03-27 04:47:23 swin_base_patch4_window7_224] INFO: Epoch: [133] [1190/1251] eta: 0:00:38 lr: 0.000588 loss: 3.2573 (3.3568) grad_norm: 1.2992 (1.3941) time: 0.6309 [2021-03-27 04:47:29 swin_base_patch4_window7_224] INFO: Epoch: [133] [1200/1251] eta: 0:00:32 lr: 0.000588 loss: 3.3647 (3.3575) grad_norm: 1.3802 (1.3944) time: 0.6291 [2021-03-27 04:47:36 swin_base_patch4_window7_224] INFO: Epoch: [133] [1210/1251] eta: 0:00:26 lr: 0.000588 loss: 3.4212 (3.3580) grad_norm: 1.3938 (1.3944) time: 0.6290 [2021-03-27 04:47:42 swin_base_patch4_window7_224] INFO: Epoch: [133] [1220/1251] eta: 0:00:19 lr: 0.000588 loss: 3.2863 (3.3581) grad_norm: 1.3923 (1.3951) time: 0.6314 [2021-03-27 04:47:48 swin_base_patch4_window7_224] INFO: Epoch: [133] [1230/1251] eta: 0:00:13 lr: 0.000588 loss: 3.2771 (3.3579) grad_norm: 1.3923 (1.3947) time: 0.6275 [2021-03-27 04:47:54 swin_base_patch4_window7_224] INFO: Epoch: [133] [1240/1251] eta: 0:00:06 lr: 0.000588 loss: 3.3199 (3.3578) grad_norm: 1.3570 (1.3944) time: 0.6226 [2021-03-27 04:48:01 swin_base_patch4_window7_224] INFO: Epoch: [133] [1250/1251] eta: 0:00:00 lr: 0.000588 loss: 3.3316 (3.3565) grad_norm: 1.3816 (1.3947) time: 0.6196 [2021-03-27 04:48:09 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:20 loss: 0.8476 (0.8476) acc1: 84.3750 (84.3750) acc5: 96.8750 (96.8750) [2021-03-27 04:48:12 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:21 loss: 1.0643 (0.9869) acc1: 76.5625 (77.4148) acc5: 93.7500 (94.3182) [2021-03-27 04:48:15 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.9884 (0.9885) acc1: 73.4375 (76.6369) acc5: 95.3125 (94.6429) [2021-03-27 04:48:17 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9883 (0.9651) acc1: 75.0000 (77.4698) acc5: 95.3125 (94.4556) [2021-03-27 04:48:19 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9499 (0.9637) acc1: 78.1250 (77.3628) acc5: 93.7500 (94.5503) [2021-03-27 04:48:20 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9499 (0.9475) acc1: 79.6875 (78.0480) acc5: 93.7500 (94.4640) [2021-03-27 04:48:26 swin_base_patch4_window7_224] INFO: * Acc@1 78.442 Acc@5 94.508 loss 0.931 [2021-03-27 04:48:26 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.4% [2021-03-27 04:48:26 swin_base_patch4_window7_224] INFO: Max accuracy: 78.44% [2021-03-27 04:48:31 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 0/1251] eta: 1:29:21 lr: 0.000588 loss: 3.1657 (3.1657) grad_norm: 1.6835 (1.6835) time: 4.2855 [2021-03-27 04:48:37 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 10/1251] eta: 0:20:14 lr: 0.000588 loss: 3.4009 (3.3878) grad_norm: 1.4156 (1.4392) time: 0.9789 [2021-03-27 04:48:43 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 20/1251] eta: 0:16:42 lr: 0.000587 loss: 3.3154 (3.3481) grad_norm: 1.3263 (1.3536) time: 0.6411 [2021-03-27 04:48:50 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 30/1251] eta: 0:15:26 lr: 0.000587 loss: 3.1863 (3.3024) grad_norm: 1.3263 (1.3882) time: 0.6374 [2021-03-27 04:48:56 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 40/1251] eta: 0:14:39 lr: 0.000587 loss: 3.2529 (3.3181) grad_norm: 1.4380 (1.3917) time: 0.6340 [2021-03-27 04:49:02 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 50/1251] eta: 0:14:11 lr: 0.000587 loss: 3.2529 (3.3224) grad_norm: 1.3590 (1.3939) time: 0.6313 [2021-03-27 04:49:09 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 60/1251] eta: 0:13:47 lr: 0.000587 loss: 3.2612 (3.3063) grad_norm: 1.4415 (1.4060) time: 0.6308 [2021-03-27 04:49:15 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 70/1251] eta: 0:13:29 lr: 0.000587 loss: 3.5631 (3.3174) grad_norm: 1.3111 (1.3872) time: 0.6267 [2021-03-27 04:49:21 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 80/1251] eta: 0:13:15 lr: 0.000587 loss: 3.4955 (3.3282) grad_norm: 1.3094 (1.3921) time: 0.6323 [2021-03-27 04:49:28 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 90/1251] eta: 0:13:04 lr: 0.000587 loss: 3.4955 (3.3132) grad_norm: 1.3842 (1.3913) time: 0.6417 [2021-03-27 04:49:34 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 100/1251] eta: 0:12:54 lr: 0.000587 loss: 3.2580 (3.2836) grad_norm: 1.3552 (1.3878) time: 0.6454 [2021-03-27 04:49:41 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 110/1251] eta: 0:12:43 lr: 0.000587 loss: 3.2265 (3.2899) grad_norm: 1.4156 (1.4005) time: 0.6376 [2021-03-27 04:49:47 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 120/1251] eta: 0:12:32 lr: 0.000587 loss: 3.5378 (3.3063) grad_norm: 1.4172 (1.4109) time: 0.6278 [2021-03-27 04:49:53 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 130/1251] eta: 0:12:23 lr: 0.000587 loss: 3.4902 (3.3028) grad_norm: 1.3842 (1.4079) time: 0.6284 [2021-03-27 04:49:59 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 140/1251] eta: 0:12:13 lr: 0.000587 loss: 3.3547 (3.3045) grad_norm: 1.3842 (1.4104) time: 0.6316 [2021-03-27 04:50:06 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 150/1251] eta: 0:12:05 lr: 0.000587 loss: 3.0850 (3.2928) grad_norm: 1.3977 (1.4130) time: 0.6328 [2021-03-27 04:50:12 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 160/1251] eta: 0:11:57 lr: 0.000587 loss: 3.3593 (3.2873) grad_norm: 1.4091 (1.4167) time: 0.6369 [2021-03-27 04:50:19 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 170/1251] eta: 0:11:49 lr: 0.000587 loss: 3.1508 (3.2713) grad_norm: 1.4706 (1.4199) time: 0.6351 [2021-03-27 04:50:25 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 180/1251] eta: 0:11:41 lr: 0.000587 loss: 2.9501 (3.2633) grad_norm: 1.4060 (1.4201) time: 0.6348 [2021-03-27 04:50:31 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 190/1251] eta: 0:11:33 lr: 0.000587 loss: 3.4429 (3.2758) grad_norm: 1.4550 (1.4299) time: 0.6361 [2021-03-27 04:50:38 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 200/1251] eta: 0:11:25 lr: 0.000587 loss: 3.4763 (3.2739) grad_norm: 1.4880 (1.4327) time: 0.6305 [2021-03-27 04:50:44 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 210/1251] eta: 0:11:18 lr: 0.000587 loss: 3.3849 (3.2839) grad_norm: 1.4880 (1.4404) time: 0.6320 [2021-03-27 04:50:50 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 220/1251] eta: 0:11:11 lr: 0.000587 loss: 3.3979 (3.2838) grad_norm: 1.4054 (1.4357) time: 0.6372 [2021-03-27 04:50:57 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 230/1251] eta: 0:11:04 lr: 0.000587 loss: 3.4358 (3.2799) grad_norm: 1.3530 (1.4388) time: 0.6375 [2021-03-27 04:51:03 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 240/1251] eta: 0:10:56 lr: 0.000587 loss: 3.2604 (3.2740) grad_norm: 1.4128 (1.4436) time: 0.6326 [2021-03-27 04:51:09 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 250/1251] eta: 0:10:49 lr: 0.000587 loss: 3.2951 (3.2791) grad_norm: 1.3749 (1.4389) time: 0.6304 [2021-03-27 04:51:16 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 260/1251] eta: 0:10:42 lr: 0.000586 loss: 3.6721 (3.2921) grad_norm: 1.3325 (1.4390) time: 0.6321 [2021-03-27 04:51:22 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 270/1251] eta: 0:10:35 lr: 0.000586 loss: 3.6505 (3.2978) grad_norm: 1.3321 (1.4381) time: 0.6381 [2021-03-27 04:51:28 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 280/1251] eta: 0:10:29 lr: 0.000586 loss: 3.5761 (3.3108) grad_norm: 1.3081 (1.4339) time: 0.6407 [2021-03-27 04:51:35 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 290/1251] eta: 0:10:21 lr: 0.000586 loss: 3.6610 (3.3232) grad_norm: 1.3066 (1.4327) time: 0.6330 [2021-03-27 04:51:41 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 300/1251] eta: 0:10:14 lr: 0.000586 loss: 3.6425 (3.3231) grad_norm: 1.3920 (1.4330) time: 0.6289 [2021-03-27 04:51:47 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 310/1251] eta: 0:10:08 lr: 0.000586 loss: 3.3991 (3.3158) grad_norm: 1.4065 (1.4336) time: 0.6310 [2021-03-27 04:51:54 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 320/1251] eta: 0:10:01 lr: 0.000586 loss: 3.0699 (3.3167) grad_norm: 1.3662 (1.4292) time: 0.6317 [2021-03-27 04:52:00 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 330/1251] eta: 0:09:54 lr: 0.000586 loss: 2.9567 (3.3064) grad_norm: 1.3723 (1.4316) time: 0.6266 [2021-03-27 04:52:06 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 340/1251] eta: 0:09:47 lr: 0.000586 loss: 3.1624 (3.3084) grad_norm: 1.4442 (1.4298) time: 0.6274 [2021-03-27 04:52:12 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 350/1251] eta: 0:09:40 lr: 0.000586 loss: 3.4927 (3.3061) grad_norm: 1.3608 (1.4287) time: 0.6301 [2021-03-27 04:52:19 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 360/1251] eta: 0:09:33 lr: 0.000586 loss: 3.2907 (3.3067) grad_norm: 1.4122 (1.4289) time: 0.6313 [2021-03-27 04:52:25 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 370/1251] eta: 0:09:26 lr: 0.000586 loss: 3.4924 (3.3121) grad_norm: 1.3947 (1.4284) time: 0.6319 [2021-03-27 04:52:31 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 380/1251] eta: 0:09:20 lr: 0.000586 loss: 3.5772 (3.3150) grad_norm: 1.3670 (1.4284) time: 0.6290 [2021-03-27 04:52:38 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 390/1251] eta: 0:09:13 lr: 0.000586 loss: 3.6185 (3.3203) grad_norm: 1.4243 (1.4292) time: 0.6295 [2021-03-27 04:52:44 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 400/1251] eta: 0:09:06 lr: 0.000586 loss: 3.6880 (3.3328) grad_norm: 1.4243 (1.4332) time: 0.6344 [2021-03-27 04:52:50 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 410/1251] eta: 0:09:00 lr: 0.000586 loss: 3.6183 (3.3348) grad_norm: 1.5275 (1.4350) time: 0.6321 [2021-03-27 04:52:57 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 420/1251] eta: 0:08:53 lr: 0.000586 loss: 3.2845 (3.3296) grad_norm: 1.4340 (1.4330) time: 0.6297 [2021-03-27 04:53:03 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 430/1251] eta: 0:08:46 lr: 0.000586 loss: 3.2462 (3.3319) grad_norm: 1.3948 (1.4334) time: 0.6318 [2021-03-27 04:53:09 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 440/1251] eta: 0:08:40 lr: 0.000586 loss: 3.2212 (3.3236) grad_norm: 1.4939 (1.4355) time: 0.6330 [2021-03-27 04:53:16 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 450/1251] eta: 0:08:33 lr: 0.000586 loss: 2.7967 (3.3142) grad_norm: 1.4648 (1.4361) time: 0.6358 [2021-03-27 04:53:22 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 460/1251] eta: 0:08:27 lr: 0.000586 loss: 3.2997 (3.3158) grad_norm: 1.3995 (1.4359) time: 0.6318 [2021-03-27 04:53:28 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 470/1251] eta: 0:08:20 lr: 0.000586 loss: 3.3795 (3.3202) grad_norm: 1.3932 (1.4384) time: 0.6289 [2021-03-27 04:53:35 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 480/1251] eta: 0:08:14 lr: 0.000586 loss: 3.3784 (3.3200) grad_norm: 1.3342 (1.4349) time: 0.6305 [2021-03-27 04:53:41 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 490/1251] eta: 0:08:07 lr: 0.000586 loss: 3.2316 (3.3197) grad_norm: 1.3492 (1.4357) time: 0.6340 [2021-03-27 04:53:47 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 500/1251] eta: 0:08:00 lr: 0.000586 loss: 3.4581 (3.3226) grad_norm: 1.3713 (1.4336) time: 0.6311 [2021-03-27 04:53:53 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 510/1251] eta: 0:07:54 lr: 0.000585 loss: 3.6509 (3.3262) grad_norm: 1.3585 (1.4326) time: 0.6258 [2021-03-27 04:54:00 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 520/1251] eta: 0:07:47 lr: 0.000585 loss: 3.4077 (3.3257) grad_norm: 1.4391 (1.4336) time: 0.6241 [2021-03-27 04:54:06 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 530/1251] eta: 0:07:41 lr: 0.000585 loss: 3.2874 (3.3279) grad_norm: 1.4213 (1.4323) time: 0.6355 [2021-03-27 04:54:13 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 540/1251] eta: 0:07:34 lr: 0.000585 loss: 3.5295 (3.3286) grad_norm: 1.3525 (1.4330) time: 0.6445 [2021-03-27 04:54:19 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 550/1251] eta: 0:07:28 lr: 0.000585 loss: 3.5548 (3.3328) grad_norm: 1.3834 (1.4327) time: 0.6486 [2021-03-27 04:54:26 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 560/1251] eta: 0:07:22 lr: 0.000585 loss: 3.3819 (3.3299) grad_norm: 1.3921 (1.4318) time: 0.6486 [2021-03-27 04:54:32 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 570/1251] eta: 0:07:15 lr: 0.000585 loss: 3.4548 (3.3338) grad_norm: 1.4003 (1.4323) time: 0.6399 [2021-03-27 04:54:38 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 580/1251] eta: 0:07:09 lr: 0.000585 loss: 3.5304 (3.3358) grad_norm: 1.4310 (1.4323) time: 0.6372 [2021-03-27 04:54:45 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 590/1251] eta: 0:07:02 lr: 0.000585 loss: 3.4464 (3.3361) grad_norm: 1.4157 (1.4316) time: 0.6312 [2021-03-27 04:54:51 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 600/1251] eta: 0:06:56 lr: 0.000585 loss: 3.2957 (3.3326) grad_norm: 1.3640 (1.4310) time: 0.6340 [2021-03-27 04:54:57 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 610/1251] eta: 0:06:50 lr: 0.000585 loss: 3.3593 (3.3343) grad_norm: 1.3533 (1.4294) time: 0.6326 [2021-03-27 04:55:04 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 620/1251] eta: 0:06:43 lr: 0.000585 loss: 3.7360 (3.3407) grad_norm: 1.3705 (1.4295) time: 0.6328 [2021-03-27 04:55:10 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 630/1251] eta: 0:06:37 lr: 0.000585 loss: 3.6616 (3.3437) grad_norm: 1.3705 (1.4283) time: 0.6354 [2021-03-27 04:55:16 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 640/1251] eta: 0:06:30 lr: 0.000585 loss: 3.6257 (3.3490) grad_norm: 1.3552 (1.4282) time: 0.6337 [2021-03-27 04:55:23 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 650/1251] eta: 0:06:24 lr: 0.000585 loss: 3.7286 (3.3534) grad_norm: 1.4284 (1.4289) time: 0.6394 [2021-03-27 04:55:29 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 660/1251] eta: 0:06:17 lr: 0.000585 loss: 3.5508 (3.3520) grad_norm: 1.4423 (1.4298) time: 0.6395 [2021-03-27 04:55:35 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 670/1251] eta: 0:06:11 lr: 0.000585 loss: 3.4094 (3.3527) grad_norm: 1.3796 (1.4304) time: 0.6336 [2021-03-27 04:55:42 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 680/1251] eta: 0:06:04 lr: 0.000585 loss: 3.4802 (3.3515) grad_norm: 1.5521 (1.4335) time: 0.6267 [2021-03-27 04:55:48 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 690/1251] eta: 0:05:58 lr: 0.000585 loss: 3.4545 (3.3499) grad_norm: 1.4887 (1.4340) time: 0.6270 [2021-03-27 04:55:54 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 700/1251] eta: 0:05:52 lr: 0.000585 loss: 2.8924 (3.3427) grad_norm: 1.5113 (1.4375) time: 0.6310 [2021-03-27 04:56:01 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 710/1251] eta: 0:05:45 lr: 0.000585 loss: 3.1052 (3.3404) grad_norm: 1.5909 (1.4376) time: 0.6289 [2021-03-27 04:56:07 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 720/1251] eta: 0:05:39 lr: 0.000585 loss: 3.2296 (3.3426) grad_norm: 1.4013 (1.4400) time: 0.6290 [2021-03-27 04:56:13 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 730/1251] eta: 0:05:32 lr: 0.000585 loss: 3.4163 (3.3423) grad_norm: 1.3971 (1.4390) time: 0.6358 [2021-03-27 04:56:20 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 740/1251] eta: 0:05:26 lr: 0.000585 loss: 3.4163 (3.3429) grad_norm: 1.3394 (1.4382) time: 0.6403 [2021-03-27 04:56:26 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 750/1251] eta: 0:05:19 lr: 0.000584 loss: 3.4177 (3.3443) grad_norm: 1.4215 (1.4386) time: 0.6396 [2021-03-27 04:56:32 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 760/1251] eta: 0:05:13 lr: 0.000584 loss: 3.3953 (3.3438) grad_norm: 1.2719 (1.4366) time: 0.6378 [2021-03-27 04:56:39 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 770/1251] eta: 0:05:07 lr: 0.000584 loss: 3.4995 (3.3451) grad_norm: 1.2767 (1.4364) time: 0.6312 [2021-03-27 04:56:45 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 780/1251] eta: 0:05:00 lr: 0.000584 loss: 3.5311 (3.3480) grad_norm: 1.3919 (1.4356) time: 0.6290 [2021-03-27 04:56:51 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 790/1251] eta: 0:04:54 lr: 0.000584 loss: 3.3139 (3.3470) grad_norm: 1.3513 (1.4356) time: 0.6300 [2021-03-27 04:56:58 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 800/1251] eta: 0:04:47 lr: 0.000584 loss: 3.2442 (3.3466) grad_norm: 1.4490 (1.4359) time: 0.6316 [2021-03-27 04:57:04 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 810/1251] eta: 0:04:41 lr: 0.000584 loss: 3.4825 (3.3492) grad_norm: 1.4497 (1.4366) time: 0.6314 [2021-03-27 04:57:10 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 820/1251] eta: 0:04:34 lr: 0.000584 loss: 3.4825 (3.3478) grad_norm: 1.4872 (1.4368) time: 0.6272 [2021-03-27 04:57:17 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 830/1251] eta: 0:04:28 lr: 0.000584 loss: 3.4577 (3.3499) grad_norm: 1.4872 (1.4376) time: 0.6307 [2021-03-27 04:57:23 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 840/1251] eta: 0:04:22 lr: 0.000584 loss: 3.3645 (3.3488) grad_norm: 1.4792 (1.4382) time: 0.6397 [2021-03-27 04:57:29 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 850/1251] eta: 0:04:15 lr: 0.000584 loss: 3.2892 (3.3474) grad_norm: 1.4628 (1.4382) time: 0.6388 [2021-03-27 04:57:36 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 860/1251] eta: 0:04:09 lr: 0.000584 loss: 3.2639 (3.3461) grad_norm: 1.4574 (1.4387) time: 0.6301 [2021-03-27 04:57:42 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 870/1251] eta: 0:04:02 lr: 0.000584 loss: 3.3243 (3.3466) grad_norm: 1.3903 (1.4380) time: 0.6295 [2021-03-27 04:57:48 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 880/1251] eta: 0:03:56 lr: 0.000584 loss: 3.4537 (3.3467) grad_norm: 1.3363 (1.4368) time: 0.6311 [2021-03-27 04:57:54 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 890/1251] eta: 0:03:50 lr: 0.000584 loss: 3.3601 (3.3457) grad_norm: 1.3274 (1.4361) time: 0.6268 [2021-03-27 04:58:01 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 900/1251] eta: 0:03:43 lr: 0.000584 loss: 3.3601 (3.3482) grad_norm: 1.2995 (1.4348) time: 0.6247 [2021-03-27 04:58:07 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 910/1251] eta: 0:03:37 lr: 0.000584 loss: 3.6429 (3.3494) grad_norm: 1.2683 (1.4336) time: 0.6250 [2021-03-27 04:58:13 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 920/1251] eta: 0:03:30 lr: 0.000584 loss: 3.3246 (3.3490) grad_norm: 1.3146 (1.4339) time: 0.6241 [2021-03-27 04:58:20 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 930/1251] eta: 0:03:24 lr: 0.000584 loss: 3.3246 (3.3495) grad_norm: 1.3949 (1.4351) time: 0.6291 [2021-03-27 04:58:26 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 940/1251] eta: 0:03:18 lr: 0.000584 loss: 3.4582 (3.3489) grad_norm: 1.3788 (1.4358) time: 0.6307 [2021-03-27 04:58:32 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 950/1251] eta: 0:03:11 lr: 0.000584 loss: 3.3648 (3.3482) grad_norm: 1.3909 (1.4356) time: 0.6297 [2021-03-27 04:58:38 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 960/1251] eta: 0:03:05 lr: 0.000584 loss: 3.4515 (3.3480) grad_norm: 1.3917 (1.4347) time: 0.6302 [2021-03-27 04:58:45 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 970/1251] eta: 0:02:58 lr: 0.000584 loss: 3.5154 (3.3504) grad_norm: 1.3709 (1.4338) time: 0.6255 [2021-03-27 04:58:51 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 980/1251] eta: 0:02:52 lr: 0.000584 loss: 3.4788 (3.3497) grad_norm: 1.3709 (1.4345) time: 0.6242 [2021-03-27 04:58:57 swin_base_patch4_window7_224] INFO: Epoch: [134] [ 990/1251] eta: 0:02:46 lr: 0.000584 loss: 3.0528 (3.3461) grad_norm: 1.3899 (1.4348) time: 0.6271 [2021-03-27 04:59:04 swin_base_patch4_window7_224] INFO: Epoch: [134] [1000/1251] eta: 0:02:39 lr: 0.000583 loss: 3.1704 (3.3466) grad_norm: 1.3636 (1.4338) time: 0.6318 [2021-03-27 04:59:10 swin_base_patch4_window7_224] INFO: Epoch: [134] [1010/1251] eta: 0:02:33 lr: 0.000583 loss: 3.5697 (3.3499) grad_norm: 1.3377 (1.4331) time: 0.6309 [2021-03-27 04:59:16 swin_base_patch4_window7_224] INFO: Epoch: [134] [1020/1251] eta: 0:02:27 lr: 0.000583 loss: 3.5017 (3.3495) grad_norm: 1.3680 (1.4329) time: 0.6339 [2021-03-27 04:59:23 swin_base_patch4_window7_224] INFO: Epoch: [134] [1030/1251] eta: 0:02:20 lr: 0.000583 loss: 3.3061 (3.3472) grad_norm: 1.3922 (1.4324) time: 0.6365 [2021-03-27 04:59:29 swin_base_patch4_window7_224] INFO: Epoch: [134] [1040/1251] eta: 0:02:14 lr: 0.000583 loss: 3.3830 (3.3487) grad_norm: 1.3455 (1.4316) time: 0.6347 [2021-03-27 04:59:35 swin_base_patch4_window7_224] INFO: Epoch: [134] [1050/1251] eta: 0:02:07 lr: 0.000583 loss: 3.4232 (3.3488) grad_norm: 1.2799 (1.4303) time: 0.6421 [2021-03-27 04:59:42 swin_base_patch4_window7_224] INFO: Epoch: [134] [1060/1251] eta: 0:02:01 lr: 0.000583 loss: 3.4924 (3.3493) grad_norm: 1.2874 (1.4303) time: 0.6409 [2021-03-27 04:59:48 swin_base_patch4_window7_224] INFO: Epoch: [134] [1070/1251] eta: 0:01:55 lr: 0.000583 loss: 3.5010 (3.3490) grad_norm: 1.4261 (1.4303) time: 0.6354 [2021-03-27 04:59:54 swin_base_patch4_window7_224] INFO: Epoch: [134] [1080/1251] eta: 0:01:48 lr: 0.000583 loss: 3.4037 (3.3473) grad_norm: 1.3608 (1.4298) time: 0.6300 [2021-03-27 05:00:01 swin_base_patch4_window7_224] INFO: Epoch: [134] [1090/1251] eta: 0:01:42 lr: 0.000583 loss: 3.3488 (3.3468) grad_norm: 1.3770 (1.4296) time: 0.6279 [2021-03-27 05:00:07 swin_base_patch4_window7_224] INFO: Epoch: [134] [1100/1251] eta: 0:01:36 lr: 0.000583 loss: 3.3710 (3.3482) grad_norm: 1.3969 (1.4293) time: 0.6307 [2021-03-27 05:00:13 swin_base_patch4_window7_224] INFO: Epoch: [134] [1110/1251] eta: 0:01:29 lr: 0.000583 loss: 3.6488 (3.3499) grad_norm: 1.4438 (1.4292) time: 0.6322 [2021-03-27 05:00:20 swin_base_patch4_window7_224] INFO: Epoch: [134] [1120/1251] eta: 0:01:23 lr: 0.000583 loss: 3.4197 (3.3488) grad_norm: 1.3691 (1.4291) time: 0.6314 [2021-03-27 05:00:26 swin_base_patch4_window7_224] INFO: Epoch: [134] [1130/1251] eta: 0:01:16 lr: 0.000583 loss: 3.3733 (3.3499) grad_norm: 1.3832 (1.4295) time: 0.6255 [2021-03-27 05:00:32 swin_base_patch4_window7_224] INFO: Epoch: [134] [1140/1251] eta: 0:01:10 lr: 0.000583 loss: 3.6334 (3.3514) grad_norm: 1.3712 (1.4289) time: 0.6265 [2021-03-27 05:00:38 swin_base_patch4_window7_224] INFO: Epoch: [134] [1150/1251] eta: 0:01:04 lr: 0.000583 loss: 3.6334 (3.3533) grad_norm: 1.4043 (1.4295) time: 0.6276 [2021-03-27 05:00:45 swin_base_patch4_window7_224] INFO: Epoch: [134] [1160/1251] eta: 0:00:57 lr: 0.000583 loss: 3.4093 (3.3515) grad_norm: 1.3815 (1.4286) time: 0.6291 [2021-03-27 05:00:51 swin_base_patch4_window7_224] INFO: Epoch: [134] [1170/1251] eta: 0:00:51 lr: 0.000583 loss: 3.3432 (3.3511) grad_norm: 1.3870 (1.4287) time: 0.6281 [2021-03-27 05:00:57 swin_base_patch4_window7_224] INFO: Epoch: [134] [1180/1251] eta: 0:00:45 lr: 0.000583 loss: 3.5256 (3.3521) grad_norm: 1.3977 (1.4282) time: 0.6220 [2021-03-27 05:01:03 swin_base_patch4_window7_224] INFO: Epoch: [134] [1190/1251] eta: 0:00:38 lr: 0.000583 loss: 3.3226 (3.3497) grad_norm: 1.3368 (1.4279) time: 0.6265 [2021-03-27 05:01:10 swin_base_patch4_window7_224] INFO: Epoch: [134] [1200/1251] eta: 0:00:32 lr: 0.000583 loss: 3.0404 (3.3498) grad_norm: 1.3884 (1.4281) time: 0.6343 [2021-03-27 05:01:16 swin_base_patch4_window7_224] INFO: Epoch: [134] [1210/1251] eta: 0:00:26 lr: 0.000583 loss: 3.5083 (3.3507) grad_norm: 1.4226 (1.4276) time: 0.6322 [2021-03-27 05:01:22 swin_base_patch4_window7_224] INFO: Epoch: [134] [1220/1251] eta: 0:00:19 lr: 0.000583 loss: 3.4650 (3.3513) grad_norm: 1.4226 (1.4284) time: 0.6282 [2021-03-27 05:01:29 swin_base_patch4_window7_224] INFO: Epoch: [134] [1230/1251] eta: 0:00:13 lr: 0.000583 loss: 3.5188 (3.3531) grad_norm: 1.3564 (1.4283) time: 0.6291 [2021-03-27 05:01:35 swin_base_patch4_window7_224] INFO: Epoch: [134] [1240/1251] eta: 0:00:06 lr: 0.000582 loss: 3.4903 (3.3509) grad_norm: 1.3612 (1.4281) time: 0.6307 [2021-03-27 05:01:41 swin_base_patch4_window7_224] INFO: Epoch: [134] [1250/1251] eta: 0:00:00 lr: 0.000582 loss: 3.1507 (3.3509) grad_norm: 1.3412 (1.4275) time: 0.6305 [2021-03-27 05:01:50 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:59 loss: 0.8389 (0.8389) acc1: 79.6875 (79.6875) acc5: 93.7500 (93.7500) [2021-03-27 05:01:53 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9956 (0.9605) acc1: 79.6875 (77.8409) acc5: 93.7500 (94.4602) [2021-03-27 05:01:55 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9685 (0.9213) acc1: 76.5625 (78.4226) acc5: 93.7500 (94.7917) [2021-03-27 05:01:57 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9685 (0.9430) acc1: 76.5625 (77.5202) acc5: 93.7500 (94.5565) [2021-03-27 05:01:59 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0137 (0.9519) acc1: 75.0000 (77.1723) acc5: 93.7500 (94.2835) [2021-03-27 05:02:00 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0013 (0.9551) acc1: 75.0000 (77.0560) acc5: 93.7500 (94.2720) [2021-03-27 05:02:07 swin_base_patch4_window7_224] INFO: * Acc@1 78.120 Acc@5 94.362 loss 0.936 [2021-03-27 05:02:07 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.1% [2021-03-27 05:02:07 swin_base_patch4_window7_224] INFO: Max accuracy: 78.44% [2021-03-27 05:02:12 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 0/1251] eta: 1:27:44 lr: 0.000582 loss: 3.8939 (3.8939) grad_norm: 1.2697 (1.2697) time: 4.2086 [2021-03-27 05:02:18 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 10/1251] eta: 0:19:58 lr: 0.000582 loss: 3.6518 (3.3542) grad_norm: 1.3368 (1.3496) time: 0.9661 [2021-03-27 05:02:25 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 20/1251] eta: 0:16:42 lr: 0.000582 loss: 3.6227 (3.4344) grad_norm: 1.3640 (1.4280) time: 0.6446 [2021-03-27 05:02:31 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 30/1251] eta: 0:15:22 lr: 0.000582 loss: 3.5027 (3.3542) grad_norm: 1.3881 (1.4270) time: 0.6394 [2021-03-27 05:02:37 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 40/1251] eta: 0:14:41 lr: 0.000582 loss: 3.3241 (3.3472) grad_norm: 1.3811 (1.4179) time: 0.6371 [2021-03-27 05:02:44 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 50/1251] eta: 0:14:14 lr: 0.000582 loss: 3.3402 (3.3545) grad_norm: 1.3716 (1.4197) time: 0.6437 [2021-03-27 05:02:50 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 60/1251] eta: 0:13:52 lr: 0.000582 loss: 3.5010 (3.3897) grad_norm: 1.3276 (1.4188) time: 0.6396 [2021-03-27 05:02:57 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 70/1251] eta: 0:13:36 lr: 0.000582 loss: 3.3439 (3.3482) grad_norm: 1.3435 (1.4111) time: 0.6401 [2021-03-27 05:03:03 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 80/1251] eta: 0:13:22 lr: 0.000582 loss: 3.3439 (3.3649) grad_norm: 1.3479 (1.4052) time: 0.6423 [2021-03-27 05:03:09 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 90/1251] eta: 0:13:07 lr: 0.000582 loss: 3.6895 (3.3972) grad_norm: 1.2783 (1.4001) time: 0.6310 [2021-03-27 05:03:15 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 100/1251] eta: 0:12:55 lr: 0.000582 loss: 3.5227 (3.3913) grad_norm: 1.2783 (1.3942) time: 0.6269 [2021-03-27 05:03:22 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 110/1251] eta: 0:12:44 lr: 0.000582 loss: 3.2797 (3.3852) grad_norm: 1.3421 (1.3983) time: 0.6311 [2021-03-27 05:03:28 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 120/1251] eta: 0:12:32 lr: 0.000582 loss: 3.2797 (3.3835) grad_norm: 1.3596 (1.4019) time: 0.6271 [2021-03-27 05:03:34 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 130/1251] eta: 0:12:23 lr: 0.000582 loss: 3.4783 (3.3936) grad_norm: 1.3764 (1.4016) time: 0.6274 [2021-03-27 05:03:41 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 140/1251] eta: 0:12:14 lr: 0.000582 loss: 3.4312 (3.3925) grad_norm: 1.3764 (1.3993) time: 0.6317 [2021-03-27 05:03:47 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 150/1251] eta: 0:12:05 lr: 0.000582 loss: 3.4682 (3.3944) grad_norm: 1.3534 (1.3987) time: 0.6306 [2021-03-27 05:03:53 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 160/1251] eta: 0:11:57 lr: 0.000582 loss: 3.6566 (3.4027) grad_norm: 1.3248 (1.3952) time: 0.6314 [2021-03-27 05:04:00 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 170/1251] eta: 0:11:48 lr: 0.000582 loss: 3.4767 (3.4007) grad_norm: 1.3615 (1.3989) time: 0.6291 [2021-03-27 05:04:06 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 180/1251] eta: 0:11:41 lr: 0.000582 loss: 3.5888 (3.4176) grad_norm: 1.3866 (1.3952) time: 0.6351 [2021-03-27 05:04:12 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 190/1251] eta: 0:11:33 lr: 0.000582 loss: 3.6464 (3.4238) grad_norm: 1.3546 (1.3966) time: 0.6364 [2021-03-27 05:04:19 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 200/1251] eta: 0:11:25 lr: 0.000582 loss: 3.5633 (3.4276) grad_norm: 1.3546 (1.3959) time: 0.6319 [2021-03-27 05:04:25 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 210/1251] eta: 0:11:18 lr: 0.000582 loss: 3.5131 (3.4202) grad_norm: 1.3387 (1.3959) time: 0.6383 [2021-03-27 05:04:31 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 220/1251] eta: 0:11:10 lr: 0.000582 loss: 3.4296 (3.4189) grad_norm: 1.2813 (1.3956) time: 0.6321 [2021-03-27 05:04:38 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 230/1251] eta: 0:11:03 lr: 0.000581 loss: 3.4296 (3.4150) grad_norm: 1.3382 (1.3954) time: 0.6262 [2021-03-27 05:04:44 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 240/1251] eta: 0:10:56 lr: 0.000581 loss: 3.5442 (3.4170) grad_norm: 1.4528 (1.4028) time: 0.6291 [2021-03-27 05:04:50 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 250/1251] eta: 0:10:48 lr: 0.000581 loss: 3.4227 (3.4168) grad_norm: 1.3846 (1.3983) time: 0.6312 [2021-03-27 05:04:57 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 260/1251] eta: 0:10:41 lr: 0.000581 loss: 3.4266 (3.4200) grad_norm: 1.2847 (1.3979) time: 0.6335 [2021-03-27 05:05:03 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 270/1251] eta: 0:10:34 lr: 0.000581 loss: 3.4266 (3.4127) grad_norm: 1.3429 (1.3982) time: 0.6321 [2021-03-27 05:05:09 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 280/1251] eta: 0:10:27 lr: 0.000581 loss: 3.4270 (3.4167) grad_norm: 1.3487 (1.3972) time: 0.6304 [2021-03-27 05:05:15 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 290/1251] eta: 0:10:20 lr: 0.000581 loss: 3.4317 (3.4134) grad_norm: 1.3911 (1.3984) time: 0.6296 [2021-03-27 05:05:22 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 300/1251] eta: 0:10:13 lr: 0.000581 loss: 3.3680 (3.4029) grad_norm: 1.4152 (1.4033) time: 0.6288 [2021-03-27 05:05:28 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 310/1251] eta: 0:10:06 lr: 0.000581 loss: 3.3808 (3.4079) grad_norm: 1.3507 (1.4017) time: 0.6309 [2021-03-27 05:05:34 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 320/1251] eta: 0:09:59 lr: 0.000581 loss: 3.6231 (3.4118) grad_norm: 1.2817 (1.3988) time: 0.6278 [2021-03-27 05:05:41 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 330/1251] eta: 0:09:53 lr: 0.000581 loss: 3.4884 (3.4132) grad_norm: 1.3020 (1.3995) time: 0.6279 [2021-03-27 05:05:47 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 340/1251] eta: 0:09:46 lr: 0.000581 loss: 3.1969 (3.4005) grad_norm: 1.3313 (1.3988) time: 0.6311 [2021-03-27 05:05:53 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 350/1251] eta: 0:09:39 lr: 0.000581 loss: 3.0786 (3.3963) grad_norm: 1.3864 (1.3995) time: 0.6285 [2021-03-27 05:05:59 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 360/1251] eta: 0:09:32 lr: 0.000581 loss: 3.1500 (3.3917) grad_norm: 1.3559 (1.3975) time: 0.6294 [2021-03-27 05:06:06 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 370/1251] eta: 0:09:25 lr: 0.000581 loss: 3.4363 (3.3927) grad_norm: 1.3210 (1.3963) time: 0.6290 [2021-03-27 05:06:12 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 380/1251] eta: 0:09:19 lr: 0.000581 loss: 3.4363 (3.3933) grad_norm: 1.3233 (1.3980) time: 0.6272 [2021-03-27 05:06:18 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 390/1251] eta: 0:09:12 lr: 0.000581 loss: 3.4445 (3.3931) grad_norm: 1.3708 (1.3966) time: 0.6284 [2021-03-27 05:06:25 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 400/1251] eta: 0:09:05 lr: 0.000581 loss: 3.4670 (3.3922) grad_norm: 1.3697 (1.3978) time: 0.6366 [2021-03-27 05:06:31 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 410/1251] eta: 0:08:59 lr: 0.000581 loss: 3.4351 (3.3919) grad_norm: 1.3898 (1.3982) time: 0.6359 [2021-03-27 05:06:37 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 420/1251] eta: 0:08:52 lr: 0.000581 loss: 3.3364 (3.3893) grad_norm: 1.3878 (1.3977) time: 0.6322 [2021-03-27 05:06:44 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 430/1251] eta: 0:08:46 lr: 0.000581 loss: 3.2931 (3.3904) grad_norm: 1.3184 (1.3962) time: 0.6344 [2021-03-27 05:06:50 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 440/1251] eta: 0:08:39 lr: 0.000581 loss: 3.5714 (3.3949) grad_norm: 1.3191 (1.3979) time: 0.6315 [2021-03-27 05:06:56 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 450/1251] eta: 0:08:33 lr: 0.000581 loss: 3.5714 (3.3958) grad_norm: 1.3896 (1.3997) time: 0.6357 [2021-03-27 05:07:03 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 460/1251] eta: 0:08:26 lr: 0.000581 loss: 3.4810 (3.3936) grad_norm: 1.3536 (1.3989) time: 0.6386 [2021-03-27 05:07:09 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 470/1251] eta: 0:08:20 lr: 0.000581 loss: 3.4783 (3.3950) grad_norm: 1.3333 (1.3987) time: 0.6321 [2021-03-27 05:07:15 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 480/1251] eta: 0:08:13 lr: 0.000580 loss: 3.4911 (3.3997) grad_norm: 1.3871 (1.3997) time: 0.6288 [2021-03-27 05:07:22 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 490/1251] eta: 0:08:06 lr: 0.000580 loss: 3.4864 (3.4024) grad_norm: 1.3857 (1.3990) time: 0.6285 [2021-03-27 05:07:28 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 500/1251] eta: 0:08:00 lr: 0.000580 loss: 3.3272 (3.3976) grad_norm: 1.3831 (1.3996) time: 0.6273 [2021-03-27 05:07:34 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 510/1251] eta: 0:07:53 lr: 0.000580 loss: 3.2757 (3.3981) grad_norm: 1.3852 (1.3993) time: 0.6308 [2021-03-27 05:07:41 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 520/1251] eta: 0:07:47 lr: 0.000580 loss: 3.5486 (3.4042) grad_norm: 1.3448 (1.3980) time: 0.6355 [2021-03-27 05:07:47 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 530/1251] eta: 0:07:40 lr: 0.000580 loss: 3.5486 (3.3999) grad_norm: 1.3508 (1.3974) time: 0.6350 [2021-03-27 05:07:53 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 540/1251] eta: 0:07:34 lr: 0.000580 loss: 3.5882 (3.4032) grad_norm: 1.3467 (1.3968) time: 0.6306 [2021-03-27 05:08:00 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 550/1251] eta: 0:07:27 lr: 0.000580 loss: 3.6690 (3.4067) grad_norm: 1.3424 (1.3958) time: 0.6307 [2021-03-27 05:08:06 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 560/1251] eta: 0:07:21 lr: 0.000580 loss: 3.5178 (3.4047) grad_norm: 1.3699 (1.3963) time: 0.6352 [2021-03-27 05:08:12 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 570/1251] eta: 0:07:15 lr: 0.000580 loss: 3.4930 (3.4054) grad_norm: 1.4061 (1.3970) time: 0.6426 [2021-03-27 05:08:19 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 580/1251] eta: 0:07:08 lr: 0.000580 loss: 3.4462 (3.4045) grad_norm: 1.3261 (1.3971) time: 0.6383 [2021-03-27 05:08:25 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 590/1251] eta: 0:07:02 lr: 0.000580 loss: 3.4420 (3.4043) grad_norm: 1.3243 (1.3969) time: 0.6318 [2021-03-27 05:08:31 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 600/1251] eta: 0:06:55 lr: 0.000580 loss: 3.4201 (3.4047) grad_norm: 1.3557 (1.3961) time: 0.6291 [2021-03-27 05:08:38 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 610/1251] eta: 0:06:49 lr: 0.000580 loss: 3.4511 (3.4066) grad_norm: 1.3112 (1.3954) time: 0.6259 [2021-03-27 05:08:44 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 620/1251] eta: 0:06:42 lr: 0.000580 loss: 3.4876 (3.4063) grad_norm: 1.2920 (1.3953) time: 0.6301 [2021-03-27 05:08:50 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 630/1251] eta: 0:06:36 lr: 0.000580 loss: 3.3353 (3.4019) grad_norm: 1.3970 (1.3954) time: 0.6276 [2021-03-27 05:08:57 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 640/1251] eta: 0:06:29 lr: 0.000580 loss: 3.3430 (3.4002) grad_norm: 1.3114 (1.3948) time: 0.6306 [2021-03-27 05:09:03 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 650/1251] eta: 0:06:23 lr: 0.000580 loss: 3.3430 (3.3987) grad_norm: 1.3695 (1.3957) time: 0.6386 [2021-03-27 05:09:09 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 660/1251] eta: 0:06:17 lr: 0.000580 loss: 3.3483 (3.3985) grad_norm: 1.4014 (1.3963) time: 0.6327 [2021-03-27 05:09:16 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 670/1251] eta: 0:06:10 lr: 0.000580 loss: 3.3938 (3.3987) grad_norm: 1.3859 (1.3973) time: 0.6270 [2021-03-27 05:09:22 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 680/1251] eta: 0:06:04 lr: 0.000580 loss: 3.3938 (3.3984) grad_norm: 1.3669 (1.3964) time: 0.6302 [2021-03-27 05:09:28 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 690/1251] eta: 0:05:57 lr: 0.000580 loss: 3.4581 (3.3998) grad_norm: 1.3160 (1.3958) time: 0.6315 [2021-03-27 05:09:35 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 700/1251] eta: 0:05:51 lr: 0.000580 loss: 3.3280 (3.3960) grad_norm: 1.3145 (1.3957) time: 0.6333 [2021-03-27 05:09:41 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 710/1251] eta: 0:05:44 lr: 0.000580 loss: 3.1222 (3.3935) grad_norm: 1.3539 (1.3967) time: 0.6351 [2021-03-27 05:09:47 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 720/1251] eta: 0:05:38 lr: 0.000579 loss: 3.3713 (3.3964) grad_norm: 1.3563 (1.3967) time: 0.6338 [2021-03-27 05:09:54 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 730/1251] eta: 0:05:32 lr: 0.000579 loss: 3.3766 (3.3958) grad_norm: 1.2966 (1.3956) time: 0.6353 [2021-03-27 05:10:00 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 740/1251] eta: 0:05:25 lr: 0.000579 loss: 3.1742 (3.3929) grad_norm: 1.3228 (1.3952) time: 0.6392 [2021-03-27 05:10:06 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 750/1251] eta: 0:05:19 lr: 0.000579 loss: 3.4371 (3.3955) grad_norm: 1.3389 (1.3950) time: 0.6422 [2021-03-27 05:10:13 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 760/1251] eta: 0:05:13 lr: 0.000579 loss: 3.5095 (3.3962) grad_norm: 1.3016 (1.3939) time: 0.6440 [2021-03-27 05:10:19 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 770/1251] eta: 0:05:06 lr: 0.000579 loss: 3.5095 (3.3968) grad_norm: 1.2718 (1.3931) time: 0.6350 [2021-03-27 05:10:25 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 780/1251] eta: 0:05:00 lr: 0.000579 loss: 3.4596 (3.3959) grad_norm: 1.3208 (1.3933) time: 0.6259 [2021-03-27 05:10:32 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 790/1251] eta: 0:04:53 lr: 0.000579 loss: 3.3048 (3.3947) grad_norm: 1.3694 (1.3942) time: 0.6317 [2021-03-27 05:10:38 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 800/1251] eta: 0:04:47 lr: 0.000579 loss: 3.5166 (3.3974) grad_norm: 1.3785 (1.3951) time: 0.6374 [2021-03-27 05:10:44 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 810/1251] eta: 0:04:41 lr: 0.000579 loss: 3.6798 (3.4017) grad_norm: 1.3708 (1.3944) time: 0.6360 [2021-03-27 05:10:51 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 820/1251] eta: 0:04:34 lr: 0.000579 loss: 3.3842 (3.3978) grad_norm: 1.3251 (1.3948) time: 0.6306 [2021-03-27 05:10:57 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 830/1251] eta: 0:04:28 lr: 0.000579 loss: 3.2000 (3.3947) grad_norm: 1.3251 (1.3942) time: 0.6308 [2021-03-27 05:11:03 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 840/1251] eta: 0:04:21 lr: 0.000579 loss: 3.2013 (3.3918) grad_norm: 1.4307 (1.3966) time: 0.6330 [2021-03-27 05:11:10 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 850/1251] eta: 0:04:15 lr: 0.000579 loss: 3.4095 (3.3941) grad_norm: 1.4408 (1.3968) time: 0.6323 [2021-03-27 05:11:16 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 860/1251] eta: 0:04:09 lr: 0.000579 loss: 3.4341 (3.3921) grad_norm: 1.3280 (1.3959) time: 0.6279 [2021-03-27 05:11:22 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 870/1251] eta: 0:04:02 lr: 0.000579 loss: 3.4341 (3.3924) grad_norm: 1.3338 (1.3958) time: 0.6248 [2021-03-27 05:11:29 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 880/1251] eta: 0:03:56 lr: 0.000579 loss: 3.3302 (3.3924) grad_norm: 1.3514 (1.3962) time: 0.6277 [2021-03-27 05:11:35 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 890/1251] eta: 0:03:49 lr: 0.000579 loss: 3.4007 (3.3929) grad_norm: 1.3250 (1.3952) time: 0.6317 [2021-03-27 05:11:41 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 900/1251] eta: 0:03:43 lr: 0.000579 loss: 3.4103 (3.3907) grad_norm: 1.3061 (1.3956) time: 0.6369 [2021-03-27 05:11:48 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 910/1251] eta: 0:03:37 lr: 0.000579 loss: 3.5006 (3.3911) grad_norm: 1.3758 (1.3956) time: 0.6344 [2021-03-27 05:11:54 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 920/1251] eta: 0:03:30 lr: 0.000579 loss: 3.4664 (3.3904) grad_norm: 1.3870 (1.3955) time: 0.6294 [2021-03-27 05:12:00 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 930/1251] eta: 0:03:24 lr: 0.000579 loss: 3.1045 (3.3874) grad_norm: 1.3822 (1.3963) time: 0.6342 [2021-03-27 05:12:07 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 940/1251] eta: 0:03:17 lr: 0.000579 loss: 3.2668 (3.3880) grad_norm: 1.4204 (1.3968) time: 0.6362 [2021-03-27 05:12:13 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 950/1251] eta: 0:03:11 lr: 0.000579 loss: 3.4775 (3.3883) grad_norm: 1.4204 (1.3967) time: 0.6285 [2021-03-27 05:12:19 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 960/1251] eta: 0:03:05 lr: 0.000579 loss: 3.4775 (3.3874) grad_norm: 1.3571 (1.3972) time: 0.6321 [2021-03-27 05:12:25 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 970/1251] eta: 0:02:58 lr: 0.000578 loss: 3.2954 (3.3837) grad_norm: 1.4821 (1.3985) time: 0.6329 [2021-03-27 05:12:32 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 980/1251] eta: 0:02:52 lr: 0.000578 loss: 3.3033 (3.3857) grad_norm: 1.4400 (1.3981) time: 0.6262 [2021-03-27 05:12:38 swin_base_patch4_window7_224] INFO: Epoch: [135] [ 990/1251] eta: 0:02:46 lr: 0.000578 loss: 3.6796 (3.3870) grad_norm: 1.3925 (1.3991) time: 0.6269 [2021-03-27 05:12:44 swin_base_patch4_window7_224] INFO: Epoch: [135] [1000/1251] eta: 0:02:39 lr: 0.000578 loss: 3.5706 (3.3864) grad_norm: 1.4298 (1.4002) time: 0.6257 [2021-03-27 05:12:51 swin_base_patch4_window7_224] INFO: Epoch: [135] [1010/1251] eta: 0:02:33 lr: 0.000578 loss: 3.2225 (3.3840) grad_norm: 1.3896 (1.4006) time: 0.6299 [2021-03-27 05:12:57 swin_base_patch4_window7_224] INFO: Epoch: [135] [1020/1251] eta: 0:02:26 lr: 0.000578 loss: 3.3325 (3.3848) grad_norm: 1.3707 (1.4004) time: 0.6326 [2021-03-27 05:13:03 swin_base_patch4_window7_224] INFO: Epoch: [135] [1030/1251] eta: 0:02:20 lr: 0.000578 loss: 3.5077 (3.3821) grad_norm: 1.3707 (1.4009) time: 0.6409 [2021-03-27 05:13:10 swin_base_patch4_window7_224] INFO: Epoch: [135] [1040/1251] eta: 0:02:14 lr: 0.000578 loss: 3.3073 (3.3810) grad_norm: 1.3784 (1.4010) time: 0.6433 [2021-03-27 05:13:16 swin_base_patch4_window7_224] INFO: Epoch: [135] [1050/1251] eta: 0:02:07 lr: 0.000578 loss: 3.4197 (3.3816) grad_norm: 1.3738 (1.4007) time: 0.6338 [2021-03-27 05:13:22 swin_base_patch4_window7_224] INFO: Epoch: [135] [1060/1251] eta: 0:02:01 lr: 0.000578 loss: 3.5855 (3.3827) grad_norm: 1.3618 (1.4004) time: 0.6275 [2021-03-27 05:13:29 swin_base_patch4_window7_224] INFO: Epoch: [135] [1070/1251] eta: 0:01:55 lr: 0.000578 loss: 3.6235 (3.3845) grad_norm: 1.3618 (1.4013) time: 0.6247 [2021-03-27 05:13:35 swin_base_patch4_window7_224] INFO: Epoch: [135] [1080/1251] eta: 0:01:48 lr: 0.000578 loss: 3.4592 (3.3821) grad_norm: 1.3645 (1.4010) time: 0.6267 [2021-03-27 05:13:41 swin_base_patch4_window7_224] INFO: Epoch: [135] [1090/1251] eta: 0:01:42 lr: 0.000578 loss: 3.3321 (3.3796) grad_norm: 1.3675 (1.4020) time: 0.6267 [2021-03-27 05:13:47 swin_base_patch4_window7_224] INFO: Epoch: [135] [1100/1251] eta: 0:01:35 lr: 0.000578 loss: 3.4358 (3.3821) grad_norm: 1.3226 (1.4008) time: 0.6295 [2021-03-27 05:13:54 swin_base_patch4_window7_224] INFO: Epoch: [135] [1110/1251] eta: 0:01:29 lr: 0.000578 loss: 3.4710 (3.3795) grad_norm: 1.2623 (1.4007) time: 0.6302 [2021-03-27 05:14:00 swin_base_patch4_window7_224] INFO: Epoch: [135] [1120/1251] eta: 0:01:23 lr: 0.000578 loss: 3.2605 (3.3784) grad_norm: 1.3875 (1.4006) time: 0.6301 [2021-03-27 05:14:06 swin_base_patch4_window7_224] INFO: Epoch: [135] [1130/1251] eta: 0:01:16 lr: 0.000578 loss: 3.4121 (3.3774) grad_norm: 1.3940 (1.4006) time: 0.6315 [2021-03-27 05:14:13 swin_base_patch4_window7_224] INFO: Epoch: [135] [1140/1251] eta: 0:01:10 lr: 0.000578 loss: 3.3646 (3.3779) grad_norm: 1.4057 (1.4006) time: 0.6274 [2021-03-27 05:14:19 swin_base_patch4_window7_224] INFO: Epoch: [135] [1150/1251] eta: 0:01:04 lr: 0.000578 loss: 3.4570 (3.3789) grad_norm: 1.3371 (1.4000) time: 0.6356 [2021-03-27 05:14:25 swin_base_patch4_window7_224] INFO: Epoch: [135] [1160/1251] eta: 0:00:57 lr: 0.000578 loss: 3.6243 (3.3801) grad_norm: 1.2765 (1.3997) time: 0.6357 [2021-03-27 05:14:32 swin_base_patch4_window7_224] INFO: Epoch: [135] [1170/1251] eta: 0:00:51 lr: 0.000578 loss: 3.4787 (3.3793) grad_norm: 1.2905 (1.3992) time: 0.6282 [2021-03-27 05:14:38 swin_base_patch4_window7_224] INFO: Epoch: [135] [1180/1251] eta: 0:00:45 lr: 0.000578 loss: 3.4403 (3.3792) grad_norm: 1.2997 (1.3988) time: 0.6268 [2021-03-27 05:14:44 swin_base_patch4_window7_224] INFO: Epoch: [135] [1190/1251] eta: 0:00:38 lr: 0.000578 loss: 3.5479 (3.3789) grad_norm: 1.3273 (1.3989) time: 0.6255 [2021-03-27 05:14:50 swin_base_patch4_window7_224] INFO: Epoch: [135] [1200/1251] eta: 0:00:32 lr: 0.000578 loss: 3.4819 (3.3784) grad_norm: 1.4272 (1.3996) time: 0.6294 [2021-03-27 05:14:57 swin_base_patch4_window7_224] INFO: Epoch: [135] [1210/1251] eta: 0:00:26 lr: 0.000577 loss: 3.4350 (3.3764) grad_norm: 1.3478 (1.3987) time: 0.6257 [2021-03-27 05:15:03 swin_base_patch4_window7_224] INFO: Epoch: [135] [1220/1251] eta: 0:00:19 lr: 0.000577 loss: 3.4655 (3.3768) grad_norm: 1.2604 (1.3984) time: 0.6257 [2021-03-27 05:15:09 swin_base_patch4_window7_224] INFO: Epoch: [135] [1230/1251] eta: 0:00:13 lr: 0.000577 loss: 3.4853 (3.3777) grad_norm: 1.3772 (1.3985) time: 0.6337 [2021-03-27 05:15:16 swin_base_patch4_window7_224] INFO: Epoch: [135] [1240/1251] eta: 0:00:06 lr: 0.000577 loss: 3.5358 (3.3786) grad_norm: 1.2968 (1.3977) time: 0.6334 [2021-03-27 05:15:22 swin_base_patch4_window7_224] INFO: Epoch: [135] [1250/1251] eta: 0:00:00 lr: 0.000577 loss: 3.6644 (3.3803) grad_norm: 1.2865 (1.3977) time: 0.6236 [2021-03-27 05:16:32 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.7753 (0.7753) acc1: 81.2500 (81.2500) acc5: 93.7500 (93.7500) [2021-03-27 05:16:33 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.9687 (0.9705) acc1: 76.5625 (76.9886) acc5: 93.7500 (94.6023) [2021-03-27 05:16:35 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9172 (0.9463) acc1: 76.5625 (77.8274) acc5: 95.3125 (94.4940) [2021-03-27 05:16:36 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.9172 (0.9552) acc1: 79.6875 (77.2177) acc5: 95.3125 (94.3548) [2021-03-27 05:16:37 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9606 (0.9418) acc1: 78.1250 (77.2104) acc5: 95.3125 (94.6646) [2021-03-27 05:16:39 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9303 (0.9290) acc1: 78.1250 (77.4720) acc5: 95.3125 (94.7840) [2021-03-27 05:16:46 swin_base_patch4_window7_224] INFO: * Acc@1 78.448 Acc@5 94.536 loss 0.914 [2021-03-27 05:16:46 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.4% [2021-03-27 05:16:46 swin_base_patch4_window7_224] INFO: Max accuracy: 78.45% [2021-03-27 05:16:51 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 0/1251] eta: 1:30:33 lr: 0.000577 loss: 3.3931 (3.3931) grad_norm: 1.3694 (1.3694) time: 4.3435 [2021-03-27 05:16:57 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 10/1251] eta: 0:19:59 lr: 0.000577 loss: 3.3384 (3.2501) grad_norm: 1.3807 (1.4131) time: 0.9666 [2021-03-27 05:17:03 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 20/1251] eta: 0:16:35 lr: 0.000577 loss: 3.4404 (3.2858) grad_norm: 1.3877 (1.4095) time: 0.6320 [2021-03-27 05:17:10 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 30/1251] eta: 0:15:22 lr: 0.000577 loss: 3.5014 (3.3404) grad_norm: 1.4261 (1.4312) time: 0.6396 [2021-03-27 05:17:16 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 40/1251] eta: 0:14:39 lr: 0.000577 loss: 3.3947 (3.3594) grad_norm: 1.5397 (1.4593) time: 0.6400 [2021-03-27 05:17:22 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 50/1251] eta: 0:14:08 lr: 0.000577 loss: 3.3476 (3.3268) grad_norm: 1.4933 (1.4557) time: 0.6303 [2021-03-27 05:17:29 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 60/1251] eta: 0:13:46 lr: 0.000577 loss: 3.3125 (3.3184) grad_norm: 1.3442 (1.4363) time: 0.6262 [2021-03-27 05:17:35 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 70/1251] eta: 0:13:29 lr: 0.000577 loss: 3.4131 (3.2828) grad_norm: 1.3740 (1.4427) time: 0.6329 [2021-03-27 05:17:41 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 80/1251] eta: 0:13:14 lr: 0.000577 loss: 3.4087 (3.2824) grad_norm: 1.3710 (1.4328) time: 0.6311 [2021-03-27 05:17:48 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 90/1251] eta: 0:13:01 lr: 0.000577 loss: 3.4243 (3.2825) grad_norm: 1.3832 (1.4339) time: 0.6281 [2021-03-27 05:17:54 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 100/1251] eta: 0:12:49 lr: 0.000577 loss: 3.3929 (3.2812) grad_norm: 1.4515 (1.4296) time: 0.6283 [2021-03-27 05:18:00 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 110/1251] eta: 0:12:39 lr: 0.000577 loss: 3.3089 (3.2926) grad_norm: 1.4047 (1.4406) time: 0.6316 [2021-03-27 05:18:07 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 120/1251] eta: 0:12:30 lr: 0.000577 loss: 3.5409 (3.3253) grad_norm: 1.4420 (1.4423) time: 0.6392 [2021-03-27 05:18:13 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 130/1251] eta: 0:12:22 lr: 0.000577 loss: 3.6063 (3.3308) grad_norm: 1.3673 (1.4314) time: 0.6438 [2021-03-27 05:18:20 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 140/1251] eta: 0:12:13 lr: 0.000577 loss: 3.4425 (3.3353) grad_norm: 1.3132 (1.4250) time: 0.6423 [2021-03-27 05:18:26 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 150/1251] eta: 0:12:04 lr: 0.000577 loss: 3.5919 (3.3605) grad_norm: 1.3481 (1.4266) time: 0.6330 [2021-03-27 05:18:32 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 160/1251] eta: 0:11:56 lr: 0.000577 loss: 3.5919 (3.3585) grad_norm: 1.4712 (1.4292) time: 0.6315 [2021-03-27 05:18:39 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 170/1251] eta: 0:11:48 lr: 0.000577 loss: 3.4509 (3.3701) grad_norm: 1.4460 (1.4278) time: 0.6354 [2021-03-27 05:18:45 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 180/1251] eta: 0:11:40 lr: 0.000577 loss: 3.6796 (3.3811) grad_norm: 1.4387 (1.4373) time: 0.6352 [2021-03-27 05:18:51 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 190/1251] eta: 0:11:33 lr: 0.000577 loss: 3.6049 (3.3827) grad_norm: 1.4387 (1.4381) time: 0.6332 [2021-03-27 05:18:58 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 200/1251] eta: 0:11:25 lr: 0.000576 loss: 3.5141 (3.3851) grad_norm: 1.3814 (1.4350) time: 0.6311 [2021-03-27 05:19:04 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 210/1251] eta: 0:11:17 lr: 0.000576 loss: 3.3676 (3.3859) grad_norm: 1.3438 (1.4367) time: 0.6279 [2021-03-27 05:19:10 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 220/1251] eta: 0:11:10 lr: 0.000576 loss: 3.4322 (3.3858) grad_norm: 1.4123 (1.4393) time: 0.6314 [2021-03-27 05:19:16 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 230/1251] eta: 0:11:02 lr: 0.000576 loss: 3.4730 (3.3850) grad_norm: 1.3675 (1.4368) time: 0.6310 [2021-03-27 05:19:23 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 240/1251] eta: 0:10:55 lr: 0.000576 loss: 3.4247 (3.3809) grad_norm: 1.3276 (1.4321) time: 0.6280 [2021-03-27 05:19:29 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 250/1251] eta: 0:10:48 lr: 0.000576 loss: 3.5347 (3.3836) grad_norm: 1.2882 (1.4271) time: 0.6270 [2021-03-27 05:19:35 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 260/1251] eta: 0:10:41 lr: 0.000576 loss: 3.5813 (3.3816) grad_norm: 1.3796 (1.4286) time: 0.6278 [2021-03-27 05:19:41 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 270/1251] eta: 0:10:33 lr: 0.000576 loss: 3.4586 (3.3870) grad_norm: 1.4008 (inf) time: 0.6247 [2021-03-27 05:19:48 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 280/1251] eta: 0:10:26 lr: 0.000576 loss: 3.5081 (3.3828) grad_norm: 1.3296 (inf) time: 0.6265 [2021-03-27 05:19:54 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 290/1251] eta: 0:10:19 lr: 0.000576 loss: 3.5081 (3.3861) grad_norm: 1.2910 (inf) time: 0.6329 [2021-03-27 05:20:01 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 300/1251] eta: 0:10:13 lr: 0.000576 loss: 3.6218 (3.3857) grad_norm: 1.4297 (inf) time: 0.6345 [2021-03-27 05:20:07 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 310/1251] eta: 0:10:06 lr: 0.000576 loss: 3.5269 (3.3892) grad_norm: 1.4173 (inf) time: 0.6385 [2021-03-27 05:20:13 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 320/1251] eta: 0:09:59 lr: 0.000576 loss: 3.5797 (3.3907) grad_norm: 1.4173 (inf) time: 0.6316 [2021-03-27 05:20:19 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 330/1251] eta: 0:09:52 lr: 0.000576 loss: 3.3698 (3.3835) grad_norm: 1.3535 (inf) time: 0.6280 [2021-03-27 05:20:26 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 340/1251] eta: 0:09:46 lr: 0.000576 loss: 3.3698 (3.3890) grad_norm: 1.2328 (inf) time: 0.6338 [2021-03-27 05:20:32 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 350/1251] eta: 0:09:39 lr: 0.000576 loss: 3.4188 (3.3841) grad_norm: 1.2715 (inf) time: 0.6370 [2021-03-27 05:20:39 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 360/1251] eta: 0:09:32 lr: 0.000576 loss: 3.3295 (3.3878) grad_norm: 1.3398 (inf) time: 0.6353 [2021-03-27 05:20:45 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 370/1251] eta: 0:09:25 lr: 0.000576 loss: 3.4164 (3.3868) grad_norm: 1.3398 (inf) time: 0.6307 [2021-03-27 05:20:51 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 380/1251] eta: 0:09:19 lr: 0.000576 loss: 3.3011 (3.3853) grad_norm: 1.3686 (inf) time: 0.6296 [2021-03-27 05:20:57 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 390/1251] eta: 0:09:12 lr: 0.000576 loss: 3.3754 (3.3855) grad_norm: 1.3686 (inf) time: 0.6307 [2021-03-27 05:21:04 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 400/1251] eta: 0:09:05 lr: 0.000576 loss: 3.3207 (3.3774) grad_norm: 1.3169 (inf) time: 0.6292 [2021-03-27 05:21:10 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 410/1251] eta: 0:08:59 lr: 0.000576 loss: 3.1178 (3.3733) grad_norm: 1.3169 (inf) time: 0.6281 [2021-03-27 05:21:16 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 420/1251] eta: 0:08:52 lr: 0.000576 loss: 3.3819 (3.3795) grad_norm: 1.3152 (inf) time: 0.6287 [2021-03-27 05:21:23 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 430/1251] eta: 0:08:46 lr: 0.000576 loss: 3.4899 (3.3787) grad_norm: 1.3800 (inf) time: 0.6331 [2021-03-27 05:21:29 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 440/1251] eta: 0:08:39 lr: 0.000576 loss: 3.4568 (3.3768) grad_norm: 1.3736 (inf) time: 0.6330 [2021-03-27 05:21:35 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 450/1251] eta: 0:08:32 lr: 0.000575 loss: 3.4654 (3.3760) grad_norm: 1.3524 (inf) time: 0.6294 [2021-03-27 05:21:42 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 460/1251] eta: 0:08:26 lr: 0.000575 loss: 3.5724 (3.3750) grad_norm: 1.3524 (inf) time: 0.6346 [2021-03-27 05:21:48 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 470/1251] eta: 0:08:19 lr: 0.000575 loss: 3.6796 (3.3819) grad_norm: 1.4112 (inf) time: 0.6357 [2021-03-27 05:21:54 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 480/1251] eta: 0:08:13 lr: 0.000575 loss: 3.4273 (3.3745) grad_norm: 1.4712 (inf) time: 0.6372 [2021-03-27 05:22:01 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 490/1251] eta: 0:08:06 lr: 0.000575 loss: 3.2639 (3.3716) grad_norm: 1.3555 (inf) time: 0.6331 [2021-03-27 05:22:07 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 500/1251] eta: 0:08:00 lr: 0.000575 loss: 3.4945 (3.3749) grad_norm: 1.4415 (inf) time: 0.6269 [2021-03-27 05:22:13 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 510/1251] eta: 0:07:53 lr: 0.000575 loss: 3.6186 (3.3774) grad_norm: 1.4415 (inf) time: 0.6287 [2021-03-27 05:22:19 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 520/1251] eta: 0:07:47 lr: 0.000575 loss: 3.3980 (3.3756) grad_norm: 1.3797 (inf) time: 0.6256 [2021-03-27 05:22:26 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 530/1251] eta: 0:07:40 lr: 0.000575 loss: 3.3076 (3.3772) grad_norm: 1.3854 (inf) time: 0.6258 [2021-03-27 05:22:32 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 540/1251] eta: 0:07:34 lr: 0.000575 loss: 3.5451 (3.3792) grad_norm: 1.4193 (inf) time: 0.6361 [2021-03-27 05:22:39 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 550/1251] eta: 0:07:28 lr: 0.000575 loss: 3.6905 (3.3823) grad_norm: 1.4052 (inf) time: 0.6539 [2021-03-27 05:22:45 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 560/1251] eta: 0:07:21 lr: 0.000575 loss: 3.5086 (3.3824) grad_norm: 1.4115 (inf) time: 0.6510 [2021-03-27 05:22:52 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 570/1251] eta: 0:07:15 lr: 0.000575 loss: 3.3772 (3.3805) grad_norm: 1.4692 (inf) time: 0.6374 [2021-03-27 05:22:58 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 580/1251] eta: 0:07:08 lr: 0.000575 loss: 3.3444 (3.3787) grad_norm: 1.3766 (inf) time: 0.6307 [2021-03-27 05:23:04 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 590/1251] eta: 0:07:02 lr: 0.000575 loss: 3.3841 (3.3784) grad_norm: 1.3915 (inf) time: 0.6324 [2021-03-27 05:23:11 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 600/1251] eta: 0:06:56 lr: 0.000575 loss: 3.3841 (3.3793) grad_norm: 1.4470 (inf) time: 0.6381 [2021-03-27 05:23:17 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 610/1251] eta: 0:06:49 lr: 0.000575 loss: 3.4212 (3.3794) grad_norm: 1.3488 (inf) time: 0.6375 [2021-03-27 05:23:23 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 620/1251] eta: 0:06:43 lr: 0.000575 loss: 3.2900 (3.3750) grad_norm: 1.3350 (inf) time: 0.6325 [2021-03-27 05:23:30 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 630/1251] eta: 0:06:36 lr: 0.000575 loss: 3.5228 (3.3784) grad_norm: 1.3504 (inf) time: 0.6297 [2021-03-27 05:23:36 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 640/1251] eta: 0:06:30 lr: 0.000575 loss: 3.4599 (3.3794) grad_norm: 1.4307 (inf) time: 0.6285 [2021-03-27 05:23:42 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 650/1251] eta: 0:06:23 lr: 0.000575 loss: 3.4371 (3.3806) grad_norm: 1.4307 (inf) time: 0.6254 [2021-03-27 05:23:48 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 660/1251] eta: 0:06:17 lr: 0.000575 loss: 3.4146 (3.3805) grad_norm: 1.4347 (inf) time: 0.6265 [2021-03-27 05:23:55 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 670/1251] eta: 0:06:10 lr: 0.000575 loss: 3.2260 (3.3781) grad_norm: 1.4518 (inf) time: 0.6305 [2021-03-27 05:24:01 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 680/1251] eta: 0:06:04 lr: 0.000575 loss: 3.3549 (3.3786) grad_norm: 1.3408 (inf) time: 0.6321 [2021-03-27 05:24:07 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 690/1251] eta: 0:05:57 lr: 0.000574 loss: 3.4833 (3.3799) grad_norm: 1.3692 (inf) time: 0.6308 [2021-03-27 05:24:14 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 700/1251] eta: 0:05:51 lr: 0.000574 loss: 3.4996 (3.3799) grad_norm: 1.3474 (inf) time: 0.6302 [2021-03-27 05:24:20 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 710/1251] eta: 0:05:45 lr: 0.000574 loss: 3.2821 (3.3773) grad_norm: 1.3161 (inf) time: 0.6314 [2021-03-27 05:24:26 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 720/1251] eta: 0:05:38 lr: 0.000574 loss: 3.5178 (3.3796) grad_norm: 1.3743 (inf) time: 0.6326 [2021-03-27 05:24:33 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 730/1251] eta: 0:05:32 lr: 0.000574 loss: 3.5540 (3.3790) grad_norm: 1.3779 (inf) time: 0.6331 [2021-03-27 05:24:39 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 740/1251] eta: 0:05:25 lr: 0.000574 loss: 3.5289 (3.3810) grad_norm: 1.3300 (inf) time: 0.6365 [2021-03-27 05:24:45 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 750/1251] eta: 0:05:19 lr: 0.000574 loss: 3.4202 (3.3792) grad_norm: 1.3375 (inf) time: 0.6318 [2021-03-27 05:24:52 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 760/1251] eta: 0:05:13 lr: 0.000574 loss: 3.4092 (3.3832) grad_norm: 1.3928 (inf) time: 0.6355 [2021-03-27 05:24:58 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 770/1251] eta: 0:05:06 lr: 0.000574 loss: 3.4881 (3.3823) grad_norm: 1.4195 (inf) time: 0.6363 [2021-03-27 05:25:04 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 780/1251] eta: 0:05:00 lr: 0.000574 loss: 3.4446 (3.3822) grad_norm: 1.4324 (inf) time: 0.6297 [2021-03-27 05:25:11 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 790/1251] eta: 0:04:53 lr: 0.000574 loss: 3.5021 (3.3836) grad_norm: 1.3472 (inf) time: 0.6330 [2021-03-27 05:25:17 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 800/1251] eta: 0:04:47 lr: 0.000574 loss: 3.3232 (3.3822) grad_norm: 1.3185 (inf) time: 0.6353 [2021-03-27 05:25:23 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 810/1251] eta: 0:04:40 lr: 0.000574 loss: 3.2775 (3.3815) grad_norm: 1.3287 (inf) time: 0.6292 [2021-03-27 05:25:30 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 820/1251] eta: 0:04:34 lr: 0.000574 loss: 3.2775 (3.3816) grad_norm: 1.3259 (inf) time: 0.6264 [2021-03-27 05:25:36 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 830/1251] eta: 0:04:28 lr: 0.000574 loss: 3.3319 (3.3826) grad_norm: 1.2597 (inf) time: 0.6328 [2021-03-27 05:25:42 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 840/1251] eta: 0:04:21 lr: 0.000574 loss: 3.4283 (3.3841) grad_norm: 1.2931 (inf) time: 0.6304 [2021-03-27 05:25:48 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 850/1251] eta: 0:04:15 lr: 0.000574 loss: 3.4928 (3.3834) grad_norm: 1.3664 (inf) time: 0.6278 [2021-03-27 05:25:55 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 860/1251] eta: 0:04:08 lr: 0.000574 loss: 3.5195 (3.3825) grad_norm: 1.3981 (inf) time: 0.6302 [2021-03-27 05:26:01 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 870/1251] eta: 0:04:02 lr: 0.000574 loss: 3.4106 (3.3816) grad_norm: 1.3989 (inf) time: 0.6321 [2021-03-27 05:26:07 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 880/1251] eta: 0:03:56 lr: 0.000574 loss: 3.3952 (3.3807) grad_norm: 1.3142 (inf) time: 0.6331 [2021-03-27 05:26:14 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 890/1251] eta: 0:03:49 lr: 0.000574 loss: 3.3952 (3.3805) grad_norm: 1.2410 (inf) time: 0.6307 [2021-03-27 05:26:20 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 900/1251] eta: 0:03:43 lr: 0.000574 loss: 3.3342 (3.3792) grad_norm: 1.3069 (inf) time: 0.6263 [2021-03-27 05:26:26 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 910/1251] eta: 0:03:37 lr: 0.000574 loss: 3.2012 (3.3755) grad_norm: 1.4218 (inf) time: 0.6318 [2021-03-27 05:26:33 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 920/1251] eta: 0:03:30 lr: 0.000574 loss: 3.4187 (3.3751) grad_norm: 1.3148 (inf) time: 0.6327 [2021-03-27 05:26:39 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 930/1251] eta: 0:03:24 lr: 0.000573 loss: 3.4094 (3.3744) grad_norm: 1.3880 (inf) time: 0.6286 [2021-03-27 05:26:45 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 940/1251] eta: 0:03:17 lr: 0.000573 loss: 3.2468 (3.3707) grad_norm: 1.4456 (inf) time: 0.6248 [2021-03-27 05:26:52 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 950/1251] eta: 0:03:11 lr: 0.000573 loss: 3.1975 (3.3695) grad_norm: 1.4415 (inf) time: 0.6292 [2021-03-27 05:26:58 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 960/1251] eta: 0:03:05 lr: 0.000573 loss: 3.2294 (3.3694) grad_norm: 1.4551 (inf) time: 0.6364 [2021-03-27 05:27:04 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 970/1251] eta: 0:02:58 lr: 0.000573 loss: 3.5747 (3.3721) grad_norm: 1.3898 (inf) time: 0.6278 [2021-03-27 05:27:10 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 980/1251] eta: 0:02:52 lr: 0.000573 loss: 3.3561 (3.3697) grad_norm: 1.3634 (inf) time: 0.6230 [2021-03-27 05:27:17 swin_base_patch4_window7_224] INFO: Epoch: [136] [ 990/1251] eta: 0:02:45 lr: 0.000573 loss: 2.9773 (3.3670) grad_norm: 1.3473 (inf) time: 0.6256 [2021-03-27 05:27:23 swin_base_patch4_window7_224] INFO: Epoch: [136] [1000/1251] eta: 0:02:39 lr: 0.000573 loss: 3.3271 (3.3680) grad_norm: 1.4456 (inf) time: 0.6251 [2021-03-27 05:27:29 swin_base_patch4_window7_224] INFO: Epoch: [136] [1010/1251] eta: 0:02:33 lr: 0.000573 loss: 3.3585 (3.3657) grad_norm: 1.4456 (inf) time: 0.6310 [2021-03-27 05:27:36 swin_base_patch4_window7_224] INFO: Epoch: [136] [1020/1251] eta: 0:02:26 lr: 0.000573 loss: 3.3407 (3.3666) grad_norm: 1.4554 (inf) time: 0.6405 [2021-03-27 05:27:42 swin_base_patch4_window7_224] INFO: Epoch: [136] [1030/1251] eta: 0:02:20 lr: 0.000573 loss: 3.5897 (3.3675) grad_norm: 1.4490 (inf) time: 0.6446 [2021-03-27 05:27:48 swin_base_patch4_window7_224] INFO: Epoch: [136] [1040/1251] eta: 0:02:14 lr: 0.000573 loss: 3.6638 (3.3695) grad_norm: 1.5958 (inf) time: 0.6381 [2021-03-27 05:27:55 swin_base_patch4_window7_224] INFO: Epoch: [136] [1050/1251] eta: 0:02:07 lr: 0.000573 loss: 3.4403 (3.3678) grad_norm: 1.5769 (inf) time: 0.6251 [2021-03-27 05:28:01 swin_base_patch4_window7_224] INFO: Epoch: [136] [1060/1251] eta: 0:02:01 lr: 0.000573 loss: 3.3439 (3.3692) grad_norm: 1.4315 (inf) time: 0.6284 [2021-03-27 05:28:07 swin_base_patch4_window7_224] INFO: Epoch: [136] [1070/1251] eta: 0:01:55 lr: 0.000573 loss: 3.3439 (3.3668) grad_norm: 1.4228 (inf) time: 0.6303 [2021-03-27 05:28:14 swin_base_patch4_window7_224] INFO: Epoch: [136] [1080/1251] eta: 0:01:48 lr: 0.000573 loss: 3.4081 (3.3683) grad_norm: 1.4228 (inf) time: 0.6264 [2021-03-27 05:28:20 swin_base_patch4_window7_224] INFO: Epoch: [136] [1090/1251] eta: 0:01:42 lr: 0.000573 loss: 3.5880 (3.3673) grad_norm: 1.5234 (inf) time: 0.6312 [2021-03-27 05:28:26 swin_base_patch4_window7_224] INFO: Epoch: [136] [1100/1251] eta: 0:01:35 lr: 0.000573 loss: 3.2319 (3.3652) grad_norm: 1.4422 (inf) time: 0.6324 [2021-03-27 05:28:32 swin_base_patch4_window7_224] INFO: Epoch: [136] [1110/1251] eta: 0:01:29 lr: 0.000573 loss: 3.2319 (3.3644) grad_norm: 1.4113 (inf) time: 0.6282 [2021-03-27 05:28:39 swin_base_patch4_window7_224] INFO: Epoch: [136] [1120/1251] eta: 0:01:23 lr: 0.000573 loss: 3.5701 (3.3653) grad_norm: 1.3707 (inf) time: 0.6310 [2021-03-27 05:28:45 swin_base_patch4_window7_224] INFO: Epoch: [136] [1130/1251] eta: 0:01:16 lr: 0.000573 loss: 3.5727 (3.3669) grad_norm: 1.3400 (inf) time: 0.6277 [2021-03-27 05:28:51 swin_base_patch4_window7_224] INFO: Epoch: [136] [1140/1251] eta: 0:01:10 lr: 0.000573 loss: 3.3164 (3.3652) grad_norm: 1.3682 (inf) time: 0.6282 [2021-03-27 05:28:58 swin_base_patch4_window7_224] INFO: Epoch: [136] [1150/1251] eta: 0:01:04 lr: 0.000573 loss: 3.2958 (3.3673) grad_norm: 1.4143 (inf) time: 0.6278 [2021-03-27 05:29:04 swin_base_patch4_window7_224] INFO: Epoch: [136] [1160/1251] eta: 0:00:57 lr: 0.000573 loss: 3.4551 (3.3663) grad_norm: 1.3896 (inf) time: 0.6271 [2021-03-27 05:29:10 swin_base_patch4_window7_224] INFO: Epoch: [136] [1170/1251] eta: 0:00:51 lr: 0.000573 loss: 3.4129 (3.3678) grad_norm: 1.3896 (inf) time: 0.6363 [2021-03-27 05:29:17 swin_base_patch4_window7_224] INFO: Epoch: [136] [1180/1251] eta: 0:00:45 lr: 0.000572 loss: 3.3476 (3.3673) grad_norm: 1.3905 (inf) time: 0.6329 [2021-03-27 05:29:23 swin_base_patch4_window7_224] INFO: Epoch: [136] [1190/1251] eta: 0:00:38 lr: 0.000572 loss: 3.3028 (3.3664) grad_norm: 1.3933 (inf) time: 0.6301 [2021-03-27 05:29:29 swin_base_patch4_window7_224] INFO: Epoch: [136] [1200/1251] eta: 0:00:32 lr: 0.000572 loss: 3.2807 (3.3662) grad_norm: 1.3775 (inf) time: 0.6366 [2021-03-27 05:29:36 swin_base_patch4_window7_224] INFO: Epoch: [136] [1210/1251] eta: 0:00:26 lr: 0.000572 loss: 3.2103 (3.3661) grad_norm: 1.3777 (inf) time: 0.6320 [2021-03-27 05:29:42 swin_base_patch4_window7_224] INFO: Epoch: [136] [1220/1251] eta: 0:00:19 lr: 0.000572 loss: 3.2268 (3.3657) grad_norm: 1.3777 (inf) time: 0.6276 [2021-03-27 05:29:48 swin_base_patch4_window7_224] INFO: Epoch: [136] [1230/1251] eta: 0:00:13 lr: 0.000572 loss: 3.5331 (3.3674) grad_norm: 1.3048 (inf) time: 0.6317 [2021-03-27 05:29:54 swin_base_patch4_window7_224] INFO: Epoch: [136] [1240/1251] eta: 0:00:06 lr: 0.000572 loss: 3.5807 (3.3688) grad_norm: 1.3430 (inf) time: 0.6310 [2021-03-27 05:30:01 swin_base_patch4_window7_224] INFO: Epoch: [136] [1250/1251] eta: 0:00:00 lr: 0.000572 loss: 3.3790 (3.3693) grad_norm: 1.3761 (inf) time: 0.6234 [2021-03-27 05:30:10 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:49 loss: 0.8724 (0.8724) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-27 05:30:13 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.8724 (0.9763) acc1: 79.6875 (78.6932) acc5: 93.7500 (93.7500) [2021-03-27 05:30:14 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9261 (0.9548) acc1: 79.6875 (79.1667) acc5: 93.7500 (94.1220) [2021-03-27 05:30:16 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9261 (0.9500) acc1: 78.1250 (79.0323) acc5: 93.7500 (94.2540) [2021-03-27 05:30:18 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9973 (0.9674) acc1: 76.5625 (77.8963) acc5: 93.7500 (94.4360) [2021-03-27 05:30:19 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0093 (0.9819) acc1: 73.4375 (77.2160) acc5: 93.7500 (94.2720) [2021-03-27 05:30:26 swin_base_patch4_window7_224] INFO: * Acc@1 78.256 Acc@5 94.404 loss 0.962 [2021-03-27 05:30:26 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.3% [2021-03-27 05:30:26 swin_base_patch4_window7_224] INFO: Max accuracy: 78.45% [2021-03-27 05:30:31 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 0/1251] eta: 1:32:18 lr: 0.000572 loss: 3.3675 (3.3675) grad_norm: 1.3471 (1.3471) time: 4.4276 [2021-03-27 05:30:37 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 10/1251] eta: 0:20:19 lr: 0.000572 loss: 3.4104 (3.4195) grad_norm: 1.4010 (1.4951) time: 0.9823 [2021-03-27 05:30:44 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 20/1251] eta: 0:16:43 lr: 0.000572 loss: 3.6104 (3.4127) grad_norm: 1.5705 (1.5639) time: 0.6347 [2021-03-27 05:30:50 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 30/1251] eta: 0:15:24 lr: 0.000572 loss: 3.1949 (3.3558) grad_norm: 1.5906 (1.5724) time: 0.6329 [2021-03-27 05:30:56 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 40/1251] eta: 0:14:38 lr: 0.000572 loss: 3.2759 (3.3668) grad_norm: 1.5045 (1.5626) time: 0.6317 [2021-03-27 05:31:02 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 50/1251] eta: 0:14:09 lr: 0.000572 loss: 3.3134 (3.3555) grad_norm: 1.3681 (1.5213) time: 0.6306 [2021-03-27 05:31:09 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 60/1251] eta: 0:13:48 lr: 0.000572 loss: 3.3134 (3.3518) grad_norm: 1.3777 (1.5017) time: 0.6350 [2021-03-27 05:31:15 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 70/1251] eta: 0:13:31 lr: 0.000572 loss: 3.3376 (3.3398) grad_norm: 1.3582 (1.4815) time: 0.6369 [2021-03-27 05:31:22 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 80/1251] eta: 0:13:17 lr: 0.000572 loss: 3.4404 (3.3719) grad_norm: 1.2985 (1.4650) time: 0.6356 [2021-03-27 05:31:28 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 90/1251] eta: 0:13:05 lr: 0.000572 loss: 3.5629 (3.3754) grad_norm: 1.3803 (1.4572) time: 0.6368 [2021-03-27 05:31:34 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 100/1251] eta: 0:12:54 lr: 0.000572 loss: 3.4832 (3.3727) grad_norm: 1.3806 (1.4462) time: 0.6383 [2021-03-27 05:31:41 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 110/1251] eta: 0:12:45 lr: 0.000572 loss: 3.4785 (3.3755) grad_norm: 1.3562 (1.4379) time: 0.6452 [2021-03-27 05:31:47 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 120/1251] eta: 0:12:35 lr: 0.000572 loss: 3.4996 (3.3894) grad_norm: 1.3710 (1.4399) time: 0.6429 [2021-03-27 05:31:54 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 130/1251] eta: 0:12:25 lr: 0.000572 loss: 3.4906 (3.3778) grad_norm: 1.3781 (1.4372) time: 0.6348 [2021-03-27 05:32:00 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 140/1251] eta: 0:12:16 lr: 0.000572 loss: 3.4194 (3.3867) grad_norm: 1.3781 (1.4401) time: 0.6343 [2021-03-27 05:32:06 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 150/1251] eta: 0:12:07 lr: 0.000572 loss: 3.4081 (3.3704) grad_norm: 1.4324 (1.4482) time: 0.6307 [2021-03-27 05:32:12 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 160/1251] eta: 0:11:58 lr: 0.000572 loss: 3.2057 (3.3694) grad_norm: 1.4358 (1.4453) time: 0.6248 [2021-03-27 05:32:19 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 170/1251] eta: 0:11:49 lr: 0.000571 loss: 3.4980 (3.3726) grad_norm: 1.3731 (1.4405) time: 0.6256 [2021-03-27 05:32:25 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 180/1251] eta: 0:11:41 lr: 0.000571 loss: 3.4980 (3.3772) grad_norm: 1.3828 (1.4379) time: 0.6288 [2021-03-27 05:32:31 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 190/1251] eta: 0:11:33 lr: 0.000571 loss: 3.3435 (3.3864) grad_norm: 1.3577 (1.4356) time: 0.6290 [2021-03-27 05:32:38 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 200/1251] eta: 0:11:26 lr: 0.000571 loss: 3.6264 (3.3920) grad_norm: 1.3933 (1.4397) time: 0.6334 [2021-03-27 05:32:44 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 210/1251] eta: 0:11:18 lr: 0.000571 loss: 3.5955 (3.3900) grad_norm: 1.4547 (1.4448) time: 0.6326 [2021-03-27 05:32:50 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 220/1251] eta: 0:11:10 lr: 0.000571 loss: 3.3498 (3.3803) grad_norm: 1.4193 (1.4436) time: 0.6293 [2021-03-27 05:32:57 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 230/1251] eta: 0:11:03 lr: 0.000571 loss: 3.1564 (3.3685) grad_norm: 1.3594 (1.4416) time: 0.6301 [2021-03-27 05:33:03 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 240/1251] eta: 0:10:56 lr: 0.000571 loss: 3.1993 (3.3618) grad_norm: 1.3309 (1.4382) time: 0.6302 [2021-03-27 05:33:09 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 250/1251] eta: 0:10:49 lr: 0.000571 loss: 3.2592 (3.3616) grad_norm: 1.3715 (1.4385) time: 0.6377 [2021-03-27 05:33:16 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 260/1251] eta: 0:10:42 lr: 0.000571 loss: 3.6194 (3.3742) grad_norm: 1.4412 (1.4391) time: 0.6404 [2021-03-27 05:33:22 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 270/1251] eta: 0:10:35 lr: 0.000571 loss: 3.6033 (3.3737) grad_norm: 1.4412 (1.4395) time: 0.6338 [2021-03-27 05:33:28 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 280/1251] eta: 0:10:28 lr: 0.000571 loss: 3.2243 (3.3742) grad_norm: 1.4240 (1.4407) time: 0.6325 [2021-03-27 05:33:35 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 290/1251] eta: 0:10:21 lr: 0.000571 loss: 3.6817 (3.3797) grad_norm: 1.4240 (1.4403) time: 0.6308 [2021-03-27 05:33:41 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 300/1251] eta: 0:10:14 lr: 0.000571 loss: 3.2073 (3.3728) grad_norm: 1.4328 (1.4449) time: 0.6297 [2021-03-27 05:33:47 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 310/1251] eta: 0:10:07 lr: 0.000571 loss: 3.0989 (3.3734) grad_norm: 1.4172 (1.4444) time: 0.6296 [2021-03-27 05:33:54 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 320/1251] eta: 0:10:00 lr: 0.000571 loss: 3.1918 (3.3609) grad_norm: 1.3963 (1.4473) time: 0.6332 [2021-03-27 05:34:00 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 330/1251] eta: 0:09:54 lr: 0.000571 loss: 3.1452 (3.3558) grad_norm: 1.4741 (1.4506) time: 0.6398 [2021-03-27 05:34:06 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 340/1251] eta: 0:09:47 lr: 0.000571 loss: 3.2824 (3.3487) grad_norm: 1.4334 (1.4497) time: 0.6365 [2021-03-27 05:34:13 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 350/1251] eta: 0:09:40 lr: 0.000571 loss: 3.3317 (3.3518) grad_norm: 1.4722 (1.4501) time: 0.6367 [2021-03-27 05:34:19 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 360/1251] eta: 0:09:34 lr: 0.000571 loss: 3.5120 (3.3511) grad_norm: 1.4622 (1.4492) time: 0.6388 [2021-03-27 05:34:25 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 370/1251] eta: 0:09:27 lr: 0.000571 loss: 3.2314 (3.3503) grad_norm: 1.3942 (1.4489) time: 0.6294 [2021-03-27 05:34:32 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 380/1251] eta: 0:09:20 lr: 0.000571 loss: 3.3903 (3.3499) grad_norm: 1.3926 (1.4480) time: 0.6310 [2021-03-27 05:34:38 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 390/1251] eta: 0:09:13 lr: 0.000571 loss: 3.4874 (3.3472) grad_norm: 1.3926 (1.4468) time: 0.6339 [2021-03-27 05:34:44 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 400/1251] eta: 0:09:07 lr: 0.000571 loss: 3.5664 (3.3578) grad_norm: 1.3503 (1.4452) time: 0.6306 [2021-03-27 05:34:51 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 410/1251] eta: 0:09:00 lr: 0.000570 loss: 3.4975 (3.3519) grad_norm: 1.3503 (1.4467) time: 0.6287 [2021-03-27 05:34:57 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 420/1251] eta: 0:08:53 lr: 0.000570 loss: 3.3740 (3.3538) grad_norm: 1.4699 (1.4469) time: 0.6286 [2021-03-27 05:35:03 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 430/1251] eta: 0:08:47 lr: 0.000570 loss: 3.5268 (3.3556) grad_norm: 1.4197 (1.4463) time: 0.6299 [2021-03-27 05:35:10 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 440/1251] eta: 0:08:40 lr: 0.000570 loss: 3.3336 (3.3489) grad_norm: 1.3444 (1.4440) time: 0.6362 [2021-03-27 05:35:16 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 450/1251] eta: 0:08:34 lr: 0.000570 loss: 3.2631 (3.3469) grad_norm: 1.3984 (1.4433) time: 0.6385 [2021-03-27 05:35:22 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 460/1251] eta: 0:08:27 lr: 0.000570 loss: 3.2631 (3.3464) grad_norm: 1.4351 (1.4436) time: 0.6309 [2021-03-27 05:35:29 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 470/1251] eta: 0:08:20 lr: 0.000570 loss: 3.3134 (3.3460) grad_norm: 1.4547 (1.4449) time: 0.6278 [2021-03-27 05:35:35 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 480/1251] eta: 0:08:14 lr: 0.000570 loss: 3.4889 (3.3449) grad_norm: 1.4108 (1.4443) time: 0.6252 [2021-03-27 05:35:41 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 490/1251] eta: 0:08:07 lr: 0.000570 loss: 3.5478 (3.3525) grad_norm: 1.3564 (1.4427) time: 0.6221 [2021-03-27 05:35:47 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 500/1251] eta: 0:08:00 lr: 0.000570 loss: 3.6378 (3.3535) grad_norm: 1.3742 (1.4422) time: 0.6245 [2021-03-27 05:35:54 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 510/1251] eta: 0:07:54 lr: 0.000570 loss: 3.3925 (3.3526) grad_norm: 1.3661 (1.4424) time: 0.6334 [2021-03-27 05:36:00 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 520/1251] eta: 0:07:47 lr: 0.000570 loss: 3.1875 (3.3463) grad_norm: 1.3661 (1.4431) time: 0.6363 [2021-03-27 05:36:06 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 530/1251] eta: 0:07:41 lr: 0.000570 loss: 3.1875 (3.3453) grad_norm: 1.3923 (1.4429) time: 0.6316 [2021-03-27 05:36:13 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 540/1251] eta: 0:07:34 lr: 0.000570 loss: 3.3416 (3.3405) grad_norm: 1.3923 (1.4469) time: 0.6269 [2021-03-27 05:36:19 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 550/1251] eta: 0:07:28 lr: 0.000570 loss: 3.3416 (3.3381) grad_norm: 1.5489 (1.4480) time: 0.6458 [2021-03-27 05:36:26 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 560/1251] eta: 0:07:22 lr: 0.000570 loss: 3.3952 (3.3392) grad_norm: 1.4973 (1.4486) time: 0.6536 [2021-03-27 05:36:32 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 570/1251] eta: 0:07:15 lr: 0.000570 loss: 3.2336 (3.3356) grad_norm: 1.3572 (1.4494) time: 0.6362 [2021-03-27 05:36:38 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 580/1251] eta: 0:07:09 lr: 0.000570 loss: 3.4769 (3.3402) grad_norm: 1.4224 (1.4506) time: 0.6364 [2021-03-27 05:36:45 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 590/1251] eta: 0:07:02 lr: 0.000570 loss: 3.4921 (3.3415) grad_norm: 1.4224 (1.4502) time: 0.6330 [2021-03-27 05:36:51 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 600/1251] eta: 0:06:56 lr: 0.000570 loss: 3.3284 (3.3413) grad_norm: 1.4122 (1.4514) time: 0.6297 [2021-03-27 05:36:57 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 610/1251] eta: 0:06:49 lr: 0.000570 loss: 3.2944 (3.3449) grad_norm: 1.4730 (1.4522) time: 0.6329 [2021-03-27 05:37:04 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 620/1251] eta: 0:06:43 lr: 0.000570 loss: 3.5429 (3.3480) grad_norm: 1.4890 (1.4517) time: 0.6285 [2021-03-27 05:37:10 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 630/1251] eta: 0:06:36 lr: 0.000570 loss: 3.4737 (3.3476) grad_norm: 1.5079 (1.4526) time: 0.6270 [2021-03-27 05:37:16 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 640/1251] eta: 0:06:30 lr: 0.000570 loss: 3.3746 (3.3460) grad_norm: 1.3964 (1.4511) time: 0.6304 [2021-03-27 05:37:22 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 650/1251] eta: 0:06:23 lr: 0.000570 loss: 3.1308 (3.3463) grad_norm: 1.3381 (1.4502) time: 0.6266 [2021-03-27 05:37:29 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 660/1251] eta: 0:06:17 lr: 0.000569 loss: 3.3735 (3.3474) grad_norm: 1.4704 (1.4510) time: 0.6279 [2021-03-27 05:37:35 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 670/1251] eta: 0:06:10 lr: 0.000569 loss: 3.4798 (3.3487) grad_norm: 1.3105 (1.4492) time: 0.6328 [2021-03-27 05:37:41 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 680/1251] eta: 0:06:04 lr: 0.000569 loss: 3.5063 (3.3487) grad_norm: 1.3546 (1.4489) time: 0.6324 [2021-03-27 05:37:48 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 690/1251] eta: 0:05:58 lr: 0.000569 loss: 3.3894 (3.3465) grad_norm: 1.3887 (1.4476) time: 0.6349 [2021-03-27 05:37:54 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 700/1251] eta: 0:05:51 lr: 0.000569 loss: 3.3894 (3.3467) grad_norm: 1.3989 (1.4472) time: 0.6324 [2021-03-27 05:38:00 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 710/1251] eta: 0:05:45 lr: 0.000569 loss: 3.0803 (3.3420) grad_norm: 1.4178 (1.4472) time: 0.6277 [2021-03-27 05:38:07 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 720/1251] eta: 0:05:38 lr: 0.000569 loss: 3.0803 (3.3427) grad_norm: 1.4575 (1.4473) time: 0.6311 [2021-03-27 05:38:13 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 730/1251] eta: 0:05:32 lr: 0.000569 loss: 3.3056 (3.3420) grad_norm: 1.4248 (1.4475) time: 0.6338 [2021-03-27 05:38:19 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 740/1251] eta: 0:05:26 lr: 0.000569 loss: 3.4411 (3.3416) grad_norm: 1.4296 (1.4476) time: 0.6368 [2021-03-27 05:38:26 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 750/1251] eta: 0:05:19 lr: 0.000569 loss: 3.3343 (3.3394) grad_norm: 1.4560 (1.4484) time: 0.6461 [2021-03-27 05:38:32 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 760/1251] eta: 0:05:13 lr: 0.000569 loss: 3.3343 (3.3372) grad_norm: 1.3985 (1.4475) time: 0.6376 [2021-03-27 05:38:38 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 770/1251] eta: 0:05:06 lr: 0.000569 loss: 3.2403 (3.3358) grad_norm: 1.3323 (1.4475) time: 0.6243 [2021-03-27 05:38:45 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 780/1251] eta: 0:05:00 lr: 0.000569 loss: 3.1931 (3.3348) grad_norm: 1.4904 (1.4493) time: 0.6277 [2021-03-27 05:38:51 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 790/1251] eta: 0:04:53 lr: 0.000569 loss: 3.2224 (3.3351) grad_norm: 1.5545 (1.4513) time: 0.6308 [2021-03-27 05:38:57 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 800/1251] eta: 0:04:47 lr: 0.000569 loss: 3.5944 (3.3390) grad_norm: 1.4597 (1.4506) time: 0.6295 [2021-03-27 05:39:04 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 810/1251] eta: 0:04:41 lr: 0.000569 loss: 3.6983 (3.3391) grad_norm: 1.3524 (1.4504) time: 0.6327 [2021-03-27 05:39:10 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 820/1251] eta: 0:04:34 lr: 0.000569 loss: 3.4594 (3.3387) grad_norm: 1.3741 (1.4496) time: 0.6331 [2021-03-27 05:39:16 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 830/1251] eta: 0:04:28 lr: 0.000569 loss: 3.0999 (3.3357) grad_norm: 1.3741 (1.4488) time: 0.6342 [2021-03-27 05:39:23 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 840/1251] eta: 0:04:21 lr: 0.000569 loss: 3.0999 (3.3364) grad_norm: 1.2986 (1.4476) time: 0.6326 [2021-03-27 05:39:29 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 850/1251] eta: 0:04:15 lr: 0.000569 loss: 3.4953 (3.3367) grad_norm: 1.3369 (1.4472) time: 0.6260 [2021-03-27 05:39:35 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 860/1251] eta: 0:04:09 lr: 0.000569 loss: 3.4300 (3.3378) grad_norm: 1.3771 (1.4469) time: 0.6269 [2021-03-27 05:39:41 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 870/1251] eta: 0:04:02 lr: 0.000569 loss: 3.3299 (3.3358) grad_norm: 1.3616 (1.4463) time: 0.6310 [2021-03-27 05:39:48 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 880/1251] eta: 0:03:56 lr: 0.000569 loss: 3.4618 (3.3393) grad_norm: 1.3531 (1.4458) time: 0.6272 [2021-03-27 05:39:54 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 890/1251] eta: 0:03:49 lr: 0.000569 loss: 3.4783 (3.3407) grad_norm: 1.4307 (1.4459) time: 0.6232 [2021-03-27 05:40:00 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 900/1251] eta: 0:03:43 lr: 0.000568 loss: 3.4315 (3.3404) grad_norm: 1.4608 (1.4463) time: 0.6279 [2021-03-27 05:40:07 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 910/1251] eta: 0:03:37 lr: 0.000568 loss: 3.5370 (3.3431) grad_norm: 1.4159 (1.4456) time: 0.6337 [2021-03-27 05:40:13 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 920/1251] eta: 0:03:30 lr: 0.000568 loss: 3.5370 (3.3419) grad_norm: 1.3505 (1.4470) time: 0.6318 [2021-03-27 05:40:19 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 930/1251] eta: 0:03:24 lr: 0.000568 loss: 3.4395 (3.3438) grad_norm: 1.4480 (1.4477) time: 0.6292 [2021-03-27 05:40:25 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 940/1251] eta: 0:03:17 lr: 0.000568 loss: 3.4354 (3.3428) grad_norm: 1.5201 (1.4492) time: 0.6292 [2021-03-27 05:40:32 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 950/1251] eta: 0:03:11 lr: 0.000568 loss: 3.4004 (3.3431) grad_norm: 1.5201 (1.4493) time: 0.6337 [2021-03-27 05:40:38 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 960/1251] eta: 0:03:05 lr: 0.000568 loss: 3.6304 (3.3461) grad_norm: 1.3792 (1.4499) time: 0.6374 [2021-03-27 05:40:44 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 970/1251] eta: 0:02:58 lr: 0.000568 loss: 3.4669 (3.3462) grad_norm: 1.4174 (1.4501) time: 0.6306 [2021-03-27 05:40:51 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 980/1251] eta: 0:02:52 lr: 0.000568 loss: 3.5419 (3.3510) grad_norm: 1.4465 (1.4508) time: 0.6228 [2021-03-27 05:40:57 swin_base_patch4_window7_224] INFO: Epoch: [137] [ 990/1251] eta: 0:02:46 lr: 0.000568 loss: 3.6298 (3.3531) grad_norm: 1.4288 (1.4506) time: 0.6207 [2021-03-27 05:41:03 swin_base_patch4_window7_224] INFO: Epoch: [137] [1000/1251] eta: 0:02:39 lr: 0.000568 loss: 3.4040 (3.3522) grad_norm: 1.4288 (1.4508) time: 0.6295 [2021-03-27 05:41:10 swin_base_patch4_window7_224] INFO: Epoch: [137] [1010/1251] eta: 0:02:33 lr: 0.000568 loss: 3.2249 (3.3507) grad_norm: 1.3712 (1.4498) time: 0.6330 [2021-03-27 05:41:16 swin_base_patch4_window7_224] INFO: Epoch: [137] [1020/1251] eta: 0:02:26 lr: 0.000568 loss: 3.5685 (3.3536) grad_norm: 1.3494 (1.4500) time: 0.6364 [2021-03-27 05:41:22 swin_base_patch4_window7_224] INFO: Epoch: [137] [1030/1251] eta: 0:02:20 lr: 0.000568 loss: 3.5438 (3.3537) grad_norm: 1.4411 (1.4510) time: 0.6298 [2021-03-27 05:41:28 swin_base_patch4_window7_224] INFO: Epoch: [137] [1040/1251] eta: 0:02:14 lr: 0.000568 loss: 3.3510 (3.3537) grad_norm: 1.4525 (1.4515) time: 0.6220 [2021-03-27 05:41:35 swin_base_patch4_window7_224] INFO: Epoch: [137] [1050/1251] eta: 0:02:07 lr: 0.000568 loss: 3.3510 (3.3540) grad_norm: 1.4525 (1.4517) time: 0.6356 [2021-03-27 05:41:41 swin_base_patch4_window7_224] INFO: Epoch: [137] [1060/1251] eta: 0:02:01 lr: 0.000568 loss: 3.4944 (3.3554) grad_norm: 1.3964 (1.4510) time: 0.6346 [2021-03-27 05:41:47 swin_base_patch4_window7_224] INFO: Epoch: [137] [1070/1251] eta: 0:01:55 lr: 0.000568 loss: 3.5046 (3.3560) grad_norm: 1.3964 (1.4504) time: 0.6295 [2021-03-27 05:41:54 swin_base_patch4_window7_224] INFO: Epoch: [137] [1080/1251] eta: 0:01:48 lr: 0.000568 loss: 3.3203 (3.3541) grad_norm: 1.4125 (1.4502) time: 0.6332 [2021-03-27 05:42:00 swin_base_patch4_window7_224] INFO: Epoch: [137] [1090/1251] eta: 0:01:42 lr: 0.000568 loss: 3.3933 (3.3558) grad_norm: 1.3873 (1.4498) time: 0.6325 [2021-03-27 05:42:06 swin_base_patch4_window7_224] INFO: Epoch: [137] [1100/1251] eta: 0:01:35 lr: 0.000568 loss: 3.5103 (3.3553) grad_norm: 1.3901 (1.4504) time: 0.6302 [2021-03-27 05:42:13 swin_base_patch4_window7_224] INFO: Epoch: [137] [1110/1251] eta: 0:01:29 lr: 0.000568 loss: 3.4385 (3.3566) grad_norm: 1.3901 (1.4501) time: 0.6305 [2021-03-27 05:42:19 swin_base_patch4_window7_224] INFO: Epoch: [137] [1120/1251] eta: 0:01:23 lr: 0.000568 loss: 3.6314 (3.3574) grad_norm: 1.3665 (1.4499) time: 0.6275 [2021-03-27 05:42:25 swin_base_patch4_window7_224] INFO: Epoch: [137] [1130/1251] eta: 0:01:16 lr: 0.000568 loss: 3.4537 (3.3573) grad_norm: 1.3584 (1.4494) time: 0.6212 [2021-03-27 05:42:32 swin_base_patch4_window7_224] INFO: Epoch: [137] [1140/1251] eta: 0:01:10 lr: 0.000567 loss: 3.3997 (3.3562) grad_norm: 1.3731 (1.4506) time: 0.6298 [2021-03-27 05:42:38 swin_base_patch4_window7_224] INFO: Epoch: [137] [1150/1251] eta: 0:01:04 lr: 0.000567 loss: 3.2995 (3.3560) grad_norm: 1.4777 (1.4511) time: 0.6338 [2021-03-27 05:42:44 swin_base_patch4_window7_224] INFO: Epoch: [137] [1160/1251] eta: 0:00:57 lr: 0.000567 loss: 3.2995 (3.3554) grad_norm: 1.4531 (1.4517) time: 0.6324 [2021-03-27 05:42:50 swin_base_patch4_window7_224] INFO: Epoch: [137] [1170/1251] eta: 0:00:51 lr: 0.000567 loss: 3.3876 (3.3564) grad_norm: 1.5046 (1.4529) time: 0.6315 [2021-03-27 05:42:57 swin_base_patch4_window7_224] INFO: Epoch: [137] [1180/1251] eta: 0:00:45 lr: 0.000567 loss: 3.3876 (3.3553) grad_norm: 1.5047 (1.4532) time: 0.6287 [2021-03-27 05:43:03 swin_base_patch4_window7_224] INFO: Epoch: [137] [1190/1251] eta: 0:00:38 lr: 0.000567 loss: 3.0205 (3.3541) grad_norm: 1.4366 (1.4525) time: 0.6324 [2021-03-27 05:43:10 swin_base_patch4_window7_224] INFO: Epoch: [137] [1200/1251] eta: 0:00:32 lr: 0.000567 loss: 3.2034 (3.3541) grad_norm: 1.4137 (1.4529) time: 0.6400 [2021-03-27 05:43:16 swin_base_patch4_window7_224] INFO: Epoch: [137] [1210/1251] eta: 0:00:26 lr: 0.000567 loss: 3.3182 (3.3533) grad_norm: 1.4245 (1.4529) time: 0.6379 [2021-03-27 05:43:22 swin_base_patch4_window7_224] INFO: Epoch: [137] [1220/1251] eta: 0:00:19 lr: 0.000567 loss: 3.3878 (3.3534) grad_norm: 1.3826 (1.4522) time: 0.6336 [2021-03-27 05:43:29 swin_base_patch4_window7_224] INFO: Epoch: [137] [1230/1251] eta: 0:00:13 lr: 0.000567 loss: 3.6386 (3.3565) grad_norm: 1.3746 (1.4517) time: 0.6316 [2021-03-27 05:43:35 swin_base_patch4_window7_224] INFO: Epoch: [137] [1240/1251] eta: 0:00:06 lr: 0.000567 loss: 3.7084 (3.3557) grad_norm: 1.3223 (1.4507) time: 0.6229 [2021-03-27 05:43:41 swin_base_patch4_window7_224] INFO: Epoch: [137] [1250/1251] eta: 0:00:00 lr: 0.000567 loss: 3.0855 (3.3542) grad_norm: 1.3608 (1.4507) time: 0.6180 [2021-03-27 05:43:54 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:07 loss: 0.9646 (0.9646) acc1: 79.6875 (79.6875) acc5: 95.3125 (95.3125) [2021-03-27 05:43:56 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.8920 (0.8588) acc1: 79.6875 (79.9716) acc5: 96.8750 (96.4489) [2021-03-27 05:43:58 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8920 (0.9065) acc1: 78.1250 (78.7202) acc5: 95.3125 (94.8661) [2021-03-27 05:44:00 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9525 (0.9329) acc1: 76.5625 (77.5202) acc5: 93.7500 (94.9093) [2021-03-27 05:44:02 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9715 (0.9494) acc1: 76.5625 (77.7439) acc5: 93.7500 (94.6646) [2021-03-27 05:44:04 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8396 (0.9322) acc1: 78.1250 (77.7280) acc5: 95.3125 (94.7520) [2021-03-27 05:44:15 swin_base_patch4_window7_224] INFO: * Acc@1 78.438 Acc@5 94.542 loss 0.925 [2021-03-27 05:44:15 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.4% [2021-03-27 05:44:15 swin_base_patch4_window7_224] INFO: Max accuracy: 78.45% [2021-03-27 05:44:20 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 0/1251] eta: 1:32:11 lr: 0.000567 loss: 3.9679 (3.9679) grad_norm: 1.5226 (1.5226) time: 4.4214 [2021-03-27 05:44:26 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 10/1251] eta: 0:20:26 lr: 0.000567 loss: 3.2187 (3.2432) grad_norm: 1.4256 (1.4623) time: 0.9879 [2021-03-27 05:44:32 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 20/1251] eta: 0:16:46 lr: 0.000567 loss: 3.3757 (3.3454) grad_norm: 1.4256 (1.4759) time: 0.6373 [2021-03-27 05:44:38 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 30/1251] eta: 0:15:21 lr: 0.000567 loss: 3.4537 (3.2328) grad_norm: 1.3922 (1.4500) time: 0.6264 [2021-03-27 05:44:45 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 40/1251] eta: 0:14:35 lr: 0.000567 loss: 3.3613 (3.2543) grad_norm: 1.3922 (1.4427) time: 0.6242 [2021-03-27 05:44:51 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 50/1251] eta: 0:14:06 lr: 0.000567 loss: 3.3613 (3.2457) grad_norm: 1.3876 (1.4345) time: 0.6284 [2021-03-27 05:44:57 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 60/1251] eta: 0:13:45 lr: 0.000567 loss: 3.3177 (3.2788) grad_norm: 1.3702 (1.4252) time: 0.6324 [2021-03-27 05:45:04 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 70/1251] eta: 0:13:31 lr: 0.000567 loss: 3.3363 (3.3104) grad_norm: 1.3798 (1.4321) time: 0.6401 [2021-03-27 05:45:10 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 80/1251] eta: 0:13:15 lr: 0.000567 loss: 3.3569 (3.3230) grad_norm: 1.3689 (1.4212) time: 0.6370 [2021-03-27 05:45:16 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 90/1251] eta: 0:13:03 lr: 0.000567 loss: 3.2749 (3.3125) grad_norm: 1.3201 (1.4185) time: 0.6312 [2021-03-27 05:45:23 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 100/1251] eta: 0:12:51 lr: 0.000567 loss: 3.4518 (3.3394) grad_norm: 1.3284 (1.4124) time: 0.6344 [2021-03-27 05:45:29 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 110/1251] eta: 0:12:40 lr: 0.000567 loss: 3.5736 (3.3621) grad_norm: 1.3078 (1.4079) time: 0.6292 [2021-03-27 05:45:35 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 120/1251] eta: 0:12:30 lr: 0.000567 loss: 3.4542 (3.3488) grad_norm: 1.4071 (1.4278) time: 0.6292 [2021-03-27 05:45:42 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 130/1251] eta: 0:12:20 lr: 0.000567 loss: 3.3735 (3.3587) grad_norm: 1.3992 (1.4241) time: 0.6286 [2021-03-27 05:45:48 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 140/1251] eta: 0:12:11 lr: 0.000566 loss: 3.5200 (3.3695) grad_norm: 1.3042 (1.4166) time: 0.6283 [2021-03-27 05:45:54 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 150/1251] eta: 0:12:02 lr: 0.000566 loss: 3.5090 (3.3684) grad_norm: 1.3364 (1.4153) time: 0.6281 [2021-03-27 05:46:00 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 160/1251] eta: 0:11:54 lr: 0.000566 loss: 3.6293 (3.3897) grad_norm: 1.3715 (1.4138) time: 0.6252 [2021-03-27 05:46:07 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 170/1251] eta: 0:11:45 lr: 0.000566 loss: 3.6190 (3.3713) grad_norm: 1.4079 (1.4239) time: 0.6240 [2021-03-27 05:46:13 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 180/1251] eta: 0:11:37 lr: 0.000566 loss: 3.3134 (3.3673) grad_norm: 1.3577 (1.4201) time: 0.6267 [2021-03-27 05:46:19 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 190/1251] eta: 0:11:29 lr: 0.000566 loss: 3.3186 (3.3678) grad_norm: 1.3909 (1.4241) time: 0.6308 [2021-03-27 05:46:26 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 200/1251] eta: 0:11:23 lr: 0.000566 loss: 3.5408 (3.3720) grad_norm: 1.4336 (1.4245) time: 0.6369 [2021-03-27 05:46:32 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 210/1251] eta: 0:11:15 lr: 0.000566 loss: 3.4634 (3.3701) grad_norm: 1.4126 (1.4251) time: 0.6321 [2021-03-27 05:46:38 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 220/1251] eta: 0:11:07 lr: 0.000566 loss: 3.3845 (3.3719) grad_norm: 1.4355 (1.4276) time: 0.6212 [2021-03-27 05:46:45 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 230/1251] eta: 0:11:00 lr: 0.000566 loss: 3.3992 (3.3679) grad_norm: 1.4047 (1.4259) time: 0.6274 [2021-03-27 05:46:51 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 240/1251] eta: 0:10:53 lr: 0.000566 loss: 3.3982 (3.3631) grad_norm: 1.4231 (1.4316) time: 0.6292 [2021-03-27 05:46:57 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 250/1251] eta: 0:10:45 lr: 0.000566 loss: 3.1019 (3.3507) grad_norm: 1.4581 (1.4372) time: 0.6235 [2021-03-27 05:47:03 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 260/1251] eta: 0:10:38 lr: 0.000566 loss: 3.3711 (3.3603) grad_norm: 1.4536 (1.4370) time: 0.6232 [2021-03-27 05:47:10 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 270/1251] eta: 0:10:31 lr: 0.000566 loss: 3.5868 (3.3638) grad_norm: 1.4536 (1.4392) time: 0.6270 [2021-03-27 05:47:16 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 280/1251] eta: 0:10:24 lr: 0.000566 loss: 3.3677 (3.3648) grad_norm: 1.4679 (1.4433) time: 0.6237 [2021-03-27 05:47:22 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 290/1251] eta: 0:10:16 lr: 0.000566 loss: 3.4758 (3.3643) grad_norm: 1.4931 (1.4434) time: 0.6204 [2021-03-27 05:47:28 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 300/1251] eta: 0:10:10 lr: 0.000566 loss: 3.3375 (3.3565) grad_norm: 1.3814 (1.4408) time: 0.6246 [2021-03-27 05:47:34 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 310/1251] eta: 0:10:03 lr: 0.000566 loss: 3.2321 (3.3513) grad_norm: 1.3846 (1.4410) time: 0.6257 [2021-03-27 05:47:41 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 320/1251] eta: 0:09:56 lr: 0.000566 loss: 3.1950 (3.3473) grad_norm: 1.4034 (1.4380) time: 0.6250 [2021-03-27 05:47:47 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 330/1251] eta: 0:09:49 lr: 0.000566 loss: 3.1817 (3.3336) grad_norm: 1.3420 (1.4371) time: 0.6263 [2021-03-27 05:47:53 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 340/1251] eta: 0:09:42 lr: 0.000566 loss: 3.2124 (3.3326) grad_norm: 1.3983 (1.4377) time: 0.6284 [2021-03-27 05:48:00 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 350/1251] eta: 0:09:36 lr: 0.000566 loss: 3.4564 (3.3352) grad_norm: 1.4039 (1.4374) time: 0.6316 [2021-03-27 05:48:06 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 360/1251] eta: 0:09:29 lr: 0.000566 loss: 3.4343 (3.3345) grad_norm: 1.3569 (1.4364) time: 0.6280 [2021-03-27 05:48:12 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 370/1251] eta: 0:09:22 lr: 0.000566 loss: 3.3126 (3.3354) grad_norm: 1.3569 (1.4350) time: 0.6283 [2021-03-27 05:48:19 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 380/1251] eta: 0:09:16 lr: 0.000565 loss: 3.2110 (3.3321) grad_norm: 1.3621 (1.4334) time: 0.6333 [2021-03-27 05:48:25 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 390/1251] eta: 0:09:10 lr: 0.000565 loss: 3.1947 (3.3273) grad_norm: 1.4626 (1.4380) time: 0.6358 [2021-03-27 05:48:31 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 400/1251] eta: 0:09:03 lr: 0.000565 loss: 3.2258 (3.3255) grad_norm: 1.5282 (1.4407) time: 0.6365 [2021-03-27 05:48:38 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 410/1251] eta: 0:08:56 lr: 0.000565 loss: 3.2258 (3.3221) grad_norm: 1.4053 (1.4406) time: 0.6325 [2021-03-27 05:48:44 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 420/1251] eta: 0:08:50 lr: 0.000565 loss: 3.3106 (3.3242) grad_norm: 1.4245 (1.4432) time: 0.6342 [2021-03-27 05:48:50 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 430/1251] eta: 0:08:43 lr: 0.000565 loss: 3.4109 (3.3279) grad_norm: 1.4295 (1.4432) time: 0.6310 [2021-03-27 05:48:56 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 440/1251] eta: 0:08:37 lr: 0.000565 loss: 3.4799 (3.3297) grad_norm: 1.4157 (1.4430) time: 0.6228 [2021-03-27 05:49:03 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 450/1251] eta: 0:08:30 lr: 0.000565 loss: 3.4742 (3.3263) grad_norm: 1.4157 (1.4442) time: 0.6238 [2021-03-27 05:49:09 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 460/1251] eta: 0:08:24 lr: 0.000565 loss: 3.4407 (3.3274) grad_norm: 1.3526 (1.4421) time: 0.6251 [2021-03-27 05:49:15 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 470/1251] eta: 0:08:17 lr: 0.000565 loss: 3.5666 (3.3258) grad_norm: 1.3526 (1.4400) time: 0.6257 [2021-03-27 05:49:22 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 480/1251] eta: 0:08:11 lr: 0.000565 loss: 3.3705 (3.3275) grad_norm: 1.3492 (1.4400) time: 0.6290 [2021-03-27 05:49:28 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 490/1251] eta: 0:08:04 lr: 0.000565 loss: 3.2519 (3.3259) grad_norm: 1.3927 (1.4396) time: 0.6292 [2021-03-27 05:49:34 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 500/1251] eta: 0:07:58 lr: 0.000565 loss: 3.4073 (3.3254) grad_norm: 1.3927 (1.4382) time: 0.6286 [2021-03-27 05:49:40 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 510/1251] eta: 0:07:51 lr: 0.000565 loss: 3.4745 (3.3289) grad_norm: 1.3747 (1.4385) time: 0.6318 [2021-03-27 05:49:47 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 520/1251] eta: 0:07:45 lr: 0.000565 loss: 3.5236 (3.3293) grad_norm: 1.3492 (1.4359) time: 0.6360 [2021-03-27 05:49:53 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 530/1251] eta: 0:07:38 lr: 0.000565 loss: 3.5727 (3.3310) grad_norm: 1.3302 (1.4348) time: 0.6360 [2021-03-27 05:49:59 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 540/1251] eta: 0:07:32 lr: 0.000565 loss: 3.5727 (3.3362) grad_norm: 1.3133 (1.4329) time: 0.6330 [2021-03-27 05:50:06 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 550/1251] eta: 0:07:26 lr: 0.000565 loss: 3.3376 (3.3297) grad_norm: 1.3063 (1.4326) time: 0.6370 [2021-03-27 05:50:12 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 560/1251] eta: 0:07:19 lr: 0.000565 loss: 2.8524 (3.3231) grad_norm: 1.3870 (1.4313) time: 0.6420 [2021-03-27 05:50:19 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 570/1251] eta: 0:07:13 lr: 0.000565 loss: 3.1523 (3.3229) grad_norm: 1.4006 (1.4316) time: 0.6336 [2021-03-27 05:50:25 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 580/1251] eta: 0:07:06 lr: 0.000565 loss: 3.2577 (3.3179) grad_norm: 1.4066 (1.4325) time: 0.6284 [2021-03-27 05:50:31 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 590/1251] eta: 0:07:00 lr: 0.000565 loss: 3.0040 (3.3108) grad_norm: 1.4423 (1.4326) time: 0.6311 [2021-03-27 05:50:38 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 600/1251] eta: 0:06:54 lr: 0.000565 loss: 3.2241 (3.3120) grad_norm: 1.4224 (1.4324) time: 0.6404 [2021-03-27 05:50:44 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 610/1251] eta: 0:06:47 lr: 0.000565 loss: 3.3600 (3.3118) grad_norm: 1.3500 (1.4318) time: 0.6425 [2021-03-27 05:50:50 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 620/1251] eta: 0:06:41 lr: 0.000564 loss: 3.4490 (3.3164) grad_norm: 1.3500 (1.4323) time: 0.6370 [2021-03-27 05:50:57 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 630/1251] eta: 0:06:35 lr: 0.000564 loss: 3.3953 (3.3117) grad_norm: 1.3369 (1.4307) time: 0.6419 [2021-03-27 05:51:03 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 640/1251] eta: 0:06:28 lr: 0.000564 loss: 3.4651 (3.3160) grad_norm: 1.3576 (1.4315) time: 0.6341 [2021-03-27 05:51:09 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 650/1251] eta: 0:06:22 lr: 0.000564 loss: 3.4007 (3.3112) grad_norm: 1.4899 (1.4331) time: 0.6275 [2021-03-27 05:51:16 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 660/1251] eta: 0:06:15 lr: 0.000564 loss: 3.2015 (3.3129) grad_norm: 1.4899 (1.4340) time: 0.6300 [2021-03-27 05:51:22 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 670/1251] eta: 0:06:09 lr: 0.000564 loss: 3.3508 (3.3134) grad_norm: 1.3742 (1.4332) time: 0.6322 [2021-03-27 05:51:28 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 680/1251] eta: 0:06:03 lr: 0.000564 loss: 3.3716 (3.3144) grad_norm: 1.4818 (1.4358) time: 0.6336 [2021-03-27 05:51:35 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 690/1251] eta: 0:05:56 lr: 0.000564 loss: 3.5860 (3.3187) grad_norm: 1.4512 (1.4353) time: 0.6260 [2021-03-27 05:51:41 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 700/1251] eta: 0:05:50 lr: 0.000564 loss: 3.4436 (3.3197) grad_norm: 1.3700 (1.4348) time: 0.6203 [2021-03-27 05:51:47 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 710/1251] eta: 0:05:43 lr: 0.000564 loss: 3.3732 (3.3195) grad_norm: 1.4481 (1.4358) time: 0.6300 [2021-03-27 05:51:54 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 720/1251] eta: 0:05:37 lr: 0.000564 loss: 3.2944 (3.3181) grad_norm: 1.5046 (1.4375) time: 0.6352 [2021-03-27 05:52:00 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 730/1251] eta: 0:05:31 lr: 0.000564 loss: 3.2944 (3.3191) grad_norm: 1.4920 (1.4377) time: 0.6329 [2021-03-27 05:52:06 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 740/1251] eta: 0:05:24 lr: 0.000564 loss: 3.3356 (3.3187) grad_norm: 1.3797 (1.4376) time: 0.6381 [2021-03-27 05:52:13 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 750/1251] eta: 0:05:18 lr: 0.000564 loss: 3.2577 (3.3200) grad_norm: 1.3710 (1.4380) time: 0.6432 [2021-03-27 05:52:19 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 760/1251] eta: 0:05:12 lr: 0.000564 loss: 3.2747 (3.3195) grad_norm: 1.4260 (1.4376) time: 0.6423 [2021-03-27 05:52:25 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 770/1251] eta: 0:05:05 lr: 0.000564 loss: 3.2747 (3.3178) grad_norm: 1.3897 (1.4374) time: 0.6312 [2021-03-27 05:52:32 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 780/1251] eta: 0:04:59 lr: 0.000564 loss: 3.4227 (3.3196) grad_norm: 1.3897 (1.4377) time: 0.6327 [2021-03-27 05:52:38 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 790/1251] eta: 0:04:53 lr: 0.000564 loss: 3.4442 (3.3208) grad_norm: 1.4196 (1.4383) time: 0.6397 [2021-03-27 05:52:45 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 800/1251] eta: 0:04:46 lr: 0.000564 loss: 3.2770 (3.3213) grad_norm: 1.4975 (1.4401) time: 0.6438 [2021-03-27 05:52:51 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 810/1251] eta: 0:04:40 lr: 0.000564 loss: 3.4809 (3.3225) grad_norm: 1.4277 (1.4391) time: 0.6413 [2021-03-27 05:52:57 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 820/1251] eta: 0:04:34 lr: 0.000564 loss: 3.5070 (3.3243) grad_norm: 1.3788 (1.4386) time: 0.6339 [2021-03-27 05:53:04 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 830/1251] eta: 0:04:27 lr: 0.000564 loss: 3.4077 (3.3244) grad_norm: 1.4025 (1.4380) time: 0.6312 [2021-03-27 05:53:10 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 840/1251] eta: 0:04:21 lr: 0.000564 loss: 3.4077 (3.3248) grad_norm: 1.3587 (1.4371) time: 0.6282 [2021-03-27 05:53:16 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 850/1251] eta: 0:04:14 lr: 0.000564 loss: 3.6047 (3.3275) grad_norm: 1.3749 (1.4371) time: 0.6298 [2021-03-27 05:53:22 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 860/1251] eta: 0:04:08 lr: 0.000564 loss: 3.4409 (3.3269) grad_norm: 1.3749 (1.4363) time: 0.6237 [2021-03-27 05:53:29 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 870/1251] eta: 0:04:02 lr: 0.000563 loss: 3.3488 (3.3267) grad_norm: 1.3599 (1.4368) time: 0.6187 [2021-03-27 05:53:35 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 880/1251] eta: 0:03:55 lr: 0.000563 loss: 3.4618 (3.3311) grad_norm: 1.3717 (1.4386) time: 0.6273 [2021-03-27 05:53:41 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 890/1251] eta: 0:03:49 lr: 0.000563 loss: 3.6244 (3.3346) grad_norm: 1.3587 (1.4387) time: 0.6351 [2021-03-27 05:53:48 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 900/1251] eta: 0:03:42 lr: 0.000563 loss: 3.5304 (3.3324) grad_norm: 1.3833 (1.4385) time: 0.6304 [2021-03-27 05:53:54 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 910/1251] eta: 0:03:36 lr: 0.000563 loss: 3.1865 (3.3320) grad_norm: 1.4272 (1.4384) time: 0.6231 [2021-03-27 05:54:00 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 920/1251] eta: 0:03:30 lr: 0.000563 loss: 3.4053 (3.3352) grad_norm: 1.4272 (1.4381) time: 0.6285 [2021-03-27 05:54:06 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 930/1251] eta: 0:03:23 lr: 0.000563 loss: 3.4053 (3.3347) grad_norm: 1.3806 (1.4388) time: 0.6338 [2021-03-27 05:54:13 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 940/1251] eta: 0:03:17 lr: 0.000563 loss: 3.3357 (3.3353) grad_norm: 1.4247 (1.4388) time: 0.6352 [2021-03-27 05:54:19 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 950/1251] eta: 0:03:11 lr: 0.000563 loss: 3.6575 (3.3377) grad_norm: 1.3945 (1.4386) time: 0.6337 [2021-03-27 05:54:25 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 960/1251] eta: 0:03:04 lr: 0.000563 loss: 3.6090 (3.3358) grad_norm: 1.4140 (1.4393) time: 0.6258 [2021-03-27 05:54:32 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 970/1251] eta: 0:02:58 lr: 0.000563 loss: 3.1278 (3.3347) grad_norm: 1.4237 (1.4402) time: 0.6266 [2021-03-27 05:54:38 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 980/1251] eta: 0:02:52 lr: 0.000563 loss: 3.3454 (3.3354) grad_norm: 1.4230 (1.4401) time: 0.6319 [2021-03-27 05:54:44 swin_base_patch4_window7_224] INFO: Epoch: [138] [ 990/1251] eta: 0:02:45 lr: 0.000563 loss: 3.4282 (3.3361) grad_norm: 1.4230 (1.4404) time: 0.6334 [2021-03-27 05:54:51 swin_base_patch4_window7_224] INFO: Epoch: [138] [1000/1251] eta: 0:02:39 lr: 0.000563 loss: 3.5009 (3.3389) grad_norm: 1.3749 (1.4398) time: 0.6281 [2021-03-27 05:54:57 swin_base_patch4_window7_224] INFO: Epoch: [138] [1010/1251] eta: 0:02:32 lr: 0.000563 loss: 3.5005 (3.3404) grad_norm: 1.3577 (1.4404) time: 0.6311 [2021-03-27 05:55:03 swin_base_patch4_window7_224] INFO: Epoch: [138] [1020/1251] eta: 0:02:26 lr: 0.000563 loss: 3.5005 (3.3426) grad_norm: 1.4337 (1.4413) time: 0.6367 [2021-03-27 05:55:10 swin_base_patch4_window7_224] INFO: Epoch: [138] [1030/1251] eta: 0:02:20 lr: 0.000563 loss: 3.4439 (3.3433) grad_norm: 1.3866 (1.4409) time: 0.6376 [2021-03-27 05:55:16 swin_base_patch4_window7_224] INFO: Epoch: [138] [1040/1251] eta: 0:02:13 lr: 0.000563 loss: 3.3554 (3.3432) grad_norm: 1.3557 (1.4400) time: 0.6367 [2021-03-27 05:55:22 swin_base_patch4_window7_224] INFO: Epoch: [138] [1050/1251] eta: 0:02:07 lr: 0.000563 loss: 3.3148 (3.3411) grad_norm: 1.3569 (1.4399) time: 0.6334 [2021-03-27 05:55:29 swin_base_patch4_window7_224] INFO: Epoch: [138] [1060/1251] eta: 0:02:01 lr: 0.000563 loss: 3.2564 (3.3395) grad_norm: 1.3741 (1.4394) time: 0.6268 [2021-03-27 05:55:35 swin_base_patch4_window7_224] INFO: Epoch: [138] [1070/1251] eta: 0:01:54 lr: 0.000563 loss: 3.2606 (3.3406) grad_norm: 1.3945 (1.4398) time: 0.6203 [2021-03-27 05:55:41 swin_base_patch4_window7_224] INFO: Epoch: [138] [1080/1251] eta: 0:01:48 lr: 0.000563 loss: 3.5703 (3.3415) grad_norm: 1.3945 (1.4398) time: 0.6288 [2021-03-27 05:55:47 swin_base_patch4_window7_224] INFO: Epoch: [138] [1090/1251] eta: 0:01:42 lr: 0.000563 loss: 3.5593 (3.3422) grad_norm: 1.3910 (1.4399) time: 0.6349 [2021-03-27 05:55:54 swin_base_patch4_window7_224] INFO: Epoch: [138] [1100/1251] eta: 0:01:35 lr: 0.000563 loss: 3.5189 (3.3433) grad_norm: 1.4825 (1.4407) time: 0.6323 [2021-03-27 05:56:00 swin_base_patch4_window7_224] INFO: Epoch: [138] [1110/1251] eta: 0:01:29 lr: 0.000562 loss: 3.5066 (3.3438) grad_norm: 1.4193 (1.4401) time: 0.6298 [2021-03-27 05:56:06 swin_base_patch4_window7_224] INFO: Epoch: [138] [1120/1251] eta: 0:01:23 lr: 0.000562 loss: 3.4807 (3.3448) grad_norm: 1.4193 (1.4401) time: 0.6285 [2021-03-27 05:56:13 swin_base_patch4_window7_224] INFO: Epoch: [138] [1130/1251] eta: 0:01:16 lr: 0.000562 loss: 3.4807 (3.3452) grad_norm: 1.3977 (1.4397) time: 0.6261 [2021-03-27 05:56:19 swin_base_patch4_window7_224] INFO: Epoch: [138] [1140/1251] eta: 0:01:10 lr: 0.000562 loss: 3.4057 (3.3441) grad_norm: 1.4022 (1.4405) time: 0.6251 [2021-03-27 05:56:25 swin_base_patch4_window7_224] INFO: Epoch: [138] [1150/1251] eta: 0:01:04 lr: 0.000562 loss: 3.2360 (3.3447) grad_norm: 1.4022 (1.4400) time: 0.6250 [2021-03-27 05:56:31 swin_base_patch4_window7_224] INFO: Epoch: [138] [1160/1251] eta: 0:00:57 lr: 0.000562 loss: 3.1918 (3.3421) grad_norm: 1.3724 (1.4405) time: 0.6233 [2021-03-27 05:56:38 swin_base_patch4_window7_224] INFO: Epoch: [138] [1170/1251] eta: 0:00:51 lr: 0.000562 loss: 3.1997 (3.3424) grad_norm: 1.4055 (1.4407) time: 0.6256 [2021-03-27 05:56:44 swin_base_patch4_window7_224] INFO: Epoch: [138] [1180/1251] eta: 0:00:45 lr: 0.000562 loss: 3.4618 (3.3424) grad_norm: 1.4332 (1.4421) time: 0.6318 [2021-03-27 05:56:50 swin_base_patch4_window7_224] INFO: Epoch: [138] [1190/1251] eta: 0:00:38 lr: 0.000562 loss: 3.5626 (3.3414) grad_norm: 1.4144 (1.4415) time: 0.6295 [2021-03-27 05:56:56 swin_base_patch4_window7_224] INFO: Epoch: [138] [1200/1251] eta: 0:00:32 lr: 0.000562 loss: 3.2684 (3.3398) grad_norm: 1.3901 (1.4420) time: 0.6242 [2021-03-27 05:57:03 swin_base_patch4_window7_224] INFO: Epoch: [138] [1210/1251] eta: 0:00:25 lr: 0.000562 loss: 3.3045 (3.3410) grad_norm: 1.4725 (1.4422) time: 0.6257 [2021-03-27 05:57:09 swin_base_patch4_window7_224] INFO: Epoch: [138] [1220/1251] eta: 0:00:19 lr: 0.000562 loss: 3.4848 (3.3423) grad_norm: 1.4549 (1.4423) time: 0.6283 [2021-03-27 05:57:15 swin_base_patch4_window7_224] INFO: Epoch: [138] [1230/1251] eta: 0:00:13 lr: 0.000562 loss: 3.4089 (3.3418) grad_norm: 1.3919 (1.4417) time: 0.6337 [2021-03-27 05:57:22 swin_base_patch4_window7_224] INFO: Epoch: [138] [1240/1251] eta: 0:00:06 lr: 0.000562 loss: 3.3593 (3.3414) grad_norm: 1.3500 (1.4416) time: 0.6304 [2021-03-27 05:57:28 swin_base_patch4_window7_224] INFO: Epoch: [138] [1250/1251] eta: 0:00:00 lr: 0.000562 loss: 3.5231 (3.3431) grad_norm: 1.3788 (1.4418) time: 0.6222 [2021-03-27 05:57:41 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:08 loss: 0.8333 (0.8333) acc1: 82.8125 (82.8125) acc5: 93.7500 (93.7500) [2021-03-27 05:57:42 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.9405 (0.9607) acc1: 78.1250 (77.2727) acc5: 96.8750 (95.0284) [2021-03-27 05:57:44 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9444 (0.9402) acc1: 78.1250 (78.1994) acc5: 95.3125 (95.0149) [2021-03-27 05:57:47 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9587 (0.9798) acc1: 78.1250 (77.7218) acc5: 95.3125 (94.3548) [2021-03-27 05:57:49 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9326 (0.9505) acc1: 78.1250 (77.6296) acc5: 95.3125 (94.6646) [2021-03-27 05:57:50 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8135 (0.9447) acc1: 78.1250 (77.5680) acc5: 95.3125 (94.8160) [2021-03-27 05:58:01 swin_base_patch4_window7_224] INFO: * Acc@1 78.386 Acc@5 94.556 loss 0.927 [2021-03-27 05:58:01 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.4% [2021-03-27 05:58:01 swin_base_patch4_window7_224] INFO: Max accuracy: 78.45% [2021-03-27 05:58:05 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 0/1251] eta: 1:31:44 lr: 0.000562 loss: 2.5453 (2.5453) grad_norm: 1.3955 (1.3955) time: 4.3999 [2021-03-27 05:58:12 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 10/1251] eta: 0:20:19 lr: 0.000562 loss: 2.9348 (3.0584) grad_norm: 1.3819 (1.3909) time: 0.9826 [2021-03-27 05:58:18 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 20/1251] eta: 0:16:48 lr: 0.000562 loss: 3.4051 (3.2977) grad_norm: 1.3351 (1.3834) time: 0.6406 [2021-03-27 05:58:24 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 30/1251] eta: 0:15:30 lr: 0.000562 loss: 3.4358 (3.2650) grad_norm: 1.3522 (1.3901) time: 0.6413 [2021-03-27 05:58:31 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 40/1251] eta: 0:14:44 lr: 0.000562 loss: 3.3929 (3.2846) grad_norm: 1.3948 (1.3896) time: 0.6363 [2021-03-27 05:58:37 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 50/1251] eta: 0:14:12 lr: 0.000562 loss: 3.0344 (3.2496) grad_norm: 1.3856 (1.3956) time: 0.6273 [2021-03-27 05:58:43 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 60/1251] eta: 0:13:49 lr: 0.000562 loss: 3.3499 (3.2972) grad_norm: 1.3461 (1.3854) time: 0.6268 [2021-03-27 05:58:50 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 70/1251] eta: 0:13:32 lr: 0.000562 loss: 3.3499 (3.2502) grad_norm: 1.3313 (1.3843) time: 0.6318 [2021-03-27 05:58:56 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 80/1251] eta: 0:13:15 lr: 0.000562 loss: 3.3460 (3.2680) grad_norm: 1.3546 (1.3981) time: 0.6274 [2021-03-27 05:59:02 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 90/1251] eta: 0:13:02 lr: 0.000562 loss: 3.4522 (3.2708) grad_norm: 1.3546 (1.3941) time: 0.6240 [2021-03-27 05:59:08 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 100/1251] eta: 0:12:50 lr: 0.000561 loss: 3.3476 (3.2755) grad_norm: 1.3686 (1.3990) time: 0.6292 [2021-03-27 05:59:15 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 110/1251] eta: 0:12:39 lr: 0.000561 loss: 3.3597 (3.2716) grad_norm: 1.3978 (1.4029) time: 0.6309 [2021-03-27 05:59:21 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 120/1251] eta: 0:12:29 lr: 0.000561 loss: 3.5099 (3.2917) grad_norm: 1.4714 (1.4134) time: 0.6310 [2021-03-27 05:59:27 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 130/1251] eta: 0:12:19 lr: 0.000561 loss: 3.4875 (3.3067) grad_norm: 1.4327 (1.4102) time: 0.6277 [2021-03-27 05:59:34 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 140/1251] eta: 0:12:10 lr: 0.000561 loss: 3.4456 (3.3099) grad_norm: 1.4193 (1.4188) time: 0.6266 [2021-03-27 05:59:40 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 150/1251] eta: 0:12:01 lr: 0.000561 loss: 3.4103 (3.3216) grad_norm: 1.5118 (1.4293) time: 0.6262 [2021-03-27 05:59:46 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 160/1251] eta: 0:11:53 lr: 0.000561 loss: 3.6173 (3.3258) grad_norm: 1.4142 (1.4273) time: 0.6251 [2021-03-27 05:59:52 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 170/1251] eta: 0:11:45 lr: 0.000561 loss: 3.4610 (3.3260) grad_norm: 1.3593 (1.4263) time: 0.6321 [2021-03-27 05:59:59 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 180/1251] eta: 0:11:37 lr: 0.000561 loss: 3.3331 (3.3161) grad_norm: 1.3593 (1.4268) time: 0.6310 [2021-03-27 06:00:05 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 190/1251] eta: 0:11:29 lr: 0.000561 loss: 3.2011 (3.3152) grad_norm: 1.5049 (1.4349) time: 0.6285 [2021-03-27 06:00:11 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 200/1251] eta: 0:11:22 lr: 0.000561 loss: 3.2011 (3.3191) grad_norm: 1.5699 (1.4449) time: 0.6323 [2021-03-27 06:00:18 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 210/1251] eta: 0:11:14 lr: 0.000561 loss: 3.4498 (3.3255) grad_norm: 1.4260 (1.4408) time: 0.6283 [2021-03-27 06:00:24 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 220/1251] eta: 0:11:07 lr: 0.000561 loss: 3.4498 (3.3190) grad_norm: 1.3700 (1.4408) time: 0.6303 [2021-03-27 06:00:30 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 230/1251] eta: 0:11:00 lr: 0.000561 loss: 3.3711 (3.3212) grad_norm: 1.4622 (1.4441) time: 0.6341 [2021-03-27 06:00:37 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 240/1251] eta: 0:10:53 lr: 0.000561 loss: 3.4937 (3.3218) grad_norm: 1.4634 (1.4465) time: 0.6312 [2021-03-27 06:00:43 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 250/1251] eta: 0:10:46 lr: 0.000561 loss: 3.3958 (3.3265) grad_norm: 1.4166 (1.4422) time: 0.6331 [2021-03-27 06:00:49 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 260/1251] eta: 0:10:39 lr: 0.000561 loss: 3.3059 (3.3247) grad_norm: 1.4083 (1.4420) time: 0.6348 [2021-03-27 06:00:56 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 270/1251] eta: 0:10:32 lr: 0.000561 loss: 3.3452 (3.3249) grad_norm: 1.4065 (1.4392) time: 0.6309 [2021-03-27 06:01:02 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 280/1251] eta: 0:10:25 lr: 0.000561 loss: 3.3988 (3.3220) grad_norm: 1.3460 (1.4377) time: 0.6270 [2021-03-27 06:01:08 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 290/1251] eta: 0:10:18 lr: 0.000561 loss: 3.4065 (3.3174) grad_norm: 1.4170 (1.4395) time: 0.6248 [2021-03-27 06:01:14 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 300/1251] eta: 0:10:11 lr: 0.000561 loss: 3.4065 (3.3238) grad_norm: 1.4601 (1.4382) time: 0.6281 [2021-03-27 06:01:21 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 310/1251] eta: 0:10:04 lr: 0.000561 loss: 3.4968 (3.3249) grad_norm: 1.3442 (1.4345) time: 0.6327 [2021-03-27 06:01:27 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 320/1251] eta: 0:09:57 lr: 0.000561 loss: 3.5361 (3.3310) grad_norm: 1.3644 (1.4373) time: 0.6293 [2021-03-27 06:01:33 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 330/1251] eta: 0:09:51 lr: 0.000561 loss: 3.4726 (3.3266) grad_norm: 1.3906 (1.4345) time: 0.6307 [2021-03-27 06:01:40 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 340/1251] eta: 0:09:44 lr: 0.000560 loss: 3.3554 (3.3208) grad_norm: 1.3614 (1.4348) time: 0.6276 [2021-03-27 06:01:46 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 350/1251] eta: 0:09:37 lr: 0.000560 loss: 3.1254 (3.3123) grad_norm: 1.4169 (1.4341) time: 0.6279 [2021-03-27 06:01:52 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 360/1251] eta: 0:09:30 lr: 0.000560 loss: 3.3661 (3.3152) grad_norm: 1.3858 (1.4319) time: 0.6321 [2021-03-27 06:01:58 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 370/1251] eta: 0:09:24 lr: 0.000560 loss: 3.5510 (3.3212) grad_norm: 1.3964 (1.4332) time: 0.6269 [2021-03-27 06:02:05 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 380/1251] eta: 0:09:17 lr: 0.000560 loss: 3.7681 (3.3292) grad_norm: 1.4491 (1.4343) time: 0.6275 [2021-03-27 06:02:11 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 390/1251] eta: 0:09:11 lr: 0.000560 loss: 3.5912 (3.3265) grad_norm: 1.4086 (1.4331) time: 0.6345 [2021-03-27 06:02:17 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 400/1251] eta: 0:09:04 lr: 0.000560 loss: 3.4707 (3.3298) grad_norm: 1.3891 (1.4332) time: 0.6311 [2021-03-27 06:02:24 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 410/1251] eta: 0:08:57 lr: 0.000560 loss: 3.5289 (3.3316) grad_norm: 1.4543 (1.4363) time: 0.6234 [2021-03-27 06:02:30 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 420/1251] eta: 0:08:51 lr: 0.000560 loss: 3.4700 (3.3318) grad_norm: 1.5273 (1.4406) time: 0.6263 [2021-03-27 06:02:36 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 430/1251] eta: 0:08:44 lr: 0.000560 loss: 3.4700 (3.3368) grad_norm: 1.4334 (1.4390) time: 0.6259 [2021-03-27 06:02:42 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 440/1251] eta: 0:08:37 lr: 0.000560 loss: 3.5327 (3.3379) grad_norm: 1.3676 (1.4383) time: 0.6234 [2021-03-27 06:02:49 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 450/1251] eta: 0:08:31 lr: 0.000560 loss: 3.3102 (3.3352) grad_norm: 1.4530 (1.4379) time: 0.6241 [2021-03-27 06:02:55 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 460/1251] eta: 0:08:24 lr: 0.000560 loss: 3.2292 (3.3348) grad_norm: 1.4339 (1.4385) time: 0.6259 [2021-03-27 06:03:01 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 470/1251] eta: 0:08:18 lr: 0.000560 loss: 3.2292 (3.3322) grad_norm: 1.3666 (1.4367) time: 0.6316 [2021-03-27 06:03:08 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 480/1251] eta: 0:08:11 lr: 0.000560 loss: 3.3942 (3.3340) grad_norm: 1.3194 (1.4353) time: 0.6310 [2021-03-27 06:03:14 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 490/1251] eta: 0:08:05 lr: 0.000560 loss: 3.3127 (3.3326) grad_norm: 1.4597 (1.4355) time: 0.6278 [2021-03-27 06:03:20 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 500/1251] eta: 0:07:58 lr: 0.000560 loss: 3.2901 (3.3336) grad_norm: 1.3777 (1.4364) time: 0.6324 [2021-03-27 06:03:26 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 510/1251] eta: 0:07:52 lr: 0.000560 loss: 3.1527 (3.3294) grad_norm: 1.3885 (1.4366) time: 0.6317 [2021-03-27 06:03:33 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 520/1251] eta: 0:07:45 lr: 0.000560 loss: 3.3154 (3.3307) grad_norm: 1.4389 (1.4391) time: 0.6358 [2021-03-27 06:03:39 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 530/1251] eta: 0:07:39 lr: 0.000560 loss: 3.4693 (3.3321) grad_norm: 1.4542 (1.4391) time: 0.6349 [2021-03-27 06:03:46 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 540/1251] eta: 0:07:32 lr: 0.000560 loss: 3.6013 (3.3345) grad_norm: 1.4233 (1.4387) time: 0.6332 [2021-03-27 06:03:52 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 550/1251] eta: 0:07:26 lr: 0.000560 loss: 3.5496 (3.3331) grad_norm: 1.4233 (1.4399) time: 0.6438 [2021-03-27 06:03:59 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 560/1251] eta: 0:07:20 lr: 0.000560 loss: 3.2754 (3.3354) grad_norm: 1.3755 (1.4379) time: 0.6584 [2021-03-27 06:04:05 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 570/1251] eta: 0:07:14 lr: 0.000560 loss: 3.3240 (3.3335) grad_norm: 1.3420 (1.4371) time: 0.6568 [2021-03-27 06:04:12 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 580/1251] eta: 0:07:08 lr: 0.000560 loss: 3.3240 (3.3352) grad_norm: 1.3589 (1.4373) time: 0.6421 [2021-03-27 06:04:18 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 590/1251] eta: 0:07:01 lr: 0.000559 loss: 3.4762 (3.3357) grad_norm: 1.3589 (1.4365) time: 0.6310 [2021-03-27 06:04:24 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 600/1251] eta: 0:06:55 lr: 0.000559 loss: 3.5332 (3.3377) grad_norm: 1.3749 (1.4362) time: 0.6275 [2021-03-27 06:04:30 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 610/1251] eta: 0:06:48 lr: 0.000559 loss: 3.5736 (3.3394) grad_norm: 1.3469 (1.4354) time: 0.6284 [2021-03-27 06:04:37 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 620/1251] eta: 0:06:42 lr: 0.000559 loss: 3.5736 (3.3410) grad_norm: 1.3141 (1.4347) time: 0.6246 [2021-03-27 06:04:43 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 630/1251] eta: 0:06:35 lr: 0.000559 loss: 3.3085 (3.3378) grad_norm: 1.4169 (1.4357) time: 0.6235 [2021-03-27 06:04:49 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 640/1251] eta: 0:06:29 lr: 0.000559 loss: 3.3754 (3.3392) grad_norm: 1.4169 (1.4350) time: 0.6254 [2021-03-27 06:04:55 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 650/1251] eta: 0:06:22 lr: 0.000559 loss: 3.4832 (3.3399) grad_norm: 1.3502 (1.4349) time: 0.6271 [2021-03-27 06:05:02 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 660/1251] eta: 0:06:16 lr: 0.000559 loss: 3.4874 (3.3410) grad_norm: 1.4011 (1.4376) time: 0.6266 [2021-03-27 06:05:08 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 670/1251] eta: 0:06:09 lr: 0.000559 loss: 3.3811 (3.3407) grad_norm: 1.3999 (1.4370) time: 0.6306 [2021-03-27 06:05:14 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 680/1251] eta: 0:06:03 lr: 0.000559 loss: 3.2384 (3.3421) grad_norm: 1.3706 (1.4386) time: 0.6295 [2021-03-27 06:05:21 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 690/1251] eta: 0:05:56 lr: 0.000559 loss: 3.2384 (3.3393) grad_norm: 1.4523 (1.4378) time: 0.6267 [2021-03-27 06:05:27 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 700/1251] eta: 0:05:50 lr: 0.000559 loss: 3.4784 (3.3425) grad_norm: 1.4256 (1.4397) time: 0.6262 [2021-03-27 06:05:33 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 710/1251] eta: 0:05:44 lr: 0.000559 loss: 3.4402 (3.3407) grad_norm: 1.4537 (1.4400) time: 0.6253 [2021-03-27 06:05:39 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 720/1251] eta: 0:05:37 lr: 0.000559 loss: 3.2768 (3.3364) grad_norm: 1.4537 (1.4416) time: 0.6276 [2021-03-27 06:05:46 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 730/1251] eta: 0:05:31 lr: 0.000559 loss: 3.3543 (3.3395) grad_norm: 1.4623 (1.4434) time: 0.6315 [2021-03-27 06:05:52 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 740/1251] eta: 0:05:24 lr: 0.000559 loss: 3.4150 (3.3355) grad_norm: 1.4559 (1.4425) time: 0.6391 [2021-03-27 06:05:59 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 750/1251] eta: 0:05:18 lr: 0.000559 loss: 3.3152 (3.3361) grad_norm: 1.4101 (1.4431) time: 0.6508 [2021-03-27 06:06:05 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 760/1251] eta: 0:05:12 lr: 0.000559 loss: 3.4152 (3.3334) grad_norm: 1.3921 (1.4426) time: 0.6533 [2021-03-27 06:06:12 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 770/1251] eta: 0:05:06 lr: 0.000559 loss: 3.4681 (3.3347) grad_norm: 1.3630 (1.4420) time: 0.6407 [2021-03-27 06:06:18 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 780/1251] eta: 0:04:59 lr: 0.000559 loss: 3.5080 (3.3355) grad_norm: 1.4110 (1.4429) time: 0.6325 [2021-03-27 06:06:24 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 790/1251] eta: 0:04:53 lr: 0.000559 loss: 3.2355 (3.3305) grad_norm: 1.4833 (1.4435) time: 0.6297 [2021-03-27 06:06:31 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 800/1251] eta: 0:04:46 lr: 0.000559 loss: 3.2249 (3.3321) grad_norm: 1.4213 (1.4424) time: 0.6336 [2021-03-27 06:06:37 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 810/1251] eta: 0:04:40 lr: 0.000559 loss: 3.5491 (3.3340) grad_norm: 1.3610 (1.4420) time: 0.6325 [2021-03-27 06:06:43 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 820/1251] eta: 0:04:34 lr: 0.000559 loss: 3.4407 (3.3324) grad_norm: 1.3881 (1.4413) time: 0.6260 [2021-03-27 06:06:49 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 830/1251] eta: 0:04:27 lr: 0.000558 loss: 3.2349 (3.3307) grad_norm: 1.4015 (1.4416) time: 0.6250 [2021-03-27 06:06:56 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 840/1251] eta: 0:04:21 lr: 0.000558 loss: 3.1857 (3.3284) grad_norm: 1.4506 (1.4419) time: 0.6229 [2021-03-27 06:07:02 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 850/1251] eta: 0:04:14 lr: 0.000558 loss: 3.1857 (3.3296) grad_norm: 1.4742 (1.4427) time: 0.6281 [2021-03-27 06:07:08 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 860/1251] eta: 0:04:08 lr: 0.000558 loss: 3.1840 (3.3271) grad_norm: 1.4331 (1.4425) time: 0.6295 [2021-03-27 06:07:14 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 870/1251] eta: 0:04:02 lr: 0.000558 loss: 3.5289 (3.3292) grad_norm: 1.4331 (1.4436) time: 0.6298 [2021-03-27 06:07:21 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 880/1251] eta: 0:03:55 lr: 0.000558 loss: 3.5412 (3.3294) grad_norm: 1.4299 (1.4441) time: 0.6327 [2021-03-27 06:07:27 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 890/1251] eta: 0:03:49 lr: 0.000558 loss: 3.4499 (3.3298) grad_norm: 1.4108 (1.4443) time: 0.6339 [2021-03-27 06:07:33 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 900/1251] eta: 0:03:43 lr: 0.000558 loss: 3.5136 (3.3310) grad_norm: 1.4619 (1.4447) time: 0.6330 [2021-03-27 06:07:40 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 910/1251] eta: 0:03:36 lr: 0.000558 loss: 3.5320 (3.3322) grad_norm: 1.4786 (1.4447) time: 0.6259 [2021-03-27 06:07:46 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 920/1251] eta: 0:03:30 lr: 0.000558 loss: 3.2297 (3.3301) grad_norm: 1.4786 (1.4455) time: 0.6236 [2021-03-27 06:07:52 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 930/1251] eta: 0:03:23 lr: 0.000558 loss: 3.2297 (3.3288) grad_norm: 1.4333 (1.4459) time: 0.6232 [2021-03-27 06:07:58 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 940/1251] eta: 0:03:17 lr: 0.000558 loss: 3.3194 (3.3263) grad_norm: 1.4033 (1.4459) time: 0.6220 [2021-03-27 06:08:05 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 950/1251] eta: 0:03:11 lr: 0.000558 loss: 3.4429 (3.3281) grad_norm: 1.4033 (1.4458) time: 0.6325 [2021-03-27 06:08:11 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 960/1251] eta: 0:03:04 lr: 0.000558 loss: 3.5462 (3.3296) grad_norm: 1.3494 (1.4449) time: 0.6355 [2021-03-27 06:08:17 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 970/1251] eta: 0:02:58 lr: 0.000558 loss: 3.2594 (3.3266) grad_norm: 1.3564 (1.4443) time: 0.6275 [2021-03-27 06:08:24 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 980/1251] eta: 0:02:52 lr: 0.000558 loss: 3.2852 (3.3285) grad_norm: 1.3910 (1.4440) time: 0.6307 [2021-03-27 06:08:30 swin_base_patch4_window7_224] INFO: Epoch: [139] [ 990/1251] eta: 0:02:45 lr: 0.000558 loss: 3.4554 (3.3263) grad_norm: 1.3676 (1.4433) time: 0.6304 [2021-03-27 06:08:36 swin_base_patch4_window7_224] INFO: Epoch: [139] [1000/1251] eta: 0:02:39 lr: 0.000558 loss: 3.4450 (3.3282) grad_norm: 1.3479 (1.4429) time: 0.6240 [2021-03-27 06:08:42 swin_base_patch4_window7_224] INFO: Epoch: [139] [1010/1251] eta: 0:02:32 lr: 0.000558 loss: 3.3693 (3.3271) grad_norm: 1.4142 (1.4435) time: 0.6241 [2021-03-27 06:08:49 swin_base_patch4_window7_224] INFO: Epoch: [139] [1020/1251] eta: 0:02:26 lr: 0.000558 loss: 3.2803 (3.3268) grad_norm: 1.3627 (1.4421) time: 0.6232 [2021-03-27 06:08:55 swin_base_patch4_window7_224] INFO: Epoch: [139] [1030/1251] eta: 0:02:20 lr: 0.000558 loss: 3.3509 (3.3285) grad_norm: 1.3051 (1.4416) time: 0.6242 [2021-03-27 06:09:01 swin_base_patch4_window7_224] INFO: Epoch: [139] [1040/1251] eta: 0:02:13 lr: 0.000558 loss: 3.4562 (3.3291) grad_norm: 1.3933 (1.4423) time: 0.6288 [2021-03-27 06:09:07 swin_base_patch4_window7_224] INFO: Epoch: [139] [1050/1251] eta: 0:02:07 lr: 0.000558 loss: 3.3839 (3.3247) grad_norm: 1.3874 (1.4416) time: 0.6281 [2021-03-27 06:09:14 swin_base_patch4_window7_224] INFO: Epoch: [139] [1060/1251] eta: 0:02:01 lr: 0.000558 loss: 3.0935 (3.3251) grad_norm: 1.3680 (1.4410) time: 0.6309 [2021-03-27 06:09:20 swin_base_patch4_window7_224] INFO: Epoch: [139] [1070/1251] eta: 0:01:54 lr: 0.000557 loss: 3.3474 (3.3247) grad_norm: 1.3458 (1.4405) time: 0.6352 [2021-03-27 06:09:27 swin_base_patch4_window7_224] INFO: Epoch: [139] [1080/1251] eta: 0:01:48 lr: 0.000557 loss: 3.4951 (3.3276) grad_norm: 1.4023 (1.4404) time: 0.6365 [2021-03-27 06:09:33 swin_base_patch4_window7_224] INFO: Epoch: [139] [1090/1251] eta: 0:01:42 lr: 0.000557 loss: 3.4978 (3.3266) grad_norm: 1.5089 (1.4420) time: 0.6314 [2021-03-27 06:09:39 swin_base_patch4_window7_224] INFO: Epoch: [139] [1100/1251] eta: 0:01:35 lr: 0.000557 loss: 3.3321 (3.3267) grad_norm: 1.4793 (1.4420) time: 0.6249 [2021-03-27 06:09:45 swin_base_patch4_window7_224] INFO: Epoch: [139] [1110/1251] eta: 0:01:29 lr: 0.000557 loss: 3.3321 (3.3251) grad_norm: 1.3784 (1.4414) time: 0.6310 [2021-03-27 06:09:52 swin_base_patch4_window7_224] INFO: Epoch: [139] [1120/1251] eta: 0:01:23 lr: 0.000557 loss: 3.3082 (3.3248) grad_norm: 1.3784 (1.4420) time: 0.6318 [2021-03-27 06:09:58 swin_base_patch4_window7_224] INFO: Epoch: [139] [1130/1251] eta: 0:01:16 lr: 0.000557 loss: 3.3153 (3.3237) grad_norm: 1.3909 (1.4417) time: 0.6291 [2021-03-27 06:10:04 swin_base_patch4_window7_224] INFO: Epoch: [139] [1140/1251] eta: 0:01:10 lr: 0.000557 loss: 3.1262 (3.3221) grad_norm: 1.3596 (1.4421) time: 0.6310 [2021-03-27 06:10:11 swin_base_patch4_window7_224] INFO: Epoch: [139] [1150/1251] eta: 0:01:04 lr: 0.000557 loss: 3.3892 (3.3255) grad_norm: 1.4354 (1.4421) time: 0.6279 [2021-03-27 06:10:17 swin_base_patch4_window7_224] INFO: Epoch: [139] [1160/1251] eta: 0:00:57 lr: 0.000557 loss: 3.6850 (3.3266) grad_norm: 1.4799 (1.4429) time: 0.6258 [2021-03-27 06:10:23 swin_base_patch4_window7_224] INFO: Epoch: [139] [1170/1251] eta: 0:00:51 lr: 0.000557 loss: 3.3623 (3.3257) grad_norm: 1.4645 (1.4429) time: 0.6301 [2021-03-27 06:10:29 swin_base_patch4_window7_224] INFO: Epoch: [139] [1180/1251] eta: 0:00:44 lr: 0.000557 loss: 3.3647 (3.3271) grad_norm: 1.4138 (1.4430) time: 0.6274 [2021-03-27 06:10:36 swin_base_patch4_window7_224] INFO: Epoch: [139] [1190/1251] eta: 0:00:38 lr: 0.000557 loss: 3.4171 (3.3247) grad_norm: 1.4838 (1.4435) time: 0.6269 [2021-03-27 06:10:42 swin_base_patch4_window7_224] INFO: Epoch: [139] [1200/1251] eta: 0:00:32 lr: 0.000557 loss: 3.3863 (3.3260) grad_norm: 1.4344 (1.4430) time: 0.6332 [2021-03-27 06:10:48 swin_base_patch4_window7_224] INFO: Epoch: [139] [1210/1251] eta: 0:00:25 lr: 0.000557 loss: 3.5934 (3.3278) grad_norm: 1.4030 (1.4436) time: 0.6267 [2021-03-27 06:10:55 swin_base_patch4_window7_224] INFO: Epoch: [139] [1220/1251] eta: 0:00:19 lr: 0.000557 loss: 3.4536 (3.3278) grad_norm: 1.3744 (1.4435) time: 0.6241 [2021-03-27 06:11:01 swin_base_patch4_window7_224] INFO: Epoch: [139] [1230/1251] eta: 0:00:13 lr: 0.000557 loss: 3.4536 (3.3293) grad_norm: 1.3272 (1.4425) time: 0.6255 [2021-03-27 06:11:07 swin_base_patch4_window7_224] INFO: Epoch: [139] [1240/1251] eta: 0:00:06 lr: 0.000557 loss: 3.4775 (3.3298) grad_norm: 1.3570 (1.4421) time: 0.6272 [2021-03-27 06:11:13 swin_base_patch4_window7_224] INFO: Epoch: [139] [1250/1251] eta: 0:00:00 lr: 0.000557 loss: 3.3617 (3.3297) grad_norm: 1.4187 (1.4424) time: 0.6294 [2021-03-27 06:11:24 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:27 loss: 1.0472 (1.0472) acc1: 73.4375 (73.4375) acc5: 96.8750 (96.8750) [2021-03-27 06:11:28 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.9152 (0.9302) acc1: 75.0000 (75.7102) acc5: 96.8750 (96.1648) [2021-03-27 06:11:30 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9152 (0.9547) acc1: 78.1250 (77.1577) acc5: 95.3125 (95.3869) [2021-03-27 06:11:32 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8853 (0.9416) acc1: 78.1250 (77.6714) acc5: 93.7500 (95.0605) [2021-03-27 06:11:35 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9213 (0.9571) acc1: 76.5625 (77.5152) acc5: 93.7500 (94.7790) [2021-03-27 06:11:36 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9213 (0.9479) acc1: 78.1250 (77.8560) acc5: 95.3125 (94.8160) [2021-03-27 06:11:44 swin_base_patch4_window7_224] INFO: * Acc@1 78.414 Acc@5 94.626 loss 0.931 [2021-03-27 06:11:44 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.4% [2021-03-27 06:11:44 swin_base_patch4_window7_224] INFO: Max accuracy: 78.45% [2021-03-27 06:11:48 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 0/1251] eta: 1:32:04 lr: 0.000557 loss: 3.8001 (3.8001) grad_norm: 1.3043 (1.3043) time: 4.4159 [2021-03-27 06:11:55 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 10/1251] eta: 0:20:20 lr: 0.000557 loss: 3.5232 (3.4726) grad_norm: 1.3153 (1.3631) time: 0.9831 [2021-03-27 06:12:01 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 20/1251] eta: 0:16:41 lr: 0.000557 loss: 3.4420 (3.3479) grad_norm: 1.3153 (1.3822) time: 0.6336 [2021-03-27 06:12:07 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 30/1251] eta: 0:15:22 lr: 0.000557 loss: 3.3869 (3.3702) grad_norm: 1.3866 (1.3811) time: 0.6300 [2021-03-27 06:12:14 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 40/1251] eta: 0:14:38 lr: 0.000557 loss: 3.3582 (3.3451) grad_norm: 1.3979 (1.4059) time: 0.6335 [2021-03-27 06:12:20 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 50/1251] eta: 0:14:08 lr: 0.000557 loss: 3.3582 (3.3313) grad_norm: 1.3780 (1.3921) time: 0.6298 [2021-03-27 06:12:26 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 60/1251] eta: 0:13:46 lr: 0.000556 loss: 3.4792 (3.3683) grad_norm: 1.3194 (inf) time: 0.6280 [2021-03-27 06:12:32 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 70/1251] eta: 0:13:28 lr: 0.000556 loss: 3.5344 (3.3528) grad_norm: 1.4194 (inf) time: 0.6300 [2021-03-27 06:12:39 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 80/1251] eta: 0:13:14 lr: 0.000556 loss: 3.2623 (3.3320) grad_norm: 1.4194 (inf) time: 0.6326 [2021-03-27 06:12:45 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 90/1251] eta: 0:13:01 lr: 0.000556 loss: 3.4091 (3.3342) grad_norm: 1.4185 (inf) time: 0.6318 [2021-03-27 06:12:51 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 100/1251] eta: 0:12:49 lr: 0.000556 loss: 3.5668 (3.3465) grad_norm: 1.4442 (inf) time: 0.6285 [2021-03-27 06:12:58 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 110/1251] eta: 0:12:38 lr: 0.000556 loss: 3.6378 (3.3712) grad_norm: 1.4374 (inf) time: 0.6262 [2021-03-27 06:13:04 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 120/1251] eta: 0:12:28 lr: 0.000556 loss: 3.6245 (3.3637) grad_norm: 1.3994 (inf) time: 0.6267 [2021-03-27 06:13:10 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 130/1251] eta: 0:12:19 lr: 0.000556 loss: 3.1427 (3.3403) grad_norm: 1.4316 (inf) time: 0.6308 [2021-03-27 06:13:16 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 140/1251] eta: 0:12:10 lr: 0.000556 loss: 3.1427 (3.3357) grad_norm: 1.4206 (inf) time: 0.6328 [2021-03-27 06:13:23 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 150/1251] eta: 0:12:02 lr: 0.000556 loss: 3.3255 (3.3138) grad_norm: 1.3986 (inf) time: 0.6355 [2021-03-27 06:13:29 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 160/1251] eta: 0:11:53 lr: 0.000556 loss: 3.3255 (3.3190) grad_norm: 1.3467 (inf) time: 0.6308 [2021-03-27 06:13:35 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 170/1251] eta: 0:11:46 lr: 0.000556 loss: 3.5910 (3.3243) grad_norm: 1.3399 (inf) time: 0.6303 [2021-03-27 06:13:42 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 180/1251] eta: 0:11:39 lr: 0.000556 loss: 3.5910 (3.3353) grad_norm: 1.4419 (inf) time: 0.6399 [2021-03-27 06:13:48 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 190/1251] eta: 0:11:31 lr: 0.000556 loss: 3.4914 (3.3205) grad_norm: 1.4735 (inf) time: 0.6407 [2021-03-27 06:13:55 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 200/1251] eta: 0:11:25 lr: 0.000556 loss: 3.3158 (3.3335) grad_norm: 1.3812 (inf) time: 0.6442 [2021-03-27 06:14:01 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 210/1251] eta: 0:11:17 lr: 0.000556 loss: 3.4439 (3.3321) grad_norm: 1.3719 (inf) time: 0.6396 [2021-03-27 06:14:07 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 220/1251] eta: 0:11:09 lr: 0.000556 loss: 3.4621 (3.3435) grad_norm: 1.4040 (inf) time: 0.6276 [2021-03-27 06:14:14 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 230/1251] eta: 0:11:02 lr: 0.000556 loss: 3.4621 (3.3377) grad_norm: 1.4506 (inf) time: 0.6278 [2021-03-27 06:14:20 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 240/1251] eta: 0:10:56 lr: 0.000556 loss: 3.2218 (3.3240) grad_norm: 1.4507 (inf) time: 0.6416 [2021-03-27 06:14:27 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 250/1251] eta: 0:10:49 lr: 0.000556 loss: 3.2453 (3.3241) grad_norm: 1.4381 (inf) time: 0.6445 [2021-03-27 06:14:33 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 260/1251] eta: 0:10:41 lr: 0.000556 loss: 3.3301 (3.3252) grad_norm: 1.4381 (inf) time: 0.6261 [2021-03-27 06:14:39 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 270/1251] eta: 0:10:34 lr: 0.000556 loss: 3.4019 (3.3303) grad_norm: 1.4293 (inf) time: 0.6250 [2021-03-27 06:14:45 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 280/1251] eta: 0:10:27 lr: 0.000556 loss: 3.4058 (3.3322) grad_norm: 1.3868 (inf) time: 0.6308 [2021-03-27 06:14:52 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 290/1251] eta: 0:10:20 lr: 0.000556 loss: 3.3540 (3.3307) grad_norm: 1.3852 (inf) time: 0.6290 [2021-03-27 06:14:58 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 300/1251] eta: 0:10:13 lr: 0.000556 loss: 3.2773 (3.3289) grad_norm: 1.4789 (inf) time: 0.6245 [2021-03-27 06:15:04 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 310/1251] eta: 0:10:06 lr: 0.000555 loss: 3.3370 (3.3281) grad_norm: 1.4599 (inf) time: 0.6325 [2021-03-27 06:15:11 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 320/1251] eta: 0:09:59 lr: 0.000555 loss: 3.5850 (3.3364) grad_norm: 1.3709 (inf) time: 0.6388 [2021-03-27 06:15:17 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 330/1251] eta: 0:09:53 lr: 0.000555 loss: 3.6275 (3.3322) grad_norm: 1.3895 (inf) time: 0.6369 [2021-03-27 06:15:23 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 340/1251] eta: 0:09:46 lr: 0.000555 loss: 3.2920 (3.3220) grad_norm: 1.3705 (inf) time: 0.6385 [2021-03-27 06:15:30 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 350/1251] eta: 0:09:40 lr: 0.000555 loss: 3.3030 (3.3285) grad_norm: 1.3484 (inf) time: 0.6381 [2021-03-27 06:15:36 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 360/1251] eta: 0:09:33 lr: 0.000555 loss: 3.7534 (3.3315) grad_norm: 1.4042 (inf) time: 0.6351 [2021-03-27 06:15:42 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 370/1251] eta: 0:09:26 lr: 0.000555 loss: 3.6717 (3.3329) grad_norm: 1.4340 (inf) time: 0.6295 [2021-03-27 06:15:49 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 380/1251] eta: 0:09:19 lr: 0.000555 loss: 3.4972 (3.3357) grad_norm: 1.4165 (inf) time: 0.6291 [2021-03-27 06:15:55 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 390/1251] eta: 0:09:12 lr: 0.000555 loss: 3.4972 (3.3401) grad_norm: 1.4165 (inf) time: 0.6275 [2021-03-27 06:16:01 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 400/1251] eta: 0:09:06 lr: 0.000555 loss: 3.4263 (3.3413) grad_norm: 1.4771 (inf) time: 0.6309 [2021-03-27 06:16:08 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 410/1251] eta: 0:09:00 lr: 0.000555 loss: 3.4168 (3.3428) grad_norm: 1.5461 (inf) time: 0.6390 [2021-03-27 06:16:14 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 420/1251] eta: 0:08:53 lr: 0.000555 loss: 3.5424 (3.3437) grad_norm: 1.5272 (inf) time: 0.6317 [2021-03-27 06:16:20 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 430/1251] eta: 0:08:46 lr: 0.000555 loss: 3.5153 (3.3452) grad_norm: 1.4229 (inf) time: 0.6336 [2021-03-27 06:16:27 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 440/1251] eta: 0:08:40 lr: 0.000555 loss: 3.2367 (3.3428) grad_norm: 1.4188 (inf) time: 0.6358 [2021-03-27 06:16:33 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 450/1251] eta: 0:08:33 lr: 0.000555 loss: 3.2367 (3.3416) grad_norm: 1.4761 (inf) time: 0.6271 [2021-03-27 06:16:39 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 460/1251] eta: 0:08:26 lr: 0.000555 loss: 3.2479 (3.3360) grad_norm: 1.4624 (inf) time: 0.6285 [2021-03-27 06:16:45 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 470/1251] eta: 0:08:20 lr: 0.000555 loss: 3.3733 (3.3368) grad_norm: 1.3726 (inf) time: 0.6274 [2021-03-27 06:16:52 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 480/1251] eta: 0:08:13 lr: 0.000555 loss: 3.5143 (3.3430) grad_norm: 1.3726 (inf) time: 0.6252 [2021-03-27 06:16:58 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 490/1251] eta: 0:08:07 lr: 0.000555 loss: 3.5143 (3.3425) grad_norm: 1.4179 (inf) time: 0.6301 [2021-03-27 06:17:04 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 500/1251] eta: 0:08:00 lr: 0.000555 loss: 3.4929 (3.3465) grad_norm: 1.4208 (inf) time: 0.6345 [2021-03-27 06:17:11 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 510/1251] eta: 0:07:53 lr: 0.000555 loss: 3.5043 (3.3477) grad_norm: 1.4394 (inf) time: 0.6290 [2021-03-27 06:17:17 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 520/1251] eta: 0:07:47 lr: 0.000555 loss: 3.3229 (3.3472) grad_norm: 1.3820 (inf) time: 0.6237 [2021-03-27 06:17:23 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 530/1251] eta: 0:07:41 lr: 0.000555 loss: 3.3981 (3.3472) grad_norm: 1.3820 (inf) time: 0.6348 [2021-03-27 06:17:30 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 540/1251] eta: 0:07:34 lr: 0.000555 loss: 3.4010 (3.3436) grad_norm: 1.4015 (inf) time: 0.6419 [2021-03-27 06:17:36 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 550/1251] eta: 0:07:28 lr: 0.000554 loss: 3.4010 (3.3462) grad_norm: 1.4369 (inf) time: 0.6448 [2021-03-27 06:17:43 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 560/1251] eta: 0:07:22 lr: 0.000554 loss: 3.2567 (3.3402) grad_norm: 1.4734 (inf) time: 0.6515 [2021-03-27 06:17:49 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 570/1251] eta: 0:07:15 lr: 0.000554 loss: 3.2707 (3.3406) grad_norm: 1.4006 (inf) time: 0.6455 [2021-03-27 06:17:55 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 580/1251] eta: 0:07:09 lr: 0.000554 loss: 3.5464 (3.3456) grad_norm: 1.3869 (inf) time: 0.6334 [2021-03-27 06:18:02 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 590/1251] eta: 0:07:02 lr: 0.000554 loss: 3.7580 (3.3493) grad_norm: 1.3857 (inf) time: 0.6328 [2021-03-27 06:18:08 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 600/1251] eta: 0:06:56 lr: 0.000554 loss: 3.5886 (3.3452) grad_norm: 1.3857 (inf) time: 0.6339 [2021-03-27 06:18:14 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 610/1251] eta: 0:06:49 lr: 0.000554 loss: 3.2591 (3.3455) grad_norm: 1.4287 (inf) time: 0.6316 [2021-03-27 06:18:21 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 620/1251] eta: 0:06:43 lr: 0.000554 loss: 3.3117 (3.3448) grad_norm: 1.4287 (inf) time: 0.6356 [2021-03-27 06:18:27 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 630/1251] eta: 0:06:36 lr: 0.000554 loss: 3.3402 (3.3453) grad_norm: 1.5798 (inf) time: 0.6367 [2021-03-27 06:18:33 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 640/1251] eta: 0:06:30 lr: 0.000554 loss: 3.5104 (3.3479) grad_norm: 1.4948 (inf) time: 0.6300 [2021-03-27 06:18:40 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 650/1251] eta: 0:06:23 lr: 0.000554 loss: 3.5104 (3.3503) grad_norm: 1.4685 (inf) time: 0.6251 [2021-03-27 06:18:46 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 660/1251] eta: 0:06:17 lr: 0.000554 loss: 3.4879 (3.3532) grad_norm: 1.5529 (inf) time: 0.6278 [2021-03-27 06:18:52 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 670/1251] eta: 0:06:11 lr: 0.000554 loss: 3.4565 (3.3529) grad_norm: 1.4446 (inf) time: 0.6299 [2021-03-27 06:18:59 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 680/1251] eta: 0:06:04 lr: 0.000554 loss: 3.4069 (3.3530) grad_norm: 1.4239 (inf) time: 0.6280 [2021-03-27 06:19:05 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 690/1251] eta: 0:05:58 lr: 0.000554 loss: 3.3976 (3.3495) grad_norm: 1.3963 (inf) time: 0.6288 [2021-03-27 06:19:11 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 700/1251] eta: 0:05:51 lr: 0.000554 loss: 3.3646 (3.3494) grad_norm: 1.3963 (inf) time: 0.6300 [2021-03-27 06:19:17 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 710/1251] eta: 0:05:45 lr: 0.000554 loss: 3.4358 (3.3517) grad_norm: 1.3666 (inf) time: 0.6236 [2021-03-27 06:19:24 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 720/1251] eta: 0:05:38 lr: 0.000554 loss: 3.3071 (3.3498) grad_norm: 1.3432 (inf) time: 0.6263 [2021-03-27 06:19:30 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 730/1251] eta: 0:05:32 lr: 0.000554 loss: 3.3939 (3.3498) grad_norm: 1.3694 (inf) time: 0.6334 [2021-03-27 06:19:37 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 740/1251] eta: 0:05:25 lr: 0.000554 loss: 3.4073 (3.3505) grad_norm: 1.4577 (inf) time: 0.6399 [2021-03-27 06:19:43 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 750/1251] eta: 0:05:19 lr: 0.000554 loss: 3.2774 (3.3475) grad_norm: 1.4334 (inf) time: 0.6515 [2021-03-27 06:19:49 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 760/1251] eta: 0:05:13 lr: 0.000554 loss: 3.3399 (3.3466) grad_norm: 1.3859 (inf) time: 0.6440 [2021-03-27 06:19:56 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 770/1251] eta: 0:05:06 lr: 0.000554 loss: 3.3399 (3.3449) grad_norm: 1.4694 (inf) time: 0.6303 [2021-03-27 06:20:02 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 780/1251] eta: 0:05:00 lr: 0.000554 loss: 3.1432 (3.3438) grad_norm: 1.4699 (inf) time: 0.6282 [2021-03-27 06:20:08 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 790/1251] eta: 0:04:54 lr: 0.000553 loss: 3.0913 (3.3388) grad_norm: 1.4146 (inf) time: 0.6332 [2021-03-27 06:20:15 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 800/1251] eta: 0:04:47 lr: 0.000553 loss: 3.3010 (3.3418) grad_norm: 1.4322 (inf) time: 0.6353 [2021-03-27 06:20:21 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 810/1251] eta: 0:04:41 lr: 0.000553 loss: 3.5227 (3.3441) grad_norm: 1.4401 (inf) time: 0.6302 [2021-03-27 06:20:27 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 820/1251] eta: 0:04:34 lr: 0.000553 loss: 3.4413 (3.3438) grad_norm: 1.3898 (inf) time: 0.6273 [2021-03-27 06:20:34 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 830/1251] eta: 0:04:28 lr: 0.000553 loss: 3.5399 (3.3470) grad_norm: 1.3347 (inf) time: 0.6291 [2021-03-27 06:20:40 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 840/1251] eta: 0:04:21 lr: 0.000553 loss: 3.4513 (3.3461) grad_norm: 1.3256 (inf) time: 0.6347 [2021-03-27 06:20:46 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 850/1251] eta: 0:04:15 lr: 0.000553 loss: 3.3868 (3.3453) grad_norm: 1.3335 (inf) time: 0.6314 [2021-03-27 06:20:53 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 860/1251] eta: 0:04:09 lr: 0.000553 loss: 3.2896 (3.3451) grad_norm: 1.3504 (inf) time: 0.6316 [2021-03-27 06:20:59 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 870/1251] eta: 0:04:02 lr: 0.000553 loss: 3.2906 (3.3437) grad_norm: 1.3818 (inf) time: 0.6349 [2021-03-27 06:21:05 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 880/1251] eta: 0:03:56 lr: 0.000553 loss: 3.5115 (3.3455) grad_norm: 1.4500 (inf) time: 0.6292 [2021-03-27 06:21:11 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 890/1251] eta: 0:03:49 lr: 0.000553 loss: 3.4695 (3.3475) grad_norm: 1.4701 (inf) time: 0.6294 [2021-03-27 06:21:18 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 900/1251] eta: 0:03:43 lr: 0.000553 loss: 3.4695 (3.3475) grad_norm: 1.4193 (inf) time: 0.6343 [2021-03-27 06:21:24 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 910/1251] eta: 0:03:37 lr: 0.000553 loss: 3.4540 (3.3476) grad_norm: 1.4172 (inf) time: 0.6293 [2021-03-27 06:21:30 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 920/1251] eta: 0:03:30 lr: 0.000553 loss: 3.2574 (3.3452) grad_norm: 1.4958 (inf) time: 0.6317 [2021-03-27 06:21:37 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 930/1251] eta: 0:03:24 lr: 0.000553 loss: 3.2574 (3.3439) grad_norm: 1.3687 (inf) time: 0.6379 [2021-03-27 06:21:43 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 940/1251] eta: 0:03:18 lr: 0.000553 loss: 3.2964 (3.3416) grad_norm: 1.3039 (inf) time: 0.6378 [2021-03-27 06:21:50 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 950/1251] eta: 0:03:11 lr: 0.000553 loss: 3.2964 (3.3427) grad_norm: 1.4301 (inf) time: 0.6335 [2021-03-27 06:21:56 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 960/1251] eta: 0:03:05 lr: 0.000553 loss: 3.4416 (3.3451) grad_norm: 1.4315 (inf) time: 0.6308 [2021-03-27 06:22:02 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 970/1251] eta: 0:02:58 lr: 0.000553 loss: 3.4013 (3.3434) grad_norm: 1.3493 (inf) time: 0.6352 [2021-03-27 06:22:09 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 980/1251] eta: 0:02:52 lr: 0.000553 loss: 3.3230 (3.3435) grad_norm: 1.4289 (inf) time: 0.6380 [2021-03-27 06:22:15 swin_base_patch4_window7_224] INFO: Epoch: [140] [ 990/1251] eta: 0:02:46 lr: 0.000553 loss: 3.3682 (3.3430) grad_norm: 1.4218 (inf) time: 0.6303 [2021-03-27 06:22:21 swin_base_patch4_window7_224] INFO: Epoch: [140] [1000/1251] eta: 0:02:39 lr: 0.000553 loss: 3.4004 (3.3431) grad_norm: 1.3886 (inf) time: 0.6276 [2021-03-27 06:22:28 swin_base_patch4_window7_224] INFO: Epoch: [140] [1010/1251] eta: 0:02:33 lr: 0.000553 loss: 3.4004 (3.3433) grad_norm: 1.4985 (inf) time: 0.6350 [2021-03-27 06:22:34 swin_base_patch4_window7_224] INFO: Epoch: [140] [1020/1251] eta: 0:02:27 lr: 0.000553 loss: 3.2568 (3.3421) grad_norm: 1.4906 (inf) time: 0.6336 [2021-03-27 06:22:40 swin_base_patch4_window7_224] INFO: Epoch: [140] [1030/1251] eta: 0:02:20 lr: 0.000552 loss: 3.2568 (3.3407) grad_norm: 1.4708 (inf) time: 0.6284 [2021-03-27 06:22:46 swin_base_patch4_window7_224] INFO: Epoch: [140] [1040/1251] eta: 0:02:14 lr: 0.000552 loss: 3.2508 (3.3396) grad_norm: 1.4549 (inf) time: 0.6242 [2021-03-27 06:22:53 swin_base_patch4_window7_224] INFO: Epoch: [140] [1050/1251] eta: 0:02:07 lr: 0.000552 loss: 3.4039 (3.3399) grad_norm: 1.4076 (inf) time: 0.6245 [2021-03-27 06:22:59 swin_base_patch4_window7_224] INFO: Epoch: [140] [1060/1251] eta: 0:02:01 lr: 0.000552 loss: 3.4047 (3.3396) grad_norm: 1.4076 (inf) time: 0.6257 [2021-03-27 06:23:05 swin_base_patch4_window7_224] INFO: Epoch: [140] [1070/1251] eta: 0:01:55 lr: 0.000552 loss: 3.5015 (3.3424) grad_norm: 1.4219 (inf) time: 0.6268 [2021-03-27 06:23:12 swin_base_patch4_window7_224] INFO: Epoch: [140] [1080/1251] eta: 0:01:48 lr: 0.000552 loss: 3.6189 (3.3420) grad_norm: 1.3867 (inf) time: 0.6337 [2021-03-27 06:23:18 swin_base_patch4_window7_224] INFO: Epoch: [140] [1090/1251] eta: 0:01:42 lr: 0.000552 loss: 3.3785 (3.3397) grad_norm: 1.4494 (inf) time: 0.6366 [2021-03-27 06:23:24 swin_base_patch4_window7_224] INFO: Epoch: [140] [1100/1251] eta: 0:01:36 lr: 0.000552 loss: 3.3618 (3.3407) grad_norm: 1.5326 (inf) time: 0.6280 [2021-03-27 06:23:30 swin_base_patch4_window7_224] INFO: Epoch: [140] [1110/1251] eta: 0:01:29 lr: 0.000552 loss: 3.5609 (3.3418) grad_norm: 1.5414 (inf) time: 0.6247 [2021-03-27 06:23:37 swin_base_patch4_window7_224] INFO: Epoch: [140] [1120/1251] eta: 0:01:23 lr: 0.000552 loss: 3.2116 (3.3404) grad_norm: 1.5009 (inf) time: 0.6272 [2021-03-27 06:23:43 swin_base_patch4_window7_224] INFO: Epoch: [140] [1130/1251] eta: 0:01:16 lr: 0.000552 loss: 3.2957 (3.3420) grad_norm: 1.4834 (inf) time: 0.6292 [2021-03-27 06:23:49 swin_base_patch4_window7_224] INFO: Epoch: [140] [1140/1251] eta: 0:01:10 lr: 0.000552 loss: 3.7660 (3.3453) grad_norm: 1.4797 (inf) time: 0.6262 [2021-03-27 06:23:55 swin_base_patch4_window7_224] INFO: Epoch: [140] [1150/1251] eta: 0:01:04 lr: 0.000552 loss: 3.7071 (3.3462) grad_norm: 1.3913 (inf) time: 0.6214 [2021-03-27 06:24:02 swin_base_patch4_window7_224] INFO: Epoch: [140] [1160/1251] eta: 0:00:57 lr: 0.000552 loss: 3.5630 (3.3478) grad_norm: 1.3497 (inf) time: 0.6272 [2021-03-27 06:24:08 swin_base_patch4_window7_224] INFO: Epoch: [140] [1170/1251] eta: 0:00:51 lr: 0.000552 loss: 3.3841 (3.3454) grad_norm: 1.3859 (inf) time: 0.6338 [2021-03-27 06:24:14 swin_base_patch4_window7_224] INFO: Epoch: [140] [1180/1251] eta: 0:00:45 lr: 0.000552 loss: 3.2470 (3.3464) grad_norm: 1.3846 (inf) time: 0.6276 [2021-03-27 06:24:21 swin_base_patch4_window7_224] INFO: Epoch: [140] [1190/1251] eta: 0:00:38 lr: 0.000552 loss: 3.4979 (3.3474) grad_norm: 1.5039 (inf) time: 0.6226 [2021-03-27 06:24:27 swin_base_patch4_window7_224] INFO: Epoch: [140] [1200/1251] eta: 0:00:32 lr: 0.000552 loss: 3.4969 (3.3494) grad_norm: 1.4801 (inf) time: 0.6268 [2021-03-27 06:24:33 swin_base_patch4_window7_224] INFO: Epoch: [140] [1210/1251] eta: 0:00:26 lr: 0.000552 loss: 3.7875 (3.3513) grad_norm: 1.3862 (inf) time: 0.6237 [2021-03-27 06:24:39 swin_base_patch4_window7_224] INFO: Epoch: [140] [1220/1251] eta: 0:00:19 lr: 0.000552 loss: 3.6517 (3.3524) grad_norm: 1.3561 (inf) time: 0.6225 [2021-03-27 06:24:46 swin_base_patch4_window7_224] INFO: Epoch: [140] [1230/1251] eta: 0:00:13 lr: 0.000552 loss: 3.4014 (3.3536) grad_norm: 1.4419 (inf) time: 0.6263 [2021-03-27 06:24:52 swin_base_patch4_window7_224] INFO: Epoch: [140] [1240/1251] eta: 0:00:06 lr: 0.000552 loss: 3.4014 (3.3545) grad_norm: 1.4659 (inf) time: 0.6305 [2021-03-27 06:24:58 swin_base_patch4_window7_224] INFO: Epoch: [140] [1250/1251] eta: 0:00:00 lr: 0.000552 loss: 3.3682 (3.3547) grad_norm: 1.4101 (inf) time: 0.6230 [2021-03-27 06:26:13 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:13 loss: 0.9733 (0.9733) acc1: 78.1250 (78.1250) acc5: 93.7500 (93.7500) [2021-03-27 06:26:14 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.9241 (0.9146) acc1: 79.6875 (78.5511) acc5: 95.3125 (95.0284) [2021-03-27 06:26:15 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9308 (0.9639) acc1: 78.1250 (77.3810) acc5: 95.3125 (94.9405) [2021-03-27 06:26:17 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.9386 (0.9682) acc1: 78.1250 (78.0242) acc5: 93.7500 (94.7077) [2021-03-27 06:26:18 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9123 (0.9543) acc1: 78.1250 (78.2393) acc5: 95.3125 (94.8171) [2021-03-27 06:26:19 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9386 (0.9539) acc1: 78.1250 (78.2080) acc5: 95.3125 (94.8480) [2021-03-27 06:26:27 swin_base_patch4_window7_224] INFO: * Acc@1 78.430 Acc@5 94.678 loss 0.932 [2021-03-27 06:26:27 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.4% [2021-03-27 06:26:27 swin_base_patch4_window7_224] INFO: Max accuracy: 78.45% [2021-03-27 06:26:32 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 0/1251] eta: 1:28:15 lr: 0.000552 loss: 2.5305 (2.5305) grad_norm: 1.4750 (1.4750) time: 4.2331 [2021-03-27 06:26:38 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 10/1251] eta: 0:20:08 lr: 0.000552 loss: 3.4847 (3.1733) grad_norm: 1.4834 (1.5026) time: 0.9738 [2021-03-27 06:26:44 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 20/1251] eta: 0:16:36 lr: 0.000552 loss: 3.5036 (3.3325) grad_norm: 1.4834 (1.4822) time: 0.6383 [2021-03-27 06:26:51 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 30/1251] eta: 0:15:21 lr: 0.000551 loss: 3.5233 (3.3035) grad_norm: 1.4459 (1.4685) time: 0.6347 [2021-03-27 06:26:57 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 40/1251] eta: 0:14:41 lr: 0.000551 loss: 3.3557 (3.3178) grad_norm: 1.3453 (1.4408) time: 0.6427 [2021-03-27 06:27:04 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 50/1251] eta: 0:14:14 lr: 0.000551 loss: 3.4252 (3.3386) grad_norm: 1.3453 (1.4454) time: 0.6450 [2021-03-27 06:27:10 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 60/1251] eta: 0:13:50 lr: 0.000551 loss: 3.4252 (3.3172) grad_norm: 1.3947 (1.4459) time: 0.6349 [2021-03-27 06:27:16 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 70/1251] eta: 0:13:32 lr: 0.000551 loss: 3.3674 (3.3311) grad_norm: 1.4349 (1.4534) time: 0.6271 [2021-03-27 06:27:22 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 80/1251] eta: 0:13:16 lr: 0.000551 loss: 3.3075 (3.3003) grad_norm: 1.4913 (1.4529) time: 0.6258 [2021-03-27 06:27:29 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 90/1251] eta: 0:13:03 lr: 0.000551 loss: 3.3698 (3.3087) grad_norm: 1.5080 (1.4642) time: 0.6292 [2021-03-27 06:27:35 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 100/1251] eta: 0:12:52 lr: 0.000551 loss: 3.3698 (3.2994) grad_norm: 1.4415 (1.4647) time: 0.6355 [2021-03-27 06:27:41 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 110/1251] eta: 0:12:41 lr: 0.000551 loss: 3.1116 (3.2740) grad_norm: 1.4208 (1.4679) time: 0.6343 [2021-03-27 06:27:48 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 120/1251] eta: 0:12:31 lr: 0.000551 loss: 3.1910 (3.2750) grad_norm: 1.4667 (1.4776) time: 0.6308 [2021-03-27 06:27:54 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 130/1251] eta: 0:12:22 lr: 0.000551 loss: 3.3055 (3.2830) grad_norm: 1.4667 (1.4746) time: 0.6312 [2021-03-27 06:28:00 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 140/1251] eta: 0:12:12 lr: 0.000551 loss: 3.2011 (3.2711) grad_norm: 1.4530 (1.4771) time: 0.6305 [2021-03-27 06:28:07 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 150/1251] eta: 0:12:03 lr: 0.000551 loss: 3.0215 (3.2513) grad_norm: 1.4060 (1.4714) time: 0.6258 [2021-03-27 06:28:13 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 160/1251] eta: 0:11:55 lr: 0.000551 loss: 3.0215 (3.2390) grad_norm: 1.3732 (1.4663) time: 0.6324 [2021-03-27 06:28:19 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 170/1251] eta: 0:11:48 lr: 0.000551 loss: 3.1162 (3.2252) grad_norm: 1.3627 (1.4583) time: 0.6389 [2021-03-27 06:28:26 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 180/1251] eta: 0:11:40 lr: 0.000551 loss: 3.2861 (3.2422) grad_norm: 1.4108 (1.4588) time: 0.6389 [2021-03-27 06:28:32 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 190/1251] eta: 0:11:33 lr: 0.000551 loss: 3.2511 (3.2293) grad_norm: 1.4523 (1.4566) time: 0.6381 [2021-03-27 06:28:38 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 200/1251] eta: 0:11:25 lr: 0.000551 loss: 3.2511 (3.2429) grad_norm: 1.4062 (1.4551) time: 0.6339 [2021-03-27 06:28:45 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 210/1251] eta: 0:11:18 lr: 0.000551 loss: 3.6115 (3.2510) grad_norm: 1.3294 (1.4515) time: 0.6326 [2021-03-27 06:28:51 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 220/1251] eta: 0:11:10 lr: 0.000551 loss: 3.4533 (3.2520) grad_norm: 1.3660 (1.4492) time: 0.6300 [2021-03-27 06:28:57 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 230/1251] eta: 0:11:03 lr: 0.000551 loss: 3.3369 (3.2489) grad_norm: 1.3894 (1.4466) time: 0.6316 [2021-03-27 06:29:04 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 240/1251] eta: 0:10:56 lr: 0.000551 loss: 3.4028 (3.2593) grad_norm: 1.4041 (1.4465) time: 0.6402 [2021-03-27 06:29:10 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 250/1251] eta: 0:10:49 lr: 0.000551 loss: 3.5017 (3.2629) grad_norm: 1.4175 (1.4470) time: 0.6374 [2021-03-27 06:29:17 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 260/1251] eta: 0:10:42 lr: 0.000551 loss: 3.3438 (3.2615) grad_norm: 1.4160 (1.4477) time: 0.6347 [2021-03-27 06:29:23 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 270/1251] eta: 0:10:35 lr: 0.000550 loss: 3.2954 (3.2559) grad_norm: 1.4381 (1.4469) time: 0.6366 [2021-03-27 06:29:29 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 280/1251] eta: 0:10:28 lr: 0.000550 loss: 3.5165 (3.2630) grad_norm: 1.4133 (1.4452) time: 0.6351 [2021-03-27 06:29:36 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 290/1251] eta: 0:10:21 lr: 0.000550 loss: 3.4731 (3.2630) grad_norm: 1.3701 (1.4452) time: 0.6306 [2021-03-27 06:29:42 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 300/1251] eta: 0:10:14 lr: 0.000550 loss: 3.3656 (3.2648) grad_norm: 1.3829 (1.4450) time: 0.6282 [2021-03-27 06:29:48 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 310/1251] eta: 0:10:07 lr: 0.000550 loss: 3.1738 (3.2585) grad_norm: 1.4155 (1.4494) time: 0.6309 [2021-03-27 06:29:55 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 320/1251] eta: 0:10:00 lr: 0.000550 loss: 2.9727 (3.2500) grad_norm: 1.5354 (1.4529) time: 0.6329 [2021-03-27 06:30:01 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 330/1251] eta: 0:09:53 lr: 0.000550 loss: 2.9727 (3.2462) grad_norm: 1.4217 (1.4517) time: 0.6297 [2021-03-27 06:30:07 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 340/1251] eta: 0:09:46 lr: 0.000550 loss: 3.2855 (3.2476) grad_norm: 1.3943 (1.4524) time: 0.6275 [2021-03-27 06:30:13 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 350/1251] eta: 0:09:40 lr: 0.000550 loss: 3.3881 (3.2537) grad_norm: 1.4434 (1.4525) time: 0.6291 [2021-03-27 06:30:20 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 360/1251] eta: 0:09:33 lr: 0.000550 loss: 3.4433 (3.2570) grad_norm: 1.4265 (1.4517) time: 0.6287 [2021-03-27 06:30:26 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 370/1251] eta: 0:09:26 lr: 0.000550 loss: 3.4099 (3.2547) grad_norm: 1.4178 (1.4528) time: 0.6289 [2021-03-27 06:30:32 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 380/1251] eta: 0:09:19 lr: 0.000550 loss: 3.1420 (3.2563) grad_norm: 1.4066 (1.4516) time: 0.6276 [2021-03-27 06:30:38 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 390/1251] eta: 0:09:12 lr: 0.000550 loss: 3.3031 (3.2595) grad_norm: 1.3972 (1.4520) time: 0.6273 [2021-03-27 06:30:45 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 400/1251] eta: 0:09:06 lr: 0.000550 loss: 3.3031 (3.2590) grad_norm: 1.4768 (1.4537) time: 0.6286 [2021-03-27 06:30:51 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 410/1251] eta: 0:08:59 lr: 0.000550 loss: 3.4330 (3.2640) grad_norm: 1.4885 (1.4545) time: 0.6283 [2021-03-27 06:30:57 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 420/1251] eta: 0:08:52 lr: 0.000550 loss: 3.3322 (3.2657) grad_norm: 1.4295 (1.4535) time: 0.6253 [2021-03-27 06:31:04 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 430/1251] eta: 0:08:46 lr: 0.000550 loss: 3.1936 (3.2656) grad_norm: 1.4179 (1.4534) time: 0.6269 [2021-03-27 06:31:10 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 440/1251] eta: 0:08:39 lr: 0.000550 loss: 3.0853 (3.2628) grad_norm: 1.4179 (1.4519) time: 0.6312 [2021-03-27 06:31:16 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 450/1251] eta: 0:08:32 lr: 0.000550 loss: 3.2282 (3.2627) grad_norm: 1.4115 (1.4526) time: 0.6319 [2021-03-27 06:31:23 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 460/1251] eta: 0:08:26 lr: 0.000550 loss: 3.3340 (3.2644) grad_norm: 1.4588 (1.4531) time: 0.6348 [2021-03-27 06:31:29 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 470/1251] eta: 0:08:19 lr: 0.000550 loss: 3.3253 (3.2636) grad_norm: 1.4588 (1.4530) time: 0.6348 [2021-03-27 06:31:35 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 480/1251] eta: 0:08:13 lr: 0.000550 loss: 3.2551 (3.2649) grad_norm: 1.4602 (1.4539) time: 0.6321 [2021-03-27 06:31:41 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 490/1251] eta: 0:08:06 lr: 0.000550 loss: 3.4710 (3.2699) grad_norm: 1.4602 (1.4537) time: 0.6282 [2021-03-27 06:31:48 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 500/1251] eta: 0:08:00 lr: 0.000550 loss: 3.2994 (3.2661) grad_norm: 1.4190 (1.4544) time: 0.6288 [2021-03-27 06:31:54 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 510/1251] eta: 0:07:53 lr: 0.000549 loss: 3.2199 (3.2670) grad_norm: 1.4190 (1.4544) time: 0.6317 [2021-03-27 06:32:00 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 520/1251] eta: 0:07:47 lr: 0.000549 loss: 3.4847 (3.2709) grad_norm: 1.4005 (1.4539) time: 0.6312 [2021-03-27 06:32:07 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 530/1251] eta: 0:07:40 lr: 0.000549 loss: 3.5944 (3.2705) grad_norm: 1.4195 (1.4552) time: 0.6314 [2021-03-27 06:32:13 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 540/1251] eta: 0:07:34 lr: 0.000549 loss: 3.3450 (3.2711) grad_norm: 1.4104 (1.4549) time: 0.6367 [2021-03-27 06:32:20 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 550/1251] eta: 0:07:28 lr: 0.000549 loss: 3.2210 (3.2703) grad_norm: 1.3811 (1.4534) time: 0.6476 [2021-03-27 06:32:26 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 560/1251] eta: 0:07:21 lr: 0.000549 loss: 3.3848 (3.2736) grad_norm: 1.3841 (1.4532) time: 0.6483 [2021-03-27 06:32:32 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 570/1251] eta: 0:07:15 lr: 0.000549 loss: 3.3848 (3.2733) grad_norm: 1.3904 (1.4524) time: 0.6370 [2021-03-27 06:32:39 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 580/1251] eta: 0:07:08 lr: 0.000549 loss: 3.1797 (3.2748) grad_norm: 1.4153 (1.4535) time: 0.6325 [2021-03-27 06:32:45 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 590/1251] eta: 0:07:02 lr: 0.000549 loss: 3.4895 (3.2769) grad_norm: 1.4477 (1.4542) time: 0.6348 [2021-03-27 06:32:52 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 600/1251] eta: 0:06:56 lr: 0.000549 loss: 3.1617 (3.2747) grad_norm: 1.4154 (1.4522) time: 0.6381 [2021-03-27 06:32:58 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 610/1251] eta: 0:06:49 lr: 0.000549 loss: 3.0669 (3.2758) grad_norm: 1.4549 (1.4532) time: 0.6400 [2021-03-27 06:33:04 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 620/1251] eta: 0:06:43 lr: 0.000549 loss: 3.0570 (3.2735) grad_norm: 1.4685 (1.4528) time: 0.6431 [2021-03-27 06:33:11 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 630/1251] eta: 0:06:36 lr: 0.000549 loss: 3.3938 (3.2805) grad_norm: 1.3840 (1.4522) time: 0.6368 [2021-03-27 06:33:17 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 640/1251] eta: 0:06:30 lr: 0.000549 loss: 3.5653 (3.2835) grad_norm: 1.4579 (1.4531) time: 0.6291 [2021-03-27 06:33:23 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 650/1251] eta: 0:06:24 lr: 0.000549 loss: 3.4221 (3.2860) grad_norm: 1.4579 (1.4550) time: 0.6371 [2021-03-27 06:33:30 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 660/1251] eta: 0:06:17 lr: 0.000549 loss: 3.4339 (3.2887) grad_norm: 1.5540 (1.4590) time: 0.6330 [2021-03-27 06:33:36 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 670/1251] eta: 0:06:11 lr: 0.000549 loss: 3.4526 (3.2916) grad_norm: 1.4185 (1.4588) time: 0.6262 [2021-03-27 06:33:42 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 680/1251] eta: 0:06:04 lr: 0.000549 loss: 3.2587 (3.2891) grad_norm: 1.4185 (1.4583) time: 0.6319 [2021-03-27 06:33:49 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 690/1251] eta: 0:05:58 lr: 0.000549 loss: 3.3916 (3.2923) grad_norm: 1.4508 (1.4596) time: 0.6306 [2021-03-27 06:33:55 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 700/1251] eta: 0:05:51 lr: 0.000549 loss: 3.4331 (3.2916) grad_norm: 1.4044 (1.4582) time: 0.6259 [2021-03-27 06:34:01 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 710/1251] eta: 0:05:45 lr: 0.000549 loss: 3.3436 (3.2914) grad_norm: 1.3606 (1.4577) time: 0.6280 [2021-03-27 06:34:07 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 720/1251] eta: 0:05:38 lr: 0.000549 loss: 3.2889 (3.2946) grad_norm: 1.4038 (1.4576) time: 0.6278 [2021-03-27 06:34:14 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 730/1251] eta: 0:05:32 lr: 0.000549 loss: 3.3596 (3.2951) grad_norm: 1.3982 (1.4571) time: 0.6313 [2021-03-27 06:34:20 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 740/1251] eta: 0:05:26 lr: 0.000549 loss: 3.3782 (3.2960) grad_norm: 1.4074 (1.4588) time: 0.6440 [2021-03-27 06:34:27 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 750/1251] eta: 0:05:19 lr: 0.000548 loss: 3.6103 (3.2968) grad_norm: 1.4310 (1.4582) time: 0.6437 [2021-03-27 06:34:33 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 760/1251] eta: 0:05:13 lr: 0.000548 loss: 3.6103 (3.2997) grad_norm: 1.4310 (1.4579) time: 0.6337 [2021-03-27 06:34:39 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 770/1251] eta: 0:05:06 lr: 0.000548 loss: 3.4340 (3.3002) grad_norm: 1.4318 (1.4580) time: 0.6267 [2021-03-27 06:34:45 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 780/1251] eta: 0:05:00 lr: 0.000548 loss: 3.2968 (3.2978) grad_norm: 1.4318 (1.4591) time: 0.6259 [2021-03-27 06:34:52 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 790/1251] eta: 0:04:53 lr: 0.000548 loss: 3.2002 (3.2965) grad_norm: 1.4093 (1.4575) time: 0.6335 [2021-03-27 06:34:58 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 800/1251] eta: 0:04:47 lr: 0.000548 loss: 3.2002 (3.2946) grad_norm: 1.3420 (1.4569) time: 0.6382 [2021-03-27 06:35:05 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 810/1251] eta: 0:04:41 lr: 0.000548 loss: 3.2828 (3.2986) grad_norm: 1.4077 (1.4570) time: 0.6372 [2021-03-27 06:35:11 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 820/1251] eta: 0:04:34 lr: 0.000548 loss: 3.4665 (3.2996) grad_norm: 1.4077 (nan) time: 0.6251 [2021-03-27 06:35:17 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 830/1251] eta: 0:04:28 lr: 0.000548 loss: 3.3322 (3.3003) grad_norm: 1.4583 (nan) time: 0.6198 [2021-03-27 06:35:23 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 840/1251] eta: 0:04:21 lr: 0.000548 loss: 3.5833 (3.3048) grad_norm: 1.4403 (nan) time: 0.6292 [2021-03-27 06:35:30 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 850/1251] eta: 0:04:15 lr: 0.000548 loss: 3.7296 (3.3071) grad_norm: 1.3818 (nan) time: 0.6351 [2021-03-27 06:35:36 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 860/1251] eta: 0:04:09 lr: 0.000548 loss: 3.5042 (3.3072) grad_norm: 1.5240 (nan) time: 0.6329 [2021-03-27 06:35:42 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 870/1251] eta: 0:04:02 lr: 0.000548 loss: 3.1594 (3.3067) grad_norm: 1.5240 (nan) time: 0.6335 [2021-03-27 06:35:49 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 880/1251] eta: 0:03:56 lr: 0.000548 loss: 3.1161 (3.3047) grad_norm: 1.4304 (nan) time: 0.6323 [2021-03-27 06:35:55 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 890/1251] eta: 0:03:49 lr: 0.000548 loss: 3.2908 (3.3074) grad_norm: 1.4419 (nan) time: 0.6289 [2021-03-27 06:36:01 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 900/1251] eta: 0:03:43 lr: 0.000548 loss: 3.5046 (3.3093) grad_norm: 1.4927 (nan) time: 0.6350 [2021-03-27 06:36:08 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 910/1251] eta: 0:03:37 lr: 0.000548 loss: 3.3022 (3.3078) grad_norm: 1.4616 (nan) time: 0.6387 [2021-03-27 06:36:14 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 920/1251] eta: 0:03:30 lr: 0.000548 loss: 3.0709 (3.3084) grad_norm: 1.4572 (nan) time: 0.6347 [2021-03-27 06:36:20 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 930/1251] eta: 0:03:24 lr: 0.000548 loss: 3.3550 (3.3105) grad_norm: 1.3819 (nan) time: 0.6281 [2021-03-27 06:36:27 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 940/1251] eta: 0:03:17 lr: 0.000548 loss: 3.3550 (3.3104) grad_norm: 1.3247 (nan) time: 0.6246 [2021-03-27 06:36:33 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 950/1251] eta: 0:03:11 lr: 0.000548 loss: 3.5026 (3.3126) grad_norm: 1.3996 (nan) time: 0.6312 [2021-03-27 06:36:39 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 960/1251] eta: 0:03:05 lr: 0.000548 loss: 3.2481 (3.3107) grad_norm: 1.4822 (nan) time: 0.6324 [2021-03-27 06:36:46 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 970/1251] eta: 0:02:58 lr: 0.000548 loss: 3.3632 (3.3140) grad_norm: 1.4715 (nan) time: 0.6290 [2021-03-27 06:36:52 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 980/1251] eta: 0:02:52 lr: 0.000548 loss: 3.5900 (3.3160) grad_norm: 1.4975 (nan) time: 0.6293 [2021-03-27 06:36:58 swin_base_patch4_window7_224] INFO: Epoch: [141] [ 990/1251] eta: 0:02:46 lr: 0.000547 loss: 3.5634 (3.3177) grad_norm: 1.5070 (nan) time: 0.6264 [2021-03-27 06:37:04 swin_base_patch4_window7_224] INFO: Epoch: [141] [1000/1251] eta: 0:02:39 lr: 0.000547 loss: 3.4810 (3.3182) grad_norm: 1.3973 (nan) time: 0.6303 [2021-03-27 06:37:11 swin_base_patch4_window7_224] INFO: Epoch: [141] [1010/1251] eta: 0:02:33 lr: 0.000547 loss: 3.5419 (3.3211) grad_norm: 1.4101 (nan) time: 0.6320 [2021-03-27 06:37:17 swin_base_patch4_window7_224] INFO: Epoch: [141] [1020/1251] eta: 0:02:26 lr: 0.000547 loss: 3.6511 (3.3242) grad_norm: 1.3871 (nan) time: 0.6300 [2021-03-27 06:37:23 swin_base_patch4_window7_224] INFO: Epoch: [141] [1030/1251] eta: 0:02:20 lr: 0.000547 loss: 3.5832 (3.3250) grad_norm: 1.3656 (nan) time: 0.6299 [2021-03-27 06:37:30 swin_base_patch4_window7_224] INFO: Epoch: [141] [1040/1251] eta: 0:02:14 lr: 0.000547 loss: 3.4699 (3.3243) grad_norm: 1.3963 (nan) time: 0.6270 [2021-03-27 06:37:36 swin_base_patch4_window7_224] INFO: Epoch: [141] [1050/1251] eta: 0:02:07 lr: 0.000547 loss: 3.6722 (3.3286) grad_norm: 1.4602 (nan) time: 0.6276 [2021-03-27 06:37:42 swin_base_patch4_window7_224] INFO: Epoch: [141] [1060/1251] eta: 0:02:01 lr: 0.000547 loss: 3.7439 (3.3313) grad_norm: 1.4417 (nan) time: 0.6277 [2021-03-27 06:37:48 swin_base_patch4_window7_224] INFO: Epoch: [141] [1070/1251] eta: 0:01:55 lr: 0.000547 loss: 3.5739 (3.3327) grad_norm: 1.4497 (nan) time: 0.6310 [2021-03-27 06:37:55 swin_base_patch4_window7_224] INFO: Epoch: [141] [1080/1251] eta: 0:01:48 lr: 0.000547 loss: 3.4583 (3.3330) grad_norm: 1.4850 (nan) time: 0.6330 [2021-03-27 06:38:01 swin_base_patch4_window7_224] INFO: Epoch: [141] [1090/1251] eta: 0:01:42 lr: 0.000547 loss: 3.4052 (3.3330) grad_norm: 1.3482 (nan) time: 0.6278 [2021-03-27 06:38:07 swin_base_patch4_window7_224] INFO: Epoch: [141] [1100/1251] eta: 0:01:35 lr: 0.000547 loss: 3.3130 (3.3331) grad_norm: 1.3679 (nan) time: 0.6286 [2021-03-27 06:38:14 swin_base_patch4_window7_224] INFO: Epoch: [141] [1110/1251] eta: 0:01:29 lr: 0.000547 loss: 3.5067 (3.3355) grad_norm: 1.5036 (nan) time: 0.6308 [2021-03-27 06:38:20 swin_base_patch4_window7_224] INFO: Epoch: [141] [1120/1251] eta: 0:01:23 lr: 0.000547 loss: 3.4881 (3.3370) grad_norm: 1.3829 (nan) time: 0.6291 [2021-03-27 06:38:26 swin_base_patch4_window7_224] INFO: Epoch: [141] [1130/1251] eta: 0:01:16 lr: 0.000547 loss: 3.6030 (3.3381) grad_norm: 1.3821 (nan) time: 0.6348 [2021-03-27 06:38:33 swin_base_patch4_window7_224] INFO: Epoch: [141] [1140/1251] eta: 0:01:10 lr: 0.000547 loss: 3.6446 (3.3415) grad_norm: 1.4312 (nan) time: 0.6334 [2021-03-27 06:38:39 swin_base_patch4_window7_224] INFO: Epoch: [141] [1150/1251] eta: 0:01:04 lr: 0.000547 loss: 3.6932 (3.3438) grad_norm: 1.3587 (nan) time: 0.6284 [2021-03-27 06:38:45 swin_base_patch4_window7_224] INFO: Epoch: [141] [1160/1251] eta: 0:00:57 lr: 0.000547 loss: 3.5839 (3.3431) grad_norm: 1.3587 (nan) time: 0.6287 [2021-03-27 06:38:52 swin_base_patch4_window7_224] INFO: Epoch: [141] [1170/1251] eta: 0:00:51 lr: 0.000547 loss: 3.2682 (3.3434) grad_norm: 1.4165 (nan) time: 0.6323 [2021-03-27 06:38:58 swin_base_patch4_window7_224] INFO: Epoch: [141] [1180/1251] eta: 0:00:45 lr: 0.000547 loss: 3.3677 (3.3438) grad_norm: 1.4209 (nan) time: 0.6366 [2021-03-27 06:39:04 swin_base_patch4_window7_224] INFO: Epoch: [141] [1190/1251] eta: 0:00:38 lr: 0.000547 loss: 3.4083 (3.3445) grad_norm: 1.4483 (nan) time: 0.6299 [2021-03-27 06:39:11 swin_base_patch4_window7_224] INFO: Epoch: [141] [1200/1251] eta: 0:00:32 lr: 0.000547 loss: 3.2849 (3.3435) grad_norm: 1.3680 (nan) time: 0.6301 [2021-03-27 06:39:17 swin_base_patch4_window7_224] INFO: Epoch: [141] [1210/1251] eta: 0:00:26 lr: 0.000547 loss: 3.1211 (3.3425) grad_norm: 1.3529 (nan) time: 0.6330 [2021-03-27 06:39:23 swin_base_patch4_window7_224] INFO: Epoch: [141] [1220/1251] eta: 0:00:19 lr: 0.000547 loss: 3.2415 (3.3421) grad_norm: 1.3154 (nan) time: 0.6334 [2021-03-27 06:39:30 swin_base_patch4_window7_224] INFO: Epoch: [141] [1230/1251] eta: 0:00:13 lr: 0.000547 loss: 3.4888 (3.3442) grad_norm: 1.3520 (nan) time: 0.6346 [2021-03-27 06:39:36 swin_base_patch4_window7_224] INFO: Epoch: [141] [1240/1251] eta: 0:00:06 lr: 0.000546 loss: 3.6151 (3.3462) grad_norm: 1.4084 (nan) time: 0.6314 [2021-03-27 06:39:42 swin_base_patch4_window7_224] INFO: Epoch: [141] [1250/1251] eta: 0:00:00 lr: 0.000546 loss: 3.5281 (3.3466) grad_norm: 1.3702 (nan) time: 0.6262 [2021-03-27 06:39:51 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:41 loss: 0.9910 (0.9910) acc1: 79.6875 (79.6875) acc5: 93.7500 (93.7500) [2021-03-27 06:39:54 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9783 (0.9499) acc1: 79.6875 (77.8409) acc5: 93.7500 (94.1761) [2021-03-27 06:39:56 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9783 (0.9823) acc1: 78.1250 (76.6369) acc5: 93.7500 (94.1964) [2021-03-27 06:39:58 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0161 (0.9645) acc1: 78.1250 (77.2681) acc5: 95.3125 (94.6573) [2021-03-27 06:40:00 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9649 (0.9571) acc1: 78.1250 (77.5152) acc5: 93.7500 (94.6265) [2021-03-27 06:40:01 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9713 (0.9498) acc1: 78.1250 (77.5680) acc5: 95.3125 (94.8160) [2021-03-27 06:40:09 swin_base_patch4_window7_224] INFO: * Acc@1 78.370 Acc@5 94.632 loss 0.929 [2021-03-27 06:40:09 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.4% [2021-03-27 06:40:09 swin_base_patch4_window7_224] INFO: Max accuracy: 78.45% [2021-03-27 06:40:14 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 0/1251] eta: 1:30:16 lr: 0.000546 loss: 2.4233 (2.4233) grad_norm: 1.3624 (1.3624) time: 4.3294 [2021-03-27 06:40:20 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 10/1251] eta: 0:20:07 lr: 0.000546 loss: 3.0712 (3.1381) grad_norm: 1.5432 (1.5365) time: 0.9729 [2021-03-27 06:40:26 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 20/1251] eta: 0:16:40 lr: 0.000546 loss: 3.3201 (3.1924) grad_norm: 1.4008 (1.4405) time: 0.6371 [2021-03-27 06:40:33 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 30/1251] eta: 0:15:20 lr: 0.000546 loss: 3.4877 (3.2477) grad_norm: 1.3818 (1.5093) time: 0.6331 [2021-03-27 06:40:39 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 40/1251] eta: 0:14:35 lr: 0.000546 loss: 3.4877 (3.2479) grad_norm: 1.5780 (1.5256) time: 0.6288 [2021-03-27 06:40:45 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 50/1251] eta: 0:14:07 lr: 0.000546 loss: 3.4643 (3.3148) grad_norm: 1.4546 (1.5176) time: 0.6303 [2021-03-27 06:40:52 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 60/1251] eta: 0:13:45 lr: 0.000546 loss: 3.4494 (3.3088) grad_norm: 1.3250 (1.4839) time: 0.6304 [2021-03-27 06:40:58 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 70/1251] eta: 0:13:26 lr: 0.000546 loss: 3.2832 (3.3116) grad_norm: 1.3151 (1.4724) time: 0.6271 [2021-03-27 06:41:04 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 80/1251] eta: 0:13:12 lr: 0.000546 loss: 3.3662 (3.2989) grad_norm: 1.3806 (1.4663) time: 0.6265 [2021-03-27 06:41:10 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 90/1251] eta: 0:12:58 lr: 0.000546 loss: 3.5278 (3.3111) grad_norm: 1.4057 (1.4682) time: 0.6269 [2021-03-27 06:41:17 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 100/1251] eta: 0:12:48 lr: 0.000546 loss: 3.5834 (3.3131) grad_norm: 1.4317 (1.4658) time: 0.6304 [2021-03-27 06:41:23 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 110/1251] eta: 0:12:37 lr: 0.000546 loss: 3.4607 (3.3237) grad_norm: 1.4595 (1.4685) time: 0.6337 [2021-03-27 06:41:29 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 120/1251] eta: 0:12:27 lr: 0.000546 loss: 3.5184 (3.3452) grad_norm: 1.4595 (1.4675) time: 0.6300 [2021-03-27 06:41:36 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 130/1251] eta: 0:12:17 lr: 0.000546 loss: 3.4026 (3.3152) grad_norm: 1.3782 (1.4652) time: 0.6256 [2021-03-27 06:41:42 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 140/1251] eta: 0:12:09 lr: 0.000546 loss: 3.1051 (3.3133) grad_norm: 1.3751 (1.4568) time: 0.6306 [2021-03-27 06:41:48 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 150/1251] eta: 0:12:00 lr: 0.000546 loss: 3.4254 (3.3095) grad_norm: 1.3775 (1.4582) time: 0.6300 [2021-03-27 06:41:55 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 160/1251] eta: 0:11:52 lr: 0.000546 loss: 3.4748 (3.3173) grad_norm: 1.4085 (1.4551) time: 0.6241 [2021-03-27 06:42:01 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 170/1251] eta: 0:11:43 lr: 0.000546 loss: 3.3738 (3.3183) grad_norm: 1.3901 (1.4533) time: 0.6251 [2021-03-27 06:42:07 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 180/1251] eta: 0:11:35 lr: 0.000546 loss: 3.1441 (3.2932) grad_norm: 1.3980 (1.4541) time: 0.6250 [2021-03-27 06:42:13 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 190/1251] eta: 0:11:28 lr: 0.000546 loss: 2.8533 (3.2846) grad_norm: 1.3815 (1.4511) time: 0.6306 [2021-03-27 06:42:20 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 200/1251] eta: 0:11:21 lr: 0.000546 loss: 3.4576 (3.2989) grad_norm: 1.4433 (1.4559) time: 0.6328 [2021-03-27 06:42:26 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 210/1251] eta: 0:11:13 lr: 0.000546 loss: 3.3773 (3.3008) grad_norm: 1.4575 (1.4531) time: 0.6317 [2021-03-27 06:42:32 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 220/1251] eta: 0:11:06 lr: 0.000546 loss: 3.4953 (3.3074) grad_norm: 1.3122 (1.4470) time: 0.6331 [2021-03-27 06:42:39 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 230/1251] eta: 0:10:59 lr: 0.000545 loss: 3.4179 (3.3014) grad_norm: 1.3283 (1.4439) time: 0.6314 [2021-03-27 06:42:45 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 240/1251] eta: 0:10:52 lr: 0.000545 loss: 3.2431 (3.2977) grad_norm: 1.4575 (1.4483) time: 0.6289 [2021-03-27 06:42:51 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 250/1251] eta: 0:10:45 lr: 0.000545 loss: 3.5006 (3.3097) grad_norm: 1.4762 (1.4477) time: 0.6262 [2021-03-27 06:42:57 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 260/1251] eta: 0:10:37 lr: 0.000545 loss: 3.5911 (3.3187) grad_norm: 1.4398 (1.4521) time: 0.6232 [2021-03-27 06:43:04 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 270/1251] eta: 0:10:31 lr: 0.000545 loss: 3.5699 (3.3172) grad_norm: 1.4585 (1.4530) time: 0.6309 [2021-03-27 06:43:10 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 280/1251] eta: 0:10:24 lr: 0.000545 loss: 3.5337 (3.3161) grad_norm: 1.4158 (1.4518) time: 0.6324 [2021-03-27 06:43:16 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 290/1251] eta: 0:10:17 lr: 0.000545 loss: 3.4119 (3.3206) grad_norm: 1.4370 (1.4535) time: 0.6269 [2021-03-27 06:43:23 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 300/1251] eta: 0:10:10 lr: 0.000545 loss: 3.3331 (3.3182) grad_norm: 1.4189 (1.4510) time: 0.6285 [2021-03-27 06:43:29 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 310/1251] eta: 0:10:03 lr: 0.000545 loss: 3.3110 (3.3125) grad_norm: 1.3744 (1.4496) time: 0.6321 [2021-03-27 06:43:35 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 320/1251] eta: 0:09:57 lr: 0.000545 loss: 3.2561 (3.3121) grad_norm: 1.3463 (1.4467) time: 0.6358 [2021-03-27 06:43:42 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 330/1251] eta: 0:09:50 lr: 0.000545 loss: 3.0392 (3.3088) grad_norm: 1.4033 (1.4468) time: 0.6367 [2021-03-27 06:43:48 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 340/1251] eta: 0:09:43 lr: 0.000545 loss: 3.1293 (3.3085) grad_norm: 1.4064 (1.4444) time: 0.6339 [2021-03-27 06:43:54 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 350/1251] eta: 0:09:37 lr: 0.000545 loss: 3.3021 (3.3072) grad_norm: 1.3941 (1.4431) time: 0.6306 [2021-03-27 06:44:01 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 360/1251] eta: 0:09:30 lr: 0.000545 loss: 3.4249 (3.3096) grad_norm: 1.4132 (1.4436) time: 0.6338 [2021-03-27 06:44:07 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 370/1251] eta: 0:09:24 lr: 0.000545 loss: 3.5014 (3.3075) grad_norm: 1.3738 (1.4428) time: 0.6317 [2021-03-27 06:44:13 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 380/1251] eta: 0:09:17 lr: 0.000545 loss: 3.3344 (3.3071) grad_norm: 1.3942 (1.4429) time: 0.6270 [2021-03-27 06:44:19 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 390/1251] eta: 0:09:10 lr: 0.000545 loss: 3.3362 (3.3091) grad_norm: 1.4823 (1.4468) time: 0.6253 [2021-03-27 06:44:26 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 400/1251] eta: 0:09:04 lr: 0.000545 loss: 3.3698 (3.3092) grad_norm: 1.5752 (1.4542) time: 0.6301 [2021-03-27 06:44:32 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 410/1251] eta: 0:08:57 lr: 0.000545 loss: 3.3032 (3.3092) grad_norm: 1.5670 (1.4554) time: 0.6303 [2021-03-27 06:44:38 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 420/1251] eta: 0:08:50 lr: 0.000545 loss: 3.3105 (3.3087) grad_norm: 1.4639 (1.4569) time: 0.6259 [2021-03-27 06:44:45 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 430/1251] eta: 0:08:44 lr: 0.000545 loss: 3.3105 (3.3047) grad_norm: 1.4629 (1.4575) time: 0.6294 [2021-03-27 06:44:51 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 440/1251] eta: 0:08:37 lr: 0.000545 loss: 3.2070 (3.3025) grad_norm: 1.3852 (1.4562) time: 0.6283 [2021-03-27 06:44:57 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 450/1251] eta: 0:08:31 lr: 0.000545 loss: 3.0433 (3.2956) grad_norm: 1.3636 (1.4556) time: 0.6252 [2021-03-27 06:45:04 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 460/1251] eta: 0:08:24 lr: 0.000545 loss: 3.3568 (3.2988) grad_norm: 1.3694 (1.4545) time: 0.6345 [2021-03-27 06:45:10 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 470/1251] eta: 0:08:18 lr: 0.000544 loss: 3.5409 (3.3028) grad_norm: 1.4163 (1.4550) time: 0.6355 [2021-03-27 06:45:16 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 480/1251] eta: 0:08:11 lr: 0.000544 loss: 3.6954 (3.3051) grad_norm: 1.3745 (1.4521) time: 0.6275 [2021-03-27 06:45:22 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 490/1251] eta: 0:08:05 lr: 0.000544 loss: 3.4285 (3.3054) grad_norm: 1.3303 (1.4504) time: 0.6261 [2021-03-27 06:45:29 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 500/1251] eta: 0:07:58 lr: 0.000544 loss: 3.3443 (3.3067) grad_norm: 1.3324 (1.4491) time: 0.6297 [2021-03-27 06:45:35 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 510/1251] eta: 0:07:52 lr: 0.000544 loss: 3.1715 (3.3022) grad_norm: 1.3922 (1.4516) time: 0.6285 [2021-03-27 06:45:41 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 520/1251] eta: 0:07:45 lr: 0.000544 loss: 2.9749 (3.3004) grad_norm: 1.4693 (1.4508) time: 0.6293 [2021-03-27 06:45:48 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 530/1251] eta: 0:07:39 lr: 0.000544 loss: 3.2955 (3.2982) grad_norm: 1.3920 (1.4495) time: 0.6310 [2021-03-27 06:45:54 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 540/1251] eta: 0:07:32 lr: 0.000544 loss: 3.3134 (3.2950) grad_norm: 1.3373 (1.4482) time: 0.6376 [2021-03-27 06:46:01 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 550/1251] eta: 0:07:26 lr: 0.000544 loss: 3.4001 (3.2983) grad_norm: 1.3220 (1.4460) time: 0.6481 [2021-03-27 06:46:07 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 560/1251] eta: 0:07:20 lr: 0.000544 loss: 3.4625 (3.2991) grad_norm: 1.3271 (1.4446) time: 0.6506 [2021-03-27 06:46:13 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 570/1251] eta: 0:07:14 lr: 0.000544 loss: 3.2609 (3.2982) grad_norm: 1.3978 (1.4469) time: 0.6405 [2021-03-27 06:46:20 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 580/1251] eta: 0:07:07 lr: 0.000544 loss: 3.5555 (3.3046) grad_norm: 1.4775 (1.4464) time: 0.6310 [2021-03-27 06:46:26 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 590/1251] eta: 0:07:01 lr: 0.000544 loss: 3.5555 (3.3012) grad_norm: 1.4340 (1.4461) time: 0.6333 [2021-03-27 06:46:32 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 600/1251] eta: 0:06:54 lr: 0.000544 loss: 3.3292 (3.3020) grad_norm: 1.4092 (1.4455) time: 0.6333 [2021-03-27 06:46:39 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 610/1251] eta: 0:06:48 lr: 0.000544 loss: 3.3292 (3.3046) grad_norm: 1.4092 (1.4469) time: 0.6311 [2021-03-27 06:46:45 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 620/1251] eta: 0:06:41 lr: 0.000544 loss: 3.3279 (3.3032) grad_norm: 1.4989 (1.4482) time: 0.6337 [2021-03-27 06:46:51 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 630/1251] eta: 0:06:35 lr: 0.000544 loss: 3.2528 (3.3034) grad_norm: 1.4380 (1.4483) time: 0.6304 [2021-03-27 06:46:58 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 640/1251] eta: 0:06:29 lr: 0.000544 loss: 3.1570 (3.3046) grad_norm: 1.3711 (1.4472) time: 0.6269 [2021-03-27 06:47:04 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 650/1251] eta: 0:06:22 lr: 0.000544 loss: 3.1544 (3.3037) grad_norm: 1.3785 (1.4460) time: 0.6316 [2021-03-27 06:47:10 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 660/1251] eta: 0:06:16 lr: 0.000544 loss: 3.1540 (3.3033) grad_norm: 1.4015 (1.4467) time: 0.6312 [2021-03-27 06:47:17 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 670/1251] eta: 0:06:09 lr: 0.000544 loss: 3.3932 (3.3044) grad_norm: 1.4232 (1.4482) time: 0.6316 [2021-03-27 06:47:23 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 680/1251] eta: 0:06:03 lr: 0.000544 loss: 3.3932 (3.3046) grad_norm: 1.3470 (1.4471) time: 0.6303 [2021-03-27 06:47:29 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 690/1251] eta: 0:05:57 lr: 0.000544 loss: 3.2107 (3.3008) grad_norm: 1.4071 (1.4471) time: 0.6342 [2021-03-27 06:47:36 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 700/1251] eta: 0:05:50 lr: 0.000544 loss: 3.2412 (3.3032) grad_norm: 1.4402 (1.4480) time: 0.6339 [2021-03-27 06:47:42 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 710/1251] eta: 0:05:44 lr: 0.000543 loss: 3.4125 (3.3017) grad_norm: 1.4281 (1.4483) time: 0.6304 [2021-03-27 06:47:48 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 720/1251] eta: 0:05:37 lr: 0.000543 loss: 3.4125 (3.3049) grad_norm: 1.4440 (1.4489) time: 0.6276 [2021-03-27 06:47:55 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 730/1251] eta: 0:05:31 lr: 0.000543 loss: 3.4266 (3.3034) grad_norm: 1.4533 (1.4500) time: 0.6318 [2021-03-27 06:48:01 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 740/1251] eta: 0:05:25 lr: 0.000543 loss: 3.1942 (3.3011) grad_norm: 1.4659 (1.4509) time: 0.6427 [2021-03-27 06:48:07 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 750/1251] eta: 0:05:18 lr: 0.000543 loss: 3.3882 (3.3044) grad_norm: 1.4419 (1.4513) time: 0.6419 [2021-03-27 06:48:14 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 760/1251] eta: 0:05:12 lr: 0.000543 loss: 3.3882 (3.3048) grad_norm: 1.4419 (1.4520) time: 0.6307 [2021-03-27 06:48:20 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 770/1251] eta: 0:05:05 lr: 0.000543 loss: 3.3692 (3.3068) grad_norm: 1.4972 (1.4536) time: 0.6242 [2021-03-27 06:48:26 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 780/1251] eta: 0:04:59 lr: 0.000543 loss: 3.3692 (3.3069) grad_norm: 1.4302 (1.4537) time: 0.6301 [2021-03-27 06:48:33 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 790/1251] eta: 0:04:53 lr: 0.000543 loss: 3.1718 (3.3069) grad_norm: 1.3985 (1.4532) time: 0.6335 [2021-03-27 06:48:39 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 800/1251] eta: 0:04:46 lr: 0.000543 loss: 3.1704 (3.3053) grad_norm: 1.3613 (1.4527) time: 0.6311 [2021-03-27 06:48:45 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 810/1251] eta: 0:04:40 lr: 0.000543 loss: 3.0718 (3.3019) grad_norm: 1.3789 (1.4524) time: 0.6331 [2021-03-27 06:48:51 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 820/1251] eta: 0:04:34 lr: 0.000543 loss: 3.2790 (3.3012) grad_norm: 1.3946 (1.4517) time: 0.6327 [2021-03-27 06:48:58 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 830/1251] eta: 0:04:27 lr: 0.000543 loss: 3.3406 (3.3021) grad_norm: 1.3946 (1.4513) time: 0.6308 [2021-03-27 06:49:04 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 840/1251] eta: 0:04:21 lr: 0.000543 loss: 3.3406 (3.3031) grad_norm: 1.3633 (1.4502) time: 0.6318 [2021-03-27 06:49:10 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 850/1251] eta: 0:04:14 lr: 0.000543 loss: 3.5715 (3.3064) grad_norm: 1.3680 (1.4498) time: 0.6296 [2021-03-27 06:49:17 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 860/1251] eta: 0:04:08 lr: 0.000543 loss: 3.4466 (3.3074) grad_norm: 1.4133 (1.4502) time: 0.6355 [2021-03-27 06:49:23 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 870/1251] eta: 0:04:02 lr: 0.000543 loss: 3.5576 (3.3121) grad_norm: 1.4791 (1.4516) time: 0.6367 [2021-03-27 06:49:30 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 880/1251] eta: 0:03:55 lr: 0.000543 loss: 3.7005 (3.3135) grad_norm: 1.4538 (1.4513) time: 0.6354 [2021-03-27 06:49:36 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 890/1251] eta: 0:03:49 lr: 0.000543 loss: 3.4918 (3.3146) grad_norm: 1.4059 (1.4506) time: 0.6385 [2021-03-27 06:49:42 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 900/1251] eta: 0:03:43 lr: 0.000543 loss: 3.4918 (3.3160) grad_norm: 1.4109 (1.4498) time: 0.6345 [2021-03-27 06:49:49 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 910/1251] eta: 0:03:36 lr: 0.000543 loss: 3.5003 (3.3180) grad_norm: 1.4109 (1.4520) time: 0.6331 [2021-03-27 06:49:55 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 920/1251] eta: 0:03:30 lr: 0.000543 loss: 3.5003 (3.3196) grad_norm: 1.4305 (1.4515) time: 0.6334 [2021-03-27 06:50:01 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 930/1251] eta: 0:03:24 lr: 0.000543 loss: 3.4832 (3.3208) grad_norm: 1.3952 (1.4519) time: 0.6317 [2021-03-27 06:50:08 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 940/1251] eta: 0:03:17 lr: 0.000543 loss: 3.1177 (3.3180) grad_norm: 1.3938 (1.4516) time: 0.6361 [2021-03-27 06:50:14 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 950/1251] eta: 0:03:11 lr: 0.000542 loss: 3.2810 (3.3205) grad_norm: 1.3760 (1.4507) time: 0.6385 [2021-03-27 06:50:20 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 960/1251] eta: 0:03:04 lr: 0.000542 loss: 3.3829 (3.3204) grad_norm: 1.3661 (1.4495) time: 0.6373 [2021-03-27 06:50:27 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 970/1251] eta: 0:02:58 lr: 0.000542 loss: 3.3980 (3.3223) grad_norm: 1.3748 (1.4496) time: 0.6379 [2021-03-27 06:50:33 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 980/1251] eta: 0:02:52 lr: 0.000542 loss: 3.4738 (3.3231) grad_norm: 1.4846 (1.4516) time: 0.6375 [2021-03-27 06:50:39 swin_base_patch4_window7_224] INFO: Epoch: [142] [ 990/1251] eta: 0:02:45 lr: 0.000542 loss: 3.4078 (3.3221) grad_norm: 1.5608 (1.4515) time: 0.6365 [2021-03-27 06:50:46 swin_base_patch4_window7_224] INFO: Epoch: [142] [1000/1251] eta: 0:02:39 lr: 0.000542 loss: 3.2113 (3.3206) grad_norm: 1.5375 (1.4529) time: 0.6312 [2021-03-27 06:50:52 swin_base_patch4_window7_224] INFO: Epoch: [142] [1010/1251] eta: 0:02:33 lr: 0.000542 loss: 3.5558 (3.3232) grad_norm: 1.5526 (1.4535) time: 0.6305 [2021-03-27 06:50:59 swin_base_patch4_window7_224] INFO: Epoch: [142] [1020/1251] eta: 0:02:26 lr: 0.000542 loss: 3.5599 (3.3234) grad_norm: 1.4924 (1.4532) time: 0.6373 [2021-03-27 06:51:05 swin_base_patch4_window7_224] INFO: Epoch: [142] [1030/1251] eta: 0:02:20 lr: 0.000542 loss: 3.2845 (3.3213) grad_norm: 1.4743 (1.4538) time: 0.6400 [2021-03-27 06:51:11 swin_base_patch4_window7_224] INFO: Epoch: [142] [1040/1251] eta: 0:02:14 lr: 0.000542 loss: 3.2266 (3.3221) grad_norm: 1.3914 (1.4535) time: 0.6346 [2021-03-27 06:51:18 swin_base_patch4_window7_224] INFO: Epoch: [142] [1050/1251] eta: 0:02:07 lr: 0.000542 loss: 3.3543 (3.3215) grad_norm: 1.3717 (1.4537) time: 0.6340 [2021-03-27 06:51:24 swin_base_patch4_window7_224] INFO: Epoch: [142] [1060/1251] eta: 0:02:01 lr: 0.000542 loss: 3.3309 (3.3206) grad_norm: 1.4209 (1.4536) time: 0.6355 [2021-03-27 06:51:30 swin_base_patch4_window7_224] INFO: Epoch: [142] [1070/1251] eta: 0:01:55 lr: 0.000542 loss: 3.4003 (3.3223) grad_norm: 1.4311 (1.4538) time: 0.6314 [2021-03-27 06:51:37 swin_base_patch4_window7_224] INFO: Epoch: [142] [1080/1251] eta: 0:01:48 lr: 0.000542 loss: 3.4003 (3.3204) grad_norm: 1.5099 (1.4554) time: 0.6318 [2021-03-27 06:51:43 swin_base_patch4_window7_224] INFO: Epoch: [142] [1090/1251] eta: 0:01:42 lr: 0.000542 loss: 3.2406 (3.3206) grad_norm: 1.4265 (1.4544) time: 0.6345 [2021-03-27 06:51:49 swin_base_patch4_window7_224] INFO: Epoch: [142] [1100/1251] eta: 0:01:35 lr: 0.000542 loss: 3.3544 (3.3212) grad_norm: 1.3706 (1.4540) time: 0.6296 [2021-03-27 06:51:56 swin_base_patch4_window7_224] INFO: Epoch: [142] [1110/1251] eta: 0:01:29 lr: 0.000542 loss: 3.2042 (3.3204) grad_norm: 1.4460 (1.4545) time: 0.6288 [2021-03-27 06:52:02 swin_base_patch4_window7_224] INFO: Epoch: [142] [1120/1251] eta: 0:01:23 lr: 0.000542 loss: 2.8781 (3.3167) grad_norm: 1.4480 (1.4546) time: 0.6401 [2021-03-27 06:52:08 swin_base_patch4_window7_224] INFO: Epoch: [142] [1130/1251] eta: 0:01:16 lr: 0.000542 loss: 2.8781 (3.3171) grad_norm: 1.3768 (1.4542) time: 0.6421 [2021-03-27 06:52:15 swin_base_patch4_window7_224] INFO: Epoch: [142] [1140/1251] eta: 0:01:10 lr: 0.000542 loss: 3.5156 (3.3180) grad_norm: 1.3850 (1.4540) time: 0.6328 [2021-03-27 06:52:21 swin_base_patch4_window7_224] INFO: Epoch: [142] [1150/1251] eta: 0:01:04 lr: 0.000542 loss: 3.4330 (3.3181) grad_norm: 1.4622 (1.4543) time: 0.6284 [2021-03-27 06:52:27 swin_base_patch4_window7_224] INFO: Epoch: [142] [1160/1251] eta: 0:00:57 lr: 0.000542 loss: 3.4330 (3.3185) grad_norm: 1.4641 (1.4540) time: 0.6319 [2021-03-27 06:52:34 swin_base_patch4_window7_224] INFO: Epoch: [142] [1170/1251] eta: 0:00:51 lr: 0.000542 loss: 3.4749 (3.3196) grad_norm: 1.4026 (1.4546) time: 0.6359 [2021-03-27 06:52:40 swin_base_patch4_window7_224] INFO: Epoch: [142] [1180/1251] eta: 0:00:45 lr: 0.000542 loss: 3.4431 (3.3199) grad_norm: 1.4043 (1.4541) time: 0.6329 [2021-03-27 06:52:46 swin_base_patch4_window7_224] INFO: Epoch: [142] [1190/1251] eta: 0:00:38 lr: 0.000542 loss: 3.5399 (3.3222) grad_norm: 1.3478 (1.4539) time: 0.6271 [2021-03-27 06:52:52 swin_base_patch4_window7_224] INFO: Epoch: [142] [1200/1251] eta: 0:00:32 lr: 0.000541 loss: 3.3823 (3.3194) grad_norm: 1.3818 (1.4540) time: 0.6273 [2021-03-27 06:52:59 swin_base_patch4_window7_224] INFO: Epoch: [142] [1210/1251] eta: 0:00:26 lr: 0.000541 loss: 3.2721 (3.3191) grad_norm: 1.4133 (1.4542) time: 0.6319 [2021-03-27 06:53:05 swin_base_patch4_window7_224] INFO: Epoch: [142] [1220/1251] eta: 0:00:19 lr: 0.000541 loss: 3.3238 (3.3191) grad_norm: 1.3858 (1.4538) time: 0.6292 [2021-03-27 06:53:11 swin_base_patch4_window7_224] INFO: Epoch: [142] [1230/1251] eta: 0:00:13 lr: 0.000541 loss: 3.3720 (3.3184) grad_norm: 1.4608 (1.4542) time: 0.6240 [2021-03-27 06:53:18 swin_base_patch4_window7_224] INFO: Epoch: [142] [1240/1251] eta: 0:00:06 lr: 0.000541 loss: 3.2932 (3.3179) grad_norm: 1.4659 (1.4542) time: 0.6284 [2021-03-27 06:53:24 swin_base_patch4_window7_224] INFO: Epoch: [142] [1250/1251] eta: 0:00:00 lr: 0.000541 loss: 3.3212 (3.3185) grad_norm: 1.4634 (1.4542) time: 0.6298 [2021-03-27 06:53:32 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:04 loss: 0.7612 (0.7612) acc1: 78.1250 (78.1250) acc5: 96.8750 (96.8750) [2021-03-27 06:53:34 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8760 (0.8877) acc1: 78.1250 (78.6932) acc5: 95.3125 (95.4545) [2021-03-27 06:53:37 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8760 (0.9099) acc1: 78.1250 (78.0506) acc5: 95.3125 (95.2381) [2021-03-27 06:53:39 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9055 (0.9030) acc1: 79.6875 (78.8810) acc5: 95.3125 (95.0101) [2021-03-27 06:53:41 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9606 (0.9314) acc1: 78.1250 (77.9726) acc5: 93.7500 (94.8552) [2021-03-27 06:53:42 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9415 (0.9266) acc1: 76.5625 (77.8560) acc5: 93.7500 (94.7840) [2021-03-27 06:53:53 swin_base_patch4_window7_224] INFO: * Acc@1 78.632 Acc@5 94.574 loss 0.924 [2021-03-27 06:53:53 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.6% [2021-03-27 06:53:53 swin_base_patch4_window7_224] INFO: Max accuracy: 78.63% [2021-03-27 06:53:58 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 0/1251] eta: 1:33:57 lr: 0.000541 loss: 2.9822 (2.9822) grad_norm: 1.6022 (1.6022) time: 4.5062 [2021-03-27 06:54:04 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 10/1251] eta: 0:20:31 lr: 0.000541 loss: 3.7149 (3.4948) grad_norm: 1.5949 (inf) time: 0.9923 [2021-03-27 06:54:10 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 20/1251] eta: 0:16:43 lr: 0.000541 loss: 3.4103 (3.4703) grad_norm: 1.5316 (inf) time: 0.6308 [2021-03-27 06:54:16 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 30/1251] eta: 0:15:24 lr: 0.000541 loss: 3.3673 (3.4103) grad_norm: 1.3881 (inf) time: 0.6282 [2021-03-27 06:54:23 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 40/1251] eta: 0:14:41 lr: 0.000541 loss: 3.2933 (3.3468) grad_norm: 1.3881 (inf) time: 0.6363 [2021-03-27 06:54:29 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 50/1251] eta: 0:14:12 lr: 0.000541 loss: 3.3841 (3.3619) grad_norm: 1.4121 (inf) time: 0.6355 [2021-03-27 06:54:35 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 60/1251] eta: 0:13:48 lr: 0.000541 loss: 3.5426 (3.3681) grad_norm: 1.4366 (inf) time: 0.6298 [2021-03-27 06:54:42 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 70/1251] eta: 0:13:31 lr: 0.000541 loss: 3.6634 (3.3730) grad_norm: 1.3976 (inf) time: 0.6298 [2021-03-27 06:54:48 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 80/1251] eta: 0:13:15 lr: 0.000541 loss: 3.5898 (3.3932) grad_norm: 1.3405 (inf) time: 0.6304 [2021-03-27 06:54:54 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 90/1251] eta: 0:13:03 lr: 0.000541 loss: 3.5190 (3.3730) grad_norm: 1.3405 (inf) time: 0.6332 [2021-03-27 06:55:01 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 100/1251] eta: 0:12:53 lr: 0.000541 loss: 3.4257 (3.3813) grad_norm: 1.4158 (inf) time: 0.6400 [2021-03-27 06:55:07 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 110/1251] eta: 0:12:42 lr: 0.000541 loss: 3.3925 (3.3692) grad_norm: 1.4129 (inf) time: 0.6349 [2021-03-27 06:55:14 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 120/1251] eta: 0:12:32 lr: 0.000541 loss: 3.3868 (3.3842) grad_norm: 1.3713 (inf) time: 0.6340 [2021-03-27 06:55:20 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 130/1251] eta: 0:12:23 lr: 0.000541 loss: 3.3305 (3.3744) grad_norm: 1.3918 (inf) time: 0.6371 [2021-03-27 06:55:26 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 140/1251] eta: 0:12:13 lr: 0.000541 loss: 3.1736 (3.3598) grad_norm: 1.4195 (inf) time: 0.6302 [2021-03-27 06:55:32 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 150/1251] eta: 0:12:05 lr: 0.000541 loss: 3.3243 (3.3612) grad_norm: 1.4623 (inf) time: 0.6286 [2021-03-27 06:55:39 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 160/1251] eta: 0:11:56 lr: 0.000541 loss: 3.4373 (3.3678) grad_norm: 1.4683 (inf) time: 0.6315 [2021-03-27 06:55:45 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 170/1251] eta: 0:11:48 lr: 0.000541 loss: 3.3939 (3.3567) grad_norm: 1.4156 (inf) time: 0.6297 [2021-03-27 06:55:51 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 180/1251] eta: 0:11:40 lr: 0.000541 loss: 3.4327 (3.3663) grad_norm: 1.3690 (inf) time: 0.6317 [2021-03-27 06:55:58 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 190/1251] eta: 0:11:32 lr: 0.000540 loss: 3.6747 (3.3770) grad_norm: 1.4185 (inf) time: 0.6289 [2021-03-27 06:56:04 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 200/1251] eta: 0:11:24 lr: 0.000540 loss: 3.5172 (3.3747) grad_norm: 1.4033 (inf) time: 0.6244 [2021-03-27 06:56:10 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 210/1251] eta: 0:11:16 lr: 0.000540 loss: 3.4236 (3.3751) grad_norm: 1.4045 (inf) time: 0.6274 [2021-03-27 06:56:17 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 220/1251] eta: 0:11:09 lr: 0.000540 loss: 3.1518 (3.3649) grad_norm: 1.4766 (inf) time: 0.6311 [2021-03-27 06:56:23 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 230/1251] eta: 0:11:01 lr: 0.000540 loss: 3.4047 (3.3680) grad_norm: 1.4901 (inf) time: 0.6287 [2021-03-27 06:56:29 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 240/1251] eta: 0:10:54 lr: 0.000540 loss: 3.4076 (3.3604) grad_norm: 1.4562 (inf) time: 0.6274 [2021-03-27 06:56:35 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 250/1251] eta: 0:10:47 lr: 0.000540 loss: 3.4492 (3.3687) grad_norm: 1.4562 (inf) time: 0.6349 [2021-03-27 06:56:42 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 260/1251] eta: 0:10:40 lr: 0.000540 loss: 3.3185 (3.3549) grad_norm: 1.5192 (inf) time: 0.6368 [2021-03-27 06:56:48 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 270/1251] eta: 0:10:33 lr: 0.000540 loss: 2.9986 (3.3476) grad_norm: 1.4600 (inf) time: 0.6284 [2021-03-27 06:56:54 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 280/1251] eta: 0:10:26 lr: 0.000540 loss: 3.0790 (3.3413) grad_norm: 1.4223 (inf) time: 0.6260 [2021-03-27 06:57:01 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 290/1251] eta: 0:10:19 lr: 0.000540 loss: 3.1761 (3.3389) grad_norm: 1.3709 (inf) time: 0.6306 [2021-03-27 06:57:07 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 300/1251] eta: 0:10:12 lr: 0.000540 loss: 3.4290 (3.3380) grad_norm: 1.4011 (inf) time: 0.6291 [2021-03-27 06:57:13 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 310/1251] eta: 0:10:05 lr: 0.000540 loss: 3.4530 (3.3409) grad_norm: 1.4134 (inf) time: 0.6249 [2021-03-27 06:57:19 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 320/1251] eta: 0:09:58 lr: 0.000540 loss: 3.4205 (3.3451) grad_norm: 1.3945 (inf) time: 0.6238 [2021-03-27 06:57:26 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 330/1251] eta: 0:09:51 lr: 0.000540 loss: 3.3940 (3.3403) grad_norm: 1.4772 (inf) time: 0.6282 [2021-03-27 06:57:32 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 340/1251] eta: 0:09:45 lr: 0.000540 loss: 3.2990 (3.3437) grad_norm: 1.4772 (inf) time: 0.6347 [2021-03-27 06:57:38 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 350/1251] eta: 0:09:38 lr: 0.000540 loss: 3.2027 (3.3337) grad_norm: 1.4059 (inf) time: 0.6329 [2021-03-27 06:57:45 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 360/1251] eta: 0:09:31 lr: 0.000540 loss: 2.9950 (3.3304) grad_norm: 1.4175 (inf) time: 0.6317 [2021-03-27 06:57:51 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 370/1251] eta: 0:09:25 lr: 0.000540 loss: 3.2678 (3.3284) grad_norm: 1.5165 (inf) time: 0.6331 [2021-03-27 06:57:57 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 380/1251] eta: 0:09:18 lr: 0.000540 loss: 3.2700 (3.3287) grad_norm: 1.5164 (inf) time: 0.6310 [2021-03-27 06:58:04 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 390/1251] eta: 0:09:11 lr: 0.000540 loss: 3.3692 (3.3272) grad_norm: 1.3649 (inf) time: 0.6322 [2021-03-27 06:58:10 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 400/1251] eta: 0:09:05 lr: 0.000540 loss: 3.4303 (3.3332) grad_norm: 1.3448 (inf) time: 0.6361 [2021-03-27 06:58:16 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 410/1251] eta: 0:08:58 lr: 0.000540 loss: 3.3830 (3.3325) grad_norm: 1.3190 (inf) time: 0.6337 [2021-03-27 06:58:23 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 420/1251] eta: 0:08:52 lr: 0.000540 loss: 3.3426 (3.3310) grad_norm: 1.3595 (inf) time: 0.6275 [2021-03-27 06:58:29 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 430/1251] eta: 0:08:45 lr: 0.000539 loss: 3.1977 (3.3284) grad_norm: 1.4852 (inf) time: 0.6283 [2021-03-27 06:58:35 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 440/1251] eta: 0:08:38 lr: 0.000539 loss: 3.1822 (3.3232) grad_norm: 1.4181 (inf) time: 0.6294 [2021-03-27 06:58:42 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 450/1251] eta: 0:08:32 lr: 0.000539 loss: 3.2167 (3.3215) grad_norm: 1.4631 (inf) time: 0.6288 [2021-03-27 06:58:48 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 460/1251] eta: 0:08:25 lr: 0.000539 loss: 3.5432 (3.3268) grad_norm: 1.4703 (inf) time: 0.6298 [2021-03-27 06:58:54 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 470/1251] eta: 0:08:19 lr: 0.000539 loss: 3.4497 (3.3218) grad_norm: 1.3434 (inf) time: 0.6334 [2021-03-27 06:59:00 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 480/1251] eta: 0:08:12 lr: 0.000539 loss: 3.3409 (3.3222) grad_norm: 1.3597 (inf) time: 0.6305 [2021-03-27 06:59:07 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 490/1251] eta: 0:08:06 lr: 0.000539 loss: 3.0695 (3.3161) grad_norm: 1.4129 (inf) time: 0.6225 [2021-03-27 06:59:13 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 500/1251] eta: 0:07:59 lr: 0.000539 loss: 3.1385 (3.3158) grad_norm: 1.4379 (inf) time: 0.6231 [2021-03-27 06:59:19 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 510/1251] eta: 0:07:52 lr: 0.000539 loss: 3.3156 (3.3156) grad_norm: 1.3758 (inf) time: 0.6277 [2021-03-27 06:59:26 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 520/1251] eta: 0:07:46 lr: 0.000539 loss: 3.3214 (3.3140) grad_norm: 1.3740 (inf) time: 0.6330 [2021-03-27 06:59:32 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 530/1251] eta: 0:07:39 lr: 0.000539 loss: 3.3839 (3.3154) grad_norm: 1.3815 (inf) time: 0.6294 [2021-03-27 06:59:38 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 540/1251] eta: 0:07:33 lr: 0.000539 loss: 3.4084 (3.3153) grad_norm: 1.4100 (inf) time: 0.6260 [2021-03-27 06:59:45 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 550/1251] eta: 0:07:27 lr: 0.000539 loss: 3.5842 (3.3205) grad_norm: 1.4100 (inf) time: 0.6384 [2021-03-27 06:59:51 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 560/1251] eta: 0:07:20 lr: 0.000539 loss: 3.6391 (3.3236) grad_norm: 1.3949 (inf) time: 0.6494 [2021-03-27 06:59:58 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 570/1251] eta: 0:07:14 lr: 0.000539 loss: 3.7210 (3.3295) grad_norm: 1.4038 (inf) time: 0.6487 [2021-03-27 07:00:04 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 580/1251] eta: 0:07:08 lr: 0.000539 loss: 3.5778 (3.3279) grad_norm: 1.4080 (inf) time: 0.6367 [2021-03-27 07:00:10 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 590/1251] eta: 0:07:01 lr: 0.000539 loss: 3.2911 (3.3276) grad_norm: 1.3891 (inf) time: 0.6350 [2021-03-27 07:00:17 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 600/1251] eta: 0:06:55 lr: 0.000539 loss: 3.2647 (3.3269) grad_norm: 1.4085 (inf) time: 0.6386 [2021-03-27 07:00:23 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 610/1251] eta: 0:06:48 lr: 0.000539 loss: 3.1699 (3.3265) grad_norm: 1.5032 (inf) time: 0.6300 [2021-03-27 07:00:29 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 620/1251] eta: 0:06:42 lr: 0.000539 loss: 3.1529 (3.3228) grad_norm: 1.5017 (inf) time: 0.6296 [2021-03-27 07:00:36 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 630/1251] eta: 0:06:36 lr: 0.000539 loss: 3.1813 (3.3203) grad_norm: 1.5089 (inf) time: 0.6321 [2021-03-27 07:00:42 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 640/1251] eta: 0:06:29 lr: 0.000539 loss: 3.3127 (3.3200) grad_norm: 1.5129 (inf) time: 0.6256 [2021-03-27 07:00:48 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 650/1251] eta: 0:06:23 lr: 0.000539 loss: 3.2970 (3.3193) grad_norm: 1.4965 (inf) time: 0.6291 [2021-03-27 07:00:54 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 660/1251] eta: 0:06:16 lr: 0.000539 loss: 3.3403 (3.3220) grad_norm: 1.3900 (inf) time: 0.6286 [2021-03-27 07:01:01 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 670/1251] eta: 0:06:10 lr: 0.000538 loss: 3.3452 (3.3212) grad_norm: 1.3831 (inf) time: 0.6286 [2021-03-27 07:01:07 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 680/1251] eta: 0:06:03 lr: 0.000538 loss: 3.3496 (3.3219) grad_norm: 1.4288 (inf) time: 0.6366 [2021-03-27 07:01:13 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 690/1251] eta: 0:05:57 lr: 0.000538 loss: 3.4026 (3.3206) grad_norm: 1.4648 (inf) time: 0.6356 [2021-03-27 07:01:20 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 700/1251] eta: 0:05:50 lr: 0.000538 loss: 3.2451 (3.3204) grad_norm: 1.4762 (inf) time: 0.6294 [2021-03-27 07:01:26 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 710/1251] eta: 0:05:44 lr: 0.000538 loss: 3.2451 (3.3196) grad_norm: 1.5006 (inf) time: 0.6252 [2021-03-27 07:01:32 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 720/1251] eta: 0:05:38 lr: 0.000538 loss: 3.0858 (3.3143) grad_norm: 1.4095 (inf) time: 0.6280 [2021-03-27 07:01:39 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 730/1251] eta: 0:05:31 lr: 0.000538 loss: 3.1864 (3.3131) grad_norm: 1.4101 (inf) time: 0.6321 [2021-03-27 07:01:45 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 740/1251] eta: 0:05:25 lr: 0.000538 loss: 3.3118 (3.3135) grad_norm: 1.5265 (inf) time: 0.6362 [2021-03-27 07:01:51 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 750/1251] eta: 0:05:18 lr: 0.000538 loss: 3.3118 (3.3116) grad_norm: 1.5262 (inf) time: 0.6376 [2021-03-27 07:01:58 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 760/1251] eta: 0:05:12 lr: 0.000538 loss: 3.3105 (3.3104) grad_norm: 1.5342 (inf) time: 0.6326 [2021-03-27 07:02:04 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 770/1251] eta: 0:05:06 lr: 0.000538 loss: 3.4833 (3.3131) grad_norm: 1.4893 (inf) time: 0.6270 [2021-03-27 07:02:10 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 780/1251] eta: 0:04:59 lr: 0.000538 loss: 3.3950 (3.3083) grad_norm: 1.4089 (inf) time: 0.6292 [2021-03-27 07:02:16 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 790/1251] eta: 0:04:53 lr: 0.000538 loss: 3.2039 (3.3069) grad_norm: 1.4435 (inf) time: 0.6277 [2021-03-27 07:02:23 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 800/1251] eta: 0:04:47 lr: 0.000538 loss: 3.4378 (3.3085) grad_norm: 1.4610 (inf) time: 0.6358 [2021-03-27 07:02:29 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 810/1251] eta: 0:04:40 lr: 0.000538 loss: 3.4991 (3.3096) grad_norm: 1.3880 (inf) time: 0.6362 [2021-03-27 07:02:35 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 820/1251] eta: 0:04:34 lr: 0.000538 loss: 3.4746 (3.3103) grad_norm: 1.4124 (inf) time: 0.6233 [2021-03-27 07:02:42 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 830/1251] eta: 0:04:27 lr: 0.000538 loss: 3.4100 (3.3110) grad_norm: 1.4238 (inf) time: 0.6265 [2021-03-27 07:02:48 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 840/1251] eta: 0:04:21 lr: 0.000538 loss: 3.3548 (3.3121) grad_norm: 1.5000 (inf) time: 0.6378 [2021-03-27 07:02:54 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 850/1251] eta: 0:04:15 lr: 0.000538 loss: 3.4669 (3.3147) grad_norm: 1.4396 (inf) time: 0.6361 [2021-03-27 07:03:01 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 860/1251] eta: 0:04:08 lr: 0.000538 loss: 3.4669 (3.3150) grad_norm: 1.4396 (inf) time: 0.6321 [2021-03-27 07:03:07 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 870/1251] eta: 0:04:02 lr: 0.000538 loss: 3.3156 (3.3133) grad_norm: 1.4617 (inf) time: 0.6367 [2021-03-27 07:03:13 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 880/1251] eta: 0:03:55 lr: 0.000538 loss: 3.3236 (3.3138) grad_norm: 1.4617 (inf) time: 0.6349 [2021-03-27 07:03:20 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 890/1251] eta: 0:03:49 lr: 0.000538 loss: 3.5958 (3.3150) grad_norm: 1.3829 (inf) time: 0.6345 [2021-03-27 07:03:26 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 900/1251] eta: 0:03:43 lr: 0.000538 loss: 3.5857 (3.3126) grad_norm: 1.3828 (inf) time: 0.6388 [2021-03-27 07:03:33 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 910/1251] eta: 0:03:36 lr: 0.000537 loss: 3.3023 (3.3128) grad_norm: 1.4782 (inf) time: 0.6381 [2021-03-27 07:03:39 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 920/1251] eta: 0:03:30 lr: 0.000537 loss: 3.3023 (3.3122) grad_norm: 1.4905 (inf) time: 0.6324 [2021-03-27 07:03:45 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 930/1251] eta: 0:03:24 lr: 0.000537 loss: 3.5765 (3.3151) grad_norm: 1.3800 (inf) time: 0.6295 [2021-03-27 07:03:51 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 940/1251] eta: 0:03:17 lr: 0.000537 loss: 3.6433 (3.3155) grad_norm: 1.4202 (inf) time: 0.6274 [2021-03-27 07:03:58 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 950/1251] eta: 0:03:11 lr: 0.000537 loss: 3.4469 (3.3157) grad_norm: 1.4558 (inf) time: 0.6248 [2021-03-27 07:04:04 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 960/1251] eta: 0:03:04 lr: 0.000537 loss: 3.5407 (3.3176) grad_norm: 1.4238 (inf) time: 0.6242 [2021-03-27 07:04:10 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 970/1251] eta: 0:02:58 lr: 0.000537 loss: 3.4094 (3.3153) grad_norm: 1.4052 (inf) time: 0.6273 [2021-03-27 07:04:16 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 980/1251] eta: 0:02:52 lr: 0.000537 loss: 3.1089 (3.3141) grad_norm: 1.4054 (inf) time: 0.6264 [2021-03-27 07:04:23 swin_base_patch4_window7_224] INFO: Epoch: [143] [ 990/1251] eta: 0:02:45 lr: 0.000537 loss: 3.2028 (3.3135) grad_norm: 1.5468 (inf) time: 0.6262 [2021-03-27 07:04:29 swin_base_patch4_window7_224] INFO: Epoch: [143] [1000/1251] eta: 0:02:39 lr: 0.000537 loss: 3.3080 (3.3109) grad_norm: 1.6371 (inf) time: 0.6332 [2021-03-27 07:04:35 swin_base_patch4_window7_224] INFO: Epoch: [143] [1010/1251] eta: 0:02:33 lr: 0.000537 loss: 3.3905 (3.3097) grad_norm: 1.5551 (inf) time: 0.6338 [2021-03-27 07:04:42 swin_base_patch4_window7_224] INFO: Epoch: [143] [1020/1251] eta: 0:02:26 lr: 0.000537 loss: 3.1543 (3.3077) grad_norm: 1.4270 (inf) time: 0.6313 [2021-03-27 07:04:48 swin_base_patch4_window7_224] INFO: Epoch: [143] [1030/1251] eta: 0:02:20 lr: 0.000537 loss: 3.2648 (3.3099) grad_norm: 1.4425 (inf) time: 0.6299 [2021-03-27 07:04:54 swin_base_patch4_window7_224] INFO: Epoch: [143] [1040/1251] eta: 0:02:14 lr: 0.000537 loss: 3.2648 (3.3055) grad_norm: 1.3792 (inf) time: 0.6304 [2021-03-27 07:05:01 swin_base_patch4_window7_224] INFO: Epoch: [143] [1050/1251] eta: 0:02:07 lr: 0.000537 loss: 2.9905 (3.3036) grad_norm: 1.3767 (inf) time: 0.6318 [2021-03-27 07:05:07 swin_base_patch4_window7_224] INFO: Epoch: [143] [1060/1251] eta: 0:02:01 lr: 0.000537 loss: 3.1613 (3.3037) grad_norm: 1.3777 (inf) time: 0.6317 [2021-03-27 07:05:13 swin_base_patch4_window7_224] INFO: Epoch: [143] [1070/1251] eta: 0:01:54 lr: 0.000537 loss: 3.3656 (3.3047) grad_norm: 1.3720 (inf) time: 0.6267 [2021-03-27 07:05:20 swin_base_patch4_window7_224] INFO: Epoch: [143] [1080/1251] eta: 0:01:48 lr: 0.000537 loss: 3.3195 (3.3035) grad_norm: 1.3248 (inf) time: 0.6253 [2021-03-27 07:05:26 swin_base_patch4_window7_224] INFO: Epoch: [143] [1090/1251] eta: 0:01:42 lr: 0.000537 loss: 3.3757 (3.3043) grad_norm: 1.3207 (inf) time: 0.6246 [2021-03-27 07:05:32 swin_base_patch4_window7_224] INFO: Epoch: [143] [1100/1251] eta: 0:01:35 lr: 0.000537 loss: 3.3882 (3.3049) grad_norm: 1.3677 (inf) time: 0.6221 [2021-03-27 07:05:38 swin_base_patch4_window7_224] INFO: Epoch: [143] [1110/1251] eta: 0:01:29 lr: 0.000537 loss: 3.5523 (3.3085) grad_norm: 1.4808 (inf) time: 0.6271 [2021-03-27 07:05:45 swin_base_patch4_window7_224] INFO: Epoch: [143] [1120/1251] eta: 0:01:23 lr: 0.000537 loss: 3.3484 (3.3062) grad_norm: 1.4611 (inf) time: 0.6285 [2021-03-27 07:05:51 swin_base_patch4_window7_224] INFO: Epoch: [143] [1130/1251] eta: 0:01:16 lr: 0.000537 loss: 3.3795 (3.3077) grad_norm: 1.3890 (inf) time: 0.6295 [2021-03-27 07:05:57 swin_base_patch4_window7_224] INFO: Epoch: [143] [1140/1251] eta: 0:01:10 lr: 0.000537 loss: 3.4826 (3.3087) grad_norm: 1.3735 (inf) time: 0.6335 [2021-03-27 07:06:03 swin_base_patch4_window7_224] INFO: Epoch: [143] [1150/1251] eta: 0:01:04 lr: 0.000536 loss: 3.3315 (3.3084) grad_norm: 1.4756 (inf) time: 0.6329 [2021-03-27 07:06:10 swin_base_patch4_window7_224] INFO: Epoch: [143] [1160/1251] eta: 0:00:57 lr: 0.000536 loss: 3.1625 (3.3078) grad_norm: 1.5466 (inf) time: 0.6319 [2021-03-27 07:06:16 swin_base_patch4_window7_224] INFO: Epoch: [143] [1170/1251] eta: 0:00:51 lr: 0.000536 loss: 3.3003 (3.3091) grad_norm: 1.5625 (inf) time: 0.6266 [2021-03-27 07:06:22 swin_base_patch4_window7_224] INFO: Epoch: [143] [1180/1251] eta: 0:00:45 lr: 0.000536 loss: 3.3976 (3.3098) grad_norm: 1.4513 (inf) time: 0.6237 [2021-03-27 07:06:29 swin_base_patch4_window7_224] INFO: Epoch: [143] [1190/1251] eta: 0:00:38 lr: 0.000536 loss: 3.4452 (3.3102) grad_norm: 1.4367 (inf) time: 0.6304 [2021-03-27 07:06:35 swin_base_patch4_window7_224] INFO: Epoch: [143] [1200/1251] eta: 0:00:32 lr: 0.000536 loss: 3.4452 (3.3117) grad_norm: 1.4813 (inf) time: 0.6293 [2021-03-27 07:06:41 swin_base_patch4_window7_224] INFO: Epoch: [143] [1210/1251] eta: 0:00:26 lr: 0.000536 loss: 3.3758 (3.3112) grad_norm: 1.4737 (inf) time: 0.6319 [2021-03-27 07:06:48 swin_base_patch4_window7_224] INFO: Epoch: [143] [1220/1251] eta: 0:00:19 lr: 0.000536 loss: 3.3959 (3.3130) grad_norm: 1.4460 (inf) time: 0.6335 [2021-03-27 07:06:54 swin_base_patch4_window7_224] INFO: Epoch: [143] [1230/1251] eta: 0:00:13 lr: 0.000536 loss: 3.6166 (3.3133) grad_norm: 1.4241 (inf) time: 0.6336 [2021-03-27 07:07:00 swin_base_patch4_window7_224] INFO: Epoch: [143] [1240/1251] eta: 0:00:06 lr: 0.000536 loss: 3.6308 (3.3150) grad_norm: 1.3860 (inf) time: 0.6348 [2021-03-27 07:07:06 swin_base_patch4_window7_224] INFO: Epoch: [143] [1250/1251] eta: 0:00:00 lr: 0.000536 loss: 3.4973 (3.3156) grad_norm: 1.3802 (inf) time: 0.6242 [2021-03-27 07:07:14 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:40 loss: 0.7676 (0.7676) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-27 07:07:16 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.9416 (0.9808) acc1: 75.0000 (75.8523) acc5: 93.7500 (94.8864) [2021-03-27 07:07:19 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.9102 (0.9493) acc1: 78.1250 (77.6786) acc5: 93.7500 (94.9405) [2021-03-27 07:07:20 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8707 (0.9324) acc1: 79.6875 (77.7218) acc5: 95.3125 (94.9597) [2021-03-27 07:07:23 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9462 (0.9535) acc1: 78.1250 (77.5915) acc5: 93.7500 (94.6265) [2021-03-27 07:07:24 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0100 (0.9482) acc1: 78.1250 (78.0480) acc5: 93.7500 (94.9440) [2021-03-27 07:07:33 swin_base_patch4_window7_224] INFO: * Acc@1 78.830 Acc@5 94.690 loss 0.932 [2021-03-27 07:07:33 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.8% [2021-03-27 07:07:33 swin_base_patch4_window7_224] INFO: Max accuracy: 78.83% [2021-03-27 07:07:37 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 0/1251] eta: 1:28:55 lr: 0.000536 loss: 3.4722 (3.4722) grad_norm: 1.3090 (1.3090) time: 4.2653 [2021-03-27 07:07:43 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 10/1251] eta: 0:20:05 lr: 0.000536 loss: 3.4052 (3.3109) grad_norm: 1.4182 (1.4017) time: 0.9718 [2021-03-27 07:07:50 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 20/1251] eta: 0:16:35 lr: 0.000536 loss: 3.3793 (3.2276) grad_norm: 1.4387 (1.4625) time: 0.6357 [2021-03-27 07:07:56 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 30/1251] eta: 0:15:21 lr: 0.000536 loss: 3.3793 (3.1591) grad_norm: 1.4451 (1.4515) time: 0.6353 [2021-03-27 07:08:02 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 40/1251] eta: 0:14:37 lr: 0.000536 loss: 3.3229 (3.1480) grad_norm: 1.3782 (1.4343) time: 0.6363 [2021-03-27 07:08:09 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 50/1251] eta: 0:14:09 lr: 0.000536 loss: 3.3229 (3.1666) grad_norm: 1.3717 (1.4234) time: 0.6342 [2021-03-27 07:08:15 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 60/1251] eta: 0:13:46 lr: 0.000536 loss: 3.3506 (3.2440) grad_norm: 1.4251 (1.4416) time: 0.6311 [2021-03-27 07:08:21 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 70/1251] eta: 0:13:28 lr: 0.000536 loss: 3.5457 (3.2665) grad_norm: 1.5104 (1.4496) time: 0.6259 [2021-03-27 07:08:28 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 80/1251] eta: 0:13:14 lr: 0.000536 loss: 3.3650 (3.2550) grad_norm: 1.4892 (1.4571) time: 0.6298 [2021-03-27 07:08:34 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 90/1251] eta: 0:13:01 lr: 0.000536 loss: 2.9622 (3.2308) grad_norm: 1.5101 (1.4629) time: 0.6311 [2021-03-27 07:08:40 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 100/1251] eta: 0:12:49 lr: 0.000536 loss: 3.5829 (3.2756) grad_norm: 1.3705 (1.4525) time: 0.6284 [2021-03-27 07:08:46 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 110/1251] eta: 0:12:38 lr: 0.000536 loss: 3.6502 (3.2868) grad_norm: 1.2988 (1.4430) time: 0.6261 [2021-03-27 07:08:53 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 120/1251] eta: 0:12:28 lr: 0.000536 loss: 3.1827 (3.2787) grad_norm: 1.4264 (1.4482) time: 0.6298 [2021-03-27 07:08:59 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 130/1251] eta: 0:12:20 lr: 0.000536 loss: 3.1827 (3.2881) grad_norm: 1.5150 (1.4552) time: 0.6379 [2021-03-27 07:09:06 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 140/1251] eta: 0:12:11 lr: 0.000536 loss: 3.1739 (3.2685) grad_norm: 1.5108 (1.4591) time: 0.6367 [2021-03-27 07:09:12 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 150/1251] eta: 0:12:04 lr: 0.000535 loss: 3.0893 (3.2598) grad_norm: 1.6098 (1.4706) time: 0.6404 [2021-03-27 07:09:18 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 160/1251] eta: 0:11:56 lr: 0.000535 loss: 3.2475 (3.2585) grad_norm: 1.5964 (1.4710) time: 0.6420 [2021-03-27 07:09:25 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 170/1251] eta: 0:11:47 lr: 0.000535 loss: 3.2495 (3.2612) grad_norm: 1.5092 (1.4724) time: 0.6331 [2021-03-27 07:09:31 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 180/1251] eta: 0:11:39 lr: 0.000535 loss: 3.2169 (3.2506) grad_norm: 1.3958 (1.4686) time: 0.6310 [2021-03-27 07:09:37 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 190/1251] eta: 0:11:32 lr: 0.000535 loss: 3.3767 (3.2639) grad_norm: 1.3853 (1.4659) time: 0.6361 [2021-03-27 07:09:44 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 200/1251] eta: 0:11:24 lr: 0.000535 loss: 3.3325 (3.2592) grad_norm: 1.4086 (1.4683) time: 0.6356 [2021-03-27 07:09:50 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 210/1251] eta: 0:11:17 lr: 0.000535 loss: 3.1216 (3.2431) grad_norm: 1.4324 (1.4694) time: 0.6279 [2021-03-27 07:09:56 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 220/1251] eta: 0:11:09 lr: 0.000535 loss: 3.3705 (3.2561) grad_norm: 1.4319 (1.4680) time: 0.6304 [2021-03-27 07:10:03 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 230/1251] eta: 0:11:02 lr: 0.000535 loss: 3.4108 (3.2533) grad_norm: 1.3821 (1.4652) time: 0.6304 [2021-03-27 07:10:09 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 240/1251] eta: 0:10:55 lr: 0.000535 loss: 3.2586 (3.2556) grad_norm: 1.3811 (1.4625) time: 0.6300 [2021-03-27 07:10:15 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 250/1251] eta: 0:10:47 lr: 0.000535 loss: 3.3824 (3.2624) grad_norm: 1.3811 (1.4622) time: 0.6270 [2021-03-27 07:10:21 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 260/1251] eta: 0:10:40 lr: 0.000535 loss: 3.3147 (3.2586) grad_norm: 1.4260 (1.4643) time: 0.6264 [2021-03-27 07:10:28 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 270/1251] eta: 0:10:33 lr: 0.000535 loss: 3.2392 (3.2578) grad_norm: 1.4877 (1.4690) time: 0.6295 [2021-03-27 07:10:34 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 280/1251] eta: 0:10:26 lr: 0.000535 loss: 3.2719 (3.2553) grad_norm: 1.5137 (1.4724) time: 0.6273 [2021-03-27 07:10:40 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 290/1251] eta: 0:10:19 lr: 0.000535 loss: 3.2125 (3.2512) grad_norm: 1.4535 (1.4701) time: 0.6285 [2021-03-27 07:10:47 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 300/1251] eta: 0:10:12 lr: 0.000535 loss: 3.2275 (3.2547) grad_norm: 1.3276 (1.4668) time: 0.6255 [2021-03-27 07:10:53 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 310/1251] eta: 0:10:05 lr: 0.000535 loss: 3.5431 (3.2607) grad_norm: 1.3276 (1.4653) time: 0.6305 [2021-03-27 07:10:59 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 320/1251] eta: 0:09:58 lr: 0.000535 loss: 3.5940 (3.2638) grad_norm: 1.3509 (1.4621) time: 0.6309 [2021-03-27 07:11:05 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 330/1251] eta: 0:09:52 lr: 0.000535 loss: 3.5756 (3.2670) grad_norm: 1.4339 (1.4644) time: 0.6298 [2021-03-27 07:11:12 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 340/1251] eta: 0:09:45 lr: 0.000535 loss: 3.3151 (3.2728) grad_norm: 1.5233 (1.4658) time: 0.6336 [2021-03-27 07:11:18 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 350/1251] eta: 0:09:38 lr: 0.000535 loss: 3.3249 (3.2785) grad_norm: 1.5009 (1.4658) time: 0.6283 [2021-03-27 07:11:24 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 360/1251] eta: 0:09:31 lr: 0.000535 loss: 3.2733 (3.2787) grad_norm: 1.4188 (1.4682) time: 0.6306 [2021-03-27 07:11:31 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 370/1251] eta: 0:09:25 lr: 0.000535 loss: 3.1765 (3.2777) grad_norm: 1.4425 (1.4687) time: 0.6324 [2021-03-27 07:11:37 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 380/1251] eta: 0:09:18 lr: 0.000535 loss: 3.2642 (3.2820) grad_norm: 1.4667 (1.4720) time: 0.6359 [2021-03-27 07:11:43 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 390/1251] eta: 0:09:12 lr: 0.000534 loss: 3.5152 (3.2838) grad_norm: 1.5244 (1.4763) time: 0.6370 [2021-03-27 07:11:50 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 400/1251] eta: 0:09:05 lr: 0.000534 loss: 3.5028 (3.2838) grad_norm: 1.5082 (1.4773) time: 0.6345 [2021-03-27 07:11:56 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 410/1251] eta: 0:08:58 lr: 0.000534 loss: 3.6504 (3.2891) grad_norm: 1.4257 (1.4785) time: 0.6343 [2021-03-27 07:12:02 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 420/1251] eta: 0:08:52 lr: 0.000534 loss: 3.4271 (3.2881) grad_norm: 1.4562 (1.4800) time: 0.6255 [2021-03-27 07:12:09 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 430/1251] eta: 0:08:45 lr: 0.000534 loss: 3.4009 (3.2907) grad_norm: 1.4720 (1.4802) time: 0.6218 [2021-03-27 07:12:15 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 440/1251] eta: 0:08:38 lr: 0.000534 loss: 3.5336 (3.2920) grad_norm: 1.4960 (1.4807) time: 0.6247 [2021-03-27 07:12:21 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 450/1251] eta: 0:08:32 lr: 0.000534 loss: 3.3488 (3.2918) grad_norm: 1.4442 (1.4795) time: 0.6292 [2021-03-27 07:12:27 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 460/1251] eta: 0:08:25 lr: 0.000534 loss: 3.1668 (3.2878) grad_norm: 1.4213 (1.4795) time: 0.6320 [2021-03-27 07:12:34 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 470/1251] eta: 0:08:19 lr: 0.000534 loss: 3.1668 (3.2840) grad_norm: 1.4213 (1.4780) time: 0.6302 [2021-03-27 07:12:40 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 480/1251] eta: 0:08:12 lr: 0.000534 loss: 3.2604 (3.2789) grad_norm: 1.3829 (1.4774) time: 0.6286 [2021-03-27 07:12:46 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 490/1251] eta: 0:08:05 lr: 0.000534 loss: 3.4243 (3.2848) grad_norm: 1.3861 (1.4759) time: 0.6248 [2021-03-27 07:12:53 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 500/1251] eta: 0:07:59 lr: 0.000534 loss: 3.5092 (3.2846) grad_norm: 1.3247 (1.4745) time: 0.6293 [2021-03-27 07:12:59 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 510/1251] eta: 0:07:53 lr: 0.000534 loss: 3.4092 (3.2889) grad_norm: 1.3725 (1.4742) time: 0.6330 [2021-03-27 07:13:05 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 520/1251] eta: 0:07:46 lr: 0.000534 loss: 3.3454 (3.2873) grad_norm: 1.4336 (1.4745) time: 0.6283 [2021-03-27 07:13:12 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 530/1251] eta: 0:07:39 lr: 0.000534 loss: 3.3454 (3.2893) grad_norm: 1.4241 (1.4745) time: 0.6286 [2021-03-27 07:13:18 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 540/1251] eta: 0:07:33 lr: 0.000534 loss: 3.4909 (3.2922) grad_norm: 1.5475 (1.4799) time: 0.6266 [2021-03-27 07:13:24 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 550/1251] eta: 0:07:27 lr: 0.000534 loss: 3.3698 (3.2919) grad_norm: 1.5558 (1.4806) time: 0.6404 [2021-03-27 07:13:31 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 560/1251] eta: 0:07:20 lr: 0.000534 loss: 3.4497 (3.2953) grad_norm: 1.5411 (1.4831) time: 0.6388 [2021-03-27 07:13:37 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 570/1251] eta: 0:07:14 lr: 0.000534 loss: 3.4497 (3.2980) grad_norm: 1.5042 (1.4819) time: 0.6215 [2021-03-27 07:13:43 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 580/1251] eta: 0:07:07 lr: 0.000534 loss: 3.4164 (3.3004) grad_norm: 1.4031 (1.4818) time: 0.6224 [2021-03-27 07:13:49 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 590/1251] eta: 0:07:01 lr: 0.000534 loss: 3.4417 (3.3001) grad_norm: 1.4754 (1.4823) time: 0.6277 [2021-03-27 07:13:56 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 600/1251] eta: 0:06:54 lr: 0.000534 loss: 3.4597 (3.3009) grad_norm: 1.4718 (1.4830) time: 0.6297 [2021-03-27 07:14:02 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 610/1251] eta: 0:06:48 lr: 0.000534 loss: 2.9366 (3.2931) grad_norm: 1.4115 (1.4819) time: 0.6287 [2021-03-27 07:14:08 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 620/1251] eta: 0:06:41 lr: 0.000534 loss: 2.9366 (3.2918) grad_norm: 1.4684 (1.4824) time: 0.6299 [2021-03-27 07:14:14 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 630/1251] eta: 0:06:35 lr: 0.000533 loss: 3.5406 (3.2970) grad_norm: 1.4804 (1.4830) time: 0.6283 [2021-03-27 07:14:21 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 640/1251] eta: 0:06:28 lr: 0.000533 loss: 3.5070 (3.2933) grad_norm: 1.4334 (1.4831) time: 0.6260 [2021-03-27 07:14:27 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 650/1251] eta: 0:06:22 lr: 0.000533 loss: 3.3311 (3.2945) grad_norm: 1.4799 (1.4841) time: 0.6247 [2021-03-27 07:14:33 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 660/1251] eta: 0:06:15 lr: 0.000533 loss: 3.4435 (3.2940) grad_norm: 1.4897 (1.4840) time: 0.6295 [2021-03-27 07:14:40 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 670/1251] eta: 0:06:09 lr: 0.000533 loss: 3.3515 (3.2934) grad_norm: 1.4126 (1.4828) time: 0.6330 [2021-03-27 07:14:46 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 680/1251] eta: 0:06:03 lr: 0.000533 loss: 3.1937 (3.2889) grad_norm: 1.4137 (1.4841) time: 0.6315 [2021-03-27 07:14:52 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 690/1251] eta: 0:05:56 lr: 0.000533 loss: 3.3986 (3.2924) grad_norm: 1.4635 (1.4842) time: 0.6351 [2021-03-27 07:14:59 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 700/1251] eta: 0:05:50 lr: 0.000533 loss: 3.3340 (3.2897) grad_norm: 1.3811 (1.4834) time: 0.6323 [2021-03-27 07:15:05 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 710/1251] eta: 0:05:44 lr: 0.000533 loss: 3.0658 (3.2897) grad_norm: 1.3947 (1.4823) time: 0.6283 [2021-03-27 07:15:11 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 720/1251] eta: 0:05:37 lr: 0.000533 loss: 3.2327 (3.2893) grad_norm: 1.4895 (1.4839) time: 0.6315 [2021-03-27 07:15:18 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 730/1251] eta: 0:05:31 lr: 0.000533 loss: 3.4073 (3.2877) grad_norm: 1.5527 (1.4850) time: 0.6334 [2021-03-27 07:15:24 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 740/1251] eta: 0:05:24 lr: 0.000533 loss: 3.2493 (3.2859) grad_norm: 1.3978 (1.4838) time: 0.6383 [2021-03-27 07:15:30 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 750/1251] eta: 0:05:18 lr: 0.000533 loss: 3.2493 (3.2851) grad_norm: 1.3978 (1.4846) time: 0.6354 [2021-03-27 07:15:37 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 760/1251] eta: 0:05:12 lr: 0.000533 loss: 3.4951 (3.2885) grad_norm: 1.3404 (1.4826) time: 0.6293 [2021-03-27 07:15:43 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 770/1251] eta: 0:05:05 lr: 0.000533 loss: 3.5568 (3.2913) grad_norm: 1.3247 (1.4814) time: 0.6272 [2021-03-27 07:15:49 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 780/1251] eta: 0:04:59 lr: 0.000533 loss: 3.4986 (3.2905) grad_norm: 1.4158 (1.4828) time: 0.6332 [2021-03-27 07:15:56 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 790/1251] eta: 0:04:52 lr: 0.000533 loss: 3.4986 (3.2925) grad_norm: 1.4158 (1.4831) time: 0.6338 [2021-03-27 07:16:02 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 800/1251] eta: 0:04:46 lr: 0.000533 loss: 3.6319 (3.2970) grad_norm: 1.3686 (1.4822) time: 0.6280 [2021-03-27 07:16:08 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 810/1251] eta: 0:04:40 lr: 0.000533 loss: 3.4176 (3.2947) grad_norm: 1.4139 (1.4814) time: 0.6277 [2021-03-27 07:16:14 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 820/1251] eta: 0:04:33 lr: 0.000533 loss: 3.3468 (3.2956) grad_norm: 1.4317 (1.4814) time: 0.6243 [2021-03-27 07:16:21 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 830/1251] eta: 0:04:27 lr: 0.000533 loss: 3.3203 (3.2949) grad_norm: 1.4415 (1.4817) time: 0.6233 [2021-03-27 07:16:27 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 840/1251] eta: 0:04:20 lr: 0.000533 loss: 3.2944 (3.2953) grad_norm: 1.4422 (1.4816) time: 0.6234 [2021-03-27 07:16:33 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 850/1251] eta: 0:04:14 lr: 0.000533 loss: 3.4426 (3.2950) grad_norm: 1.4422 (1.4811) time: 0.6237 [2021-03-27 07:16:39 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 860/1251] eta: 0:04:08 lr: 0.000533 loss: 3.4448 (3.2960) grad_norm: 1.4589 (1.4819) time: 0.6255 [2021-03-27 07:16:46 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 870/1251] eta: 0:04:01 lr: 0.000532 loss: 3.5145 (3.2974) grad_norm: 1.4985 (1.4833) time: 0.6337 [2021-03-27 07:16:52 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 880/1251] eta: 0:03:55 lr: 0.000532 loss: 3.4585 (3.2952) grad_norm: 1.4949 (1.4836) time: 0.6454 [2021-03-27 07:16:59 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 890/1251] eta: 0:03:49 lr: 0.000532 loss: 3.3289 (3.2968) grad_norm: 1.4465 (1.4834) time: 0.6409 [2021-03-27 07:17:05 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 900/1251] eta: 0:03:42 lr: 0.000532 loss: 3.5260 (3.2985) grad_norm: 1.4237 (1.4834) time: 0.6412 [2021-03-27 07:17:11 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 910/1251] eta: 0:03:36 lr: 0.000532 loss: 3.3697 (3.2984) grad_norm: 1.4275 (1.4841) time: 0.6414 [2021-03-27 07:17:18 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 920/1251] eta: 0:03:30 lr: 0.000532 loss: 3.3697 (3.3001) grad_norm: 1.4771 (1.4846) time: 0.6306 [2021-03-27 07:17:24 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 930/1251] eta: 0:03:23 lr: 0.000532 loss: 3.4598 (3.3021) grad_norm: 1.4788 (1.4852) time: 0.6283 [2021-03-27 07:17:30 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 940/1251] eta: 0:03:17 lr: 0.000532 loss: 3.3615 (3.3033) grad_norm: 1.5392 (1.4851) time: 0.6301 [2021-03-27 07:17:37 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 950/1251] eta: 0:03:11 lr: 0.000532 loss: 3.4145 (3.3055) grad_norm: 1.4892 (1.4853) time: 0.6332 [2021-03-27 07:17:43 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 960/1251] eta: 0:03:04 lr: 0.000532 loss: 3.4115 (3.3028) grad_norm: 1.4643 (1.4851) time: 0.6350 [2021-03-27 07:17:49 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 970/1251] eta: 0:02:58 lr: 0.000532 loss: 3.0940 (3.3020) grad_norm: 1.4194 (1.4845) time: 0.6389 [2021-03-27 07:17:56 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 980/1251] eta: 0:02:52 lr: 0.000532 loss: 3.1335 (3.3009) grad_norm: 1.4032 (1.4836) time: 0.6351 [2021-03-27 07:18:02 swin_base_patch4_window7_224] INFO: Epoch: [144] [ 990/1251] eta: 0:02:45 lr: 0.000532 loss: 3.0787 (3.2993) grad_norm: 1.4189 (1.4834) time: 0.6271 [2021-03-27 07:18:08 swin_base_patch4_window7_224] INFO: Epoch: [144] [1000/1251] eta: 0:02:39 lr: 0.000532 loss: 3.2917 (3.2991) grad_norm: 1.3910 (1.4832) time: 0.6270 [2021-03-27 07:18:14 swin_base_patch4_window7_224] INFO: Epoch: [144] [1010/1251] eta: 0:02:32 lr: 0.000532 loss: 3.3829 (3.2988) grad_norm: 1.4489 (1.4833) time: 0.6288 [2021-03-27 07:18:21 swin_base_patch4_window7_224] INFO: Epoch: [144] [1020/1251] eta: 0:02:26 lr: 0.000532 loss: 3.1623 (3.2959) grad_norm: 1.4624 (inf) time: 0.6245 [2021-03-27 07:18:27 swin_base_patch4_window7_224] INFO: Epoch: [144] [1030/1251] eta: 0:02:20 lr: 0.000532 loss: 3.2868 (3.2975) grad_norm: 1.4626 (inf) time: 0.6243 [2021-03-27 07:18:33 swin_base_patch4_window7_224] INFO: Epoch: [144] [1040/1251] eta: 0:02:13 lr: 0.000532 loss: 3.3581 (3.2968) grad_norm: 1.4615 (inf) time: 0.6322 [2021-03-27 07:18:40 swin_base_patch4_window7_224] INFO: Epoch: [144] [1050/1251] eta: 0:02:07 lr: 0.000532 loss: 3.3150 (3.2970) grad_norm: 1.4292 (inf) time: 0.6323 [2021-03-27 07:18:46 swin_base_patch4_window7_224] INFO: Epoch: [144] [1060/1251] eta: 0:02:01 lr: 0.000532 loss: 3.5223 (3.2996) grad_norm: 1.3982 (inf) time: 0.6296 [2021-03-27 07:18:52 swin_base_patch4_window7_224] INFO: Epoch: [144] [1070/1251] eta: 0:01:54 lr: 0.000532 loss: 3.5398 (3.3015) grad_norm: 1.4268 (inf) time: 0.6286 [2021-03-27 07:18:59 swin_base_patch4_window7_224] INFO: Epoch: [144] [1080/1251] eta: 0:01:48 lr: 0.000532 loss: 3.4187 (3.3032) grad_norm: 1.4826 (inf) time: 0.6293 [2021-03-27 07:19:05 swin_base_patch4_window7_224] INFO: Epoch: [144] [1090/1251] eta: 0:01:42 lr: 0.000532 loss: 3.5815 (3.3035) grad_norm: 1.4273 (inf) time: 0.6291 [2021-03-27 07:19:11 swin_base_patch4_window7_224] INFO: Epoch: [144] [1100/1251] eta: 0:01:35 lr: 0.000532 loss: 3.2340 (3.3015) grad_norm: 1.4892 (inf) time: 0.6275 [2021-03-27 07:19:17 swin_base_patch4_window7_224] INFO: Epoch: [144] [1110/1251] eta: 0:01:29 lr: 0.000531 loss: 3.2872 (3.3018) grad_norm: 1.4982 (inf) time: 0.6243 [2021-03-27 07:19:23 swin_base_patch4_window7_224] INFO: Epoch: [144] [1120/1251] eta: 0:01:23 lr: 0.000531 loss: 3.3366 (3.3008) grad_norm: 1.4239 (inf) time: 0.6203 [2021-03-27 07:19:30 swin_base_patch4_window7_224] INFO: Epoch: [144] [1130/1251] eta: 0:01:16 lr: 0.000531 loss: 3.2834 (3.3010) grad_norm: 1.4823 (inf) time: 0.6238 [2021-03-27 07:19:36 swin_base_patch4_window7_224] INFO: Epoch: [144] [1140/1251] eta: 0:01:10 lr: 0.000531 loss: 3.3429 (3.3013) grad_norm: 1.4823 (inf) time: 0.6309 [2021-03-27 07:19:42 swin_base_patch4_window7_224] INFO: Epoch: [144] [1150/1251] eta: 0:01:04 lr: 0.000531 loss: 3.3429 (3.2996) grad_norm: 1.4218 (inf) time: 0.6363 [2021-03-27 07:19:49 swin_base_patch4_window7_224] INFO: Epoch: [144] [1160/1251] eta: 0:00:57 lr: 0.000531 loss: 3.3961 (3.3013) grad_norm: 1.4719 (inf) time: 0.6455 [2021-03-27 07:19:55 swin_base_patch4_window7_224] INFO: Epoch: [144] [1170/1251] eta: 0:00:51 lr: 0.000531 loss: 3.4778 (3.3008) grad_norm: 1.4751 (inf) time: 0.6407 [2021-03-27 07:20:02 swin_base_patch4_window7_224] INFO: Epoch: [144] [1180/1251] eta: 0:00:45 lr: 0.000531 loss: 3.4693 (3.3020) grad_norm: 1.4465 (inf) time: 0.6281 [2021-03-27 07:20:08 swin_base_patch4_window7_224] INFO: Epoch: [144] [1190/1251] eta: 0:00:38 lr: 0.000531 loss: 3.5137 (3.3039) grad_norm: 1.5208 (inf) time: 0.6256 [2021-03-27 07:20:14 swin_base_patch4_window7_224] INFO: Epoch: [144] [1200/1251] eta: 0:00:32 lr: 0.000531 loss: 3.4709 (3.3018) grad_norm: 1.4978 (inf) time: 0.6269 [2021-03-27 07:20:20 swin_base_patch4_window7_224] INFO: Epoch: [144] [1210/1251] eta: 0:00:25 lr: 0.000531 loss: 3.3645 (3.3038) grad_norm: 1.4787 (inf) time: 0.6284 [2021-03-27 07:20:27 swin_base_patch4_window7_224] INFO: Epoch: [144] [1220/1251] eta: 0:00:19 lr: 0.000531 loss: 3.3645 (3.3044) grad_norm: 1.4995 (inf) time: 0.6275 [2021-03-27 07:20:33 swin_base_patch4_window7_224] INFO: Epoch: [144] [1230/1251] eta: 0:00:13 lr: 0.000531 loss: 3.1557 (3.3033) grad_norm: 1.5123 (inf) time: 0.6311 [2021-03-27 07:20:39 swin_base_patch4_window7_224] INFO: Epoch: [144] [1240/1251] eta: 0:00:06 lr: 0.000531 loss: 3.0294 (3.3036) grad_norm: 1.4309 (inf) time: 0.6277 [2021-03-27 07:20:45 swin_base_patch4_window7_224] INFO: Epoch: [144] [1250/1251] eta: 0:00:00 lr: 0.000531 loss: 3.2729 (3.3032) grad_norm: 1.3981 (inf) time: 0.6156 [2021-03-27 07:20:54 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:10 loss: 0.9792 (0.9792) acc1: 76.5625 (76.5625) acc5: 98.4375 (98.4375) [2021-03-27 07:20:58 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.9792 (0.9997) acc1: 78.1250 (77.6989) acc5: 93.7500 (93.8920) [2021-03-27 07:21:00 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.9360 (0.9707) acc1: 78.1250 (78.0506) acc5: 95.3125 (94.6429) [2021-03-27 07:21:03 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8936 (0.9617) acc1: 81.2500 (78.4274) acc5: 95.3125 (94.7581) [2021-03-27 07:21:04 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8638 (0.9523) acc1: 79.6875 (77.8963) acc5: 95.3125 (95.0838) [2021-03-27 07:21:05 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8298 (0.9421) acc1: 79.6875 (78.1120) acc5: 95.3125 (95.0080) [2021-03-27 07:21:13 swin_base_patch4_window7_224] INFO: * Acc@1 78.640 Acc@5 94.684 loss 0.933 [2021-03-27 07:21:13 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.6% [2021-03-27 07:21:13 swin_base_patch4_window7_224] INFO: Max accuracy: 78.83% [2021-03-27 07:21:17 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 0/1251] eta: 1:29:09 lr: 0.000531 loss: 2.3924 (2.3924) grad_norm: 1.5746 (1.5746) time: 4.2759 [2021-03-27 07:21:24 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 10/1251] eta: 0:19:59 lr: 0.000531 loss: 3.3985 (3.2769) grad_norm: 1.4789 (1.4921) time: 0.9663 [2021-03-27 07:21:30 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 20/1251] eta: 0:16:33 lr: 0.000531 loss: 3.3985 (3.2848) grad_norm: 1.4665 (1.5006) time: 0.6335 [2021-03-27 07:21:36 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 30/1251] eta: 0:15:14 lr: 0.000531 loss: 3.2345 (3.1870) grad_norm: 1.4665 (1.5090) time: 0.6296 [2021-03-27 07:21:43 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 40/1251] eta: 0:14:34 lr: 0.000531 loss: 3.2214 (3.2059) grad_norm: 1.4373 (1.5121) time: 0.6323 [2021-03-27 07:21:49 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 50/1251] eta: 0:14:05 lr: 0.000531 loss: 3.2895 (3.2309) grad_norm: 1.3852 (1.5002) time: 0.6339 [2021-03-27 07:21:55 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 60/1251] eta: 0:13:42 lr: 0.000531 loss: 3.2357 (3.1951) grad_norm: 1.3828 (1.4991) time: 0.6268 [2021-03-27 07:22:01 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 70/1251] eta: 0:13:25 lr: 0.000531 loss: 3.2357 (3.2346) grad_norm: 1.4429 (1.5029) time: 0.6259 [2021-03-27 07:22:08 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 80/1251] eta: 0:13:11 lr: 0.000531 loss: 3.5394 (3.2466) grad_norm: 1.4299 (1.4882) time: 0.6299 [2021-03-27 07:22:14 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 90/1251] eta: 0:12:58 lr: 0.000531 loss: 3.3785 (3.2607) grad_norm: 1.4299 (1.4882) time: 0.6314 [2021-03-27 07:22:20 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 100/1251] eta: 0:12:48 lr: 0.000530 loss: 3.3785 (3.2706) grad_norm: 1.4432 (1.4896) time: 0.6348 [2021-03-27 07:22:27 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 110/1251] eta: 0:12:37 lr: 0.000530 loss: 3.5654 (3.2736) grad_norm: 1.4177 (1.4817) time: 0.6307 [2021-03-27 07:22:33 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 120/1251] eta: 0:12:27 lr: 0.000530 loss: 3.5853 (3.2919) grad_norm: 1.4079 (1.4822) time: 0.6301 [2021-03-27 07:22:39 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 130/1251] eta: 0:12:18 lr: 0.000530 loss: 3.5853 (3.3028) grad_norm: 1.5267 (1.4880) time: 0.6329 [2021-03-27 07:22:46 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 140/1251] eta: 0:12:08 lr: 0.000530 loss: 3.4337 (3.3010) grad_norm: 1.6318 (1.4967) time: 0.6245 [2021-03-27 07:22:52 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 150/1251] eta: 0:12:00 lr: 0.000530 loss: 3.5763 (3.3204) grad_norm: 1.5579 (1.4995) time: 0.6230 [2021-03-27 07:22:58 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 160/1251] eta: 0:11:52 lr: 0.000530 loss: 3.5763 (3.3226) grad_norm: 1.4212 (1.4898) time: 0.6310 [2021-03-27 07:23:05 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 170/1251] eta: 0:11:44 lr: 0.000530 loss: 3.5101 (3.3342) grad_norm: 1.4329 (1.4947) time: 0.6367 [2021-03-27 07:23:11 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 180/1251] eta: 0:11:37 lr: 0.000530 loss: 3.5359 (3.3367) grad_norm: 1.4640 (1.4907) time: 0.6365 [2021-03-27 07:23:17 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 190/1251] eta: 0:11:29 lr: 0.000530 loss: 3.4452 (3.3272) grad_norm: 1.3895 (1.4877) time: 0.6323 [2021-03-27 07:23:23 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 200/1251] eta: 0:11:21 lr: 0.000530 loss: 3.1701 (3.3275) grad_norm: 1.4019 (1.4892) time: 0.6281 [2021-03-27 07:23:30 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 210/1251] eta: 0:11:14 lr: 0.000530 loss: 3.5005 (3.3414) grad_norm: 1.4333 (1.4941) time: 0.6275 [2021-03-27 07:23:36 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 220/1251] eta: 0:11:07 lr: 0.000530 loss: 3.5005 (3.3291) grad_norm: 1.4067 (1.4894) time: 0.6286 [2021-03-27 07:23:42 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 230/1251] eta: 0:10:59 lr: 0.000530 loss: 3.3641 (3.3340) grad_norm: 1.3461 (1.4882) time: 0.6277 [2021-03-27 07:23:49 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 240/1251] eta: 0:10:52 lr: 0.000530 loss: 3.3641 (3.3338) grad_norm: 1.3880 (1.4865) time: 0.6309 [2021-03-27 07:23:55 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 250/1251] eta: 0:10:46 lr: 0.000530 loss: 3.2091 (3.3216) grad_norm: 1.3880 (1.4816) time: 0.6386 [2021-03-27 07:24:01 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 260/1251] eta: 0:10:39 lr: 0.000530 loss: 3.3243 (3.3175) grad_norm: 1.3730 (1.4814) time: 0.6395 [2021-03-27 07:24:08 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 270/1251] eta: 0:10:32 lr: 0.000530 loss: 3.4026 (3.3230) grad_norm: 1.5143 (1.4848) time: 0.6398 [2021-03-27 07:24:14 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 280/1251] eta: 0:10:26 lr: 0.000530 loss: 3.4448 (3.3275) grad_norm: 1.5205 (1.4880) time: 0.6421 [2021-03-27 07:24:21 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 290/1251] eta: 0:10:19 lr: 0.000530 loss: 3.3248 (3.3284) grad_norm: 1.4763 (1.4873) time: 0.6333 [2021-03-27 07:24:27 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 300/1251] eta: 0:10:12 lr: 0.000530 loss: 3.6313 (3.3393) grad_norm: 1.4146 (1.4858) time: 0.6247 [2021-03-27 07:24:33 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 310/1251] eta: 0:10:05 lr: 0.000530 loss: 3.5380 (3.3289) grad_norm: 1.4235 (1.4844) time: 0.6267 [2021-03-27 07:24:39 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 320/1251] eta: 0:09:58 lr: 0.000530 loss: 3.3175 (3.3270) grad_norm: 1.4818 (1.4870) time: 0.6332 [2021-03-27 07:24:46 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 330/1251] eta: 0:09:51 lr: 0.000530 loss: 3.3175 (3.3244) grad_norm: 1.4820 (1.4861) time: 0.6308 [2021-03-27 07:24:52 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 340/1251] eta: 0:09:45 lr: 0.000529 loss: 3.2763 (3.3206) grad_norm: 1.3890 (1.4858) time: 0.6310 [2021-03-27 07:24:58 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 350/1251] eta: 0:09:38 lr: 0.000529 loss: 3.4305 (3.3246) grad_norm: 1.3890 (1.4858) time: 0.6345 [2021-03-27 07:25:05 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 360/1251] eta: 0:09:31 lr: 0.000529 loss: 3.3144 (3.3217) grad_norm: 1.4773 (1.4882) time: 0.6299 [2021-03-27 07:25:11 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 370/1251] eta: 0:09:24 lr: 0.000529 loss: 3.2964 (3.3240) grad_norm: 1.4863 (1.4870) time: 0.6261 [2021-03-27 07:25:17 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 380/1251] eta: 0:09:18 lr: 0.000529 loss: 3.5082 (3.3273) grad_norm: 1.4638 (1.4866) time: 0.6266 [2021-03-27 07:25:24 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 390/1251] eta: 0:09:11 lr: 0.000529 loss: 3.5737 (3.3336) grad_norm: 1.4427 (1.4858) time: 0.6349 [2021-03-27 07:25:30 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 400/1251] eta: 0:09:04 lr: 0.000529 loss: 3.4802 (3.3320) grad_norm: 1.4453 (1.4856) time: 0.6305 [2021-03-27 07:25:36 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 410/1251] eta: 0:08:58 lr: 0.000529 loss: 3.3363 (3.3276) grad_norm: 1.5083 (1.4867) time: 0.6228 [2021-03-27 07:25:42 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 420/1251] eta: 0:08:51 lr: 0.000529 loss: 3.4006 (3.3288) grad_norm: 1.5083 (1.4866) time: 0.6299 [2021-03-27 07:25:49 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 430/1251] eta: 0:08:45 lr: 0.000529 loss: 3.4006 (3.3316) grad_norm: 1.3958 (1.4844) time: 0.6302 [2021-03-27 07:25:55 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 440/1251] eta: 0:08:38 lr: 0.000529 loss: 3.2895 (3.3263) grad_norm: 1.4300 (1.4837) time: 0.6360 [2021-03-27 07:26:01 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 450/1251] eta: 0:08:32 lr: 0.000529 loss: 3.2823 (3.3222) grad_norm: 1.4631 (1.4841) time: 0.6381 [2021-03-27 07:26:08 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 460/1251] eta: 0:08:25 lr: 0.000529 loss: 3.2529 (3.3208) grad_norm: 1.4742 (1.4858) time: 0.6352 [2021-03-27 07:26:14 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 470/1251] eta: 0:08:19 lr: 0.000529 loss: 3.2712 (3.3207) grad_norm: 1.4402 (1.4833) time: 0.6335 [2021-03-27 07:26:21 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 480/1251] eta: 0:08:12 lr: 0.000529 loss: 3.4198 (3.3194) grad_norm: 1.4086 (1.4841) time: 0.6307 [2021-03-27 07:26:27 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 490/1251] eta: 0:08:06 lr: 0.000529 loss: 3.0331 (3.3141) grad_norm: 1.4671 (1.4856) time: 0.6306 [2021-03-27 07:26:33 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 500/1251] eta: 0:07:59 lr: 0.000529 loss: 3.0486 (3.3120) grad_norm: 1.4070 (1.4855) time: 0.6328 [2021-03-27 07:26:40 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 510/1251] eta: 0:07:53 lr: 0.000529 loss: 3.3963 (3.3105) grad_norm: 1.4070 (1.4857) time: 0.6392 [2021-03-27 07:26:46 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 520/1251] eta: 0:07:46 lr: 0.000529 loss: 3.3963 (3.3150) grad_norm: 1.4373 (1.4852) time: 0.6352 [2021-03-27 07:26:52 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 530/1251] eta: 0:07:40 lr: 0.000529 loss: 3.6350 (3.3234) grad_norm: 1.4700 (1.4846) time: 0.6316 [2021-03-27 07:26:58 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 540/1251] eta: 0:07:33 lr: 0.000529 loss: 3.6350 (3.3253) grad_norm: 1.4824 (1.4872) time: 0.6292 [2021-03-27 07:27:05 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 550/1251] eta: 0:07:27 lr: 0.000529 loss: 3.4134 (3.3248) grad_norm: 1.5550 (1.4875) time: 0.6367 [2021-03-27 07:27:11 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 560/1251] eta: 0:07:21 lr: 0.000529 loss: 3.3626 (3.3203) grad_norm: 1.5650 (1.4891) time: 0.6433 [2021-03-27 07:27:18 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 570/1251] eta: 0:07:14 lr: 0.000529 loss: 3.3558 (3.3220) grad_norm: 1.5856 (1.4894) time: 0.6381 [2021-03-27 07:27:24 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 580/1251] eta: 0:07:08 lr: 0.000529 loss: 3.2958 (3.3201) grad_norm: 1.4366 (1.4897) time: 0.6334 [2021-03-27 07:27:30 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 590/1251] eta: 0:07:01 lr: 0.000528 loss: 3.2789 (3.3184) grad_norm: 1.4366 (1.4883) time: 0.6317 [2021-03-27 07:27:37 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 600/1251] eta: 0:06:55 lr: 0.000528 loss: 3.4045 (3.3209) grad_norm: 1.3594 (1.4863) time: 0.6285 [2021-03-27 07:27:43 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 610/1251] eta: 0:06:48 lr: 0.000528 loss: 3.4285 (3.3224) grad_norm: 1.3450 (1.4846) time: 0.6301 [2021-03-27 07:27:49 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 620/1251] eta: 0:06:42 lr: 0.000528 loss: 3.3957 (3.3227) grad_norm: 1.4233 (1.4838) time: 0.6330 [2021-03-27 07:27:56 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 630/1251] eta: 0:06:36 lr: 0.000528 loss: 3.5418 (3.3242) grad_norm: 1.4590 (1.4836) time: 0.6332 [2021-03-27 07:28:02 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 640/1251] eta: 0:06:29 lr: 0.000528 loss: 3.4375 (3.3233) grad_norm: 1.4788 (1.4842) time: 0.6339 [2021-03-27 07:28:08 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 650/1251] eta: 0:06:23 lr: 0.000528 loss: 3.4479 (3.3262) grad_norm: 1.4099 (1.4832) time: 0.6300 [2021-03-27 07:28:15 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 660/1251] eta: 0:06:16 lr: 0.000528 loss: 3.5787 (3.3258) grad_norm: 1.3549 (1.4819) time: 0.6320 [2021-03-27 07:28:21 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 670/1251] eta: 0:06:10 lr: 0.000528 loss: 3.4624 (3.3234) grad_norm: 1.3812 (1.4808) time: 0.6341 [2021-03-27 07:28:27 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 680/1251] eta: 0:06:03 lr: 0.000528 loss: 3.2892 (3.3218) grad_norm: 1.4451 (1.4803) time: 0.6307 [2021-03-27 07:28:33 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 690/1251] eta: 0:05:57 lr: 0.000528 loss: 3.4887 (3.3260) grad_norm: 1.4541 (1.4806) time: 0.6290 [2021-03-27 07:28:40 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 700/1251] eta: 0:05:51 lr: 0.000528 loss: 3.4977 (3.3241) grad_norm: 1.5052 (1.4817) time: 0.6257 [2021-03-27 07:28:46 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 710/1251] eta: 0:05:44 lr: 0.000528 loss: 3.4514 (3.3240) grad_norm: 1.4727 (1.4817) time: 0.6282 [2021-03-27 07:28:52 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 720/1251] eta: 0:05:38 lr: 0.000528 loss: 3.4514 (3.3218) grad_norm: 1.4727 (1.4834) time: 0.6360 [2021-03-27 07:28:59 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 730/1251] eta: 0:05:31 lr: 0.000528 loss: 3.3376 (3.3209) grad_norm: 1.4064 (1.4831) time: 0.6306 [2021-03-27 07:29:05 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 740/1251] eta: 0:05:25 lr: 0.000528 loss: 3.2743 (3.3199) grad_norm: 1.4282 (1.4854) time: 0.6333 [2021-03-27 07:29:11 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 750/1251] eta: 0:05:19 lr: 0.000528 loss: 3.3722 (3.3225) grad_norm: 1.5479 (1.4871) time: 0.6401 [2021-03-27 07:29:18 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 760/1251] eta: 0:05:12 lr: 0.000528 loss: 3.3722 (3.3195) grad_norm: 1.4467 (1.4867) time: 0.6345 [2021-03-27 07:29:24 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 770/1251] eta: 0:05:06 lr: 0.000528 loss: 3.4437 (3.3213) grad_norm: 1.4819 (1.4875) time: 0.6333 [2021-03-27 07:29:30 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 780/1251] eta: 0:04:59 lr: 0.000528 loss: 3.6709 (3.3246) grad_norm: 1.4544 (1.4861) time: 0.6314 [2021-03-27 07:29:37 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 790/1251] eta: 0:04:53 lr: 0.000528 loss: 3.1797 (3.3214) grad_norm: 1.3928 (1.4856) time: 0.6334 [2021-03-27 07:29:43 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 800/1251] eta: 0:04:47 lr: 0.000528 loss: 3.2893 (3.3229) grad_norm: 1.4188 (1.4872) time: 0.6325 [2021-03-27 07:29:50 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 810/1251] eta: 0:04:40 lr: 0.000528 loss: 3.4909 (3.3252) grad_norm: 1.4188 (1.4863) time: 0.6347 [2021-03-27 07:29:56 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 820/1251] eta: 0:04:34 lr: 0.000528 loss: 3.3078 (3.3221) grad_norm: 1.4248 (1.4860) time: 0.6370 [2021-03-27 07:30:02 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 830/1251] eta: 0:04:28 lr: 0.000527 loss: 3.2447 (3.3217) grad_norm: 1.4181 (1.4845) time: 0.6384 [2021-03-27 07:30:09 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 840/1251] eta: 0:04:21 lr: 0.000527 loss: 3.3888 (3.3217) grad_norm: 1.3868 (1.4839) time: 0.6462 [2021-03-27 07:30:15 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 850/1251] eta: 0:04:15 lr: 0.000527 loss: 3.5152 (3.3222) grad_norm: 1.3686 (1.4822) time: 0.6413 [2021-03-27 07:30:21 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 860/1251] eta: 0:04:08 lr: 0.000527 loss: 3.2078 (3.3208) grad_norm: 1.3778 (1.4822) time: 0.6342 [2021-03-27 07:30:28 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 870/1251] eta: 0:04:02 lr: 0.000527 loss: 3.1386 (3.3176) grad_norm: 1.3800 (1.4815) time: 0.6357 [2021-03-27 07:30:34 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 880/1251] eta: 0:03:56 lr: 0.000527 loss: 3.2175 (3.3190) grad_norm: 1.4229 (1.4827) time: 0.6347 [2021-03-27 07:30:40 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 890/1251] eta: 0:03:49 lr: 0.000527 loss: 3.3534 (3.3182) grad_norm: 1.5207 (1.4835) time: 0.6281 [2021-03-27 07:30:47 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 900/1251] eta: 0:03:43 lr: 0.000527 loss: 3.4015 (3.3185) grad_norm: 1.4514 (1.4833) time: 0.6273 [2021-03-27 07:30:53 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 910/1251] eta: 0:03:37 lr: 0.000527 loss: 3.4164 (3.3174) grad_norm: 1.4502 (1.4830) time: 0.6375 [2021-03-27 07:30:59 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 920/1251] eta: 0:03:30 lr: 0.000527 loss: 3.3890 (3.3183) grad_norm: 1.3680 (1.4824) time: 0.6345 [2021-03-27 07:31:06 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 930/1251] eta: 0:03:24 lr: 0.000527 loss: 3.3514 (3.3171) grad_norm: 1.4254 (1.4829) time: 0.6207 [2021-03-27 07:31:12 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 940/1251] eta: 0:03:17 lr: 0.000527 loss: 3.3514 (3.3171) grad_norm: 1.4825 (1.4835) time: 0.6244 [2021-03-27 07:31:18 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 950/1251] eta: 0:03:11 lr: 0.000527 loss: 3.3176 (3.3173) grad_norm: 1.5070 (1.4841) time: 0.6277 [2021-03-27 07:31:24 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 960/1251] eta: 0:03:05 lr: 0.000527 loss: 3.1042 (3.3151) grad_norm: 1.4863 (1.4838) time: 0.6241 [2021-03-27 07:31:31 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 970/1251] eta: 0:02:58 lr: 0.000527 loss: 3.2295 (3.3147) grad_norm: 1.3754 (1.4830) time: 0.6254 [2021-03-27 07:31:37 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 980/1251] eta: 0:02:52 lr: 0.000527 loss: 3.2456 (3.3158) grad_norm: 1.3754 (1.4824) time: 0.6279 [2021-03-27 07:31:43 swin_base_patch4_window7_224] INFO: Epoch: [145] [ 990/1251] eta: 0:02:45 lr: 0.000527 loss: 3.3997 (3.3145) grad_norm: 1.3899 (1.4812) time: 0.6332 [2021-03-27 07:31:50 swin_base_patch4_window7_224] INFO: Epoch: [145] [1000/1251] eta: 0:02:39 lr: 0.000527 loss: 3.3424 (3.3141) grad_norm: 1.3752 (1.4809) time: 0.6363 [2021-03-27 07:31:56 swin_base_patch4_window7_224] INFO: Epoch: [145] [1010/1251] eta: 0:02:33 lr: 0.000527 loss: 3.3999 (3.3135) grad_norm: 1.3916 (1.4809) time: 0.6285 [2021-03-27 07:32:02 swin_base_patch4_window7_224] INFO: Epoch: [145] [1020/1251] eta: 0:02:26 lr: 0.000527 loss: 3.2309 (3.3110) grad_norm: 1.5031 (1.4809) time: 0.6269 [2021-03-27 07:32:09 swin_base_patch4_window7_224] INFO: Epoch: [145] [1030/1251] eta: 0:02:20 lr: 0.000527 loss: 3.1552 (3.3107) grad_norm: 1.4195 (1.4807) time: 0.6321 [2021-03-27 07:32:15 swin_base_patch4_window7_224] INFO: Epoch: [145] [1040/1251] eta: 0:02:14 lr: 0.000527 loss: 3.2855 (3.3108) grad_norm: 1.3930 (1.4800) time: 0.6265 [2021-03-27 07:32:21 swin_base_patch4_window7_224] INFO: Epoch: [145] [1050/1251] eta: 0:02:07 lr: 0.000527 loss: 3.3111 (3.3094) grad_norm: 1.3792 (1.4797) time: 0.6219 [2021-03-27 07:32:27 swin_base_patch4_window7_224] INFO: Epoch: [145] [1060/1251] eta: 0:02:01 lr: 0.000527 loss: 3.3822 (3.3104) grad_norm: 1.3924 (1.4795) time: 0.6299 [2021-03-27 07:32:34 swin_base_patch4_window7_224] INFO: Epoch: [145] [1070/1251] eta: 0:01:54 lr: 0.000526 loss: 3.3847 (3.3106) grad_norm: 1.4438 (1.4799) time: 0.6351 [2021-03-27 07:32:40 swin_base_patch4_window7_224] INFO: Epoch: [145] [1080/1251] eta: 0:01:48 lr: 0.000526 loss: 3.4290 (3.3112) grad_norm: 1.5060 (1.4800) time: 0.6331 [2021-03-27 07:32:46 swin_base_patch4_window7_224] INFO: Epoch: [145] [1090/1251] eta: 0:01:42 lr: 0.000526 loss: 3.4290 (3.3113) grad_norm: 1.4732 (1.4812) time: 0.6289 [2021-03-27 07:32:53 swin_base_patch4_window7_224] INFO: Epoch: [145] [1100/1251] eta: 0:01:35 lr: 0.000526 loss: 3.5801 (3.3131) grad_norm: 1.5073 (1.4817) time: 0.6311 [2021-03-27 07:32:59 swin_base_patch4_window7_224] INFO: Epoch: [145] [1110/1251] eta: 0:01:29 lr: 0.000526 loss: 3.6092 (3.3144) grad_norm: 1.4423 (1.4809) time: 0.6365 [2021-03-27 07:33:05 swin_base_patch4_window7_224] INFO: Epoch: [145] [1120/1251] eta: 0:01:23 lr: 0.000526 loss: 3.4969 (3.3152) grad_norm: 1.4090 (1.4806) time: 0.6369 [2021-03-27 07:33:12 swin_base_patch4_window7_224] INFO: Epoch: [145] [1130/1251] eta: 0:01:16 lr: 0.000526 loss: 3.2873 (3.3152) grad_norm: 1.4118 (1.4800) time: 0.6314 [2021-03-27 07:33:18 swin_base_patch4_window7_224] INFO: Epoch: [145] [1140/1251] eta: 0:01:10 lr: 0.000526 loss: 3.2081 (3.3156) grad_norm: 1.4104 (1.4792) time: 0.6267 [2021-03-27 07:33:24 swin_base_patch4_window7_224] INFO: Epoch: [145] [1150/1251] eta: 0:01:04 lr: 0.000526 loss: 3.1694 (3.3131) grad_norm: 1.4267 (1.4802) time: 0.6276 [2021-03-27 07:33:30 swin_base_patch4_window7_224] INFO: Epoch: [145] [1160/1251] eta: 0:00:57 lr: 0.000526 loss: 3.4091 (3.3137) grad_norm: 1.4708 (1.4798) time: 0.6247 [2021-03-27 07:33:37 swin_base_patch4_window7_224] INFO: Epoch: [145] [1170/1251] eta: 0:00:51 lr: 0.000526 loss: 3.5820 (3.3147) grad_norm: 1.3537 (1.4795) time: 0.6235 [2021-03-27 07:33:43 swin_base_patch4_window7_224] INFO: Epoch: [145] [1180/1251] eta: 0:00:45 lr: 0.000526 loss: 3.3558 (3.3156) grad_norm: 1.4192 (1.4802) time: 0.6311 [2021-03-27 07:33:49 swin_base_patch4_window7_224] INFO: Epoch: [145] [1190/1251] eta: 0:00:38 lr: 0.000526 loss: 3.3558 (3.3147) grad_norm: 1.5386 (1.4808) time: 0.6322 [2021-03-27 07:33:56 swin_base_patch4_window7_224] INFO: Epoch: [145] [1200/1251] eta: 0:00:32 lr: 0.000526 loss: 3.5669 (3.3170) grad_norm: 1.4905 (1.4807) time: 0.6278 [2021-03-27 07:34:02 swin_base_patch4_window7_224] INFO: Epoch: [145] [1210/1251] eta: 0:00:26 lr: 0.000526 loss: 3.5531 (3.3164) grad_norm: 1.3694 (1.4799) time: 0.6333 [2021-03-27 07:34:08 swin_base_patch4_window7_224] INFO: Epoch: [145] [1220/1251] eta: 0:00:19 lr: 0.000526 loss: 3.2353 (3.3170) grad_norm: 1.3823 (1.4796) time: 0.6297 [2021-03-27 07:34:14 swin_base_patch4_window7_224] INFO: Epoch: [145] [1230/1251] eta: 0:00:13 lr: 0.000526 loss: 3.3196 (3.3179) grad_norm: 1.4712 (1.4807) time: 0.6266 [2021-03-27 07:34:21 swin_base_patch4_window7_224] INFO: Epoch: [145] [1240/1251] eta: 0:00:06 lr: 0.000526 loss: 3.5198 (3.3190) grad_norm: 1.4669 (1.4804) time: 0.6271 [2021-03-27 07:34:27 swin_base_patch4_window7_224] INFO: Epoch: [145] [1250/1251] eta: 0:00:00 lr: 0.000526 loss: 3.4656 (3.3186) grad_norm: 1.3905 (1.4797) time: 0.6193 [2021-03-27 07:35:50 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.9480 (0.9480) acc1: 71.8750 (71.8750) acc5: 96.8750 (96.8750) [2021-03-27 07:35:51 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.9480 (0.9551) acc1: 73.4375 (75.1420) acc5: 95.3125 (95.5966) [2021-03-27 07:35:53 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9467 (0.9441) acc1: 76.5625 (76.1161) acc5: 95.3125 (95.2381) [2021-03-27 07:35:54 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8243 (0.9096) acc1: 79.6875 (77.5202) acc5: 95.3125 (95.0101) [2021-03-27 07:35:56 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8188 (0.8854) acc1: 79.6875 (77.8201) acc5: 95.3125 (95.1220) [2021-03-27 07:35:57 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8768 (0.9084) acc1: 78.1250 (77.7600) acc5: 95.3125 (94.8160) [2021-03-27 07:36:05 swin_base_patch4_window7_224] INFO: * Acc@1 78.826 Acc@5 94.686 loss 0.905 [2021-03-27 07:36:05 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.8% [2021-03-27 07:36:05 swin_base_patch4_window7_224] INFO: Max accuracy: 78.83% [2021-03-27 07:36:09 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 0/1251] eta: 1:32:31 lr: 0.000526 loss: 3.8144 (3.8144) grad_norm: 1.9083 (1.9083) time: 4.4377 [2021-03-27 07:36:15 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 10/1251] eta: 0:20:21 lr: 0.000526 loss: 3.4802 (3.3605) grad_norm: 1.4800 (1.5324) time: 0.9843 [2021-03-27 07:36:22 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 20/1251] eta: 0:16:49 lr: 0.000526 loss: 3.3536 (3.2573) grad_norm: 1.4800 (1.5545) time: 0.6388 [2021-03-27 07:36:28 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 30/1251] eta: 0:15:23 lr: 0.000526 loss: 3.3127 (3.2614) grad_norm: 1.4490 (1.4979) time: 0.6316 [2021-03-27 07:36:35 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 40/1251] eta: 0:14:45 lr: 0.000526 loss: 3.0371 (3.2003) grad_norm: 1.4490 (1.5208) time: 0.6383 [2021-03-27 07:36:41 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 50/1251] eta: 0:14:14 lr: 0.000526 loss: 3.2746 (3.2090) grad_norm: 1.4943 (1.5014) time: 0.6419 [2021-03-27 07:36:47 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 60/1251] eta: 0:13:49 lr: 0.000525 loss: 3.1831 (3.1544) grad_norm: 1.4857 (1.5135) time: 0.6256 [2021-03-27 07:36:53 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 70/1251] eta: 0:13:30 lr: 0.000525 loss: 3.0634 (3.1622) grad_norm: 1.4868 (1.5086) time: 0.6227 [2021-03-27 07:37:00 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 80/1251] eta: 0:13:17 lr: 0.000525 loss: 3.1140 (3.1755) grad_norm: 1.5624 (1.5172) time: 0.6321 [2021-03-27 07:37:06 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 90/1251] eta: 0:13:05 lr: 0.000525 loss: 3.2428 (3.1819) grad_norm: 1.5624 (1.5144) time: 0.6392 [2021-03-27 07:37:12 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 100/1251] eta: 0:12:52 lr: 0.000525 loss: 3.3868 (3.2140) grad_norm: 1.4904 (1.5127) time: 0.6333 [2021-03-27 07:37:19 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 110/1251] eta: 0:12:42 lr: 0.000525 loss: 3.4464 (3.2041) grad_norm: 1.3994 (1.5012) time: 0.6344 [2021-03-27 07:37:25 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 120/1251] eta: 0:12:32 lr: 0.000525 loss: 3.1560 (3.1966) grad_norm: 1.3771 (1.4920) time: 0.6351 [2021-03-27 07:37:31 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 130/1251] eta: 0:12:22 lr: 0.000525 loss: 3.0787 (3.1924) grad_norm: 1.3869 (1.4911) time: 0.6285 [2021-03-27 07:37:38 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 140/1251] eta: 0:12:13 lr: 0.000525 loss: 3.4315 (3.2143) grad_norm: 1.4101 (1.4828) time: 0.6294 [2021-03-27 07:37:44 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 150/1251] eta: 0:12:03 lr: 0.000525 loss: 3.4786 (3.2133) grad_norm: 1.4267 (1.4825) time: 0.6240 [2021-03-27 07:37:50 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 160/1251] eta: 0:11:55 lr: 0.000525 loss: 3.2587 (3.2201) grad_norm: 1.4799 (1.4860) time: 0.6259 [2021-03-27 07:37:57 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 170/1251] eta: 0:11:47 lr: 0.000525 loss: 3.2494 (3.2184) grad_norm: 1.5481 (1.4890) time: 0.6323 [2021-03-27 07:38:03 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 180/1251] eta: 0:11:39 lr: 0.000525 loss: 3.4722 (3.2342) grad_norm: 1.4555 (1.4844) time: 0.6335 [2021-03-27 07:38:09 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 190/1251] eta: 0:11:32 lr: 0.000525 loss: 3.5360 (3.2423) grad_norm: 1.3696 (1.4820) time: 0.6361 [2021-03-27 07:38:16 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 200/1251] eta: 0:11:24 lr: 0.000525 loss: 3.2093 (3.2373) grad_norm: 1.4092 (1.4880) time: 0.6352 [2021-03-27 07:38:22 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 210/1251] eta: 0:11:17 lr: 0.000525 loss: 3.4075 (3.2493) grad_norm: 1.5080 (1.4872) time: 0.6308 [2021-03-27 07:38:28 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 220/1251] eta: 0:11:09 lr: 0.000525 loss: 3.4075 (3.2462) grad_norm: 1.3763 (1.4834) time: 0.6269 [2021-03-27 07:38:35 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 230/1251] eta: 0:11:02 lr: 0.000525 loss: 3.5027 (3.2573) grad_norm: 1.4297 (1.4856) time: 0.6326 [2021-03-27 07:38:41 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 240/1251] eta: 0:10:55 lr: 0.000525 loss: 3.5027 (3.2559) grad_norm: 1.4377 (1.4823) time: 0.6380 [2021-03-27 07:38:47 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 250/1251] eta: 0:10:48 lr: 0.000525 loss: 3.3651 (3.2591) grad_norm: 1.4574 (1.4830) time: 0.6295 [2021-03-27 07:38:53 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 260/1251] eta: 0:10:40 lr: 0.000525 loss: 3.4593 (3.2603) grad_norm: 1.4918 (1.4838) time: 0.6228 [2021-03-27 07:39:00 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 270/1251] eta: 0:10:33 lr: 0.000525 loss: 3.5239 (3.2627) grad_norm: 1.4966 (1.4875) time: 0.6262 [2021-03-27 07:39:06 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 280/1251] eta: 0:10:26 lr: 0.000525 loss: 3.4927 (3.2571) grad_norm: 1.4966 (1.4909) time: 0.6285 [2021-03-27 07:39:12 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 290/1251] eta: 0:10:19 lr: 0.000525 loss: 3.1412 (3.2528) grad_norm: 1.4270 (1.4868) time: 0.6285 [2021-03-27 07:39:19 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 300/1251] eta: 0:10:12 lr: 0.000524 loss: 3.1633 (3.2568) grad_norm: 1.3876 (1.4845) time: 0.6295 [2021-03-27 07:39:25 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 310/1251] eta: 0:10:06 lr: 0.000524 loss: 3.4687 (3.2615) grad_norm: 1.3591 (1.4822) time: 0.6357 [2021-03-27 07:39:31 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 320/1251] eta: 0:09:59 lr: 0.000524 loss: 3.3793 (3.2616) grad_norm: 1.3814 (1.4816) time: 0.6352 [2021-03-27 07:39:38 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 330/1251] eta: 0:09:52 lr: 0.000524 loss: 3.2819 (3.2637) grad_norm: 1.4371 (1.4808) time: 0.6253 [2021-03-27 07:39:44 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 340/1251] eta: 0:09:45 lr: 0.000524 loss: 3.5079 (3.2661) grad_norm: 1.4302 (1.4804) time: 0.6254 [2021-03-27 07:39:50 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 350/1251] eta: 0:09:38 lr: 0.000524 loss: 3.5079 (3.2659) grad_norm: 1.5581 (1.4854) time: 0.6301 [2021-03-27 07:39:56 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 360/1251] eta: 0:09:32 lr: 0.000524 loss: 3.3940 (3.2701) grad_norm: 1.5581 (1.4858) time: 0.6327 [2021-03-27 07:40:03 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 370/1251] eta: 0:09:25 lr: 0.000524 loss: 3.3898 (3.2714) grad_norm: 1.4506 (1.4847) time: 0.6305 [2021-03-27 07:40:09 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 380/1251] eta: 0:09:18 lr: 0.000524 loss: 3.3525 (3.2712) grad_norm: 1.4165 (1.4864) time: 0.6288 [2021-03-27 07:40:15 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 390/1251] eta: 0:09:12 lr: 0.000524 loss: 3.3089 (3.2664) grad_norm: 1.4165 (1.4850) time: 0.6332 [2021-03-27 07:40:22 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 400/1251] eta: 0:09:05 lr: 0.000524 loss: 3.3519 (3.2696) grad_norm: 1.4645 (1.4870) time: 0.6275 [2021-03-27 07:40:28 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 410/1251] eta: 0:08:58 lr: 0.000524 loss: 3.1928 (3.2596) grad_norm: 1.4645 (1.4862) time: 0.6235 [2021-03-27 07:40:34 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 420/1251] eta: 0:08:52 lr: 0.000524 loss: 3.3490 (3.2698) grad_norm: 1.4009 (1.4866) time: 0.6353 [2021-03-27 07:40:41 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 430/1251] eta: 0:08:45 lr: 0.000524 loss: 3.5189 (3.2665) grad_norm: 1.3606 (1.4850) time: 0.6369 [2021-03-27 07:40:47 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 440/1251] eta: 0:08:38 lr: 0.000524 loss: 3.2913 (3.2701) grad_norm: 1.4449 (1.4851) time: 0.6295 [2021-03-27 07:40:53 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 450/1251] eta: 0:08:32 lr: 0.000524 loss: 3.4739 (3.2739) grad_norm: 1.4449 (1.4841) time: 0.6269 [2021-03-27 07:40:59 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 460/1251] eta: 0:08:25 lr: 0.000524 loss: 3.2618 (3.2736) grad_norm: 1.4454 (1.4839) time: 0.6273 [2021-03-27 07:41:06 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 470/1251] eta: 0:08:19 lr: 0.000524 loss: 3.2618 (3.2758) grad_norm: 1.5016 (1.4838) time: 0.6298 [2021-03-27 07:41:12 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 480/1251] eta: 0:08:12 lr: 0.000524 loss: 3.4917 (3.2823) grad_norm: 1.5311 (1.4855) time: 0.6357 [2021-03-27 07:41:18 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 490/1251] eta: 0:08:06 lr: 0.000524 loss: 3.6321 (3.2832) grad_norm: 1.5814 (1.4903) time: 0.6363 [2021-03-27 07:41:25 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 500/1251] eta: 0:07:59 lr: 0.000524 loss: 3.5409 (3.2860) grad_norm: 1.5003 (1.4906) time: 0.6309 [2021-03-27 07:41:31 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 510/1251] eta: 0:07:53 lr: 0.000524 loss: 3.4026 (3.2839) grad_norm: 1.4881 (1.4923) time: 0.6270 [2021-03-27 07:41:38 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 520/1251] eta: 0:07:47 lr: 0.000524 loss: 3.3514 (3.2828) grad_norm: 1.4843 (1.4923) time: 0.6397 [2021-03-27 07:41:44 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 530/1251] eta: 0:07:40 lr: 0.000524 loss: 3.1510 (3.2794) grad_norm: 1.4516 (1.4923) time: 0.6392 [2021-03-27 07:41:50 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 540/1251] eta: 0:07:34 lr: 0.000523 loss: 3.3741 (3.2825) grad_norm: 1.4516 (1.4918) time: 0.6342 [2021-03-27 07:41:57 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 550/1251] eta: 0:07:27 lr: 0.000523 loss: 3.4596 (3.2830) grad_norm: 1.4528 (1.4936) time: 0.6447 [2021-03-27 07:42:03 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 560/1251] eta: 0:07:21 lr: 0.000523 loss: 3.4621 (3.2820) grad_norm: 1.4766 (1.4943) time: 0.6380 [2021-03-27 07:42:09 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 570/1251] eta: 0:07:14 lr: 0.000523 loss: 3.2184 (3.2783) grad_norm: 1.4779 (1.4945) time: 0.6347 [2021-03-27 07:42:16 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 580/1251] eta: 0:07:08 lr: 0.000523 loss: 3.2184 (3.2771) grad_norm: 1.4779 (1.4938) time: 0.6392 [2021-03-27 07:42:22 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 590/1251] eta: 0:07:02 lr: 0.000523 loss: 3.3259 (3.2764) grad_norm: 1.4341 (1.4938) time: 0.6323 [2021-03-27 07:42:28 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 600/1251] eta: 0:06:55 lr: 0.000523 loss: 3.3925 (3.2813) grad_norm: 1.4427 (1.4947) time: 0.6227 [2021-03-27 07:42:34 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 610/1251] eta: 0:06:48 lr: 0.000523 loss: 3.3956 (3.2770) grad_norm: 1.4446 (1.4935) time: 0.6212 [2021-03-27 07:42:41 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 620/1251] eta: 0:06:42 lr: 0.000523 loss: 3.2276 (3.2788) grad_norm: 1.4064 (1.4931) time: 0.6216 [2021-03-27 07:42:47 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 630/1251] eta: 0:06:35 lr: 0.000523 loss: 3.2686 (3.2784) grad_norm: 1.3997 (1.4912) time: 0.6306 [2021-03-27 07:42:53 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 640/1251] eta: 0:06:29 lr: 0.000523 loss: 3.3759 (3.2815) grad_norm: 1.3946 (1.4906) time: 0.6365 [2021-03-27 07:43:00 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 650/1251] eta: 0:06:23 lr: 0.000523 loss: 3.4485 (3.2858) grad_norm: 1.4474 (1.4925) time: 0.6354 [2021-03-27 07:43:06 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 660/1251] eta: 0:06:16 lr: 0.000523 loss: 3.6109 (3.2881) grad_norm: 1.3964 (1.4913) time: 0.6373 [2021-03-27 07:43:13 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 670/1251] eta: 0:06:10 lr: 0.000523 loss: 3.3753 (3.2897) grad_norm: 1.3812 (1.4916) time: 0.6375 [2021-03-27 07:43:19 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 680/1251] eta: 0:06:03 lr: 0.000523 loss: 3.0808 (3.2854) grad_norm: 1.3926 (1.4905) time: 0.6323 [2021-03-27 07:43:25 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 690/1251] eta: 0:05:57 lr: 0.000523 loss: 3.0899 (3.2854) grad_norm: 1.4697 (1.4907) time: 0.6274 [2021-03-27 07:43:31 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 700/1251] eta: 0:05:51 lr: 0.000523 loss: 3.3732 (3.2874) grad_norm: 1.4293 (1.4897) time: 0.6263 [2021-03-27 07:43:38 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 710/1251] eta: 0:05:44 lr: 0.000523 loss: 3.3732 (3.2874) grad_norm: 1.4526 (1.4901) time: 0.6322 [2021-03-27 07:43:44 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 720/1251] eta: 0:05:38 lr: 0.000523 loss: 3.2460 (3.2854) grad_norm: 1.4848 (1.4887) time: 0.6342 [2021-03-27 07:43:50 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 730/1251] eta: 0:05:31 lr: 0.000523 loss: 3.2787 (3.2864) grad_norm: 1.4194 (1.4881) time: 0.6325 [2021-03-27 07:43:57 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 740/1251] eta: 0:05:25 lr: 0.000523 loss: 3.4523 (3.2888) grad_norm: 1.4194 (1.4871) time: 0.6354 [2021-03-27 07:44:03 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 750/1251] eta: 0:05:19 lr: 0.000523 loss: 3.2906 (3.2889) grad_norm: 1.4433 (1.4877) time: 0.6340 [2021-03-27 07:44:09 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 760/1251] eta: 0:05:12 lr: 0.000523 loss: 3.2906 (3.2890) grad_norm: 1.4337 (1.4873) time: 0.6259 [2021-03-27 07:44:16 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 770/1251] eta: 0:05:06 lr: 0.000523 loss: 3.5339 (3.2913) grad_norm: 1.3985 (1.4869) time: 0.6281 [2021-03-27 07:44:22 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 780/1251] eta: 0:04:59 lr: 0.000522 loss: 3.5239 (3.2916) grad_norm: 1.4005 (1.4862) time: 0.6377 [2021-03-27 07:44:28 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 790/1251] eta: 0:04:53 lr: 0.000522 loss: 3.2593 (3.2908) grad_norm: 1.4169 (1.4884) time: 0.6388 [2021-03-27 07:44:35 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 800/1251] eta: 0:04:47 lr: 0.000522 loss: 3.2593 (3.2905) grad_norm: 1.5825 (1.4896) time: 0.6379 [2021-03-27 07:44:41 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 810/1251] eta: 0:04:40 lr: 0.000522 loss: 3.3668 (3.2892) grad_norm: 1.5885 (1.4920) time: 0.6299 [2021-03-27 07:44:47 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 820/1251] eta: 0:04:34 lr: 0.000522 loss: 3.3094 (3.2885) grad_norm: 1.5885 (1.4928) time: 0.6243 [2021-03-27 07:44:54 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 830/1251] eta: 0:04:27 lr: 0.000522 loss: 3.2010 (3.2871) grad_norm: 1.5765 (1.4940) time: 0.6288 [2021-03-27 07:45:00 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 840/1251] eta: 0:04:21 lr: 0.000522 loss: 3.0637 (3.2856) grad_norm: 1.5117 (1.4941) time: 0.6309 [2021-03-27 07:45:06 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 850/1251] eta: 0:04:15 lr: 0.000522 loss: 3.3035 (3.2877) grad_norm: 1.6139 (1.4956) time: 0.6319 [2021-03-27 07:45:13 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 860/1251] eta: 0:04:08 lr: 0.000522 loss: 3.5500 (3.2892) grad_norm: 1.4670 (1.4946) time: 0.6298 [2021-03-27 07:45:19 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 870/1251] eta: 0:04:02 lr: 0.000522 loss: 3.4696 (3.2888) grad_norm: 1.4467 (1.4944) time: 0.6257 [2021-03-27 07:45:25 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 880/1251] eta: 0:03:55 lr: 0.000522 loss: 3.4403 (3.2903) grad_norm: 1.5066 (1.4954) time: 0.6249 [2021-03-27 07:45:31 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 890/1251] eta: 0:03:49 lr: 0.000522 loss: 3.4403 (3.2897) grad_norm: 1.5524 (1.4959) time: 0.6276 [2021-03-27 07:45:38 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 900/1251] eta: 0:03:43 lr: 0.000522 loss: 3.3901 (3.2902) grad_norm: 1.4319 (1.4945) time: 0.6338 [2021-03-27 07:45:44 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 910/1251] eta: 0:03:36 lr: 0.000522 loss: 3.5388 (3.2929) grad_norm: 1.4228 (1.4938) time: 0.6356 [2021-03-27 07:45:50 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 920/1251] eta: 0:03:30 lr: 0.000522 loss: 3.5453 (3.2952) grad_norm: 1.3504 (1.4925) time: 0.6374 [2021-03-27 07:45:57 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 930/1251] eta: 0:03:24 lr: 0.000522 loss: 3.3962 (3.2927) grad_norm: 1.4296 (1.4927) time: 0.6379 [2021-03-27 07:46:03 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 940/1251] eta: 0:03:17 lr: 0.000522 loss: 3.3445 (3.2924) grad_norm: 1.5438 (1.4937) time: 0.6330 [2021-03-27 07:46:09 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 950/1251] eta: 0:03:11 lr: 0.000522 loss: 3.4642 (3.2930) grad_norm: 1.4702 (1.4934) time: 0.6269 [2021-03-27 07:46:16 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 960/1251] eta: 0:03:04 lr: 0.000522 loss: 3.4663 (3.2930) grad_norm: 1.3870 (1.4930) time: 0.6276 [2021-03-27 07:46:22 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 970/1251] eta: 0:02:58 lr: 0.000522 loss: 3.4663 (3.2931) grad_norm: 1.4338 (1.4927) time: 0.6354 [2021-03-27 07:46:28 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 980/1251] eta: 0:02:52 lr: 0.000522 loss: 3.4929 (3.2935) grad_norm: 1.5095 (1.4933) time: 0.6326 [2021-03-27 07:46:35 swin_base_patch4_window7_224] INFO: Epoch: [146] [ 990/1251] eta: 0:02:45 lr: 0.000522 loss: 3.3904 (3.2924) grad_norm: 1.5095 (1.4923) time: 0.6226 [2021-03-27 07:46:41 swin_base_patch4_window7_224] INFO: Epoch: [146] [1000/1251] eta: 0:02:39 lr: 0.000522 loss: 3.3583 (3.2939) grad_norm: 1.3777 (1.4916) time: 0.6205 [2021-03-27 07:46:47 swin_base_patch4_window7_224] INFO: Epoch: [146] [1010/1251] eta: 0:02:33 lr: 0.000522 loss: 3.4095 (3.2930) grad_norm: 1.4154 (1.4915) time: 0.6275 [2021-03-27 07:46:53 swin_base_patch4_window7_224] INFO: Epoch: [146] [1020/1251] eta: 0:02:26 lr: 0.000522 loss: 3.3496 (3.2934) grad_norm: 1.4030 (1.4907) time: 0.6298 [2021-03-27 07:47:00 swin_base_patch4_window7_224] INFO: Epoch: [146] [1030/1251] eta: 0:02:20 lr: 0.000521 loss: 3.4574 (3.2944) grad_norm: 1.4030 (1.4902) time: 0.6234 [2021-03-27 07:47:06 swin_base_patch4_window7_224] INFO: Epoch: [146] [1040/1251] eta: 0:02:13 lr: 0.000521 loss: 3.4574 (3.2935) grad_norm: 1.4143 (1.4897) time: 0.6228 [2021-03-27 07:47:12 swin_base_patch4_window7_224] INFO: Epoch: [146] [1050/1251] eta: 0:02:07 lr: 0.000521 loss: 3.4533 (3.2948) grad_norm: 1.3710 (1.4904) time: 0.6242 [2021-03-27 07:47:18 swin_base_patch4_window7_224] INFO: Epoch: [146] [1060/1251] eta: 0:02:01 lr: 0.000521 loss: 3.5625 (3.2969) grad_norm: 1.4560 (1.4910) time: 0.6238 [2021-03-27 07:47:25 swin_base_patch4_window7_224] INFO: Epoch: [146] [1070/1251] eta: 0:01:54 lr: 0.000521 loss: 3.3779 (3.2931) grad_norm: 1.5322 (1.4915) time: 0.6267 [2021-03-27 07:47:31 swin_base_patch4_window7_224] INFO: Epoch: [146] [1080/1251] eta: 0:01:48 lr: 0.000521 loss: 3.0622 (3.2927) grad_norm: 1.5433 (1.4928) time: 0.6324 [2021-03-27 07:47:37 swin_base_patch4_window7_224] INFO: Epoch: [146] [1090/1251] eta: 0:01:42 lr: 0.000521 loss: 3.5843 (3.2960) grad_norm: 1.5815 (1.4933) time: 0.6320 [2021-03-27 07:47:43 swin_base_patch4_window7_224] INFO: Epoch: [146] [1100/1251] eta: 0:01:35 lr: 0.000521 loss: 3.6397 (3.2950) grad_norm: 1.6270 (1.4940) time: 0.6267 [2021-03-27 07:47:50 swin_base_patch4_window7_224] INFO: Epoch: [146] [1110/1251] eta: 0:01:29 lr: 0.000521 loss: 3.5463 (3.2963) grad_norm: 1.4853 (1.4936) time: 0.6259 [2021-03-27 07:47:56 swin_base_patch4_window7_224] INFO: Epoch: [146] [1120/1251] eta: 0:01:23 lr: 0.000521 loss: 3.4212 (3.2947) grad_norm: 1.3926 (1.4928) time: 0.6299 [2021-03-27 07:48:02 swin_base_patch4_window7_224] INFO: Epoch: [146] [1130/1251] eta: 0:01:16 lr: 0.000521 loss: 3.3022 (3.2964) grad_norm: 1.3942 (1.4933) time: 0.6372 [2021-03-27 07:48:09 swin_base_patch4_window7_224] INFO: Epoch: [146] [1140/1251] eta: 0:01:10 lr: 0.000521 loss: 3.3658 (3.2980) grad_norm: 1.4485 (1.4929) time: 0.6343 [2021-03-27 07:48:15 swin_base_patch4_window7_224] INFO: Epoch: [146] [1150/1251] eta: 0:01:04 lr: 0.000521 loss: 3.3658 (3.2974) grad_norm: 1.4285 (1.4922) time: 0.6322 [2021-03-27 07:48:21 swin_base_patch4_window7_224] INFO: Epoch: [146] [1160/1251] eta: 0:00:57 lr: 0.000521 loss: 3.4343 (3.2972) grad_norm: 1.3731 (1.4922) time: 0.6331 [2021-03-27 07:48:28 swin_base_patch4_window7_224] INFO: Epoch: [146] [1170/1251] eta: 0:00:51 lr: 0.000521 loss: 3.5727 (3.2987) grad_norm: 1.4170 (1.4920) time: 0.6293 [2021-03-27 07:48:34 swin_base_patch4_window7_224] INFO: Epoch: [146] [1180/1251] eta: 0:00:45 lr: 0.000521 loss: 3.5727 (3.2989) grad_norm: 1.4170 (1.4913) time: 0.6275 [2021-03-27 07:48:40 swin_base_patch4_window7_224] INFO: Epoch: [146] [1190/1251] eta: 0:00:38 lr: 0.000521 loss: 3.2805 (3.2990) grad_norm: 1.4125 (1.4913) time: 0.6319 [2021-03-27 07:48:47 swin_base_patch4_window7_224] INFO: Epoch: [146] [1200/1251] eta: 0:00:32 lr: 0.000521 loss: 3.1920 (3.2975) grad_norm: 1.4588 (1.4910) time: 0.6362 [2021-03-27 07:48:53 swin_base_patch4_window7_224] INFO: Epoch: [146] [1210/1251] eta: 0:00:26 lr: 0.000521 loss: 3.1920 (3.2975) grad_norm: 1.4588 (1.4906) time: 0.6341 [2021-03-27 07:48:59 swin_base_patch4_window7_224] INFO: Epoch: [146] [1220/1251] eta: 0:00:19 lr: 0.000521 loss: 3.4455 (3.2982) grad_norm: 1.5060 (1.4913) time: 0.6308 [2021-03-27 07:49:06 swin_base_patch4_window7_224] INFO: Epoch: [146] [1230/1251] eta: 0:00:13 lr: 0.000521 loss: 3.3686 (3.2974) grad_norm: 1.5093 (1.4912) time: 0.6265 [2021-03-27 07:49:12 swin_base_patch4_window7_224] INFO: Epoch: [146] [1240/1251] eta: 0:00:06 lr: 0.000521 loss: 3.3686 (3.2979) grad_norm: 1.4393 (1.4908) time: 0.6222 [2021-03-27 07:49:18 swin_base_patch4_window7_224] INFO: Epoch: [146] [1250/1251] eta: 0:00:00 lr: 0.000521 loss: 3.6254 (3.2973) grad_norm: 1.4219 (1.4901) time: 0.6186 [2021-03-27 07:49:26 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:23 loss: 0.9596 (0.9596) acc1: 71.8750 (71.8750) acc5: 95.3125 (95.3125) [2021-03-27 07:49:29 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9206 (0.9367) acc1: 78.1250 (77.4148) acc5: 96.8750 (95.4545) [2021-03-27 07:49:31 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8847 (0.9317) acc1: 78.1250 (77.6042) acc5: 96.8750 (95.6845) [2021-03-27 07:49:33 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9638 (0.9574) acc1: 76.5625 (77.3185) acc5: 95.3125 (95.1109) [2021-03-27 07:49:35 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9638 (0.9557) acc1: 76.5625 (77.4771) acc5: 93.7500 (95.1982) [2021-03-27 07:49:36 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9638 (0.9549) acc1: 76.5625 (77.5360) acc5: 95.3125 (95.1680) [2021-03-27 07:49:46 swin_base_patch4_window7_224] INFO: * Acc@1 78.708 Acc@5 94.732 loss 0.947 [2021-03-27 07:49:46 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.7% [2021-03-27 07:49:46 swin_base_patch4_window7_224] INFO: Max accuracy: 78.83% [2021-03-27 07:49:51 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 0/1251] eta: 1:30:53 lr: 0.000521 loss: 3.5831 (3.5831) grad_norm: 1.2298 (1.2298) time: 4.3596 [2021-03-27 07:49:57 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 10/1251] eta: 0:20:02 lr: 0.000521 loss: 3.4504 (3.1749) grad_norm: 1.3587 (1.4140) time: 0.9687 [2021-03-27 07:50:03 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 20/1251] eta: 0:16:37 lr: 0.000520 loss: 3.4504 (3.2867) grad_norm: 1.4115 (1.4430) time: 0.6330 [2021-03-27 07:50:10 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 30/1251] eta: 0:15:17 lr: 0.000520 loss: 3.4920 (3.3256) grad_norm: 1.4268 (1.4396) time: 0.6315 [2021-03-27 07:50:16 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 40/1251] eta: 0:14:34 lr: 0.000520 loss: 3.4556 (3.2948) grad_norm: 1.4224 (1.4465) time: 0.6298 [2021-03-27 07:50:22 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 50/1251] eta: 0:14:07 lr: 0.000520 loss: 3.3293 (3.2721) grad_norm: 1.4359 (1.4483) time: 0.6342 [2021-03-27 07:50:29 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 60/1251] eta: 0:13:46 lr: 0.000520 loss: 3.0585 (3.2397) grad_norm: 1.4701 (1.4571) time: 0.6350 [2021-03-27 07:50:35 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 70/1251] eta: 0:13:27 lr: 0.000520 loss: 3.4135 (3.2768) grad_norm: 1.4714 (1.4768) time: 0.6290 [2021-03-27 07:50:41 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 80/1251] eta: 0:13:12 lr: 0.000520 loss: 3.5052 (3.2952) grad_norm: 1.4818 (1.4726) time: 0.6239 [2021-03-27 07:50:48 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 90/1251] eta: 0:13:00 lr: 0.000520 loss: 3.3829 (3.2876) grad_norm: 1.4294 (1.4744) time: 0.6328 [2021-03-27 07:50:54 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 100/1251] eta: 0:12:50 lr: 0.000520 loss: 3.4963 (3.3207) grad_norm: 1.3791 (1.4711) time: 0.6402 [2021-03-27 07:51:00 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 110/1251] eta: 0:12:38 lr: 0.000520 loss: 3.4786 (3.3106) grad_norm: 1.3613 (1.4687) time: 0.6311 [2021-03-27 07:51:07 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 120/1251] eta: 0:12:29 lr: 0.000520 loss: 3.2470 (3.2898) grad_norm: 1.4152 (1.4717) time: 0.6317 [2021-03-27 07:51:13 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 130/1251] eta: 0:12:19 lr: 0.000520 loss: 3.1010 (3.2896) grad_norm: 1.4641 (1.4723) time: 0.6302 [2021-03-27 07:51:19 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 140/1251] eta: 0:12:10 lr: 0.000520 loss: 3.1410 (3.2781) grad_norm: 1.4845 (1.4703) time: 0.6220 [2021-03-27 07:51:25 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 150/1251] eta: 0:12:01 lr: 0.000520 loss: 3.1410 (3.2677) grad_norm: 1.3676 (1.4684) time: 0.6243 [2021-03-27 07:51:32 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 160/1251] eta: 0:11:52 lr: 0.000520 loss: 3.2812 (3.2814) grad_norm: 1.5037 (1.4724) time: 0.6233 [2021-03-27 07:51:38 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 170/1251] eta: 0:11:45 lr: 0.000520 loss: 3.4243 (3.2910) grad_norm: 1.5182 (1.4836) time: 0.6327 [2021-03-27 07:51:44 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 180/1251] eta: 0:11:37 lr: 0.000520 loss: 3.4243 (3.2986) grad_norm: 1.5182 (1.4854) time: 0.6372 [2021-03-27 07:51:51 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 190/1251] eta: 0:11:30 lr: 0.000520 loss: 3.5282 (3.3023) grad_norm: 1.4967 (1.4837) time: 0.6345 [2021-03-27 07:51:57 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 200/1251] eta: 0:11:22 lr: 0.000520 loss: 3.4382 (3.2968) grad_norm: 1.4967 (1.4875) time: 0.6298 [2021-03-27 07:52:03 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 210/1251] eta: 0:11:14 lr: 0.000520 loss: 3.3598 (3.2973) grad_norm: 1.5420 (1.4861) time: 0.6248 [2021-03-27 07:52:09 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 220/1251] eta: 0:11:07 lr: 0.000520 loss: 3.3414 (3.2852) grad_norm: 1.4919 (1.4891) time: 0.6266 [2021-03-27 07:52:16 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 230/1251] eta: 0:11:00 lr: 0.000520 loss: 3.3804 (3.2962) grad_norm: 1.4919 (1.4864) time: 0.6301 [2021-03-27 07:52:22 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 240/1251] eta: 0:10:53 lr: 0.000520 loss: 3.4126 (3.2994) grad_norm: 1.4327 (1.4858) time: 0.6330 [2021-03-27 07:52:28 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 250/1251] eta: 0:10:45 lr: 0.000520 loss: 3.3686 (3.3016) grad_norm: 1.4059 (1.4818) time: 0.6271 [2021-03-27 07:52:35 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 260/1251] eta: 0:10:38 lr: 0.000519 loss: 3.2547 (3.2935) grad_norm: 1.3679 (1.4798) time: 0.6254 [2021-03-27 07:52:41 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 270/1251] eta: 0:10:31 lr: 0.000519 loss: 3.2508 (3.2948) grad_norm: 1.4172 (1.4817) time: 0.6301 [2021-03-27 07:52:47 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 280/1251] eta: 0:10:24 lr: 0.000519 loss: 3.1262 (3.2792) grad_norm: 1.5362 (1.4835) time: 0.6277 [2021-03-27 07:52:53 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 290/1251] eta: 0:10:17 lr: 0.000519 loss: 2.9307 (3.2803) grad_norm: 1.5485 (1.4842) time: 0.6295 [2021-03-27 07:53:00 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 300/1251] eta: 0:10:11 lr: 0.000519 loss: 3.5104 (3.2873) grad_norm: 1.5084 (1.4873) time: 0.6327 [2021-03-27 07:53:06 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 310/1251] eta: 0:10:04 lr: 0.000519 loss: 3.6179 (3.2918) grad_norm: 1.4716 (1.4839) time: 0.6341 [2021-03-27 07:53:13 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 320/1251] eta: 0:09:58 lr: 0.000519 loss: 3.4020 (3.2870) grad_norm: 1.3891 (1.4829) time: 0.6407 [2021-03-27 07:53:19 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 330/1251] eta: 0:09:51 lr: 0.000519 loss: 3.2254 (3.2843) grad_norm: 1.4034 (1.4835) time: 0.6382 [2021-03-27 07:53:25 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 340/1251] eta: 0:09:44 lr: 0.000519 loss: 3.2778 (3.2834) grad_norm: 1.4034 (1.4819) time: 0.6304 [2021-03-27 07:53:32 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 350/1251] eta: 0:09:37 lr: 0.000519 loss: 3.2254 (3.2798) grad_norm: 1.3974 (1.4801) time: 0.6295 [2021-03-27 07:53:38 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 360/1251] eta: 0:09:31 lr: 0.000519 loss: 3.2200 (3.2823) grad_norm: 1.4397 (1.4788) time: 0.6351 [2021-03-27 07:53:44 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 370/1251] eta: 0:09:24 lr: 0.000519 loss: 3.2200 (3.2761) grad_norm: 1.4421 (1.4789) time: 0.6345 [2021-03-27 07:53:51 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 380/1251] eta: 0:09:18 lr: 0.000519 loss: 3.2718 (3.2786) grad_norm: 1.3631 (1.4767) time: 0.6306 [2021-03-27 07:53:57 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 390/1251] eta: 0:09:11 lr: 0.000519 loss: 3.3872 (3.2736) grad_norm: 1.2971 (1.4739) time: 0.6330 [2021-03-27 07:54:03 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 400/1251] eta: 0:09:04 lr: 0.000519 loss: 3.2292 (3.2709) grad_norm: 1.3378 (1.4707) time: 0.6291 [2021-03-27 07:54:09 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 410/1251] eta: 0:08:58 lr: 0.000519 loss: 3.4697 (3.2738) grad_norm: 1.3798 (1.4695) time: 0.6297 [2021-03-27 07:54:16 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 420/1251] eta: 0:08:51 lr: 0.000519 loss: 3.5850 (3.2832) grad_norm: 1.4287 (1.4709) time: 0.6341 [2021-03-27 07:54:22 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 430/1251] eta: 0:08:45 lr: 0.000519 loss: 3.6624 (3.2914) grad_norm: 1.3991 (1.4685) time: 0.6274 [2021-03-27 07:54:28 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 440/1251] eta: 0:08:38 lr: 0.000519 loss: 3.6630 (3.2952) grad_norm: 1.3933 (1.4695) time: 0.6249 [2021-03-27 07:54:35 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 450/1251] eta: 0:08:31 lr: 0.000519 loss: 3.6208 (3.2958) grad_norm: 1.4439 (1.4684) time: 0.6247 [2021-03-27 07:54:41 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 460/1251] eta: 0:08:25 lr: 0.000519 loss: 3.4812 (3.3004) grad_norm: 1.3665 (1.4670) time: 0.6254 [2021-03-27 07:54:47 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 470/1251] eta: 0:08:18 lr: 0.000519 loss: 3.3130 (3.2942) grad_norm: 1.4278 (1.4678) time: 0.6303 [2021-03-27 07:54:53 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 480/1251] eta: 0:08:11 lr: 0.000519 loss: 3.0647 (3.2894) grad_norm: 1.4623 (1.4659) time: 0.6265 [2021-03-27 07:55:00 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 490/1251] eta: 0:08:05 lr: 0.000519 loss: 3.1004 (3.2894) grad_norm: 1.3562 (1.4638) time: 0.6257 [2021-03-27 07:55:06 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 500/1251] eta: 0:07:58 lr: 0.000518 loss: 3.3062 (3.2859) grad_norm: 1.4112 (1.4648) time: 0.6296 [2021-03-27 07:55:12 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 510/1251] eta: 0:07:52 lr: 0.000518 loss: 3.4247 (3.2893) grad_norm: 1.4891 (1.4653) time: 0.6322 [2021-03-27 07:55:19 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 520/1251] eta: 0:07:46 lr: 0.000518 loss: 3.5445 (3.2872) grad_norm: 1.4768 (1.4661) time: 0.6308 [2021-03-27 07:55:25 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 530/1251] eta: 0:07:39 lr: 0.000518 loss: 3.4292 (3.2872) grad_norm: 1.3950 (1.4653) time: 0.6243 [2021-03-27 07:55:31 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 540/1251] eta: 0:07:32 lr: 0.000518 loss: 3.2657 (3.2865) grad_norm: 1.4503 (1.4657) time: 0.6254 [2021-03-27 07:55:37 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 550/1251] eta: 0:07:26 lr: 0.000518 loss: 3.3656 (3.2896) grad_norm: 1.4855 (1.4666) time: 0.6324 [2021-03-27 07:55:44 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 560/1251] eta: 0:07:20 lr: 0.000518 loss: 3.6701 (3.2958) grad_norm: 1.4983 (1.4672) time: 0.6418 [2021-03-27 07:55:50 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 570/1251] eta: 0:07:13 lr: 0.000518 loss: 3.5283 (3.2949) grad_norm: 1.4664 (1.4677) time: 0.6420 [2021-03-27 07:55:57 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 580/1251] eta: 0:07:07 lr: 0.000518 loss: 3.2170 (3.2914) grad_norm: 1.4610 (1.4670) time: 0.6393 [2021-03-27 07:56:03 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 590/1251] eta: 0:07:01 lr: 0.000518 loss: 3.3721 (3.2931) grad_norm: 1.4544 (1.4679) time: 0.6400 [2021-03-27 07:56:09 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 600/1251] eta: 0:06:54 lr: 0.000518 loss: 3.4059 (3.2929) grad_norm: 1.5566 (1.4707) time: 0.6350 [2021-03-27 07:56:16 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 610/1251] eta: 0:06:48 lr: 0.000518 loss: 3.2920 (3.2912) grad_norm: 1.5672 (1.4719) time: 0.6364 [2021-03-27 07:56:22 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 620/1251] eta: 0:06:42 lr: 0.000518 loss: 3.4730 (3.2951) grad_norm: 1.4936 (1.4723) time: 0.6374 [2021-03-27 07:56:28 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 630/1251] eta: 0:06:35 lr: 0.000518 loss: 3.5240 (3.2957) grad_norm: 1.4741 (1.4723) time: 0.6282 [2021-03-27 07:56:35 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 640/1251] eta: 0:06:29 lr: 0.000518 loss: 3.3876 (3.2957) grad_norm: 1.3816 (1.4710) time: 0.6262 [2021-03-27 07:56:41 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 650/1251] eta: 0:06:22 lr: 0.000518 loss: 3.1283 (3.2895) grad_norm: 1.4263 (1.4711) time: 0.6266 [2021-03-27 07:56:47 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 660/1251] eta: 0:06:16 lr: 0.000518 loss: 3.0765 (3.2918) grad_norm: 1.4288 (1.4702) time: 0.6235 [2021-03-27 07:56:53 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 670/1251] eta: 0:06:09 lr: 0.000518 loss: 3.5142 (3.2943) grad_norm: 1.4391 (1.4709) time: 0.6259 [2021-03-27 07:57:00 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 680/1251] eta: 0:06:03 lr: 0.000518 loss: 3.2094 (3.2896) grad_norm: 1.4455 (1.4711) time: 0.6299 [2021-03-27 07:57:06 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 690/1251] eta: 0:05:56 lr: 0.000518 loss: 2.7192 (3.2837) grad_norm: 1.5373 (1.4741) time: 0.6351 [2021-03-27 07:57:12 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 700/1251] eta: 0:05:50 lr: 0.000518 loss: 3.1432 (3.2822) grad_norm: 1.5610 (1.4763) time: 0.6332 [2021-03-27 07:57:19 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 710/1251] eta: 0:05:44 lr: 0.000518 loss: 3.2306 (3.2829) grad_norm: 1.5121 (1.4760) time: 0.6292 [2021-03-27 07:57:25 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 720/1251] eta: 0:05:37 lr: 0.000518 loss: 3.5652 (3.2866) grad_norm: 1.3827 (1.4751) time: 0.6307 [2021-03-27 07:57:31 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 730/1251] eta: 0:05:31 lr: 0.000518 loss: 3.4968 (3.2872) grad_norm: 1.3964 (1.4755) time: 0.6281 [2021-03-27 07:57:38 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 740/1251] eta: 0:05:24 lr: 0.000517 loss: 3.4968 (3.2899) grad_norm: 1.4306 (1.4752) time: 0.6298 [2021-03-27 07:57:44 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 750/1251] eta: 0:05:18 lr: 0.000517 loss: 3.5343 (3.2939) grad_norm: 1.4306 (1.4750) time: 0.6365 [2021-03-27 07:57:50 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 760/1251] eta: 0:05:12 lr: 0.000517 loss: 3.4472 (3.2960) grad_norm: 1.4606 (1.4755) time: 0.6363 [2021-03-27 07:57:57 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 770/1251] eta: 0:05:05 lr: 0.000517 loss: 3.3921 (3.2957) grad_norm: 1.4254 (1.4753) time: 0.6355 [2021-03-27 07:58:03 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 780/1251] eta: 0:04:59 lr: 0.000517 loss: 3.4360 (3.2964) grad_norm: 1.4095 (1.4748) time: 0.6369 [2021-03-27 07:58:09 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 790/1251] eta: 0:04:53 lr: 0.000517 loss: 3.4230 (3.2966) grad_norm: 1.4234 (1.4760) time: 0.6332 [2021-03-27 07:58:16 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 800/1251] eta: 0:04:46 lr: 0.000517 loss: 3.3893 (3.2969) grad_norm: 1.4234 (1.4753) time: 0.6309 [2021-03-27 07:58:22 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 810/1251] eta: 0:04:40 lr: 0.000517 loss: 3.4169 (3.2988) grad_norm: 1.3871 (1.4741) time: 0.6339 [2021-03-27 07:58:28 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 820/1251] eta: 0:04:33 lr: 0.000517 loss: 3.5633 (3.3021) grad_norm: 1.3791 (1.4747) time: 0.6334 [2021-03-27 07:58:35 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 830/1251] eta: 0:04:27 lr: 0.000517 loss: 3.5633 (3.3002) grad_norm: 1.4200 (1.4748) time: 0.6302 [2021-03-27 07:58:41 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 840/1251] eta: 0:04:21 lr: 0.000517 loss: 3.4477 (3.3018) grad_norm: 1.4045 (1.4743) time: 0.6260 [2021-03-27 07:58:47 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 850/1251] eta: 0:04:14 lr: 0.000517 loss: 3.5021 (3.3016) grad_norm: 1.4314 (1.4742) time: 0.6219 [2021-03-27 07:58:53 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 860/1251] eta: 0:04:08 lr: 0.000517 loss: 3.4355 (3.3027) grad_norm: 1.4442 (1.4740) time: 0.6279 [2021-03-27 07:59:00 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 870/1251] eta: 0:04:02 lr: 0.000517 loss: 3.3893 (3.3013) grad_norm: 1.5231 (1.4753) time: 0.6355 [2021-03-27 07:59:06 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 880/1251] eta: 0:03:55 lr: 0.000517 loss: 3.4281 (3.3044) grad_norm: 1.4857 (1.4747) time: 0.6300 [2021-03-27 07:59:12 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 890/1251] eta: 0:03:49 lr: 0.000517 loss: 3.3545 (3.3027) grad_norm: 1.3882 (1.4738) time: 0.6249 [2021-03-27 07:59:19 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 900/1251] eta: 0:03:42 lr: 0.000517 loss: 3.2206 (3.3014) grad_norm: 1.3795 (1.4732) time: 0.6302 [2021-03-27 07:59:25 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 910/1251] eta: 0:03:36 lr: 0.000517 loss: 3.2763 (3.2994) grad_norm: 1.3640 (1.4724) time: 0.6287 [2021-03-27 07:59:31 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 920/1251] eta: 0:03:30 lr: 0.000517 loss: 3.2765 (3.2978) grad_norm: 1.3969 (1.4726) time: 0.6278 [2021-03-27 07:59:38 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 930/1251] eta: 0:03:23 lr: 0.000517 loss: 3.2715 (3.2982) grad_norm: 1.4494 (1.4729) time: 0.6299 [2021-03-27 07:59:44 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 940/1251] eta: 0:03:17 lr: 0.000517 loss: 3.3283 (3.2990) grad_norm: 1.4782 (1.4733) time: 0.6275 [2021-03-27 07:59:50 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 950/1251] eta: 0:03:11 lr: 0.000517 loss: 3.4044 (3.2976) grad_norm: 1.5008 (1.4741) time: 0.6261 [2021-03-27 07:59:56 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 960/1251] eta: 0:03:04 lr: 0.000517 loss: 3.0710 (3.2925) grad_norm: 1.4740 (1.4750) time: 0.6247 [2021-03-27 08:00:03 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 970/1251] eta: 0:02:58 lr: 0.000517 loss: 3.0508 (3.2919) grad_norm: 1.4827 (1.4751) time: 0.6309 [2021-03-27 08:00:09 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 980/1251] eta: 0:02:51 lr: 0.000516 loss: 3.3780 (3.2912) grad_norm: 1.4681 (1.4746) time: 0.6337 [2021-03-27 08:00:15 swin_base_patch4_window7_224] INFO: Epoch: [147] [ 990/1251] eta: 0:02:45 lr: 0.000516 loss: 3.4313 (3.2937) grad_norm: 1.4301 (1.4740) time: 0.6276 [2021-03-27 08:00:22 swin_base_patch4_window7_224] INFO: Epoch: [147] [1000/1251] eta: 0:02:39 lr: 0.000516 loss: 3.4313 (3.2944) grad_norm: 1.4301 (1.4738) time: 0.6268 [2021-03-27 08:00:28 swin_base_patch4_window7_224] INFO: Epoch: [147] [1010/1251] eta: 0:02:32 lr: 0.000516 loss: 3.4264 (3.2960) grad_norm: 1.4853 (1.4745) time: 0.6297 [2021-03-27 08:00:34 swin_base_patch4_window7_224] INFO: Epoch: [147] [1020/1251] eta: 0:02:26 lr: 0.000516 loss: 3.4264 (3.2964) grad_norm: 1.5164 (1.4750) time: 0.6318 [2021-03-27 08:00:41 swin_base_patch4_window7_224] INFO: Epoch: [147] [1030/1251] eta: 0:02:20 lr: 0.000516 loss: 3.4018 (3.2962) grad_norm: 1.4619 (1.4753) time: 0.6338 [2021-03-27 08:00:47 swin_base_patch4_window7_224] INFO: Epoch: [147] [1040/1251] eta: 0:02:13 lr: 0.000516 loss: 3.3420 (3.2956) grad_norm: 1.5265 (1.4761) time: 0.6312 [2021-03-27 08:00:53 swin_base_patch4_window7_224] INFO: Epoch: [147] [1050/1251] eta: 0:02:07 lr: 0.000516 loss: 3.3205 (3.2943) grad_norm: 1.4819 (1.4770) time: 0.6253 [2021-03-27 08:00:59 swin_base_patch4_window7_224] INFO: Epoch: [147] [1060/1251] eta: 0:02:01 lr: 0.000516 loss: 2.9607 (3.2906) grad_norm: 1.4558 (1.4772) time: 0.6237 [2021-03-27 08:01:06 swin_base_patch4_window7_224] INFO: Epoch: [147] [1070/1251] eta: 0:01:54 lr: 0.000516 loss: 3.1142 (3.2906) grad_norm: 1.4226 (1.4769) time: 0.6239 [2021-03-27 08:01:12 swin_base_patch4_window7_224] INFO: Epoch: [147] [1080/1251] eta: 0:01:48 lr: 0.000516 loss: 3.2894 (3.2901) grad_norm: 1.4654 (1.4778) time: 0.6250 [2021-03-27 08:01:18 swin_base_patch4_window7_224] INFO: Epoch: [147] [1090/1251] eta: 0:01:42 lr: 0.000516 loss: 3.3830 (3.2907) grad_norm: 1.4111 (1.4773) time: 0.6263 [2021-03-27 08:01:24 swin_base_patch4_window7_224] INFO: Epoch: [147] [1100/1251] eta: 0:01:35 lr: 0.000516 loss: 3.4291 (3.2914) grad_norm: 1.4564 (1.4782) time: 0.6275 [2021-03-27 08:01:31 swin_base_patch4_window7_224] INFO: Epoch: [147] [1110/1251] eta: 0:01:29 lr: 0.000516 loss: 3.4291 (3.2913) grad_norm: 1.4853 (1.4782) time: 0.6355 [2021-03-27 08:01:37 swin_base_patch4_window7_224] INFO: Epoch: [147] [1120/1251] eta: 0:01:23 lr: 0.000516 loss: 3.3691 (3.2917) grad_norm: 1.4792 (1.4782) time: 0.6354 [2021-03-27 08:01:43 swin_base_patch4_window7_224] INFO: Epoch: [147] [1130/1251] eta: 0:01:16 lr: 0.000516 loss: 3.2900 (3.2906) grad_norm: 1.4724 (1.4781) time: 0.6314 [2021-03-27 08:01:50 swin_base_patch4_window7_224] INFO: Epoch: [147] [1140/1251] eta: 0:01:10 lr: 0.000516 loss: 3.2676 (3.2904) grad_norm: 1.3577 (1.4771) time: 0.6306 [2021-03-27 08:01:56 swin_base_patch4_window7_224] INFO: Epoch: [147] [1150/1251] eta: 0:01:04 lr: 0.000516 loss: 3.5075 (3.2916) grad_norm: 1.3857 (1.4768) time: 0.6274 [2021-03-27 08:02:02 swin_base_patch4_window7_224] INFO: Epoch: [147] [1160/1251] eta: 0:00:57 lr: 0.000516 loss: 3.5252 (3.2922) grad_norm: 1.4599 (1.4773) time: 0.6277 [2021-03-27 08:02:08 swin_base_patch4_window7_224] INFO: Epoch: [147] [1170/1251] eta: 0:00:51 lr: 0.000516 loss: 3.4827 (3.2944) grad_norm: 1.5235 (1.4782) time: 0.6240 [2021-03-27 08:02:15 swin_base_patch4_window7_224] INFO: Epoch: [147] [1180/1251] eta: 0:00:44 lr: 0.000516 loss: 3.4826 (3.2947) grad_norm: 1.5047 (1.4784) time: 0.6236 [2021-03-27 08:02:21 swin_base_patch4_window7_224] INFO: Epoch: [147] [1190/1251] eta: 0:00:38 lr: 0.000516 loss: 3.3923 (3.2936) grad_norm: 1.4121 (1.4780) time: 0.6263 [2021-03-27 08:02:27 swin_base_patch4_window7_224] INFO: Epoch: [147] [1200/1251] eta: 0:00:32 lr: 0.000516 loss: 3.2943 (3.2929) grad_norm: 1.4402 (1.4786) time: 0.6248 [2021-03-27 08:02:34 swin_base_patch4_window7_224] INFO: Epoch: [147] [1210/1251] eta: 0:00:25 lr: 0.000516 loss: 3.4040 (3.2929) grad_norm: 1.4389 (1.4778) time: 0.6270 [2021-03-27 08:02:40 swin_base_patch4_window7_224] INFO: Epoch: [147] [1220/1251] eta: 0:00:19 lr: 0.000515 loss: 3.3659 (3.2939) grad_norm: 1.3277 (1.4772) time: 0.6276 [2021-03-27 08:02:46 swin_base_patch4_window7_224] INFO: Epoch: [147] [1230/1251] eta: 0:00:13 lr: 0.000515 loss: 3.3626 (3.2921) grad_norm: 1.3797 (1.4779) time: 0.6306 [2021-03-27 08:02:52 swin_base_patch4_window7_224] INFO: Epoch: [147] [1240/1251] eta: 0:00:06 lr: 0.000515 loss: 3.3981 (3.2928) grad_norm: 1.4639 (1.4778) time: 0.6254 [2021-03-27 08:02:58 swin_base_patch4_window7_224] INFO: Epoch: [147] [1250/1251] eta: 0:00:00 lr: 0.000515 loss: 3.4554 (3.2945) grad_norm: 1.3993 (1.4766) time: 0.6105 [2021-03-27 08:03:07 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:18 loss: 1.0840 (1.0840) acc1: 71.8750 (71.8750) acc5: 92.1875 (92.1875) [2021-03-27 08:03:09 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9233 (0.9067) acc1: 78.1250 (79.1193) acc5: 95.3125 (94.7443) [2021-03-27 08:03:11 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9233 (0.9098) acc1: 78.1250 (78.4226) acc5: 95.3125 (95.0149) [2021-03-27 08:03:13 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9351 (0.9158) acc1: 78.1250 (78.4778) acc5: 93.7500 (94.9093) [2021-03-27 08:03:15 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9378 (0.9163) acc1: 78.1250 (78.5442) acc5: 93.7500 (95.0457) [2021-03-27 08:03:16 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9225 (0.9148) acc1: 77.3585 (78.4640) acc5: 95.3125 (94.9760) [2021-03-27 08:03:29 swin_base_patch4_window7_224] INFO: * Acc@1 78.820 Acc@5 94.754 loss 0.907 [2021-03-27 08:03:29 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.8% [2021-03-27 08:03:29 swin_base_patch4_window7_224] INFO: Max accuracy: 78.83% [2021-03-27 08:03:33 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 0/1251] eta: 1:32:41 lr: 0.000515 loss: 3.3456 (3.3456) grad_norm: 1.3645 (1.3645) time: 4.4456 [2021-03-27 08:03:40 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 10/1251] eta: 0:20:19 lr: 0.000515 loss: 3.5276 (3.5394) grad_norm: 1.4544 (1.4928) time: 0.9829 [2021-03-27 08:03:46 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 20/1251] eta: 0:16:42 lr: 0.000515 loss: 3.5207 (3.4549) grad_norm: 1.4784 (1.4839) time: 0.6327 [2021-03-27 08:03:52 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 30/1251] eta: 0:15:19 lr: 0.000515 loss: 3.4475 (3.4247) grad_norm: 1.4643 (1.4872) time: 0.6263 [2021-03-27 08:03:59 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 40/1251] eta: 0:14:36 lr: 0.000515 loss: 3.4519 (3.4180) grad_norm: 1.3738 (1.4702) time: 0.6282 [2021-03-27 08:04:05 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 50/1251] eta: 0:14:05 lr: 0.000515 loss: 3.3576 (3.3946) grad_norm: 1.3475 (1.4515) time: 0.6277 [2021-03-27 08:04:11 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 60/1251] eta: 0:13:44 lr: 0.000515 loss: 3.2124 (3.3849) grad_norm: 1.3548 (1.4803) time: 0.6276 [2021-03-27 08:04:17 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 70/1251] eta: 0:13:26 lr: 0.000515 loss: 3.2124 (3.3714) grad_norm: 1.3948 (1.4715) time: 0.6307 [2021-03-27 08:04:24 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 80/1251] eta: 0:13:11 lr: 0.000515 loss: 3.1421 (3.3530) grad_norm: 1.4096 (1.4839) time: 0.6284 [2021-03-27 08:04:30 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 90/1251] eta: 0:12:58 lr: 0.000515 loss: 3.3287 (3.3587) grad_norm: 1.4660 (nan) time: 0.6264 [2021-03-27 08:04:36 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 100/1251] eta: 0:12:49 lr: 0.000515 loss: 3.3601 (3.3290) grad_norm: 1.4660 (nan) time: 0.6387 [2021-03-27 08:04:43 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 110/1251] eta: 0:12:39 lr: 0.000515 loss: 3.2665 (3.3251) grad_norm: 1.4984 (nan) time: 0.6404 [2021-03-27 08:04:49 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 120/1251] eta: 0:12:28 lr: 0.000515 loss: 3.3878 (3.3196) grad_norm: 1.4693 (nan) time: 0.6279 [2021-03-27 08:04:55 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 130/1251] eta: 0:12:20 lr: 0.000515 loss: 3.4875 (3.3268) grad_norm: 1.4548 (nan) time: 0.6371 [2021-03-27 08:05:02 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 140/1251] eta: 0:12:11 lr: 0.000515 loss: 3.3534 (3.3267) grad_norm: 1.4152 (nan) time: 0.6373 [2021-03-27 08:05:08 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 150/1251] eta: 0:12:02 lr: 0.000515 loss: 3.2064 (3.3063) grad_norm: 1.4636 (nan) time: 0.6280 [2021-03-27 08:05:14 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 160/1251] eta: 0:11:54 lr: 0.000515 loss: 3.1326 (3.2831) grad_norm: 1.5070 (nan) time: 0.6323 [2021-03-27 08:05:21 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 170/1251] eta: 0:11:46 lr: 0.000515 loss: 3.0747 (3.2776) grad_norm: 1.5129 (nan) time: 0.6339 [2021-03-27 08:05:27 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 180/1251] eta: 0:11:38 lr: 0.000515 loss: 3.3808 (3.2847) grad_norm: 1.4549 (nan) time: 0.6284 [2021-03-27 08:05:33 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 190/1251] eta: 0:11:30 lr: 0.000515 loss: 3.4555 (3.2855) grad_norm: 1.4544 (nan) time: 0.6274 [2021-03-27 08:05:40 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 200/1251] eta: 0:11:23 lr: 0.000515 loss: 3.4555 (3.2842) grad_norm: 1.4775 (nan) time: 0.6357 [2021-03-27 08:05:46 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 210/1251] eta: 0:11:16 lr: 0.000514 loss: 3.3175 (3.2824) grad_norm: 1.5260 (nan) time: 0.6407 [2021-03-27 08:05:52 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 220/1251] eta: 0:11:09 lr: 0.000514 loss: 3.2912 (3.2836) grad_norm: 1.3965 (nan) time: 0.6333 [2021-03-27 08:05:59 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 230/1251] eta: 0:11:01 lr: 0.000514 loss: 3.2112 (3.2752) grad_norm: 1.3844 (nan) time: 0.6294 [2021-03-27 08:06:05 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 240/1251] eta: 0:10:54 lr: 0.000514 loss: 3.0281 (3.2635) grad_norm: 1.4201 (nan) time: 0.6285 [2021-03-27 08:06:11 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 250/1251] eta: 0:10:47 lr: 0.000514 loss: 3.3023 (3.2662) grad_norm: 1.5479 (nan) time: 0.6294 [2021-03-27 08:06:18 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 260/1251] eta: 0:10:40 lr: 0.000514 loss: 3.5710 (3.2807) grad_norm: 1.5445 (nan) time: 0.6295 [2021-03-27 08:06:24 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 270/1251] eta: 0:10:33 lr: 0.000514 loss: 3.5233 (3.2798) grad_norm: 1.4610 (nan) time: 0.6262 [2021-03-27 08:06:30 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 280/1251] eta: 0:10:25 lr: 0.000514 loss: 3.2640 (3.2770) grad_norm: 1.4636 (nan) time: 0.6227 [2021-03-27 08:06:36 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 290/1251] eta: 0:10:18 lr: 0.000514 loss: 3.3961 (3.2822) grad_norm: 1.4375 (nan) time: 0.6233 [2021-03-27 08:06:43 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 300/1251] eta: 0:10:11 lr: 0.000514 loss: 3.2761 (3.2735) grad_norm: 1.4280 (nan) time: 0.6264 [2021-03-27 08:06:49 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 310/1251] eta: 0:10:04 lr: 0.000514 loss: 3.2603 (3.2766) grad_norm: 1.4321 (nan) time: 0.6251 [2021-03-27 08:06:55 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 320/1251] eta: 0:09:57 lr: 0.000514 loss: 3.5352 (3.2840) grad_norm: 1.4301 (nan) time: 0.6248 [2021-03-27 08:07:01 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 330/1251] eta: 0:09:50 lr: 0.000514 loss: 3.6325 (3.2930) grad_norm: 1.5303 (nan) time: 0.6249 [2021-03-27 08:07:08 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 340/1251] eta: 0:09:44 lr: 0.000514 loss: 3.4067 (3.2887) grad_norm: 1.4466 (nan) time: 0.6257 [2021-03-27 08:07:14 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 350/1251] eta: 0:09:37 lr: 0.000514 loss: 3.3262 (3.2940) grad_norm: 1.3918 (nan) time: 0.6282 [2021-03-27 08:07:20 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 360/1251] eta: 0:09:30 lr: 0.000514 loss: 3.3262 (3.2885) grad_norm: 1.4812 (nan) time: 0.6342 [2021-03-27 08:07:27 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 370/1251] eta: 0:09:24 lr: 0.000514 loss: 3.2608 (3.2817) grad_norm: 1.4460 (nan) time: 0.6338 [2021-03-27 08:07:33 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 380/1251] eta: 0:09:17 lr: 0.000514 loss: 3.4332 (3.2886) grad_norm: 1.4211 (nan) time: 0.6261 [2021-03-27 08:07:39 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 390/1251] eta: 0:09:10 lr: 0.000514 loss: 3.4473 (3.2886) grad_norm: 1.4374 (nan) time: 0.6256 [2021-03-27 08:07:45 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 400/1251] eta: 0:09:03 lr: 0.000514 loss: 3.4153 (3.2892) grad_norm: 1.4590 (nan) time: 0.6260 [2021-03-27 08:07:52 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 410/1251] eta: 0:08:57 lr: 0.000514 loss: 3.2451 (3.2828) grad_norm: 1.4808 (nan) time: 0.6271 [2021-03-27 08:07:58 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 420/1251] eta: 0:08:50 lr: 0.000514 loss: 3.1311 (3.2813) grad_norm: 1.4090 (nan) time: 0.6290 [2021-03-27 08:08:04 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 430/1251] eta: 0:08:44 lr: 0.000514 loss: 3.1528 (3.2798) grad_norm: 1.4058 (nan) time: 0.6332 [2021-03-27 08:08:11 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 440/1251] eta: 0:08:37 lr: 0.000514 loss: 3.2596 (3.2815) grad_norm: 1.4058 (nan) time: 0.6364 [2021-03-27 08:08:17 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 450/1251] eta: 0:08:31 lr: 0.000514 loss: 3.2372 (3.2752) grad_norm: 1.3946 (nan) time: 0.6305 [2021-03-27 08:08:23 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 460/1251] eta: 0:08:24 lr: 0.000513 loss: 3.4060 (3.2806) grad_norm: 1.4506 (nan) time: 0.6279 [2021-03-27 08:08:29 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 470/1251] eta: 0:08:18 lr: 0.000513 loss: 3.4884 (3.2828) grad_norm: 1.4506 (nan) time: 0.6273 [2021-03-27 08:08:36 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 480/1251] eta: 0:08:11 lr: 0.000513 loss: 3.5980 (3.2856) grad_norm: 1.4802 (nan) time: 0.6252 [2021-03-27 08:08:42 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 490/1251] eta: 0:08:05 lr: 0.000513 loss: 3.4762 (3.2843) grad_norm: 1.4987 (nan) time: 0.6272 [2021-03-27 08:08:48 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 500/1251] eta: 0:07:58 lr: 0.000513 loss: 3.2271 (3.2863) grad_norm: 1.5340 (nan) time: 0.6352 [2021-03-27 08:08:55 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 510/1251] eta: 0:07:52 lr: 0.000513 loss: 3.2271 (3.2877) grad_norm: 1.4975 (nan) time: 0.6386 [2021-03-27 08:09:01 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 520/1251] eta: 0:07:45 lr: 0.000513 loss: 3.3889 (3.2925) grad_norm: 1.4405 (nan) time: 0.6335 [2021-03-27 08:09:07 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 530/1251] eta: 0:07:39 lr: 0.000513 loss: 3.4526 (3.2947) grad_norm: 1.3493 (nan) time: 0.6296 [2021-03-27 08:09:14 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 540/1251] eta: 0:07:32 lr: 0.000513 loss: 3.4526 (3.2942) grad_norm: 1.3493 (nan) time: 0.6281 [2021-03-27 08:09:20 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 550/1251] eta: 0:07:26 lr: 0.000513 loss: 3.2302 (3.2927) grad_norm: 1.3804 (nan) time: 0.6403 [2021-03-27 08:09:27 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 560/1251] eta: 0:07:20 lr: 0.000513 loss: 3.4308 (3.2980) grad_norm: 1.4418 (nan) time: 0.6466 [2021-03-27 08:09:33 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 570/1251] eta: 0:07:14 lr: 0.000513 loss: 3.6108 (3.3010) grad_norm: 1.4834 (nan) time: 0.6367 [2021-03-27 08:09:39 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 580/1251] eta: 0:07:07 lr: 0.000513 loss: 3.6317 (3.3072) grad_norm: 1.5017 (nan) time: 0.6282 [2021-03-27 08:09:45 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 590/1251] eta: 0:07:01 lr: 0.000513 loss: 3.3581 (3.3046) grad_norm: 1.5056 (nan) time: 0.6278 [2021-03-27 08:09:52 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 600/1251] eta: 0:06:54 lr: 0.000513 loss: 3.2864 (3.3061) grad_norm: 1.5136 (nan) time: 0.6270 [2021-03-27 08:09:58 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 610/1251] eta: 0:06:48 lr: 0.000513 loss: 3.3407 (3.3051) grad_norm: 1.3856 (nan) time: 0.6229 [2021-03-27 08:10:04 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 620/1251] eta: 0:06:41 lr: 0.000513 loss: 3.4480 (3.3016) grad_norm: 1.3856 (nan) time: 0.6211 [2021-03-27 08:10:10 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 630/1251] eta: 0:06:35 lr: 0.000513 loss: 2.7674 (3.2974) grad_norm: 1.4022 (nan) time: 0.6242 [2021-03-27 08:10:17 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 640/1251] eta: 0:06:28 lr: 0.000513 loss: 3.2464 (3.2982) grad_norm: 1.3968 (nan) time: 0.6264 [2021-03-27 08:10:23 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 650/1251] eta: 0:06:22 lr: 0.000513 loss: 3.6462 (3.3047) grad_norm: 1.4245 (nan) time: 0.6285 [2021-03-27 08:10:29 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 660/1251] eta: 0:06:15 lr: 0.000513 loss: 3.5210 (3.3008) grad_norm: 1.4614 (nan) time: 0.6325 [2021-03-27 08:10:36 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 670/1251] eta: 0:06:09 lr: 0.000513 loss: 3.2614 (3.2984) grad_norm: 1.4394 (nan) time: 0.6294 [2021-03-27 08:10:42 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 680/1251] eta: 0:06:02 lr: 0.000513 loss: 3.5014 (3.3028) grad_norm: 1.4326 (nan) time: 0.6268 [2021-03-27 08:10:48 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 690/1251] eta: 0:05:56 lr: 0.000513 loss: 3.5200 (3.3042) grad_norm: 1.4374 (nan) time: 0.6272 [2021-03-27 08:10:54 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 700/1251] eta: 0:05:50 lr: 0.000512 loss: 3.5616 (3.3059) grad_norm: 1.4374 (nan) time: 0.6286 [2021-03-27 08:11:01 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 710/1251] eta: 0:05:43 lr: 0.000512 loss: 3.6323 (3.3055) grad_norm: 1.4116 (nan) time: 0.6280 [2021-03-27 08:11:07 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 720/1251] eta: 0:05:37 lr: 0.000512 loss: 3.5532 (3.3086) grad_norm: 1.4364 (nan) time: 0.6296 [2021-03-27 08:11:13 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 730/1251] eta: 0:05:30 lr: 0.000512 loss: 3.3061 (3.3075) grad_norm: 1.4287 (nan) time: 0.6323 [2021-03-27 08:11:20 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 740/1251] eta: 0:05:24 lr: 0.000512 loss: 3.1743 (3.3053) grad_norm: 1.3863 (nan) time: 0.6396 [2021-03-27 08:11:26 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 750/1251] eta: 0:05:18 lr: 0.000512 loss: 3.4391 (3.3066) grad_norm: 1.4345 (nan) time: 0.6398 [2021-03-27 08:11:32 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 760/1251] eta: 0:05:11 lr: 0.000512 loss: 3.6014 (3.3069) grad_norm: 1.5191 (nan) time: 0.6352 [2021-03-27 08:11:39 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 770/1251] eta: 0:05:05 lr: 0.000512 loss: 3.2003 (3.3054) grad_norm: 1.5899 (nan) time: 0.6370 [2021-03-27 08:11:45 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 780/1251] eta: 0:04:59 lr: 0.000512 loss: 3.1538 (3.3023) grad_norm: 1.5104 (nan) time: 0.6286 [2021-03-27 08:11:51 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 790/1251] eta: 0:04:52 lr: 0.000512 loss: 3.2844 (3.3024) grad_norm: 1.3905 (nan) time: 0.6218 [2021-03-27 08:11:58 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 800/1251] eta: 0:04:46 lr: 0.000512 loss: 3.4344 (3.3021) grad_norm: 1.4571 (nan) time: 0.6230 [2021-03-27 08:12:04 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 810/1251] eta: 0:04:39 lr: 0.000512 loss: 3.4582 (3.3035) grad_norm: 1.4598 (nan) time: 0.6252 [2021-03-27 08:12:10 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 820/1251] eta: 0:04:33 lr: 0.000512 loss: 3.3679 (3.3041) grad_norm: 1.4678 (nan) time: 0.6284 [2021-03-27 08:12:16 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 830/1251] eta: 0:04:27 lr: 0.000512 loss: 3.5116 (3.3076) grad_norm: 1.4137 (nan) time: 0.6266 [2021-03-27 08:12:23 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 840/1251] eta: 0:04:20 lr: 0.000512 loss: 3.5759 (3.3087) grad_norm: 1.5307 (nan) time: 0.6295 [2021-03-27 08:12:29 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 850/1251] eta: 0:04:14 lr: 0.000512 loss: 3.4244 (3.3094) grad_norm: 1.4650 (nan) time: 0.6386 [2021-03-27 08:12:35 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 860/1251] eta: 0:04:08 lr: 0.000512 loss: 3.4661 (3.3128) grad_norm: 1.4537 (nan) time: 0.6387 [2021-03-27 08:12:42 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 870/1251] eta: 0:04:01 lr: 0.000512 loss: 3.4892 (3.3115) grad_norm: 1.4581 (nan) time: 0.6358 [2021-03-27 08:12:48 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 880/1251] eta: 0:03:55 lr: 0.000512 loss: 3.3032 (3.3120) grad_norm: 1.4780 (nan) time: 0.6334 [2021-03-27 08:12:54 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 890/1251] eta: 0:03:49 lr: 0.000512 loss: 3.3032 (3.3115) grad_norm: 1.4943 (nan) time: 0.6308 [2021-03-27 08:13:01 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 900/1251] eta: 0:03:42 lr: 0.000512 loss: 3.2037 (3.3088) grad_norm: 1.4581 (nan) time: 0.6277 [2021-03-27 08:13:07 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 910/1251] eta: 0:03:36 lr: 0.000512 loss: 3.3439 (3.3094) grad_norm: 1.4975 (nan) time: 0.6218 [2021-03-27 08:13:13 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 920/1251] eta: 0:03:29 lr: 0.000512 loss: 3.1458 (3.3057) grad_norm: 1.5023 (nan) time: 0.6233 [2021-03-27 08:13:19 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 930/1251] eta: 0:03:23 lr: 0.000512 loss: 3.1458 (3.3054) grad_norm: 1.5876 (nan) time: 0.6273 [2021-03-27 08:13:26 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 940/1251] eta: 0:03:17 lr: 0.000511 loss: 3.3386 (3.3065) grad_norm: 1.5958 (nan) time: 0.6256 [2021-03-27 08:13:32 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 950/1251] eta: 0:03:10 lr: 0.000511 loss: 3.3328 (3.3051) grad_norm: 1.4923 (nan) time: 0.6301 [2021-03-27 08:13:38 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 960/1251] eta: 0:03:04 lr: 0.000511 loss: 3.2882 (3.3060) grad_norm: 1.4792 (nan) time: 0.6332 [2021-03-27 08:13:45 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 970/1251] eta: 0:02:58 lr: 0.000511 loss: 3.5064 (3.3087) grad_norm: 1.4790 (nan) time: 0.6324 [2021-03-27 08:13:51 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 980/1251] eta: 0:02:51 lr: 0.000511 loss: 3.4553 (3.3097) grad_norm: 1.4790 (nan) time: 0.6309 [2021-03-27 08:13:57 swin_base_patch4_window7_224] INFO: Epoch: [148] [ 990/1251] eta: 0:02:45 lr: 0.000511 loss: 3.3973 (3.3085) grad_norm: 1.4587 (nan) time: 0.6274 [2021-03-27 08:14:04 swin_base_patch4_window7_224] INFO: Epoch: [148] [1000/1251] eta: 0:02:39 lr: 0.000511 loss: 3.3973 (3.3092) grad_norm: 1.4267 (nan) time: 0.6302 [2021-03-27 08:14:10 swin_base_patch4_window7_224] INFO: Epoch: [148] [1010/1251] eta: 0:02:32 lr: 0.000511 loss: 3.4856 (3.3107) grad_norm: 1.5009 (nan) time: 0.6324 [2021-03-27 08:14:16 swin_base_patch4_window7_224] INFO: Epoch: [148] [1020/1251] eta: 0:02:26 lr: 0.000511 loss: 3.4753 (3.3113) grad_norm: 1.5769 (nan) time: 0.6268 [2021-03-27 08:14:22 swin_base_patch4_window7_224] INFO: Epoch: [148] [1030/1251] eta: 0:02:20 lr: 0.000511 loss: 3.3667 (3.3124) grad_norm: 1.5308 (nan) time: 0.6241 [2021-03-27 08:14:29 swin_base_patch4_window7_224] INFO: Epoch: [148] [1040/1251] eta: 0:02:13 lr: 0.000511 loss: 3.3888 (3.3132) grad_norm: 1.5016 (nan) time: 0.6293 [2021-03-27 08:14:35 swin_base_patch4_window7_224] INFO: Epoch: [148] [1050/1251] eta: 0:02:07 lr: 0.000511 loss: 3.3489 (3.3129) grad_norm: 1.6062 (nan) time: 0.6302 [2021-03-27 08:14:41 swin_base_patch4_window7_224] INFO: Epoch: [148] [1060/1251] eta: 0:02:01 lr: 0.000511 loss: 3.4771 (3.3149) grad_norm: 1.5846 (nan) time: 0.6299 [2021-03-27 08:14:48 swin_base_patch4_window7_224] INFO: Epoch: [148] [1070/1251] eta: 0:01:54 lr: 0.000511 loss: 3.4413 (3.3139) grad_norm: 1.5033 (nan) time: 0.6285 [2021-03-27 08:14:54 swin_base_patch4_window7_224] INFO: Epoch: [148] [1080/1251] eta: 0:01:48 lr: 0.000511 loss: 3.4413 (3.3146) grad_norm: 1.4435 (nan) time: 0.6320 [2021-03-27 08:15:00 swin_base_patch4_window7_224] INFO: Epoch: [148] [1090/1251] eta: 0:01:42 lr: 0.000511 loss: 3.4886 (3.3153) grad_norm: 1.4095 (nan) time: 0.6365 [2021-03-27 08:15:07 swin_base_patch4_window7_224] INFO: Epoch: [148] [1100/1251] eta: 0:01:35 lr: 0.000511 loss: 3.3790 (3.3130) grad_norm: 1.4430 (nan) time: 0.6404 [2021-03-27 08:15:13 swin_base_patch4_window7_224] INFO: Epoch: [148] [1110/1251] eta: 0:01:29 lr: 0.000511 loss: 3.4033 (3.3142) grad_norm: 1.5220 (nan) time: 0.6392 [2021-03-27 08:15:19 swin_base_patch4_window7_224] INFO: Epoch: [148] [1120/1251] eta: 0:01:23 lr: 0.000511 loss: 3.5442 (3.3144) grad_norm: 1.5788 (nan) time: 0.6333 [2021-03-27 08:15:26 swin_base_patch4_window7_224] INFO: Epoch: [148] [1130/1251] eta: 0:01:16 lr: 0.000511 loss: 3.4315 (3.3153) grad_norm: 1.4683 (nan) time: 0.6343 [2021-03-27 08:15:32 swin_base_patch4_window7_224] INFO: Epoch: [148] [1140/1251] eta: 0:01:10 lr: 0.000511 loss: 3.2849 (3.3139) grad_norm: 1.5506 (nan) time: 0.6307 [2021-03-27 08:15:38 swin_base_patch4_window7_224] INFO: Epoch: [148] [1150/1251] eta: 0:01:03 lr: 0.000511 loss: 3.1961 (3.3107) grad_norm: 1.4832 (nan) time: 0.6285 [2021-03-27 08:15:45 swin_base_patch4_window7_224] INFO: Epoch: [148] [1160/1251] eta: 0:00:57 lr: 0.000511 loss: 3.1450 (3.3105) grad_norm: 1.4347 (nan) time: 0.6349 [2021-03-27 08:15:51 swin_base_patch4_window7_224] INFO: Epoch: [148] [1170/1251] eta: 0:00:51 lr: 0.000511 loss: 3.2247 (3.3105) grad_norm: 1.4696 (nan) time: 0.6321 [2021-03-27 08:15:57 swin_base_patch4_window7_224] INFO: Epoch: [148] [1180/1251] eta: 0:00:44 lr: 0.000510 loss: 3.5688 (3.3115) grad_norm: 1.4359 (nan) time: 0.6260 [2021-03-27 08:16:04 swin_base_patch4_window7_224] INFO: Epoch: [148] [1190/1251] eta: 0:00:38 lr: 0.000510 loss: 3.5943 (3.3130) grad_norm: 1.4318 (nan) time: 0.6287 [2021-03-27 08:16:10 swin_base_patch4_window7_224] INFO: Epoch: [148] [1200/1251] eta: 0:00:32 lr: 0.000510 loss: 3.5107 (3.3134) grad_norm: 1.4284 (nan) time: 0.6389 [2021-03-27 08:16:16 swin_base_patch4_window7_224] INFO: Epoch: [148] [1210/1251] eta: 0:00:25 lr: 0.000510 loss: 3.5222 (3.3137) grad_norm: 1.4137 (nan) time: 0.6418 [2021-03-27 08:16:23 swin_base_patch4_window7_224] INFO: Epoch: [148] [1220/1251] eta: 0:00:19 lr: 0.000510 loss: 3.5222 (3.3147) grad_norm: 1.4364 (nan) time: 0.6319 [2021-03-27 08:16:29 swin_base_patch4_window7_224] INFO: Epoch: [148] [1230/1251] eta: 0:00:13 lr: 0.000510 loss: 3.5462 (3.3163) grad_norm: 1.4796 (nan) time: 0.6284 [2021-03-27 08:16:35 swin_base_patch4_window7_224] INFO: Epoch: [148] [1240/1251] eta: 0:00:06 lr: 0.000510 loss: 3.2754 (3.3151) grad_norm: 1.4653 (nan) time: 0.6291 [2021-03-27 08:16:41 swin_base_patch4_window7_224] INFO: Epoch: [148] [1250/1251] eta: 0:00:00 lr: 0.000510 loss: 3.3475 (3.3146) grad_norm: 1.3668 (nan) time: 0.6214 [2021-03-27 08:16:51 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:02 loss: 0.9012 (0.9012) acc1: 79.6875 (79.6875) acc5: 96.8750 (96.8750) [2021-03-27 08:16:54 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.8462 (0.8382) acc1: 79.6875 (79.5455) acc5: 96.8750 (95.7386) [2021-03-27 08:16:57 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.8052 (0.8268) acc1: 79.6875 (80.2083) acc5: 96.8750 (95.9077) [2021-03-27 08:16:59 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8154 (0.8514) acc1: 78.1250 (79.3347) acc5: 95.3125 (95.7661) [2021-03-27 08:17:00 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9211 (0.8830) acc1: 76.5625 (78.8872) acc5: 95.3125 (95.3125) [2021-03-27 08:17:01 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9211 (0.8955) acc1: 76.5625 (78.5600) acc5: 93.7500 (95.0080) [2021-03-27 08:17:13 swin_base_patch4_window7_224] INFO: * Acc@1 78.832 Acc@5 94.784 loss 0.896 [2021-03-27 08:17:13 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.8% [2021-03-27 08:17:13 swin_base_patch4_window7_224] INFO: Max accuracy: 78.83% [2021-03-27 08:17:17 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 0/1251] eta: 1:26:00 lr: 0.000510 loss: 3.8181 (3.8181) grad_norm: 1.6679 (1.6679) time: 4.1251 [2021-03-27 08:17:23 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 10/1251] eta: 0:19:50 lr: 0.000510 loss: 3.2997 (3.1404) grad_norm: 1.4940 (1.6321) time: 0.9594 [2021-03-27 08:17:30 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 20/1251] eta: 0:16:31 lr: 0.000510 loss: 3.2997 (3.1957) grad_norm: 1.4599 (1.6033) time: 0.6390 [2021-03-27 08:17:36 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 30/1251] eta: 0:15:12 lr: 0.000510 loss: 3.2428 (3.1738) grad_norm: 1.4216 (1.5595) time: 0.6306 [2021-03-27 08:17:42 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 40/1251] eta: 0:14:32 lr: 0.000510 loss: 3.1827 (3.1770) grad_norm: 1.4421 (1.5292) time: 0.6314 [2021-03-27 08:17:49 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 50/1251] eta: 0:14:04 lr: 0.000510 loss: 3.3346 (3.2048) grad_norm: 1.4114 (1.5113) time: 0.6351 [2021-03-27 08:17:55 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 60/1251] eta: 0:13:42 lr: 0.000510 loss: 3.3625 (3.2325) grad_norm: 1.5294 (1.5332) time: 0.6287 [2021-03-27 08:18:01 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 70/1251] eta: 0:13:25 lr: 0.000510 loss: 3.4204 (3.2477) grad_norm: 1.4966 (1.5224) time: 0.6272 [2021-03-27 08:18:07 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 80/1251] eta: 0:13:11 lr: 0.000510 loss: 3.4361 (3.2565) grad_norm: 1.4424 (1.5239) time: 0.6312 [2021-03-27 08:18:14 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 90/1251] eta: 0:12:58 lr: 0.000510 loss: 3.4100 (3.2650) grad_norm: 1.5017 (1.5360) time: 0.6302 [2021-03-27 08:18:20 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 100/1251] eta: 0:12:47 lr: 0.000510 loss: 3.4100 (3.2741) grad_norm: 1.4736 (1.5250) time: 0.6288 [2021-03-27 08:18:26 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 110/1251] eta: 0:12:36 lr: 0.000510 loss: 3.3824 (3.2890) grad_norm: 1.4586 (1.5201) time: 0.6285 [2021-03-27 08:18:33 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 120/1251] eta: 0:12:26 lr: 0.000510 loss: 3.5565 (3.3023) grad_norm: 1.4810 (1.5192) time: 0.6298 [2021-03-27 08:18:39 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 130/1251] eta: 0:12:17 lr: 0.000510 loss: 3.4711 (3.2807) grad_norm: 1.4810 (1.5155) time: 0.6273 [2021-03-27 08:18:45 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 140/1251] eta: 0:12:09 lr: 0.000510 loss: 3.4711 (3.2986) grad_norm: 1.3978 (1.5101) time: 0.6359 [2021-03-27 08:18:52 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 150/1251] eta: 0:12:01 lr: 0.000510 loss: 3.4227 (3.2876) grad_norm: 1.4449 (1.5192) time: 0.6425 [2021-03-27 08:18:58 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 160/1251] eta: 0:11:53 lr: 0.000510 loss: 3.3727 (3.2967) grad_norm: 1.4605 (1.5166) time: 0.6314 [2021-03-27 08:19:04 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 170/1251] eta: 0:11:45 lr: 0.000509 loss: 3.4205 (3.2965) grad_norm: 1.4423 (1.5141) time: 0.6293 [2021-03-27 08:19:11 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 180/1251] eta: 0:11:37 lr: 0.000509 loss: 3.2312 (3.2908) grad_norm: 1.4347 (1.5133) time: 0.6339 [2021-03-27 08:19:17 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 190/1251] eta: 0:11:29 lr: 0.000509 loss: 3.3739 (3.2985) grad_norm: 1.4506 (1.5109) time: 0.6283 [2021-03-27 08:19:23 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 200/1251] eta: 0:11:22 lr: 0.000509 loss: 3.4330 (3.2977) grad_norm: 1.4819 (1.5133) time: 0.6278 [2021-03-27 08:19:29 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 210/1251] eta: 0:11:14 lr: 0.000509 loss: 2.9797 (3.2881) grad_norm: 1.4871 (1.5143) time: 0.6266 [2021-03-27 08:19:36 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 220/1251] eta: 0:11:06 lr: 0.000509 loss: 3.0691 (3.2823) grad_norm: 1.4476 (1.5122) time: 0.6237 [2021-03-27 08:19:42 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 230/1251] eta: 0:11:00 lr: 0.000509 loss: 3.2774 (3.2822) grad_norm: 1.4476 (1.5174) time: 0.6336 [2021-03-27 08:19:48 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 240/1251] eta: 0:10:52 lr: 0.000509 loss: 3.6449 (3.3032) grad_norm: 1.5028 (1.5146) time: 0.6342 [2021-03-27 08:19:55 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 250/1251] eta: 0:10:45 lr: 0.000509 loss: 3.7704 (3.3168) grad_norm: 1.5028 (1.5159) time: 0.6323 [2021-03-27 08:20:01 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 260/1251] eta: 0:10:38 lr: 0.000509 loss: 3.4561 (3.3137) grad_norm: 1.3918 (1.5111) time: 0.6307 [2021-03-27 08:20:07 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 270/1251] eta: 0:10:31 lr: 0.000509 loss: 3.2085 (3.3152) grad_norm: 1.3669 (1.5110) time: 0.6265 [2021-03-27 08:20:13 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 280/1251] eta: 0:10:24 lr: 0.000509 loss: 3.2344 (3.3072) grad_norm: 1.4017 (1.5092) time: 0.6266 [2021-03-27 08:20:20 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 290/1251] eta: 0:10:17 lr: 0.000509 loss: 3.2481 (3.3122) grad_norm: 1.3998 (1.5067) time: 0.6278 [2021-03-27 08:20:26 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 300/1251] eta: 0:10:11 lr: 0.000509 loss: 3.4179 (3.3154) grad_norm: 1.4186 (1.5079) time: 0.6321 [2021-03-27 08:20:32 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 310/1251] eta: 0:10:04 lr: 0.000509 loss: 3.4992 (3.3167) grad_norm: 1.4410 (1.5061) time: 0.6324 [2021-03-27 08:20:39 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 320/1251] eta: 0:09:57 lr: 0.000509 loss: 3.4992 (3.3150) grad_norm: 1.4866 (1.5075) time: 0.6256 [2021-03-27 08:20:45 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 330/1251] eta: 0:09:50 lr: 0.000509 loss: 3.2946 (3.3132) grad_norm: 1.5096 (1.5084) time: 0.6261 [2021-03-27 08:20:51 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 340/1251] eta: 0:09:43 lr: 0.000509 loss: 3.3237 (3.3110) grad_norm: 1.4914 (1.5083) time: 0.6258 [2021-03-27 08:20:57 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 350/1251] eta: 0:09:36 lr: 0.000509 loss: 3.3237 (3.3130) grad_norm: 1.4498 (1.5076) time: 0.6235 [2021-03-27 08:21:04 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 360/1251] eta: 0:09:30 lr: 0.000509 loss: 3.4620 (3.3121) grad_norm: 1.4698 (1.5097) time: 0.6263 [2021-03-27 08:21:10 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 370/1251] eta: 0:09:23 lr: 0.000509 loss: 3.4904 (3.3188) grad_norm: 1.4660 (1.5079) time: 0.6295 [2021-03-27 08:21:16 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 380/1251] eta: 0:09:16 lr: 0.000509 loss: 3.6254 (3.3189) grad_norm: 1.4460 (1.5075) time: 0.6292 [2021-03-27 08:21:23 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 390/1251] eta: 0:09:10 lr: 0.000509 loss: 3.2153 (3.3186) grad_norm: 1.4529 (1.5053) time: 0.6290 [2021-03-27 08:21:29 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 400/1251] eta: 0:09:03 lr: 0.000509 loss: 3.2213 (3.3212) grad_norm: 1.4250 (1.5066) time: 0.6239 [2021-03-27 08:21:35 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 410/1251] eta: 0:08:56 lr: 0.000508 loss: 3.5513 (3.3230) grad_norm: 1.3578 (1.5024) time: 0.6212 [2021-03-27 08:21:41 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 420/1251] eta: 0:08:50 lr: 0.000508 loss: 3.2537 (3.3145) grad_norm: 1.3768 (1.5022) time: 0.6245 [2021-03-27 08:21:48 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 430/1251] eta: 0:08:43 lr: 0.000508 loss: 3.3577 (3.3196) grad_norm: 1.4809 (1.5027) time: 0.6279 [2021-03-27 08:21:54 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 440/1251] eta: 0:08:36 lr: 0.000508 loss: 3.5059 (3.3211) grad_norm: 1.5104 (1.5044) time: 0.6284 [2021-03-27 08:22:00 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 450/1251] eta: 0:08:30 lr: 0.000508 loss: 3.4401 (3.3170) grad_norm: 1.5013 (1.5044) time: 0.6234 [2021-03-27 08:22:06 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 460/1251] eta: 0:08:23 lr: 0.000508 loss: 3.4062 (3.3161) grad_norm: 1.4307 (1.5023) time: 0.6226 [2021-03-27 08:22:13 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 470/1251] eta: 0:08:17 lr: 0.000508 loss: 3.5970 (3.3214) grad_norm: 1.4551 (1.5086) time: 0.6295 [2021-03-27 08:22:19 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 480/1251] eta: 0:08:10 lr: 0.000508 loss: 3.6700 (3.3234) grad_norm: 1.5558 (1.5095) time: 0.6273 [2021-03-27 08:22:25 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 490/1251] eta: 0:08:04 lr: 0.000508 loss: 3.4004 (3.3184) grad_norm: 1.5851 (1.5116) time: 0.6259 [2021-03-27 08:22:31 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 500/1251] eta: 0:07:57 lr: 0.000508 loss: 3.4004 (3.3221) grad_norm: 1.5245 (1.5110) time: 0.6281 [2021-03-27 08:22:38 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 510/1251] eta: 0:07:51 lr: 0.000508 loss: 3.6369 (3.3218) grad_norm: 1.4771 (1.5119) time: 0.6329 [2021-03-27 08:22:44 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 520/1251] eta: 0:07:45 lr: 0.000508 loss: 3.3902 (3.3178) grad_norm: 1.6045 (1.5136) time: 0.6375 [2021-03-27 08:22:50 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 530/1251] eta: 0:07:38 lr: 0.000508 loss: 2.9539 (3.3126) grad_norm: 1.4460 (1.5125) time: 0.6339 [2021-03-27 08:22:57 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 540/1251] eta: 0:07:32 lr: 0.000508 loss: 3.3635 (3.3164) grad_norm: 1.4036 (1.5095) time: 0.6328 [2021-03-27 08:23:03 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 550/1251] eta: 0:07:25 lr: 0.000508 loss: 3.4057 (3.3158) grad_norm: 1.3300 (1.5069) time: 0.6353 [2021-03-27 08:23:10 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 560/1251] eta: 0:07:19 lr: 0.000508 loss: 3.4057 (3.3164) grad_norm: 1.3837 (1.5086) time: 0.6394 [2021-03-27 08:23:16 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 570/1251] eta: 0:07:13 lr: 0.000508 loss: 3.3200 (3.3135) grad_norm: 1.4406 (1.5105) time: 0.6377 [2021-03-27 08:23:22 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 580/1251] eta: 0:07:06 lr: 0.000508 loss: 3.1372 (3.3126) grad_norm: 1.4533 (1.5105) time: 0.6327 [2021-03-27 08:23:29 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 590/1251] eta: 0:07:00 lr: 0.000508 loss: 3.3095 (3.3115) grad_norm: 1.4503 (1.5094) time: 0.6312 [2021-03-27 08:23:35 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 600/1251] eta: 0:06:53 lr: 0.000508 loss: 3.3639 (3.3099) grad_norm: 1.4503 (1.5088) time: 0.6341 [2021-03-27 08:23:41 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 610/1251] eta: 0:06:47 lr: 0.000508 loss: 3.3740 (3.3088) grad_norm: 1.4221 (1.5080) time: 0.6351 [2021-03-27 08:23:48 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 620/1251] eta: 0:06:41 lr: 0.000508 loss: 3.4704 (3.3114) grad_norm: 1.4187 (1.5077) time: 0.6344 [2021-03-27 08:23:54 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 630/1251] eta: 0:06:34 lr: 0.000508 loss: 3.3255 (3.3113) grad_norm: 1.4853 (1.5073) time: 0.6252 [2021-03-27 08:24:00 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 640/1251] eta: 0:06:28 lr: 0.000508 loss: 3.3255 (3.3114) grad_norm: 1.4663 (1.5094) time: 0.6239 [2021-03-27 08:24:06 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 650/1251] eta: 0:06:21 lr: 0.000507 loss: 3.4036 (3.3082) grad_norm: 1.4366 (1.5079) time: 0.6307 [2021-03-27 08:24:13 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 660/1251] eta: 0:06:15 lr: 0.000507 loss: 3.0387 (3.3062) grad_norm: 1.4493 (1.5094) time: 0.6317 [2021-03-27 08:24:19 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 670/1251] eta: 0:06:09 lr: 0.000507 loss: 3.4403 (3.3095) grad_norm: 1.5285 (1.5098) time: 0.6303 [2021-03-27 08:24:25 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 680/1251] eta: 0:06:02 lr: 0.000507 loss: 3.5375 (3.3100) grad_norm: 1.5193 (1.5095) time: 0.6234 [2021-03-27 08:24:32 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 690/1251] eta: 0:05:56 lr: 0.000507 loss: 3.3820 (3.3077) grad_norm: 1.4715 (1.5096) time: 0.6236 [2021-03-27 08:24:38 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 700/1251] eta: 0:05:49 lr: 0.000507 loss: 3.1034 (3.3048) grad_norm: 1.4901 (1.5103) time: 0.6270 [2021-03-27 08:24:44 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 710/1251] eta: 0:05:43 lr: 0.000507 loss: 3.1411 (3.3025) grad_norm: 1.4901 (1.5099) time: 0.6294 [2021-03-27 08:24:50 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 720/1251] eta: 0:05:37 lr: 0.000507 loss: 3.2152 (3.3026) grad_norm: 1.5114 (1.5121) time: 0.6300 [2021-03-27 08:24:57 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 730/1251] eta: 0:05:30 lr: 0.000507 loss: 3.3444 (3.2997) grad_norm: 1.5399 (1.5123) time: 0.6275 [2021-03-27 08:25:03 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 740/1251] eta: 0:05:24 lr: 0.000507 loss: 3.2415 (3.2974) grad_norm: 1.4935 (1.5124) time: 0.6298 [2021-03-27 08:25:09 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 750/1251] eta: 0:05:17 lr: 0.000507 loss: 2.9921 (3.2965) grad_norm: 1.4936 (1.5123) time: 0.6290 [2021-03-27 08:25:15 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 760/1251] eta: 0:05:11 lr: 0.000507 loss: 3.3134 (3.2967) grad_norm: 1.5089 (1.5144) time: 0.6264 [2021-03-27 08:25:22 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 770/1251] eta: 0:05:05 lr: 0.000507 loss: 3.0207 (3.2924) grad_norm: 1.5693 (1.5148) time: 0.6398 [2021-03-27 08:25:28 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 780/1251] eta: 0:04:58 lr: 0.000507 loss: 2.9977 (3.2916) grad_norm: 1.5893 (1.5166) time: 0.6472 [2021-03-27 08:25:35 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 790/1251] eta: 0:04:52 lr: 0.000507 loss: 3.3320 (3.2905) grad_norm: 1.5657 (1.5156) time: 0.6358 [2021-03-27 08:25:41 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 800/1251] eta: 0:04:46 lr: 0.000507 loss: 3.1299 (3.2885) grad_norm: 1.4062 (1.5142) time: 0.6306 [2021-03-27 08:25:47 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 810/1251] eta: 0:04:39 lr: 0.000507 loss: 3.1299 (3.2888) grad_norm: 1.4414 (1.5138) time: 0.6298 [2021-03-27 08:25:54 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 820/1251] eta: 0:04:33 lr: 0.000507 loss: 3.3466 (3.2874) grad_norm: 1.4773 (1.5135) time: 0.6252 [2021-03-27 08:26:00 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 830/1251] eta: 0:04:26 lr: 0.000507 loss: 3.2691 (3.2867) grad_norm: 1.4828 (1.5134) time: 0.6209 [2021-03-27 08:26:06 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 840/1251] eta: 0:04:20 lr: 0.000507 loss: 3.3511 (3.2880) grad_norm: 1.4395 (1.5127) time: 0.6247 [2021-03-27 08:26:12 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 850/1251] eta: 0:04:14 lr: 0.000507 loss: 3.3881 (3.2873) grad_norm: 1.4395 (1.5123) time: 0.6291 [2021-03-27 08:26:19 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 860/1251] eta: 0:04:07 lr: 0.000507 loss: 3.3025 (3.2836) grad_norm: 1.4444 (1.5126) time: 0.6316 [2021-03-27 08:26:25 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 870/1251] eta: 0:04:01 lr: 0.000507 loss: 3.1945 (3.2833) grad_norm: 1.4296 (1.5114) time: 0.6333 [2021-03-27 08:26:31 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 880/1251] eta: 0:03:55 lr: 0.000507 loss: 3.1945 (3.2814) grad_norm: 1.4296 (1.5122) time: 0.6276 [2021-03-27 08:26:38 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 890/1251] eta: 0:03:48 lr: 0.000506 loss: 3.4376 (3.2852) grad_norm: 1.5830 (1.5122) time: 0.6280 [2021-03-27 08:26:44 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 900/1251] eta: 0:03:42 lr: 0.000506 loss: 3.6604 (3.2864) grad_norm: 1.4429 (1.5126) time: 0.6306 [2021-03-27 08:26:50 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 910/1251] eta: 0:03:36 lr: 0.000506 loss: 3.5416 (3.2890) grad_norm: 1.4678 (1.5122) time: 0.6324 [2021-03-27 08:26:57 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 920/1251] eta: 0:03:29 lr: 0.000506 loss: 3.5835 (3.2888) grad_norm: 1.4218 (1.5115) time: 0.6359 [2021-03-27 08:27:03 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 930/1251] eta: 0:03:23 lr: 0.000506 loss: 3.5243 (3.2878) grad_norm: 1.4258 (1.5114) time: 0.6306 [2021-03-27 08:27:09 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 940/1251] eta: 0:03:17 lr: 0.000506 loss: 3.5243 (3.2903) grad_norm: 1.4962 (1.5122) time: 0.6304 [2021-03-27 08:27:16 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 950/1251] eta: 0:03:10 lr: 0.000506 loss: 3.5478 (3.2923) grad_norm: 1.4890 (1.5115) time: 0.6351 [2021-03-27 08:27:22 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 960/1251] eta: 0:03:04 lr: 0.000506 loss: 3.5478 (3.2937) grad_norm: 1.4916 (1.5119) time: 0.6326 [2021-03-27 08:27:28 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 970/1251] eta: 0:02:58 lr: 0.000506 loss: 3.3545 (3.2924) grad_norm: 1.5002 (1.5110) time: 0.6266 [2021-03-27 08:27:34 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 980/1251] eta: 0:02:51 lr: 0.000506 loss: 3.3027 (3.2935) grad_norm: 1.4144 (1.5108) time: 0.6254 [2021-03-27 08:27:41 swin_base_patch4_window7_224] INFO: Epoch: [149] [ 990/1251] eta: 0:02:45 lr: 0.000506 loss: 3.2412 (3.2936) grad_norm: 1.4704 (1.5124) time: 0.6287 [2021-03-27 08:27:47 swin_base_patch4_window7_224] INFO: Epoch: [149] [1000/1251] eta: 0:02:39 lr: 0.000506 loss: 3.2412 (3.2939) grad_norm: 1.4704 (1.5119) time: 0.6281 [2021-03-27 08:27:53 swin_base_patch4_window7_224] INFO: Epoch: [149] [1010/1251] eta: 0:02:32 lr: 0.000506 loss: 3.3476 (3.2928) grad_norm: 1.4474 (1.5113) time: 0.6275 [2021-03-27 08:28:00 swin_base_patch4_window7_224] INFO: Epoch: [149] [1020/1251] eta: 0:02:26 lr: 0.000506 loss: 3.5323 (3.2956) grad_norm: 1.5406 (1.5122) time: 0.6299 [2021-03-27 08:28:06 swin_base_patch4_window7_224] INFO: Epoch: [149] [1030/1251] eta: 0:02:19 lr: 0.000506 loss: 3.6220 (3.2971) grad_norm: 1.5279 (1.5116) time: 0.6265 [2021-03-27 08:28:12 swin_base_patch4_window7_224] INFO: Epoch: [149] [1040/1251] eta: 0:02:13 lr: 0.000506 loss: 3.4670 (3.2958) grad_norm: 1.4704 (1.5120) time: 0.6228 [2021-03-27 08:28:18 swin_base_patch4_window7_224] INFO: Epoch: [149] [1050/1251] eta: 0:02:07 lr: 0.000506 loss: 2.9292 (3.2926) grad_norm: 1.5762 (1.5123) time: 0.6244 [2021-03-27 08:28:25 swin_base_patch4_window7_224] INFO: Epoch: [149] [1060/1251] eta: 0:02:00 lr: 0.000506 loss: 2.9850 (3.2923) grad_norm: 1.5762 (1.5127) time: 0.6289 [2021-03-27 08:28:31 swin_base_patch4_window7_224] INFO: Epoch: [149] [1070/1251] eta: 0:01:54 lr: 0.000506 loss: 3.5039 (3.2922) grad_norm: 1.4262 (1.5124) time: 0.6332 [2021-03-27 08:28:37 swin_base_patch4_window7_224] INFO: Epoch: [149] [1080/1251] eta: 0:01:48 lr: 0.000506 loss: 3.3110 (3.2913) grad_norm: 1.4403 (1.5121) time: 0.6303 [2021-03-27 08:28:43 swin_base_patch4_window7_224] INFO: Epoch: [149] [1090/1251] eta: 0:01:41 lr: 0.000506 loss: 3.3110 (3.2920) grad_norm: 1.4685 (1.5121) time: 0.6237 [2021-03-27 08:28:50 swin_base_patch4_window7_224] INFO: Epoch: [149] [1100/1251] eta: 0:01:35 lr: 0.000506 loss: 3.3358 (3.2932) grad_norm: 1.4550 (1.5115) time: 0.6232 [2021-03-27 08:28:56 swin_base_patch4_window7_224] INFO: Epoch: [149] [1110/1251] eta: 0:01:29 lr: 0.000506 loss: 3.5996 (3.2923) grad_norm: 1.4788 (1.5122) time: 0.6304 [2021-03-27 08:29:02 swin_base_patch4_window7_224] INFO: Epoch: [149] [1120/1251] eta: 0:01:22 lr: 0.000506 loss: 3.2368 (3.2904) grad_norm: 1.5531 (1.5129) time: 0.6317 [2021-03-27 08:29:09 swin_base_patch4_window7_224] INFO: Epoch: [149] [1130/1251] eta: 0:01:16 lr: 0.000506 loss: 3.3944 (3.2926) grad_norm: 1.5522 (1.5139) time: 0.6284 [2021-03-27 08:29:15 swin_base_patch4_window7_224] INFO: Epoch: [149] [1140/1251] eta: 0:01:10 lr: 0.000505 loss: 3.5285 (3.2923) grad_norm: 1.4754 (1.5132) time: 0.6281 [2021-03-27 08:29:21 swin_base_patch4_window7_224] INFO: Epoch: [149] [1150/1251] eta: 0:01:03 lr: 0.000505 loss: 3.3842 (3.2942) grad_norm: 1.3943 (1.5123) time: 0.6274 [2021-03-27 08:29:27 swin_base_patch4_window7_224] INFO: Epoch: [149] [1160/1251] eta: 0:00:57 lr: 0.000505 loss: 3.3842 (3.2950) grad_norm: 1.4286 (1.5120) time: 0.6285 [2021-03-27 08:29:34 swin_base_patch4_window7_224] INFO: Epoch: [149] [1170/1251] eta: 0:00:51 lr: 0.000505 loss: 3.4107 (3.2956) grad_norm: 1.4094 (1.5107) time: 0.6295 [2021-03-27 08:29:40 swin_base_patch4_window7_224] INFO: Epoch: [149] [1180/1251] eta: 0:00:44 lr: 0.000505 loss: 3.1958 (3.2922) grad_norm: 1.2996 (1.5099) time: 0.6261 [2021-03-27 08:29:46 swin_base_patch4_window7_224] INFO: Epoch: [149] [1190/1251] eta: 0:00:38 lr: 0.000505 loss: 3.0013 (3.2919) grad_norm: 1.4850 (1.5104) time: 0.6251 [2021-03-27 08:29:53 swin_base_patch4_window7_224] INFO: Epoch: [149] [1200/1251] eta: 0:00:32 lr: 0.000505 loss: 3.2366 (3.2912) grad_norm: 1.4664 (1.5096) time: 0.6299 [2021-03-27 08:29:59 swin_base_patch4_window7_224] INFO: Epoch: [149] [1210/1251] eta: 0:00:25 lr: 0.000505 loss: 3.2366 (3.2908) grad_norm: 1.4613 (1.5099) time: 0.6366 [2021-03-27 08:30:05 swin_base_patch4_window7_224] INFO: Epoch: [149] [1220/1251] eta: 0:00:19 lr: 0.000505 loss: 3.4093 (3.2918) grad_norm: 1.4613 (1.5088) time: 0.6310 [2021-03-27 08:30:11 swin_base_patch4_window7_224] INFO: Epoch: [149] [1230/1251] eta: 0:00:13 lr: 0.000505 loss: 3.4530 (3.2916) grad_norm: 1.4279 (1.5096) time: 0.6256 [2021-03-27 08:30:18 swin_base_patch4_window7_224] INFO: Epoch: [149] [1240/1251] eta: 0:00:06 lr: 0.000505 loss: 3.0318 (3.2879) grad_norm: 1.4818 (1.5089) time: 0.6283 [2021-03-27 08:30:24 swin_base_patch4_window7_224] INFO: Epoch: [149] [1250/1251] eta: 0:00:00 lr: 0.000505 loss: 3.1853 (3.2885) grad_norm: 1.4442 (1.5083) time: 0.6245 [2021-03-27 08:30:33 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:43 loss: 0.9263 (0.9263) acc1: 79.6875 (79.6875) acc5: 96.8750 (96.8750) [2021-03-27 08:30:35 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.8373 (0.8116) acc1: 79.6875 (80.5398) acc5: 96.8750 (96.4489) [2021-03-27 08:30:38 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8890 (0.8813) acc1: 78.1250 (79.2411) acc5: 95.3125 (95.3125) [2021-03-27 08:30:40 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9097 (0.8919) acc1: 76.5625 (78.2258) acc5: 95.3125 (95.2621) [2021-03-27 08:30:43 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8893 (0.8859) acc1: 75.0000 (78.1631) acc5: 95.3125 (95.4649) [2021-03-27 08:30:44 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8965 (0.8975) acc1: 75.0000 (78.2400) acc5: 95.3125 (95.4240) [2021-03-27 08:30:52 swin_base_patch4_window7_224] INFO: * Acc@1 78.926 Acc@5 94.848 loss 0.899 [2021-03-27 08:30:52 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.9% [2021-03-27 08:30:52 swin_base_patch4_window7_224] INFO: Max accuracy: 78.93% [2021-03-27 08:30:56 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 0/1251] eta: 1:32:08 lr: 0.000505 loss: 3.6891 (3.6891) grad_norm: 1.3115 (1.3115) time: 4.4196 [2021-03-27 08:31:02 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 10/1251] eta: 0:20:19 lr: 0.000505 loss: 3.6472 (3.3968) grad_norm: 1.4195 (1.4555) time: 0.9829 [2021-03-27 08:31:09 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 20/1251] eta: 0:16:41 lr: 0.000505 loss: 3.4525 (3.3867) grad_norm: 1.4201 (1.4810) time: 0.6334 [2021-03-27 08:31:15 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 30/1251] eta: 0:15:22 lr: 0.000505 loss: 3.4155 (3.3114) grad_norm: 1.5205 (1.5084) time: 0.6303 [2021-03-27 08:31:21 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 40/1251] eta: 0:14:36 lr: 0.000505 loss: 3.4950 (3.3487) grad_norm: 1.4721 (1.4956) time: 0.6293 [2021-03-27 08:31:28 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 50/1251] eta: 0:14:07 lr: 0.000505 loss: 3.5421 (3.3941) grad_norm: 1.4418 (1.4944) time: 0.6284 [2021-03-27 08:31:34 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 60/1251] eta: 0:13:45 lr: 0.000505 loss: 3.5421 (3.4088) grad_norm: 1.4529 (1.4935) time: 0.6301 [2021-03-27 08:31:40 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 70/1251] eta: 0:13:27 lr: 0.000505 loss: 3.4627 (3.3976) grad_norm: 1.5250 (1.5165) time: 0.6289 [2021-03-27 08:31:46 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 80/1251] eta: 0:13:13 lr: 0.000505 loss: 3.2480 (3.3753) grad_norm: 1.5217 (1.5121) time: 0.6296 [2021-03-27 08:31:53 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 90/1251] eta: 0:13:01 lr: 0.000505 loss: 3.2325 (3.3794) grad_norm: 1.5217 (1.5250) time: 0.6332 [2021-03-27 08:31:59 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 100/1251] eta: 0:12:51 lr: 0.000505 loss: 3.1719 (3.3487) grad_norm: 1.5403 (1.5251) time: 0.6396 [2021-03-27 08:32:05 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 110/1251] eta: 0:12:40 lr: 0.000505 loss: 3.1719 (3.3335) grad_norm: 1.4375 (1.5177) time: 0.6357 [2021-03-27 08:32:12 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 120/1251] eta: 0:12:30 lr: 0.000505 loss: 3.3613 (3.3304) grad_norm: 1.4790 (1.5260) time: 0.6335 [2021-03-27 08:32:18 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 130/1251] eta: 0:12:21 lr: 0.000504 loss: 2.9464 (3.3000) grad_norm: 1.5405 (1.5267) time: 0.6365 [2021-03-27 08:32:25 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 140/1251] eta: 0:12:12 lr: 0.000504 loss: 3.0767 (3.3027) grad_norm: 1.4731 (1.5233) time: 0.6312 [2021-03-27 08:32:31 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 150/1251] eta: 0:12:04 lr: 0.000504 loss: 3.3088 (3.2956) grad_norm: 1.4383 (1.5158) time: 0.6374 [2021-03-27 08:32:37 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 160/1251] eta: 0:11:56 lr: 0.000504 loss: 3.3223 (3.2969) grad_norm: 1.3518 (1.5144) time: 0.6391 [2021-03-27 08:32:44 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 170/1251] eta: 0:11:48 lr: 0.000504 loss: 3.3223 (3.2996) grad_norm: 1.4612 (1.5181) time: 0.6304 [2021-03-27 08:32:50 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 180/1251] eta: 0:11:40 lr: 0.000504 loss: 3.4948 (3.3087) grad_norm: 1.4612 (1.5144) time: 0.6335 [2021-03-27 08:32:56 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 190/1251] eta: 0:11:32 lr: 0.000504 loss: 3.4647 (3.3082) grad_norm: 1.4320 (1.5096) time: 0.6296 [2021-03-27 08:33:03 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 200/1251] eta: 0:11:24 lr: 0.000504 loss: 3.3019 (3.2987) grad_norm: 1.3941 (1.5050) time: 0.6298 [2021-03-27 08:33:09 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 210/1251] eta: 0:11:17 lr: 0.000504 loss: 3.2399 (3.3014) grad_norm: 1.3941 (1.5016) time: 0.6342 [2021-03-27 08:33:15 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 220/1251] eta: 0:11:10 lr: 0.000504 loss: 3.4550 (3.3060) grad_norm: 1.3956 (1.4991) time: 0.6326 [2021-03-27 08:33:22 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 230/1251] eta: 0:11:02 lr: 0.000504 loss: 3.4569 (3.3024) grad_norm: 1.3872 (1.4962) time: 0.6331 [2021-03-27 08:33:28 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 240/1251] eta: 0:10:55 lr: 0.000504 loss: 3.0788 (3.2902) grad_norm: 1.4247 (1.4987) time: 0.6297 [2021-03-27 08:33:34 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 250/1251] eta: 0:10:48 lr: 0.000504 loss: 3.0584 (3.2854) grad_norm: 1.4659 (1.4974) time: 0.6329 [2021-03-27 08:33:41 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 260/1251] eta: 0:10:41 lr: 0.000504 loss: 3.1057 (3.2828) grad_norm: 1.4708 (1.4979) time: 0.6360 [2021-03-27 08:33:47 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 270/1251] eta: 0:10:34 lr: 0.000504 loss: 3.4376 (3.2818) grad_norm: 1.3928 (1.4946) time: 0.6378 [2021-03-27 08:33:53 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 280/1251] eta: 0:10:27 lr: 0.000504 loss: 3.2120 (3.2796) grad_norm: 1.3928 (1.4935) time: 0.6378 [2021-03-27 08:34:00 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 290/1251] eta: 0:10:20 lr: 0.000504 loss: 3.2120 (3.2759) grad_norm: 1.5101 (1.4956) time: 0.6302 [2021-03-27 08:34:06 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 300/1251] eta: 0:10:14 lr: 0.000504 loss: 3.1918 (3.2716) grad_norm: 1.5563 (1.4984) time: 0.6317 [2021-03-27 08:34:12 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 310/1251] eta: 0:10:06 lr: 0.000504 loss: 3.4557 (3.2731) grad_norm: 1.5213 (1.4983) time: 0.6296 [2021-03-27 08:34:18 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 320/1251] eta: 0:09:59 lr: 0.000504 loss: 3.4706 (3.2770) grad_norm: 1.4920 (1.5000) time: 0.6229 [2021-03-27 08:34:25 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 330/1251] eta: 0:09:52 lr: 0.000504 loss: 3.4485 (3.2831) grad_norm: 1.4558 (1.4983) time: 0.6232 [2021-03-27 08:34:31 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 340/1251] eta: 0:09:45 lr: 0.000504 loss: 3.3442 (3.2812) grad_norm: 1.4396 (1.4972) time: 0.6255 [2021-03-27 08:34:37 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 350/1251] eta: 0:09:39 lr: 0.000504 loss: 3.3623 (3.2854) grad_norm: 1.4178 (1.4996) time: 0.6293 [2021-03-27 08:34:44 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 360/1251] eta: 0:09:32 lr: 0.000504 loss: 3.2636 (3.2784) grad_norm: 1.4160 (1.4981) time: 0.6347 [2021-03-27 08:34:50 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 370/1251] eta: 0:09:25 lr: 0.000503 loss: 3.0053 (3.2714) grad_norm: 1.4160 (1.4964) time: 0.6343 [2021-03-27 08:34:56 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 380/1251] eta: 0:09:19 lr: 0.000503 loss: 2.9147 (3.2612) grad_norm: 1.4693 (1.4987) time: 0.6290 [2021-03-27 08:35:02 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 390/1251] eta: 0:09:12 lr: 0.000503 loss: 3.0732 (3.2656) grad_norm: 1.5606 (1.5011) time: 0.6259 [2021-03-27 08:35:09 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 400/1251] eta: 0:09:05 lr: 0.000503 loss: 3.4209 (3.2655) grad_norm: 1.5477 (1.5020) time: 0.6224 [2021-03-27 08:35:15 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 410/1251] eta: 0:08:58 lr: 0.000503 loss: 3.3345 (3.2677) grad_norm: 1.4242 (1.4994) time: 0.6262 [2021-03-27 08:35:21 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 420/1251] eta: 0:08:52 lr: 0.000503 loss: 3.1937 (3.2607) grad_norm: 1.4088 (1.4992) time: 0.6320 [2021-03-27 08:35:28 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 430/1251] eta: 0:08:45 lr: 0.000503 loss: 3.3550 (3.2635) grad_norm: 1.4975 (1.4983) time: 0.6298 [2021-03-27 08:35:34 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 440/1251] eta: 0:08:39 lr: 0.000503 loss: 3.3579 (3.2631) grad_norm: 1.4397 (1.4968) time: 0.6272 [2021-03-27 08:35:40 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 450/1251] eta: 0:08:32 lr: 0.000503 loss: 3.1215 (3.2619) grad_norm: 1.4397 (1.4973) time: 0.6294 [2021-03-27 08:35:47 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 460/1251] eta: 0:08:25 lr: 0.000503 loss: 2.8697 (3.2522) grad_norm: 1.4811 (1.4962) time: 0.6327 [2021-03-27 08:35:53 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 470/1251] eta: 0:08:19 lr: 0.000503 loss: 2.8635 (3.2490) grad_norm: 1.4901 (1.4980) time: 0.6317 [2021-03-27 08:35:59 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 480/1251] eta: 0:08:12 lr: 0.000503 loss: 2.9980 (3.2449) grad_norm: 1.5671 (1.5008) time: 0.6316 [2021-03-27 08:36:05 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 490/1251] eta: 0:08:06 lr: 0.000503 loss: 3.0345 (3.2449) grad_norm: 1.4624 (1.4993) time: 0.6313 [2021-03-27 08:36:12 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 500/1251] eta: 0:07:59 lr: 0.000503 loss: 3.2102 (3.2439) grad_norm: 1.4523 (1.4998) time: 0.6278 [2021-03-27 08:36:18 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 510/1251] eta: 0:07:53 lr: 0.000503 loss: 3.1072 (3.2432) grad_norm: 1.4820 (1.4984) time: 0.6291 [2021-03-27 08:36:24 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 520/1251] eta: 0:07:46 lr: 0.000503 loss: 3.2264 (3.2426) grad_norm: 1.4820 (1.4997) time: 0.6358 [2021-03-27 08:36:31 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 530/1251] eta: 0:07:40 lr: 0.000503 loss: 3.3199 (3.2442) grad_norm: 1.5724 (1.5013) time: 0.6397 [2021-03-27 08:36:37 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 540/1251] eta: 0:07:33 lr: 0.000503 loss: 3.4138 (3.2476) grad_norm: 1.6422 (1.5045) time: 0.6325 [2021-03-27 08:36:44 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 550/1251] eta: 0:07:27 lr: 0.000503 loss: 3.3991 (3.2510) grad_norm: 1.5469 (1.5046) time: 0.6414 [2021-03-27 08:36:50 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 560/1251] eta: 0:07:21 lr: 0.000503 loss: 3.3867 (3.2537) grad_norm: 1.4790 (1.5044) time: 0.6443 [2021-03-27 08:36:56 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 570/1251] eta: 0:07:14 lr: 0.000503 loss: 3.6366 (3.2582) grad_norm: 1.5284 (1.5057) time: 0.6335 [2021-03-27 08:37:03 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 580/1251] eta: 0:07:08 lr: 0.000503 loss: 3.5058 (3.2583) grad_norm: 1.4519 (1.5042) time: 0.6346 [2021-03-27 08:37:09 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 590/1251] eta: 0:07:02 lr: 0.000503 loss: 3.1816 (3.2524) grad_norm: 1.4519 (1.5046) time: 0.6353 [2021-03-27 08:37:15 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 600/1251] eta: 0:06:55 lr: 0.000503 loss: 3.1816 (3.2529) grad_norm: 1.5067 (1.5058) time: 0.6325 [2021-03-27 08:37:22 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 610/1251] eta: 0:06:49 lr: 0.000502 loss: 3.3682 (3.2525) grad_norm: 1.4643 (1.5063) time: 0.6260 [2021-03-27 08:37:28 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 620/1251] eta: 0:06:42 lr: 0.000502 loss: 3.3355 (3.2518) grad_norm: 1.4557 (1.5064) time: 0.6284 [2021-03-27 08:37:34 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 630/1251] eta: 0:06:36 lr: 0.000502 loss: 3.3755 (3.2506) grad_norm: 1.4610 (1.5070) time: 0.6293 [2021-03-27 08:37:41 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 640/1251] eta: 0:06:29 lr: 0.000502 loss: 3.3755 (3.2515) grad_norm: 1.4610 (1.5084) time: 0.6347 [2021-03-27 08:37:47 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 650/1251] eta: 0:06:23 lr: 0.000502 loss: 3.5202 (3.2562) grad_norm: 1.5272 (1.5087) time: 0.6395 [2021-03-27 08:37:53 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 660/1251] eta: 0:06:16 lr: 0.000502 loss: 3.4898 (3.2568) grad_norm: 1.4679 (1.5095) time: 0.6293 [2021-03-27 08:37:59 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 670/1251] eta: 0:06:10 lr: 0.000502 loss: 3.4898 (3.2592) grad_norm: 1.4679 (1.5093) time: 0.6240 [2021-03-27 08:38:06 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 680/1251] eta: 0:06:03 lr: 0.000502 loss: 3.5403 (3.2625) grad_norm: 1.4489 (1.5086) time: 0.6287 [2021-03-27 08:38:12 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 690/1251] eta: 0:05:57 lr: 0.000502 loss: 3.3181 (3.2608) grad_norm: 1.4351 (1.5088) time: 0.6339 [2021-03-27 08:38:18 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 700/1251] eta: 0:05:51 lr: 0.000502 loss: 3.1452 (3.2614) grad_norm: 1.4973 (1.5095) time: 0.6302 [2021-03-27 08:38:25 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 710/1251] eta: 0:05:44 lr: 0.000502 loss: 3.4702 (3.2648) grad_norm: 1.5725 (1.5104) time: 0.6296 [2021-03-27 08:38:31 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 720/1251] eta: 0:05:38 lr: 0.000502 loss: 3.4702 (3.2630) grad_norm: 1.5725 (1.5127) time: 0.6344 [2021-03-27 08:38:38 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 730/1251] eta: 0:05:32 lr: 0.000502 loss: 2.9587 (3.2607) grad_norm: 1.5433 (1.5134) time: 0.6407 [2021-03-27 08:38:44 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 740/1251] eta: 0:05:25 lr: 0.000502 loss: 3.2905 (3.2617) grad_norm: 1.4754 (1.5135) time: 0.6456 [2021-03-27 08:38:50 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 750/1251] eta: 0:05:19 lr: 0.000502 loss: 3.4175 (3.2619) grad_norm: 1.4536 (1.5133) time: 0.6413 [2021-03-27 08:38:57 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 760/1251] eta: 0:05:12 lr: 0.000502 loss: 3.3482 (3.2619) grad_norm: 1.5162 (1.5141) time: 0.6349 [2021-03-27 08:39:03 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 770/1251] eta: 0:05:06 lr: 0.000502 loss: 3.3464 (3.2597) grad_norm: 1.5656 (1.5147) time: 0.6328 [2021-03-27 08:39:09 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 780/1251] eta: 0:05:00 lr: 0.000502 loss: 3.3208 (3.2611) grad_norm: 1.5135 (1.5145) time: 0.6359 [2021-03-27 08:39:16 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 790/1251] eta: 0:04:53 lr: 0.000502 loss: 3.4735 (3.2623) grad_norm: 1.4583 (1.5143) time: 0.6405 [2021-03-27 08:39:22 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 800/1251] eta: 0:04:47 lr: 0.000502 loss: 3.4284 (3.2621) grad_norm: 1.4508 (1.5133) time: 0.6352 [2021-03-27 08:39:28 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 810/1251] eta: 0:04:40 lr: 0.000502 loss: 3.4337 (3.2649) grad_norm: 1.4545 (1.5128) time: 0.6292 [2021-03-27 08:39:35 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 820/1251] eta: 0:04:34 lr: 0.000502 loss: 3.4688 (3.2671) grad_norm: 1.5153 (1.5160) time: 0.6255 [2021-03-27 08:39:41 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 830/1251] eta: 0:04:28 lr: 0.000502 loss: 3.2614 (3.2629) grad_norm: 1.6289 (1.5179) time: 0.6271 [2021-03-27 08:39:47 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 840/1251] eta: 0:04:21 lr: 0.000502 loss: 2.8945 (3.2625) grad_norm: 1.6229 (1.5194) time: 0.6327 [2021-03-27 08:39:54 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 850/1251] eta: 0:04:15 lr: 0.000501 loss: 3.2090 (3.2629) grad_norm: 1.6229 (1.5207) time: 0.6280 [2021-03-27 08:40:00 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 860/1251] eta: 0:04:08 lr: 0.000501 loss: 3.4545 (3.2645) grad_norm: 1.5408 (1.5206) time: 0.6301 [2021-03-27 08:40:06 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 870/1251] eta: 0:04:02 lr: 0.000501 loss: 3.4688 (3.2634) grad_norm: 1.4516 (1.5196) time: 0.6396 [2021-03-27 08:40:13 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 880/1251] eta: 0:03:56 lr: 0.000501 loss: 3.3233 (3.2625) grad_norm: 1.4821 (1.5197) time: 0.6433 [2021-03-27 08:40:19 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 890/1251] eta: 0:03:49 lr: 0.000501 loss: 3.3129 (3.2631) grad_norm: 1.5023 (1.5189) time: 0.6345 [2021-03-27 08:40:25 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 900/1251] eta: 0:03:43 lr: 0.000501 loss: 3.5440 (3.2663) grad_norm: 1.3666 (1.5180) time: 0.6298 [2021-03-27 08:40:32 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 910/1251] eta: 0:03:37 lr: 0.000501 loss: 3.5563 (3.2653) grad_norm: 1.4756 (1.5181) time: 0.6301 [2021-03-27 08:40:38 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 920/1251] eta: 0:03:30 lr: 0.000501 loss: 2.9839 (3.2633) grad_norm: 1.4707 (1.5179) time: 0.6308 [2021-03-27 08:40:44 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 930/1251] eta: 0:03:24 lr: 0.000501 loss: 3.4887 (3.2654) grad_norm: 1.4143 (1.5175) time: 0.6352 [2021-03-27 08:40:51 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 940/1251] eta: 0:03:17 lr: 0.000501 loss: 3.5205 (3.2673) grad_norm: 1.3939 (1.5163) time: 0.6317 [2021-03-27 08:40:57 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 950/1251] eta: 0:03:11 lr: 0.000501 loss: 3.2297 (3.2665) grad_norm: 1.3941 (1.5162) time: 0.6266 [2021-03-27 08:41:03 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 960/1251] eta: 0:03:05 lr: 0.000501 loss: 3.1914 (3.2660) grad_norm: 1.4574 (1.5159) time: 0.6274 [2021-03-27 08:41:09 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 970/1251] eta: 0:02:58 lr: 0.000501 loss: 3.1914 (3.2647) grad_norm: 1.4177 (1.5147) time: 0.6312 [2021-03-27 08:41:16 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 980/1251] eta: 0:02:52 lr: 0.000501 loss: 3.2734 (3.2657) grad_norm: 1.4157 (1.5142) time: 0.6305 [2021-03-27 08:41:22 swin_base_patch4_window7_224] INFO: Epoch: [150] [ 990/1251] eta: 0:02:46 lr: 0.000501 loss: 3.2108 (3.2647) grad_norm: 1.4568 (1.5142) time: 0.6273 [2021-03-27 08:41:28 swin_base_patch4_window7_224] INFO: Epoch: [150] [1000/1251] eta: 0:02:39 lr: 0.000501 loss: 3.2345 (3.2650) grad_norm: 1.5346 (1.5141) time: 0.6317 [2021-03-27 08:41:35 swin_base_patch4_window7_224] INFO: Epoch: [150] [1010/1251] eta: 0:02:33 lr: 0.000501 loss: 3.2439 (3.2651) grad_norm: 1.5615 (1.5152) time: 0.6335 [2021-03-27 08:41:41 swin_base_patch4_window7_224] INFO: Epoch: [150] [1020/1251] eta: 0:02:26 lr: 0.000501 loss: 3.1941 (3.2643) grad_norm: 1.4956 (1.5144) time: 0.6312 [2021-03-27 08:41:47 swin_base_patch4_window7_224] INFO: Epoch: [150] [1030/1251] eta: 0:02:20 lr: 0.000501 loss: 3.4457 (3.2658) grad_norm: 1.3604 (1.5130) time: 0.6335 [2021-03-27 08:41:54 swin_base_patch4_window7_224] INFO: Epoch: [150] [1040/1251] eta: 0:02:14 lr: 0.000501 loss: 3.4457 (3.2652) grad_norm: 1.3482 (1.5127) time: 0.6331 [2021-03-27 08:42:00 swin_base_patch4_window7_224] INFO: Epoch: [150] [1050/1251] eta: 0:02:07 lr: 0.000501 loss: 3.1755 (3.2648) grad_norm: 1.4502 (1.5127) time: 0.6315 [2021-03-27 08:42:06 swin_base_patch4_window7_224] INFO: Epoch: [150] [1060/1251] eta: 0:02:01 lr: 0.000501 loss: 3.5641 (3.2689) grad_norm: 1.4516 (1.5126) time: 0.6311 [2021-03-27 08:42:13 swin_base_patch4_window7_224] INFO: Epoch: [150] [1070/1251] eta: 0:01:55 lr: 0.000501 loss: 3.5194 (3.2692) grad_norm: 1.5043 (1.5130) time: 0.6258 [2021-03-27 08:42:19 swin_base_patch4_window7_224] INFO: Epoch: [150] [1080/1251] eta: 0:01:48 lr: 0.000501 loss: 3.3057 (3.2700) grad_norm: 1.5044 (1.5131) time: 0.6281 [2021-03-27 08:42:25 swin_base_patch4_window7_224] INFO: Epoch: [150] [1090/1251] eta: 0:01:42 lr: 0.000500 loss: 3.4024 (3.2704) grad_norm: 1.5037 (1.5128) time: 0.6303 [2021-03-27 08:42:32 swin_base_patch4_window7_224] INFO: Epoch: [150] [1100/1251] eta: 0:01:35 lr: 0.000500 loss: 3.5356 (3.2728) grad_norm: 1.5398 (1.5134) time: 0.6327 [2021-03-27 08:42:38 swin_base_patch4_window7_224] INFO: Epoch: [150] [1110/1251] eta: 0:01:29 lr: 0.000500 loss: 3.3149 (3.2680) grad_norm: 1.4715 (1.5128) time: 0.6378 [2021-03-27 08:42:44 swin_base_patch4_window7_224] INFO: Epoch: [150] [1120/1251] eta: 0:01:23 lr: 0.000500 loss: 2.9430 (3.2665) grad_norm: 1.4491 (1.5127) time: 0.6378 [2021-03-27 08:42:51 swin_base_patch4_window7_224] INFO: Epoch: [150] [1130/1251] eta: 0:01:16 lr: 0.000500 loss: 3.2391 (3.2646) grad_norm: 1.4440 (1.5123) time: 0.6319 [2021-03-27 08:42:57 swin_base_patch4_window7_224] INFO: Epoch: [150] [1140/1251] eta: 0:01:10 lr: 0.000500 loss: 3.2391 (3.2634) grad_norm: 1.4676 (1.5122) time: 0.6237 [2021-03-27 08:43:03 swin_base_patch4_window7_224] INFO: Epoch: [150] [1150/1251] eta: 0:01:04 lr: 0.000500 loss: 3.2296 (3.2629) grad_norm: 1.5481 (1.5131) time: 0.6267 [2021-03-27 08:43:09 swin_base_patch4_window7_224] INFO: Epoch: [150] [1160/1251] eta: 0:00:57 lr: 0.000500 loss: 3.0251 (3.2619) grad_norm: 1.5864 (1.5141) time: 0.6280 [2021-03-27 08:43:16 swin_base_patch4_window7_224] INFO: Epoch: [150] [1170/1251] eta: 0:00:51 lr: 0.000500 loss: 3.2659 (3.2635) grad_norm: 1.5814 (1.5152) time: 0.6285 [2021-03-27 08:43:22 swin_base_patch4_window7_224] INFO: Epoch: [150] [1180/1251] eta: 0:00:45 lr: 0.000500 loss: 3.6490 (3.2659) grad_norm: 1.5037 (1.5152) time: 0.6340 [2021-03-27 08:43:28 swin_base_patch4_window7_224] INFO: Epoch: [150] [1190/1251] eta: 0:00:38 lr: 0.000500 loss: 3.4496 (3.2669) grad_norm: 1.4876 (1.5156) time: 0.6321 [2021-03-27 08:43:35 swin_base_patch4_window7_224] INFO: Epoch: [150] [1200/1251] eta: 0:00:32 lr: 0.000500 loss: 3.2891 (3.2674) grad_norm: 1.5222 (1.5157) time: 0.6244 [2021-03-27 08:43:41 swin_base_patch4_window7_224] INFO: Epoch: [150] [1210/1251] eta: 0:00:26 lr: 0.000500 loss: 3.2382 (3.2666) grad_norm: 1.5504 (1.5169) time: 0.6265 [2021-03-27 08:43:47 swin_base_patch4_window7_224] INFO: Epoch: [150] [1220/1251] eta: 0:00:19 lr: 0.000500 loss: 3.3849 (3.2687) grad_norm: 1.5892 (1.5171) time: 0.6258 [2021-03-27 08:43:53 swin_base_patch4_window7_224] INFO: Epoch: [150] [1230/1251] eta: 0:00:13 lr: 0.000500 loss: 3.3849 (3.2678) grad_norm: 1.5646 (1.5178) time: 0.6233 [2021-03-27 08:44:00 swin_base_patch4_window7_224] INFO: Epoch: [150] [1240/1251] eta: 0:00:06 lr: 0.000500 loss: 3.4171 (3.2693) grad_norm: 1.5504 (1.5178) time: 0.6254 [2021-03-27 08:44:06 swin_base_patch4_window7_224] INFO: Epoch: [150] [1250/1251] eta: 0:00:00 lr: 0.000500 loss: 3.3121 (3.2669) grad_norm: 1.5466 (1.5182) time: 0.6190 [2021-03-27 08:45:22 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 0.8623 (0.8623) acc1: 78.1250 (78.1250) acc5: 95.3125 (95.3125) [2021-03-27 08:45:24 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.9243 (0.9181) acc1: 76.5625 (77.1307) acc5: 95.3125 (95.7386) [2021-03-27 08:45:25 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9252 (0.9157) acc1: 76.5625 (77.3810) acc5: 95.3125 (95.0893) [2021-03-27 08:45:27 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.9294 (0.9332) acc1: 75.0000 (77.0161) acc5: 95.3125 (95.0101) [2021-03-27 08:45:28 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9078 (0.9113) acc1: 76.5625 (77.6677) acc5: 95.3125 (95.0457) [2021-03-27 08:45:29 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8200 (0.8874) acc1: 81.2500 (78.2400) acc5: 95.3125 (95.1040) [2021-03-27 08:45:38 swin_base_patch4_window7_224] INFO: * Acc@1 79.054 Acc@5 94.820 loss 0.886 [2021-03-27 08:45:38 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.1% [2021-03-27 08:45:38 swin_base_patch4_window7_224] INFO: Max accuracy: 79.05% [2021-03-27 08:45:42 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 0/1251] eta: 1:27:34 lr: 0.000500 loss: 3.2707 (3.2707) grad_norm: 1.7159 (1.7159) time: 4.2001 [2021-03-27 08:45:49 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 10/1251] eta: 0:19:57 lr: 0.000500 loss: 3.3081 (3.2813) grad_norm: 1.4811 (1.5550) time: 0.9650 [2021-03-27 08:45:55 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 20/1251] eta: 0:16:28 lr: 0.000500 loss: 3.3122 (3.3079) grad_norm: 1.4775 (1.5567) time: 0.6335 [2021-03-27 08:46:01 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 30/1251] eta: 0:15:15 lr: 0.000500 loss: 3.3218 (3.2881) grad_norm: 1.4740 (1.5181) time: 0.6310 [2021-03-27 08:46:08 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 40/1251] eta: 0:14:35 lr: 0.000500 loss: 3.3218 (3.2657) grad_norm: 1.4769 (1.5286) time: 0.6378 [2021-03-27 08:46:14 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 50/1251] eta: 0:14:04 lr: 0.000500 loss: 3.3073 (3.2470) grad_norm: 1.5500 (1.5450) time: 0.6312 [2021-03-27 08:46:20 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 60/1251] eta: 0:13:45 lr: 0.000500 loss: 3.2192 (3.2591) grad_norm: 1.5586 (1.5505) time: 0.6324 [2021-03-27 08:46:27 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 70/1251] eta: 0:13:27 lr: 0.000500 loss: 3.3041 (3.2522) grad_norm: 1.5168 (1.5435) time: 0.6329 [2021-03-27 08:46:33 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 80/1251] eta: 0:13:12 lr: 0.000499 loss: 3.2859 (3.2667) grad_norm: 1.4815 (1.5419) time: 0.6261 [2021-03-27 08:46:39 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 90/1251] eta: 0:12:59 lr: 0.000499 loss: 3.4212 (3.2913) grad_norm: 1.4867 (1.5466) time: 0.6306 [2021-03-27 08:46:46 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 100/1251] eta: 0:12:49 lr: 0.000499 loss: 3.3474 (3.2846) grad_norm: 1.4867 (1.5502) time: 0.6375 [2021-03-27 08:46:52 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 110/1251] eta: 0:12:39 lr: 0.000499 loss: 3.3178 (3.2849) grad_norm: 1.4431 (1.5420) time: 0.6395 [2021-03-27 08:46:58 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 120/1251] eta: 0:12:30 lr: 0.000499 loss: 3.5211 (3.3051) grad_norm: 1.4347 (1.5367) time: 0.6385 [2021-03-27 08:47:05 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 130/1251] eta: 0:12:21 lr: 0.000499 loss: 3.6430 (3.3257) grad_norm: 1.4801 (1.5326) time: 0.6352 [2021-03-27 08:47:11 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 140/1251] eta: 0:12:12 lr: 0.000499 loss: 3.6357 (3.3390) grad_norm: 1.4335 (1.5278) time: 0.6306 [2021-03-27 08:47:17 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 150/1251] eta: 0:12:03 lr: 0.000499 loss: 3.3553 (3.3287) grad_norm: 1.4016 (1.5303) time: 0.6295 [2021-03-27 08:47:24 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 160/1251] eta: 0:11:55 lr: 0.000499 loss: 3.2557 (3.3334) grad_norm: 1.4529 (1.5288) time: 0.6340 [2021-03-27 08:47:30 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 170/1251] eta: 0:11:47 lr: 0.000499 loss: 3.2698 (3.3288) grad_norm: 1.4529 (1.5277) time: 0.6331 [2021-03-27 08:47:36 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 180/1251] eta: 0:11:39 lr: 0.000499 loss: 3.1197 (3.3182) grad_norm: 1.4337 (1.5264) time: 0.6273 [2021-03-27 08:47:42 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 190/1251] eta: 0:11:31 lr: 0.000499 loss: 3.1197 (3.3105) grad_norm: 1.4815 (1.5285) time: 0.6262 [2021-03-27 08:47:49 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 200/1251] eta: 0:11:23 lr: 0.000499 loss: 3.3596 (3.3054) grad_norm: 1.4921 (1.5268) time: 0.6269 [2021-03-27 08:47:55 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 210/1251] eta: 0:11:15 lr: 0.000499 loss: 3.2488 (3.3044) grad_norm: 1.5244 (1.5285) time: 0.6293 [2021-03-27 08:48:01 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 220/1251] eta: 0:11:08 lr: 0.000499 loss: 3.2770 (3.3036) grad_norm: 1.5244 (1.5270) time: 0.6276 [2021-03-27 08:48:08 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 230/1251] eta: 0:11:01 lr: 0.000499 loss: 3.3072 (3.3086) grad_norm: 1.4609 (1.5281) time: 0.6321 [2021-03-27 08:48:14 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 240/1251] eta: 0:10:53 lr: 0.000499 loss: 3.3236 (3.3142) grad_norm: 1.4609 (1.5324) time: 0.6315 [2021-03-27 08:48:20 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 250/1251] eta: 0:10:46 lr: 0.000499 loss: 3.4925 (3.3228) grad_norm: 1.4144 (1.5243) time: 0.6214 [2021-03-27 08:48:26 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 260/1251] eta: 0:10:39 lr: 0.000499 loss: 3.6212 (3.3308) grad_norm: 1.3136 (1.5203) time: 0.6214 [2021-03-27 08:48:33 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 270/1251] eta: 0:10:32 lr: 0.000499 loss: 3.3589 (3.3279) grad_norm: 1.3736 (1.5152) time: 0.6266 [2021-03-27 08:48:39 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 280/1251] eta: 0:10:25 lr: 0.000499 loss: 3.1122 (3.3167) grad_norm: 1.3736 (1.5121) time: 0.6302 [2021-03-27 08:48:45 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 290/1251] eta: 0:10:18 lr: 0.000499 loss: 3.3058 (3.3146) grad_norm: 1.4437 (1.5101) time: 0.6297 [2021-03-27 08:48:52 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 300/1251] eta: 0:10:11 lr: 0.000499 loss: 3.3406 (3.3112) grad_norm: 1.5208 (1.5134) time: 0.6263 [2021-03-27 08:48:58 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 310/1251] eta: 0:10:04 lr: 0.000499 loss: 3.3576 (3.3067) grad_norm: 1.5769 (1.5163) time: 0.6288 [2021-03-27 08:49:04 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 320/1251] eta: 0:09:57 lr: 0.000498 loss: 3.3631 (3.3100) grad_norm: 1.5443 (1.5159) time: 0.6294 [2021-03-27 08:49:10 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 330/1251] eta: 0:09:50 lr: 0.000498 loss: 3.3379 (3.3092) grad_norm: 1.5168 (1.5168) time: 0.6316 [2021-03-27 08:49:17 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 340/1251] eta: 0:09:44 lr: 0.000498 loss: 3.3111 (3.3127) grad_norm: 1.5618 (1.5183) time: 0.6354 [2021-03-27 08:49:23 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 350/1251] eta: 0:09:37 lr: 0.000498 loss: 3.3111 (3.3093) grad_norm: 1.5786 (1.5203) time: 0.6295 [2021-03-27 08:49:29 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 360/1251] eta: 0:09:30 lr: 0.000498 loss: 3.3441 (3.3119) grad_norm: 1.5915 (1.5234) time: 0.6268 [2021-03-27 08:49:36 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 370/1251] eta: 0:09:24 lr: 0.000498 loss: 3.4108 (3.3125) grad_norm: 1.5617 (1.5241) time: 0.6286 [2021-03-27 08:49:42 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 380/1251] eta: 0:09:17 lr: 0.000498 loss: 3.4108 (3.3133) grad_norm: 1.4831 (1.5228) time: 0.6299 [2021-03-27 08:49:48 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 390/1251] eta: 0:09:11 lr: 0.000498 loss: 3.4276 (3.3134) grad_norm: 1.3883 (1.5202) time: 0.6340 [2021-03-27 08:49:55 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 400/1251] eta: 0:09:04 lr: 0.000498 loss: 3.3447 (3.3136) grad_norm: 1.3685 (1.5182) time: 0.6292 [2021-03-27 08:50:01 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 410/1251] eta: 0:08:57 lr: 0.000498 loss: 3.3447 (3.3151) grad_norm: 1.4461 (1.5182) time: 0.6270 [2021-03-27 08:50:07 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 420/1251] eta: 0:08:51 lr: 0.000498 loss: 3.3130 (3.3108) grad_norm: 1.4372 (1.5165) time: 0.6329 [2021-03-27 08:50:13 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 430/1251] eta: 0:08:44 lr: 0.000498 loss: 3.2852 (3.3114) grad_norm: 1.4894 (1.5187) time: 0.6273 [2021-03-27 08:50:20 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 440/1251] eta: 0:08:37 lr: 0.000498 loss: 3.5152 (3.3131) grad_norm: 1.5545 (1.5186) time: 0.6235 [2021-03-27 08:50:26 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 450/1251] eta: 0:08:31 lr: 0.000498 loss: 3.5152 (3.3109) grad_norm: 1.4577 (1.5173) time: 0.6248 [2021-03-27 08:50:32 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 460/1251] eta: 0:08:24 lr: 0.000498 loss: 3.2616 (3.3062) grad_norm: 1.4359 (1.5174) time: 0.6275 [2021-03-27 08:50:39 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 470/1251] eta: 0:08:18 lr: 0.000498 loss: 3.3362 (3.3086) grad_norm: 1.5722 (1.5203) time: 0.6302 [2021-03-27 08:50:45 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 480/1251] eta: 0:08:11 lr: 0.000498 loss: 3.2988 (3.3065) grad_norm: 1.5265 (1.5184) time: 0.6280 [2021-03-27 08:50:51 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 490/1251] eta: 0:08:05 lr: 0.000498 loss: 3.1081 (3.3017) grad_norm: 1.4600 (1.5196) time: 0.6280 [2021-03-27 08:50:57 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 500/1251] eta: 0:07:58 lr: 0.000498 loss: 3.5879 (3.3102) grad_norm: 1.5674 (1.5197) time: 0.6273 [2021-03-27 08:51:04 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 510/1251] eta: 0:07:52 lr: 0.000498 loss: 3.5428 (3.3111) grad_norm: 1.5349 (1.5216) time: 0.6261 [2021-03-27 08:51:10 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 520/1251] eta: 0:07:45 lr: 0.000498 loss: 3.3977 (3.3124) grad_norm: 1.5262 (1.5212) time: 0.6278 [2021-03-27 08:51:16 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 530/1251] eta: 0:07:39 lr: 0.000498 loss: 3.4226 (3.3152) grad_norm: 1.5322 (1.5244) time: 0.6351 [2021-03-27 08:51:23 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 540/1251] eta: 0:07:32 lr: 0.000498 loss: 3.5571 (3.3192) grad_norm: 1.5357 (1.5247) time: 0.6347 [2021-03-27 08:51:29 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 550/1251] eta: 0:07:26 lr: 0.000498 loss: 3.6592 (3.3227) grad_norm: 1.4773 (1.5255) time: 0.6407 [2021-03-27 08:51:35 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 560/1251] eta: 0:07:20 lr: 0.000497 loss: 3.4584 (3.3205) grad_norm: 1.4773 (1.5273) time: 0.6428 [2021-03-27 08:51:42 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 570/1251] eta: 0:07:13 lr: 0.000497 loss: 3.3505 (3.3208) grad_norm: 1.5262 (1.5282) time: 0.6317 [2021-03-27 08:51:48 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 580/1251] eta: 0:07:07 lr: 0.000497 loss: 3.4203 (3.3210) grad_norm: 1.4915 (1.5294) time: 0.6297 [2021-03-27 08:51:54 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 590/1251] eta: 0:07:00 lr: 0.000497 loss: 3.4203 (3.3201) grad_norm: 1.5851 (1.5317) time: 0.6318 [2021-03-27 08:52:01 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 600/1251] eta: 0:06:54 lr: 0.000497 loss: 3.2611 (3.3177) grad_norm: 1.6400 (1.5356) time: 0.6363 [2021-03-27 08:52:07 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 610/1251] eta: 0:06:47 lr: 0.000497 loss: 3.2235 (3.3191) grad_norm: 1.5804 (1.5357) time: 0.6307 [2021-03-27 08:52:13 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 620/1251] eta: 0:06:41 lr: 0.000497 loss: 3.2947 (3.3170) grad_norm: 1.5213 (1.5342) time: 0.6272 [2021-03-27 08:52:20 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 630/1251] eta: 0:06:35 lr: 0.000497 loss: 3.3178 (3.3148) grad_norm: 1.4726 (1.5348) time: 0.6322 [2021-03-27 08:52:26 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 640/1251] eta: 0:06:28 lr: 0.000497 loss: 3.3178 (3.3142) grad_norm: 1.5609 (1.5364) time: 0.6368 [2021-03-27 08:52:32 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 650/1251] eta: 0:06:22 lr: 0.000497 loss: 3.4001 (3.3146) grad_norm: 1.4761 (1.5347) time: 0.6312 [2021-03-27 08:52:39 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 660/1251] eta: 0:06:15 lr: 0.000497 loss: 3.3319 (3.3138) grad_norm: 1.5006 (1.5359) time: 0.6252 [2021-03-27 08:52:45 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 670/1251] eta: 0:06:09 lr: 0.000497 loss: 3.3319 (3.3143) grad_norm: 1.5051 (1.5345) time: 0.6304 [2021-03-27 08:52:51 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 680/1251] eta: 0:06:03 lr: 0.000497 loss: 3.3508 (3.3147) grad_norm: 1.4061 (1.5340) time: 0.6305 [2021-03-27 08:52:57 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 690/1251] eta: 0:05:56 lr: 0.000497 loss: 3.3508 (3.3124) grad_norm: 1.4830 (1.5340) time: 0.6275 [2021-03-27 08:53:04 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 700/1251] eta: 0:05:50 lr: 0.000497 loss: 3.3861 (3.3089) grad_norm: 1.4830 (1.5327) time: 0.6257 [2021-03-27 08:53:10 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 710/1251] eta: 0:05:43 lr: 0.000497 loss: 3.2756 (3.3079) grad_norm: 1.4323 (1.5308) time: 0.6284 [2021-03-27 08:53:16 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 720/1251] eta: 0:05:37 lr: 0.000497 loss: 3.2843 (3.3072) grad_norm: 1.4709 (1.5316) time: 0.6335 [2021-03-27 08:53:23 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 730/1251] eta: 0:05:31 lr: 0.000497 loss: 3.4369 (3.3097) grad_norm: 1.4878 (1.5306) time: 0.6378 [2021-03-27 08:53:29 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 740/1251] eta: 0:05:24 lr: 0.000497 loss: 3.4672 (3.3120) grad_norm: 1.4099 (1.5298) time: 0.6437 [2021-03-27 08:53:36 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 750/1251] eta: 0:05:18 lr: 0.000497 loss: 3.4477 (3.3111) grad_norm: 1.4927 (1.5299) time: 0.6441 [2021-03-27 08:53:42 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 760/1251] eta: 0:05:12 lr: 0.000497 loss: 3.2634 (3.3117) grad_norm: 1.5087 (1.5294) time: 0.6385 [2021-03-27 08:53:48 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 770/1251] eta: 0:05:05 lr: 0.000497 loss: 3.4226 (3.3126) grad_norm: 1.4827 (1.5285) time: 0.6367 [2021-03-27 08:53:55 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 780/1251] eta: 0:04:59 lr: 0.000497 loss: 3.4327 (3.3122) grad_norm: 1.4767 (1.5279) time: 0.6336 [2021-03-27 08:54:01 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 790/1251] eta: 0:04:53 lr: 0.000497 loss: 3.2565 (3.3105) grad_norm: 1.4021 (1.5278) time: 0.6360 [2021-03-27 08:54:08 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 800/1251] eta: 0:04:46 lr: 0.000497 loss: 3.4022 (3.3130) grad_norm: 1.5086 (1.5278) time: 0.6390 [2021-03-27 08:54:14 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 810/1251] eta: 0:04:40 lr: 0.000496 loss: 3.5086 (3.3146) grad_norm: 1.5423 (1.5290) time: 0.6266 [2021-03-27 08:54:20 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 820/1251] eta: 0:04:33 lr: 0.000496 loss: 3.4619 (3.3151) grad_norm: 1.4715 (1.5275) time: 0.6260 [2021-03-27 08:54:26 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 830/1251] eta: 0:04:27 lr: 0.000496 loss: 3.4724 (3.3163) grad_norm: 1.4776 (1.5281) time: 0.6277 [2021-03-27 08:54:33 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 840/1251] eta: 0:04:21 lr: 0.000496 loss: 3.4327 (3.3172) grad_norm: 1.5245 (1.5286) time: 0.6245 [2021-03-27 08:54:39 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 850/1251] eta: 0:04:14 lr: 0.000496 loss: 3.2369 (3.3130) grad_norm: 1.4645 (1.5273) time: 0.6293 [2021-03-27 08:54:45 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 860/1251] eta: 0:04:08 lr: 0.000496 loss: 3.3655 (3.3167) grad_norm: 1.4471 (1.5274) time: 0.6309 [2021-03-27 08:54:51 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 870/1251] eta: 0:04:02 lr: 0.000496 loss: 3.5349 (3.3156) grad_norm: 1.4820 (1.5277) time: 0.6324 [2021-03-27 08:54:58 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 880/1251] eta: 0:03:55 lr: 0.000496 loss: 3.5518 (3.3194) grad_norm: 1.4410 (1.5282) time: 0.6390 [2021-03-27 08:55:04 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 890/1251] eta: 0:03:49 lr: 0.000496 loss: 3.5518 (3.3184) grad_norm: 1.4410 (1.5277) time: 0.6395 [2021-03-27 08:55:11 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 900/1251] eta: 0:03:42 lr: 0.000496 loss: 3.1861 (3.3160) grad_norm: 1.4906 (1.5280) time: 0.6331 [2021-03-27 08:55:17 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 910/1251] eta: 0:03:36 lr: 0.000496 loss: 3.2363 (3.3147) grad_norm: 1.5478 (inf) time: 0.6275 [2021-03-27 08:55:23 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 920/1251] eta: 0:03:30 lr: 0.000496 loss: 3.4227 (3.3155) grad_norm: 1.5047 (inf) time: 0.6299 [2021-03-27 08:55:29 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 930/1251] eta: 0:03:23 lr: 0.000496 loss: 3.4778 (3.3139) grad_norm: 1.4959 (inf) time: 0.6300 [2021-03-27 08:55:36 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 940/1251] eta: 0:03:17 lr: 0.000496 loss: 3.4328 (3.3133) grad_norm: 1.4800 (inf) time: 0.6264 [2021-03-27 08:55:42 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 950/1251] eta: 0:03:11 lr: 0.000496 loss: 3.3947 (3.3142) grad_norm: 1.4800 (inf) time: 0.6268 [2021-03-27 08:55:48 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 960/1251] eta: 0:03:04 lr: 0.000496 loss: 3.2907 (3.3137) grad_norm: 1.4917 (inf) time: 0.6310 [2021-03-27 08:55:55 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 970/1251] eta: 0:02:58 lr: 0.000496 loss: 3.2097 (3.3124) grad_norm: 1.4206 (inf) time: 0.6350 [2021-03-27 08:56:01 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 980/1251] eta: 0:02:52 lr: 0.000496 loss: 3.1672 (3.3109) grad_norm: 1.3961 (inf) time: 0.6341 [2021-03-27 08:56:07 swin_base_patch4_window7_224] INFO: Epoch: [151] [ 990/1251] eta: 0:02:45 lr: 0.000496 loss: 3.2071 (3.3108) grad_norm: 1.4298 (inf) time: 0.6332 [2021-03-27 08:56:14 swin_base_patch4_window7_224] INFO: Epoch: [151] [1000/1251] eta: 0:02:39 lr: 0.000496 loss: 3.5429 (3.3124) grad_norm: 1.4724 (inf) time: 0.6318 [2021-03-27 08:56:20 swin_base_patch4_window7_224] INFO: Epoch: [151] [1010/1251] eta: 0:02:32 lr: 0.000496 loss: 3.6269 (3.3150) grad_norm: 1.4416 (inf) time: 0.6261 [2021-03-27 08:56:26 swin_base_patch4_window7_224] INFO: Epoch: [151] [1020/1251] eta: 0:02:26 lr: 0.000496 loss: 3.5160 (3.3156) grad_norm: 1.4416 (inf) time: 0.6261 [2021-03-27 08:56:32 swin_base_patch4_window7_224] INFO: Epoch: [151] [1030/1251] eta: 0:02:20 lr: 0.000496 loss: 3.3626 (3.3154) grad_norm: 1.5237 (inf) time: 0.6302 [2021-03-27 08:56:39 swin_base_patch4_window7_224] INFO: Epoch: [151] [1040/1251] eta: 0:02:13 lr: 0.000496 loss: 3.3626 (3.3170) grad_norm: 1.5480 (inf) time: 0.6265 [2021-03-27 08:56:45 swin_base_patch4_window7_224] INFO: Epoch: [151] [1050/1251] eta: 0:02:07 lr: 0.000495 loss: 3.3132 (3.3159) grad_norm: 1.5480 (inf) time: 0.6265 [2021-03-27 08:56:51 swin_base_patch4_window7_224] INFO: Epoch: [151] [1060/1251] eta: 0:02:01 lr: 0.000495 loss: 3.0814 (3.3131) grad_norm: 1.5015 (inf) time: 0.6339 [2021-03-27 08:56:58 swin_base_patch4_window7_224] INFO: Epoch: [151] [1070/1251] eta: 0:01:54 lr: 0.000495 loss: 3.3499 (3.3143) grad_norm: 1.5227 (inf) time: 0.6343 [2021-03-27 08:57:04 swin_base_patch4_window7_224] INFO: Epoch: [151] [1080/1251] eta: 0:01:48 lr: 0.000495 loss: 3.5320 (3.3146) grad_norm: 1.5227 (inf) time: 0.6279 [2021-03-27 08:57:10 swin_base_patch4_window7_224] INFO: Epoch: [151] [1090/1251] eta: 0:01:42 lr: 0.000495 loss: 3.2604 (3.3142) grad_norm: 1.4402 (inf) time: 0.6269 [2021-03-27 08:57:17 swin_base_patch4_window7_224] INFO: Epoch: [151] [1100/1251] eta: 0:01:35 lr: 0.000495 loss: 3.3847 (3.3155) grad_norm: 1.4220 (inf) time: 0.6309 [2021-03-27 08:57:23 swin_base_patch4_window7_224] INFO: Epoch: [151] [1110/1251] eta: 0:01:29 lr: 0.000495 loss: 3.5512 (3.3167) grad_norm: 1.4382 (inf) time: 0.6335 [2021-03-27 08:57:29 swin_base_patch4_window7_224] INFO: Epoch: [151] [1120/1251] eta: 0:01:23 lr: 0.000495 loss: 3.4526 (3.3182) grad_norm: 1.4365 (inf) time: 0.6248 [2021-03-27 08:57:35 swin_base_patch4_window7_224] INFO: Epoch: [151] [1130/1251] eta: 0:01:16 lr: 0.000495 loss: 3.3589 (3.3148) grad_norm: 1.4445 (inf) time: 0.6211 [2021-03-27 08:57:42 swin_base_patch4_window7_224] INFO: Epoch: [151] [1140/1251] eta: 0:01:10 lr: 0.000495 loss: 3.1181 (3.3140) grad_norm: 1.4491 (inf) time: 0.6268 [2021-03-27 08:57:48 swin_base_patch4_window7_224] INFO: Epoch: [151] [1150/1251] eta: 0:01:04 lr: 0.000495 loss: 3.3551 (3.3134) grad_norm: 1.4109 (inf) time: 0.6279 [2021-03-27 08:57:54 swin_base_patch4_window7_224] INFO: Epoch: [151] [1160/1251] eta: 0:00:57 lr: 0.000495 loss: 3.3684 (3.3137) grad_norm: 1.4239 (inf) time: 0.6285 [2021-03-27 08:58:01 swin_base_patch4_window7_224] INFO: Epoch: [151] [1170/1251] eta: 0:00:51 lr: 0.000495 loss: 3.3751 (3.3142) grad_norm: 1.4877 (inf) time: 0.6295 [2021-03-27 08:58:07 swin_base_patch4_window7_224] INFO: Epoch: [151] [1180/1251] eta: 0:00:45 lr: 0.000495 loss: 3.5661 (3.3171) grad_norm: 1.5440 (inf) time: 0.6283 [2021-03-27 08:58:13 swin_base_patch4_window7_224] INFO: Epoch: [151] [1190/1251] eta: 0:00:38 lr: 0.000495 loss: 3.5519 (3.3174) grad_norm: 1.4832 (inf) time: 0.6300 [2021-03-27 08:58:19 swin_base_patch4_window7_224] INFO: Epoch: [151] [1200/1251] eta: 0:00:32 lr: 0.000495 loss: 3.3653 (3.3174) grad_norm: 1.4750 (inf) time: 0.6317 [2021-03-27 08:58:26 swin_base_patch4_window7_224] INFO: Epoch: [151] [1210/1251] eta: 0:00:25 lr: 0.000495 loss: 3.2099 (3.3162) grad_norm: 1.5106 (inf) time: 0.6347 [2021-03-27 08:58:32 swin_base_patch4_window7_224] INFO: Epoch: [151] [1220/1251] eta: 0:00:19 lr: 0.000495 loss: 3.2098 (3.3159) grad_norm: 1.5106 (inf) time: 0.6409 [2021-03-27 08:58:39 swin_base_patch4_window7_224] INFO: Epoch: [151] [1230/1251] eta: 0:00:13 lr: 0.000495 loss: 3.4525 (3.3160) grad_norm: 1.5086 (inf) time: 0.6365 [2021-03-27 08:58:45 swin_base_patch4_window7_224] INFO: Epoch: [151] [1240/1251] eta: 0:00:06 lr: 0.000495 loss: 3.4334 (3.3174) grad_norm: 1.5734 (inf) time: 0.6232 [2021-03-27 08:58:51 swin_base_patch4_window7_224] INFO: Epoch: [151] [1250/1251] eta: 0:00:00 lr: 0.000495 loss: 3.4524 (3.3188) grad_norm: 1.5257 (inf) time: 0.6186 [2021-03-27 08:58:59 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:55 loss: 0.7998 (0.7998) acc1: 79.6875 (79.6875) acc5: 96.8750 (96.8750) [2021-03-27 08:59:02 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.9492 (0.9994) acc1: 75.0000 (75.2841) acc5: 95.3125 (95.0284) [2021-03-27 08:59:05 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9198 (0.9192) acc1: 76.5625 (78.7946) acc5: 96.8750 (95.6845) [2021-03-27 08:59:07 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7936 (0.9158) acc1: 81.2500 (78.8306) acc5: 96.8750 (95.7157) [2021-03-27 08:59:09 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8773 (0.9223) acc1: 78.1250 (78.7348) acc5: 96.8750 (95.5793) [2021-03-27 08:59:10 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9270 (0.9270) acc1: 79.6875 (78.6880) acc5: 93.7500 (95.4240) [2021-03-27 08:59:19 swin_base_patch4_window7_224] INFO: * Acc@1 79.118 Acc@5 94.874 loss 0.918 [2021-03-27 08:59:19 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.1% [2021-03-27 08:59:19 swin_base_patch4_window7_224] INFO: Max accuracy: 79.12% [2021-03-27 08:59:23 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 0/1251] eta: 1:30:02 lr: 0.000495 loss: 3.7740 (3.7740) grad_norm: 1.2741 (1.2741) time: 4.3188 [2021-03-27 08:59:29 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 10/1251] eta: 0:20:02 lr: 0.000495 loss: 3.5109 (3.4343) grad_norm: 1.4980 (1.4763) time: 0.9689 [2021-03-27 08:59:36 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 20/1251] eta: 0:16:37 lr: 0.000495 loss: 3.4546 (3.3077) grad_norm: 1.4980 (1.5096) time: 0.6347 [2021-03-27 08:59:42 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 30/1251] eta: 0:15:23 lr: 0.000495 loss: 3.1785 (3.2646) grad_norm: 1.4442 (1.4697) time: 0.6398 [2021-03-27 08:59:48 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 40/1251] eta: 0:14:41 lr: 0.000494 loss: 3.1785 (3.2665) grad_norm: 1.4064 (1.4688) time: 0.6407 [2021-03-27 08:59:55 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 50/1251] eta: 0:14:10 lr: 0.000494 loss: 3.4578 (3.3180) grad_norm: 1.4503 (1.4678) time: 0.6325 [2021-03-27 09:00:01 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 60/1251] eta: 0:13:47 lr: 0.000494 loss: 3.3940 (3.2950) grad_norm: 1.3966 (1.4599) time: 0.6289 [2021-03-27 09:00:07 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 70/1251] eta: 0:13:30 lr: 0.000494 loss: 3.2721 (3.2974) grad_norm: 1.4679 (1.4718) time: 0.6309 [2021-03-27 09:00:14 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 80/1251] eta: 0:13:17 lr: 0.000494 loss: 3.3489 (3.3083) grad_norm: 1.4710 (1.4758) time: 0.6383 [2021-03-27 09:00:20 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 90/1251] eta: 0:13:02 lr: 0.000494 loss: 3.3704 (3.2907) grad_norm: 1.4207 (1.4732) time: 0.6323 [2021-03-27 09:00:26 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 100/1251] eta: 0:12:51 lr: 0.000494 loss: 3.3704 (3.2928) grad_norm: 1.4386 (1.4739) time: 0.6256 [2021-03-27 09:00:33 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 110/1251] eta: 0:12:40 lr: 0.000494 loss: 3.3105 (3.2866) grad_norm: 1.4386 (1.4724) time: 0.6291 [2021-03-27 09:00:39 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 120/1251] eta: 0:12:29 lr: 0.000494 loss: 3.2683 (3.2785) grad_norm: 1.4488 (1.4770) time: 0.6267 [2021-03-27 09:00:45 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 130/1251] eta: 0:12:20 lr: 0.000494 loss: 3.4122 (3.2959) grad_norm: 1.4811 (1.4828) time: 0.6276 [2021-03-27 09:00:51 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 140/1251] eta: 0:12:11 lr: 0.000494 loss: 3.5316 (3.3016) grad_norm: 1.4431 (1.4825) time: 0.6335 [2021-03-27 09:00:58 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 150/1251] eta: 0:12:02 lr: 0.000494 loss: 3.3806 (3.3008) grad_norm: 1.4768 (1.4925) time: 0.6309 [2021-03-27 09:01:04 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 160/1251] eta: 0:11:54 lr: 0.000494 loss: 3.2509 (3.2912) grad_norm: 1.5352 (1.4953) time: 0.6261 [2021-03-27 09:01:10 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 170/1251] eta: 0:11:47 lr: 0.000494 loss: 3.2509 (3.2900) grad_norm: 1.5190 (1.5008) time: 0.6366 [2021-03-27 09:01:17 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 180/1251] eta: 0:11:39 lr: 0.000494 loss: 3.2911 (3.2942) grad_norm: 1.5115 (1.5054) time: 0.6405 [2021-03-27 09:01:23 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 190/1251] eta: 0:11:31 lr: 0.000494 loss: 3.4002 (3.3073) grad_norm: 1.5079 (1.5080) time: 0.6331 [2021-03-27 09:01:29 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 200/1251] eta: 0:11:23 lr: 0.000494 loss: 3.4726 (3.2991) grad_norm: 1.4873 (1.5066) time: 0.6268 [2021-03-27 09:01:36 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 210/1251] eta: 0:11:16 lr: 0.000494 loss: 3.2281 (3.2913) grad_norm: 1.3871 (1.5017) time: 0.6309 [2021-03-27 09:01:42 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 220/1251] eta: 0:11:08 lr: 0.000494 loss: 3.2281 (3.2857) grad_norm: 1.4200 (1.5049) time: 0.6297 [2021-03-27 09:01:48 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 230/1251] eta: 0:11:01 lr: 0.000494 loss: 3.1166 (3.2752) grad_norm: 1.4541 (1.5043) time: 0.6223 [2021-03-27 09:01:55 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 240/1251] eta: 0:10:53 lr: 0.000494 loss: 3.3750 (3.2809) grad_norm: 1.4745 (1.5074) time: 0.6273 [2021-03-27 09:02:01 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 250/1251] eta: 0:10:47 lr: 0.000494 loss: 3.4320 (3.2814) grad_norm: 1.4805 (1.5098) time: 0.6361 [2021-03-27 09:02:07 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 260/1251] eta: 0:10:40 lr: 0.000494 loss: 3.3387 (3.2799) grad_norm: 1.4684 (1.5067) time: 0.6360 [2021-03-27 09:02:13 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 270/1251] eta: 0:10:32 lr: 0.000494 loss: 3.3183 (3.2835) grad_norm: 1.4798 (1.5081) time: 0.6268 [2021-03-27 09:02:20 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 280/1251] eta: 0:10:25 lr: 0.000493 loss: 3.4886 (3.2907) grad_norm: 1.6217 (1.5162) time: 0.6248 [2021-03-27 09:02:26 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 290/1251] eta: 0:10:18 lr: 0.000493 loss: 3.5167 (3.2974) grad_norm: 1.6179 (1.5180) time: 0.6262 [2021-03-27 09:02:32 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 300/1251] eta: 0:10:11 lr: 0.000493 loss: 3.3916 (3.2975) grad_norm: 1.4787 (1.5147) time: 0.6268 [2021-03-27 09:02:39 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 310/1251] eta: 0:10:04 lr: 0.000493 loss: 3.3916 (3.2992) grad_norm: 1.4034 (1.5118) time: 0.6272 [2021-03-27 09:02:45 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 320/1251] eta: 0:09:58 lr: 0.000493 loss: 3.4758 (3.2984) grad_norm: 1.4574 (1.5145) time: 0.6282 [2021-03-27 09:02:51 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 330/1251] eta: 0:09:51 lr: 0.000493 loss: 3.4758 (3.2992) grad_norm: 1.5463 (1.5191) time: 0.6327 [2021-03-27 09:02:57 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 340/1251] eta: 0:09:44 lr: 0.000493 loss: 3.3795 (3.3000) grad_norm: 1.4836 (1.5175) time: 0.6309 [2021-03-27 09:03:04 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 350/1251] eta: 0:09:38 lr: 0.000493 loss: 3.3795 (3.3004) grad_norm: 1.3651 (1.5145) time: 0.6342 [2021-03-27 09:03:10 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 360/1251] eta: 0:09:31 lr: 0.000493 loss: 3.1038 (3.2946) grad_norm: 1.4014 (1.5161) time: 0.6371 [2021-03-27 09:03:16 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 370/1251] eta: 0:09:24 lr: 0.000493 loss: 3.1472 (3.2922) grad_norm: 1.5039 (1.5165) time: 0.6301 [2021-03-27 09:03:23 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 380/1251] eta: 0:09:18 lr: 0.000493 loss: 3.1472 (3.2888) grad_norm: 1.5043 (1.5161) time: 0.6290 [2021-03-27 09:03:29 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 390/1251] eta: 0:09:11 lr: 0.000493 loss: 3.0427 (3.2871) grad_norm: 1.4806 (1.5158) time: 0.6274 [2021-03-27 09:03:35 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 400/1251] eta: 0:09:04 lr: 0.000493 loss: 3.3813 (3.2892) grad_norm: 1.4335 (1.5204) time: 0.6283 [2021-03-27 09:03:42 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 410/1251] eta: 0:08:58 lr: 0.000493 loss: 3.3839 (3.2887) grad_norm: 1.4784 (1.5245) time: 0.6310 [2021-03-27 09:03:48 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 420/1251] eta: 0:08:51 lr: 0.000493 loss: 3.3295 (3.2867) grad_norm: 1.5055 (1.5237) time: 0.6343 [2021-03-27 09:03:54 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 430/1251] eta: 0:08:45 lr: 0.000493 loss: 3.4155 (3.2854) grad_norm: 1.4950 (1.5234) time: 0.6325 [2021-03-27 09:04:01 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 440/1251] eta: 0:08:38 lr: 0.000493 loss: 3.2242 (3.2774) grad_norm: 1.5262 (1.5257) time: 0.6297 [2021-03-27 09:04:07 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 450/1251] eta: 0:08:32 lr: 0.000493 loss: 3.2098 (3.2746) grad_norm: 1.4986 (1.5265) time: 0.6315 [2021-03-27 09:04:13 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 460/1251] eta: 0:08:25 lr: 0.000493 loss: 3.2705 (3.2725) grad_norm: 1.4296 (1.5234) time: 0.6353 [2021-03-27 09:04:20 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 470/1251] eta: 0:08:19 lr: 0.000493 loss: 3.2885 (3.2731) grad_norm: 1.4296 (1.5224) time: 0.6381 [2021-03-27 09:04:26 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 480/1251] eta: 0:08:12 lr: 0.000493 loss: 3.3922 (3.2723) grad_norm: 1.4601 (1.5233) time: 0.6345 [2021-03-27 09:04:32 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 490/1251] eta: 0:08:06 lr: 0.000493 loss: 3.3138 (3.2740) grad_norm: 1.4804 (1.5247) time: 0.6333 [2021-03-27 09:04:39 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 500/1251] eta: 0:07:59 lr: 0.000493 loss: 3.3601 (3.2772) grad_norm: 1.5217 (1.5244) time: 0.6316 [2021-03-27 09:04:45 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 510/1251] eta: 0:07:53 lr: 0.000493 loss: 3.3127 (3.2743) grad_norm: 1.5559 (1.5269) time: 0.6287 [2021-03-27 09:04:51 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 520/1251] eta: 0:07:46 lr: 0.000492 loss: 2.9903 (3.2683) grad_norm: 1.5453 (1.5267) time: 0.6343 [2021-03-27 09:04:58 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 530/1251] eta: 0:07:40 lr: 0.000492 loss: 3.3567 (3.2693) grad_norm: 1.5357 (1.5308) time: 0.6338 [2021-03-27 09:05:04 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 540/1251] eta: 0:07:33 lr: 0.000492 loss: 3.4529 (3.2747) grad_norm: 1.5800 (1.5333) time: 0.6302 [2021-03-27 09:05:10 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 550/1251] eta: 0:07:27 lr: 0.000492 loss: 3.3601 (3.2714) grad_norm: 1.5121 (1.5317) time: 0.6418 [2021-03-27 09:05:17 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 560/1251] eta: 0:07:21 lr: 0.000492 loss: 3.2311 (3.2722) grad_norm: 1.4174 (1.5304) time: 0.6405 [2021-03-27 09:05:23 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 570/1251] eta: 0:07:14 lr: 0.000492 loss: 3.3164 (3.2716) grad_norm: 1.5039 (1.5332) time: 0.6337 [2021-03-27 09:05:29 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 580/1251] eta: 0:07:08 lr: 0.000492 loss: 3.1178 (3.2677) grad_norm: 1.5400 (1.5352) time: 0.6321 [2021-03-27 09:05:36 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 590/1251] eta: 0:07:01 lr: 0.000492 loss: 2.9632 (3.2635) grad_norm: 1.5049 (1.5347) time: 0.6399 [2021-03-27 09:05:42 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 600/1251] eta: 0:06:55 lr: 0.000492 loss: 3.0435 (3.2613) grad_norm: 1.4155 (1.5325) time: 0.6457 [2021-03-27 09:05:49 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 610/1251] eta: 0:06:49 lr: 0.000492 loss: 3.3026 (3.2647) grad_norm: 1.3866 (1.5313) time: 0.6375 [2021-03-27 09:05:55 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 620/1251] eta: 0:06:42 lr: 0.000492 loss: 3.3866 (3.2667) grad_norm: 1.4685 (1.5309) time: 0.6319 [2021-03-27 09:06:01 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 630/1251] eta: 0:06:36 lr: 0.000492 loss: 3.3551 (3.2645) grad_norm: 1.4401 (1.5296) time: 0.6282 [2021-03-27 09:06:08 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 640/1251] eta: 0:06:29 lr: 0.000492 loss: 3.3551 (3.2662) grad_norm: 1.4492 (1.5284) time: 0.6289 [2021-03-27 09:06:14 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 650/1251] eta: 0:06:23 lr: 0.000492 loss: 3.3280 (3.2668) grad_norm: 1.4641 (1.5299) time: 0.6330 [2021-03-27 09:06:20 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 660/1251] eta: 0:06:16 lr: 0.000492 loss: 3.2972 (3.2661) grad_norm: 1.5081 (1.5305) time: 0.6307 [2021-03-27 09:06:26 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 670/1251] eta: 0:06:10 lr: 0.000492 loss: 3.4026 (3.2688) grad_norm: 1.5428 (1.5333) time: 0.6250 [2021-03-27 09:06:33 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 680/1251] eta: 0:06:03 lr: 0.000492 loss: 3.5218 (3.2694) grad_norm: 1.5265 (1.5326) time: 0.6275 [2021-03-27 09:06:39 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 690/1251] eta: 0:05:57 lr: 0.000492 loss: 3.3775 (3.2698) grad_norm: 1.5475 (1.5349) time: 0.6305 [2021-03-27 09:06:45 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 700/1251] eta: 0:05:51 lr: 0.000492 loss: 3.3056 (3.2701) grad_norm: 1.5609 (1.5345) time: 0.6297 [2021-03-27 09:06:52 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 710/1251] eta: 0:05:44 lr: 0.000492 loss: 3.3502 (3.2706) grad_norm: 1.5526 (1.5366) time: 0.6315 [2021-03-27 09:06:58 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 720/1251] eta: 0:05:38 lr: 0.000492 loss: 3.3173 (3.2707) grad_norm: 1.5466 (1.5369) time: 0.6305 [2021-03-27 09:07:04 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 730/1251] eta: 0:05:31 lr: 0.000492 loss: 3.3173 (3.2704) grad_norm: 1.5031 (1.5354) time: 0.6319 [2021-03-27 09:07:11 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 740/1251] eta: 0:05:25 lr: 0.000492 loss: 3.2514 (3.2707) grad_norm: 1.4177 (1.5348) time: 0.6375 [2021-03-27 09:07:17 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 750/1251] eta: 0:05:19 lr: 0.000492 loss: 3.1657 (3.2688) grad_norm: 1.4174 (1.5337) time: 0.6422 [2021-03-27 09:07:24 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 760/1251] eta: 0:05:12 lr: 0.000491 loss: 3.2521 (3.2696) grad_norm: 1.4283 (1.5331) time: 0.6460 [2021-03-27 09:07:30 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 770/1251] eta: 0:05:06 lr: 0.000491 loss: 3.4524 (3.2710) grad_norm: 1.5273 (1.5329) time: 0.6379 [2021-03-27 09:07:36 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 780/1251] eta: 0:05:00 lr: 0.000491 loss: 3.5048 (3.2739) grad_norm: 1.5330 (1.5339) time: 0.6294 [2021-03-27 09:07:43 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 790/1251] eta: 0:04:53 lr: 0.000491 loss: 3.3966 (3.2716) grad_norm: 1.5284 (1.5343) time: 0.6329 [2021-03-27 09:07:49 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 800/1251] eta: 0:04:47 lr: 0.000491 loss: 3.1341 (3.2700) grad_norm: 1.4553 (1.5335) time: 0.6359 [2021-03-27 09:07:55 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 810/1251] eta: 0:04:40 lr: 0.000491 loss: 3.3309 (3.2706) grad_norm: 1.4526 (1.5339) time: 0.6306 [2021-03-27 09:08:02 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 820/1251] eta: 0:04:34 lr: 0.000491 loss: 3.4869 (3.2722) grad_norm: 1.5015 (1.5335) time: 0.6356 [2021-03-27 09:08:08 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 830/1251] eta: 0:04:28 lr: 0.000491 loss: 3.4173 (3.2729) grad_norm: 1.4246 (1.5314) time: 0.6449 [2021-03-27 09:08:14 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 840/1251] eta: 0:04:21 lr: 0.000491 loss: 3.5565 (3.2767) grad_norm: 1.4141 (1.5321) time: 0.6377 [2021-03-27 09:08:21 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 850/1251] eta: 0:04:15 lr: 0.000491 loss: 3.6173 (3.2773) grad_norm: 1.4862 (1.5312) time: 0.6316 [2021-03-27 09:08:27 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 860/1251] eta: 0:04:09 lr: 0.000491 loss: 3.4314 (3.2800) grad_norm: 1.4241 (1.5310) time: 0.6319 [2021-03-27 09:08:33 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 870/1251] eta: 0:04:02 lr: 0.000491 loss: 3.4211 (3.2794) grad_norm: 1.4827 (1.5307) time: 0.6266 [2021-03-27 09:08:40 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 880/1251] eta: 0:03:56 lr: 0.000491 loss: 3.2870 (3.2809) grad_norm: 1.5051 (1.5311) time: 0.6242 [2021-03-27 09:08:46 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 890/1251] eta: 0:03:49 lr: 0.000491 loss: 3.5139 (3.2828) grad_norm: 1.5375 (1.5311) time: 0.6270 [2021-03-27 09:08:52 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 900/1251] eta: 0:03:43 lr: 0.000491 loss: 3.4278 (3.2831) grad_norm: 1.4867 (1.5303) time: 0.6237 [2021-03-27 09:08:58 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 910/1251] eta: 0:03:36 lr: 0.000491 loss: 3.3706 (3.2825) grad_norm: 1.4201 (1.5303) time: 0.6225 [2021-03-27 09:09:05 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 920/1251] eta: 0:03:30 lr: 0.000491 loss: 3.4576 (3.2847) grad_norm: 1.4321 (1.5296) time: 0.6295 [2021-03-27 09:09:11 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 930/1251] eta: 0:03:24 lr: 0.000491 loss: 3.5037 (3.2875) grad_norm: 1.4719 (1.5294) time: 0.6313 [2021-03-27 09:09:17 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 940/1251] eta: 0:03:17 lr: 0.000491 loss: 3.3110 (3.2858) grad_norm: 1.4730 (1.5303) time: 0.6304 [2021-03-27 09:09:24 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 950/1251] eta: 0:03:11 lr: 0.000491 loss: 3.1415 (3.2868) grad_norm: 1.4908 (1.5301) time: 0.6305 [2021-03-27 09:09:30 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 960/1251] eta: 0:03:05 lr: 0.000491 loss: 3.4163 (3.2868) grad_norm: 1.4468 (1.5290) time: 0.6250 [2021-03-27 09:09:36 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 970/1251] eta: 0:02:58 lr: 0.000491 loss: 3.4383 (3.2865) grad_norm: 1.4468 (1.5291) time: 0.6267 [2021-03-27 09:09:42 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 980/1251] eta: 0:02:52 lr: 0.000491 loss: 3.4013 (3.2884) grad_norm: 1.4731 (1.5282) time: 0.6340 [2021-03-27 09:09:49 swin_base_patch4_window7_224] INFO: Epoch: [152] [ 990/1251] eta: 0:02:45 lr: 0.000491 loss: 3.3195 (3.2886) grad_norm: 1.4731 (1.5287) time: 0.6304 [2021-03-27 09:09:55 swin_base_patch4_window7_224] INFO: Epoch: [152] [1000/1251] eta: 0:02:39 lr: 0.000490 loss: 3.2661 (3.2881) grad_norm: 1.5378 (1.5286) time: 0.6301 [2021-03-27 09:10:01 swin_base_patch4_window7_224] INFO: Epoch: [152] [1010/1251] eta: 0:02:33 lr: 0.000490 loss: 3.3093 (3.2871) grad_norm: 1.5773 (1.5298) time: 0.6337 [2021-03-27 09:10:08 swin_base_patch4_window7_224] INFO: Epoch: [152] [1020/1251] eta: 0:02:26 lr: 0.000490 loss: 3.0003 (3.2844) grad_norm: 1.5511 (1.5300) time: 0.6325 [2021-03-27 09:10:14 swin_base_patch4_window7_224] INFO: Epoch: [152] [1030/1251] eta: 0:02:20 lr: 0.000490 loss: 3.0003 (3.2824) grad_norm: 1.4540 (1.5297) time: 0.6273 [2021-03-27 09:10:20 swin_base_patch4_window7_224] INFO: Epoch: [152] [1040/1251] eta: 0:02:14 lr: 0.000490 loss: 3.1958 (3.2803) grad_norm: 1.4521 (1.5291) time: 0.6244 [2021-03-27 09:10:27 swin_base_patch4_window7_224] INFO: Epoch: [152] [1050/1251] eta: 0:02:07 lr: 0.000490 loss: 3.1891 (3.2785) grad_norm: 1.4896 (1.5297) time: 0.6341 [2021-03-27 09:10:33 swin_base_patch4_window7_224] INFO: Epoch: [152] [1060/1251] eta: 0:02:01 lr: 0.000490 loss: 3.1891 (3.2780) grad_norm: 1.4896 (1.5291) time: 0.6435 [2021-03-27 09:10:39 swin_base_patch4_window7_224] INFO: Epoch: [152] [1070/1251] eta: 0:01:55 lr: 0.000490 loss: 3.3282 (3.2787) grad_norm: 1.4619 (1.5293) time: 0.6415 [2021-03-27 09:10:46 swin_base_patch4_window7_224] INFO: Epoch: [152] [1080/1251] eta: 0:01:48 lr: 0.000490 loss: 3.4443 (3.2822) grad_norm: 1.5055 (1.5299) time: 0.6316 [2021-03-27 09:10:52 swin_base_patch4_window7_224] INFO: Epoch: [152] [1090/1251] eta: 0:01:42 lr: 0.000490 loss: 3.5272 (3.2819) grad_norm: 1.5204 (1.5307) time: 0.6325 [2021-03-27 09:10:58 swin_base_patch4_window7_224] INFO: Epoch: [152] [1100/1251] eta: 0:01:35 lr: 0.000490 loss: 3.3337 (3.2823) grad_norm: 1.5328 (1.5308) time: 0.6325 [2021-03-27 09:11:05 swin_base_patch4_window7_224] INFO: Epoch: [152] [1110/1251] eta: 0:01:29 lr: 0.000490 loss: 3.4840 (3.2844) grad_norm: 1.4903 (1.5301) time: 0.6270 [2021-03-27 09:11:11 swin_base_patch4_window7_224] INFO: Epoch: [152] [1120/1251] eta: 0:01:23 lr: 0.000490 loss: 3.4840 (3.2854) grad_norm: 1.4646 (1.5300) time: 0.6286 [2021-03-27 09:11:17 swin_base_patch4_window7_224] INFO: Epoch: [152] [1130/1251] eta: 0:01:16 lr: 0.000490 loss: 3.3872 (3.2858) grad_norm: 1.5385 (1.5313) time: 0.6298 [2021-03-27 09:11:24 swin_base_patch4_window7_224] INFO: Epoch: [152] [1140/1251] eta: 0:01:10 lr: 0.000490 loss: 3.2803 (3.2844) grad_norm: 1.7020 (1.5334) time: 0.6347 [2021-03-27 09:11:30 swin_base_patch4_window7_224] INFO: Epoch: [152] [1150/1251] eta: 0:01:04 lr: 0.000490 loss: 3.3052 (3.2845) grad_norm: 1.6711 (1.5349) time: 0.6335 [2021-03-27 09:11:36 swin_base_patch4_window7_224] INFO: Epoch: [152] [1160/1251] eta: 0:00:57 lr: 0.000490 loss: 3.3178 (3.2863) grad_norm: 1.5255 (1.5352) time: 0.6270 [2021-03-27 09:11:42 swin_base_patch4_window7_224] INFO: Epoch: [152] [1170/1251] eta: 0:00:51 lr: 0.000490 loss: 3.4505 (3.2879) grad_norm: 1.6047 (1.5367) time: 0.6257 [2021-03-27 09:11:49 swin_base_patch4_window7_224] INFO: Epoch: [152] [1180/1251] eta: 0:00:45 lr: 0.000490 loss: 3.4495 (3.2883) grad_norm: 1.6469 (1.5376) time: 0.6280 [2021-03-27 09:11:55 swin_base_patch4_window7_224] INFO: Epoch: [152] [1190/1251] eta: 0:00:38 lr: 0.000490 loss: 3.1864 (3.2864) grad_norm: 1.5748 (1.5377) time: 0.6305 [2021-03-27 09:12:01 swin_base_patch4_window7_224] INFO: Epoch: [152] [1200/1251] eta: 0:00:32 lr: 0.000490 loss: 3.2059 (3.2877) grad_norm: 1.5467 (1.5386) time: 0.6348 [2021-03-27 09:12:08 swin_base_patch4_window7_224] INFO: Epoch: [152] [1210/1251] eta: 0:00:26 lr: 0.000490 loss: 3.4703 (3.2899) grad_norm: 1.5170 (1.5384) time: 0.6404 [2021-03-27 09:12:14 swin_base_patch4_window7_224] INFO: Epoch: [152] [1220/1251] eta: 0:00:19 lr: 0.000490 loss: 3.4404 (3.2897) grad_norm: 1.5074 (1.5385) time: 0.6365 [2021-03-27 09:12:20 swin_base_patch4_window7_224] INFO: Epoch: [152] [1230/1251] eta: 0:00:13 lr: 0.000490 loss: 3.3011 (3.2901) grad_norm: 1.5230 (1.5389) time: 0.6309 [2021-03-27 09:12:27 swin_base_patch4_window7_224] INFO: Epoch: [152] [1240/1251] eta: 0:00:06 lr: 0.000489 loss: 3.3437 (3.2908) grad_norm: 1.5072 (1.5388) time: 0.6321 [2021-03-27 09:12:33 swin_base_patch4_window7_224] INFO: Epoch: [152] [1250/1251] eta: 0:00:00 lr: 0.000489 loss: 3.1175 (3.2873) grad_norm: 1.5072 (1.5387) time: 0.6337 [2021-03-27 09:12:41 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:59 loss: 0.9255 (0.9255) acc1: 81.2500 (81.2500) acc5: 93.7500 (93.7500) [2021-03-27 09:12:43 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9292 (0.9101) acc1: 78.1250 (77.2727) acc5: 96.8750 (95.8807) [2021-03-27 09:12:45 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8964 (0.9150) acc1: 78.1250 (77.4554) acc5: 95.3125 (95.1637) [2021-03-27 09:12:47 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8807 (0.8999) acc1: 78.1250 (77.9738) acc5: 95.3125 (95.3125) [2021-03-27 09:12:49 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8807 (0.9081) acc1: 76.5625 (78.0869) acc5: 95.3125 (95.0838) [2021-03-27 09:12:50 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8535 (0.8983) acc1: 79.6875 (78.4960) acc5: 95.3125 (95.2000) [2021-03-27 09:13:00 swin_base_patch4_window7_224] INFO: * Acc@1 79.112 Acc@5 94.852 loss 0.896 [2021-03-27 09:13:00 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.1% [2021-03-27 09:13:00 swin_base_patch4_window7_224] INFO: Max accuracy: 79.12% [2021-03-27 09:13:05 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 0/1251] eta: 1:43:16 lr: 0.000489 loss: 2.9551 (2.9551) grad_norm: 1.6020 (1.6020) time: 4.9530 [2021-03-27 09:13:11 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 10/1251] eta: 0:21:05 lr: 0.000489 loss: 2.9551 (2.9195) grad_norm: 1.5074 (1.5147) time: 1.0196 [2021-03-27 09:13:17 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 20/1251] eta: 0:17:06 lr: 0.000489 loss: 2.9997 (3.0024) grad_norm: 1.5694 (1.5496) time: 0.6278 [2021-03-27 09:13:23 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 30/1251] eta: 0:15:35 lr: 0.000489 loss: 3.0885 (3.0195) grad_norm: 1.6609 (1.6014) time: 0.6268 [2021-03-27 09:13:30 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 40/1251] eta: 0:14:46 lr: 0.000489 loss: 3.2218 (3.0776) grad_norm: 1.5617 (1.5840) time: 0.6248 [2021-03-27 09:13:36 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 50/1251] eta: 0:14:14 lr: 0.000489 loss: 3.3748 (3.0987) grad_norm: 1.5330 (1.5915) time: 0.6272 [2021-03-27 09:13:42 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 60/1251] eta: 0:13:50 lr: 0.000489 loss: 3.3748 (3.1194) grad_norm: 1.5961 (1.6120) time: 0.6269 [2021-03-27 09:13:49 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 70/1251] eta: 0:13:33 lr: 0.000489 loss: 3.4586 (3.1363) grad_norm: 1.5423 (1.5958) time: 0.6302 [2021-03-27 09:13:55 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 80/1251] eta: 0:13:18 lr: 0.000489 loss: 3.4574 (3.1628) grad_norm: 1.5167 (1.5849) time: 0.6348 [2021-03-27 09:14:01 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 90/1251] eta: 0:13:05 lr: 0.000489 loss: 3.2627 (3.1714) grad_norm: 1.5740 (1.5795) time: 0.6342 [2021-03-27 09:14:07 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 100/1251] eta: 0:12:53 lr: 0.000489 loss: 3.2627 (3.1775) grad_norm: 1.5031 (1.5734) time: 0.6310 [2021-03-27 09:14:14 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 110/1251] eta: 0:12:42 lr: 0.000489 loss: 3.3617 (3.1844) grad_norm: 1.5368 (1.5724) time: 0.6320 [2021-03-27 09:14:20 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 120/1251] eta: 0:12:34 lr: 0.000489 loss: 3.3617 (3.1894) grad_norm: 1.5128 (1.5678) time: 0.6405 [2021-03-27 09:14:27 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 130/1251] eta: 0:12:24 lr: 0.000489 loss: 3.1503 (3.1900) grad_norm: 1.5039 (1.5755) time: 0.6407 [2021-03-27 09:14:33 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 140/1251] eta: 0:12:15 lr: 0.000489 loss: 3.1503 (3.1952) grad_norm: 1.5503 (1.5673) time: 0.6339 [2021-03-27 09:14:39 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 150/1251] eta: 0:12:06 lr: 0.000489 loss: 3.5636 (3.2115) grad_norm: 1.4369 (1.5691) time: 0.6312 [2021-03-27 09:14:46 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 160/1251] eta: 0:11:58 lr: 0.000489 loss: 3.4254 (3.2013) grad_norm: 1.4862 (1.5673) time: 0.6332 [2021-03-27 09:14:52 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 170/1251] eta: 0:11:49 lr: 0.000489 loss: 3.2229 (3.1969) grad_norm: 1.4970 (1.5633) time: 0.6317 [2021-03-27 09:14:58 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 180/1251] eta: 0:11:42 lr: 0.000489 loss: 3.4731 (3.2100) grad_norm: 1.5449 (1.5749) time: 0.6320 [2021-03-27 09:15:05 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 190/1251] eta: 0:11:34 lr: 0.000489 loss: 3.5432 (3.2119) grad_norm: 1.5091 (1.5702) time: 0.6394 [2021-03-27 09:15:11 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 200/1251] eta: 0:11:27 lr: 0.000489 loss: 3.2693 (3.2005) grad_norm: 1.4644 (1.5675) time: 0.6421 [2021-03-27 09:15:17 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 210/1251] eta: 0:11:19 lr: 0.000489 loss: 3.1615 (3.1995) grad_norm: 1.5131 (1.5659) time: 0.6367 [2021-03-27 09:15:24 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 220/1251] eta: 0:11:12 lr: 0.000489 loss: 3.1755 (3.2025) grad_norm: 1.5231 (1.5654) time: 0.6302 [2021-03-27 09:15:30 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 230/1251] eta: 0:11:05 lr: 0.000488 loss: 3.2535 (3.2039) grad_norm: 1.5231 (1.5644) time: 0.6329 [2021-03-27 09:15:36 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 240/1251] eta: 0:10:57 lr: 0.000488 loss: 3.2535 (3.2114) grad_norm: 1.5465 (1.5659) time: 0.6284 [2021-03-27 09:15:43 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 250/1251] eta: 0:10:49 lr: 0.000488 loss: 3.4784 (3.2187) grad_norm: 1.5954 (1.5651) time: 0.6217 [2021-03-27 09:15:49 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 260/1251] eta: 0:10:42 lr: 0.000488 loss: 3.4810 (3.2276) grad_norm: 1.5378 (1.5666) time: 0.6255 [2021-03-27 09:15:55 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 270/1251] eta: 0:10:34 lr: 0.000488 loss: 3.3826 (3.2252) grad_norm: 1.4882 (1.5610) time: 0.6252 [2021-03-27 09:16:01 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 280/1251] eta: 0:10:27 lr: 0.000488 loss: 3.3168 (3.2312) grad_norm: 1.3920 (1.5609) time: 0.6268 [2021-03-27 09:16:08 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 290/1251] eta: 0:10:21 lr: 0.000488 loss: 3.1304 (3.2211) grad_norm: 1.5336 (1.5607) time: 0.6344 [2021-03-27 09:16:14 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 300/1251] eta: 0:10:14 lr: 0.000488 loss: 3.1613 (3.2260) grad_norm: 1.5336 (1.5606) time: 0.6440 [2021-03-27 09:16:21 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 310/1251] eta: 0:10:08 lr: 0.000488 loss: 3.3487 (3.2235) grad_norm: 1.5515 (1.5611) time: 0.6434 [2021-03-27 09:16:27 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 320/1251] eta: 0:10:01 lr: 0.000488 loss: 3.5633 (3.2266) grad_norm: 1.4777 (1.5586) time: 0.6376 [2021-03-27 09:16:33 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 330/1251] eta: 0:09:54 lr: 0.000488 loss: 3.4753 (3.2291) grad_norm: 1.5046 (1.5604) time: 0.6310 [2021-03-27 09:16:40 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 340/1251] eta: 0:09:47 lr: 0.000488 loss: 3.4398 (3.2328) grad_norm: 1.6188 (1.5641) time: 0.6288 [2021-03-27 09:16:46 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 350/1251] eta: 0:09:40 lr: 0.000488 loss: 3.3415 (3.2285) grad_norm: 1.5721 (1.5649) time: 0.6277 [2021-03-27 09:16:52 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 360/1251] eta: 0:09:33 lr: 0.000488 loss: 3.3221 (3.2254) grad_norm: 1.5537 (1.5668) time: 0.6231 [2021-03-27 09:16:58 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 370/1251] eta: 0:09:26 lr: 0.000488 loss: 3.4450 (3.2289) grad_norm: 1.4820 (1.5664) time: 0.6304 [2021-03-27 09:17:05 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 380/1251] eta: 0:09:20 lr: 0.000488 loss: 3.3678 (3.2304) grad_norm: 1.5369 (1.5669) time: 0.6310 [2021-03-27 09:17:11 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 390/1251] eta: 0:09:13 lr: 0.000488 loss: 3.3109 (3.2323) grad_norm: 1.6292 (1.5771) time: 0.6269 [2021-03-27 09:17:17 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 400/1251] eta: 0:09:06 lr: 0.000488 loss: 3.4490 (3.2365) grad_norm: 1.5810 (1.5771) time: 0.6280 [2021-03-27 09:17:24 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 410/1251] eta: 0:08:59 lr: 0.000488 loss: 3.3574 (3.2407) grad_norm: 1.5693 (1.5931) time: 0.6270 [2021-03-27 09:17:30 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 420/1251] eta: 0:08:53 lr: 0.000488 loss: 3.3574 (3.2432) grad_norm: 1.5549 (1.5913) time: 0.6297 [2021-03-27 09:17:36 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 430/1251] eta: 0:08:46 lr: 0.000488 loss: 3.3006 (3.2415) grad_norm: 1.5129 (1.5900) time: 0.6320 [2021-03-27 09:17:42 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 440/1251] eta: 0:08:40 lr: 0.000488 loss: 3.1558 (3.2376) grad_norm: 1.4529 (1.5876) time: 0.6318 [2021-03-27 09:17:49 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 450/1251] eta: 0:08:33 lr: 0.000488 loss: 3.2741 (3.2439) grad_norm: 1.4636 (1.5861) time: 0.6297 [2021-03-27 09:17:55 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 460/1251] eta: 0:08:26 lr: 0.000488 loss: 3.6467 (3.2469) grad_norm: 1.5257 (1.5884) time: 0.6259 [2021-03-27 09:18:01 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 470/1251] eta: 0:08:20 lr: 0.000488 loss: 3.4486 (3.2464) grad_norm: 1.5801 (1.5877) time: 0.6265 [2021-03-27 09:18:08 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 480/1251] eta: 0:08:13 lr: 0.000487 loss: 3.3138 (3.2439) grad_norm: 1.5293 (1.5879) time: 0.6273 [2021-03-27 09:18:14 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 490/1251] eta: 0:08:06 lr: 0.000487 loss: 3.4574 (3.2454) grad_norm: 1.5544 (1.5871) time: 0.6297 [2021-03-27 09:18:20 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 500/1251] eta: 0:08:00 lr: 0.000487 loss: 3.1029 (3.2417) grad_norm: 1.5732 (1.5901) time: 0.6333 [2021-03-27 09:18:26 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 510/1251] eta: 0:07:53 lr: 0.000487 loss: 3.0318 (3.2434) grad_norm: 1.5677 (1.5890) time: 0.6299 [2021-03-27 09:18:33 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 520/1251] eta: 0:07:47 lr: 0.000487 loss: 3.3550 (3.2419) grad_norm: 1.5100 (1.5895) time: 0.6244 [2021-03-27 09:18:39 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 530/1251] eta: 0:07:40 lr: 0.000487 loss: 3.3390 (3.2424) grad_norm: 1.4884 (1.5873) time: 0.6282 [2021-03-27 09:18:45 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 540/1251] eta: 0:07:34 lr: 0.000487 loss: 3.3328 (3.2419) grad_norm: 1.5052 (1.5870) time: 0.6291 [2021-03-27 09:18:52 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 550/1251] eta: 0:07:27 lr: 0.000487 loss: 3.3328 (3.2453) grad_norm: 1.5217 (1.5876) time: 0.6373 [2021-03-27 09:18:58 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 560/1251] eta: 0:07:21 lr: 0.000487 loss: 3.4004 (3.2449) grad_norm: 1.4570 (1.5846) time: 0.6388 [2021-03-27 09:19:04 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 570/1251] eta: 0:07:14 lr: 0.000487 loss: 3.4820 (3.2543) grad_norm: 1.3874 (1.5819) time: 0.6297 [2021-03-27 09:19:11 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 580/1251] eta: 0:07:08 lr: 0.000487 loss: 3.4820 (3.2498) grad_norm: 1.4905 (1.5825) time: 0.6298 [2021-03-27 09:19:17 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 590/1251] eta: 0:07:01 lr: 0.000487 loss: 3.2651 (3.2516) grad_norm: 1.5205 (1.5816) time: 0.6311 [2021-03-27 09:19:23 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 600/1251] eta: 0:06:55 lr: 0.000487 loss: 3.4992 (3.2552) grad_norm: 1.5154 (1.5804) time: 0.6318 [2021-03-27 09:19:30 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 610/1251] eta: 0:06:49 lr: 0.000487 loss: 3.5028 (3.2556) grad_norm: 1.5214 (1.5805) time: 0.6299 [2021-03-27 09:19:36 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 620/1251] eta: 0:06:42 lr: 0.000487 loss: 3.4160 (3.2587) grad_norm: 1.4465 (1.5783) time: 0.6297 [2021-03-27 09:19:42 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 630/1251] eta: 0:06:36 lr: 0.000487 loss: 3.4160 (3.2602) grad_norm: 1.4483 (1.5773) time: 0.6261 [2021-03-27 09:19:48 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 640/1251] eta: 0:06:29 lr: 0.000487 loss: 3.4257 (3.2642) grad_norm: 1.4502 (1.5766) time: 0.6273 [2021-03-27 09:19:55 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 650/1251] eta: 0:06:23 lr: 0.000487 loss: 3.2677 (3.2622) grad_norm: 1.4528 (1.5755) time: 0.6260 [2021-03-27 09:20:01 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 660/1251] eta: 0:06:16 lr: 0.000487 loss: 3.4155 (3.2656) grad_norm: 1.4587 (1.5742) time: 0.6291 [2021-03-27 09:20:07 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 670/1251] eta: 0:06:10 lr: 0.000487 loss: 3.1458 (3.2571) grad_norm: 1.4097 (1.5707) time: 0.6345 [2021-03-27 09:20:14 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 680/1251] eta: 0:06:03 lr: 0.000487 loss: 3.0420 (3.2587) grad_norm: 1.3759 (1.5714) time: 0.6285 [2021-03-27 09:20:20 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 690/1251] eta: 0:05:57 lr: 0.000487 loss: 3.3867 (3.2575) grad_norm: 1.5584 (1.5702) time: 0.6339 [2021-03-27 09:20:26 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 700/1251] eta: 0:05:50 lr: 0.000487 loss: 3.1745 (3.2567) grad_norm: 1.5368 (1.5745) time: 0.6328 [2021-03-27 09:20:33 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 710/1251] eta: 0:05:44 lr: 0.000487 loss: 3.0208 (3.2538) grad_norm: 1.5377 (1.5737) time: 0.6313 [2021-03-27 09:20:39 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 720/1251] eta: 0:05:38 lr: 0.000486 loss: 3.2534 (3.2556) grad_norm: 1.5377 (1.5756) time: 0.6394 [2021-03-27 09:20:45 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 730/1251] eta: 0:05:31 lr: 0.000486 loss: 3.3618 (3.2572) grad_norm: 1.6560 (1.5791) time: 0.6371 [2021-03-27 09:20:52 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 740/1251] eta: 0:05:25 lr: 0.000486 loss: 3.3735 (3.2587) grad_norm: 1.6154 (1.5787) time: 0.6408 [2021-03-27 09:20:58 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 750/1251] eta: 0:05:19 lr: 0.000486 loss: 3.4399 (3.2623) grad_norm: 1.4651 (1.5786) time: 0.6510 [2021-03-27 09:21:05 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 760/1251] eta: 0:05:12 lr: 0.000486 loss: 3.5940 (3.2645) grad_norm: 1.4488 (1.5767) time: 0.6412 [2021-03-27 09:21:11 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 770/1251] eta: 0:05:06 lr: 0.000486 loss: 3.3599 (3.2645) grad_norm: 1.4416 (1.5753) time: 0.6297 [2021-03-27 09:21:17 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 780/1251] eta: 0:05:00 lr: 0.000486 loss: 3.3599 (3.2665) grad_norm: 1.4854 (1.5763) time: 0.6286 [2021-03-27 09:21:24 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 790/1251] eta: 0:04:53 lr: 0.000486 loss: 3.1500 (3.2637) grad_norm: 1.5611 (1.5759) time: 0.6297 [2021-03-27 09:21:30 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 800/1251] eta: 0:04:47 lr: 0.000486 loss: 3.1500 (3.2636) grad_norm: 1.4395 (1.5753) time: 0.6321 [2021-03-27 09:21:36 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 810/1251] eta: 0:04:40 lr: 0.000486 loss: 3.2296 (3.2622) grad_norm: 1.4654 (1.5744) time: 0.6315 [2021-03-27 09:21:43 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 820/1251] eta: 0:04:34 lr: 0.000486 loss: 3.3896 (3.2638) grad_norm: 1.4955 (1.5741) time: 0.6357 [2021-03-27 09:21:49 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 830/1251] eta: 0:04:28 lr: 0.000486 loss: 3.4149 (3.2645) grad_norm: 1.4483 (1.5741) time: 0.6352 [2021-03-27 09:21:55 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 840/1251] eta: 0:04:21 lr: 0.000486 loss: 3.2284 (3.2637) grad_norm: 1.5277 (1.5737) time: 0.6312 [2021-03-27 09:22:02 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 850/1251] eta: 0:04:15 lr: 0.000486 loss: 3.3975 (3.2652) grad_norm: 1.5438 (1.5741) time: 0.6347 [2021-03-27 09:22:08 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 860/1251] eta: 0:04:08 lr: 0.000486 loss: 3.3844 (3.2605) grad_norm: 1.5485 (1.5747) time: 0.6359 [2021-03-27 09:22:14 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 870/1251] eta: 0:04:02 lr: 0.000486 loss: 3.3844 (3.2618) grad_norm: 1.5771 (1.5744) time: 0.6323 [2021-03-27 09:22:21 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 880/1251] eta: 0:03:56 lr: 0.000486 loss: 3.1138 (3.2577) grad_norm: 1.5576 (1.5740) time: 0.6355 [2021-03-27 09:22:27 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 890/1251] eta: 0:03:49 lr: 0.000486 loss: 2.7226 (3.2532) grad_norm: 1.5293 (1.5738) time: 0.6374 [2021-03-27 09:22:33 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 900/1251] eta: 0:03:43 lr: 0.000486 loss: 3.2878 (3.2569) grad_norm: 1.5055 (1.5732) time: 0.6308 [2021-03-27 09:22:40 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 910/1251] eta: 0:03:37 lr: 0.000486 loss: 3.4990 (3.2577) grad_norm: 1.5270 (1.5731) time: 0.6281 [2021-03-27 09:22:46 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 920/1251] eta: 0:03:30 lr: 0.000486 loss: 3.4938 (3.2594) grad_norm: 1.5124 (1.5723) time: 0.6257 [2021-03-27 09:22:52 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 930/1251] eta: 0:03:24 lr: 0.000486 loss: 3.4672 (3.2605) grad_norm: 1.4686 (1.5720) time: 0.6211 [2021-03-27 09:22:58 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 940/1251] eta: 0:03:17 lr: 0.000486 loss: 3.4672 (3.2636) grad_norm: 1.4735 (1.5716) time: 0.6286 [2021-03-27 09:23:05 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 950/1251] eta: 0:03:11 lr: 0.000486 loss: 3.4390 (3.2645) grad_norm: 1.5478 (1.5714) time: 0.6316 [2021-03-27 09:23:11 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 960/1251] eta: 0:03:05 lr: 0.000485 loss: 3.2901 (3.2639) grad_norm: 1.5483 (1.5717) time: 0.6240 [2021-03-27 09:23:17 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 970/1251] eta: 0:02:58 lr: 0.000485 loss: 3.2901 (3.2642) grad_norm: 1.5136 (1.5714) time: 0.6251 [2021-03-27 09:23:24 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 980/1251] eta: 0:02:52 lr: 0.000485 loss: 3.5299 (3.2667) grad_norm: 1.5158 (1.5723) time: 0.6332 [2021-03-27 09:23:30 swin_base_patch4_window7_224] INFO: Epoch: [153] [ 990/1251] eta: 0:02:45 lr: 0.000485 loss: 3.5299 (3.2668) grad_norm: 1.5799 (1.5732) time: 0.6377 [2021-03-27 09:23:36 swin_base_patch4_window7_224] INFO: Epoch: [153] [1000/1251] eta: 0:02:39 lr: 0.000485 loss: 3.3286 (3.2657) grad_norm: 1.5385 (1.5732) time: 0.6353 [2021-03-27 09:23:43 swin_base_patch4_window7_224] INFO: Epoch: [153] [1010/1251] eta: 0:02:33 lr: 0.000485 loss: 3.2769 (3.2655) grad_norm: 1.5484 (1.5760) time: 0.6290 [2021-03-27 09:23:49 swin_base_patch4_window7_224] INFO: Epoch: [153] [1020/1251] eta: 0:02:26 lr: 0.000485 loss: 3.2666 (3.2661) grad_norm: 1.5692 (1.5757) time: 0.6268 [2021-03-27 09:23:55 swin_base_patch4_window7_224] INFO: Epoch: [153] [1030/1251] eta: 0:02:20 lr: 0.000485 loss: 3.3693 (3.2680) grad_norm: 1.5692 (1.5761) time: 0.6263 [2021-03-27 09:24:01 swin_base_patch4_window7_224] INFO: Epoch: [153] [1040/1251] eta: 0:02:14 lr: 0.000485 loss: 3.5130 (3.2687) grad_norm: 1.5800 (1.5764) time: 0.6249 [2021-03-27 09:24:08 swin_base_patch4_window7_224] INFO: Epoch: [153] [1050/1251] eta: 0:02:07 lr: 0.000485 loss: 3.3693 (3.2707) grad_norm: 1.5097 (1.5750) time: 0.6316 [2021-03-27 09:24:14 swin_base_patch4_window7_224] INFO: Epoch: [153] [1060/1251] eta: 0:02:01 lr: 0.000485 loss: 3.3478 (3.2723) grad_norm: 1.4342 (1.5740) time: 0.6323 [2021-03-27 09:24:20 swin_base_patch4_window7_224] INFO: Epoch: [153] [1070/1251] eta: 0:01:54 lr: 0.000485 loss: 3.4506 (3.2734) grad_norm: 1.4684 (1.5727) time: 0.6270 [2021-03-27 09:24:27 swin_base_patch4_window7_224] INFO: Epoch: [153] [1080/1251] eta: 0:01:48 lr: 0.000485 loss: 3.3383 (3.2700) grad_norm: 1.5409 (1.5738) time: 0.6263 [2021-03-27 09:24:33 swin_base_patch4_window7_224] INFO: Epoch: [153] [1090/1251] eta: 0:01:42 lr: 0.000485 loss: 3.1907 (3.2694) grad_norm: 1.6346 (1.5740) time: 0.6288 [2021-03-27 09:24:39 swin_base_patch4_window7_224] INFO: Epoch: [153] [1100/1251] eta: 0:01:35 lr: 0.000485 loss: 3.2088 (3.2690) grad_norm: 1.5686 (1.5751) time: 0.6333 [2021-03-27 09:24:46 swin_base_patch4_window7_224] INFO: Epoch: [153] [1110/1251] eta: 0:01:29 lr: 0.000485 loss: 3.1816 (3.2678) grad_norm: 1.4879 (1.5742) time: 0.6345 [2021-03-27 09:24:52 swin_base_patch4_window7_224] INFO: Epoch: [153] [1120/1251] eta: 0:01:23 lr: 0.000485 loss: 3.1816 (3.2678) grad_norm: 1.4879 (1.5733) time: 0.6315 [2021-03-27 09:24:58 swin_base_patch4_window7_224] INFO: Epoch: [153] [1130/1251] eta: 0:01:16 lr: 0.000485 loss: 3.3286 (3.2676) grad_norm: 1.5139 (1.5746) time: 0.6309 [2021-03-27 09:25:04 swin_base_patch4_window7_224] INFO: Epoch: [153] [1140/1251] eta: 0:01:10 lr: 0.000485 loss: 3.3286 (3.2672) grad_norm: 1.5380 (1.5745) time: 0.6323 [2021-03-27 09:25:11 swin_base_patch4_window7_224] INFO: Epoch: [153] [1150/1251] eta: 0:01:04 lr: 0.000485 loss: 3.5768 (3.2681) grad_norm: 1.4576 (1.5737) time: 0.6312 [2021-03-27 09:25:17 swin_base_patch4_window7_224] INFO: Epoch: [153] [1160/1251] eta: 0:00:57 lr: 0.000485 loss: 3.0836 (3.2646) grad_norm: 1.4289 (1.5727) time: 0.6333 [2021-03-27 09:25:23 swin_base_patch4_window7_224] INFO: Epoch: [153] [1170/1251] eta: 0:00:51 lr: 0.000485 loss: 3.0450 (3.2623) grad_norm: 1.4747 (1.5729) time: 0.6275 [2021-03-27 09:25:30 swin_base_patch4_window7_224] INFO: Epoch: [153] [1180/1251] eta: 0:00:45 lr: 0.000485 loss: 3.0721 (3.2616) grad_norm: 1.5645 (1.5731) time: 0.6211 [2021-03-27 09:25:36 swin_base_patch4_window7_224] INFO: Epoch: [153] [1190/1251] eta: 0:00:38 lr: 0.000485 loss: 3.0740 (3.2607) grad_norm: 1.4840 (1.5729) time: 0.6222 [2021-03-27 09:25:42 swin_base_patch4_window7_224] INFO: Epoch: [153] [1200/1251] eta: 0:00:32 lr: 0.000484 loss: 3.1922 (3.2602) grad_norm: 1.4313 (1.5720) time: 0.6243 [2021-03-27 09:25:48 swin_base_patch4_window7_224] INFO: Epoch: [153] [1210/1251] eta: 0:00:26 lr: 0.000484 loss: 3.3895 (3.2619) grad_norm: 1.4288 (1.5715) time: 0.6275 [2021-03-27 09:25:55 swin_base_patch4_window7_224] INFO: Epoch: [153] [1220/1251] eta: 0:00:19 lr: 0.000484 loss: 3.5137 (3.2643) grad_norm: 1.4396 (1.5713) time: 0.6238 [2021-03-27 09:26:01 swin_base_patch4_window7_224] INFO: Epoch: [153] [1230/1251] eta: 0:00:13 lr: 0.000484 loss: 3.5378 (3.2642) grad_norm: 1.5088 (1.5715) time: 0.6253 [2021-03-27 09:26:07 swin_base_patch4_window7_224] INFO: Epoch: [153] [1240/1251] eta: 0:00:06 lr: 0.000484 loss: 3.3952 (3.2650) grad_norm: 1.4980 (1.5707) time: 0.6327 [2021-03-27 09:26:14 swin_base_patch4_window7_224] INFO: Epoch: [153] [1250/1251] eta: 0:00:00 lr: 0.000484 loss: 3.4334 (3.2659) grad_norm: 1.5079 (1.5715) time: 0.6344 [2021-03-27 09:26:22 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:27 loss: 0.9427 (0.9427) acc1: 73.4375 (73.4375) acc5: 96.8750 (96.8750) [2021-03-27 09:26:23 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.9164 (0.9153) acc1: 78.1250 (77.2727) acc5: 95.3125 (96.0227) [2021-03-27 09:26:25 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9164 (0.9597) acc1: 78.1250 (76.7113) acc5: 95.3125 (94.8661) [2021-03-27 09:26:28 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9540 (0.9557) acc1: 78.1250 (77.2177) acc5: 93.7500 (94.6573) [2021-03-27 09:26:30 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8990 (0.9449) acc1: 78.1250 (77.5534) acc5: 93.7500 (94.6265) [2021-03-27 09:26:31 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8400 (0.9171) acc1: 79.6875 (78.1120) acc5: 95.3125 (94.9120) [2021-03-27 09:26:39 swin_base_patch4_window7_224] INFO: * Acc@1 79.030 Acc@5 94.822 loss 0.894 [2021-03-27 09:26:39 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.0% [2021-03-27 09:26:39 swin_base_patch4_window7_224] INFO: Max accuracy: 79.12% [2021-03-27 09:26:43 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 0/1251] eta: 1:27:31 lr: 0.000484 loss: 3.1210 (3.1210) grad_norm: 1.4047 (1.4047) time: 4.1979 [2021-03-27 09:26:50 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 10/1251] eta: 0:20:07 lr: 0.000484 loss: 3.3874 (3.1134) grad_norm: 1.3816 (1.3926) time: 0.9730 [2021-03-27 09:26:56 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 20/1251] eta: 0:16:35 lr: 0.000484 loss: 3.2085 (3.1009) grad_norm: 1.4423 (1.4632) time: 0.6391 [2021-03-27 09:27:03 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 30/1251] eta: 0:15:23 lr: 0.000484 loss: 3.1720 (3.0441) grad_norm: 1.5166 (1.4859) time: 0.6378 [2021-03-27 09:27:09 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 40/1251] eta: 0:14:40 lr: 0.000484 loss: 3.0579 (3.0740) grad_norm: 1.5233 (1.4930) time: 0.6420 [2021-03-27 09:27:15 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 50/1251] eta: 0:14:14 lr: 0.000484 loss: 3.1559 (3.0933) grad_norm: 1.4822 (1.4945) time: 0.6417 [2021-03-27 09:27:22 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 60/1251] eta: 0:13:51 lr: 0.000484 loss: 3.2579 (3.1341) grad_norm: 1.4822 (1.4997) time: 0.6379 [2021-03-27 09:27:28 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 70/1251] eta: 0:13:33 lr: 0.000484 loss: 3.3213 (3.1570) grad_norm: 1.4995 (1.4978) time: 0.6303 [2021-03-27 09:27:34 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 80/1251] eta: 0:13:18 lr: 0.000484 loss: 3.3760 (3.1817) grad_norm: 1.4785 (inf) time: 0.6322 [2021-03-27 09:27:41 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 90/1251] eta: 0:13:05 lr: 0.000484 loss: 3.5733 (3.2192) grad_norm: 1.4785 (inf) time: 0.6338 [2021-03-27 09:27:47 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 100/1251] eta: 0:12:53 lr: 0.000484 loss: 3.5639 (3.2091) grad_norm: 1.4455 (inf) time: 0.6307 [2021-03-27 09:27:53 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 110/1251] eta: 0:12:42 lr: 0.000484 loss: 3.2684 (3.2129) grad_norm: 1.4310 (inf) time: 0.6280 [2021-03-27 09:28:00 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 120/1251] eta: 0:12:32 lr: 0.000484 loss: 3.4261 (3.2360) grad_norm: 1.4310 (inf) time: 0.6351 [2021-03-27 09:28:06 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 130/1251] eta: 0:12:23 lr: 0.000484 loss: 3.4111 (3.2359) grad_norm: 1.3968 (inf) time: 0.6387 [2021-03-27 09:28:12 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 140/1251] eta: 0:12:14 lr: 0.000484 loss: 3.4958 (3.2458) grad_norm: 1.3971 (inf) time: 0.6322 [2021-03-27 09:28:19 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 150/1251] eta: 0:12:06 lr: 0.000484 loss: 3.5095 (3.2462) grad_norm: 1.4896 (inf) time: 0.6341 [2021-03-27 09:28:25 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 160/1251] eta: 0:11:58 lr: 0.000484 loss: 3.4100 (3.2475) grad_norm: 1.5221 (inf) time: 0.6396 [2021-03-27 09:28:31 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 170/1251] eta: 0:11:49 lr: 0.000484 loss: 3.4100 (3.2505) grad_norm: 1.5663 (inf) time: 0.6329 [2021-03-27 09:28:38 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 180/1251] eta: 0:11:41 lr: 0.000484 loss: 3.5210 (3.2492) grad_norm: 1.6423 (inf) time: 0.6290 [2021-03-27 09:28:44 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 190/1251] eta: 0:11:34 lr: 0.000483 loss: 3.4865 (3.2532) grad_norm: 1.6639 (inf) time: 0.6357 [2021-03-27 09:28:51 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 200/1251] eta: 0:11:27 lr: 0.000483 loss: 3.4579 (3.2617) grad_norm: 1.5144 (inf) time: 0.6428 [2021-03-27 09:28:57 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 210/1251] eta: 0:11:19 lr: 0.000483 loss: 3.3079 (3.2488) grad_norm: 1.5643 (inf) time: 0.6369 [2021-03-27 09:29:03 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 220/1251] eta: 0:11:11 lr: 0.000483 loss: 3.1475 (3.2539) grad_norm: 1.5606 (inf) time: 0.6289 [2021-03-27 09:29:09 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 230/1251] eta: 0:11:03 lr: 0.000483 loss: 3.1828 (3.2522) grad_norm: 1.5447 (inf) time: 0.6254 [2021-03-27 09:29:16 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 240/1251] eta: 0:10:56 lr: 0.000483 loss: 3.1904 (3.2537) grad_norm: 1.6096 (inf) time: 0.6274 [2021-03-27 09:29:22 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 250/1251] eta: 0:10:50 lr: 0.000483 loss: 3.5335 (3.2583) grad_norm: 1.5108 (inf) time: 0.6392 [2021-03-27 09:29:29 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 260/1251] eta: 0:10:43 lr: 0.000483 loss: 3.4278 (3.2543) grad_norm: 1.4615 (inf) time: 0.6480 [2021-03-27 09:29:35 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 270/1251] eta: 0:10:36 lr: 0.000483 loss: 3.2672 (3.2546) grad_norm: 1.5189 (inf) time: 0.6461 [2021-03-27 09:29:41 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 280/1251] eta: 0:10:29 lr: 0.000483 loss: 3.1804 (3.2465) grad_norm: 1.5651 (inf) time: 0.6306 [2021-03-27 09:29:48 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 290/1251] eta: 0:10:22 lr: 0.000483 loss: 3.0643 (3.2415) grad_norm: 1.5787 (inf) time: 0.6285 [2021-03-27 09:29:54 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 300/1251] eta: 0:10:15 lr: 0.000483 loss: 3.1980 (3.2454) grad_norm: 1.5786 (inf) time: 0.6343 [2021-03-27 09:30:00 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 310/1251] eta: 0:10:08 lr: 0.000483 loss: 3.2277 (3.2420) grad_norm: 1.4984 (inf) time: 0.6317 [2021-03-27 09:30:07 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 320/1251] eta: 0:10:01 lr: 0.000483 loss: 3.1440 (3.2372) grad_norm: 1.4826 (inf) time: 0.6305 [2021-03-27 09:30:13 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 330/1251] eta: 0:09:54 lr: 0.000483 loss: 3.1778 (3.2417) grad_norm: 1.5672 (inf) time: 0.6343 [2021-03-27 09:30:19 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 340/1251] eta: 0:09:47 lr: 0.000483 loss: 3.3132 (3.2436) grad_norm: 1.5356 (inf) time: 0.6310 [2021-03-27 09:30:26 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 350/1251] eta: 0:09:41 lr: 0.000483 loss: 3.1382 (3.2369) grad_norm: 1.4923 (inf) time: 0.6298 [2021-03-27 09:30:32 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 360/1251] eta: 0:09:34 lr: 0.000483 loss: 3.2005 (3.2360) grad_norm: 1.4923 (inf) time: 0.6362 [2021-03-27 09:30:38 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 370/1251] eta: 0:09:27 lr: 0.000483 loss: 3.4048 (3.2382) grad_norm: 1.4777 (inf) time: 0.6334 [2021-03-27 09:30:45 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 380/1251] eta: 0:09:20 lr: 0.000483 loss: 3.3470 (3.2444) grad_norm: 1.4933 (inf) time: 0.6301 [2021-03-27 09:30:51 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 390/1251] eta: 0:09:14 lr: 0.000483 loss: 3.4507 (3.2489) grad_norm: 1.4933 (inf) time: 0.6278 [2021-03-27 09:30:57 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 400/1251] eta: 0:09:07 lr: 0.000483 loss: 3.3242 (3.2492) grad_norm: 1.5481 (inf) time: 0.6300 [2021-03-27 09:31:03 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 410/1251] eta: 0:09:00 lr: 0.000483 loss: 3.2391 (3.2474) grad_norm: 1.6352 (inf) time: 0.6257 [2021-03-27 09:31:10 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 420/1251] eta: 0:08:53 lr: 0.000483 loss: 3.2391 (3.2448) grad_norm: 1.6055 (inf) time: 0.6216 [2021-03-27 09:31:16 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 430/1251] eta: 0:08:46 lr: 0.000482 loss: 3.5024 (3.2476) grad_norm: 1.5359 (inf) time: 0.6228 [2021-03-27 09:31:22 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 440/1251] eta: 0:08:40 lr: 0.000482 loss: 3.3587 (3.2458) grad_norm: 1.5879 (inf) time: 0.6293 [2021-03-27 09:31:29 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 450/1251] eta: 0:08:33 lr: 0.000482 loss: 3.3614 (3.2521) grad_norm: 1.4268 (inf) time: 0.6347 [2021-03-27 09:31:35 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 460/1251] eta: 0:08:27 lr: 0.000482 loss: 3.3734 (3.2473) grad_norm: 1.4316 (inf) time: 0.6310 [2021-03-27 09:31:41 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 470/1251] eta: 0:08:20 lr: 0.000482 loss: 3.3734 (3.2515) grad_norm: 1.4382 (inf) time: 0.6302 [2021-03-27 09:31:47 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 480/1251] eta: 0:08:13 lr: 0.000482 loss: 3.2429 (3.2456) grad_norm: 1.4940 (inf) time: 0.6301 [2021-03-27 09:31:54 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 490/1251] eta: 0:08:07 lr: 0.000482 loss: 2.9423 (3.2451) grad_norm: 1.4901 (inf) time: 0.6264 [2021-03-27 09:32:00 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 500/1251] eta: 0:08:00 lr: 0.000482 loss: 3.1237 (3.2434) grad_norm: 1.4577 (inf) time: 0.6288 [2021-03-27 09:32:06 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 510/1251] eta: 0:07:54 lr: 0.000482 loss: 3.0554 (3.2378) grad_norm: 1.4633 (inf) time: 0.6323 [2021-03-27 09:32:13 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 520/1251] eta: 0:07:47 lr: 0.000482 loss: 3.2940 (3.2433) grad_norm: 1.6449 (inf) time: 0.6268 [2021-03-27 09:32:19 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 530/1251] eta: 0:07:41 lr: 0.000482 loss: 3.5014 (3.2439) grad_norm: 1.5603 (inf) time: 0.6308 [2021-03-27 09:32:25 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 540/1251] eta: 0:07:34 lr: 0.000482 loss: 3.3531 (3.2424) grad_norm: 1.3730 (inf) time: 0.6344 [2021-03-27 09:32:32 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 550/1251] eta: 0:07:28 lr: 0.000482 loss: 3.3531 (3.2437) grad_norm: 1.3478 (inf) time: 0.6353 [2021-03-27 09:32:38 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 560/1251] eta: 0:07:21 lr: 0.000482 loss: 3.4233 (3.2470) grad_norm: 1.3533 (inf) time: 0.6363 [2021-03-27 09:32:44 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 570/1251] eta: 0:07:15 lr: 0.000482 loss: 3.1408 (3.2414) grad_norm: 1.5388 (inf) time: 0.6304 [2021-03-27 09:32:51 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 580/1251] eta: 0:07:08 lr: 0.000482 loss: 3.1408 (3.2461) grad_norm: 1.5346 (inf) time: 0.6355 [2021-03-27 09:32:57 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 590/1251] eta: 0:07:02 lr: 0.000482 loss: 3.4169 (3.2473) grad_norm: 1.5156 (inf) time: 0.6362 [2021-03-27 09:33:03 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 600/1251] eta: 0:06:56 lr: 0.000482 loss: 3.2458 (3.2444) grad_norm: 1.4751 (inf) time: 0.6364 [2021-03-27 09:33:10 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 610/1251] eta: 0:06:49 lr: 0.000482 loss: 3.2458 (3.2425) grad_norm: 1.5000 (inf) time: 0.6384 [2021-03-27 09:33:16 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 620/1251] eta: 0:06:43 lr: 0.000482 loss: 3.2980 (3.2441) grad_norm: 1.5182 (inf) time: 0.6342 [2021-03-27 09:33:22 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 630/1251] eta: 0:06:36 lr: 0.000482 loss: 3.3866 (3.2480) grad_norm: 1.6357 (inf) time: 0.6274 [2021-03-27 09:33:29 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 640/1251] eta: 0:06:30 lr: 0.000482 loss: 3.5366 (3.2502) grad_norm: 1.5342 (inf) time: 0.6229 [2021-03-27 09:33:35 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 650/1251] eta: 0:06:23 lr: 0.000482 loss: 3.4688 (3.2541) grad_norm: 1.5342 (inf) time: 0.6291 [2021-03-27 09:33:41 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 660/1251] eta: 0:06:17 lr: 0.000482 loss: 3.3346 (3.2530) grad_norm: 1.5913 (inf) time: 0.6315 [2021-03-27 09:33:48 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 670/1251] eta: 0:06:10 lr: 0.000481 loss: 3.1516 (3.2497) grad_norm: 1.5853 (inf) time: 0.6307 [2021-03-27 09:33:54 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 680/1251] eta: 0:06:04 lr: 0.000481 loss: 3.3313 (3.2503) grad_norm: 1.5026 (inf) time: 0.6265 [2021-03-27 09:34:00 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 690/1251] eta: 0:05:57 lr: 0.000481 loss: 3.4067 (3.2550) grad_norm: 1.5278 (inf) time: 0.6286 [2021-03-27 09:34:06 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 700/1251] eta: 0:05:51 lr: 0.000481 loss: 3.4263 (3.2561) grad_norm: 1.4773 (inf) time: 0.6315 [2021-03-27 09:34:13 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 710/1251] eta: 0:05:45 lr: 0.000481 loss: 3.4369 (3.2580) grad_norm: 1.4021 (inf) time: 0.6319 [2021-03-27 09:34:19 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 720/1251] eta: 0:05:38 lr: 0.000481 loss: 3.4819 (3.2604) grad_norm: 1.4091 (inf) time: 0.6325 [2021-03-27 09:34:25 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 730/1251] eta: 0:05:32 lr: 0.000481 loss: 3.4526 (3.2618) grad_norm: 1.4977 (inf) time: 0.6327 [2021-03-27 09:34:32 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 740/1251] eta: 0:05:25 lr: 0.000481 loss: 3.1535 (3.2575) grad_norm: 1.4977 (inf) time: 0.6339 [2021-03-27 09:34:38 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 750/1251] eta: 0:05:19 lr: 0.000481 loss: 3.1535 (3.2580) grad_norm: 1.4991 (inf) time: 0.6331 [2021-03-27 09:34:44 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 760/1251] eta: 0:05:12 lr: 0.000481 loss: 3.2862 (3.2559) grad_norm: 1.4513 (inf) time: 0.6278 [2021-03-27 09:34:51 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 770/1251] eta: 0:05:06 lr: 0.000481 loss: 3.1812 (3.2575) grad_norm: 1.4990 (inf) time: 0.6247 [2021-03-27 09:34:57 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 780/1251] eta: 0:05:00 lr: 0.000481 loss: 3.4188 (3.2569) grad_norm: 1.4757 (inf) time: 0.6254 [2021-03-27 09:35:03 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 790/1251] eta: 0:04:53 lr: 0.000481 loss: 2.8978 (3.2546) grad_norm: 1.4734 (inf) time: 0.6280 [2021-03-27 09:35:09 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 800/1251] eta: 0:04:47 lr: 0.000481 loss: 3.4679 (3.2585) grad_norm: 1.5217 (inf) time: 0.6345 [2021-03-27 09:35:16 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 810/1251] eta: 0:04:40 lr: 0.000481 loss: 3.5673 (3.2587) grad_norm: 1.4339 (inf) time: 0.6319 [2021-03-27 09:35:22 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 820/1251] eta: 0:04:34 lr: 0.000481 loss: 3.3450 (3.2589) grad_norm: 1.4370 (inf) time: 0.6331 [2021-03-27 09:35:28 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 830/1251] eta: 0:04:28 lr: 0.000481 loss: 3.2370 (3.2583) grad_norm: 1.5273 (inf) time: 0.6333 [2021-03-27 09:35:35 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 840/1251] eta: 0:04:21 lr: 0.000481 loss: 3.2236 (3.2561) grad_norm: 1.5273 (inf) time: 0.6306 [2021-03-27 09:35:41 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 850/1251] eta: 0:04:15 lr: 0.000481 loss: 3.3084 (3.2579) grad_norm: 1.5677 (inf) time: 0.6351 [2021-03-27 09:35:48 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 860/1251] eta: 0:04:08 lr: 0.000481 loss: 3.3064 (3.2546) grad_norm: 1.5598 (inf) time: 0.6423 [2021-03-27 09:35:54 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 870/1251] eta: 0:04:02 lr: 0.000481 loss: 2.9530 (3.2535) grad_norm: 1.5598 (inf) time: 0.6378 [2021-03-27 09:36:00 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 880/1251] eta: 0:03:56 lr: 0.000481 loss: 3.1322 (3.2543) grad_norm: 1.4784 (inf) time: 0.6267 [2021-03-27 09:36:06 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 890/1251] eta: 0:03:49 lr: 0.000481 loss: 3.1785 (3.2520) grad_norm: 1.4452 (inf) time: 0.6255 [2021-03-27 09:36:13 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 900/1251] eta: 0:03:43 lr: 0.000481 loss: 2.9318 (3.2487) grad_norm: 1.4876 (inf) time: 0.6266 [2021-03-27 09:36:19 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 910/1251] eta: 0:03:36 lr: 0.000481 loss: 2.9284 (3.2470) grad_norm: 1.4754 (inf) time: 0.6272 [2021-03-27 09:36:25 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 920/1251] eta: 0:03:30 lr: 0.000480 loss: 3.0829 (3.2464) grad_norm: 1.4799 (inf) time: 0.6265 [2021-03-27 09:36:31 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 930/1251] eta: 0:03:24 lr: 0.000480 loss: 3.1763 (3.2459) grad_norm: 1.4799 (inf) time: 0.6242 [2021-03-27 09:36:38 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 940/1251] eta: 0:03:17 lr: 0.000480 loss: 3.4295 (3.2499) grad_norm: 1.4530 (inf) time: 0.6292 [2021-03-27 09:36:44 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 950/1251] eta: 0:03:11 lr: 0.000480 loss: 3.3810 (3.2485) grad_norm: 1.5980 (inf) time: 0.6352 [2021-03-27 09:36:50 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 960/1251] eta: 0:03:05 lr: 0.000480 loss: 3.3581 (3.2501) grad_norm: 1.6557 (inf) time: 0.6306 [2021-03-27 09:36:57 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 970/1251] eta: 0:02:58 lr: 0.000480 loss: 3.3212 (3.2506) grad_norm: 1.5919 (inf) time: 0.6286 [2021-03-27 09:37:03 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 980/1251] eta: 0:02:52 lr: 0.000480 loss: 3.2563 (3.2500) grad_norm: 1.6643 (inf) time: 0.6288 [2021-03-27 09:37:09 swin_base_patch4_window7_224] INFO: Epoch: [154] [ 990/1251] eta: 0:02:45 lr: 0.000480 loss: 3.0923 (3.2467) grad_norm: 1.5543 (inf) time: 0.6361 [2021-03-27 09:37:16 swin_base_patch4_window7_224] INFO: Epoch: [154] [1000/1251] eta: 0:02:39 lr: 0.000480 loss: 3.0469 (3.2477) grad_norm: 1.4467 (inf) time: 0.6408 [2021-03-27 09:37:22 swin_base_patch4_window7_224] INFO: Epoch: [154] [1010/1251] eta: 0:02:33 lr: 0.000480 loss: 3.3811 (3.2470) grad_norm: 1.4449 (inf) time: 0.6354 [2021-03-27 09:37:28 swin_base_patch4_window7_224] INFO: Epoch: [154] [1020/1251] eta: 0:02:26 lr: 0.000480 loss: 3.4047 (3.2493) grad_norm: 1.4168 (inf) time: 0.6322 [2021-03-27 09:37:35 swin_base_patch4_window7_224] INFO: Epoch: [154] [1030/1251] eta: 0:02:20 lr: 0.000480 loss: 3.4047 (3.2490) grad_norm: 1.5286 (inf) time: 0.6278 [2021-03-27 09:37:41 swin_base_patch4_window7_224] INFO: Epoch: [154] [1040/1251] eta: 0:02:14 lr: 0.000480 loss: 3.3757 (3.2512) grad_norm: 1.5328 (inf) time: 0.6342 [2021-03-27 09:37:47 swin_base_patch4_window7_224] INFO: Epoch: [154] [1050/1251] eta: 0:02:07 lr: 0.000480 loss: 3.3757 (3.2507) grad_norm: 1.5240 (inf) time: 0.6355 [2021-03-27 09:37:54 swin_base_patch4_window7_224] INFO: Epoch: [154] [1060/1251] eta: 0:02:01 lr: 0.000480 loss: 3.3920 (3.2531) grad_norm: 1.4483 (inf) time: 0.6274 [2021-03-27 09:38:00 swin_base_patch4_window7_224] INFO: Epoch: [154] [1070/1251] eta: 0:01:55 lr: 0.000480 loss: 3.5262 (3.2534) grad_norm: 1.5089 (inf) time: 0.6259 [2021-03-27 09:38:06 swin_base_patch4_window7_224] INFO: Epoch: [154] [1080/1251] eta: 0:01:48 lr: 0.000480 loss: 3.3105 (3.2526) grad_norm: 1.5755 (inf) time: 0.6274 [2021-03-27 09:38:13 swin_base_patch4_window7_224] INFO: Epoch: [154] [1090/1251] eta: 0:01:42 lr: 0.000480 loss: 3.3105 (3.2529) grad_norm: 1.5431 (inf) time: 0.6280 [2021-03-27 09:38:19 swin_base_patch4_window7_224] INFO: Epoch: [154] [1100/1251] eta: 0:01:35 lr: 0.000480 loss: 3.3474 (3.2529) grad_norm: 1.5336 (inf) time: 0.6305 [2021-03-27 09:38:25 swin_base_patch4_window7_224] INFO: Epoch: [154] [1110/1251] eta: 0:01:29 lr: 0.000480 loss: 3.2119 (3.2530) grad_norm: 1.4414 (inf) time: 0.6309 [2021-03-27 09:38:31 swin_base_patch4_window7_224] INFO: Epoch: [154] [1120/1251] eta: 0:01:23 lr: 0.000480 loss: 3.2481 (3.2530) grad_norm: 1.5023 (inf) time: 0.6276 [2021-03-27 09:38:38 swin_base_patch4_window7_224] INFO: Epoch: [154] [1130/1251] eta: 0:01:16 lr: 0.000480 loss: 3.4261 (3.2534) grad_norm: 1.5746 (inf) time: 0.6272 [2021-03-27 09:38:44 swin_base_patch4_window7_224] INFO: Epoch: [154] [1140/1251] eta: 0:01:10 lr: 0.000480 loss: 3.5478 (3.2560) grad_norm: 1.5104 (inf) time: 0.6307 [2021-03-27 09:38:50 swin_base_patch4_window7_224] INFO: Epoch: [154] [1150/1251] eta: 0:01:04 lr: 0.000480 loss: 3.5056 (3.2574) grad_norm: 1.4767 (inf) time: 0.6352 [2021-03-27 09:38:57 swin_base_patch4_window7_224] INFO: Epoch: [154] [1160/1251] eta: 0:00:57 lr: 0.000479 loss: 3.4195 (3.2577) grad_norm: 1.4575 (inf) time: 0.6369 [2021-03-27 09:39:03 swin_base_patch4_window7_224] INFO: Epoch: [154] [1170/1251] eta: 0:00:51 lr: 0.000479 loss: 3.4753 (3.2607) grad_norm: 1.5126 (inf) time: 0.6325 [2021-03-27 09:39:09 swin_base_patch4_window7_224] INFO: Epoch: [154] [1180/1251] eta: 0:00:45 lr: 0.000479 loss: 3.4804 (3.2607) grad_norm: 1.5060 (inf) time: 0.6288 [2021-03-27 09:39:16 swin_base_patch4_window7_224] INFO: Epoch: [154] [1190/1251] eta: 0:00:38 lr: 0.000479 loss: 3.1700 (3.2596) grad_norm: 1.4956 (inf) time: 0.6325 [2021-03-27 09:39:22 swin_base_patch4_window7_224] INFO: Epoch: [154] [1200/1251] eta: 0:00:32 lr: 0.000479 loss: 3.1700 (3.2598) grad_norm: 1.5000 (inf) time: 0.6297 [2021-03-27 09:39:28 swin_base_patch4_window7_224] INFO: Epoch: [154] [1210/1251] eta: 0:00:26 lr: 0.000479 loss: 3.1606 (3.2568) grad_norm: 1.5671 (inf) time: 0.6280 [2021-03-27 09:39:35 swin_base_patch4_window7_224] INFO: Epoch: [154] [1220/1251] eta: 0:00:19 lr: 0.000479 loss: 3.1606 (3.2563) grad_norm: 1.5460 (inf) time: 0.6313 [2021-03-27 09:39:41 swin_base_patch4_window7_224] INFO: Epoch: [154] [1230/1251] eta: 0:00:13 lr: 0.000479 loss: 3.3549 (3.2571) grad_norm: 1.4768 (inf) time: 0.6297 [2021-03-27 09:39:47 swin_base_patch4_window7_224] INFO: Epoch: [154] [1240/1251] eta: 0:00:06 lr: 0.000479 loss: 3.3963 (3.2591) grad_norm: 1.4685 (inf) time: 0.6248 [2021-03-27 09:39:53 swin_base_patch4_window7_224] INFO: Epoch: [154] [1250/1251] eta: 0:00:00 lr: 0.000479 loss: 3.4742 (3.2611) grad_norm: 1.4627 (inf) time: 0.6158 [2021-03-27 09:40:02 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:41 loss: 0.6717 (0.6717) acc1: 81.2500 (81.2500) acc5: 98.4375 (98.4375) [2021-03-27 09:40:04 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.8617 (0.8166) acc1: 79.6875 (80.3977) acc5: 96.8750 (96.1648) [2021-03-27 09:40:07 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:12 loss: 0.9251 (0.8977) acc1: 78.1250 (78.4226) acc5: 93.7500 (95.1637) [2021-03-27 09:40:09 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0145 (0.9289) acc1: 78.1250 (78.4778) acc5: 93.7500 (94.7077) [2021-03-27 09:40:11 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8463 (0.8908) acc1: 81.2500 (79.3826) acc5: 95.3125 (95.0838) [2021-03-27 09:40:12 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8580 (0.9096) acc1: 78.1250 (78.6560) acc5: 95.3125 (95.1360) [2021-03-27 09:40:22 swin_base_patch4_window7_224] INFO: * Acc@1 79.250 Acc@5 94.982 loss 0.898 [2021-03-27 09:40:22 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.3% [2021-03-27 09:40:22 swin_base_patch4_window7_224] INFO: Max accuracy: 79.25% [2021-03-27 09:40:26 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 0/1251] eta: 1:24:10 lr: 0.000479 loss: 3.1972 (3.1972) grad_norm: 1.3868 (1.3868) time: 4.0368 [2021-03-27 09:40:32 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 10/1251] eta: 0:19:50 lr: 0.000479 loss: 3.1972 (3.2059) grad_norm: 1.5676 (1.6176) time: 0.9591 [2021-03-27 09:40:39 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 20/1251] eta: 0:16:32 lr: 0.000479 loss: 3.2788 (3.2637) grad_norm: 1.5676 (1.5758) time: 0.6444 [2021-03-27 09:40:45 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 30/1251] eta: 0:15:15 lr: 0.000479 loss: 3.2691 (3.2523) grad_norm: 1.4572 (1.5347) time: 0.6348 [2021-03-27 09:40:52 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 40/1251] eta: 0:14:33 lr: 0.000479 loss: 3.4469 (3.2953) grad_norm: 1.4572 (1.5371) time: 0.6332 [2021-03-27 09:40:58 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 50/1251] eta: 0:14:04 lr: 0.000479 loss: 3.5066 (3.3065) grad_norm: 1.5153 (1.5535) time: 0.6300 [2021-03-27 09:41:04 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 60/1251] eta: 0:13:41 lr: 0.000479 loss: 3.3510 (3.3259) grad_norm: 1.5049 (1.5535) time: 0.6243 [2021-03-27 09:41:10 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 70/1251] eta: 0:13:25 lr: 0.000479 loss: 3.3341 (3.2832) grad_norm: 1.5049 (1.5432) time: 0.6280 [2021-03-27 09:41:17 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 80/1251] eta: 0:13:10 lr: 0.000479 loss: 3.1115 (3.2524) grad_norm: 1.5701 (1.5510) time: 0.6302 [2021-03-27 09:41:23 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 90/1251] eta: 0:12:58 lr: 0.000479 loss: 3.1155 (3.2603) grad_norm: 1.5669 (1.5492) time: 0.6295 [2021-03-27 09:41:29 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 100/1251] eta: 0:12:45 lr: 0.000479 loss: 3.1554 (3.2398) grad_norm: 1.5341 (1.5456) time: 0.6261 [2021-03-27 09:41:36 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 110/1251] eta: 0:12:36 lr: 0.000479 loss: 3.3358 (3.2471) grad_norm: 1.4992 (1.5437) time: 0.6285 [2021-03-27 09:41:42 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 120/1251] eta: 0:12:26 lr: 0.000479 loss: 3.3074 (3.2457) grad_norm: 1.4753 (1.5337) time: 0.6326 [2021-03-27 09:41:48 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 130/1251] eta: 0:12:17 lr: 0.000479 loss: 3.3188 (3.2463) grad_norm: 1.3838 (1.5275) time: 0.6310 [2021-03-27 09:41:54 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 140/1251] eta: 0:12:08 lr: 0.000479 loss: 3.3188 (3.2367) grad_norm: 1.3838 (1.5201) time: 0.6303 [2021-03-27 09:42:01 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 150/1251] eta: 0:12:00 lr: 0.000478 loss: 3.3724 (3.2580) grad_norm: 1.4085 (1.5152) time: 0.6289 [2021-03-27 09:42:07 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 160/1251] eta: 0:11:51 lr: 0.000478 loss: 3.3142 (3.2552) grad_norm: 1.4166 (1.5110) time: 0.6286 [2021-03-27 09:42:13 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 170/1251] eta: 0:11:43 lr: 0.000478 loss: 3.3142 (3.2656) grad_norm: 1.4166 (1.5103) time: 0.6265 [2021-03-27 09:42:20 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 180/1251] eta: 0:11:35 lr: 0.000478 loss: 3.3664 (3.2539) grad_norm: 1.5329 (1.5150) time: 0.6293 [2021-03-27 09:42:26 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 190/1251] eta: 0:11:28 lr: 0.000478 loss: 3.4479 (3.2652) grad_norm: 1.5454 (1.5196) time: 0.6317 [2021-03-27 09:42:32 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 200/1251] eta: 0:11:20 lr: 0.000478 loss: 3.4075 (3.2532) grad_norm: 1.5071 (1.5266) time: 0.6250 [2021-03-27 09:42:38 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 210/1251] eta: 0:11:12 lr: 0.000478 loss: 3.0704 (3.2442) grad_norm: 1.4891 (1.5250) time: 0.6233 [2021-03-27 09:42:45 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 220/1251] eta: 0:11:05 lr: 0.000478 loss: 3.0704 (3.2412) grad_norm: 1.4850 (1.5252) time: 0.6307 [2021-03-27 09:42:51 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 230/1251] eta: 0:10:58 lr: 0.000478 loss: 3.0826 (3.2419) grad_norm: 1.4850 (1.5228) time: 0.6281 [2021-03-27 09:42:57 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 240/1251] eta: 0:10:51 lr: 0.000478 loss: 3.0851 (3.2382) grad_norm: 1.4863 (1.5250) time: 0.6230 [2021-03-27 09:43:04 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 250/1251] eta: 0:10:44 lr: 0.000478 loss: 3.4140 (3.2434) grad_norm: 1.5144 (1.5273) time: 0.6292 [2021-03-27 09:43:10 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 260/1251] eta: 0:10:36 lr: 0.000478 loss: 3.4140 (3.2444) grad_norm: 1.5592 (1.5304) time: 0.6281 [2021-03-27 09:43:16 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 270/1251] eta: 0:10:30 lr: 0.000478 loss: 3.4051 (3.2497) grad_norm: 1.6010 (1.5417) time: 0.6311 [2021-03-27 09:43:22 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 280/1251] eta: 0:10:23 lr: 0.000478 loss: 3.4142 (3.2517) grad_norm: 1.6250 (1.5420) time: 0.6351 [2021-03-27 09:43:29 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 290/1251] eta: 0:10:16 lr: 0.000478 loss: 3.4375 (3.2589) grad_norm: 1.5507 (1.5394) time: 0.6317 [2021-03-27 09:43:35 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 300/1251] eta: 0:10:10 lr: 0.000478 loss: 3.5239 (3.2598) grad_norm: 1.5507 (1.5463) time: 0.6329 [2021-03-27 09:43:41 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 310/1251] eta: 0:10:03 lr: 0.000478 loss: 3.3121 (3.2599) grad_norm: 1.5062 (1.5458) time: 0.6351 [2021-03-27 09:43:48 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 320/1251] eta: 0:09:57 lr: 0.000478 loss: 3.3121 (3.2590) grad_norm: 1.5062 (1.5464) time: 0.6403 [2021-03-27 09:43:54 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 330/1251] eta: 0:09:50 lr: 0.000478 loss: 3.2538 (3.2574) grad_norm: 1.5737 (1.5476) time: 0.6348 [2021-03-27 09:44:01 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 340/1251] eta: 0:09:43 lr: 0.000478 loss: 3.3434 (3.2559) grad_norm: 1.4946 (1.5471) time: 0.6316 [2021-03-27 09:44:07 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 350/1251] eta: 0:09:37 lr: 0.000478 loss: 3.3425 (3.2585) grad_norm: 1.4946 (1.5448) time: 0.6338 [2021-03-27 09:44:13 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 360/1251] eta: 0:09:30 lr: 0.000478 loss: 3.1655 (3.2516) grad_norm: 1.4179 (1.5443) time: 0.6376 [2021-03-27 09:44:20 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 370/1251] eta: 0:09:24 lr: 0.000478 loss: 3.2767 (3.2547) grad_norm: 1.5413 (1.5457) time: 0.6407 [2021-03-27 09:44:26 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 380/1251] eta: 0:09:17 lr: 0.000478 loss: 3.3142 (3.2538) grad_norm: 1.4445 (1.5441) time: 0.6357 [2021-03-27 09:44:32 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 390/1251] eta: 0:09:11 lr: 0.000477 loss: 3.3164 (3.2566) grad_norm: 1.4675 (1.5435) time: 0.6331 [2021-03-27 09:44:39 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 400/1251] eta: 0:09:04 lr: 0.000477 loss: 3.0855 (3.2518) grad_norm: 1.4675 (1.5423) time: 0.6362 [2021-03-27 09:44:45 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 410/1251] eta: 0:08:58 lr: 0.000477 loss: 3.0855 (3.2525) grad_norm: 1.4700 (1.5423) time: 0.6297 [2021-03-27 09:44:51 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 420/1251] eta: 0:08:51 lr: 0.000477 loss: 3.2916 (3.2509) grad_norm: 1.4979 (1.5426) time: 0.6241 [2021-03-27 09:44:58 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 430/1251] eta: 0:08:44 lr: 0.000477 loss: 3.2090 (3.2511) grad_norm: 1.4842 (1.5406) time: 0.6311 [2021-03-27 09:45:04 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 440/1251] eta: 0:08:38 lr: 0.000477 loss: 3.4271 (3.2523) grad_norm: 1.4816 (1.5407) time: 0.6357 [2021-03-27 09:45:10 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 450/1251] eta: 0:08:32 lr: 0.000477 loss: 3.3612 (3.2464) grad_norm: 1.4689 (1.5389) time: 0.6372 [2021-03-27 09:45:17 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 460/1251] eta: 0:08:25 lr: 0.000477 loss: 3.2407 (3.2456) grad_norm: 1.4346 (1.5384) time: 0.6359 [2021-03-27 09:45:23 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 470/1251] eta: 0:08:19 lr: 0.000477 loss: 3.3029 (3.2496) grad_norm: 1.5621 (1.5415) time: 0.6336 [2021-03-27 09:45:29 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 480/1251] eta: 0:08:12 lr: 0.000477 loss: 3.1560 (3.2437) grad_norm: 1.5047 (1.5397) time: 0.6277 [2021-03-27 09:45:36 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 490/1251] eta: 0:08:05 lr: 0.000477 loss: 3.3515 (3.2505) grad_norm: 1.5047 (1.5424) time: 0.6278 [2021-03-27 09:45:42 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 500/1251] eta: 0:07:59 lr: 0.000477 loss: 3.5825 (3.2504) grad_norm: 1.5685 (1.5427) time: 0.6368 [2021-03-27 09:45:48 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 510/1251] eta: 0:07:53 lr: 0.000477 loss: 3.1976 (3.2521) grad_norm: 1.4629 (1.5413) time: 0.6387 [2021-03-27 09:45:55 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 520/1251] eta: 0:07:46 lr: 0.000477 loss: 3.2902 (3.2521) grad_norm: 1.4406 (1.5394) time: 0.6391 [2021-03-27 09:46:01 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 530/1251] eta: 0:07:40 lr: 0.000477 loss: 3.1350 (3.2454) grad_norm: 1.5174 (1.5401) time: 0.6381 [2021-03-27 09:46:07 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 540/1251] eta: 0:07:33 lr: 0.000477 loss: 3.4145 (3.2498) grad_norm: 1.5605 (1.5425) time: 0.6354 [2021-03-27 09:46:14 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 550/1251] eta: 0:07:27 lr: 0.000477 loss: 3.4145 (3.2464) grad_norm: 1.4724 (1.5401) time: 0.6419 [2021-03-27 09:46:20 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 560/1251] eta: 0:07:21 lr: 0.000477 loss: 3.0561 (3.2442) grad_norm: 1.4754 (1.5410) time: 0.6399 [2021-03-27 09:46:27 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 570/1251] eta: 0:07:14 lr: 0.000477 loss: 3.1979 (3.2418) grad_norm: 1.5656 (1.5415) time: 0.6337 [2021-03-27 09:46:33 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 580/1251] eta: 0:07:08 lr: 0.000477 loss: 3.2856 (3.2429) grad_norm: 1.5585 (1.5423) time: 0.6358 [2021-03-27 09:46:39 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 590/1251] eta: 0:07:01 lr: 0.000477 loss: 3.3612 (3.2456) grad_norm: 1.5459 (1.5424) time: 0.6309 [2021-03-27 09:46:45 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 600/1251] eta: 0:06:55 lr: 0.000477 loss: 3.4095 (3.2476) grad_norm: 1.4850 (1.5411) time: 0.6263 [2021-03-27 09:46:52 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 610/1251] eta: 0:06:48 lr: 0.000477 loss: 3.3973 (3.2507) grad_norm: 1.4022 (1.5396) time: 0.6265 [2021-03-27 09:46:58 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 620/1251] eta: 0:06:42 lr: 0.000477 loss: 3.2301 (3.2480) grad_norm: 1.4240 (1.5403) time: 0.6339 [2021-03-27 09:47:05 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 630/1251] eta: 0:06:36 lr: 0.000476 loss: 2.9491 (3.2462) grad_norm: 1.5533 (1.5410) time: 0.6434 [2021-03-27 09:47:11 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 640/1251] eta: 0:06:29 lr: 0.000476 loss: 3.1163 (3.2473) grad_norm: 1.4548 (1.5394) time: 0.6422 [2021-03-27 09:47:17 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 650/1251] eta: 0:06:23 lr: 0.000476 loss: 3.4387 (3.2467) grad_norm: 1.4603 (1.5396) time: 0.6351 [2021-03-27 09:47:24 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 660/1251] eta: 0:06:16 lr: 0.000476 loss: 3.2751 (3.2440) grad_norm: 1.4875 (1.5402) time: 0.6269 [2021-03-27 09:47:30 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 670/1251] eta: 0:06:10 lr: 0.000476 loss: 3.4151 (3.2464) grad_norm: 1.4400 (1.5387) time: 0.6240 [2021-03-27 09:47:36 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 680/1251] eta: 0:06:03 lr: 0.000476 loss: 3.6157 (3.2493) grad_norm: 1.4400 (1.5373) time: 0.6292 [2021-03-27 09:47:43 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 690/1251] eta: 0:05:57 lr: 0.000476 loss: 3.3857 (3.2491) grad_norm: 1.4839 (1.5441) time: 0.6374 [2021-03-27 09:47:49 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 700/1251] eta: 0:05:51 lr: 0.000476 loss: 3.3610 (3.2504) grad_norm: 1.5316 (1.5450) time: 0.6414 [2021-03-27 09:47:55 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 710/1251] eta: 0:05:44 lr: 0.000476 loss: 3.3610 (3.2519) grad_norm: 1.5170 (1.5465) time: 0.6370 [2021-03-27 09:48:02 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 720/1251] eta: 0:05:38 lr: 0.000476 loss: 3.5591 (3.2573) grad_norm: 1.4922 (1.5461) time: 0.6352 [2021-03-27 09:48:08 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 730/1251] eta: 0:05:32 lr: 0.000476 loss: 3.7802 (3.2623) grad_norm: 1.5082 (1.5469) time: 0.6317 [2021-03-27 09:48:14 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 740/1251] eta: 0:05:25 lr: 0.000476 loss: 3.6120 (3.2644) grad_norm: 1.4677 (1.5470) time: 0.6354 [2021-03-27 09:48:21 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 750/1251] eta: 0:05:19 lr: 0.000476 loss: 3.3960 (3.2638) grad_norm: 1.4381 (1.5464) time: 0.6372 [2021-03-27 09:48:27 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 760/1251] eta: 0:05:12 lr: 0.000476 loss: 3.3577 (3.2646) grad_norm: 1.4811 (1.5467) time: 0.6352 [2021-03-27 09:48:34 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 770/1251] eta: 0:05:06 lr: 0.000476 loss: 3.2123 (3.2619) grad_norm: 1.5342 (1.5467) time: 0.6402 [2021-03-27 09:48:40 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 780/1251] eta: 0:05:00 lr: 0.000476 loss: 3.3970 (3.2610) grad_norm: 1.4793 (1.5476) time: 0.6396 [2021-03-27 09:48:46 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 790/1251] eta: 0:04:53 lr: 0.000476 loss: 3.5517 (3.2627) grad_norm: 1.4900 (1.5477) time: 0.6326 [2021-03-27 09:48:53 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 800/1251] eta: 0:04:47 lr: 0.000476 loss: 3.4544 (3.2639) grad_norm: 1.4900 (1.5479) time: 0.6299 [2021-03-27 09:48:59 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 810/1251] eta: 0:04:40 lr: 0.000476 loss: 3.3449 (3.2625) grad_norm: 1.4580 (1.5473) time: 0.6324 [2021-03-27 09:49:05 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 820/1251] eta: 0:04:34 lr: 0.000476 loss: 3.4441 (3.2632) grad_norm: 1.4885 (1.5466) time: 0.6309 [2021-03-27 09:49:11 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 830/1251] eta: 0:04:28 lr: 0.000476 loss: 3.4514 (3.2661) grad_norm: 1.5058 (1.5461) time: 0.6329 [2021-03-27 09:49:18 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 840/1251] eta: 0:04:21 lr: 0.000476 loss: 3.4514 (3.2671) grad_norm: 1.5343 (1.5467) time: 0.6320 [2021-03-27 09:49:24 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 850/1251] eta: 0:04:15 lr: 0.000476 loss: 3.3292 (3.2667) grad_norm: 1.4912 (1.5464) time: 0.6269 [2021-03-27 09:49:30 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 860/1251] eta: 0:04:08 lr: 0.000476 loss: 3.2583 (3.2649) grad_norm: 1.4912 (1.5474) time: 0.6294 [2021-03-27 09:49:37 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 870/1251] eta: 0:04:02 lr: 0.000475 loss: 3.2583 (3.2648) grad_norm: 1.5522 (1.5467) time: 0.6332 [2021-03-27 09:49:43 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 880/1251] eta: 0:03:56 lr: 0.000475 loss: 3.2796 (3.2649) grad_norm: 1.4814 (1.5460) time: 0.6345 [2021-03-27 09:49:49 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 890/1251] eta: 0:03:49 lr: 0.000475 loss: 3.4605 (3.2671) grad_norm: 1.5854 (1.5478) time: 0.6324 [2021-03-27 09:49:56 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 900/1251] eta: 0:03:43 lr: 0.000475 loss: 3.5095 (3.2670) grad_norm: 1.4439 (1.5460) time: 0.6273 [2021-03-27 09:50:02 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 910/1251] eta: 0:03:37 lr: 0.000475 loss: 3.2419 (3.2645) grad_norm: 1.4328 (1.5465) time: 0.6290 [2021-03-27 09:50:08 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 920/1251] eta: 0:03:30 lr: 0.000475 loss: 3.1652 (3.2632) grad_norm: 1.5186 (1.5465) time: 0.6343 [2021-03-27 09:50:15 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 930/1251] eta: 0:03:24 lr: 0.000475 loss: 3.1723 (3.2637) grad_norm: 1.5982 (1.5469) time: 0.6342 [2021-03-27 09:50:21 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 940/1251] eta: 0:03:17 lr: 0.000475 loss: 3.3247 (3.2644) grad_norm: 1.6282 (1.5484) time: 0.6272 [2021-03-27 09:50:27 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 950/1251] eta: 0:03:11 lr: 0.000475 loss: 3.2197 (3.2631) grad_norm: 1.6383 (1.5498) time: 0.6242 [2021-03-27 09:50:33 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 960/1251] eta: 0:03:05 lr: 0.000475 loss: 3.2515 (3.2636) grad_norm: 1.5439 (1.5490) time: 0.6256 [2021-03-27 09:50:40 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 970/1251] eta: 0:02:58 lr: 0.000475 loss: 3.4014 (3.2621) grad_norm: 1.5172 (1.5510) time: 0.6301 [2021-03-27 09:50:46 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 980/1251] eta: 0:02:52 lr: 0.000475 loss: 3.3485 (3.2623) grad_norm: 1.6169 (1.5529) time: 0.6258 [2021-03-27 09:50:52 swin_base_patch4_window7_224] INFO: Epoch: [155] [ 990/1251] eta: 0:02:45 lr: 0.000475 loss: 3.4485 (3.2628) grad_norm: 1.5639 (1.5521) time: 0.6236 [2021-03-27 09:50:59 swin_base_patch4_window7_224] INFO: Epoch: [155] [1000/1251] eta: 0:02:39 lr: 0.000475 loss: 3.5480 (3.2653) grad_norm: 1.4334 (1.5517) time: 0.6386 [2021-03-27 09:51:05 swin_base_patch4_window7_224] INFO: Epoch: [155] [1010/1251] eta: 0:02:33 lr: 0.000475 loss: 3.4737 (3.2646) grad_norm: 1.4320 (1.5512) time: 0.6432 [2021-03-27 09:51:11 swin_base_patch4_window7_224] INFO: Epoch: [155] [1020/1251] eta: 0:02:26 lr: 0.000475 loss: 3.2590 (3.2660) grad_norm: 1.5321 (1.5520) time: 0.6374 [2021-03-27 09:51:18 swin_base_patch4_window7_224] INFO: Epoch: [155] [1030/1251] eta: 0:02:20 lr: 0.000475 loss: 3.2905 (3.2680) grad_norm: 1.5985 (1.5531) time: 0.6299 [2021-03-27 09:51:24 swin_base_patch4_window7_224] INFO: Epoch: [155] [1040/1251] eta: 0:02:14 lr: 0.000475 loss: 3.4770 (3.2704) grad_norm: 1.5666 (1.5533) time: 0.6257 [2021-03-27 09:51:30 swin_base_patch4_window7_224] INFO: Epoch: [155] [1050/1251] eta: 0:02:07 lr: 0.000475 loss: 3.4758 (3.2710) grad_norm: 1.5745 (1.5534) time: 0.6302 [2021-03-27 09:51:37 swin_base_patch4_window7_224] INFO: Epoch: [155] [1060/1251] eta: 0:02:01 lr: 0.000475 loss: 3.1665 (3.2695) grad_norm: 1.5070 (1.5534) time: 0.6291 [2021-03-27 09:51:43 swin_base_patch4_window7_224] INFO: Epoch: [155] [1070/1251] eta: 0:01:55 lr: 0.000475 loss: 3.2051 (3.2709) grad_norm: 1.4630 (1.5536) time: 0.6324 [2021-03-27 09:51:49 swin_base_patch4_window7_224] INFO: Epoch: [155] [1080/1251] eta: 0:01:48 lr: 0.000475 loss: 3.2621 (3.2691) grad_norm: 1.5006 (1.5539) time: 0.6307 [2021-03-27 09:51:55 swin_base_patch4_window7_224] INFO: Epoch: [155] [1090/1251] eta: 0:01:42 lr: 0.000475 loss: 3.2621 (3.2696) grad_norm: 1.5190 (1.5532) time: 0.6207 [2021-03-27 09:52:02 swin_base_patch4_window7_224] INFO: Epoch: [155] [1100/1251] eta: 0:01:35 lr: 0.000475 loss: 3.1354 (3.2676) grad_norm: 1.5260 (1.5533) time: 0.6213 [2021-03-27 09:52:08 swin_base_patch4_window7_224] INFO: Epoch: [155] [1110/1251] eta: 0:01:29 lr: 0.000475 loss: 3.1354 (3.2678) grad_norm: 1.6107 (1.5543) time: 0.6280 [2021-03-27 09:52:14 swin_base_patch4_window7_224] INFO: Epoch: [155] [1120/1251] eta: 0:01:23 lr: 0.000474 loss: 3.2265 (3.2657) grad_norm: 1.5029 (1.5538) time: 0.6336 [2021-03-27 09:52:20 swin_base_patch4_window7_224] INFO: Epoch: [155] [1130/1251] eta: 0:01:16 lr: 0.000474 loss: 3.1702 (3.2645) grad_norm: 1.5001 (1.5535) time: 0.6268 [2021-03-27 09:52:27 swin_base_patch4_window7_224] INFO: Epoch: [155] [1140/1251] eta: 0:01:10 lr: 0.000474 loss: 3.2327 (3.2652) grad_norm: 1.5084 (1.5536) time: 0.6224 [2021-03-27 09:52:33 swin_base_patch4_window7_224] INFO: Epoch: [155] [1150/1251] eta: 0:01:04 lr: 0.000474 loss: 3.2500 (3.2638) grad_norm: 1.4795 (1.5530) time: 0.6281 [2021-03-27 09:52:39 swin_base_patch4_window7_224] INFO: Epoch: [155] [1160/1251] eta: 0:00:57 lr: 0.000474 loss: 3.4251 (3.2647) grad_norm: 1.4686 (1.5524) time: 0.6287 [2021-03-27 09:52:46 swin_base_patch4_window7_224] INFO: Epoch: [155] [1170/1251] eta: 0:00:51 lr: 0.000474 loss: 3.4451 (3.2636) grad_norm: 1.4719 (1.5524) time: 0.6296 [2021-03-27 09:52:52 swin_base_patch4_window7_224] INFO: Epoch: [155] [1180/1251] eta: 0:00:45 lr: 0.000474 loss: 3.3983 (3.2634) grad_norm: 1.5579 (1.5525) time: 0.6385 [2021-03-27 09:52:58 swin_base_patch4_window7_224] INFO: Epoch: [155] [1190/1251] eta: 0:00:38 lr: 0.000474 loss: 3.4306 (3.2653) grad_norm: 1.4752 (1.5521) time: 0.6403 [2021-03-27 09:53:05 swin_base_patch4_window7_224] INFO: Epoch: [155] [1200/1251] eta: 0:00:32 lr: 0.000474 loss: 3.3302 (3.2642) grad_norm: 1.4729 (1.5520) time: 0.6321 [2021-03-27 09:53:11 swin_base_patch4_window7_224] INFO: Epoch: [155] [1210/1251] eta: 0:00:26 lr: 0.000474 loss: 2.9627 (3.2617) grad_norm: 1.4718 (1.5512) time: 0.6253 [2021-03-27 09:53:17 swin_base_patch4_window7_224] INFO: Epoch: [155] [1220/1251] eta: 0:00:19 lr: 0.000474 loss: 2.9179 (3.2586) grad_norm: 1.4791 (1.5514) time: 0.6259 [2021-03-27 09:53:24 swin_base_patch4_window7_224] INFO: Epoch: [155] [1230/1251] eta: 0:00:13 lr: 0.000474 loss: 2.9866 (3.2584) grad_norm: 1.5306 (1.5512) time: 0.6338 [2021-03-27 09:53:30 swin_base_patch4_window7_224] INFO: Epoch: [155] [1240/1251] eta: 0:00:06 lr: 0.000474 loss: 3.4366 (3.2593) grad_norm: 1.5306 (1.5511) time: 0.6317 [2021-03-27 09:53:36 swin_base_patch4_window7_224] INFO: Epoch: [155] [1250/1251] eta: 0:00:00 lr: 0.000474 loss: 3.4309 (3.2598) grad_norm: 1.4395 (1.5503) time: 0.6207 [2021-03-27 09:54:47 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:00:59 loss: 1.1736 (1.1736) acc1: 76.5625 (76.5625) acc5: 89.0625 (89.0625) [2021-03-27 09:54:48 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.9397 (0.9584) acc1: 76.5625 (77.8409) acc5: 95.3125 (94.1761) [2021-03-27 09:54:50 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.8622 (0.8905) acc1: 79.6875 (78.7202) acc5: 95.3125 (94.9405) [2021-03-27 09:54:51 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8320 (0.8803) acc1: 79.6875 (78.9819) acc5: 95.3125 (95.1109) [2021-03-27 09:54:52 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9438 (0.8949) acc1: 78.1250 (78.8110) acc5: 93.7500 (94.9695) [2021-03-27 09:54:53 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8979 (0.8865) acc1: 76.5625 (78.6880) acc5: 95.3125 (95.2320) [2021-03-27 09:55:02 swin_base_patch4_window7_224] INFO: * Acc@1 79.172 Acc@5 94.918 loss 0.883 [2021-03-27 09:55:02 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.2% [2021-03-27 09:55:02 swin_base_patch4_window7_224] INFO: Max accuracy: 79.25% [2021-03-27 09:55:06 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 0/1251] eta: 1:27:39 lr: 0.000474 loss: 3.3327 (3.3327) grad_norm: 1.4867 (1.4867) time: 4.2046 [2021-03-27 09:55:13 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 10/1251] eta: 0:20:01 lr: 0.000474 loss: 3.5605 (3.4376) grad_norm: 1.5303 (1.6013) time: 0.9678 [2021-03-27 09:55:19 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 20/1251] eta: 0:16:33 lr: 0.000474 loss: 3.4045 (3.3642) grad_norm: 1.5248 (1.5688) time: 0.6372 [2021-03-27 09:55:26 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 30/1251] eta: 0:15:19 lr: 0.000474 loss: 3.3630 (3.3802) grad_norm: 1.5286 (1.5754) time: 0.6352 [2021-03-27 09:55:32 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 40/1251] eta: 0:14:35 lr: 0.000474 loss: 3.4779 (3.3854) grad_norm: 1.4432 (1.5382) time: 0.6350 [2021-03-27 09:55:38 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 50/1251] eta: 0:14:06 lr: 0.000474 loss: 3.4155 (3.3600) grad_norm: 1.4322 (1.5359) time: 0.6299 [2021-03-27 09:55:44 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 60/1251] eta: 0:13:44 lr: 0.000474 loss: 3.2162 (3.2937) grad_norm: 1.4802 (1.5360) time: 0.6293 [2021-03-27 09:55:51 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 70/1251] eta: 0:13:25 lr: 0.000474 loss: 3.2129 (3.3000) grad_norm: 1.4844 (1.5469) time: 0.6236 [2021-03-27 09:55:57 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 80/1251] eta: 0:13:12 lr: 0.000474 loss: 3.1533 (3.2589) grad_norm: 1.5084 (1.5466) time: 0.6298 [2021-03-27 09:56:03 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 90/1251] eta: 0:13:00 lr: 0.000474 loss: 3.3466 (3.2883) grad_norm: 1.4470 (1.5488) time: 0.6380 [2021-03-27 09:56:10 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 100/1251] eta: 0:12:48 lr: 0.000474 loss: 3.5221 (3.3027) grad_norm: 1.4470 (1.5453) time: 0.6316 [2021-03-27 09:56:16 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 110/1251] eta: 0:12:37 lr: 0.000473 loss: 3.6724 (3.3337) grad_norm: 1.5267 (1.5530) time: 0.6272 [2021-03-27 09:56:22 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 120/1251] eta: 0:12:28 lr: 0.000473 loss: 3.4864 (3.3120) grad_norm: 1.5267 (1.5474) time: 0.6294 [2021-03-27 09:56:29 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 130/1251] eta: 0:12:18 lr: 0.000473 loss: 3.2520 (3.3022) grad_norm: 1.5019 (1.5495) time: 0.6306 [2021-03-27 09:56:35 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 140/1251] eta: 0:12:10 lr: 0.000473 loss: 3.4006 (3.2996) grad_norm: 1.5704 (1.5543) time: 0.6302 [2021-03-27 09:56:41 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 150/1251] eta: 0:12:01 lr: 0.000473 loss: 3.4006 (3.3005) grad_norm: 1.5704 (1.5569) time: 0.6298 [2021-03-27 09:56:47 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 160/1251] eta: 0:11:52 lr: 0.000473 loss: 3.3473 (3.2950) grad_norm: 1.5140 (1.5545) time: 0.6279 [2021-03-27 09:56:54 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 170/1251] eta: 0:11:46 lr: 0.000473 loss: 3.1919 (3.2816) grad_norm: 1.5398 (1.5563) time: 0.6374 [2021-03-27 09:57:00 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 180/1251] eta: 0:11:38 lr: 0.000473 loss: 3.3516 (3.2910) grad_norm: 1.4833 (1.5534) time: 0.6413 [2021-03-27 09:57:07 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 190/1251] eta: 0:11:31 lr: 0.000473 loss: 3.3958 (3.2813) grad_norm: 1.4833 (1.5525) time: 0.6388 [2021-03-27 09:57:13 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 200/1251] eta: 0:11:23 lr: 0.000473 loss: 3.0451 (3.2753) grad_norm: 1.6034 (1.5585) time: 0.6371 [2021-03-27 09:57:19 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 210/1251] eta: 0:11:16 lr: 0.000473 loss: 3.3280 (3.2733) grad_norm: 1.6304 (1.5596) time: 0.6322 [2021-03-27 09:57:26 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 220/1251] eta: 0:11:09 lr: 0.000473 loss: 3.3121 (3.2706) grad_norm: 1.5060 (1.5567) time: 0.6331 [2021-03-27 09:57:32 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 230/1251] eta: 0:11:02 lr: 0.000473 loss: 3.1412 (3.2574) grad_norm: 1.3982 (1.5543) time: 0.6340 [2021-03-27 09:57:38 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 240/1251] eta: 0:10:54 lr: 0.000473 loss: 3.1135 (3.2549) grad_norm: 1.5520 (1.5570) time: 0.6339 [2021-03-27 09:57:45 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 250/1251] eta: 0:10:47 lr: 0.000473 loss: 3.1135 (3.2379) grad_norm: 1.4886 (1.5540) time: 0.6297 [2021-03-27 09:57:51 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 260/1251] eta: 0:10:40 lr: 0.000473 loss: 3.0498 (3.2360) grad_norm: 1.4128 (1.5630) time: 0.6281 [2021-03-27 09:57:57 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 270/1251] eta: 0:10:33 lr: 0.000473 loss: 3.3455 (3.2432) grad_norm: 1.5348 (1.5608) time: 0.6271 [2021-03-27 09:58:04 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 280/1251] eta: 0:10:26 lr: 0.000473 loss: 3.4578 (3.2451) grad_norm: 1.4808 (1.5626) time: 0.6302 [2021-03-27 09:58:10 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 290/1251] eta: 0:10:19 lr: 0.000473 loss: 3.3204 (3.2401) grad_norm: 1.6403 (1.5692) time: 0.6314 [2021-03-27 09:58:16 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 300/1251] eta: 0:10:12 lr: 0.000473 loss: 3.3506 (3.2481) grad_norm: 1.5884 (1.5710) time: 0.6271 [2021-03-27 09:58:22 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 310/1251] eta: 0:10:05 lr: 0.000473 loss: 3.4623 (3.2488) grad_norm: 1.6532 (1.5748) time: 0.6250 [2021-03-27 09:58:29 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 320/1251] eta: 0:09:58 lr: 0.000473 loss: 3.4154 (3.2555) grad_norm: 1.6459 (1.5737) time: 0.6281 [2021-03-27 09:58:35 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 330/1251] eta: 0:09:51 lr: 0.000473 loss: 3.3706 (3.2567) grad_norm: 1.5609 (1.5738) time: 0.6318 [2021-03-27 09:58:41 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 340/1251] eta: 0:09:45 lr: 0.000473 loss: 3.3706 (3.2556) grad_norm: 1.4832 (1.5707) time: 0.6325 [2021-03-27 09:58:48 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 350/1251] eta: 0:09:38 lr: 0.000472 loss: 3.0930 (3.2452) grad_norm: 1.4566 (1.5693) time: 0.6316 [2021-03-27 09:58:54 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 360/1251] eta: 0:09:31 lr: 0.000472 loss: 2.9805 (3.2466) grad_norm: 1.5103 (1.5688) time: 0.6287 [2021-03-27 09:59:00 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 370/1251] eta: 0:09:24 lr: 0.000472 loss: 3.3277 (3.2464) grad_norm: 1.5535 (1.5715) time: 0.6304 [2021-03-27 09:59:06 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 380/1251] eta: 0:09:18 lr: 0.000472 loss: 3.2532 (3.2459) grad_norm: 1.5535 (1.5734) time: 0.6311 [2021-03-27 09:59:13 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 390/1251] eta: 0:09:11 lr: 0.000472 loss: 3.1149 (3.2361) grad_norm: 1.4595 (1.5725) time: 0.6349 [2021-03-27 09:59:19 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 400/1251] eta: 0:09:05 lr: 0.000472 loss: 3.1189 (3.2377) grad_norm: 1.4989 (1.5718) time: 0.6313 [2021-03-27 09:59:25 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 410/1251] eta: 0:08:58 lr: 0.000472 loss: 3.5068 (3.2416) grad_norm: 1.5513 (1.5738) time: 0.6317 [2021-03-27 09:59:32 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 420/1251] eta: 0:08:52 lr: 0.000472 loss: 3.5088 (3.2478) grad_norm: 1.6380 (1.5755) time: 0.6345 [2021-03-27 09:59:38 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 430/1251] eta: 0:08:45 lr: 0.000472 loss: 3.4462 (3.2528) grad_norm: 1.6494 (1.5786) time: 0.6292 [2021-03-27 09:59:44 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 440/1251] eta: 0:08:38 lr: 0.000472 loss: 3.4533 (3.2579) grad_norm: 1.5173 (1.5767) time: 0.6272 [2021-03-27 09:59:51 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 450/1251] eta: 0:08:32 lr: 0.000472 loss: 3.5933 (3.2655) grad_norm: 1.5653 (1.5812) time: 0.6298 [2021-03-27 09:59:57 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 460/1251] eta: 0:08:25 lr: 0.000472 loss: 3.5933 (3.2649) grad_norm: 1.5936 (1.5802) time: 0.6348 [2021-03-27 10:00:03 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 470/1251] eta: 0:08:19 lr: 0.000472 loss: 3.3527 (3.2635) grad_norm: 1.5726 (1.5817) time: 0.6346 [2021-03-27 10:00:10 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 480/1251] eta: 0:08:12 lr: 0.000472 loss: 3.0603 (3.2619) grad_norm: 1.5550 (1.5817) time: 0.6319 [2021-03-27 10:00:16 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 490/1251] eta: 0:08:06 lr: 0.000472 loss: 3.0603 (3.2569) grad_norm: 1.5246 (1.5815) time: 0.6316 [2021-03-27 10:00:22 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 500/1251] eta: 0:07:59 lr: 0.000472 loss: 3.1965 (3.2515) grad_norm: 1.5246 (1.5823) time: 0.6306 [2021-03-27 10:00:29 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 510/1251] eta: 0:07:53 lr: 0.000472 loss: 3.0734 (3.2486) grad_norm: 1.4678 (1.5795) time: 0.6248 [2021-03-27 10:00:35 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 520/1251] eta: 0:07:46 lr: 0.000472 loss: 3.2287 (3.2509) grad_norm: 1.4456 (1.5783) time: 0.6302 [2021-03-27 10:00:41 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 530/1251] eta: 0:07:40 lr: 0.000472 loss: 3.2396 (3.2481) grad_norm: 1.4907 (1.5781) time: 0.6362 [2021-03-27 10:00:47 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 540/1251] eta: 0:07:33 lr: 0.000472 loss: 3.1512 (3.2467) grad_norm: 1.5175 (1.5784) time: 0.6296 [2021-03-27 10:00:54 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 550/1251] eta: 0:07:27 lr: 0.000472 loss: 3.2595 (3.2493) grad_norm: 1.4958 (1.5765) time: 0.6383 [2021-03-27 10:01:00 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 560/1251] eta: 0:07:21 lr: 0.000472 loss: 3.4381 (3.2484) grad_norm: 1.5454 (1.5796) time: 0.6448 [2021-03-27 10:01:07 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 570/1251] eta: 0:07:14 lr: 0.000472 loss: 3.2855 (3.2472) grad_norm: 1.6464 (inf) time: 0.6292 [2021-03-27 10:01:13 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 580/1251] eta: 0:07:08 lr: 0.000472 loss: 3.3810 (3.2509) grad_norm: 1.4825 (inf) time: 0.6294 [2021-03-27 10:01:19 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 590/1251] eta: 0:07:01 lr: 0.000471 loss: 3.5158 (3.2519) grad_norm: 1.5075 (inf) time: 0.6391 [2021-03-27 10:01:26 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 600/1251] eta: 0:06:55 lr: 0.000471 loss: 3.2929 (3.2526) grad_norm: 1.5075 (inf) time: 0.6360 [2021-03-27 10:01:32 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 610/1251] eta: 0:06:48 lr: 0.000471 loss: 3.2156 (3.2519) grad_norm: 1.4408 (inf) time: 0.6355 [2021-03-27 10:01:38 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 620/1251] eta: 0:06:42 lr: 0.000471 loss: 3.2045 (3.2494) grad_norm: 1.4555 (inf) time: 0.6347 [2021-03-27 10:01:45 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 630/1251] eta: 0:06:36 lr: 0.000471 loss: 3.2247 (3.2502) grad_norm: 1.4517 (inf) time: 0.6352 [2021-03-27 10:01:51 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 640/1251] eta: 0:06:29 lr: 0.000471 loss: 2.8153 (3.2454) grad_norm: 1.5300 (inf) time: 0.6338 [2021-03-27 10:01:57 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 650/1251] eta: 0:06:23 lr: 0.000471 loss: 3.2101 (3.2490) grad_norm: 1.5300 (inf) time: 0.6339 [2021-03-27 10:02:04 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 660/1251] eta: 0:06:16 lr: 0.000471 loss: 3.2836 (3.2482) grad_norm: 1.5432 (inf) time: 0.6377 [2021-03-27 10:02:10 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 670/1251] eta: 0:06:10 lr: 0.000471 loss: 3.1983 (3.2489) grad_norm: 1.5531 (inf) time: 0.6343 [2021-03-27 10:02:16 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 680/1251] eta: 0:06:04 lr: 0.000471 loss: 3.2381 (3.2481) grad_norm: 1.5868 (inf) time: 0.6291 [2021-03-27 10:02:23 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 690/1251] eta: 0:05:57 lr: 0.000471 loss: 3.2837 (3.2524) grad_norm: 1.5166 (inf) time: 0.6231 [2021-03-27 10:02:29 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 700/1251] eta: 0:05:51 lr: 0.000471 loss: 3.2837 (3.2524) grad_norm: 1.5098 (inf) time: 0.6299 [2021-03-27 10:02:35 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 710/1251] eta: 0:05:44 lr: 0.000471 loss: 3.2071 (3.2529) grad_norm: 1.5785 (inf) time: 0.6338 [2021-03-27 10:02:42 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 720/1251] eta: 0:05:38 lr: 0.000471 loss: 3.2282 (3.2524) grad_norm: 1.6182 (inf) time: 0.6329 [2021-03-27 10:02:48 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 730/1251] eta: 0:05:31 lr: 0.000471 loss: 3.2872 (3.2525) grad_norm: 1.6358 (inf) time: 0.6333 [2021-03-27 10:02:54 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 740/1251] eta: 0:05:25 lr: 0.000471 loss: 3.3967 (3.2528) grad_norm: 1.5502 (inf) time: 0.6348 [2021-03-27 10:03:01 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 750/1251] eta: 0:05:19 lr: 0.000471 loss: 3.3718 (3.2545) grad_norm: 1.5407 (inf) time: 0.6402 [2021-03-27 10:03:07 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 760/1251] eta: 0:05:12 lr: 0.000471 loss: 3.3994 (3.2567) grad_norm: 1.4833 (inf) time: 0.6398 [2021-03-27 10:03:13 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 770/1251] eta: 0:05:06 lr: 0.000471 loss: 3.1451 (3.2525) grad_norm: 1.5164 (inf) time: 0.6337 [2021-03-27 10:03:20 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 780/1251] eta: 0:05:00 lr: 0.000471 loss: 2.7900 (3.2520) grad_norm: 1.6418 (inf) time: 0.6296 [2021-03-27 10:03:26 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 790/1251] eta: 0:04:53 lr: 0.000471 loss: 3.1772 (3.2524) grad_norm: 1.5158 (inf) time: 0.6312 [2021-03-27 10:03:33 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 800/1251] eta: 0:04:47 lr: 0.000471 loss: 3.3838 (3.2532) grad_norm: 1.4806 (inf) time: 0.6357 [2021-03-27 10:03:39 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 810/1251] eta: 0:04:40 lr: 0.000471 loss: 3.2999 (3.2536) grad_norm: 1.5772 (inf) time: 0.6409 [2021-03-27 10:03:45 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 820/1251] eta: 0:04:34 lr: 0.000471 loss: 3.2320 (3.2526) grad_norm: 1.5584 (inf) time: 0.6319 [2021-03-27 10:03:51 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 830/1251] eta: 0:04:28 lr: 0.000470 loss: 3.3169 (3.2556) grad_norm: 1.4285 (inf) time: 0.6266 [2021-03-27 10:03:58 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 840/1251] eta: 0:04:21 lr: 0.000470 loss: 3.5050 (3.2573) grad_norm: 1.4917 (inf) time: 0.6313 [2021-03-27 10:04:04 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 850/1251] eta: 0:04:15 lr: 0.000470 loss: 3.5861 (3.2617) grad_norm: 1.5615 (inf) time: 0.6280 [2021-03-27 10:04:10 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 860/1251] eta: 0:04:08 lr: 0.000470 loss: 3.5951 (3.2640) grad_norm: 1.5460 (inf) time: 0.6287 [2021-03-27 10:04:17 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 870/1251] eta: 0:04:02 lr: 0.000470 loss: 3.3598 (3.2637) grad_norm: 1.5942 (inf) time: 0.6288 [2021-03-27 10:04:23 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 880/1251] eta: 0:03:56 lr: 0.000470 loss: 3.2207 (3.2637) grad_norm: 1.7020 (inf) time: 0.6241 [2021-03-27 10:04:29 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 890/1251] eta: 0:03:49 lr: 0.000470 loss: 3.2207 (3.2626) grad_norm: 1.4940 (inf) time: 0.6271 [2021-03-27 10:04:36 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 900/1251] eta: 0:03:43 lr: 0.000470 loss: 3.2840 (3.2637) grad_norm: 1.4955 (inf) time: 0.6338 [2021-03-27 10:04:42 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 910/1251] eta: 0:03:36 lr: 0.000470 loss: 3.4170 (3.2660) grad_norm: 1.5372 (inf) time: 0.6392 [2021-03-27 10:04:48 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 920/1251] eta: 0:03:30 lr: 0.000470 loss: 3.4529 (3.2683) grad_norm: 1.5716 (inf) time: 0.6337 [2021-03-27 10:04:54 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 930/1251] eta: 0:03:24 lr: 0.000470 loss: 3.4368 (3.2701) grad_norm: 1.5424 (inf) time: 0.6264 [2021-03-27 10:05:01 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 940/1251] eta: 0:03:17 lr: 0.000470 loss: 3.3395 (3.2686) grad_norm: 1.5350 (inf) time: 0.6286 [2021-03-27 10:05:07 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 950/1251] eta: 0:03:11 lr: 0.000470 loss: 3.1798 (3.2689) grad_norm: 1.5512 (inf) time: 0.6315 [2021-03-27 10:05:13 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 960/1251] eta: 0:03:05 lr: 0.000470 loss: 3.4959 (3.2687) grad_norm: 1.5902 (inf) time: 0.6323 [2021-03-27 10:05:20 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 970/1251] eta: 0:02:58 lr: 0.000470 loss: 3.3341 (3.2680) grad_norm: 1.6032 (inf) time: 0.6359 [2021-03-27 10:05:26 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 980/1251] eta: 0:02:52 lr: 0.000470 loss: 3.2335 (3.2650) grad_norm: 1.5324 (inf) time: 0.6373 [2021-03-27 10:05:33 swin_base_patch4_window7_224] INFO: Epoch: [156] [ 990/1251] eta: 0:02:45 lr: 0.000470 loss: 3.3097 (3.2657) grad_norm: 1.6951 (inf) time: 0.6346 [2021-03-27 10:05:39 swin_base_patch4_window7_224] INFO: Epoch: [156] [1000/1251] eta: 0:02:39 lr: 0.000470 loss: 3.3097 (3.2658) grad_norm: 1.7045 (inf) time: 0.6344 [2021-03-27 10:05:45 swin_base_patch4_window7_224] INFO: Epoch: [156] [1010/1251] eta: 0:02:33 lr: 0.000470 loss: 3.3141 (3.2649) grad_norm: 1.5718 (inf) time: 0.6345 [2021-03-27 10:05:52 swin_base_patch4_window7_224] INFO: Epoch: [156] [1020/1251] eta: 0:02:26 lr: 0.000470 loss: 3.3492 (3.2648) grad_norm: 1.5230 (inf) time: 0.6323 [2021-03-27 10:05:58 swin_base_patch4_window7_224] INFO: Epoch: [156] [1030/1251] eta: 0:02:20 lr: 0.000470 loss: 3.3492 (3.2652) grad_norm: 1.5661 (inf) time: 0.6263 [2021-03-27 10:06:04 swin_base_patch4_window7_224] INFO: Epoch: [156] [1040/1251] eta: 0:02:14 lr: 0.000470 loss: 3.3473 (3.2657) grad_norm: 1.5661 (inf) time: 0.6260 [2021-03-27 10:06:10 swin_base_patch4_window7_224] INFO: Epoch: [156] [1050/1251] eta: 0:02:07 lr: 0.000470 loss: 3.2803 (3.2657) grad_norm: 1.5025 (inf) time: 0.6313 [2021-03-27 10:06:17 swin_base_patch4_window7_224] INFO: Epoch: [156] [1060/1251] eta: 0:02:01 lr: 0.000470 loss: 3.2961 (3.2669) grad_norm: 1.5760 (inf) time: 0.6276 [2021-03-27 10:06:23 swin_base_patch4_window7_224] INFO: Epoch: [156] [1070/1251] eta: 0:01:55 lr: 0.000469 loss: 3.3047 (3.2679) grad_norm: 1.6796 (inf) time: 0.6252 [2021-03-27 10:06:29 swin_base_patch4_window7_224] INFO: Epoch: [156] [1080/1251] eta: 0:01:48 lr: 0.000469 loss: 3.2659 (3.2670) grad_norm: 1.5785 (inf) time: 0.6285 [2021-03-27 10:06:35 swin_base_patch4_window7_224] INFO: Epoch: [156] [1090/1251] eta: 0:01:42 lr: 0.000469 loss: 3.2659 (3.2656) grad_norm: 1.5730 (inf) time: 0.6288 [2021-03-27 10:06:42 swin_base_patch4_window7_224] INFO: Epoch: [156] [1100/1251] eta: 0:01:35 lr: 0.000469 loss: 3.4409 (3.2663) grad_norm: 1.5715 (inf) time: 0.6310 [2021-03-27 10:06:48 swin_base_patch4_window7_224] INFO: Epoch: [156] [1110/1251] eta: 0:01:29 lr: 0.000469 loss: 3.4357 (3.2656) grad_norm: 1.5698 (inf) time: 0.6328 [2021-03-27 10:06:54 swin_base_patch4_window7_224] INFO: Epoch: [156] [1120/1251] eta: 0:01:23 lr: 0.000469 loss: 2.7449 (3.2613) grad_norm: 1.5917 (inf) time: 0.6312 [2021-03-27 10:07:01 swin_base_patch4_window7_224] INFO: Epoch: [156] [1130/1251] eta: 0:01:16 lr: 0.000469 loss: 3.2544 (3.2609) grad_norm: 1.5419 (inf) time: 0.6275 [2021-03-27 10:07:07 swin_base_patch4_window7_224] INFO: Epoch: [156] [1140/1251] eta: 0:01:10 lr: 0.000469 loss: 3.3098 (3.2610) grad_norm: 1.5483 (inf) time: 0.6232 [2021-03-27 10:07:13 swin_base_patch4_window7_224] INFO: Epoch: [156] [1150/1251] eta: 0:01:04 lr: 0.000469 loss: 3.4163 (3.2608) grad_norm: 1.5554 (inf) time: 0.6247 [2021-03-27 10:07:19 swin_base_patch4_window7_224] INFO: Epoch: [156] [1160/1251] eta: 0:00:57 lr: 0.000469 loss: 3.3916 (3.2619) grad_norm: 1.5399 (inf) time: 0.6250 [2021-03-27 10:07:26 swin_base_patch4_window7_224] INFO: Epoch: [156] [1170/1251] eta: 0:00:51 lr: 0.000469 loss: 3.3674 (3.2618) grad_norm: 1.5640 (inf) time: 0.6267 [2021-03-27 10:07:32 swin_base_patch4_window7_224] INFO: Epoch: [156] [1180/1251] eta: 0:00:45 lr: 0.000469 loss: 3.3525 (3.2617) grad_norm: 1.5780 (inf) time: 0.6312 [2021-03-27 10:07:38 swin_base_patch4_window7_224] INFO: Epoch: [156] [1190/1251] eta: 0:00:38 lr: 0.000469 loss: 3.3791 (3.2615) grad_norm: 1.4351 (inf) time: 0.6269 [2021-03-27 10:07:45 swin_base_patch4_window7_224] INFO: Epoch: [156] [1200/1251] eta: 0:00:32 lr: 0.000469 loss: 3.4915 (3.2628) grad_norm: 1.4417 (inf) time: 0.6259 [2021-03-27 10:07:51 swin_base_patch4_window7_224] INFO: Epoch: [156] [1210/1251] eta: 0:00:26 lr: 0.000469 loss: 3.2652 (3.2626) grad_norm: 1.6023 (inf) time: 0.6258 [2021-03-27 10:07:57 swin_base_patch4_window7_224] INFO: Epoch: [156] [1220/1251] eta: 0:00:19 lr: 0.000469 loss: 3.3984 (3.2643) grad_norm: 1.6067 (inf) time: 0.6226 [2021-03-27 10:08:03 swin_base_patch4_window7_224] INFO: Epoch: [156] [1230/1251] eta: 0:00:13 lr: 0.000469 loss: 3.3766 (3.2646) grad_norm: 1.5595 (inf) time: 0.6291 [2021-03-27 10:08:10 swin_base_patch4_window7_224] INFO: Epoch: [156] [1240/1251] eta: 0:00:06 lr: 0.000469 loss: 3.3736 (3.2652) grad_norm: 1.5308 (inf) time: 0.6347 [2021-03-27 10:08:16 swin_base_patch4_window7_224] INFO: Epoch: [156] [1250/1251] eta: 0:00:00 lr: 0.000469 loss: 3.4650 (3.2655) grad_norm: 1.5479 (inf) time: 0.6272 [2021-03-27 10:08:27 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:56 loss: 0.9879 (0.9879) acc1: 76.5625 (76.5625) acc5: 93.7500 (93.7500) [2021-03-27 10:08:29 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8942 (0.8982) acc1: 79.6875 (79.8295) acc5: 95.3125 (95.3125) [2021-03-27 10:08:32 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8251 (0.8569) acc1: 79.6875 (79.7619) acc5: 96.8750 (95.8333) [2021-03-27 10:08:35 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8430 (0.8739) acc1: 79.6875 (79.1331) acc5: 96.8750 (95.7661) [2021-03-27 10:08:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9114 (0.9121) acc1: 76.5625 (78.3537) acc5: 93.7500 (94.7790) [2021-03-27 10:08:37 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8711 (0.8954) acc1: 79.6875 (78.6880) acc5: 95.3125 (95.0400) [2021-03-27 10:08:46 swin_base_patch4_window7_224] INFO: * Acc@1 79.450 Acc@5 95.048 loss 0.870 [2021-03-27 10:08:46 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.5% [2021-03-27 10:08:46 swin_base_patch4_window7_224] INFO: Max accuracy: 79.45% [2021-03-27 10:08:51 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 0/1251] eta: 1:31:23 lr: 0.000469 loss: 2.2023 (2.2023) grad_norm: 1.9981 (1.9981) time: 4.3836 [2021-03-27 10:08:57 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 10/1251] eta: 0:20:23 lr: 0.000469 loss: 3.3193 (3.2029) grad_norm: 1.5697 (1.5980) time: 0.9857 [2021-03-27 10:09:04 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 20/1251] eta: 0:16:46 lr: 0.000469 loss: 3.5108 (3.3340) grad_norm: 1.5370 (1.5638) time: 0.6391 [2021-03-27 10:09:10 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 30/1251] eta: 0:15:29 lr: 0.000469 loss: 3.5108 (3.2942) grad_norm: 1.6055 (1.5917) time: 0.6373 [2021-03-27 10:09:17 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 40/1251] eta: 0:14:49 lr: 0.000469 loss: 3.4227 (3.3030) grad_norm: 1.6485 (1.5998) time: 0.6468 [2021-03-27 10:09:23 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 50/1251] eta: 0:14:21 lr: 0.000469 loss: 3.4678 (3.3237) grad_norm: 1.5836 (1.5985) time: 0.6507 [2021-03-27 10:09:29 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 60/1251] eta: 0:13:56 lr: 0.000468 loss: 3.4694 (3.3568) grad_norm: 1.5322 (1.5957) time: 0.6377 [2021-03-27 10:09:36 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 70/1251] eta: 0:13:37 lr: 0.000468 loss: 3.3396 (3.3286) grad_norm: 1.5322 (1.6015) time: 0.6277 [2021-03-27 10:09:42 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 80/1251] eta: 0:13:22 lr: 0.000468 loss: 3.3322 (3.3391) grad_norm: 1.4498 (1.5888) time: 0.6329 [2021-03-27 10:09:48 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 90/1251] eta: 0:13:09 lr: 0.000468 loss: 3.4500 (3.3313) grad_norm: 1.4191 (1.5752) time: 0.6380 [2021-03-27 10:09:55 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 100/1251] eta: 0:12:57 lr: 0.000468 loss: 3.2925 (3.3062) grad_norm: 1.4555 (1.5770) time: 0.6374 [2021-03-27 10:10:01 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 110/1251] eta: 0:12:47 lr: 0.000468 loss: 3.2777 (3.2969) grad_norm: 1.5154 (1.5696) time: 0.6384 [2021-03-27 10:10:07 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 120/1251] eta: 0:12:37 lr: 0.000468 loss: 3.2923 (3.2899) grad_norm: 1.4899 (1.5668) time: 0.6388 [2021-03-27 10:10:14 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 130/1251] eta: 0:12:27 lr: 0.000468 loss: 3.0769 (3.2899) grad_norm: 1.5406 (1.5652) time: 0.6326 [2021-03-27 10:10:20 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 140/1251] eta: 0:12:17 lr: 0.000468 loss: 3.0989 (3.2824) grad_norm: 1.6055 (1.5696) time: 0.6286 [2021-03-27 10:10:26 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 150/1251] eta: 0:12:09 lr: 0.000468 loss: 3.2552 (3.2812) grad_norm: 1.5475 (1.5681) time: 0.6329 [2021-03-27 10:10:33 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 160/1251] eta: 0:12:00 lr: 0.000468 loss: 3.1839 (3.2671) grad_norm: 1.4884 (1.5653) time: 0.6341 [2021-03-27 10:10:39 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 170/1251] eta: 0:11:51 lr: 0.000468 loss: 3.2473 (3.2713) grad_norm: 1.5597 (1.5708) time: 0.6261 [2021-03-27 10:10:45 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 180/1251] eta: 0:11:43 lr: 0.000468 loss: 3.4783 (3.2700) grad_norm: 1.5816 (1.5721) time: 0.6280 [2021-03-27 10:10:52 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 190/1251] eta: 0:11:35 lr: 0.000468 loss: 3.4390 (3.2647) grad_norm: 1.5503 (1.5717) time: 0.6306 [2021-03-27 10:10:58 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 200/1251] eta: 0:11:27 lr: 0.000468 loss: 3.5097 (3.2753) grad_norm: 1.5478 (1.5714) time: 0.6268 [2021-03-27 10:11:04 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 210/1251] eta: 0:11:19 lr: 0.000468 loss: 3.3995 (3.2764) grad_norm: 1.5160 (1.5712) time: 0.6298 [2021-03-27 10:11:10 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 220/1251] eta: 0:11:11 lr: 0.000468 loss: 3.5469 (3.2882) grad_norm: 1.5188 (1.5738) time: 0.6322 [2021-03-27 10:11:17 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 230/1251] eta: 0:11:04 lr: 0.000468 loss: 3.5469 (3.2824) grad_norm: 1.5669 (1.5723) time: 0.6313 [2021-03-27 10:11:23 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 240/1251] eta: 0:10:57 lr: 0.000468 loss: 3.3172 (3.2895) grad_norm: 1.4907 (1.5720) time: 0.6310 [2021-03-27 10:11:30 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 250/1251] eta: 0:10:50 lr: 0.000468 loss: 3.3746 (3.2956) grad_norm: 1.5057 (1.5780) time: 0.6359 [2021-03-27 10:11:36 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 260/1251] eta: 0:10:43 lr: 0.000468 loss: 3.3504 (3.2905) grad_norm: 1.6847 (1.5849) time: 0.6374 [2021-03-27 10:11:42 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 270/1251] eta: 0:10:35 lr: 0.000468 loss: 3.3504 (3.2887) grad_norm: 1.6364 (1.5832) time: 0.6298 [2021-03-27 10:11:48 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 280/1251] eta: 0:10:28 lr: 0.000468 loss: 3.2388 (3.2890) grad_norm: 1.5776 (1.5862) time: 0.6294 [2021-03-27 10:11:55 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 290/1251] eta: 0:10:21 lr: 0.000468 loss: 3.2494 (3.2876) grad_norm: 1.6315 (1.5890) time: 0.6339 [2021-03-27 10:12:01 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 300/1251] eta: 0:10:15 lr: 0.000468 loss: 3.1511 (3.2789) grad_norm: 1.5903 (1.5917) time: 0.6337 [2021-03-27 10:12:07 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 310/1251] eta: 0:10:08 lr: 0.000467 loss: 3.1193 (3.2741) grad_norm: 1.6357 (1.5928) time: 0.6317 [2021-03-27 10:12:14 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 320/1251] eta: 0:10:01 lr: 0.000467 loss: 3.4498 (3.2776) grad_norm: 1.5243 (1.5899) time: 0.6335 [2021-03-27 10:12:20 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 330/1251] eta: 0:09:54 lr: 0.000467 loss: 3.2234 (3.2748) grad_norm: 1.5243 (1.5934) time: 0.6346 [2021-03-27 10:12:26 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 340/1251] eta: 0:09:47 lr: 0.000467 loss: 3.2766 (3.2743) grad_norm: 1.7815 (1.5984) time: 0.6330 [2021-03-27 10:12:33 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 350/1251] eta: 0:09:40 lr: 0.000467 loss: 3.4732 (3.2777) grad_norm: 1.7087 (1.5981) time: 0.6312 [2021-03-27 10:12:39 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 360/1251] eta: 0:09:34 lr: 0.000467 loss: 3.3740 (3.2787) grad_norm: 1.5096 (1.5963) time: 0.6366 [2021-03-27 10:12:45 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 370/1251] eta: 0:09:27 lr: 0.000467 loss: 3.0499 (3.2710) grad_norm: 1.4878 (inf) time: 0.6347 [2021-03-27 10:12:52 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 380/1251] eta: 0:09:20 lr: 0.000467 loss: 3.3719 (3.2756) grad_norm: 1.5536 (inf) time: 0.6269 [2021-03-27 10:12:58 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 390/1251] eta: 0:09:13 lr: 0.000467 loss: 3.5360 (3.2802) grad_norm: 1.5392 (inf) time: 0.6299 [2021-03-27 10:13:04 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 400/1251] eta: 0:09:07 lr: 0.000467 loss: 3.5360 (3.2825) grad_norm: 1.4745 (inf) time: 0.6277 [2021-03-27 10:13:11 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 410/1251] eta: 0:09:00 lr: 0.000467 loss: 3.2565 (3.2782) grad_norm: 1.4745 (inf) time: 0.6275 [2021-03-27 10:13:17 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 420/1251] eta: 0:08:53 lr: 0.000467 loss: 3.5703 (3.2856) grad_norm: 1.4659 (inf) time: 0.6330 [2021-03-27 10:13:23 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 430/1251] eta: 0:08:47 lr: 0.000467 loss: 3.4845 (3.2840) grad_norm: 1.4659 (inf) time: 0.6386 [2021-03-27 10:13:30 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 440/1251] eta: 0:08:40 lr: 0.000467 loss: 3.0888 (3.2755) grad_norm: 1.6512 (inf) time: 0.6402 [2021-03-27 10:13:36 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 450/1251] eta: 0:08:34 lr: 0.000467 loss: 2.9330 (3.2696) grad_norm: 1.6964 (inf) time: 0.6354 [2021-03-27 10:13:42 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 460/1251] eta: 0:08:27 lr: 0.000467 loss: 3.0889 (3.2727) grad_norm: 1.7044 (inf) time: 0.6277 [2021-03-27 10:13:49 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 470/1251] eta: 0:08:20 lr: 0.000467 loss: 3.3366 (3.2740) grad_norm: 1.7548 (inf) time: 0.6242 [2021-03-27 10:13:55 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 480/1251] eta: 0:08:14 lr: 0.000467 loss: 3.3366 (3.2726) grad_norm: 1.7311 (inf) time: 0.6252 [2021-03-27 10:14:01 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 490/1251] eta: 0:08:07 lr: 0.000467 loss: 3.4419 (3.2721) grad_norm: 1.7273 (inf) time: 0.6240 [2021-03-27 10:14:07 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 500/1251] eta: 0:08:00 lr: 0.000467 loss: 3.2767 (3.2701) grad_norm: 1.6826 (inf) time: 0.6242 [2021-03-27 10:14:14 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 510/1251] eta: 0:07:54 lr: 0.000467 loss: 3.2342 (3.2694) grad_norm: 1.6109 (inf) time: 0.6222 [2021-03-27 10:14:20 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 520/1251] eta: 0:07:47 lr: 0.000467 loss: 3.4231 (3.2720) grad_norm: 1.5017 (inf) time: 0.6243 [2021-03-27 10:14:26 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 530/1251] eta: 0:07:41 lr: 0.000467 loss: 3.3270 (3.2689) grad_norm: 1.4583 (inf) time: 0.6310 [2021-03-27 10:14:32 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 540/1251] eta: 0:07:34 lr: 0.000467 loss: 3.0107 (3.2651) grad_norm: 1.4922 (inf) time: 0.6333 [2021-03-27 10:14:39 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 550/1251] eta: 0:07:28 lr: 0.000466 loss: 3.1819 (3.2674) grad_norm: 1.6178 (inf) time: 0.6439 [2021-03-27 10:14:45 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 560/1251] eta: 0:07:22 lr: 0.000466 loss: 3.4158 (3.2696) grad_norm: 1.6041 (inf) time: 0.6448 [2021-03-27 10:14:52 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 570/1251] eta: 0:07:15 lr: 0.000466 loss: 3.4417 (3.2712) grad_norm: 1.5999 (inf) time: 0.6382 [2021-03-27 10:14:58 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 580/1251] eta: 0:07:09 lr: 0.000466 loss: 3.3605 (3.2696) grad_norm: 1.4792 (inf) time: 0.6361 [2021-03-27 10:15:04 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 590/1251] eta: 0:07:02 lr: 0.000466 loss: 3.1390 (3.2679) grad_norm: 1.4532 (inf) time: 0.6275 [2021-03-27 10:15:11 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 600/1251] eta: 0:06:56 lr: 0.000466 loss: 3.3185 (3.2693) grad_norm: 1.4532 (inf) time: 0.6271 [2021-03-27 10:15:17 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 610/1251] eta: 0:06:49 lr: 0.000466 loss: 3.3981 (3.2697) grad_norm: 1.4384 (inf) time: 0.6353 [2021-03-27 10:15:23 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 620/1251] eta: 0:06:43 lr: 0.000466 loss: 3.3436 (3.2670) grad_norm: 1.5416 (inf) time: 0.6404 [2021-03-27 10:15:30 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 630/1251] eta: 0:06:36 lr: 0.000466 loss: 3.3979 (3.2714) grad_norm: 1.5771 (inf) time: 0.6358 [2021-03-27 10:15:36 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 640/1251] eta: 0:06:30 lr: 0.000466 loss: 3.4326 (3.2685) grad_norm: 1.5122 (inf) time: 0.6315 [2021-03-27 10:15:42 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 650/1251] eta: 0:06:23 lr: 0.000466 loss: 3.1402 (3.2674) grad_norm: 1.4596 (inf) time: 0.6339 [2021-03-27 10:15:49 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 660/1251] eta: 0:06:17 lr: 0.000466 loss: 3.3405 (3.2694) grad_norm: 1.4715 (inf) time: 0.6350 [2021-03-27 10:15:55 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 670/1251] eta: 0:06:11 lr: 0.000466 loss: 3.3879 (3.2678) grad_norm: 1.4909 (inf) time: 0.6315 [2021-03-27 10:16:01 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 680/1251] eta: 0:06:04 lr: 0.000466 loss: 3.3012 (3.2702) grad_norm: 1.5555 (inf) time: 0.6283 [2021-03-27 10:16:08 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 690/1251] eta: 0:05:58 lr: 0.000466 loss: 3.5086 (3.2748) grad_norm: 1.5931 (inf) time: 0.6297 [2021-03-27 10:16:14 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 700/1251] eta: 0:05:51 lr: 0.000466 loss: 3.4581 (3.2730) grad_norm: 1.5219 (inf) time: 0.6312 [2021-03-27 10:16:20 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 710/1251] eta: 0:05:45 lr: 0.000466 loss: 3.1390 (3.2682) grad_norm: 1.4418 (inf) time: 0.6265 [2021-03-27 10:16:27 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 720/1251] eta: 0:05:38 lr: 0.000466 loss: 3.2882 (3.2703) grad_norm: 1.4418 (inf) time: 0.6271 [2021-03-27 10:16:33 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 730/1251] eta: 0:05:32 lr: 0.000466 loss: 3.4485 (3.2700) grad_norm: 1.4533 (inf) time: 0.6330 [2021-03-27 10:16:39 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 740/1251] eta: 0:05:26 lr: 0.000466 loss: 3.2526 (3.2715) grad_norm: 1.5530 (inf) time: 0.6378 [2021-03-27 10:16:46 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 750/1251] eta: 0:05:19 lr: 0.000466 loss: 3.2526 (3.2713) grad_norm: 1.5406 (inf) time: 0.6397 [2021-03-27 10:16:52 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 760/1251] eta: 0:05:13 lr: 0.000466 loss: 3.5020 (3.2725) grad_norm: 1.5135 (inf) time: 0.6347 [2021-03-27 10:16:58 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 770/1251] eta: 0:05:06 lr: 0.000466 loss: 3.3866 (3.2731) grad_norm: 1.5535 (inf) time: 0.6287 [2021-03-27 10:17:05 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 780/1251] eta: 0:05:00 lr: 0.000466 loss: 3.3866 (3.2749) grad_norm: 1.5558 (inf) time: 0.6347 [2021-03-27 10:17:11 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 790/1251] eta: 0:04:53 lr: 0.000465 loss: 3.1863 (3.2695) grad_norm: 1.5271 (inf) time: 0.6326 [2021-03-27 10:17:17 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 800/1251] eta: 0:04:47 lr: 0.000465 loss: 3.0110 (3.2664) grad_norm: 1.4988 (inf) time: 0.6323 [2021-03-27 10:17:24 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 810/1251] eta: 0:04:41 lr: 0.000465 loss: 3.1785 (3.2660) grad_norm: 1.4699 (inf) time: 0.6411 [2021-03-27 10:17:30 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 820/1251] eta: 0:04:34 lr: 0.000465 loss: 3.4397 (3.2683) grad_norm: 1.4561 (inf) time: 0.6353 [2021-03-27 10:17:37 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 830/1251] eta: 0:04:28 lr: 0.000465 loss: 3.4397 (3.2683) grad_norm: 1.4794 (inf) time: 0.6393 [2021-03-27 10:17:43 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 840/1251] eta: 0:04:22 lr: 0.000465 loss: 3.3105 (3.2680) grad_norm: 1.4794 (inf) time: 0.6361 [2021-03-27 10:17:49 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 850/1251] eta: 0:04:15 lr: 0.000465 loss: 3.5857 (3.2705) grad_norm: 1.5343 (inf) time: 0.6245 [2021-03-27 10:17:55 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 860/1251] eta: 0:04:09 lr: 0.000465 loss: 3.4512 (3.2686) grad_norm: 1.5478 (inf) time: 0.6240 [2021-03-27 10:18:02 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 870/1251] eta: 0:04:02 lr: 0.000465 loss: 3.3184 (3.2704) grad_norm: 1.5266 (inf) time: 0.6296 [2021-03-27 10:18:08 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 880/1251] eta: 0:03:56 lr: 0.000465 loss: 3.5114 (3.2728) grad_norm: 1.5221 (inf) time: 0.6328 [2021-03-27 10:18:14 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 890/1251] eta: 0:03:49 lr: 0.000465 loss: 3.2357 (3.2722) grad_norm: 1.5353 (inf) time: 0.6281 [2021-03-27 10:18:20 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 900/1251] eta: 0:03:43 lr: 0.000465 loss: 3.3044 (3.2745) grad_norm: 1.3940 (inf) time: 0.6274 [2021-03-27 10:18:27 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 910/1251] eta: 0:03:37 lr: 0.000465 loss: 3.4832 (3.2753) grad_norm: 1.4204 (inf) time: 0.6282 [2021-03-27 10:18:33 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 920/1251] eta: 0:03:30 lr: 0.000465 loss: 3.4832 (3.2767) grad_norm: 1.5594 (inf) time: 0.6315 [2021-03-27 10:18:39 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 930/1251] eta: 0:03:24 lr: 0.000465 loss: 3.3520 (3.2738) grad_norm: 1.5594 (inf) time: 0.6296 [2021-03-27 10:18:46 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 940/1251] eta: 0:03:17 lr: 0.000465 loss: 3.2996 (3.2742) grad_norm: 1.5927 (inf) time: 0.6273 [2021-03-27 10:18:52 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 950/1251] eta: 0:03:11 lr: 0.000465 loss: 3.2996 (3.2747) grad_norm: 1.5156 (inf) time: 0.6343 [2021-03-27 10:18:58 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 960/1251] eta: 0:03:05 lr: 0.000465 loss: 3.2737 (3.2730) grad_norm: 1.4972 (inf) time: 0.6355 [2021-03-27 10:19:05 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 970/1251] eta: 0:02:58 lr: 0.000465 loss: 3.0503 (3.2693) grad_norm: 1.5369 (inf) time: 0.6310 [2021-03-27 10:19:11 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 980/1251] eta: 0:02:52 lr: 0.000465 loss: 3.0503 (3.2680) grad_norm: 1.4522 (inf) time: 0.6334 [2021-03-27 10:19:17 swin_base_patch4_window7_224] INFO: Epoch: [157] [ 990/1251] eta: 0:02:46 lr: 0.000465 loss: 3.2683 (3.2664) grad_norm: 1.5324 (inf) time: 0.6301 [2021-03-27 10:19:24 swin_base_patch4_window7_224] INFO: Epoch: [157] [1000/1251] eta: 0:02:39 lr: 0.000465 loss: 3.3313 (3.2678) grad_norm: 1.5345 (inf) time: 0.6247 [2021-03-27 10:19:30 swin_base_patch4_window7_224] INFO: Epoch: [157] [1010/1251] eta: 0:02:33 lr: 0.000465 loss: 3.4845 (3.2681) grad_norm: 1.6523 (inf) time: 0.6269 [2021-03-27 10:19:36 swin_base_patch4_window7_224] INFO: Epoch: [157] [1020/1251] eta: 0:02:26 lr: 0.000465 loss: 3.4845 (3.2672) grad_norm: 1.5883 (inf) time: 0.6310 [2021-03-27 10:19:42 swin_base_patch4_window7_224] INFO: Epoch: [157] [1030/1251] eta: 0:02:20 lr: 0.000464 loss: 3.3184 (3.2659) grad_norm: 1.5615 (inf) time: 0.6313 [2021-03-27 10:19:49 swin_base_patch4_window7_224] INFO: Epoch: [157] [1040/1251] eta: 0:02:14 lr: 0.000464 loss: 3.3312 (3.2658) grad_norm: 1.5338 (inf) time: 0.6260 [2021-03-27 10:19:55 swin_base_patch4_window7_224] INFO: Epoch: [157] [1050/1251] eta: 0:02:07 lr: 0.000464 loss: 3.3168 (3.2660) grad_norm: 1.5338 (inf) time: 0.6328 [2021-03-27 10:20:01 swin_base_patch4_window7_224] INFO: Epoch: [157] [1060/1251] eta: 0:02:01 lr: 0.000464 loss: 3.2782 (3.2643) grad_norm: 1.5277 (inf) time: 0.6380 [2021-03-27 10:20:08 swin_base_patch4_window7_224] INFO: Epoch: [157] [1070/1251] eta: 0:01:55 lr: 0.000464 loss: 3.2804 (3.2640) grad_norm: 1.5727 (inf) time: 0.6380 [2021-03-27 10:20:14 swin_base_patch4_window7_224] INFO: Epoch: [157] [1080/1251] eta: 0:01:48 lr: 0.000464 loss: 3.2804 (3.2620) grad_norm: 1.6126 (inf) time: 0.6307 [2021-03-27 10:20:20 swin_base_patch4_window7_224] INFO: Epoch: [157] [1090/1251] eta: 0:01:42 lr: 0.000464 loss: 3.0330 (3.2605) grad_norm: 1.5962 (inf) time: 0.6273 [2021-03-27 10:20:27 swin_base_patch4_window7_224] INFO: Epoch: [157] [1100/1251] eta: 0:01:36 lr: 0.000464 loss: 3.1349 (3.2602) grad_norm: 1.5733 (inf) time: 0.6301 [2021-03-27 10:20:33 swin_base_patch4_window7_224] INFO: Epoch: [157] [1110/1251] eta: 0:01:29 lr: 0.000464 loss: 3.1349 (3.2587) grad_norm: 1.6340 (inf) time: 0.6275 [2021-03-27 10:20:39 swin_base_patch4_window7_224] INFO: Epoch: [157] [1120/1251] eta: 0:01:23 lr: 0.000464 loss: 3.1867 (3.2589) grad_norm: 1.7093 (inf) time: 0.6254 [2021-03-27 10:20:45 swin_base_patch4_window7_224] INFO: Epoch: [157] [1130/1251] eta: 0:01:16 lr: 0.000464 loss: 3.3366 (3.2603) grad_norm: 1.5909 (inf) time: 0.6255 [2021-03-27 10:20:52 swin_base_patch4_window7_224] INFO: Epoch: [157] [1140/1251] eta: 0:01:10 lr: 0.000464 loss: 3.6597 (3.2628) grad_norm: 1.5010 (inf) time: 0.6262 [2021-03-27 10:20:58 swin_base_patch4_window7_224] INFO: Epoch: [157] [1150/1251] eta: 0:01:04 lr: 0.000464 loss: 3.3855 (3.2621) grad_norm: 1.5635 (inf) time: 0.6252 [2021-03-27 10:21:04 swin_base_patch4_window7_224] INFO: Epoch: [157] [1160/1251] eta: 0:00:57 lr: 0.000464 loss: 3.2325 (3.2619) grad_norm: 1.5635 (inf) time: 0.6336 [2021-03-27 10:21:11 swin_base_patch4_window7_224] INFO: Epoch: [157] [1170/1251] eta: 0:00:51 lr: 0.000464 loss: 3.2867 (3.2620) grad_norm: 1.6701 (inf) time: 0.6362 [2021-03-27 10:21:17 swin_base_patch4_window7_224] INFO: Epoch: [157] [1180/1251] eta: 0:00:45 lr: 0.000464 loss: 3.4299 (3.2622) grad_norm: 1.5746 (inf) time: 0.6314 [2021-03-27 10:21:23 swin_base_patch4_window7_224] INFO: Epoch: [157] [1190/1251] eta: 0:00:38 lr: 0.000464 loss: 3.2267 (3.2614) grad_norm: 1.4831 (inf) time: 0.6300 [2021-03-27 10:21:30 swin_base_patch4_window7_224] INFO: Epoch: [157] [1200/1251] eta: 0:00:32 lr: 0.000464 loss: 3.3278 (3.2622) grad_norm: 1.5063 (inf) time: 0.6276 [2021-03-27 10:21:36 swin_base_patch4_window7_224] INFO: Epoch: [157] [1210/1251] eta: 0:00:26 lr: 0.000464 loss: 3.4828 (3.2631) grad_norm: 1.5063 (inf) time: 0.6274 [2021-03-27 10:21:42 swin_base_patch4_window7_224] INFO: Epoch: [157] [1220/1251] eta: 0:00:19 lr: 0.000464 loss: 3.4828 (3.2636) grad_norm: 1.4996 (inf) time: 0.6300 [2021-03-27 10:21:48 swin_base_patch4_window7_224] INFO: Epoch: [157] [1230/1251] eta: 0:00:13 lr: 0.000464 loss: 3.2380 (3.2617) grad_norm: 1.5035 (inf) time: 0.6312 [2021-03-27 10:21:55 swin_base_patch4_window7_224] INFO: Epoch: [157] [1240/1251] eta: 0:00:06 lr: 0.000464 loss: 3.1555 (3.2597) grad_norm: 1.4668 (inf) time: 0.6278 [2021-03-27 10:22:01 swin_base_patch4_window7_224] INFO: Epoch: [157] [1250/1251] eta: 0:00:00 lr: 0.000464 loss: 3.1051 (3.2594) grad_norm: 1.4695 (inf) time: 0.6220 [2021-03-27 10:22:09 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:49 loss: 0.6766 (0.6766) acc1: 84.3750 (84.3750) acc5: 95.3125 (95.3125) [2021-03-27 10:22:12 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.9752 (0.9295) acc1: 76.5625 (77.5568) acc5: 95.3125 (95.1705) [2021-03-27 10:22:14 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9752 (0.9400) acc1: 75.0000 (77.6042) acc5: 95.3125 (95.0893) [2021-03-27 10:22:16 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8558 (0.8985) acc1: 79.6875 (78.4274) acc5: 96.8750 (95.5645) [2021-03-27 10:22:17 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8108 (0.9139) acc1: 79.6875 (78.2774) acc5: 96.8750 (95.3125) [2021-03-27 10:22:19 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8162 (0.9091) acc1: 79.6875 (78.4960) acc5: 95.3125 (95.3600) [2021-03-27 10:22:27 swin_base_patch4_window7_224] INFO: * Acc@1 79.162 Acc@5 94.902 loss 0.903 [2021-03-27 10:22:27 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.2% [2021-03-27 10:22:27 swin_base_patch4_window7_224] INFO: Max accuracy: 79.45% [2021-03-27 10:22:31 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 0/1251] eta: 1:28:20 lr: 0.000464 loss: 2.3865 (2.3865) grad_norm: 1.4626 (1.4626) time: 4.2371 [2021-03-27 10:22:38 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 10/1251] eta: 0:20:08 lr: 0.000464 loss: 3.3956 (3.2808) grad_norm: 1.5564 (1.6138) time: 0.9736 [2021-03-27 10:22:44 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 20/1251] eta: 0:16:33 lr: 0.000463 loss: 3.1509 (3.1492) grad_norm: 1.5767 (1.5709) time: 0.6353 [2021-03-27 10:22:50 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 30/1251] eta: 0:15:13 lr: 0.000463 loss: 3.1593 (3.1854) grad_norm: 1.5390 (1.5603) time: 0.6242 [2021-03-27 10:22:57 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 40/1251] eta: 0:14:31 lr: 0.000463 loss: 3.3089 (3.2099) grad_norm: 1.4732 (1.5518) time: 0.6277 [2021-03-27 10:23:03 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 50/1251] eta: 0:14:01 lr: 0.000463 loss: 3.2862 (3.2251) grad_norm: 1.4707 (1.5405) time: 0.6276 [2021-03-27 10:23:09 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 60/1251] eta: 0:13:40 lr: 0.000463 loss: 3.4082 (3.2596) grad_norm: 1.5122 (1.5308) time: 0.6262 [2021-03-27 10:23:15 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 70/1251] eta: 0:13:22 lr: 0.000463 loss: 3.4448 (3.2642) grad_norm: 1.5245 (1.5353) time: 0.6249 [2021-03-27 10:23:22 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 80/1251] eta: 0:13:08 lr: 0.000463 loss: 3.4983 (3.2894) grad_norm: 1.5167 (1.5334) time: 0.6250 [2021-03-27 10:23:28 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 90/1251] eta: 0:12:56 lr: 0.000463 loss: 3.4983 (3.2785) grad_norm: 1.4981 (1.5240) time: 0.6298 [2021-03-27 10:23:34 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 100/1251] eta: 0:12:45 lr: 0.000463 loss: 3.5244 (3.2880) grad_norm: 1.5175 (1.5386) time: 0.6304 [2021-03-27 10:23:41 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 110/1251] eta: 0:12:34 lr: 0.000463 loss: 3.5029 (3.3012) grad_norm: 1.5536 (1.5406) time: 0.6277 [2021-03-27 10:23:47 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 120/1251] eta: 0:12:25 lr: 0.000463 loss: 3.1201 (3.2705) grad_norm: 1.5885 (1.5493) time: 0.6309 [2021-03-27 10:23:53 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 130/1251] eta: 0:12:17 lr: 0.000463 loss: 3.1411 (3.2748) grad_norm: 1.5885 (1.5499) time: 0.6373 [2021-03-27 10:24:00 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 140/1251] eta: 0:12:08 lr: 0.000463 loss: 3.4766 (3.2751) grad_norm: 1.4103 (1.5498) time: 0.6380 [2021-03-27 10:24:06 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 150/1251] eta: 0:12:00 lr: 0.000463 loss: 3.4766 (3.2819) grad_norm: 1.4411 (1.5601) time: 0.6364 [2021-03-27 10:24:12 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 160/1251] eta: 0:11:53 lr: 0.000463 loss: 3.5053 (3.2882) grad_norm: 1.5481 (1.5948) time: 0.6377 [2021-03-27 10:24:19 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 170/1251] eta: 0:11:45 lr: 0.000463 loss: 3.3347 (3.2864) grad_norm: 1.5363 (1.5904) time: 0.6372 [2021-03-27 10:24:25 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 180/1251] eta: 0:11:38 lr: 0.000463 loss: 3.1804 (3.2720) grad_norm: 1.5467 (1.5921) time: 0.6356 [2021-03-27 10:24:31 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 190/1251] eta: 0:11:30 lr: 0.000463 loss: 3.2609 (3.2847) grad_norm: 1.5789 (1.5907) time: 0.6308 [2021-03-27 10:24:38 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 200/1251] eta: 0:11:22 lr: 0.000463 loss: 3.3599 (3.2754) grad_norm: 1.4963 (1.5870) time: 0.6250 [2021-03-27 10:24:44 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 210/1251] eta: 0:11:14 lr: 0.000463 loss: 3.4693 (3.2845) grad_norm: 1.4666 (1.5836) time: 0.6233 [2021-03-27 10:24:50 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 220/1251] eta: 0:11:06 lr: 0.000463 loss: 3.4693 (3.2787) grad_norm: 1.4855 (1.5833) time: 0.6231 [2021-03-27 10:24:57 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 230/1251] eta: 0:11:00 lr: 0.000463 loss: 2.9975 (3.2667) grad_norm: 1.5426 (1.5828) time: 0.6325 [2021-03-27 10:25:03 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 240/1251] eta: 0:10:52 lr: 0.000463 loss: 2.9975 (3.2614) grad_norm: 1.5078 (1.5830) time: 0.6348 [2021-03-27 10:25:09 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 250/1251] eta: 0:10:45 lr: 0.000463 loss: 3.3246 (3.2668) grad_norm: 1.5548 (1.5821) time: 0.6278 [2021-03-27 10:25:15 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 260/1251] eta: 0:10:38 lr: 0.000463 loss: 3.3436 (3.2648) grad_norm: 1.5262 (1.5787) time: 0.6256 [2021-03-27 10:25:22 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 270/1251] eta: 0:10:31 lr: 0.000462 loss: 3.3436 (3.2655) grad_norm: 1.5429 (1.5837) time: 0.6301 [2021-03-27 10:25:28 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 280/1251] eta: 0:10:24 lr: 0.000462 loss: 3.3633 (3.2612) grad_norm: 1.6042 (1.5962) time: 0.6346 [2021-03-27 10:25:34 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 290/1251] eta: 0:10:17 lr: 0.000462 loss: 3.1726 (3.2554) grad_norm: 1.5937 (1.5966) time: 0.6290 [2021-03-27 10:25:41 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 300/1251] eta: 0:10:11 lr: 0.000462 loss: 3.0377 (3.2513) grad_norm: 1.4843 (1.5912) time: 0.6300 [2021-03-27 10:25:47 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 310/1251] eta: 0:10:04 lr: 0.000462 loss: 3.2835 (3.2529) grad_norm: 1.4281 (1.5885) time: 0.6335 [2021-03-27 10:25:53 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 320/1251] eta: 0:09:57 lr: 0.000462 loss: 3.2835 (3.2472) grad_norm: 1.4482 (1.5882) time: 0.6309 [2021-03-27 10:26:00 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 330/1251] eta: 0:09:50 lr: 0.000462 loss: 3.3672 (3.2498) grad_norm: 1.5024 (1.5881) time: 0.6269 [2021-03-27 10:26:06 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 340/1251] eta: 0:09:43 lr: 0.000462 loss: 3.3672 (3.2541) grad_norm: 1.6161 (1.5891) time: 0.6230 [2021-03-27 10:26:12 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 350/1251] eta: 0:09:37 lr: 0.000462 loss: 3.3912 (3.2553) grad_norm: 1.5958 (1.5879) time: 0.6293 [2021-03-27 10:26:18 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 360/1251] eta: 0:09:30 lr: 0.000462 loss: 3.3495 (3.2575) grad_norm: 1.5606 (1.5908) time: 0.6320 [2021-03-27 10:26:25 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 370/1251] eta: 0:09:23 lr: 0.000462 loss: 3.3473 (3.2586) grad_norm: 1.5894 (1.5894) time: 0.6294 [2021-03-27 10:26:31 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 380/1251] eta: 0:09:17 lr: 0.000462 loss: 3.1501 (3.2477) grad_norm: 1.5466 (1.5888) time: 0.6296 [2021-03-27 10:26:37 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 390/1251] eta: 0:09:10 lr: 0.000462 loss: 3.1656 (3.2526) grad_norm: 1.6335 (1.5915) time: 0.6326 [2021-03-27 10:26:44 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 400/1251] eta: 0:09:04 lr: 0.000462 loss: 3.4127 (3.2550) grad_norm: 1.6690 (1.5926) time: 0.6309 [2021-03-27 10:26:50 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 410/1251] eta: 0:08:57 lr: 0.000462 loss: 3.3505 (3.2519) grad_norm: 1.5188 (1.6003) time: 0.6261 [2021-03-27 10:26:56 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 420/1251] eta: 0:08:50 lr: 0.000462 loss: 3.2845 (3.2480) grad_norm: 1.5861 (1.6021) time: 0.6279 [2021-03-27 10:27:02 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 430/1251] eta: 0:08:44 lr: 0.000462 loss: 3.1357 (3.2484) grad_norm: 1.5974 (1.6036) time: 0.6264 [2021-03-27 10:27:09 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 440/1251] eta: 0:08:37 lr: 0.000462 loss: 3.1357 (3.2485) grad_norm: 1.5844 (1.6023) time: 0.6276 [2021-03-27 10:27:15 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 450/1251] eta: 0:08:31 lr: 0.000462 loss: 3.2960 (3.2479) grad_norm: 1.5479 (1.6018) time: 0.6291 [2021-03-27 10:27:21 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 460/1251] eta: 0:08:24 lr: 0.000462 loss: 3.3377 (3.2513) grad_norm: 1.4605 (1.5987) time: 0.6332 [2021-03-27 10:27:28 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 470/1251] eta: 0:08:18 lr: 0.000462 loss: 3.3703 (3.2491) grad_norm: 1.4272 (1.5979) time: 0.6371 [2021-03-27 10:27:34 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 480/1251] eta: 0:08:11 lr: 0.000462 loss: 3.4341 (3.2556) grad_norm: 1.5750 (1.5997) time: 0.6354 [2021-03-27 10:27:40 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 490/1251] eta: 0:08:05 lr: 0.000462 loss: 3.4341 (3.2553) grad_norm: 1.6426 (1.6006) time: 0.6283 [2021-03-27 10:27:47 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 500/1251] eta: 0:07:58 lr: 0.000462 loss: 3.3193 (3.2560) grad_norm: 1.5086 (1.6000) time: 0.6244 [2021-03-27 10:27:53 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 510/1251] eta: 0:07:52 lr: 0.000461 loss: 3.2674 (3.2518) grad_norm: 1.4795 (1.5989) time: 0.6289 [2021-03-27 10:27:59 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 520/1251] eta: 0:07:45 lr: 0.000461 loss: 3.1107 (3.2487) grad_norm: 1.5108 (1.5978) time: 0.6279 [2021-03-27 10:28:05 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 530/1251] eta: 0:07:39 lr: 0.000461 loss: 3.3477 (3.2524) grad_norm: 1.5215 (1.5993) time: 0.6252 [2021-03-27 10:28:12 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 540/1251] eta: 0:07:32 lr: 0.000461 loss: 3.4280 (3.2519) grad_norm: 1.6107 (1.5992) time: 0.6321 [2021-03-27 10:28:18 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 550/1251] eta: 0:07:26 lr: 0.000461 loss: 3.3903 (3.2565) grad_norm: 1.6009 (1.5983) time: 0.6486 [2021-03-27 10:28:25 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 560/1251] eta: 0:07:20 lr: 0.000461 loss: 3.3903 (3.2554) grad_norm: 1.4971 (1.5970) time: 0.6425 [2021-03-27 10:28:31 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 570/1251] eta: 0:07:13 lr: 0.000461 loss: 3.3878 (3.2597) grad_norm: 1.4891 (1.5957) time: 0.6289 [2021-03-27 10:28:37 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 580/1251] eta: 0:07:07 lr: 0.000461 loss: 3.5114 (3.2642) grad_norm: 1.5520 (1.5989) time: 0.6315 [2021-03-27 10:28:44 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 590/1251] eta: 0:07:00 lr: 0.000461 loss: 3.3854 (3.2649) grad_norm: 1.6543 (1.5988) time: 0.6340 [2021-03-27 10:28:50 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 600/1251] eta: 0:06:54 lr: 0.000461 loss: 3.3854 (3.2686) grad_norm: 1.5919 (1.5992) time: 0.6338 [2021-03-27 10:28:56 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 610/1251] eta: 0:06:48 lr: 0.000461 loss: 3.5117 (3.2709) grad_norm: 1.5979 (1.6000) time: 0.6291 [2021-03-27 10:29:02 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 620/1251] eta: 0:06:41 lr: 0.000461 loss: 3.2222 (3.2719) grad_norm: 1.5878 (1.6004) time: 0.6273 [2021-03-27 10:29:09 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 630/1251] eta: 0:06:35 lr: 0.000461 loss: 3.2338 (3.2741) grad_norm: 1.5878 (1.5989) time: 0.6298 [2021-03-27 10:29:15 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 640/1251] eta: 0:06:28 lr: 0.000461 loss: 3.4318 (3.2770) grad_norm: 1.5929 (1.5991) time: 0.6269 [2021-03-27 10:29:21 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 650/1251] eta: 0:06:22 lr: 0.000461 loss: 3.4318 (3.2820) grad_norm: 1.4944 (1.5966) time: 0.6239 [2021-03-27 10:29:28 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 660/1251] eta: 0:06:15 lr: 0.000461 loss: 3.5151 (3.2811) grad_norm: 1.4846 (1.5953) time: 0.6274 [2021-03-27 10:29:34 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 670/1251] eta: 0:06:09 lr: 0.000461 loss: 3.2470 (3.2797) grad_norm: 1.5184 (1.5952) time: 0.6285 [2021-03-27 10:29:40 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 680/1251] eta: 0:06:02 lr: 0.000461 loss: 3.1286 (3.2788) grad_norm: 1.4879 (1.5939) time: 0.6245 [2021-03-27 10:29:46 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 690/1251] eta: 0:05:56 lr: 0.000461 loss: 3.3920 (3.2813) grad_norm: 1.5273 (1.5954) time: 0.6266 [2021-03-27 10:29:53 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 700/1251] eta: 0:05:50 lr: 0.000461 loss: 3.2191 (3.2776) grad_norm: 1.6632 (1.5960) time: 0.6270 [2021-03-27 10:29:59 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 710/1251] eta: 0:05:43 lr: 0.000461 loss: 3.1923 (3.2766) grad_norm: 1.6474 (1.5962) time: 0.6239 [2021-03-27 10:30:05 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 720/1251] eta: 0:05:37 lr: 0.000461 loss: 3.3657 (3.2738) grad_norm: 1.4872 (1.5950) time: 0.6296 [2021-03-27 10:30:12 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 730/1251] eta: 0:05:30 lr: 0.000461 loss: 3.3029 (3.2739) grad_norm: 1.5526 (1.5956) time: 0.6347 [2021-03-27 10:30:18 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 740/1251] eta: 0:05:24 lr: 0.000461 loss: 3.2282 (3.2726) grad_norm: 1.5867 (1.5954) time: 0.6421 [2021-03-27 10:30:24 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 750/1251] eta: 0:05:18 lr: 0.000460 loss: 3.0771 (3.2687) grad_norm: 1.4978 (1.5950) time: 0.6399 [2021-03-27 10:30:31 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 760/1251] eta: 0:05:11 lr: 0.000460 loss: 3.1351 (3.2678) grad_norm: 1.4978 (1.5936) time: 0.6325 [2021-03-27 10:30:37 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 770/1251] eta: 0:05:05 lr: 0.000460 loss: 3.2539 (3.2681) grad_norm: 1.5360 (1.5937) time: 0.6324 [2021-03-27 10:30:43 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 780/1251] eta: 0:04:59 lr: 0.000460 loss: 3.2612 (3.2701) grad_norm: 1.5404 (1.5937) time: 0.6364 [2021-03-27 10:30:50 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 790/1251] eta: 0:04:52 lr: 0.000460 loss: 3.4918 (3.2713) grad_norm: 1.5404 (1.5943) time: 0.6367 [2021-03-27 10:30:56 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 800/1251] eta: 0:04:46 lr: 0.000460 loss: 3.3812 (3.2711) grad_norm: 1.5532 (1.5935) time: 0.6297 [2021-03-27 10:31:02 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 810/1251] eta: 0:04:40 lr: 0.000460 loss: 3.1723 (3.2669) grad_norm: 1.5532 (1.5938) time: 0.6243 [2021-03-27 10:31:09 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 820/1251] eta: 0:04:33 lr: 0.000460 loss: 3.3227 (3.2706) grad_norm: 1.5846 (1.5972) time: 0.6263 [2021-03-27 10:31:15 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 830/1251] eta: 0:04:27 lr: 0.000460 loss: 3.4998 (3.2714) grad_norm: 1.6090 (1.5973) time: 0.6314 [2021-03-27 10:31:21 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 840/1251] eta: 0:04:20 lr: 0.000460 loss: 3.4998 (3.2729) grad_norm: 1.5015 (1.5962) time: 0.6308 [2021-03-27 10:31:28 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 850/1251] eta: 0:04:14 lr: 0.000460 loss: 3.5743 (3.2735) grad_norm: 1.5791 (1.5979) time: 0.6345 [2021-03-27 10:31:34 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 860/1251] eta: 0:04:08 lr: 0.000460 loss: 3.4881 (3.2734) grad_norm: 1.6136 (1.5975) time: 0.6313 [2021-03-27 10:31:40 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 870/1251] eta: 0:04:01 lr: 0.000460 loss: 3.4881 (3.2752) grad_norm: 1.4594 (1.5972) time: 0.6302 [2021-03-27 10:31:46 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 880/1251] eta: 0:03:55 lr: 0.000460 loss: 3.3646 (3.2739) grad_norm: 1.5029 (1.5979) time: 0.6288 [2021-03-27 10:31:53 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 890/1251] eta: 0:03:49 lr: 0.000460 loss: 3.2600 (3.2728) grad_norm: 1.5087 (1.5965) time: 0.6312 [2021-03-27 10:31:59 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 900/1251] eta: 0:03:42 lr: 0.000460 loss: 3.2821 (3.2739) grad_norm: 1.5234 (1.5969) time: 0.6306 [2021-03-27 10:32:05 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 910/1251] eta: 0:03:36 lr: 0.000460 loss: 3.3969 (3.2739) grad_norm: 1.5715 (1.5982) time: 0.6265 [2021-03-27 10:32:12 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 920/1251] eta: 0:03:30 lr: 0.000460 loss: 3.3969 (3.2735) grad_norm: 1.6121 (1.5990) time: 0.6345 [2021-03-27 10:32:18 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 930/1251] eta: 0:03:23 lr: 0.000460 loss: 3.3327 (3.2730) grad_norm: 1.6229 (1.5996) time: 0.6324 [2021-03-27 10:32:24 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 940/1251] eta: 0:03:17 lr: 0.000460 loss: 3.2581 (3.2740) grad_norm: 1.6090 (1.5993) time: 0.6279 [2021-03-27 10:32:31 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 950/1251] eta: 0:03:10 lr: 0.000460 loss: 3.3945 (3.2735) grad_norm: 1.4992 (1.5984) time: 0.6256 [2021-03-27 10:32:37 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 960/1251] eta: 0:03:04 lr: 0.000460 loss: 3.3236 (3.2741) grad_norm: 1.5140 (1.5983) time: 0.6258 [2021-03-27 10:32:43 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 970/1251] eta: 0:02:58 lr: 0.000460 loss: 3.3201 (3.2732) grad_norm: 1.5875 (1.5985) time: 0.6283 [2021-03-27 10:32:49 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 980/1251] eta: 0:02:51 lr: 0.000460 loss: 3.1490 (3.2714) grad_norm: 1.6310 (1.5992) time: 0.6278 [2021-03-27 10:32:56 swin_base_patch4_window7_224] INFO: Epoch: [158] [ 990/1251] eta: 0:02:45 lr: 0.000459 loss: 3.3977 (3.2736) grad_norm: 1.5855 (1.5997) time: 0.6256 [2021-03-27 10:33:02 swin_base_patch4_window7_224] INFO: Epoch: [158] [1000/1251] eta: 0:02:39 lr: 0.000459 loss: 3.5651 (3.2766) grad_norm: 1.5433 (1.5998) time: 0.6281 [2021-03-27 10:33:08 swin_base_patch4_window7_224] INFO: Epoch: [158] [1010/1251] eta: 0:02:32 lr: 0.000459 loss: 3.5589 (3.2782) grad_norm: 1.5293 (1.5996) time: 0.6282 [2021-03-27 10:33:15 swin_base_patch4_window7_224] INFO: Epoch: [158] [1020/1251] eta: 0:02:26 lr: 0.000459 loss: 3.2547 (3.2753) grad_norm: 1.5293 (1.5990) time: 0.6299 [2021-03-27 10:33:21 swin_base_patch4_window7_224] INFO: Epoch: [158] [1030/1251] eta: 0:02:20 lr: 0.000459 loss: 3.3590 (3.2771) grad_norm: 1.4811 (1.5982) time: 0.6299 [2021-03-27 10:33:27 swin_base_patch4_window7_224] INFO: Epoch: [158] [1040/1251] eta: 0:02:13 lr: 0.000459 loss: 3.3929 (3.2769) grad_norm: 1.4811 (1.5975) time: 0.6286 [2021-03-27 10:33:33 swin_base_patch4_window7_224] INFO: Epoch: [158] [1050/1251] eta: 0:02:07 lr: 0.000459 loss: 3.0332 (3.2738) grad_norm: 1.5782 (1.5986) time: 0.6284 [2021-03-27 10:33:40 swin_base_patch4_window7_224] INFO: Epoch: [158] [1060/1251] eta: 0:02:01 lr: 0.000459 loss: 3.2575 (3.2754) grad_norm: 1.6465 (1.5986) time: 0.6275 [2021-03-27 10:33:46 swin_base_patch4_window7_224] INFO: Epoch: [158] [1070/1251] eta: 0:01:54 lr: 0.000459 loss: 3.4504 (3.2750) grad_norm: 1.4690 (1.5968) time: 0.6374 [2021-03-27 10:33:52 swin_base_patch4_window7_224] INFO: Epoch: [158] [1080/1251] eta: 0:01:48 lr: 0.000459 loss: 3.4254 (3.2750) grad_norm: 1.4736 (1.5967) time: 0.6340 [2021-03-27 10:33:59 swin_base_patch4_window7_224] INFO: Epoch: [158] [1090/1251] eta: 0:01:42 lr: 0.000459 loss: 3.3321 (3.2755) grad_norm: 1.5632 (1.5968) time: 0.6318 [2021-03-27 10:34:05 swin_base_patch4_window7_224] INFO: Epoch: [158] [1100/1251] eta: 0:01:35 lr: 0.000459 loss: 3.4748 (3.2779) grad_norm: 1.5980 (1.5982) time: 0.6341 [2021-03-27 10:34:11 swin_base_patch4_window7_224] INFO: Epoch: [158] [1110/1251] eta: 0:01:29 lr: 0.000459 loss: 3.5310 (3.2803) grad_norm: 1.6271 (1.5984) time: 0.6288 [2021-03-27 10:34:18 swin_base_patch4_window7_224] INFO: Epoch: [158] [1120/1251] eta: 0:01:23 lr: 0.000459 loss: 3.4005 (3.2800) grad_norm: 1.6278 (1.5988) time: 0.6322 [2021-03-27 10:34:24 swin_base_patch4_window7_224] INFO: Epoch: [158] [1130/1251] eta: 0:01:16 lr: 0.000459 loss: 3.1665 (3.2794) grad_norm: 1.6278 (1.5990) time: 0.6293 [2021-03-27 10:34:30 swin_base_patch4_window7_224] INFO: Epoch: [158] [1140/1251] eta: 0:01:10 lr: 0.000459 loss: 2.8708 (3.2750) grad_norm: 1.5520 (1.5983) time: 0.6278 [2021-03-27 10:34:36 swin_base_patch4_window7_224] INFO: Epoch: [158] [1150/1251] eta: 0:01:03 lr: 0.000459 loss: 2.9401 (3.2749) grad_norm: 1.5184 (1.5979) time: 0.6284 [2021-03-27 10:34:43 swin_base_patch4_window7_224] INFO: Epoch: [158] [1160/1251] eta: 0:00:57 lr: 0.000459 loss: 3.2115 (3.2743) grad_norm: 1.5068 (1.5975) time: 0.6297 [2021-03-27 10:34:49 swin_base_patch4_window7_224] INFO: Epoch: [158] [1170/1251] eta: 0:00:51 lr: 0.000459 loss: 3.2358 (3.2740) grad_norm: 1.5469 (1.5978) time: 0.6275 [2021-03-27 10:34:55 swin_base_patch4_window7_224] INFO: Epoch: [158] [1180/1251] eta: 0:00:44 lr: 0.000459 loss: 3.2750 (3.2745) grad_norm: 1.5226 (1.5970) time: 0.6251 [2021-03-27 10:35:02 swin_base_patch4_window7_224] INFO: Epoch: [158] [1190/1251] eta: 0:00:38 lr: 0.000459 loss: 3.1289 (3.2737) grad_norm: 1.4779 (1.5964) time: 0.6349 [2021-03-27 10:35:08 swin_base_patch4_window7_224] INFO: Epoch: [158] [1200/1251] eta: 0:00:32 lr: 0.000459 loss: 3.3004 (3.2749) grad_norm: 1.4772 (1.5968) time: 0.6321 [2021-03-27 10:35:14 swin_base_patch4_window7_224] INFO: Epoch: [158] [1210/1251] eta: 0:00:25 lr: 0.000459 loss: 3.3828 (3.2744) grad_norm: 1.4955 (1.5972) time: 0.6300 [2021-03-27 10:35:21 swin_base_patch4_window7_224] INFO: Epoch: [158] [1220/1251] eta: 0:00:19 lr: 0.000459 loss: 3.1476 (3.2732) grad_norm: 1.6145 (1.5981) time: 0.6294 [2021-03-27 10:35:27 swin_base_patch4_window7_224] INFO: Epoch: [158] [1230/1251] eta: 0:00:13 lr: 0.000459 loss: 3.2237 (3.2723) grad_norm: 1.6052 (1.5980) time: 0.6291 [2021-03-27 10:35:33 swin_base_patch4_window7_224] INFO: Epoch: [158] [1240/1251] eta: 0:00:06 lr: 0.000458 loss: 3.2237 (3.2718) grad_norm: 1.5254 (1.5982) time: 0.6331 [2021-03-27 10:35:39 swin_base_patch4_window7_224] INFO: Epoch: [158] [1250/1251] eta: 0:00:00 lr: 0.000458 loss: 3.3026 (3.2714) grad_norm: 1.5825 (1.5983) time: 0.6258 [2021-03-27 10:35:48 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:00 loss: 0.7779 (0.7779) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-27 10:35:51 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8571 (0.8824) acc1: 81.2500 (80.1136) acc5: 95.3125 (94.8864) [2021-03-27 10:35:53 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8532 (0.8805) acc1: 79.6875 (80.2083) acc5: 95.3125 (94.9405) [2021-03-27 10:35:56 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8532 (0.9044) acc1: 79.6875 (79.2843) acc5: 95.3125 (94.9597) [2021-03-27 10:35:58 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8950 (0.9137) acc1: 78.1250 (78.9253) acc5: 95.3125 (95.0076) [2021-03-27 10:35:59 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8950 (0.9136) acc1: 78.1250 (78.4320) acc5: 95.3125 (94.9440) [2021-03-27 10:36:08 swin_base_patch4_window7_224] INFO: * Acc@1 79.334 Acc@5 94.960 loss 0.893 [2021-03-27 10:36:08 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.3% [2021-03-27 10:36:08 swin_base_patch4_window7_224] INFO: Max accuracy: 79.45% [2021-03-27 10:36:13 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 0/1251] eta: 1:31:07 lr: 0.000458 loss: 3.4913 (3.4913) grad_norm: 1.6172 (1.6172) time: 4.3702 [2021-03-27 10:36:19 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 10/1251] eta: 0:20:18 lr: 0.000458 loss: 3.4913 (3.4805) grad_norm: 1.6172 (1.6080) time: 0.9821 [2021-03-27 10:36:26 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 20/1251] eta: 0:16:45 lr: 0.000458 loss: 3.5314 (3.4472) grad_norm: 1.5188 (1.5608) time: 0.6390 [2021-03-27 10:36:32 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 30/1251] eta: 0:15:19 lr: 0.000458 loss: 3.4405 (3.3500) grad_norm: 1.4372 (1.5331) time: 0.6271 [2021-03-27 10:36:38 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 40/1251] eta: 0:14:35 lr: 0.000458 loss: 3.2653 (3.3456) grad_norm: 1.5204 (1.5426) time: 0.6253 [2021-03-27 10:36:44 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 50/1251] eta: 0:14:04 lr: 0.000458 loss: 3.3652 (3.3667) grad_norm: 1.5673 (1.5548) time: 0.6264 [2021-03-27 10:36:51 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 60/1251] eta: 0:13:44 lr: 0.000458 loss: 3.4476 (3.3537) grad_norm: 1.6101 (1.5762) time: 0.6277 [2021-03-27 10:36:57 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 70/1251] eta: 0:13:25 lr: 0.000458 loss: 3.1664 (3.3212) grad_norm: 1.6879 (1.5968) time: 0.6289 [2021-03-27 10:37:03 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 80/1251] eta: 0:13:11 lr: 0.000458 loss: 3.1636 (3.2930) grad_norm: 1.6397 (1.5946) time: 0.6254 [2021-03-27 10:37:10 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 90/1251] eta: 0:12:59 lr: 0.000458 loss: 3.3198 (3.2801) grad_norm: 1.5349 (1.5842) time: 0.6332 [2021-03-27 10:37:16 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 100/1251] eta: 0:12:48 lr: 0.000458 loss: 3.1792 (3.2711) grad_norm: 1.5693 (1.5928) time: 0.6379 [2021-03-27 10:37:22 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 110/1251] eta: 0:12:38 lr: 0.000458 loss: 3.2409 (3.2787) grad_norm: 1.5691 (1.5960) time: 0.6354 [2021-03-27 10:37:29 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 120/1251] eta: 0:12:29 lr: 0.000458 loss: 3.2711 (3.2550) grad_norm: 1.5747 (1.6062) time: 0.6332 [2021-03-27 10:37:35 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 130/1251] eta: 0:12:19 lr: 0.000458 loss: 3.0933 (3.2395) grad_norm: 1.6474 (1.6054) time: 0.6315 [2021-03-27 10:37:41 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 140/1251] eta: 0:12:11 lr: 0.000458 loss: 3.0086 (3.2208) grad_norm: 1.5216 (1.5986) time: 0.6360 [2021-03-27 10:37:48 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 150/1251] eta: 0:12:03 lr: 0.000458 loss: 3.0610 (3.2145) grad_norm: 1.5414 (1.6115) time: 0.6354 [2021-03-27 10:37:54 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 160/1251] eta: 0:11:54 lr: 0.000458 loss: 3.3527 (3.2333) grad_norm: 1.5843 (1.6079) time: 0.6291 [2021-03-27 10:38:00 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 170/1251] eta: 0:11:47 lr: 0.000458 loss: 3.2439 (3.2200) grad_norm: 1.4323 (1.5980) time: 0.6358 [2021-03-27 10:38:07 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 180/1251] eta: 0:11:38 lr: 0.000458 loss: 3.1731 (3.2081) grad_norm: 1.4323 (1.5963) time: 0.6335 [2021-03-27 10:38:13 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 190/1251] eta: 0:11:31 lr: 0.000458 loss: 3.2844 (3.2124) grad_norm: 1.5310 (1.5971) time: 0.6278 [2021-03-27 10:38:19 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 200/1251] eta: 0:11:23 lr: 0.000458 loss: 3.3894 (3.2211) grad_norm: 1.6514 (1.6089) time: 0.6317 [2021-03-27 10:38:26 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 210/1251] eta: 0:11:16 lr: 0.000458 loss: 3.3411 (3.2060) grad_norm: 1.6873 (1.6111) time: 0.6333 [2021-03-27 10:38:32 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 220/1251] eta: 0:11:09 lr: 0.000458 loss: 3.2283 (3.2104) grad_norm: 1.5502 (1.6127) time: 0.6360 [2021-03-27 10:38:38 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 230/1251] eta: 0:11:02 lr: 0.000457 loss: 3.4259 (3.2149) grad_norm: 1.5506 (1.6110) time: 0.6369 [2021-03-27 10:38:45 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 240/1251] eta: 0:10:54 lr: 0.000457 loss: 3.2965 (3.2177) grad_norm: 1.6054 (1.6137) time: 0.6314 [2021-03-27 10:38:51 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 250/1251] eta: 0:10:47 lr: 0.000457 loss: 3.2644 (3.2201) grad_norm: 1.6378 (1.6117) time: 0.6307 [2021-03-27 10:38:57 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 260/1251] eta: 0:10:40 lr: 0.000457 loss: 2.9554 (3.2022) grad_norm: 1.6201 (1.6349) time: 0.6359 [2021-03-27 10:39:04 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 270/1251] eta: 0:10:33 lr: 0.000457 loss: 3.2365 (3.2106) grad_norm: 1.4943 (1.6287) time: 0.6342 [2021-03-27 10:39:10 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 280/1251] eta: 0:10:26 lr: 0.000457 loss: 3.4419 (3.2182) grad_norm: 1.5647 (1.6290) time: 0.6316 [2021-03-27 10:39:16 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 290/1251] eta: 0:10:20 lr: 0.000457 loss: 3.5510 (3.2287) grad_norm: 1.6035 (1.6298) time: 0.6305 [2021-03-27 10:39:23 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 300/1251] eta: 0:10:13 lr: 0.000457 loss: 3.6560 (3.2428) grad_norm: 1.5812 (1.6281) time: 0.6338 [2021-03-27 10:39:29 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 310/1251] eta: 0:10:06 lr: 0.000457 loss: 3.6548 (3.2488) grad_norm: 1.5983 (1.6311) time: 0.6387 [2021-03-27 10:39:35 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 320/1251] eta: 0:09:59 lr: 0.000457 loss: 3.4797 (3.2539) grad_norm: 1.5612 (1.6289) time: 0.6348 [2021-03-27 10:39:42 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 330/1251] eta: 0:09:52 lr: 0.000457 loss: 3.4797 (3.2621) grad_norm: 1.5575 (1.6280) time: 0.6288 [2021-03-27 10:39:48 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 340/1251] eta: 0:09:46 lr: 0.000457 loss: 3.2794 (3.2527) grad_norm: 1.5575 (1.6255) time: 0.6307 [2021-03-27 10:39:54 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 350/1251] eta: 0:09:39 lr: 0.000457 loss: 3.0934 (3.2515) grad_norm: 1.5419 (1.6221) time: 0.6320 [2021-03-27 10:40:01 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 360/1251] eta: 0:09:32 lr: 0.000457 loss: 3.3188 (3.2456) grad_norm: 1.5005 (1.6202) time: 0.6306 [2021-03-27 10:40:07 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 370/1251] eta: 0:09:26 lr: 0.000457 loss: 3.0132 (3.2313) grad_norm: 1.4970 (1.6168) time: 0.6366 [2021-03-27 10:40:13 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 380/1251] eta: 0:09:19 lr: 0.000457 loss: 3.0132 (3.2333) grad_norm: 1.5547 (1.6161) time: 0.6347 [2021-03-27 10:40:20 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 390/1251] eta: 0:09:12 lr: 0.000457 loss: 3.3351 (3.2317) grad_norm: 1.5753 (1.6139) time: 0.6283 [2021-03-27 10:40:26 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 400/1251] eta: 0:09:06 lr: 0.000457 loss: 3.3892 (3.2313) grad_norm: 1.5124 (1.6114) time: 0.6336 [2021-03-27 10:40:32 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 410/1251] eta: 0:08:59 lr: 0.000457 loss: 3.2238 (3.2284) grad_norm: 1.5124 (1.6101) time: 0.6321 [2021-03-27 10:40:38 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 420/1251] eta: 0:08:52 lr: 0.000457 loss: 3.2238 (3.2331) grad_norm: 1.5935 (1.6089) time: 0.6275 [2021-03-27 10:40:45 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 430/1251] eta: 0:08:46 lr: 0.000457 loss: 3.2358 (3.2275) grad_norm: 1.5387 (1.6068) time: 0.6238 [2021-03-27 10:40:51 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 440/1251] eta: 0:08:39 lr: 0.000457 loss: 3.1425 (3.2254) grad_norm: 1.4798 (1.6039) time: 0.6207 [2021-03-27 10:40:57 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 450/1251] eta: 0:08:32 lr: 0.000457 loss: 3.2196 (3.2267) grad_norm: 1.4742 (1.6032) time: 0.6265 [2021-03-27 10:41:04 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 460/1251] eta: 0:08:26 lr: 0.000457 loss: 3.2803 (3.2271) grad_norm: 1.5211 (1.6023) time: 0.6407 [2021-03-27 10:41:10 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 470/1251] eta: 0:08:20 lr: 0.000456 loss: 3.1957 (3.2257) grad_norm: 1.6138 (1.6039) time: 0.6453 [2021-03-27 10:41:16 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 480/1251] eta: 0:08:13 lr: 0.000456 loss: 3.1060 (3.2249) grad_norm: 1.5378 (1.6008) time: 0.6351 [2021-03-27 10:41:23 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 490/1251] eta: 0:08:07 lr: 0.000456 loss: 3.3551 (3.2269) grad_norm: 1.4958 (1.5995) time: 0.6341 [2021-03-27 10:41:29 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 500/1251] eta: 0:08:00 lr: 0.000456 loss: 3.1134 (3.2199) grad_norm: 1.5172 (1.5979) time: 0.6388 [2021-03-27 10:41:35 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 510/1251] eta: 0:07:54 lr: 0.000456 loss: 2.9534 (3.2186) grad_norm: 1.4751 (1.5977) time: 0.6332 [2021-03-27 10:41:42 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 520/1251] eta: 0:07:47 lr: 0.000456 loss: 3.0272 (3.2141) grad_norm: 1.5406 (1.5987) time: 0.6283 [2021-03-27 10:41:48 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 530/1251] eta: 0:07:41 lr: 0.000456 loss: 3.2639 (3.2173) grad_norm: 1.5477 (1.5985) time: 0.6305 [2021-03-27 10:41:54 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 540/1251] eta: 0:07:34 lr: 0.000456 loss: 3.4468 (3.2235) grad_norm: 1.5249 (1.5967) time: 0.6329 [2021-03-27 10:42:01 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 550/1251] eta: 0:07:28 lr: 0.000456 loss: 3.5528 (3.2234) grad_norm: 1.6393 (1.5984) time: 0.6488 [2021-03-27 10:42:07 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 560/1251] eta: 0:07:21 lr: 0.000456 loss: 3.0584 (3.2169) grad_norm: 1.6215 (1.5978) time: 0.6419 [2021-03-27 10:42:14 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 570/1251] eta: 0:07:15 lr: 0.000456 loss: 3.0584 (3.2192) grad_norm: 1.5807 (1.5980) time: 0.6295 [2021-03-27 10:42:20 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 580/1251] eta: 0:07:08 lr: 0.000456 loss: 3.2302 (3.2178) grad_norm: 1.5868 (1.5983) time: 0.6328 [2021-03-27 10:42:26 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 590/1251] eta: 0:07:02 lr: 0.000456 loss: 3.2398 (3.2195) grad_norm: 1.5918 (1.5991) time: 0.6255 [2021-03-27 10:42:33 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 600/1251] eta: 0:06:55 lr: 0.000456 loss: 3.2565 (3.2209) grad_norm: 1.5366 (1.5984) time: 0.6296 [2021-03-27 10:42:39 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 610/1251] eta: 0:06:49 lr: 0.000456 loss: 3.1448 (3.2198) grad_norm: 1.5937 (1.5985) time: 0.6350 [2021-03-27 10:42:45 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 620/1251] eta: 0:06:43 lr: 0.000456 loss: 3.1279 (3.2183) grad_norm: 1.5583 (1.5969) time: 0.6321 [2021-03-27 10:42:51 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 630/1251] eta: 0:06:36 lr: 0.000456 loss: 3.4524 (3.2205) grad_norm: 1.4658 (1.5956) time: 0.6277 [2021-03-27 10:42:58 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 640/1251] eta: 0:06:29 lr: 0.000456 loss: 3.3383 (3.2219) grad_norm: 1.6283 (1.5973) time: 0.6230 [2021-03-27 10:43:04 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 650/1251] eta: 0:06:23 lr: 0.000456 loss: 3.3383 (3.2235) grad_norm: 1.7302 (1.6004) time: 0.6314 [2021-03-27 10:43:11 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 660/1251] eta: 0:06:17 lr: 0.000456 loss: 3.2235 (3.2178) grad_norm: 1.7086 (1.6000) time: 0.6452 [2021-03-27 10:43:17 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 670/1251] eta: 0:06:10 lr: 0.000456 loss: 3.1286 (3.2197) grad_norm: 1.5183 (1.5999) time: 0.6354 [2021-03-27 10:43:23 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 680/1251] eta: 0:06:04 lr: 0.000456 loss: 3.3777 (3.2221) grad_norm: 1.5098 (1.5988) time: 0.6299 [2021-03-27 10:43:30 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 690/1251] eta: 0:05:57 lr: 0.000456 loss: 3.3770 (3.2224) grad_norm: 1.5468 (1.5984) time: 0.6362 [2021-03-27 10:43:36 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 700/1251] eta: 0:05:51 lr: 0.000456 loss: 3.4045 (3.2262) grad_norm: 1.5468 (1.5974) time: 0.6312 [2021-03-27 10:43:42 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 710/1251] eta: 0:05:45 lr: 0.000455 loss: 3.4673 (3.2287) grad_norm: 1.4449 (1.5962) time: 0.6308 [2021-03-27 10:43:48 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 720/1251] eta: 0:05:38 lr: 0.000455 loss: 3.3704 (3.2281) grad_norm: 1.4308 (1.5947) time: 0.6322 [2021-03-27 10:43:55 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 730/1251] eta: 0:05:32 lr: 0.000455 loss: 3.2779 (3.2279) grad_norm: 1.5159 (1.5959) time: 0.6287 [2021-03-27 10:44:01 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 740/1251] eta: 0:05:25 lr: 0.000455 loss: 3.2779 (3.2309) grad_norm: 1.6325 (1.5956) time: 0.6367 [2021-03-27 10:44:07 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 750/1251] eta: 0:05:19 lr: 0.000455 loss: 3.4018 (3.2332) grad_norm: 1.5640 (1.5954) time: 0.6395 [2021-03-27 10:44:14 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 760/1251] eta: 0:05:13 lr: 0.000455 loss: 3.4018 (3.2331) grad_norm: 1.4768 (1.5939) time: 0.6303 [2021-03-27 10:44:20 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 770/1251] eta: 0:05:06 lr: 0.000455 loss: 3.1204 (3.2310) grad_norm: 1.5536 (1.5943) time: 0.6330 [2021-03-27 10:44:26 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 780/1251] eta: 0:05:00 lr: 0.000455 loss: 3.2857 (3.2331) grad_norm: 1.6174 (1.5934) time: 0.6354 [2021-03-27 10:44:33 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 790/1251] eta: 0:04:53 lr: 0.000455 loss: 3.2921 (3.2310) grad_norm: 1.4354 (1.5914) time: 0.6347 [2021-03-27 10:44:39 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 800/1251] eta: 0:04:47 lr: 0.000455 loss: 3.2849 (3.2317) grad_norm: 1.4374 (1.5919) time: 0.6321 [2021-03-27 10:44:45 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 810/1251] eta: 0:04:41 lr: 0.000455 loss: 3.3586 (3.2330) grad_norm: 1.5570 (1.5923) time: 0.6268 [2021-03-27 10:44:52 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 820/1251] eta: 0:04:34 lr: 0.000455 loss: 3.2923 (3.2297) grad_norm: 1.6363 (1.5933) time: 0.6268 [2021-03-27 10:44:58 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 830/1251] eta: 0:04:28 lr: 0.000455 loss: 3.0918 (3.2307) grad_norm: 1.5987 (1.5935) time: 0.6257 [2021-03-27 10:45:04 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 840/1251] eta: 0:04:21 lr: 0.000455 loss: 3.5281 (3.2329) grad_norm: 1.4528 (1.5923) time: 0.6264 [2021-03-27 10:45:11 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 850/1251] eta: 0:04:15 lr: 0.000455 loss: 3.2662 (3.2307) grad_norm: 1.4528 (1.5906) time: 0.6302 [2021-03-27 10:45:17 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 860/1251] eta: 0:04:08 lr: 0.000455 loss: 3.2949 (3.2323) grad_norm: 1.5036 (1.5903) time: 0.6337 [2021-03-27 10:45:23 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 870/1251] eta: 0:04:02 lr: 0.000455 loss: 3.4111 (3.2327) grad_norm: 1.5307 (1.5901) time: 0.6334 [2021-03-27 10:45:30 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 880/1251] eta: 0:03:56 lr: 0.000455 loss: 3.3461 (3.2340) grad_norm: 1.5509 (1.5900) time: 0.6340 [2021-03-27 10:45:36 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 890/1251] eta: 0:03:49 lr: 0.000455 loss: 3.3847 (3.2368) grad_norm: 1.4496 (1.5893) time: 0.6354 [2021-03-27 10:45:42 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 900/1251] eta: 0:03:43 lr: 0.000455 loss: 3.3847 (3.2393) grad_norm: 1.4661 (1.5905) time: 0.6296 [2021-03-27 10:45:48 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 910/1251] eta: 0:03:37 lr: 0.000455 loss: 3.3781 (3.2403) grad_norm: 1.6487 (1.5911) time: 0.6238 [2021-03-27 10:45:55 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 920/1251] eta: 0:03:30 lr: 0.000455 loss: 3.2696 (3.2400) grad_norm: 1.6124 (1.5908) time: 0.6251 [2021-03-27 10:46:01 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 930/1251] eta: 0:03:24 lr: 0.000455 loss: 3.3451 (3.2420) grad_norm: 1.5289 (1.5901) time: 0.6366 [2021-03-27 10:46:07 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 940/1251] eta: 0:03:17 lr: 0.000455 loss: 3.3539 (3.2403) grad_norm: 1.5422 (1.5917) time: 0.6408 [2021-03-27 10:46:14 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 950/1251] eta: 0:03:11 lr: 0.000454 loss: 3.1222 (3.2383) grad_norm: 1.6248 (1.5917) time: 0.6410 [2021-03-27 10:46:20 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 960/1251] eta: 0:03:05 lr: 0.000454 loss: 3.2120 (3.2407) grad_norm: 1.5246 (1.5912) time: 0.6427 [2021-03-27 10:46:27 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 970/1251] eta: 0:02:58 lr: 0.000454 loss: 3.5405 (3.2420) grad_norm: 1.5367 (1.5915) time: 0.6374 [2021-03-27 10:46:33 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 980/1251] eta: 0:02:52 lr: 0.000454 loss: 3.4087 (3.2420) grad_norm: 1.5369 (1.5921) time: 0.6349 [2021-03-27 10:46:39 swin_base_patch4_window7_224] INFO: Epoch: [159] [ 990/1251] eta: 0:02:46 lr: 0.000454 loss: 3.4345 (3.2430) grad_norm: 1.5281 (1.5911) time: 0.6340 [2021-03-27 10:46:46 swin_base_patch4_window7_224] INFO: Epoch: [159] [1000/1251] eta: 0:02:39 lr: 0.000454 loss: 3.3934 (3.2426) grad_norm: 1.4632 (1.5905) time: 0.6347 [2021-03-27 10:46:52 swin_base_patch4_window7_224] INFO: Epoch: [159] [1010/1251] eta: 0:02:33 lr: 0.000454 loss: 3.0975 (3.2410) grad_norm: 1.5017 (1.5900) time: 0.6337 [2021-03-27 10:46:58 swin_base_patch4_window7_224] INFO: Epoch: [159] [1020/1251] eta: 0:02:27 lr: 0.000454 loss: 3.1324 (3.2410) grad_norm: 1.5789 (1.5911) time: 0.6309 [2021-03-27 10:47:05 swin_base_patch4_window7_224] INFO: Epoch: [159] [1030/1251] eta: 0:02:20 lr: 0.000454 loss: 3.4727 (3.2414) grad_norm: 1.6082 (1.5906) time: 0.6307 [2021-03-27 10:47:11 swin_base_patch4_window7_224] INFO: Epoch: [159] [1040/1251] eta: 0:02:14 lr: 0.000454 loss: 3.4200 (3.2409) grad_norm: 1.5488 (1.5907) time: 0.6365 [2021-03-27 10:47:17 swin_base_patch4_window7_224] INFO: Epoch: [159] [1050/1251] eta: 0:02:07 lr: 0.000454 loss: 3.1395 (3.2395) grad_norm: 1.5988 (1.5902) time: 0.6412 [2021-03-27 10:47:24 swin_base_patch4_window7_224] INFO: Epoch: [159] [1060/1251] eta: 0:02:01 lr: 0.000454 loss: 3.1244 (3.2394) grad_norm: 1.5410 (1.5887) time: 0.6400 [2021-03-27 10:47:30 swin_base_patch4_window7_224] INFO: Epoch: [159] [1070/1251] eta: 0:01:55 lr: 0.000454 loss: 3.3652 (3.2401) grad_norm: 1.4404 (1.5883) time: 0.6356 [2021-03-27 10:47:36 swin_base_patch4_window7_224] INFO: Epoch: [159] [1080/1251] eta: 0:01:48 lr: 0.000454 loss: 3.5615 (3.2436) grad_norm: 1.4816 (1.5876) time: 0.6276 [2021-03-27 10:47:43 swin_base_patch4_window7_224] INFO: Epoch: [159] [1090/1251] eta: 0:01:42 lr: 0.000454 loss: 3.5615 (3.2444) grad_norm: 1.5666 (1.5886) time: 0.6303 [2021-03-27 10:47:49 swin_base_patch4_window7_224] INFO: Epoch: [159] [1100/1251] eta: 0:01:36 lr: 0.000454 loss: 3.1586 (3.2445) grad_norm: 1.6162 (1.5894) time: 0.6340 [2021-03-27 10:47:55 swin_base_patch4_window7_224] INFO: Epoch: [159] [1110/1251] eta: 0:01:29 lr: 0.000454 loss: 3.1586 (3.2443) grad_norm: 1.6449 (1.5903) time: 0.6301 [2021-03-27 10:48:02 swin_base_patch4_window7_224] INFO: Epoch: [159] [1120/1251] eta: 0:01:23 lr: 0.000454 loss: 3.3019 (3.2447) grad_norm: 1.6449 (1.5896) time: 0.6309 [2021-03-27 10:48:08 swin_base_patch4_window7_224] INFO: Epoch: [159] [1130/1251] eta: 0:01:16 lr: 0.000454 loss: 3.3962 (3.2463) grad_norm: 1.6239 (1.5903) time: 0.6282 [2021-03-27 10:48:14 swin_base_patch4_window7_224] INFO: Epoch: [159] [1140/1251] eta: 0:01:10 lr: 0.000454 loss: 3.3546 (3.2458) grad_norm: 1.4830 (1.5894) time: 0.6302 [2021-03-27 10:48:21 swin_base_patch4_window7_224] INFO: Epoch: [159] [1150/1251] eta: 0:01:04 lr: 0.000454 loss: 3.2627 (3.2460) grad_norm: 1.4515 (1.5898) time: 0.6314 [2021-03-27 10:48:27 swin_base_patch4_window7_224] INFO: Epoch: [159] [1160/1251] eta: 0:00:57 lr: 0.000454 loss: 3.3310 (3.2462) grad_norm: 1.5294 (1.5893) time: 0.6271 [2021-03-27 10:48:33 swin_base_patch4_window7_224] INFO: Epoch: [159] [1170/1251] eta: 0:00:51 lr: 0.000454 loss: 3.3310 (3.2460) grad_norm: 1.5232 (1.5892) time: 0.6262 [2021-03-27 10:48:39 swin_base_patch4_window7_224] INFO: Epoch: [159] [1180/1251] eta: 0:00:45 lr: 0.000454 loss: 3.2554 (3.2454) grad_norm: 1.5056 (1.5891) time: 0.6238 [2021-03-27 10:48:46 swin_base_patch4_window7_224] INFO: Epoch: [159] [1190/1251] eta: 0:00:38 lr: 0.000454 loss: 3.2509 (3.2445) grad_norm: 1.4944 (1.5891) time: 0.6314 [2021-03-27 10:48:52 swin_base_patch4_window7_224] INFO: Epoch: [159] [1200/1251] eta: 0:00:32 lr: 0.000453 loss: 3.1408 (3.2434) grad_norm: 1.4674 (1.5892) time: 0.6328 [2021-03-27 10:48:58 swin_base_patch4_window7_224] INFO: Epoch: [159] [1210/1251] eta: 0:00:26 lr: 0.000453 loss: 3.1399 (3.2422) grad_norm: 1.5288 (1.5898) time: 0.6276 [2021-03-27 10:49:05 swin_base_patch4_window7_224] INFO: Epoch: [159] [1220/1251] eta: 0:00:19 lr: 0.000453 loss: 3.4055 (3.2431) grad_norm: 1.5947 (1.5912) time: 0.6251 [2021-03-27 10:49:11 swin_base_patch4_window7_224] INFO: Epoch: [159] [1230/1251] eta: 0:00:13 lr: 0.000453 loss: 3.2865 (3.2423) grad_norm: 1.6754 (1.5913) time: 0.6224 [2021-03-27 10:49:17 swin_base_patch4_window7_224] INFO: Epoch: [159] [1240/1251] eta: 0:00:06 lr: 0.000453 loss: 3.2714 (3.2427) grad_norm: 1.6331 (1.5916) time: 0.6233 [2021-03-27 10:49:23 swin_base_patch4_window7_224] INFO: Epoch: [159] [1250/1251] eta: 0:00:00 lr: 0.000453 loss: 3.3207 (3.2421) grad_norm: 1.5498 (1.5906) time: 0.6208 [2021-03-27 10:49:31 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:03 loss: 0.9910 (0.9910) acc1: 71.8750 (71.8750) acc5: 96.8750 (96.8750) [2021-03-27 10:49:34 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.9480 (0.9152) acc1: 78.1250 (77.1307) acc5: 95.3125 (95.3125) [2021-03-27 10:49:36 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8611 (0.8865) acc1: 79.6875 (78.4970) acc5: 95.3125 (95.3125) [2021-03-27 10:49:38 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8524 (0.8953) acc1: 79.6875 (78.3770) acc5: 95.3125 (95.2117) [2021-03-27 10:49:40 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8471 (0.8828) acc1: 78.1250 (78.9253) acc5: 95.3125 (95.2744) [2021-03-27 10:49:42 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8500 (0.8875) acc1: 79.6875 (78.7200) acc5: 95.3125 (95.2960) [2021-03-27 10:49:54 swin_base_patch4_window7_224] INFO: * Acc@1 79.480 Acc@5 95.076 loss 0.875 [2021-03-27 10:49:54 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.5% [2021-03-27 10:49:54 swin_base_patch4_window7_224] INFO: Max accuracy: 79.48% [2021-03-27 10:49:59 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 0/1251] eta: 1:26:30 lr: 0.000453 loss: 3.7882 (3.7882) grad_norm: 1.2987 (1.2987) time: 4.1491 [2021-03-27 10:50:05 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 10/1251] eta: 0:20:00 lr: 0.000453 loss: 3.2330 (3.0856) grad_norm: 1.5390 (1.5311) time: 0.9674 [2021-03-27 10:50:12 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 20/1251] eta: 0:16:37 lr: 0.000453 loss: 3.3839 (3.2960) grad_norm: 1.5424 (1.5798) time: 0.6435 [2021-03-27 10:50:18 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 30/1251] eta: 0:15:25 lr: 0.000453 loss: 3.4767 (3.2754) grad_norm: 1.5962 (1.5882) time: 0.6425 [2021-03-27 10:50:24 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 40/1251] eta: 0:14:41 lr: 0.000453 loss: 3.3259 (3.3258) grad_norm: 1.5556 (1.5850) time: 0.6408 [2021-03-27 10:50:31 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 50/1251] eta: 0:14:11 lr: 0.000453 loss: 3.3521 (3.3127) grad_norm: 1.4923 (1.5751) time: 0.6325 [2021-03-27 10:50:37 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 60/1251] eta: 0:13:46 lr: 0.000453 loss: 3.3595 (3.3393) grad_norm: 1.5460 (1.5749) time: 0.6258 [2021-03-27 10:50:43 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 70/1251] eta: 0:13:30 lr: 0.000453 loss: 3.2991 (3.2779) grad_norm: 1.5460 (1.5680) time: 0.6277 [2021-03-27 10:50:49 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 80/1251] eta: 0:13:13 lr: 0.000453 loss: 2.7528 (3.2426) grad_norm: 1.4501 (1.5633) time: 0.6285 [2021-03-27 10:50:56 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 90/1251] eta: 0:13:01 lr: 0.000453 loss: 2.7598 (3.2295) grad_norm: 1.5112 (1.5623) time: 0.6265 [2021-03-27 10:51:02 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 100/1251] eta: 0:12:49 lr: 0.000453 loss: 3.3745 (3.2482) grad_norm: 1.5517 (1.5731) time: 0.6312 [2021-03-27 10:51:08 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 110/1251] eta: 0:12:39 lr: 0.000453 loss: 3.2378 (3.2379) grad_norm: 1.6068 (1.5803) time: 0.6333 [2021-03-27 10:51:15 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 120/1251] eta: 0:12:29 lr: 0.000453 loss: 3.2035 (3.2239) grad_norm: 1.5211 (1.5763) time: 0.6299 [2021-03-27 10:51:21 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 130/1251] eta: 0:12:20 lr: 0.000453 loss: 3.0979 (3.2255) grad_norm: 1.4864 (1.5739) time: 0.6317 [2021-03-27 10:51:27 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 140/1251] eta: 0:12:11 lr: 0.000453 loss: 3.0979 (3.2050) grad_norm: 1.4412 (1.5642) time: 0.6327 [2021-03-27 10:51:34 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 150/1251] eta: 0:12:03 lr: 0.000453 loss: 3.1476 (3.2113) grad_norm: 1.4412 (1.5633) time: 0.6329 [2021-03-27 10:51:40 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 160/1251] eta: 0:11:54 lr: 0.000453 loss: 3.2105 (3.1990) grad_norm: 1.4938 (1.5651) time: 0.6333 [2021-03-27 10:51:46 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 170/1251] eta: 0:11:46 lr: 0.000453 loss: 3.2873 (3.2141) grad_norm: 1.5644 (1.5671) time: 0.6294 [2021-03-27 10:51:53 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 180/1251] eta: 0:11:38 lr: 0.000453 loss: 3.4980 (3.2208) grad_norm: 1.5561 (1.5658) time: 0.6294 [2021-03-27 10:51:59 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 190/1251] eta: 0:11:30 lr: 0.000452 loss: 3.4440 (3.2253) grad_norm: 1.5194 (1.5652) time: 0.6286 [2021-03-27 10:52:05 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 200/1251] eta: 0:11:23 lr: 0.000452 loss: 3.2793 (3.2116) grad_norm: 1.5117 (1.5650) time: 0.6314 [2021-03-27 10:52:12 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 210/1251] eta: 0:11:15 lr: 0.000452 loss: 3.3512 (3.2221) grad_norm: 1.6147 (1.5694) time: 0.6302 [2021-03-27 10:52:18 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 220/1251] eta: 0:11:08 lr: 0.000452 loss: 3.4079 (3.2297) grad_norm: 1.5571 (1.5687) time: 0.6285 [2021-03-27 10:52:24 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 230/1251] eta: 0:11:00 lr: 0.000452 loss: 3.3097 (3.2386) grad_norm: 1.5435 (1.5697) time: 0.6291 [2021-03-27 10:52:30 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 240/1251] eta: 0:10:53 lr: 0.000452 loss: 3.2774 (3.2300) grad_norm: 1.5682 (1.5714) time: 0.6292 [2021-03-27 10:52:37 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 250/1251] eta: 0:10:47 lr: 0.000452 loss: 3.1614 (3.2270) grad_norm: 1.4822 (1.5666) time: 0.6363 [2021-03-27 10:52:43 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 260/1251] eta: 0:10:40 lr: 0.000452 loss: 2.9904 (3.2134) grad_norm: 1.4396 (1.5653) time: 0.6383 [2021-03-27 10:52:49 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 270/1251] eta: 0:10:33 lr: 0.000452 loss: 2.9264 (3.2055) grad_norm: 1.5075 (1.5655) time: 0.6319 [2021-03-27 10:52:56 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 280/1251] eta: 0:10:26 lr: 0.000452 loss: 3.1914 (3.2101) grad_norm: 1.5527 (1.5655) time: 0.6294 [2021-03-27 10:53:02 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 290/1251] eta: 0:10:19 lr: 0.000452 loss: 3.3331 (3.2114) grad_norm: 1.5529 (1.5670) time: 0.6274 [2021-03-27 10:53:08 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 300/1251] eta: 0:10:12 lr: 0.000452 loss: 3.1061 (3.2093) grad_norm: 1.5924 (1.5696) time: 0.6288 [2021-03-27 10:53:15 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 310/1251] eta: 0:10:05 lr: 0.000452 loss: 3.0652 (3.2103) grad_norm: 1.6175 (1.5719) time: 0.6313 [2021-03-27 10:53:21 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 320/1251] eta: 0:09:58 lr: 0.000452 loss: 3.3750 (3.2193) grad_norm: 1.5036 (1.5716) time: 0.6280 [2021-03-27 10:53:27 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 330/1251] eta: 0:09:51 lr: 0.000452 loss: 3.3441 (3.2149) grad_norm: 1.5019 (1.5700) time: 0.6282 [2021-03-27 10:53:34 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 340/1251] eta: 0:09:45 lr: 0.000452 loss: 3.0144 (3.2128) grad_norm: 1.4857 (1.5687) time: 0.6384 [2021-03-27 10:53:40 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 350/1251] eta: 0:09:38 lr: 0.000452 loss: 3.3310 (3.2153) grad_norm: 1.4857 (1.5675) time: 0.6346 [2021-03-27 10:53:46 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 360/1251] eta: 0:09:31 lr: 0.000452 loss: 3.3068 (3.2150) grad_norm: 1.5316 (1.5672) time: 0.6266 [2021-03-27 10:53:53 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 370/1251] eta: 0:09:25 lr: 0.000452 loss: 3.1355 (3.2105) grad_norm: 1.4476 (1.5633) time: 0.6328 [2021-03-27 10:53:59 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 380/1251] eta: 0:09:18 lr: 0.000452 loss: 3.2531 (3.2137) grad_norm: 1.4108 (1.5603) time: 0.6325 [2021-03-27 10:54:05 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 390/1251] eta: 0:09:11 lr: 0.000452 loss: 3.4864 (3.2154) grad_norm: 1.4309 (1.5585) time: 0.6305 [2021-03-27 10:54:11 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 400/1251] eta: 0:09:05 lr: 0.000452 loss: 3.3287 (3.2145) grad_norm: 1.4641 (1.5565) time: 0.6289 [2021-03-27 10:54:18 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 410/1251] eta: 0:08:58 lr: 0.000452 loss: 3.6078 (3.2177) grad_norm: 1.5340 (1.5592) time: 0.6297 [2021-03-27 10:54:24 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 420/1251] eta: 0:08:51 lr: 0.000452 loss: 3.5638 (3.2195) grad_norm: 1.6965 (1.5637) time: 0.6318 [2021-03-27 10:54:30 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 430/1251] eta: 0:08:45 lr: 0.000451 loss: 3.4607 (3.2228) grad_norm: 1.5646 (1.5617) time: 0.6315 [2021-03-27 10:54:37 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 440/1251] eta: 0:08:38 lr: 0.000451 loss: 3.4089 (3.2222) grad_norm: 1.4643 (1.5617) time: 0.6331 [2021-03-27 10:54:43 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 450/1251] eta: 0:08:32 lr: 0.000451 loss: 2.9247 (3.2139) grad_norm: 1.5630 (1.5644) time: 0.6357 [2021-03-27 10:54:49 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 460/1251] eta: 0:08:25 lr: 0.000451 loss: 2.8527 (3.2108) grad_norm: 1.5451 (1.5629) time: 0.6335 [2021-03-27 10:54:56 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 470/1251] eta: 0:08:19 lr: 0.000451 loss: 3.2056 (3.2082) grad_norm: 1.5413 (1.5650) time: 0.6305 [2021-03-27 10:55:02 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 480/1251] eta: 0:08:12 lr: 0.000451 loss: 3.2196 (3.2088) grad_norm: 1.5561 (1.5647) time: 0.6343 [2021-03-27 10:55:08 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 490/1251] eta: 0:08:06 lr: 0.000451 loss: 3.2330 (3.2080) grad_norm: 1.4477 (1.5629) time: 0.6360 [2021-03-27 10:55:15 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 500/1251] eta: 0:08:00 lr: 0.000451 loss: 3.0621 (3.2061) grad_norm: 1.4626 (1.5630) time: 0.6369 [2021-03-27 10:55:21 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 510/1251] eta: 0:07:53 lr: 0.000451 loss: 3.4142 (3.2111) grad_norm: 1.4658 (1.5619) time: 0.6335 [2021-03-27 10:55:28 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 520/1251] eta: 0:07:47 lr: 0.000451 loss: 3.4340 (3.2115) grad_norm: 1.4987 (1.5616) time: 0.6362 [2021-03-27 10:55:34 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 530/1251] eta: 0:07:40 lr: 0.000451 loss: 3.2554 (3.2111) grad_norm: 1.5504 (1.5637) time: 0.6388 [2021-03-27 10:55:40 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 540/1251] eta: 0:07:34 lr: 0.000451 loss: 3.2554 (3.2103) grad_norm: 1.5749 (1.5640) time: 0.6243 [2021-03-27 10:55:47 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 550/1251] eta: 0:07:27 lr: 0.000451 loss: 2.9400 (3.2057) grad_norm: 1.4963 (1.5629) time: 0.6323 [2021-03-27 10:55:53 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 560/1251] eta: 0:07:21 lr: 0.000451 loss: 3.3218 (3.2096) grad_norm: 1.4902 (1.5646) time: 0.6365 [2021-03-27 10:55:59 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 570/1251] eta: 0:07:14 lr: 0.000451 loss: 3.3218 (3.2004) grad_norm: 1.6014 (1.5662) time: 0.6308 [2021-03-27 10:56:06 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 580/1251] eta: 0:07:08 lr: 0.000451 loss: 3.2626 (3.2027) grad_norm: 1.5293 (1.5654) time: 0.6389 [2021-03-27 10:56:12 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 590/1251] eta: 0:07:01 lr: 0.000451 loss: 3.2793 (3.2061) grad_norm: 1.5227 (1.5648) time: 0.6349 [2021-03-27 10:56:18 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 600/1251] eta: 0:06:55 lr: 0.000451 loss: 3.3230 (3.2095) grad_norm: 1.5440 (1.5650) time: 0.6346 [2021-03-27 10:56:25 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 610/1251] eta: 0:06:49 lr: 0.000451 loss: 3.3339 (3.2076) grad_norm: 1.5440 (1.5646) time: 0.6345 [2021-03-27 10:56:31 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 620/1251] eta: 0:06:42 lr: 0.000451 loss: 3.3339 (3.2103) grad_norm: 1.5407 (1.5668) time: 0.6297 [2021-03-27 10:56:37 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 630/1251] eta: 0:06:36 lr: 0.000451 loss: 3.2796 (3.2093) grad_norm: 1.5529 (1.5676) time: 0.6262 [2021-03-27 10:56:43 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 640/1251] eta: 0:06:29 lr: 0.000451 loss: 3.2796 (3.2112) grad_norm: 1.4807 (1.5671) time: 0.6299 [2021-03-27 10:56:50 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 650/1251] eta: 0:06:23 lr: 0.000451 loss: 3.3861 (3.2147) grad_norm: 1.4570 (1.5657) time: 0.6342 [2021-03-27 10:56:56 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 660/1251] eta: 0:06:16 lr: 0.000451 loss: 3.3062 (3.2119) grad_norm: 1.4617 (1.5661) time: 0.6296 [2021-03-27 10:57:02 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 670/1251] eta: 0:06:10 lr: 0.000450 loss: 3.3024 (3.2145) grad_norm: 1.5106 (1.5655) time: 0.6274 [2021-03-27 10:57:09 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 680/1251] eta: 0:06:03 lr: 0.000450 loss: 3.3868 (3.2166) grad_norm: 1.5021 (1.5645) time: 0.6284 [2021-03-27 10:57:15 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 690/1251] eta: 0:05:57 lr: 0.000450 loss: 3.3271 (3.2135) grad_norm: 1.5282 (1.5651) time: 0.6320 [2021-03-27 10:57:21 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 700/1251] eta: 0:05:51 lr: 0.000450 loss: 3.3271 (3.2144) grad_norm: 1.6076 (1.5663) time: 0.6350 [2021-03-27 10:57:28 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 710/1251] eta: 0:05:44 lr: 0.000450 loss: 2.9870 (3.2105) grad_norm: 1.5577 (1.5662) time: 0.6331 [2021-03-27 10:57:34 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 720/1251] eta: 0:05:38 lr: 0.000450 loss: 3.1374 (3.2122) grad_norm: 1.5035 (inf) time: 0.6286 [2021-03-27 10:57:40 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 730/1251] eta: 0:05:31 lr: 0.000450 loss: 3.2863 (3.2113) grad_norm: 1.5211 (inf) time: 0.6353 [2021-03-27 10:57:47 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 740/1251] eta: 0:05:25 lr: 0.000450 loss: 3.2256 (3.2101) grad_norm: 1.5955 (inf) time: 0.6412 [2021-03-27 10:57:53 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 750/1251] eta: 0:05:19 lr: 0.000450 loss: 3.0536 (3.2095) grad_norm: 1.4913 (inf) time: 0.6322 [2021-03-27 10:57:59 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 760/1251] eta: 0:05:12 lr: 0.000450 loss: 3.3924 (3.2131) grad_norm: 1.5958 (inf) time: 0.6313 [2021-03-27 10:58:06 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 770/1251] eta: 0:05:06 lr: 0.000450 loss: 3.4635 (3.2139) grad_norm: 1.7730 (inf) time: 0.6383 [2021-03-27 10:58:12 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 780/1251] eta: 0:04:59 lr: 0.000450 loss: 3.2906 (3.2140) grad_norm: 1.5846 (inf) time: 0.6322 [2021-03-27 10:58:18 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 790/1251] eta: 0:04:53 lr: 0.000450 loss: 2.9423 (3.2100) grad_norm: 1.4756 (inf) time: 0.6239 [2021-03-27 10:58:25 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 800/1251] eta: 0:04:47 lr: 0.000450 loss: 3.0929 (3.2087) grad_norm: 1.4358 (inf) time: 0.6339 [2021-03-27 10:58:31 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 810/1251] eta: 0:04:40 lr: 0.000450 loss: 3.0929 (3.2067) grad_norm: 1.5056 (inf) time: 0.6347 [2021-03-27 10:58:37 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 820/1251] eta: 0:04:34 lr: 0.000450 loss: 3.3540 (3.2096) grad_norm: 1.5275 (inf) time: 0.6278 [2021-03-27 10:58:44 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 830/1251] eta: 0:04:27 lr: 0.000450 loss: 3.3687 (3.2087) grad_norm: 1.5670 (inf) time: 0.6281 [2021-03-27 10:58:50 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 840/1251] eta: 0:04:21 lr: 0.000450 loss: 3.1727 (3.2108) grad_norm: 1.5820 (inf) time: 0.6274 [2021-03-27 10:58:56 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 850/1251] eta: 0:04:15 lr: 0.000450 loss: 3.1869 (3.2084) grad_norm: 1.5779 (inf) time: 0.6262 [2021-03-27 10:59:02 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 860/1251] eta: 0:04:08 lr: 0.000450 loss: 3.2351 (3.2113) grad_norm: 1.5156 (inf) time: 0.6310 [2021-03-27 10:59:09 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 870/1251] eta: 0:04:02 lr: 0.000450 loss: 3.2509 (3.2105) grad_norm: 1.4798 (inf) time: 0.6400 [2021-03-27 10:59:15 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 880/1251] eta: 0:03:56 lr: 0.000450 loss: 3.2509 (3.2107) grad_norm: 1.5144 (inf) time: 0.6387 [2021-03-27 10:59:21 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 890/1251] eta: 0:03:49 lr: 0.000450 loss: 3.3085 (3.2110) grad_norm: 1.6372 (inf) time: 0.6297 [2021-03-27 10:59:28 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 900/1251] eta: 0:03:43 lr: 0.000450 loss: 3.3758 (3.2135) grad_norm: 1.5371 (inf) time: 0.6276 [2021-03-27 10:59:34 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 910/1251] eta: 0:03:36 lr: 0.000450 loss: 3.4703 (3.2140) grad_norm: 1.4819 (inf) time: 0.6280 [2021-03-27 10:59:40 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 920/1251] eta: 0:03:30 lr: 0.000449 loss: 3.3216 (3.2127) grad_norm: 1.5439 (inf) time: 0.6266 [2021-03-27 10:59:47 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 930/1251] eta: 0:03:24 lr: 0.000449 loss: 3.2274 (3.2107) grad_norm: 1.6123 (inf) time: 0.6323 [2021-03-27 10:59:53 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 940/1251] eta: 0:03:17 lr: 0.000449 loss: 3.1461 (3.2121) grad_norm: 1.5421 (inf) time: 0.6307 [2021-03-27 10:59:59 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 950/1251] eta: 0:03:11 lr: 0.000449 loss: 3.1461 (3.2133) grad_norm: 1.5629 (inf) time: 0.6250 [2021-03-27 11:00:05 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 960/1251] eta: 0:03:04 lr: 0.000449 loss: 3.2307 (3.2136) grad_norm: 1.6691 (inf) time: 0.6264 [2021-03-27 11:00:12 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 970/1251] eta: 0:02:58 lr: 0.000449 loss: 3.4314 (3.2149) grad_norm: 1.5496 (inf) time: 0.6260 [2021-03-27 11:00:18 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 980/1251] eta: 0:02:52 lr: 0.000449 loss: 3.4314 (3.2162) grad_norm: 1.5023 (inf) time: 0.6270 [2021-03-27 11:00:24 swin_base_patch4_window7_224] INFO: Epoch: [160] [ 990/1251] eta: 0:02:45 lr: 0.000449 loss: 3.3285 (3.2166) grad_norm: 1.5384 (inf) time: 0.6304 [2021-03-27 11:00:31 swin_base_patch4_window7_224] INFO: Epoch: [160] [1000/1251] eta: 0:02:39 lr: 0.000449 loss: 3.3900 (3.2180) grad_norm: 1.5537 (inf) time: 0.6319 [2021-03-27 11:00:37 swin_base_patch4_window7_224] INFO: Epoch: [160] [1010/1251] eta: 0:02:33 lr: 0.000449 loss: 3.4304 (3.2171) grad_norm: 1.5291 (inf) time: 0.6332 [2021-03-27 11:00:43 swin_base_patch4_window7_224] INFO: Epoch: [160] [1020/1251] eta: 0:02:26 lr: 0.000449 loss: 3.2629 (3.2152) grad_norm: 1.5029 (inf) time: 0.6290 [2021-03-27 11:00:50 swin_base_patch4_window7_224] INFO: Epoch: [160] [1030/1251] eta: 0:02:20 lr: 0.000449 loss: 3.1711 (3.2134) grad_norm: 1.5296 (inf) time: 0.6285 [2021-03-27 11:00:56 swin_base_patch4_window7_224] INFO: Epoch: [160] [1040/1251] eta: 0:02:14 lr: 0.000449 loss: 3.1986 (3.2139) grad_norm: 1.4874 (inf) time: 0.6383 [2021-03-27 11:01:02 swin_base_patch4_window7_224] INFO: Epoch: [160] [1050/1251] eta: 0:02:07 lr: 0.000449 loss: 3.1986 (3.2134) grad_norm: 1.4499 (inf) time: 0.6379 [2021-03-27 11:01:09 swin_base_patch4_window7_224] INFO: Epoch: [160] [1060/1251] eta: 0:02:01 lr: 0.000449 loss: 3.1902 (3.2127) grad_norm: 1.4855 (inf) time: 0.6341 [2021-03-27 11:01:15 swin_base_patch4_window7_224] INFO: Epoch: [160] [1070/1251] eta: 0:01:54 lr: 0.000449 loss: 2.9790 (3.2106) grad_norm: 1.4305 (inf) time: 0.6315 [2021-03-27 11:01:21 swin_base_patch4_window7_224] INFO: Epoch: [160] [1080/1251] eta: 0:01:48 lr: 0.000449 loss: 3.1145 (3.2126) grad_norm: 1.5332 (inf) time: 0.6312 [2021-03-27 11:01:28 swin_base_patch4_window7_224] INFO: Epoch: [160] [1090/1251] eta: 0:01:42 lr: 0.000449 loss: 3.2987 (3.2128) grad_norm: 1.5463 (inf) time: 0.6306 [2021-03-27 11:01:34 swin_base_patch4_window7_224] INFO: Epoch: [160] [1100/1251] eta: 0:01:35 lr: 0.000449 loss: 3.3868 (3.2135) grad_norm: 1.5463 (inf) time: 0.6227 [2021-03-27 11:01:40 swin_base_patch4_window7_224] INFO: Epoch: [160] [1110/1251] eta: 0:01:29 lr: 0.000449 loss: 3.4903 (3.2147) grad_norm: 1.5537 (inf) time: 0.6296 [2021-03-27 11:01:46 swin_base_patch4_window7_224] INFO: Epoch: [160] [1120/1251] eta: 0:01:23 lr: 0.000449 loss: 3.2362 (3.2151) grad_norm: 1.5191 (inf) time: 0.6367 [2021-03-27 11:01:53 swin_base_patch4_window7_224] INFO: Epoch: [160] [1130/1251] eta: 0:01:16 lr: 0.000449 loss: 3.2220 (3.2170) grad_norm: 1.5539 (inf) time: 0.6345 [2021-03-27 11:01:59 swin_base_patch4_window7_224] INFO: Epoch: [160] [1140/1251] eta: 0:01:10 lr: 0.000449 loss: 3.4169 (3.2181) grad_norm: 1.5802 (inf) time: 0.6342 [2021-03-27 11:02:06 swin_base_patch4_window7_224] INFO: Epoch: [160] [1150/1251] eta: 0:01:04 lr: 0.000449 loss: 3.3150 (3.2171) grad_norm: 1.5393 (inf) time: 0.6345 [2021-03-27 11:02:12 swin_base_patch4_window7_224] INFO: Epoch: [160] [1160/1251] eta: 0:00:57 lr: 0.000448 loss: 3.0366 (3.2147) grad_norm: 1.5732 (inf) time: 0.6303 [2021-03-27 11:02:18 swin_base_patch4_window7_224] INFO: Epoch: [160] [1170/1251] eta: 0:00:51 lr: 0.000448 loss: 3.0663 (3.2150) grad_norm: 1.5963 (inf) time: 0.6263 [2021-03-27 11:02:24 swin_base_patch4_window7_224] INFO: Epoch: [160] [1180/1251] eta: 0:00:45 lr: 0.000448 loss: 3.2190 (3.2152) grad_norm: 1.5729 (inf) time: 0.6343 [2021-03-27 11:02:31 swin_base_patch4_window7_224] INFO: Epoch: [160] [1190/1251] eta: 0:00:38 lr: 0.000448 loss: 3.2417 (3.2164) grad_norm: 1.5729 (inf) time: 0.6376 [2021-03-27 11:02:37 swin_base_patch4_window7_224] INFO: Epoch: [160] [1200/1251] eta: 0:00:32 lr: 0.000448 loss: 3.4260 (3.2181) grad_norm: 1.5683 (inf) time: 0.6264 [2021-03-27 11:02:43 swin_base_patch4_window7_224] INFO: Epoch: [160] [1210/1251] eta: 0:00:26 lr: 0.000448 loss: 3.4062 (3.2175) grad_norm: 1.5683 (inf) time: 0.6268 [2021-03-27 11:02:50 swin_base_patch4_window7_224] INFO: Epoch: [160] [1220/1251] eta: 0:00:19 lr: 0.000448 loss: 3.1442 (3.2178) grad_norm: 1.6148 (inf) time: 0.6298 [2021-03-27 11:02:56 swin_base_patch4_window7_224] INFO: Epoch: [160] [1230/1251] eta: 0:00:13 lr: 0.000448 loss: 3.0566 (3.2155) grad_norm: 1.6148 (inf) time: 0.6288 [2021-03-27 11:03:02 swin_base_patch4_window7_224] INFO: Epoch: [160] [1240/1251] eta: 0:00:06 lr: 0.000448 loss: 2.8216 (3.2121) grad_norm: 1.5559 (inf) time: 0.6335 [2021-03-27 11:03:08 swin_base_patch4_window7_224] INFO: Epoch: [160] [1250/1251] eta: 0:00:00 lr: 0.000448 loss: 2.8235 (3.2113) grad_norm: 1.4873 (inf) time: 0.6272 [2021-03-27 11:04:30 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:18 loss: 1.0630 (1.0630) acc1: 76.5625 (76.5625) acc5: 92.1875 (92.1875) [2021-03-27 11:04:32 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.9470 (0.9593) acc1: 76.5625 (76.7045) acc5: 95.3125 (94.4602) [2021-03-27 11:04:33 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:06 loss: 0.9470 (0.9741) acc1: 75.0000 (76.7113) acc5: 95.3125 (94.8661) [2021-03-27 11:04:35 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8607 (0.9182) acc1: 81.2500 (78.3770) acc5: 95.3125 (95.2621) [2021-03-27 11:04:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8127 (0.9064) acc1: 81.2500 (78.5442) acc5: 96.8750 (95.5412) [2021-03-27 11:04:37 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8418 (0.9019) acc1: 79.6875 (78.6240) acc5: 96.8750 (95.4560) [2021-03-27 11:04:48 swin_base_patch4_window7_224] INFO: * Acc@1 79.374 Acc@5 95.052 loss 0.897 [2021-03-27 11:04:48 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.4% [2021-03-27 11:04:48 swin_base_patch4_window7_224] INFO: Max accuracy: 79.48% [2021-03-27 11:04:52 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 0/1251] eta: 1:28:56 lr: 0.000448 loss: 3.4353 (3.4353) grad_norm: 1.6448 (1.6448) time: 4.2657 [2021-03-27 11:04:59 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 10/1251] eta: 0:20:11 lr: 0.000448 loss: 3.3441 (3.0914) grad_norm: 1.6448 (1.6719) time: 0.9765 [2021-03-27 11:05:05 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 20/1251] eta: 0:16:38 lr: 0.000448 loss: 3.3632 (3.2184) grad_norm: 1.5607 (1.5857) time: 0.6386 [2021-03-27 11:05:12 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 30/1251] eta: 0:15:24 lr: 0.000448 loss: 3.3632 (3.2132) grad_norm: 1.5359 (1.6203) time: 0.6370 [2021-03-27 11:05:18 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 40/1251] eta: 0:14:44 lr: 0.000448 loss: 3.2730 (3.1889) grad_norm: 1.6074 (1.6054) time: 0.6458 [2021-03-27 11:05:24 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 50/1251] eta: 0:14:14 lr: 0.000448 loss: 3.2730 (3.1883) grad_norm: 1.5816 (1.5986) time: 0.6396 [2021-03-27 11:05:31 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 60/1251] eta: 0:13:51 lr: 0.000448 loss: 3.4048 (3.1923) grad_norm: 1.4961 (1.5836) time: 0.6323 [2021-03-27 11:05:37 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 70/1251] eta: 0:13:33 lr: 0.000448 loss: 3.3872 (3.1982) grad_norm: 1.5117 (1.5916) time: 0.6316 [2021-03-27 11:05:43 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 80/1251] eta: 0:13:18 lr: 0.000448 loss: 3.1111 (3.1777) grad_norm: 1.5823 (1.5919) time: 0.6333 [2021-03-27 11:05:50 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 90/1251] eta: 0:13:06 lr: 0.000448 loss: 3.0637 (3.1564) grad_norm: 1.5051 (1.5798) time: 0.6353 [2021-03-27 11:05:56 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 100/1251] eta: 0:12:53 lr: 0.000448 loss: 2.8921 (3.1434) grad_norm: 1.4845 (1.5690) time: 0.6295 [2021-03-27 11:06:02 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 110/1251] eta: 0:12:42 lr: 0.000448 loss: 3.0904 (3.1533) grad_norm: 1.4986 (1.5764) time: 0.6301 [2021-03-27 11:06:09 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 120/1251] eta: 0:12:33 lr: 0.000448 loss: 3.0823 (3.1417) grad_norm: 1.5763 (1.5773) time: 0.6353 [2021-03-27 11:06:15 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 130/1251] eta: 0:12:24 lr: 0.000448 loss: 3.1098 (3.1537) grad_norm: 1.5431 (1.5776) time: 0.6381 [2021-03-27 11:06:22 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 140/1251] eta: 0:12:15 lr: 0.000448 loss: 3.1967 (3.1397) grad_norm: 1.5500 (1.5796) time: 0.6402 [2021-03-27 11:06:28 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 150/1251] eta: 0:12:06 lr: 0.000447 loss: 3.2567 (3.1547) grad_norm: 1.5897 (1.5868) time: 0.6334 [2021-03-27 11:06:34 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 160/1251] eta: 0:11:57 lr: 0.000447 loss: 3.3347 (3.1574) grad_norm: 1.5851 (1.5914) time: 0.6269 [2021-03-27 11:06:40 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 170/1251] eta: 0:11:49 lr: 0.000447 loss: 3.3347 (3.1653) grad_norm: 1.5559 (1.5917) time: 0.6317 [2021-03-27 11:06:47 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 180/1251] eta: 0:11:41 lr: 0.000447 loss: 3.3931 (3.1670) grad_norm: 1.5559 (1.5910) time: 0.6322 [2021-03-27 11:06:53 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 190/1251] eta: 0:11:34 lr: 0.000447 loss: 3.1176 (3.1548) grad_norm: 1.5183 (1.5904) time: 0.6332 [2021-03-27 11:06:59 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 200/1251] eta: 0:11:26 lr: 0.000447 loss: 3.1079 (3.1527) grad_norm: 1.5961 (1.5897) time: 0.6356 [2021-03-27 11:07:06 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 210/1251] eta: 0:11:18 lr: 0.000447 loss: 3.2709 (3.1659) grad_norm: 1.6300 (1.5905) time: 0.6328 [2021-03-27 11:07:12 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 220/1251] eta: 0:11:11 lr: 0.000447 loss: 3.2457 (3.1677) grad_norm: 1.6300 (1.5947) time: 0.6335 [2021-03-27 11:07:18 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 230/1251] eta: 0:11:03 lr: 0.000447 loss: 3.2269 (3.1690) grad_norm: 1.5302 (1.5907) time: 0.6259 [2021-03-27 11:07:25 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 240/1251] eta: 0:10:56 lr: 0.000447 loss: 3.2269 (3.1795) grad_norm: 1.5044 (1.5900) time: 0.6270 [2021-03-27 11:07:31 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 250/1251] eta: 0:10:49 lr: 0.000447 loss: 3.1929 (3.1828) grad_norm: 1.5610 (1.5921) time: 0.6335 [2021-03-27 11:07:37 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 260/1251] eta: 0:10:42 lr: 0.000447 loss: 3.3453 (3.1896) grad_norm: 1.6178 (1.5945) time: 0.6330 [2021-03-27 11:07:44 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 270/1251] eta: 0:10:34 lr: 0.000447 loss: 3.3453 (3.1946) grad_norm: 1.5319 (1.5908) time: 0.6301 [2021-03-27 11:07:50 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 280/1251] eta: 0:10:27 lr: 0.000447 loss: 3.3079 (3.1923) grad_norm: 1.5097 (1.5941) time: 0.6290 [2021-03-27 11:07:56 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 290/1251] eta: 0:10:21 lr: 0.000447 loss: 2.9965 (3.1841) grad_norm: 1.6152 (1.5957) time: 0.6333 [2021-03-27 11:08:03 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 300/1251] eta: 0:10:14 lr: 0.000447 loss: 3.0278 (3.1831) grad_norm: 1.5902 (1.5974) time: 0.6342 [2021-03-27 11:08:09 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 310/1251] eta: 0:10:07 lr: 0.000447 loss: 3.4225 (3.1936) grad_norm: 1.5165 (1.5973) time: 0.6310 [2021-03-27 11:08:15 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 320/1251] eta: 0:10:00 lr: 0.000447 loss: 3.3749 (3.1892) grad_norm: 1.5770 (1.5999) time: 0.6274 [2021-03-27 11:08:21 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 330/1251] eta: 0:09:53 lr: 0.000447 loss: 3.1398 (3.1892) grad_norm: 1.6043 (1.6021) time: 0.6253 [2021-03-27 11:08:28 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 340/1251] eta: 0:09:46 lr: 0.000447 loss: 3.3071 (3.1938) grad_norm: 1.5700 (1.6013) time: 0.6297 [2021-03-27 11:08:34 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 350/1251] eta: 0:09:39 lr: 0.000447 loss: 3.3605 (3.1998) grad_norm: 1.5609 (1.5997) time: 0.6365 [2021-03-27 11:08:40 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 360/1251] eta: 0:09:32 lr: 0.000447 loss: 3.3070 (3.1971) grad_norm: 1.4633 (1.5969) time: 0.6290 [2021-03-27 11:08:47 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 370/1251] eta: 0:09:26 lr: 0.000447 loss: 3.1836 (3.1986) grad_norm: 1.5605 (1.5996) time: 0.6226 [2021-03-27 11:08:53 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 380/1251] eta: 0:09:19 lr: 0.000447 loss: 3.2573 (3.2039) grad_norm: 1.6484 (1.6045) time: 0.6253 [2021-03-27 11:08:59 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 390/1251] eta: 0:09:12 lr: 0.000447 loss: 3.3784 (3.2089) grad_norm: 1.6484 (1.6050) time: 0.6311 [2021-03-27 11:09:06 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 400/1251] eta: 0:09:06 lr: 0.000446 loss: 3.4885 (3.2147) grad_norm: 1.5473 (1.6048) time: 0.6363 [2021-03-27 11:09:12 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 410/1251] eta: 0:08:59 lr: 0.000446 loss: 3.5418 (3.2198) grad_norm: 1.5599 (1.6060) time: 0.6406 [2021-03-27 11:09:18 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 420/1251] eta: 0:08:53 lr: 0.000446 loss: 3.2903 (3.2216) grad_norm: 1.5922 (1.6058) time: 0.6375 [2021-03-27 11:09:25 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 430/1251] eta: 0:08:46 lr: 0.000446 loss: 3.2063 (3.2178) grad_norm: 1.5234 (1.6059) time: 0.6385 [2021-03-27 11:09:31 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 440/1251] eta: 0:08:40 lr: 0.000446 loss: 3.1510 (3.2218) grad_norm: 1.5633 (1.6053) time: 0.6391 [2021-03-27 11:09:37 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 450/1251] eta: 0:08:33 lr: 0.000446 loss: 3.4826 (3.2300) grad_norm: 1.5740 (1.6049) time: 0.6319 [2021-03-27 11:09:44 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 460/1251] eta: 0:08:26 lr: 0.000446 loss: 3.4538 (3.2302) grad_norm: 1.5529 (1.6048) time: 0.6293 [2021-03-27 11:09:50 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 470/1251] eta: 0:08:20 lr: 0.000446 loss: 3.2993 (3.2326) grad_norm: 1.6253 (1.6071) time: 0.6312 [2021-03-27 11:09:56 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 480/1251] eta: 0:08:13 lr: 0.000446 loss: 3.2165 (3.2265) grad_norm: 1.5787 (1.6069) time: 0.6355 [2021-03-27 11:10:03 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 490/1251] eta: 0:08:07 lr: 0.000446 loss: 3.2165 (3.2286) grad_norm: 1.6041 (1.6098) time: 0.6326 [2021-03-27 11:10:09 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 500/1251] eta: 0:08:00 lr: 0.000446 loss: 3.3669 (3.2269) grad_norm: 1.5799 (1.6081) time: 0.6289 [2021-03-27 11:10:16 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 510/1251] eta: 0:07:54 lr: 0.000446 loss: 3.3669 (3.2285) grad_norm: 1.5486 (1.6067) time: 0.6395 [2021-03-27 11:10:22 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 520/1251] eta: 0:07:48 lr: 0.000446 loss: 3.2787 (3.2247) grad_norm: 1.6090 (1.6069) time: 0.6435 [2021-03-27 11:10:28 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 530/1251] eta: 0:07:41 lr: 0.000446 loss: 3.1101 (3.2253) grad_norm: 1.5725 (1.6053) time: 0.6371 [2021-03-27 11:10:35 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 540/1251] eta: 0:07:35 lr: 0.000446 loss: 3.2092 (3.2230) grad_norm: 1.5725 (1.6069) time: 0.6373 [2021-03-27 11:10:41 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 550/1251] eta: 0:07:28 lr: 0.000446 loss: 3.3545 (3.2274) grad_norm: 1.5893 (1.6061) time: 0.6370 [2021-03-27 11:10:47 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 560/1251] eta: 0:07:22 lr: 0.000446 loss: 3.3545 (3.2266) grad_norm: 1.5375 (1.6055) time: 0.6383 [2021-03-27 11:10:54 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 570/1251] eta: 0:07:15 lr: 0.000446 loss: 3.1526 (3.2238) grad_norm: 1.5895 (1.6059) time: 0.6302 [2021-03-27 11:11:00 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 580/1251] eta: 0:07:09 lr: 0.000446 loss: 3.4412 (3.2233) grad_norm: 1.5903 (1.6054) time: 0.6232 [2021-03-27 11:11:06 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 590/1251] eta: 0:07:02 lr: 0.000446 loss: 3.4830 (3.2280) grad_norm: 1.5418 (1.6044) time: 0.6281 [2021-03-27 11:11:12 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 600/1251] eta: 0:06:56 lr: 0.000446 loss: 3.3516 (3.2260) grad_norm: 1.5525 (1.6036) time: 0.6304 [2021-03-27 11:11:19 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 610/1251] eta: 0:06:49 lr: 0.000446 loss: 3.1069 (3.2250) grad_norm: 1.5597 (1.6059) time: 0.6294 [2021-03-27 11:11:25 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 620/1251] eta: 0:06:43 lr: 0.000446 loss: 3.4345 (3.2288) grad_norm: 1.6007 (1.6064) time: 0.6294 [2021-03-27 11:11:31 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 630/1251] eta: 0:06:36 lr: 0.000446 loss: 3.4567 (3.2305) grad_norm: 1.5963 (1.6064) time: 0.6277 [2021-03-27 11:11:38 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 640/1251] eta: 0:06:30 lr: 0.000445 loss: 3.3527 (3.2270) grad_norm: 1.5551 (1.6055) time: 0.6317 [2021-03-27 11:11:44 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 650/1251] eta: 0:06:23 lr: 0.000445 loss: 3.5387 (3.2319) grad_norm: 1.5861 (1.6064) time: 0.6362 [2021-03-27 11:11:50 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 660/1251] eta: 0:06:17 lr: 0.000445 loss: 3.4430 (3.2318) grad_norm: 1.5962 (1.6053) time: 0.6336 [2021-03-27 11:11:57 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 670/1251] eta: 0:06:11 lr: 0.000445 loss: 3.2882 (3.2311) grad_norm: 1.4628 (1.6034) time: 0.6350 [2021-03-27 11:12:03 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 680/1251] eta: 0:06:04 lr: 0.000445 loss: 3.1658 (3.2294) grad_norm: 1.4726 (1.6039) time: 0.6329 [2021-03-27 11:12:09 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 690/1251] eta: 0:05:58 lr: 0.000445 loss: 3.1658 (3.2297) grad_norm: 1.5805 (1.6043) time: 0.6342 [2021-03-27 11:12:16 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 700/1251] eta: 0:05:51 lr: 0.000445 loss: 3.4183 (3.2300) grad_norm: 1.5565 (1.6041) time: 0.6411 [2021-03-27 11:12:22 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 710/1251] eta: 0:05:45 lr: 0.000445 loss: 3.1592 (3.2284) grad_norm: 1.4798 (1.6025) time: 0.6340 [2021-03-27 11:12:29 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 720/1251] eta: 0:05:38 lr: 0.000445 loss: 3.2726 (3.2322) grad_norm: 1.4810 (1.6014) time: 0.6330 [2021-03-27 11:12:35 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 730/1251] eta: 0:05:32 lr: 0.000445 loss: 3.3441 (3.2316) grad_norm: 1.5301 (1.6012) time: 0.6326 [2021-03-27 11:12:41 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 740/1251] eta: 0:05:26 lr: 0.000445 loss: 3.3078 (3.2331) grad_norm: 1.4775 (1.5999) time: 0.6308 [2021-03-27 11:12:48 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 750/1251] eta: 0:05:19 lr: 0.000445 loss: 3.3078 (3.2341) grad_norm: 1.4920 (1.5994) time: 0.6389 [2021-03-27 11:12:54 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 760/1251] eta: 0:05:13 lr: 0.000445 loss: 3.2638 (3.2338) grad_norm: 1.5233 (1.6003) time: 0.6331 [2021-03-27 11:13:00 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 770/1251] eta: 0:05:06 lr: 0.000445 loss: 3.2638 (3.2343) grad_norm: 1.6140 (1.6010) time: 0.6240 [2021-03-27 11:13:07 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 780/1251] eta: 0:05:00 lr: 0.000445 loss: 3.3429 (3.2340) grad_norm: 1.6140 (1.6016) time: 0.6334 [2021-03-27 11:13:13 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 790/1251] eta: 0:04:54 lr: 0.000445 loss: 3.4826 (3.2373) grad_norm: 1.6022 (1.6021) time: 0.6374 [2021-03-27 11:13:19 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 800/1251] eta: 0:04:47 lr: 0.000445 loss: 3.4069 (3.2364) grad_norm: 1.5655 (1.6009) time: 0.6373 [2021-03-27 11:13:26 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 810/1251] eta: 0:04:41 lr: 0.000445 loss: 3.2955 (3.2363) grad_norm: 1.5516 (1.6030) time: 0.6385 [2021-03-27 11:13:32 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 820/1251] eta: 0:04:34 lr: 0.000445 loss: 3.3517 (3.2363) grad_norm: 1.5722 (1.6022) time: 0.6320 [2021-03-27 11:13:38 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 830/1251] eta: 0:04:28 lr: 0.000445 loss: 3.2066 (3.2322) grad_norm: 1.5108 (1.6030) time: 0.6311 [2021-03-27 11:13:45 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 840/1251] eta: 0:04:22 lr: 0.000445 loss: 3.1238 (3.2298) grad_norm: 1.5238 (1.6029) time: 0.6317 [2021-03-27 11:13:51 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 850/1251] eta: 0:04:15 lr: 0.000445 loss: 3.5047 (3.2348) grad_norm: 1.5376 (1.6025) time: 0.6320 [2021-03-27 11:13:57 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 860/1251] eta: 0:04:09 lr: 0.000445 loss: 3.6030 (3.2358) grad_norm: 1.5671 (1.6018) time: 0.6286 [2021-03-27 11:14:03 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 870/1251] eta: 0:04:02 lr: 0.000445 loss: 3.3784 (3.2363) grad_norm: 1.5366 (1.6014) time: 0.6295 [2021-03-27 11:14:10 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 880/1251] eta: 0:03:56 lr: 0.000444 loss: 3.0440 (3.2331) grad_norm: 1.5366 (1.6013) time: 0.6333 [2021-03-27 11:14:16 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 890/1251] eta: 0:03:50 lr: 0.000444 loss: 3.1434 (3.2338) grad_norm: 1.5672 (1.6017) time: 0.6279 [2021-03-27 11:14:22 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 900/1251] eta: 0:03:43 lr: 0.000444 loss: 3.3629 (3.2369) grad_norm: 1.6132 (1.6022) time: 0.6271 [2021-03-27 11:14:29 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 910/1251] eta: 0:03:37 lr: 0.000444 loss: 3.6341 (3.2390) grad_norm: 1.6610 (1.6038) time: 0.6281 [2021-03-27 11:14:35 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 920/1251] eta: 0:03:30 lr: 0.000444 loss: 3.3821 (3.2405) grad_norm: 1.7074 (1.6035) time: 0.6299 [2021-03-27 11:14:41 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 930/1251] eta: 0:03:24 lr: 0.000444 loss: 3.2254 (3.2388) grad_norm: 1.5549 (1.6044) time: 0.6321 [2021-03-27 11:14:48 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 940/1251] eta: 0:03:18 lr: 0.000444 loss: 3.2950 (3.2381) grad_norm: 1.5983 (1.6060) time: 0.6343 [2021-03-27 11:14:54 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 950/1251] eta: 0:03:11 lr: 0.000444 loss: 3.2950 (3.2387) grad_norm: 1.5471 (1.6052) time: 0.6400 [2021-03-27 11:15:00 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 960/1251] eta: 0:03:05 lr: 0.000444 loss: 3.4032 (3.2382) grad_norm: 1.5345 (1.6059) time: 0.6365 [2021-03-27 11:15:07 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 970/1251] eta: 0:02:58 lr: 0.000444 loss: 3.4480 (3.2401) grad_norm: 1.6455 (1.6100) time: 0.6302 [2021-03-27 11:15:13 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 980/1251] eta: 0:02:52 lr: 0.000444 loss: 3.4846 (3.2415) grad_norm: 1.6830 (1.6110) time: 0.6298 [2021-03-27 11:15:19 swin_base_patch4_window7_224] INFO: Epoch: [161] [ 990/1251] eta: 0:02:46 lr: 0.000444 loss: 3.3803 (3.2407) grad_norm: 1.6113 (1.6112) time: 0.6282 [2021-03-27 11:15:25 swin_base_patch4_window7_224] INFO: Epoch: [161] [1000/1251] eta: 0:02:39 lr: 0.000444 loss: 3.4203 (3.2410) grad_norm: 1.6113 (1.6108) time: 0.6260 [2021-03-27 11:15:32 swin_base_patch4_window7_224] INFO: Epoch: [161] [1010/1251] eta: 0:02:33 lr: 0.000444 loss: 3.1758 (3.2396) grad_norm: 1.5900 (1.6109) time: 0.6290 [2021-03-27 11:15:38 swin_base_patch4_window7_224] INFO: Epoch: [161] [1020/1251] eta: 0:02:26 lr: 0.000444 loss: 3.1510 (3.2403) grad_norm: 1.5803 (1.6103) time: 0.6301 [2021-03-27 11:15:44 swin_base_patch4_window7_224] INFO: Epoch: [161] [1030/1251] eta: 0:02:20 lr: 0.000444 loss: 3.4311 (3.2409) grad_norm: 1.5803 (1.6111) time: 0.6300 [2021-03-27 11:15:51 swin_base_patch4_window7_224] INFO: Epoch: [161] [1040/1251] eta: 0:02:14 lr: 0.000444 loss: 3.4311 (3.2416) grad_norm: 1.5271 (1.6101) time: 0.6367 [2021-03-27 11:15:57 swin_base_patch4_window7_224] INFO: Epoch: [161] [1050/1251] eta: 0:02:07 lr: 0.000444 loss: 3.4460 (3.2420) grad_norm: 1.4842 (1.6085) time: 0.6335 [2021-03-27 11:16:03 swin_base_patch4_window7_224] INFO: Epoch: [161] [1060/1251] eta: 0:02:01 lr: 0.000444 loss: 3.2083 (3.2398) grad_norm: 1.4105 (1.6090) time: 0.6240 [2021-03-27 11:16:10 swin_base_patch4_window7_224] INFO: Epoch: [161] [1070/1251] eta: 0:01:55 lr: 0.000444 loss: 2.8044 (3.2372) grad_norm: 1.5205 (1.6085) time: 0.6266 [2021-03-27 11:16:16 swin_base_patch4_window7_224] INFO: Epoch: [161] [1080/1251] eta: 0:01:48 lr: 0.000444 loss: 3.0802 (3.2376) grad_norm: 1.5205 (1.6084) time: 0.6315 [2021-03-27 11:16:22 swin_base_patch4_window7_224] INFO: Epoch: [161] [1090/1251] eta: 0:01:42 lr: 0.000444 loss: 3.3045 (3.2390) grad_norm: 1.5311 (1.6087) time: 0.6315 [2021-03-27 11:16:29 swin_base_patch4_window7_224] INFO: Epoch: [161] [1100/1251] eta: 0:01:36 lr: 0.000444 loss: 3.3205 (3.2400) grad_norm: 1.5130 (1.6090) time: 0.6302 [2021-03-27 11:16:35 swin_base_patch4_window7_224] INFO: Epoch: [161] [1110/1251] eta: 0:01:29 lr: 0.000444 loss: 3.2208 (3.2377) grad_norm: 1.5289 (1.6087) time: 0.6310 [2021-03-27 11:16:41 swin_base_patch4_window7_224] INFO: Epoch: [161] [1120/1251] eta: 0:01:23 lr: 0.000443 loss: 3.1000 (3.2396) grad_norm: 1.5346 (1.6089) time: 0.6339 [2021-03-27 11:16:48 swin_base_patch4_window7_224] INFO: Epoch: [161] [1130/1251] eta: 0:01:16 lr: 0.000443 loss: 3.4794 (3.2408) grad_norm: 1.5783 (1.6098) time: 0.6328 [2021-03-27 11:16:54 swin_base_patch4_window7_224] INFO: Epoch: [161] [1140/1251] eta: 0:01:10 lr: 0.000443 loss: 3.4851 (3.2425) grad_norm: 1.5373 (1.6091) time: 0.6278 [2021-03-27 11:17:00 swin_base_patch4_window7_224] INFO: Epoch: [161] [1150/1251] eta: 0:01:04 lr: 0.000443 loss: 3.3315 (3.2426) grad_norm: 1.4726 (1.6083) time: 0.6270 [2021-03-27 11:17:06 swin_base_patch4_window7_224] INFO: Epoch: [161] [1160/1251] eta: 0:00:57 lr: 0.000443 loss: 3.2526 (3.2427) grad_norm: 1.5762 (1.6089) time: 0.6299 [2021-03-27 11:17:13 swin_base_patch4_window7_224] INFO: Epoch: [161] [1170/1251] eta: 0:00:51 lr: 0.000443 loss: 3.2092 (3.2416) grad_norm: 1.5873 (1.6083) time: 0.6282 [2021-03-27 11:17:19 swin_base_patch4_window7_224] INFO: Epoch: [161] [1180/1251] eta: 0:00:45 lr: 0.000443 loss: 3.2092 (3.2408) grad_norm: 1.4941 (1.6082) time: 0.6251 [2021-03-27 11:17:25 swin_base_patch4_window7_224] INFO: Epoch: [161] [1190/1251] eta: 0:00:38 lr: 0.000443 loss: 3.2052 (3.2412) grad_norm: 1.4540 (1.6067) time: 0.6369 [2021-03-27 11:17:32 swin_base_patch4_window7_224] INFO: Epoch: [161] [1200/1251] eta: 0:00:32 lr: 0.000443 loss: 3.3089 (3.2419) grad_norm: 1.4489 (1.6071) time: 0.6368 [2021-03-27 11:17:38 swin_base_patch4_window7_224] INFO: Epoch: [161] [1210/1251] eta: 0:00:26 lr: 0.000443 loss: 3.1049 (3.2396) grad_norm: 1.5408 (1.6069) time: 0.6263 [2021-03-27 11:17:44 swin_base_patch4_window7_224] INFO: Epoch: [161] [1220/1251] eta: 0:00:19 lr: 0.000443 loss: 2.9882 (3.2383) grad_norm: 1.5097 (1.6064) time: 0.6247 [2021-03-27 11:17:50 swin_base_patch4_window7_224] INFO: Epoch: [161] [1230/1251] eta: 0:00:13 lr: 0.000443 loss: 3.3755 (3.2416) grad_norm: 1.5749 (1.6072) time: 0.6254 [2021-03-27 11:17:57 swin_base_patch4_window7_224] INFO: Epoch: [161] [1240/1251] eta: 0:00:06 lr: 0.000443 loss: 3.5236 (3.2438) grad_norm: 1.6459 (1.6071) time: 0.6325 [2021-03-27 11:18:03 swin_base_patch4_window7_224] INFO: Epoch: [161] [1250/1251] eta: 0:00:00 lr: 0.000443 loss: 3.5236 (3.2450) grad_norm: 1.4822 (1.6061) time: 0.6289 [2021-03-27 11:18:13 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:29 loss: 1.1050 (1.1050) acc1: 67.1875 (67.1875) acc5: 96.8750 (96.8750) [2021-03-27 11:18:15 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8848 (0.9065) acc1: 78.1250 (79.1193) acc5: 95.3125 (95.1705) [2021-03-27 11:18:17 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8509 (0.8894) acc1: 79.6875 (78.8690) acc5: 95.3125 (95.9077) [2021-03-27 11:18:19 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9784 (0.9278) acc1: 76.5625 (78.2258) acc5: 95.3125 (95.0101) [2021-03-27 11:18:21 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9603 (0.9060) acc1: 76.5625 (78.6585) acc5: 95.3125 (95.3887) [2021-03-27 11:18:22 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8084 (0.8971) acc1: 79.6875 (78.7840) acc5: 96.2264 (95.3920) [2021-03-27 11:18:32 swin_base_patch4_window7_224] INFO: * Acc@1 79.654 Acc@5 95.042 loss 0.886 [2021-03-27 11:18:32 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.7% [2021-03-27 11:18:32 swin_base_patch4_window7_224] INFO: Max accuracy: 79.65% [2021-03-27 11:18:37 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 0/1251] eta: 1:29:38 lr: 0.000443 loss: 2.3388 (2.3388) grad_norm: 1.5678 (1.5678) time: 4.2997 [2021-03-27 11:18:43 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 10/1251] eta: 0:20:03 lr: 0.000443 loss: 3.2140 (3.1142) grad_norm: 1.5377 (1.5551) time: 0.9701 [2021-03-27 11:18:49 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 20/1251] eta: 0:16:43 lr: 0.000443 loss: 3.2361 (3.1907) grad_norm: 1.5535 (1.5835) time: 0.6407 [2021-03-27 11:18:56 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 30/1251] eta: 0:15:22 lr: 0.000443 loss: 3.3358 (3.1871) grad_norm: 1.5741 (1.5809) time: 0.6377 [2021-03-27 11:19:02 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 40/1251] eta: 0:14:41 lr: 0.000443 loss: 3.1432 (3.1591) grad_norm: 1.4955 (1.5514) time: 0.6361 [2021-03-27 11:19:09 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 50/1251] eta: 0:14:14 lr: 0.000443 loss: 3.0678 (3.1494) grad_norm: 1.4779 (1.5493) time: 0.6440 [2021-03-27 11:19:15 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 60/1251] eta: 0:13:50 lr: 0.000443 loss: 3.1124 (3.1440) grad_norm: 1.5844 (1.5782) time: 0.6354 [2021-03-27 11:19:21 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 70/1251] eta: 0:13:34 lr: 0.000443 loss: 3.1976 (3.1424) grad_norm: 1.5266 (1.5696) time: 0.6324 [2021-03-27 11:19:27 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 80/1251] eta: 0:13:17 lr: 0.000443 loss: 2.8665 (3.1043) grad_norm: 1.5266 (1.5714) time: 0.6326 [2021-03-27 11:19:34 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 90/1251] eta: 0:13:04 lr: 0.000443 loss: 3.1720 (3.1277) grad_norm: 1.5977 (1.5747) time: 0.6279 [2021-03-27 11:19:40 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 100/1251] eta: 0:12:52 lr: 0.000443 loss: 3.4405 (3.1441) grad_norm: 1.5977 (1.5812) time: 0.6301 [2021-03-27 11:19:46 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 110/1251] eta: 0:12:41 lr: 0.000443 loss: 3.4281 (3.1582) grad_norm: 1.4996 (1.5773) time: 0.6273 [2021-03-27 11:19:53 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 120/1251] eta: 0:12:32 lr: 0.000442 loss: 3.1874 (3.1579) grad_norm: 1.5281 (1.5866) time: 0.6350 [2021-03-27 11:19:59 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 130/1251] eta: 0:12:24 lr: 0.000442 loss: 3.3572 (3.1761) grad_norm: 1.6140 (1.5857) time: 0.6463 [2021-03-27 11:20:05 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 140/1251] eta: 0:12:14 lr: 0.000442 loss: 3.3572 (3.1855) grad_norm: 1.6366 (1.5970) time: 0.6344 [2021-03-27 11:20:12 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 150/1251] eta: 0:12:05 lr: 0.000442 loss: 3.2870 (3.1886) grad_norm: 1.6412 (1.5999) time: 0.6253 [2021-03-27 11:20:18 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 160/1251] eta: 0:11:56 lr: 0.000442 loss: 3.2269 (3.1876) grad_norm: 1.5975 (1.6020) time: 0.6309 [2021-03-27 11:20:24 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 170/1251] eta: 0:11:48 lr: 0.000442 loss: 3.2167 (3.1864) grad_norm: 1.6182 (1.6073) time: 0.6305 [2021-03-27 11:20:31 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 180/1251] eta: 0:11:40 lr: 0.000442 loss: 3.2149 (3.1895) grad_norm: 1.5801 (1.6028) time: 0.6307 [2021-03-27 11:20:37 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 190/1251] eta: 0:11:32 lr: 0.000442 loss: 3.2297 (3.1903) grad_norm: 1.5651 (1.6053) time: 0.6310 [2021-03-27 11:20:43 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 200/1251] eta: 0:11:24 lr: 0.000442 loss: 3.2297 (3.1854) grad_norm: 1.7152 (1.6155) time: 0.6290 [2021-03-27 11:20:50 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 210/1251] eta: 0:11:17 lr: 0.000442 loss: 3.0073 (3.1722) grad_norm: 1.6343 (1.6139) time: 0.6304 [2021-03-27 11:20:56 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 220/1251] eta: 0:11:10 lr: 0.000442 loss: 3.0334 (3.1701) grad_norm: 1.6343 (1.6177) time: 0.6346 [2021-03-27 11:21:02 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 230/1251] eta: 0:11:02 lr: 0.000442 loss: 3.2980 (3.1763) grad_norm: 1.6605 (1.6171) time: 0.6327 [2021-03-27 11:21:09 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 240/1251] eta: 0:10:55 lr: 0.000442 loss: 3.3048 (3.1746) grad_norm: 1.5844 (1.6140) time: 0.6278 [2021-03-27 11:21:15 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 250/1251] eta: 0:10:48 lr: 0.000442 loss: 3.3170 (3.1803) grad_norm: 1.5845 (1.6187) time: 0.6311 [2021-03-27 11:21:21 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 260/1251] eta: 0:10:41 lr: 0.000442 loss: 3.1691 (3.1699) grad_norm: 1.6098 (1.6180) time: 0.6400 [2021-03-27 11:21:28 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 270/1251] eta: 0:10:34 lr: 0.000442 loss: 3.0199 (3.1682) grad_norm: 1.5263 (1.6143) time: 0.6377 [2021-03-27 11:21:34 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 280/1251] eta: 0:10:28 lr: 0.000442 loss: 3.2429 (3.1679) grad_norm: 1.5428 (1.6138) time: 0.6384 [2021-03-27 11:21:40 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 290/1251] eta: 0:10:21 lr: 0.000442 loss: 3.2922 (3.1726) grad_norm: 1.5116 (1.6105) time: 0.6394 [2021-03-27 11:21:47 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 300/1251] eta: 0:10:14 lr: 0.000442 loss: 3.4570 (3.1781) grad_norm: 1.5613 (1.6108) time: 0.6331 [2021-03-27 11:21:53 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 310/1251] eta: 0:10:07 lr: 0.000442 loss: 3.4883 (3.1882) grad_norm: 1.6620 (inf) time: 0.6273 [2021-03-27 11:21:59 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 320/1251] eta: 0:10:00 lr: 0.000442 loss: 3.2298 (3.1845) grad_norm: 1.6620 (inf) time: 0.6231 [2021-03-27 11:22:06 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 330/1251] eta: 0:09:53 lr: 0.000442 loss: 3.3255 (3.1890) grad_norm: 1.5320 (inf) time: 0.6344 [2021-03-27 11:22:12 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 340/1251] eta: 0:09:46 lr: 0.000442 loss: 3.3255 (3.1869) grad_norm: 1.5274 (inf) time: 0.6366 [2021-03-27 11:22:18 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 350/1251] eta: 0:09:40 lr: 0.000442 loss: 3.2382 (3.1921) grad_norm: 1.5655 (inf) time: 0.6315 [2021-03-27 11:22:25 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 360/1251] eta: 0:09:33 lr: 0.000441 loss: 3.3226 (3.1889) grad_norm: 1.5728 (inf) time: 0.6296 [2021-03-27 11:22:31 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 370/1251] eta: 0:09:26 lr: 0.000441 loss: 3.4301 (3.1969) grad_norm: 1.5923 (inf) time: 0.6284 [2021-03-27 11:22:37 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 380/1251] eta: 0:09:19 lr: 0.000441 loss: 3.4974 (3.2035) grad_norm: 1.5306 (inf) time: 0.6334 [2021-03-27 11:22:44 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 390/1251] eta: 0:09:13 lr: 0.000441 loss: 3.2825 (3.2011) grad_norm: 1.5127 (inf) time: 0.6323 [2021-03-27 11:22:50 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 400/1251] eta: 0:09:06 lr: 0.000441 loss: 3.2573 (3.2034) grad_norm: 1.5551 (inf) time: 0.6280 [2021-03-27 11:22:56 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 410/1251] eta: 0:09:00 lr: 0.000441 loss: 3.1041 (3.1984) grad_norm: 1.5551 (inf) time: 0.6338 [2021-03-27 11:23:02 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 420/1251] eta: 0:08:53 lr: 0.000441 loss: 3.1309 (3.2027) grad_norm: 1.6196 (inf) time: 0.6330 [2021-03-27 11:23:09 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 430/1251] eta: 0:08:46 lr: 0.000441 loss: 3.3903 (3.2063) grad_norm: 1.7019 (inf) time: 0.6284 [2021-03-27 11:23:15 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 440/1251] eta: 0:08:40 lr: 0.000441 loss: 3.3932 (3.2083) grad_norm: 1.7361 (inf) time: 0.6327 [2021-03-27 11:23:21 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 450/1251] eta: 0:08:33 lr: 0.000441 loss: 3.2449 (3.2100) grad_norm: 1.5672 (inf) time: 0.6299 [2021-03-27 11:23:28 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 460/1251] eta: 0:08:26 lr: 0.000441 loss: 3.0160 (3.1995) grad_norm: 1.5672 (inf) time: 0.6275 [2021-03-27 11:23:34 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 470/1251] eta: 0:08:20 lr: 0.000441 loss: 2.9240 (3.2029) grad_norm: 1.6513 (inf) time: 0.6374 [2021-03-27 11:23:40 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 480/1251] eta: 0:08:14 lr: 0.000441 loss: 3.0700 (3.2026) grad_norm: 1.5973 (inf) time: 0.6421 [2021-03-27 11:23:47 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 490/1251] eta: 0:08:07 lr: 0.000441 loss: 3.0990 (3.2036) grad_norm: 1.5925 (inf) time: 0.6368 [2021-03-27 11:23:53 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 500/1251] eta: 0:08:01 lr: 0.000441 loss: 3.2901 (3.2068) grad_norm: 1.6126 (inf) time: 0.6345 [2021-03-27 11:23:59 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 510/1251] eta: 0:07:54 lr: 0.000441 loss: 3.3147 (3.2085) grad_norm: 1.6129 (inf) time: 0.6296 [2021-03-27 11:24:06 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 520/1251] eta: 0:07:48 lr: 0.000441 loss: 3.4961 (3.2138) grad_norm: 1.5315 (inf) time: 0.6341 [2021-03-27 11:24:12 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 530/1251] eta: 0:07:41 lr: 0.000441 loss: 3.5411 (3.2191) grad_norm: 1.4437 (inf) time: 0.6393 [2021-03-27 11:24:19 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 540/1251] eta: 0:07:35 lr: 0.000441 loss: 3.4858 (3.2222) grad_norm: 1.5386 (inf) time: 0.6364 [2021-03-27 11:24:25 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 550/1251] eta: 0:07:28 lr: 0.000441 loss: 3.4858 (3.2234) grad_norm: 1.5778 (inf) time: 0.6450 [2021-03-27 11:24:31 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 560/1251] eta: 0:07:22 lr: 0.000441 loss: 3.2318 (3.2200) grad_norm: 1.5877 (inf) time: 0.6379 [2021-03-27 11:24:38 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 570/1251] eta: 0:07:15 lr: 0.000441 loss: 3.2303 (3.2210) grad_norm: 1.5854 (inf) time: 0.6282 [2021-03-27 11:24:44 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 580/1251] eta: 0:07:09 lr: 0.000441 loss: 3.3114 (3.2206) grad_norm: 1.5038 (inf) time: 0.6296 [2021-03-27 11:24:50 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 590/1251] eta: 0:07:02 lr: 0.000441 loss: 3.3114 (3.2207) grad_norm: 1.5775 (inf) time: 0.6345 [2021-03-27 11:24:57 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 600/1251] eta: 0:06:56 lr: 0.000440 loss: 3.2210 (3.2192) grad_norm: 1.5964 (inf) time: 0.6402 [2021-03-27 11:25:03 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 610/1251] eta: 0:06:49 lr: 0.000440 loss: 3.1338 (3.2189) grad_norm: 1.5332 (inf) time: 0.6307 [2021-03-27 11:25:09 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 620/1251] eta: 0:06:43 lr: 0.000440 loss: 3.1937 (3.2205) grad_norm: 1.5831 (inf) time: 0.6260 [2021-03-27 11:25:16 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 630/1251] eta: 0:06:36 lr: 0.000440 loss: 3.1877 (3.2186) grad_norm: 1.6487 (inf) time: 0.6300 [2021-03-27 11:25:22 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 640/1251] eta: 0:06:30 lr: 0.000440 loss: 3.3118 (3.2184) grad_norm: 1.6487 (inf) time: 0.6346 [2021-03-27 11:25:28 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 650/1251] eta: 0:06:23 lr: 0.000440 loss: 3.4076 (3.2213) grad_norm: 1.5170 (inf) time: 0.6320 [2021-03-27 11:25:35 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 660/1251] eta: 0:06:17 lr: 0.000440 loss: 3.4076 (3.2210) grad_norm: 1.5677 (inf) time: 0.6260 [2021-03-27 11:25:41 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 670/1251] eta: 0:06:11 lr: 0.000440 loss: 3.2795 (3.2206) grad_norm: 1.6963 (inf) time: 0.6292 [2021-03-27 11:25:47 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 680/1251] eta: 0:06:04 lr: 0.000440 loss: 3.2795 (3.2205) grad_norm: 1.6050 (inf) time: 0.6308 [2021-03-27 11:25:53 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 690/1251] eta: 0:05:58 lr: 0.000440 loss: 3.1812 (3.2212) grad_norm: 1.5567 (inf) time: 0.6270 [2021-03-27 11:26:00 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 700/1251] eta: 0:05:51 lr: 0.000440 loss: 3.4742 (3.2246) grad_norm: 1.6348 (inf) time: 0.6303 [2021-03-27 11:26:06 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 710/1251] eta: 0:05:45 lr: 0.000440 loss: 3.4915 (3.2251) grad_norm: 1.6097 (inf) time: 0.6337 [2021-03-27 11:26:12 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 720/1251] eta: 0:05:38 lr: 0.000440 loss: 3.5278 (3.2323) grad_norm: 1.4886 (inf) time: 0.6331 [2021-03-27 11:26:19 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 730/1251] eta: 0:05:32 lr: 0.000440 loss: 3.4600 (3.2277) grad_norm: 1.4704 (inf) time: 0.6399 [2021-03-27 11:26:25 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 740/1251] eta: 0:05:26 lr: 0.000440 loss: 3.0170 (3.2295) grad_norm: 1.4447 (inf) time: 0.6461 [2021-03-27 11:26:32 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 750/1251] eta: 0:05:19 lr: 0.000440 loss: 3.2674 (3.2261) grad_norm: 1.5802 (inf) time: 0.6436 [2021-03-27 11:26:38 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 760/1251] eta: 0:05:13 lr: 0.000440 loss: 3.2958 (3.2291) grad_norm: 1.5753 (inf) time: 0.6450 [2021-03-27 11:26:45 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 770/1251] eta: 0:05:07 lr: 0.000440 loss: 3.5105 (3.2316) grad_norm: 1.5628 (inf) time: 0.6418 [2021-03-27 11:26:51 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 780/1251] eta: 0:05:00 lr: 0.000440 loss: 3.3021 (3.2309) grad_norm: 1.7009 (inf) time: 0.6335 [2021-03-27 11:26:57 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 790/1251] eta: 0:04:54 lr: 0.000440 loss: 3.2663 (3.2302) grad_norm: 1.5325 (inf) time: 0.6290 [2021-03-27 11:27:04 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 800/1251] eta: 0:04:47 lr: 0.000440 loss: 3.2663 (3.2298) grad_norm: 1.5222 (inf) time: 0.6313 [2021-03-27 11:27:10 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 810/1251] eta: 0:04:41 lr: 0.000440 loss: 3.4107 (3.2341) grad_norm: 1.5222 (inf) time: 0.6324 [2021-03-27 11:27:16 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 820/1251] eta: 0:04:34 lr: 0.000440 loss: 3.5958 (3.2362) grad_norm: 1.6228 (inf) time: 0.6310 [2021-03-27 11:27:22 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 830/1251] eta: 0:04:28 lr: 0.000440 loss: 3.3454 (3.2349) grad_norm: 1.5945 (inf) time: 0.6320 [2021-03-27 11:27:29 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 840/1251] eta: 0:04:22 lr: 0.000440 loss: 3.2152 (3.2334) grad_norm: 1.4813 (inf) time: 0.6261 [2021-03-27 11:27:35 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 850/1251] eta: 0:04:15 lr: 0.000439 loss: 3.2140 (3.2316) grad_norm: 1.5257 (inf) time: 0.6258 [2021-03-27 11:27:41 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 860/1251] eta: 0:04:09 lr: 0.000439 loss: 3.3699 (3.2345) grad_norm: 1.5583 (inf) time: 0.6304 [2021-03-27 11:27:48 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 870/1251] eta: 0:04:02 lr: 0.000439 loss: 3.3834 (3.2359) grad_norm: 1.5829 (inf) time: 0.6346 [2021-03-27 11:27:54 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 880/1251] eta: 0:03:56 lr: 0.000439 loss: 3.2656 (3.2335) grad_norm: 1.5476 (inf) time: 0.6376 [2021-03-27 11:28:00 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 890/1251] eta: 0:03:50 lr: 0.000439 loss: 3.0438 (3.2333) grad_norm: 1.5822 (inf) time: 0.6330 [2021-03-27 11:28:07 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 900/1251] eta: 0:03:43 lr: 0.000439 loss: 3.1461 (3.2326) grad_norm: 1.6747 (inf) time: 0.6314 [2021-03-27 11:28:13 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 910/1251] eta: 0:03:37 lr: 0.000439 loss: 3.2864 (3.2345) grad_norm: 1.6747 (inf) time: 0.6311 [2021-03-27 11:28:19 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 920/1251] eta: 0:03:30 lr: 0.000439 loss: 3.2864 (3.2337) grad_norm: 1.5964 (inf) time: 0.6244 [2021-03-27 11:28:26 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 930/1251] eta: 0:03:24 lr: 0.000439 loss: 3.2484 (3.2346) grad_norm: 1.6801 (inf) time: 0.6286 [2021-03-27 11:28:32 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 940/1251] eta: 0:03:18 lr: 0.000439 loss: 3.2494 (3.2340) grad_norm: 1.6564 (inf) time: 0.6384 [2021-03-27 11:28:38 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 950/1251] eta: 0:03:11 lr: 0.000439 loss: 3.2334 (3.2345) grad_norm: 1.5333 (inf) time: 0.6350 [2021-03-27 11:28:45 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 960/1251] eta: 0:03:05 lr: 0.000439 loss: 3.2459 (3.2331) grad_norm: 1.5727 (inf) time: 0.6332 [2021-03-27 11:28:51 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 970/1251] eta: 0:02:58 lr: 0.000439 loss: 3.2862 (3.2340) grad_norm: 1.6393 (inf) time: 0.6323 [2021-03-27 11:28:57 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 980/1251] eta: 0:02:52 lr: 0.000439 loss: 3.1838 (3.2314) grad_norm: 1.5886 (inf) time: 0.6291 [2021-03-27 11:29:03 swin_base_patch4_window7_224] INFO: Epoch: [162] [ 990/1251] eta: 0:02:46 lr: 0.000439 loss: 3.1838 (3.2324) grad_norm: 1.5417 (inf) time: 0.6267 [2021-03-27 11:29:10 swin_base_patch4_window7_224] INFO: Epoch: [162] [1000/1251] eta: 0:02:39 lr: 0.000439 loss: 3.3800 (3.2324) grad_norm: 1.6251 (inf) time: 0.6279 [2021-03-27 11:29:16 swin_base_patch4_window7_224] INFO: Epoch: [162] [1010/1251] eta: 0:02:33 lr: 0.000439 loss: 3.4719 (3.2346) grad_norm: 1.5800 (inf) time: 0.6353 [2021-03-27 11:29:23 swin_base_patch4_window7_224] INFO: Epoch: [162] [1020/1251] eta: 0:02:27 lr: 0.000439 loss: 3.3820 (3.2352) grad_norm: 1.5800 (inf) time: 0.6377 [2021-03-27 11:29:29 swin_base_patch4_window7_224] INFO: Epoch: [162] [1030/1251] eta: 0:02:20 lr: 0.000439 loss: 3.3260 (3.2363) grad_norm: 1.6160 (inf) time: 0.6348 [2021-03-27 11:29:35 swin_base_patch4_window7_224] INFO: Epoch: [162] [1040/1251] eta: 0:02:14 lr: 0.000439 loss: 3.5327 (3.2378) grad_norm: 1.6129 (inf) time: 0.6315 [2021-03-27 11:29:41 swin_base_patch4_window7_224] INFO: Epoch: [162] [1050/1251] eta: 0:02:07 lr: 0.000439 loss: 3.5014 (3.2377) grad_norm: 1.6275 (inf) time: 0.6304 [2021-03-27 11:29:48 swin_base_patch4_window7_224] INFO: Epoch: [162] [1060/1251] eta: 0:02:01 lr: 0.000439 loss: 3.2741 (3.2366) grad_norm: 1.5184 (inf) time: 0.6285 [2021-03-27 11:29:54 swin_base_patch4_window7_224] INFO: Epoch: [162] [1070/1251] eta: 0:01:55 lr: 0.000439 loss: 3.4156 (3.2382) grad_norm: 1.4685 (inf) time: 0.6287 [2021-03-27 11:30:00 swin_base_patch4_window7_224] INFO: Epoch: [162] [1080/1251] eta: 0:01:48 lr: 0.000439 loss: 3.4216 (3.2387) grad_norm: 1.5183 (inf) time: 0.6309 [2021-03-27 11:30:07 swin_base_patch4_window7_224] INFO: Epoch: [162] [1090/1251] eta: 0:01:42 lr: 0.000438 loss: 3.2397 (3.2378) grad_norm: 1.5183 (inf) time: 0.6297 [2021-03-27 11:30:13 swin_base_patch4_window7_224] INFO: Epoch: [162] [1100/1251] eta: 0:01:36 lr: 0.000438 loss: 3.2877 (3.2383) grad_norm: 1.4992 (inf) time: 0.6250 [2021-03-27 11:30:19 swin_base_patch4_window7_224] INFO: Epoch: [162] [1110/1251] eta: 0:01:29 lr: 0.000438 loss: 3.0792 (3.2356) grad_norm: 1.4511 (inf) time: 0.6260 [2021-03-27 11:30:26 swin_base_patch4_window7_224] INFO: Epoch: [162] [1120/1251] eta: 0:01:23 lr: 0.000438 loss: 3.3785 (3.2377) grad_norm: 1.5243 (inf) time: 0.6336 [2021-03-27 11:30:32 swin_base_patch4_window7_224] INFO: Epoch: [162] [1130/1251] eta: 0:01:16 lr: 0.000438 loss: 3.3203 (3.2363) grad_norm: 1.5451 (inf) time: 0.6324 [2021-03-27 11:30:38 swin_base_patch4_window7_224] INFO: Epoch: [162] [1140/1251] eta: 0:01:10 lr: 0.000438 loss: 3.3483 (3.2391) grad_norm: 1.5451 (inf) time: 0.6303 [2021-03-27 11:30:44 swin_base_patch4_window7_224] INFO: Epoch: [162] [1150/1251] eta: 0:01:04 lr: 0.000438 loss: 3.5772 (3.2395) grad_norm: 1.5480 (inf) time: 0.6312 [2021-03-27 11:30:51 swin_base_patch4_window7_224] INFO: Epoch: [162] [1160/1251] eta: 0:00:57 lr: 0.000438 loss: 3.6010 (3.2415) grad_norm: 1.5477 (inf) time: 0.6337 [2021-03-27 11:30:57 swin_base_patch4_window7_224] INFO: Epoch: [162] [1170/1251] eta: 0:00:51 lr: 0.000438 loss: 3.6338 (3.2453) grad_norm: 1.5169 (inf) time: 0.6352 [2021-03-27 11:31:03 swin_base_patch4_window7_224] INFO: Epoch: [162] [1180/1251] eta: 0:00:45 lr: 0.000438 loss: 3.4477 (3.2456) grad_norm: 1.5186 (inf) time: 0.6324 [2021-03-27 11:31:10 swin_base_patch4_window7_224] INFO: Epoch: [162] [1190/1251] eta: 0:00:38 lr: 0.000438 loss: 3.4069 (3.2484) grad_norm: 1.5871 (inf) time: 0.6299 [2021-03-27 11:31:16 swin_base_patch4_window7_224] INFO: Epoch: [162] [1200/1251] eta: 0:00:32 lr: 0.000438 loss: 3.4176 (3.2494) grad_norm: 1.6171 (inf) time: 0.6244 [2021-03-27 11:31:22 swin_base_patch4_window7_224] INFO: Epoch: [162] [1210/1251] eta: 0:00:26 lr: 0.000438 loss: 3.3460 (3.2494) grad_norm: 1.5869 (inf) time: 0.6296 [2021-03-27 11:31:29 swin_base_patch4_window7_224] INFO: Epoch: [162] [1220/1251] eta: 0:00:19 lr: 0.000438 loss: 3.2790 (3.2482) grad_norm: 1.5635 (inf) time: 0.6329 [2021-03-27 11:31:35 swin_base_patch4_window7_224] INFO: Epoch: [162] [1230/1251] eta: 0:00:13 lr: 0.000438 loss: 3.3013 (3.2468) grad_norm: 1.5251 (inf) time: 0.6323 [2021-03-27 11:31:41 swin_base_patch4_window7_224] INFO: Epoch: [162] [1240/1251] eta: 0:00:06 lr: 0.000438 loss: 3.2674 (3.2466) grad_norm: 1.4414 (inf) time: 0.6421 [2021-03-27 11:31:48 swin_base_patch4_window7_224] INFO: Epoch: [162] [1250/1251] eta: 0:00:00 lr: 0.000438 loss: 3.5144 (3.2499) grad_norm: 1.4759 (inf) time: 0.6366 [2021-03-27 11:31:57 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 0.9799 (0.9799) acc1: 73.4375 (73.4375) acc5: 95.3125 (95.3125) [2021-03-27 11:32:00 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9030 (0.8933) acc1: 76.5625 (77.4148) acc5: 96.8750 (96.0227) [2021-03-27 11:32:02 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8379 (0.8587) acc1: 78.1250 (78.7202) acc5: 96.8750 (95.6845) [2021-03-27 11:32:05 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8379 (0.8734) acc1: 81.2500 (79.0827) acc5: 93.7500 (95.2621) [2021-03-27 11:32:07 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9509 (0.8983) acc1: 78.1250 (78.2774) acc5: 93.7500 (95.1601) [2021-03-27 11:32:08 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9191 (0.8949) acc1: 78.1250 (78.4000) acc5: 95.3125 (95.2000) [2021-03-27 11:32:21 swin_base_patch4_window7_224] INFO: * Acc@1 79.536 Acc@5 95.138 loss 0.877 [2021-03-27 11:32:21 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.5% [2021-03-27 11:32:21 swin_base_patch4_window7_224] INFO: Max accuracy: 79.65% [2021-03-27 11:32:25 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 0/1251] eta: 1:25:12 lr: 0.000438 loss: 3.6414 (3.6414) grad_norm: 1.7231 (1.7231) time: 4.0864 [2021-03-27 11:32:31 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 10/1251] eta: 0:19:46 lr: 0.000438 loss: 3.0903 (3.2056) grad_norm: 1.5770 (1.5495) time: 0.9559 [2021-03-27 11:32:37 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 20/1251] eta: 0:16:24 lr: 0.000438 loss: 3.3513 (3.3359) grad_norm: 1.5770 (1.5525) time: 0.6353 [2021-03-27 11:32:44 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 30/1251] eta: 0:15:08 lr: 0.000438 loss: 3.5016 (3.2883) grad_norm: 1.6365 (1.6115) time: 0.6269 [2021-03-27 11:32:50 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 40/1251] eta: 0:14:31 lr: 0.000438 loss: 3.2291 (3.2833) grad_norm: 1.6744 (1.6133) time: 0.6364 [2021-03-27 11:32:57 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 50/1251] eta: 0:14:06 lr: 0.000438 loss: 3.2525 (3.2695) grad_norm: 1.5559 (1.5961) time: 0.6438 [2021-03-27 11:33:03 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 60/1251] eta: 0:13:45 lr: 0.000438 loss: 3.2821 (3.2707) grad_norm: 1.5222 (1.5962) time: 0.6375 [2021-03-27 11:33:09 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 70/1251] eta: 0:13:28 lr: 0.000438 loss: 3.3943 (3.2882) grad_norm: 1.5222 (1.5855) time: 0.6349 [2021-03-27 11:33:16 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 80/1251] eta: 0:13:15 lr: 0.000437 loss: 3.3166 (3.2701) grad_norm: 1.4988 (1.5852) time: 0.6369 [2021-03-27 11:33:22 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 90/1251] eta: 0:13:01 lr: 0.000437 loss: 3.1561 (3.2612) grad_norm: 1.5273 (1.5844) time: 0.6306 [2021-03-27 11:33:28 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 100/1251] eta: 0:12:50 lr: 0.000437 loss: 3.2235 (3.2478) grad_norm: 1.5433 (1.5831) time: 0.6293 [2021-03-27 11:33:35 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 110/1251] eta: 0:12:40 lr: 0.000437 loss: 3.4075 (3.2587) grad_norm: 1.5226 (1.5858) time: 0.6381 [2021-03-27 11:33:41 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 120/1251] eta: 0:12:31 lr: 0.000437 loss: 3.3559 (3.2504) grad_norm: 1.5328 (1.5920) time: 0.6389 [2021-03-27 11:33:47 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 130/1251] eta: 0:12:22 lr: 0.000437 loss: 3.1775 (3.2615) grad_norm: 1.4848 (1.5835) time: 0.6392 [2021-03-27 11:33:54 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 140/1251] eta: 0:12:13 lr: 0.000437 loss: 3.3472 (3.2626) grad_norm: 1.4939 (1.5873) time: 0.6346 [2021-03-27 11:34:00 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 150/1251] eta: 0:12:05 lr: 0.000437 loss: 3.3897 (3.2664) grad_norm: 1.5329 (1.5888) time: 0.6356 [2021-03-27 11:34:06 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 160/1251] eta: 0:11:56 lr: 0.000437 loss: 3.2059 (3.2514) grad_norm: 1.5436 (1.5846) time: 0.6338 [2021-03-27 11:34:13 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 170/1251] eta: 0:11:48 lr: 0.000437 loss: 2.9663 (3.2296) grad_norm: 1.5436 (1.5838) time: 0.6300 [2021-03-27 11:34:19 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 180/1251] eta: 0:11:40 lr: 0.000437 loss: 3.1469 (3.2321) grad_norm: 1.4950 (1.5808) time: 0.6318 [2021-03-27 11:34:25 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 190/1251] eta: 0:11:32 lr: 0.000437 loss: 3.2865 (3.2234) grad_norm: 1.5009 (1.5796) time: 0.6257 [2021-03-27 11:34:32 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 200/1251] eta: 0:11:25 lr: 0.000437 loss: 3.3685 (3.2354) grad_norm: 1.5725 (1.5845) time: 0.6335 [2021-03-27 11:34:38 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 210/1251] eta: 0:11:17 lr: 0.000437 loss: 3.4484 (3.2387) grad_norm: 1.5916 (1.5855) time: 0.6389 [2021-03-27 11:34:44 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 220/1251] eta: 0:11:10 lr: 0.000437 loss: 3.2521 (3.2382) grad_norm: 1.5916 (1.5876) time: 0.6304 [2021-03-27 11:34:51 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 230/1251] eta: 0:11:02 lr: 0.000437 loss: 3.0303 (3.2338) grad_norm: 1.5984 (1.5993) time: 0.6284 [2021-03-27 11:34:57 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 240/1251] eta: 0:10:56 lr: 0.000437 loss: 3.3604 (3.2414) grad_norm: 1.5777 (1.5981) time: 0.6375 [2021-03-27 11:35:03 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 250/1251] eta: 0:10:48 lr: 0.000437 loss: 3.4316 (3.2503) grad_norm: 1.5780 (1.6015) time: 0.6380 [2021-03-27 11:35:10 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 260/1251] eta: 0:10:42 lr: 0.000437 loss: 3.3778 (3.2462) grad_norm: 1.5780 (1.5988) time: 0.6342 [2021-03-27 11:35:16 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 270/1251] eta: 0:10:34 lr: 0.000437 loss: 3.3070 (3.2476) grad_norm: 1.5262 (1.5996) time: 0.6278 [2021-03-27 11:35:22 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 280/1251] eta: 0:10:27 lr: 0.000437 loss: 3.2856 (3.2430) grad_norm: 1.5704 (1.6018) time: 0.6218 [2021-03-27 11:35:29 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 290/1251] eta: 0:10:20 lr: 0.000437 loss: 2.9282 (3.2341) grad_norm: 1.5742 (1.6017) time: 0.6307 [2021-03-27 11:35:35 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 300/1251] eta: 0:10:13 lr: 0.000437 loss: 2.9503 (3.2295) grad_norm: 1.5742 (1.6040) time: 0.6337 [2021-03-27 11:35:41 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 310/1251] eta: 0:10:06 lr: 0.000437 loss: 3.2801 (3.2384) grad_norm: 1.4904 (1.6044) time: 0.6296 [2021-03-27 11:35:47 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 320/1251] eta: 0:09:59 lr: 0.000437 loss: 3.3865 (3.2469) grad_norm: 1.5403 (1.6079) time: 0.6273 [2021-03-27 11:35:54 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 330/1251] eta: 0:09:52 lr: 0.000436 loss: 3.5045 (3.2527) grad_norm: 1.5620 (1.6073) time: 0.6319 [2021-03-27 11:36:00 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 340/1251] eta: 0:09:46 lr: 0.000436 loss: 3.3091 (3.2468) grad_norm: 1.5620 (1.6070) time: 0.6330 [2021-03-27 11:36:06 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 350/1251] eta: 0:09:39 lr: 0.000436 loss: 3.2343 (3.2462) grad_norm: 1.5654 (1.6062) time: 0.6338 [2021-03-27 11:36:13 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 360/1251] eta: 0:09:32 lr: 0.000436 loss: 3.4538 (3.2504) grad_norm: 1.5691 (1.6071) time: 0.6341 [2021-03-27 11:36:19 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 370/1251] eta: 0:09:26 lr: 0.000436 loss: 3.4939 (3.2510) grad_norm: 1.5691 (1.6057) time: 0.6301 [2021-03-27 11:36:25 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 380/1251] eta: 0:09:19 lr: 0.000436 loss: 3.4133 (3.2529) grad_norm: 1.5506 (1.6047) time: 0.6306 [2021-03-27 11:36:32 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 390/1251] eta: 0:09:12 lr: 0.000436 loss: 3.3624 (3.2522) grad_norm: 1.5126 (1.6034) time: 0.6310 [2021-03-27 11:36:38 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 400/1251] eta: 0:09:06 lr: 0.000436 loss: 3.2364 (3.2536) grad_norm: 1.5398 (1.6039) time: 0.6455 [2021-03-27 11:36:45 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 410/1251] eta: 0:09:00 lr: 0.000436 loss: 3.1362 (3.2486) grad_norm: 1.5499 (1.6052) time: 0.6506 [2021-03-27 11:36:51 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 420/1251] eta: 0:08:53 lr: 0.000436 loss: 3.0962 (3.2483) grad_norm: 1.5900 (1.6087) time: 0.6414 [2021-03-27 11:36:57 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 430/1251] eta: 0:08:47 lr: 0.000436 loss: 3.2543 (3.2460) grad_norm: 1.5778 (1.6068) time: 0.6341 [2021-03-27 11:37:04 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 440/1251] eta: 0:08:40 lr: 0.000436 loss: 3.2543 (3.2421) grad_norm: 1.5676 (1.6062) time: 0.6325 [2021-03-27 11:37:10 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 450/1251] eta: 0:08:34 lr: 0.000436 loss: 3.3247 (3.2475) grad_norm: 1.5183 (1.6054) time: 0.6390 [2021-03-27 11:37:16 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 460/1251] eta: 0:08:27 lr: 0.000436 loss: 3.4607 (3.2523) grad_norm: 1.5159 (1.6065) time: 0.6345 [2021-03-27 11:37:23 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 470/1251] eta: 0:08:20 lr: 0.000436 loss: 3.3532 (3.2429) grad_norm: 1.4928 (1.6049) time: 0.6273 [2021-03-27 11:37:29 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 480/1251] eta: 0:08:14 lr: 0.000436 loss: 3.2699 (3.2445) grad_norm: 1.5308 (1.6058) time: 0.6301 [2021-03-27 11:37:35 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 490/1251] eta: 0:08:07 lr: 0.000436 loss: 3.3095 (3.2418) grad_norm: 1.5885 (1.6055) time: 0.6354 [2021-03-27 11:37:42 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 500/1251] eta: 0:08:01 lr: 0.000436 loss: 3.2942 (3.2408) grad_norm: 1.4702 (1.6030) time: 0.6315 [2021-03-27 11:37:48 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 510/1251] eta: 0:07:54 lr: 0.000436 loss: 3.3499 (3.2413) grad_norm: 1.5171 (1.6026) time: 0.6287 [2021-03-27 11:37:54 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 520/1251] eta: 0:07:48 lr: 0.000436 loss: 3.3888 (3.2401) grad_norm: 1.6078 (1.6021) time: 0.6359 [2021-03-27 11:38:01 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 530/1251] eta: 0:07:41 lr: 0.000436 loss: 3.4942 (3.2473) grad_norm: 1.5816 (1.6021) time: 0.6417 [2021-03-27 11:38:07 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 540/1251] eta: 0:07:35 lr: 0.000436 loss: 3.5056 (3.2460) grad_norm: 1.6319 (1.6042) time: 0.6319 [2021-03-27 11:38:14 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 550/1251] eta: 0:07:28 lr: 0.000436 loss: 3.3051 (3.2474) grad_norm: 1.5465 (1.6032) time: 0.6370 [2021-03-27 11:38:20 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 560/1251] eta: 0:07:22 lr: 0.000436 loss: 3.3000 (3.2473) grad_norm: 1.5734 (1.6048) time: 0.6456 [2021-03-27 11:38:26 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 570/1251] eta: 0:07:16 lr: 0.000435 loss: 3.1564 (3.2466) grad_norm: 1.6115 (1.6030) time: 0.6343 [2021-03-27 11:38:33 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 580/1251] eta: 0:07:09 lr: 0.000435 loss: 3.1166 (3.2446) grad_norm: 1.5634 (1.6025) time: 0.6289 [2021-03-27 11:38:39 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 590/1251] eta: 0:07:02 lr: 0.000435 loss: 3.0844 (3.2430) grad_norm: 1.5720 (1.6043) time: 0.6282 [2021-03-27 11:38:45 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 600/1251] eta: 0:06:56 lr: 0.000435 loss: 3.2666 (3.2443) grad_norm: 1.5778 (1.6044) time: 0.6312 [2021-03-27 11:38:51 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 610/1251] eta: 0:06:49 lr: 0.000435 loss: 3.2955 (3.2454) grad_norm: 1.6063 (1.6058) time: 0.6313 [2021-03-27 11:38:58 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 620/1251] eta: 0:06:43 lr: 0.000435 loss: 3.1230 (3.2412) grad_norm: 1.5759 (1.6050) time: 0.6274 [2021-03-27 11:39:04 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 630/1251] eta: 0:06:36 lr: 0.000435 loss: 3.3098 (3.2415) grad_norm: 1.5199 (1.6039) time: 0.6239 [2021-03-27 11:39:10 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 640/1251] eta: 0:06:30 lr: 0.000435 loss: 3.3287 (3.2445) grad_norm: 1.5131 (1.6036) time: 0.6213 [2021-03-27 11:39:16 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 650/1251] eta: 0:06:23 lr: 0.000435 loss: 3.2981 (3.2431) grad_norm: 1.5437 (1.6035) time: 0.6259 [2021-03-27 11:39:23 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 660/1251] eta: 0:06:17 lr: 0.000435 loss: 3.2709 (3.2443) grad_norm: 1.5542 (1.6043) time: 0.6360 [2021-03-27 11:39:29 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 670/1251] eta: 0:06:10 lr: 0.000435 loss: 3.3974 (3.2430) grad_norm: 1.5557 (1.6042) time: 0.6330 [2021-03-27 11:39:36 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 680/1251] eta: 0:06:04 lr: 0.000435 loss: 3.2205 (3.2431) grad_norm: 1.5952 (1.6038) time: 0.6323 [2021-03-27 11:39:42 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 690/1251] eta: 0:05:58 lr: 0.000435 loss: 3.3699 (3.2392) grad_norm: 1.5299 (1.6040) time: 0.6301 [2021-03-27 11:39:48 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 700/1251] eta: 0:05:51 lr: 0.000435 loss: 3.2623 (3.2402) grad_norm: 1.5953 (1.6045) time: 0.6210 [2021-03-27 11:39:54 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 710/1251] eta: 0:05:45 lr: 0.000435 loss: 3.1410 (3.2351) grad_norm: 1.5757 (1.6040) time: 0.6271 [2021-03-27 11:40:01 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 720/1251] eta: 0:05:38 lr: 0.000435 loss: 3.1410 (3.2353) grad_norm: 1.5740 (1.6059) time: 0.6368 [2021-03-27 11:40:07 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 730/1251] eta: 0:05:32 lr: 0.000435 loss: 3.3642 (3.2354) grad_norm: 1.6508 (1.6085) time: 0.6365 [2021-03-27 11:40:13 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 740/1251] eta: 0:05:25 lr: 0.000435 loss: 3.1726 (3.2347) grad_norm: 1.5684 (1.6071) time: 0.6343 [2021-03-27 11:40:20 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 750/1251] eta: 0:05:19 lr: 0.000435 loss: 3.1997 (3.2355) grad_norm: 1.4842 (1.6061) time: 0.6404 [2021-03-27 11:40:26 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 760/1251] eta: 0:05:13 lr: 0.000435 loss: 3.4170 (3.2378) grad_norm: 1.5181 (1.6061) time: 0.6363 [2021-03-27 11:40:32 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 770/1251] eta: 0:05:06 lr: 0.000435 loss: 3.3922 (3.2359) grad_norm: 1.5206 (1.6065) time: 0.6258 [2021-03-27 11:40:39 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 780/1251] eta: 0:05:00 lr: 0.000435 loss: 3.0993 (3.2366) grad_norm: 1.5268 (1.6073) time: 0.6271 [2021-03-27 11:40:45 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 790/1251] eta: 0:04:53 lr: 0.000435 loss: 3.2155 (3.2332) grad_norm: 1.5030 (1.6064) time: 0.6314 [2021-03-27 11:40:51 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 800/1251] eta: 0:04:47 lr: 0.000435 loss: 3.1201 (3.2320) grad_norm: 1.4976 (1.6063) time: 0.6361 [2021-03-27 11:40:58 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 810/1251] eta: 0:04:41 lr: 0.000434 loss: 3.2179 (3.2315) grad_norm: 1.5829 (1.6065) time: 0.6313 [2021-03-27 11:41:04 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 820/1251] eta: 0:04:34 lr: 0.000434 loss: 3.3413 (3.2332) grad_norm: 1.5350 (1.6055) time: 0.6317 [2021-03-27 11:41:10 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 830/1251] eta: 0:04:28 lr: 0.000434 loss: 3.5417 (3.2352) grad_norm: 1.5004 (1.6048) time: 0.6348 [2021-03-27 11:41:17 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 840/1251] eta: 0:04:21 lr: 0.000434 loss: 3.3784 (3.2342) grad_norm: 1.5284 (1.6039) time: 0.6311 [2021-03-27 11:41:23 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 850/1251] eta: 0:04:15 lr: 0.000434 loss: 3.3799 (3.2375) grad_norm: 1.5851 (1.6050) time: 0.6352 [2021-03-27 11:41:29 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 860/1251] eta: 0:04:09 lr: 0.000434 loss: 3.4915 (3.2407) grad_norm: 1.6608 (1.6064) time: 0.6308 [2021-03-27 11:41:36 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 870/1251] eta: 0:04:02 lr: 0.000434 loss: 3.5155 (3.2431) grad_norm: 1.6081 (1.6067) time: 0.6285 [2021-03-27 11:41:42 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 880/1251] eta: 0:03:56 lr: 0.000434 loss: 3.4830 (3.2414) grad_norm: 1.5440 (1.6063) time: 0.6315 [2021-03-27 11:41:48 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 890/1251] eta: 0:03:49 lr: 0.000434 loss: 3.0955 (3.2387) grad_norm: 1.6366 (1.6081) time: 0.6323 [2021-03-27 11:41:55 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 900/1251] eta: 0:03:43 lr: 0.000434 loss: 2.9634 (3.2359) grad_norm: 1.6398 (1.6079) time: 0.6326 [2021-03-27 11:42:01 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 910/1251] eta: 0:03:37 lr: 0.000434 loss: 3.1572 (3.2358) grad_norm: 1.6608 (1.6092) time: 0.6341 [2021-03-27 11:42:07 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 920/1251] eta: 0:03:30 lr: 0.000434 loss: 3.3837 (3.2392) grad_norm: 1.6414 (1.6095) time: 0.6316 [2021-03-27 11:42:13 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 930/1251] eta: 0:03:24 lr: 0.000434 loss: 3.4758 (3.2390) grad_norm: 1.5668 (1.6091) time: 0.6265 [2021-03-27 11:42:20 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 940/1251] eta: 0:03:17 lr: 0.000434 loss: 3.2748 (3.2381) grad_norm: 1.5668 (1.6099) time: 0.6292 [2021-03-27 11:42:26 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 950/1251] eta: 0:03:11 lr: 0.000434 loss: 3.3002 (3.2391) grad_norm: 1.5598 (1.6098) time: 0.6329 [2021-03-27 11:42:32 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 960/1251] eta: 0:03:05 lr: 0.000434 loss: 3.3610 (3.2385) grad_norm: 1.6461 (1.6107) time: 0.6308 [2021-03-27 11:42:39 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 970/1251] eta: 0:02:58 lr: 0.000434 loss: 3.3035 (3.2387) grad_norm: 1.6500 (1.6115) time: 0.6309 [2021-03-27 11:42:45 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 980/1251] eta: 0:02:52 lr: 0.000434 loss: 3.3035 (3.2407) grad_norm: 1.6871 (1.6142) time: 0.6308 [2021-03-27 11:42:51 swin_base_patch4_window7_224] INFO: Epoch: [163] [ 990/1251] eta: 0:02:46 lr: 0.000434 loss: 3.2862 (3.2408) grad_norm: 1.6632 (1.6150) time: 0.6259 [2021-03-27 11:42:58 swin_base_patch4_window7_224] INFO: Epoch: [163] [1000/1251] eta: 0:02:39 lr: 0.000434 loss: 3.2862 (3.2401) grad_norm: 1.7847 (1.6174) time: 0.6315 [2021-03-27 11:43:04 swin_base_patch4_window7_224] INFO: Epoch: [163] [1010/1251] eta: 0:02:33 lr: 0.000434 loss: 2.9959 (3.2376) grad_norm: 1.7521 (1.6179) time: 0.6317 [2021-03-27 11:43:10 swin_base_patch4_window7_224] INFO: Epoch: [163] [1020/1251] eta: 0:02:26 lr: 0.000434 loss: 2.9959 (3.2360) grad_norm: 1.5746 (1.6179) time: 0.6233 [2021-03-27 11:43:17 swin_base_patch4_window7_224] INFO: Epoch: [163] [1030/1251] eta: 0:02:20 lr: 0.000434 loss: 3.0869 (3.2354) grad_norm: 1.5221 (1.6168) time: 0.6307 [2021-03-27 11:43:23 swin_base_patch4_window7_224] INFO: Epoch: [163] [1040/1251] eta: 0:02:14 lr: 0.000434 loss: 3.2447 (3.2358) grad_norm: 1.4701 (1.6156) time: 0.6371 [2021-03-27 11:43:29 swin_base_patch4_window7_224] INFO: Epoch: [163] [1050/1251] eta: 0:02:07 lr: 0.000434 loss: 3.3777 (3.2370) grad_norm: 1.5753 (1.6167) time: 0.6317 [2021-03-27 11:43:36 swin_base_patch4_window7_224] INFO: Epoch: [163] [1060/1251] eta: 0:02:01 lr: 0.000433 loss: 3.3469 (3.2369) grad_norm: 1.5968 (1.6159) time: 0.6335 [2021-03-27 11:43:42 swin_base_patch4_window7_224] INFO: Epoch: [163] [1070/1251] eta: 0:01:55 lr: 0.000433 loss: 3.1213 (3.2354) grad_norm: 1.5968 (1.6159) time: 0.6372 [2021-03-27 11:43:48 swin_base_patch4_window7_224] INFO: Epoch: [163] [1080/1251] eta: 0:01:48 lr: 0.000433 loss: 2.9985 (3.2331) grad_norm: 1.6141 (1.6163) time: 0.6327 [2021-03-27 11:43:54 swin_base_patch4_window7_224] INFO: Epoch: [163] [1090/1251] eta: 0:01:42 lr: 0.000433 loss: 2.9259 (3.2314) grad_norm: 1.5941 (inf) time: 0.6238 [2021-03-27 11:44:01 swin_base_patch4_window7_224] INFO: Epoch: [163] [1100/1251] eta: 0:01:36 lr: 0.000433 loss: 3.3350 (3.2356) grad_norm: 1.5035 (inf) time: 0.6301 [2021-03-27 11:44:07 swin_base_patch4_window7_224] INFO: Epoch: [163] [1110/1251] eta: 0:01:29 lr: 0.000433 loss: 3.4994 (3.2377) grad_norm: 1.5691 (inf) time: 0.6369 [2021-03-27 11:44:14 swin_base_patch4_window7_224] INFO: Epoch: [163] [1120/1251] eta: 0:01:23 lr: 0.000433 loss: 3.4154 (3.2370) grad_norm: 1.6729 (inf) time: 0.6399 [2021-03-27 11:44:20 swin_base_patch4_window7_224] INFO: Epoch: [163] [1130/1251] eta: 0:01:16 lr: 0.000433 loss: 3.3242 (3.2388) grad_norm: 1.6464 (inf) time: 0.6393 [2021-03-27 11:44:26 swin_base_patch4_window7_224] INFO: Epoch: [163] [1140/1251] eta: 0:01:10 lr: 0.000433 loss: 3.3242 (3.2380) grad_norm: 1.6030 (inf) time: 0.6292 [2021-03-27 11:44:33 swin_base_patch4_window7_224] INFO: Epoch: [163] [1150/1251] eta: 0:01:04 lr: 0.000433 loss: 3.1175 (3.2367) grad_norm: 1.5788 (inf) time: 0.6333 [2021-03-27 11:44:39 swin_base_patch4_window7_224] INFO: Epoch: [163] [1160/1251] eta: 0:00:57 lr: 0.000433 loss: 3.0529 (3.2359) grad_norm: 1.5977 (inf) time: 0.6344 [2021-03-27 11:44:45 swin_base_patch4_window7_224] INFO: Epoch: [163] [1170/1251] eta: 0:00:51 lr: 0.000433 loss: 3.2985 (3.2370) grad_norm: 1.5822 (inf) time: 0.6291 [2021-03-27 11:44:51 swin_base_patch4_window7_224] INFO: Epoch: [163] [1180/1251] eta: 0:00:45 lr: 0.000433 loss: 3.2985 (3.2362) grad_norm: 1.5957 (inf) time: 0.6290 [2021-03-27 11:44:58 swin_base_patch4_window7_224] INFO: Epoch: [163] [1190/1251] eta: 0:00:38 lr: 0.000433 loss: 3.1936 (3.2352) grad_norm: 1.5601 (inf) time: 0.6382 [2021-03-27 11:45:04 swin_base_patch4_window7_224] INFO: Epoch: [163] [1200/1251] eta: 0:00:32 lr: 0.000433 loss: 3.3477 (3.2358) grad_norm: 1.5543 (inf) time: 0.6371 [2021-03-27 11:45:10 swin_base_patch4_window7_224] INFO: Epoch: [163] [1210/1251] eta: 0:00:26 lr: 0.000433 loss: 3.3540 (3.2364) grad_norm: 1.6277 (inf) time: 0.6269 [2021-03-27 11:45:17 swin_base_patch4_window7_224] INFO: Epoch: [163] [1220/1251] eta: 0:00:19 lr: 0.000433 loss: 3.3554 (3.2382) grad_norm: 1.5598 (inf) time: 0.6254 [2021-03-27 11:45:23 swin_base_patch4_window7_224] INFO: Epoch: [163] [1230/1251] eta: 0:00:13 lr: 0.000433 loss: 3.4476 (3.2379) grad_norm: 1.5776 (inf) time: 0.6251 [2021-03-27 11:45:29 swin_base_patch4_window7_224] INFO: Epoch: [163] [1240/1251] eta: 0:00:06 lr: 0.000433 loss: 3.0707 (3.2364) grad_norm: 1.5818 (inf) time: 0.6217 [2021-03-27 11:45:35 swin_base_patch4_window7_224] INFO: Epoch: [163] [1250/1251] eta: 0:00:00 lr: 0.000433 loss: 3.2503 (3.2368) grad_norm: 1.5752 (inf) time: 0.6246 [2021-03-27 11:45:48 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:49 loss: 0.9755 (0.9755) acc1: 75.0000 (75.0000) acc5: 96.8750 (96.8750) [2021-03-27 11:45:51 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9755 (0.9220) acc1: 79.6875 (77.4148) acc5: 96.8750 (95.4545) [2021-03-27 11:45:53 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8702 (0.8945) acc1: 79.6875 (78.6458) acc5: 95.3125 (95.0149) [2021-03-27 11:45:55 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8613 (0.8904) acc1: 78.1250 (78.3266) acc5: 95.3125 (95.2117) [2021-03-27 11:45:57 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8979 (0.8842) acc1: 76.5625 (78.4680) acc5: 95.3125 (95.0838) [2021-03-27 11:45:58 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8930 (0.8973) acc1: 76.5625 (78.3360) acc5: 93.7500 (94.7520) [2021-03-27 11:46:09 swin_base_patch4_window7_224] INFO: * Acc@1 79.510 Acc@5 95.118 loss 0.870 [2021-03-27 11:46:09 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.5% [2021-03-27 11:46:09 swin_base_patch4_window7_224] INFO: Max accuracy: 79.65% [2021-03-27 11:46:14 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 0/1251] eta: 1:30:46 lr: 0.000433 loss: 3.7493 (3.7493) grad_norm: 1.4649 (1.4649) time: 4.3541 [2021-03-27 11:46:20 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 10/1251] eta: 0:20:06 lr: 0.000433 loss: 3.4424 (3.2883) grad_norm: 1.5025 (1.5296) time: 0.9724 [2021-03-27 11:46:26 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 20/1251] eta: 0:16:35 lr: 0.000433 loss: 3.3015 (3.3347) grad_norm: 1.6164 (1.5991) time: 0.6313 [2021-03-27 11:46:33 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 30/1251] eta: 0:15:18 lr: 0.000433 loss: 3.4229 (3.3609) grad_norm: 1.6682 (1.6271) time: 0.6316 [2021-03-27 11:46:39 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 40/1251] eta: 0:14:38 lr: 0.000433 loss: 3.3270 (3.2826) grad_norm: 1.6882 (1.6512) time: 0.6382 [2021-03-27 11:46:45 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 50/1251] eta: 0:14:09 lr: 0.000432 loss: 3.0023 (3.3220) grad_norm: 1.5851 (1.6524) time: 0.6368 [2021-03-27 11:46:52 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 60/1251] eta: 0:13:45 lr: 0.000432 loss: 3.3939 (3.2961) grad_norm: 1.5325 (1.6582) time: 0.6272 [2021-03-27 11:46:58 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 70/1251] eta: 0:13:28 lr: 0.000432 loss: 3.4505 (3.3269) grad_norm: 1.6058 (1.6683) time: 0.6274 [2021-03-27 11:47:04 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 80/1251] eta: 0:13:13 lr: 0.000432 loss: 3.5026 (3.3243) grad_norm: 1.7099 (1.6796) time: 0.6298 [2021-03-27 11:47:11 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 90/1251] eta: 0:13:01 lr: 0.000432 loss: 3.4675 (3.3394) grad_norm: 1.6972 (1.6755) time: 0.6313 [2021-03-27 11:47:17 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 100/1251] eta: 0:12:50 lr: 0.000432 loss: 3.3797 (3.3307) grad_norm: 1.6063 (1.6663) time: 0.6368 [2021-03-27 11:47:23 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 110/1251] eta: 0:12:40 lr: 0.000432 loss: 3.3284 (3.3257) grad_norm: 1.5492 (1.6645) time: 0.6358 [2021-03-27 11:47:30 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 120/1251] eta: 0:12:29 lr: 0.000432 loss: 3.3284 (3.3146) grad_norm: 1.5376 (1.6590) time: 0.6274 [2021-03-27 11:47:36 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 130/1251] eta: 0:12:21 lr: 0.000432 loss: 3.1730 (3.3029) grad_norm: 1.5039 (1.6494) time: 0.6326 [2021-03-27 11:47:42 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 140/1251] eta: 0:12:11 lr: 0.000432 loss: 3.3585 (3.3054) grad_norm: 1.5227 (1.6465) time: 0.6351 [2021-03-27 11:47:49 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 150/1251] eta: 0:12:03 lr: 0.000432 loss: 3.3650 (3.3131) grad_norm: 1.5998 (1.6575) time: 0.6281 [2021-03-27 11:47:55 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 160/1251] eta: 0:11:54 lr: 0.000432 loss: 3.4349 (3.3126) grad_norm: 1.6243 (1.6590) time: 0.6263 [2021-03-27 11:48:01 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 170/1251] eta: 0:11:46 lr: 0.000432 loss: 3.3765 (3.3110) grad_norm: 1.5653 (1.6571) time: 0.6326 [2021-03-27 11:48:08 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 180/1251] eta: 0:11:39 lr: 0.000432 loss: 3.2528 (3.3102) grad_norm: 1.6217 (1.6548) time: 0.6373 [2021-03-27 11:48:14 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 190/1251] eta: 0:11:31 lr: 0.000432 loss: 3.3089 (3.3093) grad_norm: 1.6695 (1.6658) time: 0.6292 [2021-03-27 11:48:20 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 200/1251] eta: 0:11:22 lr: 0.000432 loss: 3.4790 (3.3050) grad_norm: 1.6944 (1.6652) time: 0.6236 [2021-03-27 11:48:26 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 210/1251] eta: 0:11:15 lr: 0.000432 loss: 3.4448 (3.3141) grad_norm: 1.6005 (1.6599) time: 0.6257 [2021-03-27 11:48:33 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 220/1251] eta: 0:11:08 lr: 0.000432 loss: 3.4424 (3.3061) grad_norm: 1.5327 (1.6603) time: 0.6293 [2021-03-27 11:48:39 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 230/1251] eta: 0:11:00 lr: 0.000432 loss: 3.3898 (3.3095) grad_norm: 1.5327 (1.6564) time: 0.6281 [2021-03-27 11:48:45 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 240/1251] eta: 0:10:53 lr: 0.000432 loss: 3.4017 (3.2987) grad_norm: 1.5258 (1.6512) time: 0.6315 [2021-03-27 11:48:52 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 250/1251] eta: 0:10:46 lr: 0.000432 loss: 3.3968 (3.2995) grad_norm: 1.5331 (1.6489) time: 0.6347 [2021-03-27 11:48:58 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 260/1251] eta: 0:10:39 lr: 0.000432 loss: 3.3388 (3.2969) grad_norm: 1.5329 (1.6465) time: 0.6356 [2021-03-27 11:49:04 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 270/1251] eta: 0:10:32 lr: 0.000432 loss: 3.1035 (3.2833) grad_norm: 1.5395 (1.6448) time: 0.6307 [2021-03-27 11:49:11 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 280/1251] eta: 0:10:25 lr: 0.000432 loss: 3.1766 (3.2833) grad_norm: 1.5261 (1.6418) time: 0.6286 [2021-03-27 11:49:17 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 290/1251] eta: 0:10:18 lr: 0.000432 loss: 3.2768 (3.2729) grad_norm: 1.4766 (1.6393) time: 0.6322 [2021-03-27 11:49:23 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 300/1251] eta: 0:10:12 lr: 0.000431 loss: 3.0071 (3.2679) grad_norm: 1.5389 (1.6367) time: 0.6311 [2021-03-27 11:49:29 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 310/1251] eta: 0:10:05 lr: 0.000431 loss: 3.2020 (3.2724) grad_norm: 1.5675 (1.6385) time: 0.6288 [2021-03-27 11:49:36 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 320/1251] eta: 0:09:58 lr: 0.000431 loss: 3.1971 (3.2664) grad_norm: 1.6800 (1.6399) time: 0.6261 [2021-03-27 11:49:42 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 330/1251] eta: 0:09:51 lr: 0.000431 loss: 3.2311 (3.2740) grad_norm: 1.6761 (1.6374) time: 0.6337 [2021-03-27 11:49:48 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 340/1251] eta: 0:09:44 lr: 0.000431 loss: 3.2902 (3.2695) grad_norm: 1.5246 (1.6350) time: 0.6337 [2021-03-27 11:49:55 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 350/1251] eta: 0:09:38 lr: 0.000431 loss: 3.0935 (3.2716) grad_norm: 1.5680 (1.6347) time: 0.6264 [2021-03-27 11:50:01 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 360/1251] eta: 0:09:31 lr: 0.000431 loss: 3.0535 (3.2628) grad_norm: 1.5673 (1.6337) time: 0.6270 [2021-03-27 11:50:07 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 370/1251] eta: 0:09:24 lr: 0.000431 loss: 3.1613 (3.2613) grad_norm: 1.4501 (1.6308) time: 0.6274 [2021-03-27 11:50:13 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 380/1251] eta: 0:09:17 lr: 0.000431 loss: 3.2891 (3.2580) grad_norm: 1.5112 (1.6303) time: 0.6242 [2021-03-27 11:50:20 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 390/1251] eta: 0:09:11 lr: 0.000431 loss: 3.2891 (3.2577) grad_norm: 1.6101 (1.6323) time: 0.6234 [2021-03-27 11:50:26 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 400/1251] eta: 0:09:04 lr: 0.000431 loss: 3.4040 (3.2601) grad_norm: 1.6468 (1.6325) time: 0.6273 [2021-03-27 11:50:32 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 410/1251] eta: 0:08:57 lr: 0.000431 loss: 3.3400 (3.2612) grad_norm: 1.6315 (1.6334) time: 0.6278 [2021-03-27 11:50:39 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 420/1251] eta: 0:08:51 lr: 0.000431 loss: 3.3400 (3.2678) grad_norm: 1.5771 (1.6324) time: 0.6288 [2021-03-27 11:50:45 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 430/1251] eta: 0:08:44 lr: 0.000431 loss: 3.3106 (3.2658) grad_norm: 1.5379 (1.6309) time: 0.6341 [2021-03-27 11:50:51 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 440/1251] eta: 0:08:38 lr: 0.000431 loss: 3.3072 (3.2658) grad_norm: 1.5726 (1.6308) time: 0.6324 [2021-03-27 11:50:58 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 450/1251] eta: 0:08:31 lr: 0.000431 loss: 3.3679 (3.2663) grad_norm: 1.5696 (1.6281) time: 0.6292 [2021-03-27 11:51:04 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 460/1251] eta: 0:08:25 lr: 0.000431 loss: 3.4155 (3.2700) grad_norm: 1.5199 (1.6263) time: 0.6298 [2021-03-27 11:51:10 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 470/1251] eta: 0:08:18 lr: 0.000431 loss: 3.3463 (3.2654) grad_norm: 1.5267 (1.6255) time: 0.6258 [2021-03-27 11:51:16 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 480/1251] eta: 0:08:11 lr: 0.000431 loss: 3.0784 (3.2614) grad_norm: 1.5538 (1.6240) time: 0.6265 [2021-03-27 11:51:23 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 490/1251] eta: 0:08:05 lr: 0.000431 loss: 3.0920 (3.2557) grad_norm: 1.5042 (1.6215) time: 0.6320 [2021-03-27 11:51:29 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 500/1251] eta: 0:07:59 lr: 0.000431 loss: 3.1665 (3.2578) grad_norm: 1.6269 (1.6221) time: 0.6381 [2021-03-27 11:51:35 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 510/1251] eta: 0:07:52 lr: 0.000431 loss: 3.3677 (3.2532) grad_norm: 1.6269 (1.6222) time: 0.6364 [2021-03-27 11:51:42 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 520/1251] eta: 0:07:46 lr: 0.000431 loss: 3.3934 (3.2527) grad_norm: 1.6002 (1.6228) time: 0.6395 [2021-03-27 11:51:48 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 530/1251] eta: 0:07:39 lr: 0.000431 loss: 3.2763 (3.2485) grad_norm: 1.6237 (1.6232) time: 0.6349 [2021-03-27 11:51:54 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 540/1251] eta: 0:07:33 lr: 0.000430 loss: 3.2253 (3.2503) grad_norm: 1.6237 (1.6253) time: 0.6243 [2021-03-27 11:52:01 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 550/1251] eta: 0:07:26 lr: 0.000430 loss: 3.5846 (3.2558) grad_norm: 1.5532 (1.6246) time: 0.6302 [2021-03-27 11:52:07 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 560/1251] eta: 0:07:20 lr: 0.000430 loss: 3.4477 (3.2547) grad_norm: 1.4985 (1.6227) time: 0.6281 [2021-03-27 11:52:13 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 570/1251] eta: 0:07:13 lr: 0.000430 loss: 3.2059 (3.2519) grad_norm: 1.5320 (1.6238) time: 0.6227 [2021-03-27 11:52:20 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 580/1251] eta: 0:07:07 lr: 0.000430 loss: 3.3045 (3.2525) grad_norm: 1.5850 (1.6245) time: 0.6289 [2021-03-27 11:52:26 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 590/1251] eta: 0:07:00 lr: 0.000430 loss: 3.4827 (3.2538) grad_norm: 1.5809 (1.6234) time: 0.6350 [2021-03-27 11:52:32 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 600/1251] eta: 0:06:54 lr: 0.000430 loss: 3.4397 (3.2566) grad_norm: 1.5767 (1.6221) time: 0.6353 [2021-03-27 11:52:39 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 610/1251] eta: 0:06:48 lr: 0.000430 loss: 3.3619 (3.2543) grad_norm: 1.5777 (1.6212) time: 0.6323 [2021-03-27 11:52:45 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 620/1251] eta: 0:06:41 lr: 0.000430 loss: 3.3277 (3.2562) grad_norm: 1.5275 (1.6205) time: 0.6279 [2021-03-27 11:52:51 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 630/1251] eta: 0:06:35 lr: 0.000430 loss: 3.3075 (3.2558) grad_norm: 1.5240 (1.6205) time: 0.6298 [2021-03-27 11:52:57 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 640/1251] eta: 0:06:28 lr: 0.000430 loss: 3.3075 (3.2585) grad_norm: 1.5865 (1.6219) time: 0.6265 [2021-03-27 11:53:04 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 650/1251] eta: 0:06:22 lr: 0.000430 loss: 3.4929 (3.2601) grad_norm: 1.5865 (1.6218) time: 0.6253 [2021-03-27 11:53:10 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 660/1251] eta: 0:06:15 lr: 0.000430 loss: 3.2612 (3.2589) grad_norm: 1.5654 (1.6212) time: 0.6290 [2021-03-27 11:53:16 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 670/1251] eta: 0:06:09 lr: 0.000430 loss: 3.3270 (3.2597) grad_norm: 1.5654 (1.6204) time: 0.6249 [2021-03-27 11:53:22 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 680/1251] eta: 0:06:02 lr: 0.000430 loss: 3.1452 (3.2547) grad_norm: 1.5908 (1.6198) time: 0.6198 [2021-03-27 11:53:29 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 690/1251] eta: 0:05:56 lr: 0.000430 loss: 3.1452 (3.2554) grad_norm: 1.5654 (1.6190) time: 0.6251 [2021-03-27 11:53:35 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 700/1251] eta: 0:05:50 lr: 0.000430 loss: 3.3784 (3.2549) grad_norm: 1.6213 (1.6196) time: 0.6298 [2021-03-27 11:53:41 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 710/1251] eta: 0:05:43 lr: 0.000430 loss: 3.2089 (3.2556) grad_norm: 1.6296 (1.6198) time: 0.6257 [2021-03-27 11:53:48 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 720/1251] eta: 0:05:37 lr: 0.000430 loss: 3.1854 (3.2541) grad_norm: 1.5369 (1.6199) time: 0.6323 [2021-03-27 11:53:54 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 730/1251] eta: 0:05:31 lr: 0.000430 loss: 3.2701 (3.2566) grad_norm: 1.5453 (1.6194) time: 0.6399 [2021-03-27 11:54:00 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 740/1251] eta: 0:05:24 lr: 0.000430 loss: 3.4150 (3.2580) grad_norm: 1.6002 (1.6202) time: 0.6393 [2021-03-27 11:54:07 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 750/1251] eta: 0:05:18 lr: 0.000430 loss: 3.4605 (3.2628) grad_norm: 1.6002 (1.6204) time: 0.6343 [2021-03-27 11:54:13 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 760/1251] eta: 0:05:11 lr: 0.000430 loss: 3.4605 (3.2622) grad_norm: 1.5534 (1.6190) time: 0.6256 [2021-03-27 11:54:19 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 770/1251] eta: 0:05:05 lr: 0.000430 loss: 3.3805 (3.2616) grad_norm: 1.5246 (1.6196) time: 0.6249 [2021-03-27 11:54:25 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 780/1251] eta: 0:04:59 lr: 0.000429 loss: 3.2620 (3.2594) grad_norm: 1.5499 (1.6190) time: 0.6256 [2021-03-27 11:54:32 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 790/1251] eta: 0:04:52 lr: 0.000429 loss: 3.1976 (3.2601) grad_norm: 1.5293 (1.6189) time: 0.6307 [2021-03-27 11:54:38 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 800/1251] eta: 0:04:46 lr: 0.000429 loss: 3.3060 (3.2605) grad_norm: 1.5394 (1.6196) time: 0.6321 [2021-03-27 11:54:44 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 810/1251] eta: 0:04:39 lr: 0.000429 loss: 3.3060 (3.2607) grad_norm: 1.5333 (1.6188) time: 0.6265 [2021-03-27 11:54:51 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 820/1251] eta: 0:04:33 lr: 0.000429 loss: 3.1525 (3.2576) grad_norm: 1.5333 (1.6186) time: 0.6322 [2021-03-27 11:54:57 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 830/1251] eta: 0:04:27 lr: 0.000429 loss: 3.2414 (3.2568) grad_norm: 1.5459 (1.6171) time: 0.6346 [2021-03-27 11:55:03 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 840/1251] eta: 0:04:20 lr: 0.000429 loss: 3.4095 (3.2589) grad_norm: 1.5371 (1.6167) time: 0.6334 [2021-03-27 11:55:10 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 850/1251] eta: 0:04:14 lr: 0.000429 loss: 3.4702 (3.2595) grad_norm: 1.4744 (1.6163) time: 0.6360 [2021-03-27 11:55:16 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 860/1251] eta: 0:04:08 lr: 0.000429 loss: 3.1957 (3.2605) grad_norm: 1.5460 (1.6169) time: 0.6319 [2021-03-27 11:55:22 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 870/1251] eta: 0:04:01 lr: 0.000429 loss: 3.3423 (3.2607) grad_norm: 1.5424 (1.6152) time: 0.6261 [2021-03-27 11:55:29 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 880/1251] eta: 0:03:55 lr: 0.000429 loss: 3.4427 (3.2618) grad_norm: 1.5381 (1.6163) time: 0.6362 [2021-03-27 11:55:35 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 890/1251] eta: 0:03:49 lr: 0.000429 loss: 3.4427 (3.2629) grad_norm: 1.4889 (1.6146) time: 0.6343 [2021-03-27 11:55:41 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 900/1251] eta: 0:03:42 lr: 0.000429 loss: 3.5332 (3.2654) grad_norm: 1.4509 (1.6138) time: 0.6271 [2021-03-27 11:55:48 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 910/1251] eta: 0:03:36 lr: 0.000429 loss: 3.3880 (3.2630) grad_norm: 1.5779 (1.6140) time: 0.6374 [2021-03-27 11:55:54 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 920/1251] eta: 0:03:30 lr: 0.000429 loss: 3.3438 (3.2633) grad_norm: 1.6098 (1.6139) time: 0.6326 [2021-03-27 11:56:00 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 930/1251] eta: 0:03:23 lr: 0.000429 loss: 3.3838 (3.2642) grad_norm: 1.6098 (1.6146) time: 0.6283 [2021-03-27 11:56:07 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 940/1251] eta: 0:03:17 lr: 0.000429 loss: 3.2398 (3.2642) grad_norm: 1.6279 (1.6162) time: 0.6324 [2021-03-27 11:56:13 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 950/1251] eta: 0:03:10 lr: 0.000429 loss: 3.1988 (3.2629) grad_norm: 1.6173 (1.6162) time: 0.6357 [2021-03-27 11:56:19 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 960/1251] eta: 0:03:04 lr: 0.000429 loss: 2.9645 (3.2602) grad_norm: 1.5624 (1.6162) time: 0.6304 [2021-03-27 11:56:26 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 970/1251] eta: 0:02:58 lr: 0.000429 loss: 3.2662 (3.2621) grad_norm: 1.5624 (1.6176) time: 0.6263 [2021-03-27 11:56:32 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 980/1251] eta: 0:02:51 lr: 0.000429 loss: 3.2608 (3.2593) grad_norm: 1.6162 (1.6177) time: 0.6282 [2021-03-27 11:56:38 swin_base_patch4_window7_224] INFO: Epoch: [164] [ 990/1251] eta: 0:02:45 lr: 0.000429 loss: 3.2362 (3.2589) grad_norm: 1.6162 (1.6178) time: 0.6254 [2021-03-27 11:56:44 swin_base_patch4_window7_224] INFO: Epoch: [164] [1000/1251] eta: 0:02:39 lr: 0.000429 loss: 3.2362 (3.2554) grad_norm: 1.6486 (1.6194) time: 0.6280 [2021-03-27 11:56:51 swin_base_patch4_window7_224] INFO: Epoch: [164] [1010/1251] eta: 0:02:32 lr: 0.000429 loss: 2.8438 (3.2529) grad_norm: 1.6810 (1.6203) time: 0.6277 [2021-03-27 11:56:57 swin_base_patch4_window7_224] INFO: Epoch: [164] [1020/1251] eta: 0:02:26 lr: 0.000429 loss: 3.3417 (3.2550) grad_norm: 1.5785 (1.6195) time: 0.6284 [2021-03-27 11:57:03 swin_base_patch4_window7_224] INFO: Epoch: [164] [1030/1251] eta: 0:02:20 lr: 0.000428 loss: 3.5716 (3.2549) grad_norm: 1.4899 (1.6184) time: 0.6278 [2021-03-27 11:57:09 swin_base_patch4_window7_224] INFO: Epoch: [164] [1040/1251] eta: 0:02:13 lr: 0.000428 loss: 3.5384 (3.2558) grad_norm: 1.4901 (1.6181) time: 0.6290 [2021-03-27 11:57:16 swin_base_patch4_window7_224] INFO: Epoch: [164] [1050/1251] eta: 0:02:07 lr: 0.000428 loss: 3.4994 (3.2566) grad_norm: 1.5424 (1.6180) time: 0.6326 [2021-03-27 11:57:22 swin_base_patch4_window7_224] INFO: Epoch: [164] [1060/1251] eta: 0:02:01 lr: 0.000428 loss: 3.4994 (3.2583) grad_norm: 1.6266 (1.6186) time: 0.6313 [2021-03-27 11:57:28 swin_base_patch4_window7_224] INFO: Epoch: [164] [1070/1251] eta: 0:01:54 lr: 0.000428 loss: 3.4925 (3.2588) grad_norm: 1.6383 (1.6182) time: 0.6312 [2021-03-27 11:57:35 swin_base_patch4_window7_224] INFO: Epoch: [164] [1080/1251] eta: 0:01:48 lr: 0.000428 loss: 3.1700 (3.2567) grad_norm: 1.5487 (1.6205) time: 0.6370 [2021-03-27 11:57:41 swin_base_patch4_window7_224] INFO: Epoch: [164] [1090/1251] eta: 0:01:42 lr: 0.000428 loss: 2.9894 (3.2542) grad_norm: 1.5485 (1.6202) time: 0.6344 [2021-03-27 11:57:47 swin_base_patch4_window7_224] INFO: Epoch: [164] [1100/1251] eta: 0:01:35 lr: 0.000428 loss: 3.1166 (3.2539) grad_norm: 1.5485 (1.6199) time: 0.6243 [2021-03-27 11:57:54 swin_base_patch4_window7_224] INFO: Epoch: [164] [1110/1251] eta: 0:01:29 lr: 0.000428 loss: 3.4055 (3.2553) grad_norm: 1.5088 (1.6197) time: 0.6228 [2021-03-27 11:58:00 swin_base_patch4_window7_224] INFO: Epoch: [164] [1120/1251] eta: 0:01:22 lr: 0.000428 loss: 3.3799 (3.2550) grad_norm: 1.5464 (1.6202) time: 0.6246 [2021-03-27 11:58:06 swin_base_patch4_window7_224] INFO: Epoch: [164] [1130/1251] eta: 0:01:16 lr: 0.000428 loss: 3.3906 (3.2574) grad_norm: 1.6910 (1.6205) time: 0.6312 [2021-03-27 11:58:13 swin_base_patch4_window7_224] INFO: Epoch: [164] [1140/1251] eta: 0:01:10 lr: 0.000428 loss: 3.3365 (3.2564) grad_norm: 1.6314 (1.6231) time: 0.6388 [2021-03-27 11:58:19 swin_base_patch4_window7_224] INFO: Epoch: [164] [1150/1251] eta: 0:01:03 lr: 0.000428 loss: 3.2829 (3.2584) grad_norm: 1.5606 (1.6224) time: 0.6364 [2021-03-27 11:58:25 swin_base_patch4_window7_224] INFO: Epoch: [164] [1160/1251] eta: 0:00:57 lr: 0.000428 loss: 3.4265 (3.2567) grad_norm: 1.5606 (1.6227) time: 0.6284 [2021-03-27 11:58:31 swin_base_patch4_window7_224] INFO: Epoch: [164] [1170/1251] eta: 0:00:51 lr: 0.000428 loss: 3.1177 (3.2563) grad_norm: 1.6619 (1.6228) time: 0.6265 [2021-03-27 11:58:38 swin_base_patch4_window7_224] INFO: Epoch: [164] [1180/1251] eta: 0:00:44 lr: 0.000428 loss: 3.1177 (3.2558) grad_norm: 1.5846 (1.6225) time: 0.6309 [2021-03-27 11:58:44 swin_base_patch4_window7_224] INFO: Epoch: [164] [1190/1251] eta: 0:00:38 lr: 0.000428 loss: 3.0777 (3.2550) grad_norm: 1.5617 (1.6218) time: 0.6314 [2021-03-27 11:58:50 swin_base_patch4_window7_224] INFO: Epoch: [164] [1200/1251] eta: 0:00:32 lr: 0.000428 loss: 3.1209 (3.2544) grad_norm: 1.6106 (1.6225) time: 0.6284 [2021-03-27 11:58:57 swin_base_patch4_window7_224] INFO: Epoch: [164] [1210/1251] eta: 0:00:25 lr: 0.000428 loss: 3.5286 (3.2578) grad_norm: 1.6113 (1.6221) time: 0.6279 [2021-03-27 11:59:03 swin_base_patch4_window7_224] INFO: Epoch: [164] [1220/1251] eta: 0:00:19 lr: 0.000428 loss: 3.5048 (3.2585) grad_norm: 1.6338 (1.6234) time: 0.6283 [2021-03-27 11:59:09 swin_base_patch4_window7_224] INFO: Epoch: [164] [1230/1251] eta: 0:00:13 lr: 0.000428 loss: 3.5370 (3.2616) grad_norm: 1.7076 (1.6238) time: 0.6274 [2021-03-27 11:59:15 swin_base_patch4_window7_224] INFO: Epoch: [164] [1240/1251] eta: 0:00:06 lr: 0.000428 loss: 3.5370 (3.2616) grad_norm: 1.5514 (1.6228) time: 0.6257 [2021-03-27 11:59:22 swin_base_patch4_window7_224] INFO: Epoch: [164] [1250/1251] eta: 0:00:00 lr: 0.000428 loss: 3.2256 (3.2603) grad_norm: 1.5010 (1.6224) time: 0.6183 [2021-03-27 11:59:32 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:22 loss: 0.9741 (0.9741) acc1: 75.0000 (75.0000) acc5: 92.1875 (92.1875) [2021-03-27 11:59:35 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.8102 (0.8660) acc1: 79.6875 (79.4034) acc5: 96.8750 (95.4545) [2021-03-27 11:59:38 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.8102 (0.8796) acc1: 79.6875 (79.0923) acc5: 95.3125 (95.6101) [2021-03-27 11:59:40 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8211 (0.8674) acc1: 78.1250 (79.3347) acc5: 95.3125 (95.5645) [2021-03-27 11:59:42 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8211 (0.8741) acc1: 78.1250 (78.9634) acc5: 95.3125 (95.6174) [2021-03-27 11:59:44 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9196 (0.8877) acc1: 78.1250 (78.5600) acc5: 95.3125 (95.3920) [2021-03-27 11:59:54 swin_base_patch4_window7_224] INFO: * Acc@1 79.520 Acc@5 95.240 loss 0.871 [2021-03-27 11:59:54 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.5% [2021-03-27 11:59:54 swin_base_patch4_window7_224] INFO: Max accuracy: 79.65% [2021-03-27 11:59:58 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 0/1251] eta: 1:37:20 lr: 0.000428 loss: 2.9832 (2.9832) grad_norm: 1.3793 (1.3793) time: 4.6688 [2021-03-27 12:00:05 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 10/1251] eta: 0:20:41 lr: 0.000428 loss: 3.0482 (3.1256) grad_norm: 1.4943 (1.4939) time: 1.0006 [2021-03-27 12:00:11 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 20/1251] eta: 0:16:56 lr: 0.000427 loss: 3.0482 (3.0382) grad_norm: 1.4943 (1.5089) time: 0.6336 [2021-03-27 12:00:17 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 30/1251] eta: 0:15:31 lr: 0.000427 loss: 3.3177 (3.1696) grad_norm: 1.4892 (1.5032) time: 0.6324 [2021-03-27 12:00:24 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 40/1251] eta: 0:14:47 lr: 0.000427 loss: 3.3308 (3.1762) grad_norm: 1.5002 (1.5328) time: 0.6346 [2021-03-27 12:00:30 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 50/1251] eta: 0:14:15 lr: 0.000427 loss: 3.2842 (3.1750) grad_norm: 1.5569 (1.5512) time: 0.6330 [2021-03-27 12:00:36 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 60/1251] eta: 0:13:52 lr: 0.000427 loss: 3.2926 (3.1932) grad_norm: 1.6932 (1.5902) time: 0.6292 [2021-03-27 12:00:42 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 70/1251] eta: 0:13:33 lr: 0.000427 loss: 3.2813 (3.2321) grad_norm: 1.7305 (1.5976) time: 0.6295 [2021-03-27 12:00:49 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 80/1251] eta: 0:13:17 lr: 0.000427 loss: 3.5608 (3.2739) grad_norm: 1.6920 (1.6143) time: 0.6274 [2021-03-27 12:00:55 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 90/1251] eta: 0:13:06 lr: 0.000427 loss: 3.5457 (3.2662) grad_norm: 1.6296 (1.6108) time: 0.6379 [2021-03-27 12:01:02 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 100/1251] eta: 0:12:54 lr: 0.000427 loss: 3.4118 (3.2784) grad_norm: 1.5963 (1.6223) time: 0.6416 [2021-03-27 12:01:08 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 110/1251] eta: 0:12:43 lr: 0.000427 loss: 3.3929 (3.2614) grad_norm: 1.6107 (1.6229) time: 0.6291 [2021-03-27 12:01:14 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 120/1251] eta: 0:12:33 lr: 0.000427 loss: 2.9559 (3.2415) grad_norm: 1.6107 (1.6361) time: 0.6290 [2021-03-27 12:01:20 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 130/1251] eta: 0:12:23 lr: 0.000427 loss: 3.3128 (3.2369) grad_norm: 1.6185 (1.6354) time: 0.6309 [2021-03-27 12:01:27 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 140/1251] eta: 0:12:14 lr: 0.000427 loss: 3.3249 (3.2222) grad_norm: 1.6102 (1.6334) time: 0.6301 [2021-03-27 12:01:33 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 150/1251] eta: 0:12:05 lr: 0.000427 loss: 3.4159 (3.2273) grad_norm: 1.6089 (1.6359) time: 0.6350 [2021-03-27 12:01:39 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 160/1251] eta: 0:11:56 lr: 0.000427 loss: 3.3509 (3.2276) grad_norm: 1.5872 (1.6324) time: 0.6301 [2021-03-27 12:01:46 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 170/1251] eta: 0:11:48 lr: 0.000427 loss: 3.2828 (3.2330) grad_norm: 1.5845 (1.6289) time: 0.6291 [2021-03-27 12:01:52 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 180/1251] eta: 0:11:40 lr: 0.000427 loss: 3.3161 (3.2377) grad_norm: 1.5969 (1.6283) time: 0.6310 [2021-03-27 12:01:58 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 190/1251] eta: 0:11:33 lr: 0.000427 loss: 3.3630 (3.2342) grad_norm: 1.5969 (1.6263) time: 0.6329 [2021-03-27 12:02:05 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 200/1251] eta: 0:11:25 lr: 0.000427 loss: 3.4188 (3.2457) grad_norm: 1.6246 (1.6299) time: 0.6340 [2021-03-27 12:02:11 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 210/1251] eta: 0:11:18 lr: 0.000427 loss: 3.4073 (3.2527) grad_norm: 1.6704 (1.6322) time: 0.6328 [2021-03-27 12:02:17 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 220/1251] eta: 0:11:11 lr: 0.000427 loss: 3.1769 (3.2469) grad_norm: 1.6515 (1.6370) time: 0.6404 [2021-03-27 12:02:24 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 230/1251] eta: 0:11:03 lr: 0.000427 loss: 3.2762 (3.2574) grad_norm: 1.6515 (1.6353) time: 0.6354 [2021-03-27 12:02:30 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 240/1251] eta: 0:10:56 lr: 0.000427 loss: 3.2823 (3.2506) grad_norm: 1.5588 (1.6351) time: 0.6270 [2021-03-27 12:02:36 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 250/1251] eta: 0:10:48 lr: 0.000427 loss: 3.2823 (3.2538) grad_norm: 1.5588 (1.6363) time: 0.6270 [2021-03-27 12:02:43 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 260/1251] eta: 0:10:41 lr: 0.000427 loss: 3.3295 (3.2560) grad_norm: 1.5506 (1.6333) time: 0.6307 [2021-03-27 12:02:49 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 270/1251] eta: 0:10:34 lr: 0.000426 loss: 3.3295 (3.2513) grad_norm: 1.4982 (1.6275) time: 0.6296 [2021-03-27 12:02:55 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 280/1251] eta: 0:10:27 lr: 0.000426 loss: 3.1429 (3.2494) grad_norm: 1.4780 (1.6250) time: 0.6232 [2021-03-27 12:03:01 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 290/1251] eta: 0:10:20 lr: 0.000426 loss: 3.2373 (3.2517) grad_norm: 1.5317 (1.6256) time: 0.6289 [2021-03-27 12:03:08 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 300/1251] eta: 0:10:13 lr: 0.000426 loss: 3.1516 (3.2447) grad_norm: 1.6662 (1.6285) time: 0.6341 [2021-03-27 12:03:14 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 310/1251] eta: 0:10:06 lr: 0.000426 loss: 3.2226 (3.2481) grad_norm: 1.5494 (1.6289) time: 0.6316 [2021-03-27 12:03:20 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 320/1251] eta: 0:09:59 lr: 0.000426 loss: 3.3050 (3.2458) grad_norm: 1.5121 (1.6262) time: 0.6302 [2021-03-27 12:03:27 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 330/1251] eta: 0:09:52 lr: 0.000426 loss: 3.1091 (3.2371) grad_norm: 1.5585 (1.6298) time: 0.6299 [2021-03-27 12:03:33 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 340/1251] eta: 0:09:46 lr: 0.000426 loss: 3.1434 (3.2390) grad_norm: 1.5991 (1.6301) time: 0.6279 [2021-03-27 12:03:39 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 350/1251] eta: 0:09:39 lr: 0.000426 loss: 3.1434 (3.2340) grad_norm: 1.6123 (1.6325) time: 0.6301 [2021-03-27 12:03:46 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 360/1251] eta: 0:09:32 lr: 0.000426 loss: 3.1464 (3.2363) grad_norm: 1.6805 (1.6345) time: 0.6332 [2021-03-27 12:03:52 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 370/1251] eta: 0:09:25 lr: 0.000426 loss: 3.1464 (3.2277) grad_norm: 1.6677 (1.6355) time: 0.6288 [2021-03-27 12:03:58 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 380/1251] eta: 0:09:19 lr: 0.000426 loss: 3.0192 (3.2231) grad_norm: 1.6702 (1.6380) time: 0.6314 [2021-03-27 12:04:05 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 390/1251] eta: 0:09:12 lr: 0.000426 loss: 3.3216 (3.2287) grad_norm: 1.6650 (1.6372) time: 0.6311 [2021-03-27 12:04:11 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 400/1251] eta: 0:09:05 lr: 0.000426 loss: 3.3717 (3.2311) grad_norm: 1.5961 (1.6393) time: 0.6247 [2021-03-27 12:04:17 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 410/1251] eta: 0:08:59 lr: 0.000426 loss: 3.3503 (3.2320) grad_norm: 1.5917 (1.6385) time: 0.6293 [2021-03-27 12:04:23 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 420/1251] eta: 0:08:52 lr: 0.000426 loss: 3.1803 (3.2309) grad_norm: 1.5395 (1.6373) time: 0.6302 [2021-03-27 12:04:30 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 430/1251] eta: 0:08:45 lr: 0.000426 loss: 3.2139 (3.2309) grad_norm: 1.5242 (1.6344) time: 0.6229 [2021-03-27 12:04:36 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 440/1251] eta: 0:08:39 lr: 0.000426 loss: 3.2139 (3.2265) grad_norm: 1.5279 (1.6328) time: 0.6301 [2021-03-27 12:04:42 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 450/1251] eta: 0:08:32 lr: 0.000426 loss: 3.3989 (3.2335) grad_norm: 1.5865 (1.6351) time: 0.6434 [2021-03-27 12:04:49 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 460/1251] eta: 0:08:26 lr: 0.000426 loss: 3.3756 (3.2345) grad_norm: 1.5808 (1.6335) time: 0.6378 [2021-03-27 12:04:55 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 470/1251] eta: 0:08:19 lr: 0.000426 loss: 3.2930 (3.2368) grad_norm: 1.5314 (1.6335) time: 0.6316 [2021-03-27 12:05:01 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 480/1251] eta: 0:08:13 lr: 0.000426 loss: 3.1711 (3.2347) grad_norm: 1.5556 (1.6316) time: 0.6368 [2021-03-27 12:05:08 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 490/1251] eta: 0:08:06 lr: 0.000426 loss: 3.3096 (3.2386) grad_norm: 1.5303 (1.6292) time: 0.6328 [2021-03-27 12:05:14 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 500/1251] eta: 0:08:00 lr: 0.000426 loss: 3.3135 (3.2420) grad_norm: 1.5828 (1.6316) time: 0.6279 [2021-03-27 12:05:20 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 510/1251] eta: 0:07:53 lr: 0.000425 loss: 3.2342 (3.2424) grad_norm: 1.6685 (1.6321) time: 0.6284 [2021-03-27 12:05:27 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 520/1251] eta: 0:07:47 lr: 0.000425 loss: 3.2122 (3.2443) grad_norm: 1.6685 (1.6313) time: 0.6311 [2021-03-27 12:05:33 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 530/1251] eta: 0:07:40 lr: 0.000425 loss: 3.1852 (3.2428) grad_norm: 1.6643 (1.6317) time: 0.6303 [2021-03-27 12:05:39 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 540/1251] eta: 0:07:34 lr: 0.000425 loss: 3.3472 (3.2441) grad_norm: 1.6088 (1.6332) time: 0.6245 [2021-03-27 12:05:46 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 550/1251] eta: 0:07:27 lr: 0.000425 loss: 3.3846 (3.2422) grad_norm: 1.6643 (1.6348) time: 0.6297 [2021-03-27 12:05:52 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 560/1251] eta: 0:07:21 lr: 0.000425 loss: 3.0662 (3.2395) grad_norm: 1.5819 (1.6343) time: 0.6428 [2021-03-27 12:05:58 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 570/1251] eta: 0:07:14 lr: 0.000425 loss: 3.3721 (3.2440) grad_norm: 1.5809 (1.6344) time: 0.6393 [2021-03-27 12:06:05 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 580/1251] eta: 0:07:08 lr: 0.000425 loss: 3.4436 (3.2419) grad_norm: 1.5508 (1.6331) time: 0.6357 [2021-03-27 12:06:11 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 590/1251] eta: 0:07:02 lr: 0.000425 loss: 3.3937 (3.2444) grad_norm: 1.4632 (1.6301) time: 0.6405 [2021-03-27 12:06:17 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 600/1251] eta: 0:06:55 lr: 0.000425 loss: 3.5720 (3.2470) grad_norm: 1.4904 (1.6289) time: 0.6372 [2021-03-27 12:06:24 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 610/1251] eta: 0:06:49 lr: 0.000425 loss: 3.3603 (3.2480) grad_norm: 1.5670 (inf) time: 0.6295 [2021-03-27 12:06:30 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 620/1251] eta: 0:06:42 lr: 0.000425 loss: 3.2714 (3.2465) grad_norm: 1.5581 (inf) time: 0.6262 [2021-03-27 12:06:36 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 630/1251] eta: 0:06:36 lr: 0.000425 loss: 3.3047 (3.2462) grad_norm: 1.5339 (inf) time: 0.6316 [2021-03-27 12:06:43 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 640/1251] eta: 0:06:29 lr: 0.000425 loss: 3.3596 (3.2462) grad_norm: 1.5606 (inf) time: 0.6380 [2021-03-27 12:06:49 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 650/1251] eta: 0:06:23 lr: 0.000425 loss: 3.2709 (3.2477) grad_norm: 1.6459 (inf) time: 0.6317 [2021-03-27 12:06:55 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 660/1251] eta: 0:06:17 lr: 0.000425 loss: 3.4721 (3.2517) grad_norm: 1.5969 (inf) time: 0.6278 [2021-03-27 12:07:02 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 670/1251] eta: 0:06:10 lr: 0.000425 loss: 3.5042 (3.2537) grad_norm: 1.5839 (inf) time: 0.6307 [2021-03-27 12:07:08 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 680/1251] eta: 0:06:04 lr: 0.000425 loss: 3.4269 (3.2546) grad_norm: 1.5691 (inf) time: 0.6273 [2021-03-27 12:07:14 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 690/1251] eta: 0:05:57 lr: 0.000425 loss: 3.2801 (3.2551) grad_norm: 1.5670 (inf) time: 0.6354 [2021-03-27 12:07:21 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 700/1251] eta: 0:05:51 lr: 0.000425 loss: 3.3064 (3.2574) grad_norm: 1.5778 (inf) time: 0.6383 [2021-03-27 12:07:27 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 710/1251] eta: 0:05:44 lr: 0.000425 loss: 3.3652 (3.2604) grad_norm: 1.6334 (inf) time: 0.6351 [2021-03-27 12:07:33 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 720/1251] eta: 0:05:38 lr: 0.000425 loss: 3.1577 (3.2572) grad_norm: 1.6334 (inf) time: 0.6317 [2021-03-27 12:07:40 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 730/1251] eta: 0:05:32 lr: 0.000425 loss: 3.1773 (3.2573) grad_norm: 1.6371 (inf) time: 0.6292 [2021-03-27 12:07:46 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 740/1251] eta: 0:05:25 lr: 0.000425 loss: 3.2581 (3.2553) grad_norm: 1.6360 (inf) time: 0.6370 [2021-03-27 12:07:52 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 750/1251] eta: 0:05:19 lr: 0.000424 loss: 3.2538 (3.2550) grad_norm: 1.5996 (inf) time: 0.6390 [2021-03-27 12:07:59 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 760/1251] eta: 0:05:12 lr: 0.000424 loss: 3.1849 (3.2530) grad_norm: 1.5996 (inf) time: 0.6329 [2021-03-27 12:08:05 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 770/1251] eta: 0:05:06 lr: 0.000424 loss: 3.2137 (3.2535) grad_norm: 1.6138 (inf) time: 0.6275 [2021-03-27 12:08:11 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 780/1251] eta: 0:05:00 lr: 0.000424 loss: 3.3636 (3.2545) grad_norm: 1.6320 (inf) time: 0.6300 [2021-03-27 12:08:18 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 790/1251] eta: 0:04:53 lr: 0.000424 loss: 3.3499 (3.2547) grad_norm: 1.7620 (inf) time: 0.6359 [2021-03-27 12:08:24 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 800/1251] eta: 0:04:47 lr: 0.000424 loss: 3.1939 (3.2541) grad_norm: 1.7650 (inf) time: 0.6351 [2021-03-27 12:08:30 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 810/1251] eta: 0:04:41 lr: 0.000424 loss: 3.1939 (3.2551) grad_norm: 1.7302 (inf) time: 0.6394 [2021-03-27 12:08:37 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 820/1251] eta: 0:04:34 lr: 0.000424 loss: 3.3031 (3.2541) grad_norm: 1.5686 (inf) time: 0.6406 [2021-03-27 12:08:43 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 830/1251] eta: 0:04:28 lr: 0.000424 loss: 3.3031 (3.2547) grad_norm: 1.4937 (inf) time: 0.6336 [2021-03-27 12:08:49 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 840/1251] eta: 0:04:21 lr: 0.000424 loss: 3.2091 (3.2517) grad_norm: 1.6052 (inf) time: 0.6248 [2021-03-27 12:08:56 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 850/1251] eta: 0:04:15 lr: 0.000424 loss: 3.1046 (3.2512) grad_norm: 1.6897 (inf) time: 0.6255 [2021-03-27 12:09:02 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 860/1251] eta: 0:04:08 lr: 0.000424 loss: 3.1550 (3.2505) grad_norm: 1.4642 (inf) time: 0.6328 [2021-03-27 12:09:08 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 870/1251] eta: 0:04:02 lr: 0.000424 loss: 3.1588 (3.2484) grad_norm: 1.5321 (inf) time: 0.6381 [2021-03-27 12:09:15 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 880/1251] eta: 0:03:56 lr: 0.000424 loss: 3.2887 (3.2503) grad_norm: 1.5322 (inf) time: 0.6349 [2021-03-27 12:09:21 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 890/1251] eta: 0:03:49 lr: 0.000424 loss: 3.2887 (3.2465) grad_norm: 1.4572 (inf) time: 0.6298 [2021-03-27 12:09:27 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 900/1251] eta: 0:03:43 lr: 0.000424 loss: 3.0758 (3.2476) grad_norm: 1.5535 (inf) time: 0.6291 [2021-03-27 12:09:34 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 910/1251] eta: 0:03:37 lr: 0.000424 loss: 3.1944 (3.2463) grad_norm: 1.5585 (inf) time: 0.6302 [2021-03-27 12:09:40 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 920/1251] eta: 0:03:30 lr: 0.000424 loss: 3.1944 (3.2474) grad_norm: 1.5530 (inf) time: 0.6337 [2021-03-27 12:09:46 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 930/1251] eta: 0:03:24 lr: 0.000424 loss: 3.2344 (3.2466) grad_norm: 1.6242 (inf) time: 0.6294 [2021-03-27 12:09:53 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 940/1251] eta: 0:03:17 lr: 0.000424 loss: 2.9772 (3.2417) grad_norm: 1.6563 (inf) time: 0.6290 [2021-03-27 12:09:59 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 950/1251] eta: 0:03:11 lr: 0.000424 loss: 3.0514 (3.2408) grad_norm: 1.6563 (inf) time: 0.6281 [2021-03-27 12:10:05 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 960/1251] eta: 0:03:05 lr: 0.000424 loss: 3.2041 (3.2419) grad_norm: 1.6713 (inf) time: 0.6264 [2021-03-27 12:10:11 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 970/1251] eta: 0:02:58 lr: 0.000424 loss: 3.4242 (3.2421) grad_norm: 1.6289 (inf) time: 0.6286 [2021-03-27 12:10:18 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 980/1251] eta: 0:02:52 lr: 0.000424 loss: 3.0577 (3.2400) grad_norm: 1.5981 (inf) time: 0.6273 [2021-03-27 12:10:24 swin_base_patch4_window7_224] INFO: Epoch: [165] [ 990/1251] eta: 0:02:45 lr: 0.000424 loss: 3.1728 (3.2399) grad_norm: 1.5803 (inf) time: 0.6247 [2021-03-27 12:10:30 swin_base_patch4_window7_224] INFO: Epoch: [165] [1000/1251] eta: 0:02:39 lr: 0.000423 loss: 3.4561 (3.2416) grad_norm: 1.6024 (inf) time: 0.6285 [2021-03-27 12:10:37 swin_base_patch4_window7_224] INFO: Epoch: [165] [1010/1251] eta: 0:02:33 lr: 0.000423 loss: 3.4982 (3.2432) grad_norm: 1.5525 (inf) time: 0.6415 [2021-03-27 12:10:43 swin_base_patch4_window7_224] INFO: Epoch: [165] [1020/1251] eta: 0:02:26 lr: 0.000423 loss: 3.5021 (3.2463) grad_norm: 1.5812 (inf) time: 0.6395 [2021-03-27 12:10:49 swin_base_patch4_window7_224] INFO: Epoch: [165] [1030/1251] eta: 0:02:20 lr: 0.000423 loss: 3.4735 (3.2467) grad_norm: 1.5924 (inf) time: 0.6346 [2021-03-27 12:10:56 swin_base_patch4_window7_224] INFO: Epoch: [165] [1040/1251] eta: 0:02:14 lr: 0.000423 loss: 3.1195 (3.2437) grad_norm: 1.5458 (inf) time: 0.6357 [2021-03-27 12:11:02 swin_base_patch4_window7_224] INFO: Epoch: [165] [1050/1251] eta: 0:02:07 lr: 0.000423 loss: 3.2174 (3.2457) grad_norm: 1.4969 (inf) time: 0.6337 [2021-03-27 12:11:08 swin_base_patch4_window7_224] INFO: Epoch: [165] [1060/1251] eta: 0:02:01 lr: 0.000423 loss: 3.2174 (3.2418) grad_norm: 1.5189 (inf) time: 0.6340 [2021-03-27 12:11:15 swin_base_patch4_window7_224] INFO: Epoch: [165] [1070/1251] eta: 0:01:55 lr: 0.000423 loss: 2.7209 (3.2405) grad_norm: 1.6461 (inf) time: 0.6280 [2021-03-27 12:11:21 swin_base_patch4_window7_224] INFO: Epoch: [165] [1080/1251] eta: 0:01:48 lr: 0.000423 loss: 3.0629 (3.2379) grad_norm: 1.6287 (inf) time: 0.6312 [2021-03-27 12:11:27 swin_base_patch4_window7_224] INFO: Epoch: [165] [1090/1251] eta: 0:01:42 lr: 0.000423 loss: 3.0679 (3.2376) grad_norm: 1.6040 (inf) time: 0.6299 [2021-03-27 12:11:34 swin_base_patch4_window7_224] INFO: Epoch: [165] [1100/1251] eta: 0:01:35 lr: 0.000423 loss: 3.1684 (3.2388) grad_norm: 1.5986 (inf) time: 0.6272 [2021-03-27 12:11:40 swin_base_patch4_window7_224] INFO: Epoch: [165] [1110/1251] eta: 0:01:29 lr: 0.000423 loss: 3.3974 (3.2399) grad_norm: 1.5770 (inf) time: 0.6294 [2021-03-27 12:11:46 swin_base_patch4_window7_224] INFO: Epoch: [165] [1120/1251] eta: 0:01:23 lr: 0.000423 loss: 3.4153 (3.2413) grad_norm: 1.5877 (inf) time: 0.6288 [2021-03-27 12:11:53 swin_base_patch4_window7_224] INFO: Epoch: [165] [1130/1251] eta: 0:01:16 lr: 0.000423 loss: 3.3416 (3.2404) grad_norm: 1.6428 (inf) time: 0.6360 [2021-03-27 12:11:59 swin_base_patch4_window7_224] INFO: Epoch: [165] [1140/1251] eta: 0:01:10 lr: 0.000423 loss: 3.3416 (3.2413) grad_norm: 1.6628 (inf) time: 0.6359 [2021-03-27 12:12:05 swin_base_patch4_window7_224] INFO: Epoch: [165] [1150/1251] eta: 0:01:04 lr: 0.000423 loss: 3.3940 (3.2414) grad_norm: 1.5922 (inf) time: 0.6294 [2021-03-27 12:12:11 swin_base_patch4_window7_224] INFO: Epoch: [165] [1160/1251] eta: 0:00:57 lr: 0.000423 loss: 3.4351 (3.2418) grad_norm: 1.5950 (inf) time: 0.6280 [2021-03-27 12:12:18 swin_base_patch4_window7_224] INFO: Epoch: [165] [1170/1251] eta: 0:00:51 lr: 0.000423 loss: 3.3814 (3.2414) grad_norm: 1.6806 (inf) time: 0.6250 [2021-03-27 12:12:24 swin_base_patch4_window7_224] INFO: Epoch: [165] [1180/1251] eta: 0:00:45 lr: 0.000423 loss: 3.3424 (3.2418) grad_norm: 1.6665 (inf) time: 0.6258 [2021-03-27 12:12:30 swin_base_patch4_window7_224] INFO: Epoch: [165] [1190/1251] eta: 0:00:38 lr: 0.000423 loss: 3.3450 (3.2437) grad_norm: 1.5623 (inf) time: 0.6280 [2021-03-27 12:12:37 swin_base_patch4_window7_224] INFO: Epoch: [165] [1200/1251] eta: 0:00:32 lr: 0.000423 loss: 3.4855 (3.2462) grad_norm: 1.4799 (inf) time: 0.6330 [2021-03-27 12:12:43 swin_base_patch4_window7_224] INFO: Epoch: [165] [1210/1251] eta: 0:00:26 lr: 0.000423 loss: 3.4855 (3.2469) grad_norm: 1.5336 (inf) time: 0.6350 [2021-03-27 12:12:49 swin_base_patch4_window7_224] INFO: Epoch: [165] [1220/1251] eta: 0:00:19 lr: 0.000423 loss: 3.2212 (3.2458) grad_norm: 1.6268 (inf) time: 0.6337 [2021-03-27 12:12:55 swin_base_patch4_window7_224] INFO: Epoch: [165] [1230/1251] eta: 0:00:13 lr: 0.000423 loss: 3.0921 (3.2438) grad_norm: 1.6116 (inf) time: 0.6296 [2021-03-27 12:13:02 swin_base_patch4_window7_224] INFO: Epoch: [165] [1240/1251] eta: 0:00:06 lr: 0.000422 loss: 2.8978 (3.2416) grad_norm: 1.4989 (inf) time: 0.6256 [2021-03-27 12:13:08 swin_base_patch4_window7_224] INFO: Epoch: [165] [1250/1251] eta: 0:00:00 lr: 0.000422 loss: 3.0627 (3.2421) grad_norm: 1.5942 (inf) time: 0.6245 [2021-03-27 12:14:32 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:04 loss: 0.9830 (0.9830) acc1: 75.0000 (75.0000) acc5: 96.8750 (96.8750) [2021-03-27 12:14:34 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.8700 (0.8811) acc1: 78.1250 (80.2557) acc5: 95.3125 (95.3125) [2021-03-27 12:14:35 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.8271 (0.8647) acc1: 79.6875 (80.2827) acc5: 96.8750 (95.8333) [2021-03-27 12:14:37 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7956 (0.8544) acc1: 81.2500 (80.2923) acc5: 96.8750 (95.8165) [2021-03-27 12:14:38 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8888 (0.8902) acc1: 78.1250 (79.2302) acc5: 95.3125 (95.4268) [2021-03-27 12:14:39 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9278 (0.9050) acc1: 76.5625 (78.8800) acc5: 93.7500 (95.2640) [2021-03-27 12:14:48 swin_base_patch4_window7_224] INFO: * Acc@1 79.822 Acc@5 95.256 loss 0.885 [2021-03-27 12:14:48 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.8% [2021-03-27 12:14:48 swin_base_patch4_window7_224] INFO: Max accuracy: 79.82% [2021-03-27 12:14:52 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 0/1251] eta: 1:30:20 lr: 0.000422 loss: 3.6998 (3.6998) grad_norm: 1.3931 (1.3931) time: 4.3329 [2021-03-27 12:14:58 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 10/1251] eta: 0:19:58 lr: 0.000422 loss: 3.2466 (3.1773) grad_norm: 1.5790 (1.5800) time: 0.9657 [2021-03-27 12:15:04 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 20/1251] eta: 0:16:31 lr: 0.000422 loss: 3.1768 (3.1766) grad_norm: 1.5790 (1.5934) time: 0.6288 [2021-03-27 12:15:11 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 30/1251] eta: 0:15:13 lr: 0.000422 loss: 3.0785 (3.0980) grad_norm: 1.6761 (1.6539) time: 0.6287 [2021-03-27 12:15:17 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 40/1251] eta: 0:14:31 lr: 0.000422 loss: 3.2428 (3.1750) grad_norm: 1.6801 (1.6529) time: 0.6293 [2021-03-27 12:15:23 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 50/1251] eta: 0:14:02 lr: 0.000422 loss: 3.3009 (3.1721) grad_norm: 1.6579 (1.6596) time: 0.6297 [2021-03-27 12:15:30 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 60/1251] eta: 0:13:40 lr: 0.000422 loss: 3.2567 (3.1772) grad_norm: 1.6603 (1.6509) time: 0.6270 [2021-03-27 12:15:36 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 70/1251] eta: 0:13:23 lr: 0.000422 loss: 3.4128 (3.2068) grad_norm: 1.5963 (1.6434) time: 0.6263 [2021-03-27 12:15:42 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 80/1251] eta: 0:13:08 lr: 0.000422 loss: 3.5404 (3.2511) grad_norm: 1.5287 (1.6300) time: 0.6261 [2021-03-27 12:15:48 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 90/1251] eta: 0:12:56 lr: 0.000422 loss: 3.5124 (3.2541) grad_norm: 1.5584 (1.6385) time: 0.6265 [2021-03-27 12:15:55 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 100/1251] eta: 0:12:44 lr: 0.000422 loss: 3.2356 (3.2468) grad_norm: 1.6566 (1.6462) time: 0.6253 [2021-03-27 12:16:01 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 110/1251] eta: 0:12:33 lr: 0.000422 loss: 3.0723 (3.2213) grad_norm: 1.6141 (1.6404) time: 0.6237 [2021-03-27 12:16:07 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 120/1251] eta: 0:12:24 lr: 0.000422 loss: 3.1003 (3.2336) grad_norm: 1.5456 (1.6317) time: 0.6268 [2021-03-27 12:16:14 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 130/1251] eta: 0:12:15 lr: 0.000422 loss: 3.1747 (3.2181) grad_norm: 1.5147 (1.6248) time: 0.6328 [2021-03-27 12:16:20 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 140/1251] eta: 0:12:07 lr: 0.000422 loss: 3.2929 (3.2225) grad_norm: 1.5949 (1.6254) time: 0.6344 [2021-03-27 12:16:26 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 150/1251] eta: 0:11:58 lr: 0.000422 loss: 3.2689 (3.2085) grad_norm: 1.6343 (1.6335) time: 0.6282 [2021-03-27 12:16:33 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 160/1251] eta: 0:11:51 lr: 0.000422 loss: 2.9783 (3.2031) grad_norm: 1.7323 (1.6447) time: 0.6361 [2021-03-27 12:16:39 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 170/1251] eta: 0:11:43 lr: 0.000422 loss: 3.0633 (3.2042) grad_norm: 1.7131 (1.6471) time: 0.6391 [2021-03-27 12:16:45 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 180/1251] eta: 0:11:36 lr: 0.000422 loss: 3.0545 (3.1826) grad_norm: 1.5964 (1.6410) time: 0.6370 [2021-03-27 12:16:52 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 190/1251] eta: 0:11:28 lr: 0.000422 loss: 2.8556 (3.1793) grad_norm: 1.5471 (1.6485) time: 0.6328 [2021-03-27 12:16:58 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 200/1251] eta: 0:11:21 lr: 0.000422 loss: 3.2286 (3.1872) grad_norm: 1.6081 (1.6464) time: 0.6268 [2021-03-27 12:17:04 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 210/1251] eta: 0:11:13 lr: 0.000422 loss: 3.2138 (3.1800) grad_norm: 1.5127 (1.6395) time: 0.6262 [2021-03-27 12:17:10 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 220/1251] eta: 0:11:06 lr: 0.000422 loss: 3.0391 (3.1724) grad_norm: 1.5885 (1.6430) time: 0.6269 [2021-03-27 12:17:17 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 230/1251] eta: 0:10:59 lr: 0.000422 loss: 3.1342 (3.1742) grad_norm: 1.6635 (1.6478) time: 0.6298 [2021-03-27 12:17:23 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 240/1251] eta: 0:10:52 lr: 0.000421 loss: 3.1396 (3.1761) grad_norm: 1.6347 (1.6459) time: 0.6309 [2021-03-27 12:17:30 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 250/1251] eta: 0:10:45 lr: 0.000421 loss: 3.1363 (3.1727) grad_norm: 1.6777 (1.6525) time: 0.6431 [2021-03-27 12:17:36 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 260/1251] eta: 0:10:38 lr: 0.000421 loss: 3.2517 (3.1810) grad_norm: 1.6271 (1.6500) time: 0.6389 [2021-03-27 12:17:42 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 270/1251] eta: 0:10:31 lr: 0.000421 loss: 3.2743 (3.1824) grad_norm: 1.5233 (1.6452) time: 0.6282 [2021-03-27 12:17:48 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 280/1251] eta: 0:10:24 lr: 0.000421 loss: 3.2988 (3.1884) grad_norm: 1.5615 (1.6451) time: 0.6302 [2021-03-27 12:17:55 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 290/1251] eta: 0:10:17 lr: 0.000421 loss: 3.2951 (3.1865) grad_norm: 1.6636 (1.6469) time: 0.6253 [2021-03-27 12:18:01 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 300/1251] eta: 0:10:10 lr: 0.000421 loss: 3.3491 (3.1983) grad_norm: 1.6728 (1.6500) time: 0.6266 [2021-03-27 12:18:07 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 310/1251] eta: 0:10:04 lr: 0.000421 loss: 3.4522 (3.1991) grad_norm: 1.6826 (1.6527) time: 0.6297 [2021-03-27 12:18:14 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 320/1251] eta: 0:09:57 lr: 0.000421 loss: 3.2319 (3.1923) grad_norm: 1.5885 (1.6502) time: 0.6296 [2021-03-27 12:18:20 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 330/1251] eta: 0:09:50 lr: 0.000421 loss: 3.2445 (3.2031) grad_norm: 1.5984 (1.6498) time: 0.6308 [2021-03-27 12:18:26 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 340/1251] eta: 0:09:43 lr: 0.000421 loss: 3.3570 (3.2045) grad_norm: 1.5984 (1.6484) time: 0.6309 [2021-03-27 12:18:32 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 350/1251] eta: 0:09:37 lr: 0.000421 loss: 3.3808 (3.2114) grad_norm: 1.6347 (1.6531) time: 0.6314 [2021-03-27 12:18:39 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 360/1251] eta: 0:09:30 lr: 0.000421 loss: 3.3808 (3.2082) grad_norm: 1.7290 (1.6564) time: 0.6295 [2021-03-27 12:18:45 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 370/1251] eta: 0:09:23 lr: 0.000421 loss: 3.2136 (3.2104) grad_norm: 1.5803 (1.6545) time: 0.6302 [2021-03-27 12:18:51 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 380/1251] eta: 0:09:17 lr: 0.000421 loss: 3.2136 (3.2050) grad_norm: 1.5738 (1.6538) time: 0.6271 [2021-03-27 12:18:58 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 390/1251] eta: 0:09:10 lr: 0.000421 loss: 3.1428 (3.2052) grad_norm: 1.5807 (1.6526) time: 0.6252 [2021-03-27 12:19:04 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 400/1251] eta: 0:09:03 lr: 0.000421 loss: 3.2781 (3.2045) grad_norm: 1.6235 (1.6541) time: 0.6254 [2021-03-27 12:19:10 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 410/1251] eta: 0:08:57 lr: 0.000421 loss: 3.1534 (3.2028) grad_norm: 1.6497 (1.6564) time: 0.6299 [2021-03-27 12:19:17 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 420/1251] eta: 0:08:50 lr: 0.000421 loss: 3.1534 (3.2061) grad_norm: 1.5611 (1.6542) time: 0.6377 [2021-03-27 12:19:23 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 430/1251] eta: 0:08:44 lr: 0.000421 loss: 3.2365 (3.2081) grad_norm: 1.5776 (1.6543) time: 0.6341 [2021-03-27 12:19:29 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 440/1251] eta: 0:08:37 lr: 0.000421 loss: 3.5204 (3.2104) grad_norm: 1.6416 (1.6547) time: 0.6324 [2021-03-27 12:19:36 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 450/1251] eta: 0:08:31 lr: 0.000421 loss: 3.3113 (3.2069) grad_norm: 1.5518 (1.6515) time: 0.6319 [2021-03-27 12:19:42 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 460/1251] eta: 0:08:25 lr: 0.000421 loss: 3.2956 (3.2111) grad_norm: 1.5760 (1.6510) time: 0.6358 [2021-03-27 12:19:48 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 470/1251] eta: 0:08:18 lr: 0.000421 loss: 3.4138 (3.2103) grad_norm: 1.6102 (1.6518) time: 0.6366 [2021-03-27 12:19:55 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 480/1251] eta: 0:08:11 lr: 0.000420 loss: 3.3598 (3.2075) grad_norm: 1.5449 (1.6521) time: 0.6284 [2021-03-27 12:20:01 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 490/1251] eta: 0:08:05 lr: 0.000420 loss: 3.1605 (3.2096) grad_norm: 1.5331 (1.6492) time: 0.6249 [2021-03-27 12:20:07 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 500/1251] eta: 0:07:58 lr: 0.000420 loss: 3.2932 (3.2097) grad_norm: 1.5156 (1.6472) time: 0.6259 [2021-03-27 12:20:13 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 510/1251] eta: 0:07:52 lr: 0.000420 loss: 3.2932 (3.2112) grad_norm: 1.5533 (1.6470) time: 0.6339 [2021-03-27 12:20:20 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 520/1251] eta: 0:07:46 lr: 0.000420 loss: 3.2842 (3.2111) grad_norm: 1.6351 (1.6470) time: 0.6384 [2021-03-27 12:20:26 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 530/1251] eta: 0:07:39 lr: 0.000420 loss: 3.2124 (3.2127) grad_norm: 1.5901 (1.6460) time: 0.6359 [2021-03-27 12:20:32 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 540/1251] eta: 0:07:33 lr: 0.000420 loss: 3.3032 (3.2118) grad_norm: 1.5901 (1.6461) time: 0.6297 [2021-03-27 12:20:39 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 550/1251] eta: 0:07:26 lr: 0.000420 loss: 3.1956 (3.2087) grad_norm: 1.6437 (1.6464) time: 0.6396 [2021-03-27 12:20:45 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 560/1251] eta: 0:07:20 lr: 0.000420 loss: 3.3082 (3.2126) grad_norm: 1.6460 (1.6467) time: 0.6446 [2021-03-27 12:20:52 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 570/1251] eta: 0:07:14 lr: 0.000420 loss: 3.3477 (3.2128) grad_norm: 1.6434 (1.6479) time: 0.6328 [2021-03-27 12:20:58 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 580/1251] eta: 0:07:07 lr: 0.000420 loss: 3.2302 (3.2102) grad_norm: 1.6663 (1.6501) time: 0.6298 [2021-03-27 12:21:04 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 590/1251] eta: 0:07:01 lr: 0.000420 loss: 3.2628 (3.2111) grad_norm: 1.6630 (1.6497) time: 0.6277 [2021-03-27 12:21:11 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 600/1251] eta: 0:06:54 lr: 0.000420 loss: 3.2823 (3.2104) grad_norm: 1.5874 (1.6500) time: 0.6343 [2021-03-27 12:21:17 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 610/1251] eta: 0:06:48 lr: 0.000420 loss: 3.2851 (3.2091) grad_norm: 1.7415 (1.6509) time: 0.6340 [2021-03-27 12:21:23 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 620/1251] eta: 0:06:41 lr: 0.000420 loss: 3.3325 (3.2097) grad_norm: 1.7437 (1.6525) time: 0.6271 [2021-03-27 12:21:29 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 630/1251] eta: 0:06:35 lr: 0.000420 loss: 3.4122 (3.2116) grad_norm: 1.5800 (1.6513) time: 0.6248 [2021-03-27 12:21:36 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 640/1251] eta: 0:06:28 lr: 0.000420 loss: 3.3026 (3.2109) grad_norm: 1.5800 (1.6513) time: 0.6277 [2021-03-27 12:21:42 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 650/1251] eta: 0:06:22 lr: 0.000420 loss: 3.2581 (3.2110) grad_norm: 1.5407 (1.6488) time: 0.6315 [2021-03-27 12:21:48 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 660/1251] eta: 0:06:16 lr: 0.000420 loss: 3.2581 (3.2107) grad_norm: 1.4875 (1.6475) time: 0.6284 [2021-03-27 12:21:55 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 670/1251] eta: 0:06:09 lr: 0.000420 loss: 3.3527 (3.2129) grad_norm: 1.5256 (1.6462) time: 0.6388 [2021-03-27 12:22:01 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 680/1251] eta: 0:06:03 lr: 0.000420 loss: 3.3527 (3.2108) grad_norm: 1.6179 (1.6470) time: 0.6479 [2021-03-27 12:22:08 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 690/1251] eta: 0:05:57 lr: 0.000420 loss: 3.4132 (3.2134) grad_norm: 1.6520 (1.6478) time: 0.6428 [2021-03-27 12:22:14 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 700/1251] eta: 0:05:50 lr: 0.000420 loss: 3.4132 (3.2155) grad_norm: 1.6971 (1.6512) time: 0.6318 [2021-03-27 12:22:20 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 710/1251] eta: 0:05:44 lr: 0.000420 loss: 3.3820 (3.2129) grad_norm: 1.8228 (1.6528) time: 0.6251 [2021-03-27 12:22:27 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 720/1251] eta: 0:05:37 lr: 0.000420 loss: 3.2826 (3.2145) grad_norm: 1.6367 (1.6531) time: 0.6358 [2021-03-27 12:22:33 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 730/1251] eta: 0:05:31 lr: 0.000419 loss: 3.3118 (3.2137) grad_norm: 1.6113 (1.6526) time: 0.6372 [2021-03-27 12:22:39 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 740/1251] eta: 0:05:25 lr: 0.000419 loss: 3.2464 (3.2151) grad_norm: 1.6113 (1.6528) time: 0.6371 [2021-03-27 12:22:46 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 750/1251] eta: 0:05:18 lr: 0.000419 loss: 3.2464 (3.2145) grad_norm: 1.6326 (1.6543) time: 0.6449 [2021-03-27 12:22:52 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 760/1251] eta: 0:05:12 lr: 0.000419 loss: 3.3112 (3.2143) grad_norm: 1.6291 (1.6543) time: 0.6403 [2021-03-27 12:22:58 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 770/1251] eta: 0:05:06 lr: 0.000419 loss: 3.2018 (3.2116) grad_norm: 1.6227 (1.6542) time: 0.6295 [2021-03-27 12:23:05 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 780/1251] eta: 0:04:59 lr: 0.000419 loss: 3.2126 (3.2126) grad_norm: 1.6227 (1.6543) time: 0.6285 [2021-03-27 12:23:11 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 790/1251] eta: 0:04:53 lr: 0.000419 loss: 3.3440 (3.2088) grad_norm: 1.5533 (1.6530) time: 0.6334 [2021-03-27 12:23:17 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 800/1251] eta: 0:04:46 lr: 0.000419 loss: 2.9684 (3.2070) grad_norm: 1.5533 (1.6531) time: 0.6339 [2021-03-27 12:23:24 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 810/1251] eta: 0:04:40 lr: 0.000419 loss: 3.1986 (3.2052) grad_norm: 1.6376 (1.6535) time: 0.6333 [2021-03-27 12:23:30 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 820/1251] eta: 0:04:34 lr: 0.000419 loss: 3.0285 (3.2027) grad_norm: 1.5824 (1.6530) time: 0.6292 [2021-03-27 12:23:36 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 830/1251] eta: 0:04:27 lr: 0.000419 loss: 3.2813 (3.2044) grad_norm: 1.5824 (1.6540) time: 0.6314 [2021-03-27 12:23:43 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 840/1251] eta: 0:04:21 lr: 0.000419 loss: 3.3150 (3.2034) grad_norm: 1.6015 (1.6539) time: 0.6352 [2021-03-27 12:23:49 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 850/1251] eta: 0:04:15 lr: 0.000419 loss: 3.1390 (3.2026) grad_norm: 1.5497 (1.6532) time: 0.6365 [2021-03-27 12:23:55 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 860/1251] eta: 0:04:08 lr: 0.000419 loss: 3.1746 (3.2028) grad_norm: 1.6673 (1.6548) time: 0.6337 [2021-03-27 12:24:02 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 870/1251] eta: 0:04:02 lr: 0.000419 loss: 3.1759 (3.2037) grad_norm: 1.6874 (1.6555) time: 0.6301 [2021-03-27 12:24:08 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 880/1251] eta: 0:03:55 lr: 0.000419 loss: 3.3349 (3.2049) grad_norm: 1.6353 (1.6558) time: 0.6338 [2021-03-27 12:24:14 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 890/1251] eta: 0:03:49 lr: 0.000419 loss: 3.1854 (3.2037) grad_norm: 1.6414 (1.6561) time: 0.6343 [2021-03-27 12:24:21 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 900/1251] eta: 0:03:43 lr: 0.000419 loss: 3.1854 (3.2048) grad_norm: 1.6144 (1.6556) time: 0.6311 [2021-03-27 12:24:27 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 910/1251] eta: 0:03:36 lr: 0.000419 loss: 3.4780 (3.2065) grad_norm: 1.6310 (1.6565) time: 0.6335 [2021-03-27 12:24:33 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 920/1251] eta: 0:03:30 lr: 0.000419 loss: 3.2704 (3.2047) grad_norm: 1.6514 (1.6566) time: 0.6324 [2021-03-27 12:24:40 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 930/1251] eta: 0:03:24 lr: 0.000419 loss: 3.2704 (3.2072) grad_norm: 1.6127 (1.6574) time: 0.6288 [2021-03-27 12:24:46 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 940/1251] eta: 0:03:17 lr: 0.000419 loss: 3.3551 (3.2077) grad_norm: 1.6634 (1.6580) time: 0.6293 [2021-03-27 12:24:52 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 950/1251] eta: 0:03:11 lr: 0.000419 loss: 3.4471 (3.2098) grad_norm: 1.6353 (1.6587) time: 0.6255 [2021-03-27 12:24:58 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 960/1251] eta: 0:03:04 lr: 0.000419 loss: 3.4427 (3.2107) grad_norm: 1.6352 (1.6598) time: 0.6226 [2021-03-27 12:25:05 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 970/1251] eta: 0:02:58 lr: 0.000418 loss: 3.2500 (3.2096) grad_norm: 1.6058 (1.6606) time: 0.6300 [2021-03-27 12:25:11 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 980/1251] eta: 0:02:52 lr: 0.000418 loss: 3.1549 (3.2068) grad_norm: 1.5929 (1.6601) time: 0.6283 [2021-03-27 12:25:17 swin_base_patch4_window7_224] INFO: Epoch: [166] [ 990/1251] eta: 0:02:45 lr: 0.000418 loss: 3.1549 (3.2046) grad_norm: 1.5256 (1.6588) time: 0.6248 [2021-03-27 12:25:24 swin_base_patch4_window7_224] INFO: Epoch: [166] [1000/1251] eta: 0:02:39 lr: 0.000418 loss: 3.4354 (3.2091) grad_norm: 1.5131 (1.6581) time: 0.6380 [2021-03-27 12:25:30 swin_base_patch4_window7_224] INFO: Epoch: [166] [1010/1251] eta: 0:02:33 lr: 0.000418 loss: 3.4229 (3.2080) grad_norm: 1.6136 (1.6586) time: 0.6448 [2021-03-27 12:25:36 swin_base_patch4_window7_224] INFO: Epoch: [166] [1020/1251] eta: 0:02:26 lr: 0.000418 loss: 3.0686 (3.2060) grad_norm: 1.6031 (1.6577) time: 0.6357 [2021-03-27 12:25:43 swin_base_patch4_window7_224] INFO: Epoch: [166] [1030/1251] eta: 0:02:20 lr: 0.000418 loss: 3.2492 (3.2068) grad_norm: 1.5118 (1.6570) time: 0.6319 [2021-03-27 12:25:49 swin_base_patch4_window7_224] INFO: Epoch: [166] [1040/1251] eta: 0:02:14 lr: 0.000418 loss: 3.1080 (3.2045) grad_norm: 1.6359 (1.6578) time: 0.6310 [2021-03-27 12:25:55 swin_base_patch4_window7_224] INFO: Epoch: [166] [1050/1251] eta: 0:02:07 lr: 0.000418 loss: 2.9162 (3.2031) grad_norm: 1.6978 (1.6579) time: 0.6275 [2021-03-27 12:26:02 swin_base_patch4_window7_224] INFO: Epoch: [166] [1060/1251] eta: 0:02:01 lr: 0.000418 loss: 3.4895 (3.2054) grad_norm: 1.7130 (1.6595) time: 0.6345 [2021-03-27 12:26:08 swin_base_patch4_window7_224] INFO: Epoch: [166] [1070/1251] eta: 0:01:54 lr: 0.000418 loss: 3.2986 (3.2061) grad_norm: 1.7730 (1.6596) time: 0.6336 [2021-03-27 12:26:14 swin_base_patch4_window7_224] INFO: Epoch: [166] [1080/1251] eta: 0:01:48 lr: 0.000418 loss: 3.2646 (3.2064) grad_norm: 1.6451 (1.6595) time: 0.6341 [2021-03-27 12:26:21 swin_base_patch4_window7_224] INFO: Epoch: [166] [1090/1251] eta: 0:01:42 lr: 0.000418 loss: 3.3167 (3.2057) grad_norm: 1.6031 (1.6587) time: 0.6342 [2021-03-27 12:26:27 swin_base_patch4_window7_224] INFO: Epoch: [166] [1100/1251] eta: 0:01:35 lr: 0.000418 loss: 3.3256 (3.2058) grad_norm: 1.6245 (1.6589) time: 0.6262 [2021-03-27 12:26:33 swin_base_patch4_window7_224] INFO: Epoch: [166] [1110/1251] eta: 0:01:29 lr: 0.000418 loss: 3.3531 (3.2082) grad_norm: 1.6613 (1.6591) time: 0.6290 [2021-03-27 12:26:40 swin_base_patch4_window7_224] INFO: Epoch: [166] [1120/1251] eta: 0:01:23 lr: 0.000418 loss: 3.3531 (3.2081) grad_norm: 1.6474 (1.6588) time: 0.6328 [2021-03-27 12:26:46 swin_base_patch4_window7_224] INFO: Epoch: [166] [1130/1251] eta: 0:01:16 lr: 0.000418 loss: 3.2361 (3.2089) grad_norm: 1.6344 (1.6586) time: 0.6364 [2021-03-27 12:26:52 swin_base_patch4_window7_224] INFO: Epoch: [166] [1140/1251] eta: 0:01:10 lr: 0.000418 loss: 3.4545 (3.2097) grad_norm: 1.5955 (1.6583) time: 0.6324 [2021-03-27 12:26:59 swin_base_patch4_window7_224] INFO: Epoch: [166] [1150/1251] eta: 0:01:04 lr: 0.000418 loss: 3.4545 (3.2099) grad_norm: 1.6087 (1.6589) time: 0.6288 [2021-03-27 12:27:05 swin_base_patch4_window7_224] INFO: Epoch: [166] [1160/1251] eta: 0:00:57 lr: 0.000418 loss: 3.3713 (3.2114) grad_norm: 1.6087 (1.6579) time: 0.6288 [2021-03-27 12:27:11 swin_base_patch4_window7_224] INFO: Epoch: [166] [1170/1251] eta: 0:00:51 lr: 0.000418 loss: 3.5277 (3.2138) grad_norm: 1.5768 (1.6574) time: 0.6229 [2021-03-27 12:27:17 swin_base_patch4_window7_224] INFO: Epoch: [166] [1180/1251] eta: 0:00:45 lr: 0.000418 loss: 3.5269 (3.2158) grad_norm: 1.5912 (1.6572) time: 0.6215 [2021-03-27 12:27:24 swin_base_patch4_window7_224] INFO: Epoch: [166] [1190/1251] eta: 0:00:38 lr: 0.000418 loss: 3.3373 (3.2154) grad_norm: 1.6144 (1.6576) time: 0.6242 [2021-03-27 12:27:30 swin_base_patch4_window7_224] INFO: Epoch: [166] [1200/1251] eta: 0:00:32 lr: 0.000418 loss: 3.2929 (3.2171) grad_norm: 1.6903 (1.6586) time: 0.6295 [2021-03-27 12:27:36 swin_base_patch4_window7_224] INFO: Epoch: [166] [1210/1251] eta: 0:00:26 lr: 0.000418 loss: 3.4082 (3.2183) grad_norm: 1.6947 (1.6587) time: 0.6320 [2021-03-27 12:27:42 swin_base_patch4_window7_224] INFO: Epoch: [166] [1220/1251] eta: 0:00:19 lr: 0.000417 loss: 3.2412 (3.2191) grad_norm: 1.5418 (1.6577) time: 0.6302 [2021-03-27 12:27:49 swin_base_patch4_window7_224] INFO: Epoch: [166] [1230/1251] eta: 0:00:13 lr: 0.000417 loss: 3.4150 (3.2216) grad_norm: 1.5418 (1.6580) time: 0.6296 [2021-03-27 12:27:55 swin_base_patch4_window7_224] INFO: Epoch: [166] [1240/1251] eta: 0:00:06 lr: 0.000417 loss: 3.4272 (3.2220) grad_norm: 1.5610 (1.6569) time: 0.6298 [2021-03-27 12:28:01 swin_base_patch4_window7_224] INFO: Epoch: [166] [1250/1251] eta: 0:00:00 lr: 0.000417 loss: 3.0124 (3.2208) grad_norm: 1.4744 (1.6560) time: 0.6236 [2021-03-27 12:28:12 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:15 loss: 0.6437 (0.6437) acc1: 82.8125 (82.8125) acc5: 100.0000 (100.0000) [2021-03-27 12:28:15 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8462 (0.8996) acc1: 79.6875 (77.6989) acc5: 95.3125 (95.1705) [2021-03-27 12:28:17 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8462 (0.8780) acc1: 79.6875 (78.5714) acc5: 95.3125 (94.7173) [2021-03-27 12:28:20 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9279 (0.9076) acc1: 78.1250 (77.9738) acc5: 95.3125 (94.9093) [2021-03-27 12:28:22 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8410 (0.8991) acc1: 79.6875 (78.3155) acc5: 96.8750 (95.2744) [2021-03-27 12:28:23 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8267 (0.8883) acc1: 79.6875 (78.6560) acc5: 94.3396 (95.1040) [2021-03-27 12:28:34 swin_base_patch4_window7_224] INFO: * Acc@1 79.750 Acc@5 95.134 loss 0.872 [2021-03-27 12:28:34 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.8% [2021-03-27 12:28:34 swin_base_patch4_window7_224] INFO: Max accuracy: 79.82% [2021-03-27 12:28:38 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 0/1251] eta: 1:30:38 lr: 0.000417 loss: 3.7231 (3.7231) grad_norm: 1.5385 (1.5385) time: 4.3472 [2021-03-27 12:28:44 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 10/1251] eta: 0:20:10 lr: 0.000417 loss: 3.2819 (3.2136) grad_norm: 1.5552 (1.6439) time: 0.9755 [2021-03-27 12:28:51 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 20/1251] eta: 0:16:34 lr: 0.000417 loss: 3.0593 (3.1652) grad_norm: 1.7094 (1.7017) time: 0.6313 [2021-03-27 12:28:57 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 30/1251] eta: 0:15:17 lr: 0.000417 loss: 2.9626 (3.1478) grad_norm: 1.6678 (1.6874) time: 0.6284 [2021-03-27 12:29:03 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 40/1251] eta: 0:14:35 lr: 0.000417 loss: 3.2423 (3.1935) grad_norm: 1.6032 (1.6938) time: 0.6340 [2021-03-27 12:29:10 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 50/1251] eta: 0:14:05 lr: 0.000417 loss: 3.2522 (3.2236) grad_norm: 1.6063 (1.6774) time: 0.6306 [2021-03-27 12:29:16 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 60/1251] eta: 0:13:43 lr: 0.000417 loss: 3.3326 (3.2383) grad_norm: 1.5133 (1.6517) time: 0.6268 [2021-03-27 12:29:22 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 70/1251] eta: 0:13:27 lr: 0.000417 loss: 3.2931 (3.2162) grad_norm: 1.5481 (1.6477) time: 0.6304 [2021-03-27 12:29:28 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 80/1251] eta: 0:13:12 lr: 0.000417 loss: 2.9818 (3.2095) grad_norm: 1.6546 (1.6625) time: 0.6301 [2021-03-27 12:29:35 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 90/1251] eta: 0:12:59 lr: 0.000417 loss: 3.3362 (3.2098) grad_norm: 1.6639 (1.6707) time: 0.6285 [2021-03-27 12:29:41 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 100/1251] eta: 0:12:48 lr: 0.000417 loss: 3.3728 (3.2159) grad_norm: 1.5995 (1.6678) time: 0.6333 [2021-03-27 12:29:48 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 110/1251] eta: 0:12:39 lr: 0.000417 loss: 3.2179 (3.2079) grad_norm: 1.5863 (1.6599) time: 0.6380 [2021-03-27 12:29:54 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 120/1251] eta: 0:12:28 lr: 0.000417 loss: 3.2528 (3.2202) grad_norm: 1.6102 (1.6606) time: 0.6318 [2021-03-27 12:30:00 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 130/1251] eta: 0:12:19 lr: 0.000417 loss: 3.3099 (3.2204) grad_norm: 1.6384 (1.6644) time: 0.6262 [2021-03-27 12:30:06 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 140/1251] eta: 0:12:10 lr: 0.000417 loss: 3.3436 (3.2309) grad_norm: 1.6384 (1.6626) time: 0.6333 [2021-03-27 12:30:13 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 150/1251] eta: 0:12:02 lr: 0.000417 loss: 3.3764 (3.2300) grad_norm: 1.5357 (1.6556) time: 0.6344 [2021-03-27 12:30:19 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 160/1251] eta: 0:11:53 lr: 0.000417 loss: 3.2329 (3.2477) grad_norm: 1.5796 (inf) time: 0.6266 [2021-03-27 12:30:25 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 170/1251] eta: 0:11:45 lr: 0.000417 loss: 3.5772 (3.2624) grad_norm: 1.5796 (inf) time: 0.6241 [2021-03-27 12:30:32 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 180/1251] eta: 0:11:37 lr: 0.000417 loss: 3.3516 (3.2582) grad_norm: 1.5750 (inf) time: 0.6256 [2021-03-27 12:30:38 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 190/1251] eta: 0:11:29 lr: 0.000417 loss: 3.3516 (3.2672) grad_norm: 1.6897 (inf) time: 0.6320 [2021-03-27 12:30:44 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 200/1251] eta: 0:11:22 lr: 0.000417 loss: 3.5054 (3.2781) grad_norm: 1.6912 (inf) time: 0.6324 [2021-03-27 12:30:50 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 210/1251] eta: 0:11:14 lr: 0.000416 loss: 3.4514 (3.2829) grad_norm: 1.6919 (inf) time: 0.6263 [2021-03-27 12:30:57 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 220/1251] eta: 0:11:07 lr: 0.000416 loss: 3.5382 (3.2857) grad_norm: 1.6508 (inf) time: 0.6268 [2021-03-27 12:31:03 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 230/1251] eta: 0:11:00 lr: 0.000416 loss: 3.5024 (3.2883) grad_norm: 1.6764 (inf) time: 0.6323 [2021-03-27 12:31:09 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 240/1251] eta: 0:10:52 lr: 0.000416 loss: 3.4561 (3.2930) grad_norm: 1.6793 (inf) time: 0.6327 [2021-03-27 12:31:16 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 250/1251] eta: 0:10:45 lr: 0.000416 loss: 3.2730 (3.2846) grad_norm: 1.5998 (inf) time: 0.6272 [2021-03-27 12:31:22 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 260/1251] eta: 0:10:38 lr: 0.000416 loss: 3.2665 (3.2839) grad_norm: 1.5907 (inf) time: 0.6223 [2021-03-27 12:31:28 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 270/1251] eta: 0:10:31 lr: 0.000416 loss: 3.4108 (3.2853) grad_norm: 1.5976 (inf) time: 0.6258 [2021-03-27 12:31:35 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 280/1251] eta: 0:10:24 lr: 0.000416 loss: 3.3302 (3.2847) grad_norm: 1.5935 (inf) time: 0.6345 [2021-03-27 12:31:41 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 290/1251] eta: 0:10:17 lr: 0.000416 loss: 3.3302 (3.2778) grad_norm: 1.5935 (inf) time: 0.6284 [2021-03-27 12:31:47 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 300/1251] eta: 0:10:10 lr: 0.000416 loss: 3.3457 (3.2748) grad_norm: 1.5520 (inf) time: 0.6253 [2021-03-27 12:31:53 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 310/1251] eta: 0:10:03 lr: 0.000416 loss: 3.2787 (3.2625) grad_norm: 1.5578 (inf) time: 0.6279 [2021-03-27 12:32:00 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 320/1251] eta: 0:09:56 lr: 0.000416 loss: 2.6969 (3.2475) grad_norm: 1.5987 (inf) time: 0.6263 [2021-03-27 12:32:06 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 330/1251] eta: 0:09:50 lr: 0.000416 loss: 2.7795 (3.2428) grad_norm: 1.6104 (inf) time: 0.6346 [2021-03-27 12:32:12 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 340/1251] eta: 0:09:44 lr: 0.000416 loss: 3.2594 (3.2452) grad_norm: 1.6023 (inf) time: 0.6401 [2021-03-27 12:32:19 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 350/1251] eta: 0:09:37 lr: 0.000416 loss: 3.3281 (3.2456) grad_norm: 1.6023 (inf) time: 0.6371 [2021-03-27 12:32:25 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 360/1251] eta: 0:09:30 lr: 0.000416 loss: 3.3281 (3.2468) grad_norm: 1.7025 (inf) time: 0.6284 [2021-03-27 12:32:31 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 370/1251] eta: 0:09:24 lr: 0.000416 loss: 3.1822 (3.2453) grad_norm: 1.6339 (inf) time: 0.6272 [2021-03-27 12:32:38 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 380/1251] eta: 0:09:17 lr: 0.000416 loss: 3.3283 (3.2470) grad_norm: 1.6047 (inf) time: 0.6292 [2021-03-27 12:32:44 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 390/1251] eta: 0:09:10 lr: 0.000416 loss: 3.3388 (3.2470) grad_norm: 1.6711 (inf) time: 0.6300 [2021-03-27 12:32:50 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 400/1251] eta: 0:09:04 lr: 0.000416 loss: 3.3102 (3.2479) grad_norm: 1.6493 (inf) time: 0.6328 [2021-03-27 12:32:56 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 410/1251] eta: 0:08:57 lr: 0.000416 loss: 3.3102 (3.2498) grad_norm: 1.6014 (inf) time: 0.6299 [2021-03-27 12:33:03 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 420/1251] eta: 0:08:51 lr: 0.000416 loss: 3.2799 (3.2475) grad_norm: 1.5880 (inf) time: 0.6332 [2021-03-27 12:33:09 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 430/1251] eta: 0:08:44 lr: 0.000416 loss: 3.1309 (3.2404) grad_norm: 1.5837 (inf) time: 0.6315 [2021-03-27 12:33:15 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 440/1251] eta: 0:08:37 lr: 0.000416 loss: 3.1429 (3.2421) grad_norm: 1.6867 (inf) time: 0.6282 [2021-03-27 12:33:22 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 450/1251] eta: 0:08:31 lr: 0.000416 loss: 3.2027 (3.2440) grad_norm: 1.6727 (inf) time: 0.6313 [2021-03-27 12:33:28 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 460/1251] eta: 0:08:25 lr: 0.000415 loss: 3.4036 (3.2462) grad_norm: 1.5649 (inf) time: 0.6336 [2021-03-27 12:33:34 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 470/1251] eta: 0:08:18 lr: 0.000415 loss: 3.3786 (3.2410) grad_norm: 1.5287 (inf) time: 0.6324 [2021-03-27 12:33:41 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 480/1251] eta: 0:08:12 lr: 0.000415 loss: 3.3804 (3.2442) grad_norm: 1.5643 (inf) time: 0.6341 [2021-03-27 12:33:47 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 490/1251] eta: 0:08:05 lr: 0.000415 loss: 3.4357 (3.2435) grad_norm: 1.6609 (inf) time: 0.6303 [2021-03-27 12:33:53 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 500/1251] eta: 0:07:58 lr: 0.000415 loss: 3.2835 (3.2418) grad_norm: 1.5396 (inf) time: 0.6267 [2021-03-27 12:34:00 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 510/1251] eta: 0:07:52 lr: 0.000415 loss: 3.3458 (3.2453) grad_norm: 1.5396 (inf) time: 0.6282 [2021-03-27 12:34:06 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 520/1251] eta: 0:07:45 lr: 0.000415 loss: 3.3799 (3.2487) grad_norm: 1.5741 (inf) time: 0.6254 [2021-03-27 12:34:12 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 530/1251] eta: 0:07:39 lr: 0.000415 loss: 3.4033 (3.2479) grad_norm: 1.6384 (inf) time: 0.6273 [2021-03-27 12:34:18 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 540/1251] eta: 0:07:32 lr: 0.000415 loss: 3.3575 (3.2473) grad_norm: 1.6477 (inf) time: 0.6259 [2021-03-27 12:34:25 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 550/1251] eta: 0:07:26 lr: 0.000415 loss: 3.3131 (3.2457) grad_norm: 1.6170 (inf) time: 0.6404 [2021-03-27 12:34:31 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 560/1251] eta: 0:07:20 lr: 0.000415 loss: 3.3131 (3.2461) grad_norm: 1.5645 (inf) time: 0.6466 [2021-03-27 12:34:38 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 570/1251] eta: 0:07:13 lr: 0.000415 loss: 3.1784 (3.2432) grad_norm: 1.5775 (inf) time: 0.6337 [2021-03-27 12:34:44 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 580/1251] eta: 0:07:07 lr: 0.000415 loss: 3.2987 (3.2463) grad_norm: 1.6679 (inf) time: 0.6370 [2021-03-27 12:34:50 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 590/1251] eta: 0:07:01 lr: 0.000415 loss: 3.4871 (3.2480) grad_norm: 1.5663 (inf) time: 0.6357 [2021-03-27 12:34:57 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 600/1251] eta: 0:06:54 lr: 0.000415 loss: 3.3508 (3.2502) grad_norm: 1.5663 (inf) time: 0.6295 [2021-03-27 12:35:03 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 610/1251] eta: 0:06:48 lr: 0.000415 loss: 3.5481 (3.2522) grad_norm: 1.5382 (inf) time: 0.6317 [2021-03-27 12:35:09 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 620/1251] eta: 0:06:41 lr: 0.000415 loss: 3.3102 (3.2509) grad_norm: 1.6270 (inf) time: 0.6324 [2021-03-27 12:35:16 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 630/1251] eta: 0:06:35 lr: 0.000415 loss: 3.3102 (3.2525) grad_norm: 1.7523 (inf) time: 0.6278 [2021-03-27 12:35:22 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 640/1251] eta: 0:06:28 lr: 0.000415 loss: 3.3578 (3.2520) grad_norm: 1.6138 (inf) time: 0.6237 [2021-03-27 12:35:28 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 650/1251] eta: 0:06:22 lr: 0.000415 loss: 3.3680 (3.2542) grad_norm: 1.5460 (inf) time: 0.6235 [2021-03-27 12:35:34 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 660/1251] eta: 0:06:16 lr: 0.000415 loss: 3.3680 (3.2532) grad_norm: 1.6003 (inf) time: 0.6300 [2021-03-27 12:35:41 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 670/1251] eta: 0:06:09 lr: 0.000415 loss: 3.3987 (3.2546) grad_norm: 1.6691 (inf) time: 0.6315 [2021-03-27 12:35:47 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 680/1251] eta: 0:06:03 lr: 0.000415 loss: 3.3188 (3.2530) grad_norm: 1.6809 (inf) time: 0.6332 [2021-03-27 12:35:53 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 690/1251] eta: 0:05:56 lr: 0.000415 loss: 3.3188 (3.2548) grad_norm: 1.5751 (inf) time: 0.6403 [2021-03-27 12:36:00 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 700/1251] eta: 0:05:50 lr: 0.000414 loss: 3.4469 (3.2545) grad_norm: 1.5825 (inf) time: 0.6333 [2021-03-27 12:36:06 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 710/1251] eta: 0:05:44 lr: 0.000414 loss: 2.9484 (3.2498) grad_norm: 1.6369 (inf) time: 0.6264 [2021-03-27 12:36:12 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 720/1251] eta: 0:05:37 lr: 0.000414 loss: 3.1029 (3.2496) grad_norm: 1.6207 (inf) time: 0.6291 [2021-03-27 12:36:19 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 730/1251] eta: 0:05:31 lr: 0.000414 loss: 3.1327 (3.2457) grad_norm: 1.5783 (inf) time: 0.6323 [2021-03-27 12:36:25 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 740/1251] eta: 0:05:24 lr: 0.000414 loss: 3.0426 (3.2436) grad_norm: 1.5713 (inf) time: 0.6363 [2021-03-27 12:36:31 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 750/1251] eta: 0:05:18 lr: 0.000414 loss: 3.2418 (3.2445) grad_norm: 1.6792 (inf) time: 0.6390 [2021-03-27 12:36:38 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 760/1251] eta: 0:05:12 lr: 0.000414 loss: 3.3157 (3.2459) grad_norm: 1.6969 (inf) time: 0.6394 [2021-03-27 12:36:44 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 770/1251] eta: 0:05:05 lr: 0.000414 loss: 3.6010 (3.2502) grad_norm: 1.6034 (inf) time: 0.6419 [2021-03-27 12:36:51 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 780/1251] eta: 0:04:59 lr: 0.000414 loss: 3.5180 (3.2508) grad_norm: 1.5664 (inf) time: 0.6388 [2021-03-27 12:36:57 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 790/1251] eta: 0:04:53 lr: 0.000414 loss: 3.2807 (3.2511) grad_norm: 1.6577 (inf) time: 0.6357 [2021-03-27 12:37:03 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 800/1251] eta: 0:04:46 lr: 0.000414 loss: 3.2718 (3.2503) grad_norm: 1.6166 (inf) time: 0.6385 [2021-03-27 12:37:10 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 810/1251] eta: 0:04:40 lr: 0.000414 loss: 3.2514 (3.2484) grad_norm: 1.6244 (inf) time: 0.6355 [2021-03-27 12:37:16 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 820/1251] eta: 0:04:34 lr: 0.000414 loss: 3.2865 (3.2496) grad_norm: 1.6162 (inf) time: 0.6385 [2021-03-27 12:37:22 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 830/1251] eta: 0:04:27 lr: 0.000414 loss: 3.1114 (3.2457) grad_norm: 1.5445 (inf) time: 0.6357 [2021-03-27 12:37:29 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 840/1251] eta: 0:04:21 lr: 0.000414 loss: 3.2474 (3.2467) grad_norm: 1.5943 (inf) time: 0.6277 [2021-03-27 12:37:35 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 850/1251] eta: 0:04:14 lr: 0.000414 loss: 3.4621 (3.2474) grad_norm: 1.7205 (inf) time: 0.6283 [2021-03-27 12:37:41 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 860/1251] eta: 0:04:08 lr: 0.000414 loss: 3.4507 (3.2484) grad_norm: 1.7205 (inf) time: 0.6271 [2021-03-27 12:37:48 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 870/1251] eta: 0:04:02 lr: 0.000414 loss: 3.4507 (3.2494) grad_norm: 1.6152 (inf) time: 0.6294 [2021-03-27 12:37:54 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 880/1251] eta: 0:03:55 lr: 0.000414 loss: 3.3322 (3.2483) grad_norm: 1.6208 (inf) time: 0.6305 [2021-03-27 12:38:00 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 890/1251] eta: 0:03:49 lr: 0.000414 loss: 3.0442 (3.2458) grad_norm: 1.6926 (inf) time: 0.6343 [2021-03-27 12:38:06 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 900/1251] eta: 0:03:43 lr: 0.000414 loss: 3.0442 (3.2430) grad_norm: 1.6233 (inf) time: 0.6324 [2021-03-27 12:38:13 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 910/1251] eta: 0:03:36 lr: 0.000414 loss: 3.2978 (3.2444) grad_norm: 1.7108 (inf) time: 0.6286 [2021-03-27 12:38:19 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 920/1251] eta: 0:03:30 lr: 0.000414 loss: 3.3607 (3.2436) grad_norm: 1.7124 (inf) time: 0.6313 [2021-03-27 12:38:25 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 930/1251] eta: 0:03:23 lr: 0.000414 loss: 3.0862 (3.2423) grad_norm: 1.7112 (inf) time: 0.6341 [2021-03-27 12:38:32 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 940/1251] eta: 0:03:17 lr: 0.000414 loss: 3.0862 (3.2413) grad_norm: 1.7008 (inf) time: 0.6317 [2021-03-27 12:38:38 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 950/1251] eta: 0:03:11 lr: 0.000413 loss: 3.0806 (3.2404) grad_norm: 1.6327 (inf) time: 0.6366 [2021-03-27 12:38:44 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 960/1251] eta: 0:03:04 lr: 0.000413 loss: 3.1500 (3.2409) grad_norm: 1.6871 (inf) time: 0.6365 [2021-03-27 12:38:51 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 970/1251] eta: 0:02:58 lr: 0.000413 loss: 3.4159 (3.2437) grad_norm: 1.6834 (inf) time: 0.6254 [2021-03-27 12:38:57 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 980/1251] eta: 0:02:52 lr: 0.000413 loss: 3.3450 (3.2429) grad_norm: 1.5619 (inf) time: 0.6260 [2021-03-27 12:39:03 swin_base_patch4_window7_224] INFO: Epoch: [167] [ 990/1251] eta: 0:02:45 lr: 0.000413 loss: 3.3532 (3.2436) grad_norm: 1.5072 (inf) time: 0.6305 [2021-03-27 12:39:10 swin_base_patch4_window7_224] INFO: Epoch: [167] [1000/1251] eta: 0:02:39 lr: 0.000413 loss: 3.3668 (3.2417) grad_norm: 1.5746 (inf) time: 0.6347 [2021-03-27 12:39:16 swin_base_patch4_window7_224] INFO: Epoch: [167] [1010/1251] eta: 0:02:33 lr: 0.000413 loss: 3.1554 (3.2414) grad_norm: 1.6075 (inf) time: 0.6335 [2021-03-27 12:39:22 swin_base_patch4_window7_224] INFO: Epoch: [167] [1020/1251] eta: 0:02:26 lr: 0.000413 loss: 3.0638 (3.2375) grad_norm: 1.5797 (inf) time: 0.6325 [2021-03-27 12:39:29 swin_base_patch4_window7_224] INFO: Epoch: [167] [1030/1251] eta: 0:02:20 lr: 0.000413 loss: 3.0506 (3.2376) grad_norm: 1.6088 (inf) time: 0.6335 [2021-03-27 12:39:35 swin_base_patch4_window7_224] INFO: Epoch: [167] [1040/1251] eta: 0:02:13 lr: 0.000413 loss: 3.1822 (3.2391) grad_norm: 1.6088 (inf) time: 0.6254 [2021-03-27 12:39:41 swin_base_patch4_window7_224] INFO: Epoch: [167] [1050/1251] eta: 0:02:07 lr: 0.000413 loss: 3.2639 (3.2374) grad_norm: 1.7684 (inf) time: 0.6271 [2021-03-27 12:39:47 swin_base_patch4_window7_224] INFO: Epoch: [167] [1060/1251] eta: 0:02:01 lr: 0.000413 loss: 3.2639 (3.2361) grad_norm: 1.6324 (inf) time: 0.6311 [2021-03-27 12:39:54 swin_base_patch4_window7_224] INFO: Epoch: [167] [1070/1251] eta: 0:01:54 lr: 0.000413 loss: 3.2434 (3.2359) grad_norm: 1.6486 (inf) time: 0.6249 [2021-03-27 12:40:00 swin_base_patch4_window7_224] INFO: Epoch: [167] [1080/1251] eta: 0:01:48 lr: 0.000413 loss: 3.2565 (3.2375) grad_norm: 1.6942 (inf) time: 0.6290 [2021-03-27 12:40:06 swin_base_patch4_window7_224] INFO: Epoch: [167] [1090/1251] eta: 0:01:42 lr: 0.000413 loss: 3.3496 (3.2363) grad_norm: 1.6619 (inf) time: 0.6295 [2021-03-27 12:40:13 swin_base_patch4_window7_224] INFO: Epoch: [167] [1100/1251] eta: 0:01:35 lr: 0.000413 loss: 3.3736 (3.2374) grad_norm: 1.6702 (inf) time: 0.6247 [2021-03-27 12:40:19 swin_base_patch4_window7_224] INFO: Epoch: [167] [1110/1251] eta: 0:01:29 lr: 0.000413 loss: 3.3292 (3.2370) grad_norm: 1.6661 (inf) time: 0.6326 [2021-03-27 12:40:25 swin_base_patch4_window7_224] INFO: Epoch: [167] [1120/1251] eta: 0:01:23 lr: 0.000413 loss: 3.1152 (3.2366) grad_norm: 1.6661 (inf) time: 0.6381 [2021-03-27 12:40:32 swin_base_patch4_window7_224] INFO: Epoch: [167] [1130/1251] eta: 0:01:16 lr: 0.000413 loss: 3.4772 (3.2360) grad_norm: 1.6108 (inf) time: 0.6330 [2021-03-27 12:40:38 swin_base_patch4_window7_224] INFO: Epoch: [167] [1140/1251] eta: 0:01:10 lr: 0.000413 loss: 3.3353 (3.2371) grad_norm: 1.6108 (inf) time: 0.6301 [2021-03-27 12:40:44 swin_base_patch4_window7_224] INFO: Epoch: [167] [1150/1251] eta: 0:01:04 lr: 0.000413 loss: 3.3184 (3.2369) grad_norm: 1.5371 (inf) time: 0.6270 [2021-03-27 12:40:50 swin_base_patch4_window7_224] INFO: Epoch: [167] [1160/1251] eta: 0:00:57 lr: 0.000413 loss: 3.1886 (3.2356) grad_norm: 1.5239 (inf) time: 0.6231 [2021-03-27 12:40:57 swin_base_patch4_window7_224] INFO: Epoch: [167] [1170/1251] eta: 0:00:51 lr: 0.000413 loss: 3.2019 (3.2348) grad_norm: 1.5719 (inf) time: 0.6256 [2021-03-27 12:41:03 swin_base_patch4_window7_224] INFO: Epoch: [167] [1180/1251] eta: 0:00:45 lr: 0.000413 loss: 3.2650 (3.2346) grad_norm: 1.5635 (inf) time: 0.6303 [2021-03-27 12:41:09 swin_base_patch4_window7_224] INFO: Epoch: [167] [1190/1251] eta: 0:00:38 lr: 0.000412 loss: 3.2057 (3.2338) grad_norm: 1.5597 (inf) time: 0.6337 [2021-03-27 12:41:16 swin_base_patch4_window7_224] INFO: Epoch: [167] [1200/1251] eta: 0:00:32 lr: 0.000412 loss: 3.4191 (3.2344) grad_norm: 1.6074 (inf) time: 0.6319 [2021-03-27 12:41:22 swin_base_patch4_window7_224] INFO: Epoch: [167] [1210/1251] eta: 0:00:26 lr: 0.000412 loss: 2.8751 (3.2321) grad_norm: 1.5451 (inf) time: 0.6263 [2021-03-27 12:41:28 swin_base_patch4_window7_224] INFO: Epoch: [167] [1220/1251] eta: 0:00:19 lr: 0.000412 loss: 3.2304 (3.2326) grad_norm: 1.5152 (inf) time: 0.6257 [2021-03-27 12:41:34 swin_base_patch4_window7_224] INFO: Epoch: [167] [1230/1251] eta: 0:00:13 lr: 0.000412 loss: 3.2531 (3.2315) grad_norm: 1.5955 (inf) time: 0.6285 [2021-03-27 12:41:41 swin_base_patch4_window7_224] INFO: Epoch: [167] [1240/1251] eta: 0:00:06 lr: 0.000412 loss: 3.2629 (3.2328) grad_norm: 1.5939 (inf) time: 0.6247 [2021-03-27 12:41:47 swin_base_patch4_window7_224] INFO: Epoch: [167] [1250/1251] eta: 0:00:00 lr: 0.000412 loss: 3.2069 (3.2305) grad_norm: 1.5939 (inf) time: 0.6176 [2021-03-27 12:41:57 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 1.4208 (1.4208) acc1: 62.5000 (62.5000) acc5: 93.7500 (93.7500) [2021-03-27 12:42:01 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8349 (0.8900) acc1: 79.6875 (79.1193) acc5: 95.3125 (95.8807) [2021-03-27 12:42:03 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8900 (0.9308) acc1: 79.6875 (78.6458) acc5: 95.3125 (95.0149) [2021-03-27 12:42:05 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9221 (0.9276) acc1: 76.5625 (78.8306) acc5: 93.7500 (94.8085) [2021-03-27 12:42:07 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8730 (0.9012) acc1: 79.6875 (79.6494) acc5: 95.3125 (95.2363) [2021-03-27 12:42:08 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8730 (0.9014) acc1: 78.1250 (79.2320) acc5: 96.8750 (95.2960) [2021-03-27 12:42:19 swin_base_patch4_window7_224] INFO: * Acc@1 79.670 Acc@5 95.192 loss 0.880 [2021-03-27 12:42:19 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.7% [2021-03-27 12:42:19 swin_base_patch4_window7_224] INFO: Max accuracy: 79.82% [2021-03-27 12:42:23 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 0/1251] eta: 1:30:27 lr: 0.000412 loss: 3.6745 (3.6745) grad_norm: 1.6074 (1.6074) time: 4.3389 [2021-03-27 12:42:29 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 10/1251] eta: 0:19:58 lr: 0.000412 loss: 3.4227 (3.2962) grad_norm: 1.5252 (1.6033) time: 0.9654 [2021-03-27 12:42:36 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 20/1251] eta: 0:16:36 lr: 0.000412 loss: 3.1950 (3.2025) grad_norm: 1.5583 (1.6181) time: 0.6332 [2021-03-27 12:42:42 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 30/1251] eta: 0:15:21 lr: 0.000412 loss: 3.2847 (3.1608) grad_norm: 1.6250 (1.6769) time: 0.6386 [2021-03-27 12:42:48 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 40/1251] eta: 0:14:39 lr: 0.000412 loss: 3.2847 (3.1576) grad_norm: 1.7560 (1.6849) time: 0.6382 [2021-03-27 12:42:55 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 50/1251] eta: 0:14:14 lr: 0.000412 loss: 3.2523 (3.1778) grad_norm: 1.6253 (1.6692) time: 0.6453 [2021-03-27 12:43:01 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 60/1251] eta: 0:13:50 lr: 0.000412 loss: 3.2523 (3.1798) grad_norm: 1.5449 (1.6556) time: 0.6395 [2021-03-27 12:43:07 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 70/1251] eta: 0:13:32 lr: 0.000412 loss: 3.5373 (3.2077) grad_norm: 1.5926 (1.6568) time: 0.6280 [2021-03-27 12:43:14 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 80/1251] eta: 0:13:16 lr: 0.000412 loss: 3.3484 (3.1916) grad_norm: 1.6704 (1.6750) time: 0.6277 [2021-03-27 12:43:20 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 90/1251] eta: 0:13:03 lr: 0.000412 loss: 3.3421 (3.2040) grad_norm: 1.7104 (1.6789) time: 0.6268 [2021-03-27 12:43:26 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 100/1251] eta: 0:12:52 lr: 0.000412 loss: 3.5007 (3.2394) grad_norm: 1.6584 (1.6784) time: 0.6348 [2021-03-27 12:43:33 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 110/1251] eta: 0:12:41 lr: 0.000412 loss: 3.4075 (3.2208) grad_norm: 1.6350 (1.6769) time: 0.6363 [2021-03-27 12:43:39 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 120/1251] eta: 0:12:31 lr: 0.000412 loss: 3.0331 (3.1961) grad_norm: 1.5727 (1.6690) time: 0.6277 [2021-03-27 12:43:45 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 130/1251] eta: 0:12:21 lr: 0.000412 loss: 3.2479 (3.1953) grad_norm: 1.5749 (1.6653) time: 0.6246 [2021-03-27 12:43:52 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 140/1251] eta: 0:12:12 lr: 0.000412 loss: 3.3292 (3.2046) grad_norm: 1.5571 (1.6586) time: 0.6311 [2021-03-27 12:43:58 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 150/1251] eta: 0:12:04 lr: 0.000412 loss: 3.0819 (3.1862) grad_norm: 1.5615 (1.6601) time: 0.6348 [2021-03-27 12:44:04 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 160/1251] eta: 0:11:55 lr: 0.000412 loss: 2.8491 (3.1781) grad_norm: 1.5968 (1.6635) time: 0.6312 [2021-03-27 12:44:11 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 170/1251] eta: 0:11:48 lr: 0.000412 loss: 3.3324 (3.1846) grad_norm: 1.6938 (1.6693) time: 0.6351 [2021-03-27 12:44:17 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 180/1251] eta: 0:11:40 lr: 0.000412 loss: 3.4840 (3.2049) grad_norm: 1.7013 (1.6711) time: 0.6355 [2021-03-27 12:44:23 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 190/1251] eta: 0:11:32 lr: 0.000411 loss: 3.2235 (3.1817) grad_norm: 1.5562 (1.6650) time: 0.6365 [2021-03-27 12:44:30 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 200/1251] eta: 0:11:25 lr: 0.000411 loss: 2.8649 (3.1816) grad_norm: 1.5755 (1.6606) time: 0.6407 [2021-03-27 12:44:36 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 210/1251] eta: 0:11:18 lr: 0.000411 loss: 3.1904 (3.1766) grad_norm: 1.5881 (1.6606) time: 0.6421 [2021-03-27 12:44:42 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 220/1251] eta: 0:11:10 lr: 0.000411 loss: 3.1904 (3.1752) grad_norm: 1.5927 (1.6590) time: 0.6347 [2021-03-27 12:44:49 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 230/1251] eta: 0:11:03 lr: 0.000411 loss: 3.3360 (3.1779) grad_norm: 1.6336 (1.6625) time: 0.6295 [2021-03-27 12:44:55 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 240/1251] eta: 0:10:56 lr: 0.000411 loss: 3.3658 (3.1838) grad_norm: 1.5972 (1.6576) time: 0.6308 [2021-03-27 12:45:01 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 250/1251] eta: 0:10:48 lr: 0.000411 loss: 3.3896 (3.1866) grad_norm: 1.6087 (1.6645) time: 0.6267 [2021-03-27 12:45:08 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 260/1251] eta: 0:10:41 lr: 0.000411 loss: 3.3817 (3.1908) grad_norm: 1.6981 (1.6705) time: 0.6264 [2021-03-27 12:45:14 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 270/1251] eta: 0:10:34 lr: 0.000411 loss: 3.3353 (3.1848) grad_norm: 1.6385 (1.6693) time: 0.6275 [2021-03-27 12:45:20 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 280/1251] eta: 0:10:28 lr: 0.000411 loss: 3.3043 (3.1830) grad_norm: 1.6385 (1.6717) time: 0.6390 [2021-03-27 12:45:27 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 290/1251] eta: 0:10:21 lr: 0.000411 loss: 3.2909 (3.1850) grad_norm: 1.5754 (1.6690) time: 0.6401 [2021-03-27 12:45:33 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 300/1251] eta: 0:10:13 lr: 0.000411 loss: 3.0829 (3.1758) grad_norm: 1.5624 (1.6712) time: 0.6279 [2021-03-27 12:45:39 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 310/1251] eta: 0:10:07 lr: 0.000411 loss: 3.2592 (3.1912) grad_norm: 1.6092 (1.6732) time: 0.6289 [2021-03-27 12:45:46 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 320/1251] eta: 0:10:00 lr: 0.000411 loss: 3.4511 (3.1929) grad_norm: 1.6115 (1.6713) time: 0.6339 [2021-03-27 12:45:52 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 330/1251] eta: 0:09:53 lr: 0.000411 loss: 3.3725 (3.1972) grad_norm: 1.6579 (1.6757) time: 0.6408 [2021-03-27 12:45:59 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 340/1251] eta: 0:09:47 lr: 0.000411 loss: 3.3048 (3.1977) grad_norm: 1.7329 (1.6762) time: 0.6448 [2021-03-27 12:46:05 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 350/1251] eta: 0:09:40 lr: 0.000411 loss: 3.1675 (3.1979) grad_norm: 1.6375 (1.6760) time: 0.6421 [2021-03-27 12:46:11 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 360/1251] eta: 0:09:34 lr: 0.000411 loss: 2.9607 (3.1895) grad_norm: 1.6375 (1.6761) time: 0.6355 [2021-03-27 12:46:18 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 370/1251] eta: 0:09:27 lr: 0.000411 loss: 3.0387 (3.1895) grad_norm: 1.7068 (1.6859) time: 0.6327 [2021-03-27 12:46:24 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 380/1251] eta: 0:09:20 lr: 0.000411 loss: 3.1415 (3.1856) grad_norm: 1.7559 (1.6872) time: 0.6318 [2021-03-27 12:46:30 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 390/1251] eta: 0:09:14 lr: 0.000411 loss: 3.2237 (3.1880) grad_norm: 1.6644 (1.6887) time: 0.6351 [2021-03-27 12:46:37 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 400/1251] eta: 0:09:07 lr: 0.000411 loss: 3.2921 (3.1910) grad_norm: 1.6216 (1.6852) time: 0.6419 [2021-03-27 12:46:43 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 410/1251] eta: 0:09:00 lr: 0.000411 loss: 3.2921 (3.1943) grad_norm: 1.5297 (1.6815) time: 0.6331 [2021-03-27 12:46:49 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 420/1251] eta: 0:08:54 lr: 0.000411 loss: 3.2812 (3.1902) grad_norm: 1.5386 (1.6817) time: 0.6302 [2021-03-27 12:46:56 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 430/1251] eta: 0:08:47 lr: 0.000410 loss: 2.9633 (3.1879) grad_norm: 1.7090 (1.6876) time: 0.6324 [2021-03-27 12:47:02 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 440/1251] eta: 0:08:40 lr: 0.000410 loss: 3.2556 (3.1884) grad_norm: 1.7090 (1.6901) time: 0.6307 [2021-03-27 12:47:08 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 450/1251] eta: 0:08:34 lr: 0.000410 loss: 3.3058 (3.1881) grad_norm: 1.6256 (1.6894) time: 0.6324 [2021-03-27 12:47:15 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 460/1251] eta: 0:08:27 lr: 0.000410 loss: 3.2888 (3.1904) grad_norm: 1.6749 (1.6924) time: 0.6291 [2021-03-27 12:47:21 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 470/1251] eta: 0:08:21 lr: 0.000410 loss: 3.2888 (3.1929) grad_norm: 1.7638 (1.6949) time: 0.6312 [2021-03-27 12:47:27 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 480/1251] eta: 0:08:14 lr: 0.000410 loss: 3.1827 (3.1916) grad_norm: 1.6725 (1.6935) time: 0.6341 [2021-03-27 12:47:34 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 490/1251] eta: 0:08:07 lr: 0.000410 loss: 3.1230 (3.1904) grad_norm: 1.6164 (1.6934) time: 0.6305 [2021-03-27 12:47:40 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 500/1251] eta: 0:08:01 lr: 0.000410 loss: 3.2477 (3.1906) grad_norm: 1.6685 (1.6939) time: 0.6267 [2021-03-27 12:47:46 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 510/1251] eta: 0:07:54 lr: 0.000410 loss: 3.3711 (3.1934) grad_norm: 1.7867 (1.6957) time: 0.6320 [2021-03-27 12:47:52 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 520/1251] eta: 0:07:48 lr: 0.000410 loss: 3.0982 (3.1851) grad_norm: 1.7809 (1.6962) time: 0.6317 [2021-03-27 12:47:59 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 530/1251] eta: 0:07:41 lr: 0.000410 loss: 2.7238 (3.1803) grad_norm: 1.6391 (1.6960) time: 0.6240 [2021-03-27 12:48:05 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 540/1251] eta: 0:07:34 lr: 0.000410 loss: 2.8556 (3.1753) grad_norm: 1.5240 (1.6922) time: 0.6244 [2021-03-27 12:48:11 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 550/1251] eta: 0:07:28 lr: 0.000410 loss: 3.1494 (3.1784) grad_norm: 1.5240 (1.6910) time: 0.6390 [2021-03-27 12:48:18 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 560/1251] eta: 0:07:22 lr: 0.000410 loss: 3.4237 (3.1817) grad_norm: 1.6444 (1.6915) time: 0.6392 [2021-03-27 12:48:24 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 570/1251] eta: 0:07:15 lr: 0.000410 loss: 3.2837 (3.1810) grad_norm: 1.6955 (1.6917) time: 0.6259 [2021-03-27 12:48:30 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 580/1251] eta: 0:07:09 lr: 0.000410 loss: 3.2597 (3.1841) grad_norm: 1.5924 (1.6897) time: 0.6371 [2021-03-27 12:48:37 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 590/1251] eta: 0:07:02 lr: 0.000410 loss: 3.3760 (3.1873) grad_norm: 1.5696 (1.6888) time: 0.6397 [2021-03-27 12:48:43 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 600/1251] eta: 0:06:56 lr: 0.000410 loss: 3.4367 (3.1897) grad_norm: 1.6620 (1.6896) time: 0.6362 [2021-03-27 12:48:50 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 610/1251] eta: 0:06:50 lr: 0.000410 loss: 3.2273 (3.1882) grad_norm: 1.7366 (1.6882) time: 0.6440 [2021-03-27 12:48:56 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 620/1251] eta: 0:06:43 lr: 0.000410 loss: 3.1010 (3.1893) grad_norm: 1.5343 (1.6880) time: 0.6361 [2021-03-27 12:49:02 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 630/1251] eta: 0:06:37 lr: 0.000410 loss: 3.2478 (3.1880) grad_norm: 1.6541 (1.6892) time: 0.6258 [2021-03-27 12:49:09 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 640/1251] eta: 0:06:30 lr: 0.000410 loss: 3.3095 (3.1873) grad_norm: 1.7536 (1.6919) time: 0.6312 [2021-03-27 12:49:15 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 650/1251] eta: 0:06:24 lr: 0.000410 loss: 2.9832 (3.1850) grad_norm: 1.6544 (1.6900) time: 0.6349 [2021-03-27 12:49:21 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 660/1251] eta: 0:06:17 lr: 0.000410 loss: 3.3534 (3.1868) grad_norm: 1.6622 (1.6914) time: 0.6301 [2021-03-27 12:49:27 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 670/1251] eta: 0:06:11 lr: 0.000410 loss: 3.4014 (3.1867) grad_norm: 1.6894 (1.6909) time: 0.6275 [2021-03-27 12:49:34 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 680/1251] eta: 0:06:04 lr: 0.000409 loss: 3.1400 (3.1872) grad_norm: 1.6894 (1.6911) time: 0.6348 [2021-03-27 12:49:40 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 690/1251] eta: 0:05:58 lr: 0.000409 loss: 3.3207 (3.1891) grad_norm: 1.5953 (1.6909) time: 0.6355 [2021-03-27 12:49:46 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 700/1251] eta: 0:05:51 lr: 0.000409 loss: 3.1424 (3.1854) grad_norm: 1.7277 (1.6916) time: 0.6331 [2021-03-27 12:49:53 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 710/1251] eta: 0:05:45 lr: 0.000409 loss: 3.0915 (3.1873) grad_norm: 1.7194 (1.6918) time: 0.6322 [2021-03-27 12:49:59 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 720/1251] eta: 0:05:39 lr: 0.000409 loss: 3.3346 (3.1898) grad_norm: 1.5845 (1.6901) time: 0.6299 [2021-03-27 12:50:05 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 730/1251] eta: 0:05:32 lr: 0.000409 loss: 3.4653 (3.1925) grad_norm: 1.5704 (1.6884) time: 0.6340 [2021-03-27 12:50:12 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 740/1251] eta: 0:05:26 lr: 0.000409 loss: 3.4600 (3.1930) grad_norm: 1.5651 (1.6879) time: 0.6371 [2021-03-27 12:50:18 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 750/1251] eta: 0:05:19 lr: 0.000409 loss: 3.2684 (3.1916) grad_norm: 1.6332 (1.6880) time: 0.6363 [2021-03-27 12:50:25 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 760/1251] eta: 0:05:13 lr: 0.000409 loss: 2.8006 (3.1881) grad_norm: 1.5901 (1.6871) time: 0.6366 [2021-03-27 12:50:31 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 770/1251] eta: 0:05:07 lr: 0.000409 loss: 3.0853 (3.1893) grad_norm: 1.5437 (1.6853) time: 0.6387 [2021-03-27 12:50:37 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 780/1251] eta: 0:05:00 lr: 0.000409 loss: 3.2653 (3.1917) grad_norm: 1.6217 (1.6853) time: 0.6344 [2021-03-27 12:50:44 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 790/1251] eta: 0:04:54 lr: 0.000409 loss: 3.3708 (3.1936) grad_norm: 1.6274 (1.6839) time: 0.6294 [2021-03-27 12:50:50 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 800/1251] eta: 0:04:47 lr: 0.000409 loss: 3.3383 (3.1948) grad_norm: 1.5176 (1.6822) time: 0.6289 [2021-03-27 12:50:56 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 810/1251] eta: 0:04:41 lr: 0.000409 loss: 3.3937 (3.1987) grad_norm: 1.5481 (1.6816) time: 0.6290 [2021-03-27 12:51:03 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 820/1251] eta: 0:04:34 lr: 0.000409 loss: 3.5171 (3.2018) grad_norm: 1.5927 (1.6818) time: 0.6341 [2021-03-27 12:51:09 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 830/1251] eta: 0:04:28 lr: 0.000409 loss: 3.6375 (3.2077) grad_norm: 1.6641 (1.6824) time: 0.6289 [2021-03-27 12:51:15 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 840/1251] eta: 0:04:22 lr: 0.000409 loss: 3.5622 (3.2111) grad_norm: 1.6152 (1.6813) time: 0.6265 [2021-03-27 12:51:21 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 850/1251] eta: 0:04:15 lr: 0.000409 loss: 3.3881 (3.2131) grad_norm: 1.6145 (1.6819) time: 0.6375 [2021-03-27 12:51:28 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 860/1251] eta: 0:04:09 lr: 0.000409 loss: 3.3861 (3.2149) grad_norm: 1.5978 (1.6809) time: 0.6363 [2021-03-27 12:51:34 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 870/1251] eta: 0:04:02 lr: 0.000409 loss: 3.2558 (3.2142) grad_norm: 1.6461 (1.6824) time: 0.6296 [2021-03-27 12:51:40 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 880/1251] eta: 0:03:56 lr: 0.000409 loss: 3.3903 (3.2170) grad_norm: 1.6461 (1.6823) time: 0.6258 [2021-03-27 12:51:47 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 890/1251] eta: 0:03:50 lr: 0.000409 loss: 3.4408 (3.2178) grad_norm: 1.6137 (1.6816) time: 0.6271 [2021-03-27 12:51:53 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 900/1251] eta: 0:03:43 lr: 0.000409 loss: 3.2179 (3.2163) grad_norm: 1.6372 (1.6819) time: 0.6310 [2021-03-27 12:51:59 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 910/1251] eta: 0:03:37 lr: 0.000409 loss: 3.2179 (3.2169) grad_norm: 1.6372 (1.6815) time: 0.6333 [2021-03-27 12:52:06 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 920/1251] eta: 0:03:30 lr: 0.000409 loss: 3.3212 (3.2153) grad_norm: 1.6539 (1.6817) time: 0.6335 [2021-03-27 12:52:12 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 930/1251] eta: 0:03:24 lr: 0.000408 loss: 3.2275 (3.2129) grad_norm: 1.7219 (1.6838) time: 0.6375 [2021-03-27 12:52:18 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 940/1251] eta: 0:03:18 lr: 0.000408 loss: 2.9225 (3.2105) grad_norm: 1.7273 (1.6838) time: 0.6328 [2021-03-27 12:52:25 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 950/1251] eta: 0:03:11 lr: 0.000408 loss: 3.3837 (3.2124) grad_norm: 1.5237 (1.6823) time: 0.6319 [2021-03-27 12:52:31 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 960/1251] eta: 0:03:05 lr: 0.000408 loss: 3.4052 (3.2141) grad_norm: 1.5512 (1.6819) time: 0.6363 [2021-03-27 12:52:37 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 970/1251] eta: 0:02:59 lr: 0.000408 loss: 3.4052 (3.2145) grad_norm: 1.7054 (1.6832) time: 0.6364 [2021-03-27 12:52:44 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 980/1251] eta: 0:02:52 lr: 0.000408 loss: 3.4422 (3.2172) grad_norm: 1.7124 (1.6836) time: 0.6308 [2021-03-27 12:52:50 swin_base_patch4_window7_224] INFO: Epoch: [168] [ 990/1251] eta: 0:02:46 lr: 0.000408 loss: 3.4313 (3.2168) grad_norm: 1.6951 (1.6831) time: 0.6312 [2021-03-27 12:52:56 swin_base_patch4_window7_224] INFO: Epoch: [168] [1000/1251] eta: 0:02:39 lr: 0.000408 loss: 3.2372 (3.2166) grad_norm: 1.6014 (1.6831) time: 0.6352 [2021-03-27 12:53:03 swin_base_patch4_window7_224] INFO: Epoch: [168] [1010/1251] eta: 0:02:33 lr: 0.000408 loss: 3.1349 (3.2134) grad_norm: 1.6986 (1.6850) time: 0.6255 [2021-03-27 12:53:09 swin_base_patch4_window7_224] INFO: Epoch: [168] [1020/1251] eta: 0:02:27 lr: 0.000408 loss: 3.1707 (3.2143) grad_norm: 1.6986 (1.6849) time: 0.6258 [2021-03-27 12:53:15 swin_base_patch4_window7_224] INFO: Epoch: [168] [1030/1251] eta: 0:02:20 lr: 0.000408 loss: 3.3334 (3.2140) grad_norm: 1.5784 (1.6846) time: 0.6291 [2021-03-27 12:53:21 swin_base_patch4_window7_224] INFO: Epoch: [168] [1040/1251] eta: 0:02:14 lr: 0.000408 loss: 3.3335 (3.2153) grad_norm: 1.6739 (1.6852) time: 0.6265 [2021-03-27 12:53:28 swin_base_patch4_window7_224] INFO: Epoch: [168] [1050/1251] eta: 0:02:07 lr: 0.000408 loss: 3.4782 (3.2177) grad_norm: 1.6357 (1.6842) time: 0.6269 [2021-03-27 12:53:34 swin_base_patch4_window7_224] INFO: Epoch: [168] [1060/1251] eta: 0:02:01 lr: 0.000408 loss: 3.5221 (3.2208) grad_norm: 1.6210 (1.6850) time: 0.6299 [2021-03-27 12:53:40 swin_base_patch4_window7_224] INFO: Epoch: [168] [1070/1251] eta: 0:01:55 lr: 0.000408 loss: 3.5711 (3.2216) grad_norm: 1.6210 (1.6842) time: 0.6292 [2021-03-27 12:53:47 swin_base_patch4_window7_224] INFO: Epoch: [168] [1080/1251] eta: 0:01:48 lr: 0.000408 loss: 3.5305 (3.2230) grad_norm: 1.6307 (1.6846) time: 0.6286 [2021-03-27 12:53:53 swin_base_patch4_window7_224] INFO: Epoch: [168] [1090/1251] eta: 0:01:42 lr: 0.000408 loss: 3.2861 (3.2215) grad_norm: 1.6316 (1.6839) time: 0.6252 [2021-03-27 12:53:59 swin_base_patch4_window7_224] INFO: Epoch: [168] [1100/1251] eta: 0:01:36 lr: 0.000408 loss: 2.8817 (3.2170) grad_norm: 1.5516 (1.6834) time: 0.6235 [2021-03-27 12:54:05 swin_base_patch4_window7_224] INFO: Epoch: [168] [1110/1251] eta: 0:01:29 lr: 0.000408 loss: 2.5716 (3.2119) grad_norm: 1.6012 (1.6834) time: 0.6296 [2021-03-27 12:54:12 swin_base_patch4_window7_224] INFO: Epoch: [168] [1120/1251] eta: 0:01:23 lr: 0.000408 loss: 3.0131 (3.2127) grad_norm: 1.6293 (1.6840) time: 0.6355 [2021-03-27 12:54:18 swin_base_patch4_window7_224] INFO: Epoch: [168] [1130/1251] eta: 0:01:16 lr: 0.000408 loss: 3.1677 (3.2110) grad_norm: 1.5257 (1.6835) time: 0.6409 [2021-03-27 12:54:25 swin_base_patch4_window7_224] INFO: Epoch: [168] [1140/1251] eta: 0:01:10 lr: 0.000408 loss: 3.1677 (3.2104) grad_norm: 1.5225 (1.6829) time: 0.6386 [2021-03-27 12:54:31 swin_base_patch4_window7_224] INFO: Epoch: [168] [1150/1251] eta: 0:01:04 lr: 0.000408 loss: 3.2688 (3.2083) grad_norm: 1.5303 (1.6822) time: 0.6285 [2021-03-27 12:54:37 swin_base_patch4_window7_224] INFO: Epoch: [168] [1160/1251] eta: 0:00:57 lr: 0.000408 loss: 3.0073 (3.2061) grad_norm: 1.6668 (1.6825) time: 0.6313 [2021-03-27 12:54:43 swin_base_patch4_window7_224] INFO: Epoch: [168] [1170/1251] eta: 0:00:51 lr: 0.000407 loss: 3.1859 (3.2056) grad_norm: 1.6636 (1.6816) time: 0.6328 [2021-03-27 12:54:50 swin_base_patch4_window7_224] INFO: Epoch: [168] [1180/1251] eta: 0:00:45 lr: 0.000407 loss: 2.9914 (3.2024) grad_norm: 1.5685 (1.6816) time: 0.6311 [2021-03-27 12:54:56 swin_base_patch4_window7_224] INFO: Epoch: [168] [1190/1251] eta: 0:00:38 lr: 0.000407 loss: 2.9914 (3.2024) grad_norm: 1.5878 (1.6811) time: 0.6320 [2021-03-27 12:55:02 swin_base_patch4_window7_224] INFO: Epoch: [168] [1200/1251] eta: 0:00:32 lr: 0.000407 loss: 3.3259 (3.2020) grad_norm: 1.6309 (1.6818) time: 0.6322 [2021-03-27 12:55:09 swin_base_patch4_window7_224] INFO: Epoch: [168] [1210/1251] eta: 0:00:26 lr: 0.000407 loss: 3.2242 (3.2015) grad_norm: 1.6054 (1.6831) time: 0.6316 [2021-03-27 12:55:15 swin_base_patch4_window7_224] INFO: Epoch: [168] [1220/1251] eta: 0:00:19 lr: 0.000407 loss: 3.3489 (3.2030) grad_norm: 1.5583 (1.6823) time: 0.6276 [2021-03-27 12:55:21 swin_base_patch4_window7_224] INFO: Epoch: [168] [1230/1251] eta: 0:00:13 lr: 0.000407 loss: 3.3853 (3.2038) grad_norm: 1.6099 (1.6822) time: 0.6320 [2021-03-27 12:55:28 swin_base_patch4_window7_224] INFO: Epoch: [168] [1240/1251] eta: 0:00:06 lr: 0.000407 loss: 3.3515 (3.2044) grad_norm: 1.5399 (1.6808) time: 0.6314 [2021-03-27 12:55:34 swin_base_patch4_window7_224] INFO: Epoch: [168] [1250/1251] eta: 0:00:00 lr: 0.000407 loss: 3.3361 (3.2052) grad_norm: 1.5063 (1.6807) time: 0.6264 [2021-03-27 12:55:44 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:20 loss: 0.7992 (0.7992) acc1: 75.0000 (75.0000) acc5: 96.8750 (96.8750) [2021-03-27 12:55:46 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9099 (0.8999) acc1: 76.5625 (78.2670) acc5: 96.8750 (95.1705) [2021-03-27 12:55:47 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.9258 (0.8771) acc1: 79.6875 (79.3899) acc5: 95.3125 (95.0893) [2021-03-27 12:55:50 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9164 (0.8764) acc1: 79.6875 (79.2339) acc5: 93.7500 (94.7581) [2021-03-27 12:55:52 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8915 (0.8770) acc1: 78.1250 (79.2302) acc5: 93.7500 (94.8552) [2021-03-27 12:55:53 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8999 (0.8862) acc1: 78.1250 (79.1680) acc5: 95.3125 (94.8480) [2021-03-27 12:56:09 swin_base_patch4_window7_224] INFO: * Acc@1 79.922 Acc@5 95.156 loss 0.874 [2021-03-27 12:56:09 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.9% [2021-03-27 12:56:09 swin_base_patch4_window7_224] INFO: Max accuracy: 79.92% [2021-03-27 12:56:13 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 0/1251] eta: 1:30:26 lr: 0.000407 loss: 3.5482 (3.5482) grad_norm: 1.9101 (1.9101) time: 4.3379 [2021-03-27 12:56:19 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 10/1251] eta: 0:19:59 lr: 0.000407 loss: 2.9742 (2.8994) grad_norm: 1.5442 (1.6562) time: 0.9668 [2021-03-27 12:56:26 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 20/1251] eta: 0:16:31 lr: 0.000407 loss: 2.7903 (2.9193) grad_norm: 1.5442 (1.6988) time: 0.6286 [2021-03-27 12:56:32 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 30/1251] eta: 0:15:12 lr: 0.000407 loss: 3.1201 (2.9818) grad_norm: 1.6481 (1.7164) time: 0.6267 [2021-03-27 12:56:38 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 40/1251] eta: 0:14:32 lr: 0.000407 loss: 3.0643 (2.9917) grad_norm: 1.7334 (1.7411) time: 0.6322 [2021-03-27 12:56:44 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 50/1251] eta: 0:14:04 lr: 0.000407 loss: 3.3222 (3.0586) grad_norm: 1.5148 (1.6902) time: 0.6345 [2021-03-27 12:56:51 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 60/1251] eta: 0:13:42 lr: 0.000407 loss: 3.1399 (3.0426) grad_norm: 1.4377 (1.6710) time: 0.6282 [2021-03-27 12:56:57 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 70/1251] eta: 0:13:23 lr: 0.000407 loss: 2.9677 (3.0743) grad_norm: 1.6054 (1.6760) time: 0.6227 [2021-03-27 12:57:03 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 80/1251] eta: 0:13:10 lr: 0.000407 loss: 3.2159 (3.0875) grad_norm: 1.6197 (1.6700) time: 0.6279 [2021-03-27 12:57:10 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 90/1251] eta: 0:12:58 lr: 0.000407 loss: 3.3219 (3.1273) grad_norm: 1.6953 (1.6923) time: 0.6356 [2021-03-27 12:57:16 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 100/1251] eta: 0:12:46 lr: 0.000407 loss: 3.3909 (3.1382) grad_norm: 1.6825 (1.6858) time: 0.6305 [2021-03-27 12:57:22 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 110/1251] eta: 0:12:37 lr: 0.000407 loss: 3.3609 (3.1530) grad_norm: 1.5773 (1.6837) time: 0.6331 [2021-03-27 12:57:29 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 120/1251] eta: 0:12:27 lr: 0.000407 loss: 3.2922 (3.1523) grad_norm: 1.6031 (1.6833) time: 0.6363 [2021-03-27 12:57:35 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 130/1251] eta: 0:12:18 lr: 0.000407 loss: 3.2305 (3.1464) grad_norm: 1.5704 (1.6767) time: 0.6321 [2021-03-27 12:57:41 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 140/1251] eta: 0:12:09 lr: 0.000407 loss: 3.3219 (3.1605) grad_norm: 1.5905 (1.6740) time: 0.6280 [2021-03-27 12:57:47 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 150/1251] eta: 0:12:00 lr: 0.000407 loss: 3.3219 (3.1612) grad_norm: 1.5993 (1.6686) time: 0.6263 [2021-03-27 12:57:54 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 160/1251] eta: 0:11:52 lr: 0.000407 loss: 3.1778 (3.1548) grad_norm: 1.5847 (1.6664) time: 0.6304 [2021-03-27 12:58:00 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 170/1251] eta: 0:11:45 lr: 0.000406 loss: 3.0024 (3.1503) grad_norm: 1.6224 (1.6705) time: 0.6336 [2021-03-27 12:58:07 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 180/1251] eta: 0:11:37 lr: 0.000406 loss: 3.2348 (3.1496) grad_norm: 1.6257 (1.6672) time: 0.6352 [2021-03-27 12:58:13 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 190/1251] eta: 0:11:29 lr: 0.000406 loss: 3.2661 (3.1544) grad_norm: 1.6257 (1.6775) time: 0.6308 [2021-03-27 12:58:19 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 200/1251] eta: 0:11:21 lr: 0.000406 loss: 3.2099 (3.1421) grad_norm: 1.6458 (1.6764) time: 0.6265 [2021-03-27 12:58:25 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 210/1251] eta: 0:11:14 lr: 0.000406 loss: 3.2167 (3.1511) grad_norm: 1.6264 (1.6746) time: 0.6253 [2021-03-27 12:58:32 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 220/1251] eta: 0:11:07 lr: 0.000406 loss: 3.5130 (3.1663) grad_norm: 1.6250 (1.6751) time: 0.6304 [2021-03-27 12:58:38 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 230/1251] eta: 0:11:00 lr: 0.000406 loss: 3.5053 (3.1802) grad_norm: 1.6183 (1.6726) time: 0.6376 [2021-03-27 12:58:44 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 240/1251] eta: 0:10:53 lr: 0.000406 loss: 3.4121 (3.1774) grad_norm: 1.5319 (1.6719) time: 0.6410 [2021-03-27 12:58:51 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 250/1251] eta: 0:10:46 lr: 0.000406 loss: 3.2317 (3.1842) grad_norm: 1.5319 (1.6659) time: 0.6380 [2021-03-27 12:58:57 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 260/1251] eta: 0:10:39 lr: 0.000406 loss: 3.1350 (3.1726) grad_norm: 1.5347 (1.6640) time: 0.6296 [2021-03-27 12:59:03 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 270/1251] eta: 0:10:32 lr: 0.000406 loss: 3.0270 (3.1754) grad_norm: 1.5907 (1.6622) time: 0.6281 [2021-03-27 12:59:10 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 280/1251] eta: 0:10:25 lr: 0.000406 loss: 3.2399 (3.1777) grad_norm: 1.6085 (1.6600) time: 0.6279 [2021-03-27 12:59:16 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 290/1251] eta: 0:10:18 lr: 0.000406 loss: 3.2842 (3.1770) grad_norm: 1.6022 (1.6581) time: 0.6296 [2021-03-27 12:59:22 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 300/1251] eta: 0:10:11 lr: 0.000406 loss: 3.2585 (3.1803) grad_norm: 1.5980 (1.6570) time: 0.6291 [2021-03-27 12:59:29 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 310/1251] eta: 0:10:04 lr: 0.000406 loss: 3.2480 (3.1771) grad_norm: 1.5759 (1.6567) time: 0.6267 [2021-03-27 12:59:35 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 320/1251] eta: 0:09:57 lr: 0.000406 loss: 3.1678 (3.1779) grad_norm: 1.5347 (1.6554) time: 0.6301 [2021-03-27 12:59:41 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 330/1251] eta: 0:09:51 lr: 0.000406 loss: 3.2969 (3.1808) grad_norm: 1.5347 (1.6558) time: 0.6301 [2021-03-27 12:59:47 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 340/1251] eta: 0:09:44 lr: 0.000406 loss: 3.2969 (3.1842) grad_norm: 1.6421 (1.6571) time: 0.6319 [2021-03-27 12:59:54 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 350/1251] eta: 0:09:37 lr: 0.000406 loss: 3.1624 (3.1821) grad_norm: 1.6181 (1.6559) time: 0.6348 [2021-03-27 13:00:00 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 360/1251] eta: 0:09:31 lr: 0.000406 loss: 3.2804 (3.1869) grad_norm: 1.6853 (1.6617) time: 0.6387 [2021-03-27 13:00:07 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 370/1251] eta: 0:09:25 lr: 0.000406 loss: 3.3717 (3.1914) grad_norm: 1.7025 (1.6582) time: 0.6391 [2021-03-27 13:00:13 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 380/1251] eta: 0:09:18 lr: 0.000406 loss: 3.2434 (3.1906) grad_norm: 1.5315 (1.6552) time: 0.6338 [2021-03-27 13:00:19 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 390/1251] eta: 0:09:11 lr: 0.000406 loss: 3.3947 (3.1995) grad_norm: 1.5507 (1.6531) time: 0.6302 [2021-03-27 13:00:26 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 400/1251] eta: 0:09:05 lr: 0.000406 loss: 3.2943 (3.1882) grad_norm: 1.5802 (1.6533) time: 0.6321 [2021-03-27 13:00:32 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 410/1251] eta: 0:08:58 lr: 0.000405 loss: 3.1389 (3.1913) grad_norm: 1.6873 (1.6560) time: 0.6325 [2021-03-27 13:00:38 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 420/1251] eta: 0:08:51 lr: 0.000405 loss: 3.2987 (3.1892) grad_norm: 1.6873 (1.6561) time: 0.6283 [2021-03-27 13:00:44 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 430/1251] eta: 0:08:45 lr: 0.000405 loss: 3.3072 (3.1934) grad_norm: 1.6882 (1.6589) time: 0.6258 [2021-03-27 13:00:51 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 440/1251] eta: 0:08:38 lr: 0.000405 loss: 3.4440 (3.1977) grad_norm: 1.7538 (1.6610) time: 0.6267 [2021-03-27 13:00:57 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 450/1251] eta: 0:08:31 lr: 0.000405 loss: 3.4440 (3.1975) grad_norm: 1.6854 (1.6610) time: 0.6274 [2021-03-27 13:01:03 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 460/1251] eta: 0:08:25 lr: 0.000405 loss: 3.3782 (3.1943) grad_norm: 1.5931 (1.6606) time: 0.6253 [2021-03-27 13:01:10 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 470/1251] eta: 0:08:18 lr: 0.000405 loss: 3.5143 (3.2011) grad_norm: 1.5535 (1.6590) time: 0.6292 [2021-03-27 13:01:16 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 480/1251] eta: 0:08:12 lr: 0.000405 loss: 3.5143 (3.2035) grad_norm: 1.5575 (1.6594) time: 0.6304 [2021-03-27 13:01:22 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 490/1251] eta: 0:08:05 lr: 0.000405 loss: 3.2554 (3.2011) grad_norm: 1.6619 (1.6596) time: 0.6260 [2021-03-27 13:01:28 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 500/1251] eta: 0:07:59 lr: 0.000405 loss: 3.2554 (3.2024) grad_norm: 1.7285 (1.6611) time: 0.6302 [2021-03-27 13:01:35 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 510/1251] eta: 0:07:52 lr: 0.000405 loss: 3.3293 (3.2053) grad_norm: 1.6454 (1.6609) time: 0.6336 [2021-03-27 13:01:41 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 520/1251] eta: 0:07:46 lr: 0.000405 loss: 3.1953 (3.2053) grad_norm: 1.6099 (1.6610) time: 0.6338 [2021-03-27 13:01:47 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 530/1251] eta: 0:07:39 lr: 0.000405 loss: 3.2011 (3.2061) grad_norm: 1.6270 (1.6626) time: 0.6331 [2021-03-27 13:01:54 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 540/1251] eta: 0:07:33 lr: 0.000405 loss: 3.2674 (3.2089) grad_norm: 1.6995 (1.6634) time: 0.6322 [2021-03-27 13:02:00 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 550/1251] eta: 0:07:27 lr: 0.000405 loss: 3.1937 (3.2071) grad_norm: 1.6968 (1.6631) time: 0.6409 [2021-03-27 13:02:07 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 560/1251] eta: 0:07:20 lr: 0.000405 loss: 3.0458 (3.2045) grad_norm: 1.6363 (1.6628) time: 0.6451 [2021-03-27 13:02:13 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 570/1251] eta: 0:07:14 lr: 0.000405 loss: 3.4897 (3.2121) grad_norm: 1.5752 (1.6632) time: 0.6419 [2021-03-27 13:02:19 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 580/1251] eta: 0:07:08 lr: 0.000405 loss: 3.5623 (3.2154) grad_norm: 1.6046 (1.6663) time: 0.6360 [2021-03-27 13:02:26 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 590/1251] eta: 0:07:01 lr: 0.000405 loss: 3.4037 (3.2161) grad_norm: 1.7426 (1.6690) time: 0.6320 [2021-03-27 13:02:32 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 600/1251] eta: 0:06:55 lr: 0.000405 loss: 3.2760 (3.2160) grad_norm: 1.7212 (1.6682) time: 0.6306 [2021-03-27 13:02:38 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 610/1251] eta: 0:06:48 lr: 0.000405 loss: 3.3396 (3.2201) grad_norm: 1.5591 (1.6676) time: 0.6268 [2021-03-27 13:02:45 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 620/1251] eta: 0:06:42 lr: 0.000405 loss: 3.2833 (3.2190) grad_norm: 1.5300 (1.6660) time: 0.6309 [2021-03-27 13:02:51 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 630/1251] eta: 0:06:35 lr: 0.000405 loss: 2.9294 (3.2140) grad_norm: 1.5646 (1.6643) time: 0.6323 [2021-03-27 13:02:57 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 640/1251] eta: 0:06:29 lr: 0.000405 loss: 2.9450 (3.2133) grad_norm: 1.5804 (1.6641) time: 0.6281 [2021-03-27 13:03:03 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 650/1251] eta: 0:06:22 lr: 0.000405 loss: 3.2365 (3.2145) grad_norm: 1.5804 (1.6650) time: 0.6267 [2021-03-27 13:03:10 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 660/1251] eta: 0:06:16 lr: 0.000404 loss: 3.3329 (3.2148) grad_norm: 1.5769 (1.6648) time: 0.6323 [2021-03-27 13:03:16 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 670/1251] eta: 0:06:10 lr: 0.000404 loss: 3.4215 (3.2162) grad_norm: 1.6597 (1.6668) time: 0.6350 [2021-03-27 13:03:22 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 680/1251] eta: 0:06:03 lr: 0.000404 loss: 3.3316 (3.2168) grad_norm: 1.6597 (1.6647) time: 0.6324 [2021-03-27 13:03:29 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 690/1251] eta: 0:05:57 lr: 0.000404 loss: 3.2787 (3.2186) grad_norm: 1.5176 (1.6643) time: 0.6385 [2021-03-27 13:03:35 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 700/1251] eta: 0:05:50 lr: 0.000404 loss: 3.4811 (3.2215) grad_norm: 1.6167 (1.6660) time: 0.6393 [2021-03-27 13:03:42 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 710/1251] eta: 0:05:44 lr: 0.000404 loss: 3.4778 (3.2218) grad_norm: 1.6275 (1.6657) time: 0.6372 [2021-03-27 13:03:48 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 720/1251] eta: 0:05:38 lr: 0.000404 loss: 3.1978 (3.2216) grad_norm: 1.6275 (1.6666) time: 0.6361 [2021-03-27 13:03:54 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 730/1251] eta: 0:05:31 lr: 0.000404 loss: 3.2450 (3.2221) grad_norm: 1.5877 (1.6665) time: 0.6359 [2021-03-27 13:04:01 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 740/1251] eta: 0:05:25 lr: 0.000404 loss: 3.3466 (3.2238) grad_norm: 1.6090 (1.6674) time: 0.6397 [2021-03-27 13:04:07 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 750/1251] eta: 0:05:19 lr: 0.000404 loss: 3.3466 (3.2242) grad_norm: 1.6363 (1.6664) time: 0.6404 [2021-03-27 13:04:13 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 760/1251] eta: 0:05:12 lr: 0.000404 loss: 3.2859 (3.2244) grad_norm: 1.6118 (1.6670) time: 0.6322 [2021-03-27 13:04:20 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 770/1251] eta: 0:05:06 lr: 0.000404 loss: 3.2061 (3.2243) grad_norm: 1.6118 (1.6660) time: 0.6306 [2021-03-27 13:04:26 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 780/1251] eta: 0:04:59 lr: 0.000404 loss: 3.2061 (3.2239) grad_norm: 1.5525 (1.6650) time: 0.6293 [2021-03-27 13:04:32 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 790/1251] eta: 0:04:53 lr: 0.000404 loss: 3.0954 (3.2207) grad_norm: 1.5238 (1.6634) time: 0.6281 [2021-03-27 13:04:39 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 800/1251] eta: 0:04:47 lr: 0.000404 loss: 3.1358 (3.2212) grad_norm: 1.5477 (1.6637) time: 0.6429 [2021-03-27 13:04:45 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 810/1251] eta: 0:04:40 lr: 0.000404 loss: 3.3090 (3.2197) grad_norm: 1.7050 (1.6657) time: 0.6381 [2021-03-27 13:04:51 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 820/1251] eta: 0:04:34 lr: 0.000404 loss: 3.3090 (3.2200) grad_norm: 1.6525 (1.6652) time: 0.6290 [2021-03-27 13:04:58 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 830/1251] eta: 0:04:28 lr: 0.000404 loss: 3.1618 (3.2173) grad_norm: 1.5474 (1.6643) time: 0.6348 [2021-03-27 13:05:04 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 840/1251] eta: 0:04:21 lr: 0.000404 loss: 3.1618 (3.2175) grad_norm: 1.5358 (1.6628) time: 0.6330 [2021-03-27 13:05:10 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 850/1251] eta: 0:04:15 lr: 0.000404 loss: 3.2275 (3.2174) grad_norm: 1.5358 (1.6626) time: 0.6301 [2021-03-27 13:05:17 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 860/1251] eta: 0:04:08 lr: 0.000404 loss: 3.2275 (3.2189) grad_norm: 1.5317 (1.6614) time: 0.6357 [2021-03-27 13:05:23 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 870/1251] eta: 0:04:02 lr: 0.000404 loss: 3.3002 (3.2178) grad_norm: 1.5277 (1.6605) time: 0.6378 [2021-03-27 13:05:29 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 880/1251] eta: 0:03:56 lr: 0.000404 loss: 3.0896 (3.2158) grad_norm: 1.5799 (1.6635) time: 0.6273 [2021-03-27 13:05:36 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 890/1251] eta: 0:03:49 lr: 0.000404 loss: 3.0935 (3.2157) grad_norm: 1.5154 (1.6624) time: 0.6240 [2021-03-27 13:05:42 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 900/1251] eta: 0:03:43 lr: 0.000404 loss: 3.2426 (3.2145) grad_norm: 1.5454 (1.6632) time: 0.6274 [2021-03-27 13:05:48 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 910/1251] eta: 0:03:36 lr: 0.000403 loss: 3.2499 (3.2141) grad_norm: 1.6653 (1.6624) time: 0.6309 [2021-03-27 13:05:55 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 920/1251] eta: 0:03:30 lr: 0.000403 loss: 3.3498 (3.2161) grad_norm: 1.6397 (1.6618) time: 0.6357 [2021-03-27 13:06:01 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 930/1251] eta: 0:03:24 lr: 0.000403 loss: 3.4181 (3.2173) grad_norm: 1.6385 (1.6623) time: 0.6359 [2021-03-27 13:06:07 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 940/1251] eta: 0:03:17 lr: 0.000403 loss: 3.1674 (3.2156) grad_norm: 1.6938 (1.6635) time: 0.6328 [2021-03-27 13:06:14 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 950/1251] eta: 0:03:11 lr: 0.000403 loss: 3.1674 (3.2162) grad_norm: 1.6938 (1.6635) time: 0.6404 [2021-03-27 13:06:20 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 960/1251] eta: 0:03:05 lr: 0.000403 loss: 3.4153 (3.2172) grad_norm: 1.6268 (1.6640) time: 0.6419 [2021-03-27 13:06:27 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 970/1251] eta: 0:02:58 lr: 0.000403 loss: 3.4588 (3.2177) grad_norm: 1.7043 (1.6651) time: 0.6420 [2021-03-27 13:06:33 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 980/1251] eta: 0:02:52 lr: 0.000403 loss: 3.4142 (3.2196) grad_norm: 1.7221 (1.6652) time: 0.6396 [2021-03-27 13:06:39 swin_base_patch4_window7_224] INFO: Epoch: [169] [ 990/1251] eta: 0:02:46 lr: 0.000403 loss: 3.3915 (3.2214) grad_norm: 1.5989 (1.6652) time: 0.6269 [2021-03-27 13:06:46 swin_base_patch4_window7_224] INFO: Epoch: [169] [1000/1251] eta: 0:02:39 lr: 0.000403 loss: 3.3915 (3.2223) grad_norm: 1.5989 (1.6643) time: 0.6275 [2021-03-27 13:06:52 swin_base_patch4_window7_224] INFO: Epoch: [169] [1010/1251] eta: 0:02:33 lr: 0.000403 loss: 3.2783 (3.2207) grad_norm: 1.5710 (1.6640) time: 0.6377 [2021-03-27 13:06:58 swin_base_patch4_window7_224] INFO: Epoch: [169] [1020/1251] eta: 0:02:26 lr: 0.000403 loss: 3.3580 (3.2227) grad_norm: 1.5749 (1.6637) time: 0.6433 [2021-03-27 13:07:05 swin_base_patch4_window7_224] INFO: Epoch: [169] [1030/1251] eta: 0:02:20 lr: 0.000403 loss: 3.3500 (3.2224) grad_norm: 1.5686 (1.6630) time: 0.6358 [2021-03-27 13:07:11 swin_base_patch4_window7_224] INFO: Epoch: [169] [1040/1251] eta: 0:02:14 lr: 0.000403 loss: 3.3500 (3.2235) grad_norm: 1.5145 (1.6616) time: 0.6276 [2021-03-27 13:07:17 swin_base_patch4_window7_224] INFO: Epoch: [169] [1050/1251] eta: 0:02:07 lr: 0.000403 loss: 3.3530 (3.2243) grad_norm: 1.5721 (1.6619) time: 0.6264 [2021-03-27 13:07:23 swin_base_patch4_window7_224] INFO: Epoch: [169] [1060/1251] eta: 0:02:01 lr: 0.000403 loss: 3.2822 (3.2210) grad_norm: 1.6114 (1.6622) time: 0.6266 [2021-03-27 13:07:30 swin_base_patch4_window7_224] INFO: Epoch: [169] [1070/1251] eta: 0:01:55 lr: 0.000403 loss: 3.3316 (3.2233) grad_norm: 1.6578 (1.6624) time: 0.6287 [2021-03-27 13:07:36 swin_base_patch4_window7_224] INFO: Epoch: [169] [1080/1251] eta: 0:01:48 lr: 0.000403 loss: 3.4010 (3.2236) grad_norm: 1.5274 (1.6614) time: 0.6334 [2021-03-27 13:07:42 swin_base_patch4_window7_224] INFO: Epoch: [169] [1090/1251] eta: 0:01:42 lr: 0.000403 loss: 3.3793 (3.2240) grad_norm: 1.5707 (1.6614) time: 0.6323 [2021-03-27 13:07:49 swin_base_patch4_window7_224] INFO: Epoch: [169] [1100/1251] eta: 0:01:35 lr: 0.000403 loss: 3.3187 (3.2227) grad_norm: 1.6374 (1.6613) time: 0.6264 [2021-03-27 13:07:55 swin_base_patch4_window7_224] INFO: Epoch: [169] [1110/1251] eta: 0:01:29 lr: 0.000403 loss: 3.2778 (3.2212) grad_norm: 1.7323 (1.6625) time: 0.6272 [2021-03-27 13:08:01 swin_base_patch4_window7_224] INFO: Epoch: [169] [1120/1251] eta: 0:01:23 lr: 0.000403 loss: 3.2076 (3.2214) grad_norm: 1.7323 (1.6619) time: 0.6307 [2021-03-27 13:08:08 swin_base_patch4_window7_224] INFO: Epoch: [169] [1130/1251] eta: 0:01:16 lr: 0.000403 loss: 3.2198 (3.2208) grad_norm: 1.5639 (1.6615) time: 0.6346 [2021-03-27 13:08:14 swin_base_patch4_window7_224] INFO: Epoch: [169] [1140/1251] eta: 0:01:10 lr: 0.000403 loss: 3.3776 (3.2230) grad_norm: 1.5920 (1.6612) time: 0.6316 [2021-03-27 13:08:20 swin_base_patch4_window7_224] INFO: Epoch: [169] [1150/1251] eta: 0:01:04 lr: 0.000402 loss: 3.4165 (3.2238) grad_norm: 1.6763 (1.6631) time: 0.6284 [2021-03-27 13:08:27 swin_base_patch4_window7_224] INFO: Epoch: [169] [1160/1251] eta: 0:00:57 lr: 0.000402 loss: 3.3898 (3.2254) grad_norm: 1.6479 (1.6631) time: 0.6290 [2021-03-27 13:08:33 swin_base_patch4_window7_224] INFO: Epoch: [169] [1170/1251] eta: 0:00:51 lr: 0.000402 loss: 3.1238 (3.2232) grad_norm: 1.5273 (1.6626) time: 0.6291 [2021-03-27 13:08:39 swin_base_patch4_window7_224] INFO: Epoch: [169] [1180/1251] eta: 0:00:45 lr: 0.000402 loss: 3.1238 (3.2238) grad_norm: 1.5566 (1.6621) time: 0.6294 [2021-03-27 13:08:45 swin_base_patch4_window7_224] INFO: Epoch: [169] [1190/1251] eta: 0:00:38 lr: 0.000402 loss: 3.2458 (3.2245) grad_norm: 1.5868 (1.6618) time: 0.6295 [2021-03-27 13:08:52 swin_base_patch4_window7_224] INFO: Epoch: [169] [1200/1251] eta: 0:00:32 lr: 0.000402 loss: 3.2234 (3.2228) grad_norm: 1.6453 (1.6618) time: 0.6311 [2021-03-27 13:08:58 swin_base_patch4_window7_224] INFO: Epoch: [169] [1210/1251] eta: 0:00:26 lr: 0.000402 loss: 2.8775 (3.2192) grad_norm: 1.6702 (1.6620) time: 0.6320 [2021-03-27 13:09:04 swin_base_patch4_window7_224] INFO: Epoch: [169] [1220/1251] eta: 0:00:19 lr: 0.000402 loss: 3.2369 (3.2195) grad_norm: 1.6456 (1.6619) time: 0.6343 [2021-03-27 13:09:11 swin_base_patch4_window7_224] INFO: Epoch: [169] [1230/1251] eta: 0:00:13 lr: 0.000402 loss: 3.4621 (3.2221) grad_norm: 1.6107 (1.6630) time: 0.6434 [2021-03-27 13:09:17 swin_base_patch4_window7_224] INFO: Epoch: [169] [1240/1251] eta: 0:00:06 lr: 0.000402 loss: 3.3312 (3.2211) grad_norm: 1.6666 (1.6636) time: 0.6424 [2021-03-27 13:09:24 swin_base_patch4_window7_224] INFO: Epoch: [169] [1250/1251] eta: 0:00:00 lr: 0.000402 loss: 3.3549 (3.2226) grad_norm: 1.7289 (1.6639) time: 0.6376 [2021-03-27 13:09:33 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:08 loss: 0.8484 (0.8484) acc1: 78.1250 (78.1250) acc5: 96.8750 (96.8750) [2021-03-27 13:09:36 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8484 (0.8577) acc1: 78.1250 (79.5455) acc5: 95.3125 (95.4545) [2021-03-27 13:09:38 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8589 (0.8819) acc1: 78.1250 (78.1250) acc5: 95.3125 (95.2381) [2021-03-27 13:09:41 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8366 (0.8861) acc1: 76.5625 (77.8226) acc5: 93.7500 (94.8085) [2021-03-27 13:09:43 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8080 (0.8776) acc1: 78.1250 (78.2774) acc5: 93.7500 (94.8933) [2021-03-27 13:09:44 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7994 (0.8797) acc1: 79.6875 (78.3680) acc5: 95.3125 (95.0080) [2021-03-27 13:09:54 swin_base_patch4_window7_224] INFO: * Acc@1 79.640 Acc@5 95.258 loss 0.863 [2021-03-27 13:09:54 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.6% [2021-03-27 13:09:54 swin_base_patch4_window7_224] INFO: Max accuracy: 79.92% [2021-03-27 13:09:58 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 0/1251] eta: 1:22:57 lr: 0.000402 loss: 2.5266 (2.5266) grad_norm: 1.4612 (1.4612) time: 3.9791 [2021-03-27 13:10:04 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 10/1251] eta: 0:19:52 lr: 0.000402 loss: 2.8409 (2.9161) grad_norm: 1.4951 (1.5668) time: 0.9607 [2021-03-27 13:10:10 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 20/1251] eta: 0:16:27 lr: 0.000402 loss: 3.0552 (2.9983) grad_norm: 1.5309 (1.6109) time: 0.6434 [2021-03-27 13:10:17 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 30/1251] eta: 0:15:11 lr: 0.000402 loss: 3.1196 (3.0491) grad_norm: 1.6012 (1.6478) time: 0.6285 [2021-03-27 13:10:23 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 40/1251] eta: 0:14:28 lr: 0.000402 loss: 3.3927 (3.1432) grad_norm: 1.6167 (1.7064) time: 0.6283 [2021-03-27 13:10:29 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 50/1251] eta: 0:13:59 lr: 0.000402 loss: 3.3607 (3.1442) grad_norm: 1.5995 (1.6874) time: 0.6252 [2021-03-27 13:10:35 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 60/1251] eta: 0:13:38 lr: 0.000402 loss: 3.2423 (3.1392) grad_norm: 1.5770 (1.6758) time: 0.6257 [2021-03-27 13:10:42 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 70/1251] eta: 0:13:22 lr: 0.000402 loss: 3.3304 (3.1764) grad_norm: 1.6574 (1.6892) time: 0.6312 [2021-03-27 13:10:48 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 80/1251] eta: 0:13:08 lr: 0.000402 loss: 3.4634 (3.1941) grad_norm: 1.6779 (1.6893) time: 0.6299 [2021-03-27 13:10:54 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 90/1251] eta: 0:12:56 lr: 0.000402 loss: 3.2270 (3.1888) grad_norm: 1.5916 (1.6947) time: 0.6291 [2021-03-27 13:11:01 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 100/1251] eta: 0:12:45 lr: 0.000402 loss: 3.1719 (3.1958) grad_norm: 1.6916 (1.6901) time: 0.6306 [2021-03-27 13:11:07 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 110/1251] eta: 0:12:35 lr: 0.000402 loss: 3.3062 (3.2115) grad_norm: 1.7213 (1.7031) time: 0.6302 [2021-03-27 13:11:13 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 120/1251] eta: 0:12:25 lr: 0.000402 loss: 3.4001 (3.2187) grad_norm: 1.6908 (1.7010) time: 0.6328 [2021-03-27 13:11:20 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 130/1251] eta: 0:12:16 lr: 0.000402 loss: 3.3956 (3.2155) grad_norm: 1.6752 (1.6957) time: 0.6307 [2021-03-27 13:11:26 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 140/1251] eta: 0:12:08 lr: 0.000402 loss: 3.0886 (3.2125) grad_norm: 1.5987 (1.6903) time: 0.6304 [2021-03-27 13:11:32 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 150/1251] eta: 0:11:58 lr: 0.000401 loss: 3.2591 (3.2213) grad_norm: 1.5842 (1.6827) time: 0.6268 [2021-03-27 13:11:38 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 160/1251] eta: 0:11:50 lr: 0.000401 loss: 3.2591 (3.2221) grad_norm: 1.6316 (1.6878) time: 0.6251 [2021-03-27 13:11:45 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 170/1251] eta: 0:11:42 lr: 0.000401 loss: 3.2346 (3.2173) grad_norm: 1.6373 (1.6857) time: 0.6299 [2021-03-27 13:11:51 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 180/1251] eta: 0:11:35 lr: 0.000401 loss: 3.2977 (3.2259) grad_norm: 1.6868 (1.6864) time: 0.6323 [2021-03-27 13:11:57 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 190/1251] eta: 0:11:28 lr: 0.000401 loss: 3.3220 (3.2307) grad_norm: 1.6668 (1.6908) time: 0.6345 [2021-03-27 13:12:04 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 200/1251] eta: 0:11:20 lr: 0.000401 loss: 3.2728 (3.2114) grad_norm: 1.6636 (1.6925) time: 0.6339 [2021-03-27 13:12:10 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 210/1251] eta: 0:11:13 lr: 0.000401 loss: 2.8276 (3.2088) grad_norm: 1.6580 (1.6952) time: 0.6320 [2021-03-27 13:12:16 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 220/1251] eta: 0:11:05 lr: 0.000401 loss: 3.0964 (3.2064) grad_norm: 1.6545 (1.6940) time: 0.6258 [2021-03-27 13:12:23 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 230/1251] eta: 0:10:58 lr: 0.000401 loss: 3.2910 (3.2096) grad_norm: 1.6694 (1.6984) time: 0.6249 [2021-03-27 13:12:29 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 240/1251] eta: 0:10:51 lr: 0.000401 loss: 3.2613 (3.1991) grad_norm: 1.6694 (1.6957) time: 0.6274 [2021-03-27 13:12:35 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 250/1251] eta: 0:10:44 lr: 0.000401 loss: 3.0528 (3.1978) grad_norm: 1.7031 (1.6984) time: 0.6265 [2021-03-27 13:12:42 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 260/1251] eta: 0:10:37 lr: 0.000401 loss: 3.3613 (3.2016) grad_norm: 1.7780 (1.7044) time: 0.6318 [2021-03-27 13:12:48 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 270/1251] eta: 0:10:30 lr: 0.000401 loss: 3.3613 (3.1964) grad_norm: 1.7099 (1.7027) time: 0.6346 [2021-03-27 13:12:54 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 280/1251] eta: 0:10:23 lr: 0.000401 loss: 3.2457 (3.1980) grad_norm: 1.6557 (1.7050) time: 0.6319 [2021-03-27 13:13:00 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 290/1251] eta: 0:10:17 lr: 0.000401 loss: 3.2798 (3.1968) grad_norm: 1.6004 (1.6995) time: 0.6306 [2021-03-27 13:13:07 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 300/1251] eta: 0:10:10 lr: 0.000401 loss: 3.2647 (3.2011) grad_norm: 1.5862 (1.6971) time: 0.6305 [2021-03-27 13:13:13 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 310/1251] eta: 0:10:03 lr: 0.000401 loss: 3.2639 (3.1944) grad_norm: 1.6074 (1.6961) time: 0.6356 [2021-03-27 13:13:19 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 320/1251] eta: 0:09:57 lr: 0.000401 loss: 3.3318 (3.1970) grad_norm: 1.6242 (1.6935) time: 0.6352 [2021-03-27 13:13:26 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 330/1251] eta: 0:09:50 lr: 0.000401 loss: 3.4361 (3.1961) grad_norm: 1.6396 (1.6935) time: 0.6302 [2021-03-27 13:13:32 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 340/1251] eta: 0:09:43 lr: 0.000401 loss: 3.2729 (3.1935) grad_norm: 1.6526 (1.6939) time: 0.6272 [2021-03-27 13:13:38 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 350/1251] eta: 0:09:37 lr: 0.000401 loss: 3.3300 (3.1985) grad_norm: 1.7114 (1.6935) time: 0.6321 [2021-03-27 13:13:45 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 360/1251] eta: 0:09:30 lr: 0.000401 loss: 3.4939 (3.1995) grad_norm: 1.5211 (1.6908) time: 0.6371 [2021-03-27 13:13:51 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 370/1251] eta: 0:09:23 lr: 0.000401 loss: 3.3466 (3.1961) grad_norm: 1.6939 (1.6989) time: 0.6322 [2021-03-27 13:13:57 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 380/1251] eta: 0:09:17 lr: 0.000401 loss: 3.3529 (3.1967) grad_norm: 1.6403 (1.6964) time: 0.6263 [2021-03-27 13:14:04 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 390/1251] eta: 0:09:10 lr: 0.000401 loss: 3.2371 (3.1962) grad_norm: 1.6403 (1.6969) time: 0.6273 [2021-03-27 13:14:10 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 400/1251] eta: 0:09:03 lr: 0.000400 loss: 3.1489 (3.1965) grad_norm: 1.6624 (1.6960) time: 0.6298 [2021-03-27 13:14:16 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 410/1251] eta: 0:08:57 lr: 0.000400 loss: 3.2687 (3.2001) grad_norm: 1.6622 (1.6961) time: 0.6302 [2021-03-27 13:14:23 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 420/1251] eta: 0:08:50 lr: 0.000400 loss: 3.2687 (3.1994) grad_norm: 1.5993 (1.6939) time: 0.6326 [2021-03-27 13:14:29 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 430/1251] eta: 0:08:44 lr: 0.000400 loss: 3.2761 (3.1987) grad_norm: 1.5896 (1.6910) time: 0.6318 [2021-03-27 13:14:35 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 440/1251] eta: 0:08:37 lr: 0.000400 loss: 3.2761 (3.1973) grad_norm: 1.5896 (1.6893) time: 0.6309 [2021-03-27 13:14:42 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 450/1251] eta: 0:08:31 lr: 0.000400 loss: 2.9748 (3.1892) grad_norm: 1.5527 (1.6851) time: 0.6323 [2021-03-27 13:14:48 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 460/1251] eta: 0:08:24 lr: 0.000400 loss: 3.0185 (3.1906) grad_norm: 1.5215 (1.6829) time: 0.6371 [2021-03-27 13:14:54 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 470/1251] eta: 0:08:18 lr: 0.000400 loss: 3.4234 (3.1932) grad_norm: 1.5869 (1.6806) time: 0.6329 [2021-03-27 13:15:00 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 480/1251] eta: 0:08:11 lr: 0.000400 loss: 3.4969 (3.1930) grad_norm: 1.6888 (1.6941) time: 0.6252 [2021-03-27 13:15:07 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 490/1251] eta: 0:08:05 lr: 0.000400 loss: 3.1332 (3.1879) grad_norm: 1.6888 (1.6930) time: 0.6275 [2021-03-27 13:15:13 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 500/1251] eta: 0:07:58 lr: 0.000400 loss: 3.1779 (3.1930) grad_norm: 1.5856 (1.6923) time: 0.6366 [2021-03-27 13:15:20 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 510/1251] eta: 0:07:52 lr: 0.000400 loss: 3.2086 (3.1898) grad_norm: 1.6419 (1.6929) time: 0.6390 [2021-03-27 13:15:26 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 520/1251] eta: 0:07:46 lr: 0.000400 loss: 3.0886 (3.1902) grad_norm: 1.6956 (1.6942) time: 0.6371 [2021-03-27 13:15:32 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 530/1251] eta: 0:07:39 lr: 0.000400 loss: 3.2019 (3.1912) grad_norm: 1.6542 (1.6932) time: 0.6330 [2021-03-27 13:15:38 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 540/1251] eta: 0:07:33 lr: 0.000400 loss: 3.0770 (3.1890) grad_norm: 1.5884 (1.6918) time: 0.6252 [2021-03-27 13:15:45 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 550/1251] eta: 0:07:26 lr: 0.000400 loss: 3.1139 (3.1932) grad_norm: 1.6157 (1.6935) time: 0.6369 [2021-03-27 13:15:51 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 560/1251] eta: 0:07:20 lr: 0.000400 loss: 3.4369 (3.1938) grad_norm: 1.6092 (1.6926) time: 0.6403 [2021-03-27 13:15:58 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 570/1251] eta: 0:07:13 lr: 0.000400 loss: 3.3399 (3.1935) grad_norm: 1.6895 (1.6932) time: 0.6301 [2021-03-27 13:16:04 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 580/1251] eta: 0:07:07 lr: 0.000400 loss: 3.4591 (3.1970) grad_norm: 1.7184 (1.6924) time: 0.6319 [2021-03-27 13:16:10 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 590/1251] eta: 0:07:01 lr: 0.000400 loss: 3.3987 (3.1954) grad_norm: 1.6913 (1.6945) time: 0.6327 [2021-03-27 13:16:16 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 600/1251] eta: 0:06:54 lr: 0.000400 loss: 3.1443 (3.1940) grad_norm: 1.6658 (1.6941) time: 0.6279 [2021-03-27 13:16:23 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 610/1251] eta: 0:06:48 lr: 0.000400 loss: 3.1644 (3.1928) grad_norm: 1.6553 (1.6948) time: 0.6263 [2021-03-27 13:16:29 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 620/1251] eta: 0:06:41 lr: 0.000400 loss: 3.1823 (3.1936) grad_norm: 1.6376 (1.6936) time: 0.6269 [2021-03-27 13:16:35 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 630/1251] eta: 0:06:35 lr: 0.000400 loss: 3.1955 (3.1914) grad_norm: 1.5750 (1.6930) time: 0.6289 [2021-03-27 13:16:42 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 640/1251] eta: 0:06:28 lr: 0.000399 loss: 3.2804 (3.1916) grad_norm: 1.6938 (1.6948) time: 0.6351 [2021-03-27 13:16:48 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 650/1251] eta: 0:06:22 lr: 0.000399 loss: 3.2394 (3.1904) grad_norm: 1.7873 (1.6990) time: 0.6383 [2021-03-27 13:16:54 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 660/1251] eta: 0:06:16 lr: 0.000399 loss: 3.2394 (3.1932) grad_norm: 1.8982 (1.7021) time: 0.6322 [2021-03-27 13:17:01 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 670/1251] eta: 0:06:09 lr: 0.000399 loss: 3.2231 (3.1914) grad_norm: 1.8171 (1.7045) time: 0.6287 [2021-03-27 13:17:07 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 680/1251] eta: 0:06:03 lr: 0.000399 loss: 3.2555 (3.1940) grad_norm: 1.7309 (1.7052) time: 0.6305 [2021-03-27 13:17:13 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 690/1251] eta: 0:05:56 lr: 0.000399 loss: 3.3212 (3.1959) grad_norm: 1.6246 (1.7042) time: 0.6329 [2021-03-27 13:17:20 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 700/1251] eta: 0:05:50 lr: 0.000399 loss: 3.4070 (3.1973) grad_norm: 1.6228 (1.7041) time: 0.6315 [2021-03-27 13:17:26 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 710/1251] eta: 0:05:44 lr: 0.000399 loss: 3.2418 (3.1960) grad_norm: 1.6794 (1.7057) time: 0.6250 [2021-03-27 13:17:32 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 720/1251] eta: 0:05:37 lr: 0.000399 loss: 3.2190 (3.1949) grad_norm: 1.7606 (1.7064) time: 0.6290 [2021-03-27 13:17:39 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 730/1251] eta: 0:05:31 lr: 0.000399 loss: 3.2941 (3.1968) grad_norm: 1.6770 (1.7057) time: 0.6394 [2021-03-27 13:17:45 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 740/1251] eta: 0:05:25 lr: 0.000399 loss: 3.4804 (3.1995) grad_norm: 1.6742 (1.7055) time: 0.6406 [2021-03-27 13:17:51 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 750/1251] eta: 0:05:18 lr: 0.000399 loss: 3.3838 (3.2000) grad_norm: 1.6556 (1.7049) time: 0.6390 [2021-03-27 13:17:58 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 760/1251] eta: 0:05:12 lr: 0.000399 loss: 3.3576 (3.2035) grad_norm: 1.5937 (1.7039) time: 0.6356 [2021-03-27 13:18:04 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 770/1251] eta: 0:05:05 lr: 0.000399 loss: 3.3433 (3.2006) grad_norm: 1.5814 (1.7035) time: 0.6268 [2021-03-27 13:18:10 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 780/1251] eta: 0:04:59 lr: 0.000399 loss: 3.2389 (3.2015) grad_norm: 1.5972 (1.7024) time: 0.6281 [2021-03-27 13:18:17 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 790/1251] eta: 0:04:53 lr: 0.000399 loss: 3.2445 (3.1983) grad_norm: 1.5883 (1.7010) time: 0.6333 [2021-03-27 13:18:23 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 800/1251] eta: 0:04:46 lr: 0.000399 loss: 3.3282 (3.2008) grad_norm: 1.5700 (inf) time: 0.6267 [2021-03-27 13:18:29 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 810/1251] eta: 0:04:40 lr: 0.000399 loss: 3.3668 (3.2032) grad_norm: 1.6238 (inf) time: 0.6222 [2021-03-27 13:18:35 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 820/1251] eta: 0:04:33 lr: 0.000399 loss: 3.4456 (3.2063) grad_norm: 1.6544 (inf) time: 0.6288 [2021-03-27 13:18:42 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 830/1251] eta: 0:04:27 lr: 0.000399 loss: 3.4739 (3.2070) grad_norm: 1.6753 (inf) time: 0.6308 [2021-03-27 13:18:48 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 840/1251] eta: 0:04:21 lr: 0.000399 loss: 3.4739 (3.2093) grad_norm: 1.6500 (inf) time: 0.6279 [2021-03-27 13:18:54 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 850/1251] eta: 0:04:14 lr: 0.000399 loss: 3.3222 (3.2098) grad_norm: 1.5668 (inf) time: 0.6337 [2021-03-27 13:19:01 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 860/1251] eta: 0:04:08 lr: 0.000399 loss: 3.2514 (3.2103) grad_norm: 1.5833 (inf) time: 0.6396 [2021-03-27 13:19:07 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 870/1251] eta: 0:04:02 lr: 0.000399 loss: 3.3431 (3.2115) grad_norm: 1.6720 (inf) time: 0.6387 [2021-03-27 13:19:13 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 880/1251] eta: 0:03:55 lr: 0.000399 loss: 3.2359 (3.2088) grad_norm: 1.6725 (inf) time: 0.6342 [2021-03-27 13:19:20 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 890/1251] eta: 0:03:49 lr: 0.000398 loss: 3.0902 (3.2084) grad_norm: 1.6950 (inf) time: 0.6325 [2021-03-27 13:19:26 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 900/1251] eta: 0:03:42 lr: 0.000398 loss: 3.3703 (3.2090) grad_norm: 1.6215 (inf) time: 0.6333 [2021-03-27 13:19:32 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 910/1251] eta: 0:03:36 lr: 0.000398 loss: 3.3703 (3.2098) grad_norm: 1.5714 (inf) time: 0.6279 [2021-03-27 13:19:39 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 920/1251] eta: 0:03:30 lr: 0.000398 loss: 3.2150 (3.2101) grad_norm: 1.6614 (inf) time: 0.6266 [2021-03-27 13:19:45 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 930/1251] eta: 0:03:23 lr: 0.000398 loss: 3.2150 (3.2097) grad_norm: 1.5750 (inf) time: 0.6296 [2021-03-27 13:19:51 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 940/1251] eta: 0:03:17 lr: 0.000398 loss: 3.4102 (3.2103) grad_norm: 1.5474 (inf) time: 0.6329 [2021-03-27 13:19:58 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 950/1251] eta: 0:03:11 lr: 0.000398 loss: 3.4102 (3.2118) grad_norm: 1.6100 (inf) time: 0.6358 [2021-03-27 13:20:04 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 960/1251] eta: 0:03:04 lr: 0.000398 loss: 3.4344 (3.2126) grad_norm: 1.6854 (inf) time: 0.6296 [2021-03-27 13:20:10 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 970/1251] eta: 0:02:58 lr: 0.000398 loss: 3.5003 (3.2121) grad_norm: 1.6467 (inf) time: 0.6253 [2021-03-27 13:20:16 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 980/1251] eta: 0:02:52 lr: 0.000398 loss: 3.2898 (3.2120) grad_norm: 1.5818 (inf) time: 0.6303 [2021-03-27 13:20:23 swin_base_patch4_window7_224] INFO: Epoch: [170] [ 990/1251] eta: 0:02:45 lr: 0.000398 loss: 3.0899 (3.2079) grad_norm: 1.6282 (inf) time: 0.6339 [2021-03-27 13:20:29 swin_base_patch4_window7_224] INFO: Epoch: [170] [1000/1251] eta: 0:02:39 lr: 0.000398 loss: 2.9373 (3.2057) grad_norm: 1.6440 (inf) time: 0.6343 [2021-03-27 13:20:36 swin_base_patch4_window7_224] INFO: Epoch: [170] [1010/1251] eta: 0:02:32 lr: 0.000398 loss: 3.2669 (3.2061) grad_norm: 1.6113 (inf) time: 0.6338 [2021-03-27 13:20:42 swin_base_patch4_window7_224] INFO: Epoch: [170] [1020/1251] eta: 0:02:26 lr: 0.000398 loss: 3.2948 (3.2058) grad_norm: 1.5333 (inf) time: 0.6313 [2021-03-27 13:20:48 swin_base_patch4_window7_224] INFO: Epoch: [170] [1030/1251] eta: 0:02:20 lr: 0.000398 loss: 3.2075 (3.2029) grad_norm: 1.6194 (inf) time: 0.6290 [2021-03-27 13:20:54 swin_base_patch4_window7_224] INFO: Epoch: [170] [1040/1251] eta: 0:02:13 lr: 0.000398 loss: 3.2075 (3.2026) grad_norm: 1.6064 (inf) time: 0.6292 [2021-03-27 13:21:01 swin_base_patch4_window7_224] INFO: Epoch: [170] [1050/1251] eta: 0:02:07 lr: 0.000398 loss: 3.2322 (3.2022) grad_norm: 1.6064 (inf) time: 0.6338 [2021-03-27 13:21:07 swin_base_patch4_window7_224] INFO: Epoch: [170] [1060/1251] eta: 0:02:01 lr: 0.000398 loss: 3.0049 (3.2010) grad_norm: 1.6698 (inf) time: 0.6411 [2021-03-27 13:21:14 swin_base_patch4_window7_224] INFO: Epoch: [170] [1070/1251] eta: 0:01:54 lr: 0.000398 loss: 3.0049 (3.1988) grad_norm: 1.6881 (inf) time: 0.6402 [2021-03-27 13:21:20 swin_base_patch4_window7_224] INFO: Epoch: [170] [1080/1251] eta: 0:01:48 lr: 0.000398 loss: 3.1130 (3.1974) grad_norm: 1.7274 (inf) time: 0.6390 [2021-03-27 13:21:26 swin_base_patch4_window7_224] INFO: Epoch: [170] [1090/1251] eta: 0:01:42 lr: 0.000398 loss: 3.2254 (3.1976) grad_norm: 1.6253 (inf) time: 0.6318 [2021-03-27 13:21:33 swin_base_patch4_window7_224] INFO: Epoch: [170] [1100/1251] eta: 0:01:35 lr: 0.000398 loss: 3.3940 (3.1984) grad_norm: 1.5743 (inf) time: 0.6293 [2021-03-27 13:21:39 swin_base_patch4_window7_224] INFO: Epoch: [170] [1110/1251] eta: 0:01:29 lr: 0.000398 loss: 3.2309 (3.1980) grad_norm: 1.6183 (inf) time: 0.6317 [2021-03-27 13:21:45 swin_base_patch4_window7_224] INFO: Epoch: [170] [1120/1251] eta: 0:01:23 lr: 0.000398 loss: 3.2105 (3.1994) grad_norm: 1.6030 (inf) time: 0.6307 [2021-03-27 13:21:51 swin_base_patch4_window7_224] INFO: Epoch: [170] [1130/1251] eta: 0:01:16 lr: 0.000398 loss: 3.2143 (3.1986) grad_norm: 1.5743 (inf) time: 0.6315 [2021-03-27 13:21:58 swin_base_patch4_window7_224] INFO: Epoch: [170] [1140/1251] eta: 0:01:10 lr: 0.000397 loss: 3.0877 (3.1966) grad_norm: 1.6801 (inf) time: 0.6308 [2021-03-27 13:22:04 swin_base_patch4_window7_224] INFO: Epoch: [170] [1150/1251] eta: 0:01:04 lr: 0.000397 loss: 3.0326 (3.1963) grad_norm: 1.6558 (inf) time: 0.6292 [2021-03-27 13:22:10 swin_base_patch4_window7_224] INFO: Epoch: [170] [1160/1251] eta: 0:00:57 lr: 0.000397 loss: 3.4716 (3.1991) grad_norm: 1.6558 (inf) time: 0.6260 [2021-03-27 13:22:17 swin_base_patch4_window7_224] INFO: Epoch: [170] [1170/1251] eta: 0:00:51 lr: 0.000397 loss: 3.4282 (3.1992) grad_norm: 1.6408 (inf) time: 0.6257 [2021-03-27 13:22:23 swin_base_patch4_window7_224] INFO: Epoch: [170] [1180/1251] eta: 0:00:45 lr: 0.000397 loss: 3.2370 (3.2004) grad_norm: 1.5432 (inf) time: 0.6251 [2021-03-27 13:22:29 swin_base_patch4_window7_224] INFO: Epoch: [170] [1190/1251] eta: 0:00:38 lr: 0.000397 loss: 3.4856 (3.2014) grad_norm: 1.5357 (inf) time: 0.6262 [2021-03-27 13:22:35 swin_base_patch4_window7_224] INFO: Epoch: [170] [1200/1251] eta: 0:00:32 lr: 0.000397 loss: 3.5027 (3.2033) grad_norm: 1.5759 (inf) time: 0.6286 [2021-03-27 13:22:42 swin_base_patch4_window7_224] INFO: Epoch: [170] [1210/1251] eta: 0:00:26 lr: 0.000397 loss: 3.3798 (3.2023) grad_norm: 1.6358 (inf) time: 0.6320 [2021-03-27 13:22:48 swin_base_patch4_window7_224] INFO: Epoch: [170] [1220/1251] eta: 0:00:19 lr: 0.000397 loss: 2.9464 (3.2010) grad_norm: 1.5419 (inf) time: 0.6291 [2021-03-27 13:22:54 swin_base_patch4_window7_224] INFO: Epoch: [170] [1230/1251] eta: 0:00:13 lr: 0.000397 loss: 3.0782 (3.1993) grad_norm: 1.5419 (inf) time: 0.6281 [2021-03-27 13:23:00 swin_base_patch4_window7_224] INFO: Epoch: [170] [1240/1251] eta: 0:00:06 lr: 0.000397 loss: 3.1737 (3.1994) grad_norm: 1.6200 (inf) time: 0.6247 [2021-03-27 13:23:07 swin_base_patch4_window7_224] INFO: Epoch: [170] [1250/1251] eta: 0:00:00 lr: 0.000397 loss: 3.2633 (3.2001) grad_norm: 1.6174 (inf) time: 0.6231 [2021-03-27 13:24:31 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 0.6610 (0.6610) acc1: 82.8125 (82.8125) acc5: 98.4375 (98.4375) [2021-03-27 13:24:32 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.9299 (0.9082) acc1: 79.6875 (79.4034) acc5: 95.3125 (95.5966) [2021-03-27 13:24:34 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9071 (0.8936) acc1: 79.6875 (79.2411) acc5: 95.3125 (95.8333) [2021-03-27 13:24:35 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8087 (0.8767) acc1: 79.6875 (79.6875) acc5: 96.8750 (95.8669) [2021-03-27 13:24:37 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7926 (0.8762) acc1: 78.1250 (79.3064) acc5: 95.3125 (95.6936) [2021-03-27 13:24:38 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9010 (0.8805) acc1: 78.1250 (79.2000) acc5: 93.7500 (95.5520) [2021-03-27 13:24:47 swin_base_patch4_window7_224] INFO: * Acc@1 79.968 Acc@5 95.222 loss 0.874 [2021-03-27 13:24:47 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.0% [2021-03-27 13:24:47 swin_base_patch4_window7_224] INFO: Max accuracy: 79.97% [2021-03-27 13:24:51 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 0/1251] eta: 1:30:22 lr: 0.000397 loss: 3.9916 (3.9916) grad_norm: 1.6604 (1.6604) time: 4.3345 [2021-03-27 13:24:58 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 10/1251] eta: 0:19:53 lr: 0.000397 loss: 2.7128 (2.9245) grad_norm: 1.7401 (1.7877) time: 0.9621 [2021-03-27 13:25:04 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 20/1251] eta: 0:16:32 lr: 0.000397 loss: 3.0663 (3.0799) grad_norm: 1.6706 (1.7850) time: 0.6295 [2021-03-27 13:25:10 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 30/1251] eta: 0:15:12 lr: 0.000397 loss: 3.2121 (3.1644) grad_norm: 1.6706 (1.8066) time: 0.6297 [2021-03-27 13:25:16 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 40/1251] eta: 0:14:30 lr: 0.000397 loss: 3.2121 (3.0984) grad_norm: 1.7291 (1.8087) time: 0.6280 [2021-03-27 13:25:23 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 50/1251] eta: 0:14:06 lr: 0.000397 loss: 3.3467 (3.1437) grad_norm: 1.8176 (1.8185) time: 0.6381 [2021-03-27 13:25:29 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 60/1251] eta: 0:13:43 lr: 0.000397 loss: 3.1064 (3.1082) grad_norm: 1.6410 (1.7888) time: 0.6340 [2021-03-27 13:25:35 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 70/1251] eta: 0:13:26 lr: 0.000397 loss: 3.0109 (3.0925) grad_norm: 1.6410 (1.7833) time: 0.6261 [2021-03-27 13:25:42 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 80/1251] eta: 0:13:12 lr: 0.000397 loss: 3.1077 (3.0936) grad_norm: 1.7116 (1.7689) time: 0.6339 [2021-03-27 13:25:48 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 90/1251] eta: 0:13:00 lr: 0.000397 loss: 3.2213 (3.1094) grad_norm: 1.6167 (1.7544) time: 0.6367 [2021-03-27 13:25:55 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 100/1251] eta: 0:12:49 lr: 0.000397 loss: 3.4151 (3.1219) grad_norm: 1.6099 (1.7479) time: 0.6350 [2021-03-27 13:26:01 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 110/1251] eta: 0:12:38 lr: 0.000397 loss: 3.3530 (3.1180) grad_norm: 1.7014 (1.7550) time: 0.6320 [2021-03-27 13:26:07 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 120/1251] eta: 0:12:29 lr: 0.000397 loss: 3.4111 (3.1336) grad_norm: 1.6703 (1.7521) time: 0.6320 [2021-03-27 13:26:13 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 130/1251] eta: 0:12:19 lr: 0.000396 loss: 3.2795 (3.1156) grad_norm: 1.6561 (1.7505) time: 0.6316 [2021-03-27 13:26:20 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 140/1251] eta: 0:12:11 lr: 0.000396 loss: 3.3203 (3.1474) grad_norm: 1.5796 (1.7435) time: 0.6308 [2021-03-27 13:26:26 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 150/1251] eta: 0:12:03 lr: 0.000396 loss: 3.4282 (3.1719) grad_norm: 1.5796 (1.7384) time: 0.6409 [2021-03-27 13:26:33 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 160/1251] eta: 0:11:55 lr: 0.000396 loss: 3.2685 (3.1699) grad_norm: 1.6009 (1.7325) time: 0.6427 [2021-03-27 13:26:39 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 170/1251] eta: 0:11:47 lr: 0.000396 loss: 3.0532 (3.1524) grad_norm: 1.6818 (1.7382) time: 0.6321 [2021-03-27 13:26:45 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 180/1251] eta: 0:11:39 lr: 0.000396 loss: 3.1367 (3.1495) grad_norm: 1.7325 (1.7450) time: 0.6250 [2021-03-27 13:26:52 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 190/1251] eta: 0:11:31 lr: 0.000396 loss: 3.1912 (3.1580) grad_norm: 1.6530 (1.7434) time: 0.6299 [2021-03-27 13:26:58 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 200/1251] eta: 0:11:24 lr: 0.000396 loss: 3.1912 (3.1564) grad_norm: 1.6164 (1.7397) time: 0.6368 [2021-03-27 13:27:04 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 210/1251] eta: 0:11:16 lr: 0.000396 loss: 3.1866 (3.1550) grad_norm: 1.5963 (1.7380) time: 0.6335 [2021-03-27 13:27:10 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 220/1251] eta: 0:11:09 lr: 0.000396 loss: 3.1714 (3.1627) grad_norm: 1.5963 (1.7380) time: 0.6285 [2021-03-27 13:27:17 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 230/1251] eta: 0:11:01 lr: 0.000396 loss: 3.0869 (3.1573) grad_norm: 1.5158 (1.7263) time: 0.6248 [2021-03-27 13:27:23 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 240/1251] eta: 0:10:54 lr: 0.000396 loss: 3.1105 (3.1631) grad_norm: 1.4739 (1.7209) time: 0.6264 [2021-03-27 13:27:29 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 250/1251] eta: 0:10:47 lr: 0.000396 loss: 3.5047 (3.1699) grad_norm: 1.6798 (1.7224) time: 0.6351 [2021-03-27 13:27:36 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 260/1251] eta: 0:10:40 lr: 0.000396 loss: 3.4708 (3.1743) grad_norm: 1.6798 (1.7195) time: 0.6313 [2021-03-27 13:27:42 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 270/1251] eta: 0:10:33 lr: 0.000396 loss: 3.3724 (3.1747) grad_norm: 1.5383 (1.7148) time: 0.6281 [2021-03-27 13:27:48 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 280/1251] eta: 0:10:26 lr: 0.000396 loss: 3.1973 (3.1690) grad_norm: 1.6172 (1.7185) time: 0.6316 [2021-03-27 13:27:55 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 290/1251] eta: 0:10:19 lr: 0.000396 loss: 3.0956 (3.1623) grad_norm: 1.6308 (1.7135) time: 0.6274 [2021-03-27 13:28:01 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 300/1251] eta: 0:10:12 lr: 0.000396 loss: 2.9693 (3.1552) grad_norm: 1.5555 (1.7115) time: 0.6278 [2021-03-27 13:28:07 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 310/1251] eta: 0:10:05 lr: 0.000396 loss: 3.1240 (3.1573) grad_norm: 1.5920 (1.7120) time: 0.6328 [2021-03-27 13:28:13 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 320/1251] eta: 0:09:58 lr: 0.000396 loss: 3.3571 (3.1587) grad_norm: 1.6258 (1.7088) time: 0.6339 [2021-03-27 13:28:20 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 330/1251] eta: 0:09:51 lr: 0.000396 loss: 3.4636 (3.1674) grad_norm: 1.6988 (1.7123) time: 0.6261 [2021-03-27 13:28:26 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 340/1251] eta: 0:09:45 lr: 0.000396 loss: 3.4572 (3.1623) grad_norm: 1.7696 (1.7139) time: 0.6262 [2021-03-27 13:28:32 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 350/1251] eta: 0:09:38 lr: 0.000396 loss: 3.3691 (3.1643) grad_norm: 1.7035 (1.7118) time: 0.6358 [2021-03-27 13:28:39 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 360/1251] eta: 0:09:31 lr: 0.000396 loss: 3.3896 (3.1659) grad_norm: 1.6629 (1.7121) time: 0.6339 [2021-03-27 13:28:45 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 370/1251] eta: 0:09:25 lr: 0.000396 loss: 3.2276 (3.1617) grad_norm: 1.6980 (1.7163) time: 0.6269 [2021-03-27 13:28:51 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 380/1251] eta: 0:09:18 lr: 0.000395 loss: 3.1847 (3.1682) grad_norm: 1.7150 (1.7189) time: 0.6305 [2021-03-27 13:28:58 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 390/1251] eta: 0:09:11 lr: 0.000395 loss: 3.3764 (3.1728) grad_norm: 1.7302 (1.7208) time: 0.6322 [2021-03-27 13:29:04 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 400/1251] eta: 0:09:05 lr: 0.000395 loss: 3.3764 (3.1764) grad_norm: 1.7162 (1.7213) time: 0.6311 [2021-03-27 13:29:10 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 410/1251] eta: 0:08:58 lr: 0.000395 loss: 3.2167 (3.1749) grad_norm: 1.6988 (1.7222) time: 0.6343 [2021-03-27 13:29:17 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 420/1251] eta: 0:08:52 lr: 0.000395 loss: 3.2372 (3.1795) grad_norm: 1.6891 (1.7207) time: 0.6306 [2021-03-27 13:29:23 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 430/1251] eta: 0:08:45 lr: 0.000395 loss: 3.3059 (3.1781) grad_norm: 1.5759 (1.7197) time: 0.6296 [2021-03-27 13:29:29 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 440/1251] eta: 0:08:39 lr: 0.000395 loss: 3.2676 (3.1747) grad_norm: 1.6078 (1.7218) time: 0.6350 [2021-03-27 13:29:36 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 450/1251] eta: 0:08:32 lr: 0.000395 loss: 3.2676 (3.1747) grad_norm: 1.6768 (1.7277) time: 0.6350 [2021-03-27 13:29:42 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 460/1251] eta: 0:08:25 lr: 0.000395 loss: 3.2434 (3.1753) grad_norm: 1.7336 (1.7305) time: 0.6291 [2021-03-27 13:29:48 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 470/1251] eta: 0:08:19 lr: 0.000395 loss: 3.2095 (3.1731) grad_norm: 1.7345 (1.7307) time: 0.6294 [2021-03-27 13:29:54 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 480/1251] eta: 0:08:12 lr: 0.000395 loss: 3.3567 (3.1787) grad_norm: 1.7286 (1.7315) time: 0.6286 [2021-03-27 13:30:01 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 490/1251] eta: 0:08:06 lr: 0.000395 loss: 3.3986 (3.1819) grad_norm: 1.7832 (1.7387) time: 0.6286 [2021-03-27 13:30:07 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 500/1251] eta: 0:07:59 lr: 0.000395 loss: 3.2830 (3.1786) grad_norm: 1.8336 (1.7400) time: 0.6292 [2021-03-27 13:30:13 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 510/1251] eta: 0:07:53 lr: 0.000395 loss: 3.1693 (3.1786) grad_norm: 1.6593 (1.7432) time: 0.6268 [2021-03-27 13:30:20 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 520/1251] eta: 0:07:46 lr: 0.000395 loss: 3.3548 (3.1853) grad_norm: 1.7484 (1.7435) time: 0.6301 [2021-03-27 13:30:26 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 530/1251] eta: 0:07:40 lr: 0.000395 loss: 3.4923 (3.1878) grad_norm: 1.7571 (1.7442) time: 0.6313 [2021-03-27 13:30:32 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 540/1251] eta: 0:07:33 lr: 0.000395 loss: 3.2807 (3.1832) grad_norm: 1.6645 (1.7416) time: 0.6317 [2021-03-27 13:30:39 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 550/1251] eta: 0:07:27 lr: 0.000395 loss: 3.2807 (3.1879) grad_norm: 1.6452 (1.7416) time: 0.6379 [2021-03-27 13:30:45 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 560/1251] eta: 0:07:20 lr: 0.000395 loss: 3.4252 (3.1872) grad_norm: 1.7374 (1.7409) time: 0.6408 [2021-03-27 13:30:51 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 570/1251] eta: 0:07:14 lr: 0.000395 loss: 3.1305 (3.1848) grad_norm: 1.7198 (1.7425) time: 0.6359 [2021-03-27 13:30:58 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 580/1251] eta: 0:07:08 lr: 0.000395 loss: 3.3149 (3.1862) grad_norm: 1.7963 (1.7449) time: 0.6334 [2021-03-27 13:31:04 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 590/1251] eta: 0:07:01 lr: 0.000395 loss: 3.3149 (3.1891) grad_norm: 1.8253 (1.7457) time: 0.6352 [2021-03-27 13:31:11 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 600/1251] eta: 0:06:55 lr: 0.000395 loss: 3.4440 (3.1907) grad_norm: 1.7491 (1.7464) time: 0.6390 [2021-03-27 13:31:17 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 610/1251] eta: 0:06:48 lr: 0.000395 loss: 3.2127 (3.1867) grad_norm: 1.6046 (1.7447) time: 0.6309 [2021-03-27 13:31:23 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 620/1251] eta: 0:06:42 lr: 0.000395 loss: 3.0997 (3.1869) grad_norm: 1.6046 (1.7434) time: 0.6240 [2021-03-27 13:31:29 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 630/1251] eta: 0:06:35 lr: 0.000394 loss: 3.3858 (3.1886) grad_norm: 1.6721 (1.7433) time: 0.6247 [2021-03-27 13:31:36 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 640/1251] eta: 0:06:29 lr: 0.000394 loss: 3.3121 (3.1854) grad_norm: 1.6721 (1.7422) time: 0.6268 [2021-03-27 13:31:42 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 650/1251] eta: 0:06:22 lr: 0.000394 loss: 3.2964 (3.1876) grad_norm: 1.5728 (1.7402) time: 0.6338 [2021-03-27 13:31:48 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 660/1251] eta: 0:06:16 lr: 0.000394 loss: 3.2964 (3.1889) grad_norm: 1.6649 (1.7413) time: 0.6324 [2021-03-27 13:31:54 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 670/1251] eta: 0:06:10 lr: 0.000394 loss: 3.3506 (3.1921) grad_norm: 1.7361 (1.7411) time: 0.6244 [2021-03-27 13:32:01 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 680/1251] eta: 0:06:03 lr: 0.000394 loss: 3.5405 (3.1965) grad_norm: 1.6507 (1.7410) time: 0.6222 [2021-03-27 13:32:07 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 690/1251] eta: 0:05:57 lr: 0.000394 loss: 3.3982 (3.1980) grad_norm: 1.6732 (1.7417) time: 0.6252 [2021-03-27 13:32:13 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 700/1251] eta: 0:05:50 lr: 0.000394 loss: 3.3095 (3.1973) grad_norm: 1.7150 (1.7404) time: 0.6257 [2021-03-27 13:32:20 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 710/1251] eta: 0:05:44 lr: 0.000394 loss: 3.3127 (3.1974) grad_norm: 1.6395 (1.7397) time: 0.6306 [2021-03-27 13:32:26 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 720/1251] eta: 0:05:37 lr: 0.000394 loss: 3.2533 (3.1988) grad_norm: 1.6395 (1.7384) time: 0.6329 [2021-03-27 13:32:32 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 730/1251] eta: 0:05:31 lr: 0.000394 loss: 3.0813 (3.1978) grad_norm: 1.6729 (1.7389) time: 0.6285 [2021-03-27 13:32:38 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 740/1251] eta: 0:05:25 lr: 0.000394 loss: 3.1458 (3.1990) grad_norm: 1.6747 (1.7378) time: 0.6317 [2021-03-27 13:32:45 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 750/1251] eta: 0:05:18 lr: 0.000394 loss: 3.2498 (3.1998) grad_norm: 1.6187 (1.7365) time: 0.6375 [2021-03-27 13:32:51 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 760/1251] eta: 0:05:12 lr: 0.000394 loss: 3.2541 (3.1974) grad_norm: 1.6062 (1.7353) time: 0.6373 [2021-03-27 13:32:58 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 770/1251] eta: 0:05:05 lr: 0.000394 loss: 3.2727 (3.1969) grad_norm: 1.6478 (1.7375) time: 0.6338 [2021-03-27 13:33:04 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 780/1251] eta: 0:04:59 lr: 0.000394 loss: 3.2452 (3.1954) grad_norm: 1.8193 (1.7400) time: 0.6276 [2021-03-27 13:33:10 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 790/1251] eta: 0:04:53 lr: 0.000394 loss: 3.2282 (3.1933) grad_norm: 1.7206 (1.7399) time: 0.6305 [2021-03-27 13:33:16 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 800/1251] eta: 0:04:46 lr: 0.000394 loss: 3.2712 (3.1953) grad_norm: 1.7164 (1.7397) time: 0.6303 [2021-03-27 13:33:23 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 810/1251] eta: 0:04:40 lr: 0.000394 loss: 3.2086 (3.1935) grad_norm: 1.6826 (1.7385) time: 0.6276 [2021-03-27 13:33:29 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 820/1251] eta: 0:04:33 lr: 0.000394 loss: 3.2203 (3.1958) grad_norm: 1.6169 (1.7377) time: 0.6315 [2021-03-27 13:33:35 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 830/1251] eta: 0:04:27 lr: 0.000394 loss: 3.3046 (3.1969) grad_norm: 1.6034 (1.7371) time: 0.6350 [2021-03-27 13:33:42 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 840/1251] eta: 0:04:21 lr: 0.000394 loss: 3.3985 (3.1986) grad_norm: 1.5825 (1.7352) time: 0.6345 [2021-03-27 13:33:48 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 850/1251] eta: 0:04:14 lr: 0.000394 loss: 3.3532 (3.1981) grad_norm: 1.5491 (1.7335) time: 0.6267 [2021-03-27 13:33:54 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 860/1251] eta: 0:04:08 lr: 0.000394 loss: 3.2448 (3.1951) grad_norm: 1.6090 (1.7333) time: 0.6282 [2021-03-27 13:34:00 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 870/1251] eta: 0:04:02 lr: 0.000394 loss: 2.8448 (3.1912) grad_norm: 1.7216 (1.7337) time: 0.6269 [2021-03-27 13:34:07 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 880/1251] eta: 0:03:55 lr: 0.000393 loss: 3.0910 (3.1933) grad_norm: 1.7250 (1.7336) time: 0.6248 [2021-03-27 13:34:13 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 890/1251] eta: 0:03:49 lr: 0.000393 loss: 3.5725 (3.1969) grad_norm: 1.6725 (1.7331) time: 0.6313 [2021-03-27 13:34:19 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 900/1251] eta: 0:03:42 lr: 0.000393 loss: 3.4561 (3.1981) grad_norm: 1.6613 (1.7322) time: 0.6325 [2021-03-27 13:34:26 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 910/1251] eta: 0:03:36 lr: 0.000393 loss: 3.2678 (3.1952) grad_norm: 1.6259 (1.7332) time: 0.6286 [2021-03-27 13:34:32 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 920/1251] eta: 0:03:30 lr: 0.000393 loss: 3.4140 (3.1966) grad_norm: 1.7260 (1.7334) time: 0.6300 [2021-03-27 13:34:38 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 930/1251] eta: 0:03:23 lr: 0.000393 loss: 3.2330 (3.1932) grad_norm: 1.6768 (1.7321) time: 0.6279 [2021-03-27 13:34:45 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 940/1251] eta: 0:03:17 lr: 0.000393 loss: 3.2802 (3.1962) grad_norm: 1.5841 (1.7329) time: 0.6280 [2021-03-27 13:34:51 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 950/1251] eta: 0:03:11 lr: 0.000393 loss: 3.3715 (3.1980) grad_norm: 1.6542 (1.7328) time: 0.6315 [2021-03-27 13:34:57 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 960/1251] eta: 0:03:04 lr: 0.000393 loss: 3.3884 (3.1990) grad_norm: 1.6448 (1.7320) time: 0.6260 [2021-03-27 13:35:04 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 970/1251] eta: 0:02:58 lr: 0.000393 loss: 3.3884 (3.1977) grad_norm: 1.5696 (1.7309) time: 0.6303 [2021-03-27 13:35:10 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 980/1251] eta: 0:02:52 lr: 0.000393 loss: 3.0626 (3.1974) grad_norm: 1.5798 (1.7300) time: 0.6349 [2021-03-27 13:35:16 swin_base_patch4_window7_224] INFO: Epoch: [171] [ 990/1251] eta: 0:02:45 lr: 0.000393 loss: 3.0626 (3.1976) grad_norm: 1.6823 (1.7299) time: 0.6328 [2021-03-27 13:35:22 swin_base_patch4_window7_224] INFO: Epoch: [171] [1000/1251] eta: 0:02:39 lr: 0.000393 loss: 2.9562 (3.1955) grad_norm: 1.7550 (1.7315) time: 0.6325 [2021-03-27 13:35:29 swin_base_patch4_window7_224] INFO: Epoch: [171] [1010/1251] eta: 0:02:32 lr: 0.000393 loss: 3.1682 (3.1967) grad_norm: 1.8130 (1.7328) time: 0.6313 [2021-03-27 13:35:35 swin_base_patch4_window7_224] INFO: Epoch: [171] [1020/1251] eta: 0:02:26 lr: 0.000393 loss: 3.2298 (3.1975) grad_norm: 1.8311 (1.7343) time: 0.6307 [2021-03-27 13:35:41 swin_base_patch4_window7_224] INFO: Epoch: [171] [1030/1251] eta: 0:02:20 lr: 0.000393 loss: 3.2244 (3.1954) grad_norm: 1.7169 (1.7324) time: 0.6293 [2021-03-27 13:35:48 swin_base_patch4_window7_224] INFO: Epoch: [171] [1040/1251] eta: 0:02:13 lr: 0.000393 loss: 3.3079 (3.1974) grad_norm: 1.5997 (1.7337) time: 0.6273 [2021-03-27 13:35:54 swin_base_patch4_window7_224] INFO: Epoch: [171] [1050/1251] eta: 0:02:07 lr: 0.000393 loss: 3.3790 (3.1979) grad_norm: 1.7477 (1.7348) time: 0.6279 [2021-03-27 13:36:00 swin_base_patch4_window7_224] INFO: Epoch: [171] [1060/1251] eta: 0:02:01 lr: 0.000393 loss: 3.4135 (3.1990) grad_norm: 1.6037 (1.7337) time: 0.6282 [2021-03-27 13:36:06 swin_base_patch4_window7_224] INFO: Epoch: [171] [1070/1251] eta: 0:01:54 lr: 0.000393 loss: 3.4060 (3.1966) grad_norm: 1.5974 (1.7337) time: 0.6267 [2021-03-27 13:36:13 swin_base_patch4_window7_224] INFO: Epoch: [171] [1080/1251] eta: 0:01:48 lr: 0.000393 loss: 3.1939 (3.1958) grad_norm: 1.5958 (1.7320) time: 0.6257 [2021-03-27 13:36:19 swin_base_patch4_window7_224] INFO: Epoch: [171] [1090/1251] eta: 0:01:42 lr: 0.000393 loss: 3.2891 (3.1986) grad_norm: 1.6205 (1.7320) time: 0.6297 [2021-03-27 13:36:25 swin_base_patch4_window7_224] INFO: Epoch: [171] [1100/1251] eta: 0:01:35 lr: 0.000393 loss: 3.2891 (3.1981) grad_norm: 1.7346 (1.7322) time: 0.6368 [2021-03-27 13:36:32 swin_base_patch4_window7_224] INFO: Epoch: [171] [1110/1251] eta: 0:01:29 lr: 0.000393 loss: 3.3049 (3.1999) grad_norm: 1.6893 (1.7347) time: 0.6321 [2021-03-27 13:36:38 swin_base_patch4_window7_224] INFO: Epoch: [171] [1120/1251] eta: 0:01:23 lr: 0.000392 loss: 3.3617 (3.2000) grad_norm: 1.6791 (1.7344) time: 0.6275 [2021-03-27 13:36:44 swin_base_patch4_window7_224] INFO: Epoch: [171] [1130/1251] eta: 0:01:16 lr: 0.000392 loss: 3.2090 (3.1981) grad_norm: 1.6038 (1.7335) time: 0.6278 [2021-03-27 13:36:51 swin_base_patch4_window7_224] INFO: Epoch: [171] [1140/1251] eta: 0:01:10 lr: 0.000392 loss: 3.3167 (3.1993) grad_norm: 1.5636 (1.7327) time: 0.6259 [2021-03-27 13:36:57 swin_base_patch4_window7_224] INFO: Epoch: [171] [1150/1251] eta: 0:01:04 lr: 0.000392 loss: 3.4678 (3.2027) grad_norm: 1.6150 (1.7323) time: 0.6251 [2021-03-27 13:37:03 swin_base_patch4_window7_224] INFO: Epoch: [171] [1160/1251] eta: 0:00:57 lr: 0.000392 loss: 3.4521 (3.2037) grad_norm: 1.6204 (1.7323) time: 0.6307 [2021-03-27 13:37:10 swin_base_patch4_window7_224] INFO: Epoch: [171] [1170/1251] eta: 0:00:51 lr: 0.000392 loss: 3.2076 (3.2011) grad_norm: 1.5990 (1.7316) time: 0.6362 [2021-03-27 13:37:16 swin_base_patch4_window7_224] INFO: Epoch: [171] [1180/1251] eta: 0:00:45 lr: 0.000392 loss: 3.0197 (3.2001) grad_norm: 1.5997 (1.7306) time: 0.6354 [2021-03-27 13:37:22 swin_base_patch4_window7_224] INFO: Epoch: [171] [1190/1251] eta: 0:00:38 lr: 0.000392 loss: 3.3048 (3.2006) grad_norm: 1.6041 (1.7296) time: 0.6340 [2021-03-27 13:37:29 swin_base_patch4_window7_224] INFO: Epoch: [171] [1200/1251] eta: 0:00:32 lr: 0.000392 loss: 3.4333 (3.2017) grad_norm: 1.5838 (1.7284) time: 0.6332 [2021-03-27 13:37:35 swin_base_patch4_window7_224] INFO: Epoch: [171] [1210/1251] eta: 0:00:25 lr: 0.000392 loss: 3.3949 (3.2036) grad_norm: 1.5448 (1.7284) time: 0.6325 [2021-03-27 13:37:41 swin_base_patch4_window7_224] INFO: Epoch: [171] [1220/1251] eta: 0:00:19 lr: 0.000392 loss: 3.4242 (3.2046) grad_norm: 1.6029 (1.7275) time: 0.6283 [2021-03-27 13:37:47 swin_base_patch4_window7_224] INFO: Epoch: [171] [1230/1251] eta: 0:00:13 lr: 0.000392 loss: 3.1786 (3.2041) grad_norm: 1.6961 (1.7279) time: 0.6323 [2021-03-27 13:37:54 swin_base_patch4_window7_224] INFO: Epoch: [171] [1240/1251] eta: 0:00:06 lr: 0.000392 loss: 3.1786 (3.2042) grad_norm: 1.6961 (1.7269) time: 0.6372 [2021-03-27 13:38:00 swin_base_patch4_window7_224] INFO: Epoch: [171] [1250/1251] eta: 0:00:00 lr: 0.000392 loss: 3.3650 (3.2037) grad_norm: 1.5698 (1.7255) time: 0.6204 [2021-03-27 13:38:10 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:24 loss: 0.8752 (0.8752) acc1: 78.1250 (78.1250) acc5: 90.6250 (90.6250) [2021-03-27 13:38:12 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8718 (0.8749) acc1: 79.6875 (78.4091) acc5: 95.3125 (95.3125) [2021-03-27 13:38:14 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.8718 (0.9295) acc1: 78.1250 (78.1994) acc5: 95.3125 (94.7173) [2021-03-27 13:38:16 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0238 (0.9235) acc1: 78.1250 (78.4274) acc5: 95.3125 (94.6573) [2021-03-27 13:38:18 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7953 (0.8879) acc1: 81.2500 (79.3826) acc5: 96.8750 (95.1220) [2021-03-27 13:38:19 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8087 (0.8709) acc1: 82.8125 (79.6480) acc5: 96.8750 (95.4560) [2021-03-27 13:38:30 swin_base_patch4_window7_224] INFO: * Acc@1 79.970 Acc@5 95.322 loss 0.871 [2021-03-27 13:38:30 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.0% [2021-03-27 13:38:30 swin_base_patch4_window7_224] INFO: Max accuracy: 79.97% [2021-03-27 13:38:34 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 0/1251] eta: 1:29:44 lr: 0.000392 loss: 2.5044 (2.5044) grad_norm: 2.0747 (2.0747) time: 4.3045 [2021-03-27 13:38:41 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 10/1251] eta: 0:19:56 lr: 0.000392 loss: 3.3920 (3.2898) grad_norm: 1.6605 (1.7000) time: 0.9638 [2021-03-27 13:38:47 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 20/1251] eta: 0:16:35 lr: 0.000392 loss: 3.3062 (3.2488) grad_norm: 1.5994 (1.6520) time: 0.6342 [2021-03-27 13:38:53 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 30/1251] eta: 0:15:15 lr: 0.000392 loss: 3.0845 (3.1380) grad_norm: 1.5992 (1.6598) time: 0.6322 [2021-03-27 13:39:00 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 40/1251] eta: 0:14:32 lr: 0.000392 loss: 3.0441 (3.1162) grad_norm: 1.6008 (1.6492) time: 0.6277 [2021-03-27 13:39:06 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 50/1251] eta: 0:14:03 lr: 0.000392 loss: 3.1657 (3.1333) grad_norm: 1.6008 (1.6495) time: 0.6289 [2021-03-27 13:39:12 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 60/1251] eta: 0:13:41 lr: 0.000392 loss: 3.2881 (3.1369) grad_norm: 1.6175 (1.6598) time: 0.6271 [2021-03-27 13:39:18 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 70/1251] eta: 0:13:24 lr: 0.000392 loss: 3.2404 (3.1386) grad_norm: 1.6969 (1.6684) time: 0.6278 [2021-03-27 13:39:25 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 80/1251] eta: 0:13:09 lr: 0.000392 loss: 3.0565 (3.1215) grad_norm: 1.6974 (1.6704) time: 0.6278 [2021-03-27 13:39:31 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 90/1251] eta: 0:12:56 lr: 0.000392 loss: 2.9935 (3.1091) grad_norm: 1.6956 (1.6839) time: 0.6248 [2021-03-27 13:39:37 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 100/1251] eta: 0:12:45 lr: 0.000392 loss: 2.9935 (3.0942) grad_norm: 1.7400 (1.6935) time: 0.6270 [2021-03-27 13:39:44 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 110/1251] eta: 0:12:35 lr: 0.000392 loss: 3.1082 (3.0971) grad_norm: 1.7400 (1.7017) time: 0.6319 [2021-03-27 13:39:50 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 120/1251] eta: 0:12:25 lr: 0.000391 loss: 3.2526 (3.1101) grad_norm: 1.7563 (1.7036) time: 0.6266 [2021-03-27 13:39:56 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 130/1251] eta: 0:12:15 lr: 0.000391 loss: 3.3369 (3.1173) grad_norm: 1.6570 (1.7126) time: 0.6242 [2021-03-27 13:40:02 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 140/1251] eta: 0:12:07 lr: 0.000391 loss: 3.2611 (3.1186) grad_norm: 1.6652 (1.7149) time: 0.6298 [2021-03-27 13:40:09 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 150/1251] eta: 0:11:58 lr: 0.000391 loss: 3.0950 (3.1102) grad_norm: 1.6494 (1.7111) time: 0.6303 [2021-03-27 13:40:15 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 160/1251] eta: 0:11:50 lr: 0.000391 loss: 3.0544 (3.1108) grad_norm: 1.5173 (1.7004) time: 0.6291 [2021-03-27 13:40:21 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 170/1251] eta: 0:11:42 lr: 0.000391 loss: 3.0161 (3.1117) grad_norm: 1.5394 (1.6968) time: 0.6257 [2021-03-27 13:40:27 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 180/1251] eta: 0:11:34 lr: 0.000391 loss: 3.0161 (3.1036) grad_norm: 1.5897 (1.6920) time: 0.6240 [2021-03-27 13:40:34 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 190/1251] eta: 0:11:27 lr: 0.000391 loss: 3.0341 (3.1043) grad_norm: 1.6321 (1.6916) time: 0.6309 [2021-03-27 13:40:40 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 200/1251] eta: 0:11:19 lr: 0.000391 loss: 3.0472 (3.1038) grad_norm: 1.7046 (1.6921) time: 0.6311 [2021-03-27 13:40:46 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 210/1251] eta: 0:11:11 lr: 0.000391 loss: 3.0472 (3.1098) grad_norm: 1.7046 (1.6937) time: 0.6227 [2021-03-27 13:40:53 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 220/1251] eta: 0:11:04 lr: 0.000391 loss: 3.1412 (3.1063) grad_norm: 1.5842 (1.6872) time: 0.6246 [2021-03-27 13:40:59 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 230/1251] eta: 0:10:57 lr: 0.000391 loss: 3.1922 (3.1111) grad_norm: 1.5627 (1.6868) time: 0.6277 [2021-03-27 13:41:05 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 240/1251] eta: 0:10:50 lr: 0.000391 loss: 3.2682 (3.1175) grad_norm: 1.6684 (1.6907) time: 0.6260 [2021-03-27 13:41:11 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 250/1251] eta: 0:10:42 lr: 0.000391 loss: 3.2682 (3.1132) grad_norm: 1.6664 (1.6896) time: 0.6238 [2021-03-27 13:41:17 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 260/1251] eta: 0:10:35 lr: 0.000391 loss: 3.3087 (3.1193) grad_norm: 1.6266 (1.6935) time: 0.6230 [2021-03-27 13:41:24 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 270/1251] eta: 0:10:28 lr: 0.000391 loss: 3.3087 (3.1275) grad_norm: 1.5913 (1.6907) time: 0.6219 [2021-03-27 13:41:30 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 280/1251] eta: 0:10:21 lr: 0.000391 loss: 3.1723 (3.1182) grad_norm: 1.5796 (1.6869) time: 0.6213 [2021-03-27 13:41:36 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 290/1251] eta: 0:10:14 lr: 0.000391 loss: 3.1968 (3.1279) grad_norm: 1.5310 (1.6802) time: 0.6236 [2021-03-27 13:41:42 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 300/1251] eta: 0:10:07 lr: 0.000391 loss: 3.5211 (3.1372) grad_norm: 1.5554 (1.6836) time: 0.6241 [2021-03-27 13:41:49 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 310/1251] eta: 0:10:01 lr: 0.000391 loss: 3.4798 (3.1433) grad_norm: 1.6447 (1.6849) time: 0.6266 [2021-03-27 13:41:55 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 320/1251] eta: 0:09:54 lr: 0.000391 loss: 3.3431 (3.1471) grad_norm: 1.6447 (1.6883) time: 0.6269 [2021-03-27 13:42:01 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 330/1251] eta: 0:09:47 lr: 0.000391 loss: 3.1831 (3.1438) grad_norm: 1.6444 (1.6888) time: 0.6253 [2021-03-27 13:42:07 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 340/1251] eta: 0:09:40 lr: 0.000391 loss: 3.1736 (3.1414) grad_norm: 1.6882 (1.6939) time: 0.6271 [2021-03-27 13:42:14 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 350/1251] eta: 0:09:34 lr: 0.000391 loss: 3.1736 (3.1398) grad_norm: 1.7084 (1.6918) time: 0.6237 [2021-03-27 13:42:20 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 360/1251] eta: 0:09:27 lr: 0.000391 loss: 3.3513 (3.1432) grad_norm: 1.6743 (1.6935) time: 0.6217 [2021-03-27 13:42:26 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 370/1251] eta: 0:09:20 lr: 0.000390 loss: 3.3940 (3.1439) grad_norm: 1.6117 (1.6927) time: 0.6295 [2021-03-27 13:42:33 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 380/1251] eta: 0:09:14 lr: 0.000390 loss: 3.0878 (3.1368) grad_norm: 1.6038 (1.6920) time: 0.6307 [2021-03-27 13:42:39 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 390/1251] eta: 0:09:07 lr: 0.000390 loss: 3.0785 (3.1359) grad_norm: 1.6855 (1.6939) time: 0.6272 [2021-03-27 13:42:45 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 400/1251] eta: 0:09:01 lr: 0.000390 loss: 3.1960 (3.1428) grad_norm: 1.7167 (1.6920) time: 0.6251 [2021-03-27 13:42:51 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 410/1251] eta: 0:08:54 lr: 0.000390 loss: 3.4242 (3.1498) grad_norm: 1.6567 (1.6962) time: 0.6249 [2021-03-27 13:42:58 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 420/1251] eta: 0:08:48 lr: 0.000390 loss: 3.2677 (3.1511) grad_norm: 1.6140 (1.6944) time: 0.6301 [2021-03-27 13:43:04 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 430/1251] eta: 0:08:41 lr: 0.000390 loss: 3.1546 (3.1507) grad_norm: 1.5991 (1.6935) time: 0.6318 [2021-03-27 13:43:10 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 440/1251] eta: 0:08:35 lr: 0.000390 loss: 3.2535 (3.1492) grad_norm: 1.6173 (1.6939) time: 0.6286 [2021-03-27 13:43:16 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 450/1251] eta: 0:08:28 lr: 0.000390 loss: 3.2656 (3.1506) grad_norm: 1.6355 (1.6936) time: 0.6232 [2021-03-27 13:43:23 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 460/1251] eta: 0:08:22 lr: 0.000390 loss: 2.9326 (3.1466) grad_norm: 1.6564 (1.6954) time: 0.6227 [2021-03-27 13:43:29 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 470/1251] eta: 0:08:15 lr: 0.000390 loss: 2.9326 (3.1456) grad_norm: 1.7311 (1.6965) time: 0.6230 [2021-03-27 13:43:35 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 480/1251] eta: 0:08:09 lr: 0.000390 loss: 3.2390 (3.1489) grad_norm: 1.7579 (1.6994) time: 0.6250 [2021-03-27 13:43:41 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 490/1251] eta: 0:08:02 lr: 0.000390 loss: 3.3082 (3.1497) grad_norm: 1.7515 (1.6993) time: 0.6282 [2021-03-27 13:43:48 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 500/1251] eta: 0:07:56 lr: 0.000390 loss: 3.3650 (3.1540) grad_norm: 1.7086 (1.7004) time: 0.6239 [2021-03-27 13:43:54 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 510/1251] eta: 0:07:49 lr: 0.000390 loss: 3.3884 (3.1575) grad_norm: 1.7186 (1.7005) time: 0.6234 [2021-03-27 13:44:00 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 520/1251] eta: 0:07:43 lr: 0.000390 loss: 3.3134 (3.1545) grad_norm: 1.6674 (1.7003) time: 0.6258 [2021-03-27 13:44:06 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 530/1251] eta: 0:07:36 lr: 0.000390 loss: 3.3028 (3.1531) grad_norm: 1.6243 (1.6991) time: 0.6240 [2021-03-27 13:44:13 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 540/1251] eta: 0:07:30 lr: 0.000390 loss: 3.1574 (3.1525) grad_norm: 1.6842 (1.6995) time: 0.6235 [2021-03-27 13:44:19 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 550/1251] eta: 0:07:23 lr: 0.000390 loss: 3.1441 (3.1543) grad_norm: 1.7196 (1.7036) time: 0.6303 [2021-03-27 13:44:25 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 560/1251] eta: 0:07:17 lr: 0.000390 loss: 3.2897 (3.1532) grad_norm: 1.7646 (1.7039) time: 0.6361 [2021-03-27 13:44:32 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 570/1251] eta: 0:07:11 lr: 0.000390 loss: 3.3160 (3.1559) grad_norm: 1.6719 (1.7037) time: 0.6303 [2021-03-27 13:44:38 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 580/1251] eta: 0:07:04 lr: 0.000390 loss: 3.3401 (3.1570) grad_norm: 1.6719 (1.7023) time: 0.6264 [2021-03-27 13:44:44 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 590/1251] eta: 0:06:58 lr: 0.000390 loss: 3.2609 (3.1545) grad_norm: 1.7589 (1.7073) time: 0.6293 [2021-03-27 13:44:51 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 600/1251] eta: 0:06:52 lr: 0.000390 loss: 3.2352 (3.1569) grad_norm: 1.8621 (1.7090) time: 0.6295 [2021-03-27 13:44:57 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 610/1251] eta: 0:06:45 lr: 0.000390 loss: 3.1224 (3.1547) grad_norm: 1.6034 (1.7076) time: 0.6292 [2021-03-27 13:45:03 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 620/1251] eta: 0:06:39 lr: 0.000389 loss: 3.0673 (3.1551) grad_norm: 1.6031 (1.7059) time: 0.6325 [2021-03-27 13:45:09 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 630/1251] eta: 0:06:33 lr: 0.000389 loss: 3.0646 (3.1558) grad_norm: 1.6872 (1.7081) time: 0.6333 [2021-03-27 13:45:16 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 640/1251] eta: 0:06:26 lr: 0.000389 loss: 3.2719 (3.1567) grad_norm: 1.7542 (1.7101) time: 0.6295 [2021-03-27 13:45:22 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 650/1251] eta: 0:06:20 lr: 0.000389 loss: 3.2719 (3.1596) grad_norm: 1.8255 (1.7114) time: 0.6324 [2021-03-27 13:45:28 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 660/1251] eta: 0:06:13 lr: 0.000389 loss: 3.2186 (3.1565) grad_norm: 1.7578 (1.7112) time: 0.6309 [2021-03-27 13:45:35 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 670/1251] eta: 0:06:07 lr: 0.000389 loss: 3.2467 (3.1574) grad_norm: 1.6468 (1.7106) time: 0.6231 [2021-03-27 13:45:41 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 680/1251] eta: 0:06:01 lr: 0.000389 loss: 3.3223 (3.1562) grad_norm: 1.6437 (1.7109) time: 0.6275 [2021-03-27 13:45:47 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 690/1251] eta: 0:05:54 lr: 0.000389 loss: 3.0239 (3.1567) grad_norm: 1.6437 (1.7103) time: 0.6301 [2021-03-27 13:45:53 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 700/1251] eta: 0:05:48 lr: 0.000389 loss: 3.0239 (3.1580) grad_norm: 1.6741 (1.7110) time: 0.6234 [2021-03-27 13:46:00 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 710/1251] eta: 0:05:42 lr: 0.000389 loss: 3.0304 (3.1566) grad_norm: 1.6741 (1.7107) time: 0.6209 [2021-03-27 13:46:06 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 720/1251] eta: 0:05:35 lr: 0.000389 loss: 3.2871 (3.1595) grad_norm: 1.6531 (1.7119) time: 0.6281 [2021-03-27 13:46:12 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 730/1251] eta: 0:05:29 lr: 0.000389 loss: 3.4579 (3.1612) grad_norm: 1.7197 (1.7120) time: 0.6356 [2021-03-27 13:46:19 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 740/1251] eta: 0:05:23 lr: 0.000389 loss: 3.2135 (3.1601) grad_norm: 1.7197 (1.7128) time: 0.6397 [2021-03-27 13:46:25 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 750/1251] eta: 0:05:16 lr: 0.000389 loss: 3.4375 (3.1662) grad_norm: 1.7368 (1.7142) time: 0.6427 [2021-03-27 13:46:31 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 760/1251] eta: 0:05:10 lr: 0.000389 loss: 3.4375 (3.1643) grad_norm: 1.8126 (1.7191) time: 0.6341 [2021-03-27 13:46:38 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 770/1251] eta: 0:05:04 lr: 0.000389 loss: 3.4181 (3.1685) grad_norm: 1.7549 (1.7198) time: 0.6290 [2021-03-27 13:46:44 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 780/1251] eta: 0:04:57 lr: 0.000389 loss: 3.4455 (3.1703) grad_norm: 1.7113 (1.7186) time: 0.6331 [2021-03-27 13:46:50 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 790/1251] eta: 0:04:51 lr: 0.000389 loss: 3.1434 (3.1676) grad_norm: 1.6794 (1.7184) time: 0.6313 [2021-03-27 13:46:57 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 800/1251] eta: 0:04:45 lr: 0.000389 loss: 3.1434 (3.1663) grad_norm: 1.5710 (1.7170) time: 0.6269 [2021-03-27 13:47:03 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 810/1251] eta: 0:04:38 lr: 0.000389 loss: 3.2569 (3.1659) grad_norm: 1.6207 (1.7157) time: 0.6300 [2021-03-27 13:47:09 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 820/1251] eta: 0:04:32 lr: 0.000389 loss: 3.0706 (3.1643) grad_norm: 1.6371 (1.7146) time: 0.6317 [2021-03-27 13:47:16 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 830/1251] eta: 0:04:26 lr: 0.000389 loss: 3.0706 (3.1639) grad_norm: 1.6623 (1.7156) time: 0.6275 [2021-03-27 13:47:22 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 840/1251] eta: 0:04:19 lr: 0.000389 loss: 3.1188 (3.1645) grad_norm: 1.6532 (1.7150) time: 0.6293 [2021-03-27 13:47:28 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 850/1251] eta: 0:04:13 lr: 0.000389 loss: 3.3222 (3.1650) grad_norm: 1.6193 (1.7143) time: 0.6258 [2021-03-27 13:47:34 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 860/1251] eta: 0:04:07 lr: 0.000388 loss: 3.3187 (3.1661) grad_norm: 1.7595 (1.7163) time: 0.6217 [2021-03-27 13:47:41 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 870/1251] eta: 0:04:00 lr: 0.000388 loss: 3.3187 (3.1680) grad_norm: 1.6748 (1.7165) time: 0.6234 [2021-03-27 13:47:47 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 880/1251] eta: 0:03:54 lr: 0.000388 loss: 3.5332 (3.1716) grad_norm: 1.6554 (1.7172) time: 0.6253 [2021-03-27 13:47:53 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 890/1251] eta: 0:03:48 lr: 0.000388 loss: 3.2302 (3.1683) grad_norm: 1.6596 (1.7177) time: 0.6335 [2021-03-27 13:47:59 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 900/1251] eta: 0:03:41 lr: 0.000388 loss: 3.2302 (3.1703) grad_norm: 1.6596 (1.7179) time: 0.6326 [2021-03-27 13:48:06 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 910/1251] eta: 0:03:35 lr: 0.000388 loss: 3.4027 (3.1717) grad_norm: 1.6758 (1.7208) time: 0.6273 [2021-03-27 13:48:12 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 920/1251] eta: 0:03:29 lr: 0.000388 loss: 3.1496 (3.1690) grad_norm: 1.6981 (1.7208) time: 0.6270 [2021-03-27 13:48:18 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 930/1251] eta: 0:03:22 lr: 0.000388 loss: 3.1984 (3.1698) grad_norm: 1.7094 (1.7219) time: 0.6257 [2021-03-27 13:48:25 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 940/1251] eta: 0:03:16 lr: 0.000388 loss: 3.3696 (3.1710) grad_norm: 1.7527 (1.7235) time: 0.6276 [2021-03-27 13:48:31 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 950/1251] eta: 0:03:10 lr: 0.000388 loss: 3.4593 (3.1706) grad_norm: 1.7764 (1.7239) time: 0.6288 [2021-03-27 13:48:37 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 960/1251] eta: 0:03:03 lr: 0.000388 loss: 3.3656 (3.1711) grad_norm: 1.7267 (1.7239) time: 0.6287 [2021-03-27 13:48:43 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 970/1251] eta: 0:02:57 lr: 0.000388 loss: 3.3733 (3.1739) grad_norm: 1.6824 (1.7239) time: 0.6298 [2021-03-27 13:48:50 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 980/1251] eta: 0:02:51 lr: 0.000388 loss: 3.2857 (3.1743) grad_norm: 1.6797 (1.7237) time: 0.6329 [2021-03-27 13:48:56 swin_base_patch4_window7_224] INFO: Epoch: [172] [ 990/1251] eta: 0:02:44 lr: 0.000388 loss: 3.2857 (3.1764) grad_norm: 1.6651 (1.7223) time: 0.6306 [2021-03-27 13:49:02 swin_base_patch4_window7_224] INFO: Epoch: [172] [1000/1251] eta: 0:02:38 lr: 0.000388 loss: 3.2145 (3.1751) grad_norm: 1.6651 (1.7217) time: 0.6262 [2021-03-27 13:49:09 swin_base_patch4_window7_224] INFO: Epoch: [172] [1010/1251] eta: 0:02:32 lr: 0.000388 loss: 3.1014 (3.1772) grad_norm: 1.6665 (1.7218) time: 0.6324 [2021-03-27 13:49:15 swin_base_patch4_window7_224] INFO: Epoch: [172] [1020/1251] eta: 0:02:25 lr: 0.000388 loss: 3.0754 (3.1757) grad_norm: 1.6597 (1.7213) time: 0.6321 [2021-03-27 13:49:21 swin_base_patch4_window7_224] INFO: Epoch: [172] [1030/1251] eta: 0:02:19 lr: 0.000388 loss: 3.3890 (3.1777) grad_norm: 1.6766 (1.7211) time: 0.6261 [2021-03-27 13:49:27 swin_base_patch4_window7_224] INFO: Epoch: [172] [1040/1251] eta: 0:02:13 lr: 0.000388 loss: 3.3041 (3.1759) grad_norm: 1.7176 (1.7220) time: 0.6233 [2021-03-27 13:49:34 swin_base_patch4_window7_224] INFO: Epoch: [172] [1050/1251] eta: 0:02:06 lr: 0.000388 loss: 3.3111 (3.1780) grad_norm: 1.6617 (1.7238) time: 0.6209 [2021-03-27 13:49:40 swin_base_patch4_window7_224] INFO: Epoch: [172] [1060/1251] eta: 0:02:00 lr: 0.000388 loss: 3.4055 (3.1788) grad_norm: 1.6617 (1.7233) time: 0.6220 [2021-03-27 13:49:46 swin_base_patch4_window7_224] INFO: Epoch: [172] [1070/1251] eta: 0:01:54 lr: 0.000388 loss: 3.3168 (3.1786) grad_norm: 1.6135 (1.7222) time: 0.6274 [2021-03-27 13:49:53 swin_base_patch4_window7_224] INFO: Epoch: [172] [1080/1251] eta: 0:01:47 lr: 0.000388 loss: 3.2118 (3.1797) grad_norm: 1.5426 (1.7211) time: 0.6357 [2021-03-27 13:49:59 swin_base_patch4_window7_224] INFO: Epoch: [172] [1090/1251] eta: 0:01:41 lr: 0.000388 loss: 3.0990 (3.1788) grad_norm: 1.5994 (1.7205) time: 0.6373 [2021-03-27 13:50:05 swin_base_patch4_window7_224] INFO: Epoch: [172] [1100/1251] eta: 0:01:35 lr: 0.000388 loss: 3.0591 (3.1793) grad_norm: 1.6034 (1.7196) time: 0.6292 [2021-03-27 13:50:11 swin_base_patch4_window7_224] INFO: Epoch: [172] [1110/1251] eta: 0:01:29 lr: 0.000387 loss: 3.4095 (3.1795) grad_norm: 1.6296 (1.7196) time: 0.6233 [2021-03-27 13:50:18 swin_base_patch4_window7_224] INFO: Epoch: [172] [1120/1251] eta: 0:01:22 lr: 0.000387 loss: 3.1662 (3.1781) grad_norm: 1.6576 (1.7192) time: 0.6271 [2021-03-27 13:50:24 swin_base_patch4_window7_224] INFO: Epoch: [172] [1130/1251] eta: 0:01:16 lr: 0.000387 loss: 3.0978 (3.1768) grad_norm: 1.6861 (1.7195) time: 0.6340 [2021-03-27 13:50:30 swin_base_patch4_window7_224] INFO: Epoch: [172] [1140/1251] eta: 0:01:10 lr: 0.000387 loss: 3.1713 (3.1774) grad_norm: 1.7408 (1.7194) time: 0.6291 [2021-03-27 13:50:37 swin_base_patch4_window7_224] INFO: Epoch: [172] [1150/1251] eta: 0:01:03 lr: 0.000387 loss: 3.3449 (3.1771) grad_norm: 1.7421 (1.7190) time: 0.6244 [2021-03-27 13:50:43 swin_base_patch4_window7_224] INFO: Epoch: [172] [1160/1251] eta: 0:00:57 lr: 0.000387 loss: 3.3031 (3.1792) grad_norm: 1.7155 (1.7190) time: 0.6270 [2021-03-27 13:50:49 swin_base_patch4_window7_224] INFO: Epoch: [172] [1170/1251] eta: 0:00:51 lr: 0.000387 loss: 3.2573 (3.1787) grad_norm: 1.6074 (1.7182) time: 0.6238 [2021-03-27 13:50:55 swin_base_patch4_window7_224] INFO: Epoch: [172] [1180/1251] eta: 0:00:44 lr: 0.000387 loss: 3.1280 (3.1761) grad_norm: 1.6452 (1.7183) time: 0.6246 [2021-03-27 13:51:02 swin_base_patch4_window7_224] INFO: Epoch: [172] [1190/1251] eta: 0:00:38 lr: 0.000387 loss: 3.1319 (3.1759) grad_norm: 1.7038 (1.7193) time: 0.6255 [2021-03-27 13:51:08 swin_base_patch4_window7_224] INFO: Epoch: [172] [1200/1251] eta: 0:00:32 lr: 0.000387 loss: 3.2962 (3.1777) grad_norm: 1.8019 (1.7200) time: 0.6233 [2021-03-27 13:51:14 swin_base_patch4_window7_224] INFO: Epoch: [172] [1210/1251] eta: 0:00:25 lr: 0.000387 loss: 3.2116 (3.1768) grad_norm: 1.7821 (1.7212) time: 0.6206 [2021-03-27 13:51:20 swin_base_patch4_window7_224] INFO: Epoch: [172] [1220/1251] eta: 0:00:19 lr: 0.000387 loss: 3.1959 (3.1771) grad_norm: 1.7368 (1.7212) time: 0.6224 [2021-03-27 13:51:27 swin_base_patch4_window7_224] INFO: Epoch: [172] [1230/1251] eta: 0:00:13 lr: 0.000387 loss: 3.2202 (3.1774) grad_norm: 1.7035 (1.7214) time: 0.6238 [2021-03-27 13:51:33 swin_base_patch4_window7_224] INFO: Epoch: [172] [1240/1251] eta: 0:00:06 lr: 0.000387 loss: 3.2724 (3.1779) grad_norm: 1.7356 (1.7219) time: 0.6227 [2021-03-27 13:51:39 swin_base_patch4_window7_224] INFO: Epoch: [172] [1250/1251] eta: 0:00:00 lr: 0.000387 loss: 3.0731 (3.1761) grad_norm: 1.6413 (1.7223) time: 0.6197 [2021-03-27 13:51:47 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:02 loss: 0.6866 (0.6866) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-27 13:51:49 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8005 (0.8838) acc1: 81.2500 (78.5511) acc5: 95.3125 (95.1705) [2021-03-27 13:51:51 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7960 (0.8409) acc1: 81.2500 (80.5060) acc5: 96.8750 (95.6845) [2021-03-27 13:51:54 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7466 (0.8364) acc1: 81.2500 (80.0907) acc5: 95.3125 (95.4133) [2021-03-27 13:51:56 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8292 (0.8542) acc1: 79.6875 (79.3064) acc5: 95.3125 (95.2363) [2021-03-27 13:51:57 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8583 (0.8532) acc1: 76.5625 (79.1040) acc5: 95.3125 (95.3600) [2021-03-27 13:52:06 swin_base_patch4_window7_224] INFO: * Acc@1 79.894 Acc@5 95.318 loss 0.846 [2021-03-27 13:52:06 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.9% [2021-03-27 13:52:06 swin_base_patch4_window7_224] INFO: Max accuracy: 79.97% [2021-03-27 13:52:10 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 0/1251] eta: 1:30:16 lr: 0.000387 loss: 3.3176 (3.3176) grad_norm: 1.5854 (1.5854) time: 4.3294 [2021-03-27 13:52:16 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 10/1251] eta: 0:20:23 lr: 0.000387 loss: 3.2102 (3.1348) grad_norm: 1.6059 (1.6070) time: 0.9857 [2021-03-27 13:52:23 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 20/1251] eta: 0:16:40 lr: 0.000387 loss: 3.1643 (3.1198) grad_norm: 1.5894 (1.5968) time: 0.6371 [2021-03-27 13:52:29 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 30/1251] eta: 0:15:20 lr: 0.000387 loss: 3.1780 (3.1978) grad_norm: 1.6546 (1.6781) time: 0.6258 [2021-03-27 13:52:35 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 40/1251] eta: 0:14:38 lr: 0.000387 loss: 3.1675 (3.1446) grad_norm: 1.7067 (1.7289) time: 0.6342 [2021-03-27 13:52:42 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 50/1251] eta: 0:14:11 lr: 0.000387 loss: 3.0336 (3.1661) grad_norm: 1.7186 (1.7337) time: 0.6401 [2021-03-27 13:52:48 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 60/1251] eta: 0:13:49 lr: 0.000387 loss: 3.1057 (3.1502) grad_norm: 1.6525 (1.7227) time: 0.6358 [2021-03-27 13:52:54 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 70/1251] eta: 0:13:33 lr: 0.000387 loss: 3.4246 (3.1781) grad_norm: 1.7153 (1.7361) time: 0.6384 [2021-03-27 13:53:01 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 80/1251] eta: 0:13:17 lr: 0.000387 loss: 3.4592 (3.2015) grad_norm: 1.7296 (1.7584) time: 0.6346 [2021-03-27 13:53:07 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 90/1251] eta: 0:13:03 lr: 0.000387 loss: 3.4413 (3.2071) grad_norm: 1.7251 (1.7483) time: 0.6233 [2021-03-27 13:53:13 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 100/1251] eta: 0:12:52 lr: 0.000387 loss: 3.1303 (3.1635) grad_norm: 1.6127 (1.7395) time: 0.6297 [2021-03-27 13:53:20 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 110/1251] eta: 0:12:41 lr: 0.000386 loss: 2.9414 (3.1761) grad_norm: 1.7220 (1.7475) time: 0.6327 [2021-03-27 13:53:26 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 120/1251] eta: 0:12:31 lr: 0.000386 loss: 3.0514 (3.1686) grad_norm: 1.6887 (1.7412) time: 0.6332 [2021-03-27 13:53:32 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 130/1251] eta: 0:12:23 lr: 0.000386 loss: 3.1082 (3.1904) grad_norm: 1.5601 (1.7328) time: 0.6435 [2021-03-27 13:53:39 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 140/1251] eta: 0:12:14 lr: 0.000386 loss: 3.4683 (3.1981) grad_norm: 1.5439 (1.7235) time: 0.6389 [2021-03-27 13:53:45 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 150/1251] eta: 0:12:04 lr: 0.000386 loss: 3.2759 (3.1947) grad_norm: 1.5399 (1.7118) time: 0.6251 [2021-03-27 13:53:51 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 160/1251] eta: 0:11:56 lr: 0.000386 loss: 3.1217 (3.1934) grad_norm: 1.7124 (1.7209) time: 0.6248 [2021-03-27 13:53:58 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 170/1251] eta: 0:11:47 lr: 0.000386 loss: 3.0786 (3.1838) grad_norm: 1.7543 (1.7216) time: 0.6283 [2021-03-27 13:54:04 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 180/1251] eta: 0:11:40 lr: 0.000386 loss: 3.2865 (3.1989) grad_norm: 1.7517 (1.7228) time: 0.6331 [2021-03-27 13:54:10 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 190/1251] eta: 0:11:32 lr: 0.000386 loss: 3.6110 (3.2116) grad_norm: 1.7215 (1.7217) time: 0.6354 [2021-03-27 13:54:17 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 200/1251] eta: 0:11:24 lr: 0.000386 loss: 3.5827 (3.2169) grad_norm: 1.7364 (1.7263) time: 0.6302 [2021-03-27 13:54:23 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 210/1251] eta: 0:11:17 lr: 0.000386 loss: 3.3544 (3.2263) grad_norm: 1.7992 (1.7322) time: 0.6338 [2021-03-27 13:54:29 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 220/1251] eta: 0:11:09 lr: 0.000386 loss: 3.1763 (3.2208) grad_norm: 1.7547 (1.7325) time: 0.6289 [2021-03-27 13:54:35 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 230/1251] eta: 0:11:02 lr: 0.000386 loss: 3.0667 (3.2233) grad_norm: 1.6894 (1.7301) time: 0.6261 [2021-03-27 13:54:42 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 240/1251] eta: 0:10:55 lr: 0.000386 loss: 3.2599 (3.2179) grad_norm: 1.6717 (1.7273) time: 0.6301 [2021-03-27 13:54:48 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 250/1251] eta: 0:10:47 lr: 0.000386 loss: 3.3395 (3.2286) grad_norm: 1.6614 (1.7258) time: 0.6255 [2021-03-27 13:54:54 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 260/1251] eta: 0:10:40 lr: 0.000386 loss: 3.3632 (3.2236) grad_norm: 1.6269 (1.7207) time: 0.6294 [2021-03-27 13:55:01 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 270/1251] eta: 0:10:33 lr: 0.000386 loss: 3.3417 (3.2293) grad_norm: 1.6271 (1.7212) time: 0.6310 [2021-03-27 13:55:07 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 280/1251] eta: 0:10:26 lr: 0.000386 loss: 3.2523 (3.2233) grad_norm: 1.6322 (1.7223) time: 0.6278 [2021-03-27 13:55:13 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 290/1251] eta: 0:10:19 lr: 0.000386 loss: 2.9316 (3.2131) grad_norm: 1.5940 (1.7199) time: 0.6275 [2021-03-27 13:55:19 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 300/1251] eta: 0:10:12 lr: 0.000386 loss: 3.1735 (3.2197) grad_norm: 1.5813 (1.7172) time: 0.6283 [2021-03-27 13:55:26 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 310/1251] eta: 0:10:05 lr: 0.000386 loss: 3.1954 (3.2157) grad_norm: 1.5909 (1.7162) time: 0.6305 [2021-03-27 13:55:32 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 320/1251] eta: 0:09:58 lr: 0.000386 loss: 3.2024 (3.2233) grad_norm: 1.6436 (1.7143) time: 0.6311 [2021-03-27 13:55:38 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 330/1251] eta: 0:09:52 lr: 0.000386 loss: 3.4230 (3.2205) grad_norm: 1.7375 (1.7169) time: 0.6304 [2021-03-27 13:55:45 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 340/1251] eta: 0:09:45 lr: 0.000386 loss: 3.2331 (3.2222) grad_norm: 1.7375 (1.7176) time: 0.6321 [2021-03-27 13:55:51 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 350/1251] eta: 0:09:38 lr: 0.000386 loss: 3.2853 (3.2225) grad_norm: 1.7099 (1.7173) time: 0.6299 [2021-03-27 13:55:57 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 360/1251] eta: 0:09:31 lr: 0.000385 loss: 2.9248 (3.2092) grad_norm: 1.7481 (1.7228) time: 0.6303 [2021-03-27 13:56:04 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 370/1251] eta: 0:09:25 lr: 0.000385 loss: 2.9248 (3.2086) grad_norm: 1.7257 (1.7217) time: 0.6309 [2021-03-27 13:56:10 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 380/1251] eta: 0:09:18 lr: 0.000385 loss: 3.2277 (3.2029) grad_norm: 1.7623 (1.7269) time: 0.6278 [2021-03-27 13:56:16 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 390/1251] eta: 0:09:11 lr: 0.000385 loss: 3.1204 (3.2016) grad_norm: 1.7712 (1.7262) time: 0.6275 [2021-03-27 13:56:22 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 400/1251] eta: 0:09:05 lr: 0.000385 loss: 3.3514 (3.2051) grad_norm: 1.6161 (1.7240) time: 0.6289 [2021-03-27 13:56:29 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 410/1251] eta: 0:08:58 lr: 0.000385 loss: 3.3564 (3.2079) grad_norm: 1.6161 (1.7234) time: 0.6302 [2021-03-27 13:56:35 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 420/1251] eta: 0:08:51 lr: 0.000385 loss: 3.2415 (3.2079) grad_norm: 1.6322 (1.7215) time: 0.6291 [2021-03-27 13:56:41 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 430/1251] eta: 0:08:45 lr: 0.000385 loss: 3.2356 (3.2094) grad_norm: 1.6436 (1.7213) time: 0.6290 [2021-03-27 13:56:48 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 440/1251] eta: 0:08:38 lr: 0.000385 loss: 3.1205 (3.2070) grad_norm: 1.6765 (1.7198) time: 0.6278 [2021-03-27 13:56:54 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 450/1251] eta: 0:08:31 lr: 0.000385 loss: 3.1205 (3.2069) grad_norm: 1.6851 (1.7210) time: 0.6262 [2021-03-27 13:57:00 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 460/1251] eta: 0:08:25 lr: 0.000385 loss: 3.2055 (3.2043) grad_norm: 1.6851 (1.7199) time: 0.6266 [2021-03-27 13:57:07 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 470/1251] eta: 0:08:18 lr: 0.000385 loss: 3.2691 (3.2021) grad_norm: 1.6642 (1.7211) time: 0.6313 [2021-03-27 13:57:13 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 480/1251] eta: 0:08:12 lr: 0.000385 loss: 3.2691 (3.2014) grad_norm: 1.7403 (1.7208) time: 0.6324 [2021-03-27 13:57:19 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 490/1251] eta: 0:08:05 lr: 0.000385 loss: 3.2242 (3.2028) grad_norm: 1.7110 (1.7218) time: 0.6292 [2021-03-27 13:57:25 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 500/1251] eta: 0:07:59 lr: 0.000385 loss: 3.2242 (3.2041) grad_norm: 1.6917 (1.7229) time: 0.6336 [2021-03-27 13:57:32 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 510/1251] eta: 0:07:52 lr: 0.000385 loss: 3.2362 (3.2058) grad_norm: 1.7898 (1.7250) time: 0.6307 [2021-03-27 13:57:38 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 520/1251] eta: 0:07:46 lr: 0.000385 loss: 3.1923 (3.2037) grad_norm: 1.8187 (1.7265) time: 0.6275 [2021-03-27 13:57:44 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 530/1251] eta: 0:07:39 lr: 0.000385 loss: 3.1315 (3.2016) grad_norm: 1.6479 (1.7247) time: 0.6292 [2021-03-27 13:57:50 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 540/1251] eta: 0:07:33 lr: 0.000385 loss: 2.9364 (3.1979) grad_norm: 1.6740 (1.7248) time: 0.6227 [2021-03-27 13:57:57 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 550/1251] eta: 0:07:27 lr: 0.000385 loss: 3.1791 (3.2006) grad_norm: 1.7409 (1.7261) time: 0.6355 [2021-03-27 13:58:03 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 560/1251] eta: 0:07:20 lr: 0.000385 loss: 3.1791 (3.1992) grad_norm: 1.6543 (1.7249) time: 0.6400 [2021-03-27 13:58:10 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 570/1251] eta: 0:07:14 lr: 0.000385 loss: 3.1085 (3.2012) grad_norm: 1.6232 (1.7254) time: 0.6329 [2021-03-27 13:58:16 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 580/1251] eta: 0:07:07 lr: 0.000385 loss: 3.5097 (3.2046) grad_norm: 1.6232 (1.7237) time: 0.6309 [2021-03-27 13:58:22 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 590/1251] eta: 0:07:01 lr: 0.000385 loss: 3.4496 (3.2050) grad_norm: 1.7291 (1.7267) time: 0.6242 [2021-03-27 13:58:29 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 600/1251] eta: 0:06:54 lr: 0.000385 loss: 3.2063 (3.2033) grad_norm: 1.7980 (1.7270) time: 0.6297 [2021-03-27 13:58:35 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 610/1251] eta: 0:06:48 lr: 0.000384 loss: 3.2226 (3.2059) grad_norm: 1.7852 (1.7270) time: 0.6331 [2021-03-27 13:58:41 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 620/1251] eta: 0:06:41 lr: 0.000384 loss: 3.4898 (3.2077) grad_norm: 1.7159 (1.7265) time: 0.6373 [2021-03-27 13:58:48 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 630/1251] eta: 0:06:35 lr: 0.000384 loss: 3.3568 (3.2086) grad_norm: 1.6483 (1.7245) time: 0.6378 [2021-03-27 13:58:54 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 640/1251] eta: 0:06:29 lr: 0.000384 loss: 3.3568 (3.2111) grad_norm: 1.6440 (1.7244) time: 0.6344 [2021-03-27 13:59:00 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 650/1251] eta: 0:06:22 lr: 0.000384 loss: 3.4431 (3.2128) grad_norm: 1.6237 (1.7221) time: 0.6355 [2021-03-27 13:59:07 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 660/1251] eta: 0:06:16 lr: 0.000384 loss: 3.4431 (3.2118) grad_norm: 1.5600 (1.7249) time: 0.6311 [2021-03-27 13:59:13 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 670/1251] eta: 0:06:09 lr: 0.000384 loss: 3.4700 (3.2147) grad_norm: 1.7174 (1.7253) time: 0.6317 [2021-03-27 13:59:19 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 680/1251] eta: 0:06:03 lr: 0.000384 loss: 3.4031 (3.2155) grad_norm: 1.7057 (1.7263) time: 0.6341 [2021-03-27 13:59:25 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 690/1251] eta: 0:05:57 lr: 0.000384 loss: 3.3090 (3.2168) grad_norm: 1.7269 (1.7267) time: 0.6262 [2021-03-27 13:59:32 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 700/1251] eta: 0:05:50 lr: 0.000384 loss: 3.3090 (3.2166) grad_norm: 1.7177 (1.7261) time: 0.6245 [2021-03-27 13:59:38 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 710/1251] eta: 0:05:44 lr: 0.000384 loss: 3.1973 (3.2144) grad_norm: 1.6761 (1.7267) time: 0.6293 [2021-03-27 13:59:44 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 720/1251] eta: 0:05:37 lr: 0.000384 loss: 3.1324 (3.2153) grad_norm: 1.7018 (1.7272) time: 0.6302 [2021-03-27 13:59:51 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 730/1251] eta: 0:05:31 lr: 0.000384 loss: 3.1211 (3.2099) grad_norm: 1.6769 (1.7276) time: 0.6301 [2021-03-27 13:59:57 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 740/1251] eta: 0:05:25 lr: 0.000384 loss: 3.1211 (3.2092) grad_norm: 1.7365 (1.7288) time: 0.6308 [2021-03-27 14:00:03 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 750/1251] eta: 0:05:18 lr: 0.000384 loss: 3.3605 (3.2079) grad_norm: 1.6791 (1.7298) time: 0.6295 [2021-03-27 14:00:10 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 760/1251] eta: 0:05:12 lr: 0.000384 loss: 3.1836 (3.2056) grad_norm: 1.7722 (1.7302) time: 0.6401 [2021-03-27 14:00:16 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 770/1251] eta: 0:05:05 lr: 0.000384 loss: 3.0855 (3.2049) grad_norm: 1.7166 (1.7294) time: 0.6390 [2021-03-27 14:00:22 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 780/1251] eta: 0:04:59 lr: 0.000384 loss: 3.3215 (3.2091) grad_norm: 1.6879 (1.7293) time: 0.6249 [2021-03-27 14:00:29 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 790/1251] eta: 0:04:53 lr: 0.000384 loss: 3.2421 (3.2074) grad_norm: 1.5692 (1.7277) time: 0.6265 [2021-03-27 14:00:35 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 800/1251] eta: 0:04:46 lr: 0.000384 loss: 3.1958 (3.2078) grad_norm: 1.6454 (1.7289) time: 0.6320 [2021-03-27 14:00:41 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 810/1251] eta: 0:04:40 lr: 0.000384 loss: 3.1958 (3.2062) grad_norm: 1.7725 (1.7290) time: 0.6331 [2021-03-27 14:00:48 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 820/1251] eta: 0:04:33 lr: 0.000384 loss: 3.3285 (3.2075) grad_norm: 1.6632 (1.7295) time: 0.6310 [2021-03-27 14:00:54 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 830/1251] eta: 0:04:27 lr: 0.000384 loss: 3.3306 (3.2088) grad_norm: 1.6271 (1.7286) time: 0.6287 [2021-03-27 14:01:00 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 840/1251] eta: 0:04:21 lr: 0.000384 loss: 3.2783 (3.2100) grad_norm: 1.5940 (1.7270) time: 0.6222 [2021-03-27 14:01:06 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 850/1251] eta: 0:04:14 lr: 0.000384 loss: 3.4655 (3.2126) grad_norm: 1.6941 (1.7288) time: 0.6285 [2021-03-27 14:01:13 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 860/1251] eta: 0:04:08 lr: 0.000383 loss: 3.4744 (3.2110) grad_norm: 1.7292 (1.7296) time: 0.6364 [2021-03-27 14:01:19 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 870/1251] eta: 0:04:02 lr: 0.000383 loss: 3.2851 (3.2099) grad_norm: 1.7003 (1.7296) time: 0.6376 [2021-03-27 14:01:25 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 880/1251] eta: 0:03:55 lr: 0.000383 loss: 3.1587 (3.2092) grad_norm: 1.7103 (1.7292) time: 0.6327 [2021-03-27 14:01:32 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 890/1251] eta: 0:03:49 lr: 0.000383 loss: 3.2137 (3.2090) grad_norm: 1.7103 (1.7293) time: 0.6281 [2021-03-27 14:01:38 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 900/1251] eta: 0:03:42 lr: 0.000383 loss: 3.3121 (3.2101) grad_norm: 1.7400 (1.7320) time: 0.6318 [2021-03-27 14:01:44 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 910/1251] eta: 0:03:36 lr: 0.000383 loss: 3.3760 (3.2108) grad_norm: 1.7361 (1.7326) time: 0.6338 [2021-03-27 14:01:51 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 920/1251] eta: 0:03:30 lr: 0.000383 loss: 3.3663 (3.2119) grad_norm: 1.8615 (1.7348) time: 0.6325 [2021-03-27 14:01:57 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 930/1251] eta: 0:03:23 lr: 0.000383 loss: 3.3154 (3.2124) grad_norm: 1.8710 (1.7356) time: 0.6278 [2021-03-27 14:02:03 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 940/1251] eta: 0:03:17 lr: 0.000383 loss: 3.3672 (3.2147) grad_norm: 1.7846 (1.7368) time: 0.6269 [2021-03-27 14:02:10 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 950/1251] eta: 0:03:11 lr: 0.000383 loss: 3.3672 (3.2159) grad_norm: 1.7495 (1.7370) time: 0.6294 [2021-03-27 14:02:16 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 960/1251] eta: 0:03:04 lr: 0.000383 loss: 3.2590 (3.2141) grad_norm: 1.7162 (1.7377) time: 0.6278 [2021-03-27 14:02:22 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 970/1251] eta: 0:02:58 lr: 0.000383 loss: 3.0972 (3.2140) grad_norm: 1.8333 (1.7394) time: 0.6249 [2021-03-27 14:02:28 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 980/1251] eta: 0:02:52 lr: 0.000383 loss: 3.2156 (3.2130) grad_norm: 1.7082 (1.7385) time: 0.6300 [2021-03-27 14:02:35 swin_base_patch4_window7_224] INFO: Epoch: [173] [ 990/1251] eta: 0:02:45 lr: 0.000383 loss: 3.0891 (3.2118) grad_norm: 1.6692 (1.7387) time: 0.6291 [2021-03-27 14:02:41 swin_base_patch4_window7_224] INFO: Epoch: [173] [1000/1251] eta: 0:02:39 lr: 0.000383 loss: 3.3036 (3.2144) grad_norm: 1.6313 (1.7378) time: 0.6277 [2021-03-27 14:02:47 swin_base_patch4_window7_224] INFO: Epoch: [173] [1010/1251] eta: 0:02:32 lr: 0.000383 loss: 3.4310 (3.2144) grad_norm: 1.6485 (1.7371) time: 0.6295 [2021-03-27 14:02:54 swin_base_patch4_window7_224] INFO: Epoch: [173] [1020/1251] eta: 0:02:26 lr: 0.000383 loss: 3.4310 (3.2153) grad_norm: 1.6485 (1.7367) time: 0.6284 [2021-03-27 14:03:00 swin_base_patch4_window7_224] INFO: Epoch: [173] [1030/1251] eta: 0:02:20 lr: 0.000383 loss: 3.1402 (3.2137) grad_norm: 1.7003 (1.7369) time: 0.6278 [2021-03-27 14:03:06 swin_base_patch4_window7_224] INFO: Epoch: [173] [1040/1251] eta: 0:02:13 lr: 0.000383 loss: 2.9843 (3.2134) grad_norm: 1.7510 (1.7371) time: 0.6317 [2021-03-27 14:03:12 swin_base_patch4_window7_224] INFO: Epoch: [173] [1050/1251] eta: 0:02:07 lr: 0.000383 loss: 3.1570 (3.2121) grad_norm: 1.7309 (1.7365) time: 0.6299 [2021-03-27 14:03:19 swin_base_patch4_window7_224] INFO: Epoch: [173] [1060/1251] eta: 0:02:01 lr: 0.000383 loss: 3.1696 (3.2107) grad_norm: 1.6627 (1.7367) time: 0.6309 [2021-03-27 14:03:25 swin_base_patch4_window7_224] INFO: Epoch: [173] [1070/1251] eta: 0:01:54 lr: 0.000383 loss: 3.1696 (3.2100) grad_norm: 1.7054 (1.7359) time: 0.6280 [2021-03-27 14:03:31 swin_base_patch4_window7_224] INFO: Epoch: [173] [1080/1251] eta: 0:01:48 lr: 0.000383 loss: 3.2299 (3.2088) grad_norm: 1.6714 (1.7359) time: 0.6221 [2021-03-27 14:03:38 swin_base_patch4_window7_224] INFO: Epoch: [173] [1090/1251] eta: 0:01:42 lr: 0.000383 loss: 3.2491 (3.2083) grad_norm: 1.7440 (1.7352) time: 0.6287 [2021-03-27 14:03:44 swin_base_patch4_window7_224] INFO: Epoch: [173] [1100/1251] eta: 0:01:35 lr: 0.000383 loss: 3.1719 (3.2060) grad_norm: 1.7727 (1.7357) time: 0.6308 [2021-03-27 14:03:50 swin_base_patch4_window7_224] INFO: Epoch: [173] [1110/1251] eta: 0:01:29 lr: 0.000382 loss: 3.1587 (3.2053) grad_norm: 1.7878 (1.7364) time: 0.6276 [2021-03-27 14:03:56 swin_base_patch4_window7_224] INFO: Epoch: [173] [1120/1251] eta: 0:01:23 lr: 0.000382 loss: 3.2002 (3.2037) grad_norm: 1.7464 (1.7363) time: 0.6227 [2021-03-27 14:04:03 swin_base_patch4_window7_224] INFO: Epoch: [173] [1130/1251] eta: 0:01:16 lr: 0.000382 loss: 3.2192 (3.2029) grad_norm: 1.7178 (1.7359) time: 0.6214 [2021-03-27 14:04:09 swin_base_patch4_window7_224] INFO: Epoch: [173] [1140/1251] eta: 0:01:10 lr: 0.000382 loss: 3.3192 (3.2045) grad_norm: 1.7025 (1.7364) time: 0.6256 [2021-03-27 14:04:15 swin_base_patch4_window7_224] INFO: Epoch: [173] [1150/1251] eta: 0:01:04 lr: 0.000382 loss: 3.3185 (3.2047) grad_norm: 1.7367 (1.7366) time: 0.6289 [2021-03-27 14:04:21 swin_base_patch4_window7_224] INFO: Epoch: [173] [1160/1251] eta: 0:00:57 lr: 0.000382 loss: 3.2311 (3.2021) grad_norm: 1.6807 (1.7358) time: 0.6266 [2021-03-27 14:04:28 swin_base_patch4_window7_224] INFO: Epoch: [173] [1170/1251] eta: 0:00:51 lr: 0.000382 loss: 3.3059 (3.2031) grad_norm: 1.5743 (1.7353) time: 0.6301 [2021-03-27 14:04:34 swin_base_patch4_window7_224] INFO: Epoch: [173] [1180/1251] eta: 0:00:44 lr: 0.000382 loss: 3.2549 (3.2017) grad_norm: 1.6165 (1.7350) time: 0.6305 [2021-03-27 14:04:40 swin_base_patch4_window7_224] INFO: Epoch: [173] [1190/1251] eta: 0:00:38 lr: 0.000382 loss: 3.3601 (3.2051) grad_norm: 1.6830 (1.7361) time: 0.6288 [2021-03-27 14:04:46 swin_base_patch4_window7_224] INFO: Epoch: [173] [1200/1251] eta: 0:00:32 lr: 0.000382 loss: 3.4207 (3.2050) grad_norm: 1.6705 (1.7357) time: 0.6262 [2021-03-27 14:04:53 swin_base_patch4_window7_224] INFO: Epoch: [173] [1210/1251] eta: 0:00:25 lr: 0.000382 loss: 3.1812 (3.2034) grad_norm: 1.5827 (1.7345) time: 0.6214 [2021-03-27 14:04:59 swin_base_patch4_window7_224] INFO: Epoch: [173] [1220/1251] eta: 0:00:19 lr: 0.000382 loss: 3.2497 (3.2037) grad_norm: 1.6038 (1.7336) time: 0.6296 [2021-03-27 14:05:05 swin_base_patch4_window7_224] INFO: Epoch: [173] [1230/1251] eta: 0:00:13 lr: 0.000382 loss: 3.4360 (3.2043) grad_norm: 1.6697 (1.7337) time: 0.6292 [2021-03-27 14:05:12 swin_base_patch4_window7_224] INFO: Epoch: [173] [1240/1251] eta: 0:00:06 lr: 0.000382 loss: 3.4527 (3.2053) grad_norm: 1.7052 (1.7336) time: 0.6278 [2021-03-27 14:05:18 swin_base_patch4_window7_224] INFO: Epoch: [173] [1250/1251] eta: 0:00:00 lr: 0.000382 loss: 3.4876 (3.2071) grad_norm: 1.6385 (1.7329) time: 0.6322 [2021-03-27 14:05:28 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:12 loss: 0.7644 (0.7644) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-27 14:05:31 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.9631 (0.9551) acc1: 76.5625 (77.5568) acc5: 95.3125 (95.0284) [2021-03-27 14:05:32 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.9126 (0.9003) acc1: 78.1250 (78.8690) acc5: 95.3125 (95.3125) [2021-03-27 14:05:34 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.7965 (0.8757) acc1: 81.2500 (79.6875) acc5: 95.3125 (95.4133) [2021-03-27 14:05:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7537 (0.8586) acc1: 82.8125 (80.0305) acc5: 96.8750 (95.8079) [2021-03-27 14:05:37 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7893 (0.8639) acc1: 81.2500 (79.8720) acc5: 96.8750 (95.6800) [2021-03-27 14:05:50 swin_base_patch4_window7_224] INFO: * Acc@1 79.992 Acc@5 95.330 loss 0.862 [2021-03-27 14:05:50 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.0% [2021-03-27 14:05:50 swin_base_patch4_window7_224] INFO: Max accuracy: 79.99% [2021-03-27 14:05:54 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 0/1251] eta: 1:26:10 lr: 0.000382 loss: 2.7903 (2.7903) grad_norm: 1.8208 (1.8208) time: 4.1332 [2021-03-27 14:06:00 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 10/1251] eta: 0:20:06 lr: 0.000382 loss: 3.4191 (3.2002) grad_norm: 1.7082 (1.7003) time: 0.9724 [2021-03-27 14:06:07 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 20/1251] eta: 0:16:37 lr: 0.000382 loss: 3.1280 (3.0841) grad_norm: 1.6531 (1.6889) time: 0.6442 [2021-03-27 14:06:13 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 30/1251] eta: 0:15:14 lr: 0.000382 loss: 3.1280 (3.1515) grad_norm: 1.6531 (1.6692) time: 0.6258 [2021-03-27 14:06:19 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 40/1251] eta: 0:14:35 lr: 0.000382 loss: 3.2933 (3.1774) grad_norm: 1.5876 (1.6698) time: 0.6313 [2021-03-27 14:06:25 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 50/1251] eta: 0:14:04 lr: 0.000382 loss: 3.3200 (3.1898) grad_norm: 1.5841 (1.6500) time: 0.6323 [2021-03-27 14:06:32 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 60/1251] eta: 0:13:42 lr: 0.000382 loss: 2.9846 (3.1294) grad_norm: 1.5416 (1.6307) time: 0.6242 [2021-03-27 14:06:38 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 70/1251] eta: 0:13:24 lr: 0.000382 loss: 2.9229 (3.0997) grad_norm: 1.5537 (1.6476) time: 0.6239 [2021-03-27 14:06:44 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 80/1251] eta: 0:13:08 lr: 0.000382 loss: 3.1391 (3.1294) grad_norm: 1.7059 (1.6801) time: 0.6212 [2021-03-27 14:06:50 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 90/1251] eta: 0:12:55 lr: 0.000382 loss: 3.2338 (3.1355) grad_norm: 1.7551 (1.6856) time: 0.6226 [2021-03-27 14:06:57 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 100/1251] eta: 0:12:44 lr: 0.000381 loss: 3.1554 (3.1456) grad_norm: 1.7156 (1.6970) time: 0.6276 [2021-03-27 14:07:03 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 110/1251] eta: 0:12:33 lr: 0.000381 loss: 3.3179 (3.1454) grad_norm: 1.7014 (1.6981) time: 0.6267 [2021-03-27 14:07:09 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 120/1251] eta: 0:12:24 lr: 0.000381 loss: 3.3117 (3.1398) grad_norm: 1.5915 (1.6883) time: 0.6270 [2021-03-27 14:07:16 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 130/1251] eta: 0:12:15 lr: 0.000381 loss: 3.2477 (3.1428) grad_norm: 1.6076 (nan) time: 0.6299 [2021-03-27 14:07:22 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 140/1251] eta: 0:12:05 lr: 0.000381 loss: 3.3138 (3.1485) grad_norm: 1.7638 (nan) time: 0.6223 [2021-03-27 14:07:28 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 150/1251] eta: 0:11:58 lr: 0.000381 loss: 3.1931 (3.1412) grad_norm: 1.5937 (nan) time: 0.6289 [2021-03-27 14:07:34 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 160/1251] eta: 0:11:50 lr: 0.000381 loss: 3.3190 (3.1605) grad_norm: 1.6318 (nan) time: 0.6373 [2021-03-27 14:07:41 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 170/1251] eta: 0:11:43 lr: 0.000381 loss: 3.4247 (3.1726) grad_norm: 1.6774 (nan) time: 0.6355 [2021-03-27 14:07:47 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 180/1251] eta: 0:11:36 lr: 0.000381 loss: 3.3010 (3.1731) grad_norm: 1.6545 (nan) time: 0.6419 [2021-03-27 14:07:54 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 190/1251] eta: 0:11:28 lr: 0.000381 loss: 3.2737 (3.1728) grad_norm: 1.6545 (nan) time: 0.6411 [2021-03-27 14:08:00 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 200/1251] eta: 0:11:21 lr: 0.000381 loss: 3.3150 (3.1796) grad_norm: 1.6453 (nan) time: 0.6317 [2021-03-27 14:08:06 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 210/1251] eta: 0:11:13 lr: 0.000381 loss: 3.3542 (3.1917) grad_norm: 1.7382 (nan) time: 0.6273 [2021-03-27 14:08:12 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 220/1251] eta: 0:11:06 lr: 0.000381 loss: 3.4122 (3.1965) grad_norm: 1.6880 (nan) time: 0.6242 [2021-03-27 14:08:19 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 230/1251] eta: 0:10:58 lr: 0.000381 loss: 3.2180 (3.1766) grad_norm: 1.6325 (nan) time: 0.6226 [2021-03-27 14:08:25 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 240/1251] eta: 0:10:51 lr: 0.000381 loss: 3.1110 (3.1798) grad_norm: 1.6316 (nan) time: 0.6241 [2021-03-27 14:08:31 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 250/1251] eta: 0:10:45 lr: 0.000381 loss: 3.4234 (3.1883) grad_norm: 1.6144 (nan) time: 0.6367 [2021-03-27 14:08:38 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 260/1251] eta: 0:10:38 lr: 0.000381 loss: 3.3615 (3.1856) grad_norm: 1.6643 (nan) time: 0.6411 [2021-03-27 14:08:44 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 270/1251] eta: 0:10:31 lr: 0.000381 loss: 3.2199 (3.1855) grad_norm: 1.5760 (nan) time: 0.6335 [2021-03-27 14:08:50 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 280/1251] eta: 0:10:24 lr: 0.000381 loss: 3.4363 (3.1860) grad_norm: 1.6694 (nan) time: 0.6294 [2021-03-27 14:08:57 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 290/1251] eta: 0:10:17 lr: 0.000381 loss: 3.4363 (3.1871) grad_norm: 1.7829 (nan) time: 0.6273 [2021-03-27 14:09:03 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 300/1251] eta: 0:10:11 lr: 0.000381 loss: 2.9959 (3.1823) grad_norm: 1.7204 (nan) time: 0.6359 [2021-03-27 14:09:09 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 310/1251] eta: 0:10:04 lr: 0.000381 loss: 3.3020 (3.1857) grad_norm: 1.6390 (nan) time: 0.6329 [2021-03-27 14:09:16 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 320/1251] eta: 0:09:57 lr: 0.000381 loss: 3.0403 (3.1827) grad_norm: 1.6419 (nan) time: 0.6276 [2021-03-27 14:09:22 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 330/1251] eta: 0:09:50 lr: 0.000381 loss: 3.2797 (3.1926) grad_norm: 1.7889 (nan) time: 0.6295 [2021-03-27 14:09:28 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 340/1251] eta: 0:09:44 lr: 0.000381 loss: 3.2797 (3.1901) grad_norm: 1.7404 (nan) time: 0.6326 [2021-03-27 14:09:34 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 350/1251] eta: 0:09:37 lr: 0.000380 loss: 3.2026 (3.1896) grad_norm: 1.6065 (nan) time: 0.6310 [2021-03-27 14:09:41 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 360/1251] eta: 0:09:30 lr: 0.000380 loss: 3.2894 (3.1877) grad_norm: 1.6784 (nan) time: 0.6322 [2021-03-27 14:09:47 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 370/1251] eta: 0:09:23 lr: 0.000380 loss: 3.1898 (3.1876) grad_norm: 1.7474 (nan) time: 0.6310 [2021-03-27 14:09:53 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 380/1251] eta: 0:09:17 lr: 0.000380 loss: 3.1898 (3.1880) grad_norm: 1.6914 (nan) time: 0.6254 [2021-03-27 14:10:00 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 390/1251] eta: 0:09:10 lr: 0.000380 loss: 3.1430 (3.1924) grad_norm: 1.6567 (nan) time: 0.6277 [2021-03-27 14:10:06 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 400/1251] eta: 0:09:04 lr: 0.000380 loss: 3.1979 (3.1953) grad_norm: 1.6892 (nan) time: 0.6312 [2021-03-27 14:10:12 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 410/1251] eta: 0:08:57 lr: 0.000380 loss: 3.3759 (3.1998) grad_norm: 1.7007 (nan) time: 0.6358 [2021-03-27 14:10:19 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 420/1251] eta: 0:08:51 lr: 0.000380 loss: 3.3071 (3.1960) grad_norm: 1.7007 (nan) time: 0.6374 [2021-03-27 14:10:25 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 430/1251] eta: 0:08:44 lr: 0.000380 loss: 3.3071 (3.1994) grad_norm: 1.7115 (nan) time: 0.6344 [2021-03-27 14:10:31 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 440/1251] eta: 0:08:38 lr: 0.000380 loss: 3.4483 (3.2016) grad_norm: 1.6602 (nan) time: 0.6305 [2021-03-27 14:10:38 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 450/1251] eta: 0:08:31 lr: 0.000380 loss: 3.4434 (3.2051) grad_norm: 1.6602 (nan) time: 0.6266 [2021-03-27 14:10:44 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 460/1251] eta: 0:08:24 lr: 0.000380 loss: 3.5074 (3.2102) grad_norm: 1.6825 (nan) time: 0.6268 [2021-03-27 14:10:50 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 470/1251] eta: 0:08:18 lr: 0.000380 loss: 3.5704 (3.2124) grad_norm: 1.6825 (nan) time: 0.6267 [2021-03-27 14:10:56 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 480/1251] eta: 0:08:11 lr: 0.000380 loss: 3.4534 (3.2137) grad_norm: 1.6129 (nan) time: 0.6257 [2021-03-27 14:11:03 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 490/1251] eta: 0:08:05 lr: 0.000380 loss: 3.3263 (3.2110) grad_norm: 1.7476 (nan) time: 0.6295 [2021-03-27 14:11:09 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 500/1251] eta: 0:07:58 lr: 0.000380 loss: 3.0902 (3.2085) grad_norm: 1.6819 (nan) time: 0.6275 [2021-03-27 14:11:15 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 510/1251] eta: 0:07:52 lr: 0.000380 loss: 3.0902 (3.2093) grad_norm: 1.6318 (nan) time: 0.6279 [2021-03-27 14:11:22 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 520/1251] eta: 0:07:45 lr: 0.000380 loss: 3.2869 (3.2081) grad_norm: 1.6318 (nan) time: 0.6300 [2021-03-27 14:11:28 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 530/1251] eta: 0:07:39 lr: 0.000380 loss: 2.9977 (3.2025) grad_norm: 1.6544 (nan) time: 0.6338 [2021-03-27 14:11:34 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 540/1251] eta: 0:07:32 lr: 0.000380 loss: 3.1569 (3.2042) grad_norm: 1.7267 (nan) time: 0.6343 [2021-03-27 14:11:41 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 550/1251] eta: 0:07:26 lr: 0.000380 loss: 3.1610 (3.2018) grad_norm: 1.7266 (nan) time: 0.6365 [2021-03-27 14:11:47 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 560/1251] eta: 0:07:20 lr: 0.000380 loss: 3.2581 (3.2012) grad_norm: 1.6532 (nan) time: 0.6357 [2021-03-27 14:11:53 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 570/1251] eta: 0:07:13 lr: 0.000380 loss: 3.3389 (3.2021) grad_norm: 1.6382 (nan) time: 0.6321 [2021-03-27 14:12:00 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 580/1251] eta: 0:07:07 lr: 0.000380 loss: 3.3889 (3.2030) grad_norm: 1.6677 (nan) time: 0.6359 [2021-03-27 14:12:06 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 590/1251] eta: 0:07:00 lr: 0.000380 loss: 3.2488 (3.2027) grad_norm: 1.6002 (nan) time: 0.6328 [2021-03-27 14:12:12 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 600/1251] eta: 0:06:54 lr: 0.000379 loss: 3.2488 (3.2038) grad_norm: 1.6315 (nan) time: 0.6314 [2021-03-27 14:12:19 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 610/1251] eta: 0:06:48 lr: 0.000379 loss: 3.2059 (3.2002) grad_norm: 1.6411 (nan) time: 0.6345 [2021-03-27 14:12:25 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 620/1251] eta: 0:06:41 lr: 0.000379 loss: 3.3717 (3.2037) grad_norm: 1.6295 (nan) time: 0.6297 [2021-03-27 14:12:31 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 630/1251] eta: 0:06:35 lr: 0.000379 loss: 3.3768 (3.2058) grad_norm: 1.6100 (nan) time: 0.6269 [2021-03-27 14:12:38 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 640/1251] eta: 0:06:28 lr: 0.000379 loss: 3.0845 (3.2032) grad_norm: 1.5940 (nan) time: 0.6289 [2021-03-27 14:12:44 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 650/1251] eta: 0:06:22 lr: 0.000379 loss: 2.9453 (3.2016) grad_norm: 1.6440 (nan) time: 0.6256 [2021-03-27 14:12:50 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 660/1251] eta: 0:06:15 lr: 0.000379 loss: 3.1612 (3.2022) grad_norm: 1.7658 (nan) time: 0.6240 [2021-03-27 14:12:56 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 670/1251] eta: 0:06:09 lr: 0.000379 loss: 3.2007 (3.2011) grad_norm: 1.6501 (nan) time: 0.6255 [2021-03-27 14:13:03 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 680/1251] eta: 0:06:02 lr: 0.000379 loss: 3.2552 (3.2021) grad_norm: 1.6340 (nan) time: 0.6289 [2021-03-27 14:13:09 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 690/1251] eta: 0:05:56 lr: 0.000379 loss: 3.2877 (3.2018) grad_norm: 1.6534 (nan) time: 0.6267 [2021-03-27 14:13:15 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 700/1251] eta: 0:05:50 lr: 0.000379 loss: 3.0798 (3.1999) grad_norm: 1.6332 (nan) time: 0.6253 [2021-03-27 14:13:21 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 710/1251] eta: 0:05:43 lr: 0.000379 loss: 3.0816 (3.1985) grad_norm: 1.6389 (nan) time: 0.6337 [2021-03-27 14:13:28 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 720/1251] eta: 0:05:37 lr: 0.000379 loss: 3.0250 (3.1929) grad_norm: 1.6909 (nan) time: 0.6360 [2021-03-27 14:13:34 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 730/1251] eta: 0:05:31 lr: 0.000379 loss: 2.9206 (3.1914) grad_norm: 1.6705 (nan) time: 0.6343 [2021-03-27 14:13:40 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 740/1251] eta: 0:05:24 lr: 0.000379 loss: 3.3009 (3.1917) grad_norm: 1.6107 (nan) time: 0.6325 [2021-03-27 14:13:47 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 750/1251] eta: 0:05:18 lr: 0.000379 loss: 3.4827 (3.1954) grad_norm: 1.5970 (nan) time: 0.6331 [2021-03-27 14:13:53 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 760/1251] eta: 0:05:11 lr: 0.000379 loss: 3.5040 (3.1948) grad_norm: 1.6076 (nan) time: 0.6356 [2021-03-27 14:13:59 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 770/1251] eta: 0:05:05 lr: 0.000379 loss: 3.2769 (3.1939) grad_norm: 1.5884 (nan) time: 0.6302 [2021-03-27 14:14:06 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 780/1251] eta: 0:04:59 lr: 0.000379 loss: 3.1523 (3.1916) grad_norm: 1.7963 (nan) time: 0.6231 [2021-03-27 14:14:12 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 790/1251] eta: 0:04:52 lr: 0.000379 loss: 3.2614 (3.1934) grad_norm: 1.8049 (nan) time: 0.6311 [2021-03-27 14:14:18 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 800/1251] eta: 0:04:46 lr: 0.000379 loss: 3.3721 (3.1933) grad_norm: 1.6895 (nan) time: 0.6366 [2021-03-27 14:14:25 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 810/1251] eta: 0:04:40 lr: 0.000379 loss: 3.3721 (3.1947) grad_norm: 1.6561 (nan) time: 0.6289 [2021-03-27 14:14:31 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 820/1251] eta: 0:04:33 lr: 0.000379 loss: 3.3923 (3.1973) grad_norm: 1.5675 (nan) time: 0.6276 [2021-03-27 14:14:37 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 830/1251] eta: 0:04:27 lr: 0.000379 loss: 3.2872 (3.1961) grad_norm: 1.6595 (nan) time: 0.6295 [2021-03-27 14:14:44 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 840/1251] eta: 0:04:20 lr: 0.000379 loss: 3.2231 (3.1970) grad_norm: 1.6611 (nan) time: 0.6308 [2021-03-27 14:14:50 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 850/1251] eta: 0:04:14 lr: 0.000378 loss: 3.2290 (3.1970) grad_norm: 1.7249 (nan) time: 0.6355 [2021-03-27 14:14:56 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 860/1251] eta: 0:04:08 lr: 0.000378 loss: 3.2119 (3.1967) grad_norm: 1.6966 (nan) time: 0.6367 [2021-03-27 14:15:03 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 870/1251] eta: 0:04:01 lr: 0.000378 loss: 3.1569 (3.1942) grad_norm: 1.6208 (nan) time: 0.6344 [2021-03-27 14:15:09 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 880/1251] eta: 0:03:55 lr: 0.000378 loss: 3.2568 (3.1960) grad_norm: 1.6731 (nan) time: 0.6300 [2021-03-27 14:15:15 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 890/1251] eta: 0:03:49 lr: 0.000378 loss: 3.4672 (3.1984) grad_norm: 1.7394 (nan) time: 0.6239 [2021-03-27 14:15:22 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 900/1251] eta: 0:03:42 lr: 0.000378 loss: 3.5308 (3.1993) grad_norm: 1.6688 (nan) time: 0.6294 [2021-03-27 14:15:28 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 910/1251] eta: 0:03:36 lr: 0.000378 loss: 3.5308 (3.2000) grad_norm: 1.6773 (nan) time: 0.6310 [2021-03-27 14:15:34 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 920/1251] eta: 0:03:30 lr: 0.000378 loss: 3.3141 (3.2012) grad_norm: 1.6975 (nan) time: 0.6295 [2021-03-27 14:15:40 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 930/1251] eta: 0:03:23 lr: 0.000378 loss: 3.1546 (3.1986) grad_norm: 1.6166 (nan) time: 0.6348 [2021-03-27 14:15:47 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 940/1251] eta: 0:03:17 lr: 0.000378 loss: 3.1817 (3.1997) grad_norm: 1.6490 (nan) time: 0.6326 [2021-03-27 14:15:53 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 950/1251] eta: 0:03:10 lr: 0.000378 loss: 3.2953 (3.2013) grad_norm: 1.7646 (nan) time: 0.6335 [2021-03-27 14:15:59 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 960/1251] eta: 0:03:04 lr: 0.000378 loss: 3.2953 (3.2027) grad_norm: 1.6895 (nan) time: 0.6343 [2021-03-27 14:16:06 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 970/1251] eta: 0:02:58 lr: 0.000378 loss: 3.2561 (3.2013) grad_norm: 1.6613 (nan) time: 0.6301 [2021-03-27 14:16:12 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 980/1251] eta: 0:02:51 lr: 0.000378 loss: 3.1017 (3.1988) grad_norm: 1.6840 (nan) time: 0.6266 [2021-03-27 14:16:18 swin_base_patch4_window7_224] INFO: Epoch: [174] [ 990/1251] eta: 0:02:45 lr: 0.000378 loss: 3.2349 (3.1986) grad_norm: 1.6709 (nan) time: 0.6304 [2021-03-27 14:16:25 swin_base_patch4_window7_224] INFO: Epoch: [174] [1000/1251] eta: 0:02:39 lr: 0.000378 loss: 2.9564 (3.1945) grad_norm: 1.6514 (nan) time: 0.6400 [2021-03-27 14:16:31 swin_base_patch4_window7_224] INFO: Epoch: [174] [1010/1251] eta: 0:02:32 lr: 0.000378 loss: 3.0116 (3.1962) grad_norm: 1.7038 (nan) time: 0.6340 [2021-03-27 14:16:37 swin_base_patch4_window7_224] INFO: Epoch: [174] [1020/1251] eta: 0:02:26 lr: 0.000378 loss: 3.2996 (3.1945) grad_norm: 1.7024 (nan) time: 0.6262 [2021-03-27 14:16:44 swin_base_patch4_window7_224] INFO: Epoch: [174] [1030/1251] eta: 0:02:20 lr: 0.000378 loss: 3.2874 (3.1961) grad_norm: 1.7405 (nan) time: 0.6312 [2021-03-27 14:16:50 swin_base_patch4_window7_224] INFO: Epoch: [174] [1040/1251] eta: 0:02:13 lr: 0.000378 loss: 3.3175 (3.1966) grad_norm: 1.7322 (nan) time: 0.6340 [2021-03-27 14:16:56 swin_base_patch4_window7_224] INFO: Epoch: [174] [1050/1251] eta: 0:02:07 lr: 0.000378 loss: 3.1085 (3.1955) grad_norm: 1.6436 (nan) time: 0.6338 [2021-03-27 14:17:03 swin_base_patch4_window7_224] INFO: Epoch: [174] [1060/1251] eta: 0:02:01 lr: 0.000378 loss: 3.2903 (3.1970) grad_norm: 1.6608 (nan) time: 0.6300 [2021-03-27 14:17:09 swin_base_patch4_window7_224] INFO: Epoch: [174] [1070/1251] eta: 0:01:54 lr: 0.000378 loss: 3.2903 (3.1950) grad_norm: 1.6816 (nan) time: 0.6293 [2021-03-27 14:17:15 swin_base_patch4_window7_224] INFO: Epoch: [174] [1080/1251] eta: 0:01:48 lr: 0.000378 loss: 3.2082 (3.1953) grad_norm: 1.6823 (nan) time: 0.6312 [2021-03-27 14:17:22 swin_base_patch4_window7_224] INFO: Epoch: [174] [1090/1251] eta: 0:01:42 lr: 0.000378 loss: 3.2208 (3.1951) grad_norm: 1.7437 (nan) time: 0.6313 [2021-03-27 14:17:28 swin_base_patch4_window7_224] INFO: Epoch: [174] [1100/1251] eta: 0:01:35 lr: 0.000377 loss: 3.1800 (3.1944) grad_norm: 1.6688 (nan) time: 0.6326 [2021-03-27 14:17:34 swin_base_patch4_window7_224] INFO: Epoch: [174] [1110/1251] eta: 0:01:29 lr: 0.000377 loss: 3.2456 (3.1951) grad_norm: 1.6709 (nan) time: 0.6295 [2021-03-27 14:17:40 swin_base_patch4_window7_224] INFO: Epoch: [174] [1120/1251] eta: 0:01:23 lr: 0.000377 loss: 3.4035 (3.1973) grad_norm: 1.7321 (nan) time: 0.6277 [2021-03-27 14:17:47 swin_base_patch4_window7_224] INFO: Epoch: [174] [1130/1251] eta: 0:01:16 lr: 0.000377 loss: 3.3486 (3.1988) grad_norm: 1.6628 (nan) time: 0.6284 [2021-03-27 14:17:53 swin_base_patch4_window7_224] INFO: Epoch: [174] [1140/1251] eta: 0:01:10 lr: 0.000377 loss: 3.2990 (3.1979) grad_norm: 1.6590 (nan) time: 0.6242 [2021-03-27 14:17:59 swin_base_patch4_window7_224] INFO: Epoch: [174] [1150/1251] eta: 0:01:04 lr: 0.000377 loss: 3.2990 (3.1988) grad_norm: 1.6559 (nan) time: 0.6252 [2021-03-27 14:18:06 swin_base_patch4_window7_224] INFO: Epoch: [174] [1160/1251] eta: 0:00:57 lr: 0.000377 loss: 3.4655 (3.2009) grad_norm: 1.6735 (nan) time: 0.6306 [2021-03-27 14:18:12 swin_base_patch4_window7_224] INFO: Epoch: [174] [1170/1251] eta: 0:00:51 lr: 0.000377 loss: 3.4955 (3.2007) grad_norm: 1.7126 (nan) time: 0.6289 [2021-03-27 14:18:18 swin_base_patch4_window7_224] INFO: Epoch: [174] [1180/1251] eta: 0:00:44 lr: 0.000377 loss: 3.0526 (3.1983) grad_norm: 1.7367 (nan) time: 0.6263 [2021-03-27 14:18:24 swin_base_patch4_window7_224] INFO: Epoch: [174] [1190/1251] eta: 0:00:38 lr: 0.000377 loss: 3.2318 (3.1983) grad_norm: 1.7603 (nan) time: 0.6280 [2021-03-27 14:18:31 swin_base_patch4_window7_224] INFO: Epoch: [174] [1200/1251] eta: 0:00:32 lr: 0.000377 loss: 3.3347 (3.1977) grad_norm: 1.7097 (nan) time: 0.6292 [2021-03-27 14:18:37 swin_base_patch4_window7_224] INFO: Epoch: [174] [1210/1251] eta: 0:00:25 lr: 0.000377 loss: 3.3511 (3.1982) grad_norm: 1.7339 (nan) time: 0.6286 [2021-03-27 14:18:43 swin_base_patch4_window7_224] INFO: Epoch: [174] [1220/1251] eta: 0:00:19 lr: 0.000377 loss: 3.3511 (3.1978) grad_norm: 1.6952 (nan) time: 0.6320 [2021-03-27 14:18:50 swin_base_patch4_window7_224] INFO: Epoch: [174] [1230/1251] eta: 0:00:13 lr: 0.000377 loss: 3.2857 (3.1988) grad_norm: 1.6277 (nan) time: 0.6303 [2021-03-27 14:18:56 swin_base_patch4_window7_224] INFO: Epoch: [174] [1240/1251] eta: 0:00:06 lr: 0.000377 loss: 2.9034 (3.1967) grad_norm: 1.6133 (nan) time: 0.6271 [2021-03-27 14:19:02 swin_base_patch4_window7_224] INFO: Epoch: [174] [1250/1251] eta: 0:00:00 lr: 0.000377 loss: 3.0241 (3.1966) grad_norm: 1.6704 (nan) time: 0.6281 [2021-03-27 14:19:12 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:13 loss: 0.6887 (0.6887) acc1: 82.8125 (82.8125) acc5: 98.4375 (98.4375) [2021-03-27 14:19:14 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9169 (0.9034) acc1: 78.1250 (76.5625) acc5: 95.3125 (95.7386) [2021-03-27 14:19:16 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8433 (0.8815) acc1: 78.1250 (78.1994) acc5: 95.3125 (95.6101) [2021-03-27 14:19:18 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8975 (0.9025) acc1: 78.1250 (78.7802) acc5: 95.3125 (94.9093) [2021-03-27 14:19:19 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8691 (0.8801) acc1: 79.6875 (79.4588) acc5: 95.3125 (95.3887) [2021-03-27 14:19:20 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8200 (0.8818) acc1: 79.6875 (79.5200) acc5: 96.8750 (95.4880) [2021-03-27 14:19:33 swin_base_patch4_window7_224] INFO: * Acc@1 80.166 Acc@5 95.300 loss 0.870 [2021-03-27 14:19:33 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.2% [2021-03-27 14:19:33 swin_base_patch4_window7_224] INFO: Max accuracy: 80.17% [2021-03-27 14:19:38 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 0/1251] eta: 1:34:15 lr: 0.000377 loss: 3.6051 (3.6051) grad_norm: 1.5351 (1.5351) time: 4.5211 [2021-03-27 14:19:44 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 10/1251] eta: 0:20:19 lr: 0.000377 loss: 3.5647 (3.4066) grad_norm: 1.7950 (1.7224) time: 0.9825 [2021-03-27 14:19:50 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 20/1251] eta: 0:16:44 lr: 0.000377 loss: 3.3964 (3.2318) grad_norm: 1.6901 (1.6991) time: 0.6308 [2021-03-27 14:19:56 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 30/1251] eta: 0:15:19 lr: 0.000377 loss: 3.2628 (3.2004) grad_norm: 1.6494 (1.6772) time: 0.6263 [2021-03-27 14:20:03 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 40/1251] eta: 0:14:38 lr: 0.000377 loss: 3.2201 (3.1990) grad_norm: 1.6346 (1.6837) time: 0.6304 [2021-03-27 14:20:09 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 50/1251] eta: 0:14:10 lr: 0.000377 loss: 3.2129 (3.1886) grad_norm: 1.6309 (1.6762) time: 0.6393 [2021-03-27 14:20:15 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 60/1251] eta: 0:13:46 lr: 0.000377 loss: 3.3282 (3.2077) grad_norm: 1.6373 (1.6873) time: 0.6297 [2021-03-27 14:20:22 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 70/1251] eta: 0:13:29 lr: 0.000377 loss: 3.3282 (3.2226) grad_norm: 1.8203 (1.7279) time: 0.6284 [2021-03-27 14:20:28 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 80/1251] eta: 0:13:14 lr: 0.000377 loss: 3.2300 (3.1909) grad_norm: 1.8155 (1.7361) time: 0.6310 [2021-03-27 14:20:34 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 90/1251] eta: 0:13:00 lr: 0.000377 loss: 3.2842 (3.2122) grad_norm: 1.6329 (1.7198) time: 0.6258 [2021-03-27 14:20:41 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 100/1251] eta: 0:12:49 lr: 0.000376 loss: 3.4337 (3.2328) grad_norm: 1.6329 (1.7297) time: 0.6287 [2021-03-27 14:20:47 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 110/1251] eta: 0:12:39 lr: 0.000376 loss: 3.2899 (3.2180) grad_norm: 1.7266 (1.7355) time: 0.6340 [2021-03-27 14:20:53 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 120/1251] eta: 0:12:29 lr: 0.000376 loss: 2.9956 (3.2108) grad_norm: 1.7275 (1.7373) time: 0.6342 [2021-03-27 14:21:00 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 130/1251] eta: 0:12:20 lr: 0.000376 loss: 2.9956 (3.2035) grad_norm: 1.7571 (1.7450) time: 0.6297 [2021-03-27 14:21:06 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 140/1251] eta: 0:12:11 lr: 0.000376 loss: 2.9689 (3.1859) grad_norm: 1.7801 (1.7413) time: 0.6322 [2021-03-27 14:21:12 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 150/1251] eta: 0:12:02 lr: 0.000376 loss: 3.1431 (3.1818) grad_norm: 1.8114 (1.7588) time: 0.6322 [2021-03-27 14:21:19 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 160/1251] eta: 0:11:54 lr: 0.000376 loss: 3.1797 (3.1845) grad_norm: 1.8172 (1.7631) time: 0.6296 [2021-03-27 14:21:25 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 170/1251] eta: 0:11:46 lr: 0.000376 loss: 3.2540 (3.1894) grad_norm: 1.7360 (1.7635) time: 0.6354 [2021-03-27 14:21:31 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 180/1251] eta: 0:11:39 lr: 0.000376 loss: 3.4682 (3.1997) grad_norm: 1.7452 (1.7599) time: 0.6372 [2021-03-27 14:21:37 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 190/1251] eta: 0:11:31 lr: 0.000376 loss: 3.1548 (3.1759) grad_norm: 1.7452 (1.7731) time: 0.6305 [2021-03-27 14:21:44 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 200/1251] eta: 0:11:23 lr: 0.000376 loss: 3.0287 (3.1809) grad_norm: 1.8260 (1.7777) time: 0.6252 [2021-03-27 14:21:50 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 210/1251] eta: 0:11:15 lr: 0.000376 loss: 3.2228 (3.1831) grad_norm: 1.8260 (1.7788) time: 0.6264 [2021-03-27 14:21:56 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 220/1251] eta: 0:11:08 lr: 0.000376 loss: 2.9760 (3.1761) grad_norm: 1.6787 (1.7740) time: 0.6264 [2021-03-27 14:22:03 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 230/1251] eta: 0:11:00 lr: 0.000376 loss: 2.9414 (3.1647) grad_norm: 1.6745 (1.7724) time: 0.6251 [2021-03-27 14:22:09 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 240/1251] eta: 0:10:53 lr: 0.000376 loss: 2.8521 (3.1614) grad_norm: 1.6549 (1.7740) time: 0.6243 [2021-03-27 14:22:15 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 250/1251] eta: 0:10:46 lr: 0.000376 loss: 3.2782 (3.1599) grad_norm: 1.7122 (1.7736) time: 0.6264 [2021-03-27 14:22:21 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 260/1251] eta: 0:10:39 lr: 0.000376 loss: 3.3630 (3.1571) grad_norm: 1.7906 (1.7793) time: 0.6297 [2021-03-27 14:22:28 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 270/1251] eta: 0:10:32 lr: 0.000376 loss: 3.3630 (3.1568) grad_norm: 1.7906 (1.7808) time: 0.6301 [2021-03-27 14:22:34 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 280/1251] eta: 0:10:25 lr: 0.000376 loss: 3.4084 (3.1712) grad_norm: 1.7764 (1.7862) time: 0.6282 [2021-03-27 14:22:40 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 290/1251] eta: 0:10:18 lr: 0.000376 loss: 3.2459 (3.1623) grad_norm: 1.7324 (1.7872) time: 0.6306 [2021-03-27 14:22:47 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 300/1251] eta: 0:10:11 lr: 0.000376 loss: 3.3447 (3.1751) grad_norm: 1.7388 (1.7862) time: 0.6321 [2021-03-27 14:22:53 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 310/1251] eta: 0:10:04 lr: 0.000376 loss: 3.4537 (3.1743) grad_norm: 1.8179 (1.7903) time: 0.6275 [2021-03-27 14:22:59 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 320/1251] eta: 0:09:57 lr: 0.000376 loss: 3.3298 (3.1769) grad_norm: 1.8313 (1.7941) time: 0.6254 [2021-03-27 14:23:05 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 330/1251] eta: 0:09:50 lr: 0.000376 loss: 3.3122 (3.1747) grad_norm: 1.7916 (1.7920) time: 0.6279 [2021-03-27 14:23:12 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 340/1251] eta: 0:09:44 lr: 0.000376 loss: 3.1088 (3.1688) grad_norm: 1.7586 (1.7926) time: 0.6298 [2021-03-27 14:23:18 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 350/1251] eta: 0:09:37 lr: 0.000375 loss: 3.2700 (3.1705) grad_norm: 1.7448 (1.7915) time: 0.6368 [2021-03-27 14:23:24 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 360/1251] eta: 0:09:30 lr: 0.000375 loss: 3.1189 (3.1617) grad_norm: 1.6958 (1.7890) time: 0.6348 [2021-03-27 14:23:31 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 370/1251] eta: 0:09:24 lr: 0.000375 loss: 2.8331 (3.1608) grad_norm: 1.6090 (1.7854) time: 0.6274 [2021-03-27 14:23:37 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 380/1251] eta: 0:09:17 lr: 0.000375 loss: 3.0546 (3.1580) grad_norm: 1.6003 (1.7836) time: 0.6330 [2021-03-27 14:23:43 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 390/1251] eta: 0:09:10 lr: 0.000375 loss: 3.1906 (3.1638) grad_norm: 1.6417 (1.7816) time: 0.6287 [2021-03-27 14:23:50 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 400/1251] eta: 0:09:04 lr: 0.000375 loss: 3.4596 (3.1619) grad_norm: 1.6824 (1.7812) time: 0.6242 [2021-03-27 14:23:56 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 410/1251] eta: 0:08:57 lr: 0.000375 loss: 3.0248 (3.1635) grad_norm: 1.6939 (1.7827) time: 0.6289 [2021-03-27 14:24:02 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 420/1251] eta: 0:08:51 lr: 0.000375 loss: 3.3411 (3.1683) grad_norm: 1.7657 (1.7846) time: 0.6286 [2021-03-27 14:24:09 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 430/1251] eta: 0:08:44 lr: 0.000375 loss: 3.3308 (3.1672) grad_norm: 1.8269 (1.7864) time: 0.6343 [2021-03-27 14:24:15 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 440/1251] eta: 0:08:38 lr: 0.000375 loss: 2.9629 (3.1622) grad_norm: 1.7784 (1.7837) time: 0.6353 [2021-03-27 14:24:21 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 450/1251] eta: 0:08:31 lr: 0.000375 loss: 2.9853 (3.1632) grad_norm: 1.7147 (1.7858) time: 0.6309 [2021-03-27 14:24:28 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 460/1251] eta: 0:08:25 lr: 0.000375 loss: 3.2333 (3.1664) grad_norm: 1.7562 (1.7849) time: 0.6339 [2021-03-27 14:24:34 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 470/1251] eta: 0:08:18 lr: 0.000375 loss: 3.3727 (3.1712) grad_norm: 1.7562 (1.7833) time: 0.6289 [2021-03-27 14:24:40 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 480/1251] eta: 0:08:12 lr: 0.000375 loss: 3.3942 (3.1747) grad_norm: 1.6849 (1.7812) time: 0.6329 [2021-03-27 14:24:46 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 490/1251] eta: 0:08:05 lr: 0.000375 loss: 2.9926 (3.1652) grad_norm: 1.6492 (1.7785) time: 0.6338 [2021-03-27 14:24:53 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 500/1251] eta: 0:07:58 lr: 0.000375 loss: 3.0390 (3.1680) grad_norm: 1.5823 (1.7771) time: 0.6231 [2021-03-27 14:24:59 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 510/1251] eta: 0:07:52 lr: 0.000375 loss: 3.1366 (3.1621) grad_norm: 1.6310 (1.7762) time: 0.6280 [2021-03-27 14:25:05 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 520/1251] eta: 0:07:46 lr: 0.000375 loss: 3.0316 (3.1614) grad_norm: 1.6882 (1.7770) time: 0.6351 [2021-03-27 14:25:12 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 530/1251] eta: 0:07:39 lr: 0.000375 loss: 3.1688 (3.1617) grad_norm: 1.6895 (1.7750) time: 0.6333 [2021-03-27 14:25:18 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 540/1251] eta: 0:07:33 lr: 0.000375 loss: 3.3879 (3.1679) grad_norm: 1.6895 (1.7779) time: 0.6279 [2021-03-27 14:25:24 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 550/1251] eta: 0:07:27 lr: 0.000375 loss: 3.4439 (3.1693) grad_norm: 1.7871 (1.7780) time: 0.6409 [2021-03-27 14:25:31 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 560/1251] eta: 0:07:20 lr: 0.000375 loss: 3.4439 (3.1695) grad_norm: 1.7539 (1.7768) time: 0.6410 [2021-03-27 14:25:37 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 570/1251] eta: 0:07:14 lr: 0.000375 loss: 3.4419 (3.1722) grad_norm: 1.6646 (1.7752) time: 0.6274 [2021-03-27 14:25:43 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 580/1251] eta: 0:07:07 lr: 0.000375 loss: 3.4263 (3.1767) grad_norm: 1.7895 (1.7784) time: 0.6299 [2021-03-27 14:25:50 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 590/1251] eta: 0:07:01 lr: 0.000375 loss: 3.5603 (3.1833) grad_norm: 1.7703 (1.7768) time: 0.6365 [2021-03-27 14:25:56 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 600/1251] eta: 0:06:54 lr: 0.000374 loss: 3.3767 (3.1810) grad_norm: 1.6254 (1.7747) time: 0.6400 [2021-03-27 14:26:02 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 610/1251] eta: 0:06:48 lr: 0.000374 loss: 3.2087 (3.1813) grad_norm: 1.6421 (1.7724) time: 0.6294 [2021-03-27 14:26:09 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 620/1251] eta: 0:06:41 lr: 0.000374 loss: 3.3449 (3.1840) grad_norm: 1.6767 (1.7730) time: 0.6271 [2021-03-27 14:26:15 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 630/1251] eta: 0:06:35 lr: 0.000374 loss: 3.1621 (3.1813) grad_norm: 1.6929 (1.7728) time: 0.6323 [2021-03-27 14:26:21 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 640/1251] eta: 0:06:29 lr: 0.000374 loss: 3.0817 (3.1828) grad_norm: 1.6110 (1.7699) time: 0.6301 [2021-03-27 14:26:28 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 650/1251] eta: 0:06:22 lr: 0.000374 loss: 3.2513 (3.1811) grad_norm: 1.5942 (1.7690) time: 0.6310 [2021-03-27 14:26:34 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 660/1251] eta: 0:06:16 lr: 0.000374 loss: 3.0202 (3.1773) grad_norm: 1.6643 (1.7683) time: 0.6369 [2021-03-27 14:26:40 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 670/1251] eta: 0:06:09 lr: 0.000374 loss: 3.0482 (3.1773) grad_norm: 1.6684 (1.7666) time: 0.6337 [2021-03-27 14:26:47 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 680/1251] eta: 0:06:03 lr: 0.000374 loss: 3.4034 (3.1809) grad_norm: 1.6886 (1.7672) time: 0.6320 [2021-03-27 14:26:53 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 690/1251] eta: 0:05:57 lr: 0.000374 loss: 3.3437 (3.1815) grad_norm: 1.7173 (1.7665) time: 0.6362 [2021-03-27 14:26:59 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 700/1251] eta: 0:05:50 lr: 0.000374 loss: 3.2335 (3.1785) grad_norm: 1.7173 (1.7668) time: 0.6322 [2021-03-27 14:27:06 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 710/1251] eta: 0:05:44 lr: 0.000374 loss: 3.0044 (3.1761) grad_norm: 1.7385 (1.7657) time: 0.6282 [2021-03-27 14:27:12 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 720/1251] eta: 0:05:37 lr: 0.000374 loss: 3.0889 (3.1761) grad_norm: 1.7385 (1.7670) time: 0.6277 [2021-03-27 14:27:18 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 730/1251] eta: 0:05:31 lr: 0.000374 loss: 3.1402 (3.1750) grad_norm: 1.8276 (1.7692) time: 0.6310 [2021-03-27 14:27:25 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 740/1251] eta: 0:05:25 lr: 0.000374 loss: 3.3876 (3.1758) grad_norm: 1.7946 (1.7705) time: 0.6355 [2021-03-27 14:27:31 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 750/1251] eta: 0:05:18 lr: 0.000374 loss: 3.4430 (3.1771) grad_norm: 1.7292 (1.7709) time: 0.6321 [2021-03-27 14:27:37 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 760/1251] eta: 0:05:12 lr: 0.000374 loss: 3.3762 (3.1774) grad_norm: 1.6623 (1.7697) time: 0.6333 [2021-03-27 14:27:44 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 770/1251] eta: 0:05:05 lr: 0.000374 loss: 3.0832 (3.1734) grad_norm: 1.6089 (1.7674) time: 0.6329 [2021-03-27 14:27:50 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 780/1251] eta: 0:04:59 lr: 0.000374 loss: 3.0988 (3.1754) grad_norm: 1.6632 (1.7661) time: 0.6308 [2021-03-27 14:27:56 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 790/1251] eta: 0:04:53 lr: 0.000374 loss: 3.1909 (3.1745) grad_norm: 1.6728 (1.7670) time: 0.6342 [2021-03-27 14:28:03 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 800/1251] eta: 0:04:46 lr: 0.000374 loss: 3.1847 (3.1763) grad_norm: 1.8011 (1.7684) time: 0.6369 [2021-03-27 14:28:09 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 810/1251] eta: 0:04:40 lr: 0.000374 loss: 3.1432 (3.1738) grad_norm: 1.7533 (1.7689) time: 0.6355 [2021-03-27 14:28:15 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 820/1251] eta: 0:04:34 lr: 0.000374 loss: 3.2006 (3.1743) grad_norm: 1.7982 (1.7695) time: 0.6291 [2021-03-27 14:28:21 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 830/1251] eta: 0:04:27 lr: 0.000374 loss: 3.2736 (3.1748) grad_norm: 1.7551 (1.7693) time: 0.6267 [2021-03-27 14:28:28 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 840/1251] eta: 0:04:21 lr: 0.000374 loss: 3.2264 (3.1726) grad_norm: 1.6818 (1.7680) time: 0.6254 [2021-03-27 14:28:34 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 850/1251] eta: 0:04:14 lr: 0.000373 loss: 3.2306 (3.1725) grad_norm: 1.6649 (1.7674) time: 0.6303 [2021-03-27 14:28:40 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 860/1251] eta: 0:04:08 lr: 0.000373 loss: 3.3408 (3.1755) grad_norm: 1.7692 (1.7686) time: 0.6344 [2021-03-27 14:28:47 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 870/1251] eta: 0:04:02 lr: 0.000373 loss: 3.2604 (3.1751) grad_norm: 1.7426 (1.7677) time: 0.6344 [2021-03-27 14:28:53 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 880/1251] eta: 0:03:55 lr: 0.000373 loss: 3.3044 (3.1763) grad_norm: 1.7026 (1.7672) time: 0.6381 [2021-03-27 14:28:59 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 890/1251] eta: 0:03:49 lr: 0.000373 loss: 3.3240 (3.1765) grad_norm: 1.6241 (1.7655) time: 0.6332 [2021-03-27 14:29:06 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 900/1251] eta: 0:03:43 lr: 0.000373 loss: 3.1168 (3.1760) grad_norm: 1.6343 (1.7640) time: 0.6307 [2021-03-27 14:29:12 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 910/1251] eta: 0:03:36 lr: 0.000373 loss: 3.0231 (3.1736) grad_norm: 1.6658 (1.7636) time: 0.6326 [2021-03-27 14:29:18 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 920/1251] eta: 0:03:30 lr: 0.000373 loss: 3.1464 (3.1738) grad_norm: 1.6819 (1.7627) time: 0.6281 [2021-03-27 14:29:25 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 930/1251] eta: 0:03:23 lr: 0.000373 loss: 3.1916 (3.1731) grad_norm: 1.6758 (1.7652) time: 0.6285 [2021-03-27 14:29:31 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 940/1251] eta: 0:03:17 lr: 0.000373 loss: 3.0488 (3.1724) grad_norm: 1.7233 (1.7658) time: 0.6283 [2021-03-27 14:29:37 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 950/1251] eta: 0:03:11 lr: 0.000373 loss: 3.0488 (3.1708) grad_norm: 1.7233 (1.7650) time: 0.6311 [2021-03-27 14:29:44 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 960/1251] eta: 0:03:04 lr: 0.000373 loss: 3.1480 (3.1693) grad_norm: 1.6881 (1.7652) time: 0.6352 [2021-03-27 14:29:50 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 970/1251] eta: 0:02:58 lr: 0.000373 loss: 3.2382 (3.1700) grad_norm: 1.6928 (1.7644) time: 0.6310 [2021-03-27 14:29:56 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 980/1251] eta: 0:02:52 lr: 0.000373 loss: 3.2382 (3.1710) grad_norm: 1.6928 (1.7640) time: 0.6248 [2021-03-27 14:30:02 swin_base_patch4_window7_224] INFO: Epoch: [175] [ 990/1251] eta: 0:02:45 lr: 0.000373 loss: 3.1135 (3.1687) grad_norm: 1.7329 (1.7648) time: 0.6226 [2021-03-27 14:30:09 swin_base_patch4_window7_224] INFO: Epoch: [175] [1000/1251] eta: 0:02:39 lr: 0.000373 loss: 3.1135 (3.1679) grad_norm: 1.7329 (1.7640) time: 0.6256 [2021-03-27 14:30:15 swin_base_patch4_window7_224] INFO: Epoch: [175] [1010/1251] eta: 0:02:32 lr: 0.000373 loss: 3.1837 (3.1676) grad_norm: 1.7184 (1.7640) time: 0.6277 [2021-03-27 14:30:21 swin_base_patch4_window7_224] INFO: Epoch: [175] [1020/1251] eta: 0:02:26 lr: 0.000373 loss: 3.2813 (3.1702) grad_norm: 1.8407 (1.7661) time: 0.6295 [2021-03-27 14:30:27 swin_base_patch4_window7_224] INFO: Epoch: [175] [1030/1251] eta: 0:02:20 lr: 0.000373 loss: 3.5031 (3.1708) grad_norm: 1.9388 (1.7669) time: 0.6294 [2021-03-27 14:30:34 swin_base_patch4_window7_224] INFO: Epoch: [175] [1040/1251] eta: 0:02:13 lr: 0.000373 loss: 3.0568 (3.1691) grad_norm: 1.8236 (1.7692) time: 0.6281 [2021-03-27 14:30:40 swin_base_patch4_window7_224] INFO: Epoch: [175] [1050/1251] eta: 0:02:07 lr: 0.000373 loss: 3.0568 (3.1683) grad_norm: 1.7971 (1.7696) time: 0.6339 [2021-03-27 14:30:47 swin_base_patch4_window7_224] INFO: Epoch: [175] [1060/1251] eta: 0:02:01 lr: 0.000373 loss: 3.1023 (3.1687) grad_norm: 1.7506 (1.7692) time: 0.6373 [2021-03-27 14:30:53 swin_base_patch4_window7_224] INFO: Epoch: [175] [1070/1251] eta: 0:01:54 lr: 0.000373 loss: 3.3234 (3.1685) grad_norm: 1.7095 (1.7684) time: 0.6312 [2021-03-27 14:30:59 swin_base_patch4_window7_224] INFO: Epoch: [175] [1080/1251] eta: 0:01:48 lr: 0.000373 loss: 3.1582 (3.1675) grad_norm: 1.7049 (1.7681) time: 0.6263 [2021-03-27 14:31:05 swin_base_patch4_window7_224] INFO: Epoch: [175] [1090/1251] eta: 0:01:42 lr: 0.000373 loss: 3.3395 (3.1694) grad_norm: 1.7190 (1.7677) time: 0.6291 [2021-03-27 14:31:12 swin_base_patch4_window7_224] INFO: Epoch: [175] [1100/1251] eta: 0:01:35 lr: 0.000372 loss: 3.3501 (3.1701) grad_norm: 1.7190 (1.7680) time: 0.6265 [2021-03-27 14:31:18 swin_base_patch4_window7_224] INFO: Epoch: [175] [1110/1251] eta: 0:01:29 lr: 0.000372 loss: 3.2244 (3.1704) grad_norm: 1.6244 (1.7676) time: 0.6193 [2021-03-27 14:31:24 swin_base_patch4_window7_224] INFO: Epoch: [175] [1120/1251] eta: 0:01:23 lr: 0.000372 loss: 3.2244 (3.1707) grad_norm: 1.6244 (1.7681) time: 0.6213 [2021-03-27 14:31:30 swin_base_patch4_window7_224] INFO: Epoch: [175] [1130/1251] eta: 0:01:16 lr: 0.000372 loss: 3.2541 (3.1714) grad_norm: 1.6496 (1.7683) time: 0.6326 [2021-03-27 14:31:37 swin_base_patch4_window7_224] INFO: Epoch: [175] [1140/1251] eta: 0:01:10 lr: 0.000372 loss: 3.2676 (3.1711) grad_norm: 1.8642 (1.7707) time: 0.6321 [2021-03-27 14:31:43 swin_base_patch4_window7_224] INFO: Epoch: [175] [1150/1251] eta: 0:01:04 lr: 0.000372 loss: 3.1950 (3.1706) grad_norm: 1.6586 (1.7699) time: 0.6305 [2021-03-27 14:31:49 swin_base_patch4_window7_224] INFO: Epoch: [175] [1160/1251] eta: 0:00:57 lr: 0.000372 loss: 3.1335 (3.1691) grad_norm: 1.7709 (1.7719) time: 0.6354 [2021-03-27 14:31:56 swin_base_patch4_window7_224] INFO: Epoch: [175] [1170/1251] eta: 0:00:51 lr: 0.000372 loss: 2.9624 (3.1683) grad_norm: 1.7095 (1.7712) time: 0.6370 [2021-03-27 14:32:02 swin_base_patch4_window7_224] INFO: Epoch: [175] [1180/1251] eta: 0:00:45 lr: 0.000372 loss: 3.2060 (3.1678) grad_norm: 1.6411 (1.7709) time: 0.6319 [2021-03-27 14:32:08 swin_base_patch4_window7_224] INFO: Epoch: [175] [1190/1251] eta: 0:00:38 lr: 0.000372 loss: 3.3198 (3.1684) grad_norm: 1.7109 (1.7712) time: 0.6259 [2021-03-27 14:32:15 swin_base_patch4_window7_224] INFO: Epoch: [175] [1200/1251] eta: 0:00:32 lr: 0.000372 loss: 3.2572 (3.1689) grad_norm: 1.7963 (1.7711) time: 0.6282 [2021-03-27 14:32:21 swin_base_patch4_window7_224] INFO: Epoch: [175] [1210/1251] eta: 0:00:25 lr: 0.000372 loss: 3.1524 (3.1664) grad_norm: 1.6946 (1.7720) time: 0.6286 [2021-03-27 14:32:27 swin_base_patch4_window7_224] INFO: Epoch: [175] [1220/1251] eta: 0:00:19 lr: 0.000372 loss: 2.7567 (3.1654) grad_norm: 1.6946 (1.7715) time: 0.6294 [2021-03-27 14:32:33 swin_base_patch4_window7_224] INFO: Epoch: [175] [1230/1251] eta: 0:00:13 lr: 0.000372 loss: 3.1016 (3.1660) grad_norm: 1.6521 (1.7709) time: 0.6277 [2021-03-27 14:32:40 swin_base_patch4_window7_224] INFO: Epoch: [175] [1240/1251] eta: 0:00:06 lr: 0.000372 loss: 3.4230 (3.1657) grad_norm: 1.6451 (1.7699) time: 0.6275 [2021-03-27 14:32:46 swin_base_patch4_window7_224] INFO: Epoch: [175] [1250/1251] eta: 0:00:00 lr: 0.000372 loss: 3.3838 (3.1666) grad_norm: 1.6336 (1.7693) time: 0.6263 [2021-03-27 14:34:03 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 1.1767 (1.1767) acc1: 71.8750 (71.8750) acc5: 96.8750 (96.8750) [2021-03-27 14:34:04 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.9210 (0.9074) acc1: 78.1250 (78.6932) acc5: 95.3125 (96.0227) [2021-03-27 14:34:05 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9110 (0.9271) acc1: 78.1250 (77.8274) acc5: 95.3125 (95.2381) [2021-03-27 14:34:07 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8767 (0.9152) acc1: 78.1250 (77.9738) acc5: 95.3125 (95.3125) [2021-03-27 14:34:08 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8256 (0.8801) acc1: 79.6875 (78.9634) acc5: 95.3125 (95.5030) [2021-03-27 14:34:09 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7602 (0.8665) acc1: 81.2500 (79.2960) acc5: 96.2264 (95.6800) [2021-03-27 14:34:19 swin_base_patch4_window7_224] INFO: * Acc@1 80.234 Acc@5 95.374 loss 0.848 [2021-03-27 14:34:19 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.2% [2021-03-27 14:34:19 swin_base_patch4_window7_224] INFO: Max accuracy: 80.23% [2021-03-27 14:34:23 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 0/1251] eta: 1:28:20 lr: 0.000372 loss: 3.2320 (3.2320) grad_norm: 1.6159 (1.6159) time: 4.2370 [2021-03-27 14:34:29 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 10/1251] eta: 0:19:58 lr: 0.000372 loss: 3.2320 (3.1000) grad_norm: 1.7144 (1.7865) time: 0.9661 [2021-03-27 14:34:36 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 20/1251] eta: 0:16:33 lr: 0.000372 loss: 3.1935 (3.1582) grad_norm: 1.7769 (1.7904) time: 0.6356 [2021-03-27 14:34:42 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 30/1251] eta: 0:15:21 lr: 0.000372 loss: 3.0637 (3.0780) grad_norm: 1.6618 (1.7543) time: 0.6390 [2021-03-27 14:34:48 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 40/1251] eta: 0:14:39 lr: 0.000372 loss: 3.0938 (3.1619) grad_norm: 1.6820 (1.7825) time: 0.6415 [2021-03-27 14:34:55 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 50/1251] eta: 0:14:07 lr: 0.000372 loss: 3.4174 (3.1767) grad_norm: 1.6942 (1.7677) time: 0.6286 [2021-03-27 14:35:01 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 60/1251] eta: 0:13:47 lr: 0.000372 loss: 3.2786 (3.1747) grad_norm: 1.6193 (1.7445) time: 0.6313 [2021-03-27 14:35:07 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 70/1251] eta: 0:13:30 lr: 0.000372 loss: 3.3178 (3.1939) grad_norm: 1.7062 (1.7523) time: 0.6387 [2021-03-27 14:35:14 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 80/1251] eta: 0:13:15 lr: 0.000372 loss: 3.2360 (3.1858) grad_norm: 1.8383 (1.8247) time: 0.6306 [2021-03-27 14:35:20 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 90/1251] eta: 0:13:02 lr: 0.000372 loss: 3.1294 (3.1788) grad_norm: 1.9120 (1.8326) time: 0.6283 [2021-03-27 14:35:26 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 100/1251] eta: 0:12:49 lr: 0.000371 loss: 3.2576 (3.1867) grad_norm: 1.7955 (1.8398) time: 0.6264 [2021-03-27 14:35:32 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 110/1251] eta: 0:12:37 lr: 0.000371 loss: 3.0698 (3.1663) grad_norm: 1.6864 (1.8264) time: 0.6208 [2021-03-27 14:35:39 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 120/1251] eta: 0:12:29 lr: 0.000371 loss: 3.0698 (3.1632) grad_norm: 1.6864 (1.8200) time: 0.6297 [2021-03-27 14:35:45 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 130/1251] eta: 0:12:20 lr: 0.000371 loss: 3.3956 (3.1779) grad_norm: 1.7163 (1.8078) time: 0.6395 [2021-03-27 14:35:51 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 140/1251] eta: 0:12:10 lr: 0.000371 loss: 3.3443 (3.1805) grad_norm: 1.6604 (1.7993) time: 0.6312 [2021-03-27 14:35:58 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 150/1251] eta: 0:12:02 lr: 0.000371 loss: 3.1105 (3.1735) grad_norm: 1.6092 (1.7852) time: 0.6264 [2021-03-27 14:36:04 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 160/1251] eta: 0:11:53 lr: 0.000371 loss: 2.9472 (3.1661) grad_norm: 1.6092 (1.7795) time: 0.6263 [2021-03-27 14:36:10 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 170/1251] eta: 0:11:45 lr: 0.000371 loss: 3.1811 (3.1617) grad_norm: 1.6515 (1.7804) time: 0.6270 [2021-03-27 14:36:17 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 180/1251] eta: 0:11:37 lr: 0.000371 loss: 3.4138 (3.1668) grad_norm: 1.8090 (1.7824) time: 0.6299 [2021-03-27 14:36:23 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 190/1251] eta: 0:11:29 lr: 0.000371 loss: 3.3571 (3.1662) grad_norm: 1.7303 (1.7789) time: 0.6300 [2021-03-27 14:36:29 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 200/1251] eta: 0:11:22 lr: 0.000371 loss: 3.2149 (3.1654) grad_norm: 1.5955 (1.7731) time: 0.6342 [2021-03-27 14:36:35 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 210/1251] eta: 0:11:15 lr: 0.000371 loss: 3.1088 (3.1631) grad_norm: 1.6763 (1.7744) time: 0.6334 [2021-03-27 14:36:42 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 220/1251] eta: 0:11:07 lr: 0.000371 loss: 3.0950 (3.1596) grad_norm: 1.7213 (1.7777) time: 0.6301 [2021-03-27 14:36:48 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 230/1251] eta: 0:11:00 lr: 0.000371 loss: 3.1996 (3.1672) grad_norm: 1.6906 (1.7727) time: 0.6286 [2021-03-27 14:36:54 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 240/1251] eta: 0:10:53 lr: 0.000371 loss: 3.0932 (3.1569) grad_norm: 1.6990 (1.7727) time: 0.6263 [2021-03-27 14:37:01 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 250/1251] eta: 0:10:46 lr: 0.000371 loss: 2.9773 (3.1515) grad_norm: 1.7835 (1.7748) time: 0.6315 [2021-03-27 14:37:07 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 260/1251] eta: 0:10:39 lr: 0.000371 loss: 3.2298 (3.1604) grad_norm: 1.7771 (1.7785) time: 0.6343 [2021-03-27 14:37:13 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 270/1251] eta: 0:10:32 lr: 0.000371 loss: 3.3272 (3.1686) grad_norm: 1.7166 (1.7770) time: 0.6343 [2021-03-27 14:37:20 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 280/1251] eta: 0:10:25 lr: 0.000371 loss: 3.2976 (3.1707) grad_norm: 1.6757 (1.7786) time: 0.6353 [2021-03-27 14:37:26 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 290/1251] eta: 0:10:18 lr: 0.000371 loss: 3.0947 (3.1674) grad_norm: 1.6586 (1.7737) time: 0.6300 [2021-03-27 14:37:32 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 300/1251] eta: 0:10:11 lr: 0.000371 loss: 2.9372 (3.1594) grad_norm: 1.5836 (1.7709) time: 0.6267 [2021-03-27 14:37:39 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 310/1251] eta: 0:10:05 lr: 0.000371 loss: 3.0334 (3.1567) grad_norm: 1.6021 (1.7691) time: 0.6310 [2021-03-27 14:37:45 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 320/1251] eta: 0:09:58 lr: 0.000371 loss: 3.3892 (3.1652) grad_norm: 1.6544 (1.7667) time: 0.6298 [2021-03-27 14:37:51 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 330/1251] eta: 0:09:51 lr: 0.000371 loss: 3.4372 (3.1622) grad_norm: 1.6021 (1.7642) time: 0.6222 [2021-03-27 14:37:57 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 340/1251] eta: 0:09:44 lr: 0.000371 loss: 3.5299 (3.1692) grad_norm: 1.5677 (1.7593) time: 0.6254 [2021-03-27 14:38:04 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 350/1251] eta: 0:09:37 lr: 0.000370 loss: 3.3286 (3.1716) grad_norm: 1.5999 (1.7565) time: 0.6281 [2021-03-27 14:38:10 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 360/1251] eta: 0:09:30 lr: 0.000370 loss: 3.3286 (3.1755) grad_norm: 1.6079 (1.7546) time: 0.6252 [2021-03-27 14:38:16 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 370/1251] eta: 0:09:24 lr: 0.000370 loss: 3.4475 (3.1826) grad_norm: 1.7016 (1.7551) time: 0.6318 [2021-03-27 14:38:23 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 380/1251] eta: 0:09:17 lr: 0.000370 loss: 3.4200 (3.1798) grad_norm: 1.6731 (1.7541) time: 0.6317 [2021-03-27 14:38:29 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 390/1251] eta: 0:09:10 lr: 0.000370 loss: 3.3686 (3.1834) grad_norm: 1.6731 (1.7534) time: 0.6250 [2021-03-27 14:38:35 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 400/1251] eta: 0:09:04 lr: 0.000370 loss: 3.4098 (3.1822) grad_norm: 1.7489 (1.7575) time: 0.6268 [2021-03-27 14:38:42 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 410/1251] eta: 0:08:57 lr: 0.000370 loss: 3.1304 (3.1803) grad_norm: 1.6769 (1.7562) time: 0.6374 [2021-03-27 14:38:48 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 420/1251] eta: 0:08:51 lr: 0.000370 loss: 3.1205 (3.1808) grad_norm: 1.6403 (1.7546) time: 0.6404 [2021-03-27 14:38:54 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 430/1251] eta: 0:08:44 lr: 0.000370 loss: 3.2120 (3.1785) grad_norm: 1.6081 (1.7527) time: 0.6311 [2021-03-27 14:39:00 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 440/1251] eta: 0:08:38 lr: 0.000370 loss: 3.2941 (3.1817) grad_norm: 1.6603 (1.7529) time: 0.6272 [2021-03-27 14:39:07 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 450/1251] eta: 0:08:31 lr: 0.000370 loss: 3.4022 (3.1856) grad_norm: 1.7143 (1.7537) time: 0.6317 [2021-03-27 14:39:13 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 460/1251] eta: 0:08:25 lr: 0.000370 loss: 3.4022 (3.1820) grad_norm: 1.7196 (1.7551) time: 0.6286 [2021-03-27 14:39:19 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 470/1251] eta: 0:08:18 lr: 0.000370 loss: 3.2042 (3.1834) grad_norm: 1.8050 (1.7561) time: 0.6202 [2021-03-27 14:39:25 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 480/1251] eta: 0:08:11 lr: 0.000370 loss: 3.2042 (3.1799) grad_norm: 1.6562 (1.7541) time: 0.6214 [2021-03-27 14:39:32 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 490/1251] eta: 0:08:05 lr: 0.000370 loss: 3.2674 (3.1865) grad_norm: 1.6787 (1.7545) time: 0.6270 [2021-03-27 14:39:38 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 500/1251] eta: 0:07:58 lr: 0.000370 loss: 3.2674 (3.1879) grad_norm: 1.6540 (1.7520) time: 0.6279 [2021-03-27 14:39:44 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 510/1251] eta: 0:07:52 lr: 0.000370 loss: 2.9167 (3.1799) grad_norm: 1.6494 (1.7505) time: 0.6259 [2021-03-27 14:39:51 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 520/1251] eta: 0:07:45 lr: 0.000370 loss: 2.5690 (3.1746) grad_norm: 1.6450 (1.7490) time: 0.6321 [2021-03-27 14:39:57 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 530/1251] eta: 0:07:39 lr: 0.000370 loss: 3.1255 (3.1748) grad_norm: 1.6331 (1.7484) time: 0.6343 [2021-03-27 14:40:03 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 540/1251] eta: 0:07:33 lr: 0.000370 loss: 3.3898 (3.1804) grad_norm: 1.5967 (1.7471) time: 0.6375 [2021-03-27 14:40:10 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 550/1251] eta: 0:07:26 lr: 0.000370 loss: 3.4312 (3.1822) grad_norm: 1.5967 (1.7477) time: 0.6448 [2021-03-27 14:40:16 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 560/1251] eta: 0:07:20 lr: 0.000370 loss: 3.0092 (3.1771) grad_norm: 1.7841 (1.7490) time: 0.6472 [2021-03-27 14:40:23 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 570/1251] eta: 0:07:14 lr: 0.000370 loss: 3.0502 (3.1769) grad_norm: 1.8006 (1.7505) time: 0.6380 [2021-03-27 14:40:29 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 580/1251] eta: 0:07:07 lr: 0.000370 loss: 3.2636 (3.1770) grad_norm: 1.7483 (1.7493) time: 0.6306 [2021-03-27 14:40:35 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 590/1251] eta: 0:07:01 lr: 0.000370 loss: 3.2190 (3.1758) grad_norm: 1.6953 (1.7502) time: 0.6341 [2021-03-27 14:40:42 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 600/1251] eta: 0:06:54 lr: 0.000369 loss: 3.2909 (3.1774) grad_norm: 1.7304 (1.7507) time: 0.6331 [2021-03-27 14:40:48 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 610/1251] eta: 0:06:48 lr: 0.000369 loss: 3.0593 (3.1742) grad_norm: 1.7304 (1.7513) time: 0.6286 [2021-03-27 14:40:54 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 620/1251] eta: 0:06:41 lr: 0.000369 loss: 2.9081 (3.1715) grad_norm: 1.6410 (1.7501) time: 0.6275 [2021-03-27 14:41:00 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 630/1251] eta: 0:06:35 lr: 0.000369 loss: 3.1608 (3.1707) grad_norm: 1.7390 (1.7530) time: 0.6309 [2021-03-27 14:41:07 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 640/1251] eta: 0:06:29 lr: 0.000369 loss: 3.2262 (3.1681) grad_norm: 1.7848 (1.7524) time: 0.6331 [2021-03-27 14:41:13 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 650/1251] eta: 0:06:22 lr: 0.000369 loss: 3.3969 (3.1737) grad_norm: 1.5795 (1.7505) time: 0.6314 [2021-03-27 14:41:19 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 660/1251] eta: 0:06:16 lr: 0.000369 loss: 3.3906 (3.1743) grad_norm: 1.5647 (1.7481) time: 0.6281 [2021-03-27 14:41:26 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 670/1251] eta: 0:06:09 lr: 0.000369 loss: 3.0441 (3.1723) grad_norm: 1.5949 (1.7481) time: 0.6286 [2021-03-27 14:41:32 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 680/1251] eta: 0:06:03 lr: 0.000369 loss: 3.1039 (3.1728) grad_norm: 1.6692 (1.7462) time: 0.6274 [2021-03-27 14:41:38 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 690/1251] eta: 0:05:56 lr: 0.000369 loss: 3.4080 (3.1756) grad_norm: 1.6629 (1.7464) time: 0.6264 [2021-03-27 14:41:44 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 700/1251] eta: 0:05:50 lr: 0.000369 loss: 3.3816 (3.1732) grad_norm: 1.7224 (1.7463) time: 0.6271 [2021-03-27 14:41:51 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 710/1251] eta: 0:05:44 lr: 0.000369 loss: 3.0225 (3.1735) grad_norm: 1.7224 (1.7479) time: 0.6325 [2021-03-27 14:41:57 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 720/1251] eta: 0:05:37 lr: 0.000369 loss: 3.2481 (3.1767) grad_norm: 1.7081 (1.7499) time: 0.6327 [2021-03-27 14:42:03 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 730/1251] eta: 0:05:31 lr: 0.000369 loss: 3.2380 (3.1761) grad_norm: 1.6518 (1.7493) time: 0.6296 [2021-03-27 14:42:10 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 740/1251] eta: 0:05:24 lr: 0.000369 loss: 3.1311 (3.1755) grad_norm: 1.6344 (1.7494) time: 0.6332 [2021-03-27 14:42:16 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 750/1251] eta: 0:05:18 lr: 0.000369 loss: 3.1612 (3.1754) grad_norm: 1.6691 (1.7490) time: 0.6410 [2021-03-27 14:42:23 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 760/1251] eta: 0:05:12 lr: 0.000369 loss: 3.2295 (3.1767) grad_norm: 1.6691 (1.7478) time: 0.6450 [2021-03-27 14:42:29 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 770/1251] eta: 0:05:05 lr: 0.000369 loss: 3.0864 (3.1752) grad_norm: 1.6024 (1.7481) time: 0.6389 [2021-03-27 14:42:35 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 780/1251] eta: 0:04:59 lr: 0.000369 loss: 3.1665 (3.1758) grad_norm: 1.6148 (1.7483) time: 0.6302 [2021-03-27 14:42:42 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 790/1251] eta: 0:04:53 lr: 0.000369 loss: 3.2203 (3.1734) grad_norm: 1.6148 (1.7477) time: 0.6277 [2021-03-27 14:42:48 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 800/1251] eta: 0:04:46 lr: 0.000369 loss: 3.3819 (3.1762) grad_norm: 1.6007 (1.7469) time: 0.6265 [2021-03-27 14:42:54 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 810/1251] eta: 0:04:40 lr: 0.000369 loss: 3.3944 (3.1717) grad_norm: 1.6859 (1.7467) time: 0.6268 [2021-03-27 14:43:01 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 820/1251] eta: 0:04:33 lr: 0.000369 loss: 3.2604 (3.1724) grad_norm: 1.7279 (1.7474) time: 0.6331 [2021-03-27 14:43:07 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 830/1251] eta: 0:04:27 lr: 0.000369 loss: 3.3130 (3.1735) grad_norm: 1.6694 (1.7460) time: 0.6358 [2021-03-27 14:43:13 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 840/1251] eta: 0:04:21 lr: 0.000369 loss: 3.1581 (3.1710) grad_norm: 1.6253 (1.7462) time: 0.6326 [2021-03-27 14:43:20 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 850/1251] eta: 0:04:14 lr: 0.000368 loss: 2.9779 (3.1667) grad_norm: 1.7294 (1.7473) time: 0.6311 [2021-03-27 14:43:26 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 860/1251] eta: 0:04:08 lr: 0.000368 loss: 3.2363 (3.1695) grad_norm: 1.8364 (1.7477) time: 0.6338 [2021-03-27 14:43:32 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 870/1251] eta: 0:04:02 lr: 0.000368 loss: 3.3207 (3.1693) grad_norm: 1.8364 (1.7497) time: 0.6329 [2021-03-27 14:43:38 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 880/1251] eta: 0:03:55 lr: 0.000368 loss: 3.3114 (3.1702) grad_norm: 1.8243 (1.7505) time: 0.6276 [2021-03-27 14:43:45 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 890/1251] eta: 0:03:49 lr: 0.000368 loss: 3.3409 (3.1713) grad_norm: 1.6504 (1.7496) time: 0.6251 [2021-03-27 14:43:51 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 900/1251] eta: 0:03:42 lr: 0.000368 loss: 3.0873 (3.1691) grad_norm: 1.7330 (1.7497) time: 0.6266 [2021-03-27 14:43:57 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 910/1251] eta: 0:03:36 lr: 0.000368 loss: 3.1145 (3.1680) grad_norm: 1.7321 (1.7497) time: 0.6284 [2021-03-27 14:44:04 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 920/1251] eta: 0:03:30 lr: 0.000368 loss: 3.2807 (3.1706) grad_norm: 1.6806 (1.7503) time: 0.6280 [2021-03-27 14:44:10 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 930/1251] eta: 0:03:23 lr: 0.000368 loss: 3.2273 (3.1689) grad_norm: 1.7841 (1.7516) time: 0.6339 [2021-03-27 14:44:16 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 940/1251] eta: 0:03:17 lr: 0.000368 loss: 3.1769 (3.1709) grad_norm: 1.8060 (1.7532) time: 0.6352 [2021-03-27 14:44:23 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 950/1251] eta: 0:03:11 lr: 0.000368 loss: 3.1816 (3.1718) grad_norm: 1.7687 (1.7524) time: 0.6291 [2021-03-27 14:44:29 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 960/1251] eta: 0:03:04 lr: 0.000368 loss: 3.1816 (3.1706) grad_norm: 1.6709 (1.7516) time: 0.6296 [2021-03-27 14:44:35 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 970/1251] eta: 0:02:58 lr: 0.000368 loss: 3.3879 (3.1733) grad_norm: 1.6606 (1.7528) time: 0.6302 [2021-03-27 14:44:41 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 980/1251] eta: 0:02:52 lr: 0.000368 loss: 3.2991 (3.1712) grad_norm: 1.6960 (1.7575) time: 0.6291 [2021-03-27 14:44:48 swin_base_patch4_window7_224] INFO: Epoch: [176] [ 990/1251] eta: 0:02:45 lr: 0.000368 loss: 3.2426 (3.1719) grad_norm: 1.7168 (1.7580) time: 0.6310 [2021-03-27 14:44:54 swin_base_patch4_window7_224] INFO: Epoch: [176] [1000/1251] eta: 0:02:39 lr: 0.000368 loss: 3.3039 (3.1718) grad_norm: 1.7531 (1.7581) time: 0.6325 [2021-03-27 14:45:00 swin_base_patch4_window7_224] INFO: Epoch: [176] [1010/1251] eta: 0:02:32 lr: 0.000368 loss: 3.3354 (3.1729) grad_norm: 1.7157 (1.7588) time: 0.6283 [2021-03-27 14:45:07 swin_base_patch4_window7_224] INFO: Epoch: [176] [1020/1251] eta: 0:02:26 lr: 0.000368 loss: 3.3408 (3.1729) grad_norm: 1.7928 (1.7597) time: 0.6273 [2021-03-27 14:45:13 swin_base_patch4_window7_224] INFO: Epoch: [176] [1030/1251] eta: 0:02:20 lr: 0.000368 loss: 3.2690 (3.1735) grad_norm: 1.8090 (1.7609) time: 0.6248 [2021-03-27 14:45:19 swin_base_patch4_window7_224] INFO: Epoch: [176] [1040/1251] eta: 0:02:13 lr: 0.000368 loss: 3.1636 (3.1725) grad_norm: 1.7966 (1.7610) time: 0.6234 [2021-03-27 14:45:25 swin_base_patch4_window7_224] INFO: Epoch: [176] [1050/1251] eta: 0:02:07 lr: 0.000368 loss: 3.2761 (3.1729) grad_norm: 1.7560 (1.7618) time: 0.6282 [2021-03-27 14:45:32 swin_base_patch4_window7_224] INFO: Epoch: [176] [1060/1251] eta: 0:02:01 lr: 0.000368 loss: 3.3364 (3.1731) grad_norm: 1.7560 (1.7619) time: 0.6295 [2021-03-27 14:45:38 swin_base_patch4_window7_224] INFO: Epoch: [176] [1070/1251] eta: 0:01:54 lr: 0.000368 loss: 3.3318 (3.1725) grad_norm: 1.7556 (1.7614) time: 0.6303 [2021-03-27 14:45:44 swin_base_patch4_window7_224] INFO: Epoch: [176] [1080/1251] eta: 0:01:48 lr: 0.000368 loss: 3.3210 (3.1729) grad_norm: 1.7007 (1.7608) time: 0.6272 [2021-03-27 14:45:50 swin_base_patch4_window7_224] INFO: Epoch: [176] [1090/1251] eta: 0:01:42 lr: 0.000368 loss: 3.2653 (3.1734) grad_norm: 1.6328 (1.7599) time: 0.6239 [2021-03-27 14:45:57 swin_base_patch4_window7_224] INFO: Epoch: [176] [1100/1251] eta: 0:01:35 lr: 0.000368 loss: 3.2165 (3.1718) grad_norm: 1.7094 (1.7600) time: 0.6260 [2021-03-27 14:46:03 swin_base_patch4_window7_224] INFO: Epoch: [176] [1110/1251] eta: 0:01:29 lr: 0.000367 loss: 3.2165 (3.1726) grad_norm: 1.7363 (1.7591) time: 0.6290 [2021-03-27 14:46:09 swin_base_patch4_window7_224] INFO: Epoch: [176] [1120/1251] eta: 0:01:23 lr: 0.000367 loss: 3.2083 (3.1710) grad_norm: 1.7212 (1.7597) time: 0.6316 [2021-03-27 14:46:16 swin_base_patch4_window7_224] INFO: Epoch: [176] [1130/1251] eta: 0:01:16 lr: 0.000367 loss: 3.2918 (3.1725) grad_norm: 1.7555 (1.7605) time: 0.6294 [2021-03-27 14:46:22 swin_base_patch4_window7_224] INFO: Epoch: [176] [1140/1251] eta: 0:01:10 lr: 0.000367 loss: 3.3962 (3.1728) grad_norm: 1.7726 (1.7609) time: 0.6232 [2021-03-27 14:46:28 swin_base_patch4_window7_224] INFO: Epoch: [176] [1150/1251] eta: 0:01:04 lr: 0.000367 loss: 3.1566 (3.1707) grad_norm: 1.8026 (1.7624) time: 0.6265 [2021-03-27 14:46:34 swin_base_patch4_window7_224] INFO: Epoch: [176] [1160/1251] eta: 0:00:57 lr: 0.000367 loss: 3.1224 (3.1699) grad_norm: 1.6979 (1.7622) time: 0.6282 [2021-03-27 14:46:41 swin_base_patch4_window7_224] INFO: Epoch: [176] [1170/1251] eta: 0:00:51 lr: 0.000367 loss: 3.3185 (3.1712) grad_norm: 1.7870 (1.7640) time: 0.6275 [2021-03-27 14:46:47 swin_base_patch4_window7_224] INFO: Epoch: [176] [1180/1251] eta: 0:00:44 lr: 0.000367 loss: 3.3082 (3.1709) grad_norm: 1.8549 (1.7641) time: 0.6312 [2021-03-27 14:46:53 swin_base_patch4_window7_224] INFO: Epoch: [176] [1190/1251] eta: 0:00:38 lr: 0.000367 loss: 3.1365 (3.1689) grad_norm: 1.7675 (1.7639) time: 0.6298 [2021-03-27 14:47:00 swin_base_patch4_window7_224] INFO: Epoch: [176] [1200/1251] eta: 0:00:32 lr: 0.000367 loss: 3.1301 (3.1685) grad_norm: 1.7246 (1.7633) time: 0.6292 [2021-03-27 14:47:06 swin_base_patch4_window7_224] INFO: Epoch: [176] [1210/1251] eta: 0:00:25 lr: 0.000367 loss: 3.1301 (3.1679) grad_norm: 1.6676 (1.7623) time: 0.6300 [2021-03-27 14:47:12 swin_base_patch4_window7_224] INFO: Epoch: [176] [1220/1251] eta: 0:00:19 lr: 0.000367 loss: 3.3337 (3.1690) grad_norm: 1.6827 (1.7626) time: 0.6320 [2021-03-27 14:47:19 swin_base_patch4_window7_224] INFO: Epoch: [176] [1230/1251] eta: 0:00:13 lr: 0.000367 loss: 3.5055 (3.1706) grad_norm: 1.8018 (1.7640) time: 0.6332 [2021-03-27 14:47:25 swin_base_patch4_window7_224] INFO: Epoch: [176] [1240/1251] eta: 0:00:06 lr: 0.000367 loss: 3.3715 (3.1693) grad_norm: 1.8080 (1.7644) time: 0.6264 [2021-03-27 14:47:31 swin_base_patch4_window7_224] INFO: Epoch: [176] [1250/1251] eta: 0:00:00 lr: 0.000367 loss: 3.0326 (3.1681) grad_norm: 1.6635 (1.7636) time: 0.6151 [2021-03-27 14:47:41 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:02 loss: 0.9815 (0.9815) acc1: 82.8125 (82.8125) acc5: 90.6250 (90.6250) [2021-03-27 14:47:44 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.9243 (0.9104) acc1: 79.6875 (78.5511) acc5: 95.3125 (95.3125) [2021-03-27 14:47:46 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8928 (0.8951) acc1: 79.6875 (78.8690) acc5: 95.3125 (95.2381) [2021-03-27 14:47:49 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8635 (0.9029) acc1: 79.6875 (78.7298) acc5: 95.3125 (95.2117) [2021-03-27 14:47:50 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8533 (0.8837) acc1: 81.2500 (79.1159) acc5: 95.3125 (95.4268) [2021-03-27 14:47:51 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7683 (0.8717) acc1: 81.2500 (79.4240) acc5: 96.8750 (95.5520) [2021-03-27 14:48:04 swin_base_patch4_window7_224] INFO: * Acc@1 80.106 Acc@5 95.434 loss 0.856 [2021-03-27 14:48:04 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.1% [2021-03-27 14:48:04 swin_base_patch4_window7_224] INFO: Max accuracy: 80.23% [2021-03-27 14:48:08 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 0/1251] eta: 1:25:23 lr: 0.000367 loss: 4.0821 (4.0821) grad_norm: 1.7111 (1.7111) time: 4.0955 [2021-03-27 14:48:15 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 10/1251] eta: 0:20:05 lr: 0.000367 loss: 3.0970 (3.0467) grad_norm: 1.6919 (1.7117) time: 0.9718 [2021-03-27 14:48:21 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 20/1251] eta: 0:16:38 lr: 0.000367 loss: 3.1240 (3.1437) grad_norm: 1.6919 (1.7316) time: 0.6470 [2021-03-27 14:48:27 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 30/1251] eta: 0:15:16 lr: 0.000367 loss: 3.1316 (3.1150) grad_norm: 1.7413 (1.7289) time: 0.6292 [2021-03-27 14:48:34 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 40/1251] eta: 0:14:33 lr: 0.000367 loss: 3.2991 (3.1288) grad_norm: 1.7643 (1.7847) time: 0.6270 [2021-03-27 14:48:40 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 50/1251] eta: 0:14:04 lr: 0.000367 loss: 3.2304 (3.1199) grad_norm: 1.8434 (1.7980) time: 0.6301 [2021-03-27 14:48:46 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 60/1251] eta: 0:13:42 lr: 0.000367 loss: 3.2386 (3.1396) grad_norm: 1.7758 (1.8060) time: 0.6284 [2021-03-27 14:48:52 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 70/1251] eta: 0:13:24 lr: 0.000367 loss: 3.2563 (3.1230) grad_norm: 1.7431 (1.8008) time: 0.6254 [2021-03-27 14:48:59 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 80/1251] eta: 0:13:09 lr: 0.000367 loss: 3.4100 (3.1584) grad_norm: 1.7073 (1.7961) time: 0.6226 [2021-03-27 14:49:05 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 90/1251] eta: 0:12:56 lr: 0.000367 loss: 3.4721 (3.1724) grad_norm: 1.6846 (1.8015) time: 0.6244 [2021-03-27 14:49:11 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 100/1251] eta: 0:12:44 lr: 0.000367 loss: 3.0848 (3.1417) grad_norm: 1.7698 (1.8028) time: 0.6255 [2021-03-27 14:49:17 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 110/1251] eta: 0:12:33 lr: 0.000366 loss: 2.9204 (3.1439) grad_norm: 1.8400 (1.8149) time: 0.6227 [2021-03-27 14:49:24 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 120/1251] eta: 0:12:23 lr: 0.000366 loss: 3.2857 (3.1320) grad_norm: 1.7977 (1.8106) time: 0.6238 [2021-03-27 14:49:30 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 130/1251] eta: 0:12:15 lr: 0.000366 loss: 3.1901 (3.1349) grad_norm: 1.7343 (1.8057) time: 0.6320 [2021-03-27 14:49:36 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 140/1251] eta: 0:12:07 lr: 0.000366 loss: 3.0712 (3.1259) grad_norm: 1.7267 (1.8004) time: 0.6344 [2021-03-27 14:49:43 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 150/1251] eta: 0:11:58 lr: 0.000366 loss: 3.0712 (3.1340) grad_norm: 1.6510 (1.7916) time: 0.6293 [2021-03-27 14:49:49 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 160/1251] eta: 0:11:49 lr: 0.000366 loss: 3.2900 (3.1304) grad_norm: 1.6510 (1.7921) time: 0.6250 [2021-03-27 14:49:55 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 170/1251] eta: 0:11:42 lr: 0.000366 loss: 3.4006 (3.1375) grad_norm: 1.6684 (1.7838) time: 0.6314 [2021-03-27 14:50:02 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 180/1251] eta: 0:11:34 lr: 0.000366 loss: 3.4343 (3.1503) grad_norm: 1.6684 (1.7786) time: 0.6326 [2021-03-27 14:50:08 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 190/1251] eta: 0:11:27 lr: 0.000366 loss: 3.1449 (3.1415) grad_norm: 1.5897 (1.7760) time: 0.6250 [2021-03-27 14:50:14 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 200/1251] eta: 0:11:19 lr: 0.000366 loss: 3.1449 (3.1437) grad_norm: 1.6318 (1.7756) time: 0.6259 [2021-03-27 14:50:20 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 210/1251] eta: 0:11:11 lr: 0.000366 loss: 3.3862 (3.1561) grad_norm: 1.6980 (1.7731) time: 0.6224 [2021-03-27 14:50:27 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 220/1251] eta: 0:11:04 lr: 0.000366 loss: 3.4324 (3.1705) grad_norm: 1.6896 (1.7764) time: 0.6249 [2021-03-27 14:50:33 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 230/1251] eta: 0:10:57 lr: 0.000366 loss: 3.4324 (3.1814) grad_norm: 1.7623 (1.7767) time: 0.6297 [2021-03-27 14:50:39 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 240/1251] eta: 0:10:50 lr: 0.000366 loss: 3.4511 (3.1885) grad_norm: 1.6687 (1.7759) time: 0.6284 [2021-03-27 14:50:45 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 250/1251] eta: 0:10:42 lr: 0.000366 loss: 3.3698 (3.1825) grad_norm: 1.7393 (1.7789) time: 0.6252 [2021-03-27 14:50:52 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 260/1251] eta: 0:10:36 lr: 0.000366 loss: 3.3149 (3.1865) grad_norm: 1.7181 (1.7757) time: 0.6311 [2021-03-27 14:50:58 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 270/1251] eta: 0:10:29 lr: 0.000366 loss: 3.3225 (3.1917) grad_norm: 1.7015 (1.7738) time: 0.6371 [2021-03-27 14:51:04 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 280/1251] eta: 0:10:23 lr: 0.000366 loss: 3.2678 (3.1811) grad_norm: 1.6969 (1.7704) time: 0.6336 [2021-03-27 14:51:11 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 290/1251] eta: 0:10:15 lr: 0.000366 loss: 3.3668 (3.1849) grad_norm: 1.7250 (1.7731) time: 0.6271 [2021-03-27 14:51:17 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 300/1251] eta: 0:10:08 lr: 0.000366 loss: 3.4332 (3.1927) grad_norm: 1.7250 (1.7754) time: 0.6196 [2021-03-27 14:51:23 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 310/1251] eta: 0:10:01 lr: 0.000366 loss: 3.1570 (3.1755) grad_norm: 1.7356 (1.7751) time: 0.6215 [2021-03-27 14:51:29 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 320/1251] eta: 0:09:55 lr: 0.000366 loss: 2.9525 (3.1775) grad_norm: 1.7412 (1.7723) time: 0.6298 [2021-03-27 14:51:36 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 330/1251] eta: 0:09:48 lr: 0.000366 loss: 3.0954 (3.1691) grad_norm: 1.6824 (1.7727) time: 0.6287 [2021-03-27 14:51:42 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 340/1251] eta: 0:09:41 lr: 0.000366 loss: 3.0954 (3.1725) grad_norm: 1.6824 (1.7713) time: 0.6241 [2021-03-27 14:51:48 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 350/1251] eta: 0:09:35 lr: 0.000366 loss: 3.2648 (3.1669) grad_norm: 1.6404 (1.7699) time: 0.6277 [2021-03-27 14:51:54 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 360/1251] eta: 0:09:28 lr: 0.000365 loss: 3.1168 (3.1609) grad_norm: 1.6404 (1.7673) time: 0.6245 [2021-03-27 14:52:01 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 370/1251] eta: 0:09:21 lr: 0.000365 loss: 3.0217 (3.1584) grad_norm: 1.6241 (1.7632) time: 0.6271 [2021-03-27 14:52:07 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 380/1251] eta: 0:09:15 lr: 0.000365 loss: 3.0184 (3.1537) grad_norm: 1.6647 (1.7642) time: 0.6318 [2021-03-27 14:52:13 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 390/1251] eta: 0:09:08 lr: 0.000365 loss: 3.2634 (3.1547) grad_norm: 1.6880 (1.7631) time: 0.6330 [2021-03-27 14:52:20 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 400/1251] eta: 0:09:02 lr: 0.000365 loss: 3.1283 (3.1514) grad_norm: 1.7378 (1.7639) time: 0.6342 [2021-03-27 14:52:26 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 410/1251] eta: 0:08:55 lr: 0.000365 loss: 2.9397 (3.1513) grad_norm: 1.7404 (1.7639) time: 0.6337 [2021-03-27 14:52:32 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 420/1251] eta: 0:08:49 lr: 0.000365 loss: 3.3027 (3.1524) grad_norm: 1.6874 (1.7644) time: 0.6334 [2021-03-27 14:52:39 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 430/1251] eta: 0:08:42 lr: 0.000365 loss: 3.3027 (3.1555) grad_norm: 1.6691 (1.7633) time: 0.6267 [2021-03-27 14:52:45 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 440/1251] eta: 0:08:36 lr: 0.000365 loss: 3.1862 (3.1567) grad_norm: 1.6849 (1.7626) time: 0.6216 [2021-03-27 14:52:51 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 450/1251] eta: 0:08:29 lr: 0.000365 loss: 3.1496 (3.1548) grad_norm: 1.8023 (1.7630) time: 0.6293 [2021-03-27 14:52:57 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 460/1251] eta: 0:08:23 lr: 0.000365 loss: 3.0828 (3.1506) grad_norm: 1.8023 (1.7661) time: 0.6311 [2021-03-27 14:53:04 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 470/1251] eta: 0:08:16 lr: 0.000365 loss: 2.9023 (3.1473) grad_norm: 1.8330 (1.7675) time: 0.6252 [2021-03-27 14:53:10 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 480/1251] eta: 0:08:10 lr: 0.000365 loss: 2.9837 (3.1441) grad_norm: 1.8497 (1.7682) time: 0.6294 [2021-03-27 14:53:16 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 490/1251] eta: 0:08:03 lr: 0.000365 loss: 3.1732 (3.1444) grad_norm: 1.6981 (1.7659) time: 0.6263 [2021-03-27 14:53:23 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 500/1251] eta: 0:07:57 lr: 0.000365 loss: 3.2417 (3.1439) grad_norm: 1.7135 (1.7665) time: 0.6236 [2021-03-27 14:53:29 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 510/1251] eta: 0:07:50 lr: 0.000365 loss: 3.3981 (3.1523) grad_norm: 1.7927 (1.7697) time: 0.6243 [2021-03-27 14:53:35 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 520/1251] eta: 0:07:44 lr: 0.000365 loss: 3.5655 (3.1586) grad_norm: 1.8797 (1.7713) time: 0.6241 [2021-03-27 14:53:41 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 530/1251] eta: 0:07:37 lr: 0.000365 loss: 3.3122 (3.1598) grad_norm: 1.7604 (1.7725) time: 0.6258 [2021-03-27 14:53:48 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 540/1251] eta: 0:07:31 lr: 0.000365 loss: 3.2600 (3.1625) grad_norm: 1.7155 (1.7716) time: 0.6280 [2021-03-27 14:53:54 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 550/1251] eta: 0:07:25 lr: 0.000365 loss: 3.3879 (3.1670) grad_norm: 1.6803 (1.7714) time: 0.6414 [2021-03-27 14:54:01 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 560/1251] eta: 0:07:18 lr: 0.000365 loss: 3.3985 (3.1693) grad_norm: 1.7684 (1.7728) time: 0.6457 [2021-03-27 14:54:07 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 570/1251] eta: 0:07:12 lr: 0.000365 loss: 3.4859 (3.1734) grad_norm: 1.7222 (1.7721) time: 0.6353 [2021-03-27 14:54:13 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 580/1251] eta: 0:07:06 lr: 0.000365 loss: 3.4275 (3.1784) grad_norm: 1.7204 (1.7720) time: 0.6278 [2021-03-27 14:54:19 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 590/1251] eta: 0:06:59 lr: 0.000365 loss: 3.3819 (3.1797) grad_norm: 1.7209 (1.7722) time: 0.6251 [2021-03-27 14:54:26 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 600/1251] eta: 0:06:53 lr: 0.000365 loss: 3.2225 (3.1819) grad_norm: 1.7450 (nan) time: 0.6233 [2021-03-27 14:54:32 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 610/1251] eta: 0:06:46 lr: 0.000364 loss: 3.1983 (3.1786) grad_norm: 1.7447 (nan) time: 0.6225 [2021-03-27 14:54:38 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 620/1251] eta: 0:06:40 lr: 0.000364 loss: 3.3050 (3.1812) grad_norm: 1.7447 (nan) time: 0.6225 [2021-03-27 14:54:44 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 630/1251] eta: 0:06:33 lr: 0.000364 loss: 3.4247 (3.1833) grad_norm: 1.7481 (nan) time: 0.6232 [2021-03-27 14:54:50 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 640/1251] eta: 0:06:27 lr: 0.000364 loss: 3.5136 (3.1885) grad_norm: 1.7481 (nan) time: 0.6218 [2021-03-27 14:54:57 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 650/1251] eta: 0:06:20 lr: 0.000364 loss: 3.4602 (3.1914) grad_norm: 1.6282 (nan) time: 0.6240 [2021-03-27 14:55:03 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 660/1251] eta: 0:06:14 lr: 0.000364 loss: 3.3194 (3.1914) grad_norm: 1.6030 (nan) time: 0.6309 [2021-03-27 14:55:09 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 670/1251] eta: 0:06:08 lr: 0.000364 loss: 3.2189 (3.1906) grad_norm: 1.8972 (nan) time: 0.6279 [2021-03-27 14:55:16 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 680/1251] eta: 0:06:01 lr: 0.000364 loss: 3.0580 (3.1894) grad_norm: 1.8664 (nan) time: 0.6291 [2021-03-27 14:55:22 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 690/1251] eta: 0:05:55 lr: 0.000364 loss: 3.0852 (3.1889) grad_norm: 1.8050 (nan) time: 0.6350 [2021-03-27 14:55:28 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 700/1251] eta: 0:05:49 lr: 0.000364 loss: 3.2355 (3.1886) grad_norm: 1.7589 (nan) time: 0.6335 [2021-03-27 14:55:35 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 710/1251] eta: 0:05:42 lr: 0.000364 loss: 3.3535 (3.1908) grad_norm: 1.6964 (nan) time: 0.6257 [2021-03-27 14:55:41 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 720/1251] eta: 0:05:36 lr: 0.000364 loss: 3.4442 (3.1930) grad_norm: 1.6849 (nan) time: 0.6288 [2021-03-27 14:55:47 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 730/1251] eta: 0:05:29 lr: 0.000364 loss: 3.3094 (3.1904) grad_norm: 1.6823 (nan) time: 0.6292 [2021-03-27 14:55:54 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 740/1251] eta: 0:05:23 lr: 0.000364 loss: 3.2334 (3.1918) grad_norm: 1.6408 (nan) time: 0.6317 [2021-03-27 14:56:00 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 750/1251] eta: 0:05:17 lr: 0.000364 loss: 3.3367 (3.1898) grad_norm: 1.7838 (nan) time: 0.6406 [2021-03-27 14:56:06 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 760/1251] eta: 0:05:10 lr: 0.000364 loss: 2.9941 (3.1881) grad_norm: 1.7189 (nan) time: 0.6354 [2021-03-27 14:56:13 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 770/1251] eta: 0:05:04 lr: 0.000364 loss: 3.2259 (3.1877) grad_norm: 1.6800 (nan) time: 0.6328 [2021-03-27 14:56:19 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 780/1251] eta: 0:04:58 lr: 0.000364 loss: 3.0339 (3.1851) grad_norm: 1.6593 (nan) time: 0.6352 [2021-03-27 14:56:25 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 790/1251] eta: 0:04:51 lr: 0.000364 loss: 3.1635 (3.1862) grad_norm: 1.7654 (nan) time: 0.6296 [2021-03-27 14:56:31 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 800/1251] eta: 0:04:45 lr: 0.000364 loss: 3.2784 (3.1874) grad_norm: 1.7906 (nan) time: 0.6220 [2021-03-27 14:56:38 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 810/1251] eta: 0:04:39 lr: 0.000364 loss: 3.3052 (3.1880) grad_norm: 1.6723 (nan) time: 0.6223 [2021-03-27 14:56:44 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 820/1251] eta: 0:04:32 lr: 0.000364 loss: 3.3539 (3.1870) grad_norm: 1.6674 (nan) time: 0.6268 [2021-03-27 14:56:50 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 830/1251] eta: 0:04:26 lr: 0.000364 loss: 3.1431 (3.1849) grad_norm: 1.6411 (nan) time: 0.6300 [2021-03-27 14:56:57 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 840/1251] eta: 0:04:20 lr: 0.000364 loss: 3.1431 (3.1822) grad_norm: 1.5946 (nan) time: 0.6310 [2021-03-27 14:57:03 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 850/1251] eta: 0:04:13 lr: 0.000364 loss: 3.1838 (3.1827) grad_norm: 1.6106 (nan) time: 0.6307 [2021-03-27 14:57:09 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 860/1251] eta: 0:04:07 lr: 0.000363 loss: 3.1882 (3.1806) grad_norm: 1.6838 (nan) time: 0.6278 [2021-03-27 14:57:15 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 870/1251] eta: 0:04:01 lr: 0.000363 loss: 3.1519 (3.1808) grad_norm: 1.7096 (nan) time: 0.6257 [2021-03-27 14:57:22 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 880/1251] eta: 0:03:54 lr: 0.000363 loss: 3.3059 (3.1826) grad_norm: 1.7624 (nan) time: 0.6278 [2021-03-27 14:57:28 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 890/1251] eta: 0:03:48 lr: 0.000363 loss: 3.3059 (3.1838) grad_norm: 1.7624 (nan) time: 0.6314 [2021-03-27 14:57:34 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 900/1251] eta: 0:03:42 lr: 0.000363 loss: 3.0281 (3.1814) grad_norm: 1.8054 (nan) time: 0.6293 [2021-03-27 14:57:41 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 910/1251] eta: 0:03:35 lr: 0.000363 loss: 3.0732 (3.1835) grad_norm: 1.6813 (nan) time: 0.6306 [2021-03-27 14:57:47 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 920/1251] eta: 0:03:29 lr: 0.000363 loss: 3.2750 (3.1830) grad_norm: 1.6493 (nan) time: 0.6357 [2021-03-27 14:57:53 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 930/1251] eta: 0:03:23 lr: 0.000363 loss: 3.2750 (3.1850) grad_norm: 1.6792 (nan) time: 0.6339 [2021-03-27 14:58:00 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 940/1251] eta: 0:03:16 lr: 0.000363 loss: 3.4579 (3.1855) grad_norm: 1.6991 (nan) time: 0.6310 [2021-03-27 14:58:06 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 950/1251] eta: 0:03:10 lr: 0.000363 loss: 2.9956 (3.1824) grad_norm: 1.6574 (nan) time: 0.6294 [2021-03-27 14:58:12 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 960/1251] eta: 0:03:04 lr: 0.000363 loss: 2.9871 (3.1815) grad_norm: 1.7558 (nan) time: 0.6266 [2021-03-27 14:58:18 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 970/1251] eta: 0:02:57 lr: 0.000363 loss: 3.0867 (3.1816) grad_norm: 1.8163 (nan) time: 0.6244 [2021-03-27 14:58:25 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 980/1251] eta: 0:02:51 lr: 0.000363 loss: 3.0867 (3.1821) grad_norm: 1.6945 (nan) time: 0.6252 [2021-03-27 14:58:31 swin_base_patch4_window7_224] INFO: Epoch: [177] [ 990/1251] eta: 0:02:45 lr: 0.000363 loss: 3.4346 (3.1835) grad_norm: 1.6796 (nan) time: 0.6271 [2021-03-27 14:58:37 swin_base_patch4_window7_224] INFO: Epoch: [177] [1000/1251] eta: 0:02:38 lr: 0.000363 loss: 3.4346 (3.1833) grad_norm: 1.7159 (nan) time: 0.6300 [2021-03-27 14:58:44 swin_base_patch4_window7_224] INFO: Epoch: [177] [1010/1251] eta: 0:02:32 lr: 0.000363 loss: 3.1079 (3.1823) grad_norm: 1.7467 (nan) time: 0.6314 [2021-03-27 14:58:50 swin_base_patch4_window7_224] INFO: Epoch: [177] [1020/1251] eta: 0:02:26 lr: 0.000363 loss: 3.0953 (3.1798) grad_norm: 1.7097 (nan) time: 0.6296 [2021-03-27 14:58:56 swin_base_patch4_window7_224] INFO: Epoch: [177] [1030/1251] eta: 0:02:19 lr: 0.000363 loss: 3.0033 (3.1797) grad_norm: 1.7454 (nan) time: 0.6285 [2021-03-27 14:59:02 swin_base_patch4_window7_224] INFO: Epoch: [177] [1040/1251] eta: 0:02:13 lr: 0.000363 loss: 3.2517 (3.1806) grad_norm: 1.7454 (nan) time: 0.6278 [2021-03-27 14:59:09 swin_base_patch4_window7_224] INFO: Epoch: [177] [1050/1251] eta: 0:02:07 lr: 0.000363 loss: 3.3310 (3.1818) grad_norm: 1.6931 (nan) time: 0.6304 [2021-03-27 14:59:15 swin_base_patch4_window7_224] INFO: Epoch: [177] [1060/1251] eta: 0:02:00 lr: 0.000363 loss: 3.3596 (3.1825) grad_norm: 1.6806 (nan) time: 0.6283 [2021-03-27 14:59:21 swin_base_patch4_window7_224] INFO: Epoch: [177] [1070/1251] eta: 0:01:54 lr: 0.000363 loss: 3.3642 (3.1834) grad_norm: 1.6327 (nan) time: 0.6260 [2021-03-27 14:59:28 swin_base_patch4_window7_224] INFO: Epoch: [177] [1080/1251] eta: 0:01:48 lr: 0.000363 loss: 3.1786 (3.1827) grad_norm: 1.6431 (nan) time: 0.6276 [2021-03-27 14:59:34 swin_base_patch4_window7_224] INFO: Epoch: [177] [1090/1251] eta: 0:01:41 lr: 0.000363 loss: 3.2595 (3.1825) grad_norm: 1.7491 (nan) time: 0.6231 [2021-03-27 14:59:40 swin_base_patch4_window7_224] INFO: Epoch: [177] [1100/1251] eta: 0:01:35 lr: 0.000363 loss: 3.2653 (3.1809) grad_norm: 1.6737 (nan) time: 0.6253 [2021-03-27 14:59:46 swin_base_patch4_window7_224] INFO: Epoch: [177] [1110/1251] eta: 0:01:29 lr: 0.000362 loss: 3.3765 (3.1826) grad_norm: 1.7274 (nan) time: 0.6287 [2021-03-27 14:59:53 swin_base_patch4_window7_224] INFO: Epoch: [177] [1120/1251] eta: 0:01:22 lr: 0.000362 loss: 3.3765 (3.1822) grad_norm: 1.7058 (nan) time: 0.6244 [2021-03-27 14:59:59 swin_base_patch4_window7_224] INFO: Epoch: [177] [1130/1251] eta: 0:01:16 lr: 0.000362 loss: 3.2161 (3.1808) grad_norm: 1.6714 (nan) time: 0.6255 [2021-03-27 15:00:05 swin_base_patch4_window7_224] INFO: Epoch: [177] [1140/1251] eta: 0:01:10 lr: 0.000362 loss: 3.2829 (3.1821) grad_norm: 1.6959 (nan) time: 0.6262 [2021-03-27 15:00:11 swin_base_patch4_window7_224] INFO: Epoch: [177] [1150/1251] eta: 0:01:03 lr: 0.000362 loss: 3.2829 (3.1805) grad_norm: 1.7058 (nan) time: 0.6273 [2021-03-27 15:00:18 swin_base_patch4_window7_224] INFO: Epoch: [177] [1160/1251] eta: 0:00:57 lr: 0.000362 loss: 3.0908 (3.1804) grad_norm: 1.7687 (nan) time: 0.6311 [2021-03-27 15:00:24 swin_base_patch4_window7_224] INFO: Epoch: [177] [1170/1251] eta: 0:00:51 lr: 0.000362 loss: 3.1228 (3.1792) grad_norm: 1.8374 (nan) time: 0.6279 [2021-03-27 15:00:30 swin_base_patch4_window7_224] INFO: Epoch: [177] [1180/1251] eta: 0:00:44 lr: 0.000362 loss: 3.1069 (3.1784) grad_norm: 1.6331 (nan) time: 0.6270 [2021-03-27 15:00:36 swin_base_patch4_window7_224] INFO: Epoch: [177] [1190/1251] eta: 0:00:38 lr: 0.000362 loss: 3.1069 (3.1773) grad_norm: 1.6727 (nan) time: 0.6255 [2021-03-27 15:00:43 swin_base_patch4_window7_224] INFO: Epoch: [177] [1200/1251] eta: 0:00:32 lr: 0.000362 loss: 2.9861 (3.1756) grad_norm: 1.6996 (nan) time: 0.6266 [2021-03-27 15:00:49 swin_base_patch4_window7_224] INFO: Epoch: [177] [1210/1251] eta: 0:00:25 lr: 0.000362 loss: 2.9861 (3.1740) grad_norm: 1.6996 (nan) time: 0.6272 [2021-03-27 15:00:55 swin_base_patch4_window7_224] INFO: Epoch: [177] [1220/1251] eta: 0:00:19 lr: 0.000362 loss: 3.3676 (3.1768) grad_norm: 1.6564 (nan) time: 0.6243 [2021-03-27 15:01:02 swin_base_patch4_window7_224] INFO: Epoch: [177] [1230/1251] eta: 0:00:13 lr: 0.000362 loss: 3.4105 (3.1762) grad_norm: 1.6851 (nan) time: 0.6290 [2021-03-27 15:01:08 swin_base_patch4_window7_224] INFO: Epoch: [177] [1240/1251] eta: 0:00:06 lr: 0.000362 loss: 3.2037 (3.1770) grad_norm: 1.7302 (nan) time: 0.6258 [2021-03-27 15:01:14 swin_base_patch4_window7_224] INFO: Epoch: [177] [1250/1251] eta: 0:00:00 lr: 0.000362 loss: 3.1884 (3.1770) grad_norm: 1.7826 (nan) time: 0.6209 [2021-03-27 15:01:23 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:28 loss: 0.9935 (0.9935) acc1: 78.1250 (78.1250) acc5: 96.8750 (96.8750) [2021-03-27 15:01:25 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.8548 (0.8267) acc1: 79.6875 (79.9716) acc5: 96.8750 (96.4489) [2021-03-27 15:01:27 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.8586 (0.8593) acc1: 79.6875 (79.3155) acc5: 95.3125 (95.5357) [2021-03-27 15:01:29 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8586 (0.8670) acc1: 78.1250 (79.0323) acc5: 95.3125 (95.9677) [2021-03-27 15:01:32 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8342 (0.8719) acc1: 78.1250 (79.1159) acc5: 95.3125 (95.6936) [2021-03-27 15:01:33 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8847 (0.8721) acc1: 79.6875 (79.2320) acc5: 95.3125 (95.7760) [2021-03-27 15:01:43 swin_base_patch4_window7_224] INFO: * Acc@1 80.074 Acc@5 95.310 loss 0.862 [2021-03-27 15:01:43 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.1% [2021-03-27 15:01:43 swin_base_patch4_window7_224] INFO: Max accuracy: 80.23% [2021-03-27 15:01:48 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 0/1251] eta: 1:26:42 lr: 0.000362 loss: 2.1559 (2.1559) grad_norm: 1.8825 (1.8825) time: 4.1588 [2021-03-27 15:01:54 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 10/1251] eta: 0:20:08 lr: 0.000362 loss: 3.2180 (3.1077) grad_norm: 1.6210 (1.6643) time: 0.9735 [2021-03-27 15:02:01 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 20/1251] eta: 0:16:36 lr: 0.000362 loss: 3.2760 (3.1674) grad_norm: 1.6106 (1.6638) time: 0.6419 [2021-03-27 15:02:07 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 30/1251] eta: 0:15:17 lr: 0.000362 loss: 3.2760 (3.1506) grad_norm: 1.7413 (1.7201) time: 0.6294 [2021-03-27 15:02:13 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 40/1251] eta: 0:14:31 lr: 0.000362 loss: 3.1533 (3.1331) grad_norm: 1.8043 (1.7562) time: 0.6260 [2021-03-27 15:02:19 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 50/1251] eta: 0:14:01 lr: 0.000362 loss: 3.1925 (3.1529) grad_norm: 1.8865 (1.7880) time: 0.6209 [2021-03-27 15:02:25 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 60/1251] eta: 0:13:38 lr: 0.000362 loss: 3.0926 (3.1372) grad_norm: 1.7550 (1.7815) time: 0.6202 [2021-03-27 15:02:32 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 70/1251] eta: 0:13:22 lr: 0.000362 loss: 3.0926 (3.1554) grad_norm: 1.6443 (1.7763) time: 0.6269 [2021-03-27 15:02:38 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 80/1251] eta: 0:13:09 lr: 0.000362 loss: 3.1644 (3.1525) grad_norm: 1.6565 (1.7750) time: 0.6342 [2021-03-27 15:02:44 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 90/1251] eta: 0:12:56 lr: 0.000362 loss: 3.2389 (3.1709) grad_norm: 1.6616 (1.7618) time: 0.6302 [2021-03-27 15:02:51 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 100/1251] eta: 0:12:45 lr: 0.000362 loss: 3.3781 (3.1648) grad_norm: 1.5830 (1.7477) time: 0.6291 [2021-03-27 15:02:57 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 110/1251] eta: 0:12:35 lr: 0.000361 loss: 3.3137 (3.1543) grad_norm: 1.6056 (1.7397) time: 0.6317 [2021-03-27 15:03:03 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 120/1251] eta: 0:12:25 lr: 0.000361 loss: 3.3073 (3.1752) grad_norm: 1.6422 (1.7364) time: 0.6275 [2021-03-27 15:03:10 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 130/1251] eta: 0:12:16 lr: 0.000361 loss: 3.4149 (3.1891) grad_norm: 1.7238 (1.7420) time: 0.6264 [2021-03-27 15:03:16 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 140/1251] eta: 0:12:07 lr: 0.000361 loss: 3.4255 (3.1917) grad_norm: 1.7238 (1.7409) time: 0.6287 [2021-03-27 15:03:22 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 150/1251] eta: 0:11:58 lr: 0.000361 loss: 3.2436 (3.1912) grad_norm: 1.7794 (1.7519) time: 0.6274 [2021-03-27 15:03:28 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 160/1251] eta: 0:11:50 lr: 0.000361 loss: 3.2436 (3.1891) grad_norm: 1.7830 (1.7630) time: 0.6271 [2021-03-27 15:03:35 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 170/1251] eta: 0:11:42 lr: 0.000361 loss: 3.3057 (3.1827) grad_norm: 1.7789 (1.7665) time: 0.6275 [2021-03-27 15:03:41 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 180/1251] eta: 0:11:34 lr: 0.000361 loss: 3.3450 (3.1900) grad_norm: 1.6876 (1.7676) time: 0.6249 [2021-03-27 15:03:47 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 190/1251] eta: 0:11:26 lr: 0.000361 loss: 3.1959 (3.1816) grad_norm: 1.6963 (1.7687) time: 0.6253 [2021-03-27 15:03:54 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 200/1251] eta: 0:11:19 lr: 0.000361 loss: 3.1959 (3.1814) grad_norm: 1.7398 (1.7694) time: 0.6310 [2021-03-27 15:04:00 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 210/1251] eta: 0:11:11 lr: 0.000361 loss: 3.1781 (3.1766) grad_norm: 1.7370 (1.7681) time: 0.6289 [2021-03-27 15:04:06 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 220/1251] eta: 0:11:04 lr: 0.000361 loss: 3.1723 (3.1683) grad_norm: 1.6662 (1.7705) time: 0.6247 [2021-03-27 15:04:12 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 230/1251] eta: 0:10:57 lr: 0.000361 loss: 3.0862 (3.1648) grad_norm: 1.6112 (1.7646) time: 0.6249 [2021-03-27 15:04:18 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 240/1251] eta: 0:10:49 lr: 0.000361 loss: 3.0700 (3.1592) grad_norm: 1.6063 (1.7636) time: 0.6234 [2021-03-27 15:04:25 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 250/1251] eta: 0:10:42 lr: 0.000361 loss: 3.1136 (3.1521) grad_norm: 1.6200 (1.7604) time: 0.6244 [2021-03-27 15:04:31 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 260/1251] eta: 0:10:35 lr: 0.000361 loss: 3.1680 (3.1559) grad_norm: 1.7030 (1.7591) time: 0.6248 [2021-03-27 15:04:37 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 270/1251] eta: 0:10:28 lr: 0.000361 loss: 3.3517 (3.1620) grad_norm: 1.7030 (1.7581) time: 0.6239 [2021-03-27 15:04:43 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 280/1251] eta: 0:10:21 lr: 0.000361 loss: 3.1869 (3.1586) grad_norm: 1.7106 (1.7548) time: 0.6229 [2021-03-27 15:04:50 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 290/1251] eta: 0:10:14 lr: 0.000361 loss: 3.1869 (3.1585) grad_norm: 1.7106 (1.7524) time: 0.6255 [2021-03-27 15:04:56 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 300/1251] eta: 0:10:08 lr: 0.000361 loss: 3.2619 (3.1628) grad_norm: 1.6315 (1.7475) time: 0.6278 [2021-03-27 15:05:02 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 310/1251] eta: 0:10:01 lr: 0.000361 loss: 3.2890 (3.1664) grad_norm: 1.6726 (1.7486) time: 0.6299 [2021-03-27 15:05:08 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 320/1251] eta: 0:09:54 lr: 0.000361 loss: 3.3062 (3.1688) grad_norm: 1.7404 (inf) time: 0.6245 [2021-03-27 15:05:15 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 330/1251] eta: 0:09:47 lr: 0.000361 loss: 3.4020 (3.1762) grad_norm: 1.6990 (inf) time: 0.6192 [2021-03-27 15:05:21 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 340/1251] eta: 0:09:40 lr: 0.000361 loss: 3.4520 (3.1839) grad_norm: 1.6737 (inf) time: 0.6229 [2021-03-27 15:05:27 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 350/1251] eta: 0:09:33 lr: 0.000361 loss: 3.2440 (3.1773) grad_norm: 1.7802 (inf) time: 0.6221 [2021-03-27 15:05:33 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 360/1251] eta: 0:09:27 lr: 0.000361 loss: 3.0796 (3.1764) grad_norm: 1.8171 (inf) time: 0.6244 [2021-03-27 15:05:40 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 370/1251] eta: 0:09:20 lr: 0.000360 loss: 3.1629 (3.1713) grad_norm: 1.7352 (inf) time: 0.6286 [2021-03-27 15:05:46 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 380/1251] eta: 0:09:14 lr: 0.000360 loss: 3.0816 (3.1717) grad_norm: 1.6928 (inf) time: 0.6290 [2021-03-27 15:05:52 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 390/1251] eta: 0:09:07 lr: 0.000360 loss: 3.0255 (3.1627) grad_norm: 1.6929 (inf) time: 0.6257 [2021-03-27 15:05:58 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 400/1251] eta: 0:09:00 lr: 0.000360 loss: 3.0125 (3.1643) grad_norm: 1.6659 (inf) time: 0.6221 [2021-03-27 15:06:05 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 410/1251] eta: 0:08:54 lr: 0.000360 loss: 3.3499 (3.1698) grad_norm: 1.6659 (inf) time: 0.6239 [2021-03-27 15:06:11 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 420/1251] eta: 0:08:47 lr: 0.000360 loss: 3.3403 (3.1710) grad_norm: 1.6711 (inf) time: 0.6253 [2021-03-27 15:06:17 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 430/1251] eta: 0:08:41 lr: 0.000360 loss: 3.1114 (3.1661) grad_norm: 1.6647 (inf) time: 0.6285 [2021-03-27 15:06:24 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 440/1251] eta: 0:08:34 lr: 0.000360 loss: 2.9866 (3.1666) grad_norm: 1.6564 (inf) time: 0.6300 [2021-03-27 15:06:30 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 450/1251] eta: 0:08:28 lr: 0.000360 loss: 3.3733 (3.1679) grad_norm: 1.7579 (inf) time: 0.6260 [2021-03-27 15:06:36 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 460/1251] eta: 0:08:21 lr: 0.000360 loss: 3.3831 (3.1763) grad_norm: 1.8270 (inf) time: 0.6261 [2021-03-27 15:06:42 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 470/1251] eta: 0:08:15 lr: 0.000360 loss: 3.2513 (3.1759) grad_norm: 1.6891 (inf) time: 0.6285 [2021-03-27 15:06:49 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 480/1251] eta: 0:08:08 lr: 0.000360 loss: 3.1997 (3.1710) grad_norm: 1.5617 (inf) time: 0.6249 [2021-03-27 15:06:55 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 490/1251] eta: 0:08:02 lr: 0.000360 loss: 2.8685 (3.1644) grad_norm: 1.5964 (inf) time: 0.6249 [2021-03-27 15:07:01 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 500/1251] eta: 0:07:56 lr: 0.000360 loss: 3.0124 (3.1645) grad_norm: 1.6438 (inf) time: 0.6266 [2021-03-27 15:07:07 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 510/1251] eta: 0:07:49 lr: 0.000360 loss: 3.1366 (3.1620) grad_norm: 1.6210 (inf) time: 0.6260 [2021-03-27 15:07:14 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 520/1251] eta: 0:07:43 lr: 0.000360 loss: 3.0822 (3.1574) grad_norm: 1.6604 (inf) time: 0.6233 [2021-03-27 15:07:20 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 530/1251] eta: 0:07:36 lr: 0.000360 loss: 3.1440 (3.1599) grad_norm: 1.6604 (inf) time: 0.6224 [2021-03-27 15:07:26 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 540/1251] eta: 0:07:30 lr: 0.000360 loss: 3.3176 (3.1609) grad_norm: 1.6534 (inf) time: 0.6273 [2021-03-27 15:07:33 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 550/1251] eta: 0:07:24 lr: 0.000360 loss: 3.3771 (3.1604) grad_norm: 1.6680 (inf) time: 0.6371 [2021-03-27 15:07:39 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 560/1251] eta: 0:07:17 lr: 0.000360 loss: 3.1554 (3.1581) grad_norm: 1.6052 (inf) time: 0.6411 [2021-03-27 15:07:45 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 570/1251] eta: 0:07:11 lr: 0.000360 loss: 3.1554 (3.1588) grad_norm: 1.6268 (inf) time: 0.6302 [2021-03-27 15:07:51 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 580/1251] eta: 0:07:04 lr: 0.000360 loss: 3.3373 (3.1594) grad_norm: 1.6979 (inf) time: 0.6221 [2021-03-27 15:07:58 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 590/1251] eta: 0:06:58 lr: 0.000360 loss: 3.3547 (3.1613) grad_norm: 1.7211 (inf) time: 0.6290 [2021-03-27 15:08:04 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 600/1251] eta: 0:06:52 lr: 0.000360 loss: 3.3547 (3.1609) grad_norm: 1.7588 (inf) time: 0.6319 [2021-03-27 15:08:10 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 610/1251] eta: 0:06:45 lr: 0.000360 loss: 3.2946 (3.1635) grad_norm: 1.7632 (inf) time: 0.6223 [2021-03-27 15:08:17 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 620/1251] eta: 0:06:39 lr: 0.000359 loss: 3.1871 (3.1637) grad_norm: 1.8225 (inf) time: 0.6216 [2021-03-27 15:08:23 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 630/1251] eta: 0:06:32 lr: 0.000359 loss: 3.1568 (3.1631) grad_norm: 1.8288 (inf) time: 0.6253 [2021-03-27 15:08:29 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 640/1251] eta: 0:06:26 lr: 0.000359 loss: 3.1318 (3.1606) grad_norm: 1.8096 (inf) time: 0.6298 [2021-03-27 15:08:35 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 650/1251] eta: 0:06:20 lr: 0.000359 loss: 3.1169 (3.1593) grad_norm: 1.7674 (inf) time: 0.6354 [2021-03-27 15:08:42 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 660/1251] eta: 0:06:13 lr: 0.000359 loss: 3.1183 (3.1570) grad_norm: 1.6320 (inf) time: 0.6342 [2021-03-27 15:08:48 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 670/1251] eta: 0:06:07 lr: 0.000359 loss: 3.2851 (3.1587) grad_norm: 1.6320 (inf) time: 0.6289 [2021-03-27 15:08:54 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 680/1251] eta: 0:06:01 lr: 0.000359 loss: 3.3674 (3.1603) grad_norm: 1.7541 (inf) time: 0.6296 [2021-03-27 15:09:01 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 690/1251] eta: 0:05:54 lr: 0.000359 loss: 3.1197 (3.1575) grad_norm: 1.7541 (inf) time: 0.6248 [2021-03-27 15:09:07 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 700/1251] eta: 0:05:48 lr: 0.000359 loss: 3.1087 (3.1582) grad_norm: 1.8297 (inf) time: 0.6238 [2021-03-27 15:09:13 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 710/1251] eta: 0:05:42 lr: 0.000359 loss: 3.3400 (3.1618) grad_norm: 1.8200 (inf) time: 0.6284 [2021-03-27 15:09:19 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 720/1251] eta: 0:05:35 lr: 0.000359 loss: 3.3114 (3.1634) grad_norm: 1.7108 (inf) time: 0.6250 [2021-03-27 15:09:26 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 730/1251] eta: 0:05:29 lr: 0.000359 loss: 3.1876 (3.1642) grad_norm: 1.6616 (inf) time: 0.6310 [2021-03-27 15:09:32 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 740/1251] eta: 0:05:23 lr: 0.000359 loss: 3.2573 (3.1632) grad_norm: 1.6817 (inf) time: 0.6391 [2021-03-27 15:09:39 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 750/1251] eta: 0:05:16 lr: 0.000359 loss: 3.2417 (3.1636) grad_norm: 1.7066 (inf) time: 0.6443 [2021-03-27 15:09:45 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 760/1251] eta: 0:05:10 lr: 0.000359 loss: 3.1918 (3.1645) grad_norm: 1.6456 (inf) time: 0.6373 [2021-03-27 15:09:51 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 770/1251] eta: 0:05:04 lr: 0.000359 loss: 3.2516 (3.1661) grad_norm: 1.6456 (inf) time: 0.6234 [2021-03-27 15:09:57 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 780/1251] eta: 0:04:57 lr: 0.000359 loss: 3.5603 (3.1700) grad_norm: 1.7383 (inf) time: 0.6266 [2021-03-27 15:10:04 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 790/1251] eta: 0:04:51 lr: 0.000359 loss: 3.3519 (3.1700) grad_norm: 1.7696 (inf) time: 0.6265 [2021-03-27 15:10:10 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 800/1251] eta: 0:04:45 lr: 0.000359 loss: 3.3390 (3.1731) grad_norm: 1.6726 (inf) time: 0.6215 [2021-03-27 15:10:16 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 810/1251] eta: 0:04:38 lr: 0.000359 loss: 3.2092 (3.1700) grad_norm: 1.6111 (inf) time: 0.6265 [2021-03-27 15:10:22 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 820/1251] eta: 0:04:32 lr: 0.000359 loss: 3.0230 (3.1699) grad_norm: 1.6601 (inf) time: 0.6287 [2021-03-27 15:10:29 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 830/1251] eta: 0:04:26 lr: 0.000359 loss: 3.2313 (3.1712) grad_norm: 1.7042 (inf) time: 0.6344 [2021-03-27 15:10:35 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 840/1251] eta: 0:04:19 lr: 0.000359 loss: 3.3805 (3.1746) grad_norm: 1.6565 (inf) time: 0.6341 [2021-03-27 15:10:42 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 850/1251] eta: 0:04:13 lr: 0.000359 loss: 3.2757 (3.1757) grad_norm: 1.6565 (inf) time: 0.6342 [2021-03-27 15:10:48 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 860/1251] eta: 0:04:07 lr: 0.000359 loss: 3.2628 (3.1772) grad_norm: 1.6867 (inf) time: 0.6363 [2021-03-27 15:10:54 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 870/1251] eta: 0:04:00 lr: 0.000358 loss: 3.1968 (3.1758) grad_norm: 1.6939 (inf) time: 0.6293 [2021-03-27 15:11:00 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 880/1251] eta: 0:03:54 lr: 0.000358 loss: 3.2055 (3.1785) grad_norm: 1.6939 (inf) time: 0.6220 [2021-03-27 15:11:07 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 890/1251] eta: 0:03:48 lr: 0.000358 loss: 3.3441 (3.1782) grad_norm: 1.6996 (inf) time: 0.6260 [2021-03-27 15:11:13 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 900/1251] eta: 0:03:41 lr: 0.000358 loss: 3.3669 (3.1805) grad_norm: 1.7143 (inf) time: 0.6287 [2021-03-27 15:11:19 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 910/1251] eta: 0:03:35 lr: 0.000358 loss: 3.2414 (3.1787) grad_norm: 1.6575 (inf) time: 0.6200 [2021-03-27 15:11:25 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 920/1251] eta: 0:03:29 lr: 0.000358 loss: 2.9619 (3.1744) grad_norm: 1.6135 (inf) time: 0.6281 [2021-03-27 15:11:32 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 930/1251] eta: 0:03:22 lr: 0.000358 loss: 2.7028 (3.1701) grad_norm: 1.6264 (inf) time: 0.6341 [2021-03-27 15:11:38 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 940/1251] eta: 0:03:16 lr: 0.000358 loss: 3.1746 (3.1720) grad_norm: 1.6725 (inf) time: 0.6313 [2021-03-27 15:11:44 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 950/1251] eta: 0:03:10 lr: 0.000358 loss: 3.3439 (3.1732) grad_norm: 1.7264 (inf) time: 0.6306 [2021-03-27 15:11:51 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 960/1251] eta: 0:03:03 lr: 0.000358 loss: 3.4755 (3.1752) grad_norm: 1.7244 (inf) time: 0.6283 [2021-03-27 15:11:57 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 970/1251] eta: 0:02:57 lr: 0.000358 loss: 3.1896 (3.1737) grad_norm: 1.6984 (inf) time: 0.6249 [2021-03-27 15:12:03 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 980/1251] eta: 0:02:51 lr: 0.000358 loss: 2.9695 (3.1720) grad_norm: 1.7299 (inf) time: 0.6250 [2021-03-27 15:12:10 swin_base_patch4_window7_224] INFO: Epoch: [178] [ 990/1251] eta: 0:02:44 lr: 0.000358 loss: 2.8865 (3.1697) grad_norm: 1.6441 (inf) time: 0.6307 [2021-03-27 15:12:16 swin_base_patch4_window7_224] INFO: Epoch: [178] [1000/1251] eta: 0:02:38 lr: 0.000358 loss: 3.1520 (3.1708) grad_norm: 1.6309 (inf) time: 0.6305 [2021-03-27 15:12:22 swin_base_patch4_window7_224] INFO: Epoch: [178] [1010/1251] eta: 0:02:32 lr: 0.000358 loss: 3.1520 (3.1715) grad_norm: 1.6344 (inf) time: 0.6284 [2021-03-27 15:12:28 swin_base_patch4_window7_224] INFO: Epoch: [178] [1020/1251] eta: 0:02:25 lr: 0.000358 loss: 3.1061 (3.1708) grad_norm: 1.6998 (inf) time: 0.6276 [2021-03-27 15:12:35 swin_base_patch4_window7_224] INFO: Epoch: [178] [1030/1251] eta: 0:02:19 lr: 0.000358 loss: 3.3064 (3.1727) grad_norm: 1.7260 (inf) time: 0.6293 [2021-03-27 15:12:41 swin_base_patch4_window7_224] INFO: Epoch: [178] [1040/1251] eta: 0:02:13 lr: 0.000358 loss: 3.4322 (3.1748) grad_norm: 1.7545 (inf) time: 0.6323 [2021-03-27 15:12:47 swin_base_patch4_window7_224] INFO: Epoch: [178] [1050/1251] eta: 0:02:06 lr: 0.000358 loss: 3.3819 (3.1758) grad_norm: 1.7462 (inf) time: 0.6287 [2021-03-27 15:12:54 swin_base_patch4_window7_224] INFO: Epoch: [178] [1060/1251] eta: 0:02:00 lr: 0.000358 loss: 3.2743 (3.1764) grad_norm: 1.7551 (inf) time: 0.6266 [2021-03-27 15:13:00 swin_base_patch4_window7_224] INFO: Epoch: [178] [1070/1251] eta: 0:01:54 lr: 0.000358 loss: 3.3192 (3.1759) grad_norm: 1.7100 (inf) time: 0.6223 [2021-03-27 15:13:06 swin_base_patch4_window7_224] INFO: Epoch: [178] [1080/1251] eta: 0:01:47 lr: 0.000358 loss: 3.3839 (3.1770) grad_norm: 1.7011 (inf) time: 0.6261 [2021-03-27 15:13:12 swin_base_patch4_window7_224] INFO: Epoch: [178] [1090/1251] eta: 0:01:41 lr: 0.000358 loss: 3.3933 (3.1761) grad_norm: 1.7266 (inf) time: 0.6329 [2021-03-27 15:13:19 swin_base_patch4_window7_224] INFO: Epoch: [178] [1100/1251] eta: 0:01:35 lr: 0.000358 loss: 3.3730 (3.1774) grad_norm: 1.6868 (inf) time: 0.6243 [2021-03-27 15:13:25 swin_base_patch4_window7_224] INFO: Epoch: [178] [1110/1251] eta: 0:01:28 lr: 0.000358 loss: 3.3359 (3.1770) grad_norm: 1.6337 (inf) time: 0.6200 [2021-03-27 15:13:31 swin_base_patch4_window7_224] INFO: Epoch: [178] [1120/1251] eta: 0:01:22 lr: 0.000357 loss: 2.9328 (3.1741) grad_norm: 1.7527 (inf) time: 0.6251 [2021-03-27 15:13:37 swin_base_patch4_window7_224] INFO: Epoch: [178] [1130/1251] eta: 0:01:16 lr: 0.000357 loss: 2.9328 (3.1741) grad_norm: 1.8275 (inf) time: 0.6280 [2021-03-27 15:13:44 swin_base_patch4_window7_224] INFO: Epoch: [178] [1140/1251] eta: 0:01:10 lr: 0.000357 loss: 3.1787 (3.1739) grad_norm: 1.6957 (inf) time: 0.6244 [2021-03-27 15:13:50 swin_base_patch4_window7_224] INFO: Epoch: [178] [1150/1251] eta: 0:01:03 lr: 0.000357 loss: 3.1709 (3.1741) grad_norm: 1.6957 (inf) time: 0.6232 [2021-03-27 15:13:56 swin_base_patch4_window7_224] INFO: Epoch: [178] [1160/1251] eta: 0:00:57 lr: 0.000357 loss: 3.1709 (3.1743) grad_norm: 1.7619 (inf) time: 0.6271 [2021-03-27 15:14:02 swin_base_patch4_window7_224] INFO: Epoch: [178] [1170/1251] eta: 0:00:51 lr: 0.000357 loss: 3.1267 (3.1729) grad_norm: 1.7619 (inf) time: 0.6339 [2021-03-27 15:14:09 swin_base_patch4_window7_224] INFO: Epoch: [178] [1180/1251] eta: 0:00:44 lr: 0.000357 loss: 3.2009 (3.1739) grad_norm: 1.5774 (inf) time: 0.6295 [2021-03-27 15:14:15 swin_base_patch4_window7_224] INFO: Epoch: [178] [1190/1251] eta: 0:00:38 lr: 0.000357 loss: 3.2839 (3.1743) grad_norm: 1.5981 (inf) time: 0.6249 [2021-03-27 15:14:21 swin_base_patch4_window7_224] INFO: Epoch: [178] [1200/1251] eta: 0:00:32 lr: 0.000357 loss: 3.1728 (3.1734) grad_norm: 1.6957 (inf) time: 0.6263 [2021-03-27 15:14:27 swin_base_patch4_window7_224] INFO: Epoch: [178] [1210/1251] eta: 0:00:25 lr: 0.000357 loss: 3.0837 (3.1719) grad_norm: 1.6779 (inf) time: 0.6204 [2021-03-27 15:14:34 swin_base_patch4_window7_224] INFO: Epoch: [178] [1220/1251] eta: 0:00:19 lr: 0.000357 loss: 3.3677 (3.1745) grad_norm: 1.8196 (inf) time: 0.6261 [2021-03-27 15:14:40 swin_base_patch4_window7_224] INFO: Epoch: [178] [1230/1251] eta: 0:00:13 lr: 0.000357 loss: 3.3360 (3.1725) grad_norm: 1.8992 (inf) time: 0.6330 [2021-03-27 15:14:46 swin_base_patch4_window7_224] INFO: Epoch: [178] [1240/1251] eta: 0:00:06 lr: 0.000357 loss: 3.1621 (3.1719) grad_norm: 1.7995 (inf) time: 0.6226 [2021-03-27 15:14:52 swin_base_patch4_window7_224] INFO: Epoch: [178] [1250/1251] eta: 0:00:00 lr: 0.000357 loss: 3.1621 (3.1704) grad_norm: 1.7104 (inf) time: 0.6165 [2021-03-27 15:15:01 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:38 loss: 0.8795 (0.8795) acc1: 78.1250 (78.1250) acc5: 92.1875 (92.1875) [2021-03-27 15:15:04 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8589 (0.8324) acc1: 78.1250 (79.4034) acc5: 95.3125 (94.7443) [2021-03-27 15:15:06 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7637 (0.8184) acc1: 81.2500 (80.4315) acc5: 95.3125 (95.5357) [2021-03-27 15:15:08 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8051 (0.8410) acc1: 81.2500 (79.8387) acc5: 95.3125 (95.5141) [2021-03-27 15:15:10 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8814 (0.8621) acc1: 79.6875 (79.6113) acc5: 95.3125 (95.3887) [2021-03-27 15:15:11 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9274 (0.8741) acc1: 76.5625 (79.3280) acc5: 95.3125 (95.5520) [2021-03-27 15:15:22 swin_base_patch4_window7_224] INFO: * Acc@1 80.218 Acc@5 95.416 loss 0.848 [2021-03-27 15:15:22 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.2% [2021-03-27 15:15:22 swin_base_patch4_window7_224] INFO: Max accuracy: 80.23% [2021-03-27 15:15:26 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 0/1251] eta: 1:25:06 lr: 0.000357 loss: 3.1744 (3.1744) grad_norm: 1.6459 (1.6459) time: 4.0816 [2021-03-27 15:15:32 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 10/1251] eta: 0:19:54 lr: 0.000357 loss: 3.3983 (3.3283) grad_norm: 1.7714 (1.7608) time: 0.9628 [2021-03-27 15:15:39 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 20/1251] eta: 0:16:27 lr: 0.000357 loss: 3.1815 (3.2471) grad_norm: 1.7584 (1.7634) time: 0.6386 [2021-03-27 15:15:45 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 30/1251] eta: 0:15:10 lr: 0.000357 loss: 3.2909 (3.2615) grad_norm: 1.7947 (1.8367) time: 0.6266 [2021-03-27 15:15:51 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 40/1251] eta: 0:14:27 lr: 0.000357 loss: 3.4002 (3.2695) grad_norm: 1.9042 (1.8259) time: 0.6263 [2021-03-27 15:15:57 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 50/1251] eta: 0:13:59 lr: 0.000357 loss: 3.3496 (3.2196) grad_norm: 1.7858 (1.8031) time: 0.6269 [2021-03-27 15:16:04 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 60/1251] eta: 0:13:39 lr: 0.000357 loss: 3.1797 (3.1967) grad_norm: 1.7786 (1.8184) time: 0.6299 [2021-03-27 15:16:10 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 70/1251] eta: 0:13:22 lr: 0.000357 loss: 3.2077 (3.1929) grad_norm: 1.7208 (1.8021) time: 0.6298 [2021-03-27 15:16:16 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 80/1251] eta: 0:13:11 lr: 0.000357 loss: 3.3863 (3.1899) grad_norm: 1.6551 (1.8057) time: 0.6390 [2021-03-27 15:16:23 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 90/1251] eta: 0:12:58 lr: 0.000357 loss: 3.3863 (3.2020) grad_norm: 1.6949 (1.8142) time: 0.6371 [2021-03-27 15:16:29 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 100/1251] eta: 0:12:48 lr: 0.000357 loss: 3.1783 (3.1724) grad_norm: 1.8020 (1.8162) time: 0.6346 [2021-03-27 15:16:35 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 110/1251] eta: 0:12:37 lr: 0.000357 loss: 2.9859 (3.1733) grad_norm: 1.7961 (1.8133) time: 0.6362 [2021-03-27 15:16:42 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 120/1251] eta: 0:12:29 lr: 0.000357 loss: 3.2134 (3.1691) grad_norm: 1.7739 (1.8257) time: 0.6368 [2021-03-27 15:16:48 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 130/1251] eta: 0:12:20 lr: 0.000356 loss: 3.0725 (3.1641) grad_norm: 1.7381 (1.8419) time: 0.6413 [2021-03-27 15:16:55 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 140/1251] eta: 0:12:12 lr: 0.000356 loss: 3.2777 (3.1718) grad_norm: 1.6837 (1.8352) time: 0.6370 [2021-03-27 15:17:01 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 150/1251] eta: 0:12:03 lr: 0.000356 loss: 3.4606 (3.1939) grad_norm: 1.6441 (1.8236) time: 0.6338 [2021-03-27 15:17:07 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 160/1251] eta: 0:11:55 lr: 0.000356 loss: 3.4699 (3.1980) grad_norm: 1.6430 (1.8176) time: 0.6325 [2021-03-27 15:17:14 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 170/1251] eta: 0:11:47 lr: 0.000356 loss: 3.4699 (3.1953) grad_norm: 1.6734 (1.8137) time: 0.6327 [2021-03-27 15:17:20 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 180/1251] eta: 0:11:39 lr: 0.000356 loss: 3.1722 (3.1934) grad_norm: 1.6768 (1.8055) time: 0.6289 [2021-03-27 15:17:26 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 190/1251] eta: 0:11:30 lr: 0.000356 loss: 3.0128 (3.1831) grad_norm: 1.6646 (1.7988) time: 0.6257 [2021-03-27 15:17:32 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 200/1251] eta: 0:11:23 lr: 0.000356 loss: 3.1300 (3.1834) grad_norm: 1.6801 (1.8055) time: 0.6294 [2021-03-27 15:17:39 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 210/1251] eta: 0:11:16 lr: 0.000356 loss: 3.2045 (3.1877) grad_norm: 1.7779 (1.8044) time: 0.6339 [2021-03-27 15:17:45 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 220/1251] eta: 0:11:08 lr: 0.000356 loss: 3.2617 (3.1927) grad_norm: 1.6926 (1.8001) time: 0.6287 [2021-03-27 15:17:52 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 230/1251] eta: 0:11:02 lr: 0.000356 loss: 3.2617 (3.1942) grad_norm: 1.6714 (1.7974) time: 0.6406 [2021-03-27 15:17:58 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 240/1251] eta: 0:10:55 lr: 0.000356 loss: 3.1596 (3.1808) grad_norm: 1.7908 (1.7993) time: 0.6477 [2021-03-27 15:18:04 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 250/1251] eta: 0:10:48 lr: 0.000356 loss: 3.1181 (3.1820) grad_norm: 1.7912 (1.7982) time: 0.6334 [2021-03-27 15:18:11 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 260/1251] eta: 0:10:41 lr: 0.000356 loss: 3.3650 (3.1847) grad_norm: 1.7389 (1.7966) time: 0.6313 [2021-03-27 15:18:17 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 270/1251] eta: 0:10:34 lr: 0.000356 loss: 3.1678 (3.1795) grad_norm: 1.7183 (1.7967) time: 0.6307 [2021-03-27 15:18:23 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 280/1251] eta: 0:10:27 lr: 0.000356 loss: 2.8864 (3.1707) grad_norm: 1.7189 (1.7929) time: 0.6298 [2021-03-27 15:18:30 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 290/1251] eta: 0:10:20 lr: 0.000356 loss: 3.2259 (3.1736) grad_norm: 1.6947 (1.7918) time: 0.6324 [2021-03-27 15:18:36 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 300/1251] eta: 0:10:12 lr: 0.000356 loss: 3.2259 (3.1716) grad_norm: 1.6839 (1.7872) time: 0.6261 [2021-03-27 15:18:42 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 310/1251] eta: 0:10:06 lr: 0.000356 loss: 3.1172 (3.1661) grad_norm: 1.7336 (1.7903) time: 0.6312 [2021-03-27 15:18:49 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 320/1251] eta: 0:09:59 lr: 0.000356 loss: 3.1386 (3.1696) grad_norm: 1.7951 (1.7921) time: 0.6391 [2021-03-27 15:18:55 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 330/1251] eta: 0:09:53 lr: 0.000356 loss: 3.1386 (3.1647) grad_norm: 1.8263 (1.7930) time: 0.6357 [2021-03-27 15:19:01 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 340/1251] eta: 0:09:46 lr: 0.000356 loss: 3.2433 (3.1685) grad_norm: 1.7919 (1.7932) time: 0.6385 [2021-03-27 15:19:08 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 350/1251] eta: 0:09:39 lr: 0.000356 loss: 3.2986 (3.1650) grad_norm: 1.7456 (1.7917) time: 0.6359 [2021-03-27 15:19:14 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 360/1251] eta: 0:09:32 lr: 0.000356 loss: 3.1265 (3.1661) grad_norm: 1.7456 (1.7916) time: 0.6272 [2021-03-27 15:19:20 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 370/1251] eta: 0:09:26 lr: 0.000356 loss: 3.0921 (3.1645) grad_norm: 1.7881 (1.7930) time: 0.6257 [2021-03-27 15:19:26 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 380/1251] eta: 0:09:19 lr: 0.000355 loss: 3.0206 (3.1593) grad_norm: 1.6821 (1.7895) time: 0.6277 [2021-03-27 15:19:33 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 390/1251] eta: 0:09:12 lr: 0.000355 loss: 3.2358 (3.1628) grad_norm: 1.6285 (1.7871) time: 0.6282 [2021-03-27 15:19:39 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 400/1251] eta: 0:09:06 lr: 0.000355 loss: 3.2358 (3.1615) grad_norm: 1.7267 (1.7875) time: 0.6313 [2021-03-27 15:19:45 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 410/1251] eta: 0:08:59 lr: 0.000355 loss: 3.2065 (3.1642) grad_norm: 1.8219 (1.7875) time: 0.6332 [2021-03-27 15:19:52 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 420/1251] eta: 0:08:52 lr: 0.000355 loss: 3.0681 (3.1626) grad_norm: 1.7918 (1.7869) time: 0.6327 [2021-03-27 15:19:58 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 430/1251] eta: 0:08:46 lr: 0.000355 loss: 3.0879 (3.1614) grad_norm: 1.6939 (1.7852) time: 0.6300 [2021-03-27 15:20:04 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 440/1251] eta: 0:08:39 lr: 0.000355 loss: 3.2279 (3.1621) grad_norm: 1.6467 (1.7824) time: 0.6272 [2021-03-27 15:20:11 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 450/1251] eta: 0:08:32 lr: 0.000355 loss: 3.2279 (3.1634) grad_norm: 1.6467 (1.7812) time: 0.6306 [2021-03-27 15:20:17 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 460/1251] eta: 0:08:26 lr: 0.000355 loss: 3.1904 (3.1651) grad_norm: 1.6911 (1.7799) time: 0.6291 [2021-03-27 15:20:23 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 470/1251] eta: 0:08:19 lr: 0.000355 loss: 3.1191 (3.1643) grad_norm: 1.7208 (1.7800) time: 0.6259 [2021-03-27 15:20:29 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 480/1251] eta: 0:08:12 lr: 0.000355 loss: 3.1191 (3.1604) grad_norm: 1.7492 (1.7815) time: 0.6229 [2021-03-27 15:20:36 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 490/1251] eta: 0:08:06 lr: 0.000355 loss: 3.2716 (3.1597) grad_norm: 1.7492 (1.7857) time: 0.6227 [2021-03-27 15:20:42 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 500/1251] eta: 0:07:59 lr: 0.000355 loss: 3.3052 (3.1586) grad_norm: 1.6896 (1.7831) time: 0.6336 [2021-03-27 15:20:48 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 510/1251] eta: 0:07:53 lr: 0.000355 loss: 3.3704 (3.1616) grad_norm: 1.6701 (1.7830) time: 0.6356 [2021-03-27 15:20:55 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 520/1251] eta: 0:07:47 lr: 0.000355 loss: 3.3473 (3.1619) grad_norm: 1.7319 (1.7858) time: 0.6374 [2021-03-27 15:21:01 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 530/1251] eta: 0:07:40 lr: 0.000355 loss: 3.3473 (3.1603) grad_norm: 1.7549 (1.7841) time: 0.6342 [2021-03-27 15:21:07 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 540/1251] eta: 0:07:34 lr: 0.000355 loss: 3.3449 (3.1591) grad_norm: 1.7025 (1.7890) time: 0.6270 [2021-03-27 15:21:14 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 550/1251] eta: 0:07:27 lr: 0.000355 loss: 3.2804 (3.1622) grad_norm: 1.8882 (1.7919) time: 0.6371 [2021-03-27 15:21:20 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 560/1251] eta: 0:07:21 lr: 0.000355 loss: 3.2743 (3.1620) grad_norm: 1.7237 (1.7918) time: 0.6337 [2021-03-27 15:21:26 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 570/1251] eta: 0:07:14 lr: 0.000355 loss: 3.1626 (3.1629) grad_norm: 1.6747 (1.7898) time: 0.6278 [2021-03-27 15:21:33 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 580/1251] eta: 0:07:08 lr: 0.000355 loss: 3.1994 (3.1642) grad_norm: 1.6430 (1.7879) time: 0.6301 [2021-03-27 15:21:39 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 590/1251] eta: 0:07:01 lr: 0.000355 loss: 3.1994 (3.1655) grad_norm: 1.6665 (1.7876) time: 0.6261 [2021-03-27 15:21:45 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 600/1251] eta: 0:06:55 lr: 0.000355 loss: 3.1388 (3.1649) grad_norm: 1.6754 (1.7871) time: 0.6340 [2021-03-27 15:21:52 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 610/1251] eta: 0:06:48 lr: 0.000355 loss: 3.2928 (3.1705) grad_norm: 1.6515 (1.7860) time: 0.6367 [2021-03-27 15:21:58 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 620/1251] eta: 0:06:42 lr: 0.000355 loss: 3.5332 (3.1695) grad_norm: 1.7068 (1.7849) time: 0.6275 [2021-03-27 15:22:04 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 630/1251] eta: 0:06:36 lr: 0.000354 loss: 3.1324 (3.1697) grad_norm: 1.6941 (1.7828) time: 0.6317 [2021-03-27 15:22:10 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 640/1251] eta: 0:06:29 lr: 0.000354 loss: 3.2094 (3.1698) grad_norm: 1.6835 (1.7838) time: 0.6326 [2021-03-27 15:22:17 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 650/1251] eta: 0:06:23 lr: 0.000354 loss: 3.2094 (3.1711) grad_norm: 1.8011 (1.7833) time: 0.6302 [2021-03-27 15:22:23 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 660/1251] eta: 0:06:16 lr: 0.000354 loss: 3.1382 (3.1697) grad_norm: 1.7820 (1.7846) time: 0.6314 [2021-03-27 15:22:29 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 670/1251] eta: 0:06:10 lr: 0.000354 loss: 3.0247 (3.1682) grad_norm: 1.7782 (1.7849) time: 0.6300 [2021-03-27 15:22:36 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 680/1251] eta: 0:06:03 lr: 0.000354 loss: 3.0839 (3.1695) grad_norm: 1.7324 (1.7848) time: 0.6276 [2021-03-27 15:22:42 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 690/1251] eta: 0:05:57 lr: 0.000354 loss: 3.2391 (3.1689) grad_norm: 1.7571 (1.7845) time: 0.6337 [2021-03-27 15:22:48 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 700/1251] eta: 0:05:51 lr: 0.000354 loss: 3.2391 (3.1689) grad_norm: 1.7564 (1.7843) time: 0.6374 [2021-03-27 15:22:55 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 710/1251] eta: 0:05:44 lr: 0.000354 loss: 3.1340 (3.1651) grad_norm: 1.7335 (1.7849) time: 0.6338 [2021-03-27 15:23:01 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 720/1251] eta: 0:05:38 lr: 0.000354 loss: 3.1674 (3.1649) grad_norm: 1.7740 (1.7847) time: 0.6292 [2021-03-27 15:23:07 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 730/1251] eta: 0:05:31 lr: 0.000354 loss: 3.3386 (3.1673) grad_norm: 1.7287 (1.7838) time: 0.6260 [2021-03-27 15:23:14 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 740/1251] eta: 0:05:25 lr: 0.000354 loss: 3.3155 (3.1672) grad_norm: 1.6092 (1.7823) time: 0.6325 [2021-03-27 15:23:20 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 750/1251] eta: 0:05:18 lr: 0.000354 loss: 3.2371 (3.1681) grad_norm: 1.6663 (1.7815) time: 0.6316 [2021-03-27 15:23:26 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 760/1251] eta: 0:05:12 lr: 0.000354 loss: 3.2184 (3.1708) grad_norm: 1.6921 (1.7796) time: 0.6309 [2021-03-27 15:23:32 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 770/1251] eta: 0:05:06 lr: 0.000354 loss: 3.3447 (3.1715) grad_norm: 1.6226 (1.7784) time: 0.6298 [2021-03-27 15:23:39 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 780/1251] eta: 0:04:59 lr: 0.000354 loss: 3.4205 (3.1719) grad_norm: 1.6226 (1.7764) time: 0.6310 [2021-03-27 15:23:45 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 790/1251] eta: 0:04:53 lr: 0.000354 loss: 3.2065 (3.1661) grad_norm: 1.6295 (1.7765) time: 0.6312 [2021-03-27 15:23:51 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 800/1251] eta: 0:04:46 lr: 0.000354 loss: 3.0846 (3.1698) grad_norm: 1.7082 (1.7761) time: 0.6251 [2021-03-27 15:23:58 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 810/1251] eta: 0:04:40 lr: 0.000354 loss: 3.3360 (3.1684) grad_norm: 1.7198 (1.7781) time: 0.6305 [2021-03-27 15:24:04 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 820/1251] eta: 0:04:34 lr: 0.000354 loss: 3.1077 (3.1687) grad_norm: 1.6885 (1.7774) time: 0.6337 [2021-03-27 15:24:10 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 830/1251] eta: 0:04:27 lr: 0.000354 loss: 3.2652 (3.1702) grad_norm: 1.6811 (1.7774) time: 0.6327 [2021-03-27 15:24:17 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 840/1251] eta: 0:04:21 lr: 0.000354 loss: 3.3491 (3.1693) grad_norm: 1.7585 (1.7782) time: 0.6335 [2021-03-27 15:24:23 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 850/1251] eta: 0:04:15 lr: 0.000354 loss: 3.3043 (3.1667) grad_norm: 1.7801 (1.7789) time: 0.6321 [2021-03-27 15:24:29 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 860/1251] eta: 0:04:08 lr: 0.000354 loss: 3.0843 (3.1647) grad_norm: 1.7552 (1.7802) time: 0.6300 [2021-03-27 15:24:36 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 870/1251] eta: 0:04:02 lr: 0.000354 loss: 2.9478 (3.1606) grad_norm: 1.8534 (1.7818) time: 0.6338 [2021-03-27 15:24:42 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 880/1251] eta: 0:03:55 lr: 0.000353 loss: 3.2310 (3.1628) grad_norm: 1.8534 (1.7826) time: 0.6315 [2021-03-27 15:24:48 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 890/1251] eta: 0:03:49 lr: 0.000353 loss: 3.3850 (3.1631) grad_norm: 1.8080 (1.7840) time: 0.6284 [2021-03-27 15:24:55 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 900/1251] eta: 0:03:43 lr: 0.000353 loss: 3.2380 (3.1620) grad_norm: 1.7626 (1.7837) time: 0.6350 [2021-03-27 15:25:01 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 910/1251] eta: 0:03:36 lr: 0.000353 loss: 3.1417 (3.1622) grad_norm: 1.6860 (1.7829) time: 0.6307 [2021-03-27 15:25:07 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 920/1251] eta: 0:03:30 lr: 0.000353 loss: 2.9995 (3.1600) grad_norm: 1.6235 (1.7814) time: 0.6250 [2021-03-27 15:25:14 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 930/1251] eta: 0:03:24 lr: 0.000353 loss: 3.0792 (3.1604) grad_norm: 1.6189 (1.7834) time: 0.6315 [2021-03-27 15:25:20 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 940/1251] eta: 0:03:17 lr: 0.000353 loss: 3.1176 (3.1585) grad_norm: 1.6189 (1.7872) time: 0.6323 [2021-03-27 15:25:26 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 950/1251] eta: 0:03:11 lr: 0.000353 loss: 3.1405 (3.1587) grad_norm: 1.6893 (1.7867) time: 0.6316 [2021-03-27 15:25:32 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 960/1251] eta: 0:03:04 lr: 0.000353 loss: 3.2339 (3.1598) grad_norm: 1.7034 (1.7877) time: 0.6313 [2021-03-27 15:25:39 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 970/1251] eta: 0:02:58 lr: 0.000353 loss: 3.3058 (3.1613) grad_norm: 1.8703 (1.7878) time: 0.6256 [2021-03-27 15:25:45 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 980/1251] eta: 0:02:52 lr: 0.000353 loss: 3.3203 (3.1646) grad_norm: 1.7509 (1.7869) time: 0.6257 [2021-03-27 15:25:51 swin_base_patch4_window7_224] INFO: Epoch: [179] [ 990/1251] eta: 0:02:45 lr: 0.000353 loss: 3.5341 (3.1677) grad_norm: 1.6652 (1.7859) time: 0.6294 [2021-03-27 15:25:58 swin_base_patch4_window7_224] INFO: Epoch: [179] [1000/1251] eta: 0:02:39 lr: 0.000353 loss: 3.3533 (3.1664) grad_norm: 1.6629 (1.7857) time: 0.6327 [2021-03-27 15:26:04 swin_base_patch4_window7_224] INFO: Epoch: [179] [1010/1251] eta: 0:02:33 lr: 0.000353 loss: 2.9143 (3.1635) grad_norm: 1.7212 (1.7863) time: 0.6290 [2021-03-27 15:26:10 swin_base_patch4_window7_224] INFO: Epoch: [179] [1020/1251] eta: 0:02:26 lr: 0.000353 loss: 3.1045 (3.1625) grad_norm: 1.7431 (1.7862) time: 0.6304 [2021-03-27 15:26:16 swin_base_patch4_window7_224] INFO: Epoch: [179] [1030/1251] eta: 0:02:20 lr: 0.000353 loss: 3.4249 (3.1636) grad_norm: 1.6974 (1.7855) time: 0.6313 [2021-03-27 15:26:23 swin_base_patch4_window7_224] INFO: Epoch: [179] [1040/1251] eta: 0:02:13 lr: 0.000353 loss: 3.3976 (3.1594) grad_norm: 1.6683 (1.7851) time: 0.6287 [2021-03-27 15:26:29 swin_base_patch4_window7_224] INFO: Epoch: [179] [1050/1251] eta: 0:02:07 lr: 0.000353 loss: 3.2192 (3.1601) grad_norm: 1.6683 (1.7846) time: 0.6290 [2021-03-27 15:26:35 swin_base_patch4_window7_224] INFO: Epoch: [179] [1060/1251] eta: 0:02:01 lr: 0.000353 loss: 3.3059 (3.1599) grad_norm: 1.7093 (1.7849) time: 0.6291 [2021-03-27 15:26:42 swin_base_patch4_window7_224] INFO: Epoch: [179] [1070/1251] eta: 0:01:54 lr: 0.000353 loss: 3.2971 (3.1606) grad_norm: 1.7093 (1.7840) time: 0.6331 [2021-03-27 15:26:48 swin_base_patch4_window7_224] INFO: Epoch: [179] [1080/1251] eta: 0:01:48 lr: 0.000353 loss: 3.1482 (3.1596) grad_norm: 1.6672 (1.7834) time: 0.6327 [2021-03-27 15:26:54 swin_base_patch4_window7_224] INFO: Epoch: [179] [1090/1251] eta: 0:01:42 lr: 0.000353 loss: 3.3475 (3.1592) grad_norm: 1.7578 (1.7844) time: 0.6309 [2021-03-27 15:27:01 swin_base_patch4_window7_224] INFO: Epoch: [179] [1100/1251] eta: 0:01:35 lr: 0.000353 loss: 3.3475 (3.1599) grad_norm: 1.7840 (1.7842) time: 0.6278 [2021-03-27 15:27:07 swin_base_patch4_window7_224] INFO: Epoch: [179] [1110/1251] eta: 0:01:29 lr: 0.000353 loss: 3.3766 (3.1604) grad_norm: 1.6169 (1.7826) time: 0.6294 [2021-03-27 15:27:13 swin_base_patch4_window7_224] INFO: Epoch: [179] [1120/1251] eta: 0:01:23 lr: 0.000353 loss: 3.3438 (3.1603) grad_norm: 1.6169 (1.7815) time: 0.6300 [2021-03-27 15:27:20 swin_base_patch4_window7_224] INFO: Epoch: [179] [1130/1251] eta: 0:01:16 lr: 0.000353 loss: 3.0483 (3.1586) grad_norm: 1.7138 (1.7815) time: 0.6288 [2021-03-27 15:27:26 swin_base_patch4_window7_224] INFO: Epoch: [179] [1140/1251] eta: 0:01:10 lr: 0.000352 loss: 2.9684 (3.1583) grad_norm: 1.7077 (1.7807) time: 0.6271 [2021-03-27 15:27:32 swin_base_patch4_window7_224] INFO: Epoch: [179] [1150/1251] eta: 0:01:04 lr: 0.000352 loss: 3.2039 (3.1599) grad_norm: 1.7277 (1.7811) time: 0.6237 [2021-03-27 15:27:38 swin_base_patch4_window7_224] INFO: Epoch: [179] [1160/1251] eta: 0:00:57 lr: 0.000352 loss: 3.1765 (3.1599) grad_norm: 1.7708 (1.7814) time: 0.6281 [2021-03-27 15:27:45 swin_base_patch4_window7_224] INFO: Epoch: [179] [1170/1251] eta: 0:00:51 lr: 0.000352 loss: 3.0511 (3.1581) grad_norm: 1.7708 (1.7816) time: 0.6285 [2021-03-27 15:27:51 swin_base_patch4_window7_224] INFO: Epoch: [179] [1180/1251] eta: 0:00:45 lr: 0.000352 loss: 3.0511 (3.1586) grad_norm: 1.7587 (1.7817) time: 0.6274 [2021-03-27 15:27:57 swin_base_patch4_window7_224] INFO: Epoch: [179] [1190/1251] eta: 0:00:38 lr: 0.000352 loss: 3.2378 (3.1585) grad_norm: 1.7270 (1.7819) time: 0.6278 [2021-03-27 15:28:04 swin_base_patch4_window7_224] INFO: Epoch: [179] [1200/1251] eta: 0:00:32 lr: 0.000352 loss: 3.3416 (3.1601) grad_norm: 1.7180 (1.7817) time: 0.6334 [2021-03-27 15:28:10 swin_base_patch4_window7_224] INFO: Epoch: [179] [1210/1251] eta: 0:00:25 lr: 0.000352 loss: 3.2323 (3.1587) grad_norm: 1.6848 (1.7812) time: 0.6324 [2021-03-27 15:28:16 swin_base_patch4_window7_224] INFO: Epoch: [179] [1220/1251] eta: 0:00:19 lr: 0.000352 loss: 3.2323 (3.1605) grad_norm: 1.6333 (1.7798) time: 0.6240 [2021-03-27 15:28:22 swin_base_patch4_window7_224] INFO: Epoch: [179] [1230/1251] eta: 0:00:13 lr: 0.000352 loss: 3.1991 (3.1583) grad_norm: 1.6551 (1.7807) time: 0.6256 [2021-03-27 15:28:29 swin_base_patch4_window7_224] INFO: Epoch: [179] [1240/1251] eta: 0:00:06 lr: 0.000352 loss: 3.0488 (3.1586) grad_norm: 1.6946 (1.7801) time: 0.6256 [2021-03-27 15:28:35 swin_base_patch4_window7_224] INFO: Epoch: [179] [1250/1251] eta: 0:00:00 lr: 0.000352 loss: 3.1716 (3.1588) grad_norm: 1.6266 (1.7793) time: 0.6192 [2021-03-27 15:28:44 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:54 loss: 0.8970 (0.8970) acc1: 79.6875 (79.6875) acc5: 93.7500 (93.7500) [2021-03-27 15:28:46 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.7855 (0.7971) acc1: 81.2500 (81.8182) acc5: 96.8750 (95.3125) [2021-03-27 15:28:48 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.8593 (0.8645) acc1: 78.1250 (79.6131) acc5: 95.3125 (95.0149) [2021-03-27 15:28:50 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8971 (0.8488) acc1: 78.1250 (80.0403) acc5: 95.3125 (95.4637) [2021-03-27 15:28:52 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8872 (0.8533) acc1: 79.6875 (79.5732) acc5: 96.8750 (95.5030) [2021-03-27 15:28:53 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8415 (0.8511) acc1: 79.2453 (79.7760) acc5: 96.2264 (95.4560) [2021-03-27 15:29:07 swin_base_patch4_window7_224] INFO: * Acc@1 80.246 Acc@5 95.404 loss 0.838 [2021-03-27 15:29:07 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.2% [2021-03-27 15:29:07 swin_base_patch4_window7_224] INFO: Max accuracy: 80.25% [2021-03-27 15:29:11 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 0/1251] eta: 1:29:23 lr: 0.000352 loss: 3.2124 (3.2124) grad_norm: 1.8318 (1.8318) time: 4.2874 [2021-03-27 15:29:17 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 10/1251] eta: 0:20:04 lr: 0.000352 loss: 3.2746 (3.1892) grad_norm: 1.8318 (1.8653) time: 0.9707 [2021-03-27 15:29:24 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 20/1251] eta: 0:16:28 lr: 0.000352 loss: 3.1831 (3.1105) grad_norm: 1.7112 (1.8578) time: 0.6287 [2021-03-27 15:29:30 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 30/1251] eta: 0:15:10 lr: 0.000352 loss: 3.1831 (3.1894) grad_norm: 1.7112 (1.8154) time: 0.6222 [2021-03-27 15:29:36 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 40/1251] eta: 0:14:30 lr: 0.000352 loss: 3.4655 (3.2182) grad_norm: 1.7219 (1.8083) time: 0.6301 [2021-03-27 15:29:43 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 50/1251] eta: 0:14:02 lr: 0.000352 loss: 3.1152 (3.1615) grad_norm: 1.7194 (1.7837) time: 0.6330 [2021-03-27 15:29:49 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 60/1251] eta: 0:13:40 lr: 0.000352 loss: 2.9486 (3.1230) grad_norm: 1.6051 (1.7977) time: 0.6277 [2021-03-27 15:29:55 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 70/1251] eta: 0:13:23 lr: 0.000352 loss: 3.3309 (3.1586) grad_norm: 1.7297 (1.7938) time: 0.6274 [2021-03-27 15:30:01 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 80/1251] eta: 0:13:09 lr: 0.000352 loss: 3.4045 (3.1729) grad_norm: 1.7637 (1.7957) time: 0.6314 [2021-03-27 15:30:08 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 90/1251] eta: 0:12:57 lr: 0.000352 loss: 3.1784 (3.1502) grad_norm: 1.7440 (1.7906) time: 0.6315 [2021-03-27 15:30:14 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 100/1251] eta: 0:12:45 lr: 0.000352 loss: 3.2093 (3.1709) grad_norm: 1.7099 (1.7801) time: 0.6276 [2021-03-27 15:30:20 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 110/1251] eta: 0:12:35 lr: 0.000352 loss: 3.2423 (3.1648) grad_norm: 1.6798 (1.7803) time: 0.6275 [2021-03-27 15:30:26 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 120/1251] eta: 0:12:25 lr: 0.000352 loss: 3.0548 (3.1501) grad_norm: 1.7320 (1.7757) time: 0.6277 [2021-03-27 15:30:33 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 130/1251] eta: 0:12:15 lr: 0.000352 loss: 3.0113 (3.1463) grad_norm: 1.6825 (1.7710) time: 0.6217 [2021-03-27 15:30:39 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 140/1251] eta: 0:12:07 lr: 0.000351 loss: 3.2961 (3.1508) grad_norm: 1.6420 (1.7697) time: 0.6301 [2021-03-27 15:30:45 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 150/1251] eta: 0:11:58 lr: 0.000351 loss: 3.3206 (3.1456) grad_norm: 1.6579 (1.7718) time: 0.6331 [2021-03-27 15:30:52 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 160/1251] eta: 0:11:50 lr: 0.000351 loss: 3.2104 (3.1370) grad_norm: 1.7402 (1.7730) time: 0.6247 [2021-03-27 15:30:58 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 170/1251] eta: 0:11:43 lr: 0.000351 loss: 2.9787 (3.1387) grad_norm: 1.7123 (1.7635) time: 0.6310 [2021-03-27 15:31:04 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 180/1251] eta: 0:11:35 lr: 0.000351 loss: 3.3544 (3.1508) grad_norm: 1.6272 (1.7639) time: 0.6346 [2021-03-27 15:31:11 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 190/1251] eta: 0:11:28 lr: 0.000351 loss: 3.3854 (3.1555) grad_norm: 1.7197 (1.7632) time: 0.6318 [2021-03-27 15:31:17 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 200/1251] eta: 0:11:20 lr: 0.000351 loss: 3.3798 (3.1673) grad_norm: 1.6703 (1.7623) time: 0.6296 [2021-03-27 15:31:23 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 210/1251] eta: 0:11:12 lr: 0.000351 loss: 3.2867 (3.1601) grad_norm: 1.6349 (1.7576) time: 0.6263 [2021-03-27 15:31:29 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 220/1251] eta: 0:11:05 lr: 0.000351 loss: 3.2058 (3.1627) grad_norm: 1.6010 (1.7505) time: 0.6280 [2021-03-27 15:31:36 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 230/1251] eta: 0:10:58 lr: 0.000351 loss: 3.1837 (3.1621) grad_norm: 1.6121 (1.7486) time: 0.6274 [2021-03-27 15:31:42 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 240/1251] eta: 0:10:51 lr: 0.000351 loss: 3.1571 (3.1488) grad_norm: 1.6731 (1.7493) time: 0.6253 [2021-03-27 15:31:48 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 250/1251] eta: 0:10:43 lr: 0.000351 loss: 3.0391 (3.1547) grad_norm: 1.6901 (1.7469) time: 0.6270 [2021-03-27 15:31:55 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 260/1251] eta: 0:10:37 lr: 0.000351 loss: 3.1015 (3.1524) grad_norm: 1.6728 (1.7447) time: 0.6292 [2021-03-27 15:32:01 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 270/1251] eta: 0:10:30 lr: 0.000351 loss: 3.1015 (3.1519) grad_norm: 1.6840 (1.7470) time: 0.6323 [2021-03-27 15:32:07 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 280/1251] eta: 0:10:23 lr: 0.000351 loss: 3.1909 (3.1500) grad_norm: 1.7327 (1.7485) time: 0.6305 [2021-03-27 15:32:13 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 290/1251] eta: 0:10:16 lr: 0.000351 loss: 3.0881 (3.1455) grad_norm: 1.7334 (1.7563) time: 0.6303 [2021-03-27 15:32:20 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 300/1251] eta: 0:10:09 lr: 0.000351 loss: 3.0121 (3.1427) grad_norm: 1.5935 (1.7523) time: 0.6298 [2021-03-27 15:32:26 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 310/1251] eta: 0:10:02 lr: 0.000351 loss: 3.0843 (3.1408) grad_norm: 1.6828 (1.7526) time: 0.6273 [2021-03-27 15:32:32 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 320/1251] eta: 0:09:56 lr: 0.000351 loss: 2.9055 (3.1288) grad_norm: 1.6828 (1.7498) time: 0.6282 [2021-03-27 15:32:39 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 330/1251] eta: 0:09:49 lr: 0.000351 loss: 3.0308 (3.1360) grad_norm: 1.7176 (1.7510) time: 0.6327 [2021-03-27 15:32:45 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 340/1251] eta: 0:09:43 lr: 0.000351 loss: 3.3419 (3.1396) grad_norm: 1.7555 (1.7518) time: 0.6343 [2021-03-27 15:32:51 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 350/1251] eta: 0:09:36 lr: 0.000351 loss: 3.3419 (3.1447) grad_norm: 1.6938 (1.7543) time: 0.6275 [2021-03-27 15:32:58 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 360/1251] eta: 0:09:29 lr: 0.000351 loss: 3.3235 (3.1479) grad_norm: 1.6681 (1.7532) time: 0.6304 [2021-03-27 15:33:04 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 370/1251] eta: 0:09:23 lr: 0.000351 loss: 3.1307 (3.1471) grad_norm: 1.7288 (1.7529) time: 0.6317 [2021-03-27 15:33:10 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 380/1251] eta: 0:09:16 lr: 0.000351 loss: 3.0658 (3.1452) grad_norm: 1.7120 (1.7527) time: 0.6272 [2021-03-27 15:33:17 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 390/1251] eta: 0:09:09 lr: 0.000351 loss: 3.1779 (3.1473) grad_norm: 1.7517 (1.7543) time: 0.6304 [2021-03-27 15:33:23 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 400/1251] eta: 0:09:03 lr: 0.000350 loss: 3.3689 (3.1526) grad_norm: 1.8010 (1.7574) time: 0.6277 [2021-03-27 15:33:29 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 410/1251] eta: 0:08:56 lr: 0.000350 loss: 3.1789 (3.1480) grad_norm: 1.8353 (1.7599) time: 0.6232 [2021-03-27 15:33:35 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 420/1251] eta: 0:08:50 lr: 0.000350 loss: 3.0051 (3.1515) grad_norm: 1.7043 (1.7611) time: 0.6324 [2021-03-27 15:33:42 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 430/1251] eta: 0:08:43 lr: 0.000350 loss: 3.4553 (3.1541) grad_norm: 1.6623 (1.7606) time: 0.6373 [2021-03-27 15:33:48 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 440/1251] eta: 0:08:37 lr: 0.000350 loss: 3.3906 (3.1501) grad_norm: 1.6547 (1.7599) time: 0.6288 [2021-03-27 15:33:54 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 450/1251] eta: 0:08:30 lr: 0.000350 loss: 3.3292 (3.1537) grad_norm: 1.6547 (1.7579) time: 0.6272 [2021-03-27 15:34:01 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 460/1251] eta: 0:08:24 lr: 0.000350 loss: 3.2640 (3.1541) grad_norm: 1.6696 (1.7582) time: 0.6298 [2021-03-27 15:34:07 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 470/1251] eta: 0:08:17 lr: 0.000350 loss: 3.0644 (3.1479) grad_norm: 1.7810 (1.7601) time: 0.6276 [2021-03-27 15:34:13 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 480/1251] eta: 0:08:11 lr: 0.000350 loss: 3.1684 (3.1495) grad_norm: 1.7980 (1.7616) time: 0.6290 [2021-03-27 15:34:19 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 490/1251] eta: 0:08:04 lr: 0.000350 loss: 3.0315 (3.1479) grad_norm: 1.7765 (1.7629) time: 0.6303 [2021-03-27 15:34:26 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 500/1251] eta: 0:07:58 lr: 0.000350 loss: 2.8693 (3.1446) grad_norm: 1.7254 (1.7612) time: 0.6329 [2021-03-27 15:34:32 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 510/1251] eta: 0:07:51 lr: 0.000350 loss: 3.1131 (3.1470) grad_norm: 1.7274 (1.7598) time: 0.6332 [2021-03-27 15:34:39 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 520/1251] eta: 0:07:45 lr: 0.000350 loss: 3.2619 (3.1462) grad_norm: 1.7312 (1.7582) time: 0.6372 [2021-03-27 15:34:45 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 530/1251] eta: 0:07:38 lr: 0.000350 loss: 3.0719 (3.1450) grad_norm: 1.6341 (1.7566) time: 0.6351 [2021-03-27 15:34:51 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 540/1251] eta: 0:07:32 lr: 0.000350 loss: 3.0719 (3.1460) grad_norm: 1.6980 (1.7591) time: 0.6262 [2021-03-27 15:34:57 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 550/1251] eta: 0:07:25 lr: 0.000350 loss: 3.3351 (3.1486) grad_norm: 1.8364 (1.7587) time: 0.6252 [2021-03-27 15:35:04 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 560/1251] eta: 0:07:19 lr: 0.000350 loss: 3.3351 (3.1475) grad_norm: 1.8679 (1.7622) time: 0.6266 [2021-03-27 15:35:10 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 570/1251] eta: 0:07:13 lr: 0.000350 loss: 3.2464 (3.1481) grad_norm: 1.7989 (1.7611) time: 0.6302 [2021-03-27 15:35:16 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 580/1251] eta: 0:07:06 lr: 0.000350 loss: 3.3223 (3.1494) grad_norm: 1.7017 (1.7607) time: 0.6381 [2021-03-27 15:35:23 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 590/1251] eta: 0:07:00 lr: 0.000350 loss: 3.5145 (3.1512) grad_norm: 1.7696 (1.7615) time: 0.6423 [2021-03-27 15:35:29 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 600/1251] eta: 0:06:53 lr: 0.000350 loss: 3.1062 (3.1501) grad_norm: 1.7772 (1.7602) time: 0.6297 [2021-03-27 15:35:35 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 610/1251] eta: 0:06:47 lr: 0.000350 loss: 3.0862 (3.1506) grad_norm: 1.7004 (1.7598) time: 0.6208 [2021-03-27 15:35:41 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 620/1251] eta: 0:06:40 lr: 0.000350 loss: 3.1604 (3.1504) grad_norm: 1.7004 (1.7587) time: 0.6240 [2021-03-27 15:35:48 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 630/1251] eta: 0:06:34 lr: 0.000350 loss: 3.0996 (3.1503) grad_norm: 1.7118 (1.7588) time: 0.6305 [2021-03-27 15:35:54 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 640/1251] eta: 0:06:28 lr: 0.000350 loss: 3.1529 (3.1492) grad_norm: 1.7118 (1.7582) time: 0.6348 [2021-03-27 15:36:00 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 650/1251] eta: 0:06:21 lr: 0.000349 loss: 3.2403 (3.1505) grad_norm: 1.6989 (1.7583) time: 0.6336 [2021-03-27 15:36:07 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 660/1251] eta: 0:06:15 lr: 0.000349 loss: 3.2715 (3.1515) grad_norm: 1.6848 (1.7576) time: 0.6277 [2021-03-27 15:36:13 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 670/1251] eta: 0:06:08 lr: 0.000349 loss: 3.3142 (3.1531) grad_norm: 1.6500 (1.7555) time: 0.6243 [2021-03-27 15:36:19 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 680/1251] eta: 0:06:02 lr: 0.000349 loss: 3.2658 (3.1552) grad_norm: 1.6527 (1.7553) time: 0.6265 [2021-03-27 15:36:26 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 690/1251] eta: 0:05:56 lr: 0.000349 loss: 3.2510 (3.1566) grad_norm: 1.6932 (1.7564) time: 0.6300 [2021-03-27 15:36:32 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 700/1251] eta: 0:05:49 lr: 0.000349 loss: 3.3741 (3.1579) grad_norm: 1.7252 (1.7572) time: 0.6314 [2021-03-27 15:36:38 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 710/1251] eta: 0:05:43 lr: 0.000349 loss: 3.0794 (3.1561) grad_norm: 1.6160 (1.7558) time: 0.6280 [2021-03-27 15:36:44 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 720/1251] eta: 0:05:37 lr: 0.000349 loss: 3.1778 (3.1579) grad_norm: 1.6106 (1.7543) time: 0.6287 [2021-03-27 15:36:51 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 730/1251] eta: 0:05:30 lr: 0.000349 loss: 3.2936 (3.1556) grad_norm: 1.6702 (1.7542) time: 0.6342 [2021-03-27 15:36:57 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 740/1251] eta: 0:05:24 lr: 0.000349 loss: 3.1938 (3.1549) grad_norm: 1.7280 (1.7545) time: 0.6378 [2021-03-27 15:37:03 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 750/1251] eta: 0:05:17 lr: 0.000349 loss: 3.1672 (3.1540) grad_norm: 1.7763 (1.7556) time: 0.6334 [2021-03-27 15:37:10 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 760/1251] eta: 0:05:11 lr: 0.000349 loss: 3.1312 (3.1536) grad_norm: 1.6604 (1.7547) time: 0.6312 [2021-03-27 15:37:16 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 770/1251] eta: 0:05:05 lr: 0.000349 loss: 3.4155 (3.1589) grad_norm: 1.6429 (1.7543) time: 0.6365 [2021-03-27 15:37:23 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 780/1251] eta: 0:04:58 lr: 0.000349 loss: 3.4155 (3.1604) grad_norm: 1.7325 (1.7552) time: 0.6370 [2021-03-27 15:37:29 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 790/1251] eta: 0:04:52 lr: 0.000349 loss: 3.3543 (3.1606) grad_norm: 1.7680 (1.7563) time: 0.6337 [2021-03-27 15:37:35 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 800/1251] eta: 0:04:46 lr: 0.000349 loss: 3.1830 (3.1594) grad_norm: 1.7213 (1.7566) time: 0.6370 [2021-03-27 15:37:42 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 810/1251] eta: 0:04:39 lr: 0.000349 loss: 3.2232 (3.1612) grad_norm: 1.7610 (1.7579) time: 0.6353 [2021-03-27 15:37:48 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 820/1251] eta: 0:04:33 lr: 0.000349 loss: 3.4611 (3.1626) grad_norm: 1.8177 (1.7580) time: 0.6325 [2021-03-27 15:37:54 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 830/1251] eta: 0:04:27 lr: 0.000349 loss: 3.2813 (3.1623) grad_norm: 1.7567 (1.7583) time: 0.6379 [2021-03-27 15:38:01 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 840/1251] eta: 0:04:20 lr: 0.000349 loss: 3.1290 (3.1604) grad_norm: 1.7075 (1.7583) time: 0.6326 [2021-03-27 15:38:07 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 850/1251] eta: 0:04:14 lr: 0.000349 loss: 3.1857 (3.1637) grad_norm: 1.7165 (1.7589) time: 0.6238 [2021-03-27 15:38:13 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 860/1251] eta: 0:04:08 lr: 0.000349 loss: 3.1857 (3.1594) grad_norm: 1.7572 (1.7602) time: 0.6315 [2021-03-27 15:38:20 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 870/1251] eta: 0:04:01 lr: 0.000349 loss: 3.2084 (3.1606) grad_norm: 1.7539 (1.7605) time: 0.6343 [2021-03-27 15:38:26 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 880/1251] eta: 0:03:55 lr: 0.000349 loss: 3.4487 (3.1650) grad_norm: 1.8114 (1.7616) time: 0.6292 [2021-03-27 15:38:32 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 890/1251] eta: 0:03:49 lr: 0.000349 loss: 3.4945 (3.1660) grad_norm: 1.8325 (1.7625) time: 0.6377 [2021-03-27 15:38:39 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 900/1251] eta: 0:03:42 lr: 0.000348 loss: 3.3713 (3.1667) grad_norm: 1.8418 (1.7632) time: 0.6331 [2021-03-27 15:38:45 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 910/1251] eta: 0:03:36 lr: 0.000348 loss: 3.2722 (3.1667) grad_norm: 1.8704 (1.7641) time: 0.6233 [2021-03-27 15:38:51 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 920/1251] eta: 0:03:29 lr: 0.000348 loss: 3.2140 (3.1669) grad_norm: 1.8467 (1.7645) time: 0.6305 [2021-03-27 15:38:58 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 930/1251] eta: 0:03:23 lr: 0.000348 loss: 3.1523 (3.1660) grad_norm: 1.6389 (1.7631) time: 0.6388 [2021-03-27 15:39:04 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 940/1251] eta: 0:03:17 lr: 0.000348 loss: 3.1379 (3.1663) grad_norm: 1.6287 (1.7629) time: 0.6379 [2021-03-27 15:39:10 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 950/1251] eta: 0:03:10 lr: 0.000348 loss: 2.9569 (3.1617) grad_norm: 1.8700 (1.7652) time: 0.6330 [2021-03-27 15:39:17 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 960/1251] eta: 0:03:04 lr: 0.000348 loss: 2.9569 (3.1639) grad_norm: 1.9579 (1.7674) time: 0.6320 [2021-03-27 15:39:23 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 970/1251] eta: 0:02:58 lr: 0.000348 loss: 3.0536 (3.1619) grad_norm: 1.8837 (1.7685) time: 0.6280 [2021-03-27 15:39:29 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 980/1251] eta: 0:02:51 lr: 0.000348 loss: 3.0889 (3.1628) grad_norm: 1.8275 (1.7698) time: 0.6257 [2021-03-27 15:39:35 swin_base_patch4_window7_224] INFO: Epoch: [180] [ 990/1251] eta: 0:02:45 lr: 0.000348 loss: 3.2466 (3.1613) grad_norm: 1.7419 (1.7690) time: 0.6287 [2021-03-27 15:39:42 swin_base_patch4_window7_224] INFO: Epoch: [180] [1000/1251] eta: 0:02:39 lr: 0.000348 loss: 3.3300 (3.1597) grad_norm: 1.6627 (1.7689) time: 0.6340 [2021-03-27 15:39:48 swin_base_patch4_window7_224] INFO: Epoch: [180] [1010/1251] eta: 0:02:32 lr: 0.000348 loss: 3.2632 (3.1608) grad_norm: 1.7028 (1.7695) time: 0.6321 [2021-03-27 15:39:54 swin_base_patch4_window7_224] INFO: Epoch: [180] [1020/1251] eta: 0:02:26 lr: 0.000348 loss: 3.2297 (3.1601) grad_norm: 1.7019 (1.7686) time: 0.6310 [2021-03-27 15:40:01 swin_base_patch4_window7_224] INFO: Epoch: [180] [1030/1251] eta: 0:02:20 lr: 0.000348 loss: 3.2580 (3.1587) grad_norm: 1.7003 (1.7685) time: 0.6318 [2021-03-27 15:40:07 swin_base_patch4_window7_224] INFO: Epoch: [180] [1040/1251] eta: 0:02:13 lr: 0.000348 loss: 3.2580 (3.1584) grad_norm: 1.7570 (1.7684) time: 0.6241 [2021-03-27 15:40:13 swin_base_patch4_window7_224] INFO: Epoch: [180] [1050/1251] eta: 0:02:07 lr: 0.000348 loss: 3.2152 (3.1601) grad_norm: 1.7182 (1.7691) time: 0.6236 [2021-03-27 15:40:19 swin_base_patch4_window7_224] INFO: Epoch: [180] [1060/1251] eta: 0:02:01 lr: 0.000348 loss: 3.3972 (3.1618) grad_norm: 1.6528 (1.7684) time: 0.6262 [2021-03-27 15:40:26 swin_base_patch4_window7_224] INFO: Epoch: [180] [1070/1251] eta: 0:01:54 lr: 0.000348 loss: 3.3972 (3.1626) grad_norm: 1.6590 (1.7679) time: 0.6284 [2021-03-27 15:40:32 swin_base_patch4_window7_224] INFO: Epoch: [180] [1080/1251] eta: 0:01:48 lr: 0.000348 loss: 3.1787 (3.1623) grad_norm: 1.6590 (1.7670) time: 0.6290 [2021-03-27 15:40:38 swin_base_patch4_window7_224] INFO: Epoch: [180] [1090/1251] eta: 0:01:42 lr: 0.000348 loss: 3.1400 (3.1623) grad_norm: 1.6990 (1.7698) time: 0.6251 [2021-03-27 15:40:45 swin_base_patch4_window7_224] INFO: Epoch: [180] [1100/1251] eta: 0:01:35 lr: 0.000348 loss: 3.3261 (3.1649) grad_norm: 1.7531 (1.7707) time: 0.6293 [2021-03-27 15:40:51 swin_base_patch4_window7_224] INFO: Epoch: [180] [1110/1251] eta: 0:01:29 lr: 0.000348 loss: 3.4487 (3.1648) grad_norm: 1.7531 (1.7708) time: 0.6333 [2021-03-27 15:40:57 swin_base_patch4_window7_224] INFO: Epoch: [180] [1120/1251] eta: 0:01:22 lr: 0.000348 loss: 3.2070 (3.1632) grad_norm: 1.7445 (1.7707) time: 0.6296 [2021-03-27 15:41:03 swin_base_patch4_window7_224] INFO: Epoch: [180] [1130/1251] eta: 0:01:16 lr: 0.000348 loss: 3.2452 (3.1658) grad_norm: 1.7360 (1.7708) time: 0.6267 [2021-03-27 15:41:10 swin_base_patch4_window7_224] INFO: Epoch: [180] [1140/1251] eta: 0:01:10 lr: 0.000348 loss: 3.3566 (3.1662) grad_norm: 1.8682 (1.7729) time: 0.6259 [2021-03-27 15:41:16 swin_base_patch4_window7_224] INFO: Epoch: [180] [1150/1251] eta: 0:01:03 lr: 0.000348 loss: 3.2423 (3.1653) grad_norm: 1.8130 (1.7726) time: 0.6269 [2021-03-27 15:41:22 swin_base_patch4_window7_224] INFO: Epoch: [180] [1160/1251] eta: 0:00:57 lr: 0.000347 loss: 3.1746 (3.1644) grad_norm: 1.6565 (1.7723) time: 0.6267 [2021-03-27 15:41:28 swin_base_patch4_window7_224] INFO: Epoch: [180] [1170/1251] eta: 0:00:51 lr: 0.000347 loss: 3.1745 (3.1641) grad_norm: 1.7202 (1.7720) time: 0.6253 [2021-03-27 15:41:35 swin_base_patch4_window7_224] INFO: Epoch: [180] [1180/1251] eta: 0:00:44 lr: 0.000347 loss: 3.2134 (3.1647) grad_norm: 1.7545 (1.7727) time: 0.6232 [2021-03-27 15:41:41 swin_base_patch4_window7_224] INFO: Epoch: [180] [1190/1251] eta: 0:00:38 lr: 0.000347 loss: 3.1600 (3.1631) grad_norm: 1.7464 (1.7729) time: 0.6332 [2021-03-27 15:41:47 swin_base_patch4_window7_224] INFO: Epoch: [180] [1200/1251] eta: 0:00:32 lr: 0.000347 loss: 3.1600 (3.1651) grad_norm: 1.7462 (1.7724) time: 0.6334 [2021-03-27 15:41:54 swin_base_patch4_window7_224] INFO: Epoch: [180] [1210/1251] eta: 0:00:25 lr: 0.000347 loss: 3.2748 (3.1650) grad_norm: 1.7084 (1.7717) time: 0.6255 [2021-03-27 15:42:00 swin_base_patch4_window7_224] INFO: Epoch: [180] [1220/1251] eta: 0:00:19 lr: 0.000347 loss: 3.3256 (3.1682) grad_norm: 1.6628 (1.7718) time: 0.6273 [2021-03-27 15:42:06 swin_base_patch4_window7_224] INFO: Epoch: [180] [1230/1251] eta: 0:00:13 lr: 0.000347 loss: 3.4375 (3.1693) grad_norm: 1.8099 (1.7736) time: 0.6312 [2021-03-27 15:42:13 swin_base_patch4_window7_224] INFO: Epoch: [180] [1240/1251] eta: 0:00:06 lr: 0.000347 loss: 3.4102 (3.1702) grad_norm: 1.7066 (1.7732) time: 0.6353 [2021-03-27 15:42:19 swin_base_patch4_window7_224] INFO: Epoch: [180] [1250/1251] eta: 0:00:00 lr: 0.000347 loss: 3.3500 (3.1707) grad_norm: 1.7132 (1.7734) time: 0.6256 [2021-03-27 15:43:42 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 0.5859 (0.5859) acc1: 87.5000 (87.5000) acc5: 100.0000 (100.0000) [2021-03-27 15:43:44 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7855 (0.8299) acc1: 79.6875 (80.2557) acc5: 98.4375 (96.5909) [2021-03-27 15:43:45 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7855 (0.8355) acc1: 79.6875 (80.2827) acc5: 96.8750 (96.5774) [2021-03-27 15:43:46 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7756 (0.8325) acc1: 79.6875 (79.9899) acc5: 96.8750 (96.1694) [2021-03-27 15:43:48 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8749 (0.8633) acc1: 78.1250 (79.4588) acc5: 95.3125 (95.6555) [2021-03-27 15:43:49 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9332 (0.8539) acc1: 76.5625 (79.8080) acc5: 95.3125 (95.8080) [2021-03-27 15:44:01 swin_base_patch4_window7_224] INFO: * Acc@1 80.098 Acc@5 95.398 loss 0.852 [2021-03-27 15:44:01 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.1% [2021-03-27 15:44:01 swin_base_patch4_window7_224] INFO: Max accuracy: 80.25% [2021-03-27 15:44:06 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 0/1251] eta: 1:30:50 lr: 0.000347 loss: 3.5458 (3.5458) grad_norm: 2.0693 (2.0693) time: 4.3572 [2021-03-27 15:44:12 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 10/1251] eta: 0:20:10 lr: 0.000347 loss: 3.3877 (3.2160) grad_norm: 1.7733 (1.8512) time: 0.9753 [2021-03-27 15:44:19 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 20/1251] eta: 0:16:45 lr: 0.000347 loss: 3.3877 (3.2758) grad_norm: 1.7149 (1.8175) time: 0.6398 [2021-03-27 15:44:25 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 30/1251] eta: 0:15:25 lr: 0.000347 loss: 3.4246 (3.2818) grad_norm: 1.7149 (1.8261) time: 0.6388 [2021-03-27 15:44:31 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 40/1251] eta: 0:14:41 lr: 0.000347 loss: 3.2463 (3.2148) grad_norm: 1.7000 (1.8076) time: 0.6354 [2021-03-27 15:44:38 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 50/1251] eta: 0:14:12 lr: 0.000347 loss: 3.2463 (3.2495) grad_norm: 1.6544 (1.7859) time: 0.6354 [2021-03-27 15:44:44 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 60/1251] eta: 0:13:50 lr: 0.000347 loss: 3.4349 (3.2513) grad_norm: 1.6483 (1.7843) time: 0.6329 [2021-03-27 15:44:50 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 70/1251] eta: 0:13:31 lr: 0.000347 loss: 3.4678 (3.2773) grad_norm: 1.7814 (1.7744) time: 0.6299 [2021-03-27 15:44:57 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 80/1251] eta: 0:13:16 lr: 0.000347 loss: 3.3511 (3.2356) grad_norm: 1.8221 (1.8003) time: 0.6300 [2021-03-27 15:45:03 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 90/1251] eta: 0:13:03 lr: 0.000347 loss: 3.2367 (3.2420) grad_norm: 1.8239 (1.8073) time: 0.6298 [2021-03-27 15:45:09 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 100/1251] eta: 0:12:51 lr: 0.000347 loss: 3.2485 (3.2418) grad_norm: 1.7877 (1.8126) time: 0.6311 [2021-03-27 15:45:15 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 110/1251] eta: 0:12:40 lr: 0.000347 loss: 3.2480 (3.2353) grad_norm: 1.7125 (1.8051) time: 0.6277 [2021-03-27 15:45:22 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 120/1251] eta: 0:12:30 lr: 0.000347 loss: 3.0948 (3.2279) grad_norm: 1.6735 (1.7965) time: 0.6298 [2021-03-27 15:45:28 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 130/1251] eta: 0:12:20 lr: 0.000347 loss: 3.1038 (3.2145) grad_norm: 1.7139 (1.8082) time: 0.6312 [2021-03-27 15:45:34 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 140/1251] eta: 0:12:12 lr: 0.000347 loss: 3.2306 (3.2230) grad_norm: 1.8100 (1.8134) time: 0.6292 [2021-03-27 15:45:41 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 150/1251] eta: 0:12:02 lr: 0.000347 loss: 3.2739 (3.2252) grad_norm: 1.7948 (1.8165) time: 0.6284 [2021-03-27 15:45:47 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 160/1251] eta: 0:11:54 lr: 0.000346 loss: 3.2981 (3.2302) grad_norm: 1.9030 (1.8270) time: 0.6267 [2021-03-27 15:45:53 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 170/1251] eta: 0:11:46 lr: 0.000346 loss: 3.4590 (3.2345) grad_norm: 1.9034 (1.8328) time: 0.6309 [2021-03-27 15:46:00 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 180/1251] eta: 0:11:38 lr: 0.000346 loss: 3.3003 (3.2352) grad_norm: 1.9274 (1.8421) time: 0.6305 [2021-03-27 15:46:06 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 190/1251] eta: 0:11:30 lr: 0.000346 loss: 3.2372 (3.2248) grad_norm: 1.8048 (1.8388) time: 0.6303 [2021-03-27 15:46:12 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 200/1251] eta: 0:11:22 lr: 0.000346 loss: 3.2832 (3.2292) grad_norm: 1.6491 (1.8308) time: 0.6270 [2021-03-27 15:46:18 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 210/1251] eta: 0:11:15 lr: 0.000346 loss: 3.3778 (3.2299) grad_norm: 1.6629 (1.8301) time: 0.6268 [2021-03-27 15:46:25 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 220/1251] eta: 0:11:08 lr: 0.000346 loss: 3.3245 (3.2276) grad_norm: 1.7200 (1.8341) time: 0.6320 [2021-03-27 15:46:31 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 230/1251] eta: 0:11:01 lr: 0.000346 loss: 3.0690 (3.2129) grad_norm: 1.7639 (1.8320) time: 0.6331 [2021-03-27 15:46:37 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 240/1251] eta: 0:10:54 lr: 0.000346 loss: 2.8918 (3.2040) grad_norm: 1.7825 (1.8310) time: 0.6347 [2021-03-27 15:46:44 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 250/1251] eta: 0:10:46 lr: 0.000346 loss: 3.0906 (3.2001) grad_norm: 1.7076 (1.8283) time: 0.6304 [2021-03-27 15:46:50 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 260/1251] eta: 0:10:39 lr: 0.000346 loss: 3.1518 (3.1922) grad_norm: 1.6171 (1.8242) time: 0.6252 [2021-03-27 15:46:56 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 270/1251] eta: 0:10:32 lr: 0.000346 loss: 2.9920 (3.1875) grad_norm: 1.7184 (1.8285) time: 0.6282 [2021-03-27 15:47:03 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 280/1251] eta: 0:10:26 lr: 0.000346 loss: 3.1128 (3.1843) grad_norm: 1.8475 (1.8302) time: 0.6403 [2021-03-27 15:47:09 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 290/1251] eta: 0:10:19 lr: 0.000346 loss: 3.1818 (3.1883) grad_norm: 1.6857 (1.8242) time: 0.6387 [2021-03-27 15:47:15 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 300/1251] eta: 0:10:12 lr: 0.000346 loss: 3.2168 (3.1870) grad_norm: 1.5947 (1.8193) time: 0.6291 [2021-03-27 15:47:22 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 310/1251] eta: 0:10:05 lr: 0.000346 loss: 3.3695 (3.1876) grad_norm: 1.6465 (1.8152) time: 0.6329 [2021-03-27 15:47:28 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 320/1251] eta: 0:09:58 lr: 0.000346 loss: 3.3004 (3.1840) grad_norm: 1.6777 (1.8128) time: 0.6315 [2021-03-27 15:47:34 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 330/1251] eta: 0:09:51 lr: 0.000346 loss: 3.0790 (3.1806) grad_norm: 1.7611 (1.8149) time: 0.6259 [2021-03-27 15:47:40 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 340/1251] eta: 0:09:44 lr: 0.000346 loss: 3.1392 (3.1758) grad_norm: 1.9207 (1.8210) time: 0.6238 [2021-03-27 15:47:47 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 350/1251] eta: 0:09:37 lr: 0.000346 loss: 3.2146 (3.1752) grad_norm: 1.9183 (1.8206) time: 0.6229 [2021-03-27 15:47:53 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 360/1251] eta: 0:09:31 lr: 0.000346 loss: 3.1358 (3.1690) grad_norm: 1.7145 (1.8179) time: 0.6274 [2021-03-27 15:47:59 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 370/1251] eta: 0:09:24 lr: 0.000346 loss: 3.0088 (3.1666) grad_norm: 1.7726 (1.8189) time: 0.6286 [2021-03-27 15:48:06 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 380/1251] eta: 0:09:18 lr: 0.000346 loss: 3.2131 (3.1680) grad_norm: 1.9177 (1.8200) time: 0.6331 [2021-03-27 15:48:12 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 390/1251] eta: 0:09:11 lr: 0.000346 loss: 3.1845 (3.1663) grad_norm: 1.7038 (1.8198) time: 0.6370 [2021-03-27 15:48:18 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 400/1251] eta: 0:09:04 lr: 0.000346 loss: 3.1494 (3.1631) grad_norm: 1.7581 (1.8249) time: 0.6309 [2021-03-27 15:48:25 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 410/1251] eta: 0:08:58 lr: 0.000346 loss: 3.2112 (3.1668) grad_norm: 1.7998 (1.8243) time: 0.6270 [2021-03-27 15:48:31 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 420/1251] eta: 0:08:51 lr: 0.000345 loss: 3.2875 (3.1657) grad_norm: 1.6302 (1.8221) time: 0.6274 [2021-03-27 15:48:37 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 430/1251] eta: 0:08:44 lr: 0.000345 loss: 3.1752 (3.1647) grad_norm: 1.6285 (1.8209) time: 0.6294 [2021-03-27 15:48:43 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 440/1251] eta: 0:08:38 lr: 0.000345 loss: 3.2045 (3.1665) grad_norm: 1.6707 (1.8204) time: 0.6288 [2021-03-27 15:48:50 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 450/1251] eta: 0:08:31 lr: 0.000345 loss: 3.2477 (3.1665) grad_norm: 1.7320 (1.8185) time: 0.6319 [2021-03-27 15:48:56 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 460/1251] eta: 0:08:25 lr: 0.000345 loss: 3.2903 (3.1673) grad_norm: 1.7576 (1.8217) time: 0.6320 [2021-03-27 15:49:02 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 470/1251] eta: 0:08:18 lr: 0.000345 loss: 3.1572 (3.1645) grad_norm: 1.7576 (1.8213) time: 0.6271 [2021-03-27 15:49:09 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 480/1251] eta: 0:08:12 lr: 0.000345 loss: 3.3256 (3.1664) grad_norm: 1.8991 (1.8238) time: 0.6272 [2021-03-27 15:49:15 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 490/1251] eta: 0:08:05 lr: 0.000345 loss: 3.3889 (3.1693) grad_norm: 1.8121 (1.8220) time: 0.6310 [2021-03-27 15:49:21 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 500/1251] eta: 0:07:59 lr: 0.000345 loss: 3.2362 (3.1706) grad_norm: 1.7662 (1.8206) time: 0.6344 [2021-03-27 15:49:28 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 510/1251] eta: 0:07:52 lr: 0.000345 loss: 3.1067 (3.1701) grad_norm: 1.7613 (1.8209) time: 0.6352 [2021-03-27 15:49:34 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 520/1251] eta: 0:07:46 lr: 0.000345 loss: 3.1361 (3.1677) grad_norm: 1.6972 (1.8213) time: 0.6294 [2021-03-27 15:49:40 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 530/1251] eta: 0:07:39 lr: 0.000345 loss: 3.2326 (3.1710) grad_norm: 1.7342 (1.8214) time: 0.6268 [2021-03-27 15:49:47 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 540/1251] eta: 0:07:33 lr: 0.000345 loss: 3.3447 (3.1741) grad_norm: 1.8465 (1.8235) time: 0.6296 [2021-03-27 15:49:53 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 550/1251] eta: 0:07:26 lr: 0.000345 loss: 3.3075 (3.1709) grad_norm: 1.8460 (1.8242) time: 0.6288 [2021-03-27 15:49:59 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 560/1251] eta: 0:07:20 lr: 0.000345 loss: 3.1849 (3.1672) grad_norm: 1.8245 (1.8240) time: 0.6299 [2021-03-27 15:50:05 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 570/1251] eta: 0:07:13 lr: 0.000345 loss: 3.1849 (3.1670) grad_norm: 1.7697 (1.8226) time: 0.6334 [2021-03-27 15:50:12 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 580/1251] eta: 0:07:07 lr: 0.000345 loss: 3.2395 (3.1662) grad_norm: 1.7166 (1.8217) time: 0.6335 [2021-03-27 15:50:18 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 590/1251] eta: 0:07:01 lr: 0.000345 loss: 3.2395 (3.1662) grad_norm: 1.7439 (1.8223) time: 0.6347 [2021-03-27 15:50:24 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 600/1251] eta: 0:06:54 lr: 0.000345 loss: 3.2668 (3.1683) grad_norm: 1.7545 (1.8215) time: 0.6306 [2021-03-27 15:50:31 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 610/1251] eta: 0:06:48 lr: 0.000345 loss: 3.2474 (3.1682) grad_norm: 1.7720 (1.8228) time: 0.6292 [2021-03-27 15:50:37 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 620/1251] eta: 0:06:41 lr: 0.000345 loss: 3.2120 (3.1701) grad_norm: 1.8226 (1.8251) time: 0.6334 [2021-03-27 15:50:43 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 630/1251] eta: 0:06:35 lr: 0.000345 loss: 3.4082 (3.1722) grad_norm: 1.9266 (nan) time: 0.6316 [2021-03-27 15:50:50 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 640/1251] eta: 0:06:29 lr: 0.000345 loss: 3.2460 (3.1710) grad_norm: 1.9266 (nan) time: 0.6310 [2021-03-27 15:50:56 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 650/1251] eta: 0:06:22 lr: 0.000345 loss: 3.2062 (3.1685) grad_norm: 1.8497 (nan) time: 0.6342 [2021-03-27 15:51:02 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 660/1251] eta: 0:06:16 lr: 0.000345 loss: 3.2226 (3.1677) grad_norm: 1.8334 (nan) time: 0.6344 [2021-03-27 15:51:09 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 670/1251] eta: 0:06:09 lr: 0.000344 loss: 3.2226 (3.1692) grad_norm: 1.7914 (nan) time: 0.6303 [2021-03-27 15:51:15 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 680/1251] eta: 0:06:03 lr: 0.000344 loss: 3.4689 (3.1726) grad_norm: 1.7525 (nan) time: 0.6264 [2021-03-27 15:51:21 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 690/1251] eta: 0:05:56 lr: 0.000344 loss: 3.4434 (3.1720) grad_norm: 1.7101 (nan) time: 0.6280 [2021-03-27 15:51:27 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 700/1251] eta: 0:05:50 lr: 0.000344 loss: 3.1209 (3.1713) grad_norm: 1.7108 (nan) time: 0.6275 [2021-03-27 15:51:34 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 710/1251] eta: 0:05:44 lr: 0.000344 loss: 3.1242 (3.1716) grad_norm: 1.8307 (nan) time: 0.6285 [2021-03-27 15:51:40 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 720/1251] eta: 0:05:37 lr: 0.000344 loss: 2.9466 (3.1679) grad_norm: 1.8003 (nan) time: 0.6335 [2021-03-27 15:51:46 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 730/1251] eta: 0:05:31 lr: 0.000344 loss: 2.9353 (3.1665) grad_norm: 1.7176 (nan) time: 0.6334 [2021-03-27 15:51:53 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 740/1251] eta: 0:05:24 lr: 0.000344 loss: 3.2342 (3.1657) grad_norm: 1.7292 (nan) time: 0.6353 [2021-03-27 15:51:59 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 750/1251] eta: 0:05:18 lr: 0.000344 loss: 2.9728 (3.1641) grad_norm: 1.7622 (nan) time: 0.6365 [2021-03-27 15:52:06 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 760/1251] eta: 0:05:12 lr: 0.000344 loss: 2.8402 (3.1606) grad_norm: 1.7295 (nan) time: 0.6324 [2021-03-27 15:52:12 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 770/1251] eta: 0:05:05 lr: 0.000344 loss: 3.1045 (3.1607) grad_norm: 1.7465 (nan) time: 0.6374 [2021-03-27 15:52:18 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 780/1251] eta: 0:04:59 lr: 0.000344 loss: 3.1600 (3.1611) grad_norm: 1.7528 (nan) time: 0.6367 [2021-03-27 15:52:25 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 790/1251] eta: 0:04:53 lr: 0.000344 loss: 3.2252 (3.1616) grad_norm: 1.6715 (nan) time: 0.6317 [2021-03-27 15:52:31 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 800/1251] eta: 0:04:46 lr: 0.000344 loss: 3.2697 (3.1614) grad_norm: 1.7173 (nan) time: 0.6365 [2021-03-27 15:52:37 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 810/1251] eta: 0:04:40 lr: 0.000344 loss: 3.1963 (3.1615) grad_norm: 1.7593 (nan) time: 0.6370 [2021-03-27 15:52:44 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 820/1251] eta: 0:04:34 lr: 0.000344 loss: 3.2014 (3.1618) grad_norm: 1.7524 (nan) time: 0.6350 [2021-03-27 15:52:50 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 830/1251] eta: 0:04:27 lr: 0.000344 loss: 3.2014 (3.1608) grad_norm: 1.7388 (nan) time: 0.6262 [2021-03-27 15:52:56 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 840/1251] eta: 0:04:21 lr: 0.000344 loss: 3.3159 (3.1603) grad_norm: 1.7115 (nan) time: 0.6229 [2021-03-27 15:53:02 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 850/1251] eta: 0:04:14 lr: 0.000344 loss: 3.1824 (3.1603) grad_norm: 1.7223 (nan) time: 0.6298 [2021-03-27 15:53:09 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 860/1251] eta: 0:04:08 lr: 0.000344 loss: 3.1824 (3.1588) grad_norm: 1.7223 (nan) time: 0.6278 [2021-03-27 15:53:15 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 870/1251] eta: 0:04:02 lr: 0.000344 loss: 3.4177 (3.1610) grad_norm: 1.7510 (nan) time: 0.6266 [2021-03-27 15:53:21 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 880/1251] eta: 0:03:55 lr: 0.000344 loss: 3.2433 (3.1610) grad_norm: 1.7510 (nan) time: 0.6278 [2021-03-27 15:53:28 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 890/1251] eta: 0:03:49 lr: 0.000344 loss: 3.0459 (3.1579) grad_norm: 1.7164 (nan) time: 0.6322 [2021-03-27 15:53:34 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 900/1251] eta: 0:03:42 lr: 0.000344 loss: 3.0010 (3.1551) grad_norm: 1.7099 (nan) time: 0.6338 [2021-03-27 15:53:40 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 910/1251] eta: 0:03:36 lr: 0.000344 loss: 3.0206 (3.1531) grad_norm: 1.7871 (nan) time: 0.6287 [2021-03-27 15:53:47 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 920/1251] eta: 0:03:30 lr: 0.000344 loss: 3.0221 (3.1538) grad_norm: 1.8332 (nan) time: 0.6298 [2021-03-27 15:53:53 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 930/1251] eta: 0:03:23 lr: 0.000343 loss: 3.0380 (3.1512) grad_norm: 1.8160 (nan) time: 0.6334 [2021-03-27 15:53:59 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 940/1251] eta: 0:03:17 lr: 0.000343 loss: 3.0670 (3.1527) grad_norm: 1.8153 (nan) time: 0.6312 [2021-03-27 15:54:06 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 950/1251] eta: 0:03:11 lr: 0.000343 loss: 3.3815 (3.1552) grad_norm: 1.7688 (nan) time: 0.6294 [2021-03-27 15:54:12 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 960/1251] eta: 0:03:04 lr: 0.000343 loss: 3.4742 (3.1574) grad_norm: 1.7760 (nan) time: 0.6331 [2021-03-27 15:54:18 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 970/1251] eta: 0:02:58 lr: 0.000343 loss: 3.3268 (3.1575) grad_norm: 1.8091 (nan) time: 0.6291 [2021-03-27 15:54:24 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 980/1251] eta: 0:02:52 lr: 0.000343 loss: 3.2763 (3.1562) grad_norm: 1.7328 (nan) time: 0.6270 [2021-03-27 15:54:31 swin_base_patch4_window7_224] INFO: Epoch: [181] [ 990/1251] eta: 0:02:45 lr: 0.000343 loss: 3.0510 (3.1563) grad_norm: 1.6975 (nan) time: 0.6249 [2021-03-27 15:54:37 swin_base_patch4_window7_224] INFO: Epoch: [181] [1000/1251] eta: 0:02:39 lr: 0.000343 loss: 3.0510 (3.1551) grad_norm: 1.7867 (nan) time: 0.6246 [2021-03-27 15:54:43 swin_base_patch4_window7_224] INFO: Epoch: [181] [1010/1251] eta: 0:02:32 lr: 0.000343 loss: 2.9921 (3.1524) grad_norm: 1.7727 (nan) time: 0.6261 [2021-03-27 15:54:49 swin_base_patch4_window7_224] INFO: Epoch: [181] [1020/1251] eta: 0:02:26 lr: 0.000343 loss: 3.0129 (3.1544) grad_norm: 1.7639 (nan) time: 0.6298 [2021-03-27 15:54:56 swin_base_patch4_window7_224] INFO: Epoch: [181] [1030/1251] eta: 0:02:20 lr: 0.000343 loss: 3.3248 (3.1538) grad_norm: 1.7956 (nan) time: 0.6335 [2021-03-27 15:55:02 swin_base_patch4_window7_224] INFO: Epoch: [181] [1040/1251] eta: 0:02:13 lr: 0.000343 loss: 3.3248 (3.1556) grad_norm: 1.7625 (nan) time: 0.6349 [2021-03-27 15:55:08 swin_base_patch4_window7_224] INFO: Epoch: [181] [1050/1251] eta: 0:02:07 lr: 0.000343 loss: 3.4484 (3.1568) grad_norm: 1.7310 (nan) time: 0.6311 [2021-03-27 15:55:15 swin_base_patch4_window7_224] INFO: Epoch: [181] [1060/1251] eta: 0:02:01 lr: 0.000343 loss: 3.3907 (3.1586) grad_norm: 1.7295 (nan) time: 0.6247 [2021-03-27 15:55:21 swin_base_patch4_window7_224] INFO: Epoch: [181] [1070/1251] eta: 0:01:54 lr: 0.000343 loss: 3.3121 (3.1576) grad_norm: 1.6981 (nan) time: 0.6282 [2021-03-27 15:55:27 swin_base_patch4_window7_224] INFO: Epoch: [181] [1080/1251] eta: 0:01:48 lr: 0.000343 loss: 3.2710 (3.1577) grad_norm: 1.6981 (nan) time: 0.6298 [2021-03-27 15:55:34 swin_base_patch4_window7_224] INFO: Epoch: [181] [1090/1251] eta: 0:01:42 lr: 0.000343 loss: 3.2341 (3.1577) grad_norm: 1.7843 (nan) time: 0.6274 [2021-03-27 15:55:40 swin_base_patch4_window7_224] INFO: Epoch: [181] [1100/1251] eta: 0:01:35 lr: 0.000343 loss: 3.2665 (3.1594) grad_norm: 1.6632 (nan) time: 0.6274 [2021-03-27 15:55:46 swin_base_patch4_window7_224] INFO: Epoch: [181] [1110/1251] eta: 0:01:29 lr: 0.000343 loss: 3.3094 (3.1576) grad_norm: 1.6392 (nan) time: 0.6328 [2021-03-27 15:55:52 swin_base_patch4_window7_224] INFO: Epoch: [181] [1120/1251] eta: 0:01:23 lr: 0.000343 loss: 3.2470 (3.1593) grad_norm: 1.6933 (nan) time: 0.6284 [2021-03-27 15:55:59 swin_base_patch4_window7_224] INFO: Epoch: [181] [1130/1251] eta: 0:01:16 lr: 0.000343 loss: 3.1744 (3.1567) grad_norm: 1.7765 (nan) time: 0.6256 [2021-03-27 15:56:05 swin_base_patch4_window7_224] INFO: Epoch: [181] [1140/1251] eta: 0:01:10 lr: 0.000343 loss: 3.2112 (3.1577) grad_norm: 1.7425 (nan) time: 0.6300 [2021-03-27 15:56:11 swin_base_patch4_window7_224] INFO: Epoch: [181] [1150/1251] eta: 0:01:04 lr: 0.000343 loss: 3.3749 (3.1583) grad_norm: 1.7206 (nan) time: 0.6281 [2021-03-27 15:56:18 swin_base_patch4_window7_224] INFO: Epoch: [181] [1160/1251] eta: 0:00:57 lr: 0.000343 loss: 3.4658 (3.1601) grad_norm: 1.7469 (nan) time: 0.6297 [2021-03-27 15:56:24 swin_base_patch4_window7_224] INFO: Epoch: [181] [1170/1251] eta: 0:00:51 lr: 0.000343 loss: 3.4658 (3.1614) grad_norm: 1.8123 (nan) time: 0.6323 [2021-03-27 15:56:30 swin_base_patch4_window7_224] INFO: Epoch: [181] [1180/1251] eta: 0:00:44 lr: 0.000342 loss: 3.3044 (3.1611) grad_norm: 1.7693 (nan) time: 0.6275 [2021-03-27 15:56:36 swin_base_patch4_window7_224] INFO: Epoch: [181] [1190/1251] eta: 0:00:38 lr: 0.000342 loss: 3.3285 (3.1618) grad_norm: 1.6562 (nan) time: 0.6229 [2021-03-27 15:56:43 swin_base_patch4_window7_224] INFO: Epoch: [181] [1200/1251] eta: 0:00:32 lr: 0.000342 loss: 3.2204 (3.1619) grad_norm: 1.6972 (nan) time: 0.6273 [2021-03-27 15:56:49 swin_base_patch4_window7_224] INFO: Epoch: [181] [1210/1251] eta: 0:00:25 lr: 0.000342 loss: 3.0260 (3.1605) grad_norm: 1.7613 (nan) time: 0.6268 [2021-03-27 15:56:55 swin_base_patch4_window7_224] INFO: Epoch: [181] [1220/1251] eta: 0:00:19 lr: 0.000342 loss: 3.2664 (3.1619) grad_norm: 1.8443 (nan) time: 0.6254 [2021-03-27 15:57:02 swin_base_patch4_window7_224] INFO: Epoch: [181] [1230/1251] eta: 0:00:13 lr: 0.000342 loss: 3.3768 (3.1621) grad_norm: 1.8197 (nan) time: 0.6335 [2021-03-27 15:57:08 swin_base_patch4_window7_224] INFO: Epoch: [181] [1240/1251] eta: 0:00:06 lr: 0.000342 loss: 3.3508 (3.1629) grad_norm: 1.8197 (nan) time: 0.6344 [2021-03-27 15:57:14 swin_base_patch4_window7_224] INFO: Epoch: [181] [1250/1251] eta: 0:00:00 lr: 0.000342 loss: 3.2287 (3.1621) grad_norm: 1.8378 (nan) time: 0.6226 [2021-03-27 15:57:26 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:45 loss: 0.8797 (0.8797) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-27 15:57:29 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8797 (0.8505) acc1: 81.2500 (80.3977) acc5: 96.8750 (95.0284) [2021-03-27 15:57:31 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8323 (0.8537) acc1: 79.6875 (79.7619) acc5: 95.3125 (95.2381) [2021-03-27 15:57:33 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8323 (0.8667) acc1: 76.5625 (79.1331) acc5: 95.3125 (95.3629) [2021-03-27 15:57:35 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8606 (0.8572) acc1: 79.6875 (79.4207) acc5: 95.3125 (95.5030) [2021-03-27 15:57:36 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8606 (0.8690) acc1: 79.6875 (79.3920) acc5: 95.3125 (95.5200) [2021-03-27 15:57:49 swin_base_patch4_window7_224] INFO: * Acc@1 80.142 Acc@5 95.434 loss 0.844 [2021-03-27 15:57:49 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.1% [2021-03-27 15:57:49 swin_base_patch4_window7_224] INFO: Max accuracy: 80.25% [2021-03-27 15:57:54 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 0/1251] eta: 1:32:47 lr: 0.000342 loss: 2.4322 (2.4322) grad_norm: 1.9114 (1.9114) time: 4.4501 [2021-03-27 15:58:00 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 10/1251] eta: 0:20:23 lr: 0.000342 loss: 2.8281 (2.7802) grad_norm: 1.6694 (1.6968) time: 0.9860 [2021-03-27 15:58:06 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 20/1251] eta: 0:16:45 lr: 0.000342 loss: 3.2295 (3.0856) grad_norm: 1.6439 (1.6757) time: 0.6350 [2021-03-27 15:58:13 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 30/1251] eta: 0:15:22 lr: 0.000342 loss: 3.3169 (3.1492) grad_norm: 1.6439 (1.6885) time: 0.6294 [2021-03-27 15:58:19 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 40/1251] eta: 0:14:43 lr: 0.000342 loss: 3.1868 (3.1422) grad_norm: 1.7790 (1.7363) time: 0.6375 [2021-03-27 15:58:25 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 50/1251] eta: 0:14:11 lr: 0.000342 loss: 3.2332 (3.1731) grad_norm: 1.8864 (1.7790) time: 0.6368 [2021-03-27 15:58:32 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 60/1251] eta: 0:13:49 lr: 0.000342 loss: 3.2332 (3.1451) grad_norm: 1.8571 (1.7869) time: 0.6289 [2021-03-27 15:58:38 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 70/1251] eta: 0:13:31 lr: 0.000342 loss: 3.0597 (3.1315) grad_norm: 1.8127 (1.7862) time: 0.6324 [2021-03-27 15:58:44 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 80/1251] eta: 0:13:18 lr: 0.000342 loss: 3.1344 (3.1552) grad_norm: 1.8175 (1.7919) time: 0.6373 [2021-03-27 15:58:51 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 90/1251] eta: 0:13:06 lr: 0.000342 loss: 3.1499 (3.1430) grad_norm: 1.7549 (1.7950) time: 0.6422 [2021-03-27 15:58:57 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 100/1251] eta: 0:12:53 lr: 0.000342 loss: 3.3093 (3.1583) grad_norm: 1.7019 (1.7896) time: 0.6303 [2021-03-27 15:59:03 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 110/1251] eta: 0:12:42 lr: 0.000342 loss: 3.4174 (3.1643) grad_norm: 1.7001 (1.7876) time: 0.6270 [2021-03-27 15:59:10 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 120/1251] eta: 0:12:32 lr: 0.000342 loss: 3.1784 (3.1558) grad_norm: 1.7821 (1.7918) time: 0.6314 [2021-03-27 15:59:16 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 130/1251] eta: 0:12:21 lr: 0.000342 loss: 3.0860 (3.1516) grad_norm: 1.8361 (1.7998) time: 0.6252 [2021-03-27 15:59:22 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 140/1251] eta: 0:12:12 lr: 0.000342 loss: 3.1674 (3.1464) grad_norm: 1.8169 (1.7990) time: 0.6269 [2021-03-27 15:59:28 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 150/1251] eta: 0:12:04 lr: 0.000342 loss: 3.2445 (3.1554) grad_norm: 1.8391 (1.8122) time: 0.6305 [2021-03-27 15:59:35 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 160/1251] eta: 0:11:56 lr: 0.000342 loss: 3.2445 (3.1412) grad_norm: 1.9584 (1.8195) time: 0.6354 [2021-03-27 15:59:41 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 170/1251] eta: 0:11:47 lr: 0.000342 loss: 3.1423 (3.1327) grad_norm: 1.9094 (1.8202) time: 0.6321 [2021-03-27 15:59:47 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 180/1251] eta: 0:11:39 lr: 0.000342 loss: 3.2052 (3.1308) grad_norm: 1.8110 (1.8199) time: 0.6263 [2021-03-27 15:59:54 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 190/1251] eta: 0:11:31 lr: 0.000341 loss: 3.3388 (3.1468) grad_norm: 1.8098 (1.8235) time: 0.6273 [2021-03-27 16:00:00 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 200/1251] eta: 0:11:23 lr: 0.000341 loss: 3.3626 (3.1424) grad_norm: 1.8060 (1.8183) time: 0.6286 [2021-03-27 16:00:06 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 210/1251] eta: 0:11:15 lr: 0.000341 loss: 3.1755 (3.1377) grad_norm: 1.7234 (1.8185) time: 0.6258 [2021-03-27 16:00:12 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 220/1251] eta: 0:11:08 lr: 0.000341 loss: 3.3540 (3.1498) grad_norm: 1.7782 (1.8216) time: 0.6231 [2021-03-27 16:00:19 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 230/1251] eta: 0:11:00 lr: 0.000341 loss: 3.3540 (3.1486) grad_norm: 1.7827 (1.8198) time: 0.6230 [2021-03-27 16:00:25 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 240/1251] eta: 0:10:53 lr: 0.000341 loss: 2.9986 (3.1340) grad_norm: 1.8191 (1.8219) time: 0.6247 [2021-03-27 16:00:31 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 250/1251] eta: 0:10:46 lr: 0.000341 loss: 3.0056 (3.1385) grad_norm: 1.7566 (1.8171) time: 0.6295 [2021-03-27 16:00:37 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 260/1251] eta: 0:10:39 lr: 0.000341 loss: 3.3375 (3.1490) grad_norm: 1.8127 (1.8198) time: 0.6289 [2021-03-27 16:00:44 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 270/1251] eta: 0:10:32 lr: 0.000341 loss: 3.3092 (3.1453) grad_norm: 1.8313 (1.8186) time: 0.6309 [2021-03-27 16:00:50 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 280/1251] eta: 0:10:25 lr: 0.000341 loss: 3.0589 (3.1353) grad_norm: 1.7864 (1.8206) time: 0.6329 [2021-03-27 16:00:56 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 290/1251] eta: 0:10:18 lr: 0.000341 loss: 3.1586 (3.1372) grad_norm: 1.8703 (1.8207) time: 0.6302 [2021-03-27 16:01:03 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 300/1251] eta: 0:10:12 lr: 0.000341 loss: 3.2479 (3.1403) grad_norm: 1.7600 (1.8225) time: 0.6363 [2021-03-27 16:01:09 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 310/1251] eta: 0:10:05 lr: 0.000341 loss: 3.2006 (3.1438) grad_norm: 1.7379 (1.8189) time: 0.6337 [2021-03-27 16:01:15 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 320/1251] eta: 0:09:58 lr: 0.000341 loss: 3.3509 (3.1472) grad_norm: 1.6825 (1.8200) time: 0.6269 [2021-03-27 16:01:22 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 330/1251] eta: 0:09:51 lr: 0.000341 loss: 3.3952 (3.1534) grad_norm: 1.7815 (1.8202) time: 0.6266 [2021-03-27 16:01:28 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 340/1251] eta: 0:09:44 lr: 0.000341 loss: 3.3457 (3.1595) grad_norm: 1.8028 (1.8200) time: 0.6239 [2021-03-27 16:01:34 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 350/1251] eta: 0:09:37 lr: 0.000341 loss: 3.3488 (3.1662) grad_norm: 1.6655 (1.8162) time: 0.6309 [2021-03-27 16:01:41 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 360/1251] eta: 0:09:31 lr: 0.000341 loss: 3.4731 (3.1739) grad_norm: 1.6215 (1.8135) time: 0.6324 [2021-03-27 16:01:47 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 370/1251] eta: 0:09:24 lr: 0.000341 loss: 3.3468 (3.1737) grad_norm: 1.7834 (1.8156) time: 0.6247 [2021-03-27 16:01:53 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 380/1251] eta: 0:09:17 lr: 0.000341 loss: 3.3306 (3.1760) grad_norm: 1.7911 (1.8180) time: 0.6216 [2021-03-27 16:01:59 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 390/1251] eta: 0:09:10 lr: 0.000341 loss: 3.3822 (3.1787) grad_norm: 1.7721 (1.8173) time: 0.6214 [2021-03-27 16:02:05 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 400/1251] eta: 0:09:03 lr: 0.000341 loss: 3.1497 (3.1726) grad_norm: 1.7227 (1.8147) time: 0.6257 [2021-03-27 16:02:12 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 410/1251] eta: 0:08:57 lr: 0.000341 loss: 3.0654 (3.1725) grad_norm: 1.6706 (1.8109) time: 0.6257 [2021-03-27 16:02:18 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 420/1251] eta: 0:08:50 lr: 0.000341 loss: 3.3263 (3.1748) grad_norm: 1.6297 (1.8067) time: 0.6259 [2021-03-27 16:02:24 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 430/1251] eta: 0:08:43 lr: 0.000341 loss: 3.1479 (3.1673) grad_norm: 1.6523 (1.8062) time: 0.6261 [2021-03-27 16:02:31 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 440/1251] eta: 0:08:37 lr: 0.000340 loss: 2.9594 (3.1675) grad_norm: 1.7536 (1.8082) time: 0.6288 [2021-03-27 16:02:37 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 450/1251] eta: 0:08:31 lr: 0.000340 loss: 3.2263 (3.1680) grad_norm: 1.7233 (1.8052) time: 0.6324 [2021-03-27 16:02:43 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 460/1251] eta: 0:08:24 lr: 0.000340 loss: 3.2263 (3.1659) grad_norm: 1.6909 (1.8033) time: 0.6256 [2021-03-27 16:02:49 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 470/1251] eta: 0:08:17 lr: 0.000340 loss: 3.3090 (3.1697) grad_norm: 1.7046 (1.8019) time: 0.6279 [2021-03-27 16:02:56 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 480/1251] eta: 0:08:11 lr: 0.000340 loss: 3.2966 (3.1668) grad_norm: 1.6780 (1.8004) time: 0.6325 [2021-03-27 16:03:02 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 490/1251] eta: 0:08:05 lr: 0.000340 loss: 2.9917 (3.1628) grad_norm: 1.7336 (1.8030) time: 0.6331 [2021-03-27 16:03:08 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 500/1251] eta: 0:07:58 lr: 0.000340 loss: 3.1165 (3.1667) grad_norm: 1.8022 (1.8030) time: 0.6316 [2021-03-27 16:03:15 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 510/1251] eta: 0:07:52 lr: 0.000340 loss: 3.3371 (3.1683) grad_norm: 1.7608 (1.8050) time: 0.6302 [2021-03-27 16:03:21 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 520/1251] eta: 0:07:45 lr: 0.000340 loss: 3.4001 (3.1699) grad_norm: 1.7453 (1.8048) time: 0.6296 [2021-03-27 16:03:27 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 530/1251] eta: 0:07:38 lr: 0.000340 loss: 3.3732 (3.1714) grad_norm: 1.6484 (1.8033) time: 0.6248 [2021-03-27 16:03:34 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 540/1251] eta: 0:07:32 lr: 0.000340 loss: 3.3343 (3.1705) grad_norm: 1.6631 (1.8001) time: 0.6278 [2021-03-27 16:03:40 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 550/1251] eta: 0:07:26 lr: 0.000340 loss: 3.3196 (3.1728) grad_norm: 1.6804 (1.7999) time: 0.6415 [2021-03-27 16:03:46 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 560/1251] eta: 0:07:19 lr: 0.000340 loss: 3.3151 (3.1732) grad_norm: 1.7907 (1.7991) time: 0.6418 [2021-03-27 16:03:53 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 570/1251] eta: 0:07:13 lr: 0.000340 loss: 3.3151 (3.1764) grad_norm: 1.8053 (1.7982) time: 0.6351 [2021-03-27 16:03:59 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 580/1251] eta: 0:07:07 lr: 0.000340 loss: 3.3237 (3.1783) grad_norm: 1.7600 (1.7985) time: 0.6309 [2021-03-27 16:04:05 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 590/1251] eta: 0:07:00 lr: 0.000340 loss: 3.1608 (3.1770) grad_norm: 1.7143 (1.7974) time: 0.6242 [2021-03-27 16:04:12 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 600/1251] eta: 0:06:54 lr: 0.000340 loss: 3.1133 (3.1768) grad_norm: 1.7145 (1.7980) time: 0.6261 [2021-03-27 16:04:18 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 610/1251] eta: 0:06:47 lr: 0.000340 loss: 3.3969 (3.1810) grad_norm: 1.7266 (1.7960) time: 0.6249 [2021-03-27 16:04:24 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 620/1251] eta: 0:06:41 lr: 0.000340 loss: 3.1839 (3.1768) grad_norm: 1.7195 (1.7956) time: 0.6216 [2021-03-27 16:04:30 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 630/1251] eta: 0:06:34 lr: 0.000340 loss: 3.1383 (3.1762) grad_norm: 1.7333 (1.7967) time: 0.6254 [2021-03-27 16:04:36 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 640/1251] eta: 0:06:28 lr: 0.000340 loss: 3.2105 (3.1771) grad_norm: 1.6727 (1.7979) time: 0.6255 [2021-03-27 16:04:43 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 650/1251] eta: 0:06:21 lr: 0.000340 loss: 3.2105 (3.1764) grad_norm: 1.6727 (1.7983) time: 0.6231 [2021-03-27 16:04:49 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 660/1251] eta: 0:06:15 lr: 0.000340 loss: 3.1233 (3.1773) grad_norm: 1.8332 (1.8017) time: 0.6225 [2021-03-27 16:04:55 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 670/1251] eta: 0:06:08 lr: 0.000340 loss: 3.4764 (3.1808) grad_norm: 1.8662 (1.8024) time: 0.6214 [2021-03-27 16:05:01 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 680/1251] eta: 0:06:02 lr: 0.000340 loss: 3.4069 (3.1812) grad_norm: 1.7777 (1.8017) time: 0.6218 [2021-03-27 16:05:08 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 690/1251] eta: 0:05:56 lr: 0.000340 loss: 3.2302 (3.1790) grad_norm: 1.7428 (1.8061) time: 0.6282 [2021-03-27 16:05:14 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 700/1251] eta: 0:05:49 lr: 0.000339 loss: 3.2302 (3.1784) grad_norm: 1.7157 (1.8057) time: 0.6299 [2021-03-27 16:05:20 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 710/1251] eta: 0:05:43 lr: 0.000339 loss: 3.0695 (3.1769) grad_norm: 1.7132 (1.8081) time: 0.6210 [2021-03-27 16:05:27 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 720/1251] eta: 0:05:36 lr: 0.000339 loss: 3.0695 (3.1766) grad_norm: 1.8664 (1.8100) time: 0.6297 [2021-03-27 16:05:33 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 730/1251] eta: 0:05:30 lr: 0.000339 loss: 3.1254 (3.1748) grad_norm: 1.8639 (1.8099) time: 0.6341 [2021-03-27 16:05:39 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 740/1251] eta: 0:05:24 lr: 0.000339 loss: 3.1254 (3.1729) grad_norm: 1.6945 (1.8084) time: 0.6336 [2021-03-27 16:05:46 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 750/1251] eta: 0:05:17 lr: 0.000339 loss: 3.1427 (3.1735) grad_norm: 1.7424 (1.8098) time: 0.6362 [2021-03-27 16:05:52 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 760/1251] eta: 0:05:11 lr: 0.000339 loss: 3.1343 (3.1709) grad_norm: 1.7852 (1.8094) time: 0.6428 [2021-03-27 16:05:58 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 770/1251] eta: 0:05:05 lr: 0.000339 loss: 3.0953 (3.1671) grad_norm: 1.8014 (1.8118) time: 0.6381 [2021-03-27 16:06:05 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 780/1251] eta: 0:04:58 lr: 0.000339 loss: 3.0953 (3.1667) grad_norm: 1.8636 (1.8131) time: 0.6270 [2021-03-27 16:06:11 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 790/1251] eta: 0:04:52 lr: 0.000339 loss: 3.1163 (3.1626) grad_norm: 1.6948 (1.8101) time: 0.6337 [2021-03-27 16:06:17 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 800/1251] eta: 0:04:46 lr: 0.000339 loss: 3.1163 (3.1627) grad_norm: 1.6307 (1.8085) time: 0.6282 [2021-03-27 16:06:23 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 810/1251] eta: 0:04:39 lr: 0.000339 loss: 3.2413 (3.1623) grad_norm: 1.6705 (1.8078) time: 0.6236 [2021-03-27 16:06:30 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 820/1251] eta: 0:04:33 lr: 0.000339 loss: 3.2663 (3.1614) grad_norm: 1.7562 (1.8092) time: 0.6241 [2021-03-27 16:06:36 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 830/1251] eta: 0:04:26 lr: 0.000339 loss: 3.2663 (3.1602) grad_norm: 1.7296 (1.8083) time: 0.6273 [2021-03-27 16:06:42 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 840/1251] eta: 0:04:20 lr: 0.000339 loss: 3.2565 (3.1625) grad_norm: 1.6944 (1.8086) time: 0.6310 [2021-03-27 16:06:49 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 850/1251] eta: 0:04:14 lr: 0.000339 loss: 3.1061 (3.1564) grad_norm: 1.8055 (1.8093) time: 0.6247 [2021-03-27 16:06:55 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 860/1251] eta: 0:04:07 lr: 0.000339 loss: 2.7320 (3.1553) grad_norm: 1.7528 (1.8077) time: 0.6179 [2021-03-27 16:07:01 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 870/1251] eta: 0:04:01 lr: 0.000339 loss: 3.2066 (3.1550) grad_norm: 1.7505 (1.8091) time: 0.6227 [2021-03-27 16:07:07 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 880/1251] eta: 0:03:54 lr: 0.000339 loss: 3.2905 (3.1544) grad_norm: 1.7969 (1.8088) time: 0.6264 [2021-03-27 16:07:13 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 890/1251] eta: 0:03:48 lr: 0.000339 loss: 3.1837 (3.1543) grad_norm: 1.7900 (1.8085) time: 0.6236 [2021-03-27 16:07:20 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 900/1251] eta: 0:03:42 lr: 0.000339 loss: 3.1054 (3.1527) grad_norm: 1.7491 (1.8073) time: 0.6265 [2021-03-27 16:07:26 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 910/1251] eta: 0:03:35 lr: 0.000339 loss: 3.3086 (3.1582) grad_norm: 1.7585 (1.8099) time: 0.6283 [2021-03-27 16:07:32 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 920/1251] eta: 0:03:29 lr: 0.000339 loss: 3.4205 (3.1562) grad_norm: 1.8149 (1.8108) time: 0.6238 [2021-03-27 16:07:39 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 930/1251] eta: 0:03:23 lr: 0.000339 loss: 3.1190 (3.1576) grad_norm: 1.7949 (1.8115) time: 0.6250 [2021-03-27 16:07:45 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 940/1251] eta: 0:03:16 lr: 0.000339 loss: 3.2707 (3.1589) grad_norm: 1.8392 (1.8132) time: 0.6279 [2021-03-27 16:07:51 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 950/1251] eta: 0:03:10 lr: 0.000338 loss: 3.2660 (3.1570) grad_norm: 1.8858 (1.8130) time: 0.6258 [2021-03-27 16:07:57 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 960/1251] eta: 0:03:04 lr: 0.000338 loss: 3.0951 (3.1570) grad_norm: 1.7279 (1.8125) time: 0.6227 [2021-03-27 16:08:04 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 970/1251] eta: 0:02:57 lr: 0.000338 loss: 3.2848 (3.1581) grad_norm: 1.7710 (1.8136) time: 0.6284 [2021-03-27 16:08:10 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 980/1251] eta: 0:02:51 lr: 0.000338 loss: 3.1782 (3.1567) grad_norm: 1.7914 (1.8149) time: 0.6325 [2021-03-27 16:08:16 swin_base_patch4_window7_224] INFO: Epoch: [182] [ 990/1251] eta: 0:02:45 lr: 0.000338 loss: 3.0307 (3.1550) grad_norm: 1.8295 (1.8148) time: 0.6227 [2021-03-27 16:08:22 swin_base_patch4_window7_224] INFO: Epoch: [182] [1000/1251] eta: 0:02:38 lr: 0.000338 loss: 3.1925 (3.1554) grad_norm: 1.6914 (1.8139) time: 0.6262 [2021-03-27 16:08:29 swin_base_patch4_window7_224] INFO: Epoch: [182] [1010/1251] eta: 0:02:32 lr: 0.000338 loss: 3.3203 (3.1563) grad_norm: 1.6708 (1.8138) time: 0.6255 [2021-03-27 16:08:35 swin_base_patch4_window7_224] INFO: Epoch: [182] [1020/1251] eta: 0:02:26 lr: 0.000338 loss: 3.3100 (3.1542) grad_norm: 1.7415 (1.8131) time: 0.6211 [2021-03-27 16:08:41 swin_base_patch4_window7_224] INFO: Epoch: [182] [1030/1251] eta: 0:02:19 lr: 0.000338 loss: 3.0130 (3.1536) grad_norm: 1.7827 (1.8128) time: 0.6342 [2021-03-27 16:08:48 swin_base_patch4_window7_224] INFO: Epoch: [182] [1040/1251] eta: 0:02:13 lr: 0.000338 loss: 3.0393 (3.1541) grad_norm: 1.7827 (1.8127) time: 0.6360 [2021-03-27 16:08:54 swin_base_patch4_window7_224] INFO: Epoch: [182] [1050/1251] eta: 0:02:07 lr: 0.000338 loss: 3.3304 (3.1559) grad_norm: 1.7827 (1.8135) time: 0.6290 [2021-03-27 16:09:00 swin_base_patch4_window7_224] INFO: Epoch: [182] [1060/1251] eta: 0:02:00 lr: 0.000338 loss: 3.3011 (3.1567) grad_norm: 1.6969 (1.8121) time: 0.6257 [2021-03-27 16:09:06 swin_base_patch4_window7_224] INFO: Epoch: [182] [1070/1251] eta: 0:01:54 lr: 0.000338 loss: 3.3201 (3.1589) grad_norm: 1.7011 (1.8122) time: 0.6235 [2021-03-27 16:09:13 swin_base_patch4_window7_224] INFO: Epoch: [182] [1080/1251] eta: 0:01:48 lr: 0.000338 loss: 3.3714 (3.1608) grad_norm: 1.7333 (1.8116) time: 0.6302 [2021-03-27 16:09:19 swin_base_patch4_window7_224] INFO: Epoch: [182] [1090/1251] eta: 0:01:41 lr: 0.000338 loss: 3.3093 (3.1602) grad_norm: 1.7052 (1.8113) time: 0.6300 [2021-03-27 16:09:25 swin_base_patch4_window7_224] INFO: Epoch: [182] [1100/1251] eta: 0:01:35 lr: 0.000338 loss: 3.1978 (3.1614) grad_norm: 1.7730 (1.8132) time: 0.6337 [2021-03-27 16:09:32 swin_base_patch4_window7_224] INFO: Epoch: [182] [1110/1251] eta: 0:01:29 lr: 0.000338 loss: 3.1464 (3.1594) grad_norm: 1.7852 (1.8129) time: 0.6359 [2021-03-27 16:09:38 swin_base_patch4_window7_224] INFO: Epoch: [182] [1120/1251] eta: 0:01:22 lr: 0.000338 loss: 3.0430 (3.1606) grad_norm: 1.7679 (1.8117) time: 0.6291 [2021-03-27 16:09:44 swin_base_patch4_window7_224] INFO: Epoch: [182] [1130/1251] eta: 0:01:16 lr: 0.000338 loss: 3.2347 (3.1607) grad_norm: 1.6367 (1.8113) time: 0.6306 [2021-03-27 16:09:50 swin_base_patch4_window7_224] INFO: Epoch: [182] [1140/1251] eta: 0:01:10 lr: 0.000338 loss: 3.2082 (3.1609) grad_norm: 1.6367 (1.8101) time: 0.6272 [2021-03-27 16:09:57 swin_base_patch4_window7_224] INFO: Epoch: [182] [1150/1251] eta: 0:01:03 lr: 0.000338 loss: 3.2810 (3.1623) grad_norm: 1.7199 (1.8105) time: 0.6220 [2021-03-27 16:10:03 swin_base_patch4_window7_224] INFO: Epoch: [182] [1160/1251] eta: 0:00:57 lr: 0.000338 loss: 3.3156 (3.1626) grad_norm: 1.8330 (1.8105) time: 0.6251 [2021-03-27 16:10:09 swin_base_patch4_window7_224] INFO: Epoch: [182] [1170/1251] eta: 0:00:51 lr: 0.000338 loss: 3.3616 (3.1641) grad_norm: 1.6845 (1.8111) time: 0.6259 [2021-03-27 16:10:15 swin_base_patch4_window7_224] INFO: Epoch: [182] [1180/1251] eta: 0:00:44 lr: 0.000338 loss: 3.2594 (3.1645) grad_norm: 1.8444 (1.8114) time: 0.6192 [2021-03-27 16:10:22 swin_base_patch4_window7_224] INFO: Epoch: [182] [1190/1251] eta: 0:00:38 lr: 0.000338 loss: 3.2090 (3.1634) grad_norm: 1.8017 (1.8110) time: 0.6224 [2021-03-27 16:10:28 swin_base_patch4_window7_224] INFO: Epoch: [182] [1200/1251] eta: 0:00:32 lr: 0.000338 loss: 3.0611 (3.1619) grad_norm: 1.7637 (1.8111) time: 0.6245 [2021-03-27 16:10:34 swin_base_patch4_window7_224] INFO: Epoch: [182] [1210/1251] eta: 0:00:25 lr: 0.000337 loss: 3.0611 (3.1600) grad_norm: 1.8221 (1.8136) time: 0.6257 [2021-03-27 16:10:40 swin_base_patch4_window7_224] INFO: Epoch: [182] [1220/1251] eta: 0:00:19 lr: 0.000337 loss: 3.2013 (3.1605) grad_norm: 1.7622 (1.8135) time: 0.6275 [2021-03-27 16:10:47 swin_base_patch4_window7_224] INFO: Epoch: [182] [1230/1251] eta: 0:00:13 lr: 0.000337 loss: 3.2086 (3.1605) grad_norm: 1.6565 (1.8121) time: 0.6281 [2021-03-27 16:10:53 swin_base_patch4_window7_224] INFO: Epoch: [182] [1240/1251] eta: 0:00:06 lr: 0.000337 loss: 3.1782 (3.1613) grad_norm: 1.6859 (1.8121) time: 0.6307 [2021-03-27 16:10:59 swin_base_patch4_window7_224] INFO: Epoch: [182] [1250/1251] eta: 0:00:00 lr: 0.000337 loss: 3.3155 (3.1604) grad_norm: 1.8599 (1.8126) time: 0.6315 [2021-03-27 16:11:09 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:11 loss: 0.6999 (0.6999) acc1: 79.6875 (79.6875) acc5: 98.4375 (98.4375) [2021-03-27 16:11:12 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9719 (0.9570) acc1: 78.1250 (78.1250) acc5: 95.3125 (93.8920) [2021-03-27 16:11:14 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8375 (0.8891) acc1: 78.1250 (79.5387) acc5: 93.7500 (94.4940) [2021-03-27 16:11:16 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8043 (0.8625) acc1: 81.2500 (80.2419) acc5: 95.3125 (94.8589) [2021-03-27 16:11:18 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8217 (0.8598) acc1: 81.2500 (80.4878) acc5: 96.8750 (95.0838) [2021-03-27 16:11:20 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8359 (0.8568) acc1: 79.6875 (80.0000) acc5: 96.8750 (95.2960) [2021-03-27 16:11:30 swin_base_patch4_window7_224] INFO: * Acc@1 80.346 Acc@5 95.312 loss 0.849 [2021-03-27 16:11:30 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.3% [2021-03-27 16:11:30 swin_base_patch4_window7_224] INFO: Max accuracy: 80.35% [2021-03-27 16:11:34 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 0/1251] eta: 1:28:07 lr: 0.000337 loss: 2.8720 (2.8720) grad_norm: 1.6856 (1.6856) time: 4.2268 [2021-03-27 16:11:40 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 10/1251] eta: 0:19:58 lr: 0.000337 loss: 3.0320 (3.0093) grad_norm: 1.8645 (1.8847) time: 0.9659 [2021-03-27 16:11:47 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 20/1251] eta: 0:16:35 lr: 0.000337 loss: 3.0838 (3.1363) grad_norm: 1.7588 (1.9940) time: 0.6374 [2021-03-27 16:11:53 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 30/1251] eta: 0:15:17 lr: 0.000337 loss: 3.2925 (3.1199) grad_norm: 1.6976 (1.9353) time: 0.6340 [2021-03-27 16:11:59 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 40/1251] eta: 0:14:32 lr: 0.000337 loss: 3.2925 (3.1296) grad_norm: 1.6815 (1.8728) time: 0.6274 [2021-03-27 16:12:06 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 50/1251] eta: 0:14:04 lr: 0.000337 loss: 3.2889 (3.1273) grad_norm: 1.6959 (1.8762) time: 0.6286 [2021-03-27 16:12:12 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 60/1251] eta: 0:13:43 lr: 0.000337 loss: 3.2299 (3.1115) grad_norm: 1.8163 (1.8777) time: 0.6326 [2021-03-27 16:12:18 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 70/1251] eta: 0:13:25 lr: 0.000337 loss: 3.0664 (3.0951) grad_norm: 1.7826 (1.8540) time: 0.6279 [2021-03-27 16:12:24 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 80/1251] eta: 0:13:10 lr: 0.000337 loss: 3.0064 (3.0835) grad_norm: 1.6572 (1.8416) time: 0.6265 [2021-03-27 16:12:31 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 90/1251] eta: 0:12:57 lr: 0.000337 loss: 3.1481 (3.0940) grad_norm: 1.7219 (1.8455) time: 0.6255 [2021-03-27 16:12:37 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 100/1251] eta: 0:12:46 lr: 0.000337 loss: 3.1608 (3.0939) grad_norm: 1.8560 (1.8392) time: 0.6271 [2021-03-27 16:12:43 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 110/1251] eta: 0:12:35 lr: 0.000337 loss: 3.2703 (3.1114) grad_norm: 1.8096 (1.8535) time: 0.6259 [2021-03-27 16:12:49 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 120/1251] eta: 0:12:25 lr: 0.000337 loss: 3.4826 (3.1394) grad_norm: 1.7538 (1.8434) time: 0.6259 [2021-03-27 16:12:56 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 130/1251] eta: 0:12:16 lr: 0.000337 loss: 3.4582 (3.1365) grad_norm: 1.7538 (1.8345) time: 0.6278 [2021-03-27 16:13:02 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 140/1251] eta: 0:12:07 lr: 0.000337 loss: 3.3240 (3.1469) grad_norm: 1.7921 (1.8429) time: 0.6269 [2021-03-27 16:13:08 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 150/1251] eta: 0:11:59 lr: 0.000337 loss: 3.4642 (3.1600) grad_norm: 1.8569 (1.8423) time: 0.6306 [2021-03-27 16:13:15 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 160/1251] eta: 0:11:51 lr: 0.000337 loss: 3.4003 (3.1694) grad_norm: 1.7723 (1.8397) time: 0.6338 [2021-03-27 16:13:21 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 170/1251] eta: 0:11:43 lr: 0.000337 loss: 3.4003 (3.1804) grad_norm: 1.7584 (1.8357) time: 0.6364 [2021-03-27 16:13:27 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 180/1251] eta: 0:11:36 lr: 0.000337 loss: 3.2448 (3.1707) grad_norm: 1.7344 (1.8341) time: 0.6377 [2021-03-27 16:13:34 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 190/1251] eta: 0:11:29 lr: 0.000337 loss: 3.2099 (3.1759) grad_norm: 1.7581 (1.8301) time: 0.6347 [2021-03-27 16:13:40 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 200/1251] eta: 0:11:21 lr: 0.000337 loss: 3.3176 (3.1807) grad_norm: 1.7429 (1.8325) time: 0.6316 [2021-03-27 16:13:46 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 210/1251] eta: 0:11:14 lr: 0.000337 loss: 3.2798 (3.1754) grad_norm: 1.7160 (1.8275) time: 0.6345 [2021-03-27 16:13:53 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 220/1251] eta: 0:11:07 lr: 0.000336 loss: 2.9156 (3.1690) grad_norm: 1.7398 (1.8243) time: 0.6397 [2021-03-27 16:13:59 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 230/1251] eta: 0:11:00 lr: 0.000336 loss: 3.2386 (3.1744) grad_norm: 1.7332 (1.8188) time: 0.6335 [2021-03-27 16:14:05 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 240/1251] eta: 0:10:53 lr: 0.000336 loss: 3.3698 (3.1828) grad_norm: 1.7304 (1.8277) time: 0.6284 [2021-03-27 16:14:12 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 250/1251] eta: 0:10:46 lr: 0.000336 loss: 3.4533 (3.1864) grad_norm: 1.8377 (1.8338) time: 0.6306 [2021-03-27 16:14:18 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 260/1251] eta: 0:10:39 lr: 0.000336 loss: 3.2867 (3.1828) grad_norm: 1.7658 (1.8301) time: 0.6334 [2021-03-27 16:14:25 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 270/1251] eta: 0:10:32 lr: 0.000336 loss: 3.2317 (3.1825) grad_norm: 1.7009 (1.8256) time: 0.6413 [2021-03-27 16:14:31 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 280/1251] eta: 0:10:25 lr: 0.000336 loss: 3.0290 (3.1747) grad_norm: 1.6755 (1.8233) time: 0.6378 [2021-03-27 16:14:37 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 290/1251] eta: 0:10:19 lr: 0.000336 loss: 3.0270 (3.1738) grad_norm: 1.7255 (1.8241) time: 0.6304 [2021-03-27 16:14:43 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 300/1251] eta: 0:10:12 lr: 0.000336 loss: 3.3414 (3.1741) grad_norm: 1.7627 (1.8257) time: 0.6291 [2021-03-27 16:14:50 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 310/1251] eta: 0:10:05 lr: 0.000336 loss: 3.2431 (3.1716) grad_norm: 1.7324 (1.8234) time: 0.6301 [2021-03-27 16:14:56 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 320/1251] eta: 0:09:58 lr: 0.000336 loss: 3.1457 (3.1725) grad_norm: 1.6952 (1.8216) time: 0.6281 [2021-03-27 16:15:02 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 330/1251] eta: 0:09:51 lr: 0.000336 loss: 3.2383 (3.1723) grad_norm: 1.7109 (1.8212) time: 0.6247 [2021-03-27 16:15:09 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 340/1251] eta: 0:09:44 lr: 0.000336 loss: 3.1803 (3.1743) grad_norm: 1.7326 (1.8207) time: 0.6251 [2021-03-27 16:15:15 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 350/1251] eta: 0:09:37 lr: 0.000336 loss: 3.1034 (3.1631) grad_norm: 1.8071 (1.8223) time: 0.6274 [2021-03-27 16:15:21 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 360/1251] eta: 0:09:31 lr: 0.000336 loss: 3.0573 (3.1642) grad_norm: 1.7085 (1.8262) time: 0.6314 [2021-03-27 16:15:27 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 370/1251] eta: 0:09:24 lr: 0.000336 loss: 3.1610 (3.1639) grad_norm: 1.6939 (1.8237) time: 0.6300 [2021-03-27 16:15:34 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 380/1251] eta: 0:09:17 lr: 0.000336 loss: 3.2827 (3.1702) grad_norm: 1.7559 (1.8260) time: 0.6257 [2021-03-27 16:15:40 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 390/1251] eta: 0:09:11 lr: 0.000336 loss: 3.2827 (3.1659) grad_norm: 1.7715 (1.8222) time: 0.6268 [2021-03-27 16:15:46 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 400/1251] eta: 0:09:04 lr: 0.000336 loss: 2.9976 (3.1620) grad_norm: 1.6178 (1.8188) time: 0.6319 [2021-03-27 16:15:53 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 410/1251] eta: 0:08:57 lr: 0.000336 loss: 2.9978 (3.1565) grad_norm: 1.6299 (1.8199) time: 0.6274 [2021-03-27 16:15:59 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 420/1251] eta: 0:08:51 lr: 0.000336 loss: 2.9075 (3.1495) grad_norm: 1.7368 (1.8195) time: 0.6269 [2021-03-27 16:16:05 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 430/1251] eta: 0:08:44 lr: 0.000336 loss: 2.8605 (3.1434) grad_norm: 1.7226 (1.8165) time: 0.6359 [2021-03-27 16:16:12 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 440/1251] eta: 0:08:38 lr: 0.000336 loss: 2.8605 (3.1399) grad_norm: 1.7226 (1.8192) time: 0.6328 [2021-03-27 16:16:18 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 450/1251] eta: 0:08:31 lr: 0.000336 loss: 2.9495 (3.1363) grad_norm: 1.8681 (1.8199) time: 0.6278 [2021-03-27 16:16:24 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 460/1251] eta: 0:08:25 lr: 0.000336 loss: 2.9921 (3.1330) grad_norm: 1.8547 (1.8205) time: 0.6323 [2021-03-27 16:16:30 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 470/1251] eta: 0:08:18 lr: 0.000335 loss: 3.1546 (3.1328) grad_norm: 1.8076 (1.8202) time: 0.6342 [2021-03-27 16:16:37 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 480/1251] eta: 0:08:12 lr: 0.000335 loss: 3.1546 (3.1291) grad_norm: 1.7334 (1.8181) time: 0.6302 [2021-03-27 16:16:43 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 490/1251] eta: 0:08:05 lr: 0.000335 loss: 3.1398 (3.1287) grad_norm: 1.6668 (1.8168) time: 0.6246 [2021-03-27 16:16:49 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 500/1251] eta: 0:07:58 lr: 0.000335 loss: 3.1398 (3.1281) grad_norm: 1.6329 (1.8130) time: 0.6252 [2021-03-27 16:16:56 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 510/1251] eta: 0:07:52 lr: 0.000335 loss: 3.3749 (3.1331) grad_norm: 1.6329 (1.8105) time: 0.6316 [2021-03-27 16:17:02 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 520/1251] eta: 0:07:46 lr: 0.000335 loss: 3.5201 (3.1346) grad_norm: 1.6821 (1.8081) time: 0.6353 [2021-03-27 16:17:08 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 530/1251] eta: 0:07:39 lr: 0.000335 loss: 3.2376 (3.1292) grad_norm: 1.7207 (1.8082) time: 0.6321 [2021-03-27 16:17:15 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 540/1251] eta: 0:07:33 lr: 0.000335 loss: 3.2376 (3.1312) grad_norm: 1.8116 (1.8099) time: 0.6262 [2021-03-27 16:17:21 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 550/1251] eta: 0:07:26 lr: 0.000335 loss: 3.3481 (3.1359) grad_norm: 1.7623 (1.8100) time: 0.6358 [2021-03-27 16:17:27 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 560/1251] eta: 0:07:20 lr: 0.000335 loss: 3.1439 (3.1315) grad_norm: 1.7187 (1.8100) time: 0.6360 [2021-03-27 16:17:34 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 570/1251] eta: 0:07:13 lr: 0.000335 loss: 3.1155 (3.1336) grad_norm: 1.8312 (1.8111) time: 0.6306 [2021-03-27 16:17:40 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 580/1251] eta: 0:07:07 lr: 0.000335 loss: 3.1711 (3.1334) grad_norm: 1.8740 (1.8123) time: 0.6316 [2021-03-27 16:17:46 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 590/1251] eta: 0:07:00 lr: 0.000335 loss: 3.2622 (3.1334) grad_norm: 1.8740 (1.8132) time: 0.6287 [2021-03-27 16:17:52 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 600/1251] eta: 0:06:54 lr: 0.000335 loss: 3.2622 (3.1306) grad_norm: 1.7829 (1.8131) time: 0.6298 [2021-03-27 16:17:59 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 610/1251] eta: 0:06:48 lr: 0.000335 loss: 3.1962 (3.1336) grad_norm: 1.8650 (1.8152) time: 0.6300 [2021-03-27 16:18:05 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 620/1251] eta: 0:06:41 lr: 0.000335 loss: 3.2961 (3.1319) grad_norm: 1.8929 (1.8224) time: 0.6308 [2021-03-27 16:18:11 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 630/1251] eta: 0:06:35 lr: 0.000335 loss: 3.2882 (3.1339) grad_norm: 1.8536 (nan) time: 0.6227 [2021-03-27 16:18:18 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 640/1251] eta: 0:06:28 lr: 0.000335 loss: 3.2027 (3.1317) grad_norm: 1.8536 (nan) time: 0.6252 [2021-03-27 16:18:24 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 650/1251] eta: 0:06:22 lr: 0.000335 loss: 3.0237 (3.1291) grad_norm: 1.8459 (nan) time: 0.6312 [2021-03-27 16:18:30 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 660/1251] eta: 0:06:15 lr: 0.000335 loss: 3.1498 (3.1312) grad_norm: 1.8579 (nan) time: 0.6265 [2021-03-27 16:18:36 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 670/1251] eta: 0:06:09 lr: 0.000335 loss: 3.3721 (3.1330) grad_norm: 1.8856 (nan) time: 0.6270 [2021-03-27 16:18:43 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 680/1251] eta: 0:06:03 lr: 0.000335 loss: 3.3286 (3.1351) grad_norm: 1.7406 (nan) time: 0.6347 [2021-03-27 16:18:49 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 690/1251] eta: 0:05:56 lr: 0.000335 loss: 3.2920 (3.1367) grad_norm: 1.8155 (nan) time: 0.6359 [2021-03-27 16:18:55 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 700/1251] eta: 0:05:50 lr: 0.000335 loss: 3.3014 (3.1389) grad_norm: 1.8154 (nan) time: 0.6316 [2021-03-27 16:19:02 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 710/1251] eta: 0:05:43 lr: 0.000335 loss: 3.2559 (3.1381) grad_norm: 1.7890 (nan) time: 0.6313 [2021-03-27 16:19:08 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 720/1251] eta: 0:05:37 lr: 0.000335 loss: 3.0813 (3.1371) grad_norm: 1.8195 (nan) time: 0.6268 [2021-03-27 16:19:14 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 730/1251] eta: 0:05:31 lr: 0.000334 loss: 3.1474 (3.1377) grad_norm: 1.8568 (nan) time: 0.6262 [2021-03-27 16:19:21 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 740/1251] eta: 0:05:24 lr: 0.000334 loss: 3.4719 (3.1432) grad_norm: 1.8317 (nan) time: 0.6352 [2021-03-27 16:19:27 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 750/1251] eta: 0:05:18 lr: 0.000334 loss: 3.3850 (3.1414) grad_norm: 1.8395 (nan) time: 0.6402 [2021-03-27 16:19:33 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 760/1251] eta: 0:05:12 lr: 0.000334 loss: 3.1740 (3.1410) grad_norm: 1.8049 (nan) time: 0.6388 [2021-03-27 16:19:40 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 770/1251] eta: 0:05:05 lr: 0.000334 loss: 3.0986 (3.1391) grad_norm: 1.7682 (nan) time: 0.6345 [2021-03-27 16:19:46 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 780/1251] eta: 0:04:59 lr: 0.000334 loss: 2.9901 (3.1369) grad_norm: 1.7986 (nan) time: 0.6283 [2021-03-27 16:19:52 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 790/1251] eta: 0:04:52 lr: 0.000334 loss: 3.1530 (3.1378) grad_norm: 1.7986 (nan) time: 0.6269 [2021-03-27 16:19:59 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 800/1251] eta: 0:04:46 lr: 0.000334 loss: 3.1648 (3.1380) grad_norm: 1.7633 (nan) time: 0.6298 [2021-03-27 16:20:05 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 810/1251] eta: 0:04:40 lr: 0.000334 loss: 3.3843 (3.1387) grad_norm: 1.8373 (nan) time: 0.6297 [2021-03-27 16:20:11 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 820/1251] eta: 0:04:33 lr: 0.000334 loss: 3.0742 (3.1394) grad_norm: 1.9256 (nan) time: 0.6265 [2021-03-27 16:20:17 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 830/1251] eta: 0:04:27 lr: 0.000334 loss: 3.2491 (3.1413) grad_norm: 1.8400 (nan) time: 0.6269 [2021-03-27 16:20:24 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 840/1251] eta: 0:04:20 lr: 0.000334 loss: 3.3289 (3.1426) grad_norm: 1.7801 (nan) time: 0.6308 [2021-03-27 16:20:30 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 850/1251] eta: 0:04:14 lr: 0.000334 loss: 3.2872 (3.1431) grad_norm: 1.7801 (nan) time: 0.6281 [2021-03-27 16:20:36 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 860/1251] eta: 0:04:08 lr: 0.000334 loss: 3.1064 (3.1404) grad_norm: 1.7405 (nan) time: 0.6256 [2021-03-27 16:20:43 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 870/1251] eta: 0:04:01 lr: 0.000334 loss: 2.7196 (3.1394) grad_norm: 1.8786 (nan) time: 0.6263 [2021-03-27 16:20:49 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 880/1251] eta: 0:03:55 lr: 0.000334 loss: 3.0518 (3.1394) grad_norm: 1.8803 (nan) time: 0.6259 [2021-03-27 16:20:55 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 890/1251] eta: 0:03:49 lr: 0.000334 loss: 3.0356 (3.1377) grad_norm: 1.7220 (nan) time: 0.6283 [2021-03-27 16:21:01 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 900/1251] eta: 0:03:42 lr: 0.000334 loss: 3.0888 (3.1378) grad_norm: 1.6648 (nan) time: 0.6262 [2021-03-27 16:21:08 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 910/1251] eta: 0:03:36 lr: 0.000334 loss: 3.0651 (3.1334) grad_norm: 1.6648 (nan) time: 0.6263 [2021-03-27 16:21:14 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 920/1251] eta: 0:03:29 lr: 0.000334 loss: 3.0679 (3.1347) grad_norm: 1.7421 (nan) time: 0.6283 [2021-03-27 16:21:20 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 930/1251] eta: 0:03:23 lr: 0.000334 loss: 3.2622 (3.1362) grad_norm: 1.6032 (nan) time: 0.6269 [2021-03-27 16:21:27 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 940/1251] eta: 0:03:17 lr: 0.000334 loss: 3.3408 (3.1376) grad_norm: 1.6982 (nan) time: 0.6315 [2021-03-27 16:21:33 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 950/1251] eta: 0:03:10 lr: 0.000334 loss: 3.2006 (3.1361) grad_norm: 1.8052 (nan) time: 0.6274 [2021-03-27 16:21:39 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 960/1251] eta: 0:03:04 lr: 0.000334 loss: 3.1236 (3.1366) grad_norm: 1.6387 (nan) time: 0.6270 [2021-03-27 16:21:45 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 970/1251] eta: 0:02:58 lr: 0.000334 loss: 3.2910 (3.1382) grad_norm: 1.6727 (nan) time: 0.6352 [2021-03-27 16:21:52 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 980/1251] eta: 0:02:51 lr: 0.000334 loss: 3.2910 (3.1385) grad_norm: 1.7310 (nan) time: 0.6274 [2021-03-27 16:21:58 swin_base_patch4_window7_224] INFO: Epoch: [183] [ 990/1251] eta: 0:02:45 lr: 0.000333 loss: 3.3245 (3.1420) grad_norm: 1.6946 (nan) time: 0.6227 [2021-03-27 16:22:04 swin_base_patch4_window7_224] INFO: Epoch: [183] [1000/1251] eta: 0:02:39 lr: 0.000333 loss: 3.3240 (3.1410) grad_norm: 1.5943 (nan) time: 0.6272 [2021-03-27 16:22:11 swin_base_patch4_window7_224] INFO: Epoch: [183] [1010/1251] eta: 0:02:32 lr: 0.000333 loss: 3.1869 (3.1413) grad_norm: 1.6985 (nan) time: 0.6297 [2021-03-27 16:22:17 swin_base_patch4_window7_224] INFO: Epoch: [183] [1020/1251] eta: 0:02:26 lr: 0.000333 loss: 3.2468 (3.1409) grad_norm: 1.7348 (nan) time: 0.6311 [2021-03-27 16:22:23 swin_base_patch4_window7_224] INFO: Epoch: [183] [1030/1251] eta: 0:02:20 lr: 0.000333 loss: 3.1188 (3.1397) grad_norm: 1.7554 (nan) time: 0.6365 [2021-03-27 16:22:30 swin_base_patch4_window7_224] INFO: Epoch: [183] [1040/1251] eta: 0:02:13 lr: 0.000333 loss: 3.2137 (3.1409) grad_norm: 1.7254 (nan) time: 0.6338 [2021-03-27 16:22:36 swin_base_patch4_window7_224] INFO: Epoch: [183] [1050/1251] eta: 0:02:07 lr: 0.000333 loss: 3.5076 (3.1451) grad_norm: 1.7180 (nan) time: 0.6242 [2021-03-27 16:22:42 swin_base_patch4_window7_224] INFO: Epoch: [183] [1060/1251] eta: 0:02:01 lr: 0.000333 loss: 3.2925 (3.1434) grad_norm: 1.7201 (nan) time: 0.6253 [2021-03-27 16:22:48 swin_base_patch4_window7_224] INFO: Epoch: [183] [1070/1251] eta: 0:01:54 lr: 0.000333 loss: 3.0542 (3.1416) grad_norm: 1.7051 (nan) time: 0.6253 [2021-03-27 16:22:54 swin_base_patch4_window7_224] INFO: Epoch: [183] [1080/1251] eta: 0:01:48 lr: 0.000333 loss: 3.2764 (3.1431) grad_norm: 1.6710 (nan) time: 0.6233 [2021-03-27 16:23:01 swin_base_patch4_window7_224] INFO: Epoch: [183] [1090/1251] eta: 0:01:41 lr: 0.000333 loss: 3.3335 (3.1426) grad_norm: 1.7184 (nan) time: 0.6282 [2021-03-27 16:23:07 swin_base_patch4_window7_224] INFO: Epoch: [183] [1100/1251] eta: 0:01:35 lr: 0.000333 loss: 3.1977 (3.1424) grad_norm: 1.7467 (nan) time: 0.6285 [2021-03-27 16:23:13 swin_base_patch4_window7_224] INFO: Epoch: [183] [1110/1251] eta: 0:01:29 lr: 0.000333 loss: 3.1185 (3.1414) grad_norm: 1.7467 (nan) time: 0.6265 [2021-03-27 16:23:20 swin_base_patch4_window7_224] INFO: Epoch: [183] [1120/1251] eta: 0:01:22 lr: 0.000333 loss: 2.9465 (3.1396) grad_norm: 1.8130 (nan) time: 0.6241 [2021-03-27 16:23:26 swin_base_patch4_window7_224] INFO: Epoch: [183] [1130/1251] eta: 0:01:16 lr: 0.000333 loss: 3.3772 (3.1397) grad_norm: 1.8302 (nan) time: 0.6283 [2021-03-27 16:23:32 swin_base_patch4_window7_224] INFO: Epoch: [183] [1140/1251] eta: 0:01:10 lr: 0.000333 loss: 3.3387 (3.1387) grad_norm: 1.6974 (nan) time: 0.6299 [2021-03-27 16:23:38 swin_base_patch4_window7_224] INFO: Epoch: [183] [1150/1251] eta: 0:01:03 lr: 0.000333 loss: 2.9063 (3.1369) grad_norm: 1.6836 (nan) time: 0.6265 [2021-03-27 16:23:45 swin_base_patch4_window7_224] INFO: Epoch: [183] [1160/1251] eta: 0:00:57 lr: 0.000333 loss: 2.8921 (3.1370) grad_norm: 1.8033 (nan) time: 0.6337 [2021-03-27 16:23:51 swin_base_patch4_window7_224] INFO: Epoch: [183] [1170/1251] eta: 0:00:51 lr: 0.000333 loss: 3.3459 (3.1381) grad_norm: 1.8501 (nan) time: 0.6320 [2021-03-27 16:23:57 swin_base_patch4_window7_224] INFO: Epoch: [183] [1180/1251] eta: 0:00:44 lr: 0.000333 loss: 3.2094 (3.1355) grad_norm: 1.8778 (nan) time: 0.6337 [2021-03-27 16:24:04 swin_base_patch4_window7_224] INFO: Epoch: [183] [1190/1251] eta: 0:00:38 lr: 0.000333 loss: 2.9659 (3.1354) grad_norm: 1.8371 (nan) time: 0.6316 [2021-03-27 16:24:10 swin_base_patch4_window7_224] INFO: Epoch: [183] [1200/1251] eta: 0:00:32 lr: 0.000333 loss: 2.9918 (3.1333) grad_norm: 1.8371 (nan) time: 0.6217 [2021-03-27 16:24:16 swin_base_patch4_window7_224] INFO: Epoch: [183] [1210/1251] eta: 0:00:25 lr: 0.000333 loss: 2.8234 (3.1317) grad_norm: 1.9030 (nan) time: 0.6249 [2021-03-27 16:24:23 swin_base_patch4_window7_224] INFO: Epoch: [183] [1220/1251] eta: 0:00:19 lr: 0.000333 loss: 2.9808 (3.1314) grad_norm: 1.7952 (nan) time: 0.6284 [2021-03-27 16:24:29 swin_base_patch4_window7_224] INFO: Epoch: [183] [1230/1251] eta: 0:00:13 lr: 0.000333 loss: 3.4405 (3.1344) grad_norm: 1.7938 (nan) time: 0.6278 [2021-03-27 16:24:35 swin_base_patch4_window7_224] INFO: Epoch: [183] [1240/1251] eta: 0:00:06 lr: 0.000332 loss: 3.4894 (3.1353) grad_norm: 1.7938 (nan) time: 0.6226 [2021-03-27 16:24:41 swin_base_patch4_window7_224] INFO: Epoch: [183] [1250/1251] eta: 0:00:00 lr: 0.000332 loss: 3.3046 (3.1352) grad_norm: 1.6560 (nan) time: 0.6182 [2021-03-27 16:24:50 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:00 loss: 1.0394 (1.0394) acc1: 78.1250 (78.1250) acc5: 93.7500 (93.7500) [2021-03-27 16:24:53 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8572 (0.8981) acc1: 79.6875 (78.9773) acc5: 95.3125 (95.5966) [2021-03-27 16:24:55 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8476 (0.8540) acc1: 79.6875 (79.5387) acc5: 96.8750 (95.8333) [2021-03-27 16:24:57 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8786 (0.8632) acc1: 79.6875 (79.6371) acc5: 95.3125 (95.7661) [2021-03-27 16:24:59 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8844 (0.8666) acc1: 81.2500 (79.9543) acc5: 95.3125 (95.4268) [2021-03-27 16:25:01 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8240 (0.8573) acc1: 81.2500 (80.0960) acc5: 96.8750 (95.6800) [2021-03-27 16:25:10 swin_base_patch4_window7_224] INFO: * Acc@1 80.426 Acc@5 95.438 loss 0.844 [2021-03-27 16:25:10 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.4% [2021-03-27 16:25:10 swin_base_patch4_window7_224] INFO: Max accuracy: 80.43% [2021-03-27 16:25:14 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 0/1251] eta: 1:24:09 lr: 0.000332 loss: 2.2026 (2.2026) grad_norm: 1.6130 (1.6130) time: 4.0363 [2021-03-27 16:25:21 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 10/1251] eta: 0:20:01 lr: 0.000332 loss: 3.4749 (3.3149) grad_norm: 1.7198 (1.7928) time: 0.9680 [2021-03-27 16:25:27 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 20/1251] eta: 0:16:29 lr: 0.000332 loss: 3.3460 (3.2048) grad_norm: 1.7081 (1.7960) time: 0.6419 [2021-03-27 16:25:34 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 30/1251] eta: 0:15:14 lr: 0.000332 loss: 3.1146 (3.1352) grad_norm: 1.7311 (1.8174) time: 0.6284 [2021-03-27 16:25:40 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 40/1251] eta: 0:14:31 lr: 0.000332 loss: 3.0254 (3.1355) grad_norm: 1.7822 (1.8131) time: 0.6322 [2021-03-27 16:25:46 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 50/1251] eta: 0:14:01 lr: 0.000332 loss: 3.2994 (3.1383) grad_norm: 1.7736 (1.8212) time: 0.6263 [2021-03-27 16:25:52 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 60/1251] eta: 0:13:39 lr: 0.000332 loss: 3.1771 (3.1483) grad_norm: 1.7848 (1.8306) time: 0.6233 [2021-03-27 16:25:59 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 70/1251] eta: 0:13:23 lr: 0.000332 loss: 3.1346 (3.1001) grad_norm: 1.8559 (1.8285) time: 0.6271 [2021-03-27 16:26:05 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 80/1251] eta: 0:13:07 lr: 0.000332 loss: 3.0806 (3.1226) grad_norm: 1.8360 (1.8295) time: 0.6262 [2021-03-27 16:26:11 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 90/1251] eta: 0:12:54 lr: 0.000332 loss: 3.2367 (3.1229) grad_norm: 1.7619 (1.8231) time: 0.6206 [2021-03-27 16:26:17 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 100/1251] eta: 0:12:43 lr: 0.000332 loss: 3.2257 (3.1210) grad_norm: 1.7029 (1.8264) time: 0.6231 [2021-03-27 16:26:24 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 110/1251] eta: 0:12:32 lr: 0.000332 loss: 3.4149 (3.1313) grad_norm: 1.8175 (1.8279) time: 0.6261 [2021-03-27 16:26:30 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 120/1251] eta: 0:12:24 lr: 0.000332 loss: 3.2136 (3.1278) grad_norm: 1.7822 (1.8268) time: 0.6315 [2021-03-27 16:26:36 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 130/1251] eta: 0:12:15 lr: 0.000332 loss: 3.0133 (3.1161) grad_norm: 1.7822 (1.8255) time: 0.6358 [2021-03-27 16:26:43 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 140/1251] eta: 0:12:06 lr: 0.000332 loss: 2.9512 (3.1138) grad_norm: 1.7370 (1.8209) time: 0.6285 [2021-03-27 16:26:49 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 150/1251] eta: 0:11:57 lr: 0.000332 loss: 3.2410 (3.1178) grad_norm: 1.7885 (1.8237) time: 0.6253 [2021-03-27 16:26:55 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 160/1251] eta: 0:11:49 lr: 0.000332 loss: 3.2410 (3.1204) grad_norm: 1.8252 (1.8227) time: 0.6248 [2021-03-27 16:27:01 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 170/1251] eta: 0:11:41 lr: 0.000332 loss: 3.2005 (3.1212) grad_norm: 1.8475 (1.8271) time: 0.6245 [2021-03-27 16:27:08 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 180/1251] eta: 0:11:34 lr: 0.000332 loss: 3.2005 (3.1315) grad_norm: 1.7239 (1.8225) time: 0.6318 [2021-03-27 16:27:14 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 190/1251] eta: 0:11:26 lr: 0.000332 loss: 3.1138 (3.1285) grad_norm: 1.7067 (1.8173) time: 0.6298 [2021-03-27 16:27:20 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 200/1251] eta: 0:11:19 lr: 0.000332 loss: 2.9782 (3.1288) grad_norm: 1.6601 (1.8112) time: 0.6284 [2021-03-27 16:27:27 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 210/1251] eta: 0:11:11 lr: 0.000332 loss: 3.4420 (3.1466) grad_norm: 1.6775 (1.8131) time: 0.6312 [2021-03-27 16:27:33 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 220/1251] eta: 0:11:04 lr: 0.000332 loss: 3.4624 (3.1542) grad_norm: 1.7202 (1.8086) time: 0.6258 [2021-03-27 16:27:39 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 230/1251] eta: 0:10:57 lr: 0.000332 loss: 3.2145 (3.1499) grad_norm: 1.7792 (1.8119) time: 0.6252 [2021-03-27 16:27:45 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 240/1251] eta: 0:10:49 lr: 0.000332 loss: 3.1945 (3.1514) grad_norm: 1.8494 (1.8149) time: 0.6253 [2021-03-27 16:27:52 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 250/1251] eta: 0:10:42 lr: 0.000331 loss: 3.3523 (3.1609) grad_norm: 1.8161 (1.8148) time: 0.6272 [2021-03-27 16:27:58 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 260/1251] eta: 0:10:35 lr: 0.000331 loss: 3.3119 (3.1653) grad_norm: 1.7411 (1.8128) time: 0.6282 [2021-03-27 16:28:04 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 270/1251] eta: 0:10:28 lr: 0.000331 loss: 3.3119 (3.1633) grad_norm: 1.6992 (1.8158) time: 0.6257 [2021-03-27 16:28:10 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 280/1251] eta: 0:10:21 lr: 0.000331 loss: 3.0759 (3.1530) grad_norm: 1.8314 (1.8199) time: 0.6269 [2021-03-27 16:28:17 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 290/1251] eta: 0:10:14 lr: 0.000331 loss: 3.0906 (3.1505) grad_norm: 1.8314 (1.8180) time: 0.6253 [2021-03-27 16:28:23 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 300/1251] eta: 0:10:08 lr: 0.000331 loss: 3.2272 (3.1543) grad_norm: 1.7376 (1.8162) time: 0.6229 [2021-03-27 16:28:29 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 310/1251] eta: 0:10:01 lr: 0.000331 loss: 3.2413 (3.1483) grad_norm: 1.7908 (1.8201) time: 0.6222 [2021-03-27 16:28:35 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 320/1251] eta: 0:09:54 lr: 0.000331 loss: 3.1188 (3.1473) grad_norm: 1.7926 (1.8206) time: 0.6292 [2021-03-27 16:28:42 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 330/1251] eta: 0:09:48 lr: 0.000331 loss: 3.1504 (3.1452) grad_norm: 1.7890 (1.8282) time: 0.6351 [2021-03-27 16:28:48 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 340/1251] eta: 0:09:41 lr: 0.000331 loss: 3.0157 (3.1456) grad_norm: 1.8637 (1.8313) time: 0.6294 [2021-03-27 16:28:54 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 350/1251] eta: 0:09:34 lr: 0.000331 loss: 3.0315 (3.1422) grad_norm: 1.8615 (1.8357) time: 0.6294 [2021-03-27 16:29:01 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 360/1251] eta: 0:09:28 lr: 0.000331 loss: 3.0468 (3.1423) grad_norm: 1.8165 (1.8388) time: 0.6360 [2021-03-27 16:29:07 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 370/1251] eta: 0:09:22 lr: 0.000331 loss: 3.3107 (3.1475) grad_norm: 1.7250 (1.8338) time: 0.6362 [2021-03-27 16:29:13 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 380/1251] eta: 0:09:15 lr: 0.000331 loss: 3.3133 (3.1487) grad_norm: 1.7279 (1.8365) time: 0.6342 [2021-03-27 16:29:20 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 390/1251] eta: 0:09:09 lr: 0.000331 loss: 3.3581 (3.1541) grad_norm: 1.8680 (1.8355) time: 0.6360 [2021-03-27 16:29:26 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 400/1251] eta: 0:09:02 lr: 0.000331 loss: 3.3581 (3.1547) grad_norm: 1.7283 (1.8351) time: 0.6314 [2021-03-27 16:29:32 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 410/1251] eta: 0:08:55 lr: 0.000331 loss: 3.2049 (3.1577) grad_norm: 1.7702 (1.8362) time: 0.6220 [2021-03-27 16:29:39 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 420/1251] eta: 0:08:49 lr: 0.000331 loss: 3.2618 (3.1564) grad_norm: 1.7683 (1.8335) time: 0.6234 [2021-03-27 16:29:45 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 430/1251] eta: 0:08:42 lr: 0.000331 loss: 3.1881 (3.1521) grad_norm: 1.8159 (1.8345) time: 0.6311 [2021-03-27 16:29:51 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 440/1251] eta: 0:08:36 lr: 0.000331 loss: 3.1903 (3.1552) grad_norm: 1.8424 (1.8346) time: 0.6278 [2021-03-27 16:29:57 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 450/1251] eta: 0:08:29 lr: 0.000331 loss: 3.4576 (3.1585) grad_norm: 1.7695 (1.8346) time: 0.6277 [2021-03-27 16:30:04 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 460/1251] eta: 0:08:23 lr: 0.000331 loss: 3.4576 (3.1584) grad_norm: 1.7020 (1.8320) time: 0.6337 [2021-03-27 16:30:10 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 470/1251] eta: 0:08:16 lr: 0.000331 loss: 3.2595 (3.1574) grad_norm: 1.7535 (1.8312) time: 0.6288 [2021-03-27 16:30:16 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 480/1251] eta: 0:08:10 lr: 0.000331 loss: 3.3769 (3.1618) grad_norm: 1.7973 (1.8312) time: 0.6229 [2021-03-27 16:30:22 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 490/1251] eta: 0:08:03 lr: 0.000331 loss: 3.3769 (3.1603) grad_norm: 1.7190 (1.8294) time: 0.6214 [2021-03-27 16:30:29 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 500/1251] eta: 0:07:57 lr: 0.000331 loss: 3.2325 (3.1611) grad_norm: 1.7190 (1.8339) time: 0.6220 [2021-03-27 16:30:35 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 510/1251] eta: 0:07:50 lr: 0.000330 loss: 3.3308 (3.1665) grad_norm: 1.6836 (1.8317) time: 0.6251 [2021-03-27 16:30:41 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 520/1251] eta: 0:07:44 lr: 0.000330 loss: 3.3932 (3.1658) grad_norm: 1.7093 (1.8311) time: 0.6297 [2021-03-27 16:30:47 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 530/1251] eta: 0:07:37 lr: 0.000330 loss: 3.1716 (3.1642) grad_norm: 1.8055 (1.8308) time: 0.6263 [2021-03-27 16:30:54 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 540/1251] eta: 0:07:31 lr: 0.000330 loss: 3.2142 (3.1654) grad_norm: 1.8100 (1.8287) time: 0.6243 [2021-03-27 16:31:00 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 550/1251] eta: 0:07:25 lr: 0.000330 loss: 3.3510 (3.1664) grad_norm: 1.7304 (1.8276) time: 0.6383 [2021-03-27 16:31:06 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 560/1251] eta: 0:07:18 lr: 0.000330 loss: 3.2966 (3.1676) grad_norm: 1.7494 (1.8267) time: 0.6331 [2021-03-27 16:31:13 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 570/1251] eta: 0:07:11 lr: 0.000330 loss: 3.3729 (3.1698) grad_norm: 1.7494 (1.8252) time: 0.6200 [2021-03-27 16:31:19 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 580/1251] eta: 0:07:05 lr: 0.000330 loss: 3.3803 (3.1684) grad_norm: 1.6943 (1.8249) time: 0.6207 [2021-03-27 16:31:25 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 590/1251] eta: 0:06:59 lr: 0.000330 loss: 3.3286 (3.1699) grad_norm: 1.8611 (1.8257) time: 0.6229 [2021-03-27 16:31:31 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 600/1251] eta: 0:06:52 lr: 0.000330 loss: 3.3819 (3.1730) grad_norm: 1.8859 (1.8276) time: 0.6311 [2021-03-27 16:31:38 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 610/1251] eta: 0:06:46 lr: 0.000330 loss: 3.3322 (3.1733) grad_norm: 1.7668 (1.8289) time: 0.6293 [2021-03-27 16:31:44 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 620/1251] eta: 0:06:39 lr: 0.000330 loss: 3.0944 (3.1700) grad_norm: 1.8337 (1.8308) time: 0.6238 [2021-03-27 16:31:50 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 630/1251] eta: 0:06:33 lr: 0.000330 loss: 3.2830 (3.1741) grad_norm: 1.7133 (1.8298) time: 0.6257 [2021-03-27 16:31:56 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 640/1251] eta: 0:06:27 lr: 0.000330 loss: 3.4718 (3.1772) grad_norm: 1.6747 (1.8302) time: 0.6264 [2021-03-27 16:32:03 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 650/1251] eta: 0:06:20 lr: 0.000330 loss: 3.4143 (3.1762) grad_norm: 1.8035 (1.8299) time: 0.6248 [2021-03-27 16:32:09 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 660/1251] eta: 0:06:14 lr: 0.000330 loss: 2.8488 (3.1731) grad_norm: 1.8583 (1.8325) time: 0.6230 [2021-03-27 16:32:15 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 670/1251] eta: 0:06:07 lr: 0.000330 loss: 3.1363 (3.1749) grad_norm: 1.9406 (1.8340) time: 0.6226 [2021-03-27 16:32:21 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 680/1251] eta: 0:06:01 lr: 0.000330 loss: 3.1913 (3.1718) grad_norm: 1.7659 (1.8333) time: 0.6200 [2021-03-27 16:32:28 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 690/1251] eta: 0:05:54 lr: 0.000330 loss: 3.3916 (3.1752) grad_norm: 1.7564 (1.8372) time: 0.6193 [2021-03-27 16:32:34 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 700/1251] eta: 0:05:48 lr: 0.000330 loss: 3.4414 (3.1774) grad_norm: 1.8501 (1.8368) time: 0.6289 [2021-03-27 16:32:40 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 710/1251] eta: 0:05:42 lr: 0.000330 loss: 3.1969 (3.1773) grad_norm: 1.8182 (1.8368) time: 0.6303 [2021-03-27 16:32:46 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 720/1251] eta: 0:05:35 lr: 0.000330 loss: 2.9488 (3.1731) grad_norm: 1.7750 (1.8359) time: 0.6243 [2021-03-27 16:32:53 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 730/1251] eta: 0:05:29 lr: 0.000330 loss: 2.9846 (3.1724) grad_norm: 1.7655 (1.8376) time: 0.6326 [2021-03-27 16:32:59 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 740/1251] eta: 0:05:23 lr: 0.000330 loss: 3.3256 (3.1737) grad_norm: 1.7546 (1.8366) time: 0.6327 [2021-03-27 16:33:05 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 750/1251] eta: 0:05:16 lr: 0.000330 loss: 3.2561 (3.1722) grad_norm: 1.6735 (1.8343) time: 0.6316 [2021-03-27 16:33:12 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 760/1251] eta: 0:05:10 lr: 0.000330 loss: 3.2561 (3.1738) grad_norm: 1.6858 (1.8333) time: 0.6365 [2021-03-27 16:33:18 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 770/1251] eta: 0:05:04 lr: 0.000329 loss: 3.1226 (3.1714) grad_norm: 1.7741 (1.8336) time: 0.6292 [2021-03-27 16:33:24 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 780/1251] eta: 0:04:57 lr: 0.000329 loss: 2.9242 (3.1693) grad_norm: 1.8206 (1.8334) time: 0.6216 [2021-03-27 16:33:30 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 790/1251] eta: 0:04:51 lr: 0.000329 loss: 3.0464 (3.1673) grad_norm: 1.8408 (1.8327) time: 0.6212 [2021-03-27 16:33:37 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 800/1251] eta: 0:04:45 lr: 0.000329 loss: 3.2894 (3.1697) grad_norm: 1.7305 (1.8313) time: 0.6274 [2021-03-27 16:33:43 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 810/1251] eta: 0:04:38 lr: 0.000329 loss: 3.3098 (3.1682) grad_norm: 1.6758 (1.8285) time: 0.6262 [2021-03-27 16:33:49 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 820/1251] eta: 0:04:32 lr: 0.000329 loss: 2.9118 (3.1638) grad_norm: 1.6438 (1.8286) time: 0.6243 [2021-03-27 16:33:56 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 830/1251] eta: 0:04:25 lr: 0.000329 loss: 3.1207 (3.1638) grad_norm: 1.7498 (1.8285) time: 0.6256 [2021-03-27 16:34:02 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 840/1251] eta: 0:04:19 lr: 0.000329 loss: 3.2325 (3.1644) grad_norm: 1.6794 (1.8263) time: 0.6229 [2021-03-27 16:34:08 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 850/1251] eta: 0:04:13 lr: 0.000329 loss: 3.2582 (3.1644) grad_norm: 1.7064 (1.8260) time: 0.6222 [2021-03-27 16:34:14 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 860/1251] eta: 0:04:06 lr: 0.000329 loss: 2.9623 (3.1614) grad_norm: 1.6613 (1.8244) time: 0.6199 [2021-03-27 16:34:21 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 870/1251] eta: 0:04:00 lr: 0.000329 loss: 2.9928 (3.1609) grad_norm: 1.6613 (1.8240) time: 0.6293 [2021-03-27 16:34:27 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 880/1251] eta: 0:03:54 lr: 0.000329 loss: 3.1742 (3.1625) grad_norm: 1.7598 (1.8241) time: 0.6340 [2021-03-27 16:34:33 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 890/1251] eta: 0:03:47 lr: 0.000329 loss: 3.3705 (3.1651) grad_norm: 1.7461 (1.8232) time: 0.6319 [2021-03-27 16:34:39 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 900/1251] eta: 0:03:41 lr: 0.000329 loss: 3.3705 (3.1653) grad_norm: 1.7461 (1.8241) time: 0.6291 [2021-03-27 16:34:46 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 910/1251] eta: 0:03:35 lr: 0.000329 loss: 3.2404 (3.1665) grad_norm: 1.8567 (1.8253) time: 0.6225 [2021-03-27 16:34:52 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 920/1251] eta: 0:03:28 lr: 0.000329 loss: 3.0128 (3.1620) grad_norm: 1.7967 (1.8251) time: 0.6247 [2021-03-27 16:34:58 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 930/1251] eta: 0:03:22 lr: 0.000329 loss: 2.6744 (3.1596) grad_norm: 1.7408 (1.8249) time: 0.6258 [2021-03-27 16:35:04 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 940/1251] eta: 0:03:16 lr: 0.000329 loss: 3.0549 (3.1589) grad_norm: 1.7732 (1.8251) time: 0.6229 [2021-03-27 16:35:11 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 950/1251] eta: 0:03:09 lr: 0.000329 loss: 3.1917 (3.1592) grad_norm: 1.8491 (1.8261) time: 0.6245 [2021-03-27 16:35:17 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 960/1251] eta: 0:03:03 lr: 0.000329 loss: 3.1810 (3.1576) grad_norm: 1.8733 (1.8305) time: 0.6243 [2021-03-27 16:35:23 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 970/1251] eta: 0:02:57 lr: 0.000329 loss: 2.8843 (3.1550) grad_norm: 1.7408 (1.8294) time: 0.6219 [2021-03-27 16:35:29 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 980/1251] eta: 0:02:50 lr: 0.000329 loss: 2.9437 (3.1536) grad_norm: 1.7255 (1.8291) time: 0.6231 [2021-03-27 16:35:36 swin_base_patch4_window7_224] INFO: Epoch: [184] [ 990/1251] eta: 0:02:44 lr: 0.000329 loss: 3.1881 (3.1555) grad_norm: 1.7522 (1.8287) time: 0.6223 [2021-03-27 16:35:42 swin_base_patch4_window7_224] INFO: Epoch: [184] [1000/1251] eta: 0:02:38 lr: 0.000329 loss: 3.1881 (3.1532) grad_norm: 1.7087 (1.8275) time: 0.6243 [2021-03-27 16:35:48 swin_base_patch4_window7_224] INFO: Epoch: [184] [1010/1251] eta: 0:02:31 lr: 0.000329 loss: 2.9636 (3.1520) grad_norm: 1.7046 (1.8266) time: 0.6264 [2021-03-27 16:35:54 swin_base_patch4_window7_224] INFO: Epoch: [184] [1020/1251] eta: 0:02:25 lr: 0.000329 loss: 3.2645 (3.1518) grad_norm: 1.6987 (1.8253) time: 0.6252 [2021-03-27 16:36:01 swin_base_patch4_window7_224] INFO: Epoch: [184] [1030/1251] eta: 0:02:19 lr: 0.000328 loss: 3.2650 (3.1528) grad_norm: 1.7035 (1.8255) time: 0.6225 [2021-03-27 16:36:07 swin_base_patch4_window7_224] INFO: Epoch: [184] [1040/1251] eta: 0:02:13 lr: 0.000328 loss: 3.2861 (3.1542) grad_norm: 1.6991 (1.8246) time: 0.6217 [2021-03-27 16:36:13 swin_base_patch4_window7_224] INFO: Epoch: [184] [1050/1251] eta: 0:02:06 lr: 0.000328 loss: 3.2844 (3.1535) grad_norm: 1.6887 (1.8241) time: 0.6220 [2021-03-27 16:36:19 swin_base_patch4_window7_224] INFO: Epoch: [184] [1060/1251] eta: 0:02:00 lr: 0.000328 loss: 3.2215 (3.1546) grad_norm: 1.7359 (1.8239) time: 0.6264 [2021-03-27 16:36:26 swin_base_patch4_window7_224] INFO: Epoch: [184] [1070/1251] eta: 0:01:54 lr: 0.000328 loss: 3.1306 (3.1542) grad_norm: 1.7454 (1.8238) time: 0.6352 [2021-03-27 16:36:32 swin_base_patch4_window7_224] INFO: Epoch: [184] [1080/1251] eta: 0:01:47 lr: 0.000328 loss: 3.2264 (3.1554) grad_norm: 1.7812 (1.8241) time: 0.6343 [2021-03-27 16:36:38 swin_base_patch4_window7_224] INFO: Epoch: [184] [1090/1251] eta: 0:01:41 lr: 0.000328 loss: 3.0760 (3.1546) grad_norm: 1.7794 (1.8228) time: 0.6248 [2021-03-27 16:36:45 swin_base_patch4_window7_224] INFO: Epoch: [184] [1100/1251] eta: 0:01:35 lr: 0.000328 loss: 3.0760 (3.1542) grad_norm: 1.6682 (1.8223) time: 0.6294 [2021-03-27 16:36:51 swin_base_patch4_window7_224] INFO: Epoch: [184] [1110/1251] eta: 0:01:28 lr: 0.000328 loss: 2.9399 (3.1525) grad_norm: 1.7721 (1.8215) time: 0.6285 [2021-03-27 16:36:57 swin_base_patch4_window7_224] INFO: Epoch: [184] [1120/1251] eta: 0:01:22 lr: 0.000328 loss: 3.0948 (3.1522) grad_norm: 1.6735 (1.8206) time: 0.6210 [2021-03-27 16:37:03 swin_base_patch4_window7_224] INFO: Epoch: [184] [1130/1251] eta: 0:01:16 lr: 0.000328 loss: 3.1673 (3.1520) grad_norm: 1.7211 (1.8212) time: 0.6222 [2021-03-27 16:37:10 swin_base_patch4_window7_224] INFO: Epoch: [184] [1140/1251] eta: 0:01:09 lr: 0.000328 loss: 3.4198 (3.1531) grad_norm: 1.6667 (1.8194) time: 0.6283 [2021-03-27 16:37:16 swin_base_patch4_window7_224] INFO: Epoch: [184] [1150/1251] eta: 0:01:03 lr: 0.000328 loss: 3.3117 (3.1528) grad_norm: 1.6923 (1.8188) time: 0.6361 [2021-03-27 16:37:22 swin_base_patch4_window7_224] INFO: Epoch: [184] [1160/1251] eta: 0:00:57 lr: 0.000328 loss: 3.3157 (3.1554) grad_norm: 1.7312 (1.8183) time: 0.6298 [2021-03-27 16:37:28 swin_base_patch4_window7_224] INFO: Epoch: [184] [1170/1251] eta: 0:00:51 lr: 0.000328 loss: 3.3334 (3.1569) grad_norm: 1.7765 (1.8191) time: 0.6233 [2021-03-27 16:37:35 swin_base_patch4_window7_224] INFO: Epoch: [184] [1180/1251] eta: 0:00:44 lr: 0.000328 loss: 3.3215 (3.1581) grad_norm: 1.7765 (1.8189) time: 0.6239 [2021-03-27 16:37:41 swin_base_patch4_window7_224] INFO: Epoch: [184] [1190/1251] eta: 0:00:38 lr: 0.000328 loss: 3.3741 (3.1597) grad_norm: 1.7800 (1.8205) time: 0.6242 [2021-03-27 16:37:47 swin_base_patch4_window7_224] INFO: Epoch: [184] [1200/1251] eta: 0:00:32 lr: 0.000328 loss: 3.3026 (3.1601) grad_norm: 1.7709 (1.8195) time: 0.6223 [2021-03-27 16:37:53 swin_base_patch4_window7_224] INFO: Epoch: [184] [1210/1251] eta: 0:00:25 lr: 0.000328 loss: 3.3577 (3.1619) grad_norm: 1.7709 (1.8196) time: 0.6281 [2021-03-27 16:38:00 swin_base_patch4_window7_224] INFO: Epoch: [184] [1220/1251] eta: 0:00:19 lr: 0.000328 loss: 3.3577 (3.1616) grad_norm: 1.8198 (1.8193) time: 0.6390 [2021-03-27 16:38:06 swin_base_patch4_window7_224] INFO: Epoch: [184] [1230/1251] eta: 0:00:13 lr: 0.000328 loss: 3.1218 (3.1610) grad_norm: 1.8198 (1.8198) time: 0.6320 [2021-03-27 16:38:12 swin_base_patch4_window7_224] INFO: Epoch: [184] [1240/1251] eta: 0:00:06 lr: 0.000328 loss: 3.1404 (3.1609) grad_norm: 1.8854 (1.8210) time: 0.6271 [2021-03-27 16:38:19 swin_base_patch4_window7_224] INFO: Epoch: [184] [1250/1251] eta: 0:00:00 lr: 0.000328 loss: 3.2855 (3.1623) grad_norm: 1.8535 (1.8207) time: 0.6256 [2021-03-27 16:38:31 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:25 loss: 1.0474 (1.0474) acc1: 67.1875 (67.1875) acc5: 95.3125 (95.3125) [2021-03-27 16:38:33 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.8976 (0.9200) acc1: 79.6875 (78.2670) acc5: 95.3125 (94.4602) [2021-03-27 16:38:36 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8914 (0.8730) acc1: 79.6875 (79.4643) acc5: 95.3125 (95.5357) [2021-03-27 16:38:38 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8914 (0.8978) acc1: 79.6875 (79.0323) acc5: 95.3125 (95.0101) [2021-03-27 16:38:39 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8557 (0.8569) acc1: 81.2500 (80.4878) acc5: 95.3125 (95.3506) [2021-03-27 16:38:40 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8143 (0.8560) acc1: 81.2500 (79.7760) acc5: 95.3125 (95.2960) [2021-03-27 16:38:51 swin_base_patch4_window7_224] INFO: * Acc@1 80.548 Acc@5 95.430 loss 0.838 [2021-03-27 16:38:51 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.5% [2021-03-27 16:38:51 swin_base_patch4_window7_224] INFO: Max accuracy: 80.55% [2021-03-27 16:38:56 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 0/1251] eta: 1:29:38 lr: 0.000328 loss: 3.0293 (3.0293) grad_norm: 1.5219 (1.5219) time: 4.2991 [2021-03-27 16:39:02 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 10/1251] eta: 0:20:04 lr: 0.000328 loss: 3.0599 (3.0795) grad_norm: 1.6767 (1.7388) time: 0.9708 [2021-03-27 16:39:08 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 20/1251] eta: 0:16:35 lr: 0.000328 loss: 3.0599 (3.0156) grad_norm: 1.7127 (1.7651) time: 0.6339 [2021-03-27 16:39:15 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 30/1251] eta: 0:15:15 lr: 0.000327 loss: 3.1098 (3.0225) grad_norm: 1.9118 (1.8475) time: 0.6288 [2021-03-27 16:39:21 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 40/1251] eta: 0:14:33 lr: 0.000327 loss: 3.0484 (3.0258) grad_norm: 1.9118 (1.8447) time: 0.6300 [2021-03-27 16:39:27 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 50/1251] eta: 0:14:03 lr: 0.000327 loss: 3.0137 (3.0006) grad_norm: 1.8006 (1.8580) time: 0.6287 [2021-03-27 16:39:34 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 60/1251] eta: 0:13:43 lr: 0.000327 loss: 3.0137 (3.0181) grad_norm: 1.8532 (1.8694) time: 0.6297 [2021-03-27 16:39:40 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 70/1251] eta: 0:13:24 lr: 0.000327 loss: 3.1491 (3.0408) grad_norm: 1.8532 (1.8738) time: 0.6271 [2021-03-27 16:39:46 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 80/1251] eta: 0:13:10 lr: 0.000327 loss: 3.2754 (3.0665) grad_norm: 1.7801 (1.8534) time: 0.6263 [2021-03-27 16:39:52 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 90/1251] eta: 0:12:57 lr: 0.000327 loss: 3.1445 (3.0565) grad_norm: 1.7091 (1.8437) time: 0.6288 [2021-03-27 16:39:59 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 100/1251] eta: 0:12:45 lr: 0.000327 loss: 3.0937 (3.0642) grad_norm: 1.7655 (1.8357) time: 0.6233 [2021-03-27 16:40:05 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 110/1251] eta: 0:12:35 lr: 0.000327 loss: 3.0723 (3.0670) grad_norm: 1.7715 (1.8349) time: 0.6264 [2021-03-27 16:40:11 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 120/1251] eta: 0:12:26 lr: 0.000327 loss: 3.0560 (3.0701) grad_norm: 1.8182 (1.8355) time: 0.6341 [2021-03-27 16:40:18 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 130/1251] eta: 0:12:16 lr: 0.000327 loss: 3.2196 (3.0933) grad_norm: 1.7465 (1.8257) time: 0.6310 [2021-03-27 16:40:24 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 140/1251] eta: 0:12:08 lr: 0.000327 loss: 3.2196 (3.0719) grad_norm: 1.6941 (1.8192) time: 0.6281 [2021-03-27 16:40:30 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 150/1251] eta: 0:11:58 lr: 0.000327 loss: 3.2506 (3.0913) grad_norm: 1.7372 (1.8161) time: 0.6250 [2021-03-27 16:40:37 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 160/1251] eta: 0:11:51 lr: 0.000327 loss: 3.2622 (3.0841) grad_norm: 1.7577 (1.8199) time: 0.6302 [2021-03-27 16:40:43 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 170/1251] eta: 0:11:43 lr: 0.000327 loss: 3.1935 (3.0954) grad_norm: 1.7371 (1.8176) time: 0.6320 [2021-03-27 16:40:49 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 180/1251] eta: 0:11:35 lr: 0.000327 loss: 3.3863 (3.1044) grad_norm: 1.7119 (1.8166) time: 0.6269 [2021-03-27 16:40:55 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 190/1251] eta: 0:11:27 lr: 0.000327 loss: 3.1982 (3.0914) grad_norm: 1.7344 (1.8192) time: 0.6300 [2021-03-27 16:41:02 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 200/1251] eta: 0:11:20 lr: 0.000327 loss: 2.8186 (3.0693) grad_norm: 1.8623 (1.8235) time: 0.6294 [2021-03-27 16:41:08 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 210/1251] eta: 0:11:12 lr: 0.000327 loss: 3.0115 (3.0774) grad_norm: 1.8623 (1.8270) time: 0.6250 [2021-03-27 16:41:14 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 220/1251] eta: 0:11:05 lr: 0.000327 loss: 3.0623 (3.0719) grad_norm: 1.7801 (1.8256) time: 0.6227 [2021-03-27 16:41:20 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 230/1251] eta: 0:10:58 lr: 0.000327 loss: 3.0339 (3.0801) grad_norm: 1.7577 (1.8262) time: 0.6268 [2021-03-27 16:41:27 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 240/1251] eta: 0:10:50 lr: 0.000327 loss: 3.2494 (3.0854) grad_norm: 1.7368 (1.8240) time: 0.6251 [2021-03-27 16:41:33 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 250/1251] eta: 0:10:43 lr: 0.000327 loss: 3.2494 (3.0966) grad_norm: 1.7872 (1.8278) time: 0.6277 [2021-03-27 16:41:39 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 260/1251] eta: 0:10:36 lr: 0.000327 loss: 3.2723 (3.0983) grad_norm: 1.8241 (1.8294) time: 0.6287 [2021-03-27 16:41:45 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 270/1251] eta: 0:10:29 lr: 0.000327 loss: 3.0745 (3.0947) grad_norm: 1.7937 (1.8285) time: 0.6271 [2021-03-27 16:41:52 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 280/1251] eta: 0:10:22 lr: 0.000327 loss: 3.0711 (3.0920) grad_norm: 1.8061 (1.8288) time: 0.6302 [2021-03-27 16:41:58 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 290/1251] eta: 0:10:16 lr: 0.000326 loss: 3.1940 (3.0988) grad_norm: 1.8167 (1.8285) time: 0.6286 [2021-03-27 16:42:04 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 300/1251] eta: 0:10:09 lr: 0.000326 loss: 3.2946 (3.0996) grad_norm: 1.7185 (1.8249) time: 0.6280 [2021-03-27 16:42:11 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 310/1251] eta: 0:10:02 lr: 0.000326 loss: 3.2159 (3.0986) grad_norm: 1.7325 (1.8249) time: 0.6274 [2021-03-27 16:42:17 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 320/1251] eta: 0:09:55 lr: 0.000326 loss: 3.1071 (3.0997) grad_norm: 1.7398 (1.8253) time: 0.6281 [2021-03-27 16:42:23 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 330/1251] eta: 0:09:48 lr: 0.000326 loss: 3.0469 (3.0971) grad_norm: 1.7972 (1.8251) time: 0.6258 [2021-03-27 16:42:29 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 340/1251] eta: 0:09:41 lr: 0.000326 loss: 3.2168 (3.1014) grad_norm: 1.8485 (1.8304) time: 0.6208 [2021-03-27 16:42:36 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 350/1251] eta: 0:09:35 lr: 0.000326 loss: 3.2168 (3.1000) grad_norm: 1.7854 (1.8271) time: 0.6247 [2021-03-27 16:42:42 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 360/1251] eta: 0:09:28 lr: 0.000326 loss: 2.9811 (3.0979) grad_norm: 1.7531 (1.8297) time: 0.6246 [2021-03-27 16:42:48 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 370/1251] eta: 0:09:21 lr: 0.000326 loss: 3.0644 (3.0991) grad_norm: 1.7226 (1.8242) time: 0.6258 [2021-03-27 16:42:54 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 380/1251] eta: 0:09:15 lr: 0.000326 loss: 3.4392 (3.1069) grad_norm: 1.6876 (1.8241) time: 0.6262 [2021-03-27 16:43:01 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 390/1251] eta: 0:09:08 lr: 0.000326 loss: 3.3550 (3.1046) grad_norm: 1.7207 (1.8223) time: 0.6277 [2021-03-27 16:43:07 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 400/1251] eta: 0:09:02 lr: 0.000326 loss: 3.2692 (3.1068) grad_norm: 1.8330 (1.8288) time: 0.6344 [2021-03-27 16:43:13 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 410/1251] eta: 0:08:55 lr: 0.000326 loss: 3.2277 (3.1056) grad_norm: 1.8697 (1.8317) time: 0.6348 [2021-03-27 16:43:20 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 420/1251] eta: 0:08:49 lr: 0.000326 loss: 3.0304 (3.1037) grad_norm: 1.8214 (1.8339) time: 0.6385 [2021-03-27 16:43:26 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 430/1251] eta: 0:08:43 lr: 0.000326 loss: 3.0304 (3.1009) grad_norm: 1.8301 (1.8339) time: 0.6399 [2021-03-27 16:43:33 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 440/1251] eta: 0:08:36 lr: 0.000326 loss: 3.1188 (3.1023) grad_norm: 1.9061 (1.8356) time: 0.6357 [2021-03-27 16:43:39 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 450/1251] eta: 0:08:30 lr: 0.000326 loss: 3.1931 (3.1044) grad_norm: 1.8270 (1.8337) time: 0.6318 [2021-03-27 16:43:45 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 460/1251] eta: 0:08:23 lr: 0.000326 loss: 3.1931 (3.1058) grad_norm: 1.6910 (1.8316) time: 0.6257 [2021-03-27 16:43:51 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 470/1251] eta: 0:08:17 lr: 0.000326 loss: 3.2637 (3.1090) grad_norm: 1.7340 (1.8333) time: 0.6216 [2021-03-27 16:43:58 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 480/1251] eta: 0:08:10 lr: 0.000326 loss: 3.2417 (3.1103) grad_norm: 1.8714 (1.8348) time: 0.6222 [2021-03-27 16:44:04 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 490/1251] eta: 0:08:03 lr: 0.000326 loss: 3.0032 (3.1090) grad_norm: 1.7860 (1.8338) time: 0.6231 [2021-03-27 16:44:10 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 500/1251] eta: 0:07:57 lr: 0.000326 loss: 2.9708 (3.1088) grad_norm: 1.7860 (1.8329) time: 0.6244 [2021-03-27 16:44:16 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 510/1251] eta: 0:07:50 lr: 0.000326 loss: 3.2550 (3.1098) grad_norm: 1.7574 (1.8326) time: 0.6264 [2021-03-27 16:44:23 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 520/1251] eta: 0:07:44 lr: 0.000326 loss: 3.1927 (3.1076) grad_norm: 1.7236 (1.8307) time: 0.6277 [2021-03-27 16:44:29 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 530/1251] eta: 0:07:38 lr: 0.000326 loss: 3.1366 (3.1086) grad_norm: 1.8387 (1.8326) time: 0.6323 [2021-03-27 16:44:35 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 540/1251] eta: 0:07:31 lr: 0.000326 loss: 3.1640 (3.1107) grad_norm: 1.8112 (1.8312) time: 0.6332 [2021-03-27 16:44:42 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 550/1251] eta: 0:07:25 lr: 0.000325 loss: 3.1640 (3.1085) grad_norm: 1.6842 (1.8302) time: 0.6334 [2021-03-27 16:44:48 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 560/1251] eta: 0:07:18 lr: 0.000325 loss: 3.0855 (3.1067) grad_norm: 1.7919 (1.8323) time: 0.6355 [2021-03-27 16:44:54 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 570/1251] eta: 0:07:12 lr: 0.000325 loss: 3.0483 (3.1060) grad_norm: 1.7919 (1.8308) time: 0.6348 [2021-03-27 16:45:01 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 580/1251] eta: 0:07:06 lr: 0.000325 loss: 3.1336 (3.1063) grad_norm: 1.7966 (1.8329) time: 0.6324 [2021-03-27 16:45:07 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 590/1251] eta: 0:06:59 lr: 0.000325 loss: 3.1846 (3.1093) grad_norm: 1.8632 (1.8332) time: 0.6310 [2021-03-27 16:45:13 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 600/1251] eta: 0:06:53 lr: 0.000325 loss: 3.2812 (3.1124) grad_norm: 1.7669 (1.8334) time: 0.6325 [2021-03-27 16:45:20 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 610/1251] eta: 0:06:46 lr: 0.000325 loss: 3.1380 (3.1101) grad_norm: 1.7667 (1.8306) time: 0.6293 [2021-03-27 16:45:26 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 620/1251] eta: 0:06:40 lr: 0.000325 loss: 3.0549 (3.1098) grad_norm: 1.7206 (1.8303) time: 0.6232 [2021-03-27 16:45:32 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 630/1251] eta: 0:06:34 lr: 0.000325 loss: 3.0311 (3.1095) grad_norm: 1.7022 (1.8278) time: 0.6216 [2021-03-27 16:45:38 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 640/1251] eta: 0:06:27 lr: 0.000325 loss: 3.1813 (3.1104) grad_norm: 1.7022 (1.8259) time: 0.6254 [2021-03-27 16:45:45 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 650/1251] eta: 0:06:21 lr: 0.000325 loss: 3.4029 (3.1133) grad_norm: 1.7951 (1.8280) time: 0.6298 [2021-03-27 16:45:51 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 660/1251] eta: 0:06:14 lr: 0.000325 loss: 3.3863 (3.1145) grad_norm: 1.9127 (1.8336) time: 0.6288 [2021-03-27 16:45:57 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 670/1251] eta: 0:06:08 lr: 0.000325 loss: 3.3068 (3.1156) grad_norm: 1.8786 (1.8342) time: 0.6255 [2021-03-27 16:46:03 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 680/1251] eta: 0:06:01 lr: 0.000325 loss: 3.3068 (3.1191) grad_norm: 1.8572 (1.8353) time: 0.6248 [2021-03-27 16:46:10 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 690/1251] eta: 0:05:55 lr: 0.000325 loss: 3.3617 (3.1241) grad_norm: 1.7515 (1.8350) time: 0.6283 [2021-03-27 16:46:16 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 700/1251] eta: 0:05:49 lr: 0.000325 loss: 3.3611 (3.1261) grad_norm: 1.8290 (1.8350) time: 0.6278 [2021-03-27 16:46:22 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 710/1251] eta: 0:05:42 lr: 0.000325 loss: 3.3760 (3.1287) grad_norm: 1.8181 (1.8372) time: 0.6206 [2021-03-27 16:46:28 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 720/1251] eta: 0:05:36 lr: 0.000325 loss: 3.1822 (3.1274) grad_norm: 1.8000 (1.8360) time: 0.6222 [2021-03-27 16:46:35 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 730/1251] eta: 0:05:29 lr: 0.000325 loss: 3.1403 (3.1282) grad_norm: 1.8023 (1.8364) time: 0.6264 [2021-03-27 16:46:41 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 740/1251] eta: 0:05:23 lr: 0.000325 loss: 3.2608 (3.1288) grad_norm: 1.8023 (1.8354) time: 0.6237 [2021-03-27 16:46:47 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 750/1251] eta: 0:05:17 lr: 0.000325 loss: 3.1955 (3.1282) grad_norm: 1.7123 (1.8345) time: 0.6293 [2021-03-27 16:46:53 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 760/1251] eta: 0:05:10 lr: 0.000325 loss: 3.2602 (3.1292) grad_norm: 1.7518 (1.8337) time: 0.6319 [2021-03-27 16:47:00 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 770/1251] eta: 0:05:04 lr: 0.000325 loss: 3.3289 (3.1315) grad_norm: 1.7967 (1.8342) time: 0.6282 [2021-03-27 16:47:06 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 780/1251] eta: 0:04:58 lr: 0.000325 loss: 3.3289 (3.1320) grad_norm: 1.7112 (1.8333) time: 0.6306 [2021-03-27 16:47:12 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 790/1251] eta: 0:04:51 lr: 0.000325 loss: 3.2266 (3.1329) grad_norm: 1.7470 (1.8335) time: 0.6348 [2021-03-27 16:47:19 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 800/1251] eta: 0:04:45 lr: 0.000325 loss: 3.2756 (3.1365) grad_norm: 1.8173 (1.8327) time: 0.6306 [2021-03-27 16:47:25 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 810/1251] eta: 0:04:39 lr: 0.000324 loss: 3.2555 (3.1346) grad_norm: 1.8324 (1.8338) time: 0.6233 [2021-03-27 16:47:31 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 820/1251] eta: 0:04:32 lr: 0.000324 loss: 3.1184 (3.1366) grad_norm: 1.8324 (1.8335) time: 0.6284 [2021-03-27 16:47:37 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 830/1251] eta: 0:04:26 lr: 0.000324 loss: 3.3331 (3.1357) grad_norm: 1.8163 (nan) time: 0.6243 [2021-03-27 16:47:44 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 840/1251] eta: 0:04:20 lr: 0.000324 loss: 3.2205 (3.1363) grad_norm: 1.7611 (nan) time: 0.6213 [2021-03-27 16:47:50 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 850/1251] eta: 0:04:13 lr: 0.000324 loss: 3.2166 (3.1370) grad_norm: 1.7352 (nan) time: 0.6266 [2021-03-27 16:47:56 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 860/1251] eta: 0:04:07 lr: 0.000324 loss: 3.0235 (3.1350) grad_norm: 1.8405 (nan) time: 0.6271 [2021-03-27 16:48:03 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 870/1251] eta: 0:04:01 lr: 0.000324 loss: 2.9258 (3.1353) grad_norm: 1.8341 (nan) time: 0.6324 [2021-03-27 16:48:09 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 880/1251] eta: 0:03:54 lr: 0.000324 loss: 2.9898 (3.1322) grad_norm: 1.7546 (nan) time: 0.6281 [2021-03-27 16:48:15 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 890/1251] eta: 0:03:48 lr: 0.000324 loss: 2.9884 (3.1306) grad_norm: 1.7544 (nan) time: 0.6260 [2021-03-27 16:48:21 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 900/1251] eta: 0:03:41 lr: 0.000324 loss: 3.0177 (3.1296) grad_norm: 1.6788 (nan) time: 0.6265 [2021-03-27 16:48:28 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 910/1251] eta: 0:03:35 lr: 0.000324 loss: 3.1523 (3.1316) grad_norm: 1.7313 (nan) time: 0.6209 [2021-03-27 16:48:34 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 920/1251] eta: 0:03:29 lr: 0.000324 loss: 2.9888 (3.1283) grad_norm: 1.7908 (nan) time: 0.6286 [2021-03-27 16:48:40 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 930/1251] eta: 0:03:22 lr: 0.000324 loss: 3.0746 (3.1301) grad_norm: 1.7458 (nan) time: 0.6373 [2021-03-27 16:48:47 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 940/1251] eta: 0:03:16 lr: 0.000324 loss: 3.1861 (3.1284) grad_norm: 1.7108 (nan) time: 0.6328 [2021-03-27 16:48:53 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 950/1251] eta: 0:03:10 lr: 0.000324 loss: 3.1060 (3.1278) grad_norm: 1.7936 (nan) time: 0.6263 [2021-03-27 16:48:59 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 960/1251] eta: 0:03:03 lr: 0.000324 loss: 3.1345 (3.1275) grad_norm: 1.7922 (nan) time: 0.6248 [2021-03-27 16:49:05 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 970/1251] eta: 0:02:57 lr: 0.000324 loss: 3.2109 (3.1271) grad_norm: 1.7152 (nan) time: 0.6198 [2021-03-27 16:49:12 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 980/1251] eta: 0:02:51 lr: 0.000324 loss: 3.3419 (3.1298) grad_norm: 1.7505 (nan) time: 0.6245 [2021-03-27 16:49:18 swin_base_patch4_window7_224] INFO: Epoch: [185] [ 990/1251] eta: 0:02:44 lr: 0.000324 loss: 3.4879 (3.1336) grad_norm: 1.7828 (nan) time: 0.6323 [2021-03-27 16:49:24 swin_base_patch4_window7_224] INFO: Epoch: [185] [1000/1251] eta: 0:02:38 lr: 0.000324 loss: 3.3913 (3.1326) grad_norm: 1.7730 (nan) time: 0.6270 [2021-03-27 16:49:30 swin_base_patch4_window7_224] INFO: Epoch: [185] [1010/1251] eta: 0:02:32 lr: 0.000324 loss: 3.1665 (3.1344) grad_norm: 1.7430 (nan) time: 0.6262 [2021-03-27 16:49:37 swin_base_patch4_window7_224] INFO: Epoch: [185] [1020/1251] eta: 0:02:25 lr: 0.000324 loss: 3.1666 (3.1337) grad_norm: 1.8653 (nan) time: 0.6268 [2021-03-27 16:49:43 swin_base_patch4_window7_224] INFO: Epoch: [185] [1030/1251] eta: 0:02:19 lr: 0.000324 loss: 2.8103 (3.1299) grad_norm: 1.8653 (nan) time: 0.6244 [2021-03-27 16:49:49 swin_base_patch4_window7_224] INFO: Epoch: [185] [1040/1251] eta: 0:02:13 lr: 0.000324 loss: 3.0413 (3.1319) grad_norm: 1.8195 (nan) time: 0.6259 [2021-03-27 16:49:55 swin_base_patch4_window7_224] INFO: Epoch: [185] [1050/1251] eta: 0:02:06 lr: 0.000324 loss: 3.3658 (3.1340) grad_norm: 1.7729 (nan) time: 0.6244 [2021-03-27 16:50:02 swin_base_patch4_window7_224] INFO: Epoch: [185] [1060/1251] eta: 0:02:00 lr: 0.000324 loss: 3.4594 (3.1357) grad_norm: 1.7729 (nan) time: 0.6252 [2021-03-27 16:50:08 swin_base_patch4_window7_224] INFO: Epoch: [185] [1070/1251] eta: 0:01:54 lr: 0.000323 loss: 3.3578 (3.1345) grad_norm: 1.8526 (nan) time: 0.6242 [2021-03-27 16:50:14 swin_base_patch4_window7_224] INFO: Epoch: [185] [1080/1251] eta: 0:01:47 lr: 0.000323 loss: 3.2521 (3.1347) grad_norm: 1.7157 (nan) time: 0.6295 [2021-03-27 16:50:20 swin_base_patch4_window7_224] INFO: Epoch: [185] [1090/1251] eta: 0:01:41 lr: 0.000323 loss: 3.1337 (3.1337) grad_norm: 1.7157 (nan) time: 0.6300 [2021-03-27 16:50:27 swin_base_patch4_window7_224] INFO: Epoch: [185] [1100/1251] eta: 0:01:35 lr: 0.000323 loss: 3.0937 (3.1330) grad_norm: 1.8030 (nan) time: 0.6232 [2021-03-27 16:50:33 swin_base_patch4_window7_224] INFO: Epoch: [185] [1110/1251] eta: 0:01:29 lr: 0.000323 loss: 3.0959 (3.1329) grad_norm: 1.7971 (nan) time: 0.6260 [2021-03-27 16:50:39 swin_base_patch4_window7_224] INFO: Epoch: [185] [1120/1251] eta: 0:01:22 lr: 0.000323 loss: 3.3034 (3.1362) grad_norm: 1.7796 (nan) time: 0.6303 [2021-03-27 16:50:45 swin_base_patch4_window7_224] INFO: Epoch: [185] [1130/1251] eta: 0:01:16 lr: 0.000323 loss: 3.4265 (3.1377) grad_norm: 1.7999 (nan) time: 0.6261 [2021-03-27 16:50:52 swin_base_patch4_window7_224] INFO: Epoch: [185] [1140/1251] eta: 0:01:10 lr: 0.000323 loss: 3.2168 (3.1367) grad_norm: 1.9923 (nan) time: 0.6271 [2021-03-27 16:50:58 swin_base_patch4_window7_224] INFO: Epoch: [185] [1150/1251] eta: 0:01:03 lr: 0.000323 loss: 3.1210 (3.1354) grad_norm: 1.8907 (nan) time: 0.6272 [2021-03-27 16:51:04 swin_base_patch4_window7_224] INFO: Epoch: [185] [1160/1251] eta: 0:00:57 lr: 0.000323 loss: 3.1746 (3.1361) grad_norm: 1.8907 (nan) time: 0.6215 [2021-03-27 16:51:10 swin_base_patch4_window7_224] INFO: Epoch: [185] [1170/1251] eta: 0:00:51 lr: 0.000323 loss: 3.3210 (3.1371) grad_norm: 1.8525 (nan) time: 0.6229 [2021-03-27 16:51:17 swin_base_patch4_window7_224] INFO: Epoch: [185] [1180/1251] eta: 0:00:44 lr: 0.000323 loss: 3.2733 (3.1373) grad_norm: 1.7883 (nan) time: 0.6219 [2021-03-27 16:51:23 swin_base_patch4_window7_224] INFO: Epoch: [185] [1190/1251] eta: 0:00:38 lr: 0.000323 loss: 2.9947 (3.1358) grad_norm: 1.6881 (nan) time: 0.6274 [2021-03-27 16:51:29 swin_base_patch4_window7_224] INFO: Epoch: [185] [1200/1251] eta: 0:00:32 lr: 0.000323 loss: 2.9829 (3.1367) grad_norm: 1.7257 (nan) time: 0.6285 [2021-03-27 16:51:36 swin_base_patch4_window7_224] INFO: Epoch: [185] [1210/1251] eta: 0:00:25 lr: 0.000323 loss: 3.4242 (3.1399) grad_norm: 1.9432 (nan) time: 0.6240 [2021-03-27 16:51:42 swin_base_patch4_window7_224] INFO: Epoch: [185] [1220/1251] eta: 0:00:19 lr: 0.000323 loss: 3.3806 (3.1413) grad_norm: 1.8923 (nan) time: 0.6222 [2021-03-27 16:51:48 swin_base_patch4_window7_224] INFO: Epoch: [185] [1230/1251] eta: 0:00:13 lr: 0.000323 loss: 3.2869 (3.1416) grad_norm: 1.8007 (nan) time: 0.6210 [2021-03-27 16:51:54 swin_base_patch4_window7_224] INFO: Epoch: [185] [1240/1251] eta: 0:00:06 lr: 0.000323 loss: 3.2245 (3.1413) grad_norm: 1.7661 (nan) time: 0.6195 [2021-03-27 16:52:00 swin_base_patch4_window7_224] INFO: Epoch: [185] [1250/1251] eta: 0:00:00 lr: 0.000323 loss: 3.0798 (3.1399) grad_norm: 1.7846 (nan) time: 0.6224 [2021-03-27 16:53:17 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:04 loss: 0.9171 (0.9171) acc1: 81.2500 (81.2500) acc5: 92.1875 (92.1875) [2021-03-27 16:53:18 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.8746 (0.8952) acc1: 78.1250 (77.2727) acc5: 96.8750 (95.5966) [2021-03-27 16:53:20 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7985 (0.8167) acc1: 79.6875 (80.2083) acc5: 96.8750 (95.8333) [2021-03-27 16:53:21 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7893 (0.8350) acc1: 81.2500 (80.1915) acc5: 95.3125 (95.4637) [2021-03-27 16:53:22 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8410 (0.8398) acc1: 79.6875 (79.9543) acc5: 95.3125 (95.5793) [2021-03-27 16:53:24 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8394 (0.8405) acc1: 81.2500 (80.2240) acc5: 96.8750 (95.5200) [2021-03-27 16:53:34 swin_base_patch4_window7_224] INFO: * Acc@1 80.658 Acc@5 95.506 loss 0.840 [2021-03-27 16:53:34 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.7% [2021-03-27 16:53:34 swin_base_patch4_window7_224] INFO: Max accuracy: 80.66% [2021-03-27 16:53:38 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 0/1251] eta: 1:31:07 lr: 0.000323 loss: 2.6173 (2.6173) grad_norm: 1.7021 (1.7021) time: 4.3704 [2021-03-27 16:53:44 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 10/1251] eta: 0:20:02 lr: 0.000323 loss: 3.3418 (3.2278) grad_norm: 1.8160 (1.9349) time: 0.9692 [2021-03-27 16:53:51 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 20/1251] eta: 0:16:35 lr: 0.000323 loss: 3.2415 (3.1738) grad_norm: 1.7579 (1.8438) time: 0.6304 [2021-03-27 16:53:57 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 30/1251] eta: 0:15:18 lr: 0.000323 loss: 3.0258 (3.0693) grad_norm: 1.6615 (1.8011) time: 0.6329 [2021-03-27 16:54:03 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 40/1251] eta: 0:14:31 lr: 0.000323 loss: 3.0524 (3.0661) grad_norm: 1.6976 (1.8341) time: 0.6271 [2021-03-27 16:54:09 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 50/1251] eta: 0:14:02 lr: 0.000323 loss: 3.1788 (3.0676) grad_norm: 1.8787 (1.8688) time: 0.6239 [2021-03-27 16:54:16 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 60/1251] eta: 0:13:41 lr: 0.000323 loss: 3.2532 (3.1110) grad_norm: 1.7828 (1.8565) time: 0.6265 [2021-03-27 16:54:22 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 70/1251] eta: 0:13:25 lr: 0.000323 loss: 3.4019 (3.1589) grad_norm: 1.8136 (1.8598) time: 0.6323 [2021-03-27 16:54:28 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 80/1251] eta: 0:13:11 lr: 0.000322 loss: 3.4119 (3.1577) grad_norm: 1.8510 (1.8651) time: 0.6337 [2021-03-27 16:54:35 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 90/1251] eta: 0:12:58 lr: 0.000322 loss: 3.3439 (3.1553) grad_norm: 1.7224 (1.8437) time: 0.6303 [2021-03-27 16:54:41 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 100/1251] eta: 0:12:46 lr: 0.000322 loss: 3.2890 (3.1479) grad_norm: 1.6766 (1.8405) time: 0.6282 [2021-03-27 16:54:47 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 110/1251] eta: 0:12:35 lr: 0.000322 loss: 3.3382 (3.1661) grad_norm: 1.8010 (1.8392) time: 0.6246 [2021-03-27 16:54:53 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 120/1251] eta: 0:12:26 lr: 0.000322 loss: 3.1315 (3.1642) grad_norm: 1.8010 (1.8472) time: 0.6268 [2021-03-27 16:55:00 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 130/1251] eta: 0:12:16 lr: 0.000322 loss: 3.1315 (3.1700) grad_norm: 1.9463 (1.8634) time: 0.6290 [2021-03-27 16:55:06 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 140/1251] eta: 0:12:07 lr: 0.000322 loss: 3.2344 (3.1622) grad_norm: 1.9462 (1.8859) time: 0.6254 [2021-03-27 16:55:12 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 150/1251] eta: 0:11:59 lr: 0.000322 loss: 3.2927 (3.1607) grad_norm: 1.9073 (1.8801) time: 0.6274 [2021-03-27 16:55:18 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 160/1251] eta: 0:11:50 lr: 0.000322 loss: 3.2291 (3.1566) grad_norm: 1.7597 (1.8738) time: 0.6276 [2021-03-27 16:55:25 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 170/1251] eta: 0:11:42 lr: 0.000322 loss: 2.9944 (3.1566) grad_norm: 1.7597 (1.8717) time: 0.6239 [2021-03-27 16:55:31 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 180/1251] eta: 0:11:34 lr: 0.000322 loss: 3.2606 (3.1564) grad_norm: 1.7122 (1.8650) time: 0.6230 [2021-03-27 16:55:37 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 190/1251] eta: 0:11:27 lr: 0.000322 loss: 3.2228 (3.1497) grad_norm: 1.7840 (1.8612) time: 0.6267 [2021-03-27 16:55:44 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 200/1251] eta: 0:11:19 lr: 0.000322 loss: 2.9667 (3.1422) grad_norm: 1.7217 (1.8553) time: 0.6325 [2021-03-27 16:55:50 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 210/1251] eta: 0:11:11 lr: 0.000322 loss: 3.0777 (3.1385) grad_norm: 1.8261 (1.8626) time: 0.6262 [2021-03-27 16:55:56 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 220/1251] eta: 0:11:04 lr: 0.000322 loss: 3.0777 (3.1318) grad_norm: 1.9249 (1.8678) time: 0.6231 [2021-03-27 16:56:02 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 230/1251] eta: 0:10:57 lr: 0.000322 loss: 3.3476 (3.1437) grad_norm: 1.8398 (1.8708) time: 0.6298 [2021-03-27 16:56:09 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 240/1251] eta: 0:10:50 lr: 0.000322 loss: 3.2578 (3.1356) grad_norm: 1.8647 (1.8809) time: 0.6312 [2021-03-27 16:56:15 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 250/1251] eta: 0:10:43 lr: 0.000322 loss: 3.2203 (3.1402) grad_norm: 1.8353 (1.8787) time: 0.6293 [2021-03-27 16:56:21 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 260/1251] eta: 0:10:36 lr: 0.000322 loss: 3.2219 (3.1462) grad_norm: 1.7636 (1.8764) time: 0.6290 [2021-03-27 16:56:28 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 270/1251] eta: 0:10:29 lr: 0.000322 loss: 3.1377 (3.1317) grad_norm: 1.7875 (1.8767) time: 0.6279 [2021-03-27 16:56:34 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 280/1251] eta: 0:10:22 lr: 0.000322 loss: 2.9975 (3.1329) grad_norm: 1.8102 (1.8831) time: 0.6281 [2021-03-27 16:56:40 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 290/1251] eta: 0:10:16 lr: 0.000322 loss: 3.2488 (3.1359) grad_norm: 1.7924 (1.8784) time: 0.6315 [2021-03-27 16:56:46 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 300/1251] eta: 0:10:09 lr: 0.000322 loss: 3.2488 (3.1377) grad_norm: 1.7292 (1.8753) time: 0.6294 [2021-03-27 16:56:53 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 310/1251] eta: 0:10:02 lr: 0.000322 loss: 3.2404 (3.1398) grad_norm: 1.7589 (1.8748) time: 0.6255 [2021-03-27 16:56:59 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 320/1251] eta: 0:09:55 lr: 0.000322 loss: 3.2566 (3.1478) grad_norm: 1.7589 (1.8726) time: 0.6301 [2021-03-27 16:57:05 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 330/1251] eta: 0:09:49 lr: 0.000322 loss: 3.3110 (3.1469) grad_norm: 1.7702 (1.8689) time: 0.6387 [2021-03-27 16:57:12 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 340/1251] eta: 0:09:42 lr: 0.000321 loss: 3.2727 (3.1476) grad_norm: 1.7300 (1.8697) time: 0.6336 [2021-03-27 16:57:18 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 350/1251] eta: 0:09:35 lr: 0.000321 loss: 3.2376 (3.1510) grad_norm: 1.7157 (1.8688) time: 0.6235 [2021-03-27 16:57:24 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 360/1251] eta: 0:09:29 lr: 0.000321 loss: 3.2041 (3.1507) grad_norm: 1.7157 (1.8657) time: 0.6245 [2021-03-27 16:57:30 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 370/1251] eta: 0:09:22 lr: 0.000321 loss: 3.1803 (3.1523) grad_norm: 1.6901 (1.8638) time: 0.6249 [2021-03-27 16:57:37 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 380/1251] eta: 0:09:15 lr: 0.000321 loss: 3.2281 (3.1550) grad_norm: 1.6246 (1.8591) time: 0.6246 [2021-03-27 16:57:43 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 390/1251] eta: 0:09:08 lr: 0.000321 loss: 3.2594 (3.1560) grad_norm: 1.6532 (1.8584) time: 0.6240 [2021-03-27 16:57:49 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 400/1251] eta: 0:09:02 lr: 0.000321 loss: 3.2106 (3.1487) grad_norm: 1.7309 (1.8577) time: 0.6238 [2021-03-27 16:57:55 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 410/1251] eta: 0:08:55 lr: 0.000321 loss: 3.1167 (3.1456) grad_norm: 1.7948 (1.8646) time: 0.6241 [2021-03-27 16:58:02 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 420/1251] eta: 0:08:49 lr: 0.000321 loss: 3.2057 (3.1468) grad_norm: 1.8597 (1.8669) time: 0.6238 [2021-03-27 16:58:08 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 430/1251] eta: 0:08:42 lr: 0.000321 loss: 3.2145 (3.1449) grad_norm: 1.7963 (1.8651) time: 0.6213 [2021-03-27 16:58:14 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 440/1251] eta: 0:08:35 lr: 0.000321 loss: 3.3296 (3.1448) grad_norm: 1.8355 (1.8687) time: 0.6259 [2021-03-27 16:58:20 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 450/1251] eta: 0:08:29 lr: 0.000321 loss: 3.3296 (3.1475) grad_norm: 1.8185 (1.8657) time: 0.6281 [2021-03-27 16:58:27 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 460/1251] eta: 0:08:22 lr: 0.000321 loss: 3.2515 (3.1448) grad_norm: 1.8238 (1.8672) time: 0.6242 [2021-03-27 16:58:33 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 470/1251] eta: 0:08:16 lr: 0.000321 loss: 3.1687 (3.1435) grad_norm: 1.8600 (1.8695) time: 0.6259 [2021-03-27 16:58:39 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 480/1251] eta: 0:08:09 lr: 0.000321 loss: 3.2303 (3.1445) grad_norm: 1.8195 (1.8701) time: 0.6268 [2021-03-27 16:58:45 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 490/1251] eta: 0:08:03 lr: 0.000321 loss: 3.1456 (3.1392) grad_norm: 1.7738 (1.8690) time: 0.6231 [2021-03-27 16:58:52 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 500/1251] eta: 0:07:56 lr: 0.000321 loss: 3.0020 (3.1361) grad_norm: 1.7738 (1.8694) time: 0.6220 [2021-03-27 16:58:58 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 510/1251] eta: 0:07:50 lr: 0.000321 loss: 3.2479 (3.1389) grad_norm: 1.7680 (1.8672) time: 0.6234 [2021-03-27 16:59:04 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 520/1251] eta: 0:07:43 lr: 0.000321 loss: 3.1827 (3.1336) grad_norm: 1.7679 (1.8663) time: 0.6276 [2021-03-27 16:59:11 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 530/1251] eta: 0:07:37 lr: 0.000321 loss: 3.3082 (3.1397) grad_norm: 1.7567 (1.8648) time: 0.6310 [2021-03-27 16:59:17 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 540/1251] eta: 0:07:30 lr: 0.000321 loss: 3.2670 (3.1380) grad_norm: 1.7567 (1.8653) time: 0.6288 [2021-03-27 16:59:23 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 550/1251] eta: 0:07:24 lr: 0.000321 loss: 3.0884 (3.1387) grad_norm: 1.8636 (1.8661) time: 0.6422 [2021-03-27 16:59:30 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 560/1251] eta: 0:07:18 lr: 0.000321 loss: 2.9598 (3.1320) grad_norm: 1.8298 (1.8665) time: 0.6377 [2021-03-27 16:59:36 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 570/1251] eta: 0:07:11 lr: 0.000321 loss: 3.0466 (3.1320) grad_norm: 1.7056 (1.8671) time: 0.6209 [2021-03-27 16:59:42 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 580/1251] eta: 0:07:05 lr: 0.000321 loss: 3.1946 (3.1350) grad_norm: 1.8207 (1.8664) time: 0.6271 [2021-03-27 16:59:48 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 590/1251] eta: 0:06:58 lr: 0.000321 loss: 3.1519 (3.1328) grad_norm: 1.8207 (1.8664) time: 0.6242 [2021-03-27 16:59:55 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 600/1251] eta: 0:06:52 lr: 0.000320 loss: 3.1955 (3.1353) grad_norm: 1.8851 (1.8671) time: 0.6253 [2021-03-27 17:00:01 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 610/1251] eta: 0:06:46 lr: 0.000320 loss: 3.1955 (3.1303) grad_norm: 1.8311 (1.8671) time: 0.6311 [2021-03-27 17:00:07 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 620/1251] eta: 0:06:39 lr: 0.000320 loss: 3.0188 (3.1283) grad_norm: 1.7702 (1.8657) time: 0.6256 [2021-03-27 17:00:13 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 630/1251] eta: 0:06:33 lr: 0.000320 loss: 3.0756 (3.1280) grad_norm: 1.7534 (1.8649) time: 0.6272 [2021-03-27 17:00:20 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 640/1251] eta: 0:06:27 lr: 0.000320 loss: 3.0756 (3.1264) grad_norm: 1.7527 (1.8636) time: 0.6289 [2021-03-27 17:00:26 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 650/1251] eta: 0:06:20 lr: 0.000320 loss: 2.9537 (3.1236) grad_norm: 1.7751 (1.8687) time: 0.6240 [2021-03-27 17:00:32 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 660/1251] eta: 0:06:14 lr: 0.000320 loss: 3.0093 (3.1230) grad_norm: 2.0672 (1.8736) time: 0.6217 [2021-03-27 17:00:38 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 670/1251] eta: 0:06:07 lr: 0.000320 loss: 3.1759 (3.1235) grad_norm: 1.8731 (1.8723) time: 0.6225 [2021-03-27 17:00:45 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 680/1251] eta: 0:06:01 lr: 0.000320 loss: 3.2791 (3.1270) grad_norm: 1.7921 (1.8737) time: 0.6260 [2021-03-27 17:00:51 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 690/1251] eta: 0:05:55 lr: 0.000320 loss: 3.4573 (3.1318) grad_norm: 1.9435 (1.8759) time: 0.6319 [2021-03-27 17:00:57 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 700/1251] eta: 0:05:48 lr: 0.000320 loss: 3.3897 (3.1333) grad_norm: 1.9217 (1.8761) time: 0.6283 [2021-03-27 17:01:04 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 710/1251] eta: 0:05:42 lr: 0.000320 loss: 3.3907 (3.1374) grad_norm: 1.8457 (1.8753) time: 0.6240 [2021-03-27 17:01:10 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 720/1251] eta: 0:05:35 lr: 0.000320 loss: 3.3409 (3.1375) grad_norm: 1.8167 (1.8742) time: 0.6242 [2021-03-27 17:01:16 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 730/1251] eta: 0:05:29 lr: 0.000320 loss: 3.3095 (3.1409) grad_norm: 1.7753 (1.8726) time: 0.6220 [2021-03-27 17:01:22 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 740/1251] eta: 0:05:23 lr: 0.000320 loss: 3.4437 (3.1428) grad_norm: 1.7821 (1.8722) time: 0.6319 [2021-03-27 17:01:29 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 750/1251] eta: 0:05:16 lr: 0.000320 loss: 3.1604 (3.1408) grad_norm: 1.8223 (1.8719) time: 0.6427 [2021-03-27 17:01:35 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 760/1251] eta: 0:05:10 lr: 0.000320 loss: 3.0741 (3.1411) grad_norm: 1.8204 (1.8719) time: 0.6328 [2021-03-27 17:01:41 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 770/1251] eta: 0:05:04 lr: 0.000320 loss: 3.0741 (3.1398) grad_norm: 1.8263 (1.8713) time: 0.6239 [2021-03-27 17:01:48 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 780/1251] eta: 0:04:57 lr: 0.000320 loss: 3.0424 (3.1402) grad_norm: 1.7774 (1.8704) time: 0.6284 [2021-03-27 17:01:54 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 790/1251] eta: 0:04:51 lr: 0.000320 loss: 3.3256 (3.1405) grad_norm: 1.8035 (1.8712) time: 0.6276 [2021-03-27 17:02:00 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 800/1251] eta: 0:04:45 lr: 0.000320 loss: 3.2182 (3.1404) grad_norm: 1.7949 (1.8696) time: 0.6221 [2021-03-27 17:02:06 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 810/1251] eta: 0:04:38 lr: 0.000320 loss: 2.8982 (3.1381) grad_norm: 1.7500 (1.8695) time: 0.6226 [2021-03-27 17:02:13 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 820/1251] eta: 0:04:32 lr: 0.000320 loss: 3.0893 (3.1397) grad_norm: 1.7791 (1.8713) time: 0.6271 [2021-03-27 17:02:19 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 830/1251] eta: 0:04:26 lr: 0.000320 loss: 3.3607 (3.1410) grad_norm: 1.7650 (1.8703) time: 0.6316 [2021-03-27 17:02:25 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 840/1251] eta: 0:04:19 lr: 0.000320 loss: 3.2419 (3.1413) grad_norm: 1.7349 (1.8683) time: 0.6331 [2021-03-27 17:02:32 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 850/1251] eta: 0:04:13 lr: 0.000320 loss: 3.0725 (3.1412) grad_norm: 1.7182 (1.8692) time: 0.6286 [2021-03-27 17:02:38 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 860/1251] eta: 0:04:07 lr: 0.000319 loss: 2.9860 (3.1391) grad_norm: 1.8069 (1.8684) time: 0.6285 [2021-03-27 17:02:44 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 870/1251] eta: 0:04:00 lr: 0.000319 loss: 3.0016 (3.1389) grad_norm: 1.7875 (1.8697) time: 0.6294 [2021-03-27 17:02:50 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 880/1251] eta: 0:03:54 lr: 0.000319 loss: 3.1991 (3.1411) grad_norm: 1.7563 (1.8687) time: 0.6297 [2021-03-27 17:02:57 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 890/1251] eta: 0:03:48 lr: 0.000319 loss: 3.4252 (3.1436) grad_norm: 1.6569 (1.8669) time: 0.6277 [2021-03-27 17:03:03 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 900/1251] eta: 0:03:41 lr: 0.000319 loss: 3.3278 (3.1454) grad_norm: 1.6932 (1.8660) time: 0.6282 [2021-03-27 17:03:09 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 910/1251] eta: 0:03:35 lr: 0.000319 loss: 3.1833 (3.1441) grad_norm: 1.8519 (1.8666) time: 0.6277 [2021-03-27 17:03:16 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 920/1251] eta: 0:03:29 lr: 0.000319 loss: 3.1364 (3.1427) grad_norm: 1.8585 (1.8658) time: 0.6240 [2021-03-27 17:03:22 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 930/1251] eta: 0:03:22 lr: 0.000319 loss: 3.1364 (3.1412) grad_norm: 1.8211 (1.8661) time: 0.6233 [2021-03-27 17:03:28 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 940/1251] eta: 0:03:16 lr: 0.000319 loss: 3.2204 (3.1404) grad_norm: 1.8211 (1.8656) time: 0.6220 [2021-03-27 17:03:34 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 950/1251] eta: 0:03:10 lr: 0.000319 loss: 2.9107 (3.1390) grad_norm: 1.7100 (1.8646) time: 0.6259 [2021-03-27 17:03:41 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 960/1251] eta: 0:03:03 lr: 0.000319 loss: 2.8047 (3.1361) grad_norm: 1.7459 (1.8633) time: 0.6295 [2021-03-27 17:03:47 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 970/1251] eta: 0:02:57 lr: 0.000319 loss: 2.7335 (3.1335) grad_norm: 1.7639 (1.8628) time: 0.6324 [2021-03-27 17:03:53 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 980/1251] eta: 0:02:51 lr: 0.000319 loss: 3.2748 (3.1368) grad_norm: 1.8301 (1.8654) time: 0.6296 [2021-03-27 17:03:59 swin_base_patch4_window7_224] INFO: Epoch: [186] [ 990/1251] eta: 0:02:44 lr: 0.000319 loss: 3.4470 (3.1386) grad_norm: 1.9777 (1.8664) time: 0.6245 [2021-03-27 17:04:06 swin_base_patch4_window7_224] INFO: Epoch: [186] [1000/1251] eta: 0:02:38 lr: 0.000319 loss: 3.1608 (3.1368) grad_norm: 1.7809 (1.8650) time: 0.6354 [2021-03-27 17:04:12 swin_base_patch4_window7_224] INFO: Epoch: [186] [1010/1251] eta: 0:02:32 lr: 0.000319 loss: 2.8944 (3.1356) grad_norm: 1.7673 (1.8651) time: 0.6369 [2021-03-27 17:04:18 swin_base_patch4_window7_224] INFO: Epoch: [186] [1020/1251] eta: 0:02:25 lr: 0.000319 loss: 3.0591 (3.1341) grad_norm: 1.7857 (1.8651) time: 0.6283 [2021-03-27 17:04:25 swin_base_patch4_window7_224] INFO: Epoch: [186] [1030/1251] eta: 0:02:19 lr: 0.000319 loss: 3.2551 (3.1345) grad_norm: 1.7857 (1.8654) time: 0.6284 [2021-03-27 17:04:31 swin_base_patch4_window7_224] INFO: Epoch: [186] [1040/1251] eta: 0:02:13 lr: 0.000319 loss: 3.2551 (3.1345) grad_norm: 1.6928 (1.8639) time: 0.6224 [2021-03-27 17:04:37 swin_base_patch4_window7_224] INFO: Epoch: [186] [1050/1251] eta: 0:02:06 lr: 0.000319 loss: 3.3420 (3.1365) grad_norm: 1.7695 (1.8634) time: 0.6241 [2021-03-27 17:04:43 swin_base_patch4_window7_224] INFO: Epoch: [186] [1060/1251] eta: 0:02:00 lr: 0.000319 loss: 3.2771 (3.1336) grad_norm: 1.8447 (1.8636) time: 0.6289 [2021-03-27 17:04:50 swin_base_patch4_window7_224] INFO: Epoch: [186] [1070/1251] eta: 0:01:54 lr: 0.000319 loss: 3.1296 (3.1339) grad_norm: 1.8737 (1.8644) time: 0.6324 [2021-03-27 17:04:56 swin_base_patch4_window7_224] INFO: Epoch: [186] [1080/1251] eta: 0:01:47 lr: 0.000319 loss: 3.1296 (3.1314) grad_norm: 1.8250 (1.8653) time: 0.6325 [2021-03-27 17:05:02 swin_base_patch4_window7_224] INFO: Epoch: [186] [1090/1251] eta: 0:01:41 lr: 0.000319 loss: 3.1338 (3.1314) grad_norm: 1.8250 (1.8660) time: 0.6263 [2021-03-27 17:05:09 swin_base_patch4_window7_224] INFO: Epoch: [186] [1100/1251] eta: 0:01:35 lr: 0.000319 loss: 3.3602 (3.1323) grad_norm: 1.8590 (1.8657) time: 0.6230 [2021-03-27 17:05:15 swin_base_patch4_window7_224] INFO: Epoch: [186] [1110/1251] eta: 0:01:28 lr: 0.000319 loss: 2.9489 (3.1289) grad_norm: 1.7774 (1.8660) time: 0.6238 [2021-03-27 17:05:21 swin_base_patch4_window7_224] INFO: Epoch: [186] [1120/1251] eta: 0:01:22 lr: 0.000318 loss: 2.8314 (3.1280) grad_norm: 1.7774 (1.8663) time: 0.6273 [2021-03-27 17:05:27 swin_base_patch4_window7_224] INFO: Epoch: [186] [1130/1251] eta: 0:01:16 lr: 0.000318 loss: 3.1372 (3.1279) grad_norm: 1.7597 (1.8671) time: 0.6260 [2021-03-27 17:05:34 swin_base_patch4_window7_224] INFO: Epoch: [186] [1140/1251] eta: 0:01:10 lr: 0.000318 loss: 3.2056 (3.1271) grad_norm: 1.8165 (1.8663) time: 0.6232 [2021-03-27 17:05:40 swin_base_patch4_window7_224] INFO: Epoch: [186] [1150/1251] eta: 0:01:03 lr: 0.000318 loss: 3.3216 (3.1279) grad_norm: 1.8165 (1.8658) time: 0.6233 [2021-03-27 17:05:46 swin_base_patch4_window7_224] INFO: Epoch: [186] [1160/1251] eta: 0:00:57 lr: 0.000318 loss: 3.3036 (3.1271) grad_norm: 1.7972 (1.8659) time: 0.6257 [2021-03-27 17:05:52 swin_base_patch4_window7_224] INFO: Epoch: [186] [1170/1251] eta: 0:00:51 lr: 0.000318 loss: 3.2789 (3.1269) grad_norm: 1.8396 (1.8669) time: 0.6254 [2021-03-27 17:05:59 swin_base_patch4_window7_224] INFO: Epoch: [186] [1180/1251] eta: 0:00:44 lr: 0.000318 loss: 3.2677 (3.1282) grad_norm: 1.8073 (1.8661) time: 0.6237 [2021-03-27 17:06:05 swin_base_patch4_window7_224] INFO: Epoch: [186] [1190/1251] eta: 0:00:38 lr: 0.000318 loss: 3.1009 (3.1249) grad_norm: 1.6886 (1.8646) time: 0.6240 [2021-03-27 17:06:11 swin_base_patch4_window7_224] INFO: Epoch: [186] [1200/1251] eta: 0:00:32 lr: 0.000318 loss: 3.0720 (3.1257) grad_norm: 1.6897 (1.8637) time: 0.6243 [2021-03-27 17:06:17 swin_base_patch4_window7_224] INFO: Epoch: [186] [1210/1251] eta: 0:00:25 lr: 0.000318 loss: 3.1915 (3.1266) grad_norm: 1.7707 (1.8643) time: 0.6269 [2021-03-27 17:06:24 swin_base_patch4_window7_224] INFO: Epoch: [186] [1220/1251] eta: 0:00:19 lr: 0.000318 loss: 3.1659 (3.1265) grad_norm: 1.7707 (1.8638) time: 0.6295 [2021-03-27 17:06:30 swin_base_patch4_window7_224] INFO: Epoch: [186] [1230/1251] eta: 0:00:13 lr: 0.000318 loss: 3.2745 (3.1288) grad_norm: 1.7618 (1.8638) time: 0.6228 [2021-03-27 17:06:36 swin_base_patch4_window7_224] INFO: Epoch: [186] [1240/1251] eta: 0:00:06 lr: 0.000318 loss: 3.4206 (3.1302) grad_norm: 1.7142 (1.8635) time: 0.6180 [2021-03-27 17:06:42 swin_base_patch4_window7_224] INFO: Epoch: [186] [1250/1251] eta: 0:00:00 lr: 0.000318 loss: 3.2856 (3.1307) grad_norm: 1.7678 (1.8634) time: 0.6155 [2021-03-27 17:06:53 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:30 loss: 0.7592 (0.7592) acc1: 79.6875 (79.6875) acc5: 98.4375 (98.4375) [2021-03-27 17:06:55 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8428 (0.8826) acc1: 78.1250 (77.8409) acc5: 96.8750 (95.7386) [2021-03-27 17:06:57 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8428 (0.8673) acc1: 78.1250 (78.6458) acc5: 95.3125 (95.6101) [2021-03-27 17:06:59 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8269 (0.8494) acc1: 81.2500 (79.8387) acc5: 95.3125 (95.7157) [2021-03-27 17:07:01 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8159 (0.8719) acc1: 79.6875 (79.4207) acc5: 95.3125 (95.5793) [2021-03-27 17:07:02 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8159 (0.8649) acc1: 78.1250 (79.6800) acc5: 95.3125 (95.5200) [2021-03-27 17:07:16 swin_base_patch4_window7_224] INFO: * Acc@1 80.318 Acc@5 95.440 loss 0.841 [2021-03-27 17:07:16 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.3% [2021-03-27 17:07:16 swin_base_patch4_window7_224] INFO: Max accuracy: 80.66% [2021-03-27 17:07:21 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 0/1251] eta: 1:34:37 lr: 0.000318 loss: 2.9125 (2.9125) grad_norm: 1.7633 (1.7633) time: 4.5386 [2021-03-27 17:07:27 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 10/1251] eta: 0:20:25 lr: 0.000318 loss: 3.0110 (2.9243) grad_norm: 1.7633 (1.8505) time: 0.9878 [2021-03-27 17:07:34 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 20/1251] eta: 0:16:54 lr: 0.000318 loss: 3.3149 (3.0823) grad_norm: 1.8933 (1.9187) time: 0.6386 [2021-03-27 17:07:40 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 30/1251] eta: 0:15:30 lr: 0.000318 loss: 3.1414 (3.0800) grad_norm: 1.8941 (1.8956) time: 0.6380 [2021-03-27 17:07:46 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 40/1251] eta: 0:14:41 lr: 0.000318 loss: 3.3254 (3.1502) grad_norm: 1.8714 (1.9097) time: 0.6266 [2021-03-27 17:07:53 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 50/1251] eta: 0:14:11 lr: 0.000318 loss: 3.3254 (3.1690) grad_norm: 1.8490 (1.9216) time: 0.6259 [2021-03-27 17:07:59 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 60/1251] eta: 0:13:49 lr: 0.000318 loss: 3.1342 (3.1488) grad_norm: 1.7205 (1.8940) time: 0.6319 [2021-03-27 17:08:05 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 70/1251] eta: 0:13:29 lr: 0.000318 loss: 3.1841 (3.1736) grad_norm: 1.6213 (1.8722) time: 0.6272 [2021-03-27 17:08:11 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 80/1251] eta: 0:13:14 lr: 0.000318 loss: 3.2965 (3.1528) grad_norm: 1.7467 (1.8731) time: 0.6244 [2021-03-27 17:08:18 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 90/1251] eta: 0:13:02 lr: 0.000318 loss: 3.2112 (3.1545) grad_norm: 1.8409 (1.8801) time: 0.6329 [2021-03-27 17:08:24 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 100/1251] eta: 0:12:50 lr: 0.000318 loss: 3.1745 (3.1330) grad_norm: 1.8409 (1.8783) time: 0.6332 [2021-03-27 17:08:30 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 110/1251] eta: 0:12:39 lr: 0.000318 loss: 2.8844 (3.1133) grad_norm: 1.8216 (1.8755) time: 0.6278 [2021-03-27 17:08:37 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 120/1251] eta: 0:12:29 lr: 0.000318 loss: 3.1213 (3.1127) grad_norm: 1.9303 (1.9007) time: 0.6272 [2021-03-27 17:08:43 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 130/1251] eta: 0:12:19 lr: 0.000317 loss: 3.2710 (3.1255) grad_norm: 2.0452 (1.9077) time: 0.6272 [2021-03-27 17:08:49 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 140/1251] eta: 0:12:10 lr: 0.000317 loss: 3.3453 (3.1254) grad_norm: 1.8563 (1.9052) time: 0.6282 [2021-03-27 17:08:55 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 150/1251] eta: 0:12:01 lr: 0.000317 loss: 3.3453 (3.1193) grad_norm: 1.7864 (1.9026) time: 0.6265 [2021-03-27 17:09:02 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 160/1251] eta: 0:11:52 lr: 0.000317 loss: 3.3265 (3.1298) grad_norm: 1.7864 (1.8985) time: 0.6235 [2021-03-27 17:09:08 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 170/1251] eta: 0:11:44 lr: 0.000317 loss: 3.3757 (3.1437) grad_norm: 1.7692 (1.8896) time: 0.6209 [2021-03-27 17:09:14 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 180/1251] eta: 0:11:36 lr: 0.000317 loss: 3.3882 (3.1425) grad_norm: 1.7868 (1.8910) time: 0.6209 [2021-03-27 17:09:20 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 190/1251] eta: 0:11:27 lr: 0.000317 loss: 3.0083 (3.1286) grad_norm: 1.8035 (1.8880) time: 0.6213 [2021-03-27 17:09:27 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 200/1251] eta: 0:11:20 lr: 0.000317 loss: 3.2592 (3.1387) grad_norm: 1.7447 (1.8858) time: 0.6294 [2021-03-27 17:09:33 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 210/1251] eta: 0:11:13 lr: 0.000317 loss: 3.3255 (3.1424) grad_norm: 1.7142 (1.8827) time: 0.6327 [2021-03-27 17:09:39 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 220/1251] eta: 0:11:05 lr: 0.000317 loss: 3.2604 (3.1449) grad_norm: 1.7142 (1.8763) time: 0.6265 [2021-03-27 17:09:46 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 230/1251] eta: 0:10:59 lr: 0.000317 loss: 3.2604 (3.1493) grad_norm: 1.7587 (1.8699) time: 0.6315 [2021-03-27 17:09:52 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 240/1251] eta: 0:10:51 lr: 0.000317 loss: 3.1778 (3.1421) grad_norm: 1.7900 (1.8712) time: 0.6280 [2021-03-27 17:09:58 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 250/1251] eta: 0:10:44 lr: 0.000317 loss: 3.2892 (3.1581) grad_norm: 1.8467 (1.8699) time: 0.6237 [2021-03-27 17:10:04 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 260/1251] eta: 0:10:37 lr: 0.000317 loss: 3.4479 (3.1606) grad_norm: 1.8801 (1.8746) time: 0.6327 [2021-03-27 17:10:11 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 270/1251] eta: 0:10:30 lr: 0.000317 loss: 3.3630 (3.1642) grad_norm: 1.9477 (1.8752) time: 0.6338 [2021-03-27 17:10:17 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 280/1251] eta: 0:10:23 lr: 0.000317 loss: 3.2162 (3.1616) grad_norm: 1.9122 (1.8791) time: 0.6292 [2021-03-27 17:10:23 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 290/1251] eta: 0:10:17 lr: 0.000317 loss: 3.2541 (3.1665) grad_norm: 1.8051 (1.8759) time: 0.6289 [2021-03-27 17:10:30 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 300/1251] eta: 0:10:10 lr: 0.000317 loss: 3.2135 (3.1627) grad_norm: 1.7571 (1.8748) time: 0.6274 [2021-03-27 17:10:36 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 310/1251] eta: 0:10:03 lr: 0.000317 loss: 3.0542 (3.1632) grad_norm: 1.8117 (1.8707) time: 0.6241 [2021-03-27 17:10:42 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 320/1251] eta: 0:09:56 lr: 0.000317 loss: 3.1162 (3.1591) grad_norm: 1.7799 (1.8705) time: 0.6227 [2021-03-27 17:10:48 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 330/1251] eta: 0:09:49 lr: 0.000317 loss: 3.0937 (3.1611) grad_norm: 1.7686 (1.8669) time: 0.6239 [2021-03-27 17:10:55 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 340/1251] eta: 0:09:42 lr: 0.000317 loss: 2.9246 (3.1506) grad_norm: 1.7210 (1.8644) time: 0.6252 [2021-03-27 17:11:01 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 350/1251] eta: 0:09:35 lr: 0.000317 loss: 2.8726 (3.1435) grad_norm: 1.8144 (1.8686) time: 0.6291 [2021-03-27 17:11:07 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 360/1251] eta: 0:09:29 lr: 0.000317 loss: 3.0898 (3.1414) grad_norm: 1.8464 (1.8659) time: 0.6306 [2021-03-27 17:11:13 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 370/1251] eta: 0:09:22 lr: 0.000317 loss: 3.0833 (3.1382) grad_norm: 1.7204 (1.8620) time: 0.6239 [2021-03-27 17:11:20 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 380/1251] eta: 0:09:15 lr: 0.000317 loss: 2.9182 (3.1382) grad_norm: 1.7841 (1.8627) time: 0.6241 [2021-03-27 17:11:26 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 390/1251] eta: 0:09:09 lr: 0.000316 loss: 3.3421 (3.1404) grad_norm: 1.7600 (1.8591) time: 0.6306 [2021-03-27 17:11:32 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 400/1251] eta: 0:09:02 lr: 0.000316 loss: 3.2478 (3.1410) grad_norm: 1.6612 (1.8581) time: 0.6353 [2021-03-27 17:11:39 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 410/1251] eta: 0:08:56 lr: 0.000316 loss: 3.0663 (3.1382) grad_norm: 1.7547 (1.8562) time: 0.6285 [2021-03-27 17:11:45 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 420/1251] eta: 0:08:49 lr: 0.000316 loss: 3.2370 (3.1421) grad_norm: 1.7736 (1.8539) time: 0.6191 [2021-03-27 17:11:51 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 430/1251] eta: 0:08:42 lr: 0.000316 loss: 3.3009 (3.1402) grad_norm: 1.8384 (1.8536) time: 0.6222 [2021-03-27 17:11:57 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 440/1251] eta: 0:08:36 lr: 0.000316 loss: 3.3503 (3.1483) grad_norm: 1.8222 (1.8522) time: 0.6235 [2021-03-27 17:12:03 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 450/1251] eta: 0:08:29 lr: 0.000316 loss: 3.5824 (3.1562) grad_norm: 1.8222 (1.8523) time: 0.6226 [2021-03-27 17:12:10 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 460/1251] eta: 0:08:23 lr: 0.000316 loss: 3.3004 (3.1521) grad_norm: 1.7990 (1.8500) time: 0.6265 [2021-03-27 17:12:16 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 470/1251] eta: 0:08:16 lr: 0.000316 loss: 3.1533 (3.1536) grad_norm: 1.8031 (1.8536) time: 0.6247 [2021-03-27 17:12:22 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 480/1251] eta: 0:08:09 lr: 0.000316 loss: 3.2006 (3.1553) grad_norm: 1.9184 (1.8525) time: 0.6211 [2021-03-27 17:12:28 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 490/1251] eta: 0:08:03 lr: 0.000316 loss: 2.9201 (3.1460) grad_norm: 1.7194 (1.8493) time: 0.6254 [2021-03-27 17:12:35 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 500/1251] eta: 0:07:57 lr: 0.000316 loss: 2.7018 (3.1439) grad_norm: 1.7221 (1.8511) time: 0.6286 [2021-03-27 17:12:41 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 510/1251] eta: 0:07:50 lr: 0.000316 loss: 3.0128 (3.1441) grad_norm: 1.9044 (1.8560) time: 0.6284 [2021-03-27 17:12:47 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 520/1251] eta: 0:07:44 lr: 0.000316 loss: 3.1173 (3.1400) grad_norm: 1.9492 (1.8568) time: 0.6263 [2021-03-27 17:12:54 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 530/1251] eta: 0:07:37 lr: 0.000316 loss: 3.2394 (3.1431) grad_norm: 1.9380 (1.8590) time: 0.6243 [2021-03-27 17:13:00 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 540/1251] eta: 0:07:31 lr: 0.000316 loss: 3.3106 (3.1433) grad_norm: 1.9452 (1.8603) time: 0.6261 [2021-03-27 17:13:06 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 550/1251] eta: 0:07:25 lr: 0.000316 loss: 3.2618 (3.1416) grad_norm: 1.8498 (1.8626) time: 0.6402 [2021-03-27 17:13:13 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 560/1251] eta: 0:07:18 lr: 0.000316 loss: 3.3266 (3.1453) grad_norm: 1.8498 (1.8637) time: 0.6423 [2021-03-27 17:13:19 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 570/1251] eta: 0:07:12 lr: 0.000316 loss: 3.3365 (3.1465) grad_norm: 1.7867 (1.8637) time: 0.6279 [2021-03-27 17:13:25 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 580/1251] eta: 0:07:05 lr: 0.000316 loss: 3.1867 (3.1446) grad_norm: 1.7467 (1.8625) time: 0.6282 [2021-03-27 17:13:32 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 590/1251] eta: 0:06:59 lr: 0.000316 loss: 3.1867 (3.1461) grad_norm: 1.8150 (1.8637) time: 0.6323 [2021-03-27 17:13:38 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 600/1251] eta: 0:06:53 lr: 0.000316 loss: 3.1799 (3.1473) grad_norm: 1.8065 (1.8623) time: 0.6314 [2021-03-27 17:13:44 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 610/1251] eta: 0:06:46 lr: 0.000316 loss: 3.1799 (3.1459) grad_norm: 1.7222 (1.8607) time: 0.6337 [2021-03-27 17:13:51 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 620/1251] eta: 0:06:40 lr: 0.000316 loss: 3.1983 (3.1414) grad_norm: 1.7090 (1.8598) time: 0.6357 [2021-03-27 17:13:57 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 630/1251] eta: 0:06:33 lr: 0.000316 loss: 2.8420 (3.1353) grad_norm: 1.8615 (1.8596) time: 0.6338 [2021-03-27 17:14:03 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 640/1251] eta: 0:06:27 lr: 0.000316 loss: 2.9149 (3.1347) grad_norm: 1.8726 (1.8595) time: 0.6295 [2021-03-27 17:14:10 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 650/1251] eta: 0:06:21 lr: 0.000315 loss: 3.1589 (3.1352) grad_norm: 1.7685 (1.8601) time: 0.6292 [2021-03-27 17:14:16 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 660/1251] eta: 0:06:14 lr: 0.000315 loss: 3.1589 (3.1354) grad_norm: 1.8465 (1.8599) time: 0.6302 [2021-03-27 17:14:22 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 670/1251] eta: 0:06:08 lr: 0.000315 loss: 3.1621 (3.1342) grad_norm: 1.9030 (1.8611) time: 0.6256 [2021-03-27 17:14:28 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 680/1251] eta: 0:06:01 lr: 0.000315 loss: 3.1066 (3.1324) grad_norm: 1.8475 (1.8616) time: 0.6242 [2021-03-27 17:14:35 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 690/1251] eta: 0:05:55 lr: 0.000315 loss: 3.0441 (3.1318) grad_norm: 1.7620 (1.8608) time: 0.6327 [2021-03-27 17:14:41 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 700/1251] eta: 0:05:49 lr: 0.000315 loss: 3.1190 (3.1282) grad_norm: 1.7421 (1.8603) time: 0.6325 [2021-03-27 17:14:47 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 710/1251] eta: 0:05:42 lr: 0.000315 loss: 2.9456 (3.1257) grad_norm: 1.7826 (1.8599) time: 0.6281 [2021-03-27 17:14:54 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 720/1251] eta: 0:05:36 lr: 0.000315 loss: 2.9530 (3.1242) grad_norm: 1.8875 (1.8614) time: 0.6326 [2021-03-27 17:15:00 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 730/1251] eta: 0:05:30 lr: 0.000315 loss: 3.0260 (3.1221) grad_norm: 1.7671 (1.8591) time: 0.6285 [2021-03-27 17:15:06 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 740/1251] eta: 0:05:23 lr: 0.000315 loss: 3.1045 (3.1215) grad_norm: 1.6955 (1.8592) time: 0.6288 [2021-03-27 17:15:13 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 750/1251] eta: 0:05:17 lr: 0.000315 loss: 3.1717 (3.1214) grad_norm: 1.8205 (1.8596) time: 0.6408 [2021-03-27 17:15:19 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 760/1251] eta: 0:05:11 lr: 0.000315 loss: 3.1830 (3.1187) grad_norm: 1.8565 (1.8598) time: 0.6328 [2021-03-27 17:15:25 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 770/1251] eta: 0:05:04 lr: 0.000315 loss: 3.1918 (3.1189) grad_norm: 1.8595 (1.8596) time: 0.6204 [2021-03-27 17:15:31 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 780/1251] eta: 0:04:58 lr: 0.000315 loss: 3.2644 (3.1191) grad_norm: 1.7758 (1.8585) time: 0.6270 [2021-03-27 17:15:38 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 790/1251] eta: 0:04:52 lr: 0.000315 loss: 3.0616 (3.1158) grad_norm: 1.7504 (1.8584) time: 0.6337 [2021-03-27 17:15:44 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 800/1251] eta: 0:04:45 lr: 0.000315 loss: 3.0616 (3.1164) grad_norm: 1.7845 (1.8594) time: 0.6336 [2021-03-27 17:15:50 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 810/1251] eta: 0:04:39 lr: 0.000315 loss: 3.1628 (3.1142) grad_norm: 1.8231 (1.8591) time: 0.6274 [2021-03-27 17:15:57 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 820/1251] eta: 0:04:32 lr: 0.000315 loss: 3.0215 (3.1137) grad_norm: 1.8671 (1.8595) time: 0.6229 [2021-03-27 17:16:03 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 830/1251] eta: 0:04:26 lr: 0.000315 loss: 2.9793 (3.1135) grad_norm: 1.8698 (1.8608) time: 0.6223 [2021-03-27 17:16:09 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 840/1251] eta: 0:04:20 lr: 0.000315 loss: 3.1763 (3.1139) grad_norm: 1.8253 (1.8604) time: 0.6252 [2021-03-27 17:16:15 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 850/1251] eta: 0:04:13 lr: 0.000315 loss: 3.1763 (3.1130) grad_norm: 1.8102 (1.8599) time: 0.6319 [2021-03-27 17:16:22 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 860/1251] eta: 0:04:07 lr: 0.000315 loss: 3.1434 (3.1128) grad_norm: 1.7846 (1.8607) time: 0.6294 [2021-03-27 17:16:28 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 870/1251] eta: 0:04:01 lr: 0.000315 loss: 2.9090 (3.1097) grad_norm: 1.8061 (1.8614) time: 0.6222 [2021-03-27 17:16:34 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 880/1251] eta: 0:03:54 lr: 0.000315 loss: 2.8195 (3.1105) grad_norm: 1.8207 (1.8607) time: 0.6267 [2021-03-27 17:16:40 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 890/1251] eta: 0:03:48 lr: 0.000315 loss: 2.7004 (3.1052) grad_norm: 1.7909 (1.8606) time: 0.6322 [2021-03-27 17:16:47 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 900/1251] eta: 0:03:42 lr: 0.000315 loss: 2.6863 (3.1028) grad_norm: 1.6602 (1.8607) time: 0.6286 [2021-03-27 17:16:53 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 910/1251] eta: 0:03:35 lr: 0.000314 loss: 3.0298 (3.1009) grad_norm: 1.7460 (1.8605) time: 0.6255 [2021-03-27 17:16:59 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 920/1251] eta: 0:03:29 lr: 0.000314 loss: 3.1701 (3.1033) grad_norm: 1.7460 (1.8590) time: 0.6284 [2021-03-27 17:17:06 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 930/1251] eta: 0:03:23 lr: 0.000314 loss: 3.3754 (3.1056) grad_norm: 1.6902 (1.8599) time: 0.6289 [2021-03-27 17:17:12 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 940/1251] eta: 0:03:16 lr: 0.000314 loss: 3.3754 (3.1063) grad_norm: 1.6902 (nan) time: 0.6187 [2021-03-27 17:17:18 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 950/1251] eta: 0:03:10 lr: 0.000314 loss: 2.8734 (3.1044) grad_norm: 1.7574 (nan) time: 0.6197 [2021-03-27 17:17:24 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 960/1251] eta: 0:03:03 lr: 0.000314 loss: 3.2250 (3.1065) grad_norm: 1.7809 (nan) time: 0.6249 [2021-03-27 17:17:30 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 970/1251] eta: 0:02:57 lr: 0.000314 loss: 3.3902 (3.1073) grad_norm: 1.8703 (nan) time: 0.6235 [2021-03-27 17:17:37 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 980/1251] eta: 0:02:51 lr: 0.000314 loss: 3.3382 (3.1092) grad_norm: 1.8025 (nan) time: 0.6240 [2021-03-27 17:17:43 swin_base_patch4_window7_224] INFO: Epoch: [187] [ 990/1251] eta: 0:02:44 lr: 0.000314 loss: 3.3382 (3.1107) grad_norm: 1.7832 (nan) time: 0.6224 [2021-03-27 17:17:49 swin_base_patch4_window7_224] INFO: Epoch: [187] [1000/1251] eta: 0:02:38 lr: 0.000314 loss: 3.4432 (3.1130) grad_norm: 1.7400 (nan) time: 0.6228 [2021-03-27 17:17:55 swin_base_patch4_window7_224] INFO: Epoch: [187] [1010/1251] eta: 0:02:32 lr: 0.000314 loss: 3.1468 (3.1114) grad_norm: 1.7448 (nan) time: 0.6221 [2021-03-27 17:18:02 swin_base_patch4_window7_224] INFO: Epoch: [187] [1020/1251] eta: 0:02:25 lr: 0.000314 loss: 3.0869 (3.1116) grad_norm: 1.7619 (nan) time: 0.6223 [2021-03-27 17:18:08 swin_base_patch4_window7_224] INFO: Epoch: [187] [1030/1251] eta: 0:02:19 lr: 0.000314 loss: 3.1076 (3.1129) grad_norm: 1.7722 (nan) time: 0.6232 [2021-03-27 17:18:14 swin_base_patch4_window7_224] INFO: Epoch: [187] [1040/1251] eta: 0:02:13 lr: 0.000314 loss: 3.1076 (3.1119) grad_norm: 1.8452 (nan) time: 0.6251 [2021-03-27 17:18:20 swin_base_patch4_window7_224] INFO: Epoch: [187] [1050/1251] eta: 0:02:06 lr: 0.000314 loss: 3.0587 (3.1114) grad_norm: 1.8452 (nan) time: 0.6240 [2021-03-27 17:18:27 swin_base_patch4_window7_224] INFO: Epoch: [187] [1060/1251] eta: 0:02:00 lr: 0.000314 loss: 3.1587 (3.1118) grad_norm: 1.7573 (nan) time: 0.6246 [2021-03-27 17:18:33 swin_base_patch4_window7_224] INFO: Epoch: [187] [1070/1251] eta: 0:01:54 lr: 0.000314 loss: 3.1274 (3.1102) grad_norm: 1.7595 (nan) time: 0.6262 [2021-03-27 17:18:39 swin_base_patch4_window7_224] INFO: Epoch: [187] [1080/1251] eta: 0:01:47 lr: 0.000314 loss: 3.1274 (3.1103) grad_norm: 1.7466 (nan) time: 0.6261 [2021-03-27 17:18:45 swin_base_patch4_window7_224] INFO: Epoch: [187] [1090/1251] eta: 0:01:41 lr: 0.000314 loss: 3.3580 (3.1111) grad_norm: 1.7466 (nan) time: 0.6260 [2021-03-27 17:18:52 swin_base_patch4_window7_224] INFO: Epoch: [187] [1100/1251] eta: 0:01:35 lr: 0.000314 loss: 3.1571 (3.1105) grad_norm: 1.7722 (nan) time: 0.6225 [2021-03-27 17:18:58 swin_base_patch4_window7_224] INFO: Epoch: [187] [1110/1251] eta: 0:01:28 lr: 0.000314 loss: 3.0786 (3.1114) grad_norm: 1.7722 (nan) time: 0.6239 [2021-03-27 17:19:04 swin_base_patch4_window7_224] INFO: Epoch: [187] [1120/1251] eta: 0:01:22 lr: 0.000314 loss: 3.2924 (3.1123) grad_norm: 1.7015 (nan) time: 0.6284 [2021-03-27 17:19:10 swin_base_patch4_window7_224] INFO: Epoch: [187] [1130/1251] eta: 0:01:16 lr: 0.000314 loss: 3.3213 (3.1117) grad_norm: 1.8223 (nan) time: 0.6268 [2021-03-27 17:19:17 swin_base_patch4_window7_224] INFO: Epoch: [187] [1140/1251] eta: 0:01:10 lr: 0.000314 loss: 3.3213 (3.1125) grad_norm: 1.9496 (nan) time: 0.6253 [2021-03-27 17:19:23 swin_base_patch4_window7_224] INFO: Epoch: [187] [1150/1251] eta: 0:01:03 lr: 0.000314 loss: 3.1465 (3.1110) grad_norm: 1.8350 (nan) time: 0.6283 [2021-03-27 17:19:29 swin_base_patch4_window7_224] INFO: Epoch: [187] [1160/1251] eta: 0:00:57 lr: 0.000314 loss: 3.2421 (3.1115) grad_norm: 1.7934 (nan) time: 0.6300 [2021-03-27 17:19:36 swin_base_patch4_window7_224] INFO: Epoch: [187] [1170/1251] eta: 0:00:51 lr: 0.000313 loss: 3.2735 (3.1110) grad_norm: 1.7934 (nan) time: 0.6307 [2021-03-27 17:19:42 swin_base_patch4_window7_224] INFO: Epoch: [187] [1180/1251] eta: 0:00:44 lr: 0.000313 loss: 3.1356 (3.1115) grad_norm: 1.9591 (nan) time: 0.6268 [2021-03-27 17:19:48 swin_base_patch4_window7_224] INFO: Epoch: [187] [1190/1251] eta: 0:00:38 lr: 0.000313 loss: 3.2904 (3.1128) grad_norm: 1.8702 (nan) time: 0.6234 [2021-03-27 17:19:54 swin_base_patch4_window7_224] INFO: Epoch: [187] [1200/1251] eta: 0:00:32 lr: 0.000313 loss: 3.3979 (3.1145) grad_norm: 1.8151 (nan) time: 0.6272 [2021-03-27 17:20:01 swin_base_patch4_window7_224] INFO: Epoch: [187] [1210/1251] eta: 0:00:25 lr: 0.000313 loss: 3.3507 (3.1164) grad_norm: 1.7234 (nan) time: 0.6327 [2021-03-27 17:20:07 swin_base_patch4_window7_224] INFO: Epoch: [187] [1220/1251] eta: 0:00:19 lr: 0.000313 loss: 3.1966 (3.1156) grad_norm: 1.8229 (nan) time: 0.6282 [2021-03-27 17:20:13 swin_base_patch4_window7_224] INFO: Epoch: [187] [1230/1251] eta: 0:00:13 lr: 0.000313 loss: 3.1432 (3.1152) grad_norm: 1.7385 (nan) time: 0.6238 [2021-03-27 17:20:19 swin_base_patch4_window7_224] INFO: Epoch: [187] [1240/1251] eta: 0:00:06 lr: 0.000313 loss: 2.9647 (3.1128) grad_norm: 1.8709 (nan) time: 0.6296 [2021-03-27 17:20:26 swin_base_patch4_window7_224] INFO: Epoch: [187] [1250/1251] eta: 0:00:00 lr: 0.000313 loss: 2.9647 (3.1116) grad_norm: 1.9008 (nan) time: 0.6297 [2021-03-27 17:20:38 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:35 loss: 0.4815 (0.4815) acc1: 89.0625 (89.0625) acc5: 100.0000 (100.0000) [2021-03-27 17:20:41 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:21 loss: 0.9029 (0.8840) acc1: 79.6875 (80.1136) acc5: 95.3125 (96.0227) [2021-03-27 17:20:44 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.9029 (0.8607) acc1: 79.6875 (80.0595) acc5: 96.8750 (96.3542) [2021-03-27 17:20:46 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8862 (0.8665) acc1: 79.6875 (79.9899) acc5: 96.8750 (96.1694) [2021-03-27 17:20:48 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8862 (0.8738) acc1: 79.6875 (79.9924) acc5: 95.3125 (96.0366) [2021-03-27 17:20:49 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8569 (0.8644) acc1: 79.6875 (80.4480) acc5: 95.3125 (96.0320) [2021-03-27 17:21:03 swin_base_patch4_window7_224] INFO: * Acc@1 80.640 Acc@5 95.498 loss 0.846 [2021-03-27 17:21:03 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.6% [2021-03-27 17:21:03 swin_base_patch4_window7_224] INFO: Max accuracy: 80.66% [2021-03-27 17:21:08 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 0/1251] eta: 1:34:48 lr: 0.000313 loss: 2.7669 (2.7669) grad_norm: 1.7171 (1.7171) time: 4.5470 [2021-03-27 17:21:14 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 10/1251] eta: 0:20:30 lr: 0.000313 loss: 3.2523 (3.2406) grad_norm: 1.9149 (1.9424) time: 0.9919 [2021-03-27 17:21:20 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 20/1251] eta: 0:16:44 lr: 0.000313 loss: 3.1673 (3.1265) grad_norm: 1.7739 (1.8397) time: 0.6296 [2021-03-27 17:21:27 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 30/1251] eta: 0:15:32 lr: 0.000313 loss: 3.1307 (3.1180) grad_norm: 1.7614 (1.8871) time: 0.6376 [2021-03-27 17:21:33 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 40/1251] eta: 0:14:45 lr: 0.000313 loss: 3.1135 (3.0920) grad_norm: 1.8345 (1.8849) time: 0.6428 [2021-03-27 17:21:39 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 50/1251] eta: 0:14:13 lr: 0.000313 loss: 3.2233 (3.1475) grad_norm: 1.7807 (1.8632) time: 0.6299 [2021-03-27 17:21:46 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 60/1251] eta: 0:13:50 lr: 0.000313 loss: 3.2320 (3.1433) grad_norm: 1.7807 (1.8566) time: 0.6276 [2021-03-27 17:21:52 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 70/1251] eta: 0:13:31 lr: 0.000313 loss: 3.0114 (3.1054) grad_norm: 1.7731 (1.8655) time: 0.6260 [2021-03-27 17:21:58 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 80/1251] eta: 0:13:15 lr: 0.000313 loss: 2.8820 (3.0842) grad_norm: 1.7898 (1.8640) time: 0.6234 [2021-03-27 17:22:04 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 90/1251] eta: 0:13:01 lr: 0.000313 loss: 3.1360 (3.0769) grad_norm: 1.7898 (1.8597) time: 0.6254 [2021-03-27 17:22:11 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 100/1251] eta: 0:12:49 lr: 0.000313 loss: 3.2007 (3.0760) grad_norm: 1.7371 (1.8515) time: 0.6268 [2021-03-27 17:22:17 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 110/1251] eta: 0:12:40 lr: 0.000313 loss: 3.1916 (3.0889) grad_norm: 1.7550 (1.8492) time: 0.6335 [2021-03-27 17:22:23 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 120/1251] eta: 0:12:29 lr: 0.000313 loss: 3.1916 (3.0899) grad_norm: 1.8124 (1.8661) time: 0.6339 [2021-03-27 17:22:30 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 130/1251] eta: 0:12:20 lr: 0.000313 loss: 3.2977 (3.1080) grad_norm: 1.8704 (1.8745) time: 0.6297 [2021-03-27 17:22:36 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 140/1251] eta: 0:12:11 lr: 0.000313 loss: 3.2275 (3.1012) grad_norm: 1.8704 (1.8703) time: 0.6333 [2021-03-27 17:22:42 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 150/1251] eta: 0:12:02 lr: 0.000313 loss: 3.2128 (3.1079) grad_norm: 1.7805 (1.8982) time: 0.6283 [2021-03-27 17:22:49 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 160/1251] eta: 0:11:53 lr: 0.000313 loss: 3.1052 (3.1012) grad_norm: 1.8829 (1.9094) time: 0.6206 [2021-03-27 17:22:55 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 170/1251] eta: 0:11:45 lr: 0.000313 loss: 3.1719 (3.1178) grad_norm: 1.8829 (1.9087) time: 0.6214 [2021-03-27 17:23:01 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 180/1251] eta: 0:11:37 lr: 0.000312 loss: 3.4158 (3.1170) grad_norm: 1.8641 (1.9124) time: 0.6317 [2021-03-27 17:23:07 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 190/1251] eta: 0:11:29 lr: 0.000312 loss: 3.1424 (3.1132) grad_norm: 1.9321 (1.9178) time: 0.6332 [2021-03-27 17:23:14 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 200/1251] eta: 0:11:22 lr: 0.000312 loss: 3.0476 (3.1109) grad_norm: 1.9837 (1.9203) time: 0.6286 [2021-03-27 17:23:20 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 210/1251] eta: 0:11:15 lr: 0.000312 loss: 3.0373 (3.1079) grad_norm: 1.8722 (1.9183) time: 0.6347 [2021-03-27 17:23:26 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 220/1251] eta: 0:11:07 lr: 0.000312 loss: 3.1338 (3.1147) grad_norm: 1.8352 (1.9149) time: 0.6326 [2021-03-27 17:23:33 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 230/1251] eta: 0:11:00 lr: 0.000312 loss: 3.1180 (3.1134) grad_norm: 1.7160 (1.9091) time: 0.6287 [2021-03-27 17:23:39 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 240/1251] eta: 0:10:53 lr: 0.000312 loss: 3.1253 (3.1175) grad_norm: 1.7398 (1.9047) time: 0.6317 [2021-03-27 17:23:45 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 250/1251] eta: 0:10:46 lr: 0.000312 loss: 3.1824 (3.1187) grad_norm: 1.8544 (1.9046) time: 0.6284 [2021-03-27 17:23:51 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 260/1251] eta: 0:10:38 lr: 0.000312 loss: 3.1643 (3.1209) grad_norm: 1.8861 (1.9081) time: 0.6232 [2021-03-27 17:23:58 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 270/1251] eta: 0:10:31 lr: 0.000312 loss: 2.8591 (3.1074) grad_norm: 1.8790 (1.9097) time: 0.6256 [2021-03-27 17:24:04 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 280/1251] eta: 0:10:24 lr: 0.000312 loss: 2.8591 (3.1084) grad_norm: 1.8636 (1.9173) time: 0.6301 [2021-03-27 17:24:10 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 290/1251] eta: 0:10:18 lr: 0.000312 loss: 3.1194 (3.1066) grad_norm: 1.8753 (1.9188) time: 0.6293 [2021-03-27 17:24:17 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 300/1251] eta: 0:10:11 lr: 0.000312 loss: 3.1666 (3.1138) grad_norm: 1.8347 (1.9186) time: 0.6279 [2021-03-27 17:24:23 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 310/1251] eta: 0:10:04 lr: 0.000312 loss: 3.2477 (3.1110) grad_norm: 1.8347 (1.9195) time: 0.6293 [2021-03-27 17:24:29 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 320/1251] eta: 0:09:57 lr: 0.000312 loss: 3.0084 (3.1069) grad_norm: 1.7963 (1.9154) time: 0.6290 [2021-03-27 17:24:36 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 330/1251] eta: 0:09:50 lr: 0.000312 loss: 3.1807 (3.1116) grad_norm: 1.8371 (1.9166) time: 0.6295 [2021-03-27 17:24:42 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 340/1251] eta: 0:09:44 lr: 0.000312 loss: 3.2076 (3.1120) grad_norm: 1.8912 (1.9177) time: 0.6319 [2021-03-27 17:24:48 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 350/1251] eta: 0:09:37 lr: 0.000312 loss: 3.1546 (3.1109) grad_norm: 1.8912 (1.9171) time: 0.6289 [2021-03-27 17:24:54 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 360/1251] eta: 0:09:30 lr: 0.000312 loss: 3.2245 (3.1164) grad_norm: 1.7778 (1.9165) time: 0.6252 [2021-03-27 17:25:01 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 370/1251] eta: 0:09:23 lr: 0.000312 loss: 3.3924 (3.1243) grad_norm: 1.7955 (1.9131) time: 0.6239 [2021-03-27 17:25:07 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 380/1251] eta: 0:09:16 lr: 0.000312 loss: 3.3924 (3.1279) grad_norm: 1.8033 (1.9111) time: 0.6244 [2021-03-27 17:25:13 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 390/1251] eta: 0:09:10 lr: 0.000312 loss: 3.2114 (3.1259) grad_norm: 1.8811 (1.9188) time: 0.6320 [2021-03-27 17:25:19 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 400/1251] eta: 0:09:03 lr: 0.000312 loss: 3.3430 (3.1353) grad_norm: 1.9889 (1.9190) time: 0.6284 [2021-03-27 17:25:26 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 410/1251] eta: 0:08:57 lr: 0.000312 loss: 3.4629 (3.1371) grad_norm: 1.8258 (1.9161) time: 0.6220 [2021-03-27 17:25:32 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 420/1251] eta: 0:08:50 lr: 0.000312 loss: 3.3233 (3.1384) grad_norm: 1.8231 (1.9135) time: 0.6221 [2021-03-27 17:25:38 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 430/1251] eta: 0:08:43 lr: 0.000312 loss: 3.3128 (3.1399) grad_norm: 1.8700 (1.9191) time: 0.6213 [2021-03-27 17:25:44 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 440/1251] eta: 0:08:37 lr: 0.000312 loss: 3.3128 (3.1383) grad_norm: 1.8990 (1.9203) time: 0.6273 [2021-03-27 17:25:51 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 450/1251] eta: 0:08:30 lr: 0.000311 loss: 3.3189 (3.1404) grad_norm: 1.9457 (1.9215) time: 0.6308 [2021-03-27 17:25:57 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 460/1251] eta: 0:08:24 lr: 0.000311 loss: 3.1903 (3.1388) grad_norm: 1.9135 (1.9197) time: 0.6296 [2021-03-27 17:26:03 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 470/1251] eta: 0:08:17 lr: 0.000311 loss: 3.0226 (3.1347) grad_norm: 1.8759 (1.9192) time: 0.6292 [2021-03-27 17:26:10 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 480/1251] eta: 0:08:11 lr: 0.000311 loss: 2.7682 (3.1273) grad_norm: 1.8475 (1.9183) time: 0.6321 [2021-03-27 17:26:16 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 490/1251] eta: 0:08:04 lr: 0.000311 loss: 3.1518 (3.1320) grad_norm: 1.7977 (1.9158) time: 0.6283 [2021-03-27 17:26:22 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 500/1251] eta: 0:07:58 lr: 0.000311 loss: 3.2388 (3.1292) grad_norm: 1.7275 (1.9135) time: 0.6282 [2021-03-27 17:26:28 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 510/1251] eta: 0:07:51 lr: 0.000311 loss: 3.0182 (3.1270) grad_norm: 1.8172 (1.9138) time: 0.6286 [2021-03-27 17:26:35 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 520/1251] eta: 0:07:45 lr: 0.000311 loss: 3.1227 (3.1250) grad_norm: 1.7970 (1.9112) time: 0.6255 [2021-03-27 17:26:41 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 530/1251] eta: 0:07:38 lr: 0.000311 loss: 3.2345 (3.1267) grad_norm: 1.7471 (1.9104) time: 0.6293 [2021-03-27 17:26:47 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 540/1251] eta: 0:07:32 lr: 0.000311 loss: 3.3210 (3.1255) grad_norm: 1.8044 (1.9110) time: 0.6287 [2021-03-27 17:26:54 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 550/1251] eta: 0:07:26 lr: 0.000311 loss: 3.1026 (3.1232) grad_norm: 1.8687 (1.9123) time: 0.6405 [2021-03-27 17:27:00 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 560/1251] eta: 0:07:19 lr: 0.000311 loss: 3.1026 (3.1226) grad_norm: 1.7894 (1.9104) time: 0.6503 [2021-03-27 17:27:07 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 570/1251] eta: 0:07:13 lr: 0.000311 loss: 3.0764 (3.1194) grad_norm: 1.7894 (1.9119) time: 0.6346 [2021-03-27 17:27:13 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 580/1251] eta: 0:07:06 lr: 0.000311 loss: 3.1612 (3.1209) grad_norm: 1.8311 (1.9117) time: 0.6244 [2021-03-27 17:27:19 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 590/1251] eta: 0:07:00 lr: 0.000311 loss: 3.0783 (3.1208) grad_norm: 1.9035 (1.9132) time: 0.6408 [2021-03-27 17:27:26 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 600/1251] eta: 0:06:54 lr: 0.000311 loss: 2.9999 (3.1157) grad_norm: 1.9035 (1.9142) time: 0.6465 [2021-03-27 17:27:32 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 610/1251] eta: 0:06:47 lr: 0.000311 loss: 2.8931 (3.1128) grad_norm: 1.8986 (1.9142) time: 0.6331 [2021-03-27 17:27:38 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 620/1251] eta: 0:06:41 lr: 0.000311 loss: 3.1010 (3.1128) grad_norm: 1.9174 (1.9183) time: 0.6290 [2021-03-27 17:27:45 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 630/1251] eta: 0:06:34 lr: 0.000311 loss: 3.1010 (3.1117) grad_norm: 1.9400 (1.9201) time: 0.6273 [2021-03-27 17:27:51 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 640/1251] eta: 0:06:28 lr: 0.000311 loss: 3.2418 (3.1135) grad_norm: 1.8800 (1.9190) time: 0.6234 [2021-03-27 17:27:57 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 650/1251] eta: 0:06:22 lr: 0.000311 loss: 3.2098 (3.1159) grad_norm: 1.8420 (1.9197) time: 0.6237 [2021-03-27 17:28:03 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 660/1251] eta: 0:06:15 lr: 0.000311 loss: 3.3899 (3.1196) grad_norm: 2.0588 (1.9237) time: 0.6286 [2021-03-27 17:28:10 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 670/1251] eta: 0:06:09 lr: 0.000311 loss: 3.1894 (3.1188) grad_norm: 2.0260 (1.9271) time: 0.6290 [2021-03-27 17:28:16 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 680/1251] eta: 0:06:02 lr: 0.000311 loss: 3.0017 (3.1179) grad_norm: 1.9463 (1.9266) time: 0.6284 [2021-03-27 17:28:22 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 690/1251] eta: 0:05:56 lr: 0.000311 loss: 3.1954 (3.1203) grad_norm: 1.8036 (1.9248) time: 0.6277 [2021-03-27 17:28:28 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 700/1251] eta: 0:05:49 lr: 0.000311 loss: 3.2129 (3.1216) grad_norm: 1.7248 (1.9222) time: 0.6224 [2021-03-27 17:28:35 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 710/1251] eta: 0:05:43 lr: 0.000310 loss: 3.2750 (3.1226) grad_norm: 1.6874 (1.9190) time: 0.6218 [2021-03-27 17:28:41 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 720/1251] eta: 0:05:37 lr: 0.000310 loss: 3.1146 (3.1207) grad_norm: 1.7102 (1.9170) time: 0.6229 [2021-03-27 17:28:47 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 730/1251] eta: 0:05:30 lr: 0.000310 loss: 3.0855 (3.1207) grad_norm: 1.8496 (1.9226) time: 0.6231 [2021-03-27 17:28:54 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 740/1251] eta: 0:05:24 lr: 0.000310 loss: 3.1295 (3.1204) grad_norm: 1.9451 (1.9232) time: 0.6331 [2021-03-27 17:29:00 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 750/1251] eta: 0:05:17 lr: 0.000310 loss: 3.2709 (3.1214) grad_norm: 1.8230 (1.9232) time: 0.6393 [2021-03-27 17:29:06 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 760/1251] eta: 0:05:11 lr: 0.000310 loss: 3.0995 (3.1198) grad_norm: 1.7886 (1.9216) time: 0.6388 [2021-03-27 17:29:13 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 770/1251] eta: 0:05:05 lr: 0.000310 loss: 3.1512 (3.1218) grad_norm: 1.7940 (1.9222) time: 0.6335 [2021-03-27 17:29:19 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 780/1251] eta: 0:04:58 lr: 0.000310 loss: 3.3752 (3.1230) grad_norm: 1.9099 (1.9233) time: 0.6263 [2021-03-27 17:29:25 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 790/1251] eta: 0:04:52 lr: 0.000310 loss: 3.3873 (3.1252) grad_norm: 1.8489 (1.9227) time: 0.6298 [2021-03-27 17:29:32 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 800/1251] eta: 0:04:46 lr: 0.000310 loss: 3.3873 (3.1244) grad_norm: 1.7834 (1.9218) time: 0.6312 [2021-03-27 17:29:38 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 810/1251] eta: 0:04:39 lr: 0.000310 loss: 3.4230 (3.1259) grad_norm: 1.7873 (1.9211) time: 0.6299 [2021-03-27 17:29:44 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 820/1251] eta: 0:04:33 lr: 0.000310 loss: 3.3224 (3.1242) grad_norm: 1.7486 (1.9195) time: 0.6331 [2021-03-27 17:29:50 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 830/1251] eta: 0:04:27 lr: 0.000310 loss: 3.1796 (3.1230) grad_norm: 1.7486 (1.9182) time: 0.6329 [2021-03-27 17:29:57 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 840/1251] eta: 0:04:20 lr: 0.000310 loss: 3.2104 (3.1241) grad_norm: 1.7740 (1.9182) time: 0.6257 [2021-03-27 17:30:03 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 850/1251] eta: 0:04:14 lr: 0.000310 loss: 3.1031 (3.1234) grad_norm: 1.7836 (1.9164) time: 0.6267 [2021-03-27 17:30:09 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 860/1251] eta: 0:04:07 lr: 0.000310 loss: 3.0775 (3.1234) grad_norm: 1.7353 (1.9157) time: 0.6316 [2021-03-27 17:30:16 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 870/1251] eta: 0:04:01 lr: 0.000310 loss: 3.2457 (3.1237) grad_norm: 1.7423 (1.9150) time: 0.6271 [2021-03-27 17:30:22 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 880/1251] eta: 0:03:55 lr: 0.000310 loss: 3.2432 (3.1229) grad_norm: 1.7708 (1.9143) time: 0.6265 [2021-03-27 17:30:28 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 890/1251] eta: 0:03:48 lr: 0.000310 loss: 3.0762 (3.1229) grad_norm: 1.8726 (1.9155) time: 0.6329 [2021-03-27 17:30:35 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 900/1251] eta: 0:03:42 lr: 0.000310 loss: 3.2651 (3.1246) grad_norm: 1.7859 (1.9135) time: 0.6371 [2021-03-27 17:30:41 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 910/1251] eta: 0:03:36 lr: 0.000310 loss: 3.3697 (3.1260) grad_norm: 1.7254 (1.9135) time: 0.6311 [2021-03-27 17:30:47 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 920/1251] eta: 0:03:29 lr: 0.000310 loss: 3.1810 (3.1244) grad_norm: 1.7683 (1.9119) time: 0.6322 [2021-03-27 17:30:54 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 930/1251] eta: 0:03:23 lr: 0.000310 loss: 2.9853 (3.1235) grad_norm: 1.7210 (1.9103) time: 0.6372 [2021-03-27 17:31:00 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 940/1251] eta: 0:03:17 lr: 0.000310 loss: 3.1772 (3.1237) grad_norm: 1.8347 (1.9106) time: 0.6327 [2021-03-27 17:31:06 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 950/1251] eta: 0:03:10 lr: 0.000310 loss: 3.0402 (3.1198) grad_norm: 1.8533 (1.9099) time: 0.6340 [2021-03-27 17:31:13 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 960/1251] eta: 0:03:04 lr: 0.000310 loss: 2.9858 (3.1186) grad_norm: 1.7666 (1.9092) time: 0.6342 [2021-03-27 17:31:19 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 970/1251] eta: 0:02:58 lr: 0.000309 loss: 3.2955 (3.1185) grad_norm: 1.8752 (1.9092) time: 0.6273 [2021-03-27 17:31:25 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 980/1251] eta: 0:02:51 lr: 0.000309 loss: 2.9423 (3.1175) grad_norm: 1.9411 (1.9103) time: 0.6272 [2021-03-27 17:31:31 swin_base_patch4_window7_224] INFO: Epoch: [188] [ 990/1251] eta: 0:02:45 lr: 0.000309 loss: 2.9467 (3.1166) grad_norm: 1.7981 (1.9090) time: 0.6282 [2021-03-27 17:31:38 swin_base_patch4_window7_224] INFO: Epoch: [188] [1000/1251] eta: 0:02:39 lr: 0.000309 loss: 3.1608 (3.1180) grad_norm: 1.7981 (1.9092) time: 0.6244 [2021-03-27 17:31:44 swin_base_patch4_window7_224] INFO: Epoch: [188] [1010/1251] eta: 0:02:32 lr: 0.000309 loss: 3.0899 (3.1175) grad_norm: 1.8573 (1.9087) time: 0.6279 [2021-03-27 17:31:50 swin_base_patch4_window7_224] INFO: Epoch: [188] [1020/1251] eta: 0:02:26 lr: 0.000309 loss: 3.0609 (3.1149) grad_norm: 1.8455 (1.9079) time: 0.6315 [2021-03-27 17:31:56 swin_base_patch4_window7_224] INFO: Epoch: [188] [1030/1251] eta: 0:02:19 lr: 0.000309 loss: 3.1233 (3.1157) grad_norm: 1.8564 (1.9071) time: 0.6265 [2021-03-27 17:32:03 swin_base_patch4_window7_224] INFO: Epoch: [188] [1040/1251] eta: 0:02:13 lr: 0.000309 loss: 3.1233 (3.1143) grad_norm: 1.7563 (1.9067) time: 0.6247 [2021-03-27 17:32:09 swin_base_patch4_window7_224] INFO: Epoch: [188] [1050/1251] eta: 0:02:07 lr: 0.000309 loss: 3.0456 (3.1144) grad_norm: 1.7563 (1.9061) time: 0.6243 [2021-03-27 17:32:15 swin_base_patch4_window7_224] INFO: Epoch: [188] [1060/1251] eta: 0:02:00 lr: 0.000309 loss: 3.2692 (3.1141) grad_norm: 1.7398 (1.9054) time: 0.6288 [2021-03-27 17:32:22 swin_base_patch4_window7_224] INFO: Epoch: [188] [1070/1251] eta: 0:01:54 lr: 0.000309 loss: 3.1931 (3.1140) grad_norm: 1.7398 (1.9040) time: 0.6345 [2021-03-27 17:32:28 swin_base_patch4_window7_224] INFO: Epoch: [188] [1080/1251] eta: 0:01:48 lr: 0.000309 loss: 3.3538 (3.1163) grad_norm: 1.7803 (1.9048) time: 0.6323 [2021-03-27 17:32:34 swin_base_patch4_window7_224] INFO: Epoch: [188] [1090/1251] eta: 0:01:41 lr: 0.000309 loss: 3.2721 (3.1159) grad_norm: 1.9615 (1.9053) time: 0.6322 [2021-03-27 17:32:41 swin_base_patch4_window7_224] INFO: Epoch: [188] [1100/1251] eta: 0:01:35 lr: 0.000309 loss: 3.2658 (3.1161) grad_norm: 1.9543 (1.9058) time: 0.6291 [2021-03-27 17:32:47 swin_base_patch4_window7_224] INFO: Epoch: [188] [1110/1251] eta: 0:01:29 lr: 0.000309 loss: 3.0854 (3.1149) grad_norm: 1.8347 (1.9055) time: 0.6266 [2021-03-27 17:32:53 swin_base_patch4_window7_224] INFO: Epoch: [188] [1120/1251] eta: 0:01:22 lr: 0.000309 loss: 3.1899 (3.1169) grad_norm: 1.8347 (1.9062) time: 0.6263 [2021-03-27 17:32:59 swin_base_patch4_window7_224] INFO: Epoch: [188] [1130/1251] eta: 0:01:16 lr: 0.000309 loss: 3.3114 (3.1178) grad_norm: 1.8179 (1.9058) time: 0.6245 [2021-03-27 17:33:06 swin_base_patch4_window7_224] INFO: Epoch: [188] [1140/1251] eta: 0:01:10 lr: 0.000309 loss: 3.2040 (3.1167) grad_norm: 1.8612 (1.9053) time: 0.6263 [2021-03-27 17:33:12 swin_base_patch4_window7_224] INFO: Epoch: [188] [1150/1251] eta: 0:01:03 lr: 0.000309 loss: 3.1436 (3.1167) grad_norm: 1.8927 (1.9055) time: 0.6269 [2021-03-27 17:33:18 swin_base_patch4_window7_224] INFO: Epoch: [188] [1160/1251] eta: 0:00:57 lr: 0.000309 loss: 3.2830 (3.1176) grad_norm: 1.9329 (1.9066) time: 0.6246 [2021-03-27 17:33:24 swin_base_patch4_window7_224] INFO: Epoch: [188] [1170/1251] eta: 0:00:51 lr: 0.000309 loss: 3.2830 (3.1175) grad_norm: 2.0326 (1.9096) time: 0.6225 [2021-03-27 17:33:31 swin_base_patch4_window7_224] INFO: Epoch: [188] [1180/1251] eta: 0:00:44 lr: 0.000309 loss: 3.2827 (3.1184) grad_norm: 2.0016 (1.9108) time: 0.6210 [2021-03-27 17:33:37 swin_base_patch4_window7_224] INFO: Epoch: [188] [1190/1251] eta: 0:00:38 lr: 0.000309 loss: 3.2218 (3.1181) grad_norm: 1.9495 (1.9118) time: 0.6226 [2021-03-27 17:33:43 swin_base_patch4_window7_224] INFO: Epoch: [188] [1200/1251] eta: 0:00:32 lr: 0.000309 loss: 3.2015 (3.1188) grad_norm: 1.9674 (1.9116) time: 0.6302 [2021-03-27 17:33:50 swin_base_patch4_window7_224] INFO: Epoch: [188] [1210/1251] eta: 0:00:25 lr: 0.000309 loss: 3.3025 (3.1197) grad_norm: 1.8500 (1.9103) time: 0.6376 [2021-03-27 17:33:56 swin_base_patch4_window7_224] INFO: Epoch: [188] [1220/1251] eta: 0:00:19 lr: 0.000309 loss: 3.3025 (3.1209) grad_norm: 1.7850 (1.9092) time: 0.6358 [2021-03-27 17:34:02 swin_base_patch4_window7_224] INFO: Epoch: [188] [1230/1251] eta: 0:00:13 lr: 0.000308 loss: 3.1033 (3.1197) grad_norm: 1.8052 (1.9087) time: 0.6308 [2021-03-27 17:34:08 swin_base_patch4_window7_224] INFO: Epoch: [188] [1240/1251] eta: 0:00:06 lr: 0.000308 loss: 3.1109 (3.1206) grad_norm: 1.8012 (1.9071) time: 0.6305 [2021-03-27 17:34:15 swin_base_patch4_window7_224] INFO: Epoch: [188] [1250/1251] eta: 0:00:00 lr: 0.000308 loss: 3.3206 (3.1213) grad_norm: 1.7380 (1.9060) time: 0.6250 [2021-03-27 17:34:23 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:12 loss: 0.7300 (0.7300) acc1: 81.2500 (81.2500) acc5: 95.3125 (95.3125) [2021-03-27 17:34:25 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8501 (0.9067) acc1: 81.2500 (79.4034) acc5: 95.3125 (94.8864) [2021-03-27 17:34:27 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8212 (0.8579) acc1: 81.2500 (80.7292) acc5: 95.3125 (95.4613) [2021-03-27 17:34:29 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7559 (0.8443) acc1: 81.2500 (80.5948) acc5: 96.8750 (96.0685) [2021-03-27 17:34:31 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8395 (0.8422) acc1: 81.2500 (80.5640) acc5: 96.8750 (95.8079) [2021-03-27 17:34:32 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8365 (0.8445) acc1: 81.2500 (80.3200) acc5: 95.3125 (95.8400) [2021-03-27 17:34:43 swin_base_patch4_window7_224] INFO: * Acc@1 80.578 Acc@5 95.632 loss 0.839 [2021-03-27 17:34:43 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.6% [2021-03-27 17:34:43 swin_base_patch4_window7_224] INFO: Max accuracy: 80.66% [2021-03-27 17:34:47 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 0/1251] eta: 1:28:58 lr: 0.000308 loss: 3.0336 (3.0336) grad_norm: 1.8937 (1.8937) time: 4.2674 [2021-03-27 17:34:54 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 10/1251] eta: 0:20:06 lr: 0.000308 loss: 3.2147 (3.1901) grad_norm: 1.7671 (1.8205) time: 0.9722 [2021-03-27 17:35:00 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 20/1251] eta: 0:16:31 lr: 0.000308 loss: 3.2746 (3.2532) grad_norm: 1.7346 (1.7661) time: 0.6321 [2021-03-27 17:35:06 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 30/1251] eta: 0:15:12 lr: 0.000308 loss: 3.2075 (3.1035) grad_norm: 1.6950 (1.7608) time: 0.6242 [2021-03-27 17:35:12 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 40/1251] eta: 0:14:30 lr: 0.000308 loss: 2.9173 (3.0501) grad_norm: 1.7113 (1.7598) time: 0.6287 [2021-03-27 17:35:19 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 50/1251] eta: 0:14:01 lr: 0.000308 loss: 3.0813 (3.0466) grad_norm: 1.7264 (1.7628) time: 0.6279 [2021-03-27 17:35:25 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 60/1251] eta: 0:13:40 lr: 0.000308 loss: 3.1041 (3.0422) grad_norm: 1.7274 (1.7930) time: 0.6277 [2021-03-27 17:35:31 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 70/1251] eta: 0:13:23 lr: 0.000308 loss: 2.8429 (3.0360) grad_norm: 1.8975 (1.8226) time: 0.6294 [2021-03-27 17:35:37 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 80/1251] eta: 0:13:08 lr: 0.000308 loss: 3.2485 (3.0515) grad_norm: 1.9194 (1.8368) time: 0.6251 [2021-03-27 17:35:44 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 90/1251] eta: 0:12:56 lr: 0.000308 loss: 3.2485 (3.0713) grad_norm: 1.8827 (1.8602) time: 0.6271 [2021-03-27 17:35:50 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 100/1251] eta: 0:12:44 lr: 0.000308 loss: 3.1695 (3.0909) grad_norm: 1.8520 (1.8602) time: 0.6289 [2021-03-27 17:35:56 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 110/1251] eta: 0:12:33 lr: 0.000308 loss: 3.1695 (3.0755) grad_norm: 1.7966 (1.8622) time: 0.6228 [2021-03-27 17:36:03 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 120/1251] eta: 0:12:24 lr: 0.000308 loss: 3.1820 (3.0828) grad_norm: 1.7966 (1.8605) time: 0.6255 [2021-03-27 17:36:09 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 130/1251] eta: 0:12:14 lr: 0.000308 loss: 3.1943 (3.0751) grad_norm: 1.8263 (1.8607) time: 0.6270 [2021-03-27 17:36:15 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 140/1251] eta: 0:12:07 lr: 0.000308 loss: 3.2646 (3.0898) grad_norm: 1.8099 (1.8608) time: 0.6327 [2021-03-27 17:36:21 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 150/1251] eta: 0:11:58 lr: 0.000308 loss: 3.2806 (3.1026) grad_norm: 1.7997 (1.8574) time: 0.6325 [2021-03-27 17:36:28 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 160/1251] eta: 0:11:51 lr: 0.000308 loss: 3.1967 (3.1063) grad_norm: 1.7873 (1.8588) time: 0.6332 [2021-03-27 17:36:34 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 170/1251] eta: 0:11:43 lr: 0.000308 loss: 3.2253 (3.1036) grad_norm: 1.7695 (1.8584) time: 0.6401 [2021-03-27 17:36:41 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 180/1251] eta: 0:11:36 lr: 0.000308 loss: 3.1987 (3.1030) grad_norm: 1.9004 (1.8674) time: 0.6352 [2021-03-27 17:36:47 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 190/1251] eta: 0:11:28 lr: 0.000308 loss: 3.1472 (3.1071) grad_norm: 1.9537 (1.8703) time: 0.6345 [2021-03-27 17:36:53 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 200/1251] eta: 0:11:21 lr: 0.000308 loss: 3.3517 (3.1218) grad_norm: 1.9286 (1.8709) time: 0.6347 [2021-03-27 17:36:59 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 210/1251] eta: 0:11:13 lr: 0.000308 loss: 3.3517 (3.1203) grad_norm: 1.8734 (1.8711) time: 0.6265 [2021-03-27 17:37:06 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 220/1251] eta: 0:11:06 lr: 0.000308 loss: 3.1905 (3.1197) grad_norm: 1.8566 (1.8717) time: 0.6255 [2021-03-27 17:37:12 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 230/1251] eta: 0:10:59 lr: 0.000308 loss: 3.1523 (3.1207) grad_norm: 1.8626 (1.8769) time: 0.6366 [2021-03-27 17:37:18 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 240/1251] eta: 0:10:52 lr: 0.000307 loss: 3.0222 (3.1150) grad_norm: 1.7898 (1.8733) time: 0.6312 [2021-03-27 17:37:25 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 250/1251] eta: 0:10:45 lr: 0.000307 loss: 3.2734 (3.1196) grad_norm: 1.7898 (1.8719) time: 0.6252 [2021-03-27 17:37:31 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 260/1251] eta: 0:10:37 lr: 0.000307 loss: 3.3384 (3.1247) grad_norm: 1.8305 (1.8712) time: 0.6272 [2021-03-27 17:37:37 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 270/1251] eta: 0:10:31 lr: 0.000307 loss: 3.1906 (3.1204) grad_norm: 1.8101 (1.8718) time: 0.6335 [2021-03-27 17:37:44 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 280/1251] eta: 0:10:24 lr: 0.000307 loss: 2.9113 (3.1093) grad_norm: 1.7864 (1.8698) time: 0.6323 [2021-03-27 17:37:50 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 290/1251] eta: 0:10:17 lr: 0.000307 loss: 2.9174 (3.1061) grad_norm: 1.7468 (1.8660) time: 0.6258 [2021-03-27 17:37:56 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 300/1251] eta: 0:10:10 lr: 0.000307 loss: 2.9174 (3.1020) grad_norm: 1.7467 (1.8667) time: 0.6303 [2021-03-27 17:38:02 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 310/1251] eta: 0:10:03 lr: 0.000307 loss: 2.8816 (3.0963) grad_norm: 1.9767 (1.8767) time: 0.6266 [2021-03-27 17:38:09 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 320/1251] eta: 0:09:56 lr: 0.000307 loss: 2.8817 (3.0928) grad_norm: 2.0456 (1.8835) time: 0.6233 [2021-03-27 17:38:15 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 330/1251] eta: 0:09:49 lr: 0.000307 loss: 3.2012 (3.0988) grad_norm: 2.0038 (1.8834) time: 0.6267 [2021-03-27 17:38:21 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 340/1251] eta: 0:09:43 lr: 0.000307 loss: 3.2521 (3.0977) grad_norm: 1.8247 (1.8819) time: 0.6261 [2021-03-27 17:38:27 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 350/1251] eta: 0:09:36 lr: 0.000307 loss: 3.0119 (3.0945) grad_norm: 1.8551 (1.8814) time: 0.6257 [2021-03-27 17:38:34 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 360/1251] eta: 0:09:30 lr: 0.000307 loss: 3.1580 (3.0984) grad_norm: 1.8551 (1.8802) time: 0.6356 [2021-03-27 17:38:40 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 370/1251] eta: 0:09:23 lr: 0.000307 loss: 3.1834 (3.0966) grad_norm: 1.8059 (1.8783) time: 0.6372 [2021-03-27 17:38:47 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 380/1251] eta: 0:09:16 lr: 0.000307 loss: 2.9470 (3.0916) grad_norm: 1.7843 (1.8772) time: 0.6302 [2021-03-27 17:38:53 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 390/1251] eta: 0:09:10 lr: 0.000307 loss: 3.1094 (3.0978) grad_norm: 1.8287 (1.8766) time: 0.6307 [2021-03-27 17:38:59 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 400/1251] eta: 0:09:03 lr: 0.000307 loss: 3.2271 (3.0946) grad_norm: 1.8619 (1.8781) time: 0.6255 [2021-03-27 17:39:05 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 410/1251] eta: 0:08:56 lr: 0.000307 loss: 2.8776 (3.0903) grad_norm: 1.8578 (1.8784) time: 0.6265 [2021-03-27 17:39:12 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 420/1251] eta: 0:08:50 lr: 0.000307 loss: 2.9982 (3.0949) grad_norm: 1.8381 (1.8782) time: 0.6258 [2021-03-27 17:39:18 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 430/1251] eta: 0:08:43 lr: 0.000307 loss: 2.9982 (3.0905) grad_norm: 1.8670 (1.8792) time: 0.6194 [2021-03-27 17:39:24 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 440/1251] eta: 0:08:36 lr: 0.000307 loss: 2.9691 (3.0876) grad_norm: 1.8670 (1.8831) time: 0.6235 [2021-03-27 17:39:30 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 450/1251] eta: 0:08:30 lr: 0.000307 loss: 2.9794 (3.0861) grad_norm: 1.8321 (1.8841) time: 0.6307 [2021-03-27 17:39:37 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 460/1251] eta: 0:08:23 lr: 0.000307 loss: 3.0572 (3.0833) grad_norm: 2.0172 (1.8908) time: 0.6325 [2021-03-27 17:39:43 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 470/1251] eta: 0:08:17 lr: 0.000307 loss: 3.0716 (3.0849) grad_norm: 1.9151 (1.8894) time: 0.6322 [2021-03-27 17:39:49 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 480/1251] eta: 0:08:10 lr: 0.000307 loss: 3.0716 (3.0839) grad_norm: 1.8194 (1.8902) time: 0.6291 [2021-03-27 17:39:56 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 490/1251] eta: 0:08:04 lr: 0.000307 loss: 3.1687 (3.0872) grad_norm: 1.8343 (1.8927) time: 0.6284 [2021-03-27 17:40:02 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 500/1251] eta: 0:07:58 lr: 0.000307 loss: 3.0845 (3.0863) grad_norm: 1.8611 (1.8935) time: 0.6326 [2021-03-27 17:40:08 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 510/1251] eta: 0:07:51 lr: 0.000306 loss: 3.1783 (3.0887) grad_norm: 1.8395 (1.8919) time: 0.6273 [2021-03-27 17:40:14 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 520/1251] eta: 0:07:44 lr: 0.000306 loss: 3.2158 (3.0869) grad_norm: 1.7410 (1.8888) time: 0.6215 [2021-03-27 17:40:21 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 530/1251] eta: 0:07:38 lr: 0.000306 loss: 3.3043 (3.0850) grad_norm: 1.7531 (1.8887) time: 0.6242 [2021-03-27 17:40:27 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 540/1251] eta: 0:07:32 lr: 0.000306 loss: 3.4090 (3.0875) grad_norm: 1.9559 (1.8914) time: 0.6328 [2021-03-27 17:40:33 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 550/1251] eta: 0:07:25 lr: 0.000306 loss: 3.1289 (3.0855) grad_norm: 1.9516 (1.8910) time: 0.6401 [2021-03-27 17:40:40 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 560/1251] eta: 0:07:19 lr: 0.000306 loss: 2.9346 (3.0824) grad_norm: 1.9516 (1.8949) time: 0.6396 [2021-03-27 17:40:46 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 570/1251] eta: 0:07:13 lr: 0.000306 loss: 2.7743 (3.0761) grad_norm: 1.9563 (1.8954) time: 0.6373 [2021-03-27 17:40:52 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 580/1251] eta: 0:07:06 lr: 0.000306 loss: 2.7919 (3.0737) grad_norm: 1.9552 (1.8976) time: 0.6315 [2021-03-27 17:40:59 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 590/1251] eta: 0:07:00 lr: 0.000306 loss: 3.0495 (3.0720) grad_norm: 1.9044 (1.8967) time: 0.6302 [2021-03-27 17:41:05 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 600/1251] eta: 0:06:53 lr: 0.000306 loss: 3.2934 (3.0772) grad_norm: 1.8237 (1.8954) time: 0.6288 [2021-03-27 17:41:11 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 610/1251] eta: 0:06:47 lr: 0.000306 loss: 3.1191 (3.0711) grad_norm: 1.8237 (1.8951) time: 0.6243 [2021-03-27 17:41:18 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 620/1251] eta: 0:06:40 lr: 0.000306 loss: 2.9559 (3.0716) grad_norm: 1.8333 (1.8929) time: 0.6268 [2021-03-27 17:41:24 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 630/1251] eta: 0:06:34 lr: 0.000306 loss: 3.0007 (3.0698) grad_norm: 1.8341 (1.8964) time: 0.6290 [2021-03-27 17:41:30 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 640/1251] eta: 0:06:28 lr: 0.000306 loss: 2.8953 (3.0674) grad_norm: 1.8640 (1.8972) time: 0.6278 [2021-03-27 17:41:36 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 650/1251] eta: 0:06:21 lr: 0.000306 loss: 3.2824 (3.0727) grad_norm: 1.9474 (1.8996) time: 0.6311 [2021-03-27 17:41:43 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 660/1251] eta: 0:06:15 lr: 0.000306 loss: 3.2824 (3.0717) grad_norm: 1.9425 (1.8987) time: 0.6372 [2021-03-27 17:41:49 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 670/1251] eta: 0:06:08 lr: 0.000306 loss: 3.1139 (3.0694) grad_norm: 1.8372 (1.8993) time: 0.6318 [2021-03-27 17:41:55 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 680/1251] eta: 0:06:02 lr: 0.000306 loss: 3.1139 (3.0691) grad_norm: 1.8255 (1.9051) time: 0.6294 [2021-03-27 17:42:02 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 690/1251] eta: 0:05:56 lr: 0.000306 loss: 3.0609 (3.0697) grad_norm: 1.8375 (1.9050) time: 0.6326 [2021-03-27 17:42:08 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 700/1251] eta: 0:05:49 lr: 0.000306 loss: 3.2792 (3.0741) grad_norm: 1.8375 (1.9051) time: 0.6307 [2021-03-27 17:42:14 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 710/1251] eta: 0:05:43 lr: 0.000306 loss: 3.3136 (3.0741) grad_norm: 1.8032 (1.9034) time: 0.6272 [2021-03-27 17:42:21 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 720/1251] eta: 0:05:36 lr: 0.000306 loss: 3.1915 (3.0747) grad_norm: 1.8133 (1.9038) time: 0.6241 [2021-03-27 17:42:27 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 730/1251] eta: 0:05:30 lr: 0.000306 loss: 2.9737 (3.0710) grad_norm: 1.8737 (1.9035) time: 0.6311 [2021-03-27 17:42:33 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 740/1251] eta: 0:05:24 lr: 0.000306 loss: 2.9737 (3.0692) grad_norm: 1.8840 (1.9043) time: 0.6357 [2021-03-27 17:42:40 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 750/1251] eta: 0:05:18 lr: 0.000306 loss: 3.0792 (3.0694) grad_norm: 1.9800 (1.9049) time: 0.6375 [2021-03-27 17:42:46 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 760/1251] eta: 0:05:11 lr: 0.000306 loss: 3.0961 (3.0711) grad_norm: 2.0147 (1.9063) time: 0.6333 [2021-03-27 17:42:52 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 770/1251] eta: 0:05:05 lr: 0.000305 loss: 3.2196 (3.0718) grad_norm: 1.9808 (1.9060) time: 0.6219 [2021-03-27 17:42:58 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 780/1251] eta: 0:04:58 lr: 0.000305 loss: 3.2406 (3.0749) grad_norm: 1.8821 (1.9060) time: 0.6238 [2021-03-27 17:43:05 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 790/1251] eta: 0:04:52 lr: 0.000305 loss: 3.3113 (3.0770) grad_norm: 1.8379 (1.9046) time: 0.6303 [2021-03-27 17:43:11 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 800/1251] eta: 0:04:46 lr: 0.000305 loss: 3.3113 (3.0800) grad_norm: 1.7136 (1.9028) time: 0.6346 [2021-03-27 17:43:17 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 810/1251] eta: 0:04:39 lr: 0.000305 loss: 3.1397 (3.0759) grad_norm: 1.7279 (1.9034) time: 0.6350 [2021-03-27 17:43:24 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 820/1251] eta: 0:04:33 lr: 0.000305 loss: 3.0132 (3.0746) grad_norm: 1.8957 (1.9045) time: 0.6290 [2021-03-27 17:43:30 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 830/1251] eta: 0:04:26 lr: 0.000305 loss: 3.2220 (3.0777) grad_norm: 1.8180 (1.9033) time: 0.6241 [2021-03-27 17:43:36 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 840/1251] eta: 0:04:20 lr: 0.000305 loss: 3.3174 (3.0781) grad_norm: 1.9072 (1.9077) time: 0.6229 [2021-03-27 17:43:42 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 850/1251] eta: 0:04:14 lr: 0.000305 loss: 3.2317 (3.0766) grad_norm: 1.9537 (1.9066) time: 0.6224 [2021-03-27 17:43:49 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 860/1251] eta: 0:04:07 lr: 0.000305 loss: 3.0832 (3.0751) grad_norm: 1.8930 (1.9084) time: 0.6224 [2021-03-27 17:43:55 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 870/1251] eta: 0:04:01 lr: 0.000305 loss: 3.1944 (3.0772) grad_norm: 2.0521 (1.9111) time: 0.6252 [2021-03-27 17:44:01 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 880/1251] eta: 0:03:55 lr: 0.000305 loss: 3.1443 (3.0769) grad_norm: 1.8142 (1.9104) time: 0.6318 [2021-03-27 17:44:08 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 890/1251] eta: 0:03:48 lr: 0.000305 loss: 3.0392 (3.0765) grad_norm: 1.7556 (1.9095) time: 0.6364 [2021-03-27 17:44:14 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 900/1251] eta: 0:03:42 lr: 0.000305 loss: 3.0680 (3.0766) grad_norm: 1.7808 (1.9083) time: 0.6383 [2021-03-27 17:44:20 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 910/1251] eta: 0:03:36 lr: 0.000305 loss: 3.1028 (3.0754) grad_norm: 1.8116 (1.9078) time: 0.6316 [2021-03-27 17:44:27 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 920/1251] eta: 0:03:29 lr: 0.000305 loss: 3.1087 (3.0779) grad_norm: 1.8270 (1.9077) time: 0.6289 [2021-03-27 17:44:33 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 930/1251] eta: 0:03:23 lr: 0.000305 loss: 3.2928 (3.0801) grad_norm: 1.9036 (1.9085) time: 0.6321 [2021-03-27 17:44:39 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 940/1251] eta: 0:03:17 lr: 0.000305 loss: 3.2928 (3.0819) grad_norm: 1.8526 (1.9094) time: 0.6368 [2021-03-27 17:44:46 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 950/1251] eta: 0:03:10 lr: 0.000305 loss: 3.0895 (3.0805) grad_norm: 1.7754 (1.9081) time: 0.6377 [2021-03-27 17:44:52 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 960/1251] eta: 0:03:04 lr: 0.000305 loss: 3.0286 (3.0793) grad_norm: 1.7519 (1.9070) time: 0.6315 [2021-03-27 17:44:58 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 970/1251] eta: 0:02:58 lr: 0.000305 loss: 3.1639 (3.0800) grad_norm: 1.7519 (1.9059) time: 0.6253 [2021-03-27 17:45:05 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 980/1251] eta: 0:02:51 lr: 0.000305 loss: 3.1894 (3.0808) grad_norm: 1.7987 (1.9057) time: 0.6273 [2021-03-27 17:45:11 swin_base_patch4_window7_224] INFO: Epoch: [189] [ 990/1251] eta: 0:02:45 lr: 0.000305 loss: 3.2087 (3.0820) grad_norm: 1.9101 (1.9072) time: 0.6282 [2021-03-27 17:45:17 swin_base_patch4_window7_224] INFO: Epoch: [189] [1000/1251] eta: 0:02:38 lr: 0.000305 loss: 2.9445 (3.0789) grad_norm: 1.8120 (1.9062) time: 0.6252 [2021-03-27 17:45:23 swin_base_patch4_window7_224] INFO: Epoch: [189] [1010/1251] eta: 0:02:32 lr: 0.000305 loss: 2.8250 (3.0785) grad_norm: 1.8284 (1.9081) time: 0.6279 [2021-03-27 17:45:30 swin_base_patch4_window7_224] INFO: Epoch: [189] [1020/1251] eta: 0:02:26 lr: 0.000305 loss: 3.1899 (3.0790) grad_norm: 1.9645 (1.9083) time: 0.6335 [2021-03-27 17:45:36 swin_base_patch4_window7_224] INFO: Epoch: [189] [1030/1251] eta: 0:02:19 lr: 0.000305 loss: 3.1899 (3.0795) grad_norm: 1.8325 (1.9075) time: 0.6295 [2021-03-27 17:45:42 swin_base_patch4_window7_224] INFO: Epoch: [189] [1040/1251] eta: 0:02:13 lr: 0.000304 loss: 2.9430 (3.0759) grad_norm: 1.7746 (1.9062) time: 0.6248 [2021-03-27 17:45:48 swin_base_patch4_window7_224] INFO: Epoch: [189] [1050/1251] eta: 0:02:07 lr: 0.000304 loss: 2.6865 (3.0754) grad_norm: 1.7438 (1.9049) time: 0.6263 [2021-03-27 17:45:55 swin_base_patch4_window7_224] INFO: Epoch: [189] [1060/1251] eta: 0:02:00 lr: 0.000304 loss: 3.1425 (3.0749) grad_norm: 1.7252 (1.9024) time: 0.6261 [2021-03-27 17:46:01 swin_base_patch4_window7_224] INFO: Epoch: [189] [1070/1251] eta: 0:01:54 lr: 0.000304 loss: 3.1665 (3.0758) grad_norm: 1.8116 (1.9034) time: 0.6273 [2021-03-27 17:46:07 swin_base_patch4_window7_224] INFO: Epoch: [189] [1080/1251] eta: 0:01:48 lr: 0.000304 loss: 2.9571 (3.0754) grad_norm: 1.9413 (1.9054) time: 0.6242 [2021-03-27 17:46:13 swin_base_patch4_window7_224] INFO: Epoch: [189] [1090/1251] eta: 0:01:41 lr: 0.000304 loss: 2.9440 (3.0731) grad_norm: 1.8989 (1.9054) time: 0.6241 [2021-03-27 17:46:20 swin_base_patch4_window7_224] INFO: Epoch: [189] [1100/1251] eta: 0:01:35 lr: 0.000304 loss: 3.1474 (3.0750) grad_norm: 1.8691 (1.9050) time: 0.6265 [2021-03-27 17:46:26 swin_base_patch4_window7_224] INFO: Epoch: [189] [1110/1251] eta: 0:01:29 lr: 0.000304 loss: 3.1998 (3.0741) grad_norm: 1.7891 (1.9038) time: 0.6256 [2021-03-27 17:46:32 swin_base_patch4_window7_224] INFO: Epoch: [189] [1120/1251] eta: 0:01:22 lr: 0.000304 loss: 3.1719 (3.0743) grad_norm: 1.8138 (1.9038) time: 0.6246 [2021-03-27 17:46:39 swin_base_patch4_window7_224] INFO: Epoch: [189] [1130/1251] eta: 0:01:16 lr: 0.000304 loss: 3.2829 (3.0758) grad_norm: 1.7400 (1.9027) time: 0.6288 [2021-03-27 17:46:45 swin_base_patch4_window7_224] INFO: Epoch: [189] [1140/1251] eta: 0:01:10 lr: 0.000304 loss: 3.4739 (3.0786) grad_norm: 1.8053 (1.9033) time: 0.6276 [2021-03-27 17:46:51 swin_base_patch4_window7_224] INFO: Epoch: [189] [1150/1251] eta: 0:01:03 lr: 0.000304 loss: 3.4343 (3.0783) grad_norm: 1.8971 (1.9034) time: 0.6235 [2021-03-27 17:46:57 swin_base_patch4_window7_224] INFO: Epoch: [189] [1160/1251] eta: 0:00:57 lr: 0.000304 loss: 3.2546 (3.0789) grad_norm: 1.8402 (1.9028) time: 0.6225 [2021-03-27 17:47:03 swin_base_patch4_window7_224] INFO: Epoch: [189] [1170/1251] eta: 0:00:51 lr: 0.000304 loss: 3.2190 (3.0776) grad_norm: 1.8529 (1.9024) time: 0.6214 [2021-03-27 17:47:10 swin_base_patch4_window7_224] INFO: Epoch: [189] [1180/1251] eta: 0:00:44 lr: 0.000304 loss: 3.2110 (3.0794) grad_norm: 1.8047 (1.9016) time: 0.6245 [2021-03-27 17:47:16 swin_base_patch4_window7_224] INFO: Epoch: [189] [1190/1251] eta: 0:00:38 lr: 0.000304 loss: 3.3043 (3.0803) grad_norm: 1.8679 (1.9026) time: 0.6307 [2021-03-27 17:47:23 swin_base_patch4_window7_224] INFO: Epoch: [189] [1200/1251] eta: 0:00:32 lr: 0.000304 loss: 3.2451 (3.0808) grad_norm: 2.0008 (1.9026) time: 0.6407 [2021-03-27 17:47:29 swin_base_patch4_window7_224] INFO: Epoch: [189] [1210/1251] eta: 0:00:25 lr: 0.000304 loss: 3.2451 (3.0805) grad_norm: 1.8221 (1.9021) time: 0.6404 [2021-03-27 17:47:35 swin_base_patch4_window7_224] INFO: Epoch: [189] [1220/1251] eta: 0:00:19 lr: 0.000304 loss: 3.3270 (3.0825) grad_norm: 1.8177 (1.9025) time: 0.6303 [2021-03-27 17:47:41 swin_base_patch4_window7_224] INFO: Epoch: [189] [1230/1251] eta: 0:00:13 lr: 0.000304 loss: 3.0699 (3.0805) grad_norm: 1.8584 (1.9037) time: 0.6273 [2021-03-27 17:47:48 swin_base_patch4_window7_224] INFO: Epoch: [189] [1240/1251] eta: 0:00:06 lr: 0.000304 loss: 3.0742 (3.0819) grad_norm: 1.9795 (1.9048) time: 0.6237 [2021-03-27 17:47:54 swin_base_patch4_window7_224] INFO: Epoch: [189] [1250/1251] eta: 0:00:00 lr: 0.000304 loss: 3.1982 (3.0828) grad_norm: 1.8518 (1.9044) time: 0.6217 [2021-03-27 17:48:01 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:26 loss: 0.7331 (0.7331) acc1: 82.8125 (82.8125) acc5: 98.4375 (98.4375) [2021-03-27 17:48:04 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.8159 (0.8527) acc1: 79.6875 (79.5455) acc5: 96.8750 (96.0227) [2021-03-27 17:48:06 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.8462 (0.8480) acc1: 78.1250 (79.4643) acc5: 95.3125 (95.6845) [2021-03-27 17:48:08 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8846 (0.8636) acc1: 78.1250 (79.2843) acc5: 95.3125 (95.8669) [2021-03-27 17:48:10 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7642 (0.8473) acc1: 79.6875 (79.8018) acc5: 96.8750 (95.8460) [2021-03-27 17:48:11 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8514 (0.8525) acc1: 79.6875 (79.8720) acc5: 95.3125 (95.7760) [2021-03-27 17:48:21 swin_base_patch4_window7_224] INFO: * Acc@1 80.672 Acc@5 95.586 loss 0.838 [2021-03-27 17:48:21 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.7% [2021-03-27 17:48:21 swin_base_patch4_window7_224] INFO: Max accuracy: 80.67% [2021-03-27 17:48:26 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 0/1251] eta: 1:31:21 lr: 0.000304 loss: 2.9050 (2.9050) grad_norm: 1.4433 (1.4433) time: 4.3814 [2021-03-27 17:48:32 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 10/1251] eta: 0:20:10 lr: 0.000304 loss: 2.9050 (3.0305) grad_norm: 1.7026 (1.7546) time: 0.9755 [2021-03-27 17:48:38 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 20/1251] eta: 0:16:35 lr: 0.000304 loss: 3.2814 (3.0609) grad_norm: 1.8199 (1.8471) time: 0.6297 [2021-03-27 17:48:45 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 30/1251] eta: 0:15:17 lr: 0.000304 loss: 3.1203 (3.0465) grad_norm: 1.9582 (1.8932) time: 0.6285 [2021-03-27 17:48:51 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 40/1251] eta: 0:14:33 lr: 0.000304 loss: 3.0039 (3.0318) grad_norm: 1.8323 (1.8550) time: 0.6300 [2021-03-27 17:48:57 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 50/1251] eta: 0:14:08 lr: 0.000303 loss: 3.1644 (3.0755) grad_norm: 1.7675 (1.8633) time: 0.6369 [2021-03-27 17:49:04 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 60/1251] eta: 0:13:47 lr: 0.000303 loss: 3.1151 (3.0626) grad_norm: 1.7657 (1.8421) time: 0.6400 [2021-03-27 17:49:10 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 70/1251] eta: 0:13:30 lr: 0.000303 loss: 3.0706 (3.0545) grad_norm: 1.7854 (1.8378) time: 0.6352 [2021-03-27 17:49:16 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 80/1251] eta: 0:13:16 lr: 0.000303 loss: 3.2241 (3.0742) grad_norm: 1.7995 (1.8382) time: 0.6344 [2021-03-27 17:49:23 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 90/1251] eta: 0:13:02 lr: 0.000303 loss: 3.2493 (3.0886) grad_norm: 1.7571 (1.8424) time: 0.6288 [2021-03-27 17:49:29 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 100/1251] eta: 0:12:51 lr: 0.000303 loss: 3.1647 (3.0900) grad_norm: 1.9006 (1.8494) time: 0.6341 [2021-03-27 17:49:35 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 110/1251] eta: 0:12:40 lr: 0.000303 loss: 3.1855 (3.0914) grad_norm: 1.8146 (1.8423) time: 0.6347 [2021-03-27 17:49:42 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 120/1251] eta: 0:12:31 lr: 0.000303 loss: 3.2131 (3.0862) grad_norm: 1.7567 (1.8360) time: 0.6325 [2021-03-27 17:49:48 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 130/1251] eta: 0:12:22 lr: 0.000303 loss: 3.2131 (3.0965) grad_norm: 1.7704 (1.8390) time: 0.6361 [2021-03-27 17:49:54 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 140/1251] eta: 0:12:13 lr: 0.000303 loss: 3.3374 (3.0891) grad_norm: 1.7628 (1.8328) time: 0.6319 [2021-03-27 17:50:01 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 150/1251] eta: 0:12:03 lr: 0.000303 loss: 3.1235 (3.0884) grad_norm: 1.7065 (1.8241) time: 0.6278 [2021-03-27 17:50:07 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 160/1251] eta: 0:11:55 lr: 0.000303 loss: 3.0807 (3.0804) grad_norm: 1.7518 (1.8275) time: 0.6270 [2021-03-27 17:50:13 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 170/1251] eta: 0:11:46 lr: 0.000303 loss: 3.1051 (3.0866) grad_norm: 1.7960 (1.8247) time: 0.6257 [2021-03-27 17:50:20 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 180/1251] eta: 0:11:38 lr: 0.000303 loss: 3.1051 (3.0858) grad_norm: 1.7963 (1.8242) time: 0.6269 [2021-03-27 17:50:26 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 190/1251] eta: 0:11:30 lr: 0.000303 loss: 3.1967 (3.0992) grad_norm: 1.8418 (1.8276) time: 0.6268 [2021-03-27 17:50:32 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 200/1251] eta: 0:11:22 lr: 0.000303 loss: 3.2426 (3.1068) grad_norm: 1.8676 (1.8337) time: 0.6244 [2021-03-27 17:50:38 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 210/1251] eta: 0:11:15 lr: 0.000303 loss: 3.1455 (3.1042) grad_norm: 1.8424 (1.8329) time: 0.6319 [2021-03-27 17:50:45 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 220/1251] eta: 0:11:08 lr: 0.000303 loss: 3.0914 (3.0984) grad_norm: 1.7585 (1.8306) time: 0.6326 [2021-03-27 17:50:51 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 230/1251] eta: 0:11:01 lr: 0.000303 loss: 2.9234 (3.0917) grad_norm: 1.8507 (1.8349) time: 0.6299 [2021-03-27 17:50:57 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 240/1251] eta: 0:10:53 lr: 0.000303 loss: 2.9234 (3.0781) grad_norm: 1.8671 (1.8356) time: 0.6283 [2021-03-27 17:51:04 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 250/1251] eta: 0:10:46 lr: 0.000303 loss: 3.0372 (3.0843) grad_norm: 1.7890 (1.8357) time: 0.6275 [2021-03-27 17:51:10 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 260/1251] eta: 0:10:39 lr: 0.000303 loss: 3.2759 (3.0763) grad_norm: 1.7779 (1.8350) time: 0.6263 [2021-03-27 17:51:16 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 270/1251] eta: 0:10:31 lr: 0.000303 loss: 2.9804 (3.0733) grad_norm: 1.7779 (1.8345) time: 0.6216 [2021-03-27 17:51:22 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 280/1251] eta: 0:10:24 lr: 0.000303 loss: 3.1332 (3.0740) grad_norm: 1.7588 (1.8334) time: 0.6246 [2021-03-27 17:51:29 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 290/1251] eta: 0:10:18 lr: 0.000303 loss: 3.0388 (3.0680) grad_norm: 1.7819 (1.8336) time: 0.6300 [2021-03-27 17:51:35 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 300/1251] eta: 0:10:11 lr: 0.000303 loss: 3.1688 (3.0766) grad_norm: 1.7895 (1.8334) time: 0.6295 [2021-03-27 17:51:41 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 310/1251] eta: 0:10:04 lr: 0.000302 loss: 3.1900 (3.0763) grad_norm: 1.7895 (1.8323) time: 0.6332 [2021-03-27 17:51:48 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 320/1251] eta: 0:09:57 lr: 0.000302 loss: 3.0958 (3.0796) grad_norm: 1.7554 (1.8299) time: 0.6342 [2021-03-27 17:51:54 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 330/1251] eta: 0:09:51 lr: 0.000302 loss: 3.1603 (3.0798) grad_norm: 1.7768 (1.8329) time: 0.6323 [2021-03-27 17:52:00 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 340/1251] eta: 0:09:44 lr: 0.000302 loss: 3.1731 (3.0857) grad_norm: 1.8397 (1.8333) time: 0.6372 [2021-03-27 17:52:07 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 350/1251] eta: 0:09:38 lr: 0.000302 loss: 3.1731 (3.0827) grad_norm: 1.8070 (1.8329) time: 0.6367 [2021-03-27 17:52:13 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 360/1251] eta: 0:09:31 lr: 0.000302 loss: 3.0182 (3.0835) grad_norm: 1.8157 (1.8453) time: 0.6337 [2021-03-27 17:52:19 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 370/1251] eta: 0:09:24 lr: 0.000302 loss: 2.9342 (3.0753) grad_norm: 1.8670 (1.8472) time: 0.6280 [2021-03-27 17:52:25 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 380/1251] eta: 0:09:17 lr: 0.000302 loss: 3.1789 (3.0842) grad_norm: 1.7542 (1.8462) time: 0.6253 [2021-03-27 17:52:32 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 390/1251] eta: 0:09:11 lr: 0.000302 loss: 3.3308 (3.0875) grad_norm: 1.8525 (1.8476) time: 0.6245 [2021-03-27 17:52:38 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 400/1251] eta: 0:09:04 lr: 0.000302 loss: 3.1380 (3.0856) grad_norm: 1.8525 (1.8487) time: 0.6248 [2021-03-27 17:52:44 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 410/1251] eta: 0:08:57 lr: 0.000302 loss: 2.9895 (3.0820) grad_norm: 1.8583 (1.8487) time: 0.6264 [2021-03-27 17:52:51 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 420/1251] eta: 0:08:51 lr: 0.000302 loss: 2.9895 (3.0817) grad_norm: 1.8163 (1.8469) time: 0.6265 [2021-03-27 17:52:57 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 430/1251] eta: 0:08:44 lr: 0.000302 loss: 2.9665 (3.0799) grad_norm: 1.7873 (1.8481) time: 0.6281 [2021-03-27 17:53:03 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 440/1251] eta: 0:08:38 lr: 0.000302 loss: 3.1398 (3.0830) grad_norm: 1.7968 (1.8474) time: 0.6318 [2021-03-27 17:53:09 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 450/1251] eta: 0:08:31 lr: 0.000302 loss: 3.2238 (3.0844) grad_norm: 1.8704 (1.8513) time: 0.6312 [2021-03-27 17:53:16 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 460/1251] eta: 0:08:24 lr: 0.000302 loss: 3.1837 (3.0831) grad_norm: 1.9466 (1.8592) time: 0.6248 [2021-03-27 17:53:22 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 470/1251] eta: 0:08:18 lr: 0.000302 loss: 3.1148 (3.0867) grad_norm: 1.9038 (1.8630) time: 0.6233 [2021-03-27 17:53:28 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 480/1251] eta: 0:08:11 lr: 0.000302 loss: 3.2193 (3.0927) grad_norm: 1.8224 (1.8636) time: 0.6239 [2021-03-27 17:53:34 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 490/1251] eta: 0:08:04 lr: 0.000302 loss: 3.2193 (3.0941) grad_norm: 1.8254 (1.8648) time: 0.6235 [2021-03-27 17:53:41 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 500/1251] eta: 0:07:58 lr: 0.000302 loss: 3.2665 (3.0979) grad_norm: 1.9730 (1.8699) time: 0.6255 [2021-03-27 17:53:47 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 510/1251] eta: 0:07:51 lr: 0.000302 loss: 3.2170 (3.0941) grad_norm: 2.0088 (1.8724) time: 0.6261 [2021-03-27 17:53:53 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 520/1251] eta: 0:07:45 lr: 0.000302 loss: 3.0885 (3.0970) grad_norm: 1.7467 (1.8708) time: 0.6254 [2021-03-27 17:53:59 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 530/1251] eta: 0:07:38 lr: 0.000302 loss: 3.1668 (3.0972) grad_norm: 1.7467 (1.8759) time: 0.6279 [2021-03-27 17:54:06 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 540/1251] eta: 0:07:32 lr: 0.000302 loss: 3.2398 (3.0954) grad_norm: 1.8579 (1.8760) time: 0.6291 [2021-03-27 17:54:12 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 550/1251] eta: 0:07:26 lr: 0.000302 loss: 3.3475 (3.0963) grad_norm: 1.8606 (1.8761) time: 0.6392 [2021-03-27 17:54:18 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 560/1251] eta: 0:07:19 lr: 0.000302 loss: 2.8218 (3.0905) grad_norm: 1.8606 (1.8754) time: 0.6351 [2021-03-27 17:54:25 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 570/1251] eta: 0:07:13 lr: 0.000302 loss: 2.9472 (3.0926) grad_norm: 1.9582 (1.8780) time: 0.6206 [2021-03-27 17:54:31 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 580/1251] eta: 0:07:06 lr: 0.000301 loss: 3.0727 (3.0898) grad_norm: 1.9449 (1.8770) time: 0.6226 [2021-03-27 17:54:37 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 590/1251] eta: 0:07:00 lr: 0.000301 loss: 2.8962 (3.0889) grad_norm: 1.7902 (1.8795) time: 0.6282 [2021-03-27 17:54:44 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 600/1251] eta: 0:06:53 lr: 0.000301 loss: 3.1468 (3.0895) grad_norm: 1.8518 (1.8846) time: 0.6321 [2021-03-27 17:54:50 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 610/1251] eta: 0:06:47 lr: 0.000301 loss: 3.3193 (3.0923) grad_norm: 1.9378 (1.8846) time: 0.6311 [2021-03-27 17:54:56 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 620/1251] eta: 0:06:40 lr: 0.000301 loss: 3.1980 (3.0898) grad_norm: 1.8385 (1.8858) time: 0.6254 [2021-03-27 17:55:02 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 630/1251] eta: 0:06:34 lr: 0.000301 loss: 3.1073 (3.0931) grad_norm: 1.8081 (1.8839) time: 0.6240 [2021-03-27 17:55:09 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 640/1251] eta: 0:06:28 lr: 0.000301 loss: 3.1257 (3.0937) grad_norm: 1.7482 (1.8822) time: 0.6261 [2021-03-27 17:55:15 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 650/1251] eta: 0:06:21 lr: 0.000301 loss: 3.2584 (3.0952) grad_norm: 1.7659 (1.8839) time: 0.6291 [2021-03-27 17:55:21 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 660/1251] eta: 0:06:15 lr: 0.000301 loss: 3.3359 (3.0946) grad_norm: 1.8939 (1.8846) time: 0.6278 [2021-03-27 17:55:27 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 670/1251] eta: 0:06:08 lr: 0.000301 loss: 3.0719 (3.0940) grad_norm: 1.8939 (1.8869) time: 0.6269 [2021-03-27 17:55:34 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 680/1251] eta: 0:06:02 lr: 0.000301 loss: 3.2168 (3.0987) grad_norm: 1.8601 (1.8870) time: 0.6365 [2021-03-27 17:55:40 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 690/1251] eta: 0:05:56 lr: 0.000301 loss: 3.2658 (3.0976) grad_norm: 1.8051 (1.8888) time: 0.6364 [2021-03-27 17:55:46 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 700/1251] eta: 0:05:49 lr: 0.000301 loss: 3.1662 (3.1001) grad_norm: 1.7725 (1.8882) time: 0.6299 [2021-03-27 17:55:53 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 710/1251] eta: 0:05:43 lr: 0.000301 loss: 3.2220 (3.1008) grad_norm: 1.8936 (1.8892) time: 0.6270 [2021-03-27 17:55:59 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 720/1251] eta: 0:05:36 lr: 0.000301 loss: 3.0531 (3.0994) grad_norm: 1.9203 (1.8908) time: 0.6235 [2021-03-27 17:56:05 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 730/1251] eta: 0:05:30 lr: 0.000301 loss: 3.0364 (3.0988) grad_norm: 1.9203 (1.8902) time: 0.6270 [2021-03-27 17:56:12 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 740/1251] eta: 0:05:24 lr: 0.000301 loss: 3.1177 (3.0971) grad_norm: 1.8064 (1.8914) time: 0.6390 [2021-03-27 17:56:18 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 750/1251] eta: 0:05:17 lr: 0.000301 loss: 3.1760 (3.0962) grad_norm: 1.8644 (1.8924) time: 0.6319 [2021-03-27 17:56:24 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 760/1251] eta: 0:05:11 lr: 0.000301 loss: 3.2316 (3.0968) grad_norm: 1.8735 (1.8926) time: 0.6211 [2021-03-27 17:56:30 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 770/1251] eta: 0:05:05 lr: 0.000301 loss: 3.1493 (3.0969) grad_norm: 1.8037 (1.8915) time: 0.6243 [2021-03-27 17:56:37 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 780/1251] eta: 0:04:58 lr: 0.000301 loss: 3.1308 (3.0981) grad_norm: 1.7822 (1.8908) time: 0.6263 [2021-03-27 17:56:43 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 790/1251] eta: 0:04:52 lr: 0.000301 loss: 3.1982 (3.0985) grad_norm: 1.8408 (1.8914) time: 0.6310 [2021-03-27 17:56:49 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 800/1251] eta: 0:04:45 lr: 0.000301 loss: 3.1806 (3.0974) grad_norm: 1.8605 (1.8927) time: 0.6309 [2021-03-27 17:56:56 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 810/1251] eta: 0:04:39 lr: 0.000301 loss: 3.0611 (3.0955) grad_norm: 1.9169 (1.8939) time: 0.6261 [2021-03-27 17:57:02 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 820/1251] eta: 0:04:33 lr: 0.000301 loss: 2.9720 (3.0954) grad_norm: 1.8279 (1.8960) time: 0.6288 [2021-03-27 17:57:08 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 830/1251] eta: 0:04:26 lr: 0.000301 loss: 3.1971 (3.0970) grad_norm: 1.7764 (1.8971) time: 0.6320 [2021-03-27 17:57:14 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 840/1251] eta: 0:04:20 lr: 0.000300 loss: 3.1264 (3.0961) grad_norm: 1.7757 (1.8978) time: 0.6296 [2021-03-27 17:57:21 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 850/1251] eta: 0:04:14 lr: 0.000300 loss: 3.0432 (3.0945) grad_norm: 1.8379 (1.8997) time: 0.6300 [2021-03-27 17:57:27 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 860/1251] eta: 0:04:07 lr: 0.000300 loss: 2.8965 (3.0936) grad_norm: 1.9267 (1.8996) time: 0.6276 [2021-03-27 17:57:33 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 870/1251] eta: 0:04:01 lr: 0.000300 loss: 3.1906 (3.0951) grad_norm: 1.9147 (1.8996) time: 0.6264 [2021-03-27 17:57:40 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 880/1251] eta: 0:03:55 lr: 0.000300 loss: 3.0420 (3.0927) grad_norm: 1.7963 (1.8978) time: 0.6341 [2021-03-27 17:57:46 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 890/1251] eta: 0:03:48 lr: 0.000300 loss: 2.9869 (3.0926) grad_norm: 1.7611 (1.8968) time: 0.6395 [2021-03-27 17:57:52 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 900/1251] eta: 0:03:42 lr: 0.000300 loss: 3.2491 (3.0944) grad_norm: 1.7613 (1.8964) time: 0.6356 [2021-03-27 17:57:59 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 910/1251] eta: 0:03:36 lr: 0.000300 loss: 3.2491 (3.0937) grad_norm: 1.7814 (1.8952) time: 0.6280 [2021-03-27 17:58:05 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 920/1251] eta: 0:03:29 lr: 0.000300 loss: 3.1275 (3.0934) grad_norm: 1.7822 (1.8944) time: 0.6255 [2021-03-27 17:58:11 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 930/1251] eta: 0:03:23 lr: 0.000300 loss: 3.1041 (3.0921) grad_norm: 1.8247 (1.8950) time: 0.6267 [2021-03-27 17:58:17 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 940/1251] eta: 0:03:16 lr: 0.000300 loss: 3.1041 (3.0928) grad_norm: 1.9740 (1.8962) time: 0.6269 [2021-03-27 17:58:24 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 950/1251] eta: 0:03:10 lr: 0.000300 loss: 3.1440 (3.0916) grad_norm: 1.9239 (1.8970) time: 0.6278 [2021-03-27 17:58:30 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 960/1251] eta: 0:03:04 lr: 0.000300 loss: 3.2706 (3.0916) grad_norm: 1.8293 (1.8973) time: 0.6241 [2021-03-27 17:58:36 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 970/1251] eta: 0:02:57 lr: 0.000300 loss: 3.2803 (3.0928) grad_norm: 1.8293 (1.8976) time: 0.6243 [2021-03-27 17:58:43 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 980/1251] eta: 0:02:51 lr: 0.000300 loss: 3.3204 (3.0941) grad_norm: 1.8062 (1.8972) time: 0.6284 [2021-03-27 17:58:49 swin_base_patch4_window7_224] INFO: Epoch: [190] [ 990/1251] eta: 0:02:45 lr: 0.000300 loss: 3.3204 (3.0960) grad_norm: 1.8364 (1.8980) time: 0.6235 [2021-03-27 17:58:55 swin_base_patch4_window7_224] INFO: Epoch: [190] [1000/1251] eta: 0:02:38 lr: 0.000300 loss: 3.2920 (3.0939) grad_norm: 2.0225 (1.9002) time: 0.6257 [2021-03-27 17:59:01 swin_base_patch4_window7_224] INFO: Epoch: [190] [1010/1251] eta: 0:02:32 lr: 0.000300 loss: 3.0732 (3.0933) grad_norm: 1.9864 (1.9007) time: 0.6303 [2021-03-27 17:59:08 swin_base_patch4_window7_224] INFO: Epoch: [190] [1020/1251] eta: 0:02:26 lr: 0.000300 loss: 3.0917 (3.0921) grad_norm: 1.8498 (1.9004) time: 0.6328 [2021-03-27 17:59:14 swin_base_patch4_window7_224] INFO: Epoch: [190] [1030/1251] eta: 0:02:19 lr: 0.000300 loss: 3.0919 (3.0914) grad_norm: 1.8523 (1.9004) time: 0.6367 [2021-03-27 17:59:20 swin_base_patch4_window7_224] INFO: Epoch: [190] [1040/1251] eta: 0:02:13 lr: 0.000300 loss: 3.0797 (3.0917) grad_norm: 1.8637 (1.9015) time: 0.6330 [2021-03-27 17:59:27 swin_base_patch4_window7_224] INFO: Epoch: [190] [1050/1251] eta: 0:02:07 lr: 0.000300 loss: 3.2933 (3.0934) grad_norm: 1.8409 (1.9008) time: 0.6300 [2021-03-27 17:59:33 swin_base_patch4_window7_224] INFO: Epoch: [190] [1060/1251] eta: 0:02:00 lr: 0.000300 loss: 3.4109 (3.0961) grad_norm: 1.8124 (1.9003) time: 0.6310 [2021-03-27 17:59:39 swin_base_patch4_window7_224] INFO: Epoch: [190] [1070/1251] eta: 0:01:54 lr: 0.000300 loss: 3.3166 (3.0976) grad_norm: 1.8333 (1.8995) time: 0.6316 [2021-03-27 17:59:46 swin_base_patch4_window7_224] INFO: Epoch: [190] [1080/1251] eta: 0:01:48 lr: 0.000300 loss: 3.2703 (3.0978) grad_norm: 1.8305 (1.8996) time: 0.6352 [2021-03-27 17:59:52 swin_base_patch4_window7_224] INFO: Epoch: [190] [1090/1251] eta: 0:01:41 lr: 0.000300 loss: 3.2602 (3.0982) grad_norm: 1.8361 (1.8993) time: 0.6320 [2021-03-27 17:59:58 swin_base_patch4_window7_224] INFO: Epoch: [190] [1100/1251] eta: 0:01:35 lr: 0.000300 loss: 3.2429 (3.0989) grad_norm: 1.8790 (1.8995) time: 0.6261 [2021-03-27 18:00:05 swin_base_patch4_window7_224] INFO: Epoch: [190] [1110/1251] eta: 0:01:29 lr: 0.000299 loss: 3.2383 (3.1007) grad_norm: 1.8367 (1.8986) time: 0.6297 [2021-03-27 18:00:11 swin_base_patch4_window7_224] INFO: Epoch: [190] [1120/1251] eta: 0:01:22 lr: 0.000299 loss: 3.2355 (3.0997) grad_norm: 1.8184 (1.8989) time: 0.6305 [2021-03-27 18:00:17 swin_base_patch4_window7_224] INFO: Epoch: [190] [1130/1251] eta: 0:01:16 lr: 0.000299 loss: 3.1271 (3.0981) grad_norm: 1.8249 (1.8990) time: 0.6244 [2021-03-27 18:00:23 swin_base_patch4_window7_224] INFO: Epoch: [190] [1140/1251] eta: 0:01:10 lr: 0.000299 loss: 2.9528 (3.0979) grad_norm: 1.7518 (1.8981) time: 0.6271 [2021-03-27 18:00:30 swin_base_patch4_window7_224] INFO: Epoch: [190] [1150/1251] eta: 0:01:03 lr: 0.000299 loss: 3.0166 (3.0975) grad_norm: 1.7570 (1.8980) time: 0.6322 [2021-03-27 18:00:36 swin_base_patch4_window7_224] INFO: Epoch: [190] [1160/1251] eta: 0:00:57 lr: 0.000299 loss: 3.3185 (3.0994) grad_norm: 1.7953 (1.8982) time: 0.6330 [2021-03-27 18:00:42 swin_base_patch4_window7_224] INFO: Epoch: [190] [1170/1251] eta: 0:00:51 lr: 0.000299 loss: 3.3525 (3.1008) grad_norm: 1.7909 (1.8973) time: 0.6294 [2021-03-27 18:00:49 swin_base_patch4_window7_224] INFO: Epoch: [190] [1180/1251] eta: 0:00:44 lr: 0.000299 loss: 3.1998 (3.1003) grad_norm: 1.8184 (1.8968) time: 0.6256 [2021-03-27 18:00:55 swin_base_patch4_window7_224] INFO: Epoch: [190] [1190/1251] eta: 0:00:38 lr: 0.000299 loss: 3.2708 (3.1022) grad_norm: 1.9005 (1.8982) time: 0.6276 [2021-03-27 18:01:01 swin_base_patch4_window7_224] INFO: Epoch: [190] [1200/1251] eta: 0:00:32 lr: 0.000299 loss: 2.9527 (3.0982) grad_norm: 1.9166 (1.8980) time: 0.6257 [2021-03-27 18:01:07 swin_base_patch4_window7_224] INFO: Epoch: [190] [1210/1251] eta: 0:00:25 lr: 0.000299 loss: 2.5732 (3.0954) grad_norm: 1.8796 (1.8994) time: 0.6254 [2021-03-27 18:01:14 swin_base_patch4_window7_224] INFO: Epoch: [190] [1220/1251] eta: 0:00:19 lr: 0.000299 loss: 3.2293 (3.0968) grad_norm: 1.9755 (1.8997) time: 0.6361 [2021-03-27 18:01:20 swin_base_patch4_window7_224] INFO: Epoch: [190] [1230/1251] eta: 0:00:13 lr: 0.000299 loss: 3.3087 (3.0970) grad_norm: 1.7795 (1.8982) time: 0.6341 [2021-03-27 18:01:26 swin_base_patch4_window7_224] INFO: Epoch: [190] [1240/1251] eta: 0:00:06 lr: 0.000299 loss: 3.3087 (3.0983) grad_norm: 1.7746 (1.8975) time: 0.6218 [2021-03-27 18:01:32 swin_base_patch4_window7_224] INFO: Epoch: [190] [1250/1251] eta: 0:00:00 lr: 0.000299 loss: 3.1435 (3.0973) grad_norm: 1.7889 (1.8984) time: 0.6216 [2021-03-27 18:02:45 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:10 loss: 0.9810 (0.9810) acc1: 73.4375 (73.4375) acc5: 95.3125 (95.3125) [2021-03-27 18:02:46 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.8581 (0.8701) acc1: 79.6875 (78.6932) acc5: 95.3125 (95.4545) [2021-03-27 18:02:47 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.8529 (0.8849) acc1: 81.2500 (78.6458) acc5: 95.3125 (95.2381) [2021-03-27 18:02:49 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8574 (0.8840) acc1: 81.2500 (78.7298) acc5: 95.3125 (95.1613) [2021-03-27 18:02:50 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8274 (0.8610) acc1: 78.1250 (79.6113) acc5: 96.8750 (95.5412) [2021-03-27 18:02:51 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8507 (0.8580) acc1: 81.2500 (79.9680) acc5: 95.3125 (95.5840) [2021-03-27 18:03:02 swin_base_patch4_window7_224] INFO: * Acc@1 80.570 Acc@5 95.530 loss 0.847 [2021-03-27 18:03:02 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.6% [2021-03-27 18:03:02 swin_base_patch4_window7_224] INFO: Max accuracy: 80.67% [2021-03-27 18:03:06 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 0/1251] eta: 1:26:24 lr: 0.000299 loss: 3.1458 (3.1458) grad_norm: 1.6722 (1.6722) time: 4.1439 [2021-03-27 18:03:13 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 10/1251] eta: 0:20:09 lr: 0.000299 loss: 3.1458 (2.9812) grad_norm: 1.8722 (1.9393) time: 0.9747 [2021-03-27 18:03:19 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 20/1251] eta: 0:16:27 lr: 0.000299 loss: 3.1238 (2.9406) grad_norm: 1.9861 (nan) time: 0.6351 [2021-03-27 18:03:25 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 30/1251] eta: 0:15:10 lr: 0.000299 loss: 2.8024 (2.9116) grad_norm: 1.9608 (nan) time: 0.6203 [2021-03-27 18:03:31 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 40/1251] eta: 0:14:29 lr: 0.000299 loss: 2.9450 (2.9110) grad_norm: 1.9486 (nan) time: 0.6302 [2021-03-27 18:03:38 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 50/1251] eta: 0:14:00 lr: 0.000299 loss: 3.0748 (2.9706) grad_norm: 1.9114 (nan) time: 0.6286 [2021-03-27 18:03:44 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 60/1251] eta: 0:13:38 lr: 0.000299 loss: 3.2347 (2.9987) grad_norm: 1.7808 (nan) time: 0.6242 [2021-03-27 18:03:50 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 70/1251] eta: 0:13:22 lr: 0.000299 loss: 3.2440 (3.0208) grad_norm: 1.7982 (nan) time: 0.6270 [2021-03-27 18:03:56 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 80/1251] eta: 0:13:07 lr: 0.000299 loss: 3.1594 (3.0233) grad_norm: 1.9135 (nan) time: 0.6255 [2021-03-27 18:04:03 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 90/1251] eta: 0:12:55 lr: 0.000299 loss: 3.0829 (3.0225) grad_norm: 1.8960 (nan) time: 0.6290 [2021-03-27 18:04:09 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 100/1251] eta: 0:12:45 lr: 0.000299 loss: 3.2157 (3.0342) grad_norm: 1.8850 (nan) time: 0.6350 [2021-03-27 18:04:15 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 110/1251] eta: 0:12:34 lr: 0.000299 loss: 3.2588 (3.0512) grad_norm: 1.8850 (nan) time: 0.6272 [2021-03-27 18:04:21 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 120/1251] eta: 0:12:23 lr: 0.000298 loss: 3.2588 (3.0480) grad_norm: 1.7893 (nan) time: 0.6214 [2021-03-27 18:04:28 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 130/1251] eta: 0:12:14 lr: 0.000298 loss: 3.0484 (3.0417) grad_norm: 1.8163 (nan) time: 0.6214 [2021-03-27 18:04:34 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 140/1251] eta: 0:12:04 lr: 0.000298 loss: 3.1283 (3.0423) grad_norm: 1.8732 (nan) time: 0.6216 [2021-03-27 18:04:40 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 150/1251] eta: 0:11:57 lr: 0.000298 loss: 3.1974 (3.0525) grad_norm: 1.9073 (nan) time: 0.6308 [2021-03-27 18:04:47 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 160/1251] eta: 0:11:48 lr: 0.000298 loss: 3.2060 (3.0662) grad_norm: 1.8545 (nan) time: 0.6306 [2021-03-27 18:04:53 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 170/1251] eta: 0:11:41 lr: 0.000298 loss: 3.2188 (3.0755) grad_norm: 1.8545 (nan) time: 0.6275 [2021-03-27 18:04:59 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 180/1251] eta: 0:11:33 lr: 0.000298 loss: 3.1195 (3.0768) grad_norm: 1.9745 (nan) time: 0.6307 [2021-03-27 18:05:06 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 190/1251] eta: 0:11:26 lr: 0.000298 loss: 3.1195 (3.0720) grad_norm: 1.8709 (nan) time: 0.6315 [2021-03-27 18:05:12 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 200/1251] eta: 0:11:18 lr: 0.000298 loss: 2.9949 (3.0704) grad_norm: 1.8709 (nan) time: 0.6312 [2021-03-27 18:05:18 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 210/1251] eta: 0:11:11 lr: 0.000298 loss: 3.1664 (3.0845) grad_norm: 1.8814 (nan) time: 0.6271 [2021-03-27 18:05:24 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 220/1251] eta: 0:11:04 lr: 0.000298 loss: 3.2962 (3.0840) grad_norm: 1.9656 (nan) time: 0.6247 [2021-03-27 18:05:31 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 230/1251] eta: 0:10:56 lr: 0.000298 loss: 3.1965 (3.0900) grad_norm: 1.9337 (nan) time: 0.6220 [2021-03-27 18:05:37 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 240/1251] eta: 0:10:49 lr: 0.000298 loss: 3.1939 (3.0859) grad_norm: 1.8543 (nan) time: 0.6275 [2021-03-27 18:05:43 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 250/1251] eta: 0:10:42 lr: 0.000298 loss: 2.9664 (3.0868) grad_norm: 1.7708 (nan) time: 0.6293 [2021-03-27 18:05:49 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 260/1251] eta: 0:10:36 lr: 0.000298 loss: 2.9885 (3.0889) grad_norm: 1.8418 (nan) time: 0.6311 [2021-03-27 18:05:56 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 270/1251] eta: 0:10:29 lr: 0.000298 loss: 3.1080 (3.0905) grad_norm: 1.8582 (nan) time: 0.6352 [2021-03-27 18:06:02 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 280/1251] eta: 0:10:22 lr: 0.000298 loss: 3.4968 (3.1048) grad_norm: 1.8643 (nan) time: 0.6335 [2021-03-27 18:06:08 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 290/1251] eta: 0:10:15 lr: 0.000298 loss: 3.4968 (3.1132) grad_norm: 1.8618 (nan) time: 0.6310 [2021-03-27 18:06:15 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 300/1251] eta: 0:10:08 lr: 0.000298 loss: 3.3067 (3.1111) grad_norm: 1.8352 (nan) time: 0.6262 [2021-03-27 18:06:21 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 310/1251] eta: 0:10:02 lr: 0.000298 loss: 3.1803 (3.1140) grad_norm: 1.8946 (nan) time: 0.6255 [2021-03-27 18:06:27 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 320/1251] eta: 0:09:55 lr: 0.000298 loss: 3.3360 (3.1217) grad_norm: 1.8946 (nan) time: 0.6283 [2021-03-27 18:06:33 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 330/1251] eta: 0:09:48 lr: 0.000298 loss: 3.4388 (3.1286) grad_norm: 1.8905 (nan) time: 0.6267 [2021-03-27 18:06:40 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 340/1251] eta: 0:09:41 lr: 0.000298 loss: 3.2464 (3.1277) grad_norm: 1.9519 (nan) time: 0.6233 [2021-03-27 18:06:46 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 350/1251] eta: 0:09:35 lr: 0.000298 loss: 3.1219 (3.1297) grad_norm: 1.9480 (nan) time: 0.6258 [2021-03-27 18:06:52 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 360/1251] eta: 0:09:28 lr: 0.000298 loss: 3.2260 (3.1345) grad_norm: 1.8752 (nan) time: 0.6299 [2021-03-27 18:06:59 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 370/1251] eta: 0:09:21 lr: 0.000298 loss: 3.2658 (3.1337) grad_norm: 1.9248 (nan) time: 0.6272 [2021-03-27 18:07:05 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 380/1251] eta: 0:09:15 lr: 0.000298 loss: 3.2751 (3.1427) grad_norm: 1.9125 (nan) time: 0.6237 [2021-03-27 18:07:11 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 390/1251] eta: 0:09:08 lr: 0.000297 loss: 3.1591 (3.1339) grad_norm: 1.8714 (nan) time: 0.6248 [2021-03-27 18:07:17 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 400/1251] eta: 0:09:01 lr: 0.000297 loss: 2.8580 (3.1325) grad_norm: 1.8714 (nan) time: 0.6289 [2021-03-27 18:07:24 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 410/1251] eta: 0:08:55 lr: 0.000297 loss: 3.2550 (3.1340) grad_norm: 1.9553 (nan) time: 0.6274 [2021-03-27 18:07:30 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 420/1251] eta: 0:08:48 lr: 0.000297 loss: 3.1570 (3.1307) grad_norm: 1.8998 (nan) time: 0.6238 [2021-03-27 18:07:36 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 430/1251] eta: 0:08:42 lr: 0.000297 loss: 3.2603 (3.1331) grad_norm: 1.8828 (nan) time: 0.6244 [2021-03-27 18:07:42 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 440/1251] eta: 0:08:35 lr: 0.000297 loss: 3.1761 (3.1279) grad_norm: 1.9919 (nan) time: 0.6307 [2021-03-27 18:07:49 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 450/1251] eta: 0:08:29 lr: 0.000297 loss: 2.9437 (3.1241) grad_norm: 1.8721 (nan) time: 0.6287 [2021-03-27 18:07:55 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 460/1251] eta: 0:08:22 lr: 0.000297 loss: 2.9977 (3.1175) grad_norm: 1.9457 (nan) time: 0.6226 [2021-03-27 18:08:01 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 470/1251] eta: 0:08:16 lr: 0.000297 loss: 3.1947 (3.1223) grad_norm: 2.0602 (nan) time: 0.6293 [2021-03-27 18:08:07 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 480/1251] eta: 0:08:09 lr: 0.000297 loss: 3.1106 (3.1167) grad_norm: 1.9077 (nan) time: 0.6290 [2021-03-27 18:08:14 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 490/1251] eta: 0:08:03 lr: 0.000297 loss: 2.9057 (3.1161) grad_norm: 1.8380 (nan) time: 0.6231 [2021-03-27 18:08:20 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 500/1251] eta: 0:07:56 lr: 0.000297 loss: 3.1884 (3.1203) grad_norm: 1.8380 (nan) time: 0.6291 [2021-03-27 18:08:26 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 510/1251] eta: 0:07:50 lr: 0.000297 loss: 3.4851 (3.1247) grad_norm: 1.9031 (nan) time: 0.6327 [2021-03-27 18:08:33 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 520/1251] eta: 0:07:43 lr: 0.000297 loss: 3.3235 (3.1242) grad_norm: 1.9031 (nan) time: 0.6245 [2021-03-27 18:08:39 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 530/1251] eta: 0:07:37 lr: 0.000297 loss: 3.0479 (3.1241) grad_norm: 1.8822 (nan) time: 0.6222 [2021-03-27 18:08:45 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 540/1251] eta: 0:07:30 lr: 0.000297 loss: 3.2763 (3.1257) grad_norm: 1.8758 (nan) time: 0.6254 [2021-03-27 18:08:52 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 550/1251] eta: 0:07:24 lr: 0.000297 loss: 3.3009 (3.1276) grad_norm: 1.9555 (nan) time: 0.6365 [2021-03-27 18:08:58 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 560/1251] eta: 0:07:18 lr: 0.000297 loss: 3.2156 (3.1225) grad_norm: 1.9447 (nan) time: 0.6388 [2021-03-27 18:09:04 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 570/1251] eta: 0:07:12 lr: 0.000297 loss: 3.1473 (3.1216) grad_norm: 1.9187 (nan) time: 0.6351 [2021-03-27 18:09:11 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 580/1251] eta: 0:07:05 lr: 0.000297 loss: 3.2775 (3.1231) grad_norm: 1.9512 (nan) time: 0.6322 [2021-03-27 18:09:17 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 590/1251] eta: 0:06:59 lr: 0.000297 loss: 3.1196 (3.1222) grad_norm: 1.9404 (nan) time: 0.6307 [2021-03-27 18:09:23 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 600/1251] eta: 0:06:52 lr: 0.000297 loss: 3.3545 (3.1268) grad_norm: 2.0241 (nan) time: 0.6301 [2021-03-27 18:09:29 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 610/1251] eta: 0:06:46 lr: 0.000297 loss: 3.3545 (3.1285) grad_norm: 1.8074 (nan) time: 0.6229 [2021-03-27 18:09:36 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 620/1251] eta: 0:06:39 lr: 0.000297 loss: 3.1575 (3.1257) grad_norm: 1.8860 (nan) time: 0.6233 [2021-03-27 18:09:42 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 630/1251] eta: 0:06:33 lr: 0.000297 loss: 3.4433 (3.1312) grad_norm: 1.9166 (nan) time: 0.6261 [2021-03-27 18:09:48 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 640/1251] eta: 0:06:27 lr: 0.000297 loss: 3.3313 (3.1279) grad_norm: 1.8427 (nan) time: 0.6276 [2021-03-27 18:09:55 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 650/1251] eta: 0:06:20 lr: 0.000296 loss: 3.1148 (3.1275) grad_norm: 1.8180 (nan) time: 0.6333 [2021-03-27 18:10:01 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 660/1251] eta: 0:06:14 lr: 0.000296 loss: 3.2350 (3.1277) grad_norm: 1.8180 (nan) time: 0.6318 [2021-03-27 18:10:07 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 670/1251] eta: 0:06:08 lr: 0.000296 loss: 3.1689 (3.1261) grad_norm: 1.9626 (nan) time: 0.6262 [2021-03-27 18:10:13 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 680/1251] eta: 0:06:01 lr: 0.000296 loss: 3.1689 (3.1276) grad_norm: 1.9994 (nan) time: 0.6301 [2021-03-27 18:10:20 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 690/1251] eta: 0:05:55 lr: 0.000296 loss: 3.1720 (3.1261) grad_norm: 1.9186 (nan) time: 0.6295 [2021-03-27 18:10:26 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 700/1251] eta: 0:05:49 lr: 0.000296 loss: 3.1187 (3.1272) grad_norm: 1.9491 (nan) time: 0.6328 [2021-03-27 18:10:32 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 710/1251] eta: 0:05:42 lr: 0.000296 loss: 3.1187 (3.1252) grad_norm: 1.9491 (nan) time: 0.6359 [2021-03-27 18:10:39 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 720/1251] eta: 0:05:36 lr: 0.000296 loss: 3.0671 (3.1244) grad_norm: 1.8555 (nan) time: 0.6289 [2021-03-27 18:10:45 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 730/1251] eta: 0:05:29 lr: 0.000296 loss: 3.1300 (3.1262) grad_norm: 1.9020 (nan) time: 0.6224 [2021-03-27 18:10:51 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 740/1251] eta: 0:05:23 lr: 0.000296 loss: 3.1480 (3.1257) grad_norm: 1.9530 (nan) time: 0.6289 [2021-03-27 18:10:58 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 750/1251] eta: 0:05:17 lr: 0.000296 loss: 3.3902 (3.1298) grad_norm: 1.8945 (nan) time: 0.6373 [2021-03-27 18:11:04 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 760/1251] eta: 0:05:10 lr: 0.000296 loss: 3.4080 (3.1286) grad_norm: 1.8277 (nan) time: 0.6347 [2021-03-27 18:11:10 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 770/1251] eta: 0:05:04 lr: 0.000296 loss: 3.2034 (3.1311) grad_norm: 1.8066 (nan) time: 0.6285 [2021-03-27 18:11:16 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 780/1251] eta: 0:04:58 lr: 0.000296 loss: 3.3179 (3.1325) grad_norm: 1.8823 (nan) time: 0.6269 [2021-03-27 18:11:23 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 790/1251] eta: 0:04:51 lr: 0.000296 loss: 3.3179 (3.1325) grad_norm: 1.9423 (nan) time: 0.6286 [2021-03-27 18:11:29 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 800/1251] eta: 0:04:45 lr: 0.000296 loss: 3.2509 (3.1330) grad_norm: 1.8876 (nan) time: 0.6247 [2021-03-27 18:11:35 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 810/1251] eta: 0:04:39 lr: 0.000296 loss: 3.1741 (3.1312) grad_norm: 1.8683 (nan) time: 0.6216 [2021-03-27 18:11:41 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 820/1251] eta: 0:04:32 lr: 0.000296 loss: 3.0209 (3.1307) grad_norm: 1.8537 (nan) time: 0.6247 [2021-03-27 18:11:48 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 830/1251] eta: 0:04:26 lr: 0.000296 loss: 3.1262 (3.1302) grad_norm: 1.7958 (nan) time: 0.6250 [2021-03-27 18:11:54 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 840/1251] eta: 0:04:19 lr: 0.000296 loss: 3.1490 (3.1312) grad_norm: 1.7826 (nan) time: 0.6285 [2021-03-27 18:12:00 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 850/1251] eta: 0:04:13 lr: 0.000296 loss: 3.2909 (3.1337) grad_norm: 1.7245 (nan) time: 0.6302 [2021-03-27 18:12:07 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 860/1251] eta: 0:04:07 lr: 0.000296 loss: 3.2653 (3.1323) grad_norm: 1.7245 (nan) time: 0.6268 [2021-03-27 18:12:13 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 870/1251] eta: 0:04:00 lr: 0.000296 loss: 2.8190 (3.1302) grad_norm: 1.8223 (nan) time: 0.6267 [2021-03-27 18:12:19 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 880/1251] eta: 0:03:54 lr: 0.000296 loss: 3.0124 (3.1310) grad_norm: 1.8560 (nan) time: 0.6241 [2021-03-27 18:12:25 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 890/1251] eta: 0:03:48 lr: 0.000296 loss: 3.0382 (3.1307) grad_norm: 1.8510 (nan) time: 0.6249 [2021-03-27 18:12:32 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 900/1251] eta: 0:03:41 lr: 0.000296 loss: 2.9905 (3.1272) grad_norm: 1.8156 (nan) time: 0.6261 [2021-03-27 18:12:38 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 910/1251] eta: 0:03:35 lr: 0.000296 loss: 2.7896 (3.1233) grad_norm: 1.8069 (nan) time: 0.6267 [2021-03-27 18:12:44 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 920/1251] eta: 0:03:29 lr: 0.000295 loss: 2.8628 (3.1199) grad_norm: 1.8571 (nan) time: 0.6262 [2021-03-27 18:12:50 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 930/1251] eta: 0:03:22 lr: 0.000295 loss: 3.0030 (3.1188) grad_norm: 1.8746 (nan) time: 0.6283 [2021-03-27 18:12:57 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 940/1251] eta: 0:03:16 lr: 0.000295 loss: 3.0880 (3.1185) grad_norm: 1.8949 (nan) time: 0.6317 [2021-03-27 18:13:03 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 950/1251] eta: 0:03:10 lr: 0.000295 loss: 3.0635 (3.1181) grad_norm: 1.8111 (nan) time: 0.6259 [2021-03-27 18:13:09 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 960/1251] eta: 0:03:03 lr: 0.000295 loss: 3.0258 (3.1181) grad_norm: 1.9299 (nan) time: 0.6216 [2021-03-27 18:13:15 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 970/1251] eta: 0:02:57 lr: 0.000295 loss: 3.1402 (3.1179) grad_norm: 1.9285 (nan) time: 0.6253 [2021-03-27 18:13:22 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 980/1251] eta: 0:02:51 lr: 0.000295 loss: 3.1262 (3.1179) grad_norm: 1.8552 (nan) time: 0.6242 [2021-03-27 18:13:28 swin_base_patch4_window7_224] INFO: Epoch: [191] [ 990/1251] eta: 0:02:44 lr: 0.000295 loss: 3.0606 (3.1154) grad_norm: 1.8494 (nan) time: 0.6216 [2021-03-27 18:13:34 swin_base_patch4_window7_224] INFO: Epoch: [191] [1000/1251] eta: 0:02:38 lr: 0.000295 loss: 2.8089 (3.1131) grad_norm: 1.8494 (nan) time: 0.6244 [2021-03-27 18:13:40 swin_base_patch4_window7_224] INFO: Epoch: [191] [1010/1251] eta: 0:02:32 lr: 0.000295 loss: 3.2508 (3.1140) grad_norm: 1.9465 (nan) time: 0.6243 [2021-03-27 18:13:47 swin_base_patch4_window7_224] INFO: Epoch: [191] [1020/1251] eta: 0:02:25 lr: 0.000295 loss: 3.2713 (3.1137) grad_norm: 1.9614 (nan) time: 0.6226 [2021-03-27 18:13:53 swin_base_patch4_window7_224] INFO: Epoch: [191] [1030/1251] eta: 0:02:19 lr: 0.000295 loss: 3.0491 (3.1127) grad_norm: 1.8902 (nan) time: 0.6238 [2021-03-27 18:13:59 swin_base_patch4_window7_224] INFO: Epoch: [191] [1040/1251] eta: 0:02:13 lr: 0.000295 loss: 2.9824 (3.1135) grad_norm: 1.8317 (nan) time: 0.6243 [2021-03-27 18:14:05 swin_base_patch4_window7_224] INFO: Epoch: [191] [1050/1251] eta: 0:02:06 lr: 0.000295 loss: 3.2222 (3.1136) grad_norm: 1.9169 (nan) time: 0.6253 [2021-03-27 18:14:12 swin_base_patch4_window7_224] INFO: Epoch: [191] [1060/1251] eta: 0:02:00 lr: 0.000295 loss: 3.2902 (3.1138) grad_norm: 1.9315 (nan) time: 0.6249 [2021-03-27 18:14:18 swin_base_patch4_window7_224] INFO: Epoch: [191] [1070/1251] eta: 0:01:54 lr: 0.000295 loss: 3.3209 (3.1138) grad_norm: 1.9230 (nan) time: 0.6226 [2021-03-27 18:14:24 swin_base_patch4_window7_224] INFO: Epoch: [191] [1080/1251] eta: 0:01:47 lr: 0.000295 loss: 3.1463 (3.1147) grad_norm: 1.9240 (nan) time: 0.6225 [2021-03-27 18:14:30 swin_base_patch4_window7_224] INFO: Epoch: [191] [1090/1251] eta: 0:01:41 lr: 0.000295 loss: 3.1463 (3.1143) grad_norm: 1.8890 (nan) time: 0.6260 [2021-03-27 18:14:37 swin_base_patch4_window7_224] INFO: Epoch: [191] [1100/1251] eta: 0:01:35 lr: 0.000295 loss: 3.1369 (3.1156) grad_norm: 1.8890 (nan) time: 0.6269 [2021-03-27 18:14:43 swin_base_patch4_window7_224] INFO: Epoch: [191] [1110/1251] eta: 0:01:28 lr: 0.000295 loss: 3.0939 (3.1133) grad_norm: 1.9797 (nan) time: 0.6248 [2021-03-27 18:14:49 swin_base_patch4_window7_224] INFO: Epoch: [191] [1120/1251] eta: 0:01:22 lr: 0.000295 loss: 3.1297 (3.1156) grad_norm: 1.9797 (nan) time: 0.6295 [2021-03-27 18:14:55 swin_base_patch4_window7_224] INFO: Epoch: [191] [1130/1251] eta: 0:01:16 lr: 0.000295 loss: 3.2302 (3.1161) grad_norm: 1.8997 (nan) time: 0.6299 [2021-03-27 18:15:02 swin_base_patch4_window7_224] INFO: Epoch: [191] [1140/1251] eta: 0:01:10 lr: 0.000295 loss: 3.2112 (3.1176) grad_norm: 1.7783 (nan) time: 0.6256 [2021-03-27 18:15:08 swin_base_patch4_window7_224] INFO: Epoch: [191] [1150/1251] eta: 0:01:03 lr: 0.000295 loss: 3.1815 (3.1172) grad_norm: 1.7783 (nan) time: 0.6240 [2021-03-27 18:15:14 swin_base_patch4_window7_224] INFO: Epoch: [191] [1160/1251] eta: 0:00:57 lr: 0.000295 loss: 3.1775 (3.1176) grad_norm: 1.9686 (nan) time: 0.6233 [2021-03-27 18:15:20 swin_base_patch4_window7_224] INFO: Epoch: [191] [1170/1251] eta: 0:00:51 lr: 0.000295 loss: 3.2125 (3.1168) grad_norm: 1.9686 (nan) time: 0.6284 [2021-03-27 18:15:27 swin_base_patch4_window7_224] INFO: Epoch: [191] [1180/1251] eta: 0:00:44 lr: 0.000295 loss: 3.2977 (3.1184) grad_norm: 1.8785 (nan) time: 0.6276 [2021-03-27 18:15:33 swin_base_patch4_window7_224] INFO: Epoch: [191] [1190/1251] eta: 0:00:38 lr: 0.000294 loss: 3.3275 (3.1176) grad_norm: 1.8513 (nan) time: 0.6235 [2021-03-27 18:15:39 swin_base_patch4_window7_224] INFO: Epoch: [191] [1200/1251] eta: 0:00:32 lr: 0.000294 loss: 3.2102 (3.1161) grad_norm: 1.8743 (nan) time: 0.6252 [2021-03-27 18:15:46 swin_base_patch4_window7_224] INFO: Epoch: [191] [1210/1251] eta: 0:00:25 lr: 0.000294 loss: 3.1389 (3.1153) grad_norm: 1.8901 (nan) time: 0.6309 [2021-03-27 18:15:52 swin_base_patch4_window7_224] INFO: Epoch: [191] [1220/1251] eta: 0:00:19 lr: 0.000294 loss: 3.1389 (3.1142) grad_norm: 1.7988 (nan) time: 0.6334 [2021-03-27 18:15:58 swin_base_patch4_window7_224] INFO: Epoch: [191] [1230/1251] eta: 0:00:13 lr: 0.000294 loss: 3.0009 (3.1141) grad_norm: 1.7933 (nan) time: 0.6260 [2021-03-27 18:16:05 swin_base_patch4_window7_224] INFO: Epoch: [191] [1240/1251] eta: 0:00:06 lr: 0.000294 loss: 3.1968 (3.1150) grad_norm: 1.9433 (nan) time: 0.6301 [2021-03-27 18:16:11 swin_base_patch4_window7_224] INFO: Epoch: [191] [1250/1251] eta: 0:00:00 lr: 0.000294 loss: 3.3142 (3.1157) grad_norm: 2.0180 (nan) time: 0.6357 [2021-03-27 18:16:17 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:21 loss: 0.7952 (0.7952) acc1: 84.3750 (84.3750) acc5: 93.7500 (93.7500) [2021-03-27 18:16:20 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8339 (0.9219) acc1: 79.6875 (77.4148) acc5: 95.3125 (95.0284) [2021-03-27 18:16:23 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7834 (0.8612) acc1: 79.6875 (79.3899) acc5: 95.3125 (95.3869) [2021-03-27 18:16:25 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7506 (0.8566) acc1: 81.2500 (79.5867) acc5: 96.8750 (95.6149) [2021-03-27 18:16:27 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7506 (0.8420) acc1: 81.2500 (79.9543) acc5: 96.8750 (95.8079) [2021-03-27 18:16:28 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7841 (0.8423) acc1: 81.2500 (79.9680) acc5: 96.8750 (95.7760) [2021-03-27 18:16:38 swin_base_patch4_window7_224] INFO: * Acc@1 80.818 Acc@5 95.630 loss 0.830 [2021-03-27 18:16:38 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.8% [2021-03-27 18:16:38 swin_base_patch4_window7_224] INFO: Max accuracy: 80.82% [2021-03-27 18:16:42 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 0/1251] eta: 1:28:12 lr: 0.000294 loss: 2.1834 (2.1834) grad_norm: 1.9038 (1.9038) time: 4.2307 [2021-03-27 18:16:48 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 10/1251] eta: 0:20:06 lr: 0.000294 loss: 3.1767 (3.0793) grad_norm: 1.9038 (2.0307) time: 0.9720 [2021-03-27 18:16:55 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 20/1251] eta: 0:16:31 lr: 0.000294 loss: 3.2705 (3.2453) grad_norm: 1.9014 (2.0266) time: 0.6346 [2021-03-27 18:17:01 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 30/1251] eta: 0:15:20 lr: 0.000294 loss: 3.2893 (3.1575) grad_norm: 2.0480 (2.1257) time: 0.6337 [2021-03-27 18:17:07 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 40/1251] eta: 0:14:36 lr: 0.000294 loss: 3.0369 (3.1419) grad_norm: 1.9196 (2.0529) time: 0.6371 [2021-03-27 18:17:14 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 50/1251] eta: 0:14:06 lr: 0.000294 loss: 2.8801 (3.0740) grad_norm: 1.8001 (2.0238) time: 0.6291 [2021-03-27 18:17:20 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 60/1251] eta: 0:13:43 lr: 0.000294 loss: 3.2023 (3.1491) grad_norm: 1.8828 (2.0034) time: 0.6267 [2021-03-27 18:17:26 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 70/1251] eta: 0:13:26 lr: 0.000294 loss: 3.4014 (3.1405) grad_norm: 1.8686 (1.9813) time: 0.6268 [2021-03-27 18:17:32 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 80/1251] eta: 0:13:11 lr: 0.000294 loss: 3.2267 (3.1331) grad_norm: 1.7888 (1.9549) time: 0.6263 [2021-03-27 18:17:39 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 90/1251] eta: 0:12:59 lr: 0.000294 loss: 3.1791 (3.1363) grad_norm: 1.7395 (1.9424) time: 0.6290 [2021-03-27 18:17:45 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 100/1251] eta: 0:12:47 lr: 0.000294 loss: 3.3889 (3.1547) grad_norm: 1.8583 (1.9630) time: 0.6305 [2021-03-27 18:17:51 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 110/1251] eta: 0:12:37 lr: 0.000294 loss: 3.3889 (3.1438) grad_norm: 1.9120 (1.9573) time: 0.6332 [2021-03-27 18:17:58 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 120/1251] eta: 0:12:27 lr: 0.000294 loss: 2.8712 (3.1166) grad_norm: 1.8922 (1.9545) time: 0.6314 [2021-03-27 18:18:04 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 130/1251] eta: 0:12:18 lr: 0.000294 loss: 3.0405 (3.1245) grad_norm: 1.9481 (1.9592) time: 0.6266 [2021-03-27 18:18:10 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 140/1251] eta: 0:12:08 lr: 0.000294 loss: 3.2578 (3.1108) grad_norm: 1.9481 (1.9599) time: 0.6257 [2021-03-27 18:18:17 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 150/1251] eta: 0:12:00 lr: 0.000294 loss: 2.9653 (3.0939) grad_norm: 1.8738 (1.9554) time: 0.6249 [2021-03-27 18:18:23 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 160/1251] eta: 0:11:51 lr: 0.000294 loss: 3.1503 (3.0985) grad_norm: 1.7841 (1.9482) time: 0.6264 [2021-03-27 18:18:29 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 170/1251] eta: 0:11:43 lr: 0.000294 loss: 3.2898 (3.1028) grad_norm: 1.8144 (1.9523) time: 0.6283 [2021-03-27 18:18:36 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 180/1251] eta: 0:11:36 lr: 0.000294 loss: 3.1011 (3.1065) grad_norm: 2.0564 (1.9586) time: 0.6362 [2021-03-27 18:18:42 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 190/1251] eta: 0:11:28 lr: 0.000294 loss: 3.0151 (3.0943) grad_norm: 1.8851 (1.9535) time: 0.6354 [2021-03-27 18:18:48 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 200/1251] eta: 0:11:21 lr: 0.000293 loss: 3.1259 (3.0966) grad_norm: 1.8186 (1.9480) time: 0.6273 [2021-03-27 18:18:54 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 210/1251] eta: 0:11:13 lr: 0.000293 loss: 3.2507 (3.0940) grad_norm: 1.8681 (1.9517) time: 0.6250 [2021-03-27 18:19:01 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 220/1251] eta: 0:11:06 lr: 0.000293 loss: 3.1156 (3.0946) grad_norm: 1.9236 (1.9538) time: 0.6343 [2021-03-27 18:19:07 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 230/1251] eta: 0:10:59 lr: 0.000293 loss: 3.2829 (3.1023) grad_norm: 1.8772 (1.9487) time: 0.6321 [2021-03-27 18:19:13 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 240/1251] eta: 0:10:52 lr: 0.000293 loss: 3.3024 (3.1016) grad_norm: 1.9022 (1.9514) time: 0.6242 [2021-03-27 18:19:20 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 250/1251] eta: 0:10:45 lr: 0.000293 loss: 3.3220 (3.1058) grad_norm: 1.9841 (1.9540) time: 0.6294 [2021-03-27 18:19:26 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 260/1251] eta: 0:10:37 lr: 0.000293 loss: 3.0903 (3.0937) grad_norm: 1.9263 (1.9554) time: 0.6279 [2021-03-27 18:19:32 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 270/1251] eta: 0:10:30 lr: 0.000293 loss: 2.9398 (3.0946) grad_norm: 1.9046 (1.9601) time: 0.6263 [2021-03-27 18:19:38 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 280/1251] eta: 0:10:24 lr: 0.000293 loss: 2.9163 (3.0836) grad_norm: 1.8590 (1.9553) time: 0.6311 [2021-03-27 18:19:45 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 290/1251] eta: 0:10:17 lr: 0.000293 loss: 3.0404 (3.0867) grad_norm: 1.8924 (1.9531) time: 0.6336 [2021-03-27 18:19:51 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 300/1251] eta: 0:10:10 lr: 0.000293 loss: 3.2581 (3.0871) grad_norm: 1.8271 (1.9517) time: 0.6283 [2021-03-27 18:19:57 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 310/1251] eta: 0:10:03 lr: 0.000293 loss: 3.1812 (3.0877) grad_norm: 1.8271 (1.9616) time: 0.6237 [2021-03-27 18:20:03 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 320/1251] eta: 0:09:56 lr: 0.000293 loss: 3.0928 (3.0850) grad_norm: 1.8539 (1.9585) time: 0.6227 [2021-03-27 18:20:10 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 330/1251] eta: 0:09:49 lr: 0.000293 loss: 3.2341 (3.0904) grad_norm: 1.8595 (1.9614) time: 0.6218 [2021-03-27 18:20:16 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 340/1251] eta: 0:09:42 lr: 0.000293 loss: 3.2570 (3.0915) grad_norm: 1.9434 (1.9616) time: 0.6228 [2021-03-27 18:20:22 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 350/1251] eta: 0:09:35 lr: 0.000293 loss: 3.1334 (3.0831) grad_norm: 1.8916 (1.9579) time: 0.6253 [2021-03-27 18:20:28 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 360/1251] eta: 0:09:29 lr: 0.000293 loss: 3.1334 (3.0897) grad_norm: 1.7877 (1.9559) time: 0.6241 [2021-03-27 18:20:35 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 370/1251] eta: 0:09:22 lr: 0.000293 loss: 3.2619 (3.0875) grad_norm: 1.8738 (1.9597) time: 0.6206 [2021-03-27 18:20:41 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 380/1251] eta: 0:09:15 lr: 0.000293 loss: 3.2514 (3.0922) grad_norm: 1.9438 (1.9605) time: 0.6220 [2021-03-27 18:20:47 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 390/1251] eta: 0:09:09 lr: 0.000293 loss: 3.1720 (3.0927) grad_norm: 1.9383 (1.9591) time: 0.6272 [2021-03-27 18:20:53 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 400/1251] eta: 0:09:02 lr: 0.000293 loss: 3.1475 (3.0961) grad_norm: 1.8833 (1.9602) time: 0.6298 [2021-03-27 18:21:00 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 410/1251] eta: 0:08:56 lr: 0.000293 loss: 3.0705 (3.0935) grad_norm: 1.8833 (1.9624) time: 0.6309 [2021-03-27 18:21:06 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 420/1251] eta: 0:08:49 lr: 0.000293 loss: 3.1209 (3.0967) grad_norm: 1.9491 (1.9648) time: 0.6283 [2021-03-27 18:21:12 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 430/1251] eta: 0:08:42 lr: 0.000293 loss: 3.2029 (3.0971) grad_norm: 2.0293 (1.9690) time: 0.6235 [2021-03-27 18:21:19 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 440/1251] eta: 0:08:36 lr: 0.000293 loss: 3.2137 (3.1008) grad_norm: 1.9736 (1.9676) time: 0.6258 [2021-03-27 18:21:25 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 450/1251] eta: 0:08:29 lr: 0.000293 loss: 3.1848 (3.0911) grad_norm: 1.8697 (1.9674) time: 0.6292 [2021-03-27 18:21:31 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 460/1251] eta: 0:08:23 lr: 0.000293 loss: 2.7691 (3.0911) grad_norm: 1.7915 (1.9646) time: 0.6310 [2021-03-27 18:21:38 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 470/1251] eta: 0:08:16 lr: 0.000292 loss: 3.1687 (3.0934) grad_norm: 1.7850 (1.9624) time: 0.6334 [2021-03-27 18:21:44 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 480/1251] eta: 0:08:10 lr: 0.000292 loss: 3.3980 (3.0976) grad_norm: 1.7850 (1.9589) time: 0.6295 [2021-03-27 18:21:50 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 490/1251] eta: 0:08:03 lr: 0.000292 loss: 3.2657 (3.0954) grad_norm: 1.7980 (1.9567) time: 0.6213 [2021-03-27 18:21:56 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 500/1251] eta: 0:07:57 lr: 0.000292 loss: 3.1952 (3.0955) grad_norm: 1.8867 (1.9570) time: 0.6205 [2021-03-27 18:22:02 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 510/1251] eta: 0:07:50 lr: 0.000292 loss: 3.1781 (3.0917) grad_norm: 1.8177 (1.9550) time: 0.6237 [2021-03-27 18:22:09 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 520/1251] eta: 0:07:44 lr: 0.000292 loss: 3.2384 (3.0955) grad_norm: 1.8188 (1.9534) time: 0.6316 [2021-03-27 18:22:15 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 530/1251] eta: 0:07:37 lr: 0.000292 loss: 3.1390 (3.0919) grad_norm: 1.8701 (1.9563) time: 0.6307 [2021-03-27 18:22:21 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 540/1251] eta: 0:07:31 lr: 0.000292 loss: 3.1854 (3.0946) grad_norm: 1.8701 (1.9557) time: 0.6240 [2021-03-27 18:22:28 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 550/1251] eta: 0:07:25 lr: 0.000292 loss: 3.0914 (3.0905) grad_norm: 1.9445 (1.9561) time: 0.6432 [2021-03-27 18:22:34 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 560/1251] eta: 0:07:19 lr: 0.000292 loss: 3.0635 (3.0910) grad_norm: 1.9113 (1.9553) time: 0.6511 [2021-03-27 18:22:41 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 570/1251] eta: 0:07:12 lr: 0.000292 loss: 3.0635 (3.0896) grad_norm: 1.8753 (1.9555) time: 0.6360 [2021-03-27 18:22:47 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 580/1251] eta: 0:07:06 lr: 0.000292 loss: 2.9661 (3.0879) grad_norm: 1.7586 (1.9518) time: 0.6283 [2021-03-27 18:22:53 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 590/1251] eta: 0:06:59 lr: 0.000292 loss: 3.2372 (3.0891) grad_norm: 1.7617 (1.9500) time: 0.6281 [2021-03-27 18:22:59 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 600/1251] eta: 0:06:53 lr: 0.000292 loss: 3.2446 (3.0915) grad_norm: 1.8266 (1.9490) time: 0.6306 [2021-03-27 18:23:06 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 610/1251] eta: 0:06:46 lr: 0.000292 loss: 3.1253 (3.0932) grad_norm: 1.9290 (1.9513) time: 0.6279 [2021-03-27 18:23:12 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 620/1251] eta: 0:06:40 lr: 0.000292 loss: 3.0140 (3.0881) grad_norm: 1.9081 (1.9511) time: 0.6295 [2021-03-27 18:23:18 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 630/1251] eta: 0:06:34 lr: 0.000292 loss: 3.0129 (3.0896) grad_norm: 1.8408 (1.9493) time: 0.6323 [2021-03-27 18:23:25 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 640/1251] eta: 0:06:27 lr: 0.000292 loss: 3.1545 (3.0896) grad_norm: 1.9850 (1.9515) time: 0.6263 [2021-03-27 18:23:31 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 650/1251] eta: 0:06:21 lr: 0.000292 loss: 3.0456 (3.0864) grad_norm: 1.9874 (1.9515) time: 0.6230 [2021-03-27 18:23:37 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 660/1251] eta: 0:06:14 lr: 0.000292 loss: 3.1511 (3.0878) grad_norm: 1.9001 (1.9510) time: 0.6266 [2021-03-27 18:23:43 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 670/1251] eta: 0:06:08 lr: 0.000292 loss: 3.1668 (3.0892) grad_norm: 1.8177 (1.9511) time: 0.6285 [2021-03-27 18:23:50 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 680/1251] eta: 0:06:02 lr: 0.000292 loss: 3.2967 (3.0892) grad_norm: 1.7942 (1.9488) time: 0.6271 [2021-03-27 18:23:56 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 690/1251] eta: 0:05:55 lr: 0.000292 loss: 3.1248 (3.0861) grad_norm: 1.8529 (1.9504) time: 0.6248 [2021-03-27 18:24:02 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 700/1251] eta: 0:05:49 lr: 0.000292 loss: 3.1248 (3.0877) grad_norm: 1.8584 (1.9489) time: 0.6230 [2021-03-27 18:24:08 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 710/1251] eta: 0:05:42 lr: 0.000292 loss: 3.2691 (3.0892) grad_norm: 1.9965 (1.9521) time: 0.6218 [2021-03-27 18:24:15 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 720/1251] eta: 0:05:36 lr: 0.000292 loss: 3.2691 (3.0877) grad_norm: 2.0377 (1.9530) time: 0.6217 [2021-03-27 18:24:21 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 730/1251] eta: 0:05:30 lr: 0.000292 loss: 3.0734 (3.0877) grad_norm: 1.9030 (1.9522) time: 0.6298 [2021-03-27 18:24:27 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 740/1251] eta: 0:05:23 lr: 0.000291 loss: 3.0409 (3.0869) grad_norm: 1.9329 (1.9543) time: 0.6361 [2021-03-27 18:24:34 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 750/1251] eta: 0:05:17 lr: 0.000291 loss: 3.0624 (3.0869) grad_norm: 1.9329 (1.9542) time: 0.6387 [2021-03-27 18:24:40 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 760/1251] eta: 0:05:11 lr: 0.000291 loss: 3.0950 (3.0876) grad_norm: 1.9360 (1.9545) time: 0.6324 [2021-03-27 18:24:46 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 770/1251] eta: 0:05:04 lr: 0.000291 loss: 3.2020 (3.0879) grad_norm: 1.9845 (1.9553) time: 0.6351 [2021-03-27 18:24:53 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 780/1251] eta: 0:04:58 lr: 0.000291 loss: 3.3499 (3.0888) grad_norm: 1.8966 (1.9539) time: 0.6487 [2021-03-27 18:24:59 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 790/1251] eta: 0:04:52 lr: 0.000291 loss: 3.3499 (3.0914) grad_norm: 1.8791 (1.9532) time: 0.6359 [2021-03-27 18:25:06 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 800/1251] eta: 0:04:45 lr: 0.000291 loss: 3.2343 (3.0917) grad_norm: 1.8791 (1.9516) time: 0.6326 [2021-03-27 18:25:12 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 810/1251] eta: 0:04:39 lr: 0.000291 loss: 3.1752 (3.0926) grad_norm: 1.8456 (1.9515) time: 0.6321 [2021-03-27 18:25:18 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 820/1251] eta: 0:04:33 lr: 0.000291 loss: 3.1496 (3.0925) grad_norm: 1.9656 (1.9515) time: 0.6276 [2021-03-27 18:25:25 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 830/1251] eta: 0:04:26 lr: 0.000291 loss: 3.2349 (3.0961) grad_norm: 1.9656 (1.9513) time: 0.6383 [2021-03-27 18:25:31 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 840/1251] eta: 0:04:20 lr: 0.000291 loss: 3.3791 (3.1005) grad_norm: 1.8693 (1.9508) time: 0.6347 [2021-03-27 18:25:37 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 850/1251] eta: 0:04:14 lr: 0.000291 loss: 3.3747 (3.1019) grad_norm: 1.7962 (1.9490) time: 0.6238 [2021-03-27 18:25:43 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 860/1251] eta: 0:04:07 lr: 0.000291 loss: 3.1197 (3.1013) grad_norm: 1.8399 (1.9491) time: 0.6252 [2021-03-27 18:25:50 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 870/1251] eta: 0:04:01 lr: 0.000291 loss: 3.3500 (3.1040) grad_norm: 1.8524 (1.9477) time: 0.6286 [2021-03-27 18:25:56 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 880/1251] eta: 0:03:54 lr: 0.000291 loss: 3.1712 (3.1040) grad_norm: 1.7731 (1.9461) time: 0.6276 [2021-03-27 18:26:02 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 890/1251] eta: 0:03:48 lr: 0.000291 loss: 3.1398 (3.1046) grad_norm: 1.8214 (1.9466) time: 0.6255 [2021-03-27 18:26:08 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 900/1251] eta: 0:03:42 lr: 0.000291 loss: 3.2025 (3.1041) grad_norm: 1.9694 (1.9464) time: 0.6268 [2021-03-27 18:26:15 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 910/1251] eta: 0:03:35 lr: 0.000291 loss: 3.2601 (3.1066) grad_norm: 1.8935 (1.9479) time: 0.6261 [2021-03-27 18:26:21 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 920/1251] eta: 0:03:29 lr: 0.000291 loss: 3.1961 (3.1066) grad_norm: 1.7309 (1.9460) time: 0.6215 [2021-03-27 18:26:27 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 930/1251] eta: 0:03:23 lr: 0.000291 loss: 3.1877 (3.1077) grad_norm: 1.8132 (1.9461) time: 0.6315 [2021-03-27 18:26:34 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 940/1251] eta: 0:03:16 lr: 0.000291 loss: 3.1547 (3.1074) grad_norm: 1.9338 (1.9462) time: 0.6348 [2021-03-27 18:26:40 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 950/1251] eta: 0:03:10 lr: 0.000291 loss: 3.0790 (3.1065) grad_norm: 1.8808 (1.9450) time: 0.6274 [2021-03-27 18:26:46 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 960/1251] eta: 0:03:04 lr: 0.000291 loss: 2.9467 (3.1048) grad_norm: 1.8808 (1.9446) time: 0.6291 [2021-03-27 18:26:53 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 970/1251] eta: 0:02:57 lr: 0.000291 loss: 3.0474 (3.1037) grad_norm: 1.8784 (1.9437) time: 0.6357 [2021-03-27 18:26:59 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 980/1251] eta: 0:02:51 lr: 0.000291 loss: 3.2160 (3.1030) grad_norm: 1.8772 (1.9454) time: 0.6309 [2021-03-27 18:27:05 swin_base_patch4_window7_224] INFO: Epoch: [192] [ 990/1251] eta: 0:02:45 lr: 0.000291 loss: 3.2160 (3.1016) grad_norm: 1.9296 (1.9452) time: 0.6219 [2021-03-27 18:27:11 swin_base_patch4_window7_224] INFO: Epoch: [192] [1000/1251] eta: 0:02:38 lr: 0.000290 loss: 3.0520 (3.1013) grad_norm: 1.8794 (1.9444) time: 0.6268 [2021-03-27 18:27:18 swin_base_patch4_window7_224] INFO: Epoch: [192] [1010/1251] eta: 0:02:32 lr: 0.000290 loss: 3.2017 (3.1016) grad_norm: 1.8448 (1.9436) time: 0.6277 [2021-03-27 18:27:24 swin_base_patch4_window7_224] INFO: Epoch: [192] [1020/1251] eta: 0:02:26 lr: 0.000290 loss: 3.2017 (3.1013) grad_norm: 1.8435 (1.9454) time: 0.6256 [2021-03-27 18:27:30 swin_base_patch4_window7_224] INFO: Epoch: [192] [1030/1251] eta: 0:02:19 lr: 0.000290 loss: 3.1591 (3.1023) grad_norm: 1.8404 (1.9451) time: 0.6260 [2021-03-27 18:27:36 swin_base_patch4_window7_224] INFO: Epoch: [192] [1040/1251] eta: 0:02:13 lr: 0.000290 loss: 3.3342 (3.1053) grad_norm: 1.8404 (1.9446) time: 0.6262 [2021-03-27 18:27:43 swin_base_patch4_window7_224] INFO: Epoch: [192] [1050/1251] eta: 0:02:07 lr: 0.000290 loss: 3.3679 (3.1045) grad_norm: 1.8308 (1.9434) time: 0.6252 [2021-03-27 18:27:49 swin_base_patch4_window7_224] INFO: Epoch: [192] [1060/1251] eta: 0:02:00 lr: 0.000290 loss: 2.7356 (3.0997) grad_norm: 1.8454 (1.9434) time: 0.6279 [2021-03-27 18:27:55 swin_base_patch4_window7_224] INFO: Epoch: [192] [1070/1251] eta: 0:01:54 lr: 0.000290 loss: 3.0111 (3.1028) grad_norm: 1.8630 (1.9429) time: 0.6311 [2021-03-27 18:28:01 swin_base_patch4_window7_224] INFO: Epoch: [192] [1080/1251] eta: 0:01:48 lr: 0.000290 loss: 3.2649 (3.1013) grad_norm: 1.8124 (1.9422) time: 0.6257 [2021-03-27 18:28:08 swin_base_patch4_window7_224] INFO: Epoch: [192] [1090/1251] eta: 0:01:41 lr: 0.000290 loss: 3.0798 (3.1008) grad_norm: 1.8540 (1.9440) time: 0.6224 [2021-03-27 18:28:14 swin_base_patch4_window7_224] INFO: Epoch: [192] [1100/1251] eta: 0:01:35 lr: 0.000290 loss: 3.1488 (3.1008) grad_norm: 1.9257 (1.9439) time: 0.6223 [2021-03-27 18:28:20 swin_base_patch4_window7_224] INFO: Epoch: [192] [1110/1251] eta: 0:01:29 lr: 0.000290 loss: 3.4006 (3.1027) grad_norm: 1.8298 (1.9427) time: 0.6234 [2021-03-27 18:28:26 swin_base_patch4_window7_224] INFO: Epoch: [192] [1120/1251] eta: 0:01:22 lr: 0.000290 loss: 3.3446 (3.1028) grad_norm: 1.8433 (1.9431) time: 0.6266 [2021-03-27 18:28:33 swin_base_patch4_window7_224] INFO: Epoch: [192] [1130/1251] eta: 0:01:16 lr: 0.000290 loss: 3.0339 (3.1012) grad_norm: 1.8230 (1.9418) time: 0.6228 [2021-03-27 18:28:39 swin_base_patch4_window7_224] INFO: Epoch: [192] [1140/1251] eta: 0:01:10 lr: 0.000290 loss: 3.2673 (3.1047) grad_norm: 1.7629 (1.9409) time: 0.6202 [2021-03-27 18:28:45 swin_base_patch4_window7_224] INFO: Epoch: [192] [1150/1251] eta: 0:01:03 lr: 0.000290 loss: 3.3758 (3.1045) grad_norm: 1.8048 (1.9397) time: 0.6237 [2021-03-27 18:28:51 swin_base_patch4_window7_224] INFO: Epoch: [192] [1160/1251] eta: 0:00:57 lr: 0.000290 loss: 3.3053 (3.1059) grad_norm: 1.8855 (1.9395) time: 0.6232 [2021-03-27 18:28:58 swin_base_patch4_window7_224] INFO: Epoch: [192] [1170/1251] eta: 0:00:51 lr: 0.000290 loss: 3.3053 (3.1061) grad_norm: 1.8824 (1.9394) time: 0.6214 [2021-03-27 18:29:04 swin_base_patch4_window7_224] INFO: Epoch: [192] [1180/1251] eta: 0:00:44 lr: 0.000290 loss: 3.2203 (3.1069) grad_norm: 1.8381 (1.9389) time: 0.6282 [2021-03-27 18:29:10 swin_base_patch4_window7_224] INFO: Epoch: [192] [1190/1251] eta: 0:00:38 lr: 0.000290 loss: 3.1712 (3.1062) grad_norm: 1.8946 (1.9400) time: 0.6336 [2021-03-27 18:29:16 swin_base_patch4_window7_224] INFO: Epoch: [192] [1200/1251] eta: 0:00:32 lr: 0.000290 loss: 3.0859 (3.1047) grad_norm: 2.0279 (1.9406) time: 0.6263 [2021-03-27 18:29:23 swin_base_patch4_window7_224] INFO: Epoch: [192] [1210/1251] eta: 0:00:25 lr: 0.000290 loss: 3.0859 (3.1061) grad_norm: 1.9013 (1.9404) time: 0.6228 [2021-03-27 18:29:29 swin_base_patch4_window7_224] INFO: Epoch: [192] [1220/1251] eta: 0:00:19 lr: 0.000290 loss: 3.1954 (3.1070) grad_norm: 1.8930 (1.9411) time: 0.6241 [2021-03-27 18:29:35 swin_base_patch4_window7_224] INFO: Epoch: [192] [1230/1251] eta: 0:00:13 lr: 0.000290 loss: 3.1954 (3.1066) grad_norm: 2.0389 (1.9417) time: 0.6242 [2021-03-27 18:29:41 swin_base_patch4_window7_224] INFO: Epoch: [192] [1240/1251] eta: 0:00:06 lr: 0.000290 loss: 3.2325 (3.1072) grad_norm: 2.0274 (1.9425) time: 0.6205 [2021-03-27 18:29:47 swin_base_patch4_window7_224] INFO: Epoch: [192] [1250/1251] eta: 0:00:00 lr: 0.000290 loss: 3.2325 (3.1068) grad_norm: 1.9533 (1.9420) time: 0.6142 [2021-03-27 18:29:56 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:18 loss: 0.5615 (0.5615) acc1: 85.9375 (85.9375) acc5: 100.0000 (100.0000) [2021-03-27 18:29:59 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8625 (0.8435) acc1: 81.2500 (80.6818) acc5: 96.8750 (96.4489) [2021-03-27 18:30:02 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8630 (0.8583) acc1: 79.6875 (79.9851) acc5: 95.3125 (95.9821) [2021-03-27 18:30:04 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8445 (0.8488) acc1: 79.6875 (79.7379) acc5: 95.3125 (95.9677) [2021-03-27 18:30:06 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7897 (0.8328) acc1: 79.6875 (80.2591) acc5: 95.3125 (95.9604) [2021-03-27 18:30:07 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8046 (0.8429) acc1: 79.6875 (79.8080) acc5: 95.3125 (95.7440) [2021-03-27 18:30:17 swin_base_patch4_window7_224] INFO: * Acc@1 80.892 Acc@5 95.742 loss 0.823 [2021-03-27 18:30:17 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.9% [2021-03-27 18:30:17 swin_base_patch4_window7_224] INFO: Max accuracy: 80.89% [2021-03-27 18:30:21 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 0/1251] eta: 1:33:17 lr: 0.000290 loss: 3.3424 (3.3424) grad_norm: 1.9192 (1.9192) time: 4.4743 [2021-03-27 18:30:28 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 10/1251] eta: 0:20:18 lr: 0.000290 loss: 3.1814 (2.9530) grad_norm: 1.9192 (2.1197) time: 0.9816 [2021-03-27 18:30:34 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 20/1251] eta: 0:16:41 lr: 0.000289 loss: 3.1197 (2.9878) grad_norm: 1.9440 (2.0372) time: 0.6302 [2021-03-27 18:30:40 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 30/1251] eta: 0:15:17 lr: 0.000289 loss: 3.1197 (3.0279) grad_norm: 1.9549 (2.0179) time: 0.6253 [2021-03-27 18:30:47 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 40/1251] eta: 0:14:39 lr: 0.000289 loss: 3.3440 (3.1047) grad_norm: 1.8817 (2.0405) time: 0.6345 [2021-03-27 18:30:53 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 50/1251] eta: 0:14:09 lr: 0.000289 loss: 3.3440 (3.1237) grad_norm: 1.8936 (2.0978) time: 0.6392 [2021-03-27 18:31:00 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 60/1251] eta: 0:13:51 lr: 0.000289 loss: 3.2912 (3.1531) grad_norm: 1.9025 (2.0639) time: 0.6416 [2021-03-27 18:31:06 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 70/1251] eta: 0:13:32 lr: 0.000289 loss: 3.0337 (3.1069) grad_norm: 1.8817 (2.0459) time: 0.6364 [2021-03-27 18:31:12 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 80/1251] eta: 0:13:16 lr: 0.000289 loss: 3.0337 (3.1203) grad_norm: 1.8817 (2.0316) time: 0.6230 [2021-03-27 18:31:18 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 90/1251] eta: 0:13:02 lr: 0.000289 loss: 3.2041 (3.1191) grad_norm: 1.8734 (2.0281) time: 0.6250 [2021-03-27 18:31:25 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 100/1251] eta: 0:12:50 lr: 0.000289 loss: 3.0794 (3.1089) grad_norm: 1.9325 (2.0264) time: 0.6260 [2021-03-27 18:31:31 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 110/1251] eta: 0:12:39 lr: 0.000289 loss: 3.3308 (3.1217) grad_norm: 1.9733 (2.0121) time: 0.6291 [2021-03-27 18:31:37 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 120/1251] eta: 0:12:29 lr: 0.000289 loss: 3.3771 (3.1202) grad_norm: 1.8203 (2.0004) time: 0.6315 [2021-03-27 18:31:43 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 130/1251] eta: 0:12:20 lr: 0.000289 loss: 2.7173 (3.0845) grad_norm: 1.8404 (1.9906) time: 0.6293 [2021-03-27 18:31:50 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 140/1251] eta: 0:12:10 lr: 0.000289 loss: 2.7939 (3.0844) grad_norm: 1.8146 (1.9780) time: 0.6237 [2021-03-27 18:31:56 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 150/1251] eta: 0:12:02 lr: 0.000289 loss: 3.2875 (3.1024) grad_norm: 1.8146 (1.9788) time: 0.6269 [2021-03-27 18:32:02 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 160/1251] eta: 0:11:53 lr: 0.000289 loss: 3.2875 (3.1027) grad_norm: 1.9200 (1.9781) time: 0.6335 [2021-03-27 18:32:09 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 170/1251] eta: 0:11:45 lr: 0.000289 loss: 3.2013 (3.0978) grad_norm: 1.9210 (1.9865) time: 0.6292 [2021-03-27 18:32:15 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 180/1251] eta: 0:11:37 lr: 0.000289 loss: 3.3502 (3.1158) grad_norm: 2.0411 (1.9945) time: 0.6262 [2021-03-27 18:32:21 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 190/1251] eta: 0:11:29 lr: 0.000289 loss: 3.0843 (3.1053) grad_norm: 1.9269 (inf) time: 0.6235 [2021-03-27 18:32:27 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 200/1251] eta: 0:11:21 lr: 0.000289 loss: 3.0032 (3.0952) grad_norm: 1.8474 (inf) time: 0.6224 [2021-03-27 18:32:34 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 210/1251] eta: 0:11:13 lr: 0.000289 loss: 3.2704 (3.0982) grad_norm: 1.7386 (inf) time: 0.6241 [2021-03-27 18:32:40 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 220/1251] eta: 0:11:06 lr: 0.000289 loss: 3.2761 (3.0980) grad_norm: 1.6599 (inf) time: 0.6318 [2021-03-27 18:32:46 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 230/1251] eta: 0:10:59 lr: 0.000289 loss: 3.1064 (3.0994) grad_norm: 1.7897 (inf) time: 0.6360 [2021-03-27 18:32:53 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 240/1251] eta: 0:10:52 lr: 0.000289 loss: 3.1037 (3.0987) grad_norm: 1.7897 (inf) time: 0.6284 [2021-03-27 18:32:59 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 250/1251] eta: 0:10:45 lr: 0.000289 loss: 2.9676 (3.0897) grad_norm: 1.7383 (inf) time: 0.6253 [2021-03-27 18:33:05 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 260/1251] eta: 0:10:38 lr: 0.000289 loss: 3.0854 (3.0862) grad_norm: 1.8394 (inf) time: 0.6256 [2021-03-27 18:33:11 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 270/1251] eta: 0:10:30 lr: 0.000289 loss: 3.1202 (3.0814) grad_norm: 1.8394 (inf) time: 0.6247 [2021-03-27 18:33:18 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 280/1251] eta: 0:10:23 lr: 0.000289 loss: 3.3967 (3.0897) grad_norm: 1.7973 (inf) time: 0.6242 [2021-03-27 18:33:24 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 290/1251] eta: 0:10:16 lr: 0.000288 loss: 3.3490 (3.0857) grad_norm: 1.8303 (inf) time: 0.6231 [2021-03-27 18:33:30 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 300/1251] eta: 0:10:09 lr: 0.000288 loss: 3.2664 (3.0823) grad_norm: 1.8389 (inf) time: 0.6242 [2021-03-27 18:33:36 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 310/1251] eta: 0:10:03 lr: 0.000288 loss: 3.1937 (3.0859) grad_norm: 1.8389 (inf) time: 0.6290 [2021-03-27 18:33:43 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 320/1251] eta: 0:09:56 lr: 0.000288 loss: 3.0478 (3.0744) grad_norm: 1.9426 (inf) time: 0.6274 [2021-03-27 18:33:49 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 330/1251] eta: 0:09:49 lr: 0.000288 loss: 2.9913 (3.0771) grad_norm: 1.8654 (inf) time: 0.6261 [2021-03-27 18:33:55 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 340/1251] eta: 0:09:42 lr: 0.000288 loss: 3.1023 (3.0727) grad_norm: 1.8966 (inf) time: 0.6237 [2021-03-27 18:34:01 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 350/1251] eta: 0:09:36 lr: 0.000288 loss: 2.9718 (3.0673) grad_norm: 1.8915 (inf) time: 0.6282 [2021-03-27 18:34:08 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 360/1251] eta: 0:09:29 lr: 0.000288 loss: 3.1019 (3.0715) grad_norm: 1.8853 (inf) time: 0.6365 [2021-03-27 18:34:14 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 370/1251] eta: 0:09:22 lr: 0.000288 loss: 3.1619 (3.0681) grad_norm: 1.8676 (inf) time: 0.6272 [2021-03-27 18:34:20 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 380/1251] eta: 0:09:15 lr: 0.000288 loss: 3.2039 (3.0706) grad_norm: 1.8613 (inf) time: 0.6194 [2021-03-27 18:34:26 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 390/1251] eta: 0:09:09 lr: 0.000288 loss: 3.0768 (3.0650) grad_norm: 1.9328 (inf) time: 0.6216 [2021-03-27 18:34:33 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 400/1251] eta: 0:09:02 lr: 0.000288 loss: 3.0299 (3.0667) grad_norm: 1.9396 (inf) time: 0.6265 [2021-03-27 18:34:39 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 410/1251] eta: 0:08:55 lr: 0.000288 loss: 3.0299 (3.0659) grad_norm: 2.0054 (inf) time: 0.6268 [2021-03-27 18:34:45 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 420/1251] eta: 0:08:49 lr: 0.000288 loss: 3.1313 (3.0674) grad_norm: 1.8861 (inf) time: 0.6254 [2021-03-27 18:34:51 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 430/1251] eta: 0:08:42 lr: 0.000288 loss: 3.1313 (3.0649) grad_norm: 1.8683 (inf) time: 0.6249 [2021-03-27 18:34:58 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 440/1251] eta: 0:08:36 lr: 0.000288 loss: 3.0495 (3.0682) grad_norm: 1.9248 (inf) time: 0.6269 [2021-03-27 18:35:04 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 450/1251] eta: 0:08:29 lr: 0.000288 loss: 3.0263 (3.0654) grad_norm: 1.8534 (inf) time: 0.6279 [2021-03-27 18:35:10 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 460/1251] eta: 0:08:23 lr: 0.000288 loss: 2.9762 (3.0673) grad_norm: 1.8208 (inf) time: 0.6240 [2021-03-27 18:35:17 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 470/1251] eta: 0:08:16 lr: 0.000288 loss: 3.0725 (3.0663) grad_norm: 1.7459 (inf) time: 0.6307 [2021-03-27 18:35:23 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 480/1251] eta: 0:08:10 lr: 0.000288 loss: 2.9581 (3.0615) grad_norm: 1.7756 (inf) time: 0.6317 [2021-03-27 18:35:29 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 490/1251] eta: 0:08:03 lr: 0.000288 loss: 2.9457 (3.0596) grad_norm: 1.9538 (inf) time: 0.6274 [2021-03-27 18:35:35 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 500/1251] eta: 0:07:57 lr: 0.000288 loss: 3.1486 (3.0649) grad_norm: 1.8764 (inf) time: 0.6262 [2021-03-27 18:35:42 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 510/1251] eta: 0:07:50 lr: 0.000288 loss: 3.2277 (3.0627) grad_norm: 1.8764 (inf) time: 0.6262 [2021-03-27 18:35:48 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 520/1251] eta: 0:07:44 lr: 0.000288 loss: 3.1183 (3.0614) grad_norm: 1.9469 (inf) time: 0.6311 [2021-03-27 18:35:54 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 530/1251] eta: 0:07:38 lr: 0.000288 loss: 3.2939 (3.0699) grad_norm: 1.8551 (inf) time: 0.6328 [2021-03-27 18:36:01 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 540/1251] eta: 0:07:31 lr: 0.000288 loss: 3.2988 (3.0724) grad_norm: 1.8657 (inf) time: 0.6274 [2021-03-27 18:36:07 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 550/1251] eta: 0:07:25 lr: 0.000288 loss: 3.1356 (3.0700) grad_norm: 1.9669 (inf) time: 0.6346 [2021-03-27 18:36:13 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 560/1251] eta: 0:07:18 lr: 0.000287 loss: 2.9302 (3.0690) grad_norm: 1.8466 (inf) time: 0.6411 [2021-03-27 18:36:20 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 570/1251] eta: 0:07:12 lr: 0.000287 loss: 3.2716 (3.0717) grad_norm: 1.8466 (inf) time: 0.6375 [2021-03-27 18:36:26 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 580/1251] eta: 0:07:06 lr: 0.000287 loss: 3.2781 (3.0732) grad_norm: 1.9191 (inf) time: 0.6328 [2021-03-27 18:36:32 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 590/1251] eta: 0:06:59 lr: 0.000287 loss: 3.2558 (3.0748) grad_norm: 1.8667 (inf) time: 0.6249 [2021-03-27 18:36:39 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 600/1251] eta: 0:06:53 lr: 0.000287 loss: 3.1310 (3.0765) grad_norm: 1.8667 (inf) time: 0.6297 [2021-03-27 18:36:45 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 610/1251] eta: 0:06:46 lr: 0.000287 loss: 3.2492 (3.0787) grad_norm: 1.9317 (inf) time: 0.6335 [2021-03-27 18:36:51 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 620/1251] eta: 0:06:40 lr: 0.000287 loss: 3.2492 (3.0766) grad_norm: 1.9923 (inf) time: 0.6260 [2021-03-27 18:36:57 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 630/1251] eta: 0:06:34 lr: 0.000287 loss: 2.7512 (3.0739) grad_norm: 1.8538 (inf) time: 0.6215 [2021-03-27 18:37:04 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 640/1251] eta: 0:06:27 lr: 0.000287 loss: 2.7512 (3.0704) grad_norm: 1.8312 (inf) time: 0.6231 [2021-03-27 18:37:10 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 650/1251] eta: 0:06:21 lr: 0.000287 loss: 2.9110 (3.0703) grad_norm: 1.8907 (inf) time: 0.6289 [2021-03-27 18:37:16 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 660/1251] eta: 0:06:14 lr: 0.000287 loss: 3.2935 (3.0736) grad_norm: 2.0536 (inf) time: 0.6337 [2021-03-27 18:37:23 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 670/1251] eta: 0:06:08 lr: 0.000287 loss: 3.2978 (3.0776) grad_norm: 1.8192 (inf) time: 0.6288 [2021-03-27 18:37:29 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 680/1251] eta: 0:06:01 lr: 0.000287 loss: 3.2978 (3.0787) grad_norm: 1.8239 (inf) time: 0.6232 [2021-03-27 18:37:35 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 690/1251] eta: 0:05:55 lr: 0.000287 loss: 3.2589 (3.0772) grad_norm: 1.9126 (inf) time: 0.6231 [2021-03-27 18:37:41 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 700/1251] eta: 0:05:49 lr: 0.000287 loss: 3.4350 (3.0823) grad_norm: 1.9218 (inf) time: 0.6259 [2021-03-27 18:37:48 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 710/1251] eta: 0:05:42 lr: 0.000287 loss: 3.3251 (3.0819) grad_norm: 1.9400 (inf) time: 0.6285 [2021-03-27 18:37:54 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 720/1251] eta: 0:05:36 lr: 0.000287 loss: 2.9598 (3.0792) grad_norm: 1.8975 (inf) time: 0.6272 [2021-03-27 18:38:00 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 730/1251] eta: 0:05:30 lr: 0.000287 loss: 2.9752 (3.0784) grad_norm: 1.7537 (inf) time: 0.6245 [2021-03-27 18:38:06 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 740/1251] eta: 0:05:23 lr: 0.000287 loss: 3.1823 (3.0812) grad_norm: 1.8365 (inf) time: 0.6285 [2021-03-27 18:38:13 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 750/1251] eta: 0:05:17 lr: 0.000287 loss: 3.1677 (3.0810) grad_norm: 1.8730 (inf) time: 0.6366 [2021-03-27 18:38:19 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 760/1251] eta: 0:05:11 lr: 0.000287 loss: 3.0957 (3.0813) grad_norm: 1.7765 (inf) time: 0.6329 [2021-03-27 18:38:25 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 770/1251] eta: 0:05:04 lr: 0.000287 loss: 3.0957 (3.0803) grad_norm: 1.8549 (inf) time: 0.6287 [2021-03-27 18:38:32 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 780/1251] eta: 0:04:58 lr: 0.000287 loss: 3.1204 (3.0826) grad_norm: 1.9890 (inf) time: 0.6267 [2021-03-27 18:38:38 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 790/1251] eta: 0:04:51 lr: 0.000287 loss: 3.2519 (3.0840) grad_norm: 2.0258 (inf) time: 0.6275 [2021-03-27 18:38:44 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 800/1251] eta: 0:04:45 lr: 0.000287 loss: 3.2546 (3.0830) grad_norm: 2.0525 (inf) time: 0.6376 [2021-03-27 18:38:51 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 810/1251] eta: 0:04:39 lr: 0.000287 loss: 3.2546 (3.0844) grad_norm: 2.0190 (inf) time: 0.6359 [2021-03-27 18:38:57 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 820/1251] eta: 0:04:32 lr: 0.000287 loss: 3.0301 (3.0824) grad_norm: 2.0749 (inf) time: 0.6288 [2021-03-27 18:39:03 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 830/1251] eta: 0:04:26 lr: 0.000286 loss: 2.8986 (3.0818) grad_norm: 2.0933 (inf) time: 0.6241 [2021-03-27 18:39:09 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 840/1251] eta: 0:04:20 lr: 0.000286 loss: 3.1228 (3.0804) grad_norm: 2.0204 (inf) time: 0.6237 [2021-03-27 18:39:16 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 850/1251] eta: 0:04:13 lr: 0.000286 loss: 3.0548 (3.0802) grad_norm: 1.8129 (inf) time: 0.6280 [2021-03-27 18:39:22 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 860/1251] eta: 0:04:07 lr: 0.000286 loss: 3.2358 (3.0817) grad_norm: 1.8453 (inf) time: 0.6240 [2021-03-27 18:39:28 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 870/1251] eta: 0:04:01 lr: 0.000286 loss: 3.2358 (3.0802) grad_norm: 1.9394 (inf) time: 0.6258 [2021-03-27 18:39:35 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 880/1251] eta: 0:03:54 lr: 0.000286 loss: 3.0322 (3.0799) grad_norm: 1.9302 (inf) time: 0.6337 [2021-03-27 18:39:41 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 890/1251] eta: 0:03:48 lr: 0.000286 loss: 3.1180 (3.0781) grad_norm: 1.8630 (inf) time: 0.6271 [2021-03-27 18:39:47 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 900/1251] eta: 0:03:42 lr: 0.000286 loss: 3.2356 (3.0789) grad_norm: 1.8227 (inf) time: 0.6206 [2021-03-27 18:39:53 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 910/1251] eta: 0:03:35 lr: 0.000286 loss: 3.2421 (3.0794) grad_norm: 1.8015 (inf) time: 0.6292 [2021-03-27 18:40:00 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 920/1251] eta: 0:03:29 lr: 0.000286 loss: 3.2421 (3.0789) grad_norm: 1.8899 (inf) time: 0.6323 [2021-03-27 18:40:06 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 930/1251] eta: 0:03:23 lr: 0.000286 loss: 3.3144 (3.0802) grad_norm: 1.8921 (inf) time: 0.6266 [2021-03-27 18:40:12 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 940/1251] eta: 0:03:16 lr: 0.000286 loss: 3.3186 (3.0813) grad_norm: 1.8456 (inf) time: 0.6264 [2021-03-27 18:40:19 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 950/1251] eta: 0:03:10 lr: 0.000286 loss: 3.2508 (3.0824) grad_norm: 1.8456 (inf) time: 0.6335 [2021-03-27 18:40:25 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 960/1251] eta: 0:03:04 lr: 0.000286 loss: 3.2029 (3.0842) grad_norm: 1.8414 (inf) time: 0.6336 [2021-03-27 18:40:31 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 970/1251] eta: 0:02:57 lr: 0.000286 loss: 3.3285 (3.0869) grad_norm: 1.8983 (inf) time: 0.6271 [2021-03-27 18:40:37 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 980/1251] eta: 0:02:51 lr: 0.000286 loss: 2.9696 (3.0828) grad_norm: 1.8563 (inf) time: 0.6278 [2021-03-27 18:40:44 swin_base_patch4_window7_224] INFO: Epoch: [193] [ 990/1251] eta: 0:02:45 lr: 0.000286 loss: 2.9696 (3.0818) grad_norm: 1.9445 (inf) time: 0.6299 [2021-03-27 18:40:50 swin_base_patch4_window7_224] INFO: Epoch: [193] [1000/1251] eta: 0:02:38 lr: 0.000286 loss: 3.1236 (3.0812) grad_norm: 1.9445 (inf) time: 0.6260 [2021-03-27 18:40:56 swin_base_patch4_window7_224] INFO: Epoch: [193] [1010/1251] eta: 0:02:32 lr: 0.000286 loss: 3.2487 (3.0816) grad_norm: 1.8539 (inf) time: 0.6254 [2021-03-27 18:41:02 swin_base_patch4_window7_224] INFO: Epoch: [193] [1020/1251] eta: 0:02:26 lr: 0.000286 loss: 3.2487 (3.0824) grad_norm: 1.9295 (inf) time: 0.6270 [2021-03-27 18:41:09 swin_base_patch4_window7_224] INFO: Epoch: [193] [1030/1251] eta: 0:02:19 lr: 0.000286 loss: 3.1197 (3.0847) grad_norm: 1.7684 (inf) time: 0.6250 [2021-03-27 18:41:15 swin_base_patch4_window7_224] INFO: Epoch: [193] [1040/1251] eta: 0:02:13 lr: 0.000286 loss: 3.0364 (3.0826) grad_norm: 1.9164 (inf) time: 0.6301 [2021-03-27 18:41:21 swin_base_patch4_window7_224] INFO: Epoch: [193] [1050/1251] eta: 0:02:07 lr: 0.000286 loss: 2.9703 (3.0819) grad_norm: 1.9470 (inf) time: 0.6284 [2021-03-27 18:41:28 swin_base_patch4_window7_224] INFO: Epoch: [193] [1060/1251] eta: 0:02:00 lr: 0.000286 loss: 2.9951 (3.0822) grad_norm: 1.9258 (inf) time: 0.6283 [2021-03-27 18:41:34 swin_base_patch4_window7_224] INFO: Epoch: [193] [1070/1251] eta: 0:01:54 lr: 0.000286 loss: 3.1661 (3.0835) grad_norm: 1.9133 (inf) time: 0.6300 [2021-03-27 18:41:40 swin_base_patch4_window7_224] INFO: Epoch: [193] [1080/1251] eta: 0:01:48 lr: 0.000286 loss: 3.0063 (3.0812) grad_norm: 1.7874 (inf) time: 0.6290 [2021-03-27 18:41:47 swin_base_patch4_window7_224] INFO: Epoch: [193] [1090/1251] eta: 0:01:41 lr: 0.000286 loss: 2.9792 (3.0795) grad_norm: 1.7874 (inf) time: 0.6310 [2021-03-27 18:41:53 swin_base_patch4_window7_224] INFO: Epoch: [193] [1100/1251] eta: 0:01:35 lr: 0.000285 loss: 2.6513 (3.0749) grad_norm: 1.8695 (inf) time: 0.6323 [2021-03-27 18:41:59 swin_base_patch4_window7_224] INFO: Epoch: [193] [1110/1251] eta: 0:01:29 lr: 0.000285 loss: 3.0709 (3.0764) grad_norm: 1.8695 (inf) time: 0.6339 [2021-03-27 18:42:06 swin_base_patch4_window7_224] INFO: Epoch: [193] [1120/1251] eta: 0:01:22 lr: 0.000285 loss: 3.1140 (3.0757) grad_norm: 1.9974 (inf) time: 0.6318 [2021-03-27 18:42:12 swin_base_patch4_window7_224] INFO: Epoch: [193] [1130/1251] eta: 0:01:16 lr: 0.000285 loss: 3.0621 (3.0744) grad_norm: 1.9974 (inf) time: 0.6297 [2021-03-27 18:42:18 swin_base_patch4_window7_224] INFO: Epoch: [193] [1140/1251] eta: 0:01:10 lr: 0.000285 loss: 3.1799 (3.0752) grad_norm: 2.0298 (inf) time: 0.6234 [2021-03-27 18:42:24 swin_base_patch4_window7_224] INFO: Epoch: [193] [1150/1251] eta: 0:01:03 lr: 0.000285 loss: 3.0506 (3.0729) grad_norm: 2.0113 (inf) time: 0.6236 [2021-03-27 18:42:31 swin_base_patch4_window7_224] INFO: Epoch: [193] [1160/1251] eta: 0:00:57 lr: 0.000285 loss: 2.9043 (3.0720) grad_norm: 1.9990 (inf) time: 0.6294 [2021-03-27 18:42:37 swin_base_patch4_window7_224] INFO: Epoch: [193] [1170/1251] eta: 0:00:51 lr: 0.000285 loss: 2.9296 (3.0706) grad_norm: 2.0230 (inf) time: 0.6276 [2021-03-27 18:42:43 swin_base_patch4_window7_224] INFO: Epoch: [193] [1180/1251] eta: 0:00:44 lr: 0.000285 loss: 2.9296 (3.0705) grad_norm: 1.8435 (inf) time: 0.6259 [2021-03-27 18:42:49 swin_base_patch4_window7_224] INFO: Epoch: [193] [1190/1251] eta: 0:00:38 lr: 0.000285 loss: 3.0310 (3.0712) grad_norm: 1.8652 (inf) time: 0.6287 [2021-03-27 18:42:56 swin_base_patch4_window7_224] INFO: Epoch: [193] [1200/1251] eta: 0:00:32 lr: 0.000285 loss: 2.9120 (3.0669) grad_norm: 1.9057 (inf) time: 0.6333 [2021-03-27 18:43:02 swin_base_patch4_window7_224] INFO: Epoch: [193] [1210/1251] eta: 0:00:25 lr: 0.000285 loss: 2.7856 (3.0662) grad_norm: 1.9021 (inf) time: 0.6293 [2021-03-27 18:43:08 swin_base_patch4_window7_224] INFO: Epoch: [193] [1220/1251] eta: 0:00:19 lr: 0.000285 loss: 3.2526 (3.0673) grad_norm: 1.8930 (inf) time: 0.6315 [2021-03-27 18:43:15 swin_base_patch4_window7_224] INFO: Epoch: [193] [1230/1251] eta: 0:00:13 lr: 0.000285 loss: 3.2757 (3.0688) grad_norm: 1.8467 (inf) time: 0.6318 [2021-03-27 18:43:21 swin_base_patch4_window7_224] INFO: Epoch: [193] [1240/1251] eta: 0:00:06 lr: 0.000285 loss: 3.2599 (3.0701) grad_norm: 1.8706 (inf) time: 0.6260 [2021-03-27 18:43:27 swin_base_patch4_window7_224] INFO: Epoch: [193] [1250/1251] eta: 0:00:00 lr: 0.000285 loss: 3.3344 (3.0717) grad_norm: 2.0579 (inf) time: 0.6257 [2021-03-27 18:43:35 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:01 loss: 1.0921 (1.0921) acc1: 73.4375 (73.4375) acc5: 92.1875 (92.1875) [2021-03-27 18:43:38 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8521 (0.8847) acc1: 78.1250 (78.6932) acc5: 95.3125 (95.1705) [2021-03-27 18:43:40 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7448 (0.8308) acc1: 79.6875 (80.2083) acc5: 96.8750 (96.4286) [2021-03-27 18:43:43 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7448 (0.8521) acc1: 81.2500 (79.5867) acc5: 98.4375 (95.9173) [2021-03-27 18:43:45 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7605 (0.8463) acc1: 82.8125 (80.0305) acc5: 95.3125 (95.8841) [2021-03-27 18:43:46 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7464 (0.8450) acc1: 82.8125 (80.0000) acc5: 96.8750 (95.8400) [2021-03-27 18:43:53 swin_base_patch4_window7_224] INFO: * Acc@1 80.860 Acc@5 95.606 loss 0.827 [2021-03-27 18:43:53 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.9% [2021-03-27 18:43:53 swin_base_patch4_window7_224] INFO: Max accuracy: 80.89% [2021-03-27 18:43:57 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 0/1251] eta: 1:26:47 lr: 0.000285 loss: 2.9144 (2.9144) grad_norm: 1.8133 (1.8133) time: 4.1630 [2021-03-27 18:44:04 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 10/1251] eta: 0:20:02 lr: 0.000285 loss: 2.9144 (2.9352) grad_norm: 1.9787 (2.0332) time: 0.9689 [2021-03-27 18:44:10 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 20/1251] eta: 0:16:33 lr: 0.000285 loss: 3.0622 (3.0090) grad_norm: 2.1302 (2.1971) time: 0.6391 [2021-03-27 18:44:16 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 30/1251] eta: 0:15:14 lr: 0.000285 loss: 3.1563 (3.0270) grad_norm: 2.1905 (2.1919) time: 0.6279 [2021-03-27 18:44:23 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 40/1251] eta: 0:14:31 lr: 0.000285 loss: 3.2752 (3.0895) grad_norm: 1.8462 (2.1056) time: 0.6272 [2021-03-27 18:44:29 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 50/1251] eta: 0:14:00 lr: 0.000285 loss: 3.2752 (3.1111) grad_norm: 1.8428 (2.0695) time: 0.6241 [2021-03-27 18:44:35 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 60/1251] eta: 0:13:38 lr: 0.000285 loss: 3.2056 (3.0876) grad_norm: 1.7547 (2.0156) time: 0.6227 [2021-03-27 18:44:41 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 70/1251] eta: 0:13:21 lr: 0.000285 loss: 3.0969 (3.1034) grad_norm: 1.8126 (2.0467) time: 0.6238 [2021-03-27 18:44:48 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 80/1251] eta: 0:13:07 lr: 0.000285 loss: 3.2293 (3.1202) grad_norm: 1.8989 (2.0274) time: 0.6278 [2021-03-27 18:44:54 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 90/1251] eta: 0:12:55 lr: 0.000285 loss: 3.2453 (3.1140) grad_norm: 1.8454 (2.0069) time: 0.6295 [2021-03-27 18:45:00 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 100/1251] eta: 0:12:44 lr: 0.000285 loss: 3.2453 (3.1213) grad_norm: 1.9134 (2.0156) time: 0.6310 [2021-03-27 18:45:07 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 110/1251] eta: 0:12:33 lr: 0.000284 loss: 3.3266 (3.1297) grad_norm: 1.8974 (2.0025) time: 0.6283 [2021-03-27 18:45:13 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 120/1251] eta: 0:12:23 lr: 0.000284 loss: 3.2916 (3.1364) grad_norm: 1.8974 (2.0078) time: 0.6211 [2021-03-27 18:45:19 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 130/1251] eta: 0:12:15 lr: 0.000284 loss: 3.0828 (3.1160) grad_norm: 1.9029 (2.0189) time: 0.6293 [2021-03-27 18:45:26 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 140/1251] eta: 0:12:07 lr: 0.000284 loss: 2.6742 (3.0920) grad_norm: 1.9769 (2.0277) time: 0.6368 [2021-03-27 18:45:32 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 150/1251] eta: 0:11:58 lr: 0.000284 loss: 2.7191 (3.0919) grad_norm: 1.9315 (2.0153) time: 0.6285 [2021-03-27 18:45:38 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 160/1251] eta: 0:11:49 lr: 0.000284 loss: 3.0949 (3.0834) grad_norm: 1.8424 (2.0109) time: 0.6220 [2021-03-27 18:45:44 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 170/1251] eta: 0:11:41 lr: 0.000284 loss: 3.1824 (3.0881) grad_norm: 1.8552 (2.0002) time: 0.6248 [2021-03-27 18:45:51 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 180/1251] eta: 0:11:34 lr: 0.000284 loss: 3.1824 (3.0862) grad_norm: 1.8546 (2.0003) time: 0.6327 [2021-03-27 18:45:57 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 190/1251] eta: 0:11:26 lr: 0.000284 loss: 2.9794 (3.0750) grad_norm: 1.8176 (1.9911) time: 0.6309 [2021-03-27 18:46:03 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 200/1251] eta: 0:11:18 lr: 0.000284 loss: 2.8958 (3.0627) grad_norm: 1.8176 (1.9908) time: 0.6239 [2021-03-27 18:46:09 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 210/1251] eta: 0:11:11 lr: 0.000284 loss: 2.9522 (3.0640) grad_norm: 1.8961 (1.9897) time: 0.6288 [2021-03-27 18:46:16 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 220/1251] eta: 0:11:04 lr: 0.000284 loss: 3.1286 (3.0643) grad_norm: 1.9038 (1.9871) time: 0.6294 [2021-03-27 18:46:22 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 230/1251] eta: 0:10:57 lr: 0.000284 loss: 3.1731 (3.0676) grad_norm: 1.9479 (1.9957) time: 0.6325 [2021-03-27 18:46:28 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 240/1251] eta: 0:10:50 lr: 0.000284 loss: 3.1364 (3.0669) grad_norm: 1.9489 (1.9966) time: 0.6298 [2021-03-27 18:46:35 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 250/1251] eta: 0:10:43 lr: 0.000284 loss: 2.9093 (3.0621) grad_norm: 1.7939 (1.9893) time: 0.6298 [2021-03-27 18:46:41 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 260/1251] eta: 0:10:36 lr: 0.000284 loss: 2.9461 (3.0568) grad_norm: 1.7939 (1.9885) time: 0.6311 [2021-03-27 18:46:47 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 270/1251] eta: 0:10:29 lr: 0.000284 loss: 2.9734 (3.0521) grad_norm: 1.7862 (1.9832) time: 0.6232 [2021-03-27 18:46:53 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 280/1251] eta: 0:10:22 lr: 0.000284 loss: 3.0404 (3.0591) grad_norm: 1.8536 (1.9831) time: 0.6239 [2021-03-27 18:47:00 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 290/1251] eta: 0:10:15 lr: 0.000284 loss: 3.4718 (3.0617) grad_norm: 1.9448 (1.9833) time: 0.6248 [2021-03-27 18:47:06 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 300/1251] eta: 0:10:09 lr: 0.000284 loss: 3.1975 (3.0678) grad_norm: 1.8352 (1.9755) time: 0.6345 [2021-03-27 18:47:12 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 310/1251] eta: 0:10:02 lr: 0.000284 loss: 3.1749 (3.0702) grad_norm: 1.7958 (1.9730) time: 0.6322 [2021-03-27 18:47:19 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 320/1251] eta: 0:09:55 lr: 0.000284 loss: 3.1917 (3.0734) grad_norm: 1.8857 (1.9719) time: 0.6221 [2021-03-27 18:47:25 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 330/1251] eta: 0:09:48 lr: 0.000284 loss: 3.2769 (3.0776) grad_norm: 1.8790 (1.9689) time: 0.6256 [2021-03-27 18:47:31 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 340/1251] eta: 0:09:41 lr: 0.000284 loss: 3.1437 (3.0767) grad_norm: 1.7414 (1.9616) time: 0.6250 [2021-03-27 18:47:37 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 350/1251] eta: 0:09:35 lr: 0.000284 loss: 3.1337 (3.0772) grad_norm: 1.8057 (1.9630) time: 0.6270 [2021-03-27 18:47:44 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 360/1251] eta: 0:09:28 lr: 0.000284 loss: 3.1230 (3.0735) grad_norm: 1.9833 (1.9625) time: 0.6268 [2021-03-27 18:47:50 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 370/1251] eta: 0:09:21 lr: 0.000284 loss: 3.1230 (3.0796) grad_norm: 1.8268 (1.9615) time: 0.6232 [2021-03-27 18:47:56 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 380/1251] eta: 0:09:15 lr: 0.000283 loss: 3.2102 (3.0775) grad_norm: 1.8228 (1.9608) time: 0.6238 [2021-03-27 18:48:02 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 390/1251] eta: 0:09:08 lr: 0.000283 loss: 2.8629 (3.0743) grad_norm: 1.8275 (1.9588) time: 0.6214 [2021-03-27 18:48:09 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 400/1251] eta: 0:09:01 lr: 0.000283 loss: 2.8629 (3.0722) grad_norm: 1.8275 (1.9583) time: 0.6216 [2021-03-27 18:48:15 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 410/1251] eta: 0:08:55 lr: 0.000283 loss: 3.1018 (3.0714) grad_norm: 2.0363 (1.9615) time: 0.6251 [2021-03-27 18:48:21 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 420/1251] eta: 0:08:48 lr: 0.000283 loss: 3.3414 (3.0730) grad_norm: 1.9785 (1.9658) time: 0.6277 [2021-03-27 18:48:27 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 430/1251] eta: 0:08:42 lr: 0.000283 loss: 3.3716 (3.0720) grad_norm: 1.8462 (1.9643) time: 0.6287 [2021-03-27 18:48:34 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 440/1251] eta: 0:08:35 lr: 0.000283 loss: 3.1622 (3.0737) grad_norm: 1.9406 (1.9637) time: 0.6305 [2021-03-27 18:48:40 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 450/1251] eta: 0:08:29 lr: 0.000283 loss: 3.1868 (3.0790) grad_norm: 1.8231 (1.9592) time: 0.6305 [2021-03-27 18:48:46 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 460/1251] eta: 0:08:22 lr: 0.000283 loss: 3.1475 (3.0752) grad_norm: 1.7965 (1.9574) time: 0.6269 [2021-03-27 18:48:52 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 470/1251] eta: 0:08:16 lr: 0.000283 loss: 3.0208 (3.0697) grad_norm: 1.7965 (1.9560) time: 0.6233 [2021-03-27 18:48:59 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 480/1251] eta: 0:08:09 lr: 0.000283 loss: 3.0956 (3.0740) grad_norm: 1.8969 (1.9567) time: 0.6233 [2021-03-27 18:49:05 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 490/1251] eta: 0:08:03 lr: 0.000283 loss: 3.2705 (3.0806) grad_norm: 1.8969 (1.9563) time: 0.6297 [2021-03-27 18:49:11 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 500/1251] eta: 0:07:56 lr: 0.000283 loss: 3.1103 (3.0720) grad_norm: 1.8916 (1.9573) time: 0.6301 [2021-03-27 18:49:18 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 510/1251] eta: 0:07:50 lr: 0.000283 loss: 2.8984 (3.0727) grad_norm: 1.9899 (1.9585) time: 0.6271 [2021-03-27 18:49:24 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 520/1251] eta: 0:07:43 lr: 0.000283 loss: 3.1186 (3.0710) grad_norm: 2.0218 (1.9615) time: 0.6271 [2021-03-27 18:49:30 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 530/1251] eta: 0:07:37 lr: 0.000283 loss: 3.0101 (3.0720) grad_norm: 1.9511 (1.9612) time: 0.6232 [2021-03-27 18:49:36 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 540/1251] eta: 0:07:30 lr: 0.000283 loss: 3.1861 (3.0755) grad_norm: 1.9198 (1.9645) time: 0.6259 [2021-03-27 18:49:43 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 550/1251] eta: 0:07:24 lr: 0.000283 loss: 3.3186 (3.0765) grad_norm: 1.9380 (1.9667) time: 0.6401 [2021-03-27 18:49:49 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 560/1251] eta: 0:07:18 lr: 0.000283 loss: 3.3580 (3.0819) grad_norm: 1.9062 (1.9678) time: 0.6398 [2021-03-27 18:49:56 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 570/1251] eta: 0:07:11 lr: 0.000283 loss: 3.2507 (3.0830) grad_norm: 1.7982 (1.9663) time: 0.6334 [2021-03-27 18:50:02 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 580/1251] eta: 0:07:05 lr: 0.000283 loss: 3.1774 (3.0837) grad_norm: 1.8047 (1.9656) time: 0.6334 [2021-03-27 18:50:08 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 590/1251] eta: 0:06:59 lr: 0.000283 loss: 3.1903 (3.0865) grad_norm: 1.9784 (1.9689) time: 0.6307 [2021-03-27 18:50:14 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 600/1251] eta: 0:06:52 lr: 0.000283 loss: 3.1903 (3.0868) grad_norm: 1.9784 (1.9690) time: 0.6278 [2021-03-27 18:50:21 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 610/1251] eta: 0:06:46 lr: 0.000283 loss: 3.1189 (3.0815) grad_norm: 1.9598 (1.9685) time: 0.6252 [2021-03-27 18:50:27 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 620/1251] eta: 0:06:39 lr: 0.000283 loss: 2.9195 (3.0802) grad_norm: 1.9598 (1.9687) time: 0.6219 [2021-03-27 18:50:33 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 630/1251] eta: 0:06:33 lr: 0.000283 loss: 3.0681 (3.0811) grad_norm: 1.9680 (1.9697) time: 0.6213 [2021-03-27 18:50:39 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 640/1251] eta: 0:06:27 lr: 0.000283 loss: 2.9232 (3.0761) grad_norm: 1.9753 (1.9733) time: 0.6271 [2021-03-27 18:50:46 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 650/1251] eta: 0:06:20 lr: 0.000282 loss: 3.1894 (3.0827) grad_norm: 1.9187 (1.9767) time: 0.6308 [2021-03-27 18:50:52 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 660/1251] eta: 0:06:14 lr: 0.000282 loss: 3.3005 (3.0822) grad_norm: 1.9187 (1.9792) time: 0.6315 [2021-03-27 18:50:58 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 670/1251] eta: 0:06:07 lr: 0.000282 loss: 2.9509 (3.0790) grad_norm: 1.9870 (1.9819) time: 0.6283 [2021-03-27 18:51:05 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 680/1251] eta: 0:06:01 lr: 0.000282 loss: 2.7499 (3.0764) grad_norm: 1.8950 (1.9803) time: 0.6279 [2021-03-27 18:51:11 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 690/1251] eta: 0:05:55 lr: 0.000282 loss: 3.0902 (3.0765) grad_norm: 1.9065 (1.9796) time: 0.6284 [2021-03-27 18:51:17 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 700/1251] eta: 0:05:48 lr: 0.000282 loss: 3.1479 (3.0765) grad_norm: 1.9468 (1.9810) time: 0.6313 [2021-03-27 18:51:24 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 710/1251] eta: 0:05:42 lr: 0.000282 loss: 3.1181 (3.0780) grad_norm: 1.9468 (1.9823) time: 0.6366 [2021-03-27 18:51:30 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 720/1251] eta: 0:05:36 lr: 0.000282 loss: 3.1141 (3.0774) grad_norm: 1.9377 (1.9815) time: 0.6342 [2021-03-27 18:51:36 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 730/1251] eta: 0:05:29 lr: 0.000282 loss: 3.1235 (3.0784) grad_norm: 1.8769 (1.9827) time: 0.6342 [2021-03-27 18:51:43 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 740/1251] eta: 0:05:23 lr: 0.000282 loss: 3.2250 (3.0830) grad_norm: 1.8660 (1.9839) time: 0.6351 [2021-03-27 18:51:49 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 750/1251] eta: 0:05:17 lr: 0.000282 loss: 3.2535 (3.0864) grad_norm: 1.9960 (1.9841) time: 0.6308 [2021-03-27 18:51:55 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 760/1251] eta: 0:05:10 lr: 0.000282 loss: 3.3031 (3.0867) grad_norm: 2.0803 (1.9863) time: 0.6323 [2021-03-27 18:52:02 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 770/1251] eta: 0:05:04 lr: 0.000282 loss: 3.1408 (3.0842) grad_norm: 2.0535 (1.9863) time: 0.6372 [2021-03-27 18:52:08 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 780/1251] eta: 0:04:58 lr: 0.000282 loss: 3.2214 (3.0842) grad_norm: 1.9680 (1.9863) time: 0.6320 [2021-03-27 18:52:14 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 790/1251] eta: 0:04:51 lr: 0.000282 loss: 3.2640 (3.0845) grad_norm: 1.9173 (1.9857) time: 0.6250 [2021-03-27 18:52:20 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 800/1251] eta: 0:04:45 lr: 0.000282 loss: 3.2679 (3.0842) grad_norm: 1.9037 (1.9869) time: 0.6232 [2021-03-27 18:52:27 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 810/1251] eta: 0:04:39 lr: 0.000282 loss: 3.1419 (3.0832) grad_norm: 2.0182 (1.9884) time: 0.6253 [2021-03-27 18:52:33 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 820/1251] eta: 0:04:32 lr: 0.000282 loss: 3.0979 (3.0835) grad_norm: 1.9952 (1.9876) time: 0.6239 [2021-03-27 18:52:39 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 830/1251] eta: 0:04:26 lr: 0.000282 loss: 2.8682 (3.0800) grad_norm: 1.9496 (1.9886) time: 0.6202 [2021-03-27 18:52:45 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 840/1251] eta: 0:04:19 lr: 0.000282 loss: 2.9755 (3.0799) grad_norm: 2.0367 (1.9891) time: 0.6213 [2021-03-27 18:52:52 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 850/1251] eta: 0:04:13 lr: 0.000282 loss: 2.9755 (3.0778) grad_norm: 1.9274 (1.9887) time: 0.6240 [2021-03-27 18:52:58 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 860/1251] eta: 0:04:07 lr: 0.000282 loss: 2.9409 (3.0764) grad_norm: 1.8401 (1.9864) time: 0.6237 [2021-03-27 18:53:04 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 870/1251] eta: 0:04:00 lr: 0.000282 loss: 2.8437 (3.0701) grad_norm: 1.7715 (1.9847) time: 0.6272 [2021-03-27 18:53:10 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 880/1251] eta: 0:03:54 lr: 0.000282 loss: 2.8437 (3.0717) grad_norm: 1.8562 (1.9841) time: 0.6335 [2021-03-27 18:53:17 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 890/1251] eta: 0:03:48 lr: 0.000282 loss: 2.9151 (3.0674) grad_norm: 1.8823 (1.9852) time: 0.6311 [2021-03-27 18:53:23 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 900/1251] eta: 0:03:41 lr: 0.000282 loss: 3.0964 (3.0697) grad_norm: 1.8800 (1.9841) time: 0.6321 [2021-03-27 18:53:29 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 910/1251] eta: 0:03:35 lr: 0.000282 loss: 3.2427 (3.0682) grad_norm: 1.9378 (1.9874) time: 0.6294 [2021-03-27 18:53:36 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 920/1251] eta: 0:03:29 lr: 0.000281 loss: 3.1242 (3.0693) grad_norm: 1.9378 (1.9865) time: 0.6229 [2021-03-27 18:53:42 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 930/1251] eta: 0:03:22 lr: 0.000281 loss: 3.3177 (3.0723) grad_norm: 1.8528 (1.9856) time: 0.6272 [2021-03-27 18:53:48 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 940/1251] eta: 0:03:16 lr: 0.000281 loss: 3.2419 (3.0713) grad_norm: 1.9176 (1.9902) time: 0.6268 [2021-03-27 18:53:54 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 950/1251] eta: 0:03:10 lr: 0.000281 loss: 2.9617 (3.0705) grad_norm: 2.0458 (1.9941) time: 0.6247 [2021-03-27 18:54:01 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 960/1251] eta: 0:03:03 lr: 0.000281 loss: 3.0265 (3.0705) grad_norm: 1.9714 (1.9935) time: 0.6268 [2021-03-27 18:54:07 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 970/1251] eta: 0:02:57 lr: 0.000281 loss: 3.2640 (3.0732) grad_norm: 1.9366 (1.9926) time: 0.6237 [2021-03-27 18:54:13 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 980/1251] eta: 0:02:51 lr: 0.000281 loss: 3.2474 (3.0744) grad_norm: 1.9074 (1.9921) time: 0.6229 [2021-03-27 18:54:19 swin_base_patch4_window7_224] INFO: Epoch: [194] [ 990/1251] eta: 0:02:44 lr: 0.000281 loss: 3.0888 (3.0740) grad_norm: 1.8585 (1.9906) time: 0.6236 [2021-03-27 18:54:26 swin_base_patch4_window7_224] INFO: Epoch: [194] [1000/1251] eta: 0:02:38 lr: 0.000281 loss: 3.1149 (3.0736) grad_norm: 1.7724 (1.9899) time: 0.6248 [2021-03-27 18:54:32 swin_base_patch4_window7_224] INFO: Epoch: [194] [1010/1251] eta: 0:02:32 lr: 0.000281 loss: 3.1515 (3.0746) grad_norm: 1.7915 (1.9895) time: 0.6288 [2021-03-27 18:54:38 swin_base_patch4_window7_224] INFO: Epoch: [194] [1020/1251] eta: 0:02:25 lr: 0.000281 loss: 3.0727 (3.0733) grad_norm: 1.9130 (1.9901) time: 0.6286 [2021-03-27 18:54:44 swin_base_patch4_window7_224] INFO: Epoch: [194] [1030/1251] eta: 0:02:19 lr: 0.000281 loss: 3.0727 (3.0738) grad_norm: 1.8446 (1.9878) time: 0.6240 [2021-03-27 18:54:51 swin_base_patch4_window7_224] INFO: Epoch: [194] [1040/1251] eta: 0:02:13 lr: 0.000281 loss: 3.1243 (3.0741) grad_norm: 1.8211 (1.9866) time: 0.6303 [2021-03-27 18:54:57 swin_base_patch4_window7_224] INFO: Epoch: [194] [1050/1251] eta: 0:02:06 lr: 0.000281 loss: 3.1362 (3.0746) grad_norm: 1.8537 (1.9858) time: 0.6351 [2021-03-27 18:55:03 swin_base_patch4_window7_224] INFO: Epoch: [194] [1060/1251] eta: 0:02:00 lr: 0.000281 loss: 3.1362 (3.0743) grad_norm: 1.8135 (1.9862) time: 0.6275 [2021-03-27 18:55:10 swin_base_patch4_window7_224] INFO: Epoch: [194] [1070/1251] eta: 0:01:54 lr: 0.000281 loss: 3.2730 (3.0757) grad_norm: 1.9339 (1.9885) time: 0.6330 [2021-03-27 18:55:16 swin_base_patch4_window7_224] INFO: Epoch: [194] [1080/1251] eta: 0:01:47 lr: 0.000281 loss: 2.8812 (3.0740) grad_norm: 1.9339 (1.9886) time: 0.6323 [2021-03-27 18:55:22 swin_base_patch4_window7_224] INFO: Epoch: [194] [1090/1251] eta: 0:01:41 lr: 0.000281 loss: 2.8513 (3.0721) grad_norm: 2.1340 (1.9907) time: 0.6209 [2021-03-27 18:55:28 swin_base_patch4_window7_224] INFO: Epoch: [194] [1100/1251] eta: 0:01:35 lr: 0.000281 loss: 2.9389 (3.0700) grad_norm: 2.1143 (1.9901) time: 0.6225 [2021-03-27 18:55:35 swin_base_patch4_window7_224] INFO: Epoch: [194] [1110/1251] eta: 0:01:28 lr: 0.000281 loss: 2.9172 (3.0686) grad_norm: 1.8879 (1.9885) time: 0.6235 [2021-03-27 18:55:41 swin_base_patch4_window7_224] INFO: Epoch: [194] [1120/1251] eta: 0:01:22 lr: 0.000281 loss: 3.1397 (3.0708) grad_norm: 1.9843 (1.9894) time: 0.6207 [2021-03-27 18:55:47 swin_base_patch4_window7_224] INFO: Epoch: [194] [1130/1251] eta: 0:01:16 lr: 0.000281 loss: 3.3004 (3.0708) grad_norm: 1.9704 (1.9881) time: 0.6206 [2021-03-27 18:55:53 swin_base_patch4_window7_224] INFO: Epoch: [194] [1140/1251] eta: 0:01:10 lr: 0.000281 loss: 3.2159 (3.0710) grad_norm: 1.8009 (1.9866) time: 0.6210 [2021-03-27 18:56:00 swin_base_patch4_window7_224] INFO: Epoch: [194] [1150/1251] eta: 0:01:03 lr: 0.000281 loss: 2.9588 (3.0696) grad_norm: 1.8664 (1.9881) time: 0.6238 [2021-03-27 18:56:06 swin_base_patch4_window7_224] INFO: Epoch: [194] [1160/1251] eta: 0:00:57 lr: 0.000281 loss: 3.1149 (3.0714) grad_norm: 1.9547 (1.9880) time: 0.6248 [2021-03-27 18:56:12 swin_base_patch4_window7_224] INFO: Epoch: [194] [1170/1251] eta: 0:00:51 lr: 0.000281 loss: 3.1814 (3.0708) grad_norm: 1.9028 (1.9877) time: 0.6218 [2021-03-27 18:56:18 swin_base_patch4_window7_224] INFO: Epoch: [194] [1180/1251] eta: 0:00:44 lr: 0.000281 loss: 3.1554 (3.0707) grad_norm: 1.7896 (1.9866) time: 0.6210 [2021-03-27 18:56:24 swin_base_patch4_window7_224] INFO: Epoch: [194] [1190/1251] eta: 0:00:38 lr: 0.000280 loss: 3.1554 (3.0706) grad_norm: 1.7676 (1.9862) time: 0.6226 [2021-03-27 18:56:31 swin_base_patch4_window7_224] INFO: Epoch: [194] [1200/1251] eta: 0:00:32 lr: 0.000280 loss: 2.9875 (3.0705) grad_norm: 1.8163 (1.9858) time: 0.6213 [2021-03-27 18:56:37 swin_base_patch4_window7_224] INFO: Epoch: [194] [1210/1251] eta: 0:00:25 lr: 0.000280 loss: 2.7091 (3.0666) grad_norm: 1.8089 (1.9842) time: 0.6205 [2021-03-27 18:56:43 swin_base_patch4_window7_224] INFO: Epoch: [194] [1220/1251] eta: 0:00:19 lr: 0.000280 loss: 2.6938 (3.0661) grad_norm: 1.7907 (1.9836) time: 0.6216 [2021-03-27 18:56:49 swin_base_patch4_window7_224] INFO: Epoch: [194] [1230/1251] eta: 0:00:13 lr: 0.000280 loss: 2.8522 (3.0644) grad_norm: 1.9216 (1.9855) time: 0.6281 [2021-03-27 18:56:56 swin_base_patch4_window7_224] INFO: Epoch: [194] [1240/1251] eta: 0:00:06 lr: 0.000280 loss: 3.0571 (3.0637) grad_norm: 2.0817 (1.9866) time: 0.6318 [2021-03-27 18:57:02 swin_base_patch4_window7_224] INFO: Epoch: [194] [1250/1251] eta: 0:00:00 lr: 0.000280 loss: 3.2550 (3.0665) grad_norm: 2.0314 (1.9868) time: 0.6235 [2021-03-27 18:57:10 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:46 loss: 0.9764 (0.9764) acc1: 75.0000 (75.0000) acc5: 96.8750 (96.8750) [2021-03-27 18:57:13 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9387 (0.9196) acc1: 81.2500 (78.5511) acc5: 96.8750 (95.5966) [2021-03-27 18:57:15 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8843 (0.8752) acc1: 81.2500 (78.8690) acc5: 95.3125 (95.6101) [2021-03-27 18:57:17 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7937 (0.8456) acc1: 81.2500 (79.6371) acc5: 96.8750 (95.8165) [2021-03-27 18:57:19 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7868 (0.8381) acc1: 81.2500 (80.2973) acc5: 96.8750 (95.7698) [2021-03-27 18:57:20 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7937 (0.8359) acc1: 81.2500 (80.3520) acc5: 95.3125 (95.6800) [2021-03-27 18:57:29 swin_base_patch4_window7_224] INFO: * Acc@1 80.908 Acc@5 95.730 loss 0.820 [2021-03-27 18:57:29 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.9% [2021-03-27 18:57:29 swin_base_patch4_window7_224] INFO: Max accuracy: 80.91% [2021-03-27 18:57:33 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 0/1251] eta: 1:30:01 lr: 0.000280 loss: 3.4703 (3.4703) grad_norm: 1.8394 (1.8394) time: 4.3180 [2021-03-27 18:57:40 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 10/1251] eta: 0:19:54 lr: 0.000280 loss: 3.0531 (3.0749) grad_norm: 1.9906 (2.0063) time: 0.9629 [2021-03-27 18:57:46 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 20/1251] eta: 0:16:28 lr: 0.000280 loss: 3.0531 (3.0077) grad_norm: 1.9507 (1.9461) time: 0.6273 [2021-03-27 18:57:52 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 30/1251] eta: 0:15:08 lr: 0.000280 loss: 3.0069 (2.9674) grad_norm: 1.8590 (1.9125) time: 0.6236 [2021-03-27 18:57:58 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 40/1251] eta: 0:14:29 lr: 0.000280 loss: 3.0589 (3.0145) grad_norm: 1.8590 (1.9188) time: 0.6292 [2021-03-27 18:58:05 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 50/1251] eta: 0:14:01 lr: 0.000280 loss: 3.1944 (3.0233) grad_norm: 1.8683 (1.9121) time: 0.6336 [2021-03-27 18:58:11 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 60/1251] eta: 0:13:40 lr: 0.000280 loss: 3.2531 (3.0898) grad_norm: 1.8683 (1.9298) time: 0.6300 [2021-03-27 18:58:17 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 70/1251] eta: 0:13:22 lr: 0.000280 loss: 3.2887 (3.0880) grad_norm: 1.8066 (1.9389) time: 0.6265 [2021-03-27 18:58:24 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 80/1251] eta: 0:13:07 lr: 0.000280 loss: 2.9978 (3.0455) grad_norm: 1.8208 (1.9461) time: 0.6220 [2021-03-27 18:58:30 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 90/1251] eta: 0:12:55 lr: 0.000280 loss: 2.8686 (3.0293) grad_norm: 1.7984 (1.9322) time: 0.6246 [2021-03-27 18:58:36 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 100/1251] eta: 0:12:44 lr: 0.000280 loss: 3.1154 (3.0440) grad_norm: 1.7869 (1.9257) time: 0.6295 [2021-03-27 18:58:42 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 110/1251] eta: 0:12:33 lr: 0.000280 loss: 3.2575 (3.0698) grad_norm: 1.8401 (1.9202) time: 0.6278 [2021-03-27 18:58:49 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 120/1251] eta: 0:12:23 lr: 0.000280 loss: 3.3029 (3.0771) grad_norm: 1.8587 (1.9271) time: 0.6244 [2021-03-27 18:58:55 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 130/1251] eta: 0:12:15 lr: 0.000280 loss: 3.2193 (3.0826) grad_norm: 1.8938 (1.9345) time: 0.6291 [2021-03-27 18:59:01 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 140/1251] eta: 0:12:06 lr: 0.000280 loss: 3.2193 (3.0806) grad_norm: 1.8938 (1.9385) time: 0.6287 [2021-03-27 18:59:07 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 150/1251] eta: 0:11:57 lr: 0.000280 loss: 3.2247 (3.0965) grad_norm: 1.9294 (1.9467) time: 0.6279 [2021-03-27 18:59:14 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 160/1251] eta: 0:11:49 lr: 0.000280 loss: 3.1843 (3.0937) grad_norm: 1.8524 (1.9381) time: 0.6309 [2021-03-27 18:59:20 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 170/1251] eta: 0:11:41 lr: 0.000280 loss: 2.9982 (3.0748) grad_norm: 1.7826 (1.9376) time: 0.6295 [2021-03-27 18:59:26 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 180/1251] eta: 0:11:34 lr: 0.000280 loss: 2.8697 (3.0771) grad_norm: 1.8095 (1.9374) time: 0.6276 [2021-03-27 18:59:33 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 190/1251] eta: 0:11:26 lr: 0.000280 loss: 3.0401 (3.0685) grad_norm: 1.8095 (1.9537) time: 0.6253 [2021-03-27 18:59:39 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 200/1251] eta: 0:11:19 lr: 0.000280 loss: 3.1521 (3.0798) grad_norm: 1.9123 (1.9548) time: 0.6279 [2021-03-27 18:59:45 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 210/1251] eta: 0:11:11 lr: 0.000279 loss: 3.2860 (3.0891) grad_norm: 1.9518 (1.9561) time: 0.6263 [2021-03-27 18:59:51 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 220/1251] eta: 0:11:03 lr: 0.000279 loss: 3.2350 (3.0931) grad_norm: 1.9708 (1.9652) time: 0.6208 [2021-03-27 18:59:58 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 230/1251] eta: 0:10:56 lr: 0.000279 loss: 3.2165 (3.0911) grad_norm: 1.9809 (1.9659) time: 0.6225 [2021-03-27 19:00:04 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 240/1251] eta: 0:10:49 lr: 0.000279 loss: 3.2165 (3.0853) grad_norm: 1.9226 (1.9637) time: 0.6287 [2021-03-27 19:00:10 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 250/1251] eta: 0:10:42 lr: 0.000279 loss: 3.2596 (3.0858) grad_norm: 1.8373 (1.9607) time: 0.6302 [2021-03-27 19:00:17 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 260/1251] eta: 0:10:36 lr: 0.000279 loss: 3.2043 (3.0842) grad_norm: 1.8294 (1.9539) time: 0.6345 [2021-03-27 19:00:23 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 270/1251] eta: 0:10:29 lr: 0.000279 loss: 3.1167 (3.0817) grad_norm: 1.8294 (1.9522) time: 0.6363 [2021-03-27 19:00:29 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 280/1251] eta: 0:10:22 lr: 0.000279 loss: 3.1368 (3.0902) grad_norm: 1.8585 (1.9506) time: 0.6254 [2021-03-27 19:00:35 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 290/1251] eta: 0:10:15 lr: 0.000279 loss: 3.1975 (3.0897) grad_norm: 1.9523 (1.9622) time: 0.6240 [2021-03-27 19:00:42 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 300/1251] eta: 0:10:08 lr: 0.000279 loss: 3.0359 (3.0831) grad_norm: 2.0598 (1.9665) time: 0.6288 [2021-03-27 19:00:48 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 310/1251] eta: 0:10:01 lr: 0.000279 loss: 3.0523 (3.0863) grad_norm: 1.9467 (1.9724) time: 0.6273 [2021-03-27 19:00:54 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 320/1251] eta: 0:09:55 lr: 0.000279 loss: 3.2623 (3.0885) grad_norm: 2.0944 (1.9758) time: 0.6271 [2021-03-27 19:01:01 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 330/1251] eta: 0:09:48 lr: 0.000279 loss: 3.1299 (3.0901) grad_norm: 1.9735 (1.9733) time: 0.6299 [2021-03-27 19:01:07 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 340/1251] eta: 0:09:41 lr: 0.000279 loss: 3.1258 (3.0881) grad_norm: 1.8746 (1.9767) time: 0.6290 [2021-03-27 19:01:13 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 350/1251] eta: 0:09:34 lr: 0.000279 loss: 3.1309 (3.0835) grad_norm: 1.9350 (1.9778) time: 0.6254 [2021-03-27 19:01:19 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 360/1251] eta: 0:09:28 lr: 0.000279 loss: 2.8525 (3.0747) grad_norm: 1.9899 (1.9766) time: 0.6242 [2021-03-27 19:01:26 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 370/1251] eta: 0:09:21 lr: 0.000279 loss: 2.8219 (3.0762) grad_norm: 1.9953 (1.9753) time: 0.6258 [2021-03-27 19:01:32 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 380/1251] eta: 0:09:15 lr: 0.000279 loss: 3.3843 (3.0841) grad_norm: 1.9953 (1.9835) time: 0.6270 [2021-03-27 19:01:38 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 390/1251] eta: 0:09:08 lr: 0.000279 loss: 3.3004 (3.0811) grad_norm: 1.9747 (1.9837) time: 0.6246 [2021-03-27 19:01:44 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 400/1251] eta: 0:09:01 lr: 0.000279 loss: 3.1842 (3.0866) grad_norm: 1.9314 (1.9812) time: 0.6278 [2021-03-27 19:01:51 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 410/1251] eta: 0:08:55 lr: 0.000279 loss: 3.4232 (3.0915) grad_norm: 1.8954 (1.9777) time: 0.6324 [2021-03-27 19:01:57 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 420/1251] eta: 0:08:48 lr: 0.000279 loss: 2.9776 (3.0880) grad_norm: 1.8092 (1.9758) time: 0.6289 [2021-03-27 19:02:03 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 430/1251] eta: 0:08:42 lr: 0.000279 loss: 2.9776 (3.0926) grad_norm: 1.8208 (1.9751) time: 0.6292 [2021-03-27 19:02:10 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 440/1251] eta: 0:08:35 lr: 0.000279 loss: 3.2467 (3.0892) grad_norm: 1.9494 (1.9749) time: 0.6329 [2021-03-27 19:02:16 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 450/1251] eta: 0:08:29 lr: 0.000279 loss: 2.8664 (3.0870) grad_norm: 1.9590 (1.9739) time: 0.6300 [2021-03-27 19:02:22 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 460/1251] eta: 0:08:22 lr: 0.000279 loss: 3.1675 (3.0887) grad_norm: 1.8703 (1.9748) time: 0.6274 [2021-03-27 19:02:28 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 470/1251] eta: 0:08:16 lr: 0.000279 loss: 3.1734 (3.0885) grad_norm: 1.8899 (1.9831) time: 0.6254 [2021-03-27 19:02:35 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 480/1251] eta: 0:08:09 lr: 0.000279 loss: 3.2446 (3.0922) grad_norm: 1.9824 (1.9826) time: 0.6229 [2021-03-27 19:02:41 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 490/1251] eta: 0:08:03 lr: 0.000278 loss: 3.1740 (3.0887) grad_norm: 1.9567 (1.9834) time: 0.6273 [2021-03-27 19:02:47 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 500/1251] eta: 0:07:56 lr: 0.000278 loss: 3.1201 (3.0924) grad_norm: 1.8924 (1.9819) time: 0.6306 [2021-03-27 19:02:54 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 510/1251] eta: 0:07:50 lr: 0.000278 loss: 3.2477 (3.0921) grad_norm: 1.8004 (1.9814) time: 0.6319 [2021-03-27 19:03:00 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 520/1251] eta: 0:07:44 lr: 0.000278 loss: 3.0874 (3.0928) grad_norm: 1.7731 (1.9796) time: 0.6326 [2021-03-27 19:03:06 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 530/1251] eta: 0:07:37 lr: 0.000278 loss: 3.0817 (3.0931) grad_norm: 1.8395 (1.9778) time: 0.6299 [2021-03-27 19:03:13 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 540/1251] eta: 0:07:31 lr: 0.000278 loss: 3.1737 (3.0902) grad_norm: 1.7963 (1.9749) time: 0.6277 [2021-03-27 19:03:19 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 550/1251] eta: 0:07:24 lr: 0.000278 loss: 3.0636 (3.0899) grad_norm: 1.8722 (1.9764) time: 0.6314 [2021-03-27 19:03:25 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 560/1251] eta: 0:07:18 lr: 0.000278 loss: 3.1969 (3.0908) grad_norm: 1.9985 (1.9775) time: 0.6352 [2021-03-27 19:03:32 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 570/1251] eta: 0:07:12 lr: 0.000278 loss: 3.1003 (3.0886) grad_norm: 1.8843 (1.9753) time: 0.6381 [2021-03-27 19:03:38 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 580/1251] eta: 0:07:05 lr: 0.000278 loss: 2.9418 (3.0836) grad_norm: 1.8696 (1.9760) time: 0.6335 [2021-03-27 19:03:44 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 590/1251] eta: 0:06:59 lr: 0.000278 loss: 3.3878 (3.0908) grad_norm: 2.0294 (1.9785) time: 0.6281 [2021-03-27 19:03:51 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 600/1251] eta: 0:06:53 lr: 0.000278 loss: 3.2996 (3.0860) grad_norm: 1.9340 (1.9757) time: 0.6312 [2021-03-27 19:03:57 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 610/1251] eta: 0:06:46 lr: 0.000278 loss: 2.7274 (3.0830) grad_norm: 1.9061 (1.9752) time: 0.6300 [2021-03-27 19:04:03 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 620/1251] eta: 0:06:40 lr: 0.000278 loss: 3.2536 (3.0861) grad_norm: 1.9183 (1.9761) time: 0.6301 [2021-03-27 19:04:09 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 630/1251] eta: 0:06:33 lr: 0.000278 loss: 3.3673 (3.0893) grad_norm: 1.9183 (1.9766) time: 0.6311 [2021-03-27 19:04:16 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 640/1251] eta: 0:06:27 lr: 0.000278 loss: 3.1790 (3.0911) grad_norm: 1.8776 (1.9745) time: 0.6286 [2021-03-27 19:04:22 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 650/1251] eta: 0:06:21 lr: 0.000278 loss: 3.2405 (3.0925) grad_norm: 1.8483 (1.9749) time: 0.6258 [2021-03-27 19:04:28 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 660/1251] eta: 0:06:14 lr: 0.000278 loss: 3.2405 (3.0916) grad_norm: 1.9291 (1.9741) time: 0.6303 [2021-03-27 19:04:35 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 670/1251] eta: 0:06:08 lr: 0.000278 loss: 3.1857 (3.0921) grad_norm: 1.9300 (1.9733) time: 0.6340 [2021-03-27 19:04:41 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 680/1251] eta: 0:06:01 lr: 0.000278 loss: 3.2793 (3.0959) grad_norm: 1.9720 (1.9789) time: 0.6271 [2021-03-27 19:04:47 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 690/1251] eta: 0:05:55 lr: 0.000278 loss: 3.2793 (3.0969) grad_norm: 1.9520 (1.9792) time: 0.6316 [2021-03-27 19:04:54 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 700/1251] eta: 0:05:49 lr: 0.000278 loss: 3.0088 (3.0931) grad_norm: 1.9372 (1.9790) time: 0.6385 [2021-03-27 19:05:00 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 710/1251] eta: 0:05:43 lr: 0.000278 loss: 2.9497 (3.0917) grad_norm: 1.9372 (1.9772) time: 0.6340 [2021-03-27 19:05:06 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 720/1251] eta: 0:05:36 lr: 0.000278 loss: 2.9696 (3.0921) grad_norm: 1.7954 (1.9763) time: 0.6275 [2021-03-27 19:05:12 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 730/1251] eta: 0:05:30 lr: 0.000278 loss: 3.1801 (3.0942) grad_norm: 1.7888 (1.9765) time: 0.6272 [2021-03-27 19:05:19 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 740/1251] eta: 0:05:23 lr: 0.000278 loss: 3.2807 (3.0958) grad_norm: 1.9130 (1.9763) time: 0.6283 [2021-03-27 19:05:25 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 750/1251] eta: 0:05:17 lr: 0.000278 loss: 3.4286 (3.0998) grad_norm: 1.8946 (1.9752) time: 0.6314 [2021-03-27 19:05:31 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 760/1251] eta: 0:05:11 lr: 0.000277 loss: 3.3326 (3.0997) grad_norm: 1.7843 (1.9734) time: 0.6371 [2021-03-27 19:05:38 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 770/1251] eta: 0:05:04 lr: 0.000277 loss: 3.1269 (3.0991) grad_norm: 1.8265 (1.9743) time: 0.6386 [2021-03-27 19:05:44 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 780/1251] eta: 0:04:58 lr: 0.000277 loss: 3.3398 (3.1011) grad_norm: 1.9050 (1.9734) time: 0.6357 [2021-03-27 19:05:50 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 790/1251] eta: 0:04:52 lr: 0.000277 loss: 3.3330 (3.1023) grad_norm: 1.8442 (1.9728) time: 0.6304 [2021-03-27 19:05:57 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 800/1251] eta: 0:04:45 lr: 0.000277 loss: 3.0134 (3.0981) grad_norm: 1.8490 (1.9728) time: 0.6298 [2021-03-27 19:06:03 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 810/1251] eta: 0:04:39 lr: 0.000277 loss: 2.9904 (3.0979) grad_norm: 1.8523 (1.9732) time: 0.6276 [2021-03-27 19:06:09 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 820/1251] eta: 0:04:33 lr: 0.000277 loss: 3.2616 (3.0980) grad_norm: 1.9068 (1.9746) time: 0.6241 [2021-03-27 19:06:15 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 830/1251] eta: 0:04:26 lr: 0.000277 loss: 3.0981 (3.0970) grad_norm: 1.8095 (1.9728) time: 0.6210 [2021-03-27 19:06:22 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 840/1251] eta: 0:04:20 lr: 0.000277 loss: 3.1710 (3.0981) grad_norm: 1.7860 (1.9733) time: 0.6184 [2021-03-27 19:06:28 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 850/1251] eta: 0:04:13 lr: 0.000277 loss: 3.1938 (3.0966) grad_norm: 1.9012 (1.9728) time: 0.6196 [2021-03-27 19:06:34 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 860/1251] eta: 0:04:07 lr: 0.000277 loss: 2.7758 (3.0934) grad_norm: 1.8359 (1.9724) time: 0.6260 [2021-03-27 19:06:41 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 870/1251] eta: 0:04:01 lr: 0.000277 loss: 2.7853 (3.0915) grad_norm: 1.8044 (1.9706) time: 0.6319 [2021-03-27 19:06:47 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 880/1251] eta: 0:03:54 lr: 0.000277 loss: 2.9577 (3.0908) grad_norm: 1.7847 (1.9705) time: 0.6280 [2021-03-27 19:06:53 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 890/1251] eta: 0:03:48 lr: 0.000277 loss: 3.0954 (3.0902) grad_norm: 1.8261 (1.9706) time: 0.6240 [2021-03-27 19:06:59 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 900/1251] eta: 0:03:42 lr: 0.000277 loss: 3.0451 (3.0879) grad_norm: 1.9129 (1.9710) time: 0.6262 [2021-03-27 19:07:05 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 910/1251] eta: 0:03:35 lr: 0.000277 loss: 3.1161 (3.0899) grad_norm: 1.8803 (1.9707) time: 0.6250 [2021-03-27 19:07:12 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 920/1251] eta: 0:03:29 lr: 0.000277 loss: 3.1584 (3.0902) grad_norm: 1.8803 (1.9702) time: 0.6192 [2021-03-27 19:07:18 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 930/1251] eta: 0:03:22 lr: 0.000277 loss: 3.2894 (3.0923) grad_norm: 1.8709 (1.9693) time: 0.6214 [2021-03-27 19:07:24 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 940/1251] eta: 0:03:16 lr: 0.000277 loss: 3.2894 (3.0930) grad_norm: 1.8976 (1.9690) time: 0.6255 [2021-03-27 19:07:31 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 950/1251] eta: 0:03:10 lr: 0.000277 loss: 3.1695 (3.0938) grad_norm: 1.8976 (1.9691) time: 0.6338 [2021-03-27 19:07:37 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 960/1251] eta: 0:03:04 lr: 0.000277 loss: 3.1551 (3.0930) grad_norm: 1.8504 (1.9683) time: 0.6359 [2021-03-27 19:07:43 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 970/1251] eta: 0:02:57 lr: 0.000277 loss: 3.1741 (3.0948) grad_norm: 1.9296 (1.9678) time: 0.6258 [2021-03-27 19:07:49 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 980/1251] eta: 0:02:51 lr: 0.000277 loss: 3.3350 (3.0963) grad_norm: 1.9457 (1.9686) time: 0.6251 [2021-03-27 19:07:56 swin_base_patch4_window7_224] INFO: Epoch: [195] [ 990/1251] eta: 0:02:44 lr: 0.000277 loss: 3.1664 (3.0970) grad_norm: 1.9331 (1.9711) time: 0.6238 [2021-03-27 19:08:02 swin_base_patch4_window7_224] INFO: Epoch: [195] [1000/1251] eta: 0:02:38 lr: 0.000277 loss: 3.1983 (3.0976) grad_norm: 1.9620 (1.9740) time: 0.6263 [2021-03-27 19:08:08 swin_base_patch4_window7_224] INFO: Epoch: [195] [1010/1251] eta: 0:02:32 lr: 0.000277 loss: 3.2766 (3.0994) grad_norm: 1.9714 (1.9742) time: 0.6306 [2021-03-27 19:08:15 swin_base_patch4_window7_224] INFO: Epoch: [195] [1020/1251] eta: 0:02:26 lr: 0.000277 loss: 3.2844 (3.1000) grad_norm: 2.0155 (1.9741) time: 0.6302 [2021-03-27 19:08:21 swin_base_patch4_window7_224] INFO: Epoch: [195] [1030/1251] eta: 0:02:19 lr: 0.000276 loss: 3.1212 (3.0992) grad_norm: 1.9893 (1.9753) time: 0.6318 [2021-03-27 19:08:27 swin_base_patch4_window7_224] INFO: Epoch: [195] [1040/1251] eta: 0:02:13 lr: 0.000276 loss: 3.1910 (3.1008) grad_norm: 1.8864 (1.9745) time: 0.6297 [2021-03-27 19:08:33 swin_base_patch4_window7_224] INFO: Epoch: [195] [1050/1251] eta: 0:02:07 lr: 0.000276 loss: 3.3045 (3.1018) grad_norm: 1.9393 (1.9764) time: 0.6249 [2021-03-27 19:08:40 swin_base_patch4_window7_224] INFO: Epoch: [195] [1060/1251] eta: 0:02:00 lr: 0.000276 loss: 3.1315 (3.1002) grad_norm: 1.9393 (1.9751) time: 0.6223 [2021-03-27 19:08:46 swin_base_patch4_window7_224] INFO: Epoch: [195] [1070/1251] eta: 0:01:54 lr: 0.000276 loss: 3.1315 (3.1003) grad_norm: 1.8042 (1.9746) time: 0.6235 [2021-03-27 19:08:52 swin_base_patch4_window7_224] INFO: Epoch: [195] [1080/1251] eta: 0:01:48 lr: 0.000276 loss: 3.0764 (3.0974) grad_norm: 1.9093 (inf) time: 0.6205 [2021-03-27 19:08:58 swin_base_patch4_window7_224] INFO: Epoch: [195] [1090/1251] eta: 0:01:41 lr: 0.000276 loss: 3.0262 (3.0971) grad_norm: 1.9570 (inf) time: 0.6230 [2021-03-27 19:09:05 swin_base_patch4_window7_224] INFO: Epoch: [195] [1100/1251] eta: 0:01:35 lr: 0.000276 loss: 3.0694 (3.0973) grad_norm: 1.9042 (inf) time: 0.6250 [2021-03-27 19:09:11 swin_base_patch4_window7_224] INFO: Epoch: [195] [1110/1251] eta: 0:01:29 lr: 0.000276 loss: 3.1607 (3.0981) grad_norm: 1.9042 (inf) time: 0.6248 [2021-03-27 19:09:17 swin_base_patch4_window7_224] INFO: Epoch: [195] [1120/1251] eta: 0:01:22 lr: 0.000276 loss: 3.0020 (3.0963) grad_norm: 1.9333 (inf) time: 0.6245 [2021-03-27 19:09:23 swin_base_patch4_window7_224] INFO: Epoch: [195] [1130/1251] eta: 0:01:16 lr: 0.000276 loss: 2.9498 (3.0943) grad_norm: 1.9973 (inf) time: 0.6254 [2021-03-27 19:09:30 swin_base_patch4_window7_224] INFO: Epoch: [195] [1140/1251] eta: 0:01:10 lr: 0.000276 loss: 3.1690 (3.0938) grad_norm: 1.9750 (inf) time: 0.6308 [2021-03-27 19:09:36 swin_base_patch4_window7_224] INFO: Epoch: [195] [1150/1251] eta: 0:01:03 lr: 0.000276 loss: 3.2429 (3.0953) grad_norm: 2.0533 (inf) time: 0.6268 [2021-03-27 19:09:42 swin_base_patch4_window7_224] INFO: Epoch: [195] [1160/1251] eta: 0:00:57 lr: 0.000276 loss: 3.1526 (3.0944) grad_norm: 1.9597 (inf) time: 0.6233 [2021-03-27 19:09:48 swin_base_patch4_window7_224] INFO: Epoch: [195] [1170/1251] eta: 0:00:51 lr: 0.000276 loss: 2.9058 (3.0919) grad_norm: 1.9313 (inf) time: 0.6262 [2021-03-27 19:09:55 swin_base_patch4_window7_224] INFO: Epoch: [195] [1180/1251] eta: 0:00:44 lr: 0.000276 loss: 2.9058 (3.0907) grad_norm: 1.8633 (inf) time: 0.6243 [2021-03-27 19:10:01 swin_base_patch4_window7_224] INFO: Epoch: [195] [1190/1251] eta: 0:00:38 lr: 0.000276 loss: 3.2068 (3.0917) grad_norm: 1.8276 (inf) time: 0.6238 [2021-03-27 19:10:07 swin_base_patch4_window7_224] INFO: Epoch: [195] [1200/1251] eta: 0:00:32 lr: 0.000276 loss: 3.2226 (3.0915) grad_norm: 1.8689 (inf) time: 0.6261 [2021-03-27 19:10:13 swin_base_patch4_window7_224] INFO: Epoch: [195] [1210/1251] eta: 0:00:25 lr: 0.000276 loss: 3.1578 (3.0905) grad_norm: 1.8689 (inf) time: 0.6269 [2021-03-27 19:10:20 swin_base_patch4_window7_224] INFO: Epoch: [195] [1220/1251] eta: 0:00:19 lr: 0.000276 loss: 3.1997 (3.0915) grad_norm: 1.8535 (inf) time: 0.6259 [2021-03-27 19:10:26 swin_base_patch4_window7_224] INFO: Epoch: [195] [1230/1251] eta: 0:00:13 lr: 0.000276 loss: 3.1914 (3.0905) grad_norm: 1.9459 (inf) time: 0.6221 [2021-03-27 19:10:32 swin_base_patch4_window7_224] INFO: Epoch: [195] [1240/1251] eta: 0:00:06 lr: 0.000276 loss: 3.0560 (3.0893) grad_norm: 2.0008 (inf) time: 0.6232 [2021-03-27 19:10:38 swin_base_patch4_window7_224] INFO: Epoch: [195] [1250/1251] eta: 0:00:00 lr: 0.000276 loss: 3.0927 (3.0901) grad_norm: 1.8721 (inf) time: 0.6297 [2021-03-27 19:11:56 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 0.7560 (0.7560) acc1: 82.8125 (82.8125) acc5: 98.4375 (98.4375) [2021-03-27 19:11:57 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7560 (0.7546) acc1: 82.8125 (82.1023) acc5: 96.8750 (96.4489) [2021-03-27 19:11:59 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7796 (0.8438) acc1: 79.6875 (79.9107) acc5: 95.3125 (95.6101) [2021-03-27 19:12:00 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8319 (0.8457) acc1: 79.6875 (80.3931) acc5: 93.7500 (95.2117) [2021-03-27 19:12:02 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7511 (0.8223) acc1: 81.2500 (80.3735) acc5: 95.3125 (95.5412) [2021-03-27 19:12:03 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7595 (0.8285) acc1: 79.2453 (80.1600) acc5: 95.3125 (95.6160) [2021-03-27 19:12:14 swin_base_patch4_window7_224] INFO: * Acc@1 80.968 Acc@5 95.682 loss 0.816 [2021-03-27 19:12:14 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.0% [2021-03-27 19:12:14 swin_base_patch4_window7_224] INFO: Max accuracy: 80.97% [2021-03-27 19:12:18 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 0/1251] eta: 1:29:27 lr: 0.000276 loss: 3.1236 (3.1236) grad_norm: 2.1114 (2.1114) time: 4.2906 [2021-03-27 19:12:25 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 10/1251] eta: 0:20:08 lr: 0.000276 loss: 3.2838 (3.1676) grad_norm: 1.9515 (1.9115) time: 0.9737 [2021-03-27 19:12:31 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 20/1251] eta: 0:16:34 lr: 0.000276 loss: 2.9584 (2.9169) grad_norm: 1.9406 (2.1587) time: 0.6341 [2021-03-27 19:12:37 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 30/1251] eta: 0:15:17 lr: 0.000276 loss: 3.0024 (3.0343) grad_norm: 1.8922 (2.0889) time: 0.6292 [2021-03-27 19:12:44 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 40/1251] eta: 0:14:35 lr: 0.000276 loss: 3.1809 (3.0437) grad_norm: 1.8279 (2.0234) time: 0.6334 [2021-03-27 19:12:50 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 50/1251] eta: 0:14:09 lr: 0.000275 loss: 3.0292 (3.0292) grad_norm: 1.8029 (1.9957) time: 0.6382 [2021-03-27 19:12:56 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 60/1251] eta: 0:13:47 lr: 0.000275 loss: 2.9877 (3.0334) grad_norm: 1.8533 (2.0659) time: 0.6376 [2021-03-27 19:13:03 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 70/1251] eta: 0:13:29 lr: 0.000275 loss: 3.0680 (3.0331) grad_norm: 1.9142 (2.0483) time: 0.6307 [2021-03-27 19:13:09 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 80/1251] eta: 0:13:14 lr: 0.000275 loss: 3.1011 (3.0664) grad_norm: 1.9683 (2.0439) time: 0.6280 [2021-03-27 19:13:15 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 90/1251] eta: 0:13:00 lr: 0.000275 loss: 3.0857 (3.0589) grad_norm: 1.9057 (2.0182) time: 0.6245 [2021-03-27 19:13:22 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 100/1251] eta: 0:12:48 lr: 0.000275 loss: 3.0455 (3.0554) grad_norm: 1.8526 (2.0051) time: 0.6253 [2021-03-27 19:13:28 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 110/1251] eta: 0:12:38 lr: 0.000275 loss: 3.1314 (3.0577) grad_norm: 1.8982 (2.0101) time: 0.6306 [2021-03-27 19:13:34 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 120/1251] eta: 0:12:28 lr: 0.000275 loss: 3.1314 (3.0488) grad_norm: 1.8982 (2.0007) time: 0.6322 [2021-03-27 19:13:41 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 130/1251] eta: 0:12:19 lr: 0.000275 loss: 3.1577 (3.0645) grad_norm: 1.8473 (1.9972) time: 0.6316 [2021-03-27 19:13:47 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 140/1251] eta: 0:12:11 lr: 0.000275 loss: 3.1959 (3.0736) grad_norm: 1.9223 (1.9922) time: 0.6359 [2021-03-27 19:13:53 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 150/1251] eta: 0:12:02 lr: 0.000275 loss: 3.1914 (3.0777) grad_norm: 1.9153 (1.9862) time: 0.6312 [2021-03-27 19:13:59 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 160/1251] eta: 0:11:53 lr: 0.000275 loss: 2.9343 (3.0545) grad_norm: 1.9871 (1.9972) time: 0.6217 [2021-03-27 19:14:06 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 170/1251] eta: 0:11:45 lr: 0.000275 loss: 2.8001 (3.0445) grad_norm: 1.9546 (1.9978) time: 0.6279 [2021-03-27 19:14:12 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 180/1251] eta: 0:11:37 lr: 0.000275 loss: 3.1383 (3.0488) grad_norm: 1.8553 (1.9920) time: 0.6323 [2021-03-27 19:14:18 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 190/1251] eta: 0:11:29 lr: 0.000275 loss: 3.1941 (3.0543) grad_norm: 1.9294 (1.9926) time: 0.6284 [2021-03-27 19:14:25 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 200/1251] eta: 0:11:22 lr: 0.000275 loss: 3.1105 (3.0438) grad_norm: 1.9477 (1.9927) time: 0.6307 [2021-03-27 19:14:31 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 210/1251] eta: 0:11:14 lr: 0.000275 loss: 2.7687 (3.0375) grad_norm: 1.8553 (1.9978) time: 0.6291 [2021-03-27 19:14:37 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 220/1251] eta: 0:11:07 lr: 0.000275 loss: 3.0925 (3.0419) grad_norm: 1.9039 (1.9930) time: 0.6238 [2021-03-27 19:14:43 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 230/1251] eta: 0:11:00 lr: 0.000275 loss: 3.1500 (3.0378) grad_norm: 1.7994 (1.9864) time: 0.6316 [2021-03-27 19:14:50 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 240/1251] eta: 0:10:52 lr: 0.000275 loss: 3.0327 (3.0334) grad_norm: 1.7994 (1.9850) time: 0.6317 [2021-03-27 19:14:56 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 250/1251] eta: 0:10:45 lr: 0.000275 loss: 2.9831 (3.0254) grad_norm: 1.8960 (1.9795) time: 0.6253 [2021-03-27 19:15:02 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 260/1251] eta: 0:10:38 lr: 0.000275 loss: 2.7882 (3.0154) grad_norm: 1.9045 (1.9807) time: 0.6261 [2021-03-27 19:15:08 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 270/1251] eta: 0:10:31 lr: 0.000275 loss: 3.0477 (3.0170) grad_norm: 1.9385 (1.9777) time: 0.6239 [2021-03-27 19:15:15 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 280/1251] eta: 0:10:24 lr: 0.000275 loss: 3.2429 (3.0241) grad_norm: 1.8573 (1.9753) time: 0.6309 [2021-03-27 19:15:21 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 290/1251] eta: 0:10:17 lr: 0.000275 loss: 3.0388 (3.0129) grad_norm: 1.8573 (1.9716) time: 0.6323 [2021-03-27 19:15:27 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 300/1251] eta: 0:10:10 lr: 0.000275 loss: 2.9890 (3.0158) grad_norm: 1.8927 (1.9757) time: 0.6211 [2021-03-27 19:15:34 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 310/1251] eta: 0:10:03 lr: 0.000275 loss: 3.2739 (3.0268) grad_norm: 1.9261 (1.9726) time: 0.6271 [2021-03-27 19:15:40 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 320/1251] eta: 0:09:56 lr: 0.000274 loss: 3.1184 (3.0222) grad_norm: 1.9129 (1.9686) time: 0.6313 [2021-03-27 19:15:46 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 330/1251] eta: 0:09:50 lr: 0.000274 loss: 3.0197 (3.0260) grad_norm: 1.8911 (1.9684) time: 0.6316 [2021-03-27 19:15:53 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 340/1251] eta: 0:09:43 lr: 0.000274 loss: 3.0197 (3.0186) grad_norm: 1.8099 (1.9646) time: 0.6298 [2021-03-27 19:15:59 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 350/1251] eta: 0:09:36 lr: 0.000274 loss: 3.0640 (3.0237) grad_norm: 1.8099 (1.9622) time: 0.6231 [2021-03-27 19:16:05 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 360/1251] eta: 0:09:29 lr: 0.000274 loss: 3.1132 (3.0242) grad_norm: 1.7845 (1.9571) time: 0.6250 [2021-03-27 19:16:11 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 370/1251] eta: 0:09:23 lr: 0.000274 loss: 2.9503 (3.0171) grad_norm: 1.7217 (1.9546) time: 0.6259 [2021-03-27 19:16:18 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 380/1251] eta: 0:09:16 lr: 0.000274 loss: 3.1565 (3.0220) grad_norm: 1.8474 (1.9538) time: 0.6260 [2021-03-27 19:16:24 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 390/1251] eta: 0:09:09 lr: 0.000274 loss: 3.1194 (3.0204) grad_norm: 1.8474 (1.9508) time: 0.6239 [2021-03-27 19:16:30 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 400/1251] eta: 0:09:03 lr: 0.000274 loss: 3.0279 (3.0218) grad_norm: 1.9136 (1.9521) time: 0.6226 [2021-03-27 19:16:36 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 410/1251] eta: 0:08:56 lr: 0.000274 loss: 3.2238 (3.0219) grad_norm: 1.8446 (1.9474) time: 0.6243 [2021-03-27 19:16:43 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 420/1251] eta: 0:08:49 lr: 0.000274 loss: 3.1961 (3.0225) grad_norm: 1.7582 (1.9452) time: 0.6254 [2021-03-27 19:16:49 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 430/1251] eta: 0:08:43 lr: 0.000274 loss: 3.1816 (3.0253) grad_norm: 1.8942 (1.9445) time: 0.6244 [2021-03-27 19:16:55 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 440/1251] eta: 0:08:36 lr: 0.000274 loss: 3.2160 (3.0273) grad_norm: 1.9123 (1.9452) time: 0.6251 [2021-03-27 19:17:01 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 450/1251] eta: 0:08:29 lr: 0.000274 loss: 3.1520 (3.0300) grad_norm: 1.8866 (1.9452) time: 0.6257 [2021-03-27 19:17:08 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 460/1251] eta: 0:08:23 lr: 0.000274 loss: 3.1520 (3.0306) grad_norm: 1.8571 (1.9433) time: 0.6250 [2021-03-27 19:17:14 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 470/1251] eta: 0:08:17 lr: 0.000274 loss: 3.3044 (3.0362) grad_norm: 1.9221 (1.9438) time: 0.6355 [2021-03-27 19:17:20 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 480/1251] eta: 0:08:10 lr: 0.000274 loss: 3.1076 (3.0336) grad_norm: 1.9497 (1.9483) time: 0.6363 [2021-03-27 19:17:27 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 490/1251] eta: 0:08:04 lr: 0.000274 loss: 3.2331 (3.0397) grad_norm: 1.9431 (1.9535) time: 0.6265 [2021-03-27 19:17:33 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 500/1251] eta: 0:07:57 lr: 0.000274 loss: 3.2933 (3.0438) grad_norm: 1.8875 (1.9537) time: 0.6245 [2021-03-27 19:17:39 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 510/1251] eta: 0:07:51 lr: 0.000274 loss: 3.2933 (3.0452) grad_norm: 1.8578 (1.9513) time: 0.6245 [2021-03-27 19:17:45 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 520/1251] eta: 0:07:44 lr: 0.000274 loss: 3.1856 (3.0475) grad_norm: 1.8532 (1.9508) time: 0.6254 [2021-03-27 19:17:51 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 530/1251] eta: 0:07:38 lr: 0.000274 loss: 3.1673 (3.0515) grad_norm: 1.9110 (1.9531) time: 0.6243 [2021-03-27 19:17:58 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 540/1251] eta: 0:07:31 lr: 0.000274 loss: 3.2075 (3.0519) grad_norm: 1.8588 (1.9513) time: 0.6227 [2021-03-27 19:18:04 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 550/1251] eta: 0:07:25 lr: 0.000274 loss: 3.2370 (3.0544) grad_norm: 1.8099 (1.9514) time: 0.6358 [2021-03-27 19:18:11 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 560/1251] eta: 0:07:18 lr: 0.000274 loss: 3.1474 (3.0552) grad_norm: 1.8020 (1.9500) time: 0.6383 [2021-03-27 19:18:17 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 570/1251] eta: 0:07:12 lr: 0.000274 loss: 3.2324 (3.0568) grad_norm: 1.8020 (1.9481) time: 0.6301 [2021-03-27 19:18:23 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 580/1251] eta: 0:07:06 lr: 0.000274 loss: 3.1533 (3.0556) grad_norm: 1.8366 (1.9473) time: 0.6388 [2021-03-27 19:18:30 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 590/1251] eta: 0:06:59 lr: 0.000274 loss: 3.1179 (3.0551) grad_norm: 1.8382 (1.9456) time: 0.6345 [2021-03-27 19:18:36 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 600/1251] eta: 0:06:53 lr: 0.000273 loss: 3.3144 (3.0572) grad_norm: 1.8382 (1.9444) time: 0.6303 [2021-03-27 19:18:42 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 610/1251] eta: 0:06:47 lr: 0.000273 loss: 3.3214 (3.0588) grad_norm: 1.8352 (1.9441) time: 0.6325 [2021-03-27 19:18:48 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 620/1251] eta: 0:06:40 lr: 0.000273 loss: 3.2618 (3.0592) grad_norm: 1.9357 (1.9503) time: 0.6275 [2021-03-27 19:18:55 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 630/1251] eta: 0:06:34 lr: 0.000273 loss: 3.2279 (3.0605) grad_norm: 2.1437 (1.9572) time: 0.6272 [2021-03-27 19:19:01 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 640/1251] eta: 0:06:27 lr: 0.000273 loss: 3.2383 (3.0650) grad_norm: 1.9159 (1.9559) time: 0.6301 [2021-03-27 19:19:07 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 650/1251] eta: 0:06:21 lr: 0.000273 loss: 3.2082 (3.0635) grad_norm: 1.9159 (1.9589) time: 0.6339 [2021-03-27 19:19:14 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 660/1251] eta: 0:06:15 lr: 0.000273 loss: 3.2082 (3.0673) grad_norm: 2.0028 (1.9595) time: 0.6281 [2021-03-27 19:19:20 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 670/1251] eta: 0:06:08 lr: 0.000273 loss: 3.3127 (3.0697) grad_norm: 1.9179 (1.9593) time: 0.6221 [2021-03-27 19:19:26 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 680/1251] eta: 0:06:02 lr: 0.000273 loss: 3.2468 (3.0697) grad_norm: 1.9179 (1.9598) time: 0.6228 [2021-03-27 19:19:32 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 690/1251] eta: 0:05:55 lr: 0.000273 loss: 3.1652 (3.0676) grad_norm: 1.8768 (1.9586) time: 0.6313 [2021-03-27 19:19:39 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 700/1251] eta: 0:05:49 lr: 0.000273 loss: 3.2112 (3.0695) grad_norm: 1.7616 (1.9576) time: 0.6311 [2021-03-27 19:19:45 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 710/1251] eta: 0:05:42 lr: 0.000273 loss: 3.1707 (3.0659) grad_norm: 1.8330 (1.9577) time: 0.6212 [2021-03-27 19:19:51 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 720/1251] eta: 0:05:36 lr: 0.000273 loss: 3.0222 (3.0676) grad_norm: 1.7611 (1.9563) time: 0.6273 [2021-03-27 19:19:58 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 730/1251] eta: 0:05:30 lr: 0.000273 loss: 3.1115 (3.0658) grad_norm: 1.7722 (1.9564) time: 0.6319 [2021-03-27 19:20:04 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 740/1251] eta: 0:05:23 lr: 0.000273 loss: 3.0472 (3.0673) grad_norm: 1.7836 (1.9560) time: 0.6345 [2021-03-27 19:20:10 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 750/1251] eta: 0:05:17 lr: 0.000273 loss: 3.0227 (3.0669) grad_norm: 1.7836 (1.9553) time: 0.6374 [2021-03-27 19:20:17 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 760/1251] eta: 0:05:11 lr: 0.000273 loss: 3.0209 (3.0655) grad_norm: 1.8356 (1.9541) time: 0.6290 [2021-03-27 19:20:23 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 770/1251] eta: 0:05:04 lr: 0.000273 loss: 3.1733 (3.0673) grad_norm: 1.8311 (1.9524) time: 0.6247 [2021-03-27 19:20:29 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 780/1251] eta: 0:04:58 lr: 0.000273 loss: 3.1349 (3.0653) grad_norm: 1.8060 (1.9510) time: 0.6282 [2021-03-27 19:20:35 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 790/1251] eta: 0:04:52 lr: 0.000273 loss: 3.1924 (3.0678) grad_norm: 1.7852 (1.9498) time: 0.6309 [2021-03-27 19:20:42 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 800/1251] eta: 0:04:45 lr: 0.000273 loss: 3.2810 (3.0678) grad_norm: 1.8595 (1.9500) time: 0.6320 [2021-03-27 19:20:48 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 810/1251] eta: 0:04:39 lr: 0.000273 loss: 3.0766 (3.0685) grad_norm: 1.8466 (1.9472) time: 0.6339 [2021-03-27 19:20:54 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 820/1251] eta: 0:04:33 lr: 0.000273 loss: 2.9688 (3.0665) grad_norm: 1.8319 (1.9480) time: 0.6290 [2021-03-27 19:21:01 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 830/1251] eta: 0:04:26 lr: 0.000273 loss: 2.8444 (3.0648) grad_norm: 1.9439 (1.9481) time: 0.6246 [2021-03-27 19:21:07 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 840/1251] eta: 0:04:20 lr: 0.000273 loss: 3.0703 (3.0646) grad_norm: 1.8998 (1.9481) time: 0.6252 [2021-03-27 19:21:13 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 850/1251] eta: 0:04:13 lr: 0.000273 loss: 3.1174 (3.0622) grad_norm: 1.9538 (1.9478) time: 0.6248 [2021-03-27 19:21:19 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 860/1251] eta: 0:04:07 lr: 0.000273 loss: 3.0717 (3.0623) grad_norm: 1.7740 (1.9466) time: 0.6269 [2021-03-27 19:21:26 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 870/1251] eta: 0:04:01 lr: 0.000272 loss: 3.0367 (3.0621) grad_norm: 1.7617 (1.9454) time: 0.6286 [2021-03-27 19:21:32 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 880/1251] eta: 0:03:54 lr: 0.000272 loss: 2.9571 (3.0601) grad_norm: 1.8446 (1.9463) time: 0.6270 [2021-03-27 19:21:38 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 890/1251] eta: 0:03:48 lr: 0.000272 loss: 3.0107 (3.0607) grad_norm: 1.8446 (1.9461) time: 0.6321 [2021-03-27 19:21:45 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 900/1251] eta: 0:03:42 lr: 0.000272 loss: 3.2523 (3.0600) grad_norm: 1.8051 (1.9446) time: 0.6338 [2021-03-27 19:21:51 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 910/1251] eta: 0:03:35 lr: 0.000272 loss: 3.0941 (3.0596) grad_norm: 1.8485 (1.9434) time: 0.6256 [2021-03-27 19:21:57 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 920/1251] eta: 0:03:29 lr: 0.000272 loss: 3.1385 (3.0627) grad_norm: 1.8612 (1.9417) time: 0.6224 [2021-03-27 19:22:03 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 930/1251] eta: 0:03:23 lr: 0.000272 loss: 3.2009 (3.0604) grad_norm: 1.8612 (1.9427) time: 0.6248 [2021-03-27 19:22:10 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 940/1251] eta: 0:03:16 lr: 0.000272 loss: 3.0382 (3.0603) grad_norm: 1.9149 (1.9432) time: 0.6288 [2021-03-27 19:22:16 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 950/1251] eta: 0:03:10 lr: 0.000272 loss: 3.0277 (3.0586) grad_norm: 1.9162 (1.9450) time: 0.6312 [2021-03-27 19:22:22 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 960/1251] eta: 0:03:04 lr: 0.000272 loss: 3.1234 (3.0606) grad_norm: 1.8911 (1.9452) time: 0.6289 [2021-03-27 19:22:28 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 970/1251] eta: 0:02:57 lr: 0.000272 loss: 3.2139 (3.0596) grad_norm: 1.8911 (1.9453) time: 0.6262 [2021-03-27 19:22:35 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 980/1251] eta: 0:02:51 lr: 0.000272 loss: 3.1522 (3.0584) grad_norm: 1.8971 (1.9445) time: 0.6265 [2021-03-27 19:22:41 swin_base_patch4_window7_224] INFO: Epoch: [196] [ 990/1251] eta: 0:02:45 lr: 0.000272 loss: 3.1862 (3.0587) grad_norm: 1.8568 (1.9442) time: 0.6250 [2021-03-27 19:22:47 swin_base_patch4_window7_224] INFO: Epoch: [196] [1000/1251] eta: 0:02:38 lr: 0.000272 loss: 3.3454 (3.0611) grad_norm: 1.7537 (1.9427) time: 0.6239 [2021-03-27 19:22:54 swin_base_patch4_window7_224] INFO: Epoch: [196] [1010/1251] eta: 0:02:32 lr: 0.000272 loss: 3.1824 (3.0594) grad_norm: 1.7960 (1.9446) time: 0.6262 [2021-03-27 19:23:00 swin_base_patch4_window7_224] INFO: Epoch: [196] [1020/1251] eta: 0:02:26 lr: 0.000272 loss: 3.0363 (3.0613) grad_norm: 1.9957 (1.9465) time: 0.6260 [2021-03-27 19:23:06 swin_base_patch4_window7_224] INFO: Epoch: [196] [1030/1251] eta: 0:02:19 lr: 0.000272 loss: 3.1304 (3.0614) grad_norm: 1.9037 (1.9461) time: 0.6248 [2021-03-27 19:23:12 swin_base_patch4_window7_224] INFO: Epoch: [196] [1040/1251] eta: 0:02:13 lr: 0.000272 loss: 3.0654 (3.0621) grad_norm: 1.8859 (1.9468) time: 0.6331 [2021-03-27 19:23:19 swin_base_patch4_window7_224] INFO: Epoch: [196] [1050/1251] eta: 0:02:07 lr: 0.000272 loss: 3.2171 (3.0644) grad_norm: 1.9108 (1.9465) time: 0.6310 [2021-03-27 19:23:25 swin_base_patch4_window7_224] INFO: Epoch: [196] [1060/1251] eta: 0:02:00 lr: 0.000272 loss: 3.3159 (3.0654) grad_norm: 1.8590 (1.9460) time: 0.6244 [2021-03-27 19:23:31 swin_base_patch4_window7_224] INFO: Epoch: [196] [1070/1251] eta: 0:01:54 lr: 0.000272 loss: 3.0979 (3.0645) grad_norm: 1.8590 (1.9471) time: 0.6250 [2021-03-27 19:23:38 swin_base_patch4_window7_224] INFO: Epoch: [196] [1080/1251] eta: 0:01:48 lr: 0.000272 loss: 3.0635 (3.0648) grad_norm: 1.8686 (1.9466) time: 0.6324 [2021-03-27 19:23:44 swin_base_patch4_window7_224] INFO: Epoch: [196] [1090/1251] eta: 0:01:41 lr: 0.000272 loss: 3.1340 (3.0650) grad_norm: 1.8890 (1.9477) time: 0.6315 [2021-03-27 19:23:50 swin_base_patch4_window7_224] INFO: Epoch: [196] [1100/1251] eta: 0:01:35 lr: 0.000272 loss: 3.2269 (3.0657) grad_norm: 1.8688 (1.9480) time: 0.6264 [2021-03-27 19:23:56 swin_base_patch4_window7_224] INFO: Epoch: [196] [1110/1251] eta: 0:01:29 lr: 0.000272 loss: 3.3442 (3.0651) grad_norm: 1.8688 (1.9488) time: 0.6280 [2021-03-27 19:24:03 swin_base_patch4_window7_224] INFO: Epoch: [196] [1120/1251] eta: 0:01:22 lr: 0.000272 loss: 3.3921 (3.0679) grad_norm: 1.9943 (1.9520) time: 0.6280 [2021-03-27 19:24:09 swin_base_patch4_window7_224] INFO: Epoch: [196] [1130/1251] eta: 0:01:16 lr: 0.000272 loss: 3.3652 (3.0694) grad_norm: 2.0592 (1.9533) time: 0.6296 [2021-03-27 19:24:15 swin_base_patch4_window7_224] INFO: Epoch: [196] [1140/1251] eta: 0:01:10 lr: 0.000271 loss: 3.3439 (3.0709) grad_norm: 1.9453 (1.9531) time: 0.6243 [2021-03-27 19:24:21 swin_base_patch4_window7_224] INFO: Epoch: [196] [1150/1251] eta: 0:01:03 lr: 0.000271 loss: 3.2575 (3.0714) grad_norm: 1.8730 (1.9523) time: 0.6225 [2021-03-27 19:24:28 swin_base_patch4_window7_224] INFO: Epoch: [196] [1160/1251] eta: 0:00:57 lr: 0.000271 loss: 3.1259 (3.0719) grad_norm: 1.9090 (1.9530) time: 0.6246 [2021-03-27 19:24:34 swin_base_patch4_window7_224] INFO: Epoch: [196] [1170/1251] eta: 0:00:51 lr: 0.000271 loss: 3.1039 (3.0712) grad_norm: 1.8293 (1.9520) time: 0.6250 [2021-03-27 19:24:40 swin_base_patch4_window7_224] INFO: Epoch: [196] [1180/1251] eta: 0:00:44 lr: 0.000271 loss: 2.9561 (3.0705) grad_norm: 1.7974 (1.9513) time: 0.6285 [2021-03-27 19:24:46 swin_base_patch4_window7_224] INFO: Epoch: [196] [1190/1251] eta: 0:00:38 lr: 0.000271 loss: 3.1585 (3.0720) grad_norm: 1.8751 (1.9517) time: 0.6277 [2021-03-27 19:24:53 swin_base_patch4_window7_224] INFO: Epoch: [196] [1200/1251] eta: 0:00:32 lr: 0.000271 loss: 3.4122 (3.0742) grad_norm: 1.8553 (1.9508) time: 0.6253 [2021-03-27 19:24:59 swin_base_patch4_window7_224] INFO: Epoch: [196] [1210/1251] eta: 0:00:25 lr: 0.000271 loss: 3.1528 (3.0733) grad_norm: 1.8632 (1.9508) time: 0.6250 [2021-03-27 19:25:05 swin_base_patch4_window7_224] INFO: Epoch: [196] [1220/1251] eta: 0:00:19 lr: 0.000271 loss: 2.9322 (3.0715) grad_norm: 1.8920 (1.9524) time: 0.6228 [2021-03-27 19:25:11 swin_base_patch4_window7_224] INFO: Epoch: [196] [1230/1251] eta: 0:00:13 lr: 0.000271 loss: 2.9419 (3.0717) grad_norm: 1.9422 (1.9524) time: 0.6244 [2021-03-27 19:25:18 swin_base_patch4_window7_224] INFO: Epoch: [196] [1240/1251] eta: 0:00:06 lr: 0.000271 loss: 3.1240 (3.0713) grad_norm: 1.9752 (1.9540) time: 0.6238 [2021-03-27 19:25:24 swin_base_patch4_window7_224] INFO: Epoch: [196] [1250/1251] eta: 0:00:00 lr: 0.000271 loss: 3.1989 (3.0712) grad_norm: 1.9375 (1.9533) time: 0.6243 [2021-03-27 19:25:32 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:40 loss: 0.8593 (0.8593) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-27 19:25:35 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8388 (0.8255) acc1: 82.8125 (81.1080) acc5: 95.3125 (95.7386) [2021-03-27 19:25:38 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8210 (0.8311) acc1: 81.2500 (80.8780) acc5: 95.3125 (95.5357) [2021-03-27 19:25:40 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8210 (0.8434) acc1: 79.6875 (80.1411) acc5: 96.8750 (95.8669) [2021-03-27 19:25:42 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7900 (0.8437) acc1: 79.6875 (80.4116) acc5: 96.8750 (95.7317) [2021-03-27 19:25:43 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8705 (0.8523) acc1: 81.2500 (80.2880) acc5: 95.3125 (95.7120) [2021-03-27 19:25:54 swin_base_patch4_window7_224] INFO: * Acc@1 80.866 Acc@5 95.698 loss 0.828 [2021-03-27 19:25:54 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.9% [2021-03-27 19:25:54 swin_base_patch4_window7_224] INFO: Max accuracy: 80.97% [2021-03-27 19:25:58 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 0/1251] eta: 1:32:50 lr: 0.000271 loss: 3.5219 (3.5219) grad_norm: 3.0806 (3.0806) time: 4.4530 [2021-03-27 19:26:05 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 10/1251] eta: 0:20:34 lr: 0.000271 loss: 3.2730 (3.1204) grad_norm: 1.8765 (1.9869) time: 0.9945 [2021-03-27 19:26:11 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 20/1251] eta: 0:16:52 lr: 0.000271 loss: 2.8906 (3.0188) grad_norm: 1.8037 (1.9442) time: 0.6409 [2021-03-27 19:26:17 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 30/1251] eta: 0:15:28 lr: 0.000271 loss: 3.0634 (3.1035) grad_norm: 1.7928 (1.9352) time: 0.6324 [2021-03-27 19:26:24 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 40/1251] eta: 0:14:39 lr: 0.000271 loss: 3.1509 (3.0825) grad_norm: 1.9648 (1.9633) time: 0.6261 [2021-03-27 19:26:30 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 50/1251] eta: 0:14:08 lr: 0.000271 loss: 2.9319 (3.0424) grad_norm: 1.8666 (1.9541) time: 0.6229 [2021-03-27 19:26:36 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 60/1251] eta: 0:13:46 lr: 0.000271 loss: 3.1222 (3.0719) grad_norm: 1.8350 (1.9546) time: 0.6261 [2021-03-27 19:26:42 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 70/1251] eta: 0:13:29 lr: 0.000271 loss: 3.1798 (3.0848) grad_norm: 1.9098 (1.9656) time: 0.6302 [2021-03-27 19:26:49 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 80/1251] eta: 0:13:15 lr: 0.000271 loss: 3.1667 (3.0815) grad_norm: 1.9753 (1.9720) time: 0.6344 [2021-03-27 19:26:55 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 90/1251] eta: 0:13:02 lr: 0.000271 loss: 3.1229 (3.0648) grad_norm: 1.9966 (1.9961) time: 0.6324 [2021-03-27 19:27:01 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 100/1251] eta: 0:12:49 lr: 0.000271 loss: 3.1229 (3.0763) grad_norm: 1.9784 (1.9869) time: 0.6266 [2021-03-27 19:27:07 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 110/1251] eta: 0:12:38 lr: 0.000271 loss: 3.1625 (3.0673) grad_norm: 1.9384 (1.9983) time: 0.6233 [2021-03-27 19:27:14 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 120/1251] eta: 0:12:28 lr: 0.000271 loss: 3.2071 (3.0740) grad_norm: 1.9216 (1.9911) time: 0.6284 [2021-03-27 19:27:20 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 130/1251] eta: 0:12:18 lr: 0.000271 loss: 3.2071 (3.0647) grad_norm: 1.8306 (1.9827) time: 0.6292 [2021-03-27 19:27:26 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 140/1251] eta: 0:12:10 lr: 0.000271 loss: 2.9977 (3.0661) grad_norm: 1.8590 (1.9859) time: 0.6279 [2021-03-27 19:27:33 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 150/1251] eta: 0:12:01 lr: 0.000271 loss: 3.1194 (3.0755) grad_norm: 1.9280 (1.9845) time: 0.6297 [2021-03-27 19:27:39 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 160/1251] eta: 0:11:52 lr: 0.000271 loss: 3.2980 (3.0869) grad_norm: 1.8550 (1.9780) time: 0.6259 [2021-03-27 19:27:45 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 170/1251] eta: 0:11:44 lr: 0.000270 loss: 3.2870 (3.0812) grad_norm: 1.8724 (1.9765) time: 0.6231 [2021-03-27 19:27:51 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 180/1251] eta: 0:11:36 lr: 0.000270 loss: 3.0763 (3.0774) grad_norm: 2.0431 (1.9886) time: 0.6277 [2021-03-27 19:27:58 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 190/1251] eta: 0:11:29 lr: 0.000270 loss: 3.2010 (3.0818) grad_norm: 2.0610 (1.9946) time: 0.6325 [2021-03-27 19:28:04 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 200/1251] eta: 0:11:22 lr: 0.000270 loss: 3.2010 (3.0866) grad_norm: 2.0610 (2.0017) time: 0.6416 [2021-03-27 19:28:11 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 210/1251] eta: 0:11:14 lr: 0.000270 loss: 3.2403 (3.0954) grad_norm: 1.9620 (1.9936) time: 0.6376 [2021-03-27 19:28:17 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 220/1251] eta: 0:11:07 lr: 0.000270 loss: 3.3454 (3.1023) grad_norm: 1.8168 (1.9876) time: 0.6248 [2021-03-27 19:28:23 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 230/1251] eta: 0:10:59 lr: 0.000270 loss: 3.3393 (3.0992) grad_norm: 1.9125 (1.9934) time: 0.6247 [2021-03-27 19:28:29 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 240/1251] eta: 0:10:52 lr: 0.000270 loss: 3.0533 (3.1011) grad_norm: 2.0089 (1.9977) time: 0.6272 [2021-03-27 19:28:36 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 250/1251] eta: 0:10:45 lr: 0.000270 loss: 3.0943 (3.0935) grad_norm: 1.9959 (1.9997) time: 0.6286 [2021-03-27 19:28:42 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 260/1251] eta: 0:10:38 lr: 0.000270 loss: 3.1075 (3.0892) grad_norm: 1.9658 (2.0020) time: 0.6261 [2021-03-27 19:28:48 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 270/1251] eta: 0:10:31 lr: 0.000270 loss: 3.1593 (3.0901) grad_norm: 1.9658 (1.9986) time: 0.6322 [2021-03-27 19:28:55 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 280/1251] eta: 0:10:25 lr: 0.000270 loss: 3.1172 (3.0827) grad_norm: 1.9021 (1.9930) time: 0.6418 [2021-03-27 19:29:01 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 290/1251] eta: 0:10:18 lr: 0.000270 loss: 3.1378 (3.0858) grad_norm: 1.8024 (1.9901) time: 0.6360 [2021-03-27 19:29:07 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 300/1251] eta: 0:10:11 lr: 0.000270 loss: 3.3422 (3.0898) grad_norm: 1.9536 (1.9992) time: 0.6294 [2021-03-27 19:29:14 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 310/1251] eta: 0:10:04 lr: 0.000270 loss: 3.3422 (3.0941) grad_norm: 1.8869 (1.9952) time: 0.6297 [2021-03-27 19:29:20 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 320/1251] eta: 0:09:57 lr: 0.000270 loss: 3.3405 (3.0913) grad_norm: 1.9908 (1.9996) time: 0.6269 [2021-03-27 19:29:26 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 330/1251] eta: 0:09:50 lr: 0.000270 loss: 3.0959 (3.0886) grad_norm: 1.9691 (1.9964) time: 0.6271 [2021-03-27 19:29:32 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 340/1251] eta: 0:09:43 lr: 0.000270 loss: 3.1604 (3.0889) grad_norm: 1.8697 (1.9995) time: 0.6255 [2021-03-27 19:29:39 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 350/1251] eta: 0:09:37 lr: 0.000270 loss: 3.0621 (3.0884) grad_norm: 1.9574 (2.0004) time: 0.6229 [2021-03-27 19:29:45 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 360/1251] eta: 0:09:30 lr: 0.000270 loss: 3.0483 (3.0882) grad_norm: 1.8843 (1.9969) time: 0.6240 [2021-03-27 19:29:51 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 370/1251] eta: 0:09:23 lr: 0.000270 loss: 2.9632 (3.0812) grad_norm: 1.8843 (1.9949) time: 0.6292 [2021-03-27 19:29:58 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 380/1251] eta: 0:09:17 lr: 0.000270 loss: 2.9632 (3.0741) grad_norm: 1.8633 (1.9896) time: 0.6370 [2021-03-27 19:30:04 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 390/1251] eta: 0:09:11 lr: 0.000270 loss: 2.9485 (3.0695) grad_norm: 1.8744 (1.9896) time: 0.6422 [2021-03-27 19:30:10 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 400/1251] eta: 0:09:04 lr: 0.000270 loss: 3.1235 (3.0731) grad_norm: 1.8473 (1.9886) time: 0.6348 [2021-03-27 19:30:17 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 410/1251] eta: 0:08:57 lr: 0.000270 loss: 3.2355 (3.0727) grad_norm: 1.8100 (1.9844) time: 0.6263 [2021-03-27 19:30:23 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 420/1251] eta: 0:08:51 lr: 0.000270 loss: 3.2316 (3.0739) grad_norm: 1.7806 (1.9795) time: 0.6305 [2021-03-27 19:30:29 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 430/1251] eta: 0:08:44 lr: 0.000270 loss: 3.0650 (3.0756) grad_norm: 1.8767 (1.9917) time: 0.6308 [2021-03-27 19:30:36 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 440/1251] eta: 0:08:38 lr: 0.000269 loss: 3.0716 (3.0781) grad_norm: 1.9431 (1.9899) time: 0.6316 [2021-03-27 19:30:42 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 450/1251] eta: 0:08:31 lr: 0.000269 loss: 3.0232 (3.0740) grad_norm: 1.9200 (1.9932) time: 0.6296 [2021-03-27 19:30:48 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 460/1251] eta: 0:08:24 lr: 0.000269 loss: 3.0209 (3.0748) grad_norm: 1.9200 (1.9919) time: 0.6279 [2021-03-27 19:30:54 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 470/1251] eta: 0:08:18 lr: 0.000269 loss: 3.1270 (3.0754) grad_norm: 1.8759 (1.9942) time: 0.6282 [2021-03-27 19:31:01 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 480/1251] eta: 0:08:11 lr: 0.000269 loss: 3.3429 (3.0801) grad_norm: 1.9723 (1.9933) time: 0.6249 [2021-03-27 19:31:07 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 490/1251] eta: 0:08:05 lr: 0.000269 loss: 3.1694 (3.0786) grad_norm: 1.8956 (1.9930) time: 0.6257 [2021-03-27 19:31:13 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 500/1251] eta: 0:07:58 lr: 0.000269 loss: 2.9612 (3.0782) grad_norm: 1.9086 (1.9937) time: 0.6264 [2021-03-27 19:31:19 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 510/1251] eta: 0:07:52 lr: 0.000269 loss: 3.0833 (3.0804) grad_norm: 1.8693 (1.9920) time: 0.6280 [2021-03-27 19:31:26 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 520/1251] eta: 0:07:45 lr: 0.000269 loss: 3.1253 (3.0755) grad_norm: 1.8258 (1.9900) time: 0.6285 [2021-03-27 19:31:32 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 530/1251] eta: 0:07:39 lr: 0.000269 loss: 3.1307 (3.0761) grad_norm: 1.8903 (1.9903) time: 0.6268 [2021-03-27 19:31:38 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 540/1251] eta: 0:07:32 lr: 0.000269 loss: 3.0375 (3.0735) grad_norm: 1.8754 (1.9871) time: 0.6288 [2021-03-27 19:31:45 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 550/1251] eta: 0:07:26 lr: 0.000269 loss: 2.9478 (3.0698) grad_norm: 1.9039 (1.9886) time: 0.6367 [2021-03-27 19:31:51 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 560/1251] eta: 0:07:19 lr: 0.000269 loss: 3.0086 (3.0678) grad_norm: 2.0430 (1.9906) time: 0.6365 [2021-03-27 19:31:57 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 570/1251] eta: 0:07:13 lr: 0.000269 loss: 3.0086 (3.0635) grad_norm: 2.0529 (1.9923) time: 0.6262 [2021-03-27 19:32:03 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 580/1251] eta: 0:07:06 lr: 0.000269 loss: 3.0910 (3.0645) grad_norm: 2.0005 (1.9921) time: 0.6219 [2021-03-27 19:32:10 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 590/1251] eta: 0:07:00 lr: 0.000269 loss: 3.1055 (3.0645) grad_norm: 2.0498 (1.9953) time: 0.6244 [2021-03-27 19:32:16 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 600/1251] eta: 0:06:54 lr: 0.000269 loss: 3.1452 (3.0639) grad_norm: 1.9126 (1.9934) time: 0.6300 [2021-03-27 19:32:22 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 610/1251] eta: 0:06:47 lr: 0.000269 loss: 3.0562 (3.0622) grad_norm: 1.8659 (1.9918) time: 0.6280 [2021-03-27 19:32:28 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 620/1251] eta: 0:06:41 lr: 0.000269 loss: 2.9980 (3.0606) grad_norm: 1.8911 (1.9913) time: 0.6208 [2021-03-27 19:32:35 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 630/1251] eta: 0:06:34 lr: 0.000269 loss: 3.2678 (3.0629) grad_norm: 1.9135 (1.9895) time: 0.6221 [2021-03-27 19:32:41 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 640/1251] eta: 0:06:28 lr: 0.000269 loss: 3.0979 (3.0632) grad_norm: 1.8649 (1.9878) time: 0.6228 [2021-03-27 19:32:47 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 650/1251] eta: 0:06:21 lr: 0.000269 loss: 3.0979 (3.0653) grad_norm: 1.9428 (1.9887) time: 0.6271 [2021-03-27 19:32:54 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 660/1251] eta: 0:06:15 lr: 0.000269 loss: 3.2007 (3.0665) grad_norm: 2.0089 (1.9892) time: 0.6314 [2021-03-27 19:33:00 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 670/1251] eta: 0:06:08 lr: 0.000269 loss: 3.0138 (3.0643) grad_norm: 1.9586 (1.9888) time: 0.6283 [2021-03-27 19:33:06 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 680/1251] eta: 0:06:02 lr: 0.000269 loss: 3.0962 (3.0673) grad_norm: 1.9155 (1.9880) time: 0.6277 [2021-03-27 19:33:12 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 690/1251] eta: 0:05:56 lr: 0.000269 loss: 3.1338 (3.0664) grad_norm: 1.8761 (1.9884) time: 0.6290 [2021-03-27 19:33:19 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 700/1251] eta: 0:05:49 lr: 0.000269 loss: 3.1118 (3.0685) grad_norm: 1.8338 (1.9855) time: 0.6310 [2021-03-27 19:33:25 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 710/1251] eta: 0:05:43 lr: 0.000268 loss: 3.1118 (3.0700) grad_norm: 1.8509 (1.9848) time: 0.6278 [2021-03-27 19:33:31 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 720/1251] eta: 0:05:36 lr: 0.000268 loss: 3.1463 (3.0703) grad_norm: 1.9413 (1.9878) time: 0.6221 [2021-03-27 19:33:38 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 730/1251] eta: 0:05:30 lr: 0.000268 loss: 3.2960 (3.0737) grad_norm: 1.9538 (1.9866) time: 0.6303 [2021-03-27 19:33:44 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 740/1251] eta: 0:05:24 lr: 0.000268 loss: 3.2575 (3.0735) grad_norm: 2.0376 (1.9881) time: 0.6338 [2021-03-27 19:33:50 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 750/1251] eta: 0:05:17 lr: 0.000268 loss: 3.2079 (3.0755) grad_norm: 1.9736 (1.9876) time: 0.6324 [2021-03-27 19:33:56 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 760/1251] eta: 0:05:11 lr: 0.000268 loss: 3.3142 (3.0765) grad_norm: 1.9322 (1.9871) time: 0.6292 [2021-03-27 19:34:03 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 770/1251] eta: 0:05:05 lr: 0.000268 loss: 2.9892 (3.0737) grad_norm: 1.9661 (1.9886) time: 0.6240 [2021-03-27 19:34:09 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 780/1251] eta: 0:04:58 lr: 0.000268 loss: 2.9608 (3.0744) grad_norm: 1.9690 (1.9889) time: 0.6304 [2021-03-27 19:34:15 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 790/1251] eta: 0:04:52 lr: 0.000268 loss: 3.2511 (3.0745) grad_norm: 1.9228 (1.9890) time: 0.6310 [2021-03-27 19:34:22 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 800/1251] eta: 0:04:45 lr: 0.000268 loss: 3.1669 (3.0745) grad_norm: 2.0362 (1.9894) time: 0.6289 [2021-03-27 19:34:28 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 810/1251] eta: 0:04:39 lr: 0.000268 loss: 3.2006 (3.0780) grad_norm: 1.9375 (1.9875) time: 0.6291 [2021-03-27 19:34:34 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 820/1251] eta: 0:04:33 lr: 0.000268 loss: 3.1617 (3.0754) grad_norm: 1.8437 (1.9871) time: 0.6308 [2021-03-27 19:34:41 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 830/1251] eta: 0:04:26 lr: 0.000268 loss: 3.0042 (3.0783) grad_norm: 1.9198 (1.9872) time: 0.6362 [2021-03-27 19:34:47 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 840/1251] eta: 0:04:20 lr: 0.000268 loss: 3.2532 (3.0768) grad_norm: 1.9559 (1.9872) time: 0.6390 [2021-03-27 19:34:53 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 850/1251] eta: 0:04:14 lr: 0.000268 loss: 2.8973 (3.0714) grad_norm: 1.9226 (1.9868) time: 0.6356 [2021-03-27 19:35:00 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 860/1251] eta: 0:04:07 lr: 0.000268 loss: 3.0519 (3.0734) grad_norm: 1.9622 (1.9889) time: 0.6290 [2021-03-27 19:35:06 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 870/1251] eta: 0:04:01 lr: 0.000268 loss: 3.0940 (3.0690) grad_norm: 1.9629 (1.9883) time: 0.6235 [2021-03-27 19:35:12 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 880/1251] eta: 0:03:55 lr: 0.000268 loss: 2.6611 (3.0682) grad_norm: 1.8916 (1.9878) time: 0.6231 [2021-03-27 19:35:18 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 890/1251] eta: 0:03:48 lr: 0.000268 loss: 2.9790 (3.0662) grad_norm: 1.8965 (1.9862) time: 0.6231 [2021-03-27 19:35:25 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 900/1251] eta: 0:03:42 lr: 0.000268 loss: 3.3945 (3.0692) grad_norm: 1.9177 (1.9881) time: 0.6230 [2021-03-27 19:35:31 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 910/1251] eta: 0:03:36 lr: 0.000268 loss: 3.3316 (3.0701) grad_norm: 1.9219 (1.9872) time: 0.6294 [2021-03-27 19:35:37 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 920/1251] eta: 0:03:29 lr: 0.000268 loss: 3.0957 (3.0687) grad_norm: 1.8828 (1.9870) time: 0.6327 [2021-03-27 19:35:44 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 930/1251] eta: 0:03:23 lr: 0.000268 loss: 2.9907 (3.0665) grad_norm: 1.9821 (1.9874) time: 0.6306 [2021-03-27 19:35:50 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 940/1251] eta: 0:03:16 lr: 0.000268 loss: 3.0577 (3.0670) grad_norm: 1.8776 (1.9868) time: 0.6287 [2021-03-27 19:35:56 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 950/1251] eta: 0:03:10 lr: 0.000268 loss: 3.1424 (3.0665) grad_norm: 1.7829 (1.9859) time: 0.6335 [2021-03-27 19:36:02 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 960/1251] eta: 0:03:04 lr: 0.000268 loss: 3.0355 (3.0659) grad_norm: 1.9278 (1.9874) time: 0.6328 [2021-03-27 19:36:09 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 970/1251] eta: 0:02:57 lr: 0.000268 loss: 3.0472 (3.0667) grad_norm: 2.0015 (1.9874) time: 0.6282 [2021-03-27 19:36:15 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 980/1251] eta: 0:02:51 lr: 0.000268 loss: 3.1580 (3.0684) grad_norm: 1.9143 (1.9871) time: 0.6297 [2021-03-27 19:36:21 swin_base_patch4_window7_224] INFO: Epoch: [197] [ 990/1251] eta: 0:02:45 lr: 0.000267 loss: 3.3310 (3.0696) grad_norm: 1.8866 (1.9859) time: 0.6265 [2021-03-27 19:36:28 swin_base_patch4_window7_224] INFO: Epoch: [197] [1000/1251] eta: 0:02:38 lr: 0.000267 loss: 3.3312 (3.0713) grad_norm: 1.7501 (1.9839) time: 0.6247 [2021-03-27 19:36:34 swin_base_patch4_window7_224] INFO: Epoch: [197] [1010/1251] eta: 0:02:32 lr: 0.000267 loss: 3.3312 (3.0716) grad_norm: 1.7291 (1.9833) time: 0.6276 [2021-03-27 19:36:40 swin_base_patch4_window7_224] INFO: Epoch: [197] [1020/1251] eta: 0:02:26 lr: 0.000267 loss: 3.1369 (3.0713) grad_norm: 1.8919 (1.9842) time: 0.6346 [2021-03-27 19:36:46 swin_base_patch4_window7_224] INFO: Epoch: [197] [1030/1251] eta: 0:02:19 lr: 0.000267 loss: 3.1060 (3.0707) grad_norm: 2.0145 (1.9859) time: 0.6292 [2021-03-27 19:36:53 swin_base_patch4_window7_224] INFO: Epoch: [197] [1040/1251] eta: 0:02:13 lr: 0.000267 loss: 3.1247 (3.0704) grad_norm: 2.0272 (1.9872) time: 0.6272 [2021-03-27 19:36:59 swin_base_patch4_window7_224] INFO: Epoch: [197] [1050/1251] eta: 0:02:07 lr: 0.000267 loss: 3.3106 (3.0719) grad_norm: 2.0171 (1.9874) time: 0.6313 [2021-03-27 19:37:05 swin_base_patch4_window7_224] INFO: Epoch: [197] [1060/1251] eta: 0:02:00 lr: 0.000267 loss: 3.1562 (3.0706) grad_norm: 1.9404 (1.9862) time: 0.6329 [2021-03-27 19:37:12 swin_base_patch4_window7_224] INFO: Epoch: [197] [1070/1251] eta: 0:01:54 lr: 0.000267 loss: 3.1562 (3.0712) grad_norm: 1.8413 (1.9859) time: 0.6305 [2021-03-27 19:37:18 swin_base_patch4_window7_224] INFO: Epoch: [197] [1080/1251] eta: 0:01:48 lr: 0.000267 loss: 3.2047 (3.0716) grad_norm: 1.8557 (1.9851) time: 0.6241 [2021-03-27 19:37:24 swin_base_patch4_window7_224] INFO: Epoch: [197] [1090/1251] eta: 0:01:41 lr: 0.000267 loss: 3.2047 (3.0718) grad_norm: 1.8557 (1.9838) time: 0.6287 [2021-03-27 19:37:31 swin_base_patch4_window7_224] INFO: Epoch: [197] [1100/1251] eta: 0:01:35 lr: 0.000267 loss: 3.0324 (3.0709) grad_norm: 1.9169 (1.9854) time: 0.6290 [2021-03-27 19:37:37 swin_base_patch4_window7_224] INFO: Epoch: [197] [1110/1251] eta: 0:01:29 lr: 0.000267 loss: 2.8868 (3.0691) grad_norm: 1.8545 (1.9830) time: 0.6261 [2021-03-27 19:37:43 swin_base_patch4_window7_224] INFO: Epoch: [197] [1120/1251] eta: 0:01:22 lr: 0.000267 loss: 3.1097 (3.0708) grad_norm: 1.7162 (1.9813) time: 0.6276 [2021-03-27 19:37:49 swin_base_patch4_window7_224] INFO: Epoch: [197] [1130/1251] eta: 0:01:16 lr: 0.000267 loss: 3.1642 (3.0713) grad_norm: 1.8176 (1.9802) time: 0.6294 [2021-03-27 19:37:56 swin_base_patch4_window7_224] INFO: Epoch: [197] [1140/1251] eta: 0:01:10 lr: 0.000267 loss: 3.0219 (3.0703) grad_norm: 1.8158 (1.9790) time: 0.6250 [2021-03-27 19:38:02 swin_base_patch4_window7_224] INFO: Epoch: [197] [1150/1251] eta: 0:01:03 lr: 0.000267 loss: 3.0219 (3.0703) grad_norm: 1.8290 (1.9783) time: 0.6270 [2021-03-27 19:38:08 swin_base_patch4_window7_224] INFO: Epoch: [197] [1160/1251] eta: 0:00:57 lr: 0.000267 loss: 3.0596 (3.0705) grad_norm: 1.8459 (1.9774) time: 0.6316 [2021-03-27 19:38:14 swin_base_patch4_window7_224] INFO: Epoch: [197] [1170/1251] eta: 0:00:51 lr: 0.000267 loss: 3.0596 (3.0694) grad_norm: 1.8598 (1.9795) time: 0.6277 [2021-03-27 19:38:21 swin_base_patch4_window7_224] INFO: Epoch: [197] [1180/1251] eta: 0:00:44 lr: 0.000267 loss: 3.0981 (3.0695) grad_norm: 1.9523 (1.9788) time: 0.6254 [2021-03-27 19:38:27 swin_base_patch4_window7_224] INFO: Epoch: [197] [1190/1251] eta: 0:00:38 lr: 0.000267 loss: 3.1771 (3.0705) grad_norm: 1.9205 (inf) time: 0.6203 [2021-03-27 19:38:33 swin_base_patch4_window7_224] INFO: Epoch: [197] [1200/1251] eta: 0:00:32 lr: 0.000267 loss: 3.1771 (3.0702) grad_norm: 1.8348 (inf) time: 0.6204 [2021-03-27 19:38:40 swin_base_patch4_window7_224] INFO: Epoch: [197] [1210/1251] eta: 0:00:25 lr: 0.000267 loss: 3.0917 (3.0699) grad_norm: 1.8050 (inf) time: 0.6301 [2021-03-27 19:38:46 swin_base_patch4_window7_224] INFO: Epoch: [197] [1220/1251] eta: 0:00:19 lr: 0.000267 loss: 3.1664 (3.0703) grad_norm: 1.8176 (inf) time: 0.6319 [2021-03-27 19:38:52 swin_base_patch4_window7_224] INFO: Epoch: [197] [1230/1251] eta: 0:00:13 lr: 0.000267 loss: 3.1734 (3.0700) grad_norm: 1.7953 (inf) time: 0.6258 [2021-03-27 19:38:58 swin_base_patch4_window7_224] INFO: Epoch: [197] [1240/1251] eta: 0:00:06 lr: 0.000267 loss: 3.0191 (3.0695) grad_norm: 1.8685 (inf) time: 0.6231 [2021-03-27 19:39:05 swin_base_patch4_window7_224] INFO: Epoch: [197] [1250/1251] eta: 0:00:00 lr: 0.000267 loss: 3.0983 (3.0699) grad_norm: 1.8867 (inf) time: 0.6265 [2021-03-27 19:39:15 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:16 loss: 0.7112 (0.7112) acc1: 84.3750 (84.3750) acc5: 100.0000 (100.0000) [2021-03-27 19:39:18 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.6623 (0.7145) acc1: 85.9375 (84.3750) acc5: 96.8750 (97.1591) [2021-03-27 19:39:20 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7606 (0.7907) acc1: 82.8125 (81.6220) acc5: 96.8750 (96.5030) [2021-03-27 19:39:22 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8343 (0.8166) acc1: 79.6875 (80.8468) acc5: 95.3125 (96.2198) [2021-03-27 19:39:24 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8752 (0.8320) acc1: 79.6875 (80.5640) acc5: 95.3125 (95.6936) [2021-03-27 19:39:25 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9019 (0.8386) acc1: 79.6875 (80.1920) acc5: 95.3125 (95.7120) [2021-03-27 19:39:34 swin_base_patch4_window7_224] INFO: * Acc@1 81.016 Acc@5 95.642 loss 0.821 [2021-03-27 19:39:34 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.0% [2021-03-27 19:39:34 swin_base_patch4_window7_224] INFO: Max accuracy: 81.02% [2021-03-27 19:39:38 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 0/1251] eta: 1:32:00 lr: 0.000267 loss: 3.2096 (3.2096) grad_norm: 1.9685 (1.9685) time: 4.4126 [2021-03-27 19:39:44 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 10/1251] eta: 0:20:14 lr: 0.000266 loss: 3.2533 (3.2800) grad_norm: 1.9141 (1.9510) time: 0.9783 [2021-03-27 19:39:51 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 20/1251] eta: 0:16:38 lr: 0.000266 loss: 3.4092 (3.3512) grad_norm: 1.9141 (1.9443) time: 0.6314 [2021-03-27 19:39:57 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 30/1251] eta: 0:15:19 lr: 0.000266 loss: 3.4358 (3.3572) grad_norm: 1.9608 (1.9618) time: 0.6296 [2021-03-27 19:40:03 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 40/1251] eta: 0:14:35 lr: 0.000266 loss: 3.3917 (3.3090) grad_norm: 1.8715 (1.9460) time: 0.6293 [2021-03-27 19:40:10 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 50/1251] eta: 0:14:06 lr: 0.000266 loss: 3.0716 (3.2440) grad_norm: 1.8836 (1.9584) time: 0.6287 [2021-03-27 19:40:16 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 60/1251] eta: 0:13:44 lr: 0.000266 loss: 3.0587 (3.1996) grad_norm: 1.8918 (1.9356) time: 0.6308 [2021-03-27 19:40:22 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 70/1251] eta: 0:13:27 lr: 0.000266 loss: 3.0381 (3.1804) grad_norm: 1.8113 (1.9172) time: 0.6308 [2021-03-27 19:40:29 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 80/1251] eta: 0:13:14 lr: 0.000266 loss: 3.3545 (3.1738) grad_norm: 1.8124 (1.9183) time: 0.6353 [2021-03-27 19:40:35 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 90/1251] eta: 0:13:02 lr: 0.000266 loss: 3.1716 (3.1652) grad_norm: 1.8124 (1.9169) time: 0.6393 [2021-03-27 19:40:41 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 100/1251] eta: 0:12:50 lr: 0.000266 loss: 3.1316 (3.1425) grad_norm: 1.7734 (1.9232) time: 0.6330 [2021-03-27 19:40:48 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 110/1251] eta: 0:12:39 lr: 0.000266 loss: 3.1361 (3.1459) grad_norm: 1.7893 (1.9217) time: 0.6304 [2021-03-27 19:40:54 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 120/1251] eta: 0:12:30 lr: 0.000266 loss: 3.0252 (3.1264) grad_norm: 1.9411 (1.9299) time: 0.6339 [2021-03-27 19:41:00 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 130/1251] eta: 0:12:21 lr: 0.000266 loss: 2.9160 (3.1298) grad_norm: 1.9342 (1.9350) time: 0.6354 [2021-03-27 19:41:07 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 140/1251] eta: 0:12:12 lr: 0.000266 loss: 3.0324 (3.1207) grad_norm: 1.9550 (1.9385) time: 0.6324 [2021-03-27 19:41:13 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 150/1251] eta: 0:12:03 lr: 0.000266 loss: 3.0997 (3.1223) grad_norm: 2.0244 (1.9468) time: 0.6310 [2021-03-27 19:41:19 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 160/1251] eta: 0:11:54 lr: 0.000266 loss: 2.9687 (3.1086) grad_norm: 1.8621 (1.9398) time: 0.6277 [2021-03-27 19:41:25 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 170/1251] eta: 0:11:46 lr: 0.000266 loss: 3.0832 (3.1064) grad_norm: 1.8343 (1.9414) time: 0.6247 [2021-03-27 19:41:32 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 180/1251] eta: 0:11:38 lr: 0.000266 loss: 3.1619 (3.0872) grad_norm: 2.0255 (1.9674) time: 0.6270 [2021-03-27 19:41:38 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 190/1251] eta: 0:11:30 lr: 0.000266 loss: 3.1122 (3.0815) grad_norm: 1.9002 (1.9614) time: 0.6278 [2021-03-27 19:41:44 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 200/1251] eta: 0:11:22 lr: 0.000266 loss: 3.1995 (3.0925) grad_norm: 1.8346 (1.9564) time: 0.6292 [2021-03-27 19:41:51 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 210/1251] eta: 0:11:16 lr: 0.000266 loss: 3.2629 (3.0927) grad_norm: 1.9016 (1.9594) time: 0.6372 [2021-03-27 19:41:57 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 220/1251] eta: 0:11:08 lr: 0.000266 loss: 3.2449 (3.0893) grad_norm: 1.9945 (1.9592) time: 0.6393 [2021-03-27 19:42:03 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 230/1251] eta: 0:11:01 lr: 0.000266 loss: 3.1854 (3.0883) grad_norm: 1.9109 (1.9590) time: 0.6338 [2021-03-27 19:42:10 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 240/1251] eta: 0:10:54 lr: 0.000266 loss: 3.0543 (3.0791) grad_norm: 1.8443 (1.9513) time: 0.6318 [2021-03-27 19:42:16 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 250/1251] eta: 0:10:47 lr: 0.000266 loss: 3.0543 (3.0773) grad_norm: 1.7998 (1.9490) time: 0.6331 [2021-03-27 19:42:22 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 260/1251] eta: 0:10:40 lr: 0.000266 loss: 3.3229 (3.0819) grad_norm: 1.9019 (1.9453) time: 0.6297 [2021-03-27 19:42:29 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 270/1251] eta: 0:10:33 lr: 0.000266 loss: 3.2767 (3.0809) grad_norm: 1.9019 (1.9431) time: 0.6246 [2021-03-27 19:42:35 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 280/1251] eta: 0:10:26 lr: 0.000266 loss: 3.0381 (3.0745) grad_norm: 1.9229 (1.9432) time: 0.6300 [2021-03-27 19:42:41 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 290/1251] eta: 0:10:18 lr: 0.000265 loss: 3.0197 (3.0728) grad_norm: 1.9785 (1.9475) time: 0.6274 [2021-03-27 19:42:48 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 300/1251] eta: 0:10:12 lr: 0.000265 loss: 2.7598 (3.0635) grad_norm: 2.0143 (1.9553) time: 0.6265 [2021-03-27 19:42:54 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 310/1251] eta: 0:10:05 lr: 0.000265 loss: 2.8536 (3.0597) grad_norm: 1.9788 (1.9543) time: 0.6352 [2021-03-27 19:43:00 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 320/1251] eta: 0:09:58 lr: 0.000265 loss: 2.8650 (3.0503) grad_norm: 1.9216 (1.9567) time: 0.6352 [2021-03-27 19:43:06 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 330/1251] eta: 0:09:51 lr: 0.000265 loss: 2.9220 (3.0488) grad_norm: 1.9361 (1.9550) time: 0.6284 [2021-03-27 19:43:13 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 340/1251] eta: 0:09:45 lr: 0.000265 loss: 3.2786 (3.0491) grad_norm: 1.9197 (1.9550) time: 0.6274 [2021-03-27 19:43:19 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 350/1251] eta: 0:09:38 lr: 0.000265 loss: 3.0690 (3.0473) grad_norm: 1.9197 (1.9548) time: 0.6282 [2021-03-27 19:43:25 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 360/1251] eta: 0:09:31 lr: 0.000265 loss: 2.9771 (3.0390) grad_norm: 1.8968 (1.9587) time: 0.6278 [2021-03-27 19:43:32 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 370/1251] eta: 0:09:24 lr: 0.000265 loss: 3.1140 (3.0436) grad_norm: 1.7826 (1.9540) time: 0.6274 [2021-03-27 19:43:38 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 380/1251] eta: 0:09:18 lr: 0.000265 loss: 3.1489 (3.0475) grad_norm: 1.7212 (1.9494) time: 0.6341 [2021-03-27 19:43:44 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 390/1251] eta: 0:09:11 lr: 0.000265 loss: 3.2562 (3.0539) grad_norm: 1.8313 (1.9496) time: 0.6376 [2021-03-27 19:43:51 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 400/1251] eta: 0:09:05 lr: 0.000265 loss: 3.3782 (3.0614) grad_norm: 1.9700 (1.9661) time: 0.6306 [2021-03-27 19:43:57 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 410/1251] eta: 0:08:58 lr: 0.000265 loss: 3.3027 (3.0655) grad_norm: 2.0030 (1.9680) time: 0.6276 [2021-03-27 19:44:03 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 420/1251] eta: 0:08:51 lr: 0.000265 loss: 3.1260 (3.0676) grad_norm: 2.1021 (1.9715) time: 0.6239 [2021-03-27 19:44:09 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 430/1251] eta: 0:08:44 lr: 0.000265 loss: 3.0461 (3.0644) grad_norm: 2.1141 (1.9729) time: 0.6233 [2021-03-27 19:44:16 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 440/1251] eta: 0:08:38 lr: 0.000265 loss: 2.8626 (3.0552) grad_norm: 1.9257 (1.9756) time: 0.6250 [2021-03-27 19:44:22 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 450/1251] eta: 0:08:31 lr: 0.000265 loss: 2.8626 (3.0533) grad_norm: 1.8799 (1.9735) time: 0.6283 [2021-03-27 19:44:28 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 460/1251] eta: 0:08:25 lr: 0.000265 loss: 2.9096 (3.0514) grad_norm: 1.8490 (1.9765) time: 0.6284 [2021-03-27 19:44:34 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 470/1251] eta: 0:08:18 lr: 0.000265 loss: 2.9804 (3.0539) grad_norm: 1.7726 (1.9740) time: 0.6239 [2021-03-27 19:44:41 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 480/1251] eta: 0:08:11 lr: 0.000265 loss: 3.1568 (3.0509) grad_norm: 1.7536 (1.9702) time: 0.6250 [2021-03-27 19:44:47 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 490/1251] eta: 0:08:05 lr: 0.000265 loss: 3.1182 (3.0462) grad_norm: 1.8495 (1.9702) time: 0.6294 [2021-03-27 19:44:53 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 500/1251] eta: 0:07:58 lr: 0.000265 loss: 3.1317 (3.0473) grad_norm: 1.8861 (1.9722) time: 0.6300 [2021-03-27 19:44:59 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 510/1251] eta: 0:07:52 lr: 0.000265 loss: 3.2302 (3.0534) grad_norm: 1.8177 (1.9712) time: 0.6242 [2021-03-27 19:45:06 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 520/1251] eta: 0:07:45 lr: 0.000265 loss: 3.2001 (3.0539) grad_norm: 1.8505 (1.9703) time: 0.6263 [2021-03-27 19:45:12 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 530/1251] eta: 0:07:39 lr: 0.000265 loss: 3.2001 (3.0593) grad_norm: 1.8760 (1.9695) time: 0.6300 [2021-03-27 19:45:18 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 540/1251] eta: 0:07:32 lr: 0.000265 loss: 3.2856 (3.0613) grad_norm: 1.9071 (1.9690) time: 0.6253 [2021-03-27 19:45:25 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 550/1251] eta: 0:07:26 lr: 0.000265 loss: 3.1364 (3.0614) grad_norm: 1.8896 (1.9668) time: 0.6366 [2021-03-27 19:45:31 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 560/1251] eta: 0:07:20 lr: 0.000265 loss: 3.1531 (3.0616) grad_norm: 1.7916 (1.9647) time: 0.6365 [2021-03-27 19:45:37 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 570/1251] eta: 0:07:13 lr: 0.000264 loss: 3.2119 (3.0617) grad_norm: 1.8492 (1.9655) time: 0.6268 [2021-03-27 19:45:44 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 580/1251] eta: 0:07:07 lr: 0.000264 loss: 3.1461 (3.0604) grad_norm: 2.0072 (1.9658) time: 0.6279 [2021-03-27 19:45:50 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 590/1251] eta: 0:07:00 lr: 0.000264 loss: 3.2922 (3.0634) grad_norm: 2.0385 (1.9691) time: 0.6327 [2021-03-27 19:45:56 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 600/1251] eta: 0:06:54 lr: 0.000264 loss: 3.3107 (3.0616) grad_norm: 2.0709 (1.9700) time: 0.6323 [2021-03-27 19:46:03 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 610/1251] eta: 0:06:47 lr: 0.000264 loss: 2.9031 (3.0583) grad_norm: 1.8955 (1.9722) time: 0.6280 [2021-03-27 19:46:09 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 620/1251] eta: 0:06:41 lr: 0.000264 loss: 2.9682 (3.0588) grad_norm: 1.9151 (1.9717) time: 0.6268 [2021-03-27 19:46:15 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 630/1251] eta: 0:06:34 lr: 0.000264 loss: 3.0591 (3.0551) grad_norm: 2.0261 (1.9797) time: 0.6263 [2021-03-27 19:46:21 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 640/1251] eta: 0:06:28 lr: 0.000264 loss: 3.0576 (3.0540) grad_norm: 2.0380 (1.9801) time: 0.6314 [2021-03-27 19:46:28 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 650/1251] eta: 0:06:22 lr: 0.000264 loss: 2.9278 (3.0545) grad_norm: 1.9606 (1.9812) time: 0.6286 [2021-03-27 19:46:34 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 660/1251] eta: 0:06:15 lr: 0.000264 loss: 3.0354 (3.0539) grad_norm: 1.9231 (1.9809) time: 0.6293 [2021-03-27 19:46:40 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 670/1251] eta: 0:06:09 lr: 0.000264 loss: 3.2385 (3.0569) grad_norm: 1.8974 (1.9796) time: 0.6280 [2021-03-27 19:46:47 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 680/1251] eta: 0:06:02 lr: 0.000264 loss: 3.3297 (3.0568) grad_norm: 1.9491 (1.9803) time: 0.6293 [2021-03-27 19:46:53 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 690/1251] eta: 0:05:56 lr: 0.000264 loss: 3.2364 (3.0564) grad_norm: 1.9076 (1.9795) time: 0.6329 [2021-03-27 19:46:59 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 700/1251] eta: 0:05:50 lr: 0.000264 loss: 3.2364 (3.0570) grad_norm: 1.9024 (1.9780) time: 0.6262 [2021-03-27 19:47:05 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 710/1251] eta: 0:05:43 lr: 0.000264 loss: 3.1968 (3.0597) grad_norm: 1.9207 (1.9780) time: 0.6257 [2021-03-27 19:47:12 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 720/1251] eta: 0:05:37 lr: 0.000264 loss: 3.1968 (3.0611) grad_norm: 1.9634 (1.9784) time: 0.6262 [2021-03-27 19:47:18 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 730/1251] eta: 0:05:30 lr: 0.000264 loss: 3.1400 (3.0624) grad_norm: 1.9752 (1.9800) time: 0.6245 [2021-03-27 19:47:24 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 740/1251] eta: 0:05:24 lr: 0.000264 loss: 3.2351 (3.0645) grad_norm: 1.9188 (1.9801) time: 0.6275 [2021-03-27 19:47:31 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 750/1251] eta: 0:05:18 lr: 0.000264 loss: 2.9275 (3.0594) grad_norm: 1.8511 (1.9805) time: 0.6326 [2021-03-27 19:47:37 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 760/1251] eta: 0:05:11 lr: 0.000264 loss: 2.7260 (3.0563) grad_norm: 1.7686 (1.9786) time: 0.6292 [2021-03-27 19:47:43 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 770/1251] eta: 0:05:05 lr: 0.000264 loss: 2.9457 (3.0563) grad_norm: 1.7686 (1.9775) time: 0.6251 [2021-03-27 19:47:49 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 780/1251] eta: 0:04:58 lr: 0.000264 loss: 3.0959 (3.0556) grad_norm: 1.8680 (1.9770) time: 0.6304 [2021-03-27 19:47:56 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 790/1251] eta: 0:04:52 lr: 0.000264 loss: 3.0432 (3.0555) grad_norm: 1.9921 (1.9777) time: 0.6307 [2021-03-27 19:48:02 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 800/1251] eta: 0:04:46 lr: 0.000264 loss: 2.9790 (3.0564) grad_norm: 1.9300 (1.9769) time: 0.6273 [2021-03-27 19:48:08 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 810/1251] eta: 0:04:39 lr: 0.000264 loss: 3.3425 (3.0584) grad_norm: 1.8941 (1.9756) time: 0.6252 [2021-03-27 19:48:14 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 820/1251] eta: 0:04:33 lr: 0.000264 loss: 3.1034 (3.0571) grad_norm: 1.9262 (1.9765) time: 0.6235 [2021-03-27 19:48:21 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 830/1251] eta: 0:04:26 lr: 0.000264 loss: 3.0271 (3.0582) grad_norm: 1.9571 (1.9754) time: 0.6262 [2021-03-27 19:48:27 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 840/1251] eta: 0:04:20 lr: 0.000263 loss: 3.0511 (3.0549) grad_norm: 1.9007 (1.9750) time: 0.6288 [2021-03-27 19:48:33 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 850/1251] eta: 0:04:14 lr: 0.000263 loss: 3.1293 (3.0566) grad_norm: 1.9019 (1.9756) time: 0.6282 [2021-03-27 19:48:40 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 860/1251] eta: 0:04:07 lr: 0.000263 loss: 3.2205 (3.0585) grad_norm: 1.8734 (1.9745) time: 0.6338 [2021-03-27 19:48:46 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 870/1251] eta: 0:04:01 lr: 0.000263 loss: 3.1653 (3.0564) grad_norm: 1.8667 (1.9733) time: 0.6356 [2021-03-27 19:48:52 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 880/1251] eta: 0:03:55 lr: 0.000263 loss: 2.9367 (3.0548) grad_norm: 1.8297 (1.9723) time: 0.6326 [2021-03-27 19:48:59 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 890/1251] eta: 0:03:48 lr: 0.000263 loss: 3.0247 (3.0549) grad_norm: 1.8950 (1.9738) time: 0.6357 [2021-03-27 19:49:05 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 900/1251] eta: 0:03:42 lr: 0.000263 loss: 2.7233 (3.0518) grad_norm: 1.8475 (1.9726) time: 0.6314 [2021-03-27 19:49:11 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 910/1251] eta: 0:03:36 lr: 0.000263 loss: 2.8562 (3.0527) grad_norm: 1.8236 (1.9729) time: 0.6261 [2021-03-27 19:49:17 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 920/1251] eta: 0:03:29 lr: 0.000263 loss: 3.1890 (3.0544) grad_norm: 1.8236 (1.9716) time: 0.6253 [2021-03-27 19:49:24 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 930/1251] eta: 0:03:23 lr: 0.000263 loss: 3.2587 (3.0552) grad_norm: 1.9648 (1.9748) time: 0.6242 [2021-03-27 19:49:30 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 940/1251] eta: 0:03:17 lr: 0.000263 loss: 2.9762 (3.0535) grad_norm: 2.0259 (1.9745) time: 0.6221 [2021-03-27 19:49:36 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 950/1251] eta: 0:03:10 lr: 0.000263 loss: 2.9762 (3.0528) grad_norm: 1.8662 (1.9735) time: 0.6307 [2021-03-27 19:49:43 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 960/1251] eta: 0:03:04 lr: 0.000263 loss: 3.0032 (3.0535) grad_norm: 1.8225 (1.9724) time: 0.6361 [2021-03-27 19:49:49 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 970/1251] eta: 0:02:58 lr: 0.000263 loss: 3.0220 (3.0535) grad_norm: 1.8464 (1.9721) time: 0.6291 [2021-03-27 19:49:55 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 980/1251] eta: 0:02:51 lr: 0.000263 loss: 3.0220 (3.0517) grad_norm: 1.8546 (1.9720) time: 0.6240 [2021-03-27 19:50:01 swin_base_patch4_window7_224] INFO: Epoch: [198] [ 990/1251] eta: 0:02:45 lr: 0.000263 loss: 3.0049 (3.0506) grad_norm: 1.9382 (1.9718) time: 0.6233 [2021-03-27 19:50:08 swin_base_patch4_window7_224] INFO: Epoch: [198] [1000/1251] eta: 0:02:38 lr: 0.000263 loss: 3.0146 (3.0512) grad_norm: 1.9483 (1.9728) time: 0.6290 [2021-03-27 19:50:14 swin_base_patch4_window7_224] INFO: Epoch: [198] [1010/1251] eta: 0:02:32 lr: 0.000263 loss: 3.1986 (3.0507) grad_norm: 1.9666 (1.9718) time: 0.6300 [2021-03-27 19:50:20 swin_base_patch4_window7_224] INFO: Epoch: [198] [1020/1251] eta: 0:02:26 lr: 0.000263 loss: 2.9808 (3.0486) grad_norm: 1.9534 (1.9714) time: 0.6255 [2021-03-27 19:50:27 swin_base_patch4_window7_224] INFO: Epoch: [198] [1030/1251] eta: 0:02:19 lr: 0.000263 loss: 3.1134 (3.0486) grad_norm: 1.9337 (1.9711) time: 0.6238 [2021-03-27 19:50:33 swin_base_patch4_window7_224] INFO: Epoch: [198] [1040/1251] eta: 0:02:13 lr: 0.000263 loss: 3.1228 (3.0481) grad_norm: 1.9419 (1.9728) time: 0.6311 [2021-03-27 19:50:39 swin_base_patch4_window7_224] INFO: Epoch: [198] [1050/1251] eta: 0:02:07 lr: 0.000263 loss: 3.0436 (3.0474) grad_norm: 2.0036 (1.9734) time: 0.6365 [2021-03-27 19:50:45 swin_base_patch4_window7_224] INFO: Epoch: [198] [1060/1251] eta: 0:02:00 lr: 0.000263 loss: 3.1203 (3.0475) grad_norm: 1.8318 (1.9718) time: 0.6297 [2021-03-27 19:50:52 swin_base_patch4_window7_224] INFO: Epoch: [198] [1070/1251] eta: 0:01:54 lr: 0.000263 loss: 3.1744 (3.0488) grad_norm: 1.8288 (1.9725) time: 0.6313 [2021-03-27 19:50:58 swin_base_patch4_window7_224] INFO: Epoch: [198] [1080/1251] eta: 0:01:48 lr: 0.000263 loss: 3.3347 (3.0510) grad_norm: 1.9087 (1.9725) time: 0.6321 [2021-03-27 19:51:04 swin_base_patch4_window7_224] INFO: Epoch: [198] [1090/1251] eta: 0:01:41 lr: 0.000263 loss: 3.2858 (3.0515) grad_norm: 1.8579 (1.9712) time: 0.6285 [2021-03-27 19:51:11 swin_base_patch4_window7_224] INFO: Epoch: [198] [1100/1251] eta: 0:01:35 lr: 0.000263 loss: 3.1700 (3.0518) grad_norm: 1.7904 (1.9703) time: 0.6301 [2021-03-27 19:51:17 swin_base_patch4_window7_224] INFO: Epoch: [198] [1110/1251] eta: 0:01:29 lr: 0.000263 loss: 3.1648 (3.0525) grad_norm: 1.9088 (1.9718) time: 0.6278 [2021-03-27 19:51:23 swin_base_patch4_window7_224] INFO: Epoch: [198] [1120/1251] eta: 0:01:22 lr: 0.000262 loss: 3.1648 (3.0533) grad_norm: 2.0139 (1.9725) time: 0.6253 [2021-03-27 19:51:29 swin_base_patch4_window7_224] INFO: Epoch: [198] [1130/1251] eta: 0:01:16 lr: 0.000262 loss: 3.1727 (3.0534) grad_norm: 2.0139 (1.9782) time: 0.6250 [2021-03-27 19:51:36 swin_base_patch4_window7_224] INFO: Epoch: [198] [1140/1251] eta: 0:01:10 lr: 0.000262 loss: 3.0280 (3.0533) grad_norm: 1.9812 (1.9784) time: 0.6267 [2021-03-27 19:51:42 swin_base_patch4_window7_224] INFO: Epoch: [198] [1150/1251] eta: 0:01:03 lr: 0.000262 loss: 3.0095 (3.0528) grad_norm: 1.8401 (1.9768) time: 0.6324 [2021-03-27 19:51:48 swin_base_patch4_window7_224] INFO: Epoch: [198] [1160/1251] eta: 0:00:57 lr: 0.000262 loss: 2.8977 (3.0509) grad_norm: 1.9277 (1.9777) time: 0.6315 [2021-03-27 19:51:55 swin_base_patch4_window7_224] INFO: Epoch: [198] [1170/1251] eta: 0:00:51 lr: 0.000262 loss: 3.2196 (3.0532) grad_norm: 1.9466 (1.9780) time: 0.6228 [2021-03-27 19:52:01 swin_base_patch4_window7_224] INFO: Epoch: [198] [1180/1251] eta: 0:00:44 lr: 0.000262 loss: 3.2797 (3.0542) grad_norm: 1.9346 (1.9793) time: 0.6276 [2021-03-27 19:52:07 swin_base_patch4_window7_224] INFO: Epoch: [198] [1190/1251] eta: 0:00:38 lr: 0.000262 loss: 3.2079 (3.0564) grad_norm: 1.9513 (1.9793) time: 0.6276 [2021-03-27 19:52:13 swin_base_patch4_window7_224] INFO: Epoch: [198] [1200/1251] eta: 0:00:32 lr: 0.000262 loss: 3.1489 (3.0570) grad_norm: 2.1216 (1.9822) time: 0.6234 [2021-03-27 19:52:20 swin_base_patch4_window7_224] INFO: Epoch: [198] [1210/1251] eta: 0:00:25 lr: 0.000262 loss: 3.0714 (3.0570) grad_norm: 2.1752 (1.9878) time: 0.6268 [2021-03-27 19:52:26 swin_base_patch4_window7_224] INFO: Epoch: [198] [1220/1251] eta: 0:00:19 lr: 0.000262 loss: 3.0419 (3.0565) grad_norm: 1.8818 (1.9872) time: 0.6246 [2021-03-27 19:52:32 swin_base_patch4_window7_224] INFO: Epoch: [198] [1230/1251] eta: 0:00:13 lr: 0.000262 loss: 3.2789 (3.0580) grad_norm: 1.8875 (1.9867) time: 0.6207 [2021-03-27 19:52:38 swin_base_patch4_window7_224] INFO: Epoch: [198] [1240/1251] eta: 0:00:06 lr: 0.000262 loss: 3.1788 (3.0581) grad_norm: 1.9450 (1.9879) time: 0.6218 [2021-03-27 19:52:45 swin_base_patch4_window7_224] INFO: Epoch: [198] [1250/1251] eta: 0:00:00 lr: 0.000262 loss: 3.0877 (3.0575) grad_norm: 1.9022 (1.9870) time: 0.6248 [2021-03-27 19:52:55 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:42 loss: 0.7900 (0.7900) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-27 19:52:57 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.7900 (0.8511) acc1: 82.8125 (80.9659) acc5: 96.8750 (95.3125) [2021-03-27 19:52:59 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.8108 (0.8578) acc1: 82.8125 (81.1012) acc5: 95.3125 (95.0149) [2021-03-27 19:53:01 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.8108 (0.8423) acc1: 82.8125 (80.8972) acc5: 95.3125 (95.4133) [2021-03-27 19:53:02 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7412 (0.8286) acc1: 79.6875 (80.6021) acc5: 96.8750 (95.7698) [2021-03-27 19:53:03 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7384 (0.8190) acc1: 81.2500 (80.8320) acc5: 96.8750 (95.8720) [2021-03-27 19:53:17 swin_base_patch4_window7_224] INFO: * Acc@1 81.062 Acc@5 95.782 loss 0.811 [2021-03-27 19:53:17 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.1% [2021-03-27 19:53:17 swin_base_patch4_window7_224] INFO: Max accuracy: 81.06% [2021-03-27 19:53:22 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 0/1251] eta: 1:34:02 lr: 0.000262 loss: 2.3149 (2.3149) grad_norm: 1.8744 (1.8744) time: 4.5106 [2021-03-27 19:53:28 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 10/1251] eta: 0:20:16 lr: 0.000262 loss: 3.1643 (2.9239) grad_norm: 1.9295 (1.9221) time: 0.9802 [2021-03-27 19:53:35 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 20/1251] eta: 0:16:36 lr: 0.000262 loss: 3.2514 (3.0529) grad_norm: 1.8908 (1.8613) time: 0.6248 [2021-03-27 19:53:41 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 30/1251] eta: 0:15:17 lr: 0.000262 loss: 3.3400 (3.0530) grad_norm: 1.8894 (1.8781) time: 0.6261 [2021-03-27 19:53:47 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 40/1251] eta: 0:14:31 lr: 0.000262 loss: 3.1851 (3.0506) grad_norm: 1.8121 (1.9228) time: 0.6254 [2021-03-27 19:53:53 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 50/1251] eta: 0:14:01 lr: 0.000262 loss: 3.1656 (3.0449) grad_norm: 1.8199 (1.9350) time: 0.6219 [2021-03-27 19:54:00 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 60/1251] eta: 0:13:41 lr: 0.000262 loss: 3.1321 (3.0196) grad_norm: 1.8933 (1.9299) time: 0.6283 [2021-03-27 19:54:06 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 70/1251] eta: 0:13:24 lr: 0.000262 loss: 2.8845 (3.0025) grad_norm: 1.8677 (1.9281) time: 0.6305 [2021-03-27 19:54:12 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 80/1251] eta: 0:13:11 lr: 0.000262 loss: 3.1445 (3.0349) grad_norm: 1.8677 (1.9201) time: 0.6322 [2021-03-27 19:54:19 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 90/1251] eta: 0:12:59 lr: 0.000262 loss: 3.1110 (3.0329) grad_norm: 1.8366 (1.9139) time: 0.6358 [2021-03-27 19:54:25 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 100/1251] eta: 0:12:47 lr: 0.000262 loss: 2.8957 (3.0127) grad_norm: 1.8927 (1.9247) time: 0.6303 [2021-03-27 19:54:31 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 110/1251] eta: 0:12:36 lr: 0.000262 loss: 2.9536 (3.0234) grad_norm: 1.8857 (1.9185) time: 0.6286 [2021-03-27 19:54:37 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 120/1251] eta: 0:12:26 lr: 0.000262 loss: 3.1728 (3.0464) grad_norm: 1.8814 (1.9212) time: 0.6273 [2021-03-27 19:54:44 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 130/1251] eta: 0:12:16 lr: 0.000262 loss: 3.1841 (3.0458) grad_norm: 1.8814 (1.9167) time: 0.6231 [2021-03-27 19:54:50 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 140/1251] eta: 0:12:07 lr: 0.000261 loss: 3.2102 (3.0538) grad_norm: 1.8431 (1.9100) time: 0.6242 [2021-03-27 19:54:56 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 150/1251] eta: 0:11:59 lr: 0.000261 loss: 3.0036 (3.0422) grad_norm: 1.8596 (1.9082) time: 0.6257 [2021-03-27 19:55:02 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 160/1251] eta: 0:11:51 lr: 0.000261 loss: 2.9210 (3.0321) grad_norm: 1.8974 (1.9133) time: 0.6284 [2021-03-27 19:55:09 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 170/1251] eta: 0:11:43 lr: 0.000261 loss: 3.0528 (3.0363) grad_norm: 1.9020 (1.9136) time: 0.6334 [2021-03-27 19:55:15 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 180/1251] eta: 0:11:35 lr: 0.000261 loss: 3.2641 (3.0421) grad_norm: 1.8363 (1.9240) time: 0.6291 [2021-03-27 19:55:21 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 190/1251] eta: 0:11:27 lr: 0.000261 loss: 3.1757 (3.0415) grad_norm: 1.8091 (1.9187) time: 0.6214 [2021-03-27 19:55:28 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 200/1251] eta: 0:11:20 lr: 0.000261 loss: 3.0388 (3.0289) grad_norm: 1.8050 (1.9138) time: 0.6300 [2021-03-27 19:55:34 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 210/1251] eta: 0:11:12 lr: 0.000261 loss: 3.0388 (3.0324) grad_norm: 1.7348 (1.9053) time: 0.6327 [2021-03-27 19:55:40 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 220/1251] eta: 0:11:05 lr: 0.000261 loss: 3.1591 (3.0385) grad_norm: 1.7078 (1.8998) time: 0.6246 [2021-03-27 19:55:46 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 230/1251] eta: 0:10:57 lr: 0.000261 loss: 3.1591 (3.0392) grad_norm: 1.7112 (1.9023) time: 0.6237 [2021-03-27 19:55:53 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 240/1251] eta: 0:10:51 lr: 0.000261 loss: 3.1149 (3.0404) grad_norm: 1.7949 (1.8989) time: 0.6294 [2021-03-27 19:55:59 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 250/1251] eta: 0:10:43 lr: 0.000261 loss: 3.0746 (3.0378) grad_norm: 1.7949 (1.8970) time: 0.6314 [2021-03-27 19:56:05 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 260/1251] eta: 0:10:37 lr: 0.000261 loss: 3.1515 (3.0482) grad_norm: 1.7908 (1.8955) time: 0.6310 [2021-03-27 19:56:12 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 270/1251] eta: 0:10:30 lr: 0.000261 loss: 3.2457 (3.0498) grad_norm: 1.8378 (1.8986) time: 0.6290 [2021-03-27 19:56:18 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 280/1251] eta: 0:10:23 lr: 0.000261 loss: 3.1378 (3.0432) grad_norm: 1.8672 (1.8992) time: 0.6258 [2021-03-27 19:56:24 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 290/1251] eta: 0:10:16 lr: 0.000261 loss: 3.1139 (3.0444) grad_norm: 1.7647 (1.8972) time: 0.6252 [2021-03-27 19:56:30 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 300/1251] eta: 0:10:09 lr: 0.000261 loss: 3.0505 (3.0386) grad_norm: 1.8036 (1.9008) time: 0.6219 [2021-03-27 19:56:37 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 310/1251] eta: 0:10:02 lr: 0.000261 loss: 2.5980 (3.0276) grad_norm: 1.9903 (1.9049) time: 0.6225 [2021-03-27 19:56:43 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 320/1251] eta: 0:09:55 lr: 0.000261 loss: 2.8723 (3.0340) grad_norm: 1.9504 (1.9059) time: 0.6238 [2021-03-27 19:56:49 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 330/1251] eta: 0:09:48 lr: 0.000261 loss: 3.2026 (3.0375) grad_norm: 1.8451 (1.9032) time: 0.6247 [2021-03-27 19:56:55 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 340/1251] eta: 0:09:41 lr: 0.000261 loss: 3.1226 (3.0369) grad_norm: 1.8490 (1.9065) time: 0.6271 [2021-03-27 19:57:02 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 350/1251] eta: 0:09:35 lr: 0.000261 loss: 3.1077 (3.0362) grad_norm: 1.8352 (1.9054) time: 0.6273 [2021-03-27 19:57:08 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 360/1251] eta: 0:09:28 lr: 0.000261 loss: 3.1146 (3.0400) grad_norm: 1.8204 (1.9027) time: 0.6295 [2021-03-27 19:57:14 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 370/1251] eta: 0:09:21 lr: 0.000261 loss: 3.2263 (3.0438) grad_norm: 1.8081 (1.9050) time: 0.6291 [2021-03-27 19:57:20 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 380/1251] eta: 0:09:15 lr: 0.000261 loss: 3.1256 (3.0412) grad_norm: 1.8565 (1.9041) time: 0.6266 [2021-03-27 19:57:27 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 390/1251] eta: 0:09:08 lr: 0.000261 loss: 3.0023 (3.0376) grad_norm: 1.9163 (1.9071) time: 0.6271 [2021-03-27 19:57:33 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 400/1251] eta: 0:09:02 lr: 0.000261 loss: 3.0023 (3.0411) grad_norm: 1.9422 (1.9086) time: 0.6289 [2021-03-27 19:57:39 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 410/1251] eta: 0:08:55 lr: 0.000261 loss: 3.1257 (3.0405) grad_norm: 1.8045 (1.9088) time: 0.6308 [2021-03-27 19:57:46 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 420/1251] eta: 0:08:49 lr: 0.000260 loss: 3.1257 (3.0400) grad_norm: 1.9403 (1.9102) time: 0.6263 [2021-03-27 19:57:52 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 430/1251] eta: 0:08:42 lr: 0.000260 loss: 3.1572 (3.0446) grad_norm: 1.8909 (1.9103) time: 0.6302 [2021-03-27 19:57:58 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 440/1251] eta: 0:08:36 lr: 0.000260 loss: 3.1924 (3.0501) grad_norm: 1.8933 (1.9127) time: 0.6295 [2021-03-27 19:58:04 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 450/1251] eta: 0:08:29 lr: 0.000260 loss: 3.2076 (3.0514) grad_norm: 1.9187 (1.9127) time: 0.6237 [2021-03-27 19:58:11 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 460/1251] eta: 0:08:22 lr: 0.000260 loss: 3.1895 (3.0552) grad_norm: 1.9187 (1.9141) time: 0.6247 [2021-03-27 19:58:17 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 470/1251] eta: 0:08:16 lr: 0.000260 loss: 3.0133 (3.0506) grad_norm: 1.9772 (1.9165) time: 0.6256 [2021-03-27 19:58:23 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 480/1251] eta: 0:08:09 lr: 0.000260 loss: 2.8901 (3.0464) grad_norm: 1.9185 (1.9166) time: 0.6231 [2021-03-27 19:58:29 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 490/1251] eta: 0:08:03 lr: 0.000260 loss: 2.9351 (3.0461) grad_norm: 1.8799 (1.9213) time: 0.6227 [2021-03-27 19:58:36 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 500/1251] eta: 0:07:56 lr: 0.000260 loss: 2.9351 (3.0401) grad_norm: 1.8364 (1.9242) time: 0.6276 [2021-03-27 19:58:42 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 510/1251] eta: 0:07:50 lr: 0.000260 loss: 3.0891 (3.0413) grad_norm: 1.8447 (1.9251) time: 0.6287 [2021-03-27 19:58:48 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 520/1251] eta: 0:07:43 lr: 0.000260 loss: 3.2146 (3.0443) grad_norm: 1.9568 (1.9246) time: 0.6271 [2021-03-27 19:58:54 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 530/1251] eta: 0:07:37 lr: 0.000260 loss: 2.8348 (3.0360) grad_norm: 1.9568 (1.9251) time: 0.6226 [2021-03-27 19:59:01 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 540/1251] eta: 0:07:30 lr: 0.000260 loss: 2.8348 (3.0384) grad_norm: 2.0095 (1.9267) time: 0.6223 [2021-03-27 19:59:07 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 550/1251] eta: 0:07:24 lr: 0.000260 loss: 3.0937 (3.0378) grad_norm: 1.9630 (1.9280) time: 0.6313 [2021-03-27 19:59:13 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 560/1251] eta: 0:07:18 lr: 0.000260 loss: 3.1842 (3.0391) grad_norm: 1.9002 (1.9269) time: 0.6296 [2021-03-27 19:59:20 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 570/1251] eta: 0:07:11 lr: 0.000260 loss: 3.1842 (3.0393) grad_norm: 1.8057 (1.9260) time: 0.6276 [2021-03-27 19:59:26 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 580/1251] eta: 0:07:05 lr: 0.000260 loss: 3.2404 (3.0418) grad_norm: 1.7841 (1.9245) time: 0.6299 [2021-03-27 19:59:32 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 590/1251] eta: 0:06:58 lr: 0.000260 loss: 3.2404 (3.0403) grad_norm: 1.7968 (1.9232) time: 0.6220 [2021-03-27 19:59:38 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 600/1251] eta: 0:06:52 lr: 0.000260 loss: 3.3386 (3.0415) grad_norm: 1.8308 (1.9233) time: 0.6222 [2021-03-27 19:59:45 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 610/1251] eta: 0:06:46 lr: 0.000260 loss: 3.0268 (3.0373) grad_norm: 1.8308 (1.9228) time: 0.6278 [2021-03-27 19:59:51 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 620/1251] eta: 0:06:39 lr: 0.000260 loss: 3.0526 (3.0424) grad_norm: 1.7597 (1.9208) time: 0.6267 [2021-03-27 19:59:57 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 630/1251] eta: 0:06:33 lr: 0.000260 loss: 3.1819 (3.0393) grad_norm: 1.8414 (1.9204) time: 0.6269 [2021-03-27 20:00:03 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 640/1251] eta: 0:06:26 lr: 0.000260 loss: 3.1055 (3.0411) grad_norm: 1.9448 (1.9213) time: 0.6314 [2021-03-27 20:00:10 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 650/1251] eta: 0:06:20 lr: 0.000260 loss: 3.1861 (3.0418) grad_norm: 1.9678 (1.9225) time: 0.6343 [2021-03-27 20:00:16 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 660/1251] eta: 0:06:14 lr: 0.000260 loss: 3.1861 (3.0434) grad_norm: 1.9615 (1.9231) time: 0.6317 [2021-03-27 20:00:22 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 670/1251] eta: 0:06:07 lr: 0.000260 loss: 2.9391 (3.0411) grad_norm: 1.8328 (1.9226) time: 0.6274 [2021-03-27 20:00:29 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 680/1251] eta: 0:06:01 lr: 0.000260 loss: 2.8563 (3.0426) grad_norm: 1.8623 (1.9238) time: 0.6222 [2021-03-27 20:00:35 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 690/1251] eta: 0:05:54 lr: 0.000260 loss: 3.0726 (3.0422) grad_norm: 1.9259 (1.9236) time: 0.6218 [2021-03-27 20:00:41 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 700/1251] eta: 0:05:48 lr: 0.000259 loss: 3.0552 (3.0413) grad_norm: 1.9200 (1.9240) time: 0.6302 [2021-03-27 20:00:47 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 710/1251] eta: 0:05:42 lr: 0.000259 loss: 3.0736 (3.0427) grad_norm: 1.9944 (1.9260) time: 0.6318 [2021-03-27 20:00:54 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 720/1251] eta: 0:05:36 lr: 0.000259 loss: 3.0876 (3.0434) grad_norm: 1.9875 (1.9257) time: 0.6340 [2021-03-27 20:01:00 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 730/1251] eta: 0:05:29 lr: 0.000259 loss: 3.0876 (3.0440) grad_norm: 1.9490 (1.9310) time: 0.6393 [2021-03-27 20:01:07 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 740/1251] eta: 0:05:23 lr: 0.000259 loss: 3.1046 (3.0457) grad_norm: 1.9199 (1.9295) time: 0.6344 [2021-03-27 20:01:13 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 750/1251] eta: 0:05:17 lr: 0.000259 loss: 3.2321 (3.0475) grad_norm: 1.8695 (1.9298) time: 0.6352 [2021-03-27 20:01:19 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 760/1251] eta: 0:05:10 lr: 0.000259 loss: 3.3173 (3.0513) grad_norm: 1.8882 (1.9296) time: 0.6430 [2021-03-27 20:01:26 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 770/1251] eta: 0:05:04 lr: 0.000259 loss: 3.0929 (3.0474) grad_norm: 1.8882 (1.9319) time: 0.6360 [2021-03-27 20:01:32 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 780/1251] eta: 0:04:58 lr: 0.000259 loss: 2.8243 (3.0465) grad_norm: 1.8641 (1.9308) time: 0.6266 [2021-03-27 20:01:38 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 790/1251] eta: 0:04:51 lr: 0.000259 loss: 3.0818 (3.0453) grad_norm: 1.8622 (1.9297) time: 0.6307 [2021-03-27 20:01:45 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 800/1251] eta: 0:04:45 lr: 0.000259 loss: 3.0707 (3.0445) grad_norm: 1.7627 (1.9287) time: 0.6348 [2021-03-27 20:01:51 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 810/1251] eta: 0:04:39 lr: 0.000259 loss: 3.0707 (3.0455) grad_norm: 1.8622 (1.9294) time: 0.6357 [2021-03-27 20:01:57 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 820/1251] eta: 0:04:32 lr: 0.000259 loss: 3.1049 (3.0467) grad_norm: 1.9180 (1.9310) time: 0.6298 [2021-03-27 20:02:04 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 830/1251] eta: 0:04:26 lr: 0.000259 loss: 3.1137 (3.0461) grad_norm: 1.9708 (1.9327) time: 0.6334 [2021-03-27 20:02:10 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 840/1251] eta: 0:04:20 lr: 0.000259 loss: 3.1419 (3.0464) grad_norm: 2.0091 (1.9336) time: 0.6364 [2021-03-27 20:02:16 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 850/1251] eta: 0:04:13 lr: 0.000259 loss: 3.1732 (3.0487) grad_norm: 1.8695 (1.9323) time: 0.6282 [2021-03-27 20:02:22 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 860/1251] eta: 0:04:07 lr: 0.000259 loss: 3.1965 (3.0500) grad_norm: 1.8204 (nan) time: 0.6242 [2021-03-27 20:02:29 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 870/1251] eta: 0:04:01 lr: 0.000259 loss: 3.1268 (3.0513) grad_norm: 1.9538 (nan) time: 0.6265 [2021-03-27 20:02:35 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 880/1251] eta: 0:03:54 lr: 0.000259 loss: 3.1547 (3.0517) grad_norm: 1.9943 (nan) time: 0.6270 [2021-03-27 20:02:41 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 890/1251] eta: 0:03:48 lr: 0.000259 loss: 3.1864 (3.0510) grad_norm: 1.9678 (nan) time: 0.6259 [2021-03-27 20:02:48 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 900/1251] eta: 0:03:42 lr: 0.000259 loss: 3.1864 (3.0511) grad_norm: 1.8394 (nan) time: 0.6279 [2021-03-27 20:02:54 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 910/1251] eta: 0:03:35 lr: 0.000259 loss: 3.1194 (3.0501) grad_norm: 1.8859 (nan) time: 0.6253 [2021-03-27 20:03:00 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 920/1251] eta: 0:03:29 lr: 0.000259 loss: 3.0587 (3.0494) grad_norm: 1.8914 (nan) time: 0.6280 [2021-03-27 20:03:06 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 930/1251] eta: 0:03:22 lr: 0.000259 loss: 2.8598 (3.0479) grad_norm: 1.8946 (nan) time: 0.6246 [2021-03-27 20:03:13 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 940/1251] eta: 0:03:16 lr: 0.000259 loss: 3.1972 (3.0496) grad_norm: 1.8346 (nan) time: 0.6228 [2021-03-27 20:03:19 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 950/1251] eta: 0:03:10 lr: 0.000259 loss: 3.2835 (3.0528) grad_norm: 1.9389 (nan) time: 0.6285 [2021-03-27 20:03:25 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 960/1251] eta: 0:03:03 lr: 0.000259 loss: 3.3173 (3.0540) grad_norm: 1.9255 (nan) time: 0.6269 [2021-03-27 20:03:31 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 970/1251] eta: 0:02:57 lr: 0.000259 loss: 3.2944 (3.0557) grad_norm: 1.8677 (nan) time: 0.6204 [2021-03-27 20:03:37 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 980/1251] eta: 0:02:51 lr: 0.000258 loss: 3.1853 (3.0539) grad_norm: 1.9367 (nan) time: 0.6183 [2021-03-27 20:03:44 swin_base_patch4_window7_224] INFO: Epoch: [199] [ 990/1251] eta: 0:02:44 lr: 0.000258 loss: 3.0126 (3.0530) grad_norm: 1.9367 (nan) time: 0.6267 [2021-03-27 20:03:50 swin_base_patch4_window7_224] INFO: Epoch: [199] [1000/1251] eta: 0:02:38 lr: 0.000258 loss: 3.0126 (3.0521) grad_norm: 1.9468 (nan) time: 0.6281 [2021-03-27 20:03:56 swin_base_patch4_window7_224] INFO: Epoch: [199] [1010/1251] eta: 0:02:32 lr: 0.000258 loss: 2.9322 (3.0493) grad_norm: 1.9687 (nan) time: 0.6257 [2021-03-27 20:04:03 swin_base_patch4_window7_224] INFO: Epoch: [199] [1020/1251] eta: 0:02:25 lr: 0.000258 loss: 2.8930 (3.0492) grad_norm: 1.9687 (nan) time: 0.6311 [2021-03-27 20:04:09 swin_base_patch4_window7_224] INFO: Epoch: [199] [1030/1251] eta: 0:02:19 lr: 0.000258 loss: 2.8930 (3.0476) grad_norm: 1.9340 (nan) time: 0.6253 [2021-03-27 20:04:15 swin_base_patch4_window7_224] INFO: Epoch: [199] [1040/1251] eta: 0:02:13 lr: 0.000258 loss: 2.9085 (3.0465) grad_norm: 1.8464 (nan) time: 0.6207 [2021-03-27 20:04:21 swin_base_patch4_window7_224] INFO: Epoch: [199] [1050/1251] eta: 0:02:06 lr: 0.000258 loss: 3.1634 (3.0471) grad_norm: 1.9846 (nan) time: 0.6216 [2021-03-27 20:04:28 swin_base_patch4_window7_224] INFO: Epoch: [199] [1060/1251] eta: 0:02:00 lr: 0.000258 loss: 3.1634 (3.0469) grad_norm: 2.0182 (nan) time: 0.6237 [2021-03-27 20:04:34 swin_base_patch4_window7_224] INFO: Epoch: [199] [1070/1251] eta: 0:01:54 lr: 0.000258 loss: 2.9492 (3.0456) grad_norm: 1.9471 (nan) time: 0.6243 [2021-03-27 20:04:40 swin_base_patch4_window7_224] INFO: Epoch: [199] [1080/1251] eta: 0:01:47 lr: 0.000258 loss: 2.9492 (3.0472) grad_norm: 1.7085 (nan) time: 0.6227 [2021-03-27 20:04:46 swin_base_patch4_window7_224] INFO: Epoch: [199] [1090/1251] eta: 0:01:41 lr: 0.000258 loss: 3.2004 (3.0480) grad_norm: 1.8014 (nan) time: 0.6296 [2021-03-27 20:04:53 swin_base_patch4_window7_224] INFO: Epoch: [199] [1100/1251] eta: 0:01:35 lr: 0.000258 loss: 2.7610 (3.0461) grad_norm: 1.8495 (nan) time: 0.6339 [2021-03-27 20:04:59 swin_base_patch4_window7_224] INFO: Epoch: [199] [1110/1251] eta: 0:01:29 lr: 0.000258 loss: 2.9599 (3.0451) grad_norm: 1.8421 (nan) time: 0.6286 [2021-03-27 20:05:05 swin_base_patch4_window7_224] INFO: Epoch: [199] [1120/1251] eta: 0:01:22 lr: 0.000258 loss: 3.0261 (3.0443) grad_norm: 1.8297 (nan) time: 0.6269 [2021-03-27 20:05:11 swin_base_patch4_window7_224] INFO: Epoch: [199] [1130/1251] eta: 0:01:16 lr: 0.000258 loss: 3.1910 (3.0454) grad_norm: 1.9290 (nan) time: 0.6247 [2021-03-27 20:05:18 swin_base_patch4_window7_224] INFO: Epoch: [199] [1140/1251] eta: 0:01:10 lr: 0.000258 loss: 3.0898 (3.0440) grad_norm: 1.9257 (nan) time: 0.6229 [2021-03-27 20:05:24 swin_base_patch4_window7_224] INFO: Epoch: [199] [1150/1251] eta: 0:01:03 lr: 0.000258 loss: 2.6964 (3.0415) grad_norm: 1.9257 (nan) time: 0.6243 [2021-03-27 20:05:30 swin_base_patch4_window7_224] INFO: Epoch: [199] [1160/1251] eta: 0:00:57 lr: 0.000258 loss: 2.9846 (3.0418) grad_norm: 2.0094 (nan) time: 0.6225 [2021-03-27 20:05:36 swin_base_patch4_window7_224] INFO: Epoch: [199] [1170/1251] eta: 0:00:51 lr: 0.000258 loss: 3.0349 (3.0412) grad_norm: 1.9690 (nan) time: 0.6269 [2021-03-27 20:05:43 swin_base_patch4_window7_224] INFO: Epoch: [199] [1180/1251] eta: 0:00:44 lr: 0.000258 loss: 3.2831 (3.0419) grad_norm: 1.9497 (nan) time: 0.6289 [2021-03-27 20:05:49 swin_base_patch4_window7_224] INFO: Epoch: [199] [1190/1251] eta: 0:00:38 lr: 0.000258 loss: 3.0824 (3.0404) grad_norm: 1.9729 (nan) time: 0.6240 [2021-03-27 20:05:55 swin_base_patch4_window7_224] INFO: Epoch: [199] [1200/1251] eta: 0:00:32 lr: 0.000258 loss: 3.1084 (3.0412) grad_norm: 1.8996 (nan) time: 0.6236 [2021-03-27 20:06:01 swin_base_patch4_window7_224] INFO: Epoch: [199] [1210/1251] eta: 0:00:25 lr: 0.000258 loss: 3.2659 (3.0429) grad_norm: 1.8444 (nan) time: 0.6233 [2021-03-27 20:06:08 swin_base_patch4_window7_224] INFO: Epoch: [199] [1220/1251] eta: 0:00:19 lr: 0.000258 loss: 3.1861 (3.0436) grad_norm: 1.8360 (nan) time: 0.6235 [2021-03-27 20:06:14 swin_base_patch4_window7_224] INFO: Epoch: [199] [1230/1251] eta: 0:00:13 lr: 0.000258 loss: 3.1054 (3.0436) grad_norm: 1.7991 (nan) time: 0.6256 [2021-03-27 20:06:20 swin_base_patch4_window7_224] INFO: Epoch: [199] [1240/1251] eta: 0:00:06 lr: 0.000258 loss: 3.1634 (3.0442) grad_norm: 1.9399 (nan) time: 0.6217 [2021-03-27 20:06:26 swin_base_patch4_window7_224] INFO: Epoch: [199] [1250/1251] eta: 0:00:00 lr: 0.000258 loss: 3.2007 (3.0441) grad_norm: 1.9249 (nan) time: 0.6209 [2021-03-27 20:06:35 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:52 loss: 0.9092 (0.9092) acc1: 78.1250 (78.1250) acc5: 95.3125 (95.3125) [2021-03-27 20:06:37 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.8300 (0.8977) acc1: 79.6875 (79.4034) acc5: 95.3125 (94.8864) [2021-03-27 20:06:39 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7828 (0.8704) acc1: 79.6875 (79.3899) acc5: 95.3125 (95.1637) [2021-03-27 20:06:42 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7459 (0.8248) acc1: 79.6875 (80.6956) acc5: 95.3125 (95.5645) [2021-03-27 20:06:44 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7652 (0.8137) acc1: 81.2500 (80.7927) acc5: 96.8750 (95.6936) [2021-03-27 20:06:45 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7677 (0.8205) acc1: 79.6875 (80.5760) acc5: 95.3125 (95.7440) [2021-03-27 20:06:57 swin_base_patch4_window7_224] INFO: * Acc@1 81.030 Acc@5 95.758 loss 0.812 [2021-03-27 20:06:57 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.0% [2021-03-27 20:06:57 swin_base_patch4_window7_224] INFO: Max accuracy: 81.06% [2021-03-27 20:07:01 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 0/1251] eta: 1:27:32 lr: 0.000258 loss: 2.8283 (2.8283) grad_norm: 1.5746 (1.5746) time: 4.1986 [2021-03-27 20:07:07 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 10/1251] eta: 0:20:05 lr: 0.000257 loss: 2.8993 (2.9732) grad_norm: 1.8410 (1.8530) time: 0.9711 [2021-03-27 20:07:14 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 20/1251] eta: 0:16:30 lr: 0.000257 loss: 2.9753 (2.9901) grad_norm: 1.8852 (1.8697) time: 0.6352 [2021-03-27 20:07:20 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 30/1251] eta: 0:15:10 lr: 0.000257 loss: 3.0735 (3.0053) grad_norm: 1.8540 (1.8644) time: 0.6212 [2021-03-27 20:07:26 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 40/1251] eta: 0:14:27 lr: 0.000257 loss: 3.0898 (3.0345) grad_norm: 1.9828 (1.9145) time: 0.6237 [2021-03-27 20:07:33 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 50/1251] eta: 0:14:00 lr: 0.000257 loss: 3.0925 (3.0068) grad_norm: 1.9457 (1.9017) time: 0.6290 [2021-03-27 20:07:39 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 60/1251] eta: 0:13:39 lr: 0.000257 loss: 3.2129 (3.0262) grad_norm: 1.8474 (1.9229) time: 0.6305 [2021-03-27 20:07:45 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 70/1251] eta: 0:13:23 lr: 0.000257 loss: 3.1057 (3.0288) grad_norm: 1.8383 (1.9245) time: 0.6324 [2021-03-27 20:07:51 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 80/1251] eta: 0:13:09 lr: 0.000257 loss: 3.0567 (3.0327) grad_norm: 1.9214 (1.9216) time: 0.6322 [2021-03-27 20:07:58 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 90/1251] eta: 0:12:56 lr: 0.000257 loss: 3.0053 (3.0177) grad_norm: 1.9697 (1.9553) time: 0.6280 [2021-03-27 20:08:04 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 100/1251] eta: 0:12:45 lr: 0.000257 loss: 3.0053 (3.0245) grad_norm: 1.9402 (1.9513) time: 0.6268 [2021-03-27 20:08:10 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 110/1251] eta: 0:12:35 lr: 0.000257 loss: 3.1059 (3.0206) grad_norm: 1.8711 (1.9573) time: 0.6319 [2021-03-27 20:08:17 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 120/1251] eta: 0:12:25 lr: 0.000257 loss: 3.0811 (2.9916) grad_norm: 1.9286 (1.9489) time: 0.6317 [2021-03-27 20:08:23 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 130/1251] eta: 0:12:17 lr: 0.000257 loss: 2.8546 (2.9979) grad_norm: 1.9286 (1.9505) time: 0.6327 [2021-03-27 20:08:29 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 140/1251] eta: 0:12:08 lr: 0.000257 loss: 3.2553 (3.0235) grad_norm: 1.9228 (1.9500) time: 0.6341 [2021-03-27 20:08:36 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 150/1251] eta: 0:12:00 lr: 0.000257 loss: 3.2553 (3.0247) grad_norm: 1.8587 (1.9416) time: 0.6319 [2021-03-27 20:08:42 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 160/1251] eta: 0:11:52 lr: 0.000257 loss: 3.0284 (3.0197) grad_norm: 1.8361 (1.9409) time: 0.6297 [2021-03-27 20:08:48 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 170/1251] eta: 0:11:44 lr: 0.000257 loss: 3.0291 (3.0283) grad_norm: 1.9028 (1.9375) time: 0.6275 [2021-03-27 20:08:55 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 180/1251] eta: 0:11:36 lr: 0.000257 loss: 3.1196 (3.0255) grad_norm: 1.8912 (1.9354) time: 0.6312 [2021-03-27 20:09:01 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 190/1251] eta: 0:11:28 lr: 0.000257 loss: 3.0969 (3.0263) grad_norm: 1.9519 (1.9446) time: 0.6294 [2021-03-27 20:09:07 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 200/1251] eta: 0:11:21 lr: 0.000257 loss: 2.9412 (3.0177) grad_norm: 1.9519 (1.9436) time: 0.6273 [2021-03-27 20:09:13 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 210/1251] eta: 0:11:13 lr: 0.000257 loss: 2.8862 (3.0227) grad_norm: 1.9663 (1.9462) time: 0.6313 [2021-03-27 20:09:20 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 220/1251] eta: 0:11:06 lr: 0.000257 loss: 3.2102 (3.0253) grad_norm: 1.9663 (1.9480) time: 0.6337 [2021-03-27 20:09:26 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 230/1251] eta: 0:10:59 lr: 0.000257 loss: 2.9335 (3.0183) grad_norm: 1.9258 (1.9561) time: 0.6298 [2021-03-27 20:09:32 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 240/1251] eta: 0:10:52 lr: 0.000257 loss: 2.8298 (3.0064) grad_norm: 2.0298 (1.9657) time: 0.6267 [2021-03-27 20:09:39 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 250/1251] eta: 0:10:44 lr: 0.000257 loss: 3.0011 (3.0040) grad_norm: 2.0298 (1.9696) time: 0.6264 [2021-03-27 20:09:45 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 260/1251] eta: 0:10:37 lr: 0.000257 loss: 3.1237 (3.0040) grad_norm: 2.0229 (1.9713) time: 0.6281 [2021-03-27 20:09:51 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 270/1251] eta: 0:10:31 lr: 0.000257 loss: 3.1237 (3.0064) grad_norm: 2.0229 (1.9744) time: 0.6330 [2021-03-27 20:09:57 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 280/1251] eta: 0:10:24 lr: 0.000256 loss: 3.2020 (3.0092) grad_norm: 2.0125 (1.9773) time: 0.6303 [2021-03-27 20:10:04 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 290/1251] eta: 0:10:17 lr: 0.000256 loss: 3.1722 (3.0134) grad_norm: 1.9715 (1.9756) time: 0.6246 [2021-03-27 20:10:10 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 300/1251] eta: 0:10:10 lr: 0.000256 loss: 3.2058 (3.0211) grad_norm: 1.7830 (1.9691) time: 0.6312 [2021-03-27 20:10:16 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 310/1251] eta: 0:10:03 lr: 0.000256 loss: 3.2164 (3.0236) grad_norm: 1.8351 (1.9706) time: 0.6364 [2021-03-27 20:10:23 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 320/1251] eta: 0:09:57 lr: 0.000256 loss: 2.9978 (3.0143) grad_norm: 1.9703 (1.9720) time: 0.6313 [2021-03-27 20:10:29 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 330/1251] eta: 0:09:50 lr: 0.000256 loss: 2.6633 (3.0106) grad_norm: 2.1283 (1.9796) time: 0.6355 [2021-03-27 20:10:35 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 340/1251] eta: 0:09:44 lr: 0.000256 loss: 3.0483 (3.0141) grad_norm: 2.1293 (1.9842) time: 0.6371 [2021-03-27 20:10:42 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 350/1251] eta: 0:09:37 lr: 0.000256 loss: 3.0483 (3.0123) grad_norm: 2.0188 (1.9880) time: 0.6305 [2021-03-27 20:10:48 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 360/1251] eta: 0:09:31 lr: 0.000256 loss: 3.0282 (3.0125) grad_norm: 1.9800 (1.9898) time: 0.6375 [2021-03-27 20:10:55 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 370/1251] eta: 0:09:24 lr: 0.000256 loss: 3.2074 (3.0197) grad_norm: 1.8938 (1.9860) time: 0.6430 [2021-03-27 20:11:01 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 380/1251] eta: 0:09:17 lr: 0.000256 loss: 3.1886 (3.0252) grad_norm: 1.8938 (1.9876) time: 0.6333 [2021-03-27 20:11:07 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 390/1251] eta: 0:09:11 lr: 0.000256 loss: 2.9517 (3.0194) grad_norm: 2.0842 (1.9950) time: 0.6299 [2021-03-27 20:11:14 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 400/1251] eta: 0:09:04 lr: 0.000256 loss: 2.9119 (3.0225) grad_norm: 1.9141 (1.9934) time: 0.6316 [2021-03-27 20:11:20 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 410/1251] eta: 0:08:58 lr: 0.000256 loss: 3.1678 (3.0276) grad_norm: 1.9003 (1.9991) time: 0.6284 [2021-03-27 20:11:26 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 420/1251] eta: 0:08:51 lr: 0.000256 loss: 3.0327 (3.0238) grad_norm: 1.9427 (1.9992) time: 0.6252 [2021-03-27 20:11:32 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 430/1251] eta: 0:08:44 lr: 0.000256 loss: 3.1667 (3.0276) grad_norm: 2.0200 (2.0054) time: 0.6227 [2021-03-27 20:11:39 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 440/1251] eta: 0:08:37 lr: 0.000256 loss: 3.0761 (3.0240) grad_norm: 1.9914 (2.0058) time: 0.6234 [2021-03-27 20:11:45 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 450/1251] eta: 0:08:31 lr: 0.000256 loss: 2.9929 (3.0285) grad_norm: 1.8875 (2.0041) time: 0.6258 [2021-03-27 20:11:51 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 460/1251] eta: 0:08:24 lr: 0.000256 loss: 3.1948 (3.0317) grad_norm: 1.8828 (2.0021) time: 0.6300 [2021-03-27 20:11:57 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 470/1251] eta: 0:08:18 lr: 0.000256 loss: 3.0369 (3.0256) grad_norm: 1.9193 (2.0017) time: 0.6278 [2021-03-27 20:12:04 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 480/1251] eta: 0:08:11 lr: 0.000256 loss: 3.0369 (3.0306) grad_norm: 1.9141 (2.0020) time: 0.6257 [2021-03-27 20:12:10 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 490/1251] eta: 0:08:05 lr: 0.000256 loss: 3.1539 (3.0277) grad_norm: 1.9050 (2.0004) time: 0.6278 [2021-03-27 20:12:16 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 500/1251] eta: 0:07:58 lr: 0.000256 loss: 2.7781 (3.0271) grad_norm: 1.9528 (2.0008) time: 0.6273 [2021-03-27 20:12:22 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 510/1251] eta: 0:07:52 lr: 0.000256 loss: 2.7781 (3.0234) grad_norm: 1.9711 (2.0031) time: 0.6256 [2021-03-27 20:12:29 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 520/1251] eta: 0:07:45 lr: 0.000256 loss: 3.0529 (3.0209) grad_norm: 1.9825 (2.0067) time: 0.6321 [2021-03-27 20:12:35 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 530/1251] eta: 0:07:39 lr: 0.000256 loss: 3.2109 (3.0254) grad_norm: 1.9820 (2.0073) time: 0.6347 [2021-03-27 20:12:41 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 540/1251] eta: 0:07:32 lr: 0.000256 loss: 3.2569 (3.0273) grad_norm: 1.9171 (2.0056) time: 0.6302 [2021-03-27 20:12:48 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 550/1251] eta: 0:07:26 lr: 0.000256 loss: 3.0887 (3.0268) grad_norm: 1.9186 (2.0074) time: 0.6265 [2021-03-27 20:12:54 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 560/1251] eta: 0:07:19 lr: 0.000255 loss: 3.0864 (3.0270) grad_norm: 1.9110 (2.0060) time: 0.6210 [2021-03-27 20:13:00 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 570/1251] eta: 0:07:13 lr: 0.000255 loss: 3.0845 (3.0276) grad_norm: 1.8795 (2.0074) time: 0.6261 [2021-03-27 20:13:06 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 580/1251] eta: 0:07:06 lr: 0.000255 loss: 3.0023 (3.0287) grad_norm: 2.0811 (2.0085) time: 0.6298 [2021-03-27 20:13:13 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 590/1251] eta: 0:07:00 lr: 0.000255 loss: 2.9884 (3.0243) grad_norm: 2.0736 (2.0109) time: 0.6291 [2021-03-27 20:13:19 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 600/1251] eta: 0:06:53 lr: 0.000255 loss: 3.1928 (3.0285) grad_norm: 1.9700 (2.0134) time: 0.6301 [2021-03-27 20:13:25 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 610/1251] eta: 0:06:47 lr: 0.000255 loss: 3.1108 (3.0265) grad_norm: 1.8560 (2.0118) time: 0.6247 [2021-03-27 20:13:31 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 620/1251] eta: 0:06:40 lr: 0.000255 loss: 3.0976 (3.0297) grad_norm: 1.8901 (2.0123) time: 0.6212 [2021-03-27 20:13:38 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 630/1251] eta: 0:06:34 lr: 0.000255 loss: 3.2706 (3.0291) grad_norm: 1.9435 (2.0125) time: 0.6297 [2021-03-27 20:13:44 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 640/1251] eta: 0:06:28 lr: 0.000255 loss: 3.2516 (3.0316) grad_norm: 1.8995 (2.0111) time: 0.6311 [2021-03-27 20:13:50 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 650/1251] eta: 0:06:21 lr: 0.000255 loss: 3.2516 (3.0285) grad_norm: 1.9184 (2.0139) time: 0.6295 [2021-03-27 20:13:57 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 660/1251] eta: 0:06:15 lr: 0.000255 loss: 2.9876 (3.0292) grad_norm: 1.9092 (2.0122) time: 0.6287 [2021-03-27 20:14:03 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 670/1251] eta: 0:06:08 lr: 0.000255 loss: 3.1664 (3.0318) grad_norm: 1.8922 (2.0124) time: 0.6247 [2021-03-27 20:14:09 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 680/1251] eta: 0:06:02 lr: 0.000255 loss: 3.2319 (3.0351) grad_norm: 1.8659 (2.0130) time: 0.6385 [2021-03-27 20:14:16 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 690/1251] eta: 0:05:56 lr: 0.000255 loss: 3.2196 (3.0350) grad_norm: 1.8546 (2.0122) time: 0.6400 [2021-03-27 20:14:22 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 700/1251] eta: 0:05:49 lr: 0.000255 loss: 3.1171 (3.0355) grad_norm: 1.8746 (2.0177) time: 0.6309 [2021-03-27 20:14:28 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 710/1251] eta: 0:05:43 lr: 0.000255 loss: 2.8865 (3.0347) grad_norm: 1.9608 (2.0181) time: 0.6306 [2021-03-27 20:14:35 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 720/1251] eta: 0:05:37 lr: 0.000255 loss: 2.9561 (3.0335) grad_norm: 1.9956 (2.0180) time: 0.6284 [2021-03-27 20:14:41 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 730/1251] eta: 0:05:30 lr: 0.000255 loss: 3.0341 (3.0357) grad_norm: 1.9928 (2.0175) time: 0.6284 [2021-03-27 20:14:47 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 740/1251] eta: 0:05:24 lr: 0.000255 loss: 3.1775 (3.0390) grad_norm: 1.9240 (2.0168) time: 0.6273 [2021-03-27 20:14:54 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 750/1251] eta: 0:05:17 lr: 0.000255 loss: 3.2780 (3.0417) grad_norm: 1.9572 (2.0179) time: 0.6284 [2021-03-27 20:15:00 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 760/1251] eta: 0:05:11 lr: 0.000255 loss: 3.3882 (3.0448) grad_norm: 1.9493 (2.0156) time: 0.6352 [2021-03-27 20:15:06 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 770/1251] eta: 0:05:05 lr: 0.000255 loss: 3.2046 (3.0439) grad_norm: 1.8234 (2.0129) time: 0.6353 [2021-03-27 20:15:13 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 780/1251] eta: 0:04:58 lr: 0.000255 loss: 2.9177 (3.0419) grad_norm: 1.8402 (2.0119) time: 0.6342 [2021-03-27 20:15:19 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 790/1251] eta: 0:04:52 lr: 0.000255 loss: 3.0648 (3.0430) grad_norm: 1.9070 (2.0118) time: 0.6331 [2021-03-27 20:15:25 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 800/1251] eta: 0:04:46 lr: 0.000255 loss: 3.1505 (3.0428) grad_norm: 1.9002 (2.0122) time: 0.6279 [2021-03-27 20:15:31 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 810/1251] eta: 0:04:39 lr: 0.000255 loss: 3.1810 (3.0460) grad_norm: 1.9002 (2.0105) time: 0.6232 [2021-03-27 20:15:38 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 820/1251] eta: 0:04:33 lr: 0.000255 loss: 3.0856 (3.0439) grad_norm: 1.9671 (2.0108) time: 0.6258 [2021-03-27 20:15:44 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 830/1251] eta: 0:04:27 lr: 0.000255 loss: 3.0774 (3.0461) grad_norm: 1.9671 (2.0103) time: 0.6317 [2021-03-27 20:15:50 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 840/1251] eta: 0:04:20 lr: 0.000254 loss: 3.3933 (3.0487) grad_norm: 1.8988 (2.0103) time: 0.6260 [2021-03-27 20:15:56 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 850/1251] eta: 0:04:14 lr: 0.000254 loss: 3.1421 (3.0465) grad_norm: 1.9203 (2.0097) time: 0.6228 [2021-03-27 20:16:03 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 860/1251] eta: 0:04:07 lr: 0.000254 loss: 2.9866 (3.0464) grad_norm: 1.9428 (2.0095) time: 0.6301 [2021-03-27 20:16:09 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 870/1251] eta: 0:04:01 lr: 0.000254 loss: 3.1564 (3.0474) grad_norm: 1.9053 (2.0098) time: 0.6307 [2021-03-27 20:16:15 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 880/1251] eta: 0:03:55 lr: 0.000254 loss: 3.1519 (3.0461) grad_norm: 1.9053 (2.0120) time: 0.6328 [2021-03-27 20:16:22 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 890/1251] eta: 0:03:48 lr: 0.000254 loss: 3.0086 (3.0462) grad_norm: 1.9044 (2.0109) time: 0.6312 [2021-03-27 20:16:28 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 900/1251] eta: 0:03:42 lr: 0.000254 loss: 2.9847 (3.0459) grad_norm: 1.9320 (2.0125) time: 0.6218 [2021-03-27 20:16:34 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 910/1251] eta: 0:03:36 lr: 0.000254 loss: 3.1356 (3.0467) grad_norm: 1.9346 (2.0121) time: 0.6282 [2021-03-27 20:16:40 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 920/1251] eta: 0:03:29 lr: 0.000254 loss: 3.0697 (3.0450) grad_norm: 2.0373 (2.0121) time: 0.6293 [2021-03-27 20:16:47 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 930/1251] eta: 0:03:23 lr: 0.000254 loss: 3.0697 (3.0450) grad_norm: 2.0855 (2.0134) time: 0.6261 [2021-03-27 20:16:53 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 940/1251] eta: 0:03:17 lr: 0.000254 loss: 3.1467 (3.0463) grad_norm: 1.9619 (2.0130) time: 0.6321 [2021-03-27 20:16:59 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 950/1251] eta: 0:03:10 lr: 0.000254 loss: 2.9897 (3.0452) grad_norm: 1.8510 (2.0118) time: 0.6337 [2021-03-27 20:17:06 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 960/1251] eta: 0:03:04 lr: 0.000254 loss: 2.8889 (3.0442) grad_norm: 1.8020 (2.0106) time: 0.6349 [2021-03-27 20:17:12 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 970/1251] eta: 0:02:58 lr: 0.000254 loss: 2.9561 (3.0430) grad_norm: 1.8036 (2.0094) time: 0.6318 [2021-03-27 20:17:18 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 980/1251] eta: 0:02:51 lr: 0.000254 loss: 3.2368 (3.0453) grad_norm: 1.8532 (2.0087) time: 0.6258 [2021-03-27 20:17:25 swin_base_patch4_window7_224] INFO: Epoch: [200] [ 990/1251] eta: 0:02:45 lr: 0.000254 loss: 3.2088 (3.0456) grad_norm: 1.9026 (2.0092) time: 0.6259 [2021-03-27 20:17:31 swin_base_patch4_window7_224] INFO: Epoch: [200] [1000/1251] eta: 0:02:38 lr: 0.000254 loss: 3.1696 (3.0452) grad_norm: 1.9621 (2.0095) time: 0.6303 [2021-03-27 20:17:37 swin_base_patch4_window7_224] INFO: Epoch: [200] [1010/1251] eta: 0:02:32 lr: 0.000254 loss: 3.1658 (3.0456) grad_norm: 1.9621 (2.0100) time: 0.6290 [2021-03-27 20:17:44 swin_base_patch4_window7_224] INFO: Epoch: [200] [1020/1251] eta: 0:02:26 lr: 0.000254 loss: 3.1788 (3.0453) grad_norm: 1.9102 (2.0095) time: 0.6266 [2021-03-27 20:17:50 swin_base_patch4_window7_224] INFO: Epoch: [200] [1030/1251] eta: 0:02:19 lr: 0.000254 loss: 3.0766 (3.0455) grad_norm: 1.9102 (2.0100) time: 0.6275 [2021-03-27 20:17:56 swin_base_patch4_window7_224] INFO: Epoch: [200] [1040/1251] eta: 0:02:13 lr: 0.000254 loss: 3.0800 (3.0455) grad_norm: 2.0271 (2.0104) time: 0.6291 [2021-03-27 20:18:02 swin_base_patch4_window7_224] INFO: Epoch: [200] [1050/1251] eta: 0:02:07 lr: 0.000254 loss: 3.0800 (3.0448) grad_norm: 1.8774 (2.0083) time: 0.6295 [2021-03-27 20:18:09 swin_base_patch4_window7_224] INFO: Epoch: [200] [1060/1251] eta: 0:02:00 lr: 0.000254 loss: 2.8133 (3.0414) grad_norm: 1.8454 (2.0110) time: 0.6268 [2021-03-27 20:18:15 swin_base_patch4_window7_224] INFO: Epoch: [200] [1070/1251] eta: 0:01:54 lr: 0.000254 loss: 2.9437 (3.0428) grad_norm: 1.9437 (2.0116) time: 0.6311 [2021-03-27 20:18:21 swin_base_patch4_window7_224] INFO: Epoch: [200] [1080/1251] eta: 0:01:48 lr: 0.000254 loss: 3.1878 (3.0437) grad_norm: 2.0138 (2.0131) time: 0.6338 [2021-03-27 20:18:28 swin_base_patch4_window7_224] INFO: Epoch: [200] [1090/1251] eta: 0:01:41 lr: 0.000254 loss: 3.1080 (3.0438) grad_norm: 2.0385 (2.0135) time: 0.6278 [2021-03-27 20:18:34 swin_base_patch4_window7_224] INFO: Epoch: [200] [1100/1251] eta: 0:01:35 lr: 0.000254 loss: 3.0550 (3.0429) grad_norm: 1.9294 (2.0135) time: 0.6212 [2021-03-27 20:18:40 swin_base_patch4_window7_224] INFO: Epoch: [200] [1110/1251] eta: 0:01:29 lr: 0.000254 loss: 3.2025 (3.0436) grad_norm: 1.9294 (2.0131) time: 0.6241 [2021-03-27 20:18:46 swin_base_patch4_window7_224] INFO: Epoch: [200] [1120/1251] eta: 0:01:22 lr: 0.000253 loss: 3.2736 (3.0455) grad_norm: 1.9844 (2.0131) time: 0.6280 [2021-03-27 20:18:53 swin_base_patch4_window7_224] INFO: Epoch: [200] [1130/1251] eta: 0:01:16 lr: 0.000253 loss: 3.1869 (3.0441) grad_norm: 2.0127 (2.0136) time: 0.6260 [2021-03-27 20:18:59 swin_base_patch4_window7_224] INFO: Epoch: [200] [1140/1251] eta: 0:01:10 lr: 0.000253 loss: 3.1908 (3.0450) grad_norm: 1.9771 (2.0164) time: 0.6246 [2021-03-27 20:19:05 swin_base_patch4_window7_224] INFO: Epoch: [200] [1150/1251] eta: 0:01:03 lr: 0.000253 loss: 2.8762 (3.0424) grad_norm: 1.9338 (2.0164) time: 0.6292 [2021-03-27 20:19:11 swin_base_patch4_window7_224] INFO: Epoch: [200] [1160/1251] eta: 0:00:57 lr: 0.000253 loss: 2.8762 (3.0434) grad_norm: 1.9790 (2.0157) time: 0.6326 [2021-03-27 20:19:18 swin_base_patch4_window7_224] INFO: Epoch: [200] [1170/1251] eta: 0:00:51 lr: 0.000253 loss: 3.2224 (3.0440) grad_norm: 1.9790 (2.0155) time: 0.6293 [2021-03-27 20:19:24 swin_base_patch4_window7_224] INFO: Epoch: [200] [1180/1251] eta: 0:00:44 lr: 0.000253 loss: 3.2600 (3.0451) grad_norm: 1.9481 (2.0152) time: 0.6280 [2021-03-27 20:19:30 swin_base_patch4_window7_224] INFO: Epoch: [200] [1190/1251] eta: 0:00:38 lr: 0.000253 loss: 3.2600 (3.0464) grad_norm: 1.9650 (2.0151) time: 0.6322 [2021-03-27 20:19:37 swin_base_patch4_window7_224] INFO: Epoch: [200] [1200/1251] eta: 0:00:32 lr: 0.000253 loss: 3.2646 (3.0477) grad_norm: 1.9774 (2.0158) time: 0.6333 [2021-03-27 20:19:43 swin_base_patch4_window7_224] INFO: Epoch: [200] [1210/1251] eta: 0:00:25 lr: 0.000253 loss: 3.1582 (3.0492) grad_norm: 1.9848 (2.0156) time: 0.6267 [2021-03-27 20:19:49 swin_base_patch4_window7_224] INFO: Epoch: [200] [1220/1251] eta: 0:00:19 lr: 0.000253 loss: 3.1887 (3.0499) grad_norm: 2.0098 (2.0162) time: 0.6246 [2021-03-27 20:19:55 swin_base_patch4_window7_224] INFO: Epoch: [200] [1230/1251] eta: 0:00:13 lr: 0.000253 loss: 3.1918 (3.0505) grad_norm: 1.9825 (2.0166) time: 0.6264 [2021-03-27 20:20:02 swin_base_patch4_window7_224] INFO: Epoch: [200] [1240/1251] eta: 0:00:06 lr: 0.000253 loss: 2.9991 (3.0497) grad_norm: 1.9925 (2.0177) time: 0.6237 [2021-03-27 20:20:08 swin_base_patch4_window7_224] INFO: Epoch: [200] [1250/1251] eta: 0:00:00 lr: 0.000253 loss: 3.1152 (3.0525) grad_norm: 1.9936 (2.0175) time: 0.6212 [2021-03-27 20:21:26 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:04 loss: 0.8450 (0.8450) acc1: 78.1250 (78.1250) acc5: 95.3125 (95.3125) [2021-03-27 20:21:27 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.8447 (0.8697) acc1: 79.6875 (79.8295) acc5: 95.3125 (95.5966) [2021-03-27 20:21:29 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.8370 (0.8831) acc1: 79.6875 (79.6131) acc5: 95.3125 (95.1637) [2021-03-27 20:21:30 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7723 (0.8430) acc1: 79.6875 (80.1915) acc5: 96.8750 (95.7157) [2021-03-27 20:21:32 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7492 (0.8456) acc1: 79.6875 (79.9924) acc5: 96.8750 (95.6936) [2021-03-27 20:21:33 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7932 (0.8314) acc1: 79.6875 (80.6080) acc5: 96.2264 (95.7760) [2021-03-27 20:21:44 swin_base_patch4_window7_224] INFO: * Acc@1 80.928 Acc@5 95.726 loss 0.825 [2021-03-27 20:21:44 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.9% [2021-03-27 20:21:44 swin_base_patch4_window7_224] INFO: Max accuracy: 81.06% [2021-03-27 20:21:48 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 0/1251] eta: 1:28:51 lr: 0.000253 loss: 2.6138 (2.6138) grad_norm: 1.9241 (1.9241) time: 4.2616 [2021-03-27 20:21:54 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 10/1251] eta: 0:20:04 lr: 0.000253 loss: 3.2381 (3.0426) grad_norm: 1.9241 (2.0101) time: 0.9707 [2021-03-27 20:22:01 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 20/1251] eta: 0:16:34 lr: 0.000253 loss: 3.2381 (3.0928) grad_norm: 1.9017 (2.0124) time: 0.6348 [2021-03-27 20:22:07 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 30/1251] eta: 0:15:16 lr: 0.000253 loss: 3.1908 (3.1367) grad_norm: 1.9017 (2.0236) time: 0.6289 [2021-03-27 20:22:13 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 40/1251] eta: 0:14:31 lr: 0.000253 loss: 3.1211 (3.0767) grad_norm: 1.9731 (2.0374) time: 0.6273 [2021-03-27 20:22:19 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 50/1251] eta: 0:14:03 lr: 0.000253 loss: 2.9095 (3.0216) grad_norm: 1.9731 (2.0292) time: 0.6282 [2021-03-27 20:22:26 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 60/1251] eta: 0:13:43 lr: 0.000253 loss: 3.0047 (3.0258) grad_norm: 1.8611 (2.0102) time: 0.6344 [2021-03-27 20:22:32 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 70/1251] eta: 0:13:28 lr: 0.000253 loss: 3.0498 (3.0100) grad_norm: 1.8661 (1.9950) time: 0.6400 [2021-03-27 20:22:38 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 80/1251] eta: 0:13:12 lr: 0.000253 loss: 2.9809 (3.0093) grad_norm: 1.8741 (1.9895) time: 0.6324 [2021-03-27 20:22:45 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 90/1251] eta: 0:12:59 lr: 0.000253 loss: 2.6844 (2.9973) grad_norm: 1.9395 (1.9900) time: 0.6255 [2021-03-27 20:22:51 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 100/1251] eta: 0:12:48 lr: 0.000253 loss: 3.1556 (3.0282) grad_norm: 1.9498 (1.9884) time: 0.6300 [2021-03-27 20:22:57 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 110/1251] eta: 0:12:37 lr: 0.000253 loss: 3.2484 (3.0507) grad_norm: 1.9876 (1.9980) time: 0.6272 [2021-03-27 20:23:04 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 120/1251] eta: 0:12:27 lr: 0.000253 loss: 3.1932 (3.0560) grad_norm: 2.0514 (2.0090) time: 0.6286 [2021-03-27 20:23:10 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 130/1251] eta: 0:12:19 lr: 0.000253 loss: 3.0630 (3.0526) grad_norm: 2.0558 (2.0135) time: 0.6376 [2021-03-27 20:23:16 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 140/1251] eta: 0:12:11 lr: 0.000253 loss: 3.3281 (3.0690) grad_norm: 2.0558 (2.0488) time: 0.6410 [2021-03-27 20:23:23 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 150/1251] eta: 0:12:02 lr: 0.000252 loss: 3.4050 (3.0903) grad_norm: 2.1071 (2.0512) time: 0.6332 [2021-03-27 20:23:29 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 160/1251] eta: 0:11:53 lr: 0.000252 loss: 3.3314 (3.1053) grad_norm: 1.9124 (2.0447) time: 0.6233 [2021-03-27 20:23:35 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 170/1251] eta: 0:11:45 lr: 0.000252 loss: 3.2298 (3.1046) grad_norm: 1.8891 (2.0347) time: 0.6231 [2021-03-27 20:23:41 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 180/1251] eta: 0:11:36 lr: 0.000252 loss: 3.1324 (3.1069) grad_norm: 1.9100 (2.0324) time: 0.6235 [2021-03-27 20:23:48 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 190/1251] eta: 0:11:29 lr: 0.000252 loss: 3.2169 (3.1021) grad_norm: 1.9834 (2.0308) time: 0.6285 [2021-03-27 20:23:54 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 200/1251] eta: 0:11:22 lr: 0.000252 loss: 3.2169 (3.1011) grad_norm: 1.8457 (2.0188) time: 0.6376 [2021-03-27 20:24:00 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 210/1251] eta: 0:11:14 lr: 0.000252 loss: 3.2578 (3.1051) grad_norm: 1.7637 (2.0169) time: 0.6307 [2021-03-27 20:24:07 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 220/1251] eta: 0:11:07 lr: 0.000252 loss: 3.2260 (3.1039) grad_norm: 1.8933 (2.0154) time: 0.6293 [2021-03-27 20:24:13 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 230/1251] eta: 0:11:00 lr: 0.000252 loss: 3.1513 (3.1055) grad_norm: 1.9355 (2.0205) time: 0.6315 [2021-03-27 20:24:19 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 240/1251] eta: 0:10:52 lr: 0.000252 loss: 3.0785 (3.0991) grad_norm: 1.9355 (2.0152) time: 0.6257 [2021-03-27 20:24:25 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 250/1251] eta: 0:10:45 lr: 0.000252 loss: 3.0542 (3.0986) grad_norm: 1.9362 (2.0196) time: 0.6206 [2021-03-27 20:24:32 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 260/1251] eta: 0:10:38 lr: 0.000252 loss: 2.7920 (3.0759) grad_norm: 2.0209 (2.0239) time: 0.6286 [2021-03-27 20:24:38 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 270/1251] eta: 0:10:31 lr: 0.000252 loss: 2.7920 (3.0760) grad_norm: 1.9406 (2.0224) time: 0.6379 [2021-03-27 20:24:44 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 280/1251] eta: 0:10:24 lr: 0.000252 loss: 3.0340 (3.0710) grad_norm: 2.0020 (2.0275) time: 0.6291 [2021-03-27 20:24:51 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 290/1251] eta: 0:10:17 lr: 0.000252 loss: 2.9624 (3.0598) grad_norm: 2.0020 (2.0306) time: 0.6259 [2021-03-27 20:24:57 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 300/1251] eta: 0:10:10 lr: 0.000252 loss: 3.0726 (3.0629) grad_norm: 1.9672 (2.0318) time: 0.6273 [2021-03-27 20:25:03 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 310/1251] eta: 0:10:03 lr: 0.000252 loss: 3.3176 (3.0663) grad_norm: 1.9819 (2.0362) time: 0.6254 [2021-03-27 20:25:10 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 320/1251] eta: 0:09:57 lr: 0.000252 loss: 3.2493 (3.0624) grad_norm: 1.9975 (2.0346) time: 0.6263 [2021-03-27 20:25:16 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 330/1251] eta: 0:09:50 lr: 0.000252 loss: 3.1648 (3.0629) grad_norm: 1.9219 (2.0322) time: 0.6283 [2021-03-27 20:25:22 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 340/1251] eta: 0:09:43 lr: 0.000252 loss: 3.0925 (3.0631) grad_norm: 1.9067 (2.0320) time: 0.6270 [2021-03-27 20:25:28 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 350/1251] eta: 0:09:36 lr: 0.000252 loss: 3.0626 (3.0594) grad_norm: 1.8260 (2.0289) time: 0.6320 [2021-03-27 20:25:35 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 360/1251] eta: 0:09:30 lr: 0.000252 loss: 3.0170 (3.0595) grad_norm: 1.9308 (2.0302) time: 0.6309 [2021-03-27 20:25:41 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 370/1251] eta: 0:09:23 lr: 0.000252 loss: 3.1679 (3.0619) grad_norm: 1.9952 (2.0296) time: 0.6245 [2021-03-27 20:25:47 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 380/1251] eta: 0:09:16 lr: 0.000252 loss: 3.2706 (3.0610) grad_norm: 1.8598 (2.0277) time: 0.6225 [2021-03-27 20:25:53 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 390/1251] eta: 0:09:09 lr: 0.000252 loss: 2.7032 (3.0533) grad_norm: 1.8203 (2.0251) time: 0.6227 [2021-03-27 20:26:00 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 400/1251] eta: 0:09:02 lr: 0.000252 loss: 2.8826 (3.0562) grad_norm: 1.9554 (inf) time: 0.6199 [2021-03-27 20:26:06 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 410/1251] eta: 0:08:56 lr: 0.000252 loss: 3.2095 (3.0557) grad_norm: 2.1371 (inf) time: 0.6250 [2021-03-27 20:26:12 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 420/1251] eta: 0:08:50 lr: 0.000252 loss: 3.0291 (3.0544) grad_norm: 1.9622 (inf) time: 0.6337 [2021-03-27 20:26:18 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 430/1251] eta: 0:08:43 lr: 0.000251 loss: 3.2094 (3.0585) grad_norm: 1.9638 (inf) time: 0.6280 [2021-03-27 20:26:25 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 440/1251] eta: 0:08:36 lr: 0.000251 loss: 3.2437 (3.0607) grad_norm: 1.9638 (inf) time: 0.6236 [2021-03-27 20:26:31 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 450/1251] eta: 0:08:30 lr: 0.000251 loss: 3.1733 (3.0627) grad_norm: 1.8987 (inf) time: 0.6248 [2021-03-27 20:26:37 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 460/1251] eta: 0:08:23 lr: 0.000251 loss: 3.1440 (3.0630) grad_norm: 1.7745 (inf) time: 0.6264 [2021-03-27 20:26:43 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 470/1251] eta: 0:08:17 lr: 0.000251 loss: 3.1233 (3.0642) grad_norm: 1.8425 (inf) time: 0.6240 [2021-03-27 20:26:50 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 480/1251] eta: 0:08:10 lr: 0.000251 loss: 3.1094 (3.0650) grad_norm: 1.9306 (inf) time: 0.6224 [2021-03-27 20:26:56 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 490/1251] eta: 0:08:03 lr: 0.000251 loss: 3.0670 (3.0657) grad_norm: 2.0601 (inf) time: 0.6235 [2021-03-27 20:27:02 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 500/1251] eta: 0:07:57 lr: 0.000251 loss: 3.0640 (3.0646) grad_norm: 2.0509 (inf) time: 0.6282 [2021-03-27 20:27:08 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 510/1251] eta: 0:07:50 lr: 0.000251 loss: 3.0640 (3.0648) grad_norm: 1.9663 (inf) time: 0.6293 [2021-03-27 20:27:15 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 520/1251] eta: 0:07:44 lr: 0.000251 loss: 3.2493 (3.0626) grad_norm: 1.9469 (inf) time: 0.6264 [2021-03-27 20:27:21 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 530/1251] eta: 0:07:38 lr: 0.000251 loss: 3.0602 (3.0618) grad_norm: 1.9320 (inf) time: 0.6268 [2021-03-27 20:27:27 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 540/1251] eta: 0:07:31 lr: 0.000251 loss: 3.1660 (3.0603) grad_norm: 2.0298 (inf) time: 0.6291 [2021-03-27 20:27:34 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 550/1251] eta: 0:07:25 lr: 0.000251 loss: 3.1657 (3.0600) grad_norm: 2.0924 (inf) time: 0.6297 [2021-03-27 20:27:40 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 560/1251] eta: 0:07:18 lr: 0.000251 loss: 3.1657 (3.0591) grad_norm: 2.0924 (inf) time: 0.6239 [2021-03-27 20:27:46 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 570/1251] eta: 0:07:12 lr: 0.000251 loss: 3.1858 (3.0594) grad_norm: 2.0866 (inf) time: 0.6210 [2021-03-27 20:27:52 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 580/1251] eta: 0:07:05 lr: 0.000251 loss: 2.8780 (3.0542) grad_norm: 1.9883 (inf) time: 0.6312 [2021-03-27 20:27:59 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 590/1251] eta: 0:06:59 lr: 0.000251 loss: 2.7139 (3.0500) grad_norm: 2.0317 (inf) time: 0.6320 [2021-03-27 20:28:05 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 600/1251] eta: 0:06:52 lr: 0.000251 loss: 3.1310 (3.0519) grad_norm: 2.0416 (inf) time: 0.6262 [2021-03-27 20:28:11 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 610/1251] eta: 0:06:46 lr: 0.000251 loss: 3.2396 (3.0552) grad_norm: 2.1306 (inf) time: 0.6247 [2021-03-27 20:28:17 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 620/1251] eta: 0:06:40 lr: 0.000251 loss: 3.1952 (3.0527) grad_norm: 2.0708 (inf) time: 0.6252 [2021-03-27 20:28:24 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 630/1251] eta: 0:06:33 lr: 0.000251 loss: 2.9840 (3.0501) grad_norm: 1.9582 (inf) time: 0.6288 [2021-03-27 20:28:30 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 640/1251] eta: 0:06:27 lr: 0.000251 loss: 2.9840 (3.0494) grad_norm: 1.8109 (inf) time: 0.6284 [2021-03-27 20:28:36 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 650/1251] eta: 0:06:21 lr: 0.000251 loss: 3.0913 (3.0507) grad_norm: 1.8461 (inf) time: 0.6322 [2021-03-27 20:28:43 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 660/1251] eta: 0:06:14 lr: 0.000251 loss: 3.2886 (3.0547) grad_norm: 2.0079 (inf) time: 0.6332 [2021-03-27 20:28:49 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 670/1251] eta: 0:06:08 lr: 0.000251 loss: 3.1486 (3.0521) grad_norm: 1.8256 (inf) time: 0.6332 [2021-03-27 20:28:56 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 680/1251] eta: 0:06:02 lr: 0.000251 loss: 3.0961 (3.0560) grad_norm: 1.7548 (inf) time: 0.6409 [2021-03-27 20:29:02 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 690/1251] eta: 0:05:55 lr: 0.000251 loss: 2.9575 (3.0505) grad_norm: 1.8619 (inf) time: 0.6353 [2021-03-27 20:29:08 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 700/1251] eta: 0:05:49 lr: 0.000251 loss: 2.8433 (3.0504) grad_norm: 1.9954 (inf) time: 0.6261 [2021-03-27 20:29:14 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 710/1251] eta: 0:05:42 lr: 0.000250 loss: 3.1508 (3.0543) grad_norm: 1.9954 (inf) time: 0.6271 [2021-03-27 20:29:21 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 720/1251] eta: 0:05:36 lr: 0.000250 loss: 3.1679 (3.0527) grad_norm: 1.8725 (inf) time: 0.6305 [2021-03-27 20:29:27 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 730/1251] eta: 0:05:30 lr: 0.000250 loss: 3.0833 (3.0510) grad_norm: 1.8725 (inf) time: 0.6275 [2021-03-27 20:29:33 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 740/1251] eta: 0:05:23 lr: 0.000250 loss: 2.9394 (3.0467) grad_norm: 1.8930 (inf) time: 0.6227 [2021-03-27 20:29:40 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 750/1251] eta: 0:05:17 lr: 0.000250 loss: 3.1448 (3.0507) grad_norm: 1.9516 (inf) time: 0.6361 [2021-03-27 20:29:46 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 760/1251] eta: 0:05:11 lr: 0.000250 loss: 3.3283 (3.0538) grad_norm: 1.8745 (inf) time: 0.6364 [2021-03-27 20:29:52 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 770/1251] eta: 0:05:04 lr: 0.000250 loss: 3.3014 (3.0561) grad_norm: 2.0691 (inf) time: 0.6298 [2021-03-27 20:29:58 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 780/1251] eta: 0:04:58 lr: 0.000250 loss: 3.2363 (3.0580) grad_norm: 2.0526 (inf) time: 0.6273 [2021-03-27 20:30:05 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 790/1251] eta: 0:04:51 lr: 0.000250 loss: 3.2363 (3.0591) grad_norm: 1.9495 (inf) time: 0.6233 [2021-03-27 20:30:11 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 800/1251] eta: 0:04:45 lr: 0.000250 loss: 3.1595 (3.0582) grad_norm: 1.9171 (inf) time: 0.6279 [2021-03-27 20:30:17 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 810/1251] eta: 0:04:39 lr: 0.000250 loss: 2.9215 (3.0550) grad_norm: 2.0888 (inf) time: 0.6323 [2021-03-27 20:30:24 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 820/1251] eta: 0:04:32 lr: 0.000250 loss: 2.9215 (3.0539) grad_norm: 1.9829 (inf) time: 0.6373 [2021-03-27 20:30:30 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 830/1251] eta: 0:04:26 lr: 0.000250 loss: 3.0640 (3.0551) grad_norm: 2.0685 (inf) time: 0.6374 [2021-03-27 20:30:36 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 840/1251] eta: 0:04:20 lr: 0.000250 loss: 3.1306 (3.0562) grad_norm: 2.1342 (inf) time: 0.6308 [2021-03-27 20:30:43 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 850/1251] eta: 0:04:13 lr: 0.000250 loss: 3.1306 (3.0568) grad_norm: 1.9957 (inf) time: 0.6216 [2021-03-27 20:30:49 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 860/1251] eta: 0:04:07 lr: 0.000250 loss: 3.2200 (3.0594) grad_norm: 2.0371 (inf) time: 0.6182 [2021-03-27 20:30:55 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 870/1251] eta: 0:04:01 lr: 0.000250 loss: 3.2827 (3.0616) grad_norm: 2.0911 (inf) time: 0.6293 [2021-03-27 20:31:02 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 880/1251] eta: 0:03:54 lr: 0.000250 loss: 2.9502 (3.0582) grad_norm: 1.9676 (inf) time: 0.6392 [2021-03-27 20:31:08 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 890/1251] eta: 0:03:48 lr: 0.000250 loss: 3.0173 (3.0612) grad_norm: 1.9676 (inf) time: 0.6360 [2021-03-27 20:31:14 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 900/1251] eta: 0:03:42 lr: 0.000250 loss: 3.0709 (3.0604) grad_norm: 2.1044 (inf) time: 0.6272 [2021-03-27 20:31:20 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 910/1251] eta: 0:03:35 lr: 0.000250 loss: 3.0072 (3.0594) grad_norm: 1.9749 (inf) time: 0.6252 [2021-03-27 20:31:27 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 920/1251] eta: 0:03:29 lr: 0.000250 loss: 3.2597 (3.0605) grad_norm: 1.8923 (inf) time: 0.6265 [2021-03-27 20:31:33 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 930/1251] eta: 0:03:23 lr: 0.000250 loss: 3.2597 (3.0611) grad_norm: 1.8963 (inf) time: 0.6245 [2021-03-27 20:31:39 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 940/1251] eta: 0:03:16 lr: 0.000250 loss: 3.1648 (3.0612) grad_norm: 2.0005 (inf) time: 0.6276 [2021-03-27 20:31:45 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 950/1251] eta: 0:03:10 lr: 0.000250 loss: 3.1696 (3.0630) grad_norm: 2.0005 (inf) time: 0.6265 [2021-03-27 20:31:52 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 960/1251] eta: 0:03:04 lr: 0.000250 loss: 3.1053 (3.0611) grad_norm: 1.9897 (inf) time: 0.6213 [2021-03-27 20:31:58 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 970/1251] eta: 0:02:57 lr: 0.000250 loss: 3.0539 (3.0604) grad_norm: 1.9897 (inf) time: 0.6212 [2021-03-27 20:32:04 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 980/1251] eta: 0:02:51 lr: 0.000250 loss: 3.3739 (3.0616) grad_norm: 2.0223 (inf) time: 0.6251 [2021-03-27 20:32:10 swin_base_patch4_window7_224] INFO: Epoch: [201] [ 990/1251] eta: 0:02:45 lr: 0.000250 loss: 3.0825 (3.0606) grad_norm: 1.9526 (inf) time: 0.6273 [2021-03-27 20:32:17 swin_base_patch4_window7_224] INFO: Epoch: [201] [1000/1251] eta: 0:02:38 lr: 0.000249 loss: 3.0400 (3.0598) grad_norm: 1.8590 (inf) time: 0.6290 [2021-03-27 20:32:23 swin_base_patch4_window7_224] INFO: Epoch: [201] [1010/1251] eta: 0:02:32 lr: 0.000249 loss: 3.0026 (3.0578) grad_norm: 1.9212 (inf) time: 0.6334 [2021-03-27 20:32:29 swin_base_patch4_window7_224] INFO: Epoch: [201] [1020/1251] eta: 0:02:26 lr: 0.000249 loss: 3.0193 (3.0574) grad_norm: 1.9212 (inf) time: 0.6295 [2021-03-27 20:32:35 swin_base_patch4_window7_224] INFO: Epoch: [201] [1030/1251] eta: 0:02:19 lr: 0.000249 loss: 2.9831 (3.0568) grad_norm: 1.9185 (inf) time: 0.6213 [2021-03-27 20:32:42 swin_base_patch4_window7_224] INFO: Epoch: [201] [1040/1251] eta: 0:02:13 lr: 0.000249 loss: 2.9831 (3.0562) grad_norm: 1.9131 (inf) time: 0.6239 [2021-03-27 20:32:48 swin_base_patch4_window7_224] INFO: Epoch: [201] [1050/1251] eta: 0:02:07 lr: 0.000249 loss: 3.0149 (3.0557) grad_norm: 1.8918 (inf) time: 0.6251 [2021-03-27 20:32:54 swin_base_patch4_window7_224] INFO: Epoch: [201] [1060/1251] eta: 0:02:00 lr: 0.000249 loss: 3.0663 (3.0541) grad_norm: 2.0042 (inf) time: 0.6271 [2021-03-27 20:33:01 swin_base_patch4_window7_224] INFO: Epoch: [201] [1070/1251] eta: 0:01:54 lr: 0.000249 loss: 3.2914 (3.0567) grad_norm: 1.9736 (inf) time: 0.6369 [2021-03-27 20:33:07 swin_base_patch4_window7_224] INFO: Epoch: [201] [1080/1251] eta: 0:01:48 lr: 0.000249 loss: 3.3549 (3.0562) grad_norm: 1.9736 (inf) time: 0.6343 [2021-03-27 20:33:13 swin_base_patch4_window7_224] INFO: Epoch: [201] [1090/1251] eta: 0:01:41 lr: 0.000249 loss: 2.9707 (3.0541) grad_norm: 1.9780 (inf) time: 0.6242 [2021-03-27 20:33:20 swin_base_patch4_window7_224] INFO: Epoch: [201] [1100/1251] eta: 0:01:35 lr: 0.000249 loss: 3.0404 (3.0548) grad_norm: 1.9513 (inf) time: 0.6285 [2021-03-27 20:33:26 swin_base_patch4_window7_224] INFO: Epoch: [201] [1110/1251] eta: 0:01:29 lr: 0.000249 loss: 3.1174 (3.0540) grad_norm: 1.8903 (inf) time: 0.6323 [2021-03-27 20:33:32 swin_base_patch4_window7_224] INFO: Epoch: [201] [1120/1251] eta: 0:01:22 lr: 0.000249 loss: 3.0468 (3.0528) grad_norm: 1.8851 (inf) time: 0.6265 [2021-03-27 20:33:38 swin_base_patch4_window7_224] INFO: Epoch: [201] [1130/1251] eta: 0:01:16 lr: 0.000249 loss: 3.1375 (3.0530) grad_norm: 1.9237 (inf) time: 0.6246 [2021-03-27 20:33:45 swin_base_patch4_window7_224] INFO: Epoch: [201] [1140/1251] eta: 0:01:10 lr: 0.000249 loss: 3.2314 (3.0547) grad_norm: 2.0862 (inf) time: 0.6233 [2021-03-27 20:33:51 swin_base_patch4_window7_224] INFO: Epoch: [201] [1150/1251] eta: 0:01:03 lr: 0.000249 loss: 3.1739 (3.0537) grad_norm: 1.9673 (inf) time: 0.6210 [2021-03-27 20:33:57 swin_base_patch4_window7_224] INFO: Epoch: [201] [1160/1251] eta: 0:00:57 lr: 0.000249 loss: 3.0175 (3.0514) grad_norm: 1.9651 (inf) time: 0.6230 [2021-03-27 20:34:03 swin_base_patch4_window7_224] INFO: Epoch: [201] [1170/1251] eta: 0:00:51 lr: 0.000249 loss: 3.1029 (3.0529) grad_norm: 1.9651 (inf) time: 0.6227 [2021-03-27 20:34:09 swin_base_patch4_window7_224] INFO: Epoch: [201] [1180/1251] eta: 0:00:44 lr: 0.000249 loss: 3.2389 (3.0544) grad_norm: 2.0709 (inf) time: 0.6196 [2021-03-27 20:34:16 swin_base_patch4_window7_224] INFO: Epoch: [201] [1190/1251] eta: 0:00:38 lr: 0.000249 loss: 3.2200 (3.0531) grad_norm: 2.0709 (inf) time: 0.6206 [2021-03-27 20:34:22 swin_base_patch4_window7_224] INFO: Epoch: [201] [1200/1251] eta: 0:00:32 lr: 0.000249 loss: 3.1327 (3.0542) grad_norm: 1.9831 (inf) time: 0.6256 [2021-03-27 20:34:28 swin_base_patch4_window7_224] INFO: Epoch: [201] [1210/1251] eta: 0:00:25 lr: 0.000249 loss: 3.4110 (3.0553) grad_norm: 2.0457 (inf) time: 0.6268 [2021-03-27 20:34:34 swin_base_patch4_window7_224] INFO: Epoch: [201] [1220/1251] eta: 0:00:19 lr: 0.000249 loss: 2.9351 (3.0545) grad_norm: 2.1160 (inf) time: 0.6242 [2021-03-27 20:34:41 swin_base_patch4_window7_224] INFO: Epoch: [201] [1230/1251] eta: 0:00:13 lr: 0.000249 loss: 2.9351 (3.0538) grad_norm: 1.9835 (inf) time: 0.6243 [2021-03-27 20:34:47 swin_base_patch4_window7_224] INFO: Epoch: [201] [1240/1251] eta: 0:00:06 lr: 0.000249 loss: 3.1731 (3.0540) grad_norm: 1.9116 (inf) time: 0.6221 [2021-03-27 20:34:53 swin_base_patch4_window7_224] INFO: Epoch: [201] [1250/1251] eta: 0:00:00 lr: 0.000249 loss: 3.1767 (3.0538) grad_norm: 1.9703 (inf) time: 0.6181 [2021-03-27 20:35:04 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:03:10 loss: 1.3738 (1.3738) acc1: 71.8750 (71.8750) acc5: 90.6250 (90.6250) [2021-03-27 20:35:07 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:25 loss: 0.8873 (0.8890) acc1: 79.6875 (80.1136) acc5: 96.8750 (95.7386) [2021-03-27 20:35:09 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:12 loss: 0.7854 (0.8499) acc1: 81.2500 (80.5060) acc5: 96.8750 (96.3542) [2021-03-27 20:35:12 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:07 loss: 0.7761 (0.8308) acc1: 81.2500 (80.9980) acc5: 96.8750 (96.2198) [2021-03-27 20:35:13 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7888 (0.8264) acc1: 81.2500 (80.7927) acc5: 96.8750 (96.2652) [2021-03-27 20:35:14 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7674 (0.8265) acc1: 81.2500 (80.6400) acc5: 96.8750 (96.1920) [2021-03-27 20:35:25 swin_base_patch4_window7_224] INFO: * Acc@1 81.022 Acc@5 95.778 loss 0.818 [2021-03-27 20:35:25 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.0% [2021-03-27 20:35:25 swin_base_patch4_window7_224] INFO: Max accuracy: 81.06% [2021-03-27 20:35:30 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 0/1251] eta: 1:34:38 lr: 0.000249 loss: 3.4771 (3.4771) grad_norm: 1.6903 (1.6903) time: 4.5393 [2021-03-27 20:35:36 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 10/1251] eta: 0:20:43 lr: 0.000249 loss: 2.9865 (2.7783) grad_norm: 1.8440 (1.9059) time: 1.0017 [2021-03-27 20:35:43 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 20/1251] eta: 0:16:55 lr: 0.000249 loss: 3.0079 (2.9144) grad_norm: 1.9089 (1.9474) time: 0.6391 [2021-03-27 20:35:49 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 30/1251] eta: 0:15:32 lr: 0.000248 loss: 3.4249 (2.9976) grad_norm: 2.0446 (2.0078) time: 0.6333 [2021-03-27 20:35:55 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 40/1251] eta: 0:14:45 lr: 0.000248 loss: 3.0850 (3.0150) grad_norm: 2.0768 (2.0189) time: 0.6323 [2021-03-27 20:36:01 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 50/1251] eta: 0:14:14 lr: 0.000248 loss: 3.2743 (3.0472) grad_norm: 2.0751 (2.0747) time: 0.6300 [2021-03-27 20:36:08 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 60/1251] eta: 0:13:51 lr: 0.000248 loss: 3.3111 (3.0760) grad_norm: 2.0586 (2.0966) time: 0.6311 [2021-03-27 20:36:14 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 70/1251] eta: 0:13:34 lr: 0.000248 loss: 3.2622 (3.1036) grad_norm: 1.9844 (2.0949) time: 0.6347 [2021-03-27 20:36:20 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 80/1251] eta: 0:13:17 lr: 0.000248 loss: 3.2622 (3.1228) grad_norm: 2.0268 (2.0852) time: 0.6291 [2021-03-27 20:36:27 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 90/1251] eta: 0:13:03 lr: 0.000248 loss: 3.2347 (3.1162) grad_norm: 1.9227 (2.0739) time: 0.6215 [2021-03-27 20:36:33 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 100/1251] eta: 0:12:52 lr: 0.000248 loss: 3.1218 (3.1193) grad_norm: 1.9390 (2.0624) time: 0.6311 [2021-03-27 20:36:39 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 110/1251] eta: 0:12:40 lr: 0.000248 loss: 3.0450 (3.1040) grad_norm: 1.9390 (2.0555) time: 0.6293 [2021-03-27 20:36:45 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 120/1251] eta: 0:12:30 lr: 0.000248 loss: 3.0450 (3.0938) grad_norm: 1.9080 (2.0436) time: 0.6232 [2021-03-27 20:36:52 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 130/1251] eta: 0:12:21 lr: 0.000248 loss: 3.1334 (3.0886) grad_norm: 1.9280 (2.0404) time: 0.6320 [2021-03-27 20:36:58 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 140/1251] eta: 0:12:12 lr: 0.000248 loss: 3.1334 (3.0769) grad_norm: 1.9620 (2.0420) time: 0.6373 [2021-03-27 20:37:04 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 150/1251] eta: 0:12:03 lr: 0.000248 loss: 2.6206 (3.0475) grad_norm: 2.0259 (2.0539) time: 0.6317 [2021-03-27 20:37:11 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 160/1251] eta: 0:11:54 lr: 0.000248 loss: 3.0005 (3.0590) grad_norm: 2.0918 (2.0562) time: 0.6245 [2021-03-27 20:37:17 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 170/1251] eta: 0:11:46 lr: 0.000248 loss: 2.9709 (3.0473) grad_norm: 2.0187 (2.0493) time: 0.6253 [2021-03-27 20:37:23 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 180/1251] eta: 0:11:38 lr: 0.000248 loss: 3.0918 (3.0532) grad_norm: 1.9013 (2.0521) time: 0.6280 [2021-03-27 20:37:29 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 190/1251] eta: 0:11:30 lr: 0.000248 loss: 3.2528 (3.0685) grad_norm: 1.8482 (2.0382) time: 0.6241 [2021-03-27 20:37:36 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 200/1251] eta: 0:11:22 lr: 0.000248 loss: 3.2106 (3.0623) grad_norm: 1.8651 (2.0377) time: 0.6197 [2021-03-27 20:37:42 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 210/1251] eta: 0:11:14 lr: 0.000248 loss: 3.1406 (3.0691) grad_norm: 1.8888 (2.0285) time: 0.6234 [2021-03-27 20:37:48 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 220/1251] eta: 0:11:06 lr: 0.000248 loss: 3.1909 (3.0600) grad_norm: 1.8826 (2.0277) time: 0.6264 [2021-03-27 20:37:55 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 230/1251] eta: 0:10:59 lr: 0.000248 loss: 2.8271 (3.0498) grad_norm: 1.9725 (2.0314) time: 0.6297 [2021-03-27 20:38:01 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 240/1251] eta: 0:10:52 lr: 0.000248 loss: 3.0667 (3.0595) grad_norm: 2.0152 (2.0321) time: 0.6309 [2021-03-27 20:38:07 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 250/1251] eta: 0:10:45 lr: 0.000248 loss: 3.1372 (3.0543) grad_norm: 1.9151 (2.0264) time: 0.6302 [2021-03-27 20:38:14 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 260/1251] eta: 0:10:39 lr: 0.000248 loss: 3.2184 (3.0622) grad_norm: 1.8719 (2.0267) time: 0.6362 [2021-03-27 20:38:20 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 270/1251] eta: 0:10:32 lr: 0.000248 loss: 3.2181 (3.0565) grad_norm: 1.8803 (2.0219) time: 0.6397 [2021-03-27 20:38:26 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 280/1251] eta: 0:10:25 lr: 0.000248 loss: 3.1157 (3.0544) grad_norm: 1.9055 (2.0285) time: 0.6350 [2021-03-27 20:38:33 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 290/1251] eta: 0:10:18 lr: 0.000248 loss: 3.1893 (3.0553) grad_norm: 2.0717 (2.0281) time: 0.6329 [2021-03-27 20:38:39 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 300/1251] eta: 0:10:11 lr: 0.000248 loss: 3.0986 (3.0543) grad_norm: 2.0173 (2.0316) time: 0.6341 [2021-03-27 20:38:45 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 310/1251] eta: 0:10:05 lr: 0.000247 loss: 2.8545 (3.0493) grad_norm: 1.9709 (2.0326) time: 0.6296 [2021-03-27 20:38:51 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 320/1251] eta: 0:09:58 lr: 0.000247 loss: 3.0494 (3.0491) grad_norm: 1.9709 (2.0315) time: 0.6267 [2021-03-27 20:38:58 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 330/1251] eta: 0:09:51 lr: 0.000247 loss: 3.1195 (3.0476) grad_norm: 1.9992 (2.0305) time: 0.6301 [2021-03-27 20:39:04 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 340/1251] eta: 0:09:44 lr: 0.000247 loss: 3.1049 (3.0434) grad_norm: 1.8847 (2.0298) time: 0.6284 [2021-03-27 20:39:10 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 350/1251] eta: 0:09:37 lr: 0.000247 loss: 2.9934 (3.0381) grad_norm: 1.9877 (2.0300) time: 0.6231 [2021-03-27 20:39:17 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 360/1251] eta: 0:09:31 lr: 0.000247 loss: 3.1240 (3.0415) grad_norm: 1.9570 (2.0265) time: 0.6281 [2021-03-27 20:39:23 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 370/1251] eta: 0:09:24 lr: 0.000247 loss: 3.0221 (3.0392) grad_norm: 1.8444 (2.0235) time: 0.6287 [2021-03-27 20:39:29 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 380/1251] eta: 0:09:17 lr: 0.000247 loss: 3.0221 (3.0396) grad_norm: 2.0274 (2.0299) time: 0.6245 [2021-03-27 20:39:35 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 390/1251] eta: 0:09:10 lr: 0.000247 loss: 3.0241 (3.0353) grad_norm: 2.1440 (2.0324) time: 0.6241 [2021-03-27 20:39:42 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 400/1251] eta: 0:09:04 lr: 0.000247 loss: 3.0472 (3.0403) grad_norm: 1.8881 (2.0270) time: 0.6287 [2021-03-27 20:39:48 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 410/1251] eta: 0:08:57 lr: 0.000247 loss: 3.2143 (3.0418) grad_norm: 1.7641 (2.0246) time: 0.6342 [2021-03-27 20:39:54 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 420/1251] eta: 0:08:50 lr: 0.000247 loss: 3.1260 (3.0445) grad_norm: 1.8336 (2.0220) time: 0.6289 [2021-03-27 20:40:01 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 430/1251] eta: 0:08:44 lr: 0.000247 loss: 3.2801 (3.0457) grad_norm: 1.8871 (2.0209) time: 0.6234 [2021-03-27 20:40:07 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 440/1251] eta: 0:08:37 lr: 0.000247 loss: 3.2232 (3.0466) grad_norm: 1.9052 (2.0176) time: 0.6282 [2021-03-27 20:40:13 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 450/1251] eta: 0:08:31 lr: 0.000247 loss: 3.2085 (3.0480) grad_norm: 1.9188 (2.0177) time: 0.6300 [2021-03-27 20:40:20 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 460/1251] eta: 0:08:24 lr: 0.000247 loss: 3.1054 (3.0453) grad_norm: 1.9486 (2.0151) time: 0.6337 [2021-03-27 20:40:26 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 470/1251] eta: 0:08:18 lr: 0.000247 loss: 2.9977 (3.0448) grad_norm: 1.8884 (2.0143) time: 0.6322 [2021-03-27 20:40:32 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 480/1251] eta: 0:08:11 lr: 0.000247 loss: 3.0654 (3.0446) grad_norm: 1.9433 (2.0176) time: 0.6220 [2021-03-27 20:40:38 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 490/1251] eta: 0:08:04 lr: 0.000247 loss: 3.0804 (3.0458) grad_norm: 2.0384 (2.0179) time: 0.6202 [2021-03-27 20:40:44 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 500/1251] eta: 0:07:58 lr: 0.000247 loss: 3.0833 (3.0475) grad_norm: 1.9485 (2.0194) time: 0.6260 [2021-03-27 20:40:51 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 510/1251] eta: 0:07:51 lr: 0.000247 loss: 3.2392 (3.0495) grad_norm: 1.9114 (2.0186) time: 0.6261 [2021-03-27 20:40:57 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 520/1251] eta: 0:07:45 lr: 0.000247 loss: 3.0676 (3.0461) grad_norm: 1.9860 (2.0197) time: 0.6217 [2021-03-27 20:41:03 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 530/1251] eta: 0:07:38 lr: 0.000247 loss: 2.8752 (3.0420) grad_norm: 1.9683 (2.0197) time: 0.6217 [2021-03-27 20:41:09 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 540/1251] eta: 0:07:32 lr: 0.000247 loss: 2.9360 (3.0433) grad_norm: 1.9595 (2.0202) time: 0.6221 [2021-03-27 20:41:16 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 550/1251] eta: 0:07:26 lr: 0.000247 loss: 3.0838 (3.0443) grad_norm: 1.9912 (2.0211) time: 0.6375 [2021-03-27 20:41:22 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 560/1251] eta: 0:07:19 lr: 0.000247 loss: 3.1255 (3.0426) grad_norm: 2.0591 (2.0237) time: 0.6475 [2021-03-27 20:41:29 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 570/1251] eta: 0:07:13 lr: 0.000247 loss: 3.1694 (3.0447) grad_norm: 1.9501 (2.0224) time: 0.6396 [2021-03-27 20:41:35 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 580/1251] eta: 0:07:07 lr: 0.000247 loss: 3.1639 (3.0468) grad_norm: 1.8959 (2.0228) time: 0.6413 [2021-03-27 20:41:41 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 590/1251] eta: 0:07:00 lr: 0.000246 loss: 3.1418 (3.0483) grad_norm: 1.8959 (2.0224) time: 0.6400 [2021-03-27 20:41:48 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 600/1251] eta: 0:06:54 lr: 0.000246 loss: 3.1761 (3.0503) grad_norm: 2.0207 (2.0246) time: 0.6296 [2021-03-27 20:41:54 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 610/1251] eta: 0:06:47 lr: 0.000246 loss: 3.2321 (3.0527) grad_norm: 1.9582 (2.0220) time: 0.6311 [2021-03-27 20:42:00 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 620/1251] eta: 0:06:41 lr: 0.000246 loss: 3.3009 (3.0568) grad_norm: 1.8997 (2.0212) time: 0.6360 [2021-03-27 20:42:07 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 630/1251] eta: 0:06:35 lr: 0.000246 loss: 3.0836 (3.0550) grad_norm: 1.8663 (2.0190) time: 0.6363 [2021-03-27 20:42:13 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 640/1251] eta: 0:06:28 lr: 0.000246 loss: 3.0614 (3.0578) grad_norm: 1.8663 (2.0178) time: 0.6362 [2021-03-27 20:42:20 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 650/1251] eta: 0:06:22 lr: 0.000246 loss: 2.9937 (3.0526) grad_norm: 1.8399 (2.0157) time: 0.6366 [2021-03-27 20:42:26 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 660/1251] eta: 0:06:15 lr: 0.000246 loss: 2.7423 (3.0504) grad_norm: 1.9112 (2.0228) time: 0.6325 [2021-03-27 20:42:32 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 670/1251] eta: 0:06:09 lr: 0.000246 loss: 3.1765 (3.0545) grad_norm: 1.9675 (2.0204) time: 0.6260 [2021-03-27 20:42:38 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 680/1251] eta: 0:06:03 lr: 0.000246 loss: 3.2577 (3.0522) grad_norm: 1.8959 (2.0192) time: 0.6249 [2021-03-27 20:42:45 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 690/1251] eta: 0:05:56 lr: 0.000246 loss: 3.1678 (3.0530) grad_norm: 1.8678 (2.0172) time: 0.6274 [2021-03-27 20:42:51 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 700/1251] eta: 0:05:50 lr: 0.000246 loss: 3.1722 (3.0526) grad_norm: 1.7928 (2.0147) time: 0.6254 [2021-03-27 20:42:57 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 710/1251] eta: 0:05:43 lr: 0.000246 loss: 2.7651 (3.0490) grad_norm: 1.9417 (2.0155) time: 0.6237 [2021-03-27 20:43:03 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 720/1251] eta: 0:05:37 lr: 0.000246 loss: 2.7147 (3.0450) grad_norm: 2.0171 (2.0142) time: 0.6280 [2021-03-27 20:43:10 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 730/1251] eta: 0:05:30 lr: 0.000246 loss: 2.9885 (3.0442) grad_norm: 2.0171 (2.0140) time: 0.6262 [2021-03-27 20:43:16 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 740/1251] eta: 0:05:24 lr: 0.000246 loss: 2.9885 (3.0422) grad_norm: 2.0621 (2.0140) time: 0.6296 [2021-03-27 20:43:22 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 750/1251] eta: 0:05:18 lr: 0.000246 loss: 3.1411 (3.0445) grad_norm: 2.0472 (2.0134) time: 0.6381 [2021-03-27 20:43:29 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 760/1251] eta: 0:05:11 lr: 0.000246 loss: 3.1307 (3.0417) grad_norm: 1.9559 (2.0133) time: 0.6374 [2021-03-27 20:43:35 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 770/1251] eta: 0:05:05 lr: 0.000246 loss: 2.8678 (3.0389) grad_norm: 1.9999 (2.0150) time: 0.6323 [2021-03-27 20:43:41 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 780/1251] eta: 0:04:59 lr: 0.000246 loss: 2.9432 (3.0393) grad_norm: 2.1070 (2.0163) time: 0.6283 [2021-03-27 20:43:48 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 790/1251] eta: 0:04:52 lr: 0.000246 loss: 3.0836 (3.0398) grad_norm: 2.0698 (2.0170) time: 0.6240 [2021-03-27 20:43:54 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 800/1251] eta: 0:04:46 lr: 0.000246 loss: 3.1217 (3.0402) grad_norm: 2.0548 (2.0183) time: 0.6356 [2021-03-27 20:44:00 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 810/1251] eta: 0:04:40 lr: 0.000246 loss: 3.2354 (3.0414) grad_norm: 2.0680 (2.0220) time: 0.6386 [2021-03-27 20:44:07 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 820/1251] eta: 0:04:33 lr: 0.000246 loss: 3.2354 (3.0424) grad_norm: 1.9231 (2.0212) time: 0.6327 [2021-03-27 20:44:13 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 830/1251] eta: 0:04:27 lr: 0.000246 loss: 2.9891 (3.0398) grad_norm: 1.8539 (2.0232) time: 0.6289 [2021-03-27 20:44:19 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 840/1251] eta: 0:04:20 lr: 0.000246 loss: 2.9491 (3.0381) grad_norm: 1.8343 (2.0224) time: 0.6198 [2021-03-27 20:44:26 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 850/1251] eta: 0:04:14 lr: 0.000246 loss: 2.9810 (3.0368) grad_norm: 1.9866 (2.0240) time: 0.6316 [2021-03-27 20:44:32 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 860/1251] eta: 0:04:08 lr: 0.000246 loss: 3.1261 (3.0366) grad_norm: 2.1736 (2.0270) time: 0.6373 [2021-03-27 20:44:38 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 870/1251] eta: 0:04:01 lr: 0.000245 loss: 3.0640 (3.0360) grad_norm: 1.9825 (2.0262) time: 0.6320 [2021-03-27 20:44:45 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 880/1251] eta: 0:03:55 lr: 0.000245 loss: 2.9271 (3.0349) grad_norm: 1.9595 (2.0264) time: 0.6351 [2021-03-27 20:44:51 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 890/1251] eta: 0:03:49 lr: 0.000245 loss: 2.9271 (3.0333) grad_norm: 1.9729 (2.0276) time: 0.6304 [2021-03-27 20:44:57 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 900/1251] eta: 0:03:42 lr: 0.000245 loss: 3.0388 (3.0332) grad_norm: 1.9495 (2.0269) time: 0.6265 [2021-03-27 20:45:03 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 910/1251] eta: 0:03:36 lr: 0.000245 loss: 2.9350 (3.0305) grad_norm: 1.9086 (2.0271) time: 0.6248 [2021-03-27 20:45:10 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 920/1251] eta: 0:03:29 lr: 0.000245 loss: 2.9350 (3.0305) grad_norm: 2.0070 (2.0264) time: 0.6206 [2021-03-27 20:45:16 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 930/1251] eta: 0:03:23 lr: 0.000245 loss: 3.0278 (3.0285) grad_norm: 1.9269 (2.0257) time: 0.6211 [2021-03-27 20:45:22 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 940/1251] eta: 0:03:17 lr: 0.000245 loss: 3.0278 (3.0290) grad_norm: 2.0239 (2.0270) time: 0.6233 [2021-03-27 20:45:28 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 950/1251] eta: 0:03:10 lr: 0.000245 loss: 3.1533 (3.0304) grad_norm: 2.0724 (2.0275) time: 0.6230 [2021-03-27 20:45:34 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 960/1251] eta: 0:03:04 lr: 0.000245 loss: 3.2347 (3.0322) grad_norm: 2.0362 (2.0274) time: 0.6248 [2021-03-27 20:45:41 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 970/1251] eta: 0:02:58 lr: 0.000245 loss: 3.1235 (3.0316) grad_norm: 2.0034 (2.0270) time: 0.6239 [2021-03-27 20:45:47 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 980/1251] eta: 0:02:51 lr: 0.000245 loss: 3.0612 (3.0316) grad_norm: 1.9942 (2.0265) time: 0.6223 [2021-03-27 20:45:53 swin_base_patch4_window7_224] INFO: Epoch: [202] [ 990/1251] eta: 0:02:45 lr: 0.000245 loss: 3.2355 (3.0327) grad_norm: 1.8922 (2.0257) time: 0.6246 [2021-03-27 20:45:59 swin_base_patch4_window7_224] INFO: Epoch: [202] [1000/1251] eta: 0:02:39 lr: 0.000245 loss: 3.0064 (3.0318) grad_norm: 1.8583 (2.0247) time: 0.6285 [2021-03-27 20:46:06 swin_base_patch4_window7_224] INFO: Epoch: [202] [1010/1251] eta: 0:02:32 lr: 0.000245 loss: 3.2766 (3.0338) grad_norm: 1.9610 (2.0248) time: 0.6319 [2021-03-27 20:46:12 swin_base_patch4_window7_224] INFO: Epoch: [202] [1020/1251] eta: 0:02:26 lr: 0.000245 loss: 3.2090 (3.0322) grad_norm: 2.0114 (2.0272) time: 0.6278 [2021-03-27 20:46:18 swin_base_patch4_window7_224] INFO: Epoch: [202] [1030/1251] eta: 0:02:19 lr: 0.000245 loss: 3.1313 (3.0335) grad_norm: 2.0254 (2.0285) time: 0.6275 [2021-03-27 20:46:25 swin_base_patch4_window7_224] INFO: Epoch: [202] [1040/1251] eta: 0:02:13 lr: 0.000245 loss: 3.1313 (3.0308) grad_norm: 2.1471 (2.0287) time: 0.6344 [2021-03-27 20:46:31 swin_base_patch4_window7_224] INFO: Epoch: [202] [1050/1251] eta: 0:02:07 lr: 0.000245 loss: 3.1519 (3.0323) grad_norm: 2.0100 (2.0295) time: 0.6307 [2021-03-27 20:46:37 swin_base_patch4_window7_224] INFO: Epoch: [202] [1060/1251] eta: 0:02:00 lr: 0.000245 loss: 3.3238 (3.0329) grad_norm: 2.0100 (2.0300) time: 0.6220 [2021-03-27 20:46:43 swin_base_patch4_window7_224] INFO: Epoch: [202] [1070/1251] eta: 0:01:54 lr: 0.000245 loss: 3.1707 (3.0340) grad_norm: 2.0065 (2.0311) time: 0.6218 [2021-03-27 20:46:50 swin_base_patch4_window7_224] INFO: Epoch: [202] [1080/1251] eta: 0:01:48 lr: 0.000245 loss: 3.2963 (3.0355) grad_norm: 1.9525 (2.0308) time: 0.6260 [2021-03-27 20:46:56 swin_base_patch4_window7_224] INFO: Epoch: [202] [1090/1251] eta: 0:01:41 lr: 0.000245 loss: 3.3799 (3.0369) grad_norm: 1.9058 (2.0310) time: 0.6287 [2021-03-27 20:47:02 swin_base_patch4_window7_224] INFO: Epoch: [202] [1100/1251] eta: 0:01:35 lr: 0.000245 loss: 3.2762 (3.0374) grad_norm: 1.9108 (2.0313) time: 0.6275 [2021-03-27 20:47:09 swin_base_patch4_window7_224] INFO: Epoch: [202] [1110/1251] eta: 0:01:29 lr: 0.000245 loss: 2.9688 (3.0362) grad_norm: 1.9921 (2.0323) time: 0.6265 [2021-03-27 20:47:15 swin_base_patch4_window7_224] INFO: Epoch: [202] [1120/1251] eta: 0:01:22 lr: 0.000245 loss: 2.9688 (3.0368) grad_norm: 1.9921 (2.0327) time: 0.6322 [2021-03-27 20:47:21 swin_base_patch4_window7_224] INFO: Epoch: [202] [1130/1251] eta: 0:01:16 lr: 0.000245 loss: 3.2064 (3.0390) grad_norm: 1.9983 (2.0333) time: 0.6339 [2021-03-27 20:47:27 swin_base_patch4_window7_224] INFO: Epoch: [202] [1140/1251] eta: 0:01:10 lr: 0.000245 loss: 3.1475 (3.0388) grad_norm: 1.9763 (2.0330) time: 0.6244 [2021-03-27 20:47:34 swin_base_patch4_window7_224] INFO: Epoch: [202] [1150/1251] eta: 0:01:03 lr: 0.000245 loss: 3.0354 (3.0397) grad_norm: 1.9082 (2.0326) time: 0.6209 [2021-03-27 20:47:40 swin_base_patch4_window7_224] INFO: Epoch: [202] [1160/1251] eta: 0:00:57 lr: 0.000244 loss: 3.2815 (3.0408) grad_norm: 1.8623 (2.0323) time: 0.6269 [2021-03-27 20:47:46 swin_base_patch4_window7_224] INFO: Epoch: [202] [1170/1251] eta: 0:00:51 lr: 0.000244 loss: 3.2973 (3.0420) grad_norm: 2.0120 (2.0335) time: 0.6293 [2021-03-27 20:47:52 swin_base_patch4_window7_224] INFO: Epoch: [202] [1180/1251] eta: 0:00:44 lr: 0.000244 loss: 3.2117 (3.0432) grad_norm: 2.0244 (2.0327) time: 0.6277 [2021-03-27 20:47:59 swin_base_patch4_window7_224] INFO: Epoch: [202] [1190/1251] eta: 0:00:38 lr: 0.000244 loss: 3.0327 (3.0422) grad_norm: 1.9077 (2.0331) time: 0.6280 [2021-03-27 20:48:05 swin_base_patch4_window7_224] INFO: Epoch: [202] [1200/1251] eta: 0:00:32 lr: 0.000244 loss: 3.0788 (3.0417) grad_norm: 2.0634 (2.0342) time: 0.6308 [2021-03-27 20:48:11 swin_base_patch4_window7_224] INFO: Epoch: [202] [1210/1251] eta: 0:00:25 lr: 0.000244 loss: 3.0788 (3.0410) grad_norm: 1.9604 (2.0335) time: 0.6340 [2021-03-27 20:48:18 swin_base_patch4_window7_224] INFO: Epoch: [202] [1220/1251] eta: 0:00:19 lr: 0.000244 loss: 3.1067 (3.0415) grad_norm: 1.9327 (2.0328) time: 0.6299 [2021-03-27 20:48:24 swin_base_patch4_window7_224] INFO: Epoch: [202] [1230/1251] eta: 0:00:13 lr: 0.000244 loss: 3.2998 (3.0440) grad_norm: 1.9327 (2.0324) time: 0.6258 [2021-03-27 20:48:30 swin_base_patch4_window7_224] INFO: Epoch: [202] [1240/1251] eta: 0:00:06 lr: 0.000244 loss: 3.2813 (3.0422) grad_norm: 1.9684 (2.0319) time: 0.6260 [2021-03-27 20:48:37 swin_base_patch4_window7_224] INFO: Epoch: [202] [1250/1251] eta: 0:00:00 lr: 0.000244 loss: 2.8220 (3.0412) grad_norm: 2.0276 (2.0337) time: 0.6290 [2021-03-27 20:48:47 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:15 loss: 0.8386 (0.8386) acc1: 78.1250 (78.1250) acc5: 93.7500 (93.7500) [2021-03-27 20:48:49 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.8361 (0.7897) acc1: 82.8125 (81.9602) acc5: 96.8750 (95.7386) [2021-03-27 20:48:52 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7564 (0.7789) acc1: 82.8125 (81.4732) acc5: 96.8750 (96.2054) [2021-03-27 20:48:54 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7606 (0.7955) acc1: 82.8125 (81.1996) acc5: 95.3125 (96.1190) [2021-03-27 20:48:57 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7829 (0.8025) acc1: 81.2500 (80.8308) acc5: 95.3125 (96.1128) [2021-03-27 20:48:58 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8581 (0.8154) acc1: 79.6875 (80.5760) acc5: 96.2264 (96.1280) [2021-03-27 20:49:11 swin_base_patch4_window7_224] INFO: * Acc@1 81.064 Acc@5 95.668 loss 0.813 [2021-03-27 20:49:11 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.1% [2021-03-27 20:49:11 swin_base_patch4_window7_224] INFO: Max accuracy: 81.06% [2021-03-27 20:49:16 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 0/1251] eta: 1:33:29 lr: 0.000244 loss: 2.6446 (2.6446) grad_norm: 1.6950 (1.6950) time: 4.4839 [2021-03-27 20:49:22 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 10/1251] eta: 0:20:31 lr: 0.000244 loss: 3.1818 (3.1423) grad_norm: 1.9512 (2.0674) time: 0.9922 [2021-03-27 20:49:28 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 20/1251] eta: 0:16:45 lr: 0.000244 loss: 3.1750 (3.1327) grad_norm: 1.9512 (2.0325) time: 0.6338 [2021-03-27 20:49:35 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 30/1251] eta: 0:15:24 lr: 0.000244 loss: 3.1082 (3.1496) grad_norm: 1.9615 (2.0290) time: 0.6275 [2021-03-27 20:49:41 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 40/1251] eta: 0:14:39 lr: 0.000244 loss: 3.2022 (3.1342) grad_norm: 1.9803 (2.0323) time: 0.6310 [2021-03-27 20:49:47 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 50/1251] eta: 0:14:07 lr: 0.000244 loss: 3.1463 (3.1183) grad_norm: 1.9754 (2.0057) time: 0.6269 [2021-03-27 20:49:53 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 60/1251] eta: 0:13:45 lr: 0.000244 loss: 3.1400 (3.1129) grad_norm: 1.9479 (2.0059) time: 0.6245 [2021-03-27 20:50:00 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 70/1251] eta: 0:13:28 lr: 0.000244 loss: 3.0802 (3.0777) grad_norm: 1.9262 (1.9955) time: 0.6294 [2021-03-27 20:50:06 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 80/1251] eta: 0:13:12 lr: 0.000244 loss: 3.1522 (3.0879) grad_norm: 1.8922 (1.9872) time: 0.6275 [2021-03-27 20:50:12 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 90/1251] eta: 0:12:59 lr: 0.000244 loss: 3.1788 (3.0697) grad_norm: 1.9040 (2.0031) time: 0.6240 [2021-03-27 20:50:18 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 100/1251] eta: 0:12:46 lr: 0.000244 loss: 3.0120 (3.0659) grad_norm: 1.8690 (1.9921) time: 0.6233 [2021-03-27 20:50:25 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 110/1251] eta: 0:12:35 lr: 0.000244 loss: 3.1832 (3.0751) grad_norm: 1.9222 (1.9986) time: 0.6218 [2021-03-27 20:50:31 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 120/1251] eta: 0:12:26 lr: 0.000244 loss: 3.0094 (3.0764) grad_norm: 2.0230 (2.0024) time: 0.6262 [2021-03-27 20:50:37 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 130/1251] eta: 0:12:16 lr: 0.000244 loss: 3.0087 (3.0755) grad_norm: 1.9109 (2.0033) time: 0.6310 [2021-03-27 20:50:44 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 140/1251] eta: 0:12:08 lr: 0.000244 loss: 3.0087 (3.0778) grad_norm: 2.0477 (2.0116) time: 0.6336 [2021-03-27 20:50:50 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 150/1251] eta: 0:12:00 lr: 0.000244 loss: 3.2619 (3.0846) grad_norm: 2.0123 (2.0107) time: 0.6324 [2021-03-27 20:50:56 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 160/1251] eta: 0:11:51 lr: 0.000244 loss: 3.1495 (3.0835) grad_norm: 1.8743 (2.0057) time: 0.6258 [2021-03-27 20:51:02 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 170/1251] eta: 0:11:43 lr: 0.000244 loss: 3.1495 (3.0941) grad_norm: 2.0595 (2.0177) time: 0.6250 [2021-03-27 20:51:09 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 180/1251] eta: 0:11:36 lr: 0.000244 loss: 3.2894 (3.0900) grad_norm: 1.9718 (2.0119) time: 0.6321 [2021-03-27 20:51:15 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 190/1251] eta: 0:11:28 lr: 0.000243 loss: 3.3159 (3.1084) grad_norm: 1.8896 (2.0155) time: 0.6306 [2021-03-27 20:51:21 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 200/1251] eta: 0:11:21 lr: 0.000243 loss: 3.3474 (3.1085) grad_norm: 1.9683 (2.0170) time: 0.6323 [2021-03-27 20:51:28 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 210/1251] eta: 0:11:13 lr: 0.000243 loss: 3.2635 (3.1112) grad_norm: 2.0026 (2.0211) time: 0.6315 [2021-03-27 20:51:34 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 220/1251] eta: 0:11:06 lr: 0.000243 loss: 3.1631 (3.1141) grad_norm: 2.0090 (2.0216) time: 0.6240 [2021-03-27 20:51:40 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 230/1251] eta: 0:10:59 lr: 0.000243 loss: 3.0799 (3.1042) grad_norm: 1.7661 (2.0156) time: 0.6352 [2021-03-27 20:51:47 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 240/1251] eta: 0:10:52 lr: 0.000243 loss: 3.0521 (3.1067) grad_norm: 1.8473 (2.0173) time: 0.6375 [2021-03-27 20:51:53 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 250/1251] eta: 0:10:45 lr: 0.000243 loss: 3.0521 (3.0943) grad_norm: 1.8848 (2.0179) time: 0.6330 [2021-03-27 20:51:59 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 260/1251] eta: 0:10:38 lr: 0.000243 loss: 2.9654 (3.0916) grad_norm: 2.0390 (2.0220) time: 0.6311 [2021-03-27 20:52:06 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 270/1251] eta: 0:10:31 lr: 0.000243 loss: 2.9654 (3.0822) grad_norm: 2.1212 (2.0282) time: 0.6289 [2021-03-27 20:52:12 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 280/1251] eta: 0:10:24 lr: 0.000243 loss: 2.9002 (3.0747) grad_norm: 2.0786 (2.0276) time: 0.6258 [2021-03-27 20:52:18 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 290/1251] eta: 0:10:17 lr: 0.000243 loss: 3.1695 (3.0756) grad_norm: 2.0292 (2.0335) time: 0.6216 [2021-03-27 20:52:24 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 300/1251] eta: 0:10:10 lr: 0.000243 loss: 2.8879 (3.0602) grad_norm: 2.0359 (2.0312) time: 0.6283 [2021-03-27 20:52:31 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 310/1251] eta: 0:10:03 lr: 0.000243 loss: 2.6928 (3.0510) grad_norm: 1.8957 (2.0282) time: 0.6277 [2021-03-27 20:52:37 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 320/1251] eta: 0:09:56 lr: 0.000243 loss: 2.8976 (3.0508) grad_norm: 1.9699 (2.0356) time: 0.6271 [2021-03-27 20:52:43 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 330/1251] eta: 0:09:50 lr: 0.000243 loss: 3.0107 (3.0504) grad_norm: 1.9240 (2.0359) time: 0.6357 [2021-03-27 20:52:49 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 340/1251] eta: 0:09:43 lr: 0.000243 loss: 3.0385 (3.0496) grad_norm: 1.9028 (2.0348) time: 0.6321 [2021-03-27 20:52:56 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 350/1251] eta: 0:09:36 lr: 0.000243 loss: 3.0385 (3.0444) grad_norm: 1.9294 (2.0300) time: 0.6229 [2021-03-27 20:53:02 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 360/1251] eta: 0:09:29 lr: 0.000243 loss: 3.0658 (3.0416) grad_norm: 1.8043 (2.0288) time: 0.6231 [2021-03-27 20:53:08 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 370/1251] eta: 0:09:23 lr: 0.000243 loss: 3.1655 (3.0422) grad_norm: 1.9141 (2.0264) time: 0.6297 [2021-03-27 20:53:15 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 380/1251] eta: 0:09:16 lr: 0.000243 loss: 3.0945 (3.0388) grad_norm: 1.9385 (2.0243) time: 0.6313 [2021-03-27 20:53:21 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 390/1251] eta: 0:09:10 lr: 0.000243 loss: 3.0945 (3.0417) grad_norm: 1.9330 (2.0244) time: 0.6330 [2021-03-27 20:53:27 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 400/1251] eta: 0:09:03 lr: 0.000243 loss: 3.2485 (3.0409) grad_norm: 2.0124 (2.0292) time: 0.6287 [2021-03-27 20:53:33 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 410/1251] eta: 0:08:56 lr: 0.000243 loss: 3.0633 (3.0374) grad_norm: 2.1067 (2.0321) time: 0.6236 [2021-03-27 20:53:40 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 420/1251] eta: 0:08:50 lr: 0.000243 loss: 3.1506 (3.0458) grad_norm: 2.1067 (2.0383) time: 0.6223 [2021-03-27 20:53:46 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 430/1251] eta: 0:08:43 lr: 0.000243 loss: 3.1574 (3.0459) grad_norm: 2.0903 (2.0400) time: 0.6260 [2021-03-27 20:53:52 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 440/1251] eta: 0:08:36 lr: 0.000243 loss: 3.0596 (3.0442) grad_norm: 2.0159 (2.0385) time: 0.6278 [2021-03-27 20:53:58 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 450/1251] eta: 0:08:30 lr: 0.000243 loss: 2.9730 (3.0415) grad_norm: 1.9704 (2.0366) time: 0.6216 [2021-03-27 20:54:05 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 460/1251] eta: 0:08:23 lr: 0.000243 loss: 3.2027 (3.0426) grad_norm: 2.0216 (2.0378) time: 0.6256 [2021-03-27 20:54:11 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 470/1251] eta: 0:08:17 lr: 0.000243 loss: 3.1222 (3.0430) grad_norm: 2.0886 (2.0408) time: 0.6257 [2021-03-27 20:54:17 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 480/1251] eta: 0:08:10 lr: 0.000242 loss: 3.0563 (3.0453) grad_norm: 2.1112 (2.0427) time: 0.6298 [2021-03-27 20:54:24 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 490/1251] eta: 0:08:04 lr: 0.000242 loss: 3.0779 (3.0390) grad_norm: 2.0218 (2.0422) time: 0.6355 [2021-03-27 20:54:30 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 500/1251] eta: 0:07:57 lr: 0.000242 loss: 2.6253 (3.0322) grad_norm: 2.0218 (2.0428) time: 0.6298 [2021-03-27 20:54:36 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 510/1251] eta: 0:07:51 lr: 0.000242 loss: 2.9725 (3.0313) grad_norm: 1.9140 (2.0422) time: 0.6247 [2021-03-27 20:54:42 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 520/1251] eta: 0:07:44 lr: 0.000242 loss: 3.0503 (3.0301) grad_norm: 1.9140 (2.0469) time: 0.6224 [2021-03-27 20:54:49 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 530/1251] eta: 0:07:38 lr: 0.000242 loss: 3.1528 (3.0334) grad_norm: 1.9626 (2.0455) time: 0.6257 [2021-03-27 20:54:55 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 540/1251] eta: 0:07:31 lr: 0.000242 loss: 3.1528 (3.0329) grad_norm: 1.9312 (2.0447) time: 0.6345 [2021-03-27 20:55:01 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 550/1251] eta: 0:07:25 lr: 0.000242 loss: 3.2539 (3.0341) grad_norm: 2.0205 (2.0445) time: 0.6403 [2021-03-27 20:55:08 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 560/1251] eta: 0:07:19 lr: 0.000242 loss: 3.1620 (3.0323) grad_norm: 2.0205 (2.0448) time: 0.6381 [2021-03-27 20:55:14 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 570/1251] eta: 0:07:12 lr: 0.000242 loss: 3.2319 (3.0360) grad_norm: 1.9862 (2.0453) time: 0.6302 [2021-03-27 20:55:21 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 580/1251] eta: 0:07:06 lr: 0.000242 loss: 3.2359 (3.0361) grad_norm: 1.9759 (2.0450) time: 0.6352 [2021-03-27 20:55:27 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 590/1251] eta: 0:07:00 lr: 0.000242 loss: 3.2427 (3.0400) grad_norm: 1.9210 (2.0440) time: 0.6370 [2021-03-27 20:55:33 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 600/1251] eta: 0:06:53 lr: 0.000242 loss: 3.2744 (3.0425) grad_norm: 1.9126 (2.0413) time: 0.6307 [2021-03-27 20:55:39 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 610/1251] eta: 0:06:47 lr: 0.000242 loss: 3.2255 (3.0442) grad_norm: 1.9423 (2.0431) time: 0.6288 [2021-03-27 20:55:46 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 620/1251] eta: 0:06:40 lr: 0.000242 loss: 2.9643 (3.0408) grad_norm: 1.9706 (2.0444) time: 0.6243 [2021-03-27 20:55:52 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 630/1251] eta: 0:06:34 lr: 0.000242 loss: 2.9145 (3.0422) grad_norm: 2.1193 (2.0462) time: 0.6313 [2021-03-27 20:55:58 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 640/1251] eta: 0:06:28 lr: 0.000242 loss: 3.1855 (3.0416) grad_norm: 2.1414 (2.0471) time: 0.6300 [2021-03-27 20:56:05 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 650/1251] eta: 0:06:21 lr: 0.000242 loss: 3.1855 (3.0445) grad_norm: 2.0496 (2.0497) time: 0.6262 [2021-03-27 20:56:11 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 660/1251] eta: 0:06:15 lr: 0.000242 loss: 3.1503 (3.0446) grad_norm: 2.1477 (2.0537) time: 0.6282 [2021-03-27 20:56:17 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 670/1251] eta: 0:06:08 lr: 0.000242 loss: 3.1445 (3.0457) grad_norm: 2.1091 (2.0550) time: 0.6225 [2021-03-27 20:56:23 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 680/1251] eta: 0:06:02 lr: 0.000242 loss: 3.1445 (3.0460) grad_norm: 2.0103 (2.0578) time: 0.6239 [2021-03-27 20:56:30 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 690/1251] eta: 0:05:55 lr: 0.000242 loss: 3.1595 (3.0474) grad_norm: 1.9606 (2.0563) time: 0.6294 [2021-03-27 20:56:36 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 700/1251] eta: 0:05:49 lr: 0.000242 loss: 3.3702 (3.0494) grad_norm: 2.0089 (2.0569) time: 0.6318 [2021-03-27 20:56:42 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 710/1251] eta: 0:05:43 lr: 0.000242 loss: 3.2680 (3.0508) grad_norm: 2.0584 (2.0587) time: 0.6297 [2021-03-27 20:56:48 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 720/1251] eta: 0:05:36 lr: 0.000242 loss: 3.0578 (3.0500) grad_norm: 2.0106 (2.0579) time: 0.6284 [2021-03-27 20:56:55 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 730/1251] eta: 0:05:30 lr: 0.000242 loss: 3.1056 (3.0519) grad_norm: 2.1721 (2.0633) time: 0.6267 [2021-03-27 20:57:01 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 740/1251] eta: 0:05:24 lr: 0.000242 loss: 3.1792 (3.0532) grad_norm: 2.2106 (2.0650) time: 0.6277 [2021-03-27 20:57:07 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 750/1251] eta: 0:05:17 lr: 0.000242 loss: 3.1792 (3.0526) grad_norm: 2.1368 (2.0664) time: 0.6331 [2021-03-27 20:57:14 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 760/1251] eta: 0:05:11 lr: 0.000241 loss: 3.2779 (3.0534) grad_norm: 1.9889 (2.0664) time: 0.6338 [2021-03-27 20:57:20 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 770/1251] eta: 0:05:05 lr: 0.000241 loss: 3.3033 (3.0556) grad_norm: 2.0080 (2.0672) time: 0.6336 [2021-03-27 20:57:26 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 780/1251] eta: 0:04:58 lr: 0.000241 loss: 3.1547 (3.0562) grad_norm: 2.0080 (2.0671) time: 0.6288 [2021-03-27 20:57:33 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 790/1251] eta: 0:04:52 lr: 0.000241 loss: 3.1275 (3.0576) grad_norm: 1.9775 (2.0665) time: 0.6272 [2021-03-27 20:57:39 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 800/1251] eta: 0:04:45 lr: 0.000241 loss: 3.1192 (3.0589) grad_norm: 1.9982 (2.0670) time: 0.6259 [2021-03-27 20:57:45 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 810/1251] eta: 0:04:39 lr: 0.000241 loss: 3.0600 (3.0576) grad_norm: 1.9746 (2.0647) time: 0.6262 [2021-03-27 20:57:51 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 820/1251] eta: 0:04:33 lr: 0.000241 loss: 2.9239 (3.0538) grad_norm: 1.9756 (2.0658) time: 0.6329 [2021-03-27 20:57:58 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 830/1251] eta: 0:04:26 lr: 0.000241 loss: 2.9629 (3.0516) grad_norm: 2.0305 (2.0647) time: 0.6299 [2021-03-27 20:58:04 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 840/1251] eta: 0:04:20 lr: 0.000241 loss: 3.1264 (3.0505) grad_norm: 1.9510 (2.0647) time: 0.6268 [2021-03-27 20:58:10 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 850/1251] eta: 0:04:14 lr: 0.000241 loss: 3.1636 (3.0485) grad_norm: 2.0492 (2.0661) time: 0.6285 [2021-03-27 20:58:17 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 860/1251] eta: 0:04:07 lr: 0.000241 loss: 3.1327 (3.0498) grad_norm: 1.9958 (2.0654) time: 0.6324 [2021-03-27 20:58:23 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 870/1251] eta: 0:04:01 lr: 0.000241 loss: 3.1451 (3.0511) grad_norm: 2.1384 (2.0682) time: 0.6327 [2021-03-27 20:58:29 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 880/1251] eta: 0:03:55 lr: 0.000241 loss: 3.0747 (3.0520) grad_norm: 2.1654 (2.0691) time: 0.6290 [2021-03-27 20:58:36 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 890/1251] eta: 0:03:48 lr: 0.000241 loss: 3.2024 (3.0540) grad_norm: 1.9886 (2.0717) time: 0.6279 [2021-03-27 20:58:42 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 900/1251] eta: 0:03:42 lr: 0.000241 loss: 3.2102 (3.0543) grad_norm: 1.9886 (2.0740) time: 0.6257 [2021-03-27 20:58:48 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 910/1251] eta: 0:03:35 lr: 0.000241 loss: 3.2121 (3.0551) grad_norm: 2.0398 (2.0768) time: 0.6319 [2021-03-27 20:58:54 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 920/1251] eta: 0:03:29 lr: 0.000241 loss: 3.2524 (3.0571) grad_norm: 2.2259 (2.0772) time: 0.6321 [2021-03-27 20:59:01 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 930/1251] eta: 0:03:23 lr: 0.000241 loss: 3.2524 (3.0562) grad_norm: 2.0220 (2.0761) time: 0.6256 [2021-03-27 20:59:07 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 940/1251] eta: 0:03:16 lr: 0.000241 loss: 3.2480 (3.0577) grad_norm: 1.9872 (2.0765) time: 0.6261 [2021-03-27 20:59:13 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 950/1251] eta: 0:03:10 lr: 0.000241 loss: 3.2480 (3.0566) grad_norm: 2.1684 (2.0775) time: 0.6286 [2021-03-27 20:59:20 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 960/1251] eta: 0:03:04 lr: 0.000241 loss: 3.1043 (3.0579) grad_norm: 2.1684 (2.0797) time: 0.6313 [2021-03-27 20:59:26 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 970/1251] eta: 0:02:57 lr: 0.000241 loss: 3.1311 (3.0582) grad_norm: 2.0241 (2.0800) time: 0.6270 [2021-03-27 20:59:32 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 980/1251] eta: 0:02:51 lr: 0.000241 loss: 3.0030 (3.0542) grad_norm: 2.0448 (2.0821) time: 0.6300 [2021-03-27 20:59:38 swin_base_patch4_window7_224] INFO: Epoch: [203] [ 990/1251] eta: 0:02:45 lr: 0.000241 loss: 3.1070 (3.0556) grad_norm: 1.9789 (2.0808) time: 0.6315 [2021-03-27 20:59:45 swin_base_patch4_window7_224] INFO: Epoch: [203] [1000/1251] eta: 0:02:38 lr: 0.000241 loss: 3.1658 (3.0561) grad_norm: 1.8519 (2.0820) time: 0.6284 [2021-03-27 20:59:51 swin_base_patch4_window7_224] INFO: Epoch: [203] [1010/1251] eta: 0:02:32 lr: 0.000241 loss: 3.1827 (3.0566) grad_norm: 1.9649 (2.0813) time: 0.6356 [2021-03-27 20:59:57 swin_base_patch4_window7_224] INFO: Epoch: [203] [1020/1251] eta: 0:02:26 lr: 0.000241 loss: 3.1624 (3.0565) grad_norm: 2.0383 (2.0830) time: 0.6374 [2021-03-27 21:00:04 swin_base_patch4_window7_224] INFO: Epoch: [203] [1030/1251] eta: 0:02:19 lr: 0.000241 loss: 3.0629 (3.0552) grad_norm: 2.0978 (2.0833) time: 0.6322 [2021-03-27 21:00:10 swin_base_patch4_window7_224] INFO: Epoch: [203] [1040/1251] eta: 0:02:13 lr: 0.000241 loss: 2.8209 (3.0521) grad_norm: 2.0367 (2.0850) time: 0.6276 [2021-03-27 21:00:16 swin_base_patch4_window7_224] INFO: Epoch: [203] [1050/1251] eta: 0:02:07 lr: 0.000240 loss: 2.7792 (3.0518) grad_norm: 1.9817 (2.0838) time: 0.6281 [2021-03-27 21:00:23 swin_base_patch4_window7_224] INFO: Epoch: [203] [1060/1251] eta: 0:02:00 lr: 0.000240 loss: 3.2546 (3.0539) grad_norm: 1.9065 (2.0823) time: 0.6250 [2021-03-27 21:00:29 swin_base_patch4_window7_224] INFO: Epoch: [203] [1070/1251] eta: 0:01:54 lr: 0.000240 loss: 3.1733 (3.0531) grad_norm: 1.9329 (2.0819) time: 0.6252 [2021-03-27 21:00:35 swin_base_patch4_window7_224] INFO: Epoch: [203] [1080/1251] eta: 0:01:48 lr: 0.000240 loss: 3.1371 (3.0517) grad_norm: 2.0046 (2.0825) time: 0.6311 [2021-03-27 21:00:41 swin_base_patch4_window7_224] INFO: Epoch: [203] [1090/1251] eta: 0:01:41 lr: 0.000240 loss: 3.0175 (3.0522) grad_norm: 2.0312 (2.0816) time: 0.6304 [2021-03-27 21:00:48 swin_base_patch4_window7_224] INFO: Epoch: [203] [1100/1251] eta: 0:01:35 lr: 0.000240 loss: 3.3045 (3.0537) grad_norm: 1.9719 (2.0819) time: 0.6274 [2021-03-27 21:00:54 swin_base_patch4_window7_224] INFO: Epoch: [203] [1110/1251] eta: 0:01:29 lr: 0.000240 loss: 3.2343 (3.0518) grad_norm: 2.0492 (2.0821) time: 0.6286 [2021-03-27 21:01:00 swin_base_patch4_window7_224] INFO: Epoch: [203] [1120/1251] eta: 0:01:22 lr: 0.000240 loss: 2.9849 (3.0513) grad_norm: 2.0658 (2.0831) time: 0.6303 [2021-03-27 21:01:07 swin_base_patch4_window7_224] INFO: Epoch: [203] [1130/1251] eta: 0:01:16 lr: 0.000240 loss: 3.1363 (3.0522) grad_norm: 2.1591 (2.0842) time: 0.6268 [2021-03-27 21:01:13 swin_base_patch4_window7_224] INFO: Epoch: [203] [1140/1251] eta: 0:01:10 lr: 0.000240 loss: 3.1763 (3.0520) grad_norm: 2.1274 (2.0853) time: 0.6265 [2021-03-27 21:01:19 swin_base_patch4_window7_224] INFO: Epoch: [203] [1150/1251] eta: 0:01:03 lr: 0.000240 loss: 3.0676 (3.0504) grad_norm: 2.0625 (2.0853) time: 0.6291 [2021-03-27 21:01:25 swin_base_patch4_window7_224] INFO: Epoch: [203] [1160/1251] eta: 0:00:57 lr: 0.000240 loss: 2.9652 (3.0498) grad_norm: 2.0358 (2.0844) time: 0.6273 [2021-03-27 21:01:32 swin_base_patch4_window7_224] INFO: Epoch: [203] [1170/1251] eta: 0:00:51 lr: 0.000240 loss: 3.1653 (3.0515) grad_norm: 1.9807 (2.0845) time: 0.6313 [2021-03-27 21:01:38 swin_base_patch4_window7_224] INFO: Epoch: [203] [1180/1251] eta: 0:00:44 lr: 0.000240 loss: 3.3824 (3.0528) grad_norm: 2.0117 (2.0841) time: 0.6322 [2021-03-27 21:01:44 swin_base_patch4_window7_224] INFO: Epoch: [203] [1190/1251] eta: 0:00:38 lr: 0.000240 loss: 3.2427 (3.0540) grad_norm: 1.9731 (2.0840) time: 0.6223 [2021-03-27 21:01:50 swin_base_patch4_window7_224] INFO: Epoch: [203] [1200/1251] eta: 0:00:32 lr: 0.000240 loss: 3.2427 (3.0551) grad_norm: 1.9731 (2.0850) time: 0.6214 [2021-03-27 21:01:57 swin_base_patch4_window7_224] INFO: Epoch: [203] [1210/1251] eta: 0:00:25 lr: 0.000240 loss: 3.3618 (3.0565) grad_norm: 1.9796 (2.0844) time: 0.6261 [2021-03-27 21:02:03 swin_base_patch4_window7_224] INFO: Epoch: [203] [1220/1251] eta: 0:00:19 lr: 0.000240 loss: 3.3312 (3.0566) grad_norm: 1.9796 (2.0837) time: 0.6263 [2021-03-27 21:02:09 swin_base_patch4_window7_224] INFO: Epoch: [203] [1230/1251] eta: 0:00:13 lr: 0.000240 loss: 3.1692 (3.0571) grad_norm: 2.1088 (2.0852) time: 0.6232 [2021-03-27 21:02:15 swin_base_patch4_window7_224] INFO: Epoch: [203] [1240/1251] eta: 0:00:06 lr: 0.000240 loss: 3.1692 (3.0566) grad_norm: 2.1088 (2.0845) time: 0.6205 [2021-03-27 21:02:22 swin_base_patch4_window7_224] INFO: Epoch: [203] [1250/1251] eta: 0:00:00 lr: 0.000240 loss: 3.0858 (3.0553) grad_norm: 1.9722 (2.0850) time: 0.6177 [2021-03-27 21:02:32 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:21 loss: 1.1833 (1.1833) acc1: 75.0000 (75.0000) acc5: 92.1875 (92.1875) [2021-03-27 21:02:34 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8644 (0.9016) acc1: 76.5625 (76.7045) acc5: 95.3125 (95.8807) [2021-03-27 21:02:36 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8112 (0.8513) acc1: 79.6875 (79.0923) acc5: 96.8750 (96.2054) [2021-03-27 21:02:38 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8112 (0.8247) acc1: 81.2500 (79.7379) acc5: 96.8750 (96.2702) [2021-03-27 21:02:41 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7388 (0.7988) acc1: 81.2500 (80.6021) acc5: 96.8750 (96.3034) [2021-03-27 21:02:42 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7677 (0.8069) acc1: 81.2500 (80.7680) acc5: 95.3125 (96.0640) [2021-03-27 21:02:53 swin_base_patch4_window7_224] INFO: * Acc@1 81.228 Acc@5 95.864 loss 0.801 [2021-03-27 21:02:53 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.2% [2021-03-27 21:02:53 swin_base_patch4_window7_224] INFO: Max accuracy: 81.23% [2021-03-27 21:02:58 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 0/1251] eta: 1:32:37 lr: 0.000240 loss: 2.4310 (2.4310) grad_norm: 2.2548 (2.2548) time: 4.4422 [2021-03-27 21:03:04 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 10/1251] eta: 0:20:09 lr: 0.000240 loss: 3.2350 (3.1526) grad_norm: 1.9777 (1.9958) time: 0.9750 [2021-03-27 21:03:10 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 20/1251] eta: 0:16:39 lr: 0.000240 loss: 3.2163 (3.0458) grad_norm: 1.9831 (2.0736) time: 0.6302 [2021-03-27 21:03:17 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 30/1251] eta: 0:15:25 lr: 0.000240 loss: 3.0287 (3.0392) grad_norm: 2.0296 (2.0520) time: 0.6381 [2021-03-27 21:03:23 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 40/1251] eta: 0:14:37 lr: 0.000240 loss: 3.0038 (3.0097) grad_norm: 1.9485 (2.0357) time: 0.6329 [2021-03-27 21:03:29 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 50/1251] eta: 0:14:07 lr: 0.000240 loss: 3.1078 (3.0625) grad_norm: 1.9803 (2.0425) time: 0.6259 [2021-03-27 21:03:36 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 60/1251] eta: 0:13:45 lr: 0.000240 loss: 3.1274 (3.0422) grad_norm: 2.0905 (2.0487) time: 0.6292 [2021-03-27 21:03:42 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 70/1251] eta: 0:13:27 lr: 0.000240 loss: 3.1211 (3.0522) grad_norm: 2.0037 (2.0460) time: 0.6283 [2021-03-27 21:03:48 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 80/1251] eta: 0:13:12 lr: 0.000239 loss: 3.0899 (3.0406) grad_norm: 1.9870 (2.0394) time: 0.6272 [2021-03-27 21:03:54 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 90/1251] eta: 0:12:59 lr: 0.000239 loss: 3.0899 (3.0518) grad_norm: 1.9417 (2.0424) time: 0.6272 [2021-03-27 21:04:01 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 100/1251] eta: 0:12:47 lr: 0.000239 loss: 3.1935 (3.0663) grad_norm: 2.0138 (2.0610) time: 0.6278 [2021-03-27 21:04:07 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 110/1251] eta: 0:12:37 lr: 0.000239 loss: 3.1941 (3.0761) grad_norm: 2.1754 (2.0752) time: 0.6281 [2021-03-27 21:04:13 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 120/1251] eta: 0:12:27 lr: 0.000239 loss: 3.0117 (3.0580) grad_norm: 2.0869 (2.0793) time: 0.6316 [2021-03-27 21:04:20 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 130/1251] eta: 0:12:19 lr: 0.000239 loss: 2.8883 (3.0423) grad_norm: 1.9766 (2.0741) time: 0.6381 [2021-03-27 21:04:26 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 140/1251] eta: 0:12:11 lr: 0.000239 loss: 2.9049 (3.0462) grad_norm: 2.0108 (2.0786) time: 0.6378 [2021-03-27 21:04:32 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 150/1251] eta: 0:12:02 lr: 0.000239 loss: 3.2057 (3.0520) grad_norm: 2.0108 (2.0788) time: 0.6347 [2021-03-27 21:04:39 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 160/1251] eta: 0:11:54 lr: 0.000239 loss: 2.9803 (3.0423) grad_norm: 2.0472 (2.0901) time: 0.6325 [2021-03-27 21:04:45 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 170/1251] eta: 0:11:45 lr: 0.000239 loss: 2.9905 (3.0447) grad_norm: 2.0683 (2.0901) time: 0.6271 [2021-03-27 21:04:51 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 180/1251] eta: 0:11:38 lr: 0.000239 loss: 2.9905 (3.0306) grad_norm: 2.0346 (2.0859) time: 0.6268 [2021-03-27 21:04:57 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 190/1251] eta: 0:11:29 lr: 0.000239 loss: 2.8195 (3.0269) grad_norm: 2.0248 (2.0907) time: 0.6240 [2021-03-27 21:05:04 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 200/1251] eta: 0:11:21 lr: 0.000239 loss: 3.2733 (3.0464) grad_norm: 2.1388 (2.1030) time: 0.6196 [2021-03-27 21:05:10 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 210/1251] eta: 0:11:14 lr: 0.000239 loss: 3.3425 (3.0509) grad_norm: 2.1435 (2.1071) time: 0.6246 [2021-03-27 21:05:16 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 220/1251] eta: 0:11:06 lr: 0.000239 loss: 3.2755 (3.0506) grad_norm: 1.9841 (2.1048) time: 0.6265 [2021-03-27 21:05:22 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 230/1251] eta: 0:10:59 lr: 0.000239 loss: 3.2657 (3.0502) grad_norm: 1.9689 (2.1082) time: 0.6234 [2021-03-27 21:05:29 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 240/1251] eta: 0:10:51 lr: 0.000239 loss: 3.1561 (3.0512) grad_norm: 1.9480 (2.1031) time: 0.6242 [2021-03-27 21:05:35 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 250/1251] eta: 0:10:44 lr: 0.000239 loss: 3.1587 (3.0583) grad_norm: 1.9784 (2.0998) time: 0.6226 [2021-03-27 21:05:41 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 260/1251] eta: 0:10:37 lr: 0.000239 loss: 3.1574 (3.0628) grad_norm: 2.0170 (2.0981) time: 0.6229 [2021-03-27 21:05:47 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 270/1251] eta: 0:10:30 lr: 0.000239 loss: 3.2748 (3.0759) grad_norm: 2.0086 (2.0940) time: 0.6239 [2021-03-27 21:05:54 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 280/1251] eta: 0:10:23 lr: 0.000239 loss: 3.3109 (3.0717) grad_norm: 1.9935 (2.0945) time: 0.6237 [2021-03-27 21:06:00 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 290/1251] eta: 0:10:16 lr: 0.000239 loss: 2.8455 (3.0644) grad_norm: 2.1425 (2.1070) time: 0.6293 [2021-03-27 21:06:06 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 300/1251] eta: 0:10:09 lr: 0.000239 loss: 2.9457 (3.0601) grad_norm: 2.1316 (2.1059) time: 0.6299 [2021-03-27 21:06:12 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 310/1251] eta: 0:10:02 lr: 0.000239 loss: 2.9715 (3.0607) grad_norm: 2.1364 (2.1133) time: 0.6276 [2021-03-27 21:06:19 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 320/1251] eta: 0:09:56 lr: 0.000239 loss: 3.1059 (3.0638) grad_norm: 2.2274 (2.1169) time: 0.6349 [2021-03-27 21:06:25 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 330/1251] eta: 0:09:49 lr: 0.000239 loss: 3.0902 (3.0595) grad_norm: 2.0896 (2.1196) time: 0.6337 [2021-03-27 21:06:31 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 340/1251] eta: 0:09:42 lr: 0.000239 loss: 3.0938 (3.0637) grad_norm: 2.0896 (2.1221) time: 0.6246 [2021-03-27 21:06:38 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 350/1251] eta: 0:09:35 lr: 0.000239 loss: 3.1615 (3.0634) grad_norm: 2.1237 (2.1221) time: 0.6254 [2021-03-27 21:06:44 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 360/1251] eta: 0:09:29 lr: 0.000239 loss: 3.1615 (3.0642) grad_norm: 2.1474 (2.1235) time: 0.6285 [2021-03-27 21:06:50 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 370/1251] eta: 0:09:22 lr: 0.000238 loss: 3.2425 (3.0703) grad_norm: 2.0808 (2.1213) time: 0.6302 [2021-03-27 21:06:57 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 380/1251] eta: 0:09:16 lr: 0.000238 loss: 3.2414 (3.0732) grad_norm: 2.0471 (2.1181) time: 0.6286 [2021-03-27 21:07:03 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 390/1251] eta: 0:09:09 lr: 0.000238 loss: 3.2295 (3.0731) grad_norm: 2.0091 (2.1168) time: 0.6282 [2021-03-27 21:07:09 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 400/1251] eta: 0:09:02 lr: 0.000238 loss: 3.0763 (3.0717) grad_norm: 2.0443 (2.1192) time: 0.6300 [2021-03-27 21:07:15 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 410/1251] eta: 0:08:56 lr: 0.000238 loss: 2.9687 (3.0647) grad_norm: 2.1115 (inf) time: 0.6256 [2021-03-27 21:07:22 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 420/1251] eta: 0:08:49 lr: 0.000238 loss: 2.8494 (3.0623) grad_norm: 2.1115 (inf) time: 0.6272 [2021-03-27 21:07:28 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 430/1251] eta: 0:08:43 lr: 0.000238 loss: 3.0753 (3.0615) grad_norm: 1.9848 (inf) time: 0.6286 [2021-03-27 21:07:34 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 440/1251] eta: 0:08:36 lr: 0.000238 loss: 3.1440 (3.0611) grad_norm: 1.9945 (inf) time: 0.6267 [2021-03-27 21:07:40 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 450/1251] eta: 0:08:29 lr: 0.000238 loss: 2.9446 (3.0544) grad_norm: 1.9897 (inf) time: 0.6261 [2021-03-27 21:07:47 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 460/1251] eta: 0:08:23 lr: 0.000238 loss: 2.9446 (3.0542) grad_norm: 1.9896 (inf) time: 0.6283 [2021-03-27 21:07:53 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 470/1251] eta: 0:08:17 lr: 0.000238 loss: 3.2303 (3.0564) grad_norm: 2.0366 (inf) time: 0.6308 [2021-03-27 21:07:59 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 480/1251] eta: 0:08:10 lr: 0.000238 loss: 3.2679 (3.0624) grad_norm: 1.9603 (inf) time: 0.6275 [2021-03-27 21:08:06 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 490/1251] eta: 0:08:03 lr: 0.000238 loss: 3.2368 (3.0625) grad_norm: 2.0041 (inf) time: 0.6248 [2021-03-27 21:08:12 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 500/1251] eta: 0:07:57 lr: 0.000238 loss: 3.0755 (3.0642) grad_norm: 2.0890 (inf) time: 0.6330 [2021-03-27 21:08:18 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 510/1251] eta: 0:07:51 lr: 0.000238 loss: 3.0330 (3.0610) grad_norm: 2.1294 (inf) time: 0.6323 [2021-03-27 21:08:25 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 520/1251] eta: 0:07:44 lr: 0.000238 loss: 3.1762 (3.0628) grad_norm: 2.1955 (inf) time: 0.6268 [2021-03-27 21:08:31 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 530/1251] eta: 0:07:38 lr: 0.000238 loss: 3.1762 (3.0636) grad_norm: 2.0474 (inf) time: 0.6292 [2021-03-27 21:08:37 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 540/1251] eta: 0:07:31 lr: 0.000238 loss: 3.1608 (3.0645) grad_norm: 2.0474 (inf) time: 0.6251 [2021-03-27 21:08:44 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 550/1251] eta: 0:07:25 lr: 0.000238 loss: 3.1429 (3.0669) grad_norm: 2.0674 (inf) time: 0.6384 [2021-03-27 21:08:50 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 560/1251] eta: 0:07:19 lr: 0.000238 loss: 3.2885 (3.0724) grad_norm: 1.9913 (inf) time: 0.6417 [2021-03-27 21:08:56 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 570/1251] eta: 0:07:12 lr: 0.000238 loss: 3.2029 (3.0726) grad_norm: 2.0470 (inf) time: 0.6333 [2021-03-27 21:09:03 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 580/1251] eta: 0:07:06 lr: 0.000238 loss: 2.9271 (3.0706) grad_norm: 2.0502 (inf) time: 0.6320 [2021-03-27 21:09:09 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 590/1251] eta: 0:07:00 lr: 0.000238 loss: 2.8839 (3.0675) grad_norm: 2.2073 (inf) time: 0.6307 [2021-03-27 21:09:15 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 600/1251] eta: 0:06:53 lr: 0.000238 loss: 3.1839 (3.0730) grad_norm: 2.0620 (inf) time: 0.6289 [2021-03-27 21:09:21 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 610/1251] eta: 0:06:47 lr: 0.000238 loss: 3.1331 (3.0699) grad_norm: 2.0331 (inf) time: 0.6278 [2021-03-27 21:09:28 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 620/1251] eta: 0:06:40 lr: 0.000238 loss: 2.9841 (3.0691) grad_norm: 2.0719 (inf) time: 0.6315 [2021-03-27 21:09:34 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 630/1251] eta: 0:06:34 lr: 0.000238 loss: 3.2658 (3.0694) grad_norm: 2.1135 (inf) time: 0.6245 [2021-03-27 21:09:40 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 640/1251] eta: 0:06:27 lr: 0.000238 loss: 3.2966 (3.0695) grad_norm: 2.0842 (inf) time: 0.6224 [2021-03-27 21:09:46 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 650/1251] eta: 0:06:21 lr: 0.000237 loss: 2.7958 (3.0627) grad_norm: 2.0109 (inf) time: 0.6253 [2021-03-27 21:09:53 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 660/1251] eta: 0:06:14 lr: 0.000237 loss: 2.8854 (3.0643) grad_norm: 2.0894 (inf) time: 0.6234 [2021-03-27 21:09:59 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 670/1251] eta: 0:06:08 lr: 0.000237 loss: 2.9157 (3.0632) grad_norm: 2.1064 (inf) time: 0.6235 [2021-03-27 21:10:05 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 680/1251] eta: 0:06:02 lr: 0.000237 loss: 3.0483 (3.0658) grad_norm: 2.1829 (inf) time: 0.6270 [2021-03-27 21:10:11 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 690/1251] eta: 0:05:55 lr: 0.000237 loss: 3.2211 (3.0678) grad_norm: 2.0364 (inf) time: 0.6283 [2021-03-27 21:10:18 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 700/1251] eta: 0:05:49 lr: 0.000237 loss: 3.3745 (3.0708) grad_norm: 2.0270 (inf) time: 0.6286 [2021-03-27 21:10:24 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 710/1251] eta: 0:05:42 lr: 0.000237 loss: 3.2778 (3.0730) grad_norm: 2.0501 (inf) time: 0.6309 [2021-03-27 21:10:30 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 720/1251] eta: 0:05:36 lr: 0.000237 loss: 3.0792 (3.0699) grad_norm: 2.0710 (inf) time: 0.6250 [2021-03-27 21:10:36 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 730/1251] eta: 0:05:30 lr: 0.000237 loss: 2.8824 (3.0664) grad_norm: 2.0757 (inf) time: 0.6201 [2021-03-27 21:10:43 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 740/1251] eta: 0:05:23 lr: 0.000237 loss: 3.1930 (3.0680) grad_norm: 2.2105 (inf) time: 0.6333 [2021-03-27 21:10:49 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 750/1251] eta: 0:05:17 lr: 0.000237 loss: 3.2150 (3.0696) grad_norm: 2.2349 (inf) time: 0.6442 [2021-03-27 21:10:56 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 760/1251] eta: 0:05:11 lr: 0.000237 loss: 3.2681 (3.0719) grad_norm: 2.1194 (inf) time: 0.6308 [2021-03-27 21:11:02 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 770/1251] eta: 0:05:04 lr: 0.000237 loss: 3.2876 (3.0702) grad_norm: 2.1194 (inf) time: 0.6230 [2021-03-27 21:11:08 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 780/1251] eta: 0:04:58 lr: 0.000237 loss: 3.1448 (3.0700) grad_norm: 2.0731 (inf) time: 0.6289 [2021-03-27 21:11:14 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 790/1251] eta: 0:04:52 lr: 0.000237 loss: 3.1622 (3.0698) grad_norm: 2.0687 (inf) time: 0.6285 [2021-03-27 21:11:21 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 800/1251] eta: 0:04:45 lr: 0.000237 loss: 3.0258 (3.0692) grad_norm: 2.0355 (inf) time: 0.6241 [2021-03-27 21:11:27 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 810/1251] eta: 0:04:39 lr: 0.000237 loss: 3.0258 (3.0673) grad_norm: 2.1280 (inf) time: 0.6302 [2021-03-27 21:11:33 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 820/1251] eta: 0:04:32 lr: 0.000237 loss: 3.2414 (3.0682) grad_norm: 2.1555 (inf) time: 0.6329 [2021-03-27 21:11:39 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 830/1251] eta: 0:04:26 lr: 0.000237 loss: 3.2674 (3.0716) grad_norm: 2.1999 (inf) time: 0.6242 [2021-03-27 21:11:46 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 840/1251] eta: 0:04:20 lr: 0.000237 loss: 3.2468 (3.0709) grad_norm: 2.0931 (inf) time: 0.6201 [2021-03-27 21:11:52 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 850/1251] eta: 0:04:13 lr: 0.000237 loss: 3.1395 (3.0693) grad_norm: 1.9896 (inf) time: 0.6236 [2021-03-27 21:11:58 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 860/1251] eta: 0:04:07 lr: 0.000237 loss: 3.0611 (3.0693) grad_norm: 1.9896 (inf) time: 0.6263 [2021-03-27 21:12:05 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 870/1251] eta: 0:04:01 lr: 0.000237 loss: 3.0611 (3.0679) grad_norm: 2.0184 (inf) time: 0.6317 [2021-03-27 21:12:11 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 880/1251] eta: 0:03:54 lr: 0.000237 loss: 2.8697 (3.0651) grad_norm: 1.9197 (inf) time: 0.6370 [2021-03-27 21:12:17 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 890/1251] eta: 0:03:48 lr: 0.000237 loss: 3.0439 (3.0662) grad_norm: 1.9098 (inf) time: 0.6339 [2021-03-27 21:12:24 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 900/1251] eta: 0:03:42 lr: 0.000237 loss: 3.0137 (3.0638) grad_norm: 1.9551 (inf) time: 0.6314 [2021-03-27 21:12:30 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 910/1251] eta: 0:03:35 lr: 0.000237 loss: 2.9352 (3.0617) grad_norm: 2.0609 (inf) time: 0.6255 [2021-03-27 21:12:36 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 920/1251] eta: 0:03:29 lr: 0.000237 loss: 3.0454 (3.0614) grad_norm: 2.1187 (inf) time: 0.6231 [2021-03-27 21:12:42 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 930/1251] eta: 0:03:23 lr: 0.000237 loss: 3.0930 (3.0613) grad_norm: 2.0844 (inf) time: 0.6208 [2021-03-27 21:12:48 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 940/1251] eta: 0:03:16 lr: 0.000236 loss: 3.1472 (3.0626) grad_norm: 2.0179 (inf) time: 0.6198 [2021-03-27 21:12:55 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 950/1251] eta: 0:03:10 lr: 0.000236 loss: 3.1218 (3.0614) grad_norm: 2.0211 (inf) time: 0.6218 [2021-03-27 21:13:01 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 960/1251] eta: 0:03:03 lr: 0.000236 loss: 2.9927 (3.0607) grad_norm: 2.0201 (inf) time: 0.6228 [2021-03-27 21:13:07 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 970/1251] eta: 0:02:57 lr: 0.000236 loss: 3.1466 (3.0584) grad_norm: 1.9327 (inf) time: 0.6270 [2021-03-27 21:13:13 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 980/1251] eta: 0:02:51 lr: 0.000236 loss: 3.2186 (3.0588) grad_norm: 1.9749 (inf) time: 0.6251 [2021-03-27 21:13:20 swin_base_patch4_window7_224] INFO: Epoch: [204] [ 990/1251] eta: 0:02:44 lr: 0.000236 loss: 3.0679 (3.0583) grad_norm: 1.9749 (inf) time: 0.6233 [2021-03-27 21:13:26 swin_base_patch4_window7_224] INFO: Epoch: [204] [1000/1251] eta: 0:02:38 lr: 0.000236 loss: 3.0351 (3.0585) grad_norm: 1.9550 (inf) time: 0.6253 [2021-03-27 21:13:32 swin_base_patch4_window7_224] INFO: Epoch: [204] [1010/1251] eta: 0:02:32 lr: 0.000236 loss: 3.1293 (3.0608) grad_norm: 2.0866 (inf) time: 0.6270 [2021-03-27 21:13:38 swin_base_patch4_window7_224] INFO: Epoch: [204] [1020/1251] eta: 0:02:25 lr: 0.000236 loss: 3.2297 (3.0610) grad_norm: 2.1294 (inf) time: 0.6255 [2021-03-27 21:13:45 swin_base_patch4_window7_224] INFO: Epoch: [204] [1030/1251] eta: 0:02:19 lr: 0.000236 loss: 3.2292 (3.0625) grad_norm: 2.1879 (inf) time: 0.6219 [2021-03-27 21:13:51 swin_base_patch4_window7_224] INFO: Epoch: [204] [1040/1251] eta: 0:02:13 lr: 0.000236 loss: 3.2464 (3.0636) grad_norm: 2.1636 (inf) time: 0.6229 [2021-03-27 21:13:57 swin_base_patch4_window7_224] INFO: Epoch: [204] [1050/1251] eta: 0:02:06 lr: 0.000236 loss: 3.1391 (3.0631) grad_norm: 2.1636 (inf) time: 0.6253 [2021-03-27 21:14:03 swin_base_patch4_window7_224] INFO: Epoch: [204] [1060/1251] eta: 0:02:00 lr: 0.000236 loss: 3.0900 (3.0628) grad_norm: 2.1107 (inf) time: 0.6242 [2021-03-27 21:14:10 swin_base_patch4_window7_224] INFO: Epoch: [204] [1070/1251] eta: 0:01:54 lr: 0.000236 loss: 3.3233 (3.0639) grad_norm: 1.9856 (inf) time: 0.6257 [2021-03-27 21:14:16 swin_base_patch4_window7_224] INFO: Epoch: [204] [1080/1251] eta: 0:01:47 lr: 0.000236 loss: 3.2413 (3.0647) grad_norm: 1.9208 (inf) time: 0.6322 [2021-03-27 21:14:22 swin_base_patch4_window7_224] INFO: Epoch: [204] [1090/1251] eta: 0:01:41 lr: 0.000236 loss: 3.1333 (3.0649) grad_norm: 1.9972 (inf) time: 0.6284 [2021-03-27 21:14:28 swin_base_patch4_window7_224] INFO: Epoch: [204] [1100/1251] eta: 0:01:35 lr: 0.000236 loss: 3.1448 (3.0640) grad_norm: 2.0090 (inf) time: 0.6207 [2021-03-27 21:14:35 swin_base_patch4_window7_224] INFO: Epoch: [204] [1110/1251] eta: 0:01:29 lr: 0.000236 loss: 3.0802 (3.0643) grad_norm: 2.0665 (inf) time: 0.6256 [2021-03-27 21:14:41 swin_base_patch4_window7_224] INFO: Epoch: [204] [1120/1251] eta: 0:01:22 lr: 0.000236 loss: 3.0528 (3.0632) grad_norm: 2.0761 (inf) time: 0.6267 [2021-03-27 21:14:47 swin_base_patch4_window7_224] INFO: Epoch: [204] [1130/1251] eta: 0:01:16 lr: 0.000236 loss: 2.7719 (3.0629) grad_norm: 2.1494 (inf) time: 0.6231 [2021-03-27 21:14:53 swin_base_patch4_window7_224] INFO: Epoch: [204] [1140/1251] eta: 0:01:10 lr: 0.000236 loss: 3.0733 (3.0627) grad_norm: 2.1494 (inf) time: 0.6231 [2021-03-27 21:15:00 swin_base_patch4_window7_224] INFO: Epoch: [204] [1150/1251] eta: 0:01:03 lr: 0.000236 loss: 3.2829 (3.0637) grad_norm: 1.9878 (inf) time: 0.6268 [2021-03-27 21:15:06 swin_base_patch4_window7_224] INFO: Epoch: [204] [1160/1251] eta: 0:00:57 lr: 0.000236 loss: 3.3462 (3.0631) grad_norm: 1.9949 (inf) time: 0.6255 [2021-03-27 21:15:12 swin_base_patch4_window7_224] INFO: Epoch: [204] [1170/1251] eta: 0:00:51 lr: 0.000236 loss: 3.1128 (3.0626) grad_norm: 2.0719 (inf) time: 0.6264 [2021-03-27 21:15:19 swin_base_patch4_window7_224] INFO: Epoch: [204] [1180/1251] eta: 0:00:44 lr: 0.000236 loss: 3.1489 (3.0637) grad_norm: 2.0592 (inf) time: 0.6301 [2021-03-27 21:15:25 swin_base_patch4_window7_224] INFO: Epoch: [204] [1190/1251] eta: 0:00:38 lr: 0.000236 loss: 3.1574 (3.0630) grad_norm: 2.0561 (inf) time: 0.6240 [2021-03-27 21:15:31 swin_base_patch4_window7_224] INFO: Epoch: [204] [1200/1251] eta: 0:00:32 lr: 0.000236 loss: 3.1995 (3.0650) grad_norm: 2.1311 (inf) time: 0.6216 [2021-03-27 21:15:37 swin_base_patch4_window7_224] INFO: Epoch: [204] [1210/1251] eta: 0:00:25 lr: 0.000236 loss: 3.3241 (3.0658) grad_norm: 2.0671 (inf) time: 0.6270 [2021-03-27 21:15:44 swin_base_patch4_window7_224] INFO: Epoch: [204] [1220/1251] eta: 0:00:19 lr: 0.000236 loss: 3.3182 (3.0667) grad_norm: 2.0091 (inf) time: 0.6274 [2021-03-27 21:15:50 swin_base_patch4_window7_224] INFO: Epoch: [204] [1230/1251] eta: 0:00:13 lr: 0.000235 loss: 3.2723 (3.0662) grad_norm: 2.0395 (inf) time: 0.6290 [2021-03-27 21:15:56 swin_base_patch4_window7_224] INFO: Epoch: [204] [1240/1251] eta: 0:00:06 lr: 0.000235 loss: 2.8324 (3.0647) grad_norm: 2.0583 (inf) time: 0.6286 [2021-03-27 21:16:02 swin_base_patch4_window7_224] INFO: Epoch: [204] [1250/1251] eta: 0:00:00 lr: 0.000235 loss: 3.0229 (3.0654) grad_norm: 2.0900 (inf) time: 0.6203 [2021-03-27 21:16:13 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:30 loss: 0.6623 (0.6623) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-27 21:16:16 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:21 loss: 0.8549 (0.8679) acc1: 79.6875 (79.8295) acc5: 96.8750 (95.8807) [2021-03-27 21:16:18 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.7641 (0.8029) acc1: 79.6875 (80.9524) acc5: 96.8750 (96.6518) [2021-03-27 21:16:21 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7403 (0.8181) acc1: 81.2500 (80.9980) acc5: 96.8750 (96.3206) [2021-03-27 21:16:22 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7652 (0.8169) acc1: 81.2500 (81.0213) acc5: 95.3125 (96.1128) [2021-03-27 21:16:23 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7980 (0.8255) acc1: 81.2500 (80.7680) acc5: 95.3125 (95.9040) [2021-03-27 21:16:34 swin_base_patch4_window7_224] INFO: * Acc@1 81.278 Acc@5 95.828 loss 0.810 [2021-03-27 21:16:34 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.3% [2021-03-27 21:16:34 swin_base_patch4_window7_224] INFO: Max accuracy: 81.28% [2021-03-27 21:16:38 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 0/1251] eta: 1:28:56 lr: 0.000235 loss: 2.9879 (2.9879) grad_norm: 2.1587 (2.1587) time: 4.2661 [2021-03-27 21:16:45 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 10/1251] eta: 0:20:07 lr: 0.000235 loss: 3.2119 (3.1970) grad_norm: 2.0272 (2.0115) time: 0.9733 [2021-03-27 21:16:51 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 20/1251] eta: 0:16:33 lr: 0.000235 loss: 3.1399 (3.0737) grad_norm: 1.9484 (2.0250) time: 0.6341 [2021-03-27 21:16:57 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 30/1251] eta: 0:15:14 lr: 0.000235 loss: 3.1554 (3.1069) grad_norm: 1.9874 (2.0401) time: 0.6256 [2021-03-27 21:17:04 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 40/1251] eta: 0:14:32 lr: 0.000235 loss: 3.2614 (3.1112) grad_norm: 2.1252 (2.1020) time: 0.6291 [2021-03-27 21:17:10 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 50/1251] eta: 0:14:04 lr: 0.000235 loss: 3.1109 (3.0764) grad_norm: 1.9253 (2.0675) time: 0.6321 [2021-03-27 21:17:16 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 60/1251] eta: 0:13:46 lr: 0.000235 loss: 3.0164 (3.0669) grad_norm: 1.8940 (2.0450) time: 0.6399 [2021-03-27 21:17:23 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 70/1251] eta: 0:13:27 lr: 0.000235 loss: 3.2466 (3.0868) grad_norm: 1.9515 (2.0334) time: 0.6336 [2021-03-27 21:17:29 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 80/1251] eta: 0:13:12 lr: 0.000235 loss: 3.2077 (3.1018) grad_norm: 1.9782 (2.0369) time: 0.6228 [2021-03-27 21:17:35 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 90/1251] eta: 0:12:59 lr: 0.000235 loss: 3.1344 (3.1140) grad_norm: 1.9833 (2.0357) time: 0.6282 [2021-03-27 21:17:41 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 100/1251] eta: 0:12:47 lr: 0.000235 loss: 3.1344 (3.1096) grad_norm: 2.1017 (2.0635) time: 0.6282 [2021-03-27 21:17:48 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 110/1251] eta: 0:12:36 lr: 0.000235 loss: 3.0920 (3.0974) grad_norm: 2.1921 (2.0737) time: 0.6268 [2021-03-27 21:17:54 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 120/1251] eta: 0:12:26 lr: 0.000235 loss: 3.2438 (3.0966) grad_norm: 2.0897 (2.0795) time: 0.6243 [2021-03-27 21:18:00 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 130/1251] eta: 0:12:16 lr: 0.000235 loss: 3.1992 (3.0833) grad_norm: 2.0522 (2.0809) time: 0.6234 [2021-03-27 21:18:06 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 140/1251] eta: 0:12:08 lr: 0.000235 loss: 2.9026 (3.0771) grad_norm: 2.0366 (2.0813) time: 0.6299 [2021-03-27 21:18:13 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 150/1251] eta: 0:11:59 lr: 0.000235 loss: 3.0767 (3.0622) grad_norm: 2.0339 (2.0751) time: 0.6270 [2021-03-27 21:18:19 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 160/1251] eta: 0:11:50 lr: 0.000235 loss: 3.0702 (3.0662) grad_norm: 2.0607 (2.0862) time: 0.6240 [2021-03-27 21:18:25 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 170/1251] eta: 0:11:43 lr: 0.000235 loss: 3.0702 (3.0619) grad_norm: 2.1299 (2.0913) time: 0.6288 [2021-03-27 21:18:32 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 180/1251] eta: 0:11:35 lr: 0.000235 loss: 3.1548 (3.0583) grad_norm: 2.1258 (2.1037) time: 0.6318 [2021-03-27 21:18:38 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 190/1251] eta: 0:11:27 lr: 0.000235 loss: 3.1822 (3.0593) grad_norm: 2.0525 (2.1001) time: 0.6319 [2021-03-27 21:18:44 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 200/1251] eta: 0:11:20 lr: 0.000235 loss: 3.1666 (3.0601) grad_norm: 2.0082 (2.0977) time: 0.6336 [2021-03-27 21:18:51 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 210/1251] eta: 0:11:13 lr: 0.000235 loss: 3.0832 (3.0526) grad_norm: 2.1327 (2.1464) time: 0.6356 [2021-03-27 21:18:57 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 220/1251] eta: 0:11:06 lr: 0.000235 loss: 2.8426 (3.0456) grad_norm: 2.1339 (2.1381) time: 0.6276 [2021-03-27 21:19:03 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 230/1251] eta: 0:10:59 lr: 0.000235 loss: 2.8264 (3.0395) grad_norm: 1.9056 (2.1346) time: 0.6275 [2021-03-27 21:19:09 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 240/1251] eta: 0:10:51 lr: 0.000235 loss: 3.0304 (3.0375) grad_norm: 1.9476 (2.1336) time: 0.6304 [2021-03-27 21:19:16 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 250/1251] eta: 0:10:44 lr: 0.000235 loss: 3.0100 (3.0240) grad_norm: 2.0085 (2.1286) time: 0.6299 [2021-03-27 21:19:22 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 260/1251] eta: 0:10:37 lr: 0.000235 loss: 2.8896 (3.0201) grad_norm: 1.8784 (2.1202) time: 0.6322 [2021-03-27 21:19:28 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 270/1251] eta: 0:10:31 lr: 0.000234 loss: 3.0878 (3.0225) grad_norm: 1.9151 (2.1192) time: 0.6336 [2021-03-27 21:19:35 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 280/1251] eta: 0:10:24 lr: 0.000234 loss: 3.1531 (3.0218) grad_norm: 1.9727 (2.1207) time: 0.6307 [2021-03-27 21:19:41 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 290/1251] eta: 0:10:17 lr: 0.000234 loss: 3.1967 (3.0295) grad_norm: 1.9742 (2.1150) time: 0.6252 [2021-03-27 21:19:47 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 300/1251] eta: 0:10:10 lr: 0.000234 loss: 3.1988 (3.0286) grad_norm: 2.0015 (2.1144) time: 0.6262 [2021-03-27 21:19:54 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 310/1251] eta: 0:10:03 lr: 0.000234 loss: 3.1928 (3.0324) grad_norm: 2.0298 (2.1121) time: 0.6286 [2021-03-27 21:20:00 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 320/1251] eta: 0:09:56 lr: 0.000234 loss: 3.1170 (3.0362) grad_norm: 2.0823 (2.1342) time: 0.6332 [2021-03-27 21:20:06 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 330/1251] eta: 0:09:50 lr: 0.000234 loss: 3.0903 (3.0370) grad_norm: 2.0435 (2.1280) time: 0.6317 [2021-03-27 21:20:12 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 340/1251] eta: 0:09:43 lr: 0.000234 loss: 2.8681 (3.0296) grad_norm: 1.8847 (2.1235) time: 0.6262 [2021-03-27 21:20:19 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 350/1251] eta: 0:09:36 lr: 0.000234 loss: 2.8306 (3.0281) grad_norm: 1.9360 (2.1196) time: 0.6271 [2021-03-27 21:20:25 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 360/1251] eta: 0:09:29 lr: 0.000234 loss: 2.8660 (3.0263) grad_norm: 2.0024 (2.1220) time: 0.6244 [2021-03-27 21:20:31 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 370/1251] eta: 0:09:22 lr: 0.000234 loss: 3.0761 (3.0290) grad_norm: 2.1720 (2.1250) time: 0.6214 [2021-03-27 21:20:37 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 380/1251] eta: 0:09:16 lr: 0.000234 loss: 3.0355 (3.0226) grad_norm: 2.1720 (2.1250) time: 0.6257 [2021-03-27 21:20:44 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 390/1251] eta: 0:09:09 lr: 0.000234 loss: 2.9707 (3.0237) grad_norm: 2.1393 (2.1277) time: 0.6297 [2021-03-27 21:20:50 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 400/1251] eta: 0:09:03 lr: 0.000234 loss: 3.1783 (3.0232) grad_norm: 2.1236 (2.1268) time: 0.6322 [2021-03-27 21:20:56 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 410/1251] eta: 0:08:56 lr: 0.000234 loss: 3.1831 (3.0257) grad_norm: 2.1707 (2.1280) time: 0.6279 [2021-03-27 21:21:03 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 420/1251] eta: 0:08:50 lr: 0.000234 loss: 3.1710 (3.0281) grad_norm: 2.1127 (2.1278) time: 0.6259 [2021-03-27 21:21:09 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 430/1251] eta: 0:08:43 lr: 0.000234 loss: 3.2108 (3.0362) grad_norm: 2.0914 (2.1269) time: 0.6250 [2021-03-27 21:21:15 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 440/1251] eta: 0:08:36 lr: 0.000234 loss: 3.0079 (3.0288) grad_norm: 2.0650 (2.1238) time: 0.6230 [2021-03-27 21:21:21 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 450/1251] eta: 0:08:30 lr: 0.000234 loss: 3.1791 (3.0344) grad_norm: 2.0382 (2.1237) time: 0.6288 [2021-03-27 21:21:28 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 460/1251] eta: 0:08:23 lr: 0.000234 loss: 3.2355 (3.0314) grad_norm: 1.9166 (2.1218) time: 0.6300 [2021-03-27 21:21:34 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 470/1251] eta: 0:08:17 lr: 0.000234 loss: 2.9221 (3.0298) grad_norm: 2.0062 (2.1215) time: 0.6253 [2021-03-27 21:21:40 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 480/1251] eta: 0:08:10 lr: 0.000234 loss: 3.0498 (3.0335) grad_norm: 2.0578 (2.1236) time: 0.6254 [2021-03-27 21:21:46 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 490/1251] eta: 0:08:04 lr: 0.000234 loss: 3.0779 (3.0318) grad_norm: 2.0295 (2.1215) time: 0.6259 [2021-03-27 21:21:53 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 500/1251] eta: 0:07:57 lr: 0.000234 loss: 3.0388 (3.0310) grad_norm: 2.0190 (2.1205) time: 0.6326 [2021-03-27 21:21:59 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 510/1251] eta: 0:07:51 lr: 0.000234 loss: 3.1853 (3.0340) grad_norm: 2.0190 (2.1187) time: 0.6349 [2021-03-27 21:22:05 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 520/1251] eta: 0:07:44 lr: 0.000234 loss: 3.0559 (3.0316) grad_norm: 1.9688 (2.1162) time: 0.6251 [2021-03-27 21:22:12 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 530/1251] eta: 0:07:38 lr: 0.000234 loss: 3.0230 (3.0309) grad_norm: 2.0186 (2.1163) time: 0.6265 [2021-03-27 21:22:18 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 540/1251] eta: 0:07:31 lr: 0.000234 loss: 3.0230 (3.0290) grad_norm: 2.0593 (2.1154) time: 0.6290 [2021-03-27 21:22:24 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 550/1251] eta: 0:07:25 lr: 0.000233 loss: 3.0344 (3.0300) grad_norm: 2.0593 (2.1159) time: 0.6416 [2021-03-27 21:22:31 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 560/1251] eta: 0:07:19 lr: 0.000233 loss: 3.1629 (3.0333) grad_norm: 2.1148 (2.1238) time: 0.6484 [2021-03-27 21:22:37 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 570/1251] eta: 0:07:12 lr: 0.000233 loss: 3.0514 (3.0312) grad_norm: 2.1040 (2.1225) time: 0.6339 [2021-03-27 21:22:43 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 580/1251] eta: 0:07:06 lr: 0.000233 loss: 2.9814 (3.0292) grad_norm: 2.0399 (2.1220) time: 0.6260 [2021-03-27 21:22:50 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 590/1251] eta: 0:07:00 lr: 0.000233 loss: 3.0714 (3.0269) grad_norm: 2.0879 (2.1221) time: 0.6289 [2021-03-27 21:22:56 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 600/1251] eta: 0:06:53 lr: 0.000233 loss: 3.0860 (3.0295) grad_norm: 2.0175 (2.1435) time: 0.6279 [2021-03-27 21:23:02 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 610/1251] eta: 0:06:47 lr: 0.000233 loss: 3.0635 (3.0285) grad_norm: 1.9177 (2.1449) time: 0.6234 [2021-03-27 21:23:09 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 620/1251] eta: 0:06:40 lr: 0.000233 loss: 3.1839 (3.0323) grad_norm: 1.8620 (2.1397) time: 0.6281 [2021-03-27 21:23:15 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 630/1251] eta: 0:06:34 lr: 0.000233 loss: 3.0978 (3.0288) grad_norm: 1.7971 (2.1367) time: 0.6297 [2021-03-27 21:23:21 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 640/1251] eta: 0:06:27 lr: 0.000233 loss: 2.8813 (3.0298) grad_norm: 1.9077 (2.1351) time: 0.6225 [2021-03-27 21:23:27 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 650/1251] eta: 0:06:21 lr: 0.000233 loss: 2.8182 (3.0232) grad_norm: 1.9293 (2.1389) time: 0.6299 [2021-03-27 21:23:34 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 660/1251] eta: 0:06:15 lr: 0.000233 loss: 2.7791 (3.0230) grad_norm: 2.0199 (2.1377) time: 0.6354 [2021-03-27 21:23:40 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 670/1251] eta: 0:06:08 lr: 0.000233 loss: 2.9720 (3.0217) grad_norm: 2.0634 (2.1377) time: 0.6253 [2021-03-27 21:23:46 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 680/1251] eta: 0:06:02 lr: 0.000233 loss: 3.1837 (3.0236) grad_norm: 1.9561 (2.1383) time: 0.6299 [2021-03-27 21:23:53 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 690/1251] eta: 0:05:55 lr: 0.000233 loss: 3.0093 (3.0206) grad_norm: 1.8750 (2.1358) time: 0.6306 [2021-03-27 21:23:59 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 700/1251] eta: 0:05:49 lr: 0.000233 loss: 2.9810 (3.0202) grad_norm: 2.0024 (2.1352) time: 0.6210 [2021-03-27 21:24:05 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 710/1251] eta: 0:05:43 lr: 0.000233 loss: 2.9810 (3.0196) grad_norm: 1.9909 (2.1324) time: 0.6223 [2021-03-27 21:24:11 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 720/1251] eta: 0:05:36 lr: 0.000233 loss: 2.9685 (3.0193) grad_norm: 1.9343 (2.1315) time: 0.6305 [2021-03-27 21:24:18 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 730/1251] eta: 0:05:30 lr: 0.000233 loss: 3.0966 (3.0216) grad_norm: 1.9865 (2.1308) time: 0.6353 [2021-03-27 21:24:24 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 740/1251] eta: 0:05:24 lr: 0.000233 loss: 3.1794 (3.0222) grad_norm: 2.0394 (2.1307) time: 0.6412 [2021-03-27 21:24:31 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 750/1251] eta: 0:05:17 lr: 0.000233 loss: 3.1088 (3.0220) grad_norm: 2.0980 (2.1311) time: 0.6474 [2021-03-27 21:24:37 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 760/1251] eta: 0:05:11 lr: 0.000233 loss: 3.1210 (3.0230) grad_norm: 2.0900 (2.1316) time: 0.6378 [2021-03-27 21:24:43 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 770/1251] eta: 0:05:05 lr: 0.000233 loss: 3.1174 (3.0220) grad_norm: 2.1765 (2.1348) time: 0.6299 [2021-03-27 21:24:50 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 780/1251] eta: 0:04:58 lr: 0.000233 loss: 3.0452 (3.0233) grad_norm: 2.0969 (2.1327) time: 0.6322 [2021-03-27 21:24:56 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 790/1251] eta: 0:04:52 lr: 0.000233 loss: 3.0495 (3.0240) grad_norm: 2.0357 (2.1330) time: 0.6295 [2021-03-27 21:25:02 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 800/1251] eta: 0:04:45 lr: 0.000233 loss: 2.9857 (3.0217) grad_norm: 2.1462 (2.1370) time: 0.6240 [2021-03-27 21:25:08 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 810/1251] eta: 0:04:39 lr: 0.000233 loss: 3.0709 (3.0228) grad_norm: 2.1496 (2.1377) time: 0.6273 [2021-03-27 21:25:15 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 820/1251] eta: 0:04:33 lr: 0.000233 loss: 3.2992 (3.0249) grad_norm: 2.0601 (2.1365) time: 0.6277 [2021-03-27 21:25:21 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 830/1251] eta: 0:04:26 lr: 0.000233 loss: 3.2262 (3.0247) grad_norm: 2.0042 (2.1373) time: 0.6252 [2021-03-27 21:25:27 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 840/1251] eta: 0:04:20 lr: 0.000232 loss: 3.1674 (3.0261) grad_norm: 2.0042 (2.1383) time: 0.6316 [2021-03-27 21:25:34 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 850/1251] eta: 0:04:14 lr: 0.000232 loss: 3.2487 (3.0261) grad_norm: 1.9594 (2.1379) time: 0.6320 [2021-03-27 21:25:40 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 860/1251] eta: 0:04:07 lr: 0.000232 loss: 3.0924 (3.0253) grad_norm: 1.9305 (2.1360) time: 0.6255 [2021-03-27 21:25:46 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 870/1251] eta: 0:04:01 lr: 0.000232 loss: 2.8238 (3.0242) grad_norm: 2.0109 (2.1373) time: 0.6237 [2021-03-27 21:25:52 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 880/1251] eta: 0:03:55 lr: 0.000232 loss: 2.7687 (3.0229) grad_norm: 2.0937 (2.1372) time: 0.6232 [2021-03-27 21:25:59 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 890/1251] eta: 0:03:48 lr: 0.000232 loss: 3.0127 (3.0222) grad_norm: 2.1151 (2.1367) time: 0.6294 [2021-03-27 21:26:05 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 900/1251] eta: 0:03:42 lr: 0.000232 loss: 3.0127 (3.0207) grad_norm: 2.1610 (2.1376) time: 0.6338 [2021-03-27 21:26:11 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 910/1251] eta: 0:03:35 lr: 0.000232 loss: 3.0772 (3.0205) grad_norm: 2.1190 (2.1366) time: 0.6269 [2021-03-27 21:26:18 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 920/1251] eta: 0:03:29 lr: 0.000232 loss: 3.1256 (3.0216) grad_norm: 2.0056 (2.1358) time: 0.6289 [2021-03-27 21:26:24 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 930/1251] eta: 0:03:23 lr: 0.000232 loss: 3.1256 (3.0207) grad_norm: 1.9029 (2.1330) time: 0.6310 [2021-03-27 21:26:30 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 940/1251] eta: 0:03:16 lr: 0.000232 loss: 3.1599 (3.0211) grad_norm: 1.8696 (2.1309) time: 0.6346 [2021-03-27 21:26:37 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 950/1251] eta: 0:03:10 lr: 0.000232 loss: 3.0865 (3.0214) grad_norm: 1.8520 (2.1282) time: 0.6366 [2021-03-27 21:26:43 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 960/1251] eta: 0:03:04 lr: 0.000232 loss: 3.0865 (3.0223) grad_norm: 1.8924 (2.1283) time: 0.6275 [2021-03-27 21:26:49 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 970/1251] eta: 0:02:57 lr: 0.000232 loss: 3.1779 (3.0243) grad_norm: 1.9910 (2.1269) time: 0.6241 [2021-03-27 21:26:55 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 980/1251] eta: 0:02:51 lr: 0.000232 loss: 3.2101 (3.0245) grad_norm: 2.0330 (2.1267) time: 0.6275 [2021-03-27 21:27:02 swin_base_patch4_window7_224] INFO: Epoch: [205] [ 990/1251] eta: 0:02:45 lr: 0.000232 loss: 3.1201 (3.0233) grad_norm: 1.9714 (2.1256) time: 0.6271 [2021-03-27 21:27:08 swin_base_patch4_window7_224] INFO: Epoch: [205] [1000/1251] eta: 0:02:38 lr: 0.000232 loss: 2.8476 (3.0225) grad_norm: 1.9644 (2.1242) time: 0.6267 [2021-03-27 21:27:14 swin_base_patch4_window7_224] INFO: Epoch: [205] [1010/1251] eta: 0:02:32 lr: 0.000232 loss: 2.8863 (3.0217) grad_norm: 1.9903 (2.1244) time: 0.6386 [2021-03-27 21:27:21 swin_base_patch4_window7_224] INFO: Epoch: [205] [1020/1251] eta: 0:02:26 lr: 0.000232 loss: 2.9655 (3.0228) grad_norm: 2.0039 (2.1237) time: 0.6442 [2021-03-27 21:27:27 swin_base_patch4_window7_224] INFO: Epoch: [205] [1030/1251] eta: 0:02:19 lr: 0.000232 loss: 2.9655 (3.0221) grad_norm: 2.0807 (2.1242) time: 0.6309 [2021-03-27 21:27:33 swin_base_patch4_window7_224] INFO: Epoch: [205] [1040/1251] eta: 0:02:13 lr: 0.000232 loss: 2.9408 (3.0224) grad_norm: 2.0590 (2.1236) time: 0.6242 [2021-03-27 21:27:39 swin_base_patch4_window7_224] INFO: Epoch: [205] [1050/1251] eta: 0:02:07 lr: 0.000232 loss: 3.1176 (3.0240) grad_norm: 2.0611 (2.1240) time: 0.6251 [2021-03-27 21:27:46 swin_base_patch4_window7_224] INFO: Epoch: [205] [1060/1251] eta: 0:02:00 lr: 0.000232 loss: 3.2672 (3.0267) grad_norm: 2.0611 (2.1254) time: 0.6230 [2021-03-27 21:27:52 swin_base_patch4_window7_224] INFO: Epoch: [205] [1070/1251] eta: 0:01:54 lr: 0.000232 loss: 3.2662 (3.0284) grad_norm: 1.9832 (2.1249) time: 0.6229 [2021-03-27 21:27:58 swin_base_patch4_window7_224] INFO: Epoch: [205] [1080/1251] eta: 0:01:48 lr: 0.000232 loss: 3.1441 (3.0267) grad_norm: 2.0028 (2.1240) time: 0.6261 [2021-03-27 21:28:05 swin_base_patch4_window7_224] INFO: Epoch: [205] [1090/1251] eta: 0:01:41 lr: 0.000232 loss: 3.1479 (3.0277) grad_norm: 1.9715 (2.1227) time: 0.6298 [2021-03-27 21:28:11 swin_base_patch4_window7_224] INFO: Epoch: [205] [1100/1251] eta: 0:01:35 lr: 0.000232 loss: 2.9179 (3.0248) grad_norm: 1.9971 (2.1216) time: 0.6265 [2021-03-27 21:28:17 swin_base_patch4_window7_224] INFO: Epoch: [205] [1110/1251] eta: 0:01:29 lr: 0.000232 loss: 2.8382 (3.0244) grad_norm: 2.0458 (2.1214) time: 0.6264 [2021-03-27 21:28:23 swin_base_patch4_window7_224] INFO: Epoch: [205] [1120/1251] eta: 0:01:22 lr: 0.000232 loss: 3.2373 (3.0258) grad_norm: 2.0458 (2.1205) time: 0.6251 [2021-03-27 21:28:30 swin_base_patch4_window7_224] INFO: Epoch: [205] [1130/1251] eta: 0:01:16 lr: 0.000231 loss: 3.2373 (3.0252) grad_norm: 2.0536 (2.1202) time: 0.6230 [2021-03-27 21:28:36 swin_base_patch4_window7_224] INFO: Epoch: [205] [1140/1251] eta: 0:01:10 lr: 0.000231 loss: 3.1061 (3.0246) grad_norm: 2.0127 (2.1216) time: 0.6315 [2021-03-27 21:28:42 swin_base_patch4_window7_224] INFO: Epoch: [205] [1150/1251] eta: 0:01:03 lr: 0.000231 loss: 3.0687 (3.0239) grad_norm: 1.9551 (2.1207) time: 0.6301 [2021-03-27 21:28:48 swin_base_patch4_window7_224] INFO: Epoch: [205] [1160/1251] eta: 0:00:57 lr: 0.000231 loss: 3.1149 (3.0245) grad_norm: 1.9935 (2.1202) time: 0.6297 [2021-03-27 21:28:55 swin_base_patch4_window7_224] INFO: Epoch: [205] [1170/1251] eta: 0:00:51 lr: 0.000231 loss: 3.1733 (3.0246) grad_norm: 2.0079 (2.1207) time: 0.6291 [2021-03-27 21:29:01 swin_base_patch4_window7_224] INFO: Epoch: [205] [1180/1251] eta: 0:00:44 lr: 0.000231 loss: 3.0594 (3.0246) grad_norm: 2.1096 (2.1212) time: 0.6237 [2021-03-27 21:29:07 swin_base_patch4_window7_224] INFO: Epoch: [205] [1190/1251] eta: 0:00:38 lr: 0.000231 loss: 2.9957 (3.0236) grad_norm: 2.1356 (2.1221) time: 0.6279 [2021-03-27 21:29:14 swin_base_patch4_window7_224] INFO: Epoch: [205] [1200/1251] eta: 0:00:32 lr: 0.000231 loss: 2.9515 (3.0232) grad_norm: 2.0619 (2.1223) time: 0.6306 [2021-03-27 21:29:20 swin_base_patch4_window7_224] INFO: Epoch: [205] [1210/1251] eta: 0:00:25 lr: 0.000231 loss: 3.1806 (3.0239) grad_norm: 1.8995 (2.1218) time: 0.6296 [2021-03-27 21:29:26 swin_base_patch4_window7_224] INFO: Epoch: [205] [1220/1251] eta: 0:00:19 lr: 0.000231 loss: 3.2117 (3.0259) grad_norm: 1.9501 (2.1209) time: 0.6311 [2021-03-27 21:29:32 swin_base_patch4_window7_224] INFO: Epoch: [205] [1230/1251] eta: 0:00:13 lr: 0.000231 loss: 3.1780 (3.0264) grad_norm: 1.9447 (2.1209) time: 0.6269 [2021-03-27 21:29:39 swin_base_patch4_window7_224] INFO: Epoch: [205] [1240/1251] eta: 0:00:06 lr: 0.000231 loss: 3.0862 (3.0276) grad_norm: 2.0350 (2.1228) time: 0.6206 [2021-03-27 21:29:45 swin_base_patch4_window7_224] INFO: Epoch: [205] [1250/1251] eta: 0:00:00 lr: 0.000231 loss: 2.7998 (3.0241) grad_norm: 2.0558 (2.1230) time: 0.6222 [2021-03-27 21:30:56 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:17 loss: 0.6240 (0.6240) acc1: 84.3750 (84.3750) acc5: 95.3125 (95.3125) [2021-03-27 21:30:57 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.8173 (0.8058) acc1: 82.8125 (81.3920) acc5: 95.3125 (95.0284) [2021-03-27 21:30:59 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:06 loss: 0.8392 (0.8441) acc1: 79.6875 (81.1012) acc5: 95.3125 (95.3869) [2021-03-27 21:31:00 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8717 (0.8458) acc1: 79.6875 (80.4435) acc5: 95.3125 (95.3629) [2021-03-27 21:31:02 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7725 (0.8232) acc1: 79.6875 (80.3735) acc5: 95.3125 (95.6555) [2021-03-27 21:31:03 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7390 (0.8094) acc1: 81.2500 (80.8320) acc5: 96.8750 (95.8720) [2021-03-27 21:31:14 swin_base_patch4_window7_224] INFO: * Acc@1 81.480 Acc@5 95.910 loss 0.795 [2021-03-27 21:31:14 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.5% [2021-03-27 21:31:14 swin_base_patch4_window7_224] INFO: Max accuracy: 81.48% [2021-03-27 21:31:19 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 0/1251] eta: 1:28:08 lr: 0.000231 loss: 3.0833 (3.0833) grad_norm: 1.9096 (1.9096) time: 4.2271 [2021-03-27 21:31:25 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 10/1251] eta: 0:20:05 lr: 0.000231 loss: 3.0833 (3.0140) grad_norm: 2.0179 (2.2148) time: 0.9712 [2021-03-27 21:31:31 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 20/1251] eta: 0:16:31 lr: 0.000231 loss: 2.9945 (2.9335) grad_norm: 2.1487 (2.4589) time: 0.6343 [2021-03-27 21:31:38 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 30/1251] eta: 0:15:16 lr: 0.000231 loss: 2.9865 (2.9634) grad_norm: 2.1366 (2.3545) time: 0.6295 [2021-03-27 21:31:44 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 40/1251] eta: 0:14:29 lr: 0.000231 loss: 3.0492 (2.9618) grad_norm: 1.9944 (2.2630) time: 0.6263 [2021-03-27 21:31:50 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 50/1251] eta: 0:14:00 lr: 0.000231 loss: 3.0492 (2.9354) grad_norm: 1.8971 (2.2160) time: 0.6212 [2021-03-27 21:31:56 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 60/1251] eta: 0:13:38 lr: 0.000231 loss: 3.0494 (2.9557) grad_norm: 1.8666 (2.1751) time: 0.6251 [2021-03-27 21:32:03 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 70/1251] eta: 0:13:22 lr: 0.000231 loss: 3.0429 (2.9467) grad_norm: 2.0249 (2.1856) time: 0.6288 [2021-03-27 21:32:09 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 80/1251] eta: 0:13:08 lr: 0.000231 loss: 3.0970 (2.9754) grad_norm: 2.0848 (2.1962) time: 0.6315 [2021-03-27 21:32:15 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 90/1251] eta: 0:12:56 lr: 0.000231 loss: 3.0970 (2.9594) grad_norm: 2.1189 (2.2058) time: 0.6302 [2021-03-27 21:32:22 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 100/1251] eta: 0:12:45 lr: 0.000231 loss: 3.0628 (2.9697) grad_norm: 2.1405 (2.1951) time: 0.6298 [2021-03-27 21:32:28 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 110/1251] eta: 0:12:35 lr: 0.000231 loss: 3.0816 (2.9556) grad_norm: 2.0692 (2.1884) time: 0.6289 [2021-03-27 21:32:34 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 120/1251] eta: 0:12:24 lr: 0.000231 loss: 3.0791 (2.9509) grad_norm: 2.0229 (2.1719) time: 0.6244 [2021-03-27 21:32:40 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 130/1251] eta: 0:12:15 lr: 0.000231 loss: 2.9559 (2.9421) grad_norm: 2.0141 (2.1655) time: 0.6269 [2021-03-27 21:32:47 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 140/1251] eta: 0:12:07 lr: 0.000231 loss: 3.2209 (2.9609) grad_norm: 2.0615 (2.1605) time: 0.6343 [2021-03-27 21:32:53 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 150/1251] eta: 0:11:59 lr: 0.000231 loss: 3.2384 (2.9801) grad_norm: 1.9682 (2.1498) time: 0.6315 [2021-03-27 21:32:59 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 160/1251] eta: 0:11:50 lr: 0.000231 loss: 3.2384 (2.9957) grad_norm: 1.9673 (2.1435) time: 0.6274 [2021-03-27 21:33:06 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 170/1251] eta: 0:11:42 lr: 0.000230 loss: 3.0594 (2.9929) grad_norm: 2.0250 (2.1685) time: 0.6253 [2021-03-27 21:33:12 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 180/1251] eta: 0:11:34 lr: 0.000230 loss: 3.0402 (2.9953) grad_norm: 2.0857 (2.2106) time: 0.6246 [2021-03-27 21:33:18 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 190/1251] eta: 0:11:26 lr: 0.000230 loss: 3.0910 (2.9970) grad_norm: 2.0259 (2.2035) time: 0.6238 [2021-03-27 21:33:24 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 200/1251] eta: 0:11:19 lr: 0.000230 loss: 3.1253 (3.0044) grad_norm: 2.0076 (2.1999) time: 0.6242 [2021-03-27 21:33:31 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 210/1251] eta: 0:11:11 lr: 0.000230 loss: 3.2602 (3.0167) grad_norm: 2.0421 (2.1906) time: 0.6268 [2021-03-27 21:33:37 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 220/1251] eta: 0:11:04 lr: 0.000230 loss: 3.2553 (3.0189) grad_norm: 2.0421 (2.1833) time: 0.6272 [2021-03-27 21:33:43 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 230/1251] eta: 0:10:57 lr: 0.000230 loss: 3.1723 (3.0264) grad_norm: 2.0117 (2.2012) time: 0.6324 [2021-03-27 21:33:49 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 240/1251] eta: 0:10:50 lr: 0.000230 loss: 3.1723 (3.0231) grad_norm: 1.9580 (2.1958) time: 0.6288 [2021-03-27 21:33:56 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 250/1251] eta: 0:10:42 lr: 0.000230 loss: 2.8481 (3.0214) grad_norm: 2.0101 (2.1934) time: 0.6197 [2021-03-27 21:34:02 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 260/1251] eta: 0:10:35 lr: 0.000230 loss: 2.9711 (3.0227) grad_norm: 2.0631 (2.2038) time: 0.6210 [2021-03-27 21:34:08 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 270/1251] eta: 0:10:28 lr: 0.000230 loss: 3.2600 (3.0338) grad_norm: 2.2699 (2.2030) time: 0.6253 [2021-03-27 21:34:14 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 280/1251] eta: 0:10:21 lr: 0.000230 loss: 3.2495 (3.0331) grad_norm: 2.0682 (2.2006) time: 0.6274 [2021-03-27 21:34:21 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 290/1251] eta: 0:10:14 lr: 0.000230 loss: 3.0212 (3.0203) grad_norm: 2.0098 (2.1974) time: 0.6252 [2021-03-27 21:34:27 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 300/1251] eta: 0:10:07 lr: 0.000230 loss: 3.0212 (3.0169) grad_norm: 2.0135 (2.1911) time: 0.6240 [2021-03-27 21:34:33 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 310/1251] eta: 0:10:01 lr: 0.000230 loss: 3.0902 (3.0179) grad_norm: 2.0135 (2.1842) time: 0.6246 [2021-03-27 21:34:39 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 320/1251] eta: 0:09:54 lr: 0.000230 loss: 3.0902 (3.0201) grad_norm: 2.0368 (2.1861) time: 0.6264 [2021-03-27 21:34:46 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 330/1251] eta: 0:09:47 lr: 0.000230 loss: 3.0381 (3.0181) grad_norm: 2.1930 (2.1842) time: 0.6310 [2021-03-27 21:34:52 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 340/1251] eta: 0:09:41 lr: 0.000230 loss: 3.2023 (3.0239) grad_norm: 2.0934 (2.1785) time: 0.6310 [2021-03-27 21:34:58 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 350/1251] eta: 0:09:34 lr: 0.000230 loss: 2.9959 (3.0137) grad_norm: 2.0094 (2.1808) time: 0.6248 [2021-03-27 21:35:05 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 360/1251] eta: 0:09:28 lr: 0.000230 loss: 2.8362 (3.0136) grad_norm: 2.0094 (2.1764) time: 0.6282 [2021-03-27 21:35:11 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 370/1251] eta: 0:09:21 lr: 0.000230 loss: 3.1709 (3.0193) grad_norm: 2.0015 (2.1715) time: 0.6272 [2021-03-27 21:35:17 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 380/1251] eta: 0:09:14 lr: 0.000230 loss: 2.8750 (3.0102) grad_norm: 2.0213 (2.1727) time: 0.6256 [2021-03-27 21:35:23 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 390/1251] eta: 0:09:08 lr: 0.000230 loss: 2.8750 (3.0157) grad_norm: 2.0507 (2.1727) time: 0.6305 [2021-03-27 21:35:30 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 400/1251] eta: 0:09:01 lr: 0.000230 loss: 3.2071 (3.0190) grad_norm: 2.0507 (2.1735) time: 0.6255 [2021-03-27 21:35:36 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 410/1251] eta: 0:08:55 lr: 0.000230 loss: 3.1628 (3.0153) grad_norm: 1.9652 (2.1694) time: 0.6255 [2021-03-27 21:35:42 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 420/1251] eta: 0:08:48 lr: 0.000230 loss: 2.8609 (3.0127) grad_norm: 1.9980 (2.1725) time: 0.6296 [2021-03-27 21:35:48 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 430/1251] eta: 0:08:41 lr: 0.000230 loss: 2.7425 (3.0047) grad_norm: 2.0895 (2.1703) time: 0.6244 [2021-03-27 21:35:55 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 440/1251] eta: 0:08:35 lr: 0.000230 loss: 2.7425 (3.0002) grad_norm: 2.1007 (2.1705) time: 0.6203 [2021-03-27 21:36:01 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 450/1251] eta: 0:08:28 lr: 0.000230 loss: 2.9352 (3.0008) grad_norm: 2.1007 (2.1722) time: 0.6239 [2021-03-27 21:36:07 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 460/1251] eta: 0:08:22 lr: 0.000229 loss: 3.2535 (3.0075) grad_norm: 2.0792 (2.1761) time: 0.6286 [2021-03-27 21:36:13 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 470/1251] eta: 0:08:15 lr: 0.000229 loss: 3.1270 (3.0037) grad_norm: 2.2473 (2.1795) time: 0.6277 [2021-03-27 21:36:20 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 480/1251] eta: 0:08:09 lr: 0.000229 loss: 2.7703 (2.9988) grad_norm: 2.0568 (2.1769) time: 0.6254 [2021-03-27 21:36:26 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 490/1251] eta: 0:08:02 lr: 0.000229 loss: 2.7007 (2.9959) grad_norm: 1.9975 (2.1736) time: 0.6253 [2021-03-27 21:36:32 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 500/1251] eta: 0:07:56 lr: 0.000229 loss: 2.8459 (2.9929) grad_norm: 2.0501 (2.1732) time: 0.6233 [2021-03-27 21:36:38 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 510/1251] eta: 0:07:49 lr: 0.000229 loss: 2.9013 (2.9933) grad_norm: 2.0710 (2.1728) time: 0.6230 [2021-03-27 21:36:45 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 520/1251] eta: 0:07:43 lr: 0.000229 loss: 3.0826 (2.9975) grad_norm: 2.1656 (2.1732) time: 0.6219 [2021-03-27 21:36:51 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 530/1251] eta: 0:07:36 lr: 0.000229 loss: 3.0826 (2.9948) grad_norm: 2.0557 (2.1760) time: 0.6258 [2021-03-27 21:36:57 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 540/1251] eta: 0:07:30 lr: 0.000229 loss: 2.8961 (2.9919) grad_norm: 1.9427 (2.1717) time: 0.6328 [2021-03-27 21:37:04 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 550/1251] eta: 0:07:24 lr: 0.000229 loss: 2.9720 (2.9940) grad_norm: 1.9427 (2.1705) time: 0.6402 [2021-03-27 21:37:10 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 560/1251] eta: 0:07:18 lr: 0.000229 loss: 3.2921 (2.9973) grad_norm: 2.0513 (2.1675) time: 0.6436 [2021-03-27 21:37:16 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 570/1251] eta: 0:07:11 lr: 0.000229 loss: 3.2098 (2.9935) grad_norm: 1.9951 (2.1642) time: 0.6345 [2021-03-27 21:37:23 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 580/1251] eta: 0:07:05 lr: 0.000229 loss: 2.6990 (2.9900) grad_norm: 1.9988 (2.1632) time: 0.6269 [2021-03-27 21:37:29 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 590/1251] eta: 0:06:58 lr: 0.000229 loss: 3.0749 (2.9912) grad_norm: 2.0126 (2.1613) time: 0.6235 [2021-03-27 21:37:35 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 600/1251] eta: 0:06:52 lr: 0.000229 loss: 3.1707 (2.9929) grad_norm: 2.0215 (2.1599) time: 0.6217 [2021-03-27 21:37:41 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 610/1251] eta: 0:06:45 lr: 0.000229 loss: 3.1167 (2.9939) grad_norm: 2.1824 (2.1634) time: 0.6220 [2021-03-27 21:37:48 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 620/1251] eta: 0:06:39 lr: 0.000229 loss: 3.1534 (2.9981) grad_norm: 2.2177 (2.1633) time: 0.6255 [2021-03-27 21:37:54 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 630/1251] eta: 0:06:33 lr: 0.000229 loss: 3.0886 (2.9926) grad_norm: 1.9932 (2.1616) time: 0.6339 [2021-03-27 21:38:00 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 640/1251] eta: 0:06:26 lr: 0.000229 loss: 2.7550 (2.9938) grad_norm: 1.9885 (2.1615) time: 0.6329 [2021-03-27 21:38:07 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 650/1251] eta: 0:06:20 lr: 0.000229 loss: 3.1723 (2.9956) grad_norm: 1.9885 (2.1642) time: 0.6304 [2021-03-27 21:38:13 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 660/1251] eta: 0:06:14 lr: 0.000229 loss: 3.0881 (2.9927) grad_norm: 1.9726 (2.1637) time: 0.6318 [2021-03-27 21:38:19 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 670/1251] eta: 0:06:07 lr: 0.000229 loss: 2.9585 (2.9968) grad_norm: 2.0693 (2.1629) time: 0.6331 [2021-03-27 21:38:26 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 680/1251] eta: 0:06:01 lr: 0.000229 loss: 3.1631 (2.9980) grad_norm: 2.0312 (2.1623) time: 0.6288 [2021-03-27 21:38:32 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 690/1251] eta: 0:05:54 lr: 0.000229 loss: 3.1631 (2.9977) grad_norm: 2.0961 (2.1645) time: 0.6223 [2021-03-27 21:38:38 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 700/1251] eta: 0:05:48 lr: 0.000229 loss: 3.0458 (2.9990) grad_norm: 2.0961 (2.1666) time: 0.6303 [2021-03-27 21:38:44 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 710/1251] eta: 0:05:42 lr: 0.000229 loss: 3.0404 (2.9998) grad_norm: 2.0807 (2.1661) time: 0.6299 [2021-03-27 21:38:51 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 720/1251] eta: 0:05:35 lr: 0.000229 loss: 2.9462 (2.9947) grad_norm: 2.0812 (2.1645) time: 0.6214 [2021-03-27 21:38:57 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 730/1251] eta: 0:05:29 lr: 0.000229 loss: 2.9359 (2.9946) grad_norm: 1.9715 (2.1614) time: 0.6290 [2021-03-27 21:39:03 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 740/1251] eta: 0:05:23 lr: 0.000229 loss: 2.8956 (2.9924) grad_norm: 1.9616 (2.1620) time: 0.6450 [2021-03-27 21:39:10 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 750/1251] eta: 0:05:17 lr: 0.000228 loss: 2.6892 (2.9896) grad_norm: 2.0660 (2.1625) time: 0.6427 [2021-03-27 21:39:16 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 760/1251] eta: 0:05:10 lr: 0.000228 loss: 2.9950 (2.9909) grad_norm: 2.0354 (2.1602) time: 0.6266 [2021-03-27 21:39:22 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 770/1251] eta: 0:05:04 lr: 0.000228 loss: 3.0620 (2.9896) grad_norm: 2.0173 (2.1632) time: 0.6227 [2021-03-27 21:39:29 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 780/1251] eta: 0:04:57 lr: 0.000228 loss: 2.9985 (2.9897) grad_norm: 2.1772 (2.1662) time: 0.6277 [2021-03-27 21:39:35 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 790/1251] eta: 0:04:51 lr: 0.000228 loss: 2.9985 (2.9887) grad_norm: 2.1772 (2.1662) time: 0.6296 [2021-03-27 21:39:41 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 800/1251] eta: 0:04:45 lr: 0.000228 loss: 3.0690 (2.9901) grad_norm: 2.1354 (2.1653) time: 0.6281 [2021-03-27 21:39:47 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 810/1251] eta: 0:04:38 lr: 0.000228 loss: 2.9902 (2.9880) grad_norm: 2.0047 (2.1641) time: 0.6271 [2021-03-27 21:39:54 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 820/1251] eta: 0:04:32 lr: 0.000228 loss: 3.1301 (2.9910) grad_norm: 1.9400 (2.1610) time: 0.6282 [2021-03-27 21:40:00 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 830/1251] eta: 0:04:26 lr: 0.000228 loss: 3.1462 (2.9914) grad_norm: 1.9760 (2.1603) time: 0.6263 [2021-03-27 21:40:06 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 840/1251] eta: 0:04:19 lr: 0.000228 loss: 3.1118 (2.9937) grad_norm: 2.0690 (2.1606) time: 0.6245 [2021-03-27 21:40:12 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 850/1251] eta: 0:04:13 lr: 0.000228 loss: 3.2764 (2.9960) grad_norm: 2.0242 (2.1589) time: 0.6285 [2021-03-27 21:40:19 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 860/1251] eta: 0:04:07 lr: 0.000228 loss: 3.1814 (2.9980) grad_norm: 2.1139 (2.1604) time: 0.6359 [2021-03-27 21:40:25 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 870/1251] eta: 0:04:00 lr: 0.000228 loss: 3.1201 (2.9975) grad_norm: 2.2113 (2.1606) time: 0.6341 [2021-03-27 21:40:32 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 880/1251] eta: 0:03:54 lr: 0.000228 loss: 3.2268 (2.9997) grad_norm: 2.0453 (2.1599) time: 0.6322 [2021-03-27 21:40:38 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 890/1251] eta: 0:03:48 lr: 0.000228 loss: 3.1581 (3.0006) grad_norm: 1.9880 (2.1586) time: 0.6359 [2021-03-27 21:40:44 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 900/1251] eta: 0:03:41 lr: 0.000228 loss: 3.0643 (3.0016) grad_norm: 2.0151 (2.1578) time: 0.6287 [2021-03-27 21:40:50 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 910/1251] eta: 0:03:35 lr: 0.000228 loss: 3.0233 (3.0020) grad_norm: 2.0608 (2.1572) time: 0.6225 [2021-03-27 21:40:57 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 920/1251] eta: 0:03:29 lr: 0.000228 loss: 3.0233 (3.0018) grad_norm: 2.1368 (2.1582) time: 0.6230 [2021-03-27 21:41:03 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 930/1251] eta: 0:03:22 lr: 0.000228 loss: 3.0024 (3.0020) grad_norm: 2.1098 (2.1570) time: 0.6270 [2021-03-27 21:41:09 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 940/1251] eta: 0:03:16 lr: 0.000228 loss: 2.9690 (3.0023) grad_norm: 2.1098 (2.1586) time: 0.6264 [2021-03-27 21:41:15 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 950/1251] eta: 0:03:10 lr: 0.000228 loss: 3.1202 (3.0029) grad_norm: 2.1119 (2.1579) time: 0.6229 [2021-03-27 21:41:22 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 960/1251] eta: 0:03:03 lr: 0.000228 loss: 3.1248 (3.0033) grad_norm: 1.9881 (2.1563) time: 0.6275 [2021-03-27 21:41:28 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 970/1251] eta: 0:02:57 lr: 0.000228 loss: 3.1436 (3.0030) grad_norm: 1.9727 (2.1557) time: 0.6292 [2021-03-27 21:41:34 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 980/1251] eta: 0:02:51 lr: 0.000228 loss: 3.1547 (3.0021) grad_norm: 1.9870 (2.1548) time: 0.6284 [2021-03-27 21:41:41 swin_base_patch4_window7_224] INFO: Epoch: [206] [ 990/1251] eta: 0:02:44 lr: 0.000228 loss: 2.9714 (3.0005) grad_norm: 2.1215 (2.1554) time: 0.6279 [2021-03-27 21:41:47 swin_base_patch4_window7_224] INFO: Epoch: [206] [1000/1251] eta: 0:02:38 lr: 0.000228 loss: 3.0821 (3.0019) grad_norm: 2.1579 (2.1568) time: 0.6258 [2021-03-27 21:41:53 swin_base_patch4_window7_224] INFO: Epoch: [206] [1010/1251] eta: 0:02:32 lr: 0.000228 loss: 3.2289 (3.0039) grad_norm: 2.0602 (2.1550) time: 0.6258 [2021-03-27 21:41:59 swin_base_patch4_window7_224] INFO: Epoch: [206] [1020/1251] eta: 0:02:25 lr: 0.000228 loss: 3.1122 (3.0044) grad_norm: 1.9753 (2.1544) time: 0.6270 [2021-03-27 21:42:06 swin_base_patch4_window7_224] INFO: Epoch: [206] [1030/1251] eta: 0:02:19 lr: 0.000228 loss: 2.9886 (3.0057) grad_norm: 1.9826 (2.1580) time: 0.6287 [2021-03-27 21:42:12 swin_base_patch4_window7_224] INFO: Epoch: [206] [1040/1251] eta: 0:02:13 lr: 0.000227 loss: 3.0717 (3.0077) grad_norm: 1.9557 (2.1563) time: 0.6296 [2021-03-27 21:42:18 swin_base_patch4_window7_224] INFO: Epoch: [206] [1050/1251] eta: 0:02:06 lr: 0.000227 loss: 3.1818 (3.0080) grad_norm: 2.0117 (2.1560) time: 0.6305 [2021-03-27 21:42:24 swin_base_patch4_window7_224] INFO: Epoch: [206] [1060/1251] eta: 0:02:00 lr: 0.000227 loss: 3.0934 (3.0086) grad_norm: 2.0117 (2.1560) time: 0.6291 [2021-03-27 21:42:31 swin_base_patch4_window7_224] INFO: Epoch: [206] [1070/1251] eta: 0:01:54 lr: 0.000227 loss: 3.0840 (3.0079) grad_norm: 1.9645 (2.1560) time: 0.6285 [2021-03-27 21:42:37 swin_base_patch4_window7_224] INFO: Epoch: [206] [1080/1251] eta: 0:01:47 lr: 0.000227 loss: 3.1026 (3.0077) grad_norm: 2.0309 (2.1558) time: 0.6276 [2021-03-27 21:42:43 swin_base_patch4_window7_224] INFO: Epoch: [206] [1090/1251] eta: 0:01:41 lr: 0.000227 loss: 3.2682 (3.0107) grad_norm: 1.9193 (2.1545) time: 0.6229 [2021-03-27 21:42:50 swin_base_patch4_window7_224] INFO: Epoch: [206] [1100/1251] eta: 0:01:35 lr: 0.000227 loss: 3.3397 (3.0119) grad_norm: 1.8042 (2.1512) time: 0.6261 [2021-03-27 21:42:56 swin_base_patch4_window7_224] INFO: Epoch: [206] [1110/1251] eta: 0:01:28 lr: 0.000227 loss: 3.2186 (3.0099) grad_norm: 1.8551 (2.1501) time: 0.6273 [2021-03-27 21:43:02 swin_base_patch4_window7_224] INFO: Epoch: [206] [1120/1251] eta: 0:01:22 lr: 0.000227 loss: 2.8382 (3.0093) grad_norm: 1.9801 (2.1494) time: 0.6226 [2021-03-27 21:43:08 swin_base_patch4_window7_224] INFO: Epoch: [206] [1130/1251] eta: 0:01:16 lr: 0.000227 loss: 3.1922 (3.0092) grad_norm: 2.0367 (2.1499) time: 0.6204 [2021-03-27 21:43:15 swin_base_patch4_window7_224] INFO: Epoch: [206] [1140/1251] eta: 0:01:10 lr: 0.000227 loss: 2.7864 (3.0069) grad_norm: 2.0401 (2.1497) time: 0.6246 [2021-03-27 21:43:21 swin_base_patch4_window7_224] INFO: Epoch: [206] [1150/1251] eta: 0:01:03 lr: 0.000227 loss: 2.8753 (3.0085) grad_norm: 1.9928 (2.1484) time: 0.6272 [2021-03-27 21:43:27 swin_base_patch4_window7_224] INFO: Epoch: [206] [1160/1251] eta: 0:00:57 lr: 0.000227 loss: 3.3152 (3.0102) grad_norm: 1.9685 (2.1477) time: 0.6275 [2021-03-27 21:43:33 swin_base_patch4_window7_224] INFO: Epoch: [206] [1170/1251] eta: 0:00:51 lr: 0.000227 loss: 3.3102 (3.0127) grad_norm: 2.0650 (2.1480) time: 0.6279 [2021-03-27 21:43:39 swin_base_patch4_window7_224] INFO: Epoch: [206] [1180/1251] eta: 0:00:44 lr: 0.000227 loss: 3.3102 (3.0128) grad_norm: 2.0830 (2.1472) time: 0.6215 [2021-03-27 21:43:46 swin_base_patch4_window7_224] INFO: Epoch: [206] [1190/1251] eta: 0:00:38 lr: 0.000227 loss: 3.1609 (3.0137) grad_norm: 2.1007 (2.1471) time: 0.6214 [2021-03-27 21:43:52 swin_base_patch4_window7_224] INFO: Epoch: [206] [1200/1251] eta: 0:00:32 lr: 0.000227 loss: 3.1758 (3.0152) grad_norm: 2.0335 (2.1460) time: 0.6269 [2021-03-27 21:43:58 swin_base_patch4_window7_224] INFO: Epoch: [206] [1210/1251] eta: 0:00:25 lr: 0.000227 loss: 3.2092 (3.0165) grad_norm: 1.9999 (2.1450) time: 0.6265 [2021-03-27 21:44:04 swin_base_patch4_window7_224] INFO: Epoch: [206] [1220/1251] eta: 0:00:19 lr: 0.000227 loss: 3.0984 (3.0152) grad_norm: 2.0087 (2.1437) time: 0.6227 [2021-03-27 21:44:11 swin_base_patch4_window7_224] INFO: Epoch: [206] [1230/1251] eta: 0:00:13 lr: 0.000227 loss: 3.1197 (3.0172) grad_norm: 2.0199 (2.1437) time: 0.6276 [2021-03-27 21:44:17 swin_base_patch4_window7_224] INFO: Epoch: [206] [1240/1251] eta: 0:00:06 lr: 0.000227 loss: 3.1585 (3.0178) grad_norm: 1.9962 (2.1420) time: 0.6349 [2021-03-27 21:44:23 swin_base_patch4_window7_224] INFO: Epoch: [206] [1250/1251] eta: 0:00:00 lr: 0.000227 loss: 2.9885 (3.0168) grad_norm: 1.8379 (2.1407) time: 0.6314 [2021-03-27 21:44:32 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:07 loss: 0.6543 (0.6543) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-27 21:44:34 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7133 (0.7524) acc1: 82.8125 (81.5341) acc5: 96.8750 (96.3068) [2021-03-27 21:44:37 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8097 (0.8082) acc1: 79.6875 (80.3571) acc5: 96.8750 (96.2054) [2021-03-27 21:44:39 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8097 (0.8123) acc1: 79.6875 (80.6452) acc5: 96.8750 (96.1694) [2021-03-27 21:44:41 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8072 (0.8351) acc1: 79.6875 (80.3735) acc5: 95.3125 (96.0366) [2021-03-27 21:44:42 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7978 (0.8247) acc1: 81.2500 (80.6720) acc5: 95.3125 (96.0960) [2021-03-27 21:44:54 swin_base_patch4_window7_224] INFO: * Acc@1 81.268 Acc@5 95.850 loss 0.814 [2021-03-27 21:44:54 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.3% [2021-03-27 21:44:54 swin_base_patch4_window7_224] INFO: Max accuracy: 81.48% [2021-03-27 21:44:59 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 0/1251] eta: 1:47:48 lr: 0.000227 loss: 2.9827 (2.9827) grad_norm: 2.3620 (2.3620) time: 5.1708 [2021-03-27 21:45:06 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 10/1251] eta: 0:21:44 lr: 0.000227 loss: 3.1693 (3.1885) grad_norm: 2.0752 (2.1317) time: 1.0509 [2021-03-27 21:45:12 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 20/1251] eta: 0:17:30 lr: 0.000227 loss: 3.1513 (3.1475) grad_norm: 2.0158 (2.1001) time: 0.6372 [2021-03-27 21:45:18 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 30/1251] eta: 0:15:51 lr: 0.000227 loss: 3.1265 (3.0517) grad_norm: 2.0793 (2.1003) time: 0.6297 [2021-03-27 21:45:24 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 40/1251] eta: 0:14:56 lr: 0.000227 loss: 3.0870 (3.0675) grad_norm: 2.1269 (2.1355) time: 0.6227 [2021-03-27 21:45:31 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 50/1251] eta: 0:14:23 lr: 0.000227 loss: 2.9421 (2.9960) grad_norm: 2.1048 (2.1349) time: 0.6256 [2021-03-27 21:45:37 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 60/1251] eta: 0:13:59 lr: 0.000227 loss: 2.7420 (3.0120) grad_norm: 2.1183 (2.1542) time: 0.6323 [2021-03-27 21:45:43 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 70/1251] eta: 0:13:40 lr: 0.000227 loss: 3.0078 (2.9767) grad_norm: 2.1391 (2.1707) time: 0.6318 [2021-03-27 21:45:50 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 80/1251] eta: 0:13:24 lr: 0.000226 loss: 2.7318 (2.9652) grad_norm: 1.9372 (2.1406) time: 0.6328 [2021-03-27 21:45:56 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 90/1251] eta: 0:13:09 lr: 0.000226 loss: 3.0609 (2.9894) grad_norm: 1.8783 (2.1194) time: 0.6294 [2021-03-27 21:46:02 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 100/1251] eta: 0:12:55 lr: 0.000226 loss: 3.0163 (2.9467) grad_norm: 2.0505 (2.1284) time: 0.6211 [2021-03-27 21:46:08 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 110/1251] eta: 0:12:44 lr: 0.000226 loss: 3.0163 (2.9648) grad_norm: 2.1580 (2.1212) time: 0.6230 [2021-03-27 21:46:15 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 120/1251] eta: 0:12:33 lr: 0.000226 loss: 3.1085 (2.9744) grad_norm: 1.9266 (2.1028) time: 0.6273 [2021-03-27 21:46:21 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 130/1251] eta: 0:12:23 lr: 0.000226 loss: 3.0356 (2.9771) grad_norm: 1.9637 (2.1002) time: 0.6292 [2021-03-27 21:46:27 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 140/1251] eta: 0:12:15 lr: 0.000226 loss: 3.0354 (2.9661) grad_norm: 1.9637 (2.1032) time: 0.6382 [2021-03-27 21:46:34 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 150/1251] eta: 0:12:06 lr: 0.000226 loss: 2.7606 (2.9574) grad_norm: 1.9243 (2.1008) time: 0.6357 [2021-03-27 21:46:40 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 160/1251] eta: 0:11:57 lr: 0.000226 loss: 3.1070 (2.9751) grad_norm: 1.9767 (2.1199) time: 0.6255 [2021-03-27 21:46:46 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 170/1251] eta: 0:11:49 lr: 0.000226 loss: 3.2619 (2.9902) grad_norm: 1.9767 (2.1263) time: 0.6273 [2021-03-27 21:46:53 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 180/1251] eta: 0:11:41 lr: 0.000226 loss: 3.0728 (2.9840) grad_norm: 2.0205 (2.1264) time: 0.6305 [2021-03-27 21:46:59 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 190/1251] eta: 0:11:33 lr: 0.000226 loss: 3.0320 (2.9878) grad_norm: 1.9945 (2.1182) time: 0.6315 [2021-03-27 21:47:05 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 200/1251] eta: 0:11:25 lr: 0.000226 loss: 3.1625 (3.0026) grad_norm: 1.9435 (2.1123) time: 0.6298 [2021-03-27 21:47:12 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 210/1251] eta: 0:11:18 lr: 0.000226 loss: 3.1531 (2.9982) grad_norm: 2.0911 (2.1185) time: 0.6347 [2021-03-27 21:47:18 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 220/1251] eta: 0:11:10 lr: 0.000226 loss: 2.9487 (2.9995) grad_norm: 2.1054 (2.1159) time: 0.6313 [2021-03-27 21:47:24 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 230/1251] eta: 0:11:02 lr: 0.000226 loss: 3.0085 (3.0012) grad_norm: 1.9653 (2.1131) time: 0.6232 [2021-03-27 21:47:30 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 240/1251] eta: 0:10:55 lr: 0.000226 loss: 3.1961 (3.0105) grad_norm: 1.9252 (2.1108) time: 0.6227 [2021-03-27 21:47:37 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 250/1251] eta: 0:10:47 lr: 0.000226 loss: 3.1746 (3.0068) grad_norm: 1.9946 (2.1122) time: 0.6234 [2021-03-27 21:47:43 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 260/1251] eta: 0:10:41 lr: 0.000226 loss: 2.9942 (3.0022) grad_norm: 2.0718 (2.1152) time: 0.6322 [2021-03-27 21:47:49 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 270/1251] eta: 0:10:34 lr: 0.000226 loss: 3.1649 (3.0066) grad_norm: 2.0269 (2.1181) time: 0.6374 [2021-03-27 21:47:56 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 280/1251] eta: 0:10:27 lr: 0.000226 loss: 3.0152 (3.0026) grad_norm: 2.0202 (2.1164) time: 0.6332 [2021-03-27 21:48:02 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 290/1251] eta: 0:10:20 lr: 0.000226 loss: 2.9552 (3.0030) grad_norm: 2.0841 (2.1247) time: 0.6281 [2021-03-27 21:48:08 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 300/1251] eta: 0:10:12 lr: 0.000226 loss: 3.2818 (3.0180) grad_norm: 2.2545 (2.1278) time: 0.6238 [2021-03-27 21:48:14 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 310/1251] eta: 0:10:06 lr: 0.000226 loss: 3.2516 (3.0146) grad_norm: 2.1579 (2.1255) time: 0.6275 [2021-03-27 21:48:21 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 320/1251] eta: 0:09:59 lr: 0.000226 loss: 3.1403 (3.0151) grad_norm: 1.9118 (2.1197) time: 0.6341 [2021-03-27 21:48:27 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 330/1251] eta: 0:09:52 lr: 0.000226 loss: 2.8940 (3.0069) grad_norm: 1.9542 (2.1178) time: 0.6311 [2021-03-27 21:48:33 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 340/1251] eta: 0:09:45 lr: 0.000226 loss: 2.8627 (3.0040) grad_norm: 2.1020 (2.1180) time: 0.6242 [2021-03-27 21:48:40 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 350/1251] eta: 0:09:38 lr: 0.000226 loss: 2.9067 (2.9998) grad_norm: 2.0452 (2.1154) time: 0.6266 [2021-03-27 21:48:46 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 360/1251] eta: 0:09:32 lr: 0.000226 loss: 2.7461 (2.9957) grad_norm: 2.0299 (2.1128) time: 0.6345 [2021-03-27 21:48:52 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 370/1251] eta: 0:09:25 lr: 0.000226 loss: 3.0425 (3.0014) grad_norm: 1.9961 (2.1087) time: 0.6281 [2021-03-27 21:48:58 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 380/1251] eta: 0:09:18 lr: 0.000225 loss: 3.2236 (3.0031) grad_norm: 1.9316 (2.1015) time: 0.6265 [2021-03-27 21:49:05 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 390/1251] eta: 0:09:11 lr: 0.000225 loss: 3.2236 (3.0112) grad_norm: 1.9649 (2.1073) time: 0.6286 [2021-03-27 21:49:11 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 400/1251] eta: 0:09:05 lr: 0.000225 loss: 3.3856 (3.0143) grad_norm: 1.9852 (2.1056) time: 0.6255 [2021-03-27 21:49:17 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 410/1251] eta: 0:08:58 lr: 0.000225 loss: 3.1645 (3.0123) grad_norm: 2.0153 (2.1061) time: 0.6374 [2021-03-27 21:49:24 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 420/1251] eta: 0:08:52 lr: 0.000225 loss: 3.1946 (3.0181) grad_norm: 2.0713 (2.1065) time: 0.6376 [2021-03-27 21:49:30 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 430/1251] eta: 0:08:45 lr: 0.000225 loss: 3.3382 (3.0251) grad_norm: 2.0765 (2.1067) time: 0.6255 [2021-03-27 21:49:36 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 440/1251] eta: 0:08:38 lr: 0.000225 loss: 3.2937 (3.0244) grad_norm: 2.1005 (2.1070) time: 0.6282 [2021-03-27 21:49:43 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 450/1251] eta: 0:08:32 lr: 0.000225 loss: 2.9190 (3.0224) grad_norm: 1.9843 (2.1044) time: 0.6318 [2021-03-27 21:49:49 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 460/1251] eta: 0:08:25 lr: 0.000225 loss: 2.9712 (3.0239) grad_norm: 1.9638 (2.1052) time: 0.6294 [2021-03-27 21:49:55 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 470/1251] eta: 0:08:19 lr: 0.000225 loss: 2.9806 (3.0230) grad_norm: 1.9760 (2.1061) time: 0.6263 [2021-03-27 21:50:01 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 480/1251] eta: 0:08:12 lr: 0.000225 loss: 3.0389 (3.0242) grad_norm: 1.9925 (2.1070) time: 0.6230 [2021-03-27 21:50:08 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 490/1251] eta: 0:08:05 lr: 0.000225 loss: 3.1985 (3.0244) grad_norm: 1.9925 (2.1039) time: 0.6243 [2021-03-27 21:50:14 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 500/1251] eta: 0:07:59 lr: 0.000225 loss: 3.1957 (3.0250) grad_norm: 1.9910 (2.1029) time: 0.6252 [2021-03-27 21:50:20 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 510/1251] eta: 0:07:52 lr: 0.000225 loss: 3.1416 (3.0270) grad_norm: 1.9961 (2.1028) time: 0.6288 [2021-03-27 21:50:26 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 520/1251] eta: 0:07:46 lr: 0.000225 loss: 3.0548 (3.0261) grad_norm: 1.9961 (2.1017) time: 0.6278 [2021-03-27 21:50:33 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 530/1251] eta: 0:07:39 lr: 0.000225 loss: 3.0900 (3.0243) grad_norm: 1.9754 (2.0994) time: 0.6230 [2021-03-27 21:50:39 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 540/1251] eta: 0:07:33 lr: 0.000225 loss: 3.1498 (3.0219) grad_norm: 2.0128 (2.0990) time: 0.6236 [2021-03-27 21:50:45 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 550/1251] eta: 0:07:26 lr: 0.000225 loss: 2.9236 (3.0202) grad_norm: 2.0520 (2.1042) time: 0.6294 [2021-03-27 21:50:52 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 560/1251] eta: 0:07:20 lr: 0.000225 loss: 2.9660 (3.0210) grad_norm: 2.0520 (2.1031) time: 0.6474 [2021-03-27 21:50:58 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 570/1251] eta: 0:07:14 lr: 0.000225 loss: 2.9660 (3.0168) grad_norm: 2.0423 (2.1046) time: 0.6431 [2021-03-27 21:51:04 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 580/1251] eta: 0:07:07 lr: 0.000225 loss: 3.0264 (3.0163) grad_norm: 1.9788 (2.1034) time: 0.6289 [2021-03-27 21:51:11 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 590/1251] eta: 0:07:01 lr: 0.000225 loss: 3.0523 (3.0151) grad_norm: 1.8658 (2.0994) time: 0.6323 [2021-03-27 21:51:17 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 600/1251] eta: 0:06:54 lr: 0.000225 loss: 2.9208 (3.0127) grad_norm: 1.8695 (2.0987) time: 0.6329 [2021-03-27 21:51:23 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 610/1251] eta: 0:06:48 lr: 0.000225 loss: 3.1004 (3.0170) grad_norm: 2.0020 (2.0975) time: 0.6278 [2021-03-27 21:51:30 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 620/1251] eta: 0:06:41 lr: 0.000225 loss: 3.1659 (3.0177) grad_norm: 1.8957 (2.0938) time: 0.6322 [2021-03-27 21:51:36 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 630/1251] eta: 0:06:35 lr: 0.000225 loss: 3.1258 (3.0164) grad_norm: 1.8957 (2.0924) time: 0.6321 [2021-03-27 21:51:42 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 640/1251] eta: 0:06:28 lr: 0.000225 loss: 3.0690 (3.0149) grad_norm: 1.9808 (2.0913) time: 0.6250 [2021-03-27 21:51:48 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 650/1251] eta: 0:06:22 lr: 0.000225 loss: 3.0180 (3.0133) grad_norm: 1.9203 (2.0899) time: 0.6246 [2021-03-27 21:51:55 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 660/1251] eta: 0:06:15 lr: 0.000225 loss: 2.6725 (3.0072) grad_norm: 1.9795 (2.0900) time: 0.6217 [2021-03-27 21:52:01 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 670/1251] eta: 0:06:09 lr: 0.000224 loss: 2.8579 (3.0078) grad_norm: 1.9822 (2.0876) time: 0.6231 [2021-03-27 21:52:07 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 680/1251] eta: 0:06:03 lr: 0.000224 loss: 2.9976 (3.0051) grad_norm: 1.9822 (2.0875) time: 0.6269 [2021-03-27 21:52:13 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 690/1251] eta: 0:05:56 lr: 0.000224 loss: 2.9976 (3.0029) grad_norm: 2.0446 (2.0889) time: 0.6234 [2021-03-27 21:52:20 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 700/1251] eta: 0:05:50 lr: 0.000224 loss: 3.1455 (3.0053) grad_norm: 2.0908 (2.0910) time: 0.6212 [2021-03-27 21:52:26 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 710/1251] eta: 0:05:43 lr: 0.000224 loss: 3.1913 (3.0064) grad_norm: 2.0680 (2.0908) time: 0.6233 [2021-03-27 21:52:32 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 720/1251] eta: 0:05:37 lr: 0.000224 loss: 3.1378 (3.0068) grad_norm: 2.0321 (2.0926) time: 0.6250 [2021-03-27 21:52:38 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 730/1251] eta: 0:05:30 lr: 0.000224 loss: 2.9361 (3.0057) grad_norm: 2.1755 (2.0932) time: 0.6281 [2021-03-27 21:52:45 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 740/1251] eta: 0:05:24 lr: 0.000224 loss: 2.9361 (3.0065) grad_norm: 2.0765 (2.0925) time: 0.6307 [2021-03-27 21:52:51 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 750/1251] eta: 0:05:18 lr: 0.000224 loss: 2.9091 (3.0017) grad_norm: 1.9676 (2.0917) time: 0.6358 [2021-03-27 21:52:57 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 760/1251] eta: 0:05:11 lr: 0.000224 loss: 2.9870 (3.0042) grad_norm: 2.1091 (2.0954) time: 0.6340 [2021-03-27 21:53:04 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 770/1251] eta: 0:05:05 lr: 0.000224 loss: 3.0581 (3.0047) grad_norm: 2.1497 (2.0952) time: 0.6270 [2021-03-27 21:53:10 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 780/1251] eta: 0:04:59 lr: 0.000224 loss: 3.1611 (3.0072) grad_norm: 2.1133 (2.0958) time: 0.6259 [2021-03-27 21:53:16 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 790/1251] eta: 0:04:52 lr: 0.000224 loss: 3.2087 (3.0061) grad_norm: 2.1133 (2.0962) time: 0.6301 [2021-03-27 21:53:23 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 800/1251] eta: 0:04:46 lr: 0.000224 loss: 3.1676 (3.0054) grad_norm: 1.9831 (2.0954) time: 0.6318 [2021-03-27 21:53:29 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 810/1251] eta: 0:04:39 lr: 0.000224 loss: 3.2363 (3.0075) grad_norm: 2.0159 (2.0953) time: 0.6305 [2021-03-27 21:53:35 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 820/1251] eta: 0:04:33 lr: 0.000224 loss: 3.3325 (3.0106) grad_norm: 2.0503 (2.0971) time: 0.6313 [2021-03-27 21:53:42 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 830/1251] eta: 0:04:27 lr: 0.000224 loss: 3.0995 (3.0086) grad_norm: 2.0496 (2.0980) time: 0.6344 [2021-03-27 21:53:48 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 840/1251] eta: 0:04:20 lr: 0.000224 loss: 2.9197 (3.0062) grad_norm: 1.9199 (2.0972) time: 0.6283 [2021-03-27 21:53:54 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 850/1251] eta: 0:04:14 lr: 0.000224 loss: 2.9512 (3.0053) grad_norm: 1.9173 (2.0973) time: 0.6204 [2021-03-27 21:54:00 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 860/1251] eta: 0:04:07 lr: 0.000224 loss: 3.0222 (3.0058) grad_norm: 1.9048 (2.0947) time: 0.6201 [2021-03-27 21:54:07 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 870/1251] eta: 0:04:01 lr: 0.000224 loss: 2.9888 (3.0031) grad_norm: 1.9404 (2.0957) time: 0.6254 [2021-03-27 21:54:13 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 880/1251] eta: 0:03:55 lr: 0.000224 loss: 3.0525 (3.0052) grad_norm: 1.9555 (2.0953) time: 0.6317 [2021-03-27 21:54:19 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 890/1251] eta: 0:03:48 lr: 0.000224 loss: 3.1819 (3.0039) grad_norm: 1.9632 (2.0950) time: 0.6328 [2021-03-27 21:54:26 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 900/1251] eta: 0:03:42 lr: 0.000224 loss: 2.8878 (3.0019) grad_norm: 2.0954 (2.0955) time: 0.6321 [2021-03-27 21:54:32 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 910/1251] eta: 0:03:36 lr: 0.000224 loss: 2.9946 (3.0044) grad_norm: 2.1127 (2.0961) time: 0.6272 [2021-03-27 21:54:38 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 920/1251] eta: 0:03:29 lr: 0.000224 loss: 3.3310 (3.0079) grad_norm: 2.1507 (2.0994) time: 0.6256 [2021-03-27 21:54:44 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 930/1251] eta: 0:03:23 lr: 0.000224 loss: 3.2811 (3.0091) grad_norm: 2.2112 (2.1038) time: 0.6308 [2021-03-27 21:54:51 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 940/1251] eta: 0:03:17 lr: 0.000224 loss: 2.9087 (3.0091) grad_norm: 2.1103 (2.1042) time: 0.6350 [2021-03-27 21:54:57 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 950/1251] eta: 0:03:10 lr: 0.000224 loss: 3.0054 (3.0081) grad_norm: 2.0889 (2.1052) time: 0.6294 [2021-03-27 21:55:03 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 960/1251] eta: 0:03:04 lr: 0.000223 loss: 3.0397 (3.0094) grad_norm: 2.0747 (2.1077) time: 0.6245 [2021-03-27 21:55:10 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 970/1251] eta: 0:02:58 lr: 0.000223 loss: 3.1313 (3.0088) grad_norm: 2.1011 (2.1080) time: 0.6269 [2021-03-27 21:55:16 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 980/1251] eta: 0:02:51 lr: 0.000223 loss: 3.1008 (3.0087) grad_norm: 2.0774 (2.1080) time: 0.6298 [2021-03-27 21:55:22 swin_base_patch4_window7_224] INFO: Epoch: [207] [ 990/1251] eta: 0:02:45 lr: 0.000223 loss: 3.2653 (3.0121) grad_norm: 1.9975 (2.1082) time: 0.6260 [2021-03-27 21:55:28 swin_base_patch4_window7_224] INFO: Epoch: [207] [1000/1251] eta: 0:02:38 lr: 0.000223 loss: 3.2569 (3.0119) grad_norm: 2.0687 (2.1091) time: 0.6247 [2021-03-27 21:55:35 swin_base_patch4_window7_224] INFO: Epoch: [207] [1010/1251] eta: 0:02:32 lr: 0.000223 loss: 3.1376 (3.0132) grad_norm: 2.1586 (2.1103) time: 0.6322 [2021-03-27 21:55:41 swin_base_patch4_window7_224] INFO: Epoch: [207] [1020/1251] eta: 0:02:26 lr: 0.000223 loss: 3.0634 (3.0129) grad_norm: 2.1586 (2.1099) time: 0.6380 [2021-03-27 21:55:47 swin_base_patch4_window7_224] INFO: Epoch: [207] [1030/1251] eta: 0:02:19 lr: 0.000223 loss: 3.0260 (3.0133) grad_norm: 2.1363 (2.1099) time: 0.6314 [2021-03-27 21:55:54 swin_base_patch4_window7_224] INFO: Epoch: [207] [1040/1251] eta: 0:02:13 lr: 0.000223 loss: 3.1295 (3.0131) grad_norm: 2.0860 (2.1098) time: 0.6247 [2021-03-27 21:56:00 swin_base_patch4_window7_224] INFO: Epoch: [207] [1050/1251] eta: 0:02:07 lr: 0.000223 loss: 2.9826 (3.0117) grad_norm: 2.0607 (2.1095) time: 0.6242 [2021-03-27 21:56:06 swin_base_patch4_window7_224] INFO: Epoch: [207] [1060/1251] eta: 0:02:00 lr: 0.000223 loss: 2.8595 (3.0110) grad_norm: 2.0607 (2.1096) time: 0.6280 [2021-03-27 21:56:12 swin_base_patch4_window7_224] INFO: Epoch: [207] [1070/1251] eta: 0:01:54 lr: 0.000223 loss: 3.1812 (3.0143) grad_norm: 2.0608 (2.1101) time: 0.6298 [2021-03-27 21:56:19 swin_base_patch4_window7_224] INFO: Epoch: [207] [1080/1251] eta: 0:01:48 lr: 0.000223 loss: 3.2635 (3.0170) grad_norm: 2.0271 (2.1119) time: 0.6235 [2021-03-27 21:56:25 swin_base_patch4_window7_224] INFO: Epoch: [207] [1090/1251] eta: 0:01:41 lr: 0.000223 loss: 3.2166 (3.0162) grad_norm: 2.0271 (2.1117) time: 0.6235 [2021-03-27 21:56:31 swin_base_patch4_window7_224] INFO: Epoch: [207] [1100/1251] eta: 0:01:35 lr: 0.000223 loss: 3.1701 (3.0179) grad_norm: 2.0537 (2.1117) time: 0.6270 [2021-03-27 21:56:37 swin_base_patch4_window7_224] INFO: Epoch: [207] [1110/1251] eta: 0:01:29 lr: 0.000223 loss: 3.0339 (3.0181) grad_norm: 2.0786 (2.1118) time: 0.6239 [2021-03-27 21:56:44 swin_base_patch4_window7_224] INFO: Epoch: [207] [1120/1251] eta: 0:01:22 lr: 0.000223 loss: 2.9787 (3.0173) grad_norm: 1.9889 (2.1100) time: 0.6243 [2021-03-27 21:56:50 swin_base_patch4_window7_224] INFO: Epoch: [207] [1130/1251] eta: 0:01:16 lr: 0.000223 loss: 3.0689 (3.0164) grad_norm: 1.9446 (2.1096) time: 0.6252 [2021-03-27 21:56:56 swin_base_patch4_window7_224] INFO: Epoch: [207] [1140/1251] eta: 0:01:10 lr: 0.000223 loss: 2.8461 (3.0142) grad_norm: 2.0375 (2.1132) time: 0.6207 [2021-03-27 21:57:02 swin_base_patch4_window7_224] INFO: Epoch: [207] [1150/1251] eta: 0:01:03 lr: 0.000223 loss: 2.7604 (3.0130) grad_norm: 2.1247 (2.1143) time: 0.6210 [2021-03-27 21:57:09 swin_base_patch4_window7_224] INFO: Epoch: [207] [1160/1251] eta: 0:00:57 lr: 0.000223 loss: 3.0625 (3.0131) grad_norm: 2.0417 (2.1135) time: 0.6225 [2021-03-27 21:57:15 swin_base_patch4_window7_224] INFO: Epoch: [207] [1170/1251] eta: 0:00:51 lr: 0.000223 loss: 3.0665 (3.0136) grad_norm: 1.9950 (2.1134) time: 0.6238 [2021-03-27 21:57:21 swin_base_patch4_window7_224] INFO: Epoch: [207] [1180/1251] eta: 0:00:44 lr: 0.000223 loss: 3.0665 (3.0133) grad_norm: 2.1052 (inf) time: 0.6203 [2021-03-27 21:57:27 swin_base_patch4_window7_224] INFO: Epoch: [207] [1190/1251] eta: 0:00:38 lr: 0.000223 loss: 3.0888 (3.0142) grad_norm: 2.0922 (inf) time: 0.6209 [2021-03-27 21:57:34 swin_base_patch4_window7_224] INFO: Epoch: [207] [1200/1251] eta: 0:00:32 lr: 0.000223 loss: 3.0888 (3.0132) grad_norm: 2.0492 (inf) time: 0.6309 [2021-03-27 21:57:40 swin_base_patch4_window7_224] INFO: Epoch: [207] [1210/1251] eta: 0:00:25 lr: 0.000223 loss: 3.1095 (3.0143) grad_norm: 2.1329 (inf) time: 0.6321 [2021-03-27 21:57:46 swin_base_patch4_window7_224] INFO: Epoch: [207] [1220/1251] eta: 0:00:19 lr: 0.000223 loss: 3.1534 (3.0137) grad_norm: 2.1329 (inf) time: 0.6277 [2021-03-27 21:57:52 swin_base_patch4_window7_224] INFO: Epoch: [207] [1230/1251] eta: 0:00:13 lr: 0.000223 loss: 2.8616 (3.0124) grad_norm: 1.9777 (inf) time: 0.6282 [2021-03-27 21:57:59 swin_base_patch4_window7_224] INFO: Epoch: [207] [1240/1251] eta: 0:00:06 lr: 0.000223 loss: 2.9688 (3.0118) grad_norm: 2.0629 (inf) time: 0.6249 [2021-03-27 21:58:05 swin_base_patch4_window7_224] INFO: Epoch: [207] [1250/1251] eta: 0:00:00 lr: 0.000223 loss: 3.0374 (3.0128) grad_norm: 2.0264 (inf) time: 0.6196 [2021-03-27 21:58:14 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:14 loss: 0.9188 (0.9188) acc1: 78.1250 (78.1250) acc5: 96.8750 (96.8750) [2021-03-27 21:58:17 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.9188 (0.9519) acc1: 76.5625 (77.9830) acc5: 96.8750 (94.7443) [2021-03-27 21:58:19 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8747 (0.8929) acc1: 76.5625 (79.0923) acc5: 95.3125 (94.9405) [2021-03-27 21:58:21 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8681 (0.8769) acc1: 79.6875 (79.4355) acc5: 95.3125 (95.0101) [2021-03-27 21:58:23 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7235 (0.8333) acc1: 81.2500 (80.2210) acc5: 96.8750 (95.5793) [2021-03-27 21:58:24 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7629 (0.8229) acc1: 81.2500 (80.5120) acc5: 96.8750 (95.5840) [2021-03-27 21:58:35 swin_base_patch4_window7_224] INFO: * Acc@1 81.540 Acc@5 95.738 loss 0.801 [2021-03-27 21:58:35 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.5% [2021-03-27 21:58:35 swin_base_patch4_window7_224] INFO: Max accuracy: 81.54% [2021-03-27 21:58:39 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 0/1251] eta: 1:32:11 lr: 0.000222 loss: 3.1534 (3.1534) grad_norm: 2.6885 (2.6885) time: 4.4214 [2021-03-27 21:58:46 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 10/1251] eta: 0:20:27 lr: 0.000222 loss: 3.1429 (3.1156) grad_norm: 2.0892 (2.1575) time: 0.9889 [2021-03-27 21:58:52 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 20/1251] eta: 0:16:47 lr: 0.000222 loss: 2.7904 (2.9514) grad_norm: 2.0335 (2.1490) time: 0.6384 [2021-03-27 21:58:58 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 30/1251] eta: 0:15:22 lr: 0.000222 loss: 2.7733 (2.9443) grad_norm: 1.9667 (2.1136) time: 0.6277 [2021-03-27 21:59:05 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 40/1251] eta: 0:14:37 lr: 0.000222 loss: 3.1504 (2.9499) grad_norm: 2.0641 (2.1803) time: 0.6260 [2021-03-27 21:59:11 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 50/1251] eta: 0:14:09 lr: 0.000222 loss: 3.2238 (2.9815) grad_norm: 2.0641 (2.1790) time: 0.6326 [2021-03-27 21:59:17 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 60/1251] eta: 0:13:46 lr: 0.000222 loss: 3.1958 (2.9734) grad_norm: 2.0887 (2.1762) time: 0.6322 [2021-03-27 21:59:24 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 70/1251] eta: 0:13:27 lr: 0.000222 loss: 3.2086 (3.0232) grad_norm: 1.9846 (2.1602) time: 0.6243 [2021-03-27 21:59:30 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 80/1251] eta: 0:13:13 lr: 0.000222 loss: 3.2550 (3.0376) grad_norm: 1.9812 (2.1405) time: 0.6275 [2021-03-27 21:59:36 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 90/1251] eta: 0:13:00 lr: 0.000222 loss: 3.1352 (3.0063) grad_norm: 1.9987 (2.2619) time: 0.6294 [2021-03-27 21:59:42 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 100/1251] eta: 0:12:48 lr: 0.000222 loss: 3.1352 (3.0138) grad_norm: 2.1071 (2.2438) time: 0.6247 [2021-03-27 21:59:49 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 110/1251] eta: 0:12:37 lr: 0.000222 loss: 3.1299 (3.0013) grad_norm: 2.0852 (2.2320) time: 0.6243 [2021-03-27 21:59:55 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 120/1251] eta: 0:12:27 lr: 0.000222 loss: 2.8733 (2.9999) grad_norm: 2.0990 (2.2300) time: 0.6279 [2021-03-27 22:00:01 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 130/1251] eta: 0:12:17 lr: 0.000222 loss: 2.9845 (3.0005) grad_norm: 2.1204 (2.2337) time: 0.6277 [2021-03-27 22:00:08 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 140/1251] eta: 0:12:08 lr: 0.000222 loss: 3.0423 (3.0068) grad_norm: 2.1976 (2.2306) time: 0.6277 [2021-03-27 22:00:14 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 150/1251] eta: 0:12:00 lr: 0.000222 loss: 2.9139 (2.9931) grad_norm: 2.0197 (2.2159) time: 0.6291 [2021-03-27 22:00:20 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 160/1251] eta: 0:11:51 lr: 0.000222 loss: 3.0355 (3.0034) grad_norm: 2.0332 (2.2187) time: 0.6255 [2021-03-27 22:00:26 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 170/1251] eta: 0:11:42 lr: 0.000222 loss: 3.0751 (3.0145) grad_norm: 1.9861 (2.2023) time: 0.6207 [2021-03-27 22:00:33 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 180/1251] eta: 0:11:35 lr: 0.000222 loss: 3.0751 (3.0198) grad_norm: 1.9286 (2.1992) time: 0.6283 [2021-03-27 22:00:39 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 190/1251] eta: 0:11:27 lr: 0.000222 loss: 3.1200 (3.0094) grad_norm: 2.0450 (2.1897) time: 0.6306 [2021-03-27 22:00:45 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 200/1251] eta: 0:11:20 lr: 0.000222 loss: 3.1114 (3.0062) grad_norm: 1.9633 (2.1786) time: 0.6307 [2021-03-27 22:00:52 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 210/1251] eta: 0:11:13 lr: 0.000222 loss: 3.2093 (3.0030) grad_norm: 1.9574 (2.1797) time: 0.6344 [2021-03-27 22:00:58 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 220/1251] eta: 0:11:06 lr: 0.000222 loss: 3.0469 (3.0048) grad_norm: 2.0722 (2.1810) time: 0.6332 [2021-03-27 22:01:04 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 230/1251] eta: 0:10:59 lr: 0.000222 loss: 3.0337 (3.0015) grad_norm: 1.9711 (2.1709) time: 0.6344 [2021-03-27 22:01:11 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 240/1251] eta: 0:10:52 lr: 0.000222 loss: 3.0874 (3.0039) grad_norm: 1.9602 (2.1659) time: 0.6304 [2021-03-27 22:01:17 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 250/1251] eta: 0:10:45 lr: 0.000222 loss: 3.0017 (2.9864) grad_norm: 2.0675 (2.1604) time: 0.6309 [2021-03-27 22:01:23 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 260/1251] eta: 0:10:37 lr: 0.000222 loss: 2.7449 (2.9851) grad_norm: 2.0853 (2.1576) time: 0.6273 [2021-03-27 22:01:29 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 270/1251] eta: 0:10:31 lr: 0.000222 loss: 3.1056 (2.9898) grad_norm: 2.0200 (2.1509) time: 0.6269 [2021-03-27 22:01:36 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 280/1251] eta: 0:10:24 lr: 0.000222 loss: 3.1907 (2.9928) grad_norm: 1.9368 (2.1458) time: 0.6310 [2021-03-27 22:01:42 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 290/1251] eta: 0:10:17 lr: 0.000222 loss: 3.1907 (2.9959) grad_norm: 2.0550 (2.1504) time: 0.6256 [2021-03-27 22:01:48 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 300/1251] eta: 0:10:10 lr: 0.000221 loss: 3.1920 (2.9978) grad_norm: 2.0550 (2.1468) time: 0.6238 [2021-03-27 22:01:55 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 310/1251] eta: 0:10:03 lr: 0.000221 loss: 3.1650 (2.9980) grad_norm: 1.9081 (2.1424) time: 0.6283 [2021-03-27 22:02:01 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 320/1251] eta: 0:09:56 lr: 0.000221 loss: 3.1767 (3.0002) grad_norm: 1.9918 (2.1449) time: 0.6307 [2021-03-27 22:02:07 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 330/1251] eta: 0:09:49 lr: 0.000221 loss: 3.1375 (3.0011) grad_norm: 2.1684 (2.1463) time: 0.6265 [2021-03-27 22:02:13 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 340/1251] eta: 0:09:43 lr: 0.000221 loss: 3.0106 (2.9992) grad_norm: 2.2854 (2.1520) time: 0.6254 [2021-03-27 22:02:20 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 350/1251] eta: 0:09:36 lr: 0.000221 loss: 3.0871 (3.0030) grad_norm: 2.2505 (2.1542) time: 0.6301 [2021-03-27 22:02:26 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 360/1251] eta: 0:09:29 lr: 0.000221 loss: 3.0391 (2.9976) grad_norm: 2.1221 (2.1520) time: 0.6276 [2021-03-27 22:02:32 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 370/1251] eta: 0:09:22 lr: 0.000221 loss: 2.8294 (2.9922) grad_norm: 1.9833 (2.1505) time: 0.6229 [2021-03-27 22:02:38 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 380/1251] eta: 0:09:16 lr: 0.000221 loss: 3.0870 (2.9985) grad_norm: 2.1303 (2.1529) time: 0.6214 [2021-03-27 22:02:45 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 390/1251] eta: 0:09:09 lr: 0.000221 loss: 3.0205 (2.9937) grad_norm: 2.1948 (2.1584) time: 0.6223 [2021-03-27 22:02:51 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 400/1251] eta: 0:09:02 lr: 0.000221 loss: 2.8506 (2.9922) grad_norm: 2.1400 (2.1663) time: 0.6258 [2021-03-27 22:02:57 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 410/1251] eta: 0:08:56 lr: 0.000221 loss: 3.0377 (2.9913) grad_norm: 2.1400 (2.1714) time: 0.6271 [2021-03-27 22:03:03 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 420/1251] eta: 0:08:49 lr: 0.000221 loss: 3.0658 (2.9924) grad_norm: 2.1520 (2.1764) time: 0.6300 [2021-03-27 22:03:10 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 430/1251] eta: 0:08:43 lr: 0.000221 loss: 3.1094 (2.9910) grad_norm: 2.1063 (2.1774) time: 0.6289 [2021-03-27 22:03:16 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 440/1251] eta: 0:08:36 lr: 0.000221 loss: 2.9536 (2.9908) grad_norm: 2.0183 (2.1725) time: 0.6290 [2021-03-27 22:03:22 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 450/1251] eta: 0:08:29 lr: 0.000221 loss: 3.0773 (2.9947) grad_norm: 1.9926 (2.1685) time: 0.6280 [2021-03-27 22:03:28 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 460/1251] eta: 0:08:23 lr: 0.000221 loss: 3.1658 (2.9949) grad_norm: 1.9973 (2.1673) time: 0.6216 [2021-03-27 22:03:35 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 470/1251] eta: 0:08:16 lr: 0.000221 loss: 3.1658 (2.9950) grad_norm: 1.9241 (2.1624) time: 0.6232 [2021-03-27 22:03:41 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 480/1251] eta: 0:08:10 lr: 0.000221 loss: 3.0499 (2.9960) grad_norm: 1.8971 (2.1598) time: 0.6263 [2021-03-27 22:03:47 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 490/1251] eta: 0:08:03 lr: 0.000221 loss: 2.9238 (2.9954) grad_norm: 2.0162 (2.1619) time: 0.6296 [2021-03-27 22:03:54 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 500/1251] eta: 0:07:57 lr: 0.000221 loss: 3.0521 (2.9962) grad_norm: 2.2845 (2.1628) time: 0.6279 [2021-03-27 22:04:00 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 510/1251] eta: 0:07:50 lr: 0.000221 loss: 3.1197 (2.9992) grad_norm: 2.2845 (2.1665) time: 0.6248 [2021-03-27 22:04:06 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 520/1251] eta: 0:07:44 lr: 0.000221 loss: 3.1640 (3.0009) grad_norm: 2.1026 (2.1628) time: 0.6255 [2021-03-27 22:04:12 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 530/1251] eta: 0:07:37 lr: 0.000221 loss: 3.0476 (2.9954) grad_norm: 2.1026 (2.1639) time: 0.6225 [2021-03-27 22:04:19 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 540/1251] eta: 0:07:31 lr: 0.000221 loss: 3.0837 (2.9971) grad_norm: 2.2368 (2.1638) time: 0.6240 [2021-03-27 22:04:25 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 550/1251] eta: 0:07:25 lr: 0.000221 loss: 3.1253 (2.9928) grad_norm: 2.1213 (2.1640) time: 0.6349 [2021-03-27 22:04:31 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 560/1251] eta: 0:07:18 lr: 0.000221 loss: 3.1872 (2.9951) grad_norm: 2.0632 (2.1639) time: 0.6385 [2021-03-27 22:04:38 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 570/1251] eta: 0:07:12 lr: 0.000221 loss: 3.2187 (2.9942) grad_norm: 2.1288 (2.1641) time: 0.6310 [2021-03-27 22:04:44 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 580/1251] eta: 0:07:05 lr: 0.000221 loss: 3.0488 (2.9960) grad_norm: 2.1797 (2.1645) time: 0.6310 [2021-03-27 22:04:50 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 590/1251] eta: 0:06:59 lr: 0.000220 loss: 2.9896 (2.9949) grad_norm: 2.1515 (2.1653) time: 0.6301 [2021-03-27 22:04:57 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 600/1251] eta: 0:06:53 lr: 0.000220 loss: 3.0236 (2.9968) grad_norm: 2.1655 (2.1672) time: 0.6309 [2021-03-27 22:05:03 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 610/1251] eta: 0:06:46 lr: 0.000220 loss: 3.0082 (2.9932) grad_norm: 2.0520 (2.1646) time: 0.6310 [2021-03-27 22:05:09 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 620/1251] eta: 0:06:40 lr: 0.000220 loss: 3.0082 (2.9941) grad_norm: 2.0049 (2.1644) time: 0.6269 [2021-03-27 22:05:15 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 630/1251] eta: 0:06:33 lr: 0.000220 loss: 3.0474 (2.9913) grad_norm: 2.0215 (2.1651) time: 0.6254 [2021-03-27 22:05:22 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 640/1251] eta: 0:06:27 lr: 0.000220 loss: 2.8347 (2.9934) grad_norm: 2.0869 (inf) time: 0.6223 [2021-03-27 22:05:28 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 650/1251] eta: 0:06:20 lr: 0.000220 loss: 2.9862 (2.9927) grad_norm: 2.1195 (inf) time: 0.6228 [2021-03-27 22:05:34 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 660/1251] eta: 0:06:14 lr: 0.000220 loss: 2.9235 (2.9893) grad_norm: 2.0621 (inf) time: 0.6249 [2021-03-27 22:05:40 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 670/1251] eta: 0:06:08 lr: 0.000220 loss: 3.0612 (2.9935) grad_norm: 2.0621 (inf) time: 0.6235 [2021-03-27 22:05:47 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 680/1251] eta: 0:06:01 lr: 0.000220 loss: 3.0695 (2.9932) grad_norm: 2.1638 (inf) time: 0.6247 [2021-03-27 22:05:53 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 690/1251] eta: 0:05:55 lr: 0.000220 loss: 2.9674 (2.9914) grad_norm: 2.1553 (inf) time: 0.6309 [2021-03-27 22:05:59 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 700/1251] eta: 0:05:48 lr: 0.000220 loss: 2.9674 (2.9928) grad_norm: 2.0725 (inf) time: 0.6262 [2021-03-27 22:06:05 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 710/1251] eta: 0:05:42 lr: 0.000220 loss: 3.1209 (2.9934) grad_norm: 2.0634 (inf) time: 0.6217 [2021-03-27 22:06:12 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 720/1251] eta: 0:05:36 lr: 0.000220 loss: 3.0417 (2.9922) grad_norm: 2.0550 (inf) time: 0.6270 [2021-03-27 22:06:18 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 730/1251] eta: 0:05:29 lr: 0.000220 loss: 2.8658 (2.9889) grad_norm: 1.9584 (inf) time: 0.6286 [2021-03-27 22:06:24 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 740/1251] eta: 0:05:23 lr: 0.000220 loss: 2.8499 (2.9874) grad_norm: 2.1884 (inf) time: 0.6283 [2021-03-27 22:06:31 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 750/1251] eta: 0:05:17 lr: 0.000220 loss: 3.0840 (2.9883) grad_norm: 2.1553 (inf) time: 0.6374 [2021-03-27 22:06:37 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 760/1251] eta: 0:05:10 lr: 0.000220 loss: 3.2333 (2.9915) grad_norm: 2.0321 (inf) time: 0.6351 [2021-03-27 22:06:43 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 770/1251] eta: 0:05:04 lr: 0.000220 loss: 3.3134 (2.9931) grad_norm: 2.0321 (inf) time: 0.6260 [2021-03-27 22:06:49 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 780/1251] eta: 0:04:58 lr: 0.000220 loss: 3.2927 (2.9922) grad_norm: 2.2084 (inf) time: 0.6284 [2021-03-27 22:06:56 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 790/1251] eta: 0:04:51 lr: 0.000220 loss: 2.8898 (2.9911) grad_norm: 2.0769 (inf) time: 0.6314 [2021-03-27 22:07:02 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 800/1251] eta: 0:04:45 lr: 0.000220 loss: 2.9057 (2.9920) grad_norm: 2.1636 (inf) time: 0.6355 [2021-03-27 22:07:09 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 810/1251] eta: 0:04:39 lr: 0.000220 loss: 3.0963 (2.9911) grad_norm: 2.2508 (inf) time: 0.6368 [2021-03-27 22:07:15 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 820/1251] eta: 0:04:32 lr: 0.000220 loss: 3.0059 (2.9904) grad_norm: 2.1141 (inf) time: 0.6362 [2021-03-27 22:07:21 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 830/1251] eta: 0:04:26 lr: 0.000220 loss: 2.9537 (2.9884) grad_norm: 2.0343 (inf) time: 0.6316 [2021-03-27 22:07:27 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 840/1251] eta: 0:04:20 lr: 0.000220 loss: 2.9726 (2.9881) grad_norm: 2.0668 (inf) time: 0.6258 [2021-03-27 22:07:34 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 850/1251] eta: 0:04:13 lr: 0.000220 loss: 3.0878 (2.9902) grad_norm: 2.1023 (inf) time: 0.6262 [2021-03-27 22:07:40 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 860/1251] eta: 0:04:07 lr: 0.000220 loss: 3.0525 (2.9883) grad_norm: 2.0979 (inf) time: 0.6317 [2021-03-27 22:07:46 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 870/1251] eta: 0:04:01 lr: 0.000220 loss: 2.6011 (2.9850) grad_norm: 2.0818 (inf) time: 0.6381 [2021-03-27 22:07:53 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 880/1251] eta: 0:03:54 lr: 0.000220 loss: 2.9737 (2.9857) grad_norm: 2.0305 (inf) time: 0.6346 [2021-03-27 22:07:59 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 890/1251] eta: 0:03:48 lr: 0.000219 loss: 3.1285 (2.9866) grad_norm: 2.0459 (inf) time: 0.6281 [2021-03-27 22:08:05 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 900/1251] eta: 0:03:42 lr: 0.000219 loss: 3.1656 (2.9872) grad_norm: 2.0490 (inf) time: 0.6253 [2021-03-27 22:08:12 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 910/1251] eta: 0:03:35 lr: 0.000219 loss: 3.0118 (2.9864) grad_norm: 2.0405 (inf) time: 0.6268 [2021-03-27 22:08:18 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 920/1251] eta: 0:03:29 lr: 0.000219 loss: 3.0118 (2.9890) grad_norm: 2.1685 (inf) time: 0.6323 [2021-03-27 22:08:24 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 930/1251] eta: 0:03:23 lr: 0.000219 loss: 3.1980 (2.9886) grad_norm: 2.1685 (inf) time: 0.6330 [2021-03-27 22:08:30 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 940/1251] eta: 0:03:16 lr: 0.000219 loss: 3.1892 (2.9877) grad_norm: 2.0021 (inf) time: 0.6279 [2021-03-27 22:08:37 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 950/1251] eta: 0:03:10 lr: 0.000219 loss: 3.1892 (2.9873) grad_norm: 2.0021 (inf) time: 0.6316 [2021-03-27 22:08:43 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 960/1251] eta: 0:03:04 lr: 0.000219 loss: 2.8954 (2.9862) grad_norm: 2.0368 (inf) time: 0.6361 [2021-03-27 22:08:50 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 970/1251] eta: 0:02:57 lr: 0.000219 loss: 3.0251 (2.9877) grad_norm: 2.2107 (inf) time: 0.6348 [2021-03-27 22:08:56 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 980/1251] eta: 0:02:51 lr: 0.000219 loss: 2.9036 (2.9841) grad_norm: 2.1690 (inf) time: 0.6291 [2021-03-27 22:09:02 swin_base_patch4_window7_224] INFO: Epoch: [208] [ 990/1251] eta: 0:02:45 lr: 0.000219 loss: 2.7073 (2.9849) grad_norm: 2.1544 (inf) time: 0.6217 [2021-03-27 22:09:08 swin_base_patch4_window7_224] INFO: Epoch: [208] [1000/1251] eta: 0:02:38 lr: 0.000219 loss: 3.1496 (2.9861) grad_norm: 2.1795 (inf) time: 0.6260 [2021-03-27 22:09:15 swin_base_patch4_window7_224] INFO: Epoch: [208] [1010/1251] eta: 0:02:32 lr: 0.000219 loss: 3.0356 (2.9864) grad_norm: 1.9879 (inf) time: 0.6274 [2021-03-27 22:09:21 swin_base_patch4_window7_224] INFO: Epoch: [208] [1020/1251] eta: 0:02:26 lr: 0.000219 loss: 2.9933 (2.9863) grad_norm: 1.9552 (inf) time: 0.6244 [2021-03-27 22:09:27 swin_base_patch4_window7_224] INFO: Epoch: [208] [1030/1251] eta: 0:02:19 lr: 0.000219 loss: 2.9933 (2.9860) grad_norm: 2.1121 (inf) time: 0.6243 [2021-03-27 22:09:33 swin_base_patch4_window7_224] INFO: Epoch: [208] [1040/1251] eta: 0:02:13 lr: 0.000219 loss: 2.9938 (2.9873) grad_norm: 2.0887 (inf) time: 0.6227 [2021-03-27 22:09:39 swin_base_patch4_window7_224] INFO: Epoch: [208] [1050/1251] eta: 0:02:07 lr: 0.000219 loss: 3.0143 (2.9867) grad_norm: 2.0692 (inf) time: 0.6214 [2021-03-27 22:09:46 swin_base_patch4_window7_224] INFO: Epoch: [208] [1060/1251] eta: 0:02:00 lr: 0.000219 loss: 3.0981 (2.9884) grad_norm: 2.0692 (inf) time: 0.6237 [2021-03-27 22:09:52 swin_base_patch4_window7_224] INFO: Epoch: [208] [1070/1251] eta: 0:01:54 lr: 0.000219 loss: 3.0956 (2.9881) grad_norm: 2.1349 (inf) time: 0.6259 [2021-03-27 22:09:58 swin_base_patch4_window7_224] INFO: Epoch: [208] [1080/1251] eta: 0:01:48 lr: 0.000219 loss: 2.9462 (2.9882) grad_norm: 2.1424 (inf) time: 0.6276 [2021-03-27 22:10:05 swin_base_patch4_window7_224] INFO: Epoch: [208] [1090/1251] eta: 0:01:41 lr: 0.000219 loss: 2.9740 (2.9883) grad_norm: 2.1424 (inf) time: 0.6280 [2021-03-27 22:10:11 swin_base_patch4_window7_224] INFO: Epoch: [208] [1100/1251] eta: 0:01:35 lr: 0.000219 loss: 3.0163 (2.9881) grad_norm: 2.1303 (inf) time: 0.6249 [2021-03-27 22:10:17 swin_base_patch4_window7_224] INFO: Epoch: [208] [1110/1251] eta: 0:01:29 lr: 0.000219 loss: 2.8658 (2.9871) grad_norm: 2.1150 (inf) time: 0.6241 [2021-03-27 22:10:23 swin_base_patch4_window7_224] INFO: Epoch: [208] [1120/1251] eta: 0:01:22 lr: 0.000219 loss: 3.1134 (2.9886) grad_norm: 2.2244 (inf) time: 0.6249 [2021-03-27 22:10:30 swin_base_patch4_window7_224] INFO: Epoch: [208] [1130/1251] eta: 0:01:16 lr: 0.000219 loss: 3.1249 (2.9902) grad_norm: 2.0024 (inf) time: 0.6284 [2021-03-27 22:10:36 swin_base_patch4_window7_224] INFO: Epoch: [208] [1140/1251] eta: 0:01:10 lr: 0.000219 loss: 3.1268 (2.9908) grad_norm: 1.9519 (inf) time: 0.6360 [2021-03-27 22:10:42 swin_base_patch4_window7_224] INFO: Epoch: [208] [1150/1251] eta: 0:01:03 lr: 0.000219 loss: 3.0936 (2.9884) grad_norm: 2.0140 (inf) time: 0.6323 [2021-03-27 22:10:49 swin_base_patch4_window7_224] INFO: Epoch: [208] [1160/1251] eta: 0:00:57 lr: 0.000219 loss: 2.9887 (2.9890) grad_norm: 2.0929 (inf) time: 0.6275 [2021-03-27 22:10:55 swin_base_patch4_window7_224] INFO: Epoch: [208] [1170/1251] eta: 0:00:51 lr: 0.000219 loss: 2.9448 (2.9878) grad_norm: 2.0929 (inf) time: 0.6272 [2021-03-27 22:11:01 swin_base_patch4_window7_224] INFO: Epoch: [208] [1180/1251] eta: 0:00:44 lr: 0.000218 loss: 2.9374 (2.9878) grad_norm: 2.0316 (inf) time: 0.6229 [2021-03-27 22:11:07 swin_base_patch4_window7_224] INFO: Epoch: [208] [1190/1251] eta: 0:00:38 lr: 0.000218 loss: 3.0839 (2.9895) grad_norm: 2.0343 (inf) time: 0.6271 [2021-03-27 22:11:14 swin_base_patch4_window7_224] INFO: Epoch: [208] [1200/1251] eta: 0:00:32 lr: 0.000218 loss: 3.1682 (2.9905) grad_norm: 2.1758 (inf) time: 0.6340 [2021-03-27 22:11:20 swin_base_patch4_window7_224] INFO: Epoch: [208] [1210/1251] eta: 0:00:25 lr: 0.000218 loss: 3.2250 (2.9922) grad_norm: 2.1642 (inf) time: 0.6327 [2021-03-27 22:11:26 swin_base_patch4_window7_224] INFO: Epoch: [208] [1220/1251] eta: 0:00:19 lr: 0.000218 loss: 3.2289 (2.9929) grad_norm: 2.0740 (inf) time: 0.6286 [2021-03-27 22:11:33 swin_base_patch4_window7_224] INFO: Epoch: [208] [1230/1251] eta: 0:00:13 lr: 0.000218 loss: 3.1745 (2.9947) grad_norm: 2.0740 (inf) time: 0.6232 [2021-03-27 22:11:39 swin_base_patch4_window7_224] INFO: Epoch: [208] [1240/1251] eta: 0:00:06 lr: 0.000218 loss: 3.0552 (2.9939) grad_norm: 2.0525 (inf) time: 0.6166 [2021-03-27 22:11:45 swin_base_patch4_window7_224] INFO: Epoch: [208] [1250/1251] eta: 0:00:00 lr: 0.000218 loss: 3.0455 (2.9940) grad_norm: 2.1938 (inf) time: 0.6195 [2021-03-27 22:11:53 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:31 loss: 0.4842 (0.4842) acc1: 90.6250 (90.6250) acc5: 98.4375 (98.4375) [2021-03-27 22:11:55 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.7554 (0.7326) acc1: 84.3750 (82.6705) acc5: 96.8750 (96.8750) [2021-03-27 22:11:58 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7554 (0.7664) acc1: 81.2500 (82.0685) acc5: 96.8750 (96.2054) [2021-03-27 22:12:00 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7377 (0.7731) acc1: 82.8125 (82.6613) acc5: 95.3125 (96.1190) [2021-03-27 22:12:02 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7462 (0.7739) acc1: 81.2500 (82.1265) acc5: 95.3125 (95.8841) [2021-03-27 22:12:03 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7859 (0.7988) acc1: 79.6875 (81.2480) acc5: 95.3125 (95.7440) [2021-03-27 22:12:14 swin_base_patch4_window7_224] INFO: * Acc@1 81.450 Acc@5 95.828 loss 0.799 [2021-03-27 22:12:14 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.5% [2021-03-27 22:12:14 swin_base_patch4_window7_224] INFO: Max accuracy: 81.54% [2021-03-27 22:12:18 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 0/1251] eta: 1:35:08 lr: 0.000218 loss: 2.9065 (2.9065) grad_norm: 2.2417 (2.2417) time: 4.5632 [2021-03-27 22:12:25 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 10/1251] eta: 0:20:23 lr: 0.000218 loss: 3.1455 (2.9978) grad_norm: 2.0445 (2.1045) time: 0.9861 [2021-03-27 22:12:31 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 20/1251] eta: 0:16:46 lr: 0.000218 loss: 3.1455 (3.0253) grad_norm: 2.0556 (2.1349) time: 0.6306 [2021-03-27 22:12:37 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 30/1251] eta: 0:15:23 lr: 0.000218 loss: 3.0761 (3.0094) grad_norm: 2.1320 (2.1492) time: 0.6299 [2021-03-27 22:12:44 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 40/1251] eta: 0:14:39 lr: 0.000218 loss: 3.0137 (3.0030) grad_norm: 1.9461 (2.1353) time: 0.6302 [2021-03-27 22:12:50 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 50/1251] eta: 0:14:09 lr: 0.000218 loss: 3.0678 (3.0259) grad_norm: 2.0837 (2.1588) time: 0.6309 [2021-03-27 22:12:56 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 60/1251] eta: 0:13:45 lr: 0.000218 loss: 3.1038 (3.0366) grad_norm: 2.1018 (2.1651) time: 0.6243 [2021-03-27 22:13:02 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 70/1251] eta: 0:13:28 lr: 0.000218 loss: 3.1114 (3.0137) grad_norm: 2.0953 (2.1587) time: 0.6264 [2021-03-27 22:13:09 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 80/1251] eta: 0:13:13 lr: 0.000218 loss: 3.0793 (3.0232) grad_norm: 2.1597 (2.1965) time: 0.6300 [2021-03-27 22:13:15 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 90/1251] eta: 0:13:00 lr: 0.000218 loss: 3.0793 (3.0140) grad_norm: 2.1847 (2.2097) time: 0.6285 [2021-03-27 22:13:21 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 100/1251] eta: 0:12:49 lr: 0.000218 loss: 3.2293 (3.0476) grad_norm: 2.0303 (2.1896) time: 0.6324 [2021-03-27 22:13:28 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 110/1251] eta: 0:12:37 lr: 0.000218 loss: 3.1239 (3.0449) grad_norm: 2.0127 (2.1723) time: 0.6279 [2021-03-27 22:13:34 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 120/1251] eta: 0:12:27 lr: 0.000218 loss: 3.0266 (3.0304) grad_norm: 2.0104 (2.1568) time: 0.6254 [2021-03-27 22:13:40 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 130/1251] eta: 0:12:19 lr: 0.000218 loss: 3.1131 (3.0319) grad_norm: 2.0037 (2.1589) time: 0.6324 [2021-03-27 22:13:47 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 140/1251] eta: 0:12:11 lr: 0.000218 loss: 3.3007 (3.0544) grad_norm: 1.9943 (2.1527) time: 0.6421 [2021-03-27 22:13:53 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 150/1251] eta: 0:12:03 lr: 0.000218 loss: 3.1437 (3.0487) grad_norm: 2.0346 (2.1438) time: 0.6437 [2021-03-27 22:13:59 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 160/1251] eta: 0:11:54 lr: 0.000218 loss: 2.7245 (3.0367) grad_norm: 1.9565 (2.1368) time: 0.6307 [2021-03-27 22:14:06 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 170/1251] eta: 0:11:46 lr: 0.000218 loss: 3.0743 (3.0406) grad_norm: 1.9565 (2.1340) time: 0.6246 [2021-03-27 22:14:12 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 180/1251] eta: 0:11:38 lr: 0.000218 loss: 3.0743 (3.0298) grad_norm: 2.0353 (2.1353) time: 0.6294 [2021-03-27 22:14:18 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 190/1251] eta: 0:11:30 lr: 0.000218 loss: 2.9840 (3.0230) grad_norm: 2.1088 (2.1337) time: 0.6311 [2021-03-27 22:14:25 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 200/1251] eta: 0:11:23 lr: 0.000218 loss: 2.9879 (3.0141) grad_norm: 1.9815 (2.1281) time: 0.6308 [2021-03-27 22:14:31 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 210/1251] eta: 0:11:15 lr: 0.000218 loss: 2.8527 (3.0093) grad_norm: 1.9330 (2.1295) time: 0.6261 [2021-03-27 22:14:37 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 220/1251] eta: 0:11:07 lr: 0.000218 loss: 2.8527 (2.9987) grad_norm: 2.1013 (2.1516) time: 0.6210 [2021-03-27 22:14:43 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 230/1251] eta: 0:10:59 lr: 0.000217 loss: 2.9555 (2.9981) grad_norm: 2.1544 (2.1506) time: 0.6211 [2021-03-27 22:14:49 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 240/1251] eta: 0:10:52 lr: 0.000217 loss: 2.8580 (2.9917) grad_norm: 2.0931 (2.1439) time: 0.6207 [2021-03-27 22:14:56 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 250/1251] eta: 0:10:45 lr: 0.000217 loss: 2.8879 (2.9949) grad_norm: 2.0469 (2.1464) time: 0.6288 [2021-03-27 22:15:02 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 260/1251] eta: 0:10:38 lr: 0.000217 loss: 3.1714 (3.0026) grad_norm: 2.0772 (2.1459) time: 0.6369 [2021-03-27 22:15:08 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 270/1251] eta: 0:10:31 lr: 0.000217 loss: 3.1663 (3.0015) grad_norm: 2.0820 (2.1488) time: 0.6338 [2021-03-27 22:15:15 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 280/1251] eta: 0:10:24 lr: 0.000217 loss: 3.1224 (3.0010) grad_norm: 1.9909 (2.1404) time: 0.6280 [2021-03-27 22:15:21 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 290/1251] eta: 0:10:17 lr: 0.000217 loss: 2.9588 (2.9966) grad_norm: 1.9621 (2.1385) time: 0.6240 [2021-03-27 22:15:27 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 300/1251] eta: 0:10:10 lr: 0.000217 loss: 2.7773 (2.9956) grad_norm: 2.0131 (2.1350) time: 0.6247 [2021-03-27 22:15:33 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 310/1251] eta: 0:10:03 lr: 0.000217 loss: 3.1440 (3.0032) grad_norm: 1.9560 (2.1298) time: 0.6289 [2021-03-27 22:15:40 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 320/1251] eta: 0:09:56 lr: 0.000217 loss: 3.2079 (3.0047) grad_norm: 1.9432 (2.1299) time: 0.6248 [2021-03-27 22:15:46 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 330/1251] eta: 0:09:50 lr: 0.000217 loss: 3.0510 (3.0019) grad_norm: 1.9432 (2.1243) time: 0.6283 [2021-03-27 22:15:52 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 340/1251] eta: 0:09:43 lr: 0.000217 loss: 2.8659 (2.9971) grad_norm: 1.8986 (2.1204) time: 0.6334 [2021-03-27 22:15:59 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 350/1251] eta: 0:09:37 lr: 0.000217 loss: 2.9638 (2.9992) grad_norm: 1.9330 (2.1181) time: 0.6313 [2021-03-27 22:16:05 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 360/1251] eta: 0:09:30 lr: 0.000217 loss: 3.0325 (2.9992) grad_norm: 2.0457 (2.1176) time: 0.6336 [2021-03-27 22:16:11 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 370/1251] eta: 0:09:23 lr: 0.000217 loss: 2.8750 (2.9954) grad_norm: 2.1658 (2.1240) time: 0.6350 [2021-03-27 22:16:18 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 380/1251] eta: 0:09:17 lr: 0.000217 loss: 2.9933 (2.9951) grad_norm: 2.0542 (2.1205) time: 0.6305 [2021-03-27 22:16:24 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 390/1251] eta: 0:09:10 lr: 0.000217 loss: 3.0800 (2.9906) grad_norm: 2.0542 (2.1340) time: 0.6246 [2021-03-27 22:16:30 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 400/1251] eta: 0:09:03 lr: 0.000217 loss: 3.0007 (2.9895) grad_norm: 2.1661 (2.1333) time: 0.6249 [2021-03-27 22:16:36 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 410/1251] eta: 0:08:57 lr: 0.000217 loss: 3.0816 (2.9954) grad_norm: 2.1017 (2.1327) time: 0.6257 [2021-03-27 22:16:43 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 420/1251] eta: 0:08:50 lr: 0.000217 loss: 3.1223 (2.9918) grad_norm: 2.0723 (2.1327) time: 0.6268 [2021-03-27 22:16:49 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 430/1251] eta: 0:08:43 lr: 0.000217 loss: 2.7883 (2.9899) grad_norm: 2.1225 (2.1357) time: 0.6248 [2021-03-27 22:16:55 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 440/1251] eta: 0:08:37 lr: 0.000217 loss: 3.0350 (2.9891) grad_norm: 2.1071 (2.1369) time: 0.6284 [2021-03-27 22:17:02 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 450/1251] eta: 0:08:30 lr: 0.000217 loss: 3.1037 (2.9886) grad_norm: 2.1053 (2.1382) time: 0.6327 [2021-03-27 22:17:08 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 460/1251] eta: 0:08:24 lr: 0.000217 loss: 2.9911 (2.9873) grad_norm: 2.0422 (2.1342) time: 0.6263 [2021-03-27 22:17:14 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 470/1251] eta: 0:08:17 lr: 0.000217 loss: 2.9114 (2.9827) grad_norm: 1.9541 (2.1344) time: 0.6234 [2021-03-27 22:17:20 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 480/1251] eta: 0:08:11 lr: 0.000217 loss: 2.8364 (2.9763) grad_norm: 2.0688 (2.1355) time: 0.6226 [2021-03-27 22:17:27 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 490/1251] eta: 0:08:04 lr: 0.000217 loss: 2.9975 (2.9775) grad_norm: 2.0250 (2.1334) time: 0.6255 [2021-03-27 22:17:33 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 500/1251] eta: 0:07:58 lr: 0.000217 loss: 3.1265 (2.9819) grad_norm: 1.9875 (2.1339) time: 0.6295 [2021-03-27 22:17:39 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 510/1251] eta: 0:07:51 lr: 0.000217 loss: 3.2182 (2.9857) grad_norm: 2.0921 (2.1348) time: 0.6271 [2021-03-27 22:17:45 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 520/1251] eta: 0:07:44 lr: 0.000217 loss: 2.7670 (2.9786) grad_norm: 2.0267 (2.1320) time: 0.6220 [2021-03-27 22:17:52 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 530/1251] eta: 0:07:38 lr: 0.000216 loss: 2.7333 (2.9811) grad_norm: 1.9774 (2.1307) time: 0.6202 [2021-03-27 22:17:58 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 540/1251] eta: 0:07:31 lr: 0.000216 loss: 3.1432 (2.9831) grad_norm: 1.9894 (2.1301) time: 0.6269 [2021-03-27 22:18:04 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 550/1251] eta: 0:07:25 lr: 0.000216 loss: 3.0841 (2.9782) grad_norm: 2.1695 (2.1321) time: 0.6366 [2021-03-27 22:18:11 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 560/1251] eta: 0:07:19 lr: 0.000216 loss: 2.6312 (2.9725) grad_norm: 2.0409 (2.1293) time: 0.6405 [2021-03-27 22:18:17 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 570/1251] eta: 0:07:12 lr: 0.000216 loss: 2.9551 (2.9738) grad_norm: 1.9335 (2.1264) time: 0.6298 [2021-03-27 22:18:23 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 580/1251] eta: 0:07:06 lr: 0.000216 loss: 3.1061 (2.9745) grad_norm: 2.0352 (2.1267) time: 0.6253 [2021-03-27 22:18:29 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 590/1251] eta: 0:06:59 lr: 0.000216 loss: 3.1061 (2.9754) grad_norm: 2.0574 (2.1252) time: 0.6301 [2021-03-27 22:18:36 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 600/1251] eta: 0:06:53 lr: 0.000216 loss: 2.8246 (2.9693) grad_norm: 2.0558 (2.1241) time: 0.6319 [2021-03-27 22:18:42 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 610/1251] eta: 0:06:47 lr: 0.000216 loss: 2.8246 (2.9725) grad_norm: 2.0787 (2.1243) time: 0.6268 [2021-03-27 22:18:48 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 620/1251] eta: 0:06:40 lr: 0.000216 loss: 3.0901 (2.9722) grad_norm: 2.0284 (2.1248) time: 0.6229 [2021-03-27 22:18:55 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 630/1251] eta: 0:06:34 lr: 0.000216 loss: 3.0755 (2.9706) grad_norm: 2.0729 (2.1289) time: 0.6263 [2021-03-27 22:19:01 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 640/1251] eta: 0:06:27 lr: 0.000216 loss: 3.2367 (2.9756) grad_norm: 2.1289 (2.1284) time: 0.6298 [2021-03-27 22:19:07 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 650/1251] eta: 0:06:21 lr: 0.000216 loss: 3.2261 (2.9763) grad_norm: 2.0654 (2.1269) time: 0.6272 [2021-03-27 22:19:13 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 660/1251] eta: 0:06:14 lr: 0.000216 loss: 3.1005 (2.9761) grad_norm: 2.0775 (2.1265) time: 0.6246 [2021-03-27 22:19:20 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 670/1251] eta: 0:06:08 lr: 0.000216 loss: 3.0027 (2.9755) grad_norm: 2.0427 (2.1251) time: 0.6305 [2021-03-27 22:19:26 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 680/1251] eta: 0:06:02 lr: 0.000216 loss: 2.6476 (2.9702) grad_norm: 2.1225 (2.1260) time: 0.6301 [2021-03-27 22:19:32 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 690/1251] eta: 0:05:55 lr: 0.000216 loss: 2.7367 (2.9717) grad_norm: 2.1848 (2.1261) time: 0.6274 [2021-03-27 22:19:39 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 700/1251] eta: 0:05:49 lr: 0.000216 loss: 3.1951 (2.9755) grad_norm: 2.0925 (2.1285) time: 0.6287 [2021-03-27 22:19:45 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 710/1251] eta: 0:05:42 lr: 0.000216 loss: 3.1733 (2.9758) grad_norm: 2.1544 (2.1327) time: 0.6241 [2021-03-27 22:19:51 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 720/1251] eta: 0:05:36 lr: 0.000216 loss: 3.3287 (2.9788) grad_norm: 2.1444 (2.1342) time: 0.6207 [2021-03-27 22:19:57 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 730/1251] eta: 0:05:30 lr: 0.000216 loss: 3.1320 (2.9791) grad_norm: 2.1595 (2.1395) time: 0.6322 [2021-03-27 22:20:04 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 740/1251] eta: 0:05:23 lr: 0.000216 loss: 3.0458 (2.9801) grad_norm: 2.1595 (2.1405) time: 0.6385 [2021-03-27 22:20:10 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 750/1251] eta: 0:05:17 lr: 0.000216 loss: 3.2535 (2.9842) grad_norm: 2.0999 (2.1412) time: 0.6325 [2021-03-27 22:20:16 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 760/1251] eta: 0:05:11 lr: 0.000216 loss: 3.0630 (2.9836) grad_norm: 2.0019 (2.1391) time: 0.6255 [2021-03-27 22:20:23 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 770/1251] eta: 0:05:04 lr: 0.000216 loss: 2.9000 (2.9813) grad_norm: 2.0010 (2.1406) time: 0.6251 [2021-03-27 22:20:29 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 780/1251] eta: 0:04:58 lr: 0.000216 loss: 2.9000 (2.9821) grad_norm: 2.0698 (2.1422) time: 0.6269 [2021-03-27 22:20:35 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 790/1251] eta: 0:04:52 lr: 0.000216 loss: 3.1086 (2.9824) grad_norm: 2.0965 (2.1436) time: 0.6274 [2021-03-27 22:20:41 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 800/1251] eta: 0:04:45 lr: 0.000216 loss: 3.0800 (2.9845) grad_norm: 2.0539 (2.1448) time: 0.6266 [2021-03-27 22:20:48 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 810/1251] eta: 0:04:39 lr: 0.000216 loss: 3.0100 (2.9846) grad_norm: 1.9882 (2.1442) time: 0.6295 [2021-03-27 22:20:54 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 820/1251] eta: 0:04:32 lr: 0.000215 loss: 3.0203 (2.9856) grad_norm: 2.1442 (2.1447) time: 0.6289 [2021-03-27 22:21:00 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 830/1251] eta: 0:04:26 lr: 0.000215 loss: 3.2321 (2.9875) grad_norm: 2.2012 (2.1458) time: 0.6267 [2021-03-27 22:21:06 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 840/1251] eta: 0:04:20 lr: 0.000215 loss: 3.0693 (2.9849) grad_norm: 2.2012 (2.1457) time: 0.6275 [2021-03-27 22:21:13 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 850/1251] eta: 0:04:13 lr: 0.000215 loss: 3.0734 (2.9873) grad_norm: 2.1608 (2.1474) time: 0.6266 [2021-03-27 22:21:19 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 860/1251] eta: 0:04:07 lr: 0.000215 loss: 3.1618 (2.9876) grad_norm: 2.1643 (2.1486) time: 0.6261 [2021-03-27 22:21:25 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 870/1251] eta: 0:04:01 lr: 0.000215 loss: 3.1089 (2.9880) grad_norm: 2.0257 (2.1464) time: 0.6231 [2021-03-27 22:21:32 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 880/1251] eta: 0:03:54 lr: 0.000215 loss: 3.0117 (2.9870) grad_norm: 2.0257 (2.1467) time: 0.6289 [2021-03-27 22:21:38 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 890/1251] eta: 0:03:48 lr: 0.000215 loss: 2.7596 (2.9843) grad_norm: 1.9702 (2.1445) time: 0.6384 [2021-03-27 22:21:44 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 900/1251] eta: 0:03:42 lr: 0.000215 loss: 2.9848 (2.9852) grad_norm: 1.9634 (2.1454) time: 0.6329 [2021-03-27 22:21:50 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 910/1251] eta: 0:03:35 lr: 0.000215 loss: 3.1704 (2.9882) grad_norm: 2.1242 (2.1457) time: 0.6248 [2021-03-27 22:21:57 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 920/1251] eta: 0:03:29 lr: 0.000215 loss: 3.1854 (2.9881) grad_norm: 2.0506 (2.1449) time: 0.6256 [2021-03-27 22:22:03 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 930/1251] eta: 0:03:23 lr: 0.000215 loss: 3.1062 (2.9897) grad_norm: 1.9400 (2.1432) time: 0.6291 [2021-03-27 22:22:09 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 940/1251] eta: 0:03:16 lr: 0.000215 loss: 3.1881 (2.9905) grad_norm: 2.1154 (2.1448) time: 0.6276 [2021-03-27 22:22:16 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 950/1251] eta: 0:03:10 lr: 0.000215 loss: 3.0719 (2.9897) grad_norm: 2.2335 (2.1465) time: 0.6251 [2021-03-27 22:22:22 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 960/1251] eta: 0:03:04 lr: 0.000215 loss: 3.1881 (2.9923) grad_norm: 2.1550 (2.1448) time: 0.6276 [2021-03-27 22:22:28 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 970/1251] eta: 0:02:57 lr: 0.000215 loss: 3.2775 (2.9943) grad_norm: 2.0100 (2.1439) time: 0.6239 [2021-03-27 22:22:34 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 980/1251] eta: 0:02:51 lr: 0.000215 loss: 3.1552 (2.9948) grad_norm: 2.0376 (2.1425) time: 0.6215 [2021-03-27 22:22:40 swin_base_patch4_window7_224] INFO: Epoch: [209] [ 990/1251] eta: 0:02:45 lr: 0.000215 loss: 3.0829 (2.9956) grad_norm: 2.0376 (2.1428) time: 0.6231 [2021-03-27 22:22:47 swin_base_patch4_window7_224] INFO: Epoch: [209] [1000/1251] eta: 0:02:38 lr: 0.000215 loss: 3.2428 (2.9984) grad_norm: 1.9847 (2.1410) time: 0.6291 [2021-03-27 22:22:53 swin_base_patch4_window7_224] INFO: Epoch: [209] [1010/1251] eta: 0:02:32 lr: 0.000215 loss: 3.0890 (2.9982) grad_norm: 1.9140 (2.1393) time: 0.6288 [2021-03-27 22:22:59 swin_base_patch4_window7_224] INFO: Epoch: [209] [1020/1251] eta: 0:02:26 lr: 0.000215 loss: 2.9210 (2.9983) grad_norm: 2.0369 (2.1393) time: 0.6293 [2021-03-27 22:23:06 swin_base_patch4_window7_224] INFO: Epoch: [209] [1030/1251] eta: 0:02:19 lr: 0.000215 loss: 3.1401 (2.9989) grad_norm: 2.1245 (2.1395) time: 0.6306 [2021-03-27 22:23:12 swin_base_patch4_window7_224] INFO: Epoch: [209] [1040/1251] eta: 0:02:13 lr: 0.000215 loss: 3.1090 (3.0004) grad_norm: 2.0500 (2.1386) time: 0.6285 [2021-03-27 22:23:18 swin_base_patch4_window7_224] INFO: Epoch: [209] [1050/1251] eta: 0:02:07 lr: 0.000215 loss: 3.0183 (2.9991) grad_norm: 1.9653 (2.1373) time: 0.6289 [2021-03-27 22:23:24 swin_base_patch4_window7_224] INFO: Epoch: [209] [1060/1251] eta: 0:02:00 lr: 0.000215 loss: 3.0909 (3.0017) grad_norm: 1.9643 (2.1364) time: 0.6230 [2021-03-27 22:23:31 swin_base_patch4_window7_224] INFO: Epoch: [209] [1070/1251] eta: 0:01:54 lr: 0.000215 loss: 3.1510 (3.0015) grad_norm: 1.9925 (2.1358) time: 0.6225 [2021-03-27 22:23:37 swin_base_patch4_window7_224] INFO: Epoch: [209] [1080/1251] eta: 0:01:48 lr: 0.000215 loss: 3.1160 (3.0022) grad_norm: 2.1632 (2.1370) time: 0.6293 [2021-03-27 22:23:43 swin_base_patch4_window7_224] INFO: Epoch: [209] [1090/1251] eta: 0:01:41 lr: 0.000215 loss: 3.1160 (3.0019) grad_norm: 2.1538 (2.1367) time: 0.6291 [2021-03-27 22:23:50 swin_base_patch4_window7_224] INFO: Epoch: [209] [1100/1251] eta: 0:01:35 lr: 0.000215 loss: 2.9814 (3.0018) grad_norm: 1.9473 (2.1348) time: 0.6218 [2021-03-27 22:23:56 swin_base_patch4_window7_224] INFO: Epoch: [209] [1110/1251] eta: 0:01:29 lr: 0.000215 loss: 3.0723 (3.0012) grad_norm: 1.9647 (2.1351) time: 0.6280 [2021-03-27 22:24:02 swin_base_patch4_window7_224] INFO: Epoch: [209] [1120/1251] eta: 0:01:22 lr: 0.000214 loss: 3.1725 (3.0014) grad_norm: 2.0140 (2.1344) time: 0.6296 [2021-03-27 22:24:08 swin_base_patch4_window7_224] INFO: Epoch: [209] [1130/1251] eta: 0:01:16 lr: 0.000214 loss: 3.1418 (3.0023) grad_norm: 2.0140 (2.1338) time: 0.6247 [2021-03-27 22:24:15 swin_base_patch4_window7_224] INFO: Epoch: [209] [1140/1251] eta: 0:01:10 lr: 0.000214 loss: 3.1418 (3.0023) grad_norm: 2.1288 (2.1345) time: 0.6273 [2021-03-27 22:24:21 swin_base_patch4_window7_224] INFO: Epoch: [209] [1150/1251] eta: 0:01:03 lr: 0.000214 loss: 2.8811 (3.0006) grad_norm: 2.0377 (2.1332) time: 0.6233 [2021-03-27 22:24:27 swin_base_patch4_window7_224] INFO: Epoch: [209] [1160/1251] eta: 0:00:57 lr: 0.000214 loss: 3.0223 (3.0012) grad_norm: 1.8954 (2.1323) time: 0.6192 [2021-03-27 22:24:33 swin_base_patch4_window7_224] INFO: Epoch: [209] [1170/1251] eta: 0:00:51 lr: 0.000214 loss: 3.0223 (3.0002) grad_norm: 1.9858 (2.1317) time: 0.6239 [2021-03-27 22:24:40 swin_base_patch4_window7_224] INFO: Epoch: [209] [1180/1251] eta: 0:00:44 lr: 0.000214 loss: 2.9400 (3.0000) grad_norm: 2.1081 (2.1322) time: 0.6240 [2021-03-27 22:24:46 swin_base_patch4_window7_224] INFO: Epoch: [209] [1190/1251] eta: 0:00:38 lr: 0.000214 loss: 3.1390 (3.0005) grad_norm: 2.1475 (2.1343) time: 0.6246 [2021-03-27 22:24:52 swin_base_patch4_window7_224] INFO: Epoch: [209] [1200/1251] eta: 0:00:32 lr: 0.000214 loss: 3.1467 (3.0016) grad_norm: 2.0583 (2.1334) time: 0.6266 [2021-03-27 22:24:58 swin_base_patch4_window7_224] INFO: Epoch: [209] [1210/1251] eta: 0:00:25 lr: 0.000214 loss: 2.8736 (2.9990) grad_norm: 2.0461 (2.1330) time: 0.6239 [2021-03-27 22:25:05 swin_base_patch4_window7_224] INFO: Epoch: [209] [1220/1251] eta: 0:00:19 lr: 0.000214 loss: 2.8736 (2.9998) grad_norm: 2.2514 (2.1354) time: 0.6285 [2021-03-27 22:25:11 swin_base_patch4_window7_224] INFO: Epoch: [209] [1230/1251] eta: 0:00:13 lr: 0.000214 loss: 3.0713 (2.9996) grad_norm: 2.2365 (2.1347) time: 0.6293 [2021-03-27 22:25:17 swin_base_patch4_window7_224] INFO: Epoch: [209] [1240/1251] eta: 0:00:06 lr: 0.000214 loss: 3.0130 (2.9992) grad_norm: 2.1000 (2.1351) time: 0.6197 [2021-03-27 22:25:23 swin_base_patch4_window7_224] INFO: Epoch: [209] [1250/1251] eta: 0:00:00 lr: 0.000214 loss: 3.0388 (2.9984) grad_norm: 2.1043 (2.1353) time: 0.6171 [2021-03-27 22:25:32 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:27 loss: 0.5626 (0.5626) acc1: 89.0625 (89.0625) acc5: 98.4375 (98.4375) [2021-03-27 22:25:34 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7873 (0.7955) acc1: 81.2500 (81.3920) acc5: 96.8750 (96.0227) [2021-03-27 22:25:37 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7873 (0.7937) acc1: 81.2500 (82.0685) acc5: 95.3125 (95.9821) [2021-03-27 22:25:39 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7877 (0.8129) acc1: 81.2500 (81.5020) acc5: 96.8750 (95.8165) [2021-03-27 22:25:41 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7701 (0.8033) acc1: 79.6875 (81.1738) acc5: 96.8750 (96.0747) [2021-03-27 22:25:42 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7701 (0.8125) acc1: 79.6875 (81.0240) acc5: 95.3125 (95.7440) [2021-03-27 22:25:53 swin_base_patch4_window7_224] INFO: * Acc@1 81.420 Acc@5 95.822 loss 0.799 [2021-03-27 22:25:53 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.4% [2021-03-27 22:25:53 swin_base_patch4_window7_224] INFO: Max accuracy: 81.54% [2021-03-27 22:25:58 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 0/1251] eta: 1:25:59 lr: 0.000214 loss: 3.7332 (3.7332) grad_norm: 2.4338 (2.4338) time: 4.1245 [2021-03-27 22:26:04 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 10/1251] eta: 0:20:13 lr: 0.000214 loss: 2.8992 (2.8493) grad_norm: 2.2045 (2.3142) time: 0.9781 [2021-03-27 22:26:11 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 20/1251] eta: 0:16:39 lr: 0.000214 loss: 2.8992 (2.9330) grad_norm: 2.0591 (2.1981) time: 0.6461 [2021-03-27 22:26:17 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 30/1251] eta: 0:15:18 lr: 0.000214 loss: 3.1625 (2.9911) grad_norm: 2.0294 (2.1621) time: 0.6275 [2021-03-27 22:26:23 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 40/1251] eta: 0:14:34 lr: 0.000214 loss: 3.0146 (2.9865) grad_norm: 2.0006 (2.1184) time: 0.6278 [2021-03-27 22:26:29 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 50/1251] eta: 0:14:04 lr: 0.000214 loss: 2.8850 (2.9521) grad_norm: 1.9877 (2.1042) time: 0.6277 [2021-03-27 22:26:36 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 60/1251] eta: 0:13:42 lr: 0.000214 loss: 3.0085 (2.9482) grad_norm: 1.9651 (2.1398) time: 0.6257 [2021-03-27 22:26:42 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 70/1251] eta: 0:13:23 lr: 0.000214 loss: 3.1103 (2.9785) grad_norm: 2.0652 (2.1317) time: 0.6217 [2021-03-27 22:26:48 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 80/1251] eta: 0:13:09 lr: 0.000214 loss: 3.1365 (2.9647) grad_norm: 2.1042 (2.1324) time: 0.6251 [2021-03-27 22:26:54 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 90/1251] eta: 0:12:57 lr: 0.000214 loss: 2.5932 (2.9217) grad_norm: 2.1241 (2.1402) time: 0.6321 [2021-03-27 22:27:01 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 100/1251] eta: 0:12:46 lr: 0.000214 loss: 2.6961 (2.9209) grad_norm: 2.1138 (2.1410) time: 0.6307 [2021-03-27 22:27:07 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 110/1251] eta: 0:12:35 lr: 0.000214 loss: 3.0101 (2.9261) grad_norm: 2.0182 (2.1358) time: 0.6282 [2021-03-27 22:27:13 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 120/1251] eta: 0:12:26 lr: 0.000214 loss: 2.9486 (2.9214) grad_norm: 2.0511 (2.1575) time: 0.6294 [2021-03-27 22:27:20 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 130/1251] eta: 0:12:16 lr: 0.000214 loss: 2.8023 (2.9225) grad_norm: 2.0494 (2.1471) time: 0.6294 [2021-03-27 22:27:26 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 140/1251] eta: 0:12:07 lr: 0.000214 loss: 2.9380 (2.9256) grad_norm: 1.9666 (2.1395) time: 0.6237 [2021-03-27 22:27:32 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 150/1251] eta: 0:11:58 lr: 0.000214 loss: 2.9587 (2.9266) grad_norm: 1.9878 (2.1345) time: 0.6227 [2021-03-27 22:27:38 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 160/1251] eta: 0:11:50 lr: 0.000214 loss: 3.0085 (2.9329) grad_norm: 2.0874 (2.1403) time: 0.6263 [2021-03-27 22:27:45 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 170/1251] eta: 0:11:42 lr: 0.000213 loss: 3.0262 (2.9340) grad_norm: 2.1476 (2.1420) time: 0.6279 [2021-03-27 22:27:51 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 180/1251] eta: 0:11:34 lr: 0.000213 loss: 3.0870 (2.9475) grad_norm: 2.0703 (2.1375) time: 0.6281 [2021-03-27 22:27:57 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 190/1251] eta: 0:11:26 lr: 0.000213 loss: 3.2131 (2.9641) grad_norm: 1.9710 (2.1275) time: 0.6273 [2021-03-27 22:28:03 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 200/1251] eta: 0:11:19 lr: 0.000213 loss: 3.0829 (2.9599) grad_norm: 2.0477 (2.1417) time: 0.6245 [2021-03-27 22:28:10 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 210/1251] eta: 0:11:12 lr: 0.000213 loss: 3.1634 (2.9801) grad_norm: 2.2865 (2.1584) time: 0.6289 [2021-03-27 22:28:16 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 220/1251] eta: 0:11:05 lr: 0.000213 loss: 3.1818 (2.9727) grad_norm: 2.2234 (2.1625) time: 0.6353 [2021-03-27 22:28:22 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 230/1251] eta: 0:10:58 lr: 0.000213 loss: 3.1818 (2.9883) grad_norm: 2.0640 (2.1661) time: 0.6343 [2021-03-27 22:28:29 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 240/1251] eta: 0:10:50 lr: 0.000213 loss: 3.2736 (2.9880) grad_norm: 2.0697 (2.1707) time: 0.6277 [2021-03-27 22:28:35 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 250/1251] eta: 0:10:43 lr: 0.000213 loss: 3.2136 (2.9897) grad_norm: 2.1029 (2.1641) time: 0.6244 [2021-03-27 22:28:41 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 260/1251] eta: 0:10:36 lr: 0.000213 loss: 3.0722 (2.9866) grad_norm: 1.9721 (2.1609) time: 0.6249 [2021-03-27 22:28:47 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 270/1251] eta: 0:10:29 lr: 0.000213 loss: 2.8300 (2.9807) grad_norm: 2.1531 (2.1677) time: 0.6285 [2021-03-27 22:28:54 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 280/1251] eta: 0:10:22 lr: 0.000213 loss: 2.8855 (2.9790) grad_norm: 2.2278 (2.1733) time: 0.6292 [2021-03-27 22:29:00 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 290/1251] eta: 0:10:15 lr: 0.000213 loss: 3.1070 (2.9894) grad_norm: 2.1557 (2.1706) time: 0.6279 [2021-03-27 22:29:06 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 300/1251] eta: 0:10:08 lr: 0.000213 loss: 3.1201 (2.9897) grad_norm: 2.1065 (2.1772) time: 0.6260 [2021-03-27 22:29:13 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 310/1251] eta: 0:10:02 lr: 0.000213 loss: 3.0191 (2.9946) grad_norm: 2.1920 (2.1805) time: 0.6233 [2021-03-27 22:29:19 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 320/1251] eta: 0:09:55 lr: 0.000213 loss: 2.9511 (2.9909) grad_norm: 2.0996 (2.1752) time: 0.6263 [2021-03-27 22:29:25 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 330/1251] eta: 0:09:48 lr: 0.000213 loss: 3.2544 (3.0029) grad_norm: 2.1055 (2.1788) time: 0.6240 [2021-03-27 22:29:31 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 340/1251] eta: 0:09:41 lr: 0.000213 loss: 3.2748 (3.0040) grad_norm: 2.1055 (2.1759) time: 0.6225 [2021-03-27 22:29:37 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 350/1251] eta: 0:09:34 lr: 0.000213 loss: 3.1732 (3.0071) grad_norm: 2.0050 (2.1823) time: 0.6228 [2021-03-27 22:29:44 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 360/1251] eta: 0:09:28 lr: 0.000213 loss: 3.2135 (3.0097) grad_norm: 2.1407 (2.1810) time: 0.6222 [2021-03-27 22:29:50 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 370/1251] eta: 0:09:21 lr: 0.000213 loss: 3.1577 (3.0119) grad_norm: 1.9809 (2.1753) time: 0.6222 [2021-03-27 22:29:56 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 380/1251] eta: 0:09:14 lr: 0.000213 loss: 3.0771 (3.0092) grad_norm: 1.9509 (2.1710) time: 0.6225 [2021-03-27 22:30:03 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 390/1251] eta: 0:09:08 lr: 0.000213 loss: 2.9297 (3.0100) grad_norm: 1.9942 (2.1701) time: 0.6318 [2021-03-27 22:30:09 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 400/1251] eta: 0:09:02 lr: 0.000213 loss: 3.1454 (3.0117) grad_norm: 2.0978 (2.1682) time: 0.6438 [2021-03-27 22:30:15 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 410/1251] eta: 0:08:55 lr: 0.000213 loss: 3.1881 (3.0138) grad_norm: 2.1090 (2.1671) time: 0.6394 [2021-03-27 22:30:22 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 420/1251] eta: 0:08:49 lr: 0.000213 loss: 3.0008 (3.0090) grad_norm: 2.0295 (2.1653) time: 0.6304 [2021-03-27 22:30:28 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 430/1251] eta: 0:08:42 lr: 0.000213 loss: 2.9858 (3.0110) grad_norm: 2.0295 (2.1623) time: 0.6246 [2021-03-27 22:30:34 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 440/1251] eta: 0:08:35 lr: 0.000213 loss: 3.0165 (3.0054) grad_norm: 2.1327 (2.1658) time: 0.6238 [2021-03-27 22:30:40 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 450/1251] eta: 0:08:29 lr: 0.000213 loss: 2.6489 (2.9976) grad_norm: 2.1969 (2.1655) time: 0.6251 [2021-03-27 22:30:47 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 460/1251] eta: 0:08:22 lr: 0.000213 loss: 2.8059 (2.9974) grad_norm: 2.1705 (2.1643) time: 0.6270 [2021-03-27 22:30:53 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 470/1251] eta: 0:08:16 lr: 0.000212 loss: 2.8541 (2.9919) grad_norm: 2.0891 (2.1612) time: 0.6313 [2021-03-27 22:30:59 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 480/1251] eta: 0:08:09 lr: 0.000212 loss: 2.7857 (2.9889) grad_norm: 1.9549 (2.1569) time: 0.6272 [2021-03-27 22:31:05 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 490/1251] eta: 0:08:03 lr: 0.000212 loss: 2.9457 (2.9891) grad_norm: 1.9943 (2.1548) time: 0.6229 [2021-03-27 22:31:12 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 500/1251] eta: 0:07:57 lr: 0.000212 loss: 3.1225 (2.9875) grad_norm: 1.9943 (2.1532) time: 0.6294 [2021-03-27 22:31:18 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 510/1251] eta: 0:07:50 lr: 0.000212 loss: 2.9259 (2.9859) grad_norm: 2.0997 (2.1530) time: 0.6305 [2021-03-27 22:31:24 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 520/1251] eta: 0:07:44 lr: 0.000212 loss: 2.9259 (2.9876) grad_norm: 2.0921 (2.1506) time: 0.6248 [2021-03-27 22:31:30 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 530/1251] eta: 0:07:37 lr: 0.000212 loss: 3.0558 (2.9864) grad_norm: 2.0921 (2.1524) time: 0.6205 [2021-03-27 22:31:37 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 540/1251] eta: 0:07:31 lr: 0.000212 loss: 3.0325 (2.9887) grad_norm: 2.3516 (2.1675) time: 0.6237 [2021-03-27 22:31:43 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 550/1251] eta: 0:07:24 lr: 0.000212 loss: 3.0558 (2.9909) grad_norm: 2.1992 (2.1668) time: 0.6411 [2021-03-27 22:31:50 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 560/1251] eta: 0:07:18 lr: 0.000212 loss: 3.2384 (2.9950) grad_norm: 2.1039 (2.1648) time: 0.6395 [2021-03-27 22:31:56 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 570/1251] eta: 0:07:12 lr: 0.000212 loss: 3.1474 (2.9965) grad_norm: 2.0422 (2.1629) time: 0.6276 [2021-03-27 22:32:02 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 580/1251] eta: 0:07:05 lr: 0.000212 loss: 3.0529 (2.9952) grad_norm: 1.9536 (2.1605) time: 0.6311 [2021-03-27 22:32:08 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 590/1251] eta: 0:06:59 lr: 0.000212 loss: 3.2257 (2.9995) grad_norm: 1.9536 (2.1591) time: 0.6299 [2021-03-27 22:32:15 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 600/1251] eta: 0:06:52 lr: 0.000212 loss: 3.0684 (2.9936) grad_norm: 1.9583 (2.1560) time: 0.6322 [2021-03-27 22:32:21 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 610/1251] eta: 0:06:46 lr: 0.000212 loss: 3.0613 (2.9944) grad_norm: 1.8939 (2.1542) time: 0.6332 [2021-03-27 22:32:27 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 620/1251] eta: 0:06:40 lr: 0.000212 loss: 3.1748 (2.9969) grad_norm: 1.9759 (2.1525) time: 0.6266 [2021-03-27 22:32:34 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 630/1251] eta: 0:06:33 lr: 0.000212 loss: 3.0613 (2.9969) grad_norm: 2.1922 (2.1564) time: 0.6250 [2021-03-27 22:32:40 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 640/1251] eta: 0:06:27 lr: 0.000212 loss: 3.0613 (2.9978) grad_norm: 2.2040 (2.1574) time: 0.6239 [2021-03-27 22:32:46 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 650/1251] eta: 0:06:20 lr: 0.000212 loss: 3.2869 (3.0024) grad_norm: 2.0280 (2.1558) time: 0.6308 [2021-03-27 22:32:53 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 660/1251] eta: 0:06:14 lr: 0.000212 loss: 3.2670 (3.0021) grad_norm: 2.0456 (2.1565) time: 0.6344 [2021-03-27 22:32:59 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 670/1251] eta: 0:06:08 lr: 0.000212 loss: 3.1172 (3.0012) grad_norm: 2.0985 (2.1564) time: 0.6250 [2021-03-27 22:33:05 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 680/1251] eta: 0:06:01 lr: 0.000212 loss: 3.2089 (3.0022) grad_norm: 2.0171 (2.1541) time: 0.6251 [2021-03-27 22:33:11 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 690/1251] eta: 0:05:55 lr: 0.000212 loss: 3.2477 (3.0062) grad_norm: 2.0107 (2.1537) time: 0.6305 [2021-03-27 22:33:18 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 700/1251] eta: 0:05:49 lr: 0.000212 loss: 3.1684 (3.0050) grad_norm: 2.1265 (2.1543) time: 0.6308 [2021-03-27 22:33:24 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 710/1251] eta: 0:05:42 lr: 0.000212 loss: 3.0260 (3.0051) grad_norm: 2.1503 (2.1545) time: 0.6278 [2021-03-27 22:33:30 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 720/1251] eta: 0:05:36 lr: 0.000212 loss: 3.1335 (3.0074) grad_norm: 2.0716 (2.1540) time: 0.6240 [2021-03-27 22:33:36 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 730/1251] eta: 0:05:29 lr: 0.000212 loss: 3.1996 (3.0101) grad_norm: 2.0654 (2.1530) time: 0.6252 [2021-03-27 22:33:43 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 740/1251] eta: 0:05:23 lr: 0.000212 loss: 3.1765 (3.0077) grad_norm: 2.0250 (2.1508) time: 0.6293 [2021-03-27 22:33:49 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 750/1251] eta: 0:05:17 lr: 0.000212 loss: 3.0453 (3.0049) grad_norm: 1.9834 (2.1490) time: 0.6299 [2021-03-27 22:33:55 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 760/1251] eta: 0:05:10 lr: 0.000212 loss: 2.8896 (3.0016) grad_norm: 1.9509 (2.1470) time: 0.6309 [2021-03-27 22:34:02 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 770/1251] eta: 0:05:04 lr: 0.000211 loss: 2.8896 (3.0006) grad_norm: 1.9720 (2.1476) time: 0.6296 [2021-03-27 22:34:08 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 780/1251] eta: 0:04:58 lr: 0.000211 loss: 2.9690 (3.0003) grad_norm: 2.0975 (2.1473) time: 0.6237 [2021-03-27 22:34:14 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 790/1251] eta: 0:04:51 lr: 0.000211 loss: 2.9786 (2.9973) grad_norm: 2.0809 (2.1481) time: 0.6208 [2021-03-27 22:34:20 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 800/1251] eta: 0:04:45 lr: 0.000211 loss: 3.0051 (2.9982) grad_norm: 2.1341 (2.1478) time: 0.6231 [2021-03-27 22:34:27 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 810/1251] eta: 0:04:38 lr: 0.000211 loss: 3.0632 (2.9975) grad_norm: 2.1020 (2.1469) time: 0.6249 [2021-03-27 22:34:33 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 820/1251] eta: 0:04:32 lr: 0.000211 loss: 2.8855 (2.9968) grad_norm: 2.0290 (2.1453) time: 0.6311 [2021-03-27 22:34:39 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 830/1251] eta: 0:04:26 lr: 0.000211 loss: 2.8036 (2.9963) grad_norm: 1.9855 (2.1441) time: 0.6407 [2021-03-27 22:34:46 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 840/1251] eta: 0:04:20 lr: 0.000211 loss: 3.1729 (2.9985) grad_norm: 2.0753 (2.1445) time: 0.6376 [2021-03-27 22:34:52 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 850/1251] eta: 0:04:13 lr: 0.000211 loss: 3.1729 (3.0012) grad_norm: 2.0806 (2.1447) time: 0.6283 [2021-03-27 22:34:58 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 860/1251] eta: 0:04:07 lr: 0.000211 loss: 3.1325 (3.0011) grad_norm: 2.0721 (2.1443) time: 0.6244 [2021-03-27 22:35:04 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 870/1251] eta: 0:04:00 lr: 0.000211 loss: 3.1325 (3.0022) grad_norm: 2.1258 (2.1448) time: 0.6275 [2021-03-27 22:35:11 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 880/1251] eta: 0:03:54 lr: 0.000211 loss: 3.1897 (3.0037) grad_norm: 2.1154 (2.1449) time: 0.6294 [2021-03-27 22:35:17 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 890/1251] eta: 0:03:48 lr: 0.000211 loss: 3.1897 (3.0053) grad_norm: 2.0610 (2.1445) time: 0.6243 [2021-03-27 22:35:23 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 900/1251] eta: 0:03:41 lr: 0.000211 loss: 3.2235 (3.0063) grad_norm: 2.0056 (2.1440) time: 0.6220 [2021-03-27 22:35:30 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 910/1251] eta: 0:03:35 lr: 0.000211 loss: 3.0439 (3.0046) grad_norm: 1.9802 (2.1446) time: 0.6281 [2021-03-27 22:35:36 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 920/1251] eta: 0:03:29 lr: 0.000211 loss: 3.0562 (3.0062) grad_norm: 1.9802 (2.1439) time: 0.6277 [2021-03-27 22:35:42 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 930/1251] eta: 0:03:22 lr: 0.000211 loss: 2.9320 (3.0026) grad_norm: 1.9891 (2.1433) time: 0.6287 [2021-03-27 22:35:48 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 940/1251] eta: 0:03:16 lr: 0.000211 loss: 2.5911 (2.9998) grad_norm: 2.0700 (2.1497) time: 0.6285 [2021-03-27 22:35:55 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 950/1251] eta: 0:03:10 lr: 0.000211 loss: 3.1562 (3.0024) grad_norm: 2.1743 (2.1515) time: 0.6235 [2021-03-27 22:36:01 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 960/1251] eta: 0:03:03 lr: 0.000211 loss: 3.2137 (3.0028) grad_norm: 2.0591 (2.1515) time: 0.6271 [2021-03-27 22:36:07 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 970/1251] eta: 0:02:57 lr: 0.000211 loss: 3.1621 (3.0028) grad_norm: 2.0882 (2.1516) time: 0.6268 [2021-03-27 22:36:13 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 980/1251] eta: 0:02:51 lr: 0.000211 loss: 3.0829 (3.0022) grad_norm: 2.1557 (2.1523) time: 0.6233 [2021-03-27 22:36:20 swin_base_patch4_window7_224] INFO: Epoch: [210] [ 990/1251] eta: 0:02:44 lr: 0.000211 loss: 3.0057 (3.0019) grad_norm: 2.0207 (2.1518) time: 0.6227 [2021-03-27 22:36:26 swin_base_patch4_window7_224] INFO: Epoch: [210] [1000/1251] eta: 0:02:38 lr: 0.000211 loss: 3.1229 (3.0041) grad_norm: 2.0071 (2.1528) time: 0.6223 [2021-03-27 22:36:32 swin_base_patch4_window7_224] INFO: Epoch: [210] [1010/1251] eta: 0:02:32 lr: 0.000211 loss: 3.1229 (3.0042) grad_norm: 2.0882 (2.1523) time: 0.6263 [2021-03-27 22:36:39 swin_base_patch4_window7_224] INFO: Epoch: [210] [1020/1251] eta: 0:02:25 lr: 0.000211 loss: 3.1173 (3.0056) grad_norm: 2.0680 (2.1530) time: 0.6360 [2021-03-27 22:36:45 swin_base_patch4_window7_224] INFO: Epoch: [210] [1030/1251] eta: 0:02:19 lr: 0.000211 loss: 3.0499 (3.0045) grad_norm: 2.1094 (2.1541) time: 0.6313 [2021-03-27 22:36:51 swin_base_patch4_window7_224] INFO: Epoch: [210] [1040/1251] eta: 0:02:13 lr: 0.000211 loss: 2.9435 (3.0044) grad_norm: 2.2776 (2.1553) time: 0.6236 [2021-03-27 22:36:57 swin_base_patch4_window7_224] INFO: Epoch: [210] [1050/1251] eta: 0:02:06 lr: 0.000211 loss: 3.2068 (3.0052) grad_norm: 2.1897 (2.1544) time: 0.6248 [2021-03-27 22:37:04 swin_base_patch4_window7_224] INFO: Epoch: [210] [1060/1251] eta: 0:02:00 lr: 0.000211 loss: 3.2068 (3.0059) grad_norm: 2.2503 (2.1574) time: 0.6276 [2021-03-27 22:37:10 swin_base_patch4_window7_224] INFO: Epoch: [210] [1070/1251] eta: 0:01:54 lr: 0.000210 loss: 3.1203 (3.0047) grad_norm: 2.2503 (2.1567) time: 0.6254 [2021-03-27 22:37:16 swin_base_patch4_window7_224] INFO: Epoch: [210] [1080/1251] eta: 0:01:47 lr: 0.000210 loss: 3.0033 (3.0030) grad_norm: 2.0391 (2.1569) time: 0.6211 [2021-03-27 22:37:22 swin_base_patch4_window7_224] INFO: Epoch: [210] [1090/1251] eta: 0:01:41 lr: 0.000210 loss: 2.9154 (3.0024) grad_norm: 2.0775 (2.1562) time: 0.6218 [2021-03-27 22:37:28 swin_base_patch4_window7_224] INFO: Epoch: [210] [1100/1251] eta: 0:01:35 lr: 0.000210 loss: 2.9023 (3.0022) grad_norm: 2.0625 (2.1560) time: 0.6225 [2021-03-27 22:37:35 swin_base_patch4_window7_224] INFO: Epoch: [210] [1110/1251] eta: 0:01:28 lr: 0.000210 loss: 3.0639 (3.0041) grad_norm: 2.0382 (2.1549) time: 0.6237 [2021-03-27 22:37:41 swin_base_patch4_window7_224] INFO: Epoch: [210] [1120/1251] eta: 0:01:22 lr: 0.000210 loss: 3.2909 (3.0051) grad_norm: 2.0254 (2.1547) time: 0.6247 [2021-03-27 22:37:47 swin_base_patch4_window7_224] INFO: Epoch: [210] [1130/1251] eta: 0:01:16 lr: 0.000210 loss: 3.0106 (3.0043) grad_norm: 2.0431 (2.1549) time: 0.6264 [2021-03-27 22:37:53 swin_base_patch4_window7_224] INFO: Epoch: [210] [1140/1251] eta: 0:01:10 lr: 0.000210 loss: 2.8738 (3.0038) grad_norm: 2.0422 (2.1543) time: 0.6255 [2021-03-27 22:38:00 swin_base_patch4_window7_224] INFO: Epoch: [210] [1150/1251] eta: 0:01:03 lr: 0.000210 loss: 3.1514 (3.0051) grad_norm: 1.9756 (2.1530) time: 0.6282 [2021-03-27 22:38:06 swin_base_patch4_window7_224] INFO: Epoch: [210] [1160/1251] eta: 0:00:57 lr: 0.000210 loss: 3.0893 (3.0049) grad_norm: 1.9070 (2.1521) time: 0.6332 [2021-03-27 22:38:12 swin_base_patch4_window7_224] INFO: Epoch: [210] [1170/1251] eta: 0:00:51 lr: 0.000210 loss: 2.7985 (3.0030) grad_norm: 1.9647 (2.1512) time: 0.6314 [2021-03-27 22:38:19 swin_base_patch4_window7_224] INFO: Epoch: [210] [1180/1251] eta: 0:00:44 lr: 0.000210 loss: 2.8659 (3.0025) grad_norm: 2.0063 (2.1517) time: 0.6274 [2021-03-27 22:38:25 swin_base_patch4_window7_224] INFO: Epoch: [210] [1190/1251] eta: 0:00:38 lr: 0.000210 loss: 3.0307 (3.0024) grad_norm: 2.0408 (2.1510) time: 0.6302 [2021-03-27 22:38:31 swin_base_patch4_window7_224] INFO: Epoch: [210] [1200/1251] eta: 0:00:32 lr: 0.000210 loss: 2.9235 (3.0012) grad_norm: 2.0004 (2.1502) time: 0.6328 [2021-03-27 22:38:38 swin_base_patch4_window7_224] INFO: Epoch: [210] [1210/1251] eta: 0:00:25 lr: 0.000210 loss: 2.8208 (2.9990) grad_norm: 1.9775 (2.1500) time: 0.6357 [2021-03-27 22:38:44 swin_base_patch4_window7_224] INFO: Epoch: [210] [1220/1251] eta: 0:00:19 lr: 0.000210 loss: 2.7173 (2.9971) grad_norm: 2.0955 (2.1524) time: 0.6314 [2021-03-27 22:38:50 swin_base_patch4_window7_224] INFO: Epoch: [210] [1230/1251] eta: 0:00:13 lr: 0.000210 loss: 2.9675 (2.9970) grad_norm: 2.2248 (2.1526) time: 0.6249 [2021-03-27 22:38:56 swin_base_patch4_window7_224] INFO: Epoch: [210] [1240/1251] eta: 0:00:06 lr: 0.000210 loss: 2.9675 (2.9956) grad_norm: 2.0009 (2.1515) time: 0.6250 [2021-03-27 22:39:03 swin_base_patch4_window7_224] INFO: Epoch: [210] [1250/1251] eta: 0:00:00 lr: 0.000210 loss: 3.0267 (2.9970) grad_norm: 2.0009 (2.1519) time: 0.6155 [2021-03-27 22:40:22 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:09 loss: 1.0436 (1.0436) acc1: 71.8750 (71.8750) acc5: 95.3125 (95.3125) [2021-03-27 22:40:23 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.8276 (0.8349) acc1: 81.2500 (80.1136) acc5: 95.3125 (95.7386) [2021-03-27 22:40:25 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.6886 (0.7791) acc1: 81.2500 (81.1756) acc5: 95.3125 (96.2054) [2021-03-27 22:40:26 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7681 (0.8001) acc1: 81.2500 (80.8468) acc5: 96.8750 (96.1190) [2021-03-27 22:40:28 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8413 (0.8149) acc1: 78.1250 (80.1448) acc5: 95.3125 (95.9985) [2021-03-27 22:40:29 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8121 (0.8104) acc1: 79.6875 (80.1920) acc5: 95.3125 (96.0320) [2021-03-27 22:40:43 swin_base_patch4_window7_224] INFO: * Acc@1 81.454 Acc@5 95.846 loss 0.793 [2021-03-27 22:40:43 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.5% [2021-03-27 22:40:43 swin_base_patch4_window7_224] INFO: Max accuracy: 81.54% [2021-03-27 22:40:47 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 0/1251] eta: 1:27:50 lr: 0.000210 loss: 2.8007 (2.8007) grad_norm: 1.8722 (1.8722) time: 4.2129 [2021-03-27 22:40:54 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 10/1251] eta: 0:20:03 lr: 0.000210 loss: 2.8267 (2.8406) grad_norm: 2.2839 (2.3179) time: 0.9698 [2021-03-27 22:41:00 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 20/1251] eta: 0:16:36 lr: 0.000210 loss: 2.8267 (2.7861) grad_norm: 2.0486 (2.1810) time: 0.6396 [2021-03-27 22:41:06 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 30/1251] eta: 0:15:14 lr: 0.000210 loss: 3.0322 (2.8717) grad_norm: 2.0486 (2.1632) time: 0.6281 [2021-03-27 22:41:13 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 40/1251] eta: 0:14:32 lr: 0.000210 loss: 3.0622 (2.8511) grad_norm: 2.0993 (2.1552) time: 0.6265 [2021-03-27 22:41:19 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 50/1251] eta: 0:14:03 lr: 0.000210 loss: 3.0318 (2.9092) grad_norm: 2.0479 (2.1290) time: 0.6291 [2021-03-27 22:41:25 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 60/1251] eta: 0:13:41 lr: 0.000210 loss: 3.1951 (2.9504) grad_norm: 2.0479 (2.1422) time: 0.6265 [2021-03-27 22:41:31 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 70/1251] eta: 0:13:25 lr: 0.000210 loss: 3.0916 (2.9159) grad_norm: 2.2163 (2.1807) time: 0.6312 [2021-03-27 22:41:38 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 80/1251] eta: 0:13:10 lr: 0.000210 loss: 2.9461 (2.9194) grad_norm: 2.3150 (2.1769) time: 0.6321 [2021-03-27 22:41:44 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 90/1251] eta: 0:12:57 lr: 0.000210 loss: 2.9461 (2.9201) grad_norm: 2.2039 (2.1871) time: 0.6265 [2021-03-27 22:41:50 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 100/1251] eta: 0:12:47 lr: 0.000210 loss: 2.9772 (2.9286) grad_norm: 2.0185 (2.1623) time: 0.6315 [2021-03-27 22:41:57 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 110/1251] eta: 0:12:37 lr: 0.000210 loss: 3.0747 (2.9428) grad_norm: 1.9078 (2.1516) time: 0.6359 [2021-03-27 22:42:03 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 120/1251] eta: 0:12:29 lr: 0.000209 loss: 3.0091 (2.9410) grad_norm: 2.0756 (2.1804) time: 0.6408 [2021-03-27 22:42:09 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 130/1251] eta: 0:12:19 lr: 0.000209 loss: 2.9033 (2.9443) grad_norm: 2.1755 (2.1882) time: 0.6363 [2021-03-27 22:42:16 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 140/1251] eta: 0:12:10 lr: 0.000209 loss: 2.9644 (2.9440) grad_norm: 2.1755 (2.1847) time: 0.6283 [2021-03-27 22:42:22 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 150/1251] eta: 0:12:01 lr: 0.000209 loss: 2.9770 (2.9384) grad_norm: 2.0179 (2.1727) time: 0.6286 [2021-03-27 22:42:28 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 160/1251] eta: 0:11:54 lr: 0.000209 loss: 2.9218 (2.9353) grad_norm: 2.0162 (2.1666) time: 0.6367 [2021-03-27 22:42:35 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 170/1251] eta: 0:11:46 lr: 0.000209 loss: 2.6563 (2.9164) grad_norm: 1.9858 (2.1637) time: 0.6369 [2021-03-27 22:42:41 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 180/1251] eta: 0:11:37 lr: 0.000209 loss: 2.8815 (2.9185) grad_norm: 1.9767 (2.1562) time: 0.6254 [2021-03-27 22:42:47 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 190/1251] eta: 0:11:30 lr: 0.000209 loss: 2.9719 (2.9155) grad_norm: 2.0643 (2.1546) time: 0.6258 [2021-03-27 22:42:54 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 200/1251] eta: 0:11:22 lr: 0.000209 loss: 2.7605 (2.9082) grad_norm: 1.9989 (2.1660) time: 0.6281 [2021-03-27 22:43:00 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 210/1251] eta: 0:11:15 lr: 0.000209 loss: 3.1275 (2.9166) grad_norm: 2.0077 (2.1693) time: 0.6293 [2021-03-27 22:43:06 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 220/1251] eta: 0:11:07 lr: 0.000209 loss: 3.1710 (2.9247) grad_norm: 2.1463 (2.1682) time: 0.6263 [2021-03-27 22:43:12 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 230/1251] eta: 0:11:00 lr: 0.000209 loss: 3.3059 (2.9359) grad_norm: 2.1463 (2.1709) time: 0.6260 [2021-03-27 22:43:19 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 240/1251] eta: 0:10:52 lr: 0.000209 loss: 3.3080 (2.9452) grad_norm: 2.0157 (2.1710) time: 0.6295 [2021-03-27 22:43:25 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 250/1251] eta: 0:10:45 lr: 0.000209 loss: 3.0757 (2.9408) grad_norm: 2.0043 (2.1641) time: 0.6303 [2021-03-27 22:43:31 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 260/1251] eta: 0:10:38 lr: 0.000209 loss: 2.5968 (2.9284) grad_norm: 1.9700 (2.1584) time: 0.6284 [2021-03-27 22:43:38 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 270/1251] eta: 0:10:31 lr: 0.000209 loss: 2.6399 (2.9259) grad_norm: 1.9894 (2.1560) time: 0.6295 [2021-03-27 22:43:44 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 280/1251] eta: 0:10:24 lr: 0.000209 loss: 3.0269 (2.9412) grad_norm: 1.9754 (2.1468) time: 0.6258 [2021-03-27 22:43:50 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 290/1251] eta: 0:10:17 lr: 0.000209 loss: 3.0890 (2.9385) grad_norm: 1.9852 (2.1456) time: 0.6206 [2021-03-27 22:43:56 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 300/1251] eta: 0:10:10 lr: 0.000209 loss: 2.9754 (2.9455) grad_norm: 2.1225 (2.1481) time: 0.6258 [2021-03-27 22:44:03 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 310/1251] eta: 0:10:03 lr: 0.000209 loss: 3.2225 (2.9463) grad_norm: 2.1503 (2.1491) time: 0.6269 [2021-03-27 22:44:09 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 320/1251] eta: 0:09:56 lr: 0.000209 loss: 3.2225 (2.9497) grad_norm: 2.1503 (2.1490) time: 0.6244 [2021-03-27 22:44:15 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 330/1251] eta: 0:09:49 lr: 0.000209 loss: 3.2627 (2.9525) grad_norm: 2.1050 (2.1490) time: 0.6233 [2021-03-27 22:44:21 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 340/1251] eta: 0:09:42 lr: 0.000209 loss: 3.1844 (2.9552) grad_norm: 2.0360 (2.1518) time: 0.6235 [2021-03-27 22:44:27 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 350/1251] eta: 0:09:36 lr: 0.000209 loss: 3.0410 (2.9537) grad_norm: 2.1232 (2.1545) time: 0.6220 [2021-03-27 22:44:34 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 360/1251] eta: 0:09:29 lr: 0.000209 loss: 2.6876 (2.9501) grad_norm: 2.2200 (2.1588) time: 0.6233 [2021-03-27 22:44:40 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 370/1251] eta: 0:09:22 lr: 0.000209 loss: 2.6525 (2.9485) grad_norm: 2.2030 (2.1675) time: 0.6323 [2021-03-27 22:44:46 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 380/1251] eta: 0:09:16 lr: 0.000209 loss: 2.9455 (2.9508) grad_norm: 2.1396 (2.1671) time: 0.6289 [2021-03-27 22:44:53 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 390/1251] eta: 0:09:09 lr: 0.000209 loss: 2.8963 (2.9446) grad_norm: 2.0840 (2.1642) time: 0.6259 [2021-03-27 22:44:59 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 400/1251] eta: 0:09:03 lr: 0.000209 loss: 3.0462 (2.9516) grad_norm: 2.0478 (2.1635) time: 0.6326 [2021-03-27 22:45:05 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 410/1251] eta: 0:08:56 lr: 0.000209 loss: 3.1726 (2.9513) grad_norm: 2.0649 (2.1634) time: 0.6347 [2021-03-27 22:45:12 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 420/1251] eta: 0:08:50 lr: 0.000208 loss: 3.1726 (2.9573) grad_norm: 2.0815 (2.1641) time: 0.6349 [2021-03-27 22:45:18 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 430/1251] eta: 0:08:43 lr: 0.000208 loss: 3.1575 (2.9588) grad_norm: 2.1902 (2.1643) time: 0.6275 [2021-03-27 22:45:24 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 440/1251] eta: 0:08:36 lr: 0.000208 loss: 3.1621 (2.9659) grad_norm: 2.2018 (2.1661) time: 0.6245 [2021-03-27 22:45:31 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 450/1251] eta: 0:08:30 lr: 0.000208 loss: 3.2308 (2.9695) grad_norm: 2.2890 (2.1695) time: 0.6347 [2021-03-27 22:45:37 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 460/1251] eta: 0:08:23 lr: 0.000208 loss: 3.2729 (2.9729) grad_norm: 2.2340 (2.1695) time: 0.6322 [2021-03-27 22:45:43 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 470/1251] eta: 0:08:17 lr: 0.000208 loss: 3.1720 (2.9751) grad_norm: 2.1356 (2.1733) time: 0.6278 [2021-03-27 22:45:49 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 480/1251] eta: 0:08:10 lr: 0.000208 loss: 3.0980 (2.9702) grad_norm: 2.2108 (2.1750) time: 0.6254 [2021-03-27 22:45:56 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 490/1251] eta: 0:08:04 lr: 0.000208 loss: 2.8410 (2.9640) grad_norm: 2.1670 (2.1740) time: 0.6207 [2021-03-27 22:46:02 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 500/1251] eta: 0:07:57 lr: 0.000208 loss: 2.8558 (2.9586) grad_norm: 2.1196 (2.1761) time: 0.6238 [2021-03-27 22:46:08 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 510/1251] eta: 0:07:51 lr: 0.000208 loss: 3.0372 (2.9607) grad_norm: 2.0338 (2.1759) time: 0.6289 [2021-03-27 22:46:14 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 520/1251] eta: 0:07:44 lr: 0.000208 loss: 3.1484 (2.9627) grad_norm: 2.1203 (2.1748) time: 0.6313 [2021-03-27 22:46:21 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 530/1251] eta: 0:07:38 lr: 0.000208 loss: 3.1484 (2.9636) grad_norm: 2.1969 (2.1777) time: 0.6246 [2021-03-27 22:46:27 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 540/1251] eta: 0:07:31 lr: 0.000208 loss: 3.2430 (2.9678) grad_norm: 2.1745 (2.1764) time: 0.6241 [2021-03-27 22:46:33 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 550/1251] eta: 0:07:25 lr: 0.000208 loss: 3.1170 (2.9661) grad_norm: 2.0265 (2.1738) time: 0.6354 [2021-03-27 22:46:40 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 560/1251] eta: 0:07:19 lr: 0.000208 loss: 3.0501 (2.9686) grad_norm: 2.0325 (2.1728) time: 0.6374 [2021-03-27 22:46:46 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 570/1251] eta: 0:07:12 lr: 0.000208 loss: 2.9953 (2.9658) grad_norm: 2.1006 (2.1710) time: 0.6331 [2021-03-27 22:46:52 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 580/1251] eta: 0:07:06 lr: 0.000208 loss: 2.7414 (2.9599) grad_norm: 2.0862 (2.1693) time: 0.6273 [2021-03-27 22:46:58 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 590/1251] eta: 0:06:59 lr: 0.000208 loss: 3.1469 (2.9665) grad_norm: 2.1180 (2.1703) time: 0.6222 [2021-03-27 22:47:05 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 600/1251] eta: 0:06:53 lr: 0.000208 loss: 3.1584 (2.9678) grad_norm: 2.1818 (2.1714) time: 0.6241 [2021-03-27 22:47:11 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 610/1251] eta: 0:06:46 lr: 0.000208 loss: 3.2008 (2.9712) grad_norm: 2.2793 (2.1742) time: 0.6266 [2021-03-27 22:47:17 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 620/1251] eta: 0:06:40 lr: 0.000208 loss: 3.3034 (2.9736) grad_norm: 2.3459 (2.1844) time: 0.6253 [2021-03-27 22:47:23 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 630/1251] eta: 0:06:34 lr: 0.000208 loss: 3.1580 (2.9756) grad_norm: 2.2408 (2.1865) time: 0.6235 [2021-03-27 22:47:30 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 640/1251] eta: 0:06:27 lr: 0.000208 loss: 3.0674 (2.9727) grad_norm: 2.0823 (2.1844) time: 0.6253 [2021-03-27 22:47:36 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 650/1251] eta: 0:06:21 lr: 0.000208 loss: 3.0792 (2.9739) grad_norm: 2.1117 (2.1846) time: 0.6315 [2021-03-27 22:47:42 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 660/1251] eta: 0:06:14 lr: 0.000208 loss: 3.1557 (2.9719) grad_norm: 2.1117 (2.1842) time: 0.6344 [2021-03-27 22:47:49 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 670/1251] eta: 0:06:08 lr: 0.000208 loss: 2.9548 (2.9741) grad_norm: 2.1031 (2.1862) time: 0.6315 [2021-03-27 22:47:55 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 680/1251] eta: 0:06:02 lr: 0.000208 loss: 3.0600 (2.9740) grad_norm: 2.1679 (2.1861) time: 0.6312 [2021-03-27 22:48:01 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 690/1251] eta: 0:05:55 lr: 0.000208 loss: 2.9793 (2.9715) grad_norm: 2.1679 (2.1853) time: 0.6315 [2021-03-27 22:48:08 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 700/1251] eta: 0:05:49 lr: 0.000208 loss: 3.0639 (2.9741) grad_norm: 2.1739 (2.1864) time: 0.6312 [2021-03-27 22:48:14 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 710/1251] eta: 0:05:42 lr: 0.000208 loss: 3.0858 (2.9750) grad_norm: 2.1398 (2.1875) time: 0.6256 [2021-03-27 22:48:20 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 720/1251] eta: 0:05:36 lr: 0.000207 loss: 3.0858 (2.9771) grad_norm: 2.0570 (2.1852) time: 0.6287 [2021-03-27 22:48:26 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 730/1251] eta: 0:05:30 lr: 0.000207 loss: 3.1073 (2.9805) grad_norm: 2.0277 (2.1836) time: 0.6272 [2021-03-27 22:48:33 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 740/1251] eta: 0:05:23 lr: 0.000207 loss: 3.1175 (2.9815) grad_norm: 2.0275 (2.1821) time: 0.6272 [2021-03-27 22:48:39 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 750/1251] eta: 0:05:17 lr: 0.000207 loss: 3.1100 (2.9827) grad_norm: 1.9433 (2.1788) time: 0.6327 [2021-03-27 22:48:45 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 760/1251] eta: 0:05:11 lr: 0.000207 loss: 3.1201 (2.9839) grad_norm: 2.0329 (2.1786) time: 0.6331 [2021-03-27 22:48:52 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 770/1251] eta: 0:05:04 lr: 0.000207 loss: 3.2390 (2.9843) grad_norm: 2.0752 (2.1784) time: 0.6285 [2021-03-27 22:48:58 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 780/1251] eta: 0:04:58 lr: 0.000207 loss: 3.1409 (2.9818) grad_norm: 2.0379 (2.1771) time: 0.6231 [2021-03-27 22:49:04 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 790/1251] eta: 0:04:52 lr: 0.000207 loss: 2.7607 (2.9803) grad_norm: 2.1961 (2.1774) time: 0.6265 [2021-03-27 22:49:10 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 800/1251] eta: 0:04:45 lr: 0.000207 loss: 2.8780 (2.9789) grad_norm: 2.1961 (2.1760) time: 0.6258 [2021-03-27 22:49:17 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 810/1251] eta: 0:04:39 lr: 0.000207 loss: 3.1997 (2.9841) grad_norm: 2.0689 (2.1757) time: 0.6339 [2021-03-27 22:49:23 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 820/1251] eta: 0:04:32 lr: 0.000207 loss: 3.2800 (2.9838) grad_norm: 2.0689 (2.1749) time: 0.6348 [2021-03-27 22:49:29 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 830/1251] eta: 0:04:26 lr: 0.000207 loss: 3.0710 (2.9847) grad_norm: 2.0529 (2.1744) time: 0.6287 [2021-03-27 22:49:36 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 840/1251] eta: 0:04:20 lr: 0.000207 loss: 3.0791 (2.9854) grad_norm: 2.0937 (2.1735) time: 0.6296 [2021-03-27 22:49:42 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 850/1251] eta: 0:04:13 lr: 0.000207 loss: 3.0791 (2.9859) grad_norm: 2.0937 (2.1724) time: 0.6274 [2021-03-27 22:49:48 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 860/1251] eta: 0:04:07 lr: 0.000207 loss: 3.1091 (2.9864) grad_norm: 2.0752 (2.1728) time: 0.6243 [2021-03-27 22:49:55 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 870/1251] eta: 0:04:01 lr: 0.000207 loss: 3.1091 (2.9862) grad_norm: 2.0752 (2.1719) time: 0.6318 [2021-03-27 22:50:01 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 880/1251] eta: 0:03:54 lr: 0.000207 loss: 3.0687 (2.9853) grad_norm: 1.9967 (2.1741) time: 0.6338 [2021-03-27 22:50:07 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 890/1251] eta: 0:03:48 lr: 0.000207 loss: 3.0128 (2.9846) grad_norm: 2.1641 (2.1750) time: 0.6274 [2021-03-27 22:50:13 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 900/1251] eta: 0:03:42 lr: 0.000207 loss: 3.0569 (2.9846) grad_norm: 2.1340 (2.1744) time: 0.6272 [2021-03-27 22:50:20 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 910/1251] eta: 0:03:35 lr: 0.000207 loss: 2.9033 (2.9816) grad_norm: 2.0615 (2.1749) time: 0.6250 [2021-03-27 22:50:26 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 920/1251] eta: 0:03:29 lr: 0.000207 loss: 3.0519 (2.9833) grad_norm: 2.0213 (2.1732) time: 0.6282 [2021-03-27 22:50:32 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 930/1251] eta: 0:03:23 lr: 0.000207 loss: 3.1578 (2.9827) grad_norm: 2.0296 (2.1732) time: 0.6271 [2021-03-27 22:50:39 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 940/1251] eta: 0:03:16 lr: 0.000207 loss: 3.1199 (2.9813) grad_norm: 2.0622 (2.1721) time: 0.6279 [2021-03-27 22:50:45 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 950/1251] eta: 0:03:10 lr: 0.000207 loss: 2.7907 (2.9799) grad_norm: 2.0498 (2.1718) time: 0.6306 [2021-03-27 22:50:51 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 960/1251] eta: 0:03:04 lr: 0.000207 loss: 3.0337 (2.9812) grad_norm: 2.0929 (2.1712) time: 0.6305 [2021-03-27 22:50:57 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 970/1251] eta: 0:02:57 lr: 0.000207 loss: 3.1383 (2.9805) grad_norm: 2.0585 (2.1738) time: 0.6314 [2021-03-27 22:51:04 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 980/1251] eta: 0:02:51 lr: 0.000207 loss: 3.1890 (2.9825) grad_norm: 2.0400 (2.1741) time: 0.6305 [2021-03-27 22:51:10 swin_base_patch4_window7_224] INFO: Epoch: [211] [ 990/1251] eta: 0:02:45 lr: 0.000207 loss: 3.1703 (2.9824) grad_norm: 2.1263 (2.1763) time: 0.6255 [2021-03-27 22:51:16 swin_base_patch4_window7_224] INFO: Epoch: [211] [1000/1251] eta: 0:02:38 lr: 0.000207 loss: 3.0972 (2.9830) grad_norm: 2.1030 (2.1763) time: 0.6212 [2021-03-27 22:51:22 swin_base_patch4_window7_224] INFO: Epoch: [211] [1010/1251] eta: 0:02:32 lr: 0.000207 loss: 3.0972 (2.9832) grad_norm: 2.0687 (2.1761) time: 0.6259 [2021-03-27 22:51:29 swin_base_patch4_window7_224] INFO: Epoch: [211] [1020/1251] eta: 0:02:26 lr: 0.000206 loss: 3.1150 (2.9842) grad_norm: 2.1454 (2.1767) time: 0.6312 [2021-03-27 22:51:35 swin_base_patch4_window7_224] INFO: Epoch: [211] [1030/1251] eta: 0:02:19 lr: 0.000206 loss: 3.0085 (2.9839) grad_norm: 2.2097 (2.1773) time: 0.6305 [2021-03-27 22:51:41 swin_base_patch4_window7_224] INFO: Epoch: [211] [1040/1251] eta: 0:02:13 lr: 0.000206 loss: 2.9870 (2.9827) grad_norm: 2.1831 (2.1782) time: 0.6266 [2021-03-27 22:51:48 swin_base_patch4_window7_224] INFO: Epoch: [211] [1050/1251] eta: 0:02:07 lr: 0.000206 loss: 3.0025 (2.9832) grad_norm: 2.1814 (2.1781) time: 0.6245 [2021-03-27 22:51:54 swin_base_patch4_window7_224] INFO: Epoch: [211] [1060/1251] eta: 0:02:00 lr: 0.000206 loss: 3.1432 (2.9839) grad_norm: 2.0398 (2.1772) time: 0.6266 [2021-03-27 22:52:00 swin_base_patch4_window7_224] INFO: Epoch: [211] [1070/1251] eta: 0:01:54 lr: 0.000206 loss: 3.0653 (2.9853) grad_norm: 1.9963 (2.1766) time: 0.6232 [2021-03-27 22:52:06 swin_base_patch4_window7_224] INFO: Epoch: [211] [1080/1251] eta: 0:01:48 lr: 0.000206 loss: 2.9877 (2.9833) grad_norm: 2.1078 (inf) time: 0.6166 [2021-03-27 22:52:12 swin_base_patch4_window7_224] INFO: Epoch: [211] [1090/1251] eta: 0:01:41 lr: 0.000206 loss: 2.9043 (2.9822) grad_norm: 2.2006 (inf) time: 0.6199 [2021-03-27 22:52:19 swin_base_patch4_window7_224] INFO: Epoch: [211] [1100/1251] eta: 0:01:35 lr: 0.000206 loss: 2.9428 (2.9798) grad_norm: 2.3003 (inf) time: 0.6231 [2021-03-27 22:52:25 swin_base_patch4_window7_224] INFO: Epoch: [211] [1110/1251] eta: 0:01:29 lr: 0.000206 loss: 2.9222 (2.9786) grad_norm: 2.1708 (inf) time: 0.6309 [2021-03-27 22:52:31 swin_base_patch4_window7_224] INFO: Epoch: [211] [1120/1251] eta: 0:01:22 lr: 0.000206 loss: 2.9730 (2.9776) grad_norm: 2.0608 (inf) time: 0.6291 [2021-03-27 22:52:38 swin_base_patch4_window7_224] INFO: Epoch: [211] [1130/1251] eta: 0:01:16 lr: 0.000206 loss: 3.0032 (2.9783) grad_norm: 2.0408 (inf) time: 0.6208 [2021-03-27 22:52:44 swin_base_patch4_window7_224] INFO: Epoch: [211] [1140/1251] eta: 0:01:10 lr: 0.000206 loss: 3.0746 (2.9780) grad_norm: 2.0569 (inf) time: 0.6226 [2021-03-27 22:52:50 swin_base_patch4_window7_224] INFO: Epoch: [211] [1150/1251] eta: 0:01:03 lr: 0.000206 loss: 2.9860 (2.9770) grad_norm: 2.0778 (inf) time: 0.6259 [2021-03-27 22:52:56 swin_base_patch4_window7_224] INFO: Epoch: [211] [1160/1251] eta: 0:00:57 lr: 0.000206 loss: 2.9915 (2.9777) grad_norm: 2.1665 (inf) time: 0.6247 [2021-03-27 22:53:03 swin_base_patch4_window7_224] INFO: Epoch: [211] [1170/1251] eta: 0:00:51 lr: 0.000206 loss: 3.1282 (2.9781) grad_norm: 2.2769 (inf) time: 0.6266 [2021-03-27 22:53:09 swin_base_patch4_window7_224] INFO: Epoch: [211] [1180/1251] eta: 0:00:44 lr: 0.000206 loss: 3.0343 (2.9768) grad_norm: 2.1186 (inf) time: 0.6253 [2021-03-27 22:53:15 swin_base_patch4_window7_224] INFO: Epoch: [211] [1190/1251] eta: 0:00:38 lr: 0.000206 loss: 2.7458 (2.9756) grad_norm: 2.1062 (inf) time: 0.6248 [2021-03-27 22:53:21 swin_base_patch4_window7_224] INFO: Epoch: [211] [1200/1251] eta: 0:00:32 lr: 0.000206 loss: 2.9645 (2.9741) grad_norm: 2.0334 (inf) time: 0.6370 [2021-03-27 22:53:28 swin_base_patch4_window7_224] INFO: Epoch: [211] [1210/1251] eta: 0:00:25 lr: 0.000206 loss: 2.9645 (2.9740) grad_norm: 2.0046 (inf) time: 0.6323 [2021-03-27 22:53:34 swin_base_patch4_window7_224] INFO: Epoch: [211] [1220/1251] eta: 0:00:19 lr: 0.000206 loss: 2.7894 (2.9734) grad_norm: 2.0995 (inf) time: 0.6240 [2021-03-27 22:53:40 swin_base_patch4_window7_224] INFO: Epoch: [211] [1230/1251] eta: 0:00:13 lr: 0.000206 loss: 3.1156 (2.9748) grad_norm: 2.1054 (inf) time: 0.6231 [2021-03-27 22:53:46 swin_base_patch4_window7_224] INFO: Epoch: [211] [1240/1251] eta: 0:00:06 lr: 0.000206 loss: 3.1156 (2.9745) grad_norm: 2.1616 (inf) time: 0.6261 [2021-03-27 22:53:53 swin_base_patch4_window7_224] INFO: Epoch: [211] [1250/1251] eta: 0:00:00 lr: 0.000206 loss: 3.0487 (2.9759) grad_norm: 2.1674 (inf) time: 0.6239 [2021-03-27 22:54:02 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:19 loss: 0.8761 (0.8761) acc1: 81.2500 (81.2500) acc5: 93.7500 (93.7500) [2021-03-27 22:54:04 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8547 (0.8054) acc1: 82.8125 (80.3977) acc5: 95.3125 (95.8807) [2021-03-27 22:54:06 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8084 (0.8159) acc1: 79.6875 (80.2827) acc5: 95.3125 (96.0565) [2021-03-27 22:54:09 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7664 (0.8073) acc1: 79.6875 (80.8972) acc5: 95.3125 (96.3710) [2021-03-27 22:54:11 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7388 (0.8039) acc1: 82.8125 (81.1357) acc5: 95.3125 (96.3034) [2021-03-27 22:54:12 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8039 (0.8154) acc1: 82.8125 (81.0240) acc5: 95.3125 (96.1920) [2021-03-27 22:54:21 swin_base_patch4_window7_224] INFO: * Acc@1 81.480 Acc@5 95.922 loss 0.802 [2021-03-27 22:54:21 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.5% [2021-03-27 22:54:21 swin_base_patch4_window7_224] INFO: Max accuracy: 81.54% [2021-03-27 22:54:25 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 0/1251] eta: 1:26:49 lr: 0.000206 loss: 1.9340 (1.9340) grad_norm: 1.8277 (1.8277) time: 4.1640 [2021-03-27 22:54:32 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 10/1251] eta: 0:19:39 lr: 0.000206 loss: 2.8000 (2.7233) grad_norm: 2.1663 (2.2385) time: 0.9503 [2021-03-27 22:54:38 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 20/1251] eta: 0:16:17 lr: 0.000206 loss: 2.9604 (2.8784) grad_norm: 2.1663 (2.2382) time: 0.6253 [2021-03-27 22:54:44 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 30/1251] eta: 0:15:04 lr: 0.000206 loss: 3.0360 (2.8547) grad_norm: 2.1345 (2.2082) time: 0.6251 [2021-03-27 22:54:50 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 40/1251] eta: 0:14:24 lr: 0.000206 loss: 2.6780 (2.8313) grad_norm: 2.1460 (2.2216) time: 0.6292 [2021-03-27 22:54:57 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 50/1251] eta: 0:13:56 lr: 0.000206 loss: 2.8750 (2.8673) grad_norm: 2.2197 (2.2519) time: 0.6292 [2021-03-27 22:55:03 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 60/1251] eta: 0:13:36 lr: 0.000206 loss: 2.9884 (2.8645) grad_norm: 2.2197 (2.2620) time: 0.6290 [2021-03-27 22:55:09 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 70/1251] eta: 0:13:24 lr: 0.000205 loss: 3.2186 (2.9045) grad_norm: 2.1477 (2.3335) time: 0.6401 [2021-03-27 22:55:16 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 80/1251] eta: 0:13:11 lr: 0.000205 loss: 3.2186 (2.9280) grad_norm: 2.2382 (2.3527) time: 0.6455 [2021-03-27 22:55:22 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 90/1251] eta: 0:12:58 lr: 0.000205 loss: 2.9462 (2.9139) grad_norm: 2.2172 (2.3298) time: 0.6350 [2021-03-27 22:55:29 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 100/1251] eta: 0:12:48 lr: 0.000205 loss: 2.8456 (2.9282) grad_norm: 2.0842 (2.3405) time: 0.6344 [2021-03-27 22:55:35 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 110/1251] eta: 0:12:37 lr: 0.000205 loss: 3.0357 (2.9268) grad_norm: 2.1038 (2.3238) time: 0.6324 [2021-03-27 22:55:41 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 120/1251] eta: 0:12:28 lr: 0.000205 loss: 3.1409 (2.9297) grad_norm: 2.1038 (2.3122) time: 0.6298 [2021-03-27 22:55:47 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 130/1251] eta: 0:12:18 lr: 0.000205 loss: 3.2536 (2.9633) grad_norm: 2.0578 (2.2963) time: 0.6308 [2021-03-27 22:55:54 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 140/1251] eta: 0:12:09 lr: 0.000205 loss: 3.2786 (2.9715) grad_norm: 1.9773 (2.2751) time: 0.6282 [2021-03-27 22:56:00 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 150/1251] eta: 0:12:00 lr: 0.000205 loss: 2.9552 (2.9714) grad_norm: 1.9555 (2.2678) time: 0.6251 [2021-03-27 22:56:06 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 160/1251] eta: 0:11:51 lr: 0.000205 loss: 2.9552 (2.9728) grad_norm: 2.0719 (2.2594) time: 0.6207 [2021-03-27 22:56:12 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 170/1251] eta: 0:11:43 lr: 0.000205 loss: 3.0341 (2.9770) grad_norm: 2.0587 (2.2494) time: 0.6215 [2021-03-27 22:56:19 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 180/1251] eta: 0:11:35 lr: 0.000205 loss: 2.9901 (2.9687) grad_norm: 2.1337 (2.2471) time: 0.6232 [2021-03-27 22:56:25 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 190/1251] eta: 0:11:27 lr: 0.000205 loss: 3.0344 (2.9794) grad_norm: 2.2027 (2.2546) time: 0.6232 [2021-03-27 22:56:31 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 200/1251] eta: 0:11:20 lr: 0.000205 loss: 3.1430 (2.9838) grad_norm: 2.1718 (2.2523) time: 0.6357 [2021-03-27 22:56:38 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 210/1251] eta: 0:11:13 lr: 0.000205 loss: 2.9019 (2.9811) grad_norm: 2.0477 (2.2415) time: 0.6380 [2021-03-27 22:56:44 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 220/1251] eta: 0:11:05 lr: 0.000205 loss: 2.8613 (2.9777) grad_norm: 2.0037 (2.2349) time: 0.6260 [2021-03-27 22:56:50 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 230/1251] eta: 0:10:58 lr: 0.000205 loss: 2.9853 (2.9815) grad_norm: 2.0883 (2.2346) time: 0.6239 [2021-03-27 22:56:56 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 240/1251] eta: 0:10:51 lr: 0.000205 loss: 2.9849 (2.9712) grad_norm: 2.2743 (2.2409) time: 0.6261 [2021-03-27 22:57:03 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 250/1251] eta: 0:10:44 lr: 0.000205 loss: 3.0349 (2.9725) grad_norm: 2.2452 (2.2394) time: 0.6320 [2021-03-27 22:57:09 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 260/1251] eta: 0:10:37 lr: 0.000205 loss: 2.8493 (2.9628) grad_norm: 2.2203 (2.2402) time: 0.6334 [2021-03-27 22:57:15 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 270/1251] eta: 0:10:30 lr: 0.000205 loss: 2.7084 (2.9571) grad_norm: 2.2203 (2.2417) time: 0.6334 [2021-03-27 22:57:22 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 280/1251] eta: 0:10:23 lr: 0.000205 loss: 2.7858 (2.9525) grad_norm: 2.2776 (2.2492) time: 0.6299 [2021-03-27 22:57:28 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 290/1251] eta: 0:10:16 lr: 0.000205 loss: 2.7988 (2.9531) grad_norm: 2.2432 (2.2467) time: 0.6259 [2021-03-27 22:57:34 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 300/1251] eta: 0:10:09 lr: 0.000205 loss: 3.0461 (2.9472) grad_norm: 2.1291 (2.2482) time: 0.6259 [2021-03-27 22:57:40 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 310/1251] eta: 0:10:02 lr: 0.000205 loss: 2.9943 (2.9446) grad_norm: 2.1656 (2.2487) time: 0.6236 [2021-03-27 22:57:47 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 320/1251] eta: 0:09:56 lr: 0.000205 loss: 2.7538 (2.9381) grad_norm: 2.0777 (2.2438) time: 0.6242 [2021-03-27 22:57:53 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 330/1251] eta: 0:09:49 lr: 0.000205 loss: 2.7293 (2.9332) grad_norm: 2.0777 (2.2410) time: 0.6268 [2021-03-27 22:57:59 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 340/1251] eta: 0:09:42 lr: 0.000205 loss: 2.7880 (2.9298) grad_norm: 2.1103 (2.2430) time: 0.6245 [2021-03-27 22:58:05 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 350/1251] eta: 0:09:35 lr: 0.000205 loss: 3.0828 (2.9354) grad_norm: 2.2067 (2.2446) time: 0.6275 [2021-03-27 22:58:12 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 360/1251] eta: 0:09:29 lr: 0.000205 loss: 3.1486 (2.9389) grad_norm: 2.2750 (2.2456) time: 0.6308 [2021-03-27 22:58:18 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 370/1251] eta: 0:09:22 lr: 0.000205 loss: 3.0392 (2.9393) grad_norm: 2.3256 (2.2471) time: 0.6329 [2021-03-27 22:58:24 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 380/1251] eta: 0:09:15 lr: 0.000204 loss: 2.9914 (2.9333) grad_norm: 2.1303 (2.2459) time: 0.6300 [2021-03-27 22:58:31 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 390/1251] eta: 0:09:09 lr: 0.000204 loss: 2.7348 (2.9295) grad_norm: 2.1453 (2.2462) time: 0.6273 [2021-03-27 22:58:37 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 400/1251] eta: 0:09:02 lr: 0.000204 loss: 2.9029 (2.9328) grad_norm: 2.1620 (2.2451) time: 0.6287 [2021-03-27 22:58:43 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 410/1251] eta: 0:08:56 lr: 0.000204 loss: 3.0352 (2.9358) grad_norm: 2.0899 (2.2422) time: 0.6263 [2021-03-27 22:58:49 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 420/1251] eta: 0:08:49 lr: 0.000204 loss: 3.0202 (2.9327) grad_norm: 2.0409 (2.2377) time: 0.6249 [2021-03-27 22:58:56 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 430/1251] eta: 0:08:42 lr: 0.000204 loss: 3.0202 (2.9306) grad_norm: 2.0293 (2.2362) time: 0.6213 [2021-03-27 22:59:02 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 440/1251] eta: 0:08:36 lr: 0.000204 loss: 3.0592 (2.9303) grad_norm: 2.0293 (2.2325) time: 0.6235 [2021-03-27 22:59:08 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 450/1251] eta: 0:08:29 lr: 0.000204 loss: 3.0694 (2.9351) grad_norm: 1.9895 (2.2306) time: 0.6239 [2021-03-27 22:59:14 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 460/1251] eta: 0:08:23 lr: 0.000204 loss: 3.0362 (2.9340) grad_norm: 2.0332 (2.2285) time: 0.6204 [2021-03-27 22:59:21 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 470/1251] eta: 0:08:16 lr: 0.000204 loss: 2.8627 (2.9358) grad_norm: 2.0740 (2.2269) time: 0.6249 [2021-03-27 22:59:27 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 480/1251] eta: 0:08:09 lr: 0.000204 loss: 2.9147 (2.9367) grad_norm: 2.0810 (2.2262) time: 0.6233 [2021-03-27 22:59:33 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 490/1251] eta: 0:08:03 lr: 0.000204 loss: 2.9588 (2.9352) grad_norm: 2.1115 (2.2241) time: 0.6175 [2021-03-27 22:59:39 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 500/1251] eta: 0:07:56 lr: 0.000204 loss: 2.9852 (2.9366) grad_norm: 2.1115 (2.2243) time: 0.6243 [2021-03-27 22:59:46 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 510/1251] eta: 0:07:50 lr: 0.000204 loss: 3.1831 (2.9376) grad_norm: 2.0686 (2.2251) time: 0.6293 [2021-03-27 22:59:52 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 520/1251] eta: 0:07:43 lr: 0.000204 loss: 3.1376 (2.9401) grad_norm: 2.0762 (2.2237) time: 0.6225 [2021-03-27 22:59:58 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 530/1251] eta: 0:07:37 lr: 0.000204 loss: 3.1207 (2.9414) grad_norm: 2.0408 (2.2185) time: 0.6193 [2021-03-27 23:00:04 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 540/1251] eta: 0:07:30 lr: 0.000204 loss: 3.0736 (2.9428) grad_norm: 2.1454 (2.2227) time: 0.6249 [2021-03-27 23:00:11 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 550/1251] eta: 0:07:24 lr: 0.000204 loss: 3.0736 (2.9459) grad_norm: 2.2787 (2.2224) time: 0.6390 [2021-03-27 23:00:17 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 560/1251] eta: 0:07:18 lr: 0.000204 loss: 3.1378 (2.9466) grad_norm: 2.1583 (2.2204) time: 0.6368 [2021-03-27 23:00:23 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 570/1251] eta: 0:07:11 lr: 0.000204 loss: 2.9323 (2.9473) grad_norm: 2.1406 (2.2270) time: 0.6246 [2021-03-27 23:00:29 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 580/1251] eta: 0:07:05 lr: 0.000204 loss: 2.9323 (2.9466) grad_norm: 2.1406 (2.2267) time: 0.6239 [2021-03-27 23:00:36 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 590/1251] eta: 0:06:58 lr: 0.000204 loss: 3.0755 (2.9478) grad_norm: 2.0218 (2.2284) time: 0.6224 [2021-03-27 23:00:42 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 600/1251] eta: 0:06:52 lr: 0.000204 loss: 3.1260 (2.9519) grad_norm: 2.1466 (2.2266) time: 0.6202 [2021-03-27 23:00:48 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 610/1251] eta: 0:06:45 lr: 0.000204 loss: 3.0486 (2.9522) grad_norm: 2.1040 (2.2273) time: 0.6220 [2021-03-27 23:00:55 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 620/1251] eta: 0:06:39 lr: 0.000204 loss: 3.0822 (2.9545) grad_norm: 2.1237 (2.2256) time: 0.6316 [2021-03-27 23:01:01 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 630/1251] eta: 0:06:33 lr: 0.000204 loss: 3.1117 (2.9537) grad_norm: 2.0600 (2.2224) time: 0.6312 [2021-03-27 23:01:07 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 640/1251] eta: 0:06:26 lr: 0.000204 loss: 2.9696 (2.9526) grad_norm: 2.0866 (2.2329) time: 0.6292 [2021-03-27 23:01:13 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 650/1251] eta: 0:06:20 lr: 0.000204 loss: 3.0327 (2.9549) grad_norm: 2.2783 (2.2305) time: 0.6322 [2021-03-27 23:01:20 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 660/1251] eta: 0:06:14 lr: 0.000204 loss: 3.3155 (2.9577) grad_norm: 1.9924 (2.2294) time: 0.6266 [2021-03-27 23:01:26 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 670/1251] eta: 0:06:07 lr: 0.000204 loss: 3.1778 (2.9608) grad_norm: 2.1413 (2.2291) time: 0.6240 [2021-03-27 23:01:32 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 680/1251] eta: 0:06:01 lr: 0.000203 loss: 3.0825 (2.9594) grad_norm: 2.1959 (2.2293) time: 0.6314 [2021-03-27 23:01:38 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 690/1251] eta: 0:05:55 lr: 0.000203 loss: 2.8303 (2.9569) grad_norm: 2.0380 (2.2261) time: 0.6292 [2021-03-27 23:01:45 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 700/1251] eta: 0:05:48 lr: 0.000203 loss: 2.8303 (2.9563) grad_norm: 2.0201 (2.2249) time: 0.6300 [2021-03-27 23:01:51 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 710/1251] eta: 0:05:42 lr: 0.000203 loss: 2.9644 (2.9587) grad_norm: 2.1309 (2.2244) time: 0.6385 [2021-03-27 23:01:58 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 720/1251] eta: 0:05:36 lr: 0.000203 loss: 3.0524 (2.9591) grad_norm: 2.1309 (2.2227) time: 0.6383 [2021-03-27 23:02:04 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 730/1251] eta: 0:05:29 lr: 0.000203 loss: 3.0335 (2.9585) grad_norm: 2.0482 (2.2212) time: 0.6328 [2021-03-27 23:02:10 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 740/1251] eta: 0:05:23 lr: 0.000203 loss: 3.0323 (2.9564) grad_norm: 2.0600 (2.2214) time: 0.6381 [2021-03-27 23:02:17 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 750/1251] eta: 0:05:17 lr: 0.000203 loss: 2.8833 (2.9565) grad_norm: 2.1666 (2.2216) time: 0.6388 [2021-03-27 23:02:23 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 760/1251] eta: 0:05:10 lr: 0.000203 loss: 2.8833 (2.9532) grad_norm: 2.0908 (2.2205) time: 0.6302 [2021-03-27 23:02:29 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 770/1251] eta: 0:05:04 lr: 0.000203 loss: 2.7604 (2.9526) grad_norm: 2.0513 (2.2190) time: 0.6336 [2021-03-27 23:02:36 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 780/1251] eta: 0:04:58 lr: 0.000203 loss: 2.8949 (2.9527) grad_norm: 2.0739 (2.2196) time: 0.6315 [2021-03-27 23:02:42 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 790/1251] eta: 0:04:51 lr: 0.000203 loss: 3.1434 (2.9560) grad_norm: 2.0321 (2.2164) time: 0.6249 [2021-03-27 23:02:48 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 800/1251] eta: 0:04:45 lr: 0.000203 loss: 3.1657 (2.9572) grad_norm: 2.0189 (2.2158) time: 0.6220 [2021-03-27 23:02:54 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 810/1251] eta: 0:04:39 lr: 0.000203 loss: 2.8836 (2.9571) grad_norm: 2.1499 (2.2216) time: 0.6254 [2021-03-27 23:03:01 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 820/1251] eta: 0:04:32 lr: 0.000203 loss: 2.8836 (2.9541) grad_norm: 2.1997 (2.2271) time: 0.6358 [2021-03-27 23:03:07 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 830/1251] eta: 0:04:26 lr: 0.000203 loss: 3.0333 (2.9536) grad_norm: 2.2941 (2.2285) time: 0.6428 [2021-03-27 23:03:14 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 840/1251] eta: 0:04:20 lr: 0.000203 loss: 3.0711 (2.9520) grad_norm: 2.1418 (2.2274) time: 0.6431 [2021-03-27 23:03:20 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 850/1251] eta: 0:04:13 lr: 0.000203 loss: 3.1242 (2.9543) grad_norm: 2.0427 (2.2287) time: 0.6357 [2021-03-27 23:03:26 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 860/1251] eta: 0:04:07 lr: 0.000203 loss: 3.0793 (2.9548) grad_norm: 2.1361 (2.2291) time: 0.6308 [2021-03-27 23:03:32 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 870/1251] eta: 0:04:01 lr: 0.000203 loss: 2.9205 (2.9540) grad_norm: 2.0914 (2.2273) time: 0.6256 [2021-03-27 23:03:39 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 880/1251] eta: 0:03:54 lr: 0.000203 loss: 3.1367 (2.9589) grad_norm: 2.0544 (2.2332) time: 0.6257 [2021-03-27 23:03:45 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 890/1251] eta: 0:03:48 lr: 0.000203 loss: 3.2819 (2.9586) grad_norm: 2.0640 (2.2320) time: 0.6300 [2021-03-27 23:03:51 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 900/1251] eta: 0:03:42 lr: 0.000203 loss: 2.9541 (2.9601) grad_norm: 2.0083 (2.2300) time: 0.6265 [2021-03-27 23:03:58 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 910/1251] eta: 0:03:35 lr: 0.000203 loss: 3.1073 (2.9614) grad_norm: 2.0915 (2.2314) time: 0.6257 [2021-03-27 23:04:04 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 920/1251] eta: 0:03:29 lr: 0.000203 loss: 3.1550 (2.9616) grad_norm: 2.1678 (2.2345) time: 0.6242 [2021-03-27 23:04:10 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 930/1251] eta: 0:03:23 lr: 0.000203 loss: 3.0870 (2.9638) grad_norm: 2.2567 (2.2352) time: 0.6226 [2021-03-27 23:04:16 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 940/1251] eta: 0:03:16 lr: 0.000203 loss: 3.0286 (2.9629) grad_norm: 2.1566 (2.2355) time: 0.6256 [2021-03-27 23:04:23 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 950/1251] eta: 0:03:10 lr: 0.000203 loss: 2.8688 (2.9616) grad_norm: 2.1429 (2.2346) time: 0.6295 [2021-03-27 23:04:29 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 960/1251] eta: 0:03:03 lr: 0.000203 loss: 2.8244 (2.9610) grad_norm: 2.1656 (2.2362) time: 0.6244 [2021-03-27 23:04:35 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 970/1251] eta: 0:02:57 lr: 0.000203 loss: 2.9841 (2.9614) grad_norm: 2.2082 (2.2390) time: 0.6241 [2021-03-27 23:04:41 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 980/1251] eta: 0:02:51 lr: 0.000202 loss: 2.8987 (2.9611) grad_norm: 2.2383 (2.2405) time: 0.6255 [2021-03-27 23:04:48 swin_base_patch4_window7_224] INFO: Epoch: [212] [ 990/1251] eta: 0:02:44 lr: 0.000202 loss: 2.8802 (2.9612) grad_norm: 2.3194 (2.2439) time: 0.6290 [2021-03-27 23:04:54 swin_base_patch4_window7_224] INFO: Epoch: [212] [1000/1251] eta: 0:02:38 lr: 0.000202 loss: 2.9787 (2.9616) grad_norm: 2.1182 (2.2425) time: 0.6357 [2021-03-27 23:05:00 swin_base_patch4_window7_224] INFO: Epoch: [212] [1010/1251] eta: 0:02:32 lr: 0.000202 loss: 3.0227 (2.9623) grad_norm: 2.1182 (2.2515) time: 0.6324 [2021-03-27 23:05:07 swin_base_patch4_window7_224] INFO: Epoch: [212] [1020/1251] eta: 0:02:26 lr: 0.000202 loss: 3.0227 (2.9605) grad_norm: 2.0726 (2.2496) time: 0.6305 [2021-03-27 23:05:13 swin_base_patch4_window7_224] INFO: Epoch: [212] [1030/1251] eta: 0:02:19 lr: 0.000202 loss: 2.7170 (2.9602) grad_norm: 2.0739 (2.2485) time: 0.6252 [2021-03-27 23:05:19 swin_base_patch4_window7_224] INFO: Epoch: [212] [1040/1251] eta: 0:02:13 lr: 0.000202 loss: 3.0109 (2.9613) grad_norm: 2.1495 (2.2504) time: 0.6201 [2021-03-27 23:05:25 swin_base_patch4_window7_224] INFO: Epoch: [212] [1050/1251] eta: 0:02:07 lr: 0.000202 loss: 3.0109 (2.9599) grad_norm: 2.0772 (2.2483) time: 0.6266 [2021-03-27 23:05:32 swin_base_patch4_window7_224] INFO: Epoch: [212] [1060/1251] eta: 0:02:00 lr: 0.000202 loss: 3.1172 (2.9613) grad_norm: 2.0960 (2.2493) time: 0.6263 [2021-03-27 23:05:38 swin_base_patch4_window7_224] INFO: Epoch: [212] [1070/1251] eta: 0:01:54 lr: 0.000202 loss: 3.1915 (2.9610) grad_norm: 2.2781 (2.2513) time: 0.6226 [2021-03-27 23:05:44 swin_base_patch4_window7_224] INFO: Epoch: [212] [1080/1251] eta: 0:01:48 lr: 0.000202 loss: 2.9675 (2.9605) grad_norm: 2.1965 (2.2512) time: 0.6232 [2021-03-27 23:05:50 swin_base_patch4_window7_224] INFO: Epoch: [212] [1090/1251] eta: 0:01:41 lr: 0.000202 loss: 2.9970 (2.9611) grad_norm: 2.0316 (2.2493) time: 0.6266 [2021-03-27 23:05:57 swin_base_patch4_window7_224] INFO: Epoch: [212] [1100/1251] eta: 0:01:35 lr: 0.000202 loss: 3.0013 (2.9606) grad_norm: 2.0087 (2.2484) time: 0.6267 [2021-03-27 23:06:03 swin_base_patch4_window7_224] INFO: Epoch: [212] [1110/1251] eta: 0:01:29 lr: 0.000202 loss: 2.9721 (2.9616) grad_norm: 2.0087 (2.2472) time: 0.6225 [2021-03-27 23:06:09 swin_base_patch4_window7_224] INFO: Epoch: [212] [1120/1251] eta: 0:01:22 lr: 0.000202 loss: 3.0839 (2.9623) grad_norm: 2.0075 (2.2482) time: 0.6230 [2021-03-27 23:06:15 swin_base_patch4_window7_224] INFO: Epoch: [212] [1130/1251] eta: 0:01:16 lr: 0.000202 loss: 2.6050 (2.9602) grad_norm: 2.1470 (2.2485) time: 0.6223 [2021-03-27 23:06:22 swin_base_patch4_window7_224] INFO: Epoch: [212] [1140/1251] eta: 0:01:10 lr: 0.000202 loss: 3.0585 (2.9614) grad_norm: 2.1485 (2.2473) time: 0.6215 [2021-03-27 23:06:28 swin_base_patch4_window7_224] INFO: Epoch: [212] [1150/1251] eta: 0:01:03 lr: 0.000202 loss: 3.0993 (2.9613) grad_norm: 2.0914 (2.2473) time: 0.6207 [2021-03-27 23:06:34 swin_base_patch4_window7_224] INFO: Epoch: [212] [1160/1251] eta: 0:00:57 lr: 0.000202 loss: 3.1466 (2.9621) grad_norm: 2.1132 (2.2462) time: 0.6232 [2021-03-27 23:06:40 swin_base_patch4_window7_224] INFO: Epoch: [212] [1170/1251] eta: 0:00:51 lr: 0.000202 loss: 3.0419 (2.9608) grad_norm: 2.1568 (2.2476) time: 0.6317 [2021-03-27 23:06:47 swin_base_patch4_window7_224] INFO: Epoch: [212] [1180/1251] eta: 0:00:44 lr: 0.000202 loss: 3.0419 (2.9614) grad_norm: 2.2471 (2.2493) time: 0.6293 [2021-03-27 23:06:53 swin_base_patch4_window7_224] INFO: Epoch: [212] [1190/1251] eta: 0:00:38 lr: 0.000202 loss: 3.2160 (2.9635) grad_norm: 2.0509 (2.2490) time: 0.6204 [2021-03-27 23:06:59 swin_base_patch4_window7_224] INFO: Epoch: [212] [1200/1251] eta: 0:00:32 lr: 0.000202 loss: 3.1474 (2.9634) grad_norm: 2.0633 (2.2477) time: 0.6236 [2021-03-27 23:07:05 swin_base_patch4_window7_224] INFO: Epoch: [212] [1210/1251] eta: 0:00:25 lr: 0.000202 loss: 3.1005 (2.9649) grad_norm: 2.0491 (2.2462) time: 0.6260 [2021-03-27 23:07:12 swin_base_patch4_window7_224] INFO: Epoch: [212] [1220/1251] eta: 0:00:19 lr: 0.000202 loss: 3.1972 (2.9661) grad_norm: 2.0491 (2.2474) time: 0.6227 [2021-03-27 23:07:18 swin_base_patch4_window7_224] INFO: Epoch: [212] [1230/1251] eta: 0:00:13 lr: 0.000202 loss: 3.1972 (2.9662) grad_norm: 2.0761 (2.2458) time: 0.6204 [2021-03-27 23:07:24 swin_base_patch4_window7_224] INFO: Epoch: [212] [1240/1251] eta: 0:00:06 lr: 0.000202 loss: 2.9479 (2.9655) grad_norm: 2.0316 (2.2445) time: 0.6240 [2021-03-27 23:07:30 swin_base_patch4_window7_224] INFO: Epoch: [212] [1250/1251] eta: 0:00:00 lr: 0.000202 loss: 2.9479 (2.9647) grad_norm: 2.0408 (2.2430) time: 0.6242 [2021-03-27 23:07:39 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:06 loss: 0.6702 (0.6702) acc1: 84.3750 (84.3750) acc5: 96.8750 (96.8750) [2021-03-27 23:07:42 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.9069 (0.8380) acc1: 79.6875 (79.9716) acc5: 96.8750 (95.5966) [2021-03-27 23:07:44 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7821 (0.8172) acc1: 79.6875 (80.2083) acc5: 96.8750 (95.8333) [2021-03-27 23:07:46 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7821 (0.8140) acc1: 81.2500 (80.2923) acc5: 96.8750 (96.2198) [2021-03-27 23:07:48 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7863 (0.8049) acc1: 81.2500 (80.4116) acc5: 96.8750 (96.2271) [2021-03-27 23:07:49 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7474 (0.8040) acc1: 81.2500 (80.8000) acc5: 96.2264 (96.1280) [2021-03-27 23:08:00 swin_base_patch4_window7_224] INFO: * Acc@1 81.502 Acc@5 95.896 loss 0.798 [2021-03-27 23:08:00 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.5% [2021-03-27 23:08:00 swin_base_patch4_window7_224] INFO: Max accuracy: 81.54% [2021-03-27 23:08:04 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 0/1251] eta: 1:31:52 lr: 0.000202 loss: 3.7346 (3.7346) grad_norm: 2.6247 (2.6247) time: 4.4069 [2021-03-27 23:08:10 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 10/1251] eta: 0:20:23 lr: 0.000202 loss: 3.4049 (3.2736) grad_norm: 2.2882 (2.3009) time: 0.9856 [2021-03-27 23:08:17 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 20/1251] eta: 0:16:47 lr: 0.000202 loss: 3.1772 (3.1012) grad_norm: 2.1451 (2.2034) time: 0.6386 [2021-03-27 23:08:23 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 30/1251] eta: 0:15:26 lr: 0.000202 loss: 2.8307 (2.9778) grad_norm: 2.0212 (2.1803) time: 0.6336 [2021-03-27 23:08:29 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 40/1251] eta: 0:14:41 lr: 0.000201 loss: 2.7935 (2.9368) grad_norm: 2.0552 (2.1851) time: 0.6337 [2021-03-27 23:08:36 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 50/1251] eta: 0:14:08 lr: 0.000201 loss: 2.9071 (2.9306) grad_norm: 2.1459 (2.2021) time: 0.6269 [2021-03-27 23:08:42 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 60/1251] eta: 0:13:44 lr: 0.000201 loss: 2.7935 (2.8984) grad_norm: 2.1410 (2.1920) time: 0.6199 [2021-03-27 23:08:48 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 70/1251] eta: 0:13:30 lr: 0.000201 loss: 2.8442 (2.9216) grad_norm: 2.0942 (2.1742) time: 0.6322 [2021-03-27 23:08:54 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 80/1251] eta: 0:13:14 lr: 0.000201 loss: 3.0549 (2.9226) grad_norm: 2.1296 (2.2235) time: 0.6346 [2021-03-27 23:09:01 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 90/1251] eta: 0:13:01 lr: 0.000201 loss: 2.8156 (2.9057) grad_norm: 2.1296 (2.2251) time: 0.6270 [2021-03-27 23:09:07 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 100/1251] eta: 0:12:49 lr: 0.000201 loss: 2.9094 (2.9080) grad_norm: 2.1658 (2.2382) time: 0.6293 [2021-03-27 23:09:13 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 110/1251] eta: 0:12:37 lr: 0.000201 loss: 2.9106 (2.9018) grad_norm: 2.3369 (2.2482) time: 0.6251 [2021-03-27 23:09:20 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 120/1251] eta: 0:12:28 lr: 0.000201 loss: 3.0965 (2.9225) grad_norm: 2.0925 (2.2342) time: 0.6276 [2021-03-27 23:09:26 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 130/1251] eta: 0:12:19 lr: 0.000201 loss: 3.2264 (2.9362) grad_norm: 2.1274 (2.2379) time: 0.6317 [2021-03-27 23:09:32 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 140/1251] eta: 0:12:10 lr: 0.000201 loss: 3.0263 (2.9406) grad_norm: 2.1995 (2.2386) time: 0.6303 [2021-03-27 23:09:39 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 150/1251] eta: 0:12:01 lr: 0.000201 loss: 3.0263 (2.9431) grad_norm: 2.1222 (2.2368) time: 0.6299 [2021-03-27 23:09:45 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 160/1251] eta: 0:11:53 lr: 0.000201 loss: 3.0640 (2.9435) grad_norm: 2.2016 (2.2454) time: 0.6294 [2021-03-27 23:09:51 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 170/1251] eta: 0:11:44 lr: 0.000201 loss: 2.7136 (2.9281) grad_norm: 2.2375 (2.2456) time: 0.6262 [2021-03-27 23:09:57 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 180/1251] eta: 0:11:36 lr: 0.000201 loss: 2.8840 (2.9360) grad_norm: 2.0689 (2.2434) time: 0.6238 [2021-03-27 23:10:04 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 190/1251] eta: 0:11:29 lr: 0.000201 loss: 3.0518 (2.9438) grad_norm: 2.1754 (2.2450) time: 0.6298 [2021-03-27 23:10:10 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 200/1251] eta: 0:11:22 lr: 0.000201 loss: 3.2026 (2.9522) grad_norm: 2.0659 (2.2365) time: 0.6376 [2021-03-27 23:10:16 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 210/1251] eta: 0:11:14 lr: 0.000201 loss: 3.1050 (2.9447) grad_norm: 2.1464 (2.2401) time: 0.6337 [2021-03-27 23:10:23 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 220/1251] eta: 0:11:08 lr: 0.000201 loss: 2.7041 (2.9437) grad_norm: 2.2137 (2.2394) time: 0.6345 [2021-03-27 23:10:29 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 230/1251] eta: 0:11:00 lr: 0.000201 loss: 2.9238 (2.9423) grad_norm: 2.2097 (2.2426) time: 0.6331 [2021-03-27 23:10:35 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 240/1251] eta: 0:10:53 lr: 0.000201 loss: 3.1710 (2.9511) grad_norm: 2.1874 (2.2382) time: 0.6284 [2021-03-27 23:10:42 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 250/1251] eta: 0:10:46 lr: 0.000201 loss: 3.1146 (2.9473) grad_norm: 2.1775 (2.2447) time: 0.6281 [2021-03-27 23:10:48 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 260/1251] eta: 0:10:38 lr: 0.000201 loss: 3.1146 (2.9607) grad_norm: 2.2709 (2.2451) time: 0.6261 [2021-03-27 23:10:54 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 270/1251] eta: 0:10:31 lr: 0.000201 loss: 3.2246 (2.9602) grad_norm: 2.1188 (2.2437) time: 0.6282 [2021-03-27 23:11:00 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 280/1251] eta: 0:10:24 lr: 0.000201 loss: 3.0087 (2.9615) grad_norm: 2.1188 (2.2436) time: 0.6235 [2021-03-27 23:11:07 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 290/1251] eta: 0:10:17 lr: 0.000201 loss: 3.0930 (2.9678) grad_norm: 2.0702 (2.2542) time: 0.6246 [2021-03-27 23:11:13 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 300/1251] eta: 0:10:10 lr: 0.000201 loss: 3.0399 (2.9662) grad_norm: 2.0277 (2.2573) time: 0.6265 [2021-03-27 23:11:19 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 310/1251] eta: 0:10:03 lr: 0.000201 loss: 3.0399 (2.9688) grad_norm: 1.9935 (2.2532) time: 0.6228 [2021-03-27 23:11:25 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 320/1251] eta: 0:09:56 lr: 0.000201 loss: 3.0202 (2.9669) grad_norm: 2.0033 (2.2517) time: 0.6257 [2021-03-27 23:11:32 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 330/1251] eta: 0:09:50 lr: 0.000201 loss: 3.0202 (2.9672) grad_norm: 2.0356 (2.2531) time: 0.6322 [2021-03-27 23:11:38 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 340/1251] eta: 0:09:43 lr: 0.000200 loss: 2.7820 (2.9598) grad_norm: 2.1869 (2.2517) time: 0.6311 [2021-03-27 23:11:44 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 350/1251] eta: 0:09:36 lr: 0.000200 loss: 2.7733 (2.9573) grad_norm: 2.0448 (2.2482) time: 0.6284 [2021-03-27 23:11:51 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 360/1251] eta: 0:09:30 lr: 0.000200 loss: 2.8952 (2.9568) grad_norm: 1.9849 (2.2434) time: 0.6314 [2021-03-27 23:11:57 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 370/1251] eta: 0:09:23 lr: 0.000200 loss: 2.9831 (2.9595) grad_norm: 2.1272 (2.2430) time: 0.6304 [2021-03-27 23:12:03 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 380/1251] eta: 0:09:17 lr: 0.000200 loss: 3.0732 (2.9620) grad_norm: 2.2252 (2.2475) time: 0.6324 [2021-03-27 23:12:10 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 390/1251] eta: 0:09:10 lr: 0.000200 loss: 3.0131 (2.9613) grad_norm: 2.2252 (2.2473) time: 0.6339 [2021-03-27 23:12:16 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 400/1251] eta: 0:09:03 lr: 0.000200 loss: 3.1066 (2.9634) grad_norm: 2.0663 (2.2423) time: 0.6316 [2021-03-27 23:12:22 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 410/1251] eta: 0:08:57 lr: 0.000200 loss: 3.1505 (2.9661) grad_norm: 2.1486 (2.2451) time: 0.6266 [2021-03-27 23:12:28 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 420/1251] eta: 0:08:50 lr: 0.000200 loss: 3.1129 (2.9646) grad_norm: 2.2128 (2.2458) time: 0.6208 [2021-03-27 23:12:35 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 430/1251] eta: 0:08:43 lr: 0.000200 loss: 2.9468 (2.9659) grad_norm: 2.2607 (2.2464) time: 0.6235 [2021-03-27 23:12:41 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 440/1251] eta: 0:08:37 lr: 0.000200 loss: 3.0410 (2.9636) grad_norm: 2.3571 (2.2532) time: 0.6250 [2021-03-27 23:12:47 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 450/1251] eta: 0:08:30 lr: 0.000200 loss: 2.9848 (2.9578) grad_norm: 2.2851 (2.2526) time: 0.6246 [2021-03-27 23:12:53 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 460/1251] eta: 0:08:23 lr: 0.000200 loss: 2.7616 (2.9555) grad_norm: 2.2756 (2.2559) time: 0.6230 [2021-03-27 23:13:00 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 470/1251] eta: 0:08:17 lr: 0.000200 loss: 2.8872 (2.9501) grad_norm: 2.3149 (2.2577) time: 0.6210 [2021-03-27 23:13:06 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 480/1251] eta: 0:08:10 lr: 0.000200 loss: 2.8872 (2.9468) grad_norm: 2.1618 (2.2574) time: 0.6226 [2021-03-27 23:13:12 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 490/1251] eta: 0:08:04 lr: 0.000200 loss: 2.8817 (2.9456) grad_norm: 2.0492 (2.2551) time: 0.6258 [2021-03-27 23:13:18 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 500/1251] eta: 0:07:57 lr: 0.000200 loss: 2.8060 (2.9420) grad_norm: 2.2247 (2.2583) time: 0.6263 [2021-03-27 23:13:25 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 510/1251] eta: 0:07:51 lr: 0.000200 loss: 2.8175 (2.9426) grad_norm: 2.2247 (2.2572) time: 0.6274 [2021-03-27 23:13:31 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 520/1251] eta: 0:07:44 lr: 0.000200 loss: 3.1267 (2.9425) grad_norm: 2.1017 (2.2586) time: 0.6309 [2021-03-27 23:13:37 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 530/1251] eta: 0:07:38 lr: 0.000200 loss: 3.1107 (2.9439) grad_norm: 2.1684 (2.2574) time: 0.6275 [2021-03-27 23:13:43 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 540/1251] eta: 0:07:31 lr: 0.000200 loss: 2.9707 (2.9442) grad_norm: 2.1173 (2.2556) time: 0.6257 [2021-03-27 23:13:50 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 550/1251] eta: 0:07:25 lr: 0.000200 loss: 2.9020 (2.9441) grad_norm: 2.1404 (2.2595) time: 0.6377 [2021-03-27 23:13:56 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 560/1251] eta: 0:07:19 lr: 0.000200 loss: 3.0172 (2.9433) grad_norm: 2.1768 (2.2592) time: 0.6429 [2021-03-27 23:14:03 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 570/1251] eta: 0:07:12 lr: 0.000200 loss: 3.0611 (2.9458) grad_norm: 2.1593 (2.2577) time: 0.6326 [2021-03-27 23:14:09 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 580/1251] eta: 0:07:06 lr: 0.000200 loss: 3.2037 (2.9505) grad_norm: 2.1013 (2.2546) time: 0.6259 [2021-03-27 23:14:15 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 590/1251] eta: 0:06:59 lr: 0.000200 loss: 3.1327 (2.9520) grad_norm: 1.9852 (2.2514) time: 0.6274 [2021-03-27 23:14:21 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 600/1251] eta: 0:06:53 lr: 0.000200 loss: 3.0944 (2.9551) grad_norm: 2.1098 (2.2627) time: 0.6259 [2021-03-27 23:14:28 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 610/1251] eta: 0:06:46 lr: 0.000200 loss: 3.2248 (2.9596) grad_norm: 2.2087 (2.2621) time: 0.6236 [2021-03-27 23:14:34 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 620/1251] eta: 0:06:40 lr: 0.000200 loss: 3.0480 (2.9576) grad_norm: 2.1730 (2.2608) time: 0.6217 [2021-03-27 23:14:40 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 630/1251] eta: 0:06:34 lr: 0.000200 loss: 3.0480 (2.9590) grad_norm: 2.2235 (2.2610) time: 0.6252 [2021-03-27 23:14:47 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 640/1251] eta: 0:06:27 lr: 0.000200 loss: 3.2889 (2.9620) grad_norm: 2.1059 (2.2603) time: 0.6389 [2021-03-27 23:14:53 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 650/1251] eta: 0:06:21 lr: 0.000199 loss: 3.1142 (2.9628) grad_norm: 2.0840 (2.2589) time: 0.6398 [2021-03-27 23:14:59 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 660/1251] eta: 0:06:15 lr: 0.000199 loss: 3.0271 (2.9620) grad_norm: 2.0210 (2.2558) time: 0.6296 [2021-03-27 23:15:05 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 670/1251] eta: 0:06:08 lr: 0.000199 loss: 3.0188 (2.9648) grad_norm: 1.9715 (2.2532) time: 0.6301 [2021-03-27 23:15:12 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 680/1251] eta: 0:06:02 lr: 0.000199 loss: 2.9515 (2.9634) grad_norm: 2.0115 (2.2584) time: 0.6277 [2021-03-27 23:15:18 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 690/1251] eta: 0:05:55 lr: 0.000199 loss: 3.0097 (2.9649) grad_norm: 2.0796 (2.2567) time: 0.6233 [2021-03-27 23:15:24 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 700/1251] eta: 0:05:49 lr: 0.000199 loss: 3.0097 (2.9635) grad_norm: 2.1138 (2.2560) time: 0.6230 [2021-03-27 23:15:30 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 710/1251] eta: 0:05:42 lr: 0.000199 loss: 3.0147 (2.9646) grad_norm: 2.1138 (2.2543) time: 0.6232 [2021-03-27 23:15:37 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 720/1251] eta: 0:05:36 lr: 0.000199 loss: 2.9554 (2.9612) grad_norm: 2.0771 (2.2546) time: 0.6255 [2021-03-27 23:15:43 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 730/1251] eta: 0:05:30 lr: 0.000199 loss: 2.7632 (2.9584) grad_norm: 2.1710 (2.2582) time: 0.6271 [2021-03-27 23:15:49 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 740/1251] eta: 0:05:23 lr: 0.000199 loss: 2.8709 (2.9573) grad_norm: 2.2387 (2.2625) time: 0.6316 [2021-03-27 23:15:56 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 750/1251] eta: 0:05:17 lr: 0.000199 loss: 3.1390 (2.9608) grad_norm: 2.2175 (2.2604) time: 0.6335 [2021-03-27 23:16:02 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 760/1251] eta: 0:05:11 lr: 0.000199 loss: 3.1390 (2.9611) grad_norm: 2.1228 (2.2589) time: 0.6351 [2021-03-27 23:16:08 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 770/1251] eta: 0:05:04 lr: 0.000199 loss: 3.0049 (2.9608) grad_norm: 2.0820 (2.2564) time: 0.6361 [2021-03-27 23:16:15 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 780/1251] eta: 0:04:58 lr: 0.000199 loss: 2.7716 (2.9563) grad_norm: 2.0204 (2.2589) time: 0.6333 [2021-03-27 23:16:21 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 790/1251] eta: 0:04:52 lr: 0.000199 loss: 2.8882 (2.9573) grad_norm: 1.9951 (2.2567) time: 0.6355 [2021-03-27 23:16:27 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 800/1251] eta: 0:04:45 lr: 0.000199 loss: 3.1726 (2.9597) grad_norm: 2.0624 (2.2561) time: 0.6325 [2021-03-27 23:16:34 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 810/1251] eta: 0:04:39 lr: 0.000199 loss: 3.0253 (2.9579) grad_norm: 2.1252 (2.2556) time: 0.6250 [2021-03-27 23:16:40 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 820/1251] eta: 0:04:33 lr: 0.000199 loss: 3.1487 (2.9617) grad_norm: 2.3625 (2.2598) time: 0.6324 [2021-03-27 23:16:46 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 830/1251] eta: 0:04:26 lr: 0.000199 loss: 3.2245 (2.9642) grad_norm: 2.3609 (2.2605) time: 0.6365 [2021-03-27 23:16:53 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 840/1251] eta: 0:04:20 lr: 0.000199 loss: 3.1328 (2.9650) grad_norm: 2.2685 (2.2618) time: 0.6299 [2021-03-27 23:16:59 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 850/1251] eta: 0:04:14 lr: 0.000199 loss: 2.8380 (2.9637) grad_norm: 2.1790 (2.2593) time: 0.6257 [2021-03-27 23:17:05 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 860/1251] eta: 0:04:07 lr: 0.000199 loss: 2.8380 (2.9633) grad_norm: 2.0640 (2.2573) time: 0.6261 [2021-03-27 23:17:11 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 870/1251] eta: 0:04:01 lr: 0.000199 loss: 2.7678 (2.9612) grad_norm: 2.0306 (2.2557) time: 0.6319 [2021-03-27 23:17:18 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 880/1251] eta: 0:03:55 lr: 0.000199 loss: 2.7678 (2.9627) grad_norm: 2.1046 (2.2557) time: 0.6354 [2021-03-27 23:17:24 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 890/1251] eta: 0:03:48 lr: 0.000199 loss: 2.9505 (2.9621) grad_norm: 2.1140 (2.2550) time: 0.6376 [2021-03-27 23:17:30 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 900/1251] eta: 0:03:42 lr: 0.000199 loss: 2.9877 (2.9613) grad_norm: 2.0942 (2.2534) time: 0.6315 [2021-03-27 23:17:37 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 910/1251] eta: 0:03:36 lr: 0.000199 loss: 3.0117 (2.9614) grad_norm: 2.0942 (2.2525) time: 0.6280 [2021-03-27 23:17:43 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 920/1251] eta: 0:03:29 lr: 0.000199 loss: 3.0163 (2.9613) grad_norm: 2.1044 (2.2519) time: 0.6306 [2021-03-27 23:17:49 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 930/1251] eta: 0:03:23 lr: 0.000199 loss: 3.0364 (2.9621) grad_norm: 2.1016 (2.2503) time: 0.6304 [2021-03-27 23:17:56 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 940/1251] eta: 0:03:17 lr: 0.000199 loss: 3.0355 (2.9632) grad_norm: 2.1076 (2.2495) time: 0.6340 [2021-03-27 23:18:02 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 950/1251] eta: 0:03:10 lr: 0.000199 loss: 3.0206 (2.9638) grad_norm: 2.0232 (2.2485) time: 0.6491 [2021-03-27 23:18:09 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 960/1251] eta: 0:03:04 lr: 0.000198 loss: 3.1015 (2.9639) grad_norm: 2.2041 (2.2498) time: 0.6427 [2021-03-27 23:18:15 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 970/1251] eta: 0:02:58 lr: 0.000198 loss: 3.1220 (2.9641) grad_norm: 2.2492 (2.2501) time: 0.6246 [2021-03-27 23:18:21 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 980/1251] eta: 0:02:51 lr: 0.000198 loss: 3.0184 (2.9620) grad_norm: 2.2562 (2.2498) time: 0.6268 [2021-03-27 23:18:27 swin_base_patch4_window7_224] INFO: Epoch: [213] [ 990/1251] eta: 0:02:45 lr: 0.000198 loss: 3.1014 (2.9641) grad_norm: 2.1809 (2.2504) time: 0.6255 [2021-03-27 23:18:34 swin_base_patch4_window7_224] INFO: Epoch: [213] [1000/1251] eta: 0:02:38 lr: 0.000198 loss: 3.1572 (2.9641) grad_norm: 2.1950 (2.2532) time: 0.6234 [2021-03-27 23:18:40 swin_base_patch4_window7_224] INFO: Epoch: [213] [1010/1251] eta: 0:02:32 lr: 0.000198 loss: 2.9067 (2.9650) grad_norm: 2.2053 (2.2531) time: 0.6295 [2021-03-27 23:18:46 swin_base_patch4_window7_224] INFO: Epoch: [213] [1020/1251] eta: 0:02:26 lr: 0.000198 loss: 3.0079 (2.9650) grad_norm: 1.9924 (2.2510) time: 0.6277 [2021-03-27 23:18:53 swin_base_patch4_window7_224] INFO: Epoch: [213] [1030/1251] eta: 0:02:19 lr: 0.000198 loss: 2.7286 (2.9635) grad_norm: 2.1526 (2.2533) time: 0.6270 [2021-03-27 23:18:59 swin_base_patch4_window7_224] INFO: Epoch: [213] [1040/1251] eta: 0:02:13 lr: 0.000198 loss: 3.0514 (2.9650) grad_norm: 2.3034 (2.2527) time: 0.6327 [2021-03-27 23:19:05 swin_base_patch4_window7_224] INFO: Epoch: [213] [1050/1251] eta: 0:02:07 lr: 0.000198 loss: 3.1454 (2.9655) grad_norm: 2.1939 (2.2539) time: 0.6249 [2021-03-27 23:19:11 swin_base_patch4_window7_224] INFO: Epoch: [213] [1060/1251] eta: 0:02:00 lr: 0.000198 loss: 2.9900 (2.9644) grad_norm: 2.1939 (2.2561) time: 0.6198 [2021-03-27 23:19:18 swin_base_patch4_window7_224] INFO: Epoch: [213] [1070/1251] eta: 0:01:54 lr: 0.000198 loss: 2.9900 (2.9658) grad_norm: 2.0800 (2.2567) time: 0.6247 [2021-03-27 23:19:24 swin_base_patch4_window7_224] INFO: Epoch: [213] [1080/1251] eta: 0:01:48 lr: 0.000198 loss: 3.2143 (2.9678) grad_norm: 2.0190 (2.2539) time: 0.6301 [2021-03-27 23:19:30 swin_base_patch4_window7_224] INFO: Epoch: [213] [1090/1251] eta: 0:01:41 lr: 0.000198 loss: 3.1507 (2.9690) grad_norm: 2.0190 (2.2541) time: 0.6286 [2021-03-27 23:19:36 swin_base_patch4_window7_224] INFO: Epoch: [213] [1100/1251] eta: 0:01:35 lr: 0.000198 loss: 3.0204 (2.9703) grad_norm: 2.2656 (2.2552) time: 0.6280 [2021-03-27 23:19:43 swin_base_patch4_window7_224] INFO: Epoch: [213] [1110/1251] eta: 0:01:29 lr: 0.000198 loss: 3.0573 (2.9702) grad_norm: 2.1326 (2.2544) time: 0.6290 [2021-03-27 23:19:49 swin_base_patch4_window7_224] INFO: Epoch: [213] [1120/1251] eta: 0:01:22 lr: 0.000198 loss: 2.8503 (2.9691) grad_norm: 2.1687 (2.2546) time: 0.6299 [2021-03-27 23:19:55 swin_base_patch4_window7_224] INFO: Epoch: [213] [1130/1251] eta: 0:01:16 lr: 0.000198 loss: 2.9930 (2.9696) grad_norm: 2.0765 (2.2533) time: 0.6302 [2021-03-27 23:20:02 swin_base_patch4_window7_224] INFO: Epoch: [213] [1140/1251] eta: 0:01:10 lr: 0.000198 loss: 2.9930 (2.9689) grad_norm: 2.0232 (2.2527) time: 0.6264 [2021-03-27 23:20:08 swin_base_patch4_window7_224] INFO: Epoch: [213] [1150/1251] eta: 0:01:03 lr: 0.000198 loss: 3.0860 (2.9694) grad_norm: 2.0073 (2.2511) time: 0.6259 [2021-03-27 23:20:14 swin_base_patch4_window7_224] INFO: Epoch: [213] [1160/1251] eta: 0:00:57 lr: 0.000198 loss: 3.0860 (2.9702) grad_norm: 2.0896 (2.2508) time: 0.6273 [2021-03-27 23:20:21 swin_base_patch4_window7_224] INFO: Epoch: [213] [1170/1251] eta: 0:00:51 lr: 0.000198 loss: 3.0153 (2.9675) grad_norm: 2.2780 (2.2529) time: 0.6332 [2021-03-27 23:20:27 swin_base_patch4_window7_224] INFO: Epoch: [213] [1180/1251] eta: 0:00:44 lr: 0.000198 loss: 3.1633 (2.9695) grad_norm: 2.3757 (2.2531) time: 0.6328 [2021-03-27 23:20:33 swin_base_patch4_window7_224] INFO: Epoch: [213] [1190/1251] eta: 0:00:38 lr: 0.000198 loss: 3.1470 (2.9686) grad_norm: 2.1652 (2.2533) time: 0.6264 [2021-03-27 23:20:39 swin_base_patch4_window7_224] INFO: Epoch: [213] [1200/1251] eta: 0:00:32 lr: 0.000198 loss: 3.1470 (2.9698) grad_norm: 2.1069 (2.2524) time: 0.6308 [2021-03-27 23:20:46 swin_base_patch4_window7_224] INFO: Epoch: [213] [1210/1251] eta: 0:00:25 lr: 0.000198 loss: 3.1785 (2.9707) grad_norm: 2.1271 (2.2529) time: 0.6288 [2021-03-27 23:20:52 swin_base_patch4_window7_224] INFO: Epoch: [213] [1220/1251] eta: 0:00:19 lr: 0.000198 loss: 3.1914 (2.9716) grad_norm: 2.1794 (2.2528) time: 0.6269 [2021-03-27 23:20:58 swin_base_patch4_window7_224] INFO: Epoch: [213] [1230/1251] eta: 0:00:13 lr: 0.000198 loss: 3.2797 (2.9736) grad_norm: 2.0552 (2.2513) time: 0.6258 [2021-03-27 23:21:04 swin_base_patch4_window7_224] INFO: Epoch: [213] [1240/1251] eta: 0:00:06 lr: 0.000198 loss: 3.1976 (2.9754) grad_norm: 2.0552 (2.2512) time: 0.6247 [2021-03-27 23:21:11 swin_base_patch4_window7_224] INFO: Epoch: [213] [1250/1251] eta: 0:00:00 lr: 0.000198 loss: 3.1006 (2.9743) grad_norm: 2.1543 (2.2518) time: 0.6291 [2021-03-27 23:21:18 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:58 loss: 0.7453 (0.7453) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-27 23:21:21 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8473 (0.8761) acc1: 79.6875 (78.9773) acc5: 95.3125 (96.0227) [2021-03-27 23:21:22 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8341 (0.8483) acc1: 79.6875 (80.2083) acc5: 95.3125 (95.8333) [2021-03-27 23:21:24 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7963 (0.8140) acc1: 81.2500 (80.6452) acc5: 96.8750 (96.4214) [2021-03-27 23:21:26 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6837 (0.7991) acc1: 82.8125 (81.1357) acc5: 96.8750 (96.2652) [2021-03-27 23:21:27 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8016 (0.8157) acc1: 81.2500 (80.7680) acc5: 96.2264 (96.1280) [2021-03-27 23:21:37 swin_base_patch4_window7_224] INFO: * Acc@1 81.758 Acc@5 95.948 loss 0.799 [2021-03-27 23:21:37 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.8% [2021-03-27 23:21:37 swin_base_patch4_window7_224] INFO: Max accuracy: 81.76% [2021-03-27 23:21:42 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 0/1251] eta: 1:36:16 lr: 0.000198 loss: 3.4608 (3.4608) grad_norm: 2.3692 (2.3692) time: 4.6174 [2021-03-27 23:21:48 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 10/1251] eta: 0:20:34 lr: 0.000197 loss: 3.2417 (3.2123) grad_norm: 2.1547 (2.3592) time: 0.9944 [2021-03-27 23:21:54 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 20/1251] eta: 0:16:47 lr: 0.000197 loss: 3.1179 (3.1014) grad_norm: 2.1547 (2.3452) time: 0.6285 [2021-03-27 23:22:01 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 30/1251] eta: 0:15:25 lr: 0.000197 loss: 3.1179 (3.1134) grad_norm: 2.2439 (2.2906) time: 0.6283 [2021-03-27 23:22:07 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 40/1251] eta: 0:14:38 lr: 0.000197 loss: 3.0979 (3.0443) grad_norm: 2.1552 (2.2661) time: 0.6278 [2021-03-27 23:22:13 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 50/1251] eta: 0:14:09 lr: 0.000197 loss: 3.0210 (3.0404) grad_norm: 2.0845 (2.2249) time: 0.6287 [2021-03-27 23:22:20 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 60/1251] eta: 0:13:49 lr: 0.000197 loss: 3.0210 (3.0233) grad_norm: 2.1500 (2.2404) time: 0.6361 [2021-03-27 23:22:26 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 70/1251] eta: 0:13:30 lr: 0.000197 loss: 2.7225 (2.9989) grad_norm: 2.1865 (2.2262) time: 0.6334 [2021-03-27 23:22:32 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 80/1251] eta: 0:13:15 lr: 0.000197 loss: 2.7405 (2.9945) grad_norm: 2.1266 (2.2258) time: 0.6294 [2021-03-27 23:22:38 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 90/1251] eta: 0:13:02 lr: 0.000197 loss: 3.1931 (3.0046) grad_norm: 2.2459 (2.2303) time: 0.6279 [2021-03-27 23:22:45 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 100/1251] eta: 0:12:49 lr: 0.000197 loss: 3.0671 (3.0005) grad_norm: 2.2646 (2.2234) time: 0.6246 [2021-03-27 23:22:51 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 110/1251] eta: 0:12:39 lr: 0.000197 loss: 2.7744 (2.9996) grad_norm: 2.1663 (2.2204) time: 0.6277 [2021-03-27 23:22:57 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 120/1251] eta: 0:12:29 lr: 0.000197 loss: 3.1552 (3.0142) grad_norm: 2.2050 (2.2281) time: 0.6330 [2021-03-27 23:23:04 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 130/1251] eta: 0:12:19 lr: 0.000197 loss: 3.1552 (2.9928) grad_norm: 2.1989 (2.2233) time: 0.6299 [2021-03-27 23:23:10 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 140/1251] eta: 0:12:11 lr: 0.000197 loss: 3.0804 (2.9961) grad_norm: 2.1362 (2.2189) time: 0.6291 [2021-03-27 23:23:16 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 150/1251] eta: 0:12:02 lr: 0.000197 loss: 3.0636 (2.9842) grad_norm: 2.2135 (2.2191) time: 0.6328 [2021-03-27 23:23:23 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 160/1251] eta: 0:11:54 lr: 0.000197 loss: 2.9504 (2.9854) grad_norm: 2.1942 (2.2175) time: 0.6310 [2021-03-27 23:23:29 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 170/1251] eta: 0:11:46 lr: 0.000197 loss: 3.0985 (2.9894) grad_norm: 2.0998 (2.2094) time: 0.6311 [2021-03-27 23:23:35 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 180/1251] eta: 0:11:38 lr: 0.000197 loss: 2.8828 (2.9777) grad_norm: 2.1130 (2.2096) time: 0.6343 [2021-03-27 23:23:42 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 190/1251] eta: 0:11:31 lr: 0.000197 loss: 2.7913 (2.9721) grad_norm: 2.1678 (2.2092) time: 0.6381 [2021-03-27 23:23:48 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 200/1251] eta: 0:11:24 lr: 0.000197 loss: 3.0971 (2.9782) grad_norm: 2.0905 (2.2058) time: 0.6365 [2021-03-27 23:23:54 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 210/1251] eta: 0:11:16 lr: 0.000197 loss: 3.1671 (2.9842) grad_norm: 2.0937 (2.2075) time: 0.6345 [2021-03-27 23:24:01 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 220/1251] eta: 0:11:09 lr: 0.000197 loss: 3.1942 (2.9917) grad_norm: 2.2582 (2.2150) time: 0.6338 [2021-03-27 23:24:07 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 230/1251] eta: 0:11:01 lr: 0.000197 loss: 3.1524 (2.9890) grad_norm: 2.1464 (2.2059) time: 0.6270 [2021-03-27 23:24:13 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 240/1251] eta: 0:10:54 lr: 0.000197 loss: 2.9617 (2.9903) grad_norm: 2.0398 (2.2133) time: 0.6262 [2021-03-27 23:24:19 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 250/1251] eta: 0:10:47 lr: 0.000197 loss: 3.0260 (2.9922) grad_norm: 2.1618 (2.2107) time: 0.6272 [2021-03-27 23:24:26 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 260/1251] eta: 0:10:39 lr: 0.000197 loss: 3.1503 (2.9979) grad_norm: 2.1975 (2.2182) time: 0.6243 [2021-03-27 23:24:32 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 270/1251] eta: 0:10:33 lr: 0.000197 loss: 3.1471 (2.9997) grad_norm: 2.1975 (2.2189) time: 0.6344 [2021-03-27 23:24:38 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 280/1251] eta: 0:10:26 lr: 0.000197 loss: 3.0923 (2.9967) grad_norm: 2.1143 (2.2189) time: 0.6348 [2021-03-27 23:24:45 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 290/1251] eta: 0:10:18 lr: 0.000197 loss: 3.0923 (3.0039) grad_norm: 2.1143 (2.2166) time: 0.6233 [2021-03-27 23:24:51 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 300/1251] eta: 0:10:12 lr: 0.000197 loss: 3.1150 (2.9989) grad_norm: 2.0859 (2.2198) time: 0.6259 [2021-03-27 23:24:57 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 310/1251] eta: 0:10:05 lr: 0.000197 loss: 2.9142 (2.9919) grad_norm: 2.0713 (2.2133) time: 0.6297 [2021-03-27 23:25:04 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 320/1251] eta: 0:09:58 lr: 0.000196 loss: 3.0715 (2.9946) grad_norm: 1.9904 (2.2147) time: 0.6351 [2021-03-27 23:25:10 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 330/1251] eta: 0:09:51 lr: 0.000196 loss: 3.1876 (3.0003) grad_norm: 2.0869 (2.2184) time: 0.6347 [2021-03-27 23:25:16 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 340/1251] eta: 0:09:44 lr: 0.000196 loss: 2.9542 (2.9887) grad_norm: 2.1939 (2.2368) time: 0.6238 [2021-03-27 23:25:22 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 350/1251] eta: 0:09:38 lr: 0.000196 loss: 2.6272 (2.9785) grad_norm: 2.2218 (2.2354) time: 0.6261 [2021-03-27 23:25:29 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 360/1251] eta: 0:09:31 lr: 0.000196 loss: 3.0435 (2.9838) grad_norm: 2.0183 (2.2347) time: 0.6325 [2021-03-27 23:25:35 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 370/1251] eta: 0:09:24 lr: 0.000196 loss: 3.0435 (2.9780) grad_norm: 2.0868 (2.2327) time: 0.6294 [2021-03-27 23:25:41 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 380/1251] eta: 0:09:17 lr: 0.000196 loss: 2.7582 (2.9700) grad_norm: 2.0846 (2.2295) time: 0.6244 [2021-03-27 23:25:47 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 390/1251] eta: 0:09:11 lr: 0.000196 loss: 3.1461 (2.9798) grad_norm: 2.0946 (2.2284) time: 0.6229 [2021-03-27 23:25:54 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 400/1251] eta: 0:09:04 lr: 0.000196 loss: 3.2698 (2.9825) grad_norm: 2.2023 (2.2295) time: 0.6275 [2021-03-27 23:26:00 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 410/1251] eta: 0:08:58 lr: 0.000196 loss: 3.1065 (2.9845) grad_norm: 2.2023 (2.2298) time: 0.6322 [2021-03-27 23:26:06 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 420/1251] eta: 0:08:51 lr: 0.000196 loss: 3.1588 (2.9908) grad_norm: 2.2786 (2.2346) time: 0.6312 [2021-03-27 23:26:13 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 430/1251] eta: 0:08:44 lr: 0.000196 loss: 3.1588 (2.9877) grad_norm: 2.1559 (2.2300) time: 0.6297 [2021-03-27 23:26:19 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 440/1251] eta: 0:08:38 lr: 0.000196 loss: 2.8585 (2.9854) grad_norm: 2.0648 (2.2269) time: 0.6304 [2021-03-27 23:26:25 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 450/1251] eta: 0:08:31 lr: 0.000196 loss: 2.8226 (2.9808) grad_norm: 2.0704 (2.2268) time: 0.6301 [2021-03-27 23:26:32 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 460/1251] eta: 0:08:25 lr: 0.000196 loss: 2.9449 (2.9800) grad_norm: 2.2085 (2.2426) time: 0.6290 [2021-03-27 23:26:38 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 470/1251] eta: 0:08:18 lr: 0.000196 loss: 3.0750 (2.9790) grad_norm: 2.1326 (2.2426) time: 0.6311 [2021-03-27 23:26:44 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 480/1251] eta: 0:08:12 lr: 0.000196 loss: 3.0048 (2.9766) grad_norm: 2.1724 (2.2452) time: 0.6345 [2021-03-27 23:26:50 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 490/1251] eta: 0:08:05 lr: 0.000196 loss: 3.1022 (2.9811) grad_norm: 2.2216 (2.2456) time: 0.6280 [2021-03-27 23:26:57 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 500/1251] eta: 0:07:58 lr: 0.000196 loss: 2.9704 (2.9780) grad_norm: 2.2284 (2.2473) time: 0.6201 [2021-03-27 23:27:03 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 510/1251] eta: 0:07:52 lr: 0.000196 loss: 3.0528 (2.9799) grad_norm: 2.2314 (2.2457) time: 0.6267 [2021-03-27 23:27:09 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 520/1251] eta: 0:07:46 lr: 0.000196 loss: 3.2106 (2.9828) grad_norm: 2.1671 (2.2448) time: 0.6334 [2021-03-27 23:27:16 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 530/1251] eta: 0:07:39 lr: 0.000196 loss: 3.0221 (2.9778) grad_norm: 2.1073 (2.2419) time: 0.6269 [2021-03-27 23:27:22 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 540/1251] eta: 0:07:33 lr: 0.000196 loss: 3.0221 (2.9797) grad_norm: 1.9959 (2.2417) time: 0.6285 [2021-03-27 23:27:28 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 550/1251] eta: 0:07:26 lr: 0.000196 loss: 3.0978 (2.9813) grad_norm: 2.1834 (2.2400) time: 0.6331 [2021-03-27 23:27:35 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 560/1251] eta: 0:07:20 lr: 0.000196 loss: 3.2087 (2.9866) grad_norm: 2.1580 (2.2403) time: 0.6415 [2021-03-27 23:27:41 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 570/1251] eta: 0:07:14 lr: 0.000196 loss: 3.1858 (2.9876) grad_norm: 2.1606 (2.2393) time: 0.6432 [2021-03-27 23:27:47 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 580/1251] eta: 0:07:07 lr: 0.000196 loss: 3.0568 (2.9864) grad_norm: 2.1606 (2.2405) time: 0.6268 [2021-03-27 23:27:53 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 590/1251] eta: 0:07:00 lr: 0.000196 loss: 3.2008 (2.9891) grad_norm: 2.0702 (2.2384) time: 0.6207 [2021-03-27 23:28:00 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 600/1251] eta: 0:06:54 lr: 0.000196 loss: 3.2098 (2.9934) grad_norm: 2.0549 (2.2361) time: 0.6260 [2021-03-27 23:28:06 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 610/1251] eta: 0:06:48 lr: 0.000196 loss: 3.1505 (2.9952) grad_norm: 2.0509 (2.2348) time: 0.6315 [2021-03-27 23:28:12 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 620/1251] eta: 0:06:41 lr: 0.000196 loss: 3.1461 (2.9930) grad_norm: 2.0509 (2.2366) time: 0.6331 [2021-03-27 23:28:19 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 630/1251] eta: 0:06:35 lr: 0.000195 loss: 2.6828 (2.9884) grad_norm: 2.0975 (2.2356) time: 0.6314 [2021-03-27 23:28:25 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 640/1251] eta: 0:06:28 lr: 0.000195 loss: 2.6828 (2.9896) grad_norm: 2.1904 (2.2378) time: 0.6279 [2021-03-27 23:28:31 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 650/1251] eta: 0:06:22 lr: 0.000195 loss: 3.1016 (2.9905) grad_norm: 2.1528 (2.2377) time: 0.6286 [2021-03-27 23:28:38 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 660/1251] eta: 0:06:16 lr: 0.000195 loss: 2.7966 (2.9858) grad_norm: 2.0541 (2.2336) time: 0.6381 [2021-03-27 23:28:44 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 670/1251] eta: 0:06:09 lr: 0.000195 loss: 2.7966 (2.9864) grad_norm: 2.0364 (2.2328) time: 0.6382 [2021-03-27 23:28:50 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 680/1251] eta: 0:06:03 lr: 0.000195 loss: 2.9544 (2.9827) grad_norm: 2.1395 (2.2365) time: 0.6300 [2021-03-27 23:28:57 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 690/1251] eta: 0:05:56 lr: 0.000195 loss: 2.6453 (2.9788) grad_norm: 2.1578 (2.2362) time: 0.6280 [2021-03-27 23:29:03 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 700/1251] eta: 0:05:50 lr: 0.000195 loss: 2.7400 (2.9778) grad_norm: 2.0536 (2.2344) time: 0.6318 [2021-03-27 23:29:09 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 710/1251] eta: 0:05:43 lr: 0.000195 loss: 3.1702 (2.9797) grad_norm: 2.0596 (2.2337) time: 0.6288 [2021-03-27 23:29:16 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 720/1251] eta: 0:05:37 lr: 0.000195 loss: 3.1468 (2.9817) grad_norm: 2.0803 (2.2308) time: 0.6255 [2021-03-27 23:29:22 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 730/1251] eta: 0:05:31 lr: 0.000195 loss: 3.1026 (2.9793) grad_norm: 2.0803 (2.2294) time: 0.6308 [2021-03-27 23:29:28 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 740/1251] eta: 0:05:24 lr: 0.000195 loss: 3.2372 (2.9819) grad_norm: 2.1392 (2.2305) time: 0.6307 [2021-03-27 23:29:35 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 750/1251] eta: 0:05:18 lr: 0.000195 loss: 3.1851 (2.9806) grad_norm: 2.3200 (2.2340) time: 0.6371 [2021-03-27 23:29:41 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 760/1251] eta: 0:05:12 lr: 0.000195 loss: 2.9557 (2.9789) grad_norm: 2.5281 (2.2374) time: 0.6433 [2021-03-27 23:29:47 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 770/1251] eta: 0:05:05 lr: 0.000195 loss: 2.9557 (2.9781) grad_norm: 2.1814 (2.2362) time: 0.6397 [2021-03-27 23:29:54 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 780/1251] eta: 0:04:59 lr: 0.000195 loss: 3.2396 (2.9818) grad_norm: 2.2741 (2.2372) time: 0.6352 [2021-03-27 23:30:00 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 790/1251] eta: 0:04:53 lr: 0.000195 loss: 3.2436 (2.9816) grad_norm: 2.2631 (2.2378) time: 0.6314 [2021-03-27 23:30:06 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 800/1251] eta: 0:04:46 lr: 0.000195 loss: 3.1809 (2.9830) grad_norm: 2.2410 (2.2403) time: 0.6301 [2021-03-27 23:30:13 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 810/1251] eta: 0:04:40 lr: 0.000195 loss: 3.0524 (2.9820) grad_norm: 2.2401 (2.2394) time: 0.6268 [2021-03-27 23:30:19 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 820/1251] eta: 0:04:33 lr: 0.000195 loss: 3.0354 (2.9846) grad_norm: 2.0872 (2.2386) time: 0.6214 [2021-03-27 23:30:25 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 830/1251] eta: 0:04:27 lr: 0.000195 loss: 3.1791 (2.9863) grad_norm: 2.0413 (2.2371) time: 0.6258 [2021-03-27 23:30:31 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 840/1251] eta: 0:04:21 lr: 0.000195 loss: 3.1128 (2.9861) grad_norm: 2.0038 (2.2403) time: 0.6315 [2021-03-27 23:30:38 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 850/1251] eta: 0:04:14 lr: 0.000195 loss: 3.0629 (2.9856) grad_norm: 2.0834 (2.2403) time: 0.6320 [2021-03-27 23:30:44 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 860/1251] eta: 0:04:08 lr: 0.000195 loss: 3.1066 (2.9868) grad_norm: 2.1571 (2.2398) time: 0.6349 [2021-03-27 23:30:50 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 870/1251] eta: 0:04:01 lr: 0.000195 loss: 3.1022 (2.9867) grad_norm: 2.1076 (2.2400) time: 0.6348 [2021-03-27 23:30:57 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 880/1251] eta: 0:03:55 lr: 0.000195 loss: 3.0963 (2.9879) grad_norm: 2.1486 (2.2409) time: 0.6337 [2021-03-27 23:31:03 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 890/1251] eta: 0:03:49 lr: 0.000195 loss: 3.1512 (2.9894) grad_norm: 2.3130 (2.2435) time: 0.6305 [2021-03-27 23:31:09 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 900/1251] eta: 0:03:42 lr: 0.000195 loss: 3.2329 (2.9903) grad_norm: 2.3542 (2.2445) time: 0.6320 [2021-03-27 23:31:16 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 910/1251] eta: 0:03:36 lr: 0.000195 loss: 2.8911 (2.9898) grad_norm: 2.1779 (2.2432) time: 0.6297 [2021-03-27 23:31:22 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 920/1251] eta: 0:03:30 lr: 0.000195 loss: 2.9741 (2.9904) grad_norm: 2.1779 (2.2459) time: 0.6219 [2021-03-27 23:31:28 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 930/1251] eta: 0:03:23 lr: 0.000195 loss: 3.0671 (2.9883) grad_norm: 2.1677 (2.2459) time: 0.6251 [2021-03-27 23:31:35 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 940/1251] eta: 0:03:17 lr: 0.000194 loss: 2.8892 (2.9872) grad_norm: 2.1677 (2.2468) time: 0.6330 [2021-03-27 23:31:41 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 950/1251] eta: 0:03:11 lr: 0.000194 loss: 2.9467 (2.9887) grad_norm: 2.2742 (2.2485) time: 0.6370 [2021-03-27 23:31:47 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 960/1251] eta: 0:03:04 lr: 0.000194 loss: 3.2161 (2.9898) grad_norm: 2.1660 (2.2483) time: 0.6313 [2021-03-27 23:31:54 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 970/1251] eta: 0:02:58 lr: 0.000194 loss: 2.7795 (2.9863) grad_norm: 2.2293 (2.2489) time: 0.6312 [2021-03-27 23:32:00 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 980/1251] eta: 0:02:51 lr: 0.000194 loss: 2.9170 (2.9889) grad_norm: 2.2227 (2.2476) time: 0.6296 [2021-03-27 23:32:06 swin_base_patch4_window7_224] INFO: Epoch: [214] [ 990/1251] eta: 0:02:45 lr: 0.000194 loss: 3.2039 (2.9882) grad_norm: 2.2071 (2.2484) time: 0.6254 [2021-03-27 23:32:12 swin_base_patch4_window7_224] INFO: Epoch: [214] [1000/1251] eta: 0:02:39 lr: 0.000194 loss: 3.0699 (2.9893) grad_norm: 2.1837 (2.2462) time: 0.6247 [2021-03-27 23:32:19 swin_base_patch4_window7_224] INFO: Epoch: [214] [1010/1251] eta: 0:02:32 lr: 0.000194 loss: 3.1171 (2.9904) grad_norm: 2.0558 (2.2449) time: 0.6259 [2021-03-27 23:32:25 swin_base_patch4_window7_224] INFO: Epoch: [214] [1020/1251] eta: 0:02:26 lr: 0.000194 loss: 3.1171 (2.9915) grad_norm: 2.1803 (2.2450) time: 0.6320 [2021-03-27 23:32:31 swin_base_patch4_window7_224] INFO: Epoch: [214] [1030/1251] eta: 0:02:20 lr: 0.000194 loss: 3.1420 (2.9910) grad_norm: 2.1749 (2.2449) time: 0.6299 [2021-03-27 23:32:37 swin_base_patch4_window7_224] INFO: Epoch: [214] [1040/1251] eta: 0:02:13 lr: 0.000194 loss: 3.1420 (2.9931) grad_norm: 2.0676 (2.2432) time: 0.6262 [2021-03-27 23:32:44 swin_base_patch4_window7_224] INFO: Epoch: [214] [1050/1251] eta: 0:02:07 lr: 0.000194 loss: 2.9549 (2.9941) grad_norm: 2.1798 (2.2442) time: 0.6252 [2021-03-27 23:32:50 swin_base_patch4_window7_224] INFO: Epoch: [214] [1060/1251] eta: 0:02:01 lr: 0.000194 loss: 2.9549 (2.9929) grad_norm: 2.2474 (2.2436) time: 0.6273 [2021-03-27 23:32:56 swin_base_patch4_window7_224] INFO: Epoch: [214] [1070/1251] eta: 0:01:54 lr: 0.000194 loss: 3.1362 (2.9932) grad_norm: 2.1093 (2.2435) time: 0.6280 [2021-03-27 23:33:03 swin_base_patch4_window7_224] INFO: Epoch: [214] [1080/1251] eta: 0:01:48 lr: 0.000194 loss: 3.0498 (2.9927) grad_norm: 2.0977 (2.2436) time: 0.6287 [2021-03-27 23:33:09 swin_base_patch4_window7_224] INFO: Epoch: [214] [1090/1251] eta: 0:01:42 lr: 0.000194 loss: 2.9157 (2.9910) grad_norm: 2.0707 (2.2411) time: 0.6295 [2021-03-27 23:33:15 swin_base_patch4_window7_224] INFO: Epoch: [214] [1100/1251] eta: 0:01:35 lr: 0.000194 loss: 3.0253 (2.9911) grad_norm: 2.0693 (2.2408) time: 0.6256 [2021-03-27 23:33:21 swin_base_patch4_window7_224] INFO: Epoch: [214] [1110/1251] eta: 0:01:29 lr: 0.000194 loss: 3.0573 (2.9920) grad_norm: 2.1560 (2.2416) time: 0.6216 [2021-03-27 23:33:27 swin_base_patch4_window7_224] INFO: Epoch: [214] [1120/1251] eta: 0:01:22 lr: 0.000194 loss: 3.1344 (2.9931) grad_norm: 2.2080 (2.2413) time: 0.6188 [2021-03-27 23:33:34 swin_base_patch4_window7_224] INFO: Epoch: [214] [1130/1251] eta: 0:01:16 lr: 0.000194 loss: 3.1384 (2.9943) grad_norm: 2.1401 (2.2400) time: 0.6249 [2021-03-27 23:33:40 swin_base_patch4_window7_224] INFO: Epoch: [214] [1140/1251] eta: 0:01:10 lr: 0.000194 loss: 3.1128 (2.9930) grad_norm: 2.0906 (2.2396) time: 0.6258 [2021-03-27 23:33:46 swin_base_patch4_window7_224] INFO: Epoch: [214] [1150/1251] eta: 0:01:03 lr: 0.000194 loss: 2.8229 (2.9939) grad_norm: 2.1262 (2.2397) time: 0.6246 [2021-03-27 23:33:52 swin_base_patch4_window7_224] INFO: Epoch: [214] [1160/1251] eta: 0:00:57 lr: 0.000194 loss: 3.0377 (2.9920) grad_norm: 2.1650 (2.2407) time: 0.6259 [2021-03-27 23:33:59 swin_base_patch4_window7_224] INFO: Epoch: [214] [1170/1251] eta: 0:00:51 lr: 0.000194 loss: 3.0109 (2.9922) grad_norm: 2.2136 (2.2410) time: 0.6275 [2021-03-27 23:34:05 swin_base_patch4_window7_224] INFO: Epoch: [214] [1180/1251] eta: 0:00:44 lr: 0.000194 loss: 2.8808 (2.9909) grad_norm: 2.1960 (2.2412) time: 0.6270 [2021-03-27 23:34:11 swin_base_patch4_window7_224] INFO: Epoch: [214] [1190/1251] eta: 0:00:38 lr: 0.000194 loss: 2.9064 (2.9904) grad_norm: 2.0082 (2.2392) time: 0.6258 [2021-03-27 23:34:18 swin_base_patch4_window7_224] INFO: Epoch: [214] [1200/1251] eta: 0:00:32 lr: 0.000194 loss: 3.0409 (2.9911) grad_norm: 2.0294 (2.2390) time: 0.6283 [2021-03-27 23:34:24 swin_base_patch4_window7_224] INFO: Epoch: [214] [1210/1251] eta: 0:00:25 lr: 0.000194 loss: 3.0409 (2.9920) grad_norm: 2.1937 (2.2384) time: 0.6337 [2021-03-27 23:34:30 swin_base_patch4_window7_224] INFO: Epoch: [214] [1220/1251] eta: 0:00:19 lr: 0.000194 loss: 3.0195 (2.9904) grad_norm: 2.1770 (2.2378) time: 0.6355 [2021-03-27 23:34:37 swin_base_patch4_window7_224] INFO: Epoch: [214] [1230/1251] eta: 0:00:13 lr: 0.000194 loss: 3.0863 (2.9916) grad_norm: 2.2708 (2.2398) time: 0.6280 [2021-03-27 23:34:43 swin_base_patch4_window7_224] INFO: Epoch: [214] [1240/1251] eta: 0:00:06 lr: 0.000194 loss: 3.2681 (2.9928) grad_norm: 2.2800 (2.2404) time: 0.6248 [2021-03-27 23:34:49 swin_base_patch4_window7_224] INFO: Epoch: [214] [1250/1251] eta: 0:00:00 lr: 0.000193 loss: 3.1290 (2.9910) grad_norm: 2.0852 (2.2395) time: 0.6203 [2021-03-27 23:34:59 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:40 loss: 0.4693 (0.4693) acc1: 89.0625 (89.0625) acc5: 100.0000 (100.0000) [2021-03-27 23:35:02 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.7874 (0.7554) acc1: 81.2500 (82.2443) acc5: 96.8750 (96.8750) [2021-03-27 23:35:04 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8301 (0.8162) acc1: 81.2500 (81.0268) acc5: 95.3125 (96.0565) [2021-03-27 23:35:07 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8560 (0.8182) acc1: 79.6875 (80.7964) acc5: 95.3125 (96.0685) [2021-03-27 23:35:09 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8528 (0.8277) acc1: 79.6875 (80.5259) acc5: 95.3125 (95.8841) [2021-03-27 23:35:10 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7571 (0.8079) acc1: 81.1321 (80.8640) acc5: 96.8750 (96.0960) [2021-03-27 23:35:20 swin_base_patch4_window7_224] INFO: * Acc@1 81.620 Acc@5 95.978 loss 0.794 [2021-03-27 23:35:20 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.6% [2021-03-27 23:35:20 swin_base_patch4_window7_224] INFO: Max accuracy: 81.76% [2021-03-27 23:35:26 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 0/1251] eta: 1:45:46 lr: 0.000193 loss: 2.4048 (2.4048) grad_norm: 2.6801 (2.6801) time: 5.0735 [2021-03-27 23:35:32 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 10/1251] eta: 0:21:31 lr: 0.000193 loss: 3.3040 (3.1335) grad_norm: 2.2832 (2.5896) time: 1.0409 [2021-03-27 23:35:38 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 20/1251] eta: 0:17:29 lr: 0.000193 loss: 3.2849 (3.1235) grad_norm: 2.2946 (2.5313) time: 0.6418 [2021-03-27 23:35:45 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 30/1251] eta: 0:15:51 lr: 0.000193 loss: 3.2620 (3.1521) grad_norm: 2.2728 (2.3954) time: 0.6351 [2021-03-27 23:35:51 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 40/1251] eta: 0:14:56 lr: 0.000193 loss: 3.1256 (3.1338) grad_norm: 2.1351 (2.3725) time: 0.6224 [2021-03-27 23:35:57 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 50/1251] eta: 0:14:25 lr: 0.000193 loss: 3.1373 (3.1430) grad_norm: 2.1245 (2.3193) time: 0.6307 [2021-03-27 23:36:03 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 60/1251] eta: 0:13:59 lr: 0.000193 loss: 3.0361 (3.0604) grad_norm: 2.0818 (2.3353) time: 0.6325 [2021-03-27 23:36:10 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 70/1251] eta: 0:13:38 lr: 0.000193 loss: 2.9895 (3.0897) grad_norm: 2.1710 (inf) time: 0.6217 [2021-03-27 23:36:16 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 80/1251] eta: 0:13:22 lr: 0.000193 loss: 3.0540 (3.0631) grad_norm: 2.1980 (inf) time: 0.6236 [2021-03-27 23:36:22 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 90/1251] eta: 0:13:07 lr: 0.000193 loss: 3.0188 (3.0415) grad_norm: 2.1352 (inf) time: 0.6247 [2021-03-27 23:36:28 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 100/1251] eta: 0:12:54 lr: 0.000193 loss: 3.0188 (3.0193) grad_norm: 2.2487 (inf) time: 0.6248 [2021-03-27 23:36:35 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 110/1251] eta: 0:12:42 lr: 0.000193 loss: 3.0420 (3.0124) grad_norm: 2.2487 (inf) time: 0.6267 [2021-03-27 23:36:41 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 120/1251] eta: 0:12:33 lr: 0.000193 loss: 3.0839 (3.0129) grad_norm: 2.1812 (inf) time: 0.6305 [2021-03-27 23:36:47 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 130/1251] eta: 0:12:23 lr: 0.000193 loss: 3.0459 (3.0034) grad_norm: 2.1812 (inf) time: 0.6338 [2021-03-27 23:36:54 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 140/1251] eta: 0:12:14 lr: 0.000193 loss: 2.8281 (2.9976) grad_norm: 2.2084 (inf) time: 0.6311 [2021-03-27 23:37:00 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 150/1251] eta: 0:12:05 lr: 0.000193 loss: 3.1821 (2.9964) grad_norm: 2.2190 (inf) time: 0.6329 [2021-03-27 23:37:06 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 160/1251] eta: 0:11:57 lr: 0.000193 loss: 2.8706 (2.9771) grad_norm: 2.1482 (inf) time: 0.6330 [2021-03-27 23:37:13 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 170/1251] eta: 0:11:50 lr: 0.000193 loss: 2.8706 (2.9728) grad_norm: 2.2323 (inf) time: 0.6395 [2021-03-27 23:37:19 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 180/1251] eta: 0:11:42 lr: 0.000193 loss: 3.0181 (2.9806) grad_norm: 2.2186 (inf) time: 0.6387 [2021-03-27 23:37:25 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 190/1251] eta: 0:11:34 lr: 0.000193 loss: 2.9980 (2.9800) grad_norm: 2.1163 (inf) time: 0.6294 [2021-03-27 23:37:32 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 200/1251] eta: 0:11:26 lr: 0.000193 loss: 3.0996 (2.9866) grad_norm: 2.1163 (inf) time: 0.6302 [2021-03-27 23:37:38 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 210/1251] eta: 0:11:18 lr: 0.000193 loss: 3.1494 (2.9908) grad_norm: 2.1234 (inf) time: 0.6313 [2021-03-27 23:37:44 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 220/1251] eta: 0:11:10 lr: 0.000193 loss: 2.9692 (2.9840) grad_norm: 2.1603 (inf) time: 0.6252 [2021-03-27 23:37:51 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 230/1251] eta: 0:11:03 lr: 0.000193 loss: 2.9347 (2.9800) grad_norm: 2.2128 (inf) time: 0.6228 [2021-03-27 23:37:57 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 240/1251] eta: 0:10:55 lr: 0.000193 loss: 2.9347 (2.9760) grad_norm: 2.2128 (inf) time: 0.6236 [2021-03-27 23:38:03 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 250/1251] eta: 0:10:48 lr: 0.000193 loss: 3.0819 (2.9815) grad_norm: 2.0592 (inf) time: 0.6292 [2021-03-27 23:38:09 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 260/1251] eta: 0:10:41 lr: 0.000193 loss: 3.0936 (2.9795) grad_norm: 2.1332 (inf) time: 0.6368 [2021-03-27 23:38:16 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 270/1251] eta: 0:10:34 lr: 0.000193 loss: 3.0670 (2.9768) grad_norm: 2.1678 (inf) time: 0.6345 [2021-03-27 23:38:22 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 280/1251] eta: 0:10:27 lr: 0.000193 loss: 3.0886 (2.9795) grad_norm: 2.3095 (inf) time: 0.6318 [2021-03-27 23:38:28 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 290/1251] eta: 0:10:20 lr: 0.000193 loss: 3.0886 (2.9799) grad_norm: 2.2919 (inf) time: 0.6240 [2021-03-27 23:38:35 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 300/1251] eta: 0:10:13 lr: 0.000193 loss: 3.2428 (2.9854) grad_norm: 2.2248 (inf) time: 0.6234 [2021-03-27 23:38:41 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 310/1251] eta: 0:10:06 lr: 0.000192 loss: 3.1208 (2.9842) grad_norm: 2.1327 (inf) time: 0.6325 [2021-03-27 23:38:47 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 320/1251] eta: 0:09:59 lr: 0.000192 loss: 3.1140 (2.9845) grad_norm: 2.1257 (inf) time: 0.6318 [2021-03-27 23:38:53 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 330/1251] eta: 0:09:52 lr: 0.000192 loss: 2.8744 (2.9785) grad_norm: 2.3687 (inf) time: 0.6283 [2021-03-27 23:39:00 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 340/1251] eta: 0:09:45 lr: 0.000192 loss: 2.9958 (2.9835) grad_norm: 2.3687 (inf) time: 0.6264 [2021-03-27 23:39:06 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 350/1251] eta: 0:09:38 lr: 0.000192 loss: 2.9958 (2.9818) grad_norm: 2.2128 (inf) time: 0.6266 [2021-03-27 23:39:12 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 360/1251] eta: 0:09:32 lr: 0.000192 loss: 2.9537 (2.9815) grad_norm: 2.2214 (inf) time: 0.6324 [2021-03-27 23:39:19 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 370/1251] eta: 0:09:25 lr: 0.000192 loss: 3.0690 (2.9833) grad_norm: 2.2399 (inf) time: 0.6301 [2021-03-27 23:39:25 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 380/1251] eta: 0:09:18 lr: 0.000192 loss: 3.2910 (2.9885) grad_norm: 2.1993 (inf) time: 0.6247 [2021-03-27 23:39:31 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 390/1251] eta: 0:09:12 lr: 0.000192 loss: 3.1505 (2.9884) grad_norm: 2.1562 (inf) time: 0.6276 [2021-03-27 23:39:38 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 400/1251] eta: 0:09:05 lr: 0.000192 loss: 2.9472 (2.9883) grad_norm: 2.1387 (inf) time: 0.6309 [2021-03-27 23:39:44 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 410/1251] eta: 0:08:58 lr: 0.000192 loss: 2.9457 (2.9831) grad_norm: 2.3214 (inf) time: 0.6292 [2021-03-27 23:39:50 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 420/1251] eta: 0:08:51 lr: 0.000192 loss: 3.0609 (2.9878) grad_norm: 2.3214 (inf) time: 0.6247 [2021-03-27 23:39:56 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 430/1251] eta: 0:08:45 lr: 0.000192 loss: 3.3436 (2.9961) grad_norm: 2.1993 (inf) time: 0.6223 [2021-03-27 23:40:03 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 440/1251] eta: 0:08:38 lr: 0.000192 loss: 3.2618 (2.9925) grad_norm: 2.1767 (inf) time: 0.6279 [2021-03-27 23:40:09 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 450/1251] eta: 0:08:32 lr: 0.000192 loss: 3.1112 (2.9973) grad_norm: 2.1645 (inf) time: 0.6318 [2021-03-27 23:40:15 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 460/1251] eta: 0:08:25 lr: 0.000192 loss: 2.9860 (2.9948) grad_norm: 2.1321 (inf) time: 0.6332 [2021-03-27 23:40:22 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 470/1251] eta: 0:08:19 lr: 0.000192 loss: 2.9169 (2.9941) grad_norm: 2.1027 (inf) time: 0.6327 [2021-03-27 23:40:28 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 480/1251] eta: 0:08:12 lr: 0.000192 loss: 3.1836 (2.9989) grad_norm: 2.2398 (inf) time: 0.6257 [2021-03-27 23:40:34 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 490/1251] eta: 0:08:05 lr: 0.000192 loss: 3.1836 (2.9993) grad_norm: 2.2666 (inf) time: 0.6224 [2021-03-27 23:40:40 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 500/1251] eta: 0:07:59 lr: 0.000192 loss: 2.9325 (2.9972) grad_norm: 2.3367 (inf) time: 0.6227 [2021-03-27 23:40:46 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 510/1251] eta: 0:07:52 lr: 0.000192 loss: 2.9325 (2.9977) grad_norm: 2.3289 (inf) time: 0.6230 [2021-03-27 23:40:53 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 520/1251] eta: 0:07:46 lr: 0.000192 loss: 3.2065 (2.9999) grad_norm: 2.2445 (inf) time: 0.6246 [2021-03-27 23:40:59 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 530/1251] eta: 0:07:39 lr: 0.000192 loss: 3.2065 (2.9977) grad_norm: 2.1050 (inf) time: 0.6251 [2021-03-27 23:41:05 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 540/1251] eta: 0:07:33 lr: 0.000192 loss: 3.0175 (2.9971) grad_norm: 2.1559 (inf) time: 0.6295 [2021-03-27 23:41:12 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 550/1251] eta: 0:07:26 lr: 0.000192 loss: 3.0334 (2.9965) grad_norm: 2.3287 (inf) time: 0.6326 [2021-03-27 23:41:18 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 560/1251] eta: 0:07:20 lr: 0.000192 loss: 3.1034 (2.9981) grad_norm: 2.2952 (inf) time: 0.6327 [2021-03-27 23:41:24 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 570/1251] eta: 0:07:13 lr: 0.000192 loss: 3.0896 (2.9960) grad_norm: 2.0480 (inf) time: 0.6329 [2021-03-27 23:41:31 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 580/1251] eta: 0:07:07 lr: 0.000192 loss: 2.8784 (2.9937) grad_norm: 2.1439 (inf) time: 0.6340 [2021-03-27 23:41:37 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 590/1251] eta: 0:07:00 lr: 0.000192 loss: 3.1582 (2.9975) grad_norm: 2.2027 (inf) time: 0.6326 [2021-03-27 23:41:43 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 600/1251] eta: 0:06:54 lr: 0.000192 loss: 3.1489 (2.9920) grad_norm: 2.1056 (inf) time: 0.6318 [2021-03-27 23:41:50 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 610/1251] eta: 0:06:48 lr: 0.000192 loss: 2.4831 (2.9877) grad_norm: 2.1569 (inf) time: 0.6373 [2021-03-27 23:41:56 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 620/1251] eta: 0:06:41 lr: 0.000191 loss: 3.0678 (2.9910) grad_norm: 2.2909 (inf) time: 0.6328 [2021-03-27 23:42:02 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 630/1251] eta: 0:06:35 lr: 0.000191 loss: 3.2293 (2.9925) grad_norm: 2.4349 (inf) time: 0.6259 [2021-03-27 23:42:08 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 640/1251] eta: 0:06:28 lr: 0.000191 loss: 3.1006 (2.9928) grad_norm: 2.2740 (inf) time: 0.6229 [2021-03-27 23:42:15 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 650/1251] eta: 0:06:22 lr: 0.000191 loss: 2.8984 (2.9918) grad_norm: 2.2316 (inf) time: 0.6227 [2021-03-27 23:42:21 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 660/1251] eta: 0:06:15 lr: 0.000191 loss: 3.0654 (2.9912) grad_norm: 2.0787 (inf) time: 0.6298 [2021-03-27 23:42:27 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 670/1251] eta: 0:06:09 lr: 0.000191 loss: 3.1206 (2.9913) grad_norm: 2.1832 (inf) time: 0.6321 [2021-03-27 23:42:34 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 680/1251] eta: 0:06:03 lr: 0.000191 loss: 3.0547 (2.9899) grad_norm: 2.1832 (inf) time: 0.6275 [2021-03-27 23:42:40 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 690/1251] eta: 0:05:56 lr: 0.000191 loss: 3.0418 (2.9914) grad_norm: 2.0611 (inf) time: 0.6273 [2021-03-27 23:42:46 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 700/1251] eta: 0:05:50 lr: 0.000191 loss: 2.8539 (2.9872) grad_norm: 2.0581 (inf) time: 0.6285 [2021-03-27 23:42:52 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 710/1251] eta: 0:05:43 lr: 0.000191 loss: 2.8003 (2.9860) grad_norm: 2.1071 (inf) time: 0.6250 [2021-03-27 23:42:59 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 720/1251] eta: 0:05:37 lr: 0.000191 loss: 3.0348 (2.9858) grad_norm: 2.0981 (inf) time: 0.6215 [2021-03-27 23:43:05 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 730/1251] eta: 0:05:30 lr: 0.000191 loss: 3.1087 (2.9867) grad_norm: 2.1355 (inf) time: 0.6272 [2021-03-27 23:43:11 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 740/1251] eta: 0:05:24 lr: 0.000191 loss: 3.0754 (2.9880) grad_norm: 2.1760 (inf) time: 0.6322 [2021-03-27 23:43:18 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 750/1251] eta: 0:05:18 lr: 0.000191 loss: 3.2182 (2.9919) grad_norm: 2.1666 (inf) time: 0.6333 [2021-03-27 23:43:24 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 760/1251] eta: 0:05:11 lr: 0.000191 loss: 3.2019 (2.9893) grad_norm: 2.1764 (inf) time: 0.6286 [2021-03-27 23:43:30 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 770/1251] eta: 0:05:05 lr: 0.000191 loss: 2.9954 (2.9894) grad_norm: 2.1956 (inf) time: 0.6269 [2021-03-27 23:43:36 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 780/1251] eta: 0:04:58 lr: 0.000191 loss: 2.9869 (2.9885) grad_norm: 2.1896 (inf) time: 0.6278 [2021-03-27 23:43:43 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 790/1251] eta: 0:04:52 lr: 0.000191 loss: 2.8735 (2.9866) grad_norm: 2.1896 (inf) time: 0.6256 [2021-03-27 23:43:49 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 800/1251] eta: 0:04:46 lr: 0.000191 loss: 3.0307 (2.9878) grad_norm: 2.2703 (inf) time: 0.6288 [2021-03-27 23:43:55 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 810/1251] eta: 0:04:39 lr: 0.000191 loss: 3.0307 (2.9869) grad_norm: 2.2703 (inf) time: 0.6247 [2021-03-27 23:44:01 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 820/1251] eta: 0:04:33 lr: 0.000191 loss: 2.9972 (2.9860) grad_norm: 2.1868 (inf) time: 0.6270 [2021-03-27 23:44:08 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 830/1251] eta: 0:04:27 lr: 0.000191 loss: 2.8572 (2.9850) grad_norm: 2.2202 (inf) time: 0.6340 [2021-03-27 23:44:14 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 840/1251] eta: 0:04:20 lr: 0.000191 loss: 3.2577 (2.9883) grad_norm: 2.2921 (inf) time: 0.6282 [2021-03-27 23:44:20 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 850/1251] eta: 0:04:14 lr: 0.000191 loss: 3.1076 (2.9877) grad_norm: 2.2298 (inf) time: 0.6289 [2021-03-27 23:44:27 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 860/1251] eta: 0:04:08 lr: 0.000191 loss: 3.0001 (2.9858) grad_norm: 2.2298 (inf) time: 0.6337 [2021-03-27 23:44:33 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 870/1251] eta: 0:04:01 lr: 0.000191 loss: 3.0001 (2.9858) grad_norm: 2.2374 (inf) time: 0.6309 [2021-03-27 23:44:39 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 880/1251] eta: 0:03:55 lr: 0.000191 loss: 3.0450 (2.9867) grad_norm: 2.1842 (inf) time: 0.6264 [2021-03-27 23:44:46 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 890/1251] eta: 0:03:48 lr: 0.000191 loss: 3.0450 (2.9859) grad_norm: 2.1414 (inf) time: 0.6288 [2021-03-27 23:44:52 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 900/1251] eta: 0:03:42 lr: 0.000191 loss: 3.1158 (2.9883) grad_norm: 2.1414 (inf) time: 0.6336 [2021-03-27 23:44:58 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 910/1251] eta: 0:03:36 lr: 0.000191 loss: 3.2131 (2.9896) grad_norm: 2.3977 (inf) time: 0.6292 [2021-03-27 23:45:04 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 920/1251] eta: 0:03:29 lr: 0.000191 loss: 2.9412 (2.9888) grad_norm: 2.1880 (inf) time: 0.6265 [2021-03-27 23:45:11 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 930/1251] eta: 0:03:23 lr: 0.000191 loss: 2.9412 (2.9871) grad_norm: 2.1615 (inf) time: 0.6259 [2021-03-27 23:45:17 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 940/1251] eta: 0:03:17 lr: 0.000190 loss: 3.0261 (2.9886) grad_norm: 2.2305 (inf) time: 0.6255 [2021-03-27 23:45:23 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 950/1251] eta: 0:03:10 lr: 0.000190 loss: 3.0445 (2.9847) grad_norm: 2.2625 (inf) time: 0.6343 [2021-03-27 23:45:30 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 960/1251] eta: 0:03:04 lr: 0.000190 loss: 3.0882 (2.9857) grad_norm: 2.1747 (inf) time: 0.6360 [2021-03-27 23:45:36 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 970/1251] eta: 0:02:58 lr: 0.000190 loss: 3.0917 (2.9835) grad_norm: 2.2047 (inf) time: 0.6338 [2021-03-27 23:45:42 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 980/1251] eta: 0:02:51 lr: 0.000190 loss: 2.9082 (2.9831) grad_norm: 2.2047 (inf) time: 0.6284 [2021-03-27 23:45:48 swin_base_patch4_window7_224] INFO: Epoch: [215] [ 990/1251] eta: 0:02:45 lr: 0.000190 loss: 2.9082 (2.9816) grad_norm: 2.0626 (inf) time: 0.6204 [2021-03-27 23:45:55 swin_base_patch4_window7_224] INFO: Epoch: [215] [1000/1251] eta: 0:02:39 lr: 0.000190 loss: 3.0416 (2.9833) grad_norm: 2.1015 (inf) time: 0.6240 [2021-03-27 23:46:01 swin_base_patch4_window7_224] INFO: Epoch: [215] [1010/1251] eta: 0:02:32 lr: 0.000190 loss: 3.0305 (2.9826) grad_norm: 2.2280 (inf) time: 0.6273 [2021-03-27 23:46:07 swin_base_patch4_window7_224] INFO: Epoch: [215] [1020/1251] eta: 0:02:26 lr: 0.000190 loss: 3.0978 (2.9816) grad_norm: 2.3358 (inf) time: 0.6279 [2021-03-27 23:46:14 swin_base_patch4_window7_224] INFO: Epoch: [215] [1030/1251] eta: 0:02:19 lr: 0.000190 loss: 3.1065 (2.9823) grad_norm: 2.2177 (inf) time: 0.6299 [2021-03-27 23:46:20 swin_base_patch4_window7_224] INFO: Epoch: [215] [1040/1251] eta: 0:02:13 lr: 0.000190 loss: 3.2202 (2.9856) grad_norm: 2.1209 (inf) time: 0.6304 [2021-03-27 23:46:26 swin_base_patch4_window7_224] INFO: Epoch: [215] [1050/1251] eta: 0:02:07 lr: 0.000190 loss: 3.2202 (2.9873) grad_norm: 2.2141 (inf) time: 0.6262 [2021-03-27 23:46:32 swin_base_patch4_window7_224] INFO: Epoch: [215] [1060/1251] eta: 0:02:00 lr: 0.000190 loss: 3.0140 (2.9867) grad_norm: 2.1916 (inf) time: 0.6229 [2021-03-27 23:46:39 swin_base_patch4_window7_224] INFO: Epoch: [215] [1070/1251] eta: 0:01:54 lr: 0.000190 loss: 3.0863 (2.9870) grad_norm: 2.1503 (inf) time: 0.6206 [2021-03-27 23:46:45 swin_base_patch4_window7_224] INFO: Epoch: [215] [1080/1251] eta: 0:01:48 lr: 0.000190 loss: 3.1067 (2.9858) grad_norm: 2.2360 (inf) time: 0.6261 [2021-03-27 23:46:51 swin_base_patch4_window7_224] INFO: Epoch: [215] [1090/1251] eta: 0:01:41 lr: 0.000190 loss: 3.0613 (2.9836) grad_norm: 2.2967 (inf) time: 0.6305 [2021-03-27 23:46:57 swin_base_patch4_window7_224] INFO: Epoch: [215] [1100/1251] eta: 0:01:35 lr: 0.000190 loss: 3.0652 (2.9842) grad_norm: 2.3266 (inf) time: 0.6270 [2021-03-27 23:47:04 swin_base_patch4_window7_224] INFO: Epoch: [215] [1110/1251] eta: 0:01:29 lr: 0.000190 loss: 3.1504 (2.9853) grad_norm: 2.2032 (inf) time: 0.6260 [2021-03-27 23:47:10 swin_base_patch4_window7_224] INFO: Epoch: [215] [1120/1251] eta: 0:01:22 lr: 0.000190 loss: 3.1504 (2.9849) grad_norm: 2.1629 (inf) time: 0.6245 [2021-03-27 23:47:16 swin_base_patch4_window7_224] INFO: Epoch: [215] [1130/1251] eta: 0:01:16 lr: 0.000190 loss: 3.1723 (2.9863) grad_norm: 2.1653 (inf) time: 0.6245 [2021-03-27 23:47:22 swin_base_patch4_window7_224] INFO: Epoch: [215] [1140/1251] eta: 0:01:10 lr: 0.000190 loss: 3.1018 (2.9845) grad_norm: 2.1653 (inf) time: 0.6252 [2021-03-27 23:47:29 swin_base_patch4_window7_224] INFO: Epoch: [215] [1150/1251] eta: 0:01:03 lr: 0.000190 loss: 3.1018 (2.9860) grad_norm: 2.2094 (inf) time: 0.6307 [2021-03-27 23:47:35 swin_base_patch4_window7_224] INFO: Epoch: [215] [1160/1251] eta: 0:00:57 lr: 0.000190 loss: 3.1724 (2.9860) grad_norm: 2.1963 (inf) time: 0.6319 [2021-03-27 23:47:41 swin_base_patch4_window7_224] INFO: Epoch: [215] [1170/1251] eta: 0:00:51 lr: 0.000190 loss: 2.7730 (2.9816) grad_norm: 2.1204 (inf) time: 0.6246 [2021-03-27 23:47:48 swin_base_patch4_window7_224] INFO: Epoch: [215] [1180/1251] eta: 0:00:44 lr: 0.000190 loss: 3.0762 (2.9830) grad_norm: 2.2276 (inf) time: 0.6264 [2021-03-27 23:47:54 swin_base_patch4_window7_224] INFO: Epoch: [215] [1190/1251] eta: 0:00:38 lr: 0.000190 loss: 3.0943 (2.9807) grad_norm: 2.2369 (inf) time: 0.6319 [2021-03-27 23:48:00 swin_base_patch4_window7_224] INFO: Epoch: [215] [1200/1251] eta: 0:00:32 lr: 0.000190 loss: 2.8437 (2.9800) grad_norm: 2.1700 (inf) time: 0.6283 [2021-03-27 23:48:06 swin_base_patch4_window7_224] INFO: Epoch: [215] [1210/1251] eta: 0:00:25 lr: 0.000190 loss: 2.9719 (2.9803) grad_norm: 2.1667 (inf) time: 0.6228 [2021-03-27 23:48:13 swin_base_patch4_window7_224] INFO: Epoch: [215] [1220/1251] eta: 0:00:19 lr: 0.000190 loss: 3.1727 (2.9818) grad_norm: 2.1667 (inf) time: 0.6297 [2021-03-27 23:48:19 swin_base_patch4_window7_224] INFO: Epoch: [215] [1230/1251] eta: 0:00:13 lr: 0.000190 loss: 3.1247 (2.9816) grad_norm: 2.1654 (inf) time: 0.6335 [2021-03-27 23:48:25 swin_base_patch4_window7_224] INFO: Epoch: [215] [1240/1251] eta: 0:00:06 lr: 0.000190 loss: 2.9882 (2.9804) grad_norm: 2.1167 (inf) time: 0.6299 [2021-03-27 23:48:32 swin_base_patch4_window7_224] INFO: Epoch: [215] [1250/1251] eta: 0:00:00 lr: 0.000189 loss: 2.7466 (2.9794) grad_norm: 2.1941 (inf) time: 0.6207 [2021-03-27 23:49:44 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:12 loss: 1.1615 (1.1615) acc1: 73.4375 (73.4375) acc5: 92.1875 (92.1875) [2021-03-27 23:49:45 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.7624 (0.7619) acc1: 82.8125 (82.2443) acc5: 96.8750 (96.1648) [2021-03-27 23:49:46 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7219 (0.7685) acc1: 82.8125 (82.5149) acc5: 96.8750 (96.2798) [2021-03-27 23:49:48 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7816 (0.7941) acc1: 82.8125 (81.8044) acc5: 96.8750 (96.0685) [2021-03-27 23:49:49 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8550 (0.7984) acc1: 81.2500 (81.6692) acc5: 96.8750 (96.2652) [2021-03-27 23:49:50 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8550 (0.8038) acc1: 81.2500 (81.6000) acc5: 96.8750 (96.0960) [2021-03-27 23:50:01 swin_base_patch4_window7_224] INFO: * Acc@1 81.904 Acc@5 96.014 loss 0.790 [2021-03-27 23:50:01 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.9% [2021-03-27 23:50:01 swin_base_patch4_window7_224] INFO: Max accuracy: 81.90% [2021-03-27 23:50:05 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 0/1251] eta: 1:30:39 lr: 0.000189 loss: 3.1019 (3.1019) grad_norm: 2.2487 (2.2487) time: 4.3485 [2021-03-27 23:50:11 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 10/1251] eta: 0:20:14 lr: 0.000189 loss: 3.1019 (2.9224) grad_norm: 2.2544 (2.2810) time: 0.9787 [2021-03-27 23:50:18 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 20/1251] eta: 0:16:35 lr: 0.000189 loss: 3.1153 (3.0914) grad_norm: 2.1909 (2.2554) time: 0.6314 [2021-03-27 23:50:24 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 30/1251] eta: 0:15:16 lr: 0.000189 loss: 3.1481 (3.0509) grad_norm: 2.1224 (2.2442) time: 0.6253 [2021-03-27 23:50:30 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 40/1251] eta: 0:14:35 lr: 0.000189 loss: 3.0675 (3.0059) grad_norm: 2.0897 (2.2179) time: 0.6334 [2021-03-27 23:50:36 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 50/1251] eta: 0:14:05 lr: 0.000189 loss: 3.2361 (3.0068) grad_norm: 2.0897 (2.2589) time: 0.6320 [2021-03-27 23:50:43 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 60/1251] eta: 0:13:43 lr: 0.000189 loss: 3.2365 (2.9996) grad_norm: 2.4548 (2.2905) time: 0.6271 [2021-03-27 23:50:49 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 70/1251] eta: 0:13:27 lr: 0.000189 loss: 3.1741 (3.0036) grad_norm: 2.3929 (2.2924) time: 0.6322 [2021-03-27 23:50:56 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 80/1251] eta: 0:13:15 lr: 0.000189 loss: 2.9129 (2.9811) grad_norm: 2.2025 (2.2787) time: 0.6405 [2021-03-27 23:51:02 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 90/1251] eta: 0:13:03 lr: 0.000189 loss: 3.0160 (2.9869) grad_norm: 2.2380 (2.2844) time: 0.6423 [2021-03-27 23:51:08 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 100/1251] eta: 0:12:52 lr: 0.000189 loss: 3.2092 (3.0003) grad_norm: 2.2712 (2.2908) time: 0.6387 [2021-03-27 23:51:15 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 110/1251] eta: 0:12:41 lr: 0.000189 loss: 3.2092 (3.0001) grad_norm: 2.1274 (2.2815) time: 0.6320 [2021-03-27 23:51:21 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 120/1251] eta: 0:12:31 lr: 0.000189 loss: 2.8037 (2.9795) grad_norm: 2.1274 (2.2998) time: 0.6311 [2021-03-27 23:51:27 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 130/1251] eta: 0:12:22 lr: 0.000189 loss: 2.8037 (2.9848) grad_norm: 2.2136 (2.3024) time: 0.6360 [2021-03-27 23:51:34 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 140/1251] eta: 0:12:13 lr: 0.000189 loss: 2.7972 (2.9472) grad_norm: 2.3941 (2.3087) time: 0.6369 [2021-03-27 23:51:40 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 150/1251] eta: 0:12:05 lr: 0.000189 loss: 2.7972 (2.9427) grad_norm: 2.4146 (2.3093) time: 0.6338 [2021-03-27 23:51:46 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 160/1251] eta: 0:11:56 lr: 0.000189 loss: 3.1140 (2.9576) grad_norm: 2.2446 (2.3135) time: 0.6277 [2021-03-27 23:51:53 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 170/1251] eta: 0:11:47 lr: 0.000189 loss: 3.1235 (2.9574) grad_norm: 2.2193 (2.3080) time: 0.6271 [2021-03-27 23:51:59 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 180/1251] eta: 0:11:40 lr: 0.000189 loss: 2.9499 (2.9521) grad_norm: 2.2577 (2.3027) time: 0.6312 [2021-03-27 23:52:05 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 190/1251] eta: 0:11:31 lr: 0.000189 loss: 2.9842 (2.9551) grad_norm: 2.2946 (2.3055) time: 0.6295 [2021-03-27 23:52:11 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 200/1251] eta: 0:11:24 lr: 0.000189 loss: 2.9842 (2.9538) grad_norm: 2.2707 (2.3164) time: 0.6301 [2021-03-27 23:52:18 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 210/1251] eta: 0:11:16 lr: 0.000189 loss: 2.8024 (2.9466) grad_norm: 2.2597 (2.3253) time: 0.6296 [2021-03-27 23:52:24 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 220/1251] eta: 0:11:09 lr: 0.000189 loss: 2.8641 (2.9402) grad_norm: 2.2597 (2.3236) time: 0.6265 [2021-03-27 23:52:30 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 230/1251] eta: 0:11:01 lr: 0.000189 loss: 2.8641 (2.9389) grad_norm: 2.2165 (2.3165) time: 0.6251 [2021-03-27 23:52:37 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 240/1251] eta: 0:10:54 lr: 0.000189 loss: 3.0513 (2.9373) grad_norm: 2.1658 (2.3263) time: 0.6244 [2021-03-27 23:52:43 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 250/1251] eta: 0:10:47 lr: 0.000189 loss: 2.9450 (2.9354) grad_norm: 2.2524 (2.3282) time: 0.6370 [2021-03-27 23:52:49 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 260/1251] eta: 0:10:40 lr: 0.000189 loss: 2.8891 (2.9315) grad_norm: 2.3609 (2.3315) time: 0.6354 [2021-03-27 23:52:56 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 270/1251] eta: 0:10:33 lr: 0.000189 loss: 2.9854 (2.9334) grad_norm: 2.4059 (2.3365) time: 0.6304 [2021-03-27 23:53:02 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 280/1251] eta: 0:10:26 lr: 0.000189 loss: 3.1489 (2.9400) grad_norm: 2.3852 (2.3363) time: 0.6288 [2021-03-27 23:53:08 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 290/1251] eta: 0:10:19 lr: 0.000189 loss: 3.1659 (2.9440) grad_norm: 2.2071 (2.3325) time: 0.6262 [2021-03-27 23:53:14 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 300/1251] eta: 0:10:12 lr: 0.000189 loss: 3.1207 (2.9480) grad_norm: 2.2071 (2.3349) time: 0.6335 [2021-03-27 23:53:21 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 310/1251] eta: 0:10:06 lr: 0.000188 loss: 2.9182 (2.9411) grad_norm: 2.3609 (2.3374) time: 0.6374 [2021-03-27 23:53:27 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 320/1251] eta: 0:09:59 lr: 0.000188 loss: 2.8134 (2.9361) grad_norm: 2.2803 (2.3419) time: 0.6340 [2021-03-27 23:53:33 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 330/1251] eta: 0:09:52 lr: 0.000188 loss: 3.0222 (2.9395) grad_norm: 2.2645 (2.3408) time: 0.6302 [2021-03-27 23:53:40 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 340/1251] eta: 0:09:45 lr: 0.000188 loss: 3.0357 (2.9388) grad_norm: 2.3245 (2.3411) time: 0.6303 [2021-03-27 23:53:46 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 350/1251] eta: 0:09:38 lr: 0.000188 loss: 3.1002 (2.9403) grad_norm: 2.3245 (2.3438) time: 0.6282 [2021-03-27 23:53:52 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 360/1251] eta: 0:09:32 lr: 0.000188 loss: 3.1323 (2.9417) grad_norm: 2.2715 (2.3410) time: 0.6314 [2021-03-27 23:53:59 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 370/1251] eta: 0:09:25 lr: 0.000188 loss: 2.9007 (2.9406) grad_norm: 2.1955 (2.3635) time: 0.6287 [2021-03-27 23:54:05 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 380/1251] eta: 0:09:18 lr: 0.000188 loss: 2.9007 (2.9422) grad_norm: 2.4774 (2.3651) time: 0.6268 [2021-03-27 23:54:11 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 390/1251] eta: 0:09:12 lr: 0.000188 loss: 3.0993 (2.9446) grad_norm: 2.1580 (2.3607) time: 0.6324 [2021-03-27 23:54:18 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 400/1251] eta: 0:09:05 lr: 0.000188 loss: 3.0993 (2.9470) grad_norm: 2.1173 (2.3817) time: 0.6288 [2021-03-27 23:54:24 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 410/1251] eta: 0:08:58 lr: 0.000188 loss: 2.8288 (2.9424) grad_norm: 2.2639 (2.3778) time: 0.6249 [2021-03-27 23:54:30 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 420/1251] eta: 0:08:51 lr: 0.000188 loss: 2.7192 (2.9424) grad_norm: 2.1885 (2.3783) time: 0.6244 [2021-03-27 23:54:36 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 430/1251] eta: 0:08:45 lr: 0.000188 loss: 2.8920 (2.9394) grad_norm: 2.1422 (2.3750) time: 0.6261 [2021-03-27 23:54:43 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 440/1251] eta: 0:08:38 lr: 0.000188 loss: 2.9123 (2.9407) grad_norm: 2.1422 (2.3766) time: 0.6295 [2021-03-27 23:54:49 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 450/1251] eta: 0:08:32 lr: 0.000188 loss: 3.0255 (2.9412) grad_norm: 2.2158 (2.3735) time: 0.6300 [2021-03-27 23:54:55 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 460/1251] eta: 0:08:25 lr: 0.000188 loss: 2.8945 (2.9425) grad_norm: 2.2091 (2.3724) time: 0.6346 [2021-03-27 23:55:02 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 470/1251] eta: 0:08:19 lr: 0.000188 loss: 2.8714 (2.9434) grad_norm: 2.3058 (2.3742) time: 0.6356 [2021-03-27 23:55:08 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 480/1251] eta: 0:08:12 lr: 0.000188 loss: 2.8923 (2.9426) grad_norm: 2.2327 (2.3710) time: 0.6282 [2021-03-27 23:55:14 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 490/1251] eta: 0:08:05 lr: 0.000188 loss: 3.0448 (2.9476) grad_norm: 2.2327 (2.3724) time: 0.6210 [2021-03-27 23:55:20 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 500/1251] eta: 0:07:59 lr: 0.000188 loss: 3.1396 (2.9520) grad_norm: 2.2260 (2.3729) time: 0.6262 [2021-03-27 23:55:27 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 510/1251] eta: 0:07:52 lr: 0.000188 loss: 3.0987 (2.9529) grad_norm: 2.1787 (2.3805) time: 0.6302 [2021-03-27 23:55:33 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 520/1251] eta: 0:07:46 lr: 0.000188 loss: 3.0182 (2.9509) grad_norm: 2.1847 (2.3769) time: 0.6258 [2021-03-27 23:55:39 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 530/1251] eta: 0:07:39 lr: 0.000188 loss: 2.8613 (2.9469) grad_norm: 2.2524 (2.3774) time: 0.6257 [2021-03-27 23:55:45 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 540/1251] eta: 0:07:33 lr: 0.000188 loss: 2.4891 (2.9403) grad_norm: 2.2993 (2.3762) time: 0.6266 [2021-03-27 23:55:52 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 550/1251] eta: 0:07:26 lr: 0.000188 loss: 3.0429 (2.9426) grad_norm: 2.2611 (2.3748) time: 0.6350 [2021-03-27 23:55:58 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 560/1251] eta: 0:07:20 lr: 0.000188 loss: 3.1427 (2.9442) grad_norm: 2.2611 (2.3748) time: 0.6381 [2021-03-27 23:56:04 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 570/1251] eta: 0:07:13 lr: 0.000188 loss: 3.1427 (2.9439) grad_norm: 2.2053 (2.3724) time: 0.6300 [2021-03-27 23:56:11 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 580/1251] eta: 0:07:07 lr: 0.000188 loss: 2.6596 (2.9362) grad_norm: 2.1647 (2.3719) time: 0.6291 [2021-03-27 23:56:17 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 590/1251] eta: 0:07:01 lr: 0.000188 loss: 2.5178 (2.9318) grad_norm: 2.4158 (2.3723) time: 0.6331 [2021-03-27 23:56:24 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 600/1251] eta: 0:06:54 lr: 0.000188 loss: 2.7692 (2.9287) grad_norm: 2.2148 (2.3734) time: 0.6366 [2021-03-27 23:56:30 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 610/1251] eta: 0:06:48 lr: 0.000188 loss: 2.6660 (2.9256) grad_norm: 2.2148 (2.3725) time: 0.6320 [2021-03-27 23:56:36 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 620/1251] eta: 0:06:41 lr: 0.000187 loss: 2.8906 (2.9250) grad_norm: 2.2385 (2.3697) time: 0.6293 [2021-03-27 23:56:42 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 630/1251] eta: 0:06:35 lr: 0.000187 loss: 2.8906 (2.9244) grad_norm: 2.1654 (2.3664) time: 0.6341 [2021-03-27 23:56:49 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 640/1251] eta: 0:06:29 lr: 0.000187 loss: 3.0796 (2.9281) grad_norm: 2.1650 (2.3662) time: 0.6316 [2021-03-27 23:56:55 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 650/1251] eta: 0:06:22 lr: 0.000187 loss: 3.0248 (2.9269) grad_norm: 2.1959 (2.3647) time: 0.6275 [2021-03-27 23:57:01 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 660/1251] eta: 0:06:16 lr: 0.000187 loss: 2.9012 (2.9282) grad_norm: 2.2880 (2.3652) time: 0.6314 [2021-03-27 23:57:08 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 670/1251] eta: 0:06:09 lr: 0.000187 loss: 3.0324 (2.9271) grad_norm: 2.3042 (2.3641) time: 0.6316 [2021-03-27 23:57:14 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 680/1251] eta: 0:06:03 lr: 0.000187 loss: 2.8510 (2.9248) grad_norm: 2.1223 (2.3599) time: 0.6281 [2021-03-27 23:57:20 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 690/1251] eta: 0:05:56 lr: 0.000187 loss: 3.2303 (2.9282) grad_norm: 2.1434 (2.3602) time: 0.6334 [2021-03-27 23:57:27 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 700/1251] eta: 0:05:50 lr: 0.000187 loss: 3.2303 (2.9274) grad_norm: 2.3035 (2.3612) time: 0.6352 [2021-03-27 23:57:33 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 710/1251] eta: 0:05:44 lr: 0.000187 loss: 2.9116 (2.9260) grad_norm: 2.2433 (2.3575) time: 0.6302 [2021-03-27 23:57:39 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 720/1251] eta: 0:05:37 lr: 0.000187 loss: 3.0817 (2.9274) grad_norm: 2.1101 (2.3551) time: 0.6298 [2021-03-27 23:57:46 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 730/1251] eta: 0:05:31 lr: 0.000187 loss: 3.0817 (2.9264) grad_norm: 2.1133 (2.3531) time: 0.6322 [2021-03-27 23:57:52 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 740/1251] eta: 0:05:25 lr: 0.000187 loss: 2.9659 (2.9244) grad_norm: 2.0997 (2.3502) time: 0.6377 [2021-03-27 23:57:58 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 750/1251] eta: 0:05:18 lr: 0.000187 loss: 3.0404 (2.9262) grad_norm: 2.2360 (2.3512) time: 0.6374 [2021-03-27 23:58:05 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 760/1251] eta: 0:05:12 lr: 0.000187 loss: 3.0530 (2.9255) grad_norm: 2.3124 (2.3517) time: 0.6393 [2021-03-27 23:58:11 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 770/1251] eta: 0:05:05 lr: 0.000187 loss: 2.9329 (2.9269) grad_norm: 2.1865 (2.3509) time: 0.6374 [2021-03-27 23:58:17 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 780/1251] eta: 0:04:59 lr: 0.000187 loss: 2.9327 (2.9270) grad_norm: 2.2233 (2.3505) time: 0.6272 [2021-03-27 23:58:24 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 790/1251] eta: 0:04:53 lr: 0.000187 loss: 2.7686 (2.9239) grad_norm: 2.2735 (2.3499) time: 0.6271 [2021-03-27 23:58:30 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 800/1251] eta: 0:04:46 lr: 0.000187 loss: 2.7605 (2.9237) grad_norm: 2.2596 (2.3481) time: 0.6295 [2021-03-27 23:58:36 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 810/1251] eta: 0:04:40 lr: 0.000187 loss: 3.1159 (2.9261) grad_norm: 2.1286 (2.3540) time: 0.6335 [2021-03-27 23:58:43 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 820/1251] eta: 0:04:34 lr: 0.000187 loss: 3.0330 (2.9257) grad_norm: 2.3076 (2.3530) time: 0.6350 [2021-03-27 23:58:49 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 830/1251] eta: 0:04:27 lr: 0.000187 loss: 3.0330 (2.9269) grad_norm: 2.3409 (2.3549) time: 0.6316 [2021-03-27 23:58:55 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 840/1251] eta: 0:04:21 lr: 0.000187 loss: 3.0499 (2.9252) grad_norm: 2.1679 (2.3535) time: 0.6261 [2021-03-27 23:59:02 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 850/1251] eta: 0:04:14 lr: 0.000187 loss: 2.7181 (2.9231) grad_norm: 2.2306 (2.3544) time: 0.6293 [2021-03-27 23:59:08 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 860/1251] eta: 0:04:08 lr: 0.000187 loss: 2.9804 (2.9242) grad_norm: 2.1888 (2.3522) time: 0.6349 [2021-03-27 23:59:14 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 870/1251] eta: 0:04:02 lr: 0.000187 loss: 3.0753 (2.9244) grad_norm: 2.0943 (2.3499) time: 0.6308 [2021-03-27 23:59:20 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 880/1251] eta: 0:03:55 lr: 0.000187 loss: 3.1240 (2.9274) grad_norm: 2.1014 (2.3483) time: 0.6297 [2021-03-27 23:59:27 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 890/1251] eta: 0:03:49 lr: 0.000187 loss: 3.1238 (2.9272) grad_norm: 2.1112 (2.3473) time: 0.6370 [2021-03-27 23:59:33 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 900/1251] eta: 0:03:43 lr: 0.000187 loss: 2.8260 (2.9260) grad_norm: 2.1902 (2.3467) time: 0.6373 [2021-03-27 23:59:39 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 910/1251] eta: 0:03:36 lr: 0.000187 loss: 3.0291 (2.9268) grad_norm: 2.2787 (2.3535) time: 0.6273 [2021-03-27 23:59:46 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 920/1251] eta: 0:03:30 lr: 0.000187 loss: 3.0607 (2.9265) grad_norm: 2.1804 (2.3533) time: 0.6270 [2021-03-27 23:59:52 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 930/1251] eta: 0:03:23 lr: 0.000187 loss: 3.1432 (2.9267) grad_norm: 2.1313 (2.3535) time: 0.6300 [2021-03-27 23:59:58 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 940/1251] eta: 0:03:17 lr: 0.000186 loss: 3.1651 (2.9292) grad_norm: 2.2856 (2.3540) time: 0.6293 [2021-03-28 00:00:05 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 950/1251] eta: 0:03:11 lr: 0.000186 loss: 3.2562 (2.9323) grad_norm: 2.2794 (2.3524) time: 0.6290 [2021-03-28 00:00:11 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 960/1251] eta: 0:03:04 lr: 0.000186 loss: 3.1373 (2.9322) grad_norm: 2.2119 (2.3504) time: 0.6308 [2021-03-28 00:00:17 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 970/1251] eta: 0:02:58 lr: 0.000186 loss: 3.0020 (2.9327) grad_norm: 2.0871 (2.3489) time: 0.6312 [2021-03-28 00:00:23 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 980/1251] eta: 0:02:52 lr: 0.000186 loss: 2.7777 (2.9308) grad_norm: 2.1982 (2.3486) time: 0.6260 [2021-03-28 00:00:30 swin_base_patch4_window7_224] INFO: Epoch: [216] [ 990/1251] eta: 0:02:45 lr: 0.000186 loss: 2.7777 (2.9310) grad_norm: 2.2274 (2.3478) time: 0.6243 [2021-03-28 00:00:36 swin_base_patch4_window7_224] INFO: Epoch: [216] [1000/1251] eta: 0:02:39 lr: 0.000186 loss: 2.8320 (2.9303) grad_norm: 2.1579 (2.3460) time: 0.6227 [2021-03-28 00:00:42 swin_base_patch4_window7_224] INFO: Epoch: [216] [1010/1251] eta: 0:02:32 lr: 0.000186 loss: 2.7969 (2.9309) grad_norm: 2.0865 (2.3445) time: 0.6267 [2021-03-28 00:00:49 swin_base_patch4_window7_224] INFO: Epoch: [216] [1020/1251] eta: 0:02:26 lr: 0.000186 loss: 2.9668 (2.9306) grad_norm: 2.1061 (2.3437) time: 0.6342 [2021-03-28 00:00:55 swin_base_patch4_window7_224] INFO: Epoch: [216] [1030/1251] eta: 0:02:20 lr: 0.000186 loss: 3.0530 (2.9322) grad_norm: 2.1063 (2.3437) time: 0.6305 [2021-03-28 00:01:01 swin_base_patch4_window7_224] INFO: Epoch: [216] [1040/1251] eta: 0:02:13 lr: 0.000186 loss: 3.1676 (2.9332) grad_norm: 2.2577 (2.3434) time: 0.6252 [2021-03-28 00:01:07 swin_base_patch4_window7_224] INFO: Epoch: [216] [1050/1251] eta: 0:02:07 lr: 0.000186 loss: 2.9906 (2.9337) grad_norm: 2.1699 (2.3416) time: 0.6234 [2021-03-28 00:01:14 swin_base_patch4_window7_224] INFO: Epoch: [216] [1060/1251] eta: 0:02:01 lr: 0.000186 loss: 3.0719 (2.9366) grad_norm: 2.1773 (2.3417) time: 0.6262 [2021-03-28 00:01:20 swin_base_patch4_window7_224] INFO: Epoch: [216] [1070/1251] eta: 0:01:54 lr: 0.000186 loss: 3.2785 (2.9383) grad_norm: 2.4508 (2.3472) time: 0.6322 [2021-03-28 00:01:26 swin_base_patch4_window7_224] INFO: Epoch: [216] [1080/1251] eta: 0:01:48 lr: 0.000186 loss: 3.0957 (2.9395) grad_norm: 2.4508 (2.3470) time: 0.6294 [2021-03-28 00:01:33 swin_base_patch4_window7_224] INFO: Epoch: [216] [1090/1251] eta: 0:01:42 lr: 0.000186 loss: 3.2280 (2.9424) grad_norm: 2.3184 (2.3469) time: 0.6289 [2021-03-28 00:01:39 swin_base_patch4_window7_224] INFO: Epoch: [216] [1100/1251] eta: 0:01:35 lr: 0.000186 loss: 3.2280 (2.9443) grad_norm: 2.2610 (2.3464) time: 0.6322 [2021-03-28 00:01:45 swin_base_patch4_window7_224] INFO: Epoch: [216] [1110/1251] eta: 0:01:29 lr: 0.000186 loss: 3.0748 (2.9448) grad_norm: 2.1186 (2.3434) time: 0.6310 [2021-03-28 00:01:51 swin_base_patch4_window7_224] INFO: Epoch: [216] [1120/1251] eta: 0:01:23 lr: 0.000186 loss: 3.1528 (2.9458) grad_norm: 2.0430 (2.3414) time: 0.6287 [2021-03-28 00:01:58 swin_base_patch4_window7_224] INFO: Epoch: [216] [1130/1251] eta: 0:01:16 lr: 0.000186 loss: 3.0698 (2.9469) grad_norm: 2.1029 (2.3412) time: 0.6281 [2021-03-28 00:02:04 swin_base_patch4_window7_224] INFO: Epoch: [216] [1140/1251] eta: 0:01:10 lr: 0.000186 loss: 3.0605 (2.9472) grad_norm: 2.1447 (2.3406) time: 0.6306 [2021-03-28 00:02:10 swin_base_patch4_window7_224] INFO: Epoch: [216] [1150/1251] eta: 0:01:04 lr: 0.000186 loss: 2.9754 (2.9468) grad_norm: 2.1331 (2.3400) time: 0.6323 [2021-03-28 00:02:17 swin_base_patch4_window7_224] INFO: Epoch: [216] [1160/1251] eta: 0:00:57 lr: 0.000186 loss: 2.8763 (2.9460) grad_norm: 2.1548 (2.3392) time: 0.6336 [2021-03-28 00:02:23 swin_base_patch4_window7_224] INFO: Epoch: [216] [1170/1251] eta: 0:00:51 lr: 0.000186 loss: 2.6343 (2.9444) grad_norm: 2.2686 (inf) time: 0.6302 [2021-03-28 00:02:29 swin_base_patch4_window7_224] INFO: Epoch: [216] [1180/1251] eta: 0:00:45 lr: 0.000186 loss: 3.0739 (2.9464) grad_norm: 2.2608 (inf) time: 0.6272 [2021-03-28 00:02:36 swin_base_patch4_window7_224] INFO: Epoch: [216] [1190/1251] eta: 0:00:38 lr: 0.000186 loss: 3.1168 (2.9464) grad_norm: 2.1767 (inf) time: 0.6276 [2021-03-28 00:02:42 swin_base_patch4_window7_224] INFO: Epoch: [216] [1200/1251] eta: 0:00:32 lr: 0.000186 loss: 3.1168 (2.9475) grad_norm: 2.3297 (inf) time: 0.6281 [2021-03-28 00:02:48 swin_base_patch4_window7_224] INFO: Epoch: [216] [1210/1251] eta: 0:00:25 lr: 0.000186 loss: 3.0516 (2.9482) grad_norm: 2.2805 (inf) time: 0.6272 [2021-03-28 00:02:54 swin_base_patch4_window7_224] INFO: Epoch: [216] [1220/1251] eta: 0:00:19 lr: 0.000186 loss: 3.0822 (2.9503) grad_norm: 2.2169 (inf) time: 0.6248 [2021-03-28 00:03:01 swin_base_patch4_window7_224] INFO: Epoch: [216] [1230/1251] eta: 0:00:13 lr: 0.000186 loss: 3.0368 (2.9503) grad_norm: 2.2004 (inf) time: 0.6246 [2021-03-28 00:03:07 swin_base_patch4_window7_224] INFO: Epoch: [216] [1240/1251] eta: 0:00:06 lr: 0.000186 loss: 3.0368 (2.9515) grad_norm: 2.2219 (inf) time: 0.6267 [2021-03-28 00:03:13 swin_base_patch4_window7_224] INFO: Epoch: [216] [1250/1251] eta: 0:00:00 lr: 0.000186 loss: 3.0858 (2.9521) grad_norm: 2.2191 (inf) time: 0.6279 [2021-03-28 00:03:23 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:16 loss: 0.7216 (0.7216) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-28 00:03:26 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7216 (0.7779) acc1: 81.2500 (81.6761) acc5: 95.3125 (95.7386) [2021-03-28 00:03:29 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8182 (0.7995) acc1: 81.2500 (80.8780) acc5: 95.3125 (95.9077) [2021-03-28 00:03:31 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8757 (0.8247) acc1: 78.1250 (80.5444) acc5: 95.3125 (95.8165) [2021-03-28 00:03:33 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8413 (0.8097) acc1: 81.2500 (80.9070) acc5: 96.8750 (95.8460) [2021-03-28 00:03:34 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7294 (0.8083) acc1: 81.2500 (81.1200) acc5: 96.8750 (95.9360) [2021-03-28 00:03:44 swin_base_patch4_window7_224] INFO: * Acc@1 81.848 Acc@5 96.006 loss 0.793 [2021-03-28 00:03:44 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.8% [2021-03-28 00:03:44 swin_base_patch4_window7_224] INFO: Max accuracy: 81.90% [2021-03-28 00:03:48 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 0/1251] eta: 1:35:44 lr: 0.000185 loss: 2.9955 (2.9955) grad_norm: 2.2381 (2.2381) time: 4.5915 [2021-03-28 00:03:55 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 10/1251] eta: 0:20:26 lr: 0.000185 loss: 2.9191 (2.8193) grad_norm: 2.1772 (2.1923) time: 0.9884 [2021-03-28 00:04:01 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 20/1251] eta: 0:16:46 lr: 0.000185 loss: 3.1132 (3.1132) grad_norm: 2.1821 (2.2135) time: 0.6285 [2021-03-28 00:04:07 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 30/1251] eta: 0:15:26 lr: 0.000185 loss: 2.9905 (2.9614) grad_norm: 2.2207 (2.2479) time: 0.6329 [2021-03-28 00:04:14 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 40/1251] eta: 0:14:39 lr: 0.000185 loss: 2.7597 (2.9239) grad_norm: 2.3081 (2.3401) time: 0.6305 [2021-03-28 00:04:20 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 50/1251] eta: 0:14:10 lr: 0.000185 loss: 2.7134 (2.8711) grad_norm: 2.4506 (2.3483) time: 0.6284 [2021-03-28 00:04:26 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 60/1251] eta: 0:13:46 lr: 0.000185 loss: 2.8538 (2.8647) grad_norm: 2.4178 (2.3749) time: 0.6267 [2021-03-28 00:04:32 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 70/1251] eta: 0:13:29 lr: 0.000185 loss: 3.0368 (2.8920) grad_norm: 2.5463 (2.4205) time: 0.6292 [2021-03-28 00:04:39 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 80/1251] eta: 0:13:14 lr: 0.000185 loss: 2.9906 (2.9060) grad_norm: 2.2727 (2.3919) time: 0.6340 [2021-03-28 00:04:45 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 90/1251] eta: 0:13:03 lr: 0.000185 loss: 2.9349 (2.8893) grad_norm: 2.1633 (2.3771) time: 0.6357 [2021-03-28 00:04:52 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 100/1251] eta: 0:12:52 lr: 0.000185 loss: 3.0924 (2.9048) grad_norm: 2.1650 (2.3654) time: 0.6414 [2021-03-28 00:04:58 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 110/1251] eta: 0:12:41 lr: 0.000185 loss: 3.1228 (2.9111) grad_norm: 2.1301 (2.3530) time: 0.6351 [2021-03-28 00:05:04 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 120/1251] eta: 0:12:31 lr: 0.000185 loss: 2.6993 (2.8851) grad_norm: 2.1817 (2.3449) time: 0.6319 [2021-03-28 00:05:11 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 130/1251] eta: 0:12:22 lr: 0.000185 loss: 3.0106 (2.9071) grad_norm: 2.2027 (2.3318) time: 0.6333 [2021-03-28 00:05:17 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 140/1251] eta: 0:12:12 lr: 0.000185 loss: 3.1403 (2.9083) grad_norm: 2.0989 (2.3134) time: 0.6251 [2021-03-28 00:05:23 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 150/1251] eta: 0:12:04 lr: 0.000185 loss: 3.0814 (2.9026) grad_norm: 2.0989 (2.3067) time: 0.6299 [2021-03-28 00:05:29 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 160/1251] eta: 0:11:56 lr: 0.000185 loss: 2.9444 (2.9021) grad_norm: 2.2799 (2.3316) time: 0.6359 [2021-03-28 00:05:36 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 170/1251] eta: 0:11:47 lr: 0.000185 loss: 3.0087 (2.9096) grad_norm: 2.2846 (2.3318) time: 0.6294 [2021-03-28 00:05:42 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 180/1251] eta: 0:11:40 lr: 0.000185 loss: 2.9820 (2.9110) grad_norm: 2.1964 (2.3213) time: 0.6337 [2021-03-28 00:05:48 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 190/1251] eta: 0:11:32 lr: 0.000185 loss: 3.0480 (2.9208) grad_norm: 2.1526 (2.3209) time: 0.6321 [2021-03-28 00:05:55 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 200/1251] eta: 0:11:24 lr: 0.000185 loss: 3.0330 (2.9189) grad_norm: 2.1526 (2.3162) time: 0.6270 [2021-03-28 00:06:01 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 210/1251] eta: 0:11:17 lr: 0.000185 loss: 3.1115 (2.9335) grad_norm: 2.2480 (2.3194) time: 0.6330 [2021-03-28 00:06:07 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 220/1251] eta: 0:11:10 lr: 0.000185 loss: 3.1115 (2.9335) grad_norm: 2.2947 (2.3257) time: 0.6403 [2021-03-28 00:06:14 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 230/1251] eta: 0:11:02 lr: 0.000185 loss: 2.8270 (2.9227) grad_norm: 2.2774 (2.3262) time: 0.6371 [2021-03-28 00:06:20 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 240/1251] eta: 0:10:55 lr: 0.000185 loss: 2.8408 (2.9253) grad_norm: 2.3820 (2.3557) time: 0.6290 [2021-03-28 00:06:26 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 250/1251] eta: 0:10:48 lr: 0.000185 loss: 2.9095 (2.9138) grad_norm: 2.4143 (2.3554) time: 0.6254 [2021-03-28 00:06:33 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 260/1251] eta: 0:10:40 lr: 0.000185 loss: 2.6355 (2.9053) grad_norm: 2.2247 (2.3519) time: 0.6222 [2021-03-28 00:06:39 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 270/1251] eta: 0:10:33 lr: 0.000185 loss: 2.7443 (2.9045) grad_norm: 2.1968 (2.3494) time: 0.6253 [2021-03-28 00:06:45 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 280/1251] eta: 0:10:26 lr: 0.000185 loss: 3.2008 (2.9162) grad_norm: 2.2114 (2.3657) time: 0.6270 [2021-03-28 00:06:51 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 290/1251] eta: 0:10:19 lr: 0.000185 loss: 3.1540 (2.9108) grad_norm: 2.2847 (2.3608) time: 0.6277 [2021-03-28 00:06:58 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 300/1251] eta: 0:10:12 lr: 0.000185 loss: 2.7014 (2.9101) grad_norm: 2.1558 (2.3576) time: 0.6312 [2021-03-28 00:07:04 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 310/1251] eta: 0:10:05 lr: 0.000185 loss: 2.9788 (2.9137) grad_norm: 2.1215 (2.3518) time: 0.6310 [2021-03-28 00:07:10 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 320/1251] eta: 0:09:59 lr: 0.000184 loss: 3.0319 (2.9146) grad_norm: 2.0869 (2.3432) time: 0.6353 [2021-03-28 00:07:17 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 330/1251] eta: 0:09:52 lr: 0.000184 loss: 3.0319 (2.9191) grad_norm: 2.2579 (2.3488) time: 0.6312 [2021-03-28 00:07:23 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 340/1251] eta: 0:09:45 lr: 0.000184 loss: 2.9900 (2.9183) grad_norm: 2.5110 (2.3496) time: 0.6277 [2021-03-28 00:07:29 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 350/1251] eta: 0:09:38 lr: 0.000184 loss: 3.0464 (2.9257) grad_norm: 2.2804 (2.3488) time: 0.6343 [2021-03-28 00:07:36 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 360/1251] eta: 0:09:31 lr: 0.000184 loss: 3.0464 (2.9250) grad_norm: 2.2536 (2.3473) time: 0.6290 [2021-03-28 00:07:42 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 370/1251] eta: 0:09:25 lr: 0.000184 loss: 2.9424 (2.9234) grad_norm: 2.1734 (2.3427) time: 0.6236 [2021-03-28 00:07:48 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 380/1251] eta: 0:09:18 lr: 0.000184 loss: 2.9785 (2.9264) grad_norm: 2.2949 (2.3478) time: 0.6225 [2021-03-28 00:07:54 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 390/1251] eta: 0:09:11 lr: 0.000184 loss: 2.9785 (2.9240) grad_norm: 2.3570 (2.3477) time: 0.6214 [2021-03-28 00:08:00 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 400/1251] eta: 0:09:04 lr: 0.000184 loss: 2.9889 (2.9252) grad_norm: 2.2017 (2.3451) time: 0.6242 [2021-03-28 00:08:07 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 410/1251] eta: 0:08:57 lr: 0.000184 loss: 3.0114 (2.9252) grad_norm: 2.2017 (2.3476) time: 0.6263 [2021-03-28 00:08:13 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 420/1251] eta: 0:08:51 lr: 0.000184 loss: 3.0291 (2.9242) grad_norm: 2.2558 (2.3455) time: 0.6304 [2021-03-28 00:08:19 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 430/1251] eta: 0:08:44 lr: 0.000184 loss: 3.0323 (2.9238) grad_norm: 2.2785 (2.3439) time: 0.6333 [2021-03-28 00:08:26 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 440/1251] eta: 0:08:38 lr: 0.000184 loss: 2.9945 (2.9230) grad_norm: 2.1959 (2.3413) time: 0.6280 [2021-03-28 00:08:32 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 450/1251] eta: 0:08:31 lr: 0.000184 loss: 2.8903 (2.9219) grad_norm: 2.1198 (2.3365) time: 0.6320 [2021-03-28 00:08:38 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 460/1251] eta: 0:08:25 lr: 0.000184 loss: 2.9249 (2.9217) grad_norm: 2.1663 (2.3367) time: 0.6395 [2021-03-28 00:08:45 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 470/1251] eta: 0:08:18 lr: 0.000184 loss: 2.9878 (2.9255) grad_norm: 2.1864 (2.3365) time: 0.6342 [2021-03-28 00:08:51 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 480/1251] eta: 0:08:12 lr: 0.000184 loss: 3.1329 (2.9273) grad_norm: 2.0999 (2.3331) time: 0.6324 [2021-03-28 00:08:57 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 490/1251] eta: 0:08:06 lr: 0.000184 loss: 2.9415 (2.9274) grad_norm: 2.0350 (2.3300) time: 0.6344 [2021-03-28 00:09:04 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 500/1251] eta: 0:07:59 lr: 0.000184 loss: 2.9667 (2.9310) grad_norm: 2.1289 (2.3276) time: 0.6312 [2021-03-28 00:09:10 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 510/1251] eta: 0:07:52 lr: 0.000184 loss: 3.0668 (2.9298) grad_norm: 2.1897 (2.3254) time: 0.6270 [2021-03-28 00:09:16 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 520/1251] eta: 0:07:46 lr: 0.000184 loss: 2.8326 (2.9284) grad_norm: 2.1497 (2.3282) time: 0.6289 [2021-03-28 00:09:23 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 530/1251] eta: 0:07:39 lr: 0.000184 loss: 2.9280 (2.9309) grad_norm: 2.1635 (2.3272) time: 0.6300 [2021-03-28 00:09:29 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 540/1251] eta: 0:07:33 lr: 0.000184 loss: 2.9826 (2.9297) grad_norm: 2.1635 (2.3230) time: 0.6280 [2021-03-28 00:09:35 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 550/1251] eta: 0:07:27 lr: 0.000184 loss: 3.0830 (2.9344) grad_norm: 2.1854 (2.3210) time: 0.6362 [2021-03-28 00:09:42 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 560/1251] eta: 0:07:20 lr: 0.000184 loss: 3.0949 (2.9348) grad_norm: 2.1122 (2.3176) time: 0.6415 [2021-03-28 00:09:48 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 570/1251] eta: 0:07:14 lr: 0.000184 loss: 3.0187 (2.9345) grad_norm: 2.0341 (2.3186) time: 0.6335 [2021-03-28 00:09:54 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 580/1251] eta: 0:07:08 lr: 0.000184 loss: 3.1867 (2.9388) grad_norm: 2.1233 (2.3185) time: 0.6371 [2021-03-28 00:10:01 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 590/1251] eta: 0:07:01 lr: 0.000184 loss: 3.2508 (2.9417) grad_norm: 2.1042 (2.3143) time: 0.6370 [2021-03-28 00:10:07 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 600/1251] eta: 0:06:55 lr: 0.000184 loss: 3.0917 (2.9414) grad_norm: 2.2142 (2.3149) time: 0.6299 [2021-03-28 00:10:13 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 610/1251] eta: 0:06:48 lr: 0.000184 loss: 3.0109 (2.9423) grad_norm: 2.2772 (2.3138) time: 0.6308 [2021-03-28 00:10:20 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 620/1251] eta: 0:06:42 lr: 0.000184 loss: 2.9027 (2.9419) grad_norm: 2.1340 (2.3118) time: 0.6284 [2021-03-28 00:10:26 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 630/1251] eta: 0:06:35 lr: 0.000184 loss: 2.8628 (2.9396) grad_norm: 2.2103 (2.3112) time: 0.6269 [2021-03-28 00:10:32 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 640/1251] eta: 0:06:29 lr: 0.000183 loss: 2.9434 (2.9420) grad_norm: 2.2362 (2.3115) time: 0.6284 [2021-03-28 00:10:38 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 650/1251] eta: 0:06:22 lr: 0.000183 loss: 3.1897 (2.9463) grad_norm: 2.2960 (2.3119) time: 0.6307 [2021-03-28 00:10:45 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 660/1251] eta: 0:06:16 lr: 0.000183 loss: 3.1897 (2.9472) grad_norm: 2.4945 (2.3152) time: 0.6248 [2021-03-28 00:10:51 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 670/1251] eta: 0:06:09 lr: 0.000183 loss: 3.1472 (2.9481) grad_norm: 2.0856 (2.3152) time: 0.6232 [2021-03-28 00:10:57 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 680/1251] eta: 0:06:03 lr: 0.000183 loss: 2.9576 (2.9495) grad_norm: 2.0752 (2.3136) time: 0.6251 [2021-03-28 00:11:04 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 690/1251] eta: 0:05:56 lr: 0.000183 loss: 2.8696 (2.9451) grad_norm: 2.1224 (2.3148) time: 0.6284 [2021-03-28 00:11:10 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 700/1251] eta: 0:05:50 lr: 0.000183 loss: 2.8707 (2.9466) grad_norm: 2.1712 (2.3167) time: 0.6307 [2021-03-28 00:11:16 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 710/1251] eta: 0:05:44 lr: 0.000183 loss: 2.9703 (2.9475) grad_norm: 2.3931 (2.3168) time: 0.6258 [2021-03-28 00:11:22 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 720/1251] eta: 0:05:37 lr: 0.000183 loss: 2.9918 (2.9478) grad_norm: 2.1801 (2.3158) time: 0.6255 [2021-03-28 00:11:29 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 730/1251] eta: 0:05:31 lr: 0.000183 loss: 3.0065 (2.9460) grad_norm: 2.1704 (2.3153) time: 0.6309 [2021-03-28 00:11:35 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 740/1251] eta: 0:05:25 lr: 0.000183 loss: 2.8479 (2.9434) grad_norm: 2.2172 (2.3160) time: 0.6425 [2021-03-28 00:11:42 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 750/1251] eta: 0:05:18 lr: 0.000183 loss: 2.8352 (2.9413) grad_norm: 2.2172 (2.3183) time: 0.6455 [2021-03-28 00:11:48 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 760/1251] eta: 0:05:12 lr: 0.000183 loss: 3.0534 (2.9447) grad_norm: 2.2523 (2.3176) time: 0.6349 [2021-03-28 00:11:54 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 770/1251] eta: 0:05:05 lr: 0.000183 loss: 3.2656 (2.9469) grad_norm: 2.2301 (2.3180) time: 0.6327 [2021-03-28 00:12:01 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 780/1251] eta: 0:04:59 lr: 0.000183 loss: 3.2138 (2.9470) grad_norm: 2.0873 (2.3149) time: 0.6327 [2021-03-28 00:12:07 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 790/1251] eta: 0:04:53 lr: 0.000183 loss: 3.0199 (2.9452) grad_norm: 1.9987 (2.3167) time: 0.6276 [2021-03-28 00:12:13 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 800/1251] eta: 0:04:46 lr: 0.000183 loss: 2.9735 (2.9463) grad_norm: 1.9987 (2.3146) time: 0.6359 [2021-03-28 00:12:20 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 810/1251] eta: 0:04:40 lr: 0.000183 loss: 3.0406 (2.9479) grad_norm: 2.0595 (2.3136) time: 0.6392 [2021-03-28 00:12:26 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 820/1251] eta: 0:04:34 lr: 0.000183 loss: 2.8991 (2.9449) grad_norm: 2.1693 (2.3131) time: 0.6375 [2021-03-28 00:12:32 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 830/1251] eta: 0:04:27 lr: 0.000183 loss: 2.8600 (2.9439) grad_norm: 2.1749 (2.3155) time: 0.6328 [2021-03-28 00:12:39 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 840/1251] eta: 0:04:21 lr: 0.000183 loss: 2.8684 (2.9414) grad_norm: 2.1387 (2.3164) time: 0.6258 [2021-03-28 00:12:45 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 850/1251] eta: 0:04:14 lr: 0.000183 loss: 3.0202 (2.9434) grad_norm: 2.2522 (2.3176) time: 0.6299 [2021-03-28 00:12:51 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 860/1251] eta: 0:04:08 lr: 0.000183 loss: 3.0025 (2.9438) grad_norm: 2.3536 (2.3400) time: 0.6329 [2021-03-28 00:12:57 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 870/1251] eta: 0:04:02 lr: 0.000183 loss: 2.9419 (2.9430) grad_norm: 2.2972 (2.3384) time: 0.6294 [2021-03-28 00:13:04 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 880/1251] eta: 0:03:55 lr: 0.000183 loss: 2.9497 (2.9421) grad_norm: 2.2213 (2.3382) time: 0.6243 [2021-03-28 00:13:10 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 890/1251] eta: 0:03:49 lr: 0.000183 loss: 3.0014 (2.9442) grad_norm: 2.2518 (2.3375) time: 0.6286 [2021-03-28 00:13:16 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 900/1251] eta: 0:03:43 lr: 0.000183 loss: 3.0182 (2.9439) grad_norm: 2.2589 (2.3400) time: 0.6370 [2021-03-28 00:13:23 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 910/1251] eta: 0:03:36 lr: 0.000183 loss: 3.0037 (2.9435) grad_norm: 2.3416 (2.3406) time: 0.6319 [2021-03-28 00:13:29 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 920/1251] eta: 0:03:30 lr: 0.000183 loss: 2.8285 (2.9415) grad_norm: 2.2968 (2.3409) time: 0.6247 [2021-03-28 00:13:35 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 930/1251] eta: 0:03:23 lr: 0.000183 loss: 2.8285 (2.9411) grad_norm: 2.3711 (2.3406) time: 0.6274 [2021-03-28 00:13:42 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 940/1251] eta: 0:03:17 lr: 0.000183 loss: 3.0825 (2.9426) grad_norm: 2.1547 (2.3399) time: 0.6309 [2021-03-28 00:13:48 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 950/1251] eta: 0:03:11 lr: 0.000183 loss: 3.1676 (2.9451) grad_norm: 2.1066 (2.3378) time: 0.6266 [2021-03-28 00:13:54 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 960/1251] eta: 0:03:04 lr: 0.000182 loss: 3.1963 (2.9462) grad_norm: 2.0928 (2.3374) time: 0.6237 [2021-03-28 00:14:00 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 970/1251] eta: 0:02:58 lr: 0.000182 loss: 3.0212 (2.9471) grad_norm: 2.1783 (2.3381) time: 0.6335 [2021-03-28 00:14:07 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 980/1251] eta: 0:02:52 lr: 0.000182 loss: 2.8348 (2.9453) grad_norm: 2.2700 (2.3389) time: 0.6351 [2021-03-28 00:14:13 swin_base_patch4_window7_224] INFO: Epoch: [217] [ 990/1251] eta: 0:02:45 lr: 0.000182 loss: 2.7258 (2.9426) grad_norm: 2.2684 (2.3383) time: 0.6283 [2021-03-28 00:14:19 swin_base_patch4_window7_224] INFO: Epoch: [217] [1000/1251] eta: 0:02:39 lr: 0.000182 loss: 2.9419 (2.9434) grad_norm: 2.2587 (2.3389) time: 0.6278 [2021-03-28 00:14:26 swin_base_patch4_window7_224] INFO: Epoch: [217] [1010/1251] eta: 0:02:32 lr: 0.000182 loss: 3.0992 (2.9437) grad_norm: 2.1171 (2.3364) time: 0.6334 [2021-03-28 00:14:32 swin_base_patch4_window7_224] INFO: Epoch: [217] [1020/1251] eta: 0:02:26 lr: 0.000182 loss: 2.9780 (2.9442) grad_norm: 2.1352 (2.3374) time: 0.6300 [2021-03-28 00:14:38 swin_base_patch4_window7_224] INFO: Epoch: [217] [1030/1251] eta: 0:02:20 lr: 0.000182 loss: 2.9508 (2.9432) grad_norm: 2.2630 (2.3373) time: 0.6241 [2021-03-28 00:14:44 swin_base_patch4_window7_224] INFO: Epoch: [217] [1040/1251] eta: 0:02:13 lr: 0.000182 loss: 2.8210 (2.9405) grad_norm: 2.2101 (2.3376) time: 0.6241 [2021-03-28 00:14:51 swin_base_patch4_window7_224] INFO: Epoch: [217] [1050/1251] eta: 0:02:07 lr: 0.000182 loss: 2.7448 (2.9385) grad_norm: 2.2643 (2.3421) time: 0.6258 [2021-03-28 00:14:57 swin_base_patch4_window7_224] INFO: Epoch: [217] [1060/1251] eta: 0:02:01 lr: 0.000182 loss: 2.8595 (2.9366) grad_norm: 2.2287 (2.3407) time: 0.6291 [2021-03-28 00:15:03 swin_base_patch4_window7_224] INFO: Epoch: [217] [1070/1251] eta: 0:01:54 lr: 0.000182 loss: 2.5468 (2.9333) grad_norm: 2.1588 (2.3412) time: 0.6246 [2021-03-28 00:15:09 swin_base_patch4_window7_224] INFO: Epoch: [217] [1080/1251] eta: 0:01:48 lr: 0.000182 loss: 2.5609 (2.9324) grad_norm: 2.1831 (2.3400) time: 0.6239 [2021-03-28 00:15:16 swin_base_patch4_window7_224] INFO: Epoch: [217] [1090/1251] eta: 0:01:42 lr: 0.000182 loss: 2.9646 (2.9323) grad_norm: 2.2240 (2.3394) time: 0.6316 [2021-03-28 00:15:22 swin_base_patch4_window7_224] INFO: Epoch: [217] [1100/1251] eta: 0:01:35 lr: 0.000182 loss: 3.0016 (2.9306) grad_norm: 2.1774 (2.3387) time: 0.6317 [2021-03-28 00:15:28 swin_base_patch4_window7_224] INFO: Epoch: [217] [1110/1251] eta: 0:01:29 lr: 0.000182 loss: 2.7039 (2.9281) grad_norm: 2.1513 (2.3387) time: 0.6255 [2021-03-28 00:15:35 swin_base_patch4_window7_224] INFO: Epoch: [217] [1120/1251] eta: 0:01:23 lr: 0.000182 loss: 2.9333 (2.9277) grad_norm: 2.1827 (2.3388) time: 0.6251 [2021-03-28 00:15:41 swin_base_patch4_window7_224] INFO: Epoch: [217] [1130/1251] eta: 0:01:16 lr: 0.000182 loss: 3.1136 (2.9297) grad_norm: 2.2066 (2.3387) time: 0.6307 [2021-03-28 00:15:47 swin_base_patch4_window7_224] INFO: Epoch: [217] [1140/1251] eta: 0:01:10 lr: 0.000182 loss: 3.0391 (2.9287) grad_norm: 2.2475 (2.3389) time: 0.6349 [2021-03-28 00:15:54 swin_base_patch4_window7_224] INFO: Epoch: [217] [1150/1251] eta: 0:01:04 lr: 0.000182 loss: 3.0391 (2.9301) grad_norm: 2.2765 (2.3396) time: 0.6356 [2021-03-28 00:16:00 swin_base_patch4_window7_224] INFO: Epoch: [217] [1160/1251] eta: 0:00:57 lr: 0.000182 loss: 3.0583 (2.9296) grad_norm: 2.1386 (2.3383) time: 0.6279 [2021-03-28 00:16:06 swin_base_patch4_window7_224] INFO: Epoch: [217] [1170/1251] eta: 0:00:51 lr: 0.000182 loss: 2.8694 (2.9302) grad_norm: 2.0373 (2.3397) time: 0.6261 [2021-03-28 00:16:12 swin_base_patch4_window7_224] INFO: Epoch: [217] [1180/1251] eta: 0:00:44 lr: 0.000182 loss: 2.9884 (2.9297) grad_norm: 2.0990 (2.3391) time: 0.6264 [2021-03-28 00:16:19 swin_base_patch4_window7_224] INFO: Epoch: [217] [1190/1251] eta: 0:00:38 lr: 0.000182 loss: 2.9572 (2.9297) grad_norm: 2.1186 (2.3381) time: 0.6241 [2021-03-28 00:16:25 swin_base_patch4_window7_224] INFO: Epoch: [217] [1200/1251] eta: 0:00:32 lr: 0.000182 loss: 2.9425 (2.9295) grad_norm: 2.1438 (2.3405) time: 0.6243 [2021-03-28 00:16:31 swin_base_patch4_window7_224] INFO: Epoch: [217] [1210/1251] eta: 0:00:25 lr: 0.000182 loss: 2.9425 (2.9294) grad_norm: 2.1833 (2.3399) time: 0.6226 [2021-03-28 00:16:37 swin_base_patch4_window7_224] INFO: Epoch: [217] [1220/1251] eta: 0:00:19 lr: 0.000182 loss: 2.9770 (2.9298) grad_norm: 2.1912 (2.3394) time: 0.6240 [2021-03-28 00:16:44 swin_base_patch4_window7_224] INFO: Epoch: [217] [1230/1251] eta: 0:00:13 lr: 0.000182 loss: 3.1350 (2.9317) grad_norm: 2.0887 (2.3383) time: 0.6234 [2021-03-28 00:16:50 swin_base_patch4_window7_224] INFO: Epoch: [217] [1240/1251] eta: 0:00:06 lr: 0.000182 loss: 3.1784 (2.9312) grad_norm: 2.0899 (2.3367) time: 0.6224 [2021-03-28 00:16:56 swin_base_patch4_window7_224] INFO: Epoch: [217] [1250/1251] eta: 0:00:00 lr: 0.000182 loss: 3.1036 (2.9324) grad_norm: 2.1124 (2.3363) time: 0.6285 [2021-03-28 00:17:07 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:31 loss: 0.6828 (0.6828) acc1: 84.3750 (84.3750) acc5: 96.8750 (96.8750) [2021-03-28 00:17:10 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7814 (0.7918) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.3068) [2021-03-28 00:17:12 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7843 (0.7623) acc1: 81.2500 (82.5893) acc5: 96.8750 (96.4286) [2021-03-28 00:17:13 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8140 (0.8016) acc1: 81.2500 (81.0484) acc5: 96.8750 (96.5726) [2021-03-28 00:17:15 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7593 (0.7744) acc1: 81.2500 (81.6311) acc5: 96.8750 (96.7607) [2021-03-28 00:17:16 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7593 (0.7903) acc1: 81.2500 (81.2800) acc5: 96.8750 (96.6720) [2021-03-28 00:17:32 swin_base_patch4_window7_224] INFO: * Acc@1 81.850 Acc@5 96.074 loss 0.784 [2021-03-28 00:17:32 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.9% [2021-03-28 00:17:32 swin_base_patch4_window7_224] INFO: Max accuracy: 81.90% [2021-03-28 00:17:36 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 0/1251] eta: 1:23:02 lr: 0.000182 loss: 3.1108 (3.1108) grad_norm: 2.1459 (2.1459) time: 3.9826 [2021-03-28 00:17:42 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 10/1251] eta: 0:19:45 lr: 0.000182 loss: 3.1108 (3.0651) grad_norm: 2.0591 (2.0793) time: 0.9552 [2021-03-28 00:17:48 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 20/1251] eta: 0:16:19 lr: 0.000181 loss: 3.2442 (3.1526) grad_norm: 2.1530 (2.3188) time: 0.6360 [2021-03-28 00:17:55 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 30/1251] eta: 0:15:09 lr: 0.000181 loss: 3.0852 (3.0452) grad_norm: 2.1954 (2.2777) time: 0.6297 [2021-03-28 00:18:01 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 40/1251] eta: 0:14:27 lr: 0.000181 loss: 3.1010 (3.0917) grad_norm: 2.1954 (2.2702) time: 0.6333 [2021-03-28 00:18:07 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 50/1251] eta: 0:13:58 lr: 0.000181 loss: 3.1010 (3.0598) grad_norm: 2.2084 (2.3055) time: 0.6246 [2021-03-28 00:18:13 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 60/1251] eta: 0:13:36 lr: 0.000181 loss: 2.7874 (3.0245) grad_norm: 2.1376 (2.3068) time: 0.6227 [2021-03-28 00:18:20 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 70/1251] eta: 0:13:19 lr: 0.000181 loss: 3.0038 (3.0244) grad_norm: 2.1294 (2.2836) time: 0.6241 [2021-03-28 00:18:26 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 80/1251] eta: 0:13:08 lr: 0.000181 loss: 3.0745 (3.0182) grad_norm: 2.1327 (2.2760) time: 0.6363 [2021-03-28 00:18:32 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 90/1251] eta: 0:12:57 lr: 0.000181 loss: 2.9971 (3.0013) grad_norm: 2.1627 (2.2947) time: 0.6424 [2021-03-28 00:18:39 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 100/1251] eta: 0:12:45 lr: 0.000181 loss: 2.9663 (2.9917) grad_norm: 2.3306 (2.3604) time: 0.6333 [2021-03-28 00:18:45 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 110/1251] eta: 0:12:36 lr: 0.000181 loss: 3.1872 (2.9978) grad_norm: 2.3025 (2.3586) time: 0.6327 [2021-03-28 00:18:51 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 120/1251] eta: 0:12:27 lr: 0.000181 loss: 3.0202 (2.9898) grad_norm: 2.2050 (2.3709) time: 0.6364 [2021-03-28 00:18:58 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 130/1251] eta: 0:12:18 lr: 0.000181 loss: 2.9805 (2.9877) grad_norm: 2.3479 (2.3721) time: 0.6382 [2021-03-28 00:19:04 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 140/1251] eta: 0:12:09 lr: 0.000181 loss: 3.0974 (2.9877) grad_norm: 2.2912 (2.3593) time: 0.6314 [2021-03-28 00:19:10 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 150/1251] eta: 0:12:00 lr: 0.000181 loss: 2.9801 (2.9777) grad_norm: 2.1675 (2.3481) time: 0.6248 [2021-03-28 00:19:17 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 160/1251] eta: 0:11:53 lr: 0.000181 loss: 2.9801 (2.9837) grad_norm: 2.2281 (2.3380) time: 0.6354 [2021-03-28 00:19:23 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 170/1251] eta: 0:11:44 lr: 0.000181 loss: 3.0874 (2.9750) grad_norm: 2.2107 (2.3415) time: 0.6321 [2021-03-28 00:19:29 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 180/1251] eta: 0:11:36 lr: 0.000181 loss: 3.0217 (2.9733) grad_norm: 2.0678 (2.3312) time: 0.6240 [2021-03-28 00:19:36 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 190/1251] eta: 0:11:29 lr: 0.000181 loss: 3.1430 (2.9758) grad_norm: 2.0678 (2.3268) time: 0.6331 [2021-03-28 00:19:42 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 200/1251] eta: 0:11:22 lr: 0.000181 loss: 3.2082 (2.9836) grad_norm: 2.3109 (2.3321) time: 0.6396 [2021-03-28 00:19:48 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 210/1251] eta: 0:11:14 lr: 0.000181 loss: 3.2082 (2.9963) grad_norm: 2.3034 (2.3296) time: 0.6305 [2021-03-28 00:19:55 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 220/1251] eta: 0:11:07 lr: 0.000181 loss: 3.1228 (2.9940) grad_norm: 2.1968 (2.3237) time: 0.6244 [2021-03-28 00:20:01 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 230/1251] eta: 0:10:59 lr: 0.000181 loss: 2.8874 (2.9835) grad_norm: 2.1842 (2.3270) time: 0.6285 [2021-03-28 00:20:07 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 240/1251] eta: 0:10:52 lr: 0.000181 loss: 2.9299 (2.9839) grad_norm: 2.1842 (2.3300) time: 0.6246 [2021-03-28 00:20:13 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 250/1251] eta: 0:10:45 lr: 0.000181 loss: 3.0378 (2.9886) grad_norm: 2.3368 (2.3308) time: 0.6286 [2021-03-28 00:20:20 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 260/1251] eta: 0:10:38 lr: 0.000181 loss: 3.0152 (2.9860) grad_norm: 2.2480 (2.3274) time: 0.6339 [2021-03-28 00:20:26 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 270/1251] eta: 0:10:31 lr: 0.000181 loss: 2.8190 (2.9806) grad_norm: 2.1139 (2.3175) time: 0.6313 [2021-03-28 00:20:32 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 280/1251] eta: 0:10:24 lr: 0.000181 loss: 2.8490 (2.9737) grad_norm: 2.0482 (2.3125) time: 0.6295 [2021-03-28 00:20:39 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 290/1251] eta: 0:10:17 lr: 0.000181 loss: 2.6491 (2.9568) grad_norm: 2.1548 (2.3057) time: 0.6272 [2021-03-28 00:20:45 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 300/1251] eta: 0:10:10 lr: 0.000181 loss: 2.8729 (2.9623) grad_norm: 2.2364 (2.3069) time: 0.6229 [2021-03-28 00:20:51 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 310/1251] eta: 0:10:04 lr: 0.000181 loss: 3.0348 (2.9562) grad_norm: 2.3161 (2.3061) time: 0.6286 [2021-03-28 00:20:58 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 320/1251] eta: 0:09:57 lr: 0.000181 loss: 2.9018 (2.9518) grad_norm: 2.1954 (2.3029) time: 0.6331 [2021-03-28 00:21:04 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 330/1251] eta: 0:09:50 lr: 0.000181 loss: 3.0226 (2.9550) grad_norm: 2.1249 (2.3002) time: 0.6326 [2021-03-28 00:21:10 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 340/1251] eta: 0:09:44 lr: 0.000180 loss: 3.0226 (2.9573) grad_norm: 2.1838 (2.2974) time: 0.6370 [2021-03-28 00:21:17 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 350/1251] eta: 0:09:37 lr: 0.000180 loss: 3.0786 (2.9606) grad_norm: 2.2593 (2.3149) time: 0.6318 [2021-03-28 00:21:23 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 360/1251] eta: 0:09:30 lr: 0.000180 loss: 3.1629 (2.9630) grad_norm: 2.3032 (2.3137) time: 0.6226 [2021-03-28 00:21:29 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 370/1251] eta: 0:09:23 lr: 0.000180 loss: 3.0777 (2.9615) grad_norm: 2.2544 (2.3149) time: 0.6193 [2021-03-28 00:21:35 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 380/1251] eta: 0:09:16 lr: 0.000180 loss: 2.7936 (2.9565) grad_norm: 2.2434 (2.3132) time: 0.6263 [2021-03-28 00:21:42 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 390/1251] eta: 0:09:10 lr: 0.000180 loss: 2.9034 (2.9562) grad_norm: 2.2434 (2.3117) time: 0.6351 [2021-03-28 00:21:48 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 400/1251] eta: 0:09:04 lr: 0.000180 loss: 2.9120 (2.9572) grad_norm: 2.2565 (2.3076) time: 0.6373 [2021-03-28 00:21:54 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 410/1251] eta: 0:08:57 lr: 0.000180 loss: 2.9993 (2.9529) grad_norm: 2.2163 (2.3070) time: 0.6359 [2021-03-28 00:22:01 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 420/1251] eta: 0:08:50 lr: 0.000180 loss: 3.1198 (2.9553) grad_norm: 2.2773 (2.3073) time: 0.6287 [2021-03-28 00:22:07 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 430/1251] eta: 0:08:44 lr: 0.000180 loss: 3.0946 (2.9557) grad_norm: 2.1569 (2.3057) time: 0.6278 [2021-03-28 00:22:13 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 440/1251] eta: 0:08:37 lr: 0.000180 loss: 3.0259 (2.9561) grad_norm: 2.1524 (2.3035) time: 0.6306 [2021-03-28 00:22:19 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 450/1251] eta: 0:08:31 lr: 0.000180 loss: 3.0055 (2.9559) grad_norm: 2.1571 (2.3004) time: 0.6286 [2021-03-28 00:22:26 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 460/1251] eta: 0:08:24 lr: 0.000180 loss: 3.0157 (2.9607) grad_norm: 2.1969 (2.2990) time: 0.6313 [2021-03-28 00:22:32 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 470/1251] eta: 0:08:18 lr: 0.000180 loss: 3.0715 (2.9600) grad_norm: 2.1163 (2.2955) time: 0.6315 [2021-03-28 00:22:38 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 480/1251] eta: 0:08:11 lr: 0.000180 loss: 3.0063 (2.9609) grad_norm: 2.0918 (2.2929) time: 0.6287 [2021-03-28 00:22:45 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 490/1251] eta: 0:08:05 lr: 0.000180 loss: 2.9074 (2.9595) grad_norm: 2.0736 (2.2907) time: 0.6268 [2021-03-28 00:22:51 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 500/1251] eta: 0:07:58 lr: 0.000180 loss: 3.0036 (2.9590) grad_norm: 2.2562 (2.2958) time: 0.6227 [2021-03-28 00:22:57 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 510/1251] eta: 0:07:51 lr: 0.000180 loss: 3.0036 (2.9578) grad_norm: 2.1732 (2.2941) time: 0.6227 [2021-03-28 00:23:03 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 520/1251] eta: 0:07:45 lr: 0.000180 loss: 2.8121 (2.9556) grad_norm: 2.1504 (2.2943) time: 0.6314 [2021-03-28 00:23:10 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 530/1251] eta: 0:07:39 lr: 0.000180 loss: 2.8803 (2.9561) grad_norm: 2.2357 (2.2973) time: 0.6320 [2021-03-28 00:23:16 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 540/1251] eta: 0:07:32 lr: 0.000180 loss: 3.1402 (2.9601) grad_norm: 2.2419 (2.2990) time: 0.6264 [2021-03-28 00:23:22 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 550/1251] eta: 0:07:26 lr: 0.000180 loss: 3.0675 (2.9594) grad_norm: 2.2449 (2.2996) time: 0.6325 [2021-03-28 00:23:29 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 560/1251] eta: 0:07:19 lr: 0.000180 loss: 2.9567 (2.9603) grad_norm: 2.1699 (2.2996) time: 0.6311 [2021-03-28 00:23:35 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 570/1251] eta: 0:07:13 lr: 0.000180 loss: 2.8455 (2.9538) grad_norm: 2.1690 (2.2981) time: 0.6329 [2021-03-28 00:23:41 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 580/1251] eta: 0:07:06 lr: 0.000180 loss: 3.1385 (2.9585) grad_norm: 2.0247 (2.2952) time: 0.6342 [2021-03-28 00:23:48 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 590/1251] eta: 0:07:00 lr: 0.000180 loss: 3.2162 (2.9614) grad_norm: 2.1073 (2.2945) time: 0.6231 [2021-03-28 00:23:54 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 600/1251] eta: 0:06:53 lr: 0.000180 loss: 3.1543 (2.9619) grad_norm: 2.2316 (2.2932) time: 0.6219 [2021-03-28 00:24:00 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 610/1251] eta: 0:06:47 lr: 0.000180 loss: 3.0157 (2.9605) grad_norm: 2.2316 (2.2923) time: 0.6300 [2021-03-28 00:24:06 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 620/1251] eta: 0:06:41 lr: 0.000180 loss: 2.9311 (2.9594) grad_norm: 2.2168 (2.2934) time: 0.6321 [2021-03-28 00:24:13 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 630/1251] eta: 0:06:34 lr: 0.000180 loss: 2.9344 (2.9616) grad_norm: 2.1502 (2.2961) time: 0.6291 [2021-03-28 00:24:19 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 640/1251] eta: 0:06:28 lr: 0.000180 loss: 2.8814 (2.9577) grad_norm: 2.1489 (2.2959) time: 0.6294 [2021-03-28 00:24:25 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 650/1251] eta: 0:06:21 lr: 0.000180 loss: 2.8162 (2.9599) grad_norm: 2.2262 (2.2972) time: 0.6299 [2021-03-28 00:24:32 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 660/1251] eta: 0:06:15 lr: 0.000179 loss: 3.1054 (2.9605) grad_norm: 2.4113 (2.2989) time: 0.6314 [2021-03-28 00:24:38 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 670/1251] eta: 0:06:09 lr: 0.000179 loss: 3.0564 (2.9595) grad_norm: 2.3254 (2.2976) time: 0.6314 [2021-03-28 00:24:44 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 680/1251] eta: 0:06:02 lr: 0.000179 loss: 2.8794 (2.9604) grad_norm: 2.2456 (2.2955) time: 0.6268 [2021-03-28 00:24:50 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 690/1251] eta: 0:05:56 lr: 0.000179 loss: 2.8794 (2.9587) grad_norm: 2.0814 (2.2914) time: 0.6203 [2021-03-28 00:24:57 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 700/1251] eta: 0:05:49 lr: 0.000179 loss: 3.1148 (2.9637) grad_norm: 2.1147 (2.2919) time: 0.6208 [2021-03-28 00:25:03 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 710/1251] eta: 0:05:43 lr: 0.000179 loss: 3.1316 (2.9612) grad_norm: 2.2673 (2.2922) time: 0.6241 [2021-03-28 00:25:09 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 720/1251] eta: 0:05:36 lr: 0.000179 loss: 2.9221 (2.9593) grad_norm: 2.4889 (2.2988) time: 0.6239 [2021-03-28 00:25:15 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 730/1251] eta: 0:05:30 lr: 0.000179 loss: 2.9694 (2.9581) grad_norm: 2.5075 (2.2999) time: 0.6306 [2021-03-28 00:25:22 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 740/1251] eta: 0:05:24 lr: 0.000179 loss: 3.0874 (2.9606) grad_norm: 2.3248 (2.3017) time: 0.6371 [2021-03-28 00:25:28 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 750/1251] eta: 0:05:17 lr: 0.000179 loss: 3.1022 (2.9612) grad_norm: 2.2881 (2.3015) time: 0.6369 [2021-03-28 00:25:35 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 760/1251] eta: 0:05:11 lr: 0.000179 loss: 3.0630 (2.9624) grad_norm: 2.2881 (2.3027) time: 0.6385 [2021-03-28 00:25:41 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 770/1251] eta: 0:05:05 lr: 0.000179 loss: 3.0358 (2.9601) grad_norm: 2.2863 (2.3010) time: 0.6339 [2021-03-28 00:25:47 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 780/1251] eta: 0:04:58 lr: 0.000179 loss: 2.9166 (2.9592) grad_norm: 2.1530 (2.3004) time: 0.6293 [2021-03-28 00:25:53 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 790/1251] eta: 0:04:52 lr: 0.000179 loss: 2.9166 (2.9571) grad_norm: 2.1608 (2.3000) time: 0.6288 [2021-03-28 00:26:00 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 800/1251] eta: 0:04:46 lr: 0.000179 loss: 2.8784 (2.9588) grad_norm: 2.2418 (2.3005) time: 0.6258 [2021-03-28 00:26:06 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 810/1251] eta: 0:04:39 lr: 0.000179 loss: 2.9987 (2.9597) grad_norm: 2.2418 (2.2995) time: 0.6256 [2021-03-28 00:26:12 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 820/1251] eta: 0:04:33 lr: 0.000179 loss: 2.9987 (2.9594) grad_norm: 2.2128 (2.2987) time: 0.6282 [2021-03-28 00:26:19 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 830/1251] eta: 0:04:26 lr: 0.000179 loss: 2.9506 (2.9595) grad_norm: 2.2128 (2.2994) time: 0.6291 [2021-03-28 00:26:25 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 840/1251] eta: 0:04:20 lr: 0.000179 loss: 3.0225 (2.9609) grad_norm: 2.2242 (2.2988) time: 0.6339 [2021-03-28 00:26:31 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 850/1251] eta: 0:04:14 lr: 0.000179 loss: 3.1069 (2.9623) grad_norm: 2.2857 (2.3036) time: 0.6314 [2021-03-28 00:26:37 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 860/1251] eta: 0:04:07 lr: 0.000179 loss: 3.0290 (2.9595) grad_norm: 2.4759 (2.3077) time: 0.6272 [2021-03-28 00:26:44 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 870/1251] eta: 0:04:01 lr: 0.000179 loss: 2.7938 (2.9576) grad_norm: 2.2358 (2.3105) time: 0.6304 [2021-03-28 00:26:50 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 880/1251] eta: 0:03:55 lr: 0.000179 loss: 2.8108 (2.9572) grad_norm: 2.1720 (2.3116) time: 0.6270 [2021-03-28 00:26:56 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 890/1251] eta: 0:03:48 lr: 0.000179 loss: 2.9224 (2.9573) grad_norm: 2.2493 (2.3163) time: 0.6255 [2021-03-28 00:27:03 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 900/1251] eta: 0:03:42 lr: 0.000179 loss: 2.9346 (2.9572) grad_norm: 2.2493 (2.3168) time: 0.6247 [2021-03-28 00:27:09 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 910/1251] eta: 0:03:36 lr: 0.000179 loss: 3.1473 (2.9574) grad_norm: 2.1531 (2.3153) time: 0.6282 [2021-03-28 00:27:15 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 920/1251] eta: 0:03:29 lr: 0.000179 loss: 3.1638 (2.9586) grad_norm: 2.1392 (2.3147) time: 0.6288 [2021-03-28 00:27:21 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 930/1251] eta: 0:03:23 lr: 0.000179 loss: 3.1638 (2.9590) grad_norm: 2.1557 (2.3133) time: 0.6280 [2021-03-28 00:27:28 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 940/1251] eta: 0:03:16 lr: 0.000179 loss: 2.9733 (2.9587) grad_norm: 2.1715 (2.3138) time: 0.6314 [2021-03-28 00:27:34 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 950/1251] eta: 0:03:10 lr: 0.000179 loss: 2.9723 (2.9577) grad_norm: 2.2568 (2.3155) time: 0.6333 [2021-03-28 00:27:40 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 960/1251] eta: 0:03:04 lr: 0.000179 loss: 2.9435 (2.9567) grad_norm: 2.3060 (2.3162) time: 0.6351 [2021-03-28 00:27:47 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 970/1251] eta: 0:02:57 lr: 0.000179 loss: 2.9476 (2.9562) grad_norm: 2.3058 (2.3152) time: 0.6321 [2021-03-28 00:27:53 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 980/1251] eta: 0:02:51 lr: 0.000178 loss: 2.9890 (2.9579) grad_norm: 2.1765 (2.3146) time: 0.6267 [2021-03-28 00:27:59 swin_base_patch4_window7_224] INFO: Epoch: [218] [ 990/1251] eta: 0:02:45 lr: 0.000178 loss: 3.0121 (2.9578) grad_norm: 2.2950 (2.3176) time: 0.6231 [2021-03-28 00:28:05 swin_base_patch4_window7_224] INFO: Epoch: [218] [1000/1251] eta: 0:02:38 lr: 0.000178 loss: 2.9332 (2.9567) grad_norm: 2.2188 (2.3183) time: 0.6234 [2021-03-28 00:28:12 swin_base_patch4_window7_224] INFO: Epoch: [218] [1010/1251] eta: 0:02:32 lr: 0.000178 loss: 2.8566 (2.9552) grad_norm: 2.2162 (2.3180) time: 0.6229 [2021-03-28 00:28:18 swin_base_patch4_window7_224] INFO: Epoch: [218] [1020/1251] eta: 0:02:26 lr: 0.000178 loss: 2.7841 (2.9546) grad_norm: 2.2162 (2.3176) time: 0.6248 [2021-03-28 00:28:24 swin_base_patch4_window7_224] INFO: Epoch: [218] [1030/1251] eta: 0:02:19 lr: 0.000178 loss: 2.9932 (2.9559) grad_norm: 2.2399 (2.3183) time: 0.6302 [2021-03-28 00:28:30 swin_base_patch4_window7_224] INFO: Epoch: [218] [1040/1251] eta: 0:02:13 lr: 0.000178 loss: 2.7729 (2.9518) grad_norm: 2.3058 (2.3187) time: 0.6260 [2021-03-28 00:28:37 swin_base_patch4_window7_224] INFO: Epoch: [218] [1050/1251] eta: 0:02:07 lr: 0.000178 loss: 2.7289 (2.9514) grad_norm: 2.3058 (2.3189) time: 0.6244 [2021-03-28 00:28:43 swin_base_patch4_window7_224] INFO: Epoch: [218] [1060/1251] eta: 0:02:00 lr: 0.000178 loss: 2.8946 (2.9514) grad_norm: 2.2712 (2.3229) time: 0.6272 [2021-03-28 00:28:49 swin_base_patch4_window7_224] INFO: Epoch: [218] [1070/1251] eta: 0:01:54 lr: 0.000178 loss: 2.9631 (2.9527) grad_norm: 2.2712 (2.3223) time: 0.6277 [2021-03-28 00:28:56 swin_base_patch4_window7_224] INFO: Epoch: [218] [1080/1251] eta: 0:01:48 lr: 0.000178 loss: 3.0540 (2.9546) grad_norm: 2.3376 (2.3241) time: 0.6294 [2021-03-28 00:29:02 swin_base_patch4_window7_224] INFO: Epoch: [218] [1090/1251] eta: 0:01:41 lr: 0.000178 loss: 3.0347 (2.9550) grad_norm: 2.3376 (2.3243) time: 0.6271 [2021-03-28 00:29:08 swin_base_patch4_window7_224] INFO: Epoch: [218] [1100/1251] eta: 0:01:35 lr: 0.000178 loss: 2.8419 (2.9532) grad_norm: 2.2790 (2.3236) time: 0.6294 [2021-03-28 00:29:15 swin_base_patch4_window7_224] INFO: Epoch: [218] [1110/1251] eta: 0:01:29 lr: 0.000178 loss: 2.9715 (2.9549) grad_norm: 2.1936 (2.3228) time: 0.6321 [2021-03-28 00:29:21 swin_base_patch4_window7_224] INFO: Epoch: [218] [1120/1251] eta: 0:01:22 lr: 0.000178 loss: 3.0169 (2.9535) grad_norm: 2.3024 (2.3234) time: 0.6341 [2021-03-28 00:29:27 swin_base_patch4_window7_224] INFO: Epoch: [218] [1130/1251] eta: 0:01:16 lr: 0.000178 loss: 3.0338 (2.9537) grad_norm: 2.3589 (2.3233) time: 0.6304 [2021-03-28 00:29:33 swin_base_patch4_window7_224] INFO: Epoch: [218] [1140/1251] eta: 0:01:10 lr: 0.000178 loss: 3.0338 (2.9536) grad_norm: 2.3848 (2.3258) time: 0.6287 [2021-03-28 00:29:40 swin_base_patch4_window7_224] INFO: Epoch: [218] [1150/1251] eta: 0:01:03 lr: 0.000178 loss: 3.0323 (2.9542) grad_norm: 2.3032 (2.3249) time: 0.6322 [2021-03-28 00:29:46 swin_base_patch4_window7_224] INFO: Epoch: [218] [1160/1251] eta: 0:00:57 lr: 0.000178 loss: 3.0193 (2.9525) grad_norm: 2.1792 (2.3249) time: 0.6313 [2021-03-28 00:29:52 swin_base_patch4_window7_224] INFO: Epoch: [218] [1170/1251] eta: 0:00:51 lr: 0.000178 loss: 3.1692 (2.9554) grad_norm: 2.4176 (2.3264) time: 0.6302 [2021-03-28 00:29:59 swin_base_patch4_window7_224] INFO: Epoch: [218] [1180/1251] eta: 0:00:44 lr: 0.000178 loss: 3.1827 (2.9539) grad_norm: 2.3305 (2.3255) time: 0.6323 [2021-03-28 00:30:05 swin_base_patch4_window7_224] INFO: Epoch: [218] [1190/1251] eta: 0:00:38 lr: 0.000178 loss: 2.9872 (2.9542) grad_norm: 2.1245 (2.3239) time: 0.6314 [2021-03-28 00:30:11 swin_base_patch4_window7_224] INFO: Epoch: [218] [1200/1251] eta: 0:00:32 lr: 0.000178 loss: 3.0981 (2.9552) grad_norm: 2.0907 (inf) time: 0.6236 [2021-03-28 00:30:17 swin_base_patch4_window7_224] INFO: Epoch: [218] [1210/1251] eta: 0:00:25 lr: 0.000178 loss: 3.0171 (2.9542) grad_norm: 2.2421 (inf) time: 0.6225 [2021-03-28 00:30:24 swin_base_patch4_window7_224] INFO: Epoch: [218] [1220/1251] eta: 0:00:19 lr: 0.000178 loss: 2.7239 (2.9507) grad_norm: 2.2767 (inf) time: 0.6230 [2021-03-28 00:30:30 swin_base_patch4_window7_224] INFO: Epoch: [218] [1230/1251] eta: 0:00:13 lr: 0.000178 loss: 2.7279 (2.9508) grad_norm: 2.2508 (inf) time: 0.6232 [2021-03-28 00:30:36 swin_base_patch4_window7_224] INFO: Epoch: [218] [1240/1251] eta: 0:00:06 lr: 0.000178 loss: 3.1047 (2.9529) grad_norm: 2.2781 (inf) time: 0.6224 [2021-03-28 00:30:42 swin_base_patch4_window7_224] INFO: Epoch: [218] [1250/1251] eta: 0:00:00 lr: 0.000178 loss: 3.1408 (2.9544) grad_norm: 2.1549 (inf) time: 0.6144 [2021-03-28 00:30:53 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.8669 (0.8669) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-28 00:30:56 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.8272 (0.8171) acc1: 82.8125 (81.1080) acc5: 95.3125 (96.3068) [2021-03-28 00:30:58 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7509 (0.7788) acc1: 82.8125 (81.9940) acc5: 95.3125 (96.3542) [2021-03-28 00:31:00 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6953 (0.7715) acc1: 81.2500 (81.5524) acc5: 96.8750 (96.3710) [2021-03-28 00:31:03 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7917 (0.7897) acc1: 81.2500 (80.9451) acc5: 96.8750 (96.2271) [2021-03-28 00:31:04 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7917 (0.8040) acc1: 81.1321 (80.7360) acc5: 95.3125 (96.0640) [2021-03-28 00:31:18 swin_base_patch4_window7_224] INFO: * Acc@1 81.870 Acc@5 96.072 loss 0.788 [2021-03-28 00:31:18 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.9% [2021-03-28 00:31:18 swin_base_patch4_window7_224] INFO: Max accuracy: 81.90% [2021-03-28 00:31:23 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 0/1251] eta: 1:35:33 lr: 0.000178 loss: 2.9024 (2.9024) grad_norm: 2.3495 (2.3495) time: 4.5834 [2021-03-28 00:31:29 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 10/1251] eta: 0:20:29 lr: 0.000178 loss: 2.9878 (2.9354) grad_norm: 2.5451 (2.8315) time: 0.9906 [2021-03-28 00:31:35 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 20/1251] eta: 0:16:46 lr: 0.000178 loss: 2.9878 (2.8541) grad_norm: 2.4076 (2.5918) time: 0.6295 [2021-03-28 00:31:42 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 30/1251] eta: 0:15:24 lr: 0.000178 loss: 3.0219 (2.9294) grad_norm: 2.2933 (2.5529) time: 0.6282 [2021-03-28 00:31:48 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 40/1251] eta: 0:14:44 lr: 0.000178 loss: 3.0566 (2.9575) grad_norm: 2.3065 (2.5261) time: 0.6391 [2021-03-28 00:31:54 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 50/1251] eta: 0:14:13 lr: 0.000177 loss: 3.0303 (2.9902) grad_norm: 2.3499 (2.5025) time: 0.6401 [2021-03-28 00:32:01 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 60/1251] eta: 0:13:51 lr: 0.000177 loss: 3.0263 (2.9569) grad_norm: 2.4816 (2.4987) time: 0.6320 [2021-03-28 00:32:07 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 70/1251] eta: 0:13:32 lr: 0.000177 loss: 2.9457 (2.9495) grad_norm: 2.2914 (2.4632) time: 0.6305 [2021-03-28 00:32:13 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 80/1251] eta: 0:13:17 lr: 0.000177 loss: 2.9719 (2.9341) grad_norm: 2.2717 (2.4605) time: 0.6295 [2021-03-28 00:32:20 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 90/1251] eta: 0:13:04 lr: 0.000177 loss: 2.9914 (2.9462) grad_norm: 2.3341 (2.4664) time: 0.6324 [2021-03-28 00:32:26 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 100/1251] eta: 0:12:51 lr: 0.000177 loss: 2.9743 (2.9335) grad_norm: 2.2665 (2.4468) time: 0.6271 [2021-03-28 00:32:32 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 110/1251] eta: 0:12:40 lr: 0.000177 loss: 3.1571 (2.9611) grad_norm: 2.1878 (2.4333) time: 0.6217 [2021-03-28 00:32:38 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 120/1251] eta: 0:12:30 lr: 0.000177 loss: 3.1976 (2.9598) grad_norm: 2.2564 (2.4301) time: 0.6288 [2021-03-28 00:32:45 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 130/1251] eta: 0:12:20 lr: 0.000177 loss: 2.9925 (2.9596) grad_norm: 2.3596 (2.4278) time: 0.6282 [2021-03-28 00:32:51 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 140/1251] eta: 0:12:10 lr: 0.000177 loss: 2.9925 (2.9469) grad_norm: 2.1791 (2.4121) time: 0.6229 [2021-03-28 00:32:57 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 150/1251] eta: 0:12:01 lr: 0.000177 loss: 3.1575 (2.9608) grad_norm: 2.1710 (2.4017) time: 0.6243 [2021-03-28 00:33:03 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 160/1251] eta: 0:11:53 lr: 0.000177 loss: 3.1618 (2.9689) grad_norm: 2.2358 (2.4438) time: 0.6283 [2021-03-28 00:33:10 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 170/1251] eta: 0:11:45 lr: 0.000177 loss: 3.1070 (2.9711) grad_norm: 2.3227 (2.4364) time: 0.6275 [2021-03-28 00:33:16 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 180/1251] eta: 0:11:37 lr: 0.000177 loss: 3.0599 (2.9769) grad_norm: 2.2726 (2.4364) time: 0.6291 [2021-03-28 00:33:22 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 190/1251] eta: 0:11:29 lr: 0.000177 loss: 3.0455 (2.9668) grad_norm: 2.2899 (2.4335) time: 0.6300 [2021-03-28 00:33:29 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 200/1251] eta: 0:11:22 lr: 0.000177 loss: 2.7808 (2.9566) grad_norm: 2.3635 (2.4319) time: 0.6265 [2021-03-28 00:33:35 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 210/1251] eta: 0:11:14 lr: 0.000177 loss: 2.9305 (2.9633) grad_norm: 2.2467 (2.4239) time: 0.6261 [2021-03-28 00:33:41 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 220/1251] eta: 0:11:07 lr: 0.000177 loss: 3.0624 (2.9687) grad_norm: 2.1222 (2.4173) time: 0.6332 [2021-03-28 00:33:48 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 230/1251] eta: 0:11:00 lr: 0.000177 loss: 3.0624 (2.9661) grad_norm: 2.3176 (2.4232) time: 0.6404 [2021-03-28 00:33:54 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 240/1251] eta: 0:10:53 lr: 0.000177 loss: 3.1627 (2.9696) grad_norm: 2.1837 (2.4127) time: 0.6396 [2021-03-28 00:34:00 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 250/1251] eta: 0:10:47 lr: 0.000177 loss: 3.1627 (2.9703) grad_norm: 2.1579 (2.4041) time: 0.6392 [2021-03-28 00:34:07 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 260/1251] eta: 0:10:39 lr: 0.000177 loss: 3.0838 (2.9684) grad_norm: 2.1579 (2.3980) time: 0.6300 [2021-03-28 00:34:13 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 270/1251] eta: 0:10:32 lr: 0.000177 loss: 2.9179 (2.9672) grad_norm: 2.1387 (2.3970) time: 0.6279 [2021-03-28 00:34:19 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 280/1251] eta: 0:10:26 lr: 0.000177 loss: 2.9728 (2.9692) grad_norm: 2.1852 (2.3961) time: 0.6345 [2021-03-28 00:34:26 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 290/1251] eta: 0:10:19 lr: 0.000177 loss: 2.8685 (2.9653) grad_norm: 2.2209 (2.3928) time: 0.6310 [2021-03-28 00:34:32 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 300/1251] eta: 0:10:12 lr: 0.000177 loss: 2.8768 (2.9630) grad_norm: 2.2224 (2.3859) time: 0.6258 [2021-03-28 00:34:38 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 310/1251] eta: 0:10:04 lr: 0.000177 loss: 2.9708 (2.9612) grad_norm: 2.1729 (2.3863) time: 0.6245 [2021-03-28 00:34:44 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 320/1251] eta: 0:09:58 lr: 0.000177 loss: 2.9708 (2.9626) grad_norm: 2.2049 (2.3838) time: 0.6265 [2021-03-28 00:34:51 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 330/1251] eta: 0:09:51 lr: 0.000177 loss: 2.9037 (2.9598) grad_norm: 2.3202 (2.3864) time: 0.6363 [2021-03-28 00:34:57 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 340/1251] eta: 0:09:45 lr: 0.000177 loss: 2.7703 (2.9534) grad_norm: 2.2190 (2.3886) time: 0.6373 [2021-03-28 00:35:03 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 350/1251] eta: 0:09:38 lr: 0.000177 loss: 3.1142 (2.9575) grad_norm: 2.1845 (2.3883) time: 0.6279 [2021-03-28 00:35:10 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 360/1251] eta: 0:09:31 lr: 0.000177 loss: 3.0759 (2.9576) grad_norm: 2.2953 (2.3877) time: 0.6284 [2021-03-28 00:35:16 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 370/1251] eta: 0:09:24 lr: 0.000177 loss: 3.0133 (2.9589) grad_norm: 2.1258 (2.3792) time: 0.6323 [2021-03-28 00:35:22 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 380/1251] eta: 0:09:18 lr: 0.000176 loss: 2.9098 (2.9588) grad_norm: 2.0673 (2.3730) time: 0.6342 [2021-03-28 00:35:29 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 390/1251] eta: 0:09:11 lr: 0.000176 loss: 2.9993 (2.9583) grad_norm: 2.2020 (2.3709) time: 0.6319 [2021-03-28 00:35:35 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 400/1251] eta: 0:09:05 lr: 0.000176 loss: 3.0759 (2.9584) grad_norm: 2.2553 (2.3708) time: 0.6311 [2021-03-28 00:35:41 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 410/1251] eta: 0:08:58 lr: 0.000176 loss: 3.1712 (2.9608) grad_norm: 2.2917 (2.3709) time: 0.6350 [2021-03-28 00:35:48 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 420/1251] eta: 0:08:51 lr: 0.000176 loss: 3.1712 (2.9644) grad_norm: 2.2041 (2.3669) time: 0.6311 [2021-03-28 00:35:54 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 430/1251] eta: 0:08:45 lr: 0.000176 loss: 2.9985 (2.9593) grad_norm: 2.3685 (2.3746) time: 0.6262 [2021-03-28 00:36:00 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 440/1251] eta: 0:08:38 lr: 0.000176 loss: 2.9750 (2.9580) grad_norm: 2.3840 (2.3762) time: 0.6251 [2021-03-28 00:36:06 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 450/1251] eta: 0:08:31 lr: 0.000176 loss: 2.9218 (2.9513) grad_norm: 2.3075 (2.3745) time: 0.6257 [2021-03-28 00:36:13 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 460/1251] eta: 0:08:25 lr: 0.000176 loss: 2.6983 (2.9461) grad_norm: 2.2019 (2.3735) time: 0.6242 [2021-03-28 00:36:19 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 470/1251] eta: 0:08:18 lr: 0.000176 loss: 2.7312 (2.9458) grad_norm: 2.2874 (2.3803) time: 0.6249 [2021-03-28 00:36:25 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 480/1251] eta: 0:08:12 lr: 0.000176 loss: 2.6336 (2.9357) grad_norm: 2.2018 (2.3759) time: 0.6256 [2021-03-28 00:36:31 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 490/1251] eta: 0:08:05 lr: 0.000176 loss: 2.9227 (2.9398) grad_norm: 2.1337 (2.3756) time: 0.6317 [2021-03-28 00:36:38 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 500/1251] eta: 0:07:59 lr: 0.000176 loss: 3.0772 (2.9401) grad_norm: 2.2011 (2.3748) time: 0.6371 [2021-03-28 00:36:44 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 510/1251] eta: 0:07:52 lr: 0.000176 loss: 2.9861 (2.9381) grad_norm: 2.2526 (2.3930) time: 0.6310 [2021-03-28 00:36:50 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 520/1251] eta: 0:07:46 lr: 0.000176 loss: 2.9861 (2.9383) grad_norm: 2.3124 (2.3933) time: 0.6330 [2021-03-28 00:36:57 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 530/1251] eta: 0:07:39 lr: 0.000176 loss: 3.0459 (2.9371) grad_norm: 2.3045 (2.3910) time: 0.6335 [2021-03-28 00:37:03 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 540/1251] eta: 0:07:33 lr: 0.000176 loss: 2.9595 (2.9328) grad_norm: 2.2610 (2.3922) time: 0.6316 [2021-03-28 00:37:10 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 550/1251] eta: 0:07:27 lr: 0.000176 loss: 2.9836 (2.9375) grad_norm: 2.5444 (2.3976) time: 0.6365 [2021-03-28 00:37:16 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 560/1251] eta: 0:07:20 lr: 0.000176 loss: 3.2498 (2.9410) grad_norm: 2.4100 (2.3963) time: 0.6376 [2021-03-28 00:37:22 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 570/1251] eta: 0:07:14 lr: 0.000176 loss: 3.2498 (2.9455) grad_norm: 2.3102 (2.3948) time: 0.6369 [2021-03-28 00:37:29 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 580/1251] eta: 0:07:07 lr: 0.000176 loss: 3.0887 (2.9451) grad_norm: 2.3694 (2.3983) time: 0.6316 [2021-03-28 00:37:35 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 590/1251] eta: 0:07:01 lr: 0.000176 loss: 2.8911 (2.9406) grad_norm: 2.3481 (2.3970) time: 0.6294 [2021-03-28 00:37:41 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 600/1251] eta: 0:06:55 lr: 0.000176 loss: 2.8911 (2.9389) grad_norm: 2.3399 (2.3993) time: 0.6370 [2021-03-28 00:37:48 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 610/1251] eta: 0:06:48 lr: 0.000176 loss: 2.8531 (2.9353) grad_norm: 2.2430 (2.3957) time: 0.6342 [2021-03-28 00:37:54 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 620/1251] eta: 0:06:42 lr: 0.000176 loss: 2.8531 (2.9338) grad_norm: 2.2412 (2.3978) time: 0.6280 [2021-03-28 00:38:00 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 630/1251] eta: 0:06:35 lr: 0.000176 loss: 2.9950 (2.9366) grad_norm: 2.3837 (2.3985) time: 0.6265 [2021-03-28 00:38:06 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 640/1251] eta: 0:06:29 lr: 0.000176 loss: 3.1073 (2.9337) grad_norm: 2.2743 (2.3957) time: 0.6250 [2021-03-28 00:38:13 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 650/1251] eta: 0:06:22 lr: 0.000176 loss: 2.8378 (2.9325) grad_norm: 2.3253 (2.4008) time: 0.6242 [2021-03-28 00:38:19 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 660/1251] eta: 0:06:16 lr: 0.000176 loss: 3.1095 (2.9349) grad_norm: 2.3134 (2.3999) time: 0.6249 [2021-03-28 00:38:25 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 670/1251] eta: 0:06:09 lr: 0.000176 loss: 3.1322 (2.9376) grad_norm: 2.2602 (2.3988) time: 0.6295 [2021-03-28 00:38:31 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 680/1251] eta: 0:06:03 lr: 0.000176 loss: 3.0430 (2.9374) grad_norm: 2.2826 (2.4029) time: 0.6329 [2021-03-28 00:38:38 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 690/1251] eta: 0:05:56 lr: 0.000176 loss: 2.9083 (2.9379) grad_norm: 2.1753 (2.3989) time: 0.6344 [2021-03-28 00:38:44 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 700/1251] eta: 0:05:50 lr: 0.000175 loss: 3.0783 (2.9390) grad_norm: 2.1327 (2.3971) time: 0.6300 [2021-03-28 00:38:50 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 710/1251] eta: 0:05:44 lr: 0.000175 loss: 3.1001 (2.9384) grad_norm: 2.2343 (2.3944) time: 0.6284 [2021-03-28 00:38:57 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 720/1251] eta: 0:05:37 lr: 0.000175 loss: 2.9987 (2.9382) grad_norm: 2.2343 (2.3931) time: 0.6263 [2021-03-28 00:39:03 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 730/1251] eta: 0:05:31 lr: 0.000175 loss: 3.0071 (2.9369) grad_norm: 2.2346 (2.3912) time: 0.6314 [2021-03-28 00:39:09 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 740/1251] eta: 0:05:24 lr: 0.000175 loss: 3.0071 (2.9388) grad_norm: 2.2795 (2.3907) time: 0.6368 [2021-03-28 00:39:16 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 750/1251] eta: 0:05:18 lr: 0.000175 loss: 2.9889 (2.9367) grad_norm: 2.2645 (2.3917) time: 0.6275 [2021-03-28 00:39:22 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 760/1251] eta: 0:05:12 lr: 0.000175 loss: 2.9889 (2.9388) grad_norm: 2.2856 (2.3934) time: 0.6291 [2021-03-28 00:39:28 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 770/1251] eta: 0:05:05 lr: 0.000175 loss: 3.0316 (2.9367) grad_norm: 2.2912 (2.3927) time: 0.6303 [2021-03-28 00:39:35 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 780/1251] eta: 0:04:59 lr: 0.000175 loss: 3.1388 (2.9381) grad_norm: 2.2777 (2.3912) time: 0.6364 [2021-03-28 00:39:41 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 790/1251] eta: 0:04:53 lr: 0.000175 loss: 3.0961 (2.9389) grad_norm: 2.2777 (2.3931) time: 0.6426 [2021-03-28 00:39:47 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 800/1251] eta: 0:04:46 lr: 0.000175 loss: 3.0404 (2.9368) grad_norm: 2.2737 (2.3916) time: 0.6364 [2021-03-28 00:39:54 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 810/1251] eta: 0:04:40 lr: 0.000175 loss: 3.0135 (2.9373) grad_norm: 2.1691 (2.3894) time: 0.6334 [2021-03-28 00:40:00 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 820/1251] eta: 0:04:33 lr: 0.000175 loss: 3.0124 (2.9374) grad_norm: 2.1661 (2.3890) time: 0.6298 [2021-03-28 00:40:06 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 830/1251] eta: 0:04:27 lr: 0.000175 loss: 2.9712 (2.9395) grad_norm: 2.1774 (2.3890) time: 0.6256 [2021-03-28 00:40:12 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 840/1251] eta: 0:04:21 lr: 0.000175 loss: 3.1058 (2.9412) grad_norm: 2.1588 (2.3873) time: 0.6237 [2021-03-28 00:40:19 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 850/1251] eta: 0:04:14 lr: 0.000175 loss: 3.1191 (2.9404) grad_norm: 2.2772 (2.3895) time: 0.6228 [2021-03-28 00:40:25 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 860/1251] eta: 0:04:08 lr: 0.000175 loss: 3.1340 (2.9428) grad_norm: 2.3405 (2.3901) time: 0.6252 [2021-03-28 00:40:31 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 870/1251] eta: 0:04:01 lr: 0.000175 loss: 2.9566 (2.9418) grad_norm: 2.2483 (2.3907) time: 0.6269 [2021-03-28 00:40:38 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 880/1251] eta: 0:03:55 lr: 0.000175 loss: 2.9566 (2.9448) grad_norm: 2.2090 (2.3898) time: 0.6259 [2021-03-28 00:40:44 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 890/1251] eta: 0:03:49 lr: 0.000175 loss: 3.0558 (2.9453) grad_norm: 2.1969 (2.3910) time: 0.6286 [2021-03-28 00:40:50 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 900/1251] eta: 0:03:42 lr: 0.000175 loss: 2.9970 (2.9431) grad_norm: 2.2480 (2.3901) time: 0.6261 [2021-03-28 00:40:56 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 910/1251] eta: 0:03:36 lr: 0.000175 loss: 2.9970 (2.9436) grad_norm: 2.2907 (2.3914) time: 0.6230 [2021-03-28 00:41:03 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 920/1251] eta: 0:03:29 lr: 0.000175 loss: 3.2198 (2.9457) grad_norm: 2.2907 (2.3903) time: 0.6232 [2021-03-28 00:41:09 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 930/1251] eta: 0:03:23 lr: 0.000175 loss: 3.1199 (2.9456) grad_norm: 2.3883 (2.3922) time: 0.6246 [2021-03-28 00:41:15 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 940/1251] eta: 0:03:17 lr: 0.000175 loss: 2.8915 (2.9454) grad_norm: 2.4381 (2.3929) time: 0.6255 [2021-03-28 00:41:21 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 950/1251] eta: 0:03:10 lr: 0.000175 loss: 3.1524 (2.9475) grad_norm: 2.3372 (2.3923) time: 0.6248 [2021-03-28 00:41:27 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 960/1251] eta: 0:03:04 lr: 0.000175 loss: 2.4926 (2.9420) grad_norm: 2.2439 (2.3923) time: 0.6235 [2021-03-28 00:41:34 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 970/1251] eta: 0:02:58 lr: 0.000175 loss: 2.6562 (2.9430) grad_norm: 2.1956 (2.3931) time: 0.6302 [2021-03-28 00:41:40 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 980/1251] eta: 0:02:51 lr: 0.000175 loss: 3.0590 (2.9433) grad_norm: 2.0714 (2.3913) time: 0.6344 [2021-03-28 00:41:47 swin_base_patch4_window7_224] INFO: Epoch: [219] [ 990/1251] eta: 0:02:45 lr: 0.000175 loss: 2.8765 (2.9432) grad_norm: 2.1253 (2.3893) time: 0.6310 [2021-03-28 00:41:53 swin_base_patch4_window7_224] INFO: Epoch: [219] [1000/1251] eta: 0:02:39 lr: 0.000175 loss: 3.0402 (2.9442) grad_norm: 2.2468 (2.3918) time: 0.6339 [2021-03-28 00:41:59 swin_base_patch4_window7_224] INFO: Epoch: [219] [1010/1251] eta: 0:02:32 lr: 0.000175 loss: 2.8762 (2.9431) grad_norm: 2.4369 (2.3964) time: 0.6267 [2021-03-28 00:42:05 swin_base_patch4_window7_224] INFO: Epoch: [219] [1020/1251] eta: 0:02:26 lr: 0.000174 loss: 2.6451 (2.9406) grad_norm: 2.4091 (2.3958) time: 0.6235 [2021-03-28 00:42:12 swin_base_patch4_window7_224] INFO: Epoch: [219] [1030/1251] eta: 0:02:20 lr: 0.000174 loss: 2.9768 (2.9422) grad_norm: 2.2869 (2.3983) time: 0.6287 [2021-03-28 00:42:18 swin_base_patch4_window7_224] INFO: Epoch: [219] [1040/1251] eta: 0:02:13 lr: 0.000174 loss: 3.0835 (2.9430) grad_norm: 2.4105 (2.4001) time: 0.6345 [2021-03-28 00:42:24 swin_base_patch4_window7_224] INFO: Epoch: [219] [1050/1251] eta: 0:02:07 lr: 0.000174 loss: 2.9989 (2.9418) grad_norm: 2.2418 (2.3999) time: 0.6334 [2021-03-28 00:42:31 swin_base_patch4_window7_224] INFO: Epoch: [219] [1060/1251] eta: 0:02:01 lr: 0.000174 loss: 2.9989 (2.9430) grad_norm: 2.2375 (2.3989) time: 0.6277 [2021-03-28 00:42:37 swin_base_patch4_window7_224] INFO: Epoch: [219] [1070/1251] eta: 0:01:54 lr: 0.000174 loss: 2.9679 (2.9441) grad_norm: 2.2375 (2.3975) time: 0.6292 [2021-03-28 00:42:43 swin_base_patch4_window7_224] INFO: Epoch: [219] [1080/1251] eta: 0:01:48 lr: 0.000174 loss: 2.9130 (2.9419) grad_norm: 2.2489 (2.3983) time: 0.6261 [2021-03-28 00:42:49 swin_base_patch4_window7_224] INFO: Epoch: [219] [1090/1251] eta: 0:01:42 lr: 0.000174 loss: 2.9535 (2.9432) grad_norm: 2.1865 (2.3962) time: 0.6277 [2021-03-28 00:42:56 swin_base_patch4_window7_224] INFO: Epoch: [219] [1100/1251] eta: 0:01:35 lr: 0.000174 loss: 3.0816 (2.9436) grad_norm: 2.1754 (2.3964) time: 0.6282 [2021-03-28 00:43:02 swin_base_patch4_window7_224] INFO: Epoch: [219] [1110/1251] eta: 0:01:29 lr: 0.000174 loss: 3.0610 (2.9441) grad_norm: 2.3543 (2.3951) time: 0.6307 [2021-03-28 00:43:08 swin_base_patch4_window7_224] INFO: Epoch: [219] [1120/1251] eta: 0:01:22 lr: 0.000174 loss: 2.9521 (2.9442) grad_norm: 2.3110 (2.3955) time: 0.6376 [2021-03-28 00:43:15 swin_base_patch4_window7_224] INFO: Epoch: [219] [1130/1251] eta: 0:01:16 lr: 0.000174 loss: 2.8285 (2.9425) grad_norm: 2.2487 (2.3977) time: 0.6316 [2021-03-28 00:43:21 swin_base_patch4_window7_224] INFO: Epoch: [219] [1140/1251] eta: 0:01:10 lr: 0.000174 loss: 2.8131 (2.9417) grad_norm: 2.3569 (2.3973) time: 0.6223 [2021-03-28 00:43:27 swin_base_patch4_window7_224] INFO: Epoch: [219] [1150/1251] eta: 0:01:03 lr: 0.000174 loss: 2.9100 (2.9422) grad_norm: 2.3569 (2.3973) time: 0.6306 [2021-03-28 00:43:34 swin_base_patch4_window7_224] INFO: Epoch: [219] [1160/1251] eta: 0:00:57 lr: 0.000174 loss: 3.1519 (2.9417) grad_norm: 2.3950 (2.3977) time: 0.6363 [2021-03-28 00:43:40 swin_base_patch4_window7_224] INFO: Epoch: [219] [1170/1251] eta: 0:00:51 lr: 0.000174 loss: 3.0183 (2.9402) grad_norm: 2.3286 (2.3963) time: 0.6269 [2021-03-28 00:43:46 swin_base_patch4_window7_224] INFO: Epoch: [219] [1180/1251] eta: 0:00:44 lr: 0.000174 loss: 2.9770 (2.9405) grad_norm: 2.2834 (2.3960) time: 0.6275 [2021-03-28 00:43:52 swin_base_patch4_window7_224] INFO: Epoch: [219] [1190/1251] eta: 0:00:38 lr: 0.000174 loss: 2.8773 (2.9386) grad_norm: 2.3536 (2.3954) time: 0.6287 [2021-03-28 00:43:59 swin_base_patch4_window7_224] INFO: Epoch: [219] [1200/1251] eta: 0:00:32 lr: 0.000174 loss: 2.6303 (2.9365) grad_norm: 2.2493 (2.3938) time: 0.6258 [2021-03-28 00:44:05 swin_base_patch4_window7_224] INFO: Epoch: [219] [1210/1251] eta: 0:00:25 lr: 0.000174 loss: 2.7512 (2.9359) grad_norm: 2.3489 (2.3982) time: 0.6268 [2021-03-28 00:44:11 swin_base_patch4_window7_224] INFO: Epoch: [219] [1220/1251] eta: 0:00:19 lr: 0.000174 loss: 2.9794 (2.9359) grad_norm: 2.3838 (2.3990) time: 0.6264 [2021-03-28 00:44:17 swin_base_patch4_window7_224] INFO: Epoch: [219] [1230/1251] eta: 0:00:13 lr: 0.000174 loss: 2.9740 (2.9355) grad_norm: 2.2899 (2.3997) time: 0.6248 [2021-03-28 00:44:24 swin_base_patch4_window7_224] INFO: Epoch: [219] [1240/1251] eta: 0:00:06 lr: 0.000174 loss: 2.9740 (2.9365) grad_norm: 2.2604 (2.3993) time: 0.6236 [2021-03-28 00:44:30 swin_base_patch4_window7_224] INFO: Epoch: [219] [1250/1251] eta: 0:00:00 lr: 0.000174 loss: 3.0160 (2.9372) grad_norm: 2.3413 (2.4004) time: 0.6187 [2021-03-28 00:44:42 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:32 loss: 0.7142 (0.7142) acc1: 82.8125 (82.8125) acc5: 98.4375 (98.4375) [2021-03-28 00:44:44 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7833 (0.8002) acc1: 79.6875 (80.6818) acc5: 96.8750 (96.1648) [2021-03-28 00:44:46 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7698 (0.8010) acc1: 81.2500 (81.7708) acc5: 96.8750 (96.2054) [2021-03-28 00:44:49 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7698 (0.8278) acc1: 81.2500 (80.3427) acc5: 96.8750 (96.0685) [2021-03-28 00:44:51 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7606 (0.8075) acc1: 81.2500 (81.2119) acc5: 96.8750 (96.3796) [2021-03-28 00:44:52 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7606 (0.8012) acc1: 82.8125 (81.3440) acc5: 96.8750 (96.2880) [2021-03-28 00:45:04 swin_base_patch4_window7_224] INFO: * Acc@1 81.776 Acc@5 95.984 loss 0.793 [2021-03-28 00:45:04 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.8% [2021-03-28 00:45:04 swin_base_patch4_window7_224] INFO: Max accuracy: 81.90% [2021-03-28 00:45:10 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 0/1251] eta: 1:51:44 lr: 0.000174 loss: 3.3610 (3.3610) grad_norm: 2.5741 (2.5741) time: 5.3592 [2021-03-28 00:45:16 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 10/1251] eta: 0:21:57 lr: 0.000174 loss: 3.0899 (2.8936) grad_norm: 2.3702 (2.3453) time: 1.0615 [2021-03-28 00:45:22 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 20/1251] eta: 0:17:31 lr: 0.000174 loss: 2.9932 (2.9003) grad_norm: 2.3021 (2.3637) time: 0.6293 [2021-03-28 00:45:29 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 30/1251] eta: 0:15:52 lr: 0.000174 loss: 2.9932 (2.9206) grad_norm: 2.2112 (2.3026) time: 0.6254 [2021-03-28 00:45:35 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 40/1251] eta: 0:14:58 lr: 0.000174 loss: 2.9106 (2.9129) grad_norm: 2.0675 (2.2711) time: 0.6235 [2021-03-28 00:45:41 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 50/1251] eta: 0:14:26 lr: 0.000174 loss: 3.0391 (2.9565) grad_norm: 2.2083 (2.2781) time: 0.6306 [2021-03-28 00:45:48 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 60/1251] eta: 0:14:00 lr: 0.000174 loss: 3.0391 (2.9447) grad_norm: 2.2008 (2.2579) time: 0.6325 [2021-03-28 00:45:54 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 70/1251] eta: 0:13:39 lr: 0.000174 loss: 2.7187 (2.9199) grad_norm: 2.2072 (2.3114) time: 0.6233 [2021-03-28 00:46:00 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 80/1251] eta: 0:13:23 lr: 0.000174 loss: 2.9777 (2.9396) grad_norm: 2.2072 (2.2881) time: 0.6253 [2021-03-28 00:46:06 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 90/1251] eta: 0:13:10 lr: 0.000174 loss: 3.0374 (2.9486) grad_norm: 2.2841 (2.3061) time: 0.6351 [2021-03-28 00:46:13 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 100/1251] eta: 0:12:57 lr: 0.000173 loss: 3.0207 (2.9457) grad_norm: 2.3504 (2.3205) time: 0.6333 [2021-03-28 00:46:19 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 110/1251] eta: 0:12:46 lr: 0.000173 loss: 2.9150 (2.9324) grad_norm: 2.2239 (2.3085) time: 0.6297 [2021-03-28 00:46:25 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 120/1251] eta: 0:12:35 lr: 0.000173 loss: 2.9558 (2.9492) grad_norm: 2.2102 (2.3079) time: 0.6321 [2021-03-28 00:46:32 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 130/1251] eta: 0:12:26 lr: 0.000173 loss: 3.1883 (2.9503) grad_norm: 2.1881 (2.3034) time: 0.6325 [2021-03-28 00:46:38 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 140/1251] eta: 0:12:17 lr: 0.000173 loss: 3.1567 (2.9595) grad_norm: 2.1763 (2.3050) time: 0.6356 [2021-03-28 00:46:44 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 150/1251] eta: 0:12:07 lr: 0.000173 loss: 3.2187 (2.9772) grad_norm: 2.2348 (2.3212) time: 0.6306 [2021-03-28 00:46:51 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 160/1251] eta: 0:11:58 lr: 0.000173 loss: 3.1420 (2.9879) grad_norm: 2.1774 (2.3169) time: 0.6243 [2021-03-28 00:46:57 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 170/1251] eta: 0:11:49 lr: 0.000173 loss: 3.1160 (2.9879) grad_norm: 2.1774 (2.3110) time: 0.6239 [2021-03-28 00:47:03 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 180/1251] eta: 0:11:41 lr: 0.000173 loss: 2.8679 (2.9701) grad_norm: 2.0926 (2.2987) time: 0.6237 [2021-03-28 00:47:09 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 190/1251] eta: 0:11:33 lr: 0.000173 loss: 2.9115 (2.9717) grad_norm: 2.1051 (2.3053) time: 0.6291 [2021-03-28 00:47:16 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 200/1251] eta: 0:11:25 lr: 0.000173 loss: 3.0072 (2.9749) grad_norm: 2.3159 (2.3081) time: 0.6320 [2021-03-28 00:47:22 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 210/1251] eta: 0:11:18 lr: 0.000173 loss: 3.0072 (2.9650) grad_norm: 2.2255 (2.3024) time: 0.6279 [2021-03-28 00:47:28 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 220/1251] eta: 0:11:10 lr: 0.000173 loss: 2.8386 (2.9636) grad_norm: 2.2124 (2.3129) time: 0.6308 [2021-03-28 00:47:35 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 230/1251] eta: 0:11:03 lr: 0.000173 loss: 2.9793 (2.9626) grad_norm: 2.2124 (2.3195) time: 0.6295 [2021-03-28 00:47:41 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 240/1251] eta: 0:10:55 lr: 0.000173 loss: 3.0713 (2.9757) grad_norm: 2.2239 (2.3331) time: 0.6258 [2021-03-28 00:47:47 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 250/1251] eta: 0:10:48 lr: 0.000173 loss: 3.1965 (2.9770) grad_norm: 2.4362 (2.3441) time: 0.6289 [2021-03-28 00:47:53 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 260/1251] eta: 0:10:41 lr: 0.000173 loss: 2.9724 (2.9766) grad_norm: 2.3253 (2.3420) time: 0.6292 [2021-03-28 00:48:00 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 270/1251] eta: 0:10:34 lr: 0.000173 loss: 2.9535 (2.9755) grad_norm: 2.2679 (2.3392) time: 0.6341 [2021-03-28 00:48:06 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 280/1251] eta: 0:10:27 lr: 0.000173 loss: 3.1221 (2.9820) grad_norm: 2.2142 (2.3371) time: 0.6308 [2021-03-28 00:48:12 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 290/1251] eta: 0:10:20 lr: 0.000173 loss: 3.0331 (2.9716) grad_norm: 2.2978 (2.3578) time: 0.6269 [2021-03-28 00:48:19 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 300/1251] eta: 0:10:13 lr: 0.000173 loss: 2.7865 (2.9683) grad_norm: 2.4662 (2.3591) time: 0.6306 [2021-03-28 00:48:25 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 310/1251] eta: 0:10:06 lr: 0.000173 loss: 2.7865 (2.9600) grad_norm: 2.2200 (2.3531) time: 0.6294 [2021-03-28 00:48:31 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 320/1251] eta: 0:09:59 lr: 0.000173 loss: 2.9723 (2.9595) grad_norm: 2.0932 (2.3590) time: 0.6257 [2021-03-28 00:48:37 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 330/1251] eta: 0:09:52 lr: 0.000173 loss: 3.0986 (2.9648) grad_norm: 2.3968 (2.3573) time: 0.6223 [2021-03-28 00:48:44 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 340/1251] eta: 0:09:45 lr: 0.000173 loss: 2.9044 (2.9525) grad_norm: 2.3021 (2.3568) time: 0.6237 [2021-03-28 00:48:50 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 350/1251] eta: 0:09:38 lr: 0.000173 loss: 2.7350 (2.9529) grad_norm: 2.3021 (2.3613) time: 0.6285 [2021-03-28 00:48:56 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 360/1251] eta: 0:09:32 lr: 0.000173 loss: 3.0672 (2.9595) grad_norm: 2.3426 (2.3607) time: 0.6331 [2021-03-28 00:49:03 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 370/1251] eta: 0:09:25 lr: 0.000173 loss: 3.1582 (2.9576) grad_norm: 2.1295 (2.3552) time: 0.6355 [2021-03-28 00:49:09 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 380/1251] eta: 0:09:18 lr: 0.000173 loss: 3.0792 (2.9567) grad_norm: 2.0322 (2.3516) time: 0.6297 [2021-03-28 00:49:15 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 390/1251] eta: 0:09:12 lr: 0.000173 loss: 3.0792 (2.9553) grad_norm: 2.0890 (2.3501) time: 0.6294 [2021-03-28 00:49:22 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 400/1251] eta: 0:09:05 lr: 0.000173 loss: 3.1291 (2.9559) grad_norm: 2.1714 (2.3490) time: 0.6295 [2021-03-28 00:49:28 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 410/1251] eta: 0:08:58 lr: 0.000173 loss: 3.0597 (2.9534) grad_norm: 2.2527 (2.3472) time: 0.6232 [2021-03-28 00:49:34 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 420/1251] eta: 0:08:51 lr: 0.000172 loss: 3.1115 (2.9601) grad_norm: 2.3117 (2.3475) time: 0.6224 [2021-03-28 00:49:40 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 430/1251] eta: 0:08:45 lr: 0.000172 loss: 3.0375 (2.9566) grad_norm: 2.2548 (2.3467) time: 0.6266 [2021-03-28 00:49:47 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 440/1251] eta: 0:08:38 lr: 0.000172 loss: 2.7501 (2.9529) grad_norm: 2.2548 (2.3455) time: 0.6277 [2021-03-28 00:49:53 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 450/1251] eta: 0:08:31 lr: 0.000172 loss: 2.7501 (2.9463) grad_norm: 2.2775 (2.3471) time: 0.6267 [2021-03-28 00:49:59 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 460/1251] eta: 0:08:25 lr: 0.000172 loss: 2.8657 (2.9449) grad_norm: 2.1557 (2.3437) time: 0.6283 [2021-03-28 00:50:05 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 470/1251] eta: 0:08:18 lr: 0.000172 loss: 2.9133 (2.9435) grad_norm: 2.1347 (2.3413) time: 0.6316 [2021-03-28 00:50:12 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 480/1251] eta: 0:08:12 lr: 0.000172 loss: 3.0277 (2.9485) grad_norm: 2.2003 (2.3397) time: 0.6312 [2021-03-28 00:50:18 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 490/1251] eta: 0:08:05 lr: 0.000172 loss: 3.1272 (2.9522) grad_norm: 2.3526 (2.3408) time: 0.6320 [2021-03-28 00:50:24 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 500/1251] eta: 0:07:59 lr: 0.000172 loss: 2.9144 (2.9474) grad_norm: 2.2475 (2.3404) time: 0.6360 [2021-03-28 00:50:31 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 510/1251] eta: 0:07:52 lr: 0.000172 loss: 2.9144 (2.9481) grad_norm: 2.1133 (2.3373) time: 0.6282 [2021-03-28 00:50:37 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 520/1251] eta: 0:07:46 lr: 0.000172 loss: 3.0274 (2.9464) grad_norm: 2.0291 (2.3308) time: 0.6328 [2021-03-28 00:50:43 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 530/1251] eta: 0:07:40 lr: 0.000172 loss: 2.9784 (2.9448) grad_norm: 2.0857 (2.3317) time: 0.6408 [2021-03-28 00:50:50 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 540/1251] eta: 0:07:33 lr: 0.000172 loss: 2.8995 (2.9450) grad_norm: 2.1947 (2.3292) time: 0.6330 [2021-03-28 00:50:56 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 550/1251] eta: 0:07:27 lr: 0.000172 loss: 2.8995 (2.9449) grad_norm: 2.1248 (2.3249) time: 0.6363 [2021-03-28 00:51:03 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 560/1251] eta: 0:07:21 lr: 0.000172 loss: 2.9561 (2.9441) grad_norm: 2.1694 (2.3257) time: 0.6432 [2021-03-28 00:51:09 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 570/1251] eta: 0:07:14 lr: 0.000172 loss: 2.9323 (2.9433) grad_norm: 2.2504 (2.3258) time: 0.6325 [2021-03-28 00:51:15 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 580/1251] eta: 0:07:08 lr: 0.000172 loss: 3.0878 (2.9452) grad_norm: 2.2825 (2.3279) time: 0.6295 [2021-03-28 00:51:21 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 590/1251] eta: 0:07:01 lr: 0.000172 loss: 3.0753 (2.9456) grad_norm: 2.2890 (2.3286) time: 0.6292 [2021-03-28 00:51:28 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 600/1251] eta: 0:06:54 lr: 0.000172 loss: 2.6625 (2.9411) grad_norm: 2.3027 (2.3269) time: 0.6233 [2021-03-28 00:51:34 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 610/1251] eta: 0:06:48 lr: 0.000172 loss: 3.1436 (2.9443) grad_norm: 2.1784 (2.3237) time: 0.6219 [2021-03-28 00:51:40 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 620/1251] eta: 0:06:42 lr: 0.000172 loss: 3.2200 (2.9470) grad_norm: 2.2593 (2.3261) time: 0.6309 [2021-03-28 00:51:47 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 630/1251] eta: 0:06:35 lr: 0.000172 loss: 3.0017 (2.9468) grad_norm: 2.2799 (2.3253) time: 0.6321 [2021-03-28 00:51:53 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 640/1251] eta: 0:06:29 lr: 0.000172 loss: 2.9906 (2.9486) grad_norm: 2.2055 (2.3247) time: 0.6239 [2021-03-28 00:51:59 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 650/1251] eta: 0:06:22 lr: 0.000172 loss: 3.1177 (2.9502) grad_norm: 2.2053 (2.3226) time: 0.6290 [2021-03-28 00:52:05 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 660/1251] eta: 0:06:16 lr: 0.000172 loss: 3.0107 (2.9495) grad_norm: 2.1252 (2.3199) time: 0.6313 [2021-03-28 00:52:12 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 670/1251] eta: 0:06:09 lr: 0.000172 loss: 3.0839 (2.9519) grad_norm: 2.1908 (2.3206) time: 0.6302 [2021-03-28 00:52:18 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 680/1251] eta: 0:06:03 lr: 0.000172 loss: 3.0052 (2.9497) grad_norm: 2.3238 (2.3213) time: 0.6251 [2021-03-28 00:52:24 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 690/1251] eta: 0:05:56 lr: 0.000172 loss: 2.9065 (2.9496) grad_norm: 2.3238 (2.3232) time: 0.6218 [2021-03-28 00:52:30 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 700/1251] eta: 0:05:50 lr: 0.000172 loss: 3.0708 (2.9510) grad_norm: 2.2484 (2.3209) time: 0.6234 [2021-03-28 00:52:37 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 710/1251] eta: 0:05:43 lr: 0.000172 loss: 2.9783 (2.9510) grad_norm: 2.1621 (2.3225) time: 0.6228 [2021-03-28 00:52:43 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 720/1251] eta: 0:05:37 lr: 0.000172 loss: 3.0727 (2.9533) grad_norm: 2.2489 (2.3268) time: 0.6220 [2021-03-28 00:52:49 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 730/1251] eta: 0:05:31 lr: 0.000172 loss: 3.1376 (2.9546) grad_norm: 2.3233 (2.3295) time: 0.6256 [2021-03-28 00:52:56 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 740/1251] eta: 0:05:24 lr: 0.000172 loss: 2.9789 (2.9512) grad_norm: 2.2610 (2.3291) time: 0.6348 [2021-03-28 00:53:02 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 750/1251] eta: 0:05:18 lr: 0.000171 loss: 2.9799 (2.9533) grad_norm: 2.2443 (2.3294) time: 0.6389 [2021-03-28 00:53:08 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 760/1251] eta: 0:05:12 lr: 0.000171 loss: 3.1609 (2.9515) grad_norm: 2.1529 (2.3261) time: 0.6400 [2021-03-28 00:53:15 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 770/1251] eta: 0:05:05 lr: 0.000171 loss: 3.0487 (2.9518) grad_norm: 2.0842 (2.3279) time: 0.6330 [2021-03-28 00:53:21 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 780/1251] eta: 0:04:59 lr: 0.000171 loss: 3.1440 (2.9548) grad_norm: 2.2318 (2.3269) time: 0.6265 [2021-03-28 00:53:27 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 790/1251] eta: 0:04:52 lr: 0.000171 loss: 3.1660 (2.9534) grad_norm: 2.1242 (2.3242) time: 0.6344 [2021-03-28 00:53:34 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 800/1251] eta: 0:04:46 lr: 0.000171 loss: 3.0728 (2.9530) grad_norm: 2.1242 (2.3245) time: 0.6343 [2021-03-28 00:53:40 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 810/1251] eta: 0:04:40 lr: 0.000171 loss: 3.1791 (2.9557) grad_norm: 2.2431 (2.3239) time: 0.6281 [2021-03-28 00:53:46 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 820/1251] eta: 0:04:33 lr: 0.000171 loss: 3.0575 (2.9522) grad_norm: 2.2106 (2.3220) time: 0.6235 [2021-03-28 00:53:52 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 830/1251] eta: 0:04:27 lr: 0.000171 loss: 2.7200 (2.9521) grad_norm: 2.2029 (2.3216) time: 0.6226 [2021-03-28 00:53:59 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 840/1251] eta: 0:04:20 lr: 0.000171 loss: 2.8993 (2.9520) grad_norm: 2.2903 (2.3246) time: 0.6244 [2021-03-28 00:54:05 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 850/1251] eta: 0:04:14 lr: 0.000171 loss: 2.9158 (2.9504) grad_norm: 2.3675 (2.3251) time: 0.6254 [2021-03-28 00:54:11 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 860/1251] eta: 0:04:08 lr: 0.000171 loss: 2.9285 (2.9506) grad_norm: 2.2487 (2.3258) time: 0.6326 [2021-03-28 00:54:17 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 870/1251] eta: 0:04:01 lr: 0.000171 loss: 3.0949 (2.9520) grad_norm: 2.2745 (2.3271) time: 0.6302 [2021-03-28 00:54:24 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 880/1251] eta: 0:03:55 lr: 0.000171 loss: 3.1293 (2.9525) grad_norm: 2.3542 (2.3285) time: 0.6230 [2021-03-28 00:54:30 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 890/1251] eta: 0:03:49 lr: 0.000171 loss: 3.0550 (2.9526) grad_norm: 2.3908 (2.3288) time: 0.6250 [2021-03-28 00:54:36 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 900/1251] eta: 0:03:42 lr: 0.000171 loss: 2.9458 (2.9521) grad_norm: 2.3993 (2.3316) time: 0.6266 [2021-03-28 00:54:42 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 910/1251] eta: 0:03:36 lr: 0.000171 loss: 2.7617 (2.9496) grad_norm: 2.3799 (2.3318) time: 0.6258 [2021-03-28 00:54:49 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 920/1251] eta: 0:03:29 lr: 0.000171 loss: 2.7575 (2.9497) grad_norm: 2.3593 (2.3322) time: 0.6259 [2021-03-28 00:54:55 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 930/1251] eta: 0:03:23 lr: 0.000171 loss: 3.1248 (2.9510) grad_norm: 2.4236 (2.3351) time: 0.6251 [2021-03-28 00:55:01 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 940/1251] eta: 0:03:17 lr: 0.000171 loss: 3.2314 (2.9541) grad_norm: 2.4482 (2.3358) time: 0.6297 [2021-03-28 00:55:08 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 950/1251] eta: 0:03:10 lr: 0.000171 loss: 3.1691 (2.9535) grad_norm: 2.2649 (2.3358) time: 0.6335 [2021-03-28 00:55:14 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 960/1251] eta: 0:03:04 lr: 0.000171 loss: 3.2195 (2.9555) grad_norm: 2.2405 (2.3360) time: 0.6257 [2021-03-28 00:55:20 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 970/1251] eta: 0:02:58 lr: 0.000171 loss: 3.2368 (2.9558) grad_norm: 2.2277 (2.3353) time: 0.6222 [2021-03-28 00:55:26 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 980/1251] eta: 0:02:51 lr: 0.000171 loss: 3.1485 (2.9577) grad_norm: 2.1791 (2.3343) time: 0.6310 [2021-03-28 00:55:33 swin_base_patch4_window7_224] INFO: Epoch: [220] [ 990/1251] eta: 0:02:45 lr: 0.000171 loss: 3.1640 (2.9603) grad_norm: 2.1721 (2.3324) time: 0.6330 [2021-03-28 00:55:39 swin_base_patch4_window7_224] INFO: Epoch: [220] [1000/1251] eta: 0:02:39 lr: 0.000171 loss: 2.9976 (2.9582) grad_norm: 2.2315 (2.3317) time: 0.6303 [2021-03-28 00:55:45 swin_base_patch4_window7_224] INFO: Epoch: [220] [1010/1251] eta: 0:02:32 lr: 0.000171 loss: 2.9976 (2.9583) grad_norm: 2.2749 (2.3316) time: 0.6322 [2021-03-28 00:55:52 swin_base_patch4_window7_224] INFO: Epoch: [220] [1020/1251] eta: 0:02:26 lr: 0.000171 loss: 3.2040 (2.9571) grad_norm: 2.2632 (2.3305) time: 0.6270 [2021-03-28 00:55:58 swin_base_patch4_window7_224] INFO: Epoch: [220] [1030/1251] eta: 0:02:20 lr: 0.000171 loss: 3.0351 (2.9573) grad_norm: 2.2632 (2.3316) time: 0.6248 [2021-03-28 00:56:04 swin_base_patch4_window7_224] INFO: Epoch: [220] [1040/1251] eta: 0:02:13 lr: 0.000171 loss: 3.0351 (2.9557) grad_norm: 2.2483 (2.3300) time: 0.6307 [2021-03-28 00:56:11 swin_base_patch4_window7_224] INFO: Epoch: [220] [1050/1251] eta: 0:02:07 lr: 0.000171 loss: 2.8521 (2.9544) grad_norm: 2.2383 (2.3308) time: 0.6342 [2021-03-28 00:56:17 swin_base_patch4_window7_224] INFO: Epoch: [220] [1060/1251] eta: 0:02:00 lr: 0.000171 loss: 2.8345 (2.9532) grad_norm: 2.3927 (2.3298) time: 0.6274 [2021-03-28 00:56:23 swin_base_patch4_window7_224] INFO: Epoch: [220] [1070/1251] eta: 0:01:54 lr: 0.000170 loss: 2.8345 (2.9519) grad_norm: 2.1667 (2.3310) time: 0.6272 [2021-03-28 00:56:29 swin_base_patch4_window7_224] INFO: Epoch: [220] [1080/1251] eta: 0:01:48 lr: 0.000170 loss: 3.0518 (2.9534) grad_norm: 2.2083 (2.3305) time: 0.6284 [2021-03-28 00:56:36 swin_base_patch4_window7_224] INFO: Epoch: [220] [1090/1251] eta: 0:01:41 lr: 0.000170 loss: 3.0518 (2.9523) grad_norm: 2.1338 (2.3292) time: 0.6232 [2021-03-28 00:56:42 swin_base_patch4_window7_224] INFO: Epoch: [220] [1100/1251] eta: 0:01:35 lr: 0.000170 loss: 2.4248 (2.9469) grad_norm: 2.1338 (2.3305) time: 0.6211 [2021-03-28 00:56:48 swin_base_patch4_window7_224] INFO: Epoch: [220] [1110/1251] eta: 0:01:29 lr: 0.000170 loss: 2.5622 (2.9489) grad_norm: 2.2978 (2.3321) time: 0.6305 [2021-03-28 00:56:54 swin_base_patch4_window7_224] INFO: Epoch: [220] [1120/1251] eta: 0:01:22 lr: 0.000170 loss: 3.0696 (2.9488) grad_norm: 2.2713 (2.3306) time: 0.6316 [2021-03-28 00:57:01 swin_base_patch4_window7_224] INFO: Epoch: [220] [1130/1251] eta: 0:01:16 lr: 0.000170 loss: 3.0444 (2.9492) grad_norm: 2.2151 (2.3298) time: 0.6269 [2021-03-28 00:57:07 swin_base_patch4_window7_224] INFO: Epoch: [220] [1140/1251] eta: 0:01:10 lr: 0.000170 loss: 3.0348 (2.9499) grad_norm: 2.1573 (2.3285) time: 0.6286 [2021-03-28 00:57:13 swin_base_patch4_window7_224] INFO: Epoch: [220] [1150/1251] eta: 0:01:03 lr: 0.000170 loss: 3.0298 (2.9487) grad_norm: 2.0614 (2.3278) time: 0.6286 [2021-03-28 00:57:20 swin_base_patch4_window7_224] INFO: Epoch: [220] [1160/1251] eta: 0:00:57 lr: 0.000170 loss: 3.1294 (2.9493) grad_norm: 2.1494 (2.3278) time: 0.6305 [2021-03-28 00:57:26 swin_base_patch4_window7_224] INFO: Epoch: [220] [1170/1251] eta: 0:00:51 lr: 0.000170 loss: 2.9373 (2.9475) grad_norm: 2.1535 (2.3264) time: 0.6276 [2021-03-28 00:57:32 swin_base_patch4_window7_224] INFO: Epoch: [220] [1180/1251] eta: 0:00:44 lr: 0.000170 loss: 2.9373 (2.9493) grad_norm: 2.0916 (2.3308) time: 0.6285 [2021-03-28 00:57:39 swin_base_patch4_window7_224] INFO: Epoch: [220] [1190/1251] eta: 0:00:38 lr: 0.000170 loss: 3.1484 (2.9492) grad_norm: 2.2408 (2.3331) time: 0.6334 [2021-03-28 00:57:45 swin_base_patch4_window7_224] INFO: Epoch: [220] [1200/1251] eta: 0:00:32 lr: 0.000170 loss: 3.0481 (2.9507) grad_norm: 2.3851 (2.3349) time: 0.6317 [2021-03-28 00:57:51 swin_base_patch4_window7_224] INFO: Epoch: [220] [1210/1251] eta: 0:00:25 lr: 0.000170 loss: 3.0014 (2.9500) grad_norm: 2.2065 (2.3333) time: 0.6241 [2021-03-28 00:57:57 swin_base_patch4_window7_224] INFO: Epoch: [220] [1220/1251] eta: 0:00:19 lr: 0.000170 loss: 2.9839 (2.9501) grad_norm: 2.1608 (2.3333) time: 0.6297 [2021-03-28 00:58:04 swin_base_patch4_window7_224] INFO: Epoch: [220] [1230/1251] eta: 0:00:13 lr: 0.000170 loss: 2.9679 (2.9499) grad_norm: 2.4192 (2.3329) time: 0.6322 [2021-03-28 00:58:10 swin_base_patch4_window7_224] INFO: Epoch: [220] [1240/1251] eta: 0:00:06 lr: 0.000170 loss: 3.0420 (2.9511) grad_norm: 2.1922 (2.3313) time: 0.6238 [2021-03-28 00:58:16 swin_base_patch4_window7_224] INFO: Epoch: [220] [1250/1251] eta: 0:00:00 lr: 0.000170 loss: 3.2061 (2.9517) grad_norm: 2.1896 (2.3315) time: 0.6202 [2021-03-28 00:59:29 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.5349 (0.5349) acc1: 89.0625 (89.0625) acc5: 100.0000 (100.0000) [2021-03-28 00:59:31 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.7964 (0.7677) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.5909) [2021-03-28 00:59:32 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.8151 (0.7911) acc1: 81.2500 (81.5476) acc5: 96.8750 (96.4286) [2021-03-28 00:59:34 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8151 (0.8091) acc1: 79.6875 (81.4012) acc5: 95.3125 (95.9677) [2021-03-28 00:59:35 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7841 (0.8068) acc1: 79.6875 (81.0595) acc5: 95.3125 (96.0366) [2021-03-28 00:59:36 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7663 (0.8043) acc1: 81.1321 (81.2480) acc5: 95.3125 (95.9680) [2021-03-28 00:59:48 swin_base_patch4_window7_224] INFO: * Acc@1 81.880 Acc@5 95.998 loss 0.790 [2021-03-28 00:59:48 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.9% [2021-03-28 00:59:48 swin_base_patch4_window7_224] INFO: Max accuracy: 81.90% [2021-03-28 00:59:53 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 0/1251] eta: 1:32:26 lr: 0.000170 loss: 2.5963 (2.5963) grad_norm: 2.1385 (2.1385) time: 4.4333 [2021-03-28 00:59:59 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 10/1251] eta: 0:20:27 lr: 0.000170 loss: 2.7954 (2.9068) grad_norm: 2.0798 (2.1998) time: 0.9891 [2021-03-28 01:00:05 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 20/1251] eta: 0:16:47 lr: 0.000170 loss: 3.0001 (2.9140) grad_norm: 2.1306 (2.2438) time: 0.6380 [2021-03-28 01:00:12 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 30/1251] eta: 0:15:26 lr: 0.000170 loss: 2.9300 (2.8950) grad_norm: 2.2477 (2.2506) time: 0.6319 [2021-03-28 01:00:18 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 40/1251] eta: 0:14:40 lr: 0.000170 loss: 2.8343 (2.9149) grad_norm: 2.2742 (2.2657) time: 0.6311 [2021-03-28 01:00:24 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 50/1251] eta: 0:14:10 lr: 0.000170 loss: 3.0716 (2.9540) grad_norm: 2.2512 (2.2891) time: 0.6309 [2021-03-28 01:00:31 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 60/1251] eta: 0:13:48 lr: 0.000170 loss: 3.0716 (2.9478) grad_norm: 2.3329 (2.3033) time: 0.6317 [2021-03-28 01:00:37 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 70/1251] eta: 0:13:29 lr: 0.000170 loss: 2.8996 (2.9352) grad_norm: 2.3164 (2.3304) time: 0.6279 [2021-03-28 01:00:43 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 80/1251] eta: 0:13:17 lr: 0.000170 loss: 3.0620 (2.9587) grad_norm: 2.3479 (2.3606) time: 0.6342 [2021-03-28 01:00:50 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 90/1251] eta: 0:13:04 lr: 0.000170 loss: 3.0480 (2.9481) grad_norm: 2.3640 (2.3595) time: 0.6380 [2021-03-28 01:00:56 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 100/1251] eta: 0:12:51 lr: 0.000170 loss: 2.7229 (2.9070) grad_norm: 2.3150 (2.3749) time: 0.6294 [2021-03-28 01:01:02 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 110/1251] eta: 0:12:40 lr: 0.000170 loss: 2.7229 (2.9172) grad_norm: 2.3150 (2.3622) time: 0.6257 [2021-03-28 01:01:09 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 120/1251] eta: 0:12:31 lr: 0.000170 loss: 2.9783 (2.9214) grad_norm: 2.3158 (2.4019) time: 0.6320 [2021-03-28 01:01:15 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 130/1251] eta: 0:12:21 lr: 0.000170 loss: 2.9667 (2.9202) grad_norm: 2.4911 (2.4052) time: 0.6369 [2021-03-28 01:01:21 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 140/1251] eta: 0:12:13 lr: 0.000170 loss: 3.0044 (2.9203) grad_norm: 2.4621 (2.4101) time: 0.6366 [2021-03-28 01:01:28 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 150/1251] eta: 0:12:05 lr: 0.000169 loss: 2.9857 (2.9133) grad_norm: 2.3358 (2.4035) time: 0.6367 [2021-03-28 01:01:34 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 160/1251] eta: 0:11:56 lr: 0.000169 loss: 3.0244 (2.9297) grad_norm: 2.2216 (2.4010) time: 0.6309 [2021-03-28 01:01:40 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 170/1251] eta: 0:11:47 lr: 0.000169 loss: 3.0244 (2.9239) grad_norm: 2.2126 (2.3994) time: 0.6272 [2021-03-28 01:01:47 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 180/1251] eta: 0:11:39 lr: 0.000169 loss: 2.9450 (2.9239) grad_norm: 2.2346 (2.4081) time: 0.6267 [2021-03-28 01:01:53 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 190/1251] eta: 0:11:32 lr: 0.000169 loss: 2.9207 (2.9223) grad_norm: 2.3065 (2.4034) time: 0.6295 [2021-03-28 01:01:59 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 200/1251] eta: 0:11:24 lr: 0.000169 loss: 2.9480 (2.9302) grad_norm: 2.2797 (2.3974) time: 0.6329 [2021-03-28 01:02:06 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 210/1251] eta: 0:11:17 lr: 0.000169 loss: 3.0978 (2.9346) grad_norm: 2.3608 (2.4300) time: 0.6328 [2021-03-28 01:02:12 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 220/1251] eta: 0:11:09 lr: 0.000169 loss: 3.0113 (2.9235) grad_norm: 2.4041 (2.4245) time: 0.6310 [2021-03-28 01:02:18 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 230/1251] eta: 0:11:01 lr: 0.000169 loss: 2.9798 (2.9325) grad_norm: 2.2307 (2.4205) time: 0.6253 [2021-03-28 01:02:24 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 240/1251] eta: 0:10:54 lr: 0.000169 loss: 3.0959 (2.9369) grad_norm: 2.1761 (2.4142) time: 0.6195 [2021-03-28 01:02:31 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 250/1251] eta: 0:10:47 lr: 0.000169 loss: 3.0510 (2.9392) grad_norm: 2.2861 (2.4143) time: 0.6272 [2021-03-28 01:02:37 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 260/1251] eta: 0:10:40 lr: 0.000169 loss: 3.0781 (2.9464) grad_norm: 2.3446 (2.4128) time: 0.6333 [2021-03-28 01:02:43 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 270/1251] eta: 0:10:32 lr: 0.000169 loss: 3.1812 (2.9524) grad_norm: 2.1950 (2.4186) time: 0.6292 [2021-03-28 01:02:49 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 280/1251] eta: 0:10:25 lr: 0.000169 loss: 3.0257 (2.9514) grad_norm: 2.2705 (2.4191) time: 0.6253 [2021-03-28 01:02:56 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 290/1251] eta: 0:10:18 lr: 0.000169 loss: 2.9997 (2.9451) grad_norm: 2.2277 (2.4111) time: 0.6228 [2021-03-28 01:03:02 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 300/1251] eta: 0:10:11 lr: 0.000169 loss: 2.9997 (2.9408) grad_norm: 2.2574 (inf) time: 0.6220 [2021-03-28 01:03:08 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 310/1251] eta: 0:10:04 lr: 0.000169 loss: 2.7583 (2.9311) grad_norm: 2.2839 (inf) time: 0.6268 [2021-03-28 01:03:14 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 320/1251] eta: 0:09:57 lr: 0.000169 loss: 2.8668 (2.9312) grad_norm: 2.1716 (inf) time: 0.6306 [2021-03-28 01:03:21 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 330/1251] eta: 0:09:51 lr: 0.000169 loss: 3.0003 (2.9276) grad_norm: 2.3276 (inf) time: 0.6275 [2021-03-28 01:03:27 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 340/1251] eta: 0:09:44 lr: 0.000169 loss: 3.0332 (2.9290) grad_norm: 2.3435 (inf) time: 0.6281 [2021-03-28 01:03:33 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 350/1251] eta: 0:09:37 lr: 0.000169 loss: 3.0098 (2.9285) grad_norm: 2.1174 (inf) time: 0.6297 [2021-03-28 01:03:40 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 360/1251] eta: 0:09:30 lr: 0.000169 loss: 2.9101 (2.9263) grad_norm: 2.1664 (inf) time: 0.6263 [2021-03-28 01:03:46 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 370/1251] eta: 0:09:23 lr: 0.000169 loss: 2.9264 (2.9211) grad_norm: 2.2388 (inf) time: 0.6232 [2021-03-28 01:03:52 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 380/1251] eta: 0:09:17 lr: 0.000169 loss: 3.0449 (2.9224) grad_norm: 2.1805 (inf) time: 0.6232 [2021-03-28 01:03:58 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 390/1251] eta: 0:09:10 lr: 0.000169 loss: 2.9837 (2.9206) grad_norm: 2.2803 (inf) time: 0.6236 [2021-03-28 01:04:05 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 400/1251] eta: 0:09:03 lr: 0.000169 loss: 3.0029 (2.9244) grad_norm: 2.2672 (inf) time: 0.6259 [2021-03-28 01:04:11 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 410/1251] eta: 0:08:57 lr: 0.000169 loss: 2.9486 (2.9210) grad_norm: 2.2672 (inf) time: 0.6266 [2021-03-28 01:04:17 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 420/1251] eta: 0:08:50 lr: 0.000169 loss: 2.9279 (2.9196) grad_norm: 2.2893 (inf) time: 0.6257 [2021-03-28 01:04:23 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 430/1251] eta: 0:08:43 lr: 0.000169 loss: 2.9662 (2.9168) grad_norm: 2.2797 (inf) time: 0.6258 [2021-03-28 01:04:30 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 440/1251] eta: 0:08:37 lr: 0.000169 loss: 2.8287 (2.9106) grad_norm: 2.2797 (inf) time: 0.6269 [2021-03-28 01:04:36 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 450/1251] eta: 0:08:30 lr: 0.000169 loss: 2.8550 (2.9131) grad_norm: 2.2685 (inf) time: 0.6342 [2021-03-28 01:04:42 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 460/1251] eta: 0:08:24 lr: 0.000169 loss: 3.2385 (2.9194) grad_norm: 2.2680 (inf) time: 0.6385 [2021-03-28 01:04:49 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 470/1251] eta: 0:08:17 lr: 0.000169 loss: 3.1751 (2.9176) grad_norm: 2.2449 (inf) time: 0.6315 [2021-03-28 01:04:55 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 480/1251] eta: 0:08:11 lr: 0.000168 loss: 2.7366 (2.9127) grad_norm: 2.3125 (inf) time: 0.6235 [2021-03-28 01:05:01 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 490/1251] eta: 0:08:04 lr: 0.000168 loss: 2.9078 (2.9149) grad_norm: 2.2476 (inf) time: 0.6220 [2021-03-28 01:05:07 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 500/1251] eta: 0:07:58 lr: 0.000168 loss: 2.9330 (2.9135) grad_norm: 2.2449 (inf) time: 0.6247 [2021-03-28 01:05:14 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 510/1251] eta: 0:07:51 lr: 0.000168 loss: 3.1041 (2.9148) grad_norm: 2.2080 (inf) time: 0.6317 [2021-03-28 01:05:20 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 520/1251] eta: 0:07:45 lr: 0.000168 loss: 3.0911 (2.9152) grad_norm: 2.1387 (inf) time: 0.6309 [2021-03-28 01:05:26 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 530/1251] eta: 0:07:38 lr: 0.000168 loss: 3.0649 (2.9192) grad_norm: 2.1134 (inf) time: 0.6284 [2021-03-28 01:05:33 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 540/1251] eta: 0:07:32 lr: 0.000168 loss: 3.0649 (2.9203) grad_norm: 2.2917 (inf) time: 0.6326 [2021-03-28 01:05:39 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 550/1251] eta: 0:07:26 lr: 0.000168 loss: 2.8830 (2.9205) grad_norm: 2.3296 (inf) time: 0.6344 [2021-03-28 01:05:45 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 560/1251] eta: 0:07:19 lr: 0.000168 loss: 3.0564 (2.9238) grad_norm: 2.2751 (inf) time: 0.6429 [2021-03-28 01:05:52 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 570/1251] eta: 0:07:13 lr: 0.000168 loss: 3.2421 (2.9300) grad_norm: 2.3854 (inf) time: 0.6409 [2021-03-28 01:05:58 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 580/1251] eta: 0:07:06 lr: 0.000168 loss: 3.1390 (2.9282) grad_norm: 2.3324 (inf) time: 0.6277 [2021-03-28 01:06:04 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 590/1251] eta: 0:07:00 lr: 0.000168 loss: 2.9807 (2.9282) grad_norm: 2.3009 (inf) time: 0.6278 [2021-03-28 01:06:11 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 600/1251] eta: 0:06:54 lr: 0.000168 loss: 2.9809 (2.9276) grad_norm: 2.2269 (inf) time: 0.6293 [2021-03-28 01:06:17 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 610/1251] eta: 0:06:47 lr: 0.000168 loss: 3.0136 (2.9271) grad_norm: 2.1404 (inf) time: 0.6267 [2021-03-28 01:06:23 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 620/1251] eta: 0:06:41 lr: 0.000168 loss: 3.0585 (2.9276) grad_norm: 2.3791 (inf) time: 0.6287 [2021-03-28 01:06:29 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 630/1251] eta: 0:06:34 lr: 0.000168 loss: 3.1258 (2.9284) grad_norm: 2.3885 (inf) time: 0.6249 [2021-03-28 01:06:36 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 640/1251] eta: 0:06:28 lr: 0.000168 loss: 3.2306 (2.9329) grad_norm: 2.3272 (inf) time: 0.6266 [2021-03-28 01:06:42 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 650/1251] eta: 0:06:21 lr: 0.000168 loss: 3.1146 (2.9327) grad_norm: 2.3630 (inf) time: 0.6300 [2021-03-28 01:06:48 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 660/1251] eta: 0:06:15 lr: 0.000168 loss: 3.0383 (2.9352) grad_norm: 2.3052 (inf) time: 0.6289 [2021-03-28 01:06:55 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 670/1251] eta: 0:06:09 lr: 0.000168 loss: 2.8249 (2.9330) grad_norm: 2.3052 (inf) time: 0.6342 [2021-03-28 01:07:01 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 680/1251] eta: 0:06:02 lr: 0.000168 loss: 2.8249 (2.9329) grad_norm: 2.2483 (inf) time: 0.6293 [2021-03-28 01:07:07 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 690/1251] eta: 0:05:56 lr: 0.000168 loss: 3.0716 (2.9346) grad_norm: 2.1860 (inf) time: 0.6245 [2021-03-28 01:07:13 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 700/1251] eta: 0:05:49 lr: 0.000168 loss: 3.1007 (2.9361) grad_norm: 2.1989 (inf) time: 0.6257 [2021-03-28 01:07:20 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 710/1251] eta: 0:05:43 lr: 0.000168 loss: 2.9708 (2.9355) grad_norm: 2.2599 (inf) time: 0.6273 [2021-03-28 01:07:26 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 720/1251] eta: 0:05:37 lr: 0.000168 loss: 2.7797 (2.9330) grad_norm: 2.2599 (inf) time: 0.6273 [2021-03-28 01:07:32 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 730/1251] eta: 0:05:30 lr: 0.000168 loss: 3.0298 (2.9364) grad_norm: 2.4661 (inf) time: 0.6285 [2021-03-28 01:07:39 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 740/1251] eta: 0:05:24 lr: 0.000168 loss: 3.1542 (2.9368) grad_norm: 2.4010 (inf) time: 0.6353 [2021-03-28 01:07:45 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 750/1251] eta: 0:05:18 lr: 0.000168 loss: 2.8124 (2.9345) grad_norm: 2.2371 (inf) time: 0.6425 [2021-03-28 01:07:51 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 760/1251] eta: 0:05:11 lr: 0.000168 loss: 2.8296 (2.9343) grad_norm: 2.1396 (inf) time: 0.6402 [2021-03-28 01:07:58 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 770/1251] eta: 0:05:05 lr: 0.000168 loss: 2.8852 (2.9325) grad_norm: 2.2315 (inf) time: 0.6344 [2021-03-28 01:08:04 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 780/1251] eta: 0:04:58 lr: 0.000168 loss: 3.0020 (2.9327) grad_norm: 2.2581 (inf) time: 0.6333 [2021-03-28 01:08:10 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 790/1251] eta: 0:04:52 lr: 0.000168 loss: 3.0110 (2.9336) grad_norm: 2.2854 (inf) time: 0.6301 [2021-03-28 01:08:17 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 800/1251] eta: 0:04:46 lr: 0.000168 loss: 2.9239 (2.9329) grad_norm: 2.2883 (inf) time: 0.6265 [2021-03-28 01:08:23 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 810/1251] eta: 0:04:39 lr: 0.000167 loss: 2.8040 (2.9306) grad_norm: 2.2635 (inf) time: 0.6276 [2021-03-28 01:08:29 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 820/1251] eta: 0:04:33 lr: 0.000167 loss: 2.7390 (2.9295) grad_norm: 2.4043 (inf) time: 0.6284 [2021-03-28 01:08:36 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 830/1251] eta: 0:04:27 lr: 0.000167 loss: 2.8509 (2.9274) grad_norm: 2.4231 (inf) time: 0.6269 [2021-03-28 01:08:42 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 840/1251] eta: 0:04:20 lr: 0.000167 loss: 2.8529 (2.9271) grad_norm: 2.4018 (inf) time: 0.6284 [2021-03-28 01:08:48 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 850/1251] eta: 0:04:14 lr: 0.000167 loss: 2.9260 (2.9267) grad_norm: 2.2711 (inf) time: 0.6259 [2021-03-28 01:08:54 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 860/1251] eta: 0:04:07 lr: 0.000167 loss: 2.9856 (2.9285) grad_norm: 2.2269 (inf) time: 0.6213 [2021-03-28 01:09:01 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 870/1251] eta: 0:04:01 lr: 0.000167 loss: 3.0904 (2.9270) grad_norm: 2.1826 (inf) time: 0.6278 [2021-03-28 01:09:07 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 880/1251] eta: 0:03:55 lr: 0.000167 loss: 3.0833 (2.9288) grad_norm: 2.2273 (inf) time: 0.6386 [2021-03-28 01:09:13 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 890/1251] eta: 0:03:48 lr: 0.000167 loss: 3.0420 (2.9268) grad_norm: 2.3568 (inf) time: 0.6365 [2021-03-28 01:09:20 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 900/1251] eta: 0:03:42 lr: 0.000167 loss: 2.7814 (2.9266) grad_norm: 2.2303 (inf) time: 0.6301 [2021-03-28 01:09:26 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 910/1251] eta: 0:03:36 lr: 0.000167 loss: 3.0608 (2.9265) grad_norm: 2.2199 (inf) time: 0.6262 [2021-03-28 01:09:32 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 920/1251] eta: 0:03:29 lr: 0.000167 loss: 3.1105 (2.9265) grad_norm: 2.2656 (inf) time: 0.6335 [2021-03-28 01:09:39 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 930/1251] eta: 0:03:23 lr: 0.000167 loss: 3.0727 (2.9271) grad_norm: 2.2874 (inf) time: 0.6330 [2021-03-28 01:09:45 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 940/1251] eta: 0:03:17 lr: 0.000167 loss: 3.0452 (2.9271) grad_norm: 2.2263 (inf) time: 0.6224 [2021-03-28 01:09:51 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 950/1251] eta: 0:03:10 lr: 0.000167 loss: 3.0692 (2.9282) grad_norm: 2.1755 (inf) time: 0.6330 [2021-03-28 01:09:57 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 960/1251] eta: 0:03:04 lr: 0.000167 loss: 3.0900 (2.9286) grad_norm: 2.2939 (inf) time: 0.6352 [2021-03-28 01:10:04 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 970/1251] eta: 0:02:58 lr: 0.000167 loss: 3.1293 (2.9304) grad_norm: 2.2880 (inf) time: 0.6229 [2021-03-28 01:10:10 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 980/1251] eta: 0:02:51 lr: 0.000167 loss: 3.1222 (2.9288) grad_norm: 2.2880 (inf) time: 0.6236 [2021-03-28 01:10:16 swin_base_patch4_window7_224] INFO: Epoch: [221] [ 990/1251] eta: 0:02:45 lr: 0.000167 loss: 3.0415 (2.9301) grad_norm: 2.2647 (inf) time: 0.6237 [2021-03-28 01:10:23 swin_base_patch4_window7_224] INFO: Epoch: [221] [1000/1251] eta: 0:02:39 lr: 0.000167 loss: 3.1865 (2.9330) grad_norm: 2.2262 (inf) time: 0.6306 [2021-03-28 01:10:29 swin_base_patch4_window7_224] INFO: Epoch: [221] [1010/1251] eta: 0:02:32 lr: 0.000167 loss: 3.1865 (2.9344) grad_norm: 2.1723 (inf) time: 0.6311 [2021-03-28 01:10:35 swin_base_patch4_window7_224] INFO: Epoch: [221] [1020/1251] eta: 0:02:26 lr: 0.000167 loss: 2.9219 (2.9326) grad_norm: 2.2188 (inf) time: 0.6235 [2021-03-28 01:10:41 swin_base_patch4_window7_224] INFO: Epoch: [221] [1030/1251] eta: 0:02:19 lr: 0.000167 loss: 2.8105 (2.9323) grad_norm: 2.3140 (inf) time: 0.6269 [2021-03-28 01:10:48 swin_base_patch4_window7_224] INFO: Epoch: [221] [1040/1251] eta: 0:02:13 lr: 0.000167 loss: 2.9356 (2.9295) grad_norm: 2.4736 (inf) time: 0.6273 [2021-03-28 01:10:54 swin_base_patch4_window7_224] INFO: Epoch: [221] [1050/1251] eta: 0:02:07 lr: 0.000167 loss: 2.8939 (2.9301) grad_norm: 2.4267 (inf) time: 0.6235 [2021-03-28 01:11:00 swin_base_patch4_window7_224] INFO: Epoch: [221] [1060/1251] eta: 0:02:00 lr: 0.000167 loss: 2.8939 (2.9279) grad_norm: 2.2510 (inf) time: 0.6229 [2021-03-28 01:11:06 swin_base_patch4_window7_224] INFO: Epoch: [221] [1070/1251] eta: 0:01:54 lr: 0.000167 loss: 2.9314 (2.9289) grad_norm: 2.1691 (inf) time: 0.6306 [2021-03-28 01:11:13 swin_base_patch4_window7_224] INFO: Epoch: [221] [1080/1251] eta: 0:01:48 lr: 0.000167 loss: 2.9632 (2.9294) grad_norm: 2.0809 (inf) time: 0.6296 [2021-03-28 01:11:19 swin_base_patch4_window7_224] INFO: Epoch: [221] [1090/1251] eta: 0:01:41 lr: 0.000167 loss: 2.9097 (2.9261) grad_norm: 2.2887 (inf) time: 0.6224 [2021-03-28 01:11:25 swin_base_patch4_window7_224] INFO: Epoch: [221] [1100/1251] eta: 0:01:35 lr: 0.000167 loss: 2.7236 (2.9271) grad_norm: 2.2887 (inf) time: 0.6234 [2021-03-28 01:11:31 swin_base_patch4_window7_224] INFO: Epoch: [221] [1110/1251] eta: 0:01:29 lr: 0.000167 loss: 3.0109 (2.9271) grad_norm: 2.3071 (inf) time: 0.6239 [2021-03-28 01:11:38 swin_base_patch4_window7_224] INFO: Epoch: [221] [1120/1251] eta: 0:01:22 lr: 0.000167 loss: 3.0109 (2.9284) grad_norm: 2.3641 (inf) time: 0.6233 [2021-03-28 01:11:44 swin_base_patch4_window7_224] INFO: Epoch: [221] [1130/1251] eta: 0:01:16 lr: 0.000167 loss: 3.2134 (2.9289) grad_norm: 2.3641 (inf) time: 0.6271 [2021-03-28 01:11:50 swin_base_patch4_window7_224] INFO: Epoch: [221] [1140/1251] eta: 0:01:10 lr: 0.000166 loss: 3.0079 (2.9284) grad_norm: 2.2828 (inf) time: 0.6268 [2021-03-28 01:11:57 swin_base_patch4_window7_224] INFO: Epoch: [221] [1150/1251] eta: 0:01:03 lr: 0.000166 loss: 2.8844 (2.9271) grad_norm: 2.2139 (inf) time: 0.6324 [2021-03-28 01:12:03 swin_base_patch4_window7_224] INFO: Epoch: [221] [1160/1251] eta: 0:00:57 lr: 0.000166 loss: 2.9323 (2.9273) grad_norm: 2.2024 (inf) time: 0.6340 [2021-03-28 01:12:09 swin_base_patch4_window7_224] INFO: Epoch: [221] [1170/1251] eta: 0:00:51 lr: 0.000166 loss: 2.9208 (2.9265) grad_norm: 2.1617 (inf) time: 0.6334 [2021-03-28 01:12:15 swin_base_patch4_window7_224] INFO: Epoch: [221] [1180/1251] eta: 0:00:44 lr: 0.000166 loss: 2.8579 (2.9245) grad_norm: 2.2697 (inf) time: 0.6315 [2021-03-28 01:12:22 swin_base_patch4_window7_224] INFO: Epoch: [221] [1190/1251] eta: 0:00:38 lr: 0.000166 loss: 2.8925 (2.9236) grad_norm: 2.2366 (inf) time: 0.6278 [2021-03-28 01:12:28 swin_base_patch4_window7_224] INFO: Epoch: [221] [1200/1251] eta: 0:00:32 lr: 0.000166 loss: 3.1319 (2.9255) grad_norm: 2.2258 (inf) time: 0.6264 [2021-03-28 01:12:34 swin_base_patch4_window7_224] INFO: Epoch: [221] [1210/1251] eta: 0:00:25 lr: 0.000166 loss: 3.0002 (2.9253) grad_norm: 2.3561 (inf) time: 0.6259 [2021-03-28 01:12:40 swin_base_patch4_window7_224] INFO: Epoch: [221] [1220/1251] eta: 0:00:19 lr: 0.000166 loss: 2.7865 (2.9258) grad_norm: 2.3824 (inf) time: 0.6265 [2021-03-28 01:12:47 swin_base_patch4_window7_224] INFO: Epoch: [221] [1230/1251] eta: 0:00:13 lr: 0.000166 loss: 2.9777 (2.9263) grad_norm: 2.3733 (inf) time: 0.6210 [2021-03-28 01:12:53 swin_base_patch4_window7_224] INFO: Epoch: [221] [1240/1251] eta: 0:00:06 lr: 0.000166 loss: 3.1294 (2.9262) grad_norm: 2.3319 (inf) time: 0.6251 [2021-03-28 01:12:59 swin_base_patch4_window7_224] INFO: Epoch: [221] [1250/1251] eta: 0:00:00 lr: 0.000166 loss: 3.0465 (2.9256) grad_norm: 2.3427 (inf) time: 0.6295 [2021-03-28 01:13:12 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:01 loss: 0.5690 (0.5690) acc1: 87.5000 (87.5000) acc5: 98.4375 (98.4375) [2021-03-28 01:13:15 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9543 (0.8946) acc1: 78.1250 (78.1250) acc5: 93.7500 (95.0284) [2021-03-28 01:13:18 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.8189 (0.8266) acc1: 78.1250 (79.9107) acc5: 95.3125 (95.4613) [2021-03-28 01:13:21 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8027 (0.8122) acc1: 82.8125 (80.7460) acc5: 96.8750 (95.8165) [2021-03-28 01:13:22 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8325 (0.8203) acc1: 82.8125 (80.7546) acc5: 96.8750 (95.8841) [2021-03-28 01:13:23 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7649 (0.8085) acc1: 81.2500 (81.0240) acc5: 95.3125 (96.0000) [2021-03-28 01:13:37 swin_base_patch4_window7_224] INFO: * Acc@1 81.898 Acc@5 96.074 loss 0.782 [2021-03-28 01:13:37 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.9% [2021-03-28 01:13:37 swin_base_patch4_window7_224] INFO: Max accuracy: 81.90% [2021-03-28 01:13:41 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 0/1251] eta: 1:28:41 lr: 0.000166 loss: 3.3824 (3.3824) grad_norm: 2.0143 (2.0143) time: 4.2535 [2021-03-28 01:13:48 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 10/1251] eta: 0:20:07 lr: 0.000166 loss: 3.0383 (3.0439) grad_norm: 2.1143 (2.1875) time: 0.9730 [2021-03-28 01:13:54 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 20/1251] eta: 0:16:33 lr: 0.000166 loss: 3.0314 (2.9513) grad_norm: 2.2419 (2.2882) time: 0.6351 [2021-03-28 01:14:00 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 30/1251] eta: 0:15:14 lr: 0.000166 loss: 3.0342 (2.9715) grad_norm: 2.2419 (2.2934) time: 0.6263 [2021-03-28 01:14:06 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 40/1251] eta: 0:14:35 lr: 0.000166 loss: 3.1021 (2.9988) grad_norm: 2.3265 (2.3848) time: 0.6345 [2021-03-28 01:14:13 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 50/1251] eta: 0:14:07 lr: 0.000166 loss: 3.0618 (2.9658) grad_norm: 2.4045 (2.3595) time: 0.6375 [2021-03-28 01:14:19 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 60/1251] eta: 0:13:44 lr: 0.000166 loss: 2.7014 (2.9230) grad_norm: 2.2444 (2.3588) time: 0.6303 [2021-03-28 01:14:25 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 70/1251] eta: 0:13:26 lr: 0.000166 loss: 2.8983 (2.9088) grad_norm: 2.1862 (2.3587) time: 0.6264 [2021-03-28 01:14:32 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 80/1251] eta: 0:13:10 lr: 0.000166 loss: 3.1060 (2.9368) grad_norm: 2.2053 (2.3738) time: 0.6228 [2021-03-28 01:14:38 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 90/1251] eta: 0:12:57 lr: 0.000166 loss: 2.8162 (2.8831) grad_norm: 2.2009 (2.3537) time: 0.6231 [2021-03-28 01:14:44 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 100/1251] eta: 0:12:45 lr: 0.000166 loss: 2.3971 (2.8564) grad_norm: 2.1317 (2.3359) time: 0.6252 [2021-03-28 01:14:50 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 110/1251] eta: 0:12:35 lr: 0.000166 loss: 2.6979 (2.8478) grad_norm: 2.1388 (2.3352) time: 0.6283 [2021-03-28 01:14:57 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 120/1251] eta: 0:12:26 lr: 0.000166 loss: 2.9634 (2.8637) grad_norm: 2.2664 (2.3312) time: 0.6318 [2021-03-28 01:15:03 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 130/1251] eta: 0:12:17 lr: 0.000166 loss: 3.0171 (2.8649) grad_norm: 2.1926 (2.3165) time: 0.6300 [2021-03-28 01:15:09 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 140/1251] eta: 0:12:09 lr: 0.000166 loss: 2.9302 (2.8656) grad_norm: 2.2449 (2.3175) time: 0.6340 [2021-03-28 01:15:16 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 150/1251] eta: 0:12:00 lr: 0.000166 loss: 2.8598 (2.8550) grad_norm: 2.3180 (2.3168) time: 0.6364 [2021-03-28 01:15:22 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 160/1251] eta: 0:11:53 lr: 0.000166 loss: 2.9140 (2.8671) grad_norm: 2.3487 (2.3306) time: 0.6356 [2021-03-28 01:15:28 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 170/1251] eta: 0:11:44 lr: 0.000166 loss: 3.0144 (2.8667) grad_norm: 2.3953 (2.3396) time: 0.6291 [2021-03-28 01:15:35 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 180/1251] eta: 0:11:36 lr: 0.000166 loss: 2.9513 (2.8624) grad_norm: 2.2782 (2.3402) time: 0.6241 [2021-03-28 01:15:41 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 190/1251] eta: 0:11:29 lr: 0.000166 loss: 2.9513 (2.8566) grad_norm: 2.2184 (2.3472) time: 0.6308 [2021-03-28 01:15:47 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 200/1251] eta: 0:11:21 lr: 0.000166 loss: 3.0184 (2.8631) grad_norm: 2.2352 (2.3470) time: 0.6344 [2021-03-28 01:15:54 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 210/1251] eta: 0:11:14 lr: 0.000166 loss: 3.0445 (2.8761) grad_norm: 2.2352 (2.3569) time: 0.6355 [2021-03-28 01:16:00 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 220/1251] eta: 0:11:07 lr: 0.000165 loss: 3.0732 (2.8797) grad_norm: 2.2219 (2.3533) time: 0.6338 [2021-03-28 01:16:06 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 230/1251] eta: 0:11:00 lr: 0.000165 loss: 2.8793 (2.8746) grad_norm: 2.1613 (2.3507) time: 0.6278 [2021-03-28 01:16:12 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 240/1251] eta: 0:10:52 lr: 0.000165 loss: 2.8620 (2.8757) grad_norm: 2.1519 (2.3495) time: 0.6242 [2021-03-28 01:16:19 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 250/1251] eta: 0:10:45 lr: 0.000165 loss: 3.0293 (2.8795) grad_norm: 2.2380 (2.3482) time: 0.6269 [2021-03-28 01:16:25 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 260/1251] eta: 0:10:38 lr: 0.000165 loss: 3.0053 (2.8759) grad_norm: 2.2380 (2.3443) time: 0.6361 [2021-03-28 01:16:31 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 270/1251] eta: 0:10:32 lr: 0.000165 loss: 2.9569 (2.8812) grad_norm: 2.1554 (2.3371) time: 0.6362 [2021-03-28 01:16:38 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 280/1251] eta: 0:10:25 lr: 0.000165 loss: 3.0604 (2.8841) grad_norm: 2.1813 (2.3335) time: 0.6311 [2021-03-28 01:16:44 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 290/1251] eta: 0:10:18 lr: 0.000165 loss: 3.1082 (2.8918) grad_norm: 2.3373 (2.3368) time: 0.6302 [2021-03-28 01:16:50 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 300/1251] eta: 0:10:11 lr: 0.000165 loss: 2.9249 (2.8847) grad_norm: 2.2849 (2.3348) time: 0.6252 [2021-03-28 01:16:57 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 310/1251] eta: 0:10:04 lr: 0.000165 loss: 2.7066 (2.8798) grad_norm: 2.1956 (2.3320) time: 0.6266 [2021-03-28 01:17:03 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 320/1251] eta: 0:09:57 lr: 0.000165 loss: 2.7030 (2.8692) grad_norm: 2.2527 (2.3316) time: 0.6282 [2021-03-28 01:17:09 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 330/1251] eta: 0:09:50 lr: 0.000165 loss: 2.7323 (2.8731) grad_norm: 2.2658 (2.3332) time: 0.6277 [2021-03-28 01:17:15 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 340/1251] eta: 0:09:43 lr: 0.000165 loss: 2.9395 (2.8721) grad_norm: 2.4050 (2.3355) time: 0.6293 [2021-03-28 01:17:22 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 350/1251] eta: 0:09:37 lr: 0.000165 loss: 2.9395 (2.8674) grad_norm: 2.4050 (2.3390) time: 0.6319 [2021-03-28 01:17:28 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 360/1251] eta: 0:09:30 lr: 0.000165 loss: 2.9806 (2.8681) grad_norm: 2.4227 (2.3449) time: 0.6336 [2021-03-28 01:17:34 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 370/1251] eta: 0:09:24 lr: 0.000165 loss: 3.1185 (2.8725) grad_norm: 2.3554 (2.3445) time: 0.6295 [2021-03-28 01:17:41 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 380/1251] eta: 0:09:17 lr: 0.000165 loss: 2.9272 (2.8664) grad_norm: 2.2014 (2.3412) time: 0.6252 [2021-03-28 01:17:47 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 390/1251] eta: 0:09:10 lr: 0.000165 loss: 2.6738 (2.8665) grad_norm: 2.1280 (2.3397) time: 0.6262 [2021-03-28 01:17:53 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 400/1251] eta: 0:09:03 lr: 0.000165 loss: 3.1004 (2.8714) grad_norm: 2.1673 (2.3373) time: 0.6297 [2021-03-28 01:18:00 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 410/1251] eta: 0:08:57 lr: 0.000165 loss: 2.9670 (2.8678) grad_norm: 2.1601 (2.3377) time: 0.6355 [2021-03-28 01:18:06 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 420/1251] eta: 0:08:50 lr: 0.000165 loss: 2.9528 (2.8713) grad_norm: 2.1468 (2.3331) time: 0.6325 [2021-03-28 01:18:12 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 430/1251] eta: 0:08:44 lr: 0.000165 loss: 3.0692 (2.8794) grad_norm: 2.1498 (2.3350) time: 0.6244 [2021-03-28 01:18:18 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 440/1251] eta: 0:08:37 lr: 0.000165 loss: 3.0032 (2.8769) grad_norm: 2.2446 (2.3356) time: 0.6237 [2021-03-28 01:18:25 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 450/1251] eta: 0:08:31 lr: 0.000165 loss: 2.8138 (2.8749) grad_norm: 2.2959 (2.3506) time: 0.6253 [2021-03-28 01:18:31 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 460/1251] eta: 0:08:24 lr: 0.000165 loss: 2.9283 (2.8775) grad_norm: 2.2959 (2.3538) time: 0.6234 [2021-03-28 01:18:37 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 470/1251] eta: 0:08:17 lr: 0.000165 loss: 2.8883 (2.8732) grad_norm: 2.1655 (2.3528) time: 0.6216 [2021-03-28 01:18:43 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 480/1251] eta: 0:08:11 lr: 0.000165 loss: 3.0988 (2.8786) grad_norm: 2.1876 (2.3547) time: 0.6229 [2021-03-28 01:18:50 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 490/1251] eta: 0:08:04 lr: 0.000165 loss: 3.0988 (2.8769) grad_norm: 2.2725 (2.3525) time: 0.6244 [2021-03-28 01:18:56 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 500/1251] eta: 0:07:58 lr: 0.000165 loss: 2.6320 (2.8719) grad_norm: 2.2619 (2.3504) time: 0.6276 [2021-03-28 01:19:02 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 510/1251] eta: 0:07:51 lr: 0.000165 loss: 2.8002 (2.8752) grad_norm: 2.2619 (2.3545) time: 0.6291 [2021-03-28 01:19:08 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 520/1251] eta: 0:07:45 lr: 0.000165 loss: 2.8002 (2.8715) grad_norm: 2.3041 (2.3542) time: 0.6285 [2021-03-28 01:19:15 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 530/1251] eta: 0:07:38 lr: 0.000165 loss: 2.7547 (2.8713) grad_norm: 2.1877 (2.3531) time: 0.6299 [2021-03-28 01:19:21 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 540/1251] eta: 0:07:32 lr: 0.000165 loss: 2.7552 (2.8702) grad_norm: 2.1940 (2.3519) time: 0.6331 [2021-03-28 01:19:27 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 550/1251] eta: 0:07:25 lr: 0.000164 loss: 2.6181 (2.8666) grad_norm: 2.2163 (2.3492) time: 0.6357 [2021-03-28 01:19:34 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 560/1251] eta: 0:07:19 lr: 0.000164 loss: 2.9868 (2.8715) grad_norm: 2.2163 (2.3482) time: 0.6354 [2021-03-28 01:19:40 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 570/1251] eta: 0:07:13 lr: 0.000164 loss: 3.0580 (2.8724) grad_norm: 2.1530 (2.3460) time: 0.6293 [2021-03-28 01:19:46 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 580/1251] eta: 0:07:06 lr: 0.000164 loss: 2.9844 (2.8724) grad_norm: 2.1402 (2.3447) time: 0.6269 [2021-03-28 01:19:53 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 590/1251] eta: 0:07:00 lr: 0.000164 loss: 3.0169 (2.8710) grad_norm: 2.1425 (2.3486) time: 0.6326 [2021-03-28 01:19:59 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 600/1251] eta: 0:06:53 lr: 0.000164 loss: 3.0169 (2.8736) grad_norm: 2.3945 (2.3514) time: 0.6370 [2021-03-28 01:20:05 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 610/1251] eta: 0:06:47 lr: 0.000164 loss: 3.0208 (2.8766) grad_norm: 2.3945 (2.3504) time: 0.6359 [2021-03-28 01:20:12 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 620/1251] eta: 0:06:41 lr: 0.000164 loss: 3.0208 (2.8764) grad_norm: 2.1821 (2.3476) time: 0.6296 [2021-03-28 01:20:18 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 630/1251] eta: 0:06:34 lr: 0.000164 loss: 2.9735 (2.8787) grad_norm: 2.2386 (2.3498) time: 0.6242 [2021-03-28 01:20:24 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 640/1251] eta: 0:06:28 lr: 0.000164 loss: 2.9588 (2.8767) grad_norm: 2.2789 (2.3494) time: 0.6237 [2021-03-28 01:20:30 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 650/1251] eta: 0:06:21 lr: 0.000164 loss: 2.8437 (2.8793) grad_norm: 2.3123 (2.3508) time: 0.6247 [2021-03-28 01:20:37 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 660/1251] eta: 0:06:15 lr: 0.000164 loss: 2.8437 (2.8789) grad_norm: 2.3376 (2.3580) time: 0.6317 [2021-03-28 01:20:43 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 670/1251] eta: 0:06:08 lr: 0.000164 loss: 2.8349 (2.8786) grad_norm: 2.3376 (2.3573) time: 0.6305 [2021-03-28 01:20:49 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 680/1251] eta: 0:06:02 lr: 0.000164 loss: 2.9164 (2.8792) grad_norm: 2.3117 (2.3570) time: 0.6281 [2021-03-28 01:20:56 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 690/1251] eta: 0:05:56 lr: 0.000164 loss: 2.8467 (2.8788) grad_norm: 2.2501 (2.3571) time: 0.6274 [2021-03-28 01:21:02 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 700/1251] eta: 0:05:49 lr: 0.000164 loss: 2.7982 (2.8773) grad_norm: 2.1645 (2.3569) time: 0.6242 [2021-03-28 01:21:08 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 710/1251] eta: 0:05:43 lr: 0.000164 loss: 2.6002 (2.8730) grad_norm: 2.2692 (2.3574) time: 0.6309 [2021-03-28 01:21:14 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 720/1251] eta: 0:05:36 lr: 0.000164 loss: 2.9085 (2.8738) grad_norm: 2.2692 (2.3575) time: 0.6317 [2021-03-28 01:21:21 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 730/1251] eta: 0:05:30 lr: 0.000164 loss: 2.9433 (2.8749) grad_norm: 2.1941 (2.3564) time: 0.6259 [2021-03-28 01:21:27 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 740/1251] eta: 0:05:24 lr: 0.000164 loss: 2.9201 (2.8741) grad_norm: 2.2375 (2.3579) time: 0.6359 [2021-03-28 01:21:34 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 750/1251] eta: 0:05:17 lr: 0.000164 loss: 2.9201 (2.8736) grad_norm: 2.3164 (2.3570) time: 0.6386 [2021-03-28 01:21:40 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 760/1251] eta: 0:05:11 lr: 0.000164 loss: 2.9153 (2.8756) grad_norm: 2.1964 (2.3566) time: 0.6356 [2021-03-28 01:21:46 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 770/1251] eta: 0:05:05 lr: 0.000164 loss: 2.9153 (2.8746) grad_norm: 2.2584 (2.3572) time: 0.6337 [2021-03-28 01:21:52 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 780/1251] eta: 0:04:58 lr: 0.000164 loss: 3.0134 (2.8765) grad_norm: 2.1138 (2.3550) time: 0.6269 [2021-03-28 01:21:59 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 790/1251] eta: 0:04:52 lr: 0.000164 loss: 3.0134 (2.8730) grad_norm: 2.1325 (2.3544) time: 0.6323 [2021-03-28 01:22:05 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 800/1251] eta: 0:04:46 lr: 0.000164 loss: 2.8064 (2.8731) grad_norm: 2.4232 (2.3558) time: 0.6370 [2021-03-28 01:22:11 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 810/1251] eta: 0:04:39 lr: 0.000164 loss: 2.9779 (2.8739) grad_norm: 2.3713 (2.3553) time: 0.6329 [2021-03-28 01:22:18 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 820/1251] eta: 0:04:33 lr: 0.000164 loss: 3.0559 (2.8761) grad_norm: 2.3115 (2.3544) time: 0.6278 [2021-03-28 01:22:24 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 830/1251] eta: 0:04:27 lr: 0.000164 loss: 3.0559 (2.8763) grad_norm: 2.1605 (2.3519) time: 0.6271 [2021-03-28 01:22:30 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 840/1251] eta: 0:04:20 lr: 0.000164 loss: 3.0383 (2.8762) grad_norm: 2.1688 (2.3512) time: 0.6259 [2021-03-28 01:22:37 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 850/1251] eta: 0:04:14 lr: 0.000164 loss: 3.0634 (2.8784) grad_norm: 2.4123 (2.3582) time: 0.6255 [2021-03-28 01:22:43 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 860/1251] eta: 0:04:07 lr: 0.000164 loss: 3.1695 (2.8800) grad_norm: 2.4360 (2.3576) time: 0.6245 [2021-03-28 01:22:49 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 870/1251] eta: 0:04:01 lr: 0.000164 loss: 3.1213 (2.8797) grad_norm: 2.1960 (2.3560) time: 0.6292 [2021-03-28 01:22:55 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 880/1251] eta: 0:03:55 lr: 0.000164 loss: 2.8665 (2.8791) grad_norm: 2.2598 (2.3589) time: 0.6317 [2021-03-28 01:23:02 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 890/1251] eta: 0:03:48 lr: 0.000163 loss: 2.9256 (2.8804) grad_norm: 2.3335 (2.3623) time: 0.6339 [2021-03-28 01:23:08 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 900/1251] eta: 0:03:42 lr: 0.000163 loss: 2.9644 (2.8807) grad_norm: 2.3889 (2.3626) time: 0.6369 [2021-03-28 01:23:14 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 910/1251] eta: 0:03:36 lr: 0.000163 loss: 2.8376 (2.8792) grad_norm: 2.3553 (2.3618) time: 0.6302 [2021-03-28 01:23:21 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 920/1251] eta: 0:03:29 lr: 0.000163 loss: 2.8708 (2.8818) grad_norm: 2.2345 (2.3597) time: 0.6264 [2021-03-28 01:23:27 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 930/1251] eta: 0:03:23 lr: 0.000163 loss: 3.1187 (2.8822) grad_norm: 2.1436 (2.3600) time: 0.6318 [2021-03-28 01:23:33 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 940/1251] eta: 0:03:17 lr: 0.000163 loss: 2.9224 (2.8803) grad_norm: 2.3275 (2.3591) time: 0.6332 [2021-03-28 01:23:40 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 950/1251] eta: 0:03:10 lr: 0.000163 loss: 3.0494 (2.8833) grad_norm: 2.3055 (2.3592) time: 0.6315 [2021-03-28 01:23:46 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 960/1251] eta: 0:03:04 lr: 0.000163 loss: 3.1116 (2.8858) grad_norm: 2.3751 (2.3605) time: 0.6305 [2021-03-28 01:23:52 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 970/1251] eta: 0:02:58 lr: 0.000163 loss: 3.1056 (2.8878) grad_norm: 2.3288 (2.3587) time: 0.6291 [2021-03-28 01:23:58 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 980/1251] eta: 0:02:51 lr: 0.000163 loss: 3.1056 (2.8892) grad_norm: 2.1748 (2.3593) time: 0.6250 [2021-03-28 01:24:05 swin_base_patch4_window7_224] INFO: Epoch: [222] [ 990/1251] eta: 0:02:45 lr: 0.000163 loss: 2.9337 (2.8874) grad_norm: 2.1656 (2.3573) time: 0.6270 [2021-03-28 01:24:11 swin_base_patch4_window7_224] INFO: Epoch: [222] [1000/1251] eta: 0:02:39 lr: 0.000163 loss: 2.8384 (2.8870) grad_norm: 2.2155 (2.3570) time: 0.6353 [2021-03-28 01:24:17 swin_base_patch4_window7_224] INFO: Epoch: [222] [1010/1251] eta: 0:02:32 lr: 0.000163 loss: 2.8384 (2.8858) grad_norm: 2.2901 (2.3572) time: 0.6298 [2021-03-28 01:24:24 swin_base_patch4_window7_224] INFO: Epoch: [222] [1020/1251] eta: 0:02:26 lr: 0.000163 loss: 2.8767 (2.8863) grad_norm: 2.2116 (2.3553) time: 0.6265 [2021-03-28 01:24:30 swin_base_patch4_window7_224] INFO: Epoch: [222] [1030/1251] eta: 0:02:19 lr: 0.000163 loss: 2.9678 (2.8863) grad_norm: 2.1647 (2.3547) time: 0.6343 [2021-03-28 01:24:36 swin_base_patch4_window7_224] INFO: Epoch: [222] [1040/1251] eta: 0:02:13 lr: 0.000163 loss: 2.8799 (2.8851) grad_norm: 2.2277 (2.3546) time: 0.6346 [2021-03-28 01:24:43 swin_base_patch4_window7_224] INFO: Epoch: [222] [1050/1251] eta: 0:02:07 lr: 0.000163 loss: 2.8799 (2.8860) grad_norm: 2.2593 (2.3548) time: 0.6319 [2021-03-28 01:24:49 swin_base_patch4_window7_224] INFO: Epoch: [222] [1060/1251] eta: 0:02:00 lr: 0.000163 loss: 2.8244 (2.8834) grad_norm: 2.2799 (2.3544) time: 0.6288 [2021-03-28 01:24:55 swin_base_patch4_window7_224] INFO: Epoch: [222] [1070/1251] eta: 0:01:54 lr: 0.000163 loss: 2.8896 (2.8842) grad_norm: 2.2826 (2.3548) time: 0.6280 [2021-03-28 01:25:02 swin_base_patch4_window7_224] INFO: Epoch: [222] [1080/1251] eta: 0:01:48 lr: 0.000163 loss: 2.9078 (2.8840) grad_norm: 2.4133 (2.3559) time: 0.6366 [2021-03-28 01:25:08 swin_base_patch4_window7_224] INFO: Epoch: [222] [1090/1251] eta: 0:01:41 lr: 0.000163 loss: 2.9078 (2.8841) grad_norm: 2.2440 (2.3551) time: 0.6322 [2021-03-28 01:25:14 swin_base_patch4_window7_224] INFO: Epoch: [222] [1100/1251] eta: 0:01:35 lr: 0.000163 loss: 3.0428 (2.8855) grad_norm: 2.1234 (2.3535) time: 0.6323 [2021-03-28 01:25:21 swin_base_patch4_window7_224] INFO: Epoch: [222] [1110/1251] eta: 0:01:29 lr: 0.000163 loss: 3.0345 (2.8854) grad_norm: 2.2386 (2.3541) time: 0.6350 [2021-03-28 01:25:27 swin_base_patch4_window7_224] INFO: Epoch: [222] [1120/1251] eta: 0:01:22 lr: 0.000163 loss: 2.9424 (2.8853) grad_norm: 2.2712 (2.3540) time: 0.6262 [2021-03-28 01:25:33 swin_base_patch4_window7_224] INFO: Epoch: [222] [1130/1251] eta: 0:01:16 lr: 0.000163 loss: 3.1557 (2.8888) grad_norm: 2.2940 (2.3548) time: 0.6230 [2021-03-28 01:25:39 swin_base_patch4_window7_224] INFO: Epoch: [222] [1140/1251] eta: 0:01:10 lr: 0.000163 loss: 3.1001 (2.8893) grad_norm: 2.3509 (2.3549) time: 0.6253 [2021-03-28 01:25:46 swin_base_patch4_window7_224] INFO: Epoch: [222] [1150/1251] eta: 0:01:03 lr: 0.000163 loss: 3.0519 (2.8908) grad_norm: 2.3071 (2.3556) time: 0.6258 [2021-03-28 01:25:52 swin_base_patch4_window7_224] INFO: Epoch: [222] [1160/1251] eta: 0:00:57 lr: 0.000163 loss: 3.0184 (2.8904) grad_norm: 2.3382 (2.3563) time: 0.6316 [2021-03-28 01:25:58 swin_base_patch4_window7_224] INFO: Epoch: [222] [1170/1251] eta: 0:00:51 lr: 0.000163 loss: 2.9447 (2.8892) grad_norm: 2.4078 (2.3571) time: 0.6344 [2021-03-28 01:26:05 swin_base_patch4_window7_224] INFO: Epoch: [222] [1180/1251] eta: 0:00:44 lr: 0.000163 loss: 2.9867 (2.8891) grad_norm: 2.2233 (2.3561) time: 0.6275 [2021-03-28 01:26:11 swin_base_patch4_window7_224] INFO: Epoch: [222] [1190/1251] eta: 0:00:38 lr: 0.000163 loss: 2.9867 (2.8901) grad_norm: 2.2859 (2.3574) time: 0.6268 [2021-03-28 01:26:17 swin_base_patch4_window7_224] INFO: Epoch: [222] [1200/1251] eta: 0:00:32 lr: 0.000163 loss: 2.9746 (2.8900) grad_norm: 2.3065 (2.3573) time: 0.6280 [2021-03-28 01:26:23 swin_base_patch4_window7_224] INFO: Epoch: [222] [1210/1251] eta: 0:00:25 lr: 0.000163 loss: 2.9109 (2.8898) grad_norm: 2.3315 (2.3584) time: 0.6251 [2021-03-28 01:26:30 swin_base_patch4_window7_224] INFO: Epoch: [222] [1220/1251] eta: 0:00:19 lr: 0.000162 loss: 3.1301 (2.8913) grad_norm: 2.4372 (2.3601) time: 0.6256 [2021-03-28 01:26:36 swin_base_patch4_window7_224] INFO: Epoch: [222] [1230/1251] eta: 0:00:13 lr: 0.000162 loss: 3.0751 (2.8916) grad_norm: 2.4478 (2.3610) time: 0.6317 [2021-03-28 01:26:42 swin_base_patch4_window7_224] INFO: Epoch: [222] [1240/1251] eta: 0:00:06 lr: 0.000162 loss: 2.9692 (2.8913) grad_norm: 2.3611 (2.3621) time: 0.6280 [2021-03-28 01:26:48 swin_base_patch4_window7_224] INFO: Epoch: [222] [1250/1251] eta: 0:00:00 lr: 0.000162 loss: 2.8630 (2.8906) grad_norm: 2.3015 (2.3622) time: 0.6166 [2021-03-28 01:27:00 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:36 loss: 0.6051 (0.6051) acc1: 89.0625 (89.0625) acc5: 98.4375 (98.4375) [2021-03-28 01:27:02 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7772 (0.7435) acc1: 82.8125 (82.5284) acc5: 96.8750 (96.8750) [2021-03-28 01:27:04 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7962 (0.7947) acc1: 81.2500 (81.9940) acc5: 95.3125 (95.9821) [2021-03-28 01:27:07 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7852 (0.8017) acc1: 81.2500 (81.8044) acc5: 95.3125 (96.0181) [2021-03-28 01:27:08 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7830 (0.8052) acc1: 81.2500 (81.6692) acc5: 95.3125 (95.9223) [2021-03-28 01:27:09 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7600 (0.8005) acc1: 79.6875 (81.6000) acc5: 96.8750 (96.0320) [2021-03-28 01:27:25 swin_base_patch4_window7_224] INFO: * Acc@1 81.888 Acc@5 96.002 loss 0.785 [2021-03-28 01:27:25 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.9% [2021-03-28 01:27:25 swin_base_patch4_window7_224] INFO: Max accuracy: 81.90% [2021-03-28 01:27:30 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 0/1251] eta: 1:31:37 lr: 0.000162 loss: 3.3702 (3.3702) grad_norm: 1.6912 (1.6912) time: 4.3943 [2021-03-28 01:27:36 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 10/1251] eta: 0:20:07 lr: 0.000162 loss: 2.5717 (2.6902) grad_norm: 2.1787 (2.2471) time: 0.9727 [2021-03-28 01:27:42 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 20/1251] eta: 0:16:34 lr: 0.000162 loss: 2.8297 (2.8007) grad_norm: 2.2308 (2.2324) time: 0.6288 [2021-03-28 01:27:49 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 30/1251] eta: 0:15:14 lr: 0.000162 loss: 3.0567 (2.8902) grad_norm: 2.2668 (2.2814) time: 0.6253 [2021-03-28 01:27:55 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 40/1251] eta: 0:14:30 lr: 0.000162 loss: 3.0799 (2.9174) grad_norm: 2.2668 (2.2453) time: 0.6252 [2021-03-28 01:28:01 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 50/1251] eta: 0:14:03 lr: 0.000162 loss: 3.0799 (2.9022) grad_norm: 2.2611 (2.3441) time: 0.6302 [2021-03-28 01:28:08 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 60/1251] eta: 0:13:44 lr: 0.000162 loss: 2.9749 (2.8988) grad_norm: 2.4117 (2.3716) time: 0.6367 [2021-03-28 01:28:14 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 70/1251] eta: 0:13:29 lr: 0.000162 loss: 3.0135 (2.9230) grad_norm: 2.5106 (2.5004) time: 0.6416 [2021-03-28 01:28:20 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 80/1251] eta: 0:13:14 lr: 0.000162 loss: 3.1122 (2.9405) grad_norm: 2.4830 (2.5090) time: 0.6367 [2021-03-28 01:28:27 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 90/1251] eta: 0:13:01 lr: 0.000162 loss: 3.0293 (2.9546) grad_norm: 2.3420 (2.4905) time: 0.6294 [2021-03-28 01:28:33 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 100/1251] eta: 0:12:50 lr: 0.000162 loss: 3.0464 (2.9537) grad_norm: 2.2411 (2.4799) time: 0.6318 [2021-03-28 01:28:39 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 110/1251] eta: 0:12:39 lr: 0.000162 loss: 3.0464 (2.9513) grad_norm: 2.2259 (2.4736) time: 0.6323 [2021-03-28 01:28:46 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 120/1251] eta: 0:12:28 lr: 0.000162 loss: 2.9528 (2.9263) grad_norm: 2.3017 (2.4708) time: 0.6255 [2021-03-28 01:28:52 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 130/1251] eta: 0:12:19 lr: 0.000162 loss: 2.8724 (2.9267) grad_norm: 2.3655 (2.4644) time: 0.6251 [2021-03-28 01:28:58 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 140/1251] eta: 0:12:09 lr: 0.000162 loss: 3.1022 (2.9283) grad_norm: 2.3504 (inf) time: 0.6255 [2021-03-28 01:29:04 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 150/1251] eta: 0:12:00 lr: 0.000162 loss: 2.9761 (2.9174) grad_norm: 2.3604 (inf) time: 0.6240 [2021-03-28 01:29:11 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 160/1251] eta: 0:11:52 lr: 0.000162 loss: 2.7244 (2.9124) grad_norm: 2.4928 (inf) time: 0.6281 [2021-03-28 01:29:17 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 170/1251] eta: 0:11:44 lr: 0.000162 loss: 2.8280 (2.9026) grad_norm: 2.5005 (inf) time: 0.6305 [2021-03-28 01:29:23 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 180/1251] eta: 0:11:37 lr: 0.000162 loss: 3.0658 (2.9163) grad_norm: 2.2062 (inf) time: 0.6349 [2021-03-28 01:29:30 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 190/1251] eta: 0:11:29 lr: 0.000162 loss: 3.0908 (2.9182) grad_norm: 2.2133 (inf) time: 0.6323 [2021-03-28 01:29:36 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 200/1251] eta: 0:11:22 lr: 0.000162 loss: 3.0298 (2.9221) grad_norm: 2.2932 (inf) time: 0.6314 [2021-03-28 01:29:42 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 210/1251] eta: 0:11:14 lr: 0.000162 loss: 2.9860 (2.9192) grad_norm: 2.3497 (inf) time: 0.6335 [2021-03-28 01:29:49 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 220/1251] eta: 0:11:07 lr: 0.000162 loss: 2.8963 (2.9119) grad_norm: 2.4520 (inf) time: 0.6285 [2021-03-28 01:29:55 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 230/1251] eta: 0:11:00 lr: 0.000162 loss: 3.0272 (2.9259) grad_norm: 2.3479 (inf) time: 0.6309 [2021-03-28 01:30:01 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 240/1251] eta: 0:10:52 lr: 0.000162 loss: 3.1600 (2.9263) grad_norm: 2.4074 (inf) time: 0.6290 [2021-03-28 01:30:07 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 250/1251] eta: 0:10:45 lr: 0.000162 loss: 2.8143 (2.9154) grad_norm: 2.5104 (inf) time: 0.6245 [2021-03-28 01:30:14 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 260/1251] eta: 0:10:38 lr: 0.000162 loss: 3.0202 (2.9211) grad_norm: 2.5141 (inf) time: 0.6247 [2021-03-28 01:30:20 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 270/1251] eta: 0:10:31 lr: 0.000162 loss: 3.0754 (2.9237) grad_norm: 2.5078 (inf) time: 0.6296 [2021-03-28 01:30:26 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 280/1251] eta: 0:10:25 lr: 0.000162 loss: 2.8535 (2.9143) grad_norm: 2.3392 (inf) time: 0.6395 [2021-03-28 01:30:33 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 290/1251] eta: 0:10:18 lr: 0.000162 loss: 2.5556 (2.9019) grad_norm: 2.2191 (inf) time: 0.6376 [2021-03-28 01:30:39 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 300/1251] eta: 0:10:11 lr: 0.000161 loss: 2.6198 (2.8956) grad_norm: 2.1553 (inf) time: 0.6286 [2021-03-28 01:30:45 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 310/1251] eta: 0:10:04 lr: 0.000161 loss: 2.9140 (2.8988) grad_norm: 2.5045 (inf) time: 0.6295 [2021-03-28 01:30:52 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 320/1251] eta: 0:09:58 lr: 0.000161 loss: 3.0835 (2.9016) grad_norm: 2.5515 (inf) time: 0.6381 [2021-03-28 01:30:58 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 330/1251] eta: 0:09:51 lr: 0.000161 loss: 2.9168 (2.9037) grad_norm: 2.4249 (inf) time: 0.6380 [2021-03-28 01:31:04 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 340/1251] eta: 0:09:44 lr: 0.000161 loss: 3.0688 (2.9066) grad_norm: 2.4249 (inf) time: 0.6309 [2021-03-28 01:31:11 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 350/1251] eta: 0:09:37 lr: 0.000161 loss: 3.1579 (2.9138) grad_norm: 2.3240 (inf) time: 0.6259 [2021-03-28 01:31:17 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 360/1251] eta: 0:09:31 lr: 0.000161 loss: 3.0358 (2.9161) grad_norm: 2.2241 (inf) time: 0.6256 [2021-03-28 01:31:23 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 370/1251] eta: 0:09:24 lr: 0.000161 loss: 2.9288 (2.9171) grad_norm: 2.3491 (inf) time: 0.6268 [2021-03-28 01:31:29 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 380/1251] eta: 0:09:17 lr: 0.000161 loss: 3.0068 (2.9179) grad_norm: 2.3149 (inf) time: 0.6261 [2021-03-28 01:31:36 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 390/1251] eta: 0:09:10 lr: 0.000161 loss: 2.9814 (2.9180) grad_norm: 2.2261 (inf) time: 0.6258 [2021-03-28 01:31:42 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 400/1251] eta: 0:09:04 lr: 0.000161 loss: 2.9814 (2.9204) grad_norm: 2.2403 (inf) time: 0.6254 [2021-03-28 01:31:48 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 410/1251] eta: 0:08:57 lr: 0.000161 loss: 3.0714 (2.9251) grad_norm: 2.2427 (inf) time: 0.6235 [2021-03-28 01:31:54 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 420/1251] eta: 0:08:50 lr: 0.000161 loss: 3.0507 (2.9304) grad_norm: 2.2449 (inf) time: 0.6225 [2021-03-28 01:32:01 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 430/1251] eta: 0:08:44 lr: 0.000161 loss: 3.0295 (2.9269) grad_norm: 2.2470 (inf) time: 0.6292 [2021-03-28 01:32:07 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 440/1251] eta: 0:08:37 lr: 0.000161 loss: 2.8315 (2.9263) grad_norm: 2.2592 (inf) time: 0.6313 [2021-03-28 01:32:13 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 450/1251] eta: 0:08:31 lr: 0.000161 loss: 2.9930 (2.9284) grad_norm: 2.3000 (inf) time: 0.6279 [2021-03-28 01:32:20 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 460/1251] eta: 0:08:24 lr: 0.000161 loss: 3.0501 (2.9293) grad_norm: 2.3276 (inf) time: 0.6341 [2021-03-28 01:32:26 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 470/1251] eta: 0:08:18 lr: 0.000161 loss: 2.9762 (2.9293) grad_norm: 2.1630 (inf) time: 0.6323 [2021-03-28 01:32:32 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 480/1251] eta: 0:08:11 lr: 0.000161 loss: 3.2057 (2.9341) grad_norm: 2.1076 (inf) time: 0.6289 [2021-03-28 01:32:39 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 490/1251] eta: 0:08:05 lr: 0.000161 loss: 2.9181 (2.9267) grad_norm: 2.1861 (inf) time: 0.6329 [2021-03-28 01:32:45 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 500/1251] eta: 0:07:58 lr: 0.000161 loss: 2.7385 (2.9262) grad_norm: 2.1819 (inf) time: 0.6342 [2021-03-28 01:32:51 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 510/1251] eta: 0:07:52 lr: 0.000161 loss: 3.1340 (2.9296) grad_norm: 2.2174 (inf) time: 0.6345 [2021-03-28 01:32:58 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 520/1251] eta: 0:07:45 lr: 0.000161 loss: 3.0142 (2.9291) grad_norm: 2.3843 (inf) time: 0.6262 [2021-03-28 01:33:04 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 530/1251] eta: 0:07:39 lr: 0.000161 loss: 2.9602 (2.9280) grad_norm: 2.1989 (inf) time: 0.6294 [2021-03-28 01:33:10 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 540/1251] eta: 0:07:32 lr: 0.000161 loss: 3.0199 (2.9252) grad_norm: 2.2844 (inf) time: 0.6337 [2021-03-28 01:33:17 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 550/1251] eta: 0:07:26 lr: 0.000161 loss: 2.9864 (2.9239) grad_norm: 2.3200 (inf) time: 0.6387 [2021-03-28 01:33:23 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 560/1251] eta: 0:07:20 lr: 0.000161 loss: 3.0484 (2.9294) grad_norm: 2.3200 (inf) time: 0.6372 [2021-03-28 01:33:29 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 570/1251] eta: 0:07:13 lr: 0.000161 loss: 3.1389 (2.9310) grad_norm: 2.2342 (inf) time: 0.6224 [2021-03-28 01:33:35 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 580/1251] eta: 0:07:07 lr: 0.000161 loss: 3.0233 (2.9291) grad_norm: 2.3265 (inf) time: 0.6254 [2021-03-28 01:33:42 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 590/1251] eta: 0:07:00 lr: 0.000161 loss: 3.0005 (2.9286) grad_norm: 2.3677 (inf) time: 0.6276 [2021-03-28 01:33:48 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 600/1251] eta: 0:06:54 lr: 0.000161 loss: 3.0217 (2.9297) grad_norm: 2.2055 (inf) time: 0.6347 [2021-03-28 01:33:54 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 610/1251] eta: 0:06:47 lr: 0.000161 loss: 3.1780 (2.9321) grad_norm: 2.2583 (inf) time: 0.6347 [2021-03-28 01:34:01 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 620/1251] eta: 0:06:41 lr: 0.000161 loss: 3.1565 (2.9329) grad_norm: 2.4247 (inf) time: 0.6254 [2021-03-28 01:34:07 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 630/1251] eta: 0:06:35 lr: 0.000161 loss: 3.0290 (2.9346) grad_norm: 2.2488 (inf) time: 0.6279 [2021-03-28 01:34:13 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 640/1251] eta: 0:06:28 lr: 0.000160 loss: 3.0290 (2.9358) grad_norm: 2.2097 (inf) time: 0.6286 [2021-03-28 01:34:20 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 650/1251] eta: 0:06:22 lr: 0.000160 loss: 2.9979 (2.9349) grad_norm: 2.3463 (inf) time: 0.6271 [2021-03-28 01:34:26 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 660/1251] eta: 0:06:15 lr: 0.000160 loss: 2.9146 (2.9350) grad_norm: 2.2896 (inf) time: 0.6258 [2021-03-28 01:34:32 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 670/1251] eta: 0:06:09 lr: 0.000160 loss: 2.9146 (2.9346) grad_norm: 2.1869 (inf) time: 0.6283 [2021-03-28 01:34:38 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 680/1251] eta: 0:06:02 lr: 0.000160 loss: 2.9285 (2.9342) grad_norm: 2.2636 (inf) time: 0.6287 [2021-03-28 01:34:45 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 690/1251] eta: 0:05:56 lr: 0.000160 loss: 2.9078 (2.9343) grad_norm: 2.3757 (inf) time: 0.6323 [2021-03-28 01:34:51 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 700/1251] eta: 0:05:50 lr: 0.000160 loss: 3.1710 (2.9380) grad_norm: 2.4233 (inf) time: 0.6347 [2021-03-28 01:34:57 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 710/1251] eta: 0:05:43 lr: 0.000160 loss: 3.2396 (2.9380) grad_norm: 2.2211 (inf) time: 0.6291 [2021-03-28 01:35:04 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 720/1251] eta: 0:05:37 lr: 0.000160 loss: 2.9369 (2.9365) grad_norm: 2.3125 (inf) time: 0.6269 [2021-03-28 01:35:10 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 730/1251] eta: 0:05:30 lr: 0.000160 loss: 3.0472 (2.9395) grad_norm: 2.2386 (inf) time: 0.6347 [2021-03-28 01:35:16 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 740/1251] eta: 0:05:24 lr: 0.000160 loss: 2.8601 (2.9351) grad_norm: 2.3111 (inf) time: 0.6413 [2021-03-28 01:35:23 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 750/1251] eta: 0:05:18 lr: 0.000160 loss: 2.8198 (2.9360) grad_norm: 2.4462 (inf) time: 0.6367 [2021-03-28 01:35:29 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 760/1251] eta: 0:05:11 lr: 0.000160 loss: 3.1761 (2.9388) grad_norm: 2.4462 (inf) time: 0.6286 [2021-03-28 01:35:35 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 770/1251] eta: 0:05:05 lr: 0.000160 loss: 3.1682 (2.9373) grad_norm: 2.4281 (inf) time: 0.6287 [2021-03-28 01:35:42 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 780/1251] eta: 0:04:59 lr: 0.000160 loss: 2.8631 (2.9365) grad_norm: 2.4281 (inf) time: 0.6286 [2021-03-28 01:35:48 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 790/1251] eta: 0:04:52 lr: 0.000160 loss: 2.7920 (2.9324) grad_norm: 2.2101 (inf) time: 0.6334 [2021-03-28 01:35:54 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 800/1251] eta: 0:04:46 lr: 0.000160 loss: 2.7693 (2.9306) grad_norm: 2.2109 (inf) time: 0.6386 [2021-03-28 01:36:01 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 810/1251] eta: 0:04:40 lr: 0.000160 loss: 2.7693 (2.9299) grad_norm: 2.2821 (inf) time: 0.6339 [2021-03-28 01:36:07 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 820/1251] eta: 0:04:33 lr: 0.000160 loss: 2.6584 (2.9273) grad_norm: 2.2296 (inf) time: 0.6323 [2021-03-28 01:36:13 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 830/1251] eta: 0:04:27 lr: 0.000160 loss: 2.9658 (2.9270) grad_norm: 2.2296 (inf) time: 0.6305 [2021-03-28 01:36:20 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 840/1251] eta: 0:04:20 lr: 0.000160 loss: 2.9658 (2.9265) grad_norm: 2.2790 (inf) time: 0.6310 [2021-03-28 01:36:26 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 850/1251] eta: 0:04:14 lr: 0.000160 loss: 3.0429 (2.9279) grad_norm: 2.2041 (inf) time: 0.6268 [2021-03-28 01:36:32 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 860/1251] eta: 0:04:08 lr: 0.000160 loss: 3.0670 (2.9278) grad_norm: 2.2639 (inf) time: 0.6256 [2021-03-28 01:36:38 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 870/1251] eta: 0:04:01 lr: 0.000160 loss: 3.0102 (2.9280) grad_norm: 2.3349 (inf) time: 0.6279 [2021-03-28 01:36:45 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 880/1251] eta: 0:03:55 lr: 0.000160 loss: 2.8980 (2.9259) grad_norm: 2.2030 (inf) time: 0.6317 [2021-03-28 01:36:51 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 890/1251] eta: 0:03:49 lr: 0.000160 loss: 2.7376 (2.9255) grad_norm: 2.1672 (inf) time: 0.6313 [2021-03-28 01:36:57 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 900/1251] eta: 0:03:42 lr: 0.000160 loss: 2.9825 (2.9248) grad_norm: 2.3871 (inf) time: 0.6312 [2021-03-28 01:37:04 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 910/1251] eta: 0:03:36 lr: 0.000160 loss: 3.1768 (2.9269) grad_norm: 2.2849 (inf) time: 0.6296 [2021-03-28 01:37:10 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 920/1251] eta: 0:03:29 lr: 0.000160 loss: 3.0017 (2.9254) grad_norm: 2.2550 (inf) time: 0.6259 [2021-03-28 01:37:16 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 930/1251] eta: 0:03:23 lr: 0.000160 loss: 3.0017 (2.9264) grad_norm: 2.2550 (inf) time: 0.6310 [2021-03-28 01:37:23 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 940/1251] eta: 0:03:17 lr: 0.000160 loss: 3.0537 (2.9252) grad_norm: 2.2746 (inf) time: 0.6306 [2021-03-28 01:37:29 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 950/1251] eta: 0:03:10 lr: 0.000160 loss: 2.8344 (2.9234) grad_norm: 2.2604 (inf) time: 0.6294 [2021-03-28 01:37:35 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 960/1251] eta: 0:03:04 lr: 0.000160 loss: 2.8812 (2.9250) grad_norm: 2.2855 (inf) time: 0.6276 [2021-03-28 01:37:41 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 970/1251] eta: 0:02:58 lr: 0.000159 loss: 3.1575 (2.9266) grad_norm: 2.3063 (inf) time: 0.6245 [2021-03-28 01:37:48 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 980/1251] eta: 0:02:51 lr: 0.000159 loss: 3.0398 (2.9252) grad_norm: 2.2233 (inf) time: 0.6243 [2021-03-28 01:37:54 swin_base_patch4_window7_224] INFO: Epoch: [223] [ 990/1251] eta: 0:02:45 lr: 0.000159 loss: 3.0398 (2.9270) grad_norm: 2.1645 (inf) time: 0.6248 [2021-03-28 01:38:00 swin_base_patch4_window7_224] INFO: Epoch: [223] [1000/1251] eta: 0:02:39 lr: 0.000159 loss: 3.1457 (2.9292) grad_norm: 2.2503 (inf) time: 0.6258 [2021-03-28 01:38:06 swin_base_patch4_window7_224] INFO: Epoch: [223] [1010/1251] eta: 0:02:32 lr: 0.000159 loss: 3.1684 (2.9297) grad_norm: 2.5141 (inf) time: 0.6257 [2021-03-28 01:38:13 swin_base_patch4_window7_224] INFO: Epoch: [223] [1020/1251] eta: 0:02:26 lr: 0.000159 loss: 3.0763 (2.9312) grad_norm: 2.3690 (inf) time: 0.6282 [2021-03-28 01:38:19 swin_base_patch4_window7_224] INFO: Epoch: [223] [1030/1251] eta: 0:02:20 lr: 0.000159 loss: 3.0332 (2.9315) grad_norm: 2.2083 (inf) time: 0.6310 [2021-03-28 01:38:25 swin_base_patch4_window7_224] INFO: Epoch: [223] [1040/1251] eta: 0:02:13 lr: 0.000159 loss: 2.9648 (2.9302) grad_norm: 2.3084 (inf) time: 0.6294 [2021-03-28 01:38:31 swin_base_patch4_window7_224] INFO: Epoch: [223] [1050/1251] eta: 0:02:07 lr: 0.000159 loss: 2.8008 (2.9278) grad_norm: 2.2561 (inf) time: 0.6251 [2021-03-28 01:38:38 swin_base_patch4_window7_224] INFO: Epoch: [223] [1060/1251] eta: 0:02:00 lr: 0.000159 loss: 2.9455 (2.9273) grad_norm: 2.2561 (inf) time: 0.6241 [2021-03-28 01:38:44 swin_base_patch4_window7_224] INFO: Epoch: [223] [1070/1251] eta: 0:01:54 lr: 0.000159 loss: 3.0457 (2.9285) grad_norm: 2.3199 (inf) time: 0.6229 [2021-03-28 01:38:50 swin_base_patch4_window7_224] INFO: Epoch: [223] [1080/1251] eta: 0:01:48 lr: 0.000159 loss: 2.9777 (2.9276) grad_norm: 2.2261 (inf) time: 0.6213 [2021-03-28 01:38:56 swin_base_patch4_window7_224] INFO: Epoch: [223] [1090/1251] eta: 0:01:41 lr: 0.000159 loss: 2.8086 (2.9273) grad_norm: 2.3200 (inf) time: 0.6245 [2021-03-28 01:39:03 swin_base_patch4_window7_224] INFO: Epoch: [223] [1100/1251] eta: 0:01:35 lr: 0.000159 loss: 2.8366 (2.9258) grad_norm: 2.2443 (inf) time: 0.6235 [2021-03-28 01:39:09 swin_base_patch4_window7_224] INFO: Epoch: [223] [1110/1251] eta: 0:01:29 lr: 0.000159 loss: 2.7743 (2.9239) grad_norm: 2.2064 (inf) time: 0.6219 [2021-03-28 01:39:15 swin_base_patch4_window7_224] INFO: Epoch: [223] [1120/1251] eta: 0:01:22 lr: 0.000159 loss: 2.8394 (2.9234) grad_norm: 2.2759 (inf) time: 0.6211 [2021-03-28 01:39:21 swin_base_patch4_window7_224] INFO: Epoch: [223] [1130/1251] eta: 0:01:16 lr: 0.000159 loss: 2.9516 (2.9249) grad_norm: 2.2702 (inf) time: 0.6250 [2021-03-28 01:39:28 swin_base_patch4_window7_224] INFO: Epoch: [223] [1140/1251] eta: 0:01:10 lr: 0.000159 loss: 2.9900 (2.9243) grad_norm: 2.2896 (inf) time: 0.6294 [2021-03-28 01:39:34 swin_base_patch4_window7_224] INFO: Epoch: [223] [1150/1251] eta: 0:01:03 lr: 0.000159 loss: 2.9900 (2.9252) grad_norm: 2.2996 (inf) time: 0.6326 [2021-03-28 01:39:40 swin_base_patch4_window7_224] INFO: Epoch: [223] [1160/1251] eta: 0:00:57 lr: 0.000159 loss: 2.7714 (2.9236) grad_norm: 2.3665 (inf) time: 0.6325 [2021-03-28 01:39:47 swin_base_patch4_window7_224] INFO: Epoch: [223] [1170/1251] eta: 0:00:51 lr: 0.000159 loss: 2.7103 (2.9219) grad_norm: 2.3873 (inf) time: 0.6315 [2021-03-28 01:39:53 swin_base_patch4_window7_224] INFO: Epoch: [223] [1180/1251] eta: 0:00:44 lr: 0.000159 loss: 3.0599 (2.9226) grad_norm: 2.3873 (inf) time: 0.6286 [2021-03-28 01:39:59 swin_base_patch4_window7_224] INFO: Epoch: [223] [1190/1251] eta: 0:00:38 lr: 0.000159 loss: 3.0363 (2.9221) grad_norm: 2.4205 (inf) time: 0.6229 [2021-03-28 01:40:05 swin_base_patch4_window7_224] INFO: Epoch: [223] [1200/1251] eta: 0:00:32 lr: 0.000159 loss: 3.0131 (2.9217) grad_norm: 2.4721 (inf) time: 0.6232 [2021-03-28 01:40:12 swin_base_patch4_window7_224] INFO: Epoch: [223] [1210/1251] eta: 0:00:25 lr: 0.000159 loss: 3.0862 (2.9222) grad_norm: 2.4548 (inf) time: 0.6269 [2021-03-28 01:40:18 swin_base_patch4_window7_224] INFO: Epoch: [223] [1220/1251] eta: 0:00:19 lr: 0.000159 loss: 3.0862 (2.9235) grad_norm: 2.4072 (inf) time: 0.6282 [2021-03-28 01:40:24 swin_base_patch4_window7_224] INFO: Epoch: [223] [1230/1251] eta: 0:00:13 lr: 0.000159 loss: 3.0605 (2.9227) grad_norm: 2.3702 (inf) time: 0.6279 [2021-03-28 01:40:31 swin_base_patch4_window7_224] INFO: Epoch: [223] [1240/1251] eta: 0:00:06 lr: 0.000159 loss: 2.8023 (2.9219) grad_norm: 2.2094 (inf) time: 0.6294 [2021-03-28 01:40:37 swin_base_patch4_window7_224] INFO: Epoch: [223] [1250/1251] eta: 0:00:00 lr: 0.000159 loss: 2.9636 (2.9231) grad_norm: 2.2845 (inf) time: 0.6314 [2021-03-28 01:40:46 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:34 loss: 1.0147 (1.0147) acc1: 84.3750 (84.3750) acc5: 93.7500 (93.7500) [2021-03-28 01:40:48 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:13 loss: 0.8098 (0.7855) acc1: 81.2500 (81.9602) acc5: 95.3125 (95.8807) [2021-03-28 01:40:50 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7377 (0.7734) acc1: 81.2500 (82.2917) acc5: 95.3125 (95.9821) [2021-03-28 01:40:53 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7511 (0.7743) acc1: 81.2500 (82.2581) acc5: 96.8750 (96.2198) [2021-03-28 01:40:55 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7905 (0.7938) acc1: 81.2500 (81.7454) acc5: 95.3125 (95.8841) [2021-03-28 01:40:56 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7805 (0.7930) acc1: 79.6875 (81.5680) acc5: 95.3125 (95.9680) [2021-03-28 01:41:09 swin_base_patch4_window7_224] INFO: * Acc@1 81.892 Acc@5 96.060 loss 0.774 [2021-03-28 01:41:09 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.9% [2021-03-28 01:41:09 swin_base_patch4_window7_224] INFO: Max accuracy: 81.90% [2021-03-28 01:41:15 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 0/1251] eta: 1:53:17 lr: 0.000159 loss: 2.9641 (2.9641) grad_norm: 8.5186 (8.5186) time: 5.4334 [2021-03-28 01:41:21 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 10/1251] eta: 0:22:16 lr: 0.000159 loss: 2.9641 (2.8733) grad_norm: 2.5538 (3.1014) time: 1.0766 [2021-03-28 01:41:27 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 20/1251] eta: 0:17:46 lr: 0.000159 loss: 3.0173 (2.9568) grad_norm: 2.3037 (2.7416) time: 0.6377 [2021-03-28 01:41:34 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 30/1251] eta: 0:16:03 lr: 0.000159 loss: 3.1582 (2.9221) grad_norm: 2.2222 (2.5650) time: 0.6304 [2021-03-28 01:41:40 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 40/1251] eta: 0:15:05 lr: 0.000159 loss: 3.0203 (2.9253) grad_norm: 2.1731 (2.4822) time: 0.6229 [2021-03-28 01:41:46 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 50/1251] eta: 0:14:31 lr: 0.000159 loss: 3.1903 (2.9767) grad_norm: 2.2229 (2.4526) time: 0.6276 [2021-03-28 01:41:52 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 60/1251] eta: 0:14:06 lr: 0.000158 loss: 3.1519 (2.9801) grad_norm: 2.2015 (2.4163) time: 0.6343 [2021-03-28 01:41:59 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 70/1251] eta: 0:13:47 lr: 0.000158 loss: 3.0469 (2.9675) grad_norm: 2.2263 (2.4088) time: 0.6372 [2021-03-28 01:42:05 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 80/1251] eta: 0:13:30 lr: 0.000158 loss: 3.0469 (2.9926) grad_norm: 2.2817 (2.3903) time: 0.6380 [2021-03-28 01:42:12 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 90/1251] eta: 0:13:16 lr: 0.000158 loss: 3.0340 (2.9751) grad_norm: 2.2917 (2.3845) time: 0.6341 [2021-03-28 01:42:18 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 100/1251] eta: 0:13:03 lr: 0.000158 loss: 2.9638 (2.9786) grad_norm: 2.2891 (2.3744) time: 0.6333 [2021-03-28 01:42:24 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 110/1251] eta: 0:12:50 lr: 0.000158 loss: 3.1471 (2.9824) grad_norm: 2.3823 (2.3879) time: 0.6267 [2021-03-28 01:42:30 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 120/1251] eta: 0:12:39 lr: 0.000158 loss: 3.0264 (2.9808) grad_norm: 2.4400 (2.3916) time: 0.6274 [2021-03-28 01:42:37 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 130/1251] eta: 0:12:30 lr: 0.000158 loss: 3.0007 (2.9656) grad_norm: 2.2372 (2.3851) time: 0.6365 [2021-03-28 01:42:43 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 140/1251] eta: 0:12:21 lr: 0.000158 loss: 2.6646 (2.9434) grad_norm: 2.3543 (2.3893) time: 0.6372 [2021-03-28 01:42:49 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 150/1251] eta: 0:12:11 lr: 0.000158 loss: 2.8925 (2.9415) grad_norm: 2.4094 (2.3914) time: 0.6317 [2021-03-28 01:42:56 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 160/1251] eta: 0:12:02 lr: 0.000158 loss: 2.4983 (2.9143) grad_norm: 2.3127 (2.3853) time: 0.6291 [2021-03-28 01:43:02 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 170/1251] eta: 0:11:53 lr: 0.000158 loss: 2.8189 (2.9125) grad_norm: 2.3209 (2.3900) time: 0.6232 [2021-03-28 01:43:08 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 180/1251] eta: 0:11:44 lr: 0.000158 loss: 2.8946 (2.8918) grad_norm: 2.3209 (2.3925) time: 0.6242 [2021-03-28 01:43:14 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 190/1251] eta: 0:11:36 lr: 0.000158 loss: 2.8946 (2.8944) grad_norm: 2.3541 (2.3913) time: 0.6267 [2021-03-28 01:43:21 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 200/1251] eta: 0:11:28 lr: 0.000158 loss: 3.0800 (2.8980) grad_norm: 2.3307 (2.3863) time: 0.6250 [2021-03-28 01:43:27 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 210/1251] eta: 0:11:20 lr: 0.000158 loss: 3.1697 (2.9076) grad_norm: 2.2719 (2.3893) time: 0.6293 [2021-03-28 01:43:34 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 220/1251] eta: 0:11:13 lr: 0.000158 loss: 3.1383 (2.8998) grad_norm: 2.2221 (2.3874) time: 0.6378 [2021-03-28 01:43:40 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 230/1251] eta: 0:11:05 lr: 0.000158 loss: 2.7005 (2.9010) grad_norm: 2.2094 (2.3916) time: 0.6367 [2021-03-28 01:43:46 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 240/1251] eta: 0:10:58 lr: 0.000158 loss: 3.1564 (2.9064) grad_norm: 2.3992 (2.3902) time: 0.6286 [2021-03-28 01:43:52 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 250/1251] eta: 0:10:50 lr: 0.000158 loss: 3.0632 (2.9086) grad_norm: 2.3992 (2.3932) time: 0.6290 [2021-03-28 01:43:59 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 260/1251] eta: 0:10:43 lr: 0.000158 loss: 2.9464 (2.9075) grad_norm: 2.4528 (2.4032) time: 0.6239 [2021-03-28 01:44:05 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 270/1251] eta: 0:10:36 lr: 0.000158 loss: 3.0103 (2.9139) grad_norm: 2.4308 (2.4019) time: 0.6237 [2021-03-28 01:44:11 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 280/1251] eta: 0:10:28 lr: 0.000158 loss: 3.0553 (2.9184) grad_norm: 2.3199 (2.4050) time: 0.6252 [2021-03-28 01:44:17 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 290/1251] eta: 0:10:21 lr: 0.000158 loss: 3.0553 (2.9202) grad_norm: 2.4170 (2.4106) time: 0.6295 [2021-03-28 01:44:24 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 300/1251] eta: 0:10:14 lr: 0.000158 loss: 2.9921 (2.9187) grad_norm: 2.3746 (2.4058) time: 0.6291 [2021-03-28 01:44:30 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 310/1251] eta: 0:10:07 lr: 0.000158 loss: 3.0544 (2.9242) grad_norm: 2.1950 (2.4080) time: 0.6230 [2021-03-28 01:44:36 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 320/1251] eta: 0:10:00 lr: 0.000158 loss: 3.3290 (2.9372) grad_norm: 2.3369 (2.4077) time: 0.6270 [2021-03-28 01:44:42 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 330/1251] eta: 0:09:53 lr: 0.000158 loss: 3.1547 (2.9346) grad_norm: 2.3977 (2.4068) time: 0.6265 [2021-03-28 01:44:49 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 340/1251] eta: 0:09:46 lr: 0.000158 loss: 2.9156 (2.9302) grad_norm: 2.4092 (2.4127) time: 0.6244 [2021-03-28 01:44:55 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 350/1251] eta: 0:09:39 lr: 0.000158 loss: 2.6976 (2.9239) grad_norm: 2.3749 (2.4079) time: 0.6250 [2021-03-28 01:45:01 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 360/1251] eta: 0:09:32 lr: 0.000158 loss: 2.8596 (2.9241) grad_norm: 2.1657 (2.4055) time: 0.6236 [2021-03-28 01:45:07 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 370/1251] eta: 0:09:25 lr: 0.000158 loss: 2.9432 (2.9282) grad_norm: 2.2351 (2.4084) time: 0.6271 [2021-03-28 01:45:14 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 380/1251] eta: 0:09:19 lr: 0.000158 loss: 3.0424 (2.9237) grad_norm: 2.4804 (2.4144) time: 0.6330 [2021-03-28 01:45:20 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 390/1251] eta: 0:09:12 lr: 0.000158 loss: 2.9094 (2.9230) grad_norm: 2.4955 (2.4181) time: 0.6286 [2021-03-28 01:45:26 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 400/1251] eta: 0:09:05 lr: 0.000157 loss: 2.8195 (2.9211) grad_norm: 2.4442 (2.4187) time: 0.6276 [2021-03-28 01:45:33 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 410/1251] eta: 0:08:59 lr: 0.000157 loss: 2.7845 (2.9193) grad_norm: 2.4371 (2.4218) time: 0.6261 [2021-03-28 01:45:39 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 420/1251] eta: 0:08:52 lr: 0.000157 loss: 2.8811 (2.9209) grad_norm: 2.5456 (2.4362) time: 0.6265 [2021-03-28 01:45:45 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 430/1251] eta: 0:08:45 lr: 0.000157 loss: 2.8116 (2.9143) grad_norm: 2.2398 (2.4316) time: 0.6305 [2021-03-28 01:45:51 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 440/1251] eta: 0:08:39 lr: 0.000157 loss: 2.6631 (2.9160) grad_norm: 2.2398 (2.4292) time: 0.6253 [2021-03-28 01:45:58 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 450/1251] eta: 0:08:32 lr: 0.000157 loss: 3.2125 (2.9238) grad_norm: 2.3282 (2.4374) time: 0.6246 [2021-03-28 01:46:04 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 460/1251] eta: 0:08:25 lr: 0.000157 loss: 3.1413 (2.9285) grad_norm: 2.7709 (2.4621) time: 0.6283 [2021-03-28 01:46:10 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 470/1251] eta: 0:08:19 lr: 0.000157 loss: 3.1616 (2.9345) grad_norm: 2.6224 (2.4594) time: 0.6282 [2021-03-28 01:46:17 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 480/1251] eta: 0:08:12 lr: 0.000157 loss: 3.1616 (2.9319) grad_norm: 2.3543 (2.4620) time: 0.6246 [2021-03-28 01:46:23 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 490/1251] eta: 0:08:06 lr: 0.000157 loss: 2.8637 (2.9322) grad_norm: 2.3377 (2.4588) time: 0.6245 [2021-03-28 01:46:29 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 500/1251] eta: 0:07:59 lr: 0.000157 loss: 2.9903 (2.9347) grad_norm: 2.1849 (2.4543) time: 0.6258 [2021-03-28 01:46:35 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 510/1251] eta: 0:07:52 lr: 0.000157 loss: 3.0468 (2.9360) grad_norm: 2.3161 (2.4533) time: 0.6267 [2021-03-28 01:46:42 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 520/1251] eta: 0:07:46 lr: 0.000157 loss: 2.9122 (2.9360) grad_norm: 2.3161 (2.4537) time: 0.6293 [2021-03-28 01:46:48 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 530/1251] eta: 0:07:39 lr: 0.000157 loss: 2.8052 (2.9353) grad_norm: 2.2720 (2.4546) time: 0.6277 [2021-03-28 01:46:54 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 540/1251] eta: 0:07:33 lr: 0.000157 loss: 3.1183 (2.9388) grad_norm: 2.3272 (2.4521) time: 0.6244 [2021-03-28 01:47:00 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 550/1251] eta: 0:07:26 lr: 0.000157 loss: 3.1663 (2.9401) grad_norm: 2.3790 (2.4519) time: 0.6287 [2021-03-28 01:47:07 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 560/1251] eta: 0:07:20 lr: 0.000157 loss: 2.7374 (2.9351) grad_norm: 2.3906 (2.4566) time: 0.6334 [2021-03-28 01:47:13 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 570/1251] eta: 0:07:13 lr: 0.000157 loss: 2.9314 (2.9385) grad_norm: 2.2483 (2.4568) time: 0.6329 [2021-03-28 01:47:19 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 580/1251] eta: 0:07:07 lr: 0.000157 loss: 3.0209 (2.9376) grad_norm: 2.2884 (2.4554) time: 0.6264 [2021-03-28 01:47:26 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 590/1251] eta: 0:07:01 lr: 0.000157 loss: 2.9412 (2.9391) grad_norm: 2.2307 (2.4525) time: 0.6291 [2021-03-28 01:47:32 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 600/1251] eta: 0:06:54 lr: 0.000157 loss: 2.9853 (2.9379) grad_norm: 2.2906 (2.4516) time: 0.6358 [2021-03-28 01:47:38 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 610/1251] eta: 0:06:48 lr: 0.000157 loss: 2.8456 (2.9386) grad_norm: 2.3904 (2.4487) time: 0.6311 [2021-03-28 01:47:45 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 620/1251] eta: 0:06:41 lr: 0.000157 loss: 2.7847 (2.9323) grad_norm: 2.1263 (2.4430) time: 0.6277 [2021-03-28 01:47:51 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 630/1251] eta: 0:06:35 lr: 0.000157 loss: 2.9116 (2.9356) grad_norm: 2.1628 (2.4582) time: 0.6236 [2021-03-28 01:47:57 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 640/1251] eta: 0:06:28 lr: 0.000157 loss: 3.0334 (2.9347) grad_norm: 2.3074 (2.4568) time: 0.6231 [2021-03-28 01:48:03 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 650/1251] eta: 0:06:22 lr: 0.000157 loss: 2.9550 (2.9337) grad_norm: 2.3397 (2.4573) time: 0.6246 [2021-03-28 01:48:10 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 660/1251] eta: 0:06:15 lr: 0.000157 loss: 2.9638 (2.9333) grad_norm: 2.3716 (2.4582) time: 0.6244 [2021-03-28 01:48:16 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 670/1251] eta: 0:06:09 lr: 0.000157 loss: 3.1421 (2.9378) grad_norm: 2.3369 (2.4558) time: 0.6246 [2021-03-28 01:48:22 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 680/1251] eta: 0:06:02 lr: 0.000157 loss: 3.1911 (2.9383) grad_norm: 2.2439 (2.4550) time: 0.6244 [2021-03-28 01:48:28 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 690/1251] eta: 0:05:56 lr: 0.000157 loss: 3.3278 (2.9400) grad_norm: 2.2439 (2.4529) time: 0.6293 [2021-03-28 01:48:35 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 700/1251] eta: 0:05:50 lr: 0.000157 loss: 2.9761 (2.9373) grad_norm: 2.3972 (2.4563) time: 0.6311 [2021-03-28 01:48:41 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 710/1251] eta: 0:05:43 lr: 0.000157 loss: 2.9676 (2.9378) grad_norm: 2.3716 (2.4565) time: 0.6332 [2021-03-28 01:48:47 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 720/1251] eta: 0:05:37 lr: 0.000157 loss: 2.9794 (2.9382) grad_norm: 2.3385 (2.4547) time: 0.6292 [2021-03-28 01:48:54 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 730/1251] eta: 0:05:30 lr: 0.000157 loss: 2.8416 (2.9371) grad_norm: 2.2857 (2.4533) time: 0.6252 [2021-03-28 01:49:00 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 740/1251] eta: 0:05:24 lr: 0.000156 loss: 2.8416 (2.9366) grad_norm: 2.2857 (2.4520) time: 0.6309 [2021-03-28 01:49:06 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 750/1251] eta: 0:05:18 lr: 0.000156 loss: 2.8934 (2.9342) grad_norm: 2.4523 (2.4589) time: 0.6430 [2021-03-28 01:49:13 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 760/1251] eta: 0:05:12 lr: 0.000156 loss: 2.6518 (2.9307) grad_norm: 2.5564 (2.4580) time: 0.6508 [2021-03-28 01:49:19 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 770/1251] eta: 0:05:05 lr: 0.000156 loss: 2.6518 (2.9298) grad_norm: 2.4025 (2.4598) time: 0.6420 [2021-03-28 01:49:26 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 780/1251] eta: 0:04:59 lr: 0.000156 loss: 2.9069 (2.9286) grad_norm: 2.3893 (2.4593) time: 0.6346 [2021-03-28 01:49:32 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 790/1251] eta: 0:04:52 lr: 0.000156 loss: 2.9293 (2.9267) grad_norm: 2.2503 (2.4586) time: 0.6341 [2021-03-28 01:49:38 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 800/1251] eta: 0:04:46 lr: 0.000156 loss: 2.8175 (2.9250) grad_norm: 2.2767 (2.4597) time: 0.6293 [2021-03-28 01:49:45 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 810/1251] eta: 0:04:40 lr: 0.000156 loss: 2.9384 (2.9246) grad_norm: 2.4351 (2.4609) time: 0.6303 [2021-03-28 01:49:51 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 820/1251] eta: 0:04:33 lr: 0.000156 loss: 2.9486 (2.9228) grad_norm: 2.4050 (2.4589) time: 0.6369 [2021-03-28 01:49:57 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 830/1251] eta: 0:04:27 lr: 0.000156 loss: 3.0526 (2.9257) grad_norm: 2.2559 (2.4593) time: 0.6320 [2021-03-28 01:50:03 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 840/1251] eta: 0:04:21 lr: 0.000156 loss: 3.1220 (2.9268) grad_norm: 2.3080 (2.4600) time: 0.6246 [2021-03-28 01:50:10 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 850/1251] eta: 0:04:14 lr: 0.000156 loss: 3.0348 (2.9276) grad_norm: 2.2479 (2.4573) time: 0.6230 [2021-03-28 01:50:16 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 860/1251] eta: 0:04:08 lr: 0.000156 loss: 2.9454 (2.9279) grad_norm: 2.3322 (2.4610) time: 0.6231 [2021-03-28 01:50:22 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 870/1251] eta: 0:04:01 lr: 0.000156 loss: 3.0917 (2.9292) grad_norm: 2.5442 (2.4638) time: 0.6237 [2021-03-28 01:50:28 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 880/1251] eta: 0:03:55 lr: 0.000156 loss: 3.0884 (2.9309) grad_norm: 2.3386 (2.4623) time: 0.6254 [2021-03-28 01:50:35 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 890/1251] eta: 0:03:49 lr: 0.000156 loss: 3.0884 (2.9313) grad_norm: 2.4053 (2.4633) time: 0.6288 [2021-03-28 01:50:41 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 900/1251] eta: 0:03:42 lr: 0.000156 loss: 3.2007 (2.9331) grad_norm: 2.3627 (2.4609) time: 0.6368 [2021-03-28 01:50:47 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 910/1251] eta: 0:03:36 lr: 0.000156 loss: 3.0186 (2.9308) grad_norm: 2.3333 (2.4604) time: 0.6340 [2021-03-28 01:50:54 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 920/1251] eta: 0:03:29 lr: 0.000156 loss: 2.9685 (2.9324) grad_norm: 2.3505 (2.4616) time: 0.6217 [2021-03-28 01:51:00 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 930/1251] eta: 0:03:23 lr: 0.000156 loss: 2.9477 (2.9299) grad_norm: 2.3898 (2.4629) time: 0.6270 [2021-03-28 01:51:06 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 940/1251] eta: 0:03:17 lr: 0.000156 loss: 2.8439 (2.9297) grad_norm: 2.5183 (2.4623) time: 0.6312 [2021-03-28 01:51:13 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 950/1251] eta: 0:03:10 lr: 0.000156 loss: 3.0938 (2.9321) grad_norm: 2.4771 (2.4648) time: 0.6297 [2021-03-28 01:51:19 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 960/1251] eta: 0:03:04 lr: 0.000156 loss: 3.1600 (2.9329) grad_norm: 2.3487 (2.4630) time: 0.6269 [2021-03-28 01:51:25 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 970/1251] eta: 0:02:58 lr: 0.000156 loss: 2.9353 (2.9317) grad_norm: 2.3795 (2.4645) time: 0.6206 [2021-03-28 01:51:31 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 980/1251] eta: 0:02:51 lr: 0.000156 loss: 2.8676 (2.9319) grad_norm: 2.4920 (2.4636) time: 0.6221 [2021-03-28 01:51:37 swin_base_patch4_window7_224] INFO: Epoch: [224] [ 990/1251] eta: 0:02:45 lr: 0.000156 loss: 3.0543 (2.9341) grad_norm: 2.3062 (2.4632) time: 0.6231 [2021-03-28 01:51:44 swin_base_patch4_window7_224] INFO: Epoch: [224] [1000/1251] eta: 0:02:39 lr: 0.000156 loss: 3.0543 (2.9329) grad_norm: 2.3062 (2.4671) time: 0.6267 [2021-03-28 01:51:50 swin_base_patch4_window7_224] INFO: Epoch: [224] [1010/1251] eta: 0:02:32 lr: 0.000156 loss: 2.8063 (2.9320) grad_norm: 2.1958 (2.4655) time: 0.6314 [2021-03-28 01:51:56 swin_base_patch4_window7_224] INFO: Epoch: [224] [1020/1251] eta: 0:02:26 lr: 0.000156 loss: 2.9124 (2.9323) grad_norm: 2.1372 (2.4630) time: 0.6321 [2021-03-28 01:52:03 swin_base_patch4_window7_224] INFO: Epoch: [224] [1030/1251] eta: 0:02:20 lr: 0.000156 loss: 2.9998 (2.9315) grad_norm: 2.2508 (2.4630) time: 0.6270 [2021-03-28 01:52:09 swin_base_patch4_window7_224] INFO: Epoch: [224] [1040/1251] eta: 0:02:13 lr: 0.000156 loss: 2.7197 (2.9316) grad_norm: 2.4031 (2.4620) time: 0.6258 [2021-03-28 01:52:15 swin_base_patch4_window7_224] INFO: Epoch: [224] [1050/1251] eta: 0:02:07 lr: 0.000156 loss: 3.0602 (2.9330) grad_norm: 2.3802 (2.4625) time: 0.6278 [2021-03-28 01:52:21 swin_base_patch4_window7_224] INFO: Epoch: [224] [1060/1251] eta: 0:02:00 lr: 0.000156 loss: 3.0419 (2.9344) grad_norm: 2.1871 (2.4605) time: 0.6267 [2021-03-28 01:52:28 swin_base_patch4_window7_224] INFO: Epoch: [224] [1070/1251] eta: 0:01:54 lr: 0.000156 loss: 2.7948 (2.9308) grad_norm: 2.3286 (2.4615) time: 0.6280 [2021-03-28 01:52:34 swin_base_patch4_window7_224] INFO: Epoch: [224] [1080/1251] eta: 0:01:48 lr: 0.000155 loss: 2.7948 (2.9318) grad_norm: 2.3318 (2.4601) time: 0.6247 [2021-03-28 01:52:40 swin_base_patch4_window7_224] INFO: Epoch: [224] [1090/1251] eta: 0:01:41 lr: 0.000155 loss: 3.0829 (2.9295) grad_norm: 2.3092 (2.4597) time: 0.6216 [2021-03-28 01:52:46 swin_base_patch4_window7_224] INFO: Epoch: [224] [1100/1251] eta: 0:01:35 lr: 0.000155 loss: 2.8432 (2.9300) grad_norm: 2.3544 (2.4595) time: 0.6255 [2021-03-28 01:52:53 swin_base_patch4_window7_224] INFO: Epoch: [224] [1110/1251] eta: 0:01:29 lr: 0.000155 loss: 3.0337 (2.9297) grad_norm: 2.3544 (2.4583) time: 0.6256 [2021-03-28 01:52:59 swin_base_patch4_window7_224] INFO: Epoch: [224] [1120/1251] eta: 0:01:22 lr: 0.000155 loss: 2.7012 (2.9282) grad_norm: 2.4052 (2.4590) time: 0.6246 [2021-03-28 01:53:05 swin_base_patch4_window7_224] INFO: Epoch: [224] [1130/1251] eta: 0:01:16 lr: 0.000155 loss: 2.7012 (2.9272) grad_norm: 2.3065 (2.4577) time: 0.6239 [2021-03-28 01:53:11 swin_base_patch4_window7_224] INFO: Epoch: [224] [1140/1251] eta: 0:01:10 lr: 0.000155 loss: 2.9266 (2.9278) grad_norm: 2.2479 (2.4581) time: 0.6251 [2021-03-28 01:53:18 swin_base_patch4_window7_224] INFO: Epoch: [224] [1150/1251] eta: 0:01:03 lr: 0.000155 loss: 2.9832 (2.9293) grad_norm: 2.4302 (2.4599) time: 0.6286 [2021-03-28 01:53:24 swin_base_patch4_window7_224] INFO: Epoch: [224] [1160/1251] eta: 0:00:57 lr: 0.000155 loss: 3.1377 (2.9290) grad_norm: 2.4626 (2.4603) time: 0.6342 [2021-03-28 01:53:30 swin_base_patch4_window7_224] INFO: Epoch: [224] [1170/1251] eta: 0:00:51 lr: 0.000155 loss: 3.0486 (2.9307) grad_norm: 2.4799 (2.4603) time: 0.6345 [2021-03-28 01:53:37 swin_base_patch4_window7_224] INFO: Epoch: [224] [1180/1251] eta: 0:00:44 lr: 0.000155 loss: 3.0057 (2.9305) grad_norm: 2.3093 (2.4583) time: 0.6256 [2021-03-28 01:53:43 swin_base_patch4_window7_224] INFO: Epoch: [224] [1190/1251] eta: 0:00:38 lr: 0.000155 loss: 2.8123 (2.9288) grad_norm: 2.2881 (2.4581) time: 0.6235 [2021-03-28 01:53:49 swin_base_patch4_window7_224] INFO: Epoch: [224] [1200/1251] eta: 0:00:32 lr: 0.000155 loss: 2.8791 (2.9292) grad_norm: 2.3984 (2.4586) time: 0.6244 [2021-03-28 01:53:55 swin_base_patch4_window7_224] INFO: Epoch: [224] [1210/1251] eta: 0:00:25 lr: 0.000155 loss: 3.0508 (2.9302) grad_norm: 2.3984 (2.4587) time: 0.6213 [2021-03-28 01:54:02 swin_base_patch4_window7_224] INFO: Epoch: [224] [1220/1251] eta: 0:00:19 lr: 0.000155 loss: 3.0142 (2.9293) grad_norm: 2.4165 (2.4595) time: 0.6215 [2021-03-28 01:54:08 swin_base_patch4_window7_224] INFO: Epoch: [224] [1230/1251] eta: 0:00:13 lr: 0.000155 loss: 2.8739 (2.9284) grad_norm: 2.5210 (2.4602) time: 0.6251 [2021-03-28 01:54:14 swin_base_patch4_window7_224] INFO: Epoch: [224] [1240/1251] eta: 0:00:06 lr: 0.000155 loss: 2.9122 (2.9293) grad_norm: 2.3727 (2.4596) time: 0.6254 [2021-03-28 01:54:20 swin_base_patch4_window7_224] INFO: Epoch: [224] [1250/1251] eta: 0:00:00 lr: 0.000155 loss: 2.9662 (2.9272) grad_norm: 2.3419 (2.4594) time: 0.6246 [2021-03-28 01:54:34 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:47 loss: 0.7026 (0.7026) acc1: 84.3750 (84.3750) acc5: 96.8750 (96.8750) [2021-03-28 01:54:37 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7330 (0.8071) acc1: 81.2500 (80.6818) acc5: 95.3125 (95.8807) [2021-03-28 01:54:40 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7706 (0.7986) acc1: 81.2500 (80.7292) acc5: 96.8750 (96.3542) [2021-03-28 01:54:42 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7452 (0.7980) acc1: 81.2500 (81.1996) acc5: 96.8750 (95.8669) [2021-03-28 01:54:44 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7443 (0.7967) acc1: 82.8125 (81.2500) acc5: 95.3125 (95.6174) [2021-03-28 01:54:45 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7443 (0.7925) acc1: 79.6875 (80.9920) acc5: 96.8750 (95.8400) [2021-03-28 01:54:56 swin_base_patch4_window7_224] INFO: * Acc@1 82.082 Acc@5 96.090 loss 0.779 [2021-03-28 01:54:56 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.1% [2021-03-28 01:54:56 swin_base_patch4_window7_224] INFO: Max accuracy: 82.08% [2021-03-28 01:55:02 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 0/1251] eta: 1:48:25 lr: 0.000155 loss: 2.1097 (2.1097) grad_norm: 2.4234 (2.4234) time: 5.1999 [2021-03-28 01:55:08 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 10/1251] eta: 0:21:35 lr: 0.000155 loss: 2.8949 (2.7934) grad_norm: 2.5304 (2.6365) time: 1.0440 [2021-03-28 01:55:14 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 20/1251] eta: 0:17:18 lr: 0.000155 loss: 2.7776 (2.7345) grad_norm: 2.5304 (2.8281) time: 0.6262 [2021-03-28 01:55:20 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 30/1251] eta: 0:15:43 lr: 0.000155 loss: 2.6968 (2.7115) grad_norm: 2.3790 (2.7235) time: 0.6235 [2021-03-28 01:55:27 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 40/1251] eta: 0:14:56 lr: 0.000155 loss: 2.6353 (2.6949) grad_norm: 2.3915 (2.6817) time: 0.6317 [2021-03-28 01:55:33 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 50/1251] eta: 0:14:25 lr: 0.000155 loss: 2.8744 (2.7300) grad_norm: 2.4859 (2.6939) time: 0.6393 [2021-03-28 01:55:40 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 60/1251] eta: 0:14:02 lr: 0.000155 loss: 3.0871 (2.8084) grad_norm: 2.5279 (2.6767) time: 0.6390 [2021-03-28 01:55:46 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 70/1251] eta: 0:13:44 lr: 0.000155 loss: 2.9086 (2.7886) grad_norm: 2.4624 (2.6410) time: 0.6408 [2021-03-28 01:55:52 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 80/1251] eta: 0:13:28 lr: 0.000155 loss: 2.6694 (2.7782) grad_norm: 2.3294 (2.6355) time: 0.6388 [2021-03-28 01:55:59 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 90/1251] eta: 0:13:14 lr: 0.000155 loss: 2.8595 (2.7986) grad_norm: 2.5338 (2.6338) time: 0.6341 [2021-03-28 01:56:05 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 100/1251] eta: 0:13:01 lr: 0.000155 loss: 2.9091 (2.8132) grad_norm: 2.4129 (2.6146) time: 0.6346 [2021-03-28 01:56:11 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 110/1251] eta: 0:12:51 lr: 0.000155 loss: 2.9659 (2.8200) grad_norm: 2.3819 (2.6086) time: 0.6392 [2021-03-28 01:56:18 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 120/1251] eta: 0:12:39 lr: 0.000155 loss: 2.8653 (2.8259) grad_norm: 2.4605 (2.6199) time: 0.6332 [2021-03-28 01:56:24 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 130/1251] eta: 0:12:28 lr: 0.000155 loss: 2.7802 (2.8263) grad_norm: 2.5474 (2.6349) time: 0.6247 [2021-03-28 01:56:30 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 140/1251] eta: 0:12:19 lr: 0.000155 loss: 2.9193 (2.8276) grad_norm: 2.3966 (2.6341) time: 0.6287 [2021-03-28 01:56:37 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 150/1251] eta: 0:12:09 lr: 0.000155 loss: 2.8943 (2.8306) grad_norm: 2.4097 (2.6199) time: 0.6279 [2021-03-28 01:56:43 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 160/1251] eta: 0:12:00 lr: 0.000155 loss: 2.8401 (2.8197) grad_norm: 2.4567 (2.6336) time: 0.6259 [2021-03-28 01:56:49 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 170/1251] eta: 0:11:52 lr: 0.000154 loss: 2.8665 (2.8255) grad_norm: 2.2265 (2.6092) time: 0.6294 [2021-03-28 01:56:55 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 180/1251] eta: 0:11:43 lr: 0.000154 loss: 2.9294 (2.8221) grad_norm: 2.2914 (2.6034) time: 0.6294 [2021-03-28 01:57:02 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 190/1251] eta: 0:11:35 lr: 0.000154 loss: 2.9294 (2.8237) grad_norm: 2.3676 (2.5907) time: 0.6278 [2021-03-28 01:57:08 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 200/1251] eta: 0:11:27 lr: 0.000154 loss: 3.0359 (2.8354) grad_norm: 2.3676 (2.5928) time: 0.6293 [2021-03-28 01:57:14 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 210/1251] eta: 0:11:20 lr: 0.000154 loss: 3.0712 (2.8433) grad_norm: 2.4985 (2.5912) time: 0.6360 [2021-03-28 01:57:21 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 220/1251] eta: 0:11:12 lr: 0.000154 loss: 3.0712 (2.8464) grad_norm: 2.4428 (inf) time: 0.6301 [2021-03-28 01:57:27 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 230/1251] eta: 0:11:04 lr: 0.000154 loss: 3.0541 (2.8521) grad_norm: 2.2137 (inf) time: 0.6213 [2021-03-28 01:57:33 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 240/1251] eta: 0:10:57 lr: 0.000154 loss: 3.0621 (2.8595) grad_norm: 2.2517 (inf) time: 0.6247 [2021-03-28 01:57:39 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 250/1251] eta: 0:10:49 lr: 0.000154 loss: 2.8601 (2.8637) grad_norm: 2.3195 (inf) time: 0.6289 [2021-03-28 01:57:46 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 260/1251] eta: 0:10:42 lr: 0.000154 loss: 2.8737 (2.8684) grad_norm: 2.3195 (inf) time: 0.6316 [2021-03-28 01:57:52 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 270/1251] eta: 0:10:35 lr: 0.000154 loss: 3.0345 (2.8669) grad_norm: 2.3547 (inf) time: 0.6325 [2021-03-28 01:57:58 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 280/1251] eta: 0:10:28 lr: 0.000154 loss: 2.8591 (2.8594) grad_norm: 2.4291 (inf) time: 0.6299 [2021-03-28 01:58:05 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 290/1251] eta: 0:10:21 lr: 0.000154 loss: 2.8374 (2.8553) grad_norm: 2.3220 (inf) time: 0.6271 [2021-03-28 01:58:11 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 300/1251] eta: 0:10:14 lr: 0.000154 loss: 2.7089 (2.8533) grad_norm: 2.2575 (inf) time: 0.6261 [2021-03-28 01:58:17 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 310/1251] eta: 0:10:07 lr: 0.000154 loss: 2.6978 (2.8435) grad_norm: 2.2477 (inf) time: 0.6292 [2021-03-28 01:58:23 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 320/1251] eta: 0:10:00 lr: 0.000154 loss: 2.7427 (2.8449) grad_norm: 2.4386 (inf) time: 0.6279 [2021-03-28 01:58:30 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 330/1251] eta: 0:09:53 lr: 0.000154 loss: 2.8027 (2.8414) grad_norm: 2.4386 (inf) time: 0.6258 [2021-03-28 01:58:36 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 340/1251] eta: 0:09:46 lr: 0.000154 loss: 2.7156 (2.8361) grad_norm: 2.3533 (inf) time: 0.6259 [2021-03-28 01:58:42 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 350/1251] eta: 0:09:39 lr: 0.000154 loss: 2.9512 (2.8378) grad_norm: 2.3125 (inf) time: 0.6288 [2021-03-28 01:58:49 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 360/1251] eta: 0:09:32 lr: 0.000154 loss: 2.9240 (2.8377) grad_norm: 2.3125 (inf) time: 0.6347 [2021-03-28 01:58:55 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 370/1251] eta: 0:09:26 lr: 0.000154 loss: 2.8763 (2.8317) grad_norm: 2.4399 (inf) time: 0.6309 [2021-03-28 01:59:01 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 380/1251] eta: 0:09:19 lr: 0.000154 loss: 2.9269 (2.8370) grad_norm: 2.3790 (inf) time: 0.6305 [2021-03-28 01:59:08 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 390/1251] eta: 0:09:12 lr: 0.000154 loss: 3.1412 (2.8425) grad_norm: 2.3790 (inf) time: 0.6301 [2021-03-28 01:59:14 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 400/1251] eta: 0:09:06 lr: 0.000154 loss: 3.1412 (2.8417) grad_norm: 2.3980 (inf) time: 0.6297 [2021-03-28 01:59:20 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 410/1251] eta: 0:08:59 lr: 0.000154 loss: 2.9584 (2.8424) grad_norm: 2.3320 (inf) time: 0.6310 [2021-03-28 01:59:26 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 420/1251] eta: 0:08:52 lr: 0.000154 loss: 2.9851 (2.8471) grad_norm: 2.4052 (inf) time: 0.6260 [2021-03-28 01:59:33 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 430/1251] eta: 0:08:46 lr: 0.000154 loss: 3.0242 (2.8520) grad_norm: 2.4052 (inf) time: 0.6307 [2021-03-28 01:59:39 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 440/1251] eta: 0:08:39 lr: 0.000154 loss: 3.0508 (2.8554) grad_norm: 2.3676 (inf) time: 0.6393 [2021-03-28 01:59:45 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 450/1251] eta: 0:08:33 lr: 0.000154 loss: 3.0096 (2.8547) grad_norm: 2.2701 (inf) time: 0.6314 [2021-03-28 01:59:52 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 460/1251] eta: 0:08:26 lr: 0.000154 loss: 2.9450 (2.8579) grad_norm: 2.3708 (inf) time: 0.6244 [2021-03-28 01:59:58 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 470/1251] eta: 0:08:20 lr: 0.000154 loss: 2.8986 (2.8561) grad_norm: 2.2888 (inf) time: 0.6323 [2021-03-28 02:00:04 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 480/1251] eta: 0:08:13 lr: 0.000154 loss: 2.7338 (2.8568) grad_norm: 2.2112 (inf) time: 0.6351 [2021-03-28 02:00:11 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 490/1251] eta: 0:08:06 lr: 0.000154 loss: 2.9258 (2.8574) grad_norm: 2.3037 (inf) time: 0.6277 [2021-03-28 02:00:17 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 500/1251] eta: 0:08:00 lr: 0.000154 loss: 2.9258 (2.8561) grad_norm: 2.3024 (inf) time: 0.6251 [2021-03-28 02:00:23 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 510/1251] eta: 0:07:53 lr: 0.000153 loss: 2.9742 (2.8541) grad_norm: 2.2982 (inf) time: 0.6274 [2021-03-28 02:00:29 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 520/1251] eta: 0:07:47 lr: 0.000153 loss: 2.9584 (2.8574) grad_norm: 2.4988 (inf) time: 0.6273 [2021-03-28 02:00:36 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 530/1251] eta: 0:07:40 lr: 0.000153 loss: 2.9216 (2.8561) grad_norm: 2.4371 (inf) time: 0.6273 [2021-03-28 02:00:42 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 540/1251] eta: 0:07:34 lr: 0.000153 loss: 2.7687 (2.8535) grad_norm: 2.3454 (inf) time: 0.6313 [2021-03-28 02:00:49 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 550/1251] eta: 0:07:27 lr: 0.000153 loss: 3.0004 (2.8569) grad_norm: 2.3480 (inf) time: 0.6451 [2021-03-28 02:00:55 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 560/1251] eta: 0:07:21 lr: 0.000153 loss: 3.0004 (2.8576) grad_norm: 2.3201 (inf) time: 0.6422 [2021-03-28 02:01:01 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 570/1251] eta: 0:07:14 lr: 0.000153 loss: 2.9996 (2.8594) grad_norm: 2.3201 (inf) time: 0.6274 [2021-03-28 02:01:07 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 580/1251] eta: 0:07:08 lr: 0.000153 loss: 2.9396 (2.8589) grad_norm: 2.2705 (inf) time: 0.6272 [2021-03-28 02:01:14 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 590/1251] eta: 0:07:02 lr: 0.000153 loss: 2.8671 (2.8597) grad_norm: 2.2636 (inf) time: 0.6378 [2021-03-28 02:01:20 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 600/1251] eta: 0:06:55 lr: 0.000153 loss: 2.8671 (2.8583) grad_norm: 2.2850 (inf) time: 0.6376 [2021-03-28 02:01:26 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 610/1251] eta: 0:06:49 lr: 0.000153 loss: 2.9168 (2.8602) grad_norm: 2.2398 (inf) time: 0.6249 [2021-03-28 02:01:33 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 620/1251] eta: 0:06:42 lr: 0.000153 loss: 3.0534 (2.8607) grad_norm: 2.2398 (inf) time: 0.6246 [2021-03-28 02:01:39 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 630/1251] eta: 0:06:36 lr: 0.000153 loss: 3.1204 (2.8617) grad_norm: 2.1073 (inf) time: 0.6345 [2021-03-28 02:01:45 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 640/1251] eta: 0:06:29 lr: 0.000153 loss: 3.1637 (2.8638) grad_norm: 2.2089 (inf) time: 0.6358 [2021-03-28 02:01:52 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 650/1251] eta: 0:06:23 lr: 0.000153 loss: 3.0694 (2.8631) grad_norm: 2.3255 (inf) time: 0.6296 [2021-03-28 02:01:58 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 660/1251] eta: 0:06:16 lr: 0.000153 loss: 2.9470 (2.8640) grad_norm: 2.3444 (inf) time: 0.6300 [2021-03-28 02:02:04 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 670/1251] eta: 0:06:10 lr: 0.000153 loss: 2.9641 (2.8666) grad_norm: 2.3249 (inf) time: 0.6254 [2021-03-28 02:02:11 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 680/1251] eta: 0:06:03 lr: 0.000153 loss: 3.1207 (2.8680) grad_norm: 2.3561 (inf) time: 0.6269 [2021-03-28 02:02:17 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 690/1251] eta: 0:05:57 lr: 0.000153 loss: 3.1207 (2.8717) grad_norm: 2.3464 (inf) time: 0.6273 [2021-03-28 02:02:23 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 700/1251] eta: 0:05:50 lr: 0.000153 loss: 3.1201 (2.8702) grad_norm: 2.2633 (inf) time: 0.6235 [2021-03-28 02:02:29 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 710/1251] eta: 0:05:44 lr: 0.000153 loss: 3.0011 (2.8724) grad_norm: 2.4119 (inf) time: 0.6250 [2021-03-28 02:02:36 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 720/1251] eta: 0:05:38 lr: 0.000153 loss: 3.0251 (2.8750) grad_norm: 2.4383 (inf) time: 0.6269 [2021-03-28 02:02:42 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 730/1251] eta: 0:05:31 lr: 0.000153 loss: 2.8764 (2.8734) grad_norm: 2.3076 (inf) time: 0.6286 [2021-03-28 02:02:48 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 740/1251] eta: 0:05:25 lr: 0.000153 loss: 2.8224 (2.8740) grad_norm: 2.1553 (inf) time: 0.6339 [2021-03-28 02:02:55 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 750/1251] eta: 0:05:18 lr: 0.000153 loss: 2.9163 (2.8753) grad_norm: 2.1738 (inf) time: 0.6434 [2021-03-28 02:03:01 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 760/1251] eta: 0:05:12 lr: 0.000153 loss: 3.0031 (2.8740) grad_norm: 2.2549 (inf) time: 0.6353 [2021-03-28 02:03:07 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 770/1251] eta: 0:05:06 lr: 0.000153 loss: 2.6426 (2.8708) grad_norm: 2.2769 (inf) time: 0.6266 [2021-03-28 02:03:14 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 780/1251] eta: 0:04:59 lr: 0.000153 loss: 2.6116 (2.8694) grad_norm: 2.3218 (inf) time: 0.6301 [2021-03-28 02:03:20 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 790/1251] eta: 0:04:53 lr: 0.000153 loss: 2.9677 (2.8703) grad_norm: 2.2076 (inf) time: 0.6367 [2021-03-28 02:03:26 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 800/1251] eta: 0:04:47 lr: 0.000153 loss: 3.1185 (2.8727) grad_norm: 2.2188 (inf) time: 0.6394 [2021-03-28 02:03:33 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 810/1251] eta: 0:04:40 lr: 0.000153 loss: 3.1732 (2.8766) grad_norm: 2.4077 (inf) time: 0.6299 [2021-03-28 02:03:39 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 820/1251] eta: 0:04:34 lr: 0.000153 loss: 2.9691 (2.8743) grad_norm: 2.5256 (inf) time: 0.6283 [2021-03-28 02:03:45 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 830/1251] eta: 0:04:27 lr: 0.000153 loss: 2.8667 (2.8738) grad_norm: 2.4309 (inf) time: 0.6322 [2021-03-28 02:03:52 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 840/1251] eta: 0:04:21 lr: 0.000153 loss: 2.9078 (2.8752) grad_norm: 2.3117 (inf) time: 0.6337 [2021-03-28 02:03:58 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 850/1251] eta: 0:04:15 lr: 0.000153 loss: 3.0765 (2.8780) grad_norm: 2.2909 (inf) time: 0.6299 [2021-03-28 02:04:04 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 860/1251] eta: 0:04:08 lr: 0.000152 loss: 3.0765 (2.8776) grad_norm: 2.2909 (inf) time: 0.6274 [2021-03-28 02:04:10 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 870/1251] eta: 0:04:02 lr: 0.000152 loss: 2.9028 (2.8782) grad_norm: 2.1862 (inf) time: 0.6275 [2021-03-28 02:04:17 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 880/1251] eta: 0:03:55 lr: 0.000152 loss: 2.8679 (2.8786) grad_norm: 2.1413 (inf) time: 0.6282 [2021-03-28 02:04:23 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 890/1251] eta: 0:03:49 lr: 0.000152 loss: 2.7525 (2.8764) grad_norm: 2.3501 (inf) time: 0.6362 [2021-03-28 02:04:29 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 900/1251] eta: 0:03:43 lr: 0.000152 loss: 2.7525 (2.8761) grad_norm: 2.3408 (inf) time: 0.6323 [2021-03-28 02:04:36 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 910/1251] eta: 0:03:36 lr: 0.000152 loss: 2.9219 (2.8789) grad_norm: 2.3516 (inf) time: 0.6263 [2021-03-28 02:04:42 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 920/1251] eta: 0:03:30 lr: 0.000152 loss: 2.9456 (2.8800) grad_norm: 2.3762 (inf) time: 0.6319 [2021-03-28 02:04:48 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 930/1251] eta: 0:03:24 lr: 0.000152 loss: 3.0262 (2.8824) grad_norm: 2.2147 (inf) time: 0.6333 [2021-03-28 02:04:55 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 940/1251] eta: 0:03:17 lr: 0.000152 loss: 3.1546 (2.8830) grad_norm: 2.1560 (inf) time: 0.6325 [2021-03-28 02:05:01 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 950/1251] eta: 0:03:11 lr: 0.000152 loss: 2.9782 (2.8842) grad_norm: 2.3068 (inf) time: 0.6315 [2021-03-28 02:05:07 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 960/1251] eta: 0:03:04 lr: 0.000152 loss: 2.8369 (2.8820) grad_norm: 2.4057 (inf) time: 0.6301 [2021-03-28 02:05:14 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 970/1251] eta: 0:02:58 lr: 0.000152 loss: 2.7657 (2.8821) grad_norm: 2.4057 (inf) time: 0.6304 [2021-03-28 02:05:20 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 980/1251] eta: 0:02:52 lr: 0.000152 loss: 3.0527 (2.8833) grad_norm: 2.2437 (inf) time: 0.6307 [2021-03-28 02:05:26 swin_base_patch4_window7_224] INFO: Epoch: [225] [ 990/1251] eta: 0:02:45 lr: 0.000152 loss: 2.9045 (2.8833) grad_norm: 2.2658 (inf) time: 0.6359 [2021-03-28 02:05:33 swin_base_patch4_window7_224] INFO: Epoch: [225] [1000/1251] eta: 0:02:39 lr: 0.000152 loss: 2.8706 (2.8846) grad_norm: 2.2658 (inf) time: 0.6325 [2021-03-28 02:05:39 swin_base_patch4_window7_224] INFO: Epoch: [225] [1010/1251] eta: 0:02:33 lr: 0.000152 loss: 2.9559 (2.8853) grad_norm: 2.1854 (inf) time: 0.6239 [2021-03-28 02:05:45 swin_base_patch4_window7_224] INFO: Epoch: [225] [1020/1251] eta: 0:02:26 lr: 0.000152 loss: 2.9916 (2.8873) grad_norm: 2.2514 (inf) time: 0.6290 [2021-03-28 02:05:51 swin_base_patch4_window7_224] INFO: Epoch: [225] [1030/1251] eta: 0:02:20 lr: 0.000152 loss: 2.9916 (2.8878) grad_norm: 2.3513 (inf) time: 0.6340 [2021-03-28 02:05:58 swin_base_patch4_window7_224] INFO: Epoch: [225] [1040/1251] eta: 0:02:13 lr: 0.000152 loss: 2.8836 (2.8889) grad_norm: 2.3459 (inf) time: 0.6270 [2021-03-28 02:06:04 swin_base_patch4_window7_224] INFO: Epoch: [225] [1050/1251] eta: 0:02:07 lr: 0.000152 loss: 3.1461 (2.8898) grad_norm: 2.2791 (inf) time: 0.6235 [2021-03-28 02:06:10 swin_base_patch4_window7_224] INFO: Epoch: [225] [1060/1251] eta: 0:02:01 lr: 0.000152 loss: 3.0379 (2.8893) grad_norm: 2.2458 (inf) time: 0.6254 [2021-03-28 02:06:16 swin_base_patch4_window7_224] INFO: Epoch: [225] [1070/1251] eta: 0:01:54 lr: 0.000152 loss: 3.0379 (2.8907) grad_norm: 2.3814 (inf) time: 0.6279 [2021-03-28 02:06:23 swin_base_patch4_window7_224] INFO: Epoch: [225] [1080/1251] eta: 0:01:48 lr: 0.000152 loss: 3.1425 (2.8931) grad_norm: 2.4089 (inf) time: 0.6297 [2021-03-28 02:06:29 swin_base_patch4_window7_224] INFO: Epoch: [225] [1090/1251] eta: 0:01:42 lr: 0.000152 loss: 3.1013 (2.8938) grad_norm: 2.4830 (inf) time: 0.6269 [2021-03-28 02:06:35 swin_base_patch4_window7_224] INFO: Epoch: [225] [1100/1251] eta: 0:01:35 lr: 0.000152 loss: 2.9430 (2.8946) grad_norm: 2.5292 (inf) time: 0.6233 [2021-03-28 02:06:42 swin_base_patch4_window7_224] INFO: Epoch: [225] [1110/1251] eta: 0:01:29 lr: 0.000152 loss: 2.8252 (2.8948) grad_norm: 2.4823 (inf) time: 0.6257 [2021-03-28 02:06:48 swin_base_patch4_window7_224] INFO: Epoch: [225] [1120/1251] eta: 0:01:23 lr: 0.000152 loss: 2.6540 (2.8935) grad_norm: 2.3175 (inf) time: 0.6267 [2021-03-28 02:06:54 swin_base_patch4_window7_224] INFO: Epoch: [225] [1130/1251] eta: 0:01:16 lr: 0.000152 loss: 2.6144 (2.8926) grad_norm: 2.4445 (inf) time: 0.6228 [2021-03-28 02:07:00 swin_base_patch4_window7_224] INFO: Epoch: [225] [1140/1251] eta: 0:01:10 lr: 0.000152 loss: 2.9557 (2.8913) grad_norm: 2.4445 (inf) time: 0.6254 [2021-03-28 02:07:07 swin_base_patch4_window7_224] INFO: Epoch: [225] [1150/1251] eta: 0:01:04 lr: 0.000152 loss: 2.9714 (2.8927) grad_norm: 2.2804 (inf) time: 0.6298 [2021-03-28 02:07:13 swin_base_patch4_window7_224] INFO: Epoch: [225] [1160/1251] eta: 0:00:57 lr: 0.000152 loss: 3.0341 (2.8942) grad_norm: 2.3167 (inf) time: 0.6368 [2021-03-28 02:07:19 swin_base_patch4_window7_224] INFO: Epoch: [225] [1170/1251] eta: 0:00:51 lr: 0.000152 loss: 3.0572 (2.8939) grad_norm: 2.3642 (inf) time: 0.6320 [2021-03-28 02:07:26 swin_base_patch4_window7_224] INFO: Epoch: [225] [1180/1251] eta: 0:00:45 lr: 0.000152 loss: 2.8465 (2.8952) grad_norm: 2.3636 (inf) time: 0.6264 [2021-03-28 02:07:32 swin_base_patch4_window7_224] INFO: Epoch: [225] [1190/1251] eta: 0:00:38 lr: 0.000152 loss: 2.8465 (2.8946) grad_norm: 2.3972 (inf) time: 0.6271 [2021-03-28 02:07:38 swin_base_patch4_window7_224] INFO: Epoch: [225] [1200/1251] eta: 0:00:32 lr: 0.000151 loss: 2.7310 (2.8940) grad_norm: 2.5184 (inf) time: 0.6257 [2021-03-28 02:07:44 swin_base_patch4_window7_224] INFO: Epoch: [225] [1210/1251] eta: 0:00:25 lr: 0.000151 loss: 2.8281 (2.8926) grad_norm: 2.3422 (inf) time: 0.6266 [2021-03-28 02:07:51 swin_base_patch4_window7_224] INFO: Epoch: [225] [1220/1251] eta: 0:00:19 lr: 0.000151 loss: 2.9346 (2.8938) grad_norm: 2.3422 (inf) time: 0.6288 [2021-03-28 02:07:57 swin_base_patch4_window7_224] INFO: Epoch: [225] [1230/1251] eta: 0:00:13 lr: 0.000151 loss: 2.9049 (2.8931) grad_norm: 2.2117 (inf) time: 0.6293 [2021-03-28 02:08:03 swin_base_patch4_window7_224] INFO: Epoch: [225] [1240/1251] eta: 0:00:06 lr: 0.000151 loss: 2.9080 (2.8943) grad_norm: 2.2117 (inf) time: 0.6208 [2021-03-28 02:08:09 swin_base_patch4_window7_224] INFO: Epoch: [225] [1250/1251] eta: 0:00:00 lr: 0.000151 loss: 3.0286 (2.8954) grad_norm: 2.3151 (inf) time: 0.6174 [2021-03-28 02:09:31 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:10 loss: 0.8466 (0.8466) acc1: 78.1250 (78.1250) acc5: 95.3125 (95.3125) [2021-03-28 02:09:32 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.7421 (0.7857) acc1: 82.8125 (81.1080) acc5: 96.8750 (96.7330) [2021-03-28 02:09:34 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7421 (0.7874) acc1: 81.2500 (80.9524) acc5: 96.8750 (96.4286) [2021-03-28 02:09:35 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8148 (0.8232) acc1: 79.6875 (80.1915) acc5: 95.3125 (96.2702) [2021-03-28 02:09:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7899 (0.7962) acc1: 81.2500 (80.9451) acc5: 96.8750 (96.1890) [2021-03-28 02:09:38 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7743 (0.8034) acc1: 81.2500 (80.9600) acc5: 96.2264 (96.0640) [2021-03-28 02:09:53 swin_base_patch4_window7_224] INFO: * Acc@1 81.998 Acc@5 96.018 loss 0.792 [2021-03-28 02:09:53 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.0% [2021-03-28 02:09:53 swin_base_patch4_window7_224] INFO: Max accuracy: 82.08% [2021-03-28 02:09:57 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 0/1251] eta: 1:38:21 lr: 0.000151 loss: 3.1479 (3.1479) grad_norm: 2.4543 (2.4543) time: 4.7173 [2021-03-28 02:10:04 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 10/1251] eta: 0:20:47 lr: 0.000151 loss: 3.1479 (2.9303) grad_norm: 2.4543 (2.5111) time: 1.0053 [2021-03-28 02:10:10 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 20/1251] eta: 0:16:51 lr: 0.000151 loss: 2.6598 (2.7676) grad_norm: 2.4963 (2.6287) time: 0.6265 [2021-03-28 02:10:16 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 30/1251] eta: 0:15:30 lr: 0.000151 loss: 2.7297 (2.7827) grad_norm: 2.5994 (2.6323) time: 0.6279 [2021-03-28 02:10:23 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 40/1251] eta: 0:14:44 lr: 0.000151 loss: 2.9566 (2.8073) grad_norm: 2.4560 (2.6054) time: 0.6345 [2021-03-28 02:10:29 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 50/1251] eta: 0:14:11 lr: 0.000151 loss: 3.0224 (2.8575) grad_norm: 2.4475 (2.7217) time: 0.6271 [2021-03-28 02:10:35 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 60/1251] eta: 0:13:49 lr: 0.000151 loss: 2.9034 (2.8194) grad_norm: 2.4613 (2.7137) time: 0.6273 [2021-03-28 02:10:41 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 70/1251] eta: 0:13:30 lr: 0.000151 loss: 2.9007 (2.8417) grad_norm: 2.4340 (2.6605) time: 0.6294 [2021-03-28 02:10:48 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 80/1251] eta: 0:13:16 lr: 0.000151 loss: 2.9254 (2.8442) grad_norm: 2.4112 (2.6462) time: 0.6292 [2021-03-28 02:10:54 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 90/1251] eta: 0:13:02 lr: 0.000151 loss: 3.0114 (2.8740) grad_norm: 2.4230 (2.6190) time: 0.6288 [2021-03-28 02:11:00 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 100/1251] eta: 0:12:50 lr: 0.000151 loss: 3.0379 (2.8597) grad_norm: 2.4230 (2.6017) time: 0.6285 [2021-03-28 02:11:07 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 110/1251] eta: 0:12:40 lr: 0.000151 loss: 3.0282 (2.8644) grad_norm: 2.4419 (2.5995) time: 0.6322 [2021-03-28 02:11:13 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 120/1251] eta: 0:12:30 lr: 0.000151 loss: 3.1094 (2.8860) grad_norm: 2.4353 (2.5928) time: 0.6328 [2021-03-28 02:11:19 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 130/1251] eta: 0:12:21 lr: 0.000151 loss: 3.0449 (2.8837) grad_norm: 2.3695 (2.5697) time: 0.6347 [2021-03-28 02:11:26 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 140/1251] eta: 0:12:11 lr: 0.000151 loss: 3.0449 (2.8899) grad_norm: 2.3695 (2.5885) time: 0.6294 [2021-03-28 02:11:32 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 150/1251] eta: 0:12:03 lr: 0.000151 loss: 3.0774 (2.8800) grad_norm: 2.3766 (2.5732) time: 0.6262 [2021-03-28 02:11:38 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 160/1251] eta: 0:11:54 lr: 0.000151 loss: 2.7935 (2.8770) grad_norm: 2.3472 (2.5774) time: 0.6284 [2021-03-28 02:11:44 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 170/1251] eta: 0:11:46 lr: 0.000151 loss: 3.1195 (2.8898) grad_norm: 2.5513 (2.5799) time: 0.6307 [2021-03-28 02:11:51 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 180/1251] eta: 0:11:38 lr: 0.000151 loss: 3.1195 (2.8904) grad_norm: 2.4181 (2.5692) time: 0.6303 [2021-03-28 02:11:57 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 190/1251] eta: 0:11:30 lr: 0.000151 loss: 2.9286 (2.8894) grad_norm: 2.3443 (2.5589) time: 0.6241 [2021-03-28 02:12:03 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 200/1251] eta: 0:11:22 lr: 0.000151 loss: 2.9616 (2.8910) grad_norm: 2.3213 (2.5492) time: 0.6239 [2021-03-28 02:12:10 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 210/1251] eta: 0:11:15 lr: 0.000151 loss: 2.8079 (2.8727) grad_norm: 2.2537 (2.5342) time: 0.6284 [2021-03-28 02:12:16 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 220/1251] eta: 0:11:07 lr: 0.000151 loss: 2.4253 (2.8634) grad_norm: 2.2329 (2.5305) time: 0.6310 [2021-03-28 02:12:22 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 230/1251] eta: 0:11:00 lr: 0.000151 loss: 2.8684 (2.8673) grad_norm: 2.3782 (2.5713) time: 0.6326 [2021-03-28 02:12:29 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 240/1251] eta: 0:10:53 lr: 0.000151 loss: 2.9689 (2.8650) grad_norm: 2.3628 (2.5634) time: 0.6353 [2021-03-28 02:12:35 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 250/1251] eta: 0:10:47 lr: 0.000151 loss: 3.0044 (2.8702) grad_norm: 2.1947 (2.5498) time: 0.6370 [2021-03-28 02:12:41 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 260/1251] eta: 0:10:39 lr: 0.000151 loss: 2.9251 (2.8694) grad_norm: 2.1784 (2.5603) time: 0.6319 [2021-03-28 02:12:47 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 270/1251] eta: 0:10:32 lr: 0.000151 loss: 2.9907 (2.8729) grad_norm: 2.5703 (2.5638) time: 0.6288 [2021-03-28 02:12:54 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 280/1251] eta: 0:10:25 lr: 0.000151 loss: 3.0911 (2.8822) grad_norm: 2.3949 (2.5596) time: 0.6282 [2021-03-28 02:13:00 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 290/1251] eta: 0:10:18 lr: 0.000150 loss: 2.9255 (2.8728) grad_norm: 2.2197 (2.5524) time: 0.6278 [2021-03-28 02:13:06 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 300/1251] eta: 0:10:11 lr: 0.000150 loss: 2.8671 (2.8774) grad_norm: 2.3018 (2.5453) time: 0.6280 [2021-03-28 02:13:13 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 310/1251] eta: 0:10:05 lr: 0.000150 loss: 3.0836 (2.8836) grad_norm: 2.3977 (2.5495) time: 0.6291 [2021-03-28 02:13:19 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 320/1251] eta: 0:09:58 lr: 0.000150 loss: 3.0498 (2.8870) grad_norm: 2.4058 (2.5457) time: 0.6317 [2021-03-28 02:13:25 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 330/1251] eta: 0:09:51 lr: 0.000150 loss: 3.0511 (2.8843) grad_norm: 2.4058 (2.5504) time: 0.6276 [2021-03-28 02:13:32 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 340/1251] eta: 0:09:44 lr: 0.000150 loss: 2.7862 (2.8772) grad_norm: 2.3849 (2.5510) time: 0.6308 [2021-03-28 02:13:38 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 350/1251] eta: 0:09:37 lr: 0.000150 loss: 3.0222 (2.8868) grad_norm: 2.3849 (2.5519) time: 0.6309 [2021-03-28 02:13:44 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 360/1251] eta: 0:09:31 lr: 0.000150 loss: 3.0222 (2.8851) grad_norm: 2.6114 (2.5545) time: 0.6239 [2021-03-28 02:13:50 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 370/1251] eta: 0:09:24 lr: 0.000150 loss: 2.8716 (2.8843) grad_norm: 2.3790 (2.5483) time: 0.6232 [2021-03-28 02:13:56 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 380/1251] eta: 0:09:17 lr: 0.000150 loss: 2.6937 (2.8798) grad_norm: 2.3104 (2.5488) time: 0.6219 [2021-03-28 02:14:03 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 390/1251] eta: 0:09:10 lr: 0.000150 loss: 2.8082 (2.8812) grad_norm: 2.3543 (2.5519) time: 0.6213 [2021-03-28 02:14:09 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 400/1251] eta: 0:09:03 lr: 0.000150 loss: 3.1175 (2.8872) grad_norm: 2.3296 (2.5466) time: 0.6263 [2021-03-28 02:14:15 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 410/1251] eta: 0:08:57 lr: 0.000150 loss: 3.0216 (2.8890) grad_norm: 2.2506 (2.5452) time: 0.6316 [2021-03-28 02:14:22 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 420/1251] eta: 0:08:50 lr: 0.000150 loss: 3.0353 (2.8917) grad_norm: 2.2809 (2.5448) time: 0.6291 [2021-03-28 02:14:28 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 430/1251] eta: 0:08:44 lr: 0.000150 loss: 3.0404 (2.8923) grad_norm: 2.2809 (2.5411) time: 0.6234 [2021-03-28 02:14:34 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 440/1251] eta: 0:08:37 lr: 0.000150 loss: 3.0547 (2.8966) grad_norm: 2.2523 (2.5402) time: 0.6241 [2021-03-28 02:14:40 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 450/1251] eta: 0:08:31 lr: 0.000150 loss: 3.0547 (2.8974) grad_norm: 2.2211 (2.5434) time: 0.6311 [2021-03-28 02:14:47 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 460/1251] eta: 0:08:24 lr: 0.000150 loss: 2.9519 (2.8949) grad_norm: 2.4135 (2.5425) time: 0.6340 [2021-03-28 02:14:53 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 470/1251] eta: 0:08:17 lr: 0.000150 loss: 3.0787 (2.9001) grad_norm: 2.4623 (2.5409) time: 0.6285 [2021-03-28 02:14:59 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 480/1251] eta: 0:08:11 lr: 0.000150 loss: 3.0220 (2.8983) grad_norm: 2.3224 (2.5379) time: 0.6235 [2021-03-28 02:15:05 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 490/1251] eta: 0:08:04 lr: 0.000150 loss: 2.5689 (2.8907) grad_norm: 2.3422 (2.5385) time: 0.6235 [2021-03-28 02:15:12 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 500/1251] eta: 0:07:58 lr: 0.000150 loss: 2.8659 (2.8923) grad_norm: 2.3377 (2.5317) time: 0.6275 [2021-03-28 02:15:18 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 510/1251] eta: 0:07:51 lr: 0.000150 loss: 2.7762 (2.8845) grad_norm: 2.2009 (2.5296) time: 0.6289 [2021-03-28 02:15:24 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 520/1251] eta: 0:07:45 lr: 0.000150 loss: 2.7066 (2.8868) grad_norm: 2.2745 (2.5268) time: 0.6288 [2021-03-28 02:15:31 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 530/1251] eta: 0:07:38 lr: 0.000150 loss: 2.9994 (2.8872) grad_norm: 2.3944 (2.5284) time: 0.6281 [2021-03-28 02:15:37 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 540/1251] eta: 0:07:32 lr: 0.000150 loss: 2.9135 (2.8865) grad_norm: 2.3778 (2.5251) time: 0.6299 [2021-03-28 02:15:43 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 550/1251] eta: 0:07:26 lr: 0.000150 loss: 2.9135 (2.8848) grad_norm: 2.4747 (2.5268) time: 0.6398 [2021-03-28 02:15:50 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 560/1251] eta: 0:07:19 lr: 0.000150 loss: 2.9667 (2.8851) grad_norm: 2.4495 (2.5234) time: 0.6393 [2021-03-28 02:15:56 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 570/1251] eta: 0:07:13 lr: 0.000150 loss: 3.1077 (2.8905) grad_norm: 2.2757 (2.5216) time: 0.6318 [2021-03-28 02:16:02 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 580/1251] eta: 0:07:06 lr: 0.000150 loss: 3.0446 (2.8901) grad_norm: 2.2757 (2.5176) time: 0.6293 [2021-03-28 02:16:09 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 590/1251] eta: 0:07:00 lr: 0.000150 loss: 3.0163 (2.8946) grad_norm: 2.1631 (2.5123) time: 0.6302 [2021-03-28 02:16:15 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 600/1251] eta: 0:06:54 lr: 0.000150 loss: 3.0163 (2.8933) grad_norm: 2.2413 (2.5118) time: 0.6309 [2021-03-28 02:16:21 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 610/1251] eta: 0:06:47 lr: 0.000150 loss: 2.9074 (2.8953) grad_norm: 2.4074 (2.5118) time: 0.6285 [2021-03-28 02:16:28 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 620/1251] eta: 0:06:41 lr: 0.000150 loss: 2.9430 (2.8949) grad_norm: 2.3302 (2.5097) time: 0.6316 [2021-03-28 02:16:34 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 630/1251] eta: 0:06:34 lr: 0.000150 loss: 3.0299 (2.8966) grad_norm: 2.3302 (2.5088) time: 0.6281 [2021-03-28 02:16:40 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 640/1251] eta: 0:06:28 lr: 0.000149 loss: 2.9595 (2.8987) grad_norm: 2.3577 (2.5064) time: 0.6221 [2021-03-28 02:16:46 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 650/1251] eta: 0:06:21 lr: 0.000149 loss: 3.1097 (2.8996) grad_norm: 2.3387 (2.5036) time: 0.6221 [2021-03-28 02:16:53 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 660/1251] eta: 0:06:15 lr: 0.000149 loss: 3.1465 (2.9008) grad_norm: 2.3897 (2.5040) time: 0.6253 [2021-03-28 02:16:59 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 670/1251] eta: 0:06:08 lr: 0.000149 loss: 3.0480 (2.9001) grad_norm: 2.4728 (2.5028) time: 0.6252 [2021-03-28 02:17:05 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 680/1251] eta: 0:06:02 lr: 0.000149 loss: 2.8878 (2.9005) grad_norm: 2.3492 (2.5032) time: 0.6249 [2021-03-28 02:17:11 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 690/1251] eta: 0:05:56 lr: 0.000149 loss: 2.8389 (2.8979) grad_norm: 2.3896 (2.5059) time: 0.6273 [2021-03-28 02:17:18 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 700/1251] eta: 0:05:49 lr: 0.000149 loss: 2.9564 (2.9003) grad_norm: 2.4438 (2.5047) time: 0.6265 [2021-03-28 02:17:24 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 710/1251] eta: 0:05:43 lr: 0.000149 loss: 2.8947 (2.8979) grad_norm: 2.4936 (2.5078) time: 0.6275 [2021-03-28 02:17:30 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 720/1251] eta: 0:05:36 lr: 0.000149 loss: 2.8827 (2.8979) grad_norm: 2.6373 (2.5086) time: 0.6276 [2021-03-28 02:17:36 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 730/1251] eta: 0:05:30 lr: 0.000149 loss: 2.9253 (2.8980) grad_norm: 2.4215 (2.5067) time: 0.6298 [2021-03-28 02:17:43 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 740/1251] eta: 0:05:24 lr: 0.000149 loss: 2.7585 (2.8958) grad_norm: 2.3199 (2.5053) time: 0.6323 [2021-03-28 02:17:49 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 750/1251] eta: 0:05:17 lr: 0.000149 loss: 2.9901 (2.8991) grad_norm: 2.3995 (2.5049) time: 0.6333 [2021-03-28 02:17:55 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 760/1251] eta: 0:05:11 lr: 0.000149 loss: 3.2040 (2.9033) grad_norm: 2.3996 (2.5050) time: 0.6324 [2021-03-28 02:18:02 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 770/1251] eta: 0:05:05 lr: 0.000149 loss: 3.2086 (2.9062) grad_norm: 2.5590 (2.5082) time: 0.6315 [2021-03-28 02:18:08 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 780/1251] eta: 0:04:58 lr: 0.000149 loss: 3.1266 (2.9093) grad_norm: 2.3788 (2.5051) time: 0.6335 [2021-03-28 02:18:14 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 790/1251] eta: 0:04:52 lr: 0.000149 loss: 2.9979 (2.9085) grad_norm: 2.3261 (2.5065) time: 0.6274 [2021-03-28 02:18:21 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 800/1251] eta: 0:04:45 lr: 0.000149 loss: 2.9922 (2.9076) grad_norm: 2.3261 (2.5055) time: 0.6230 [2021-03-28 02:18:27 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 810/1251] eta: 0:04:39 lr: 0.000149 loss: 3.0768 (2.9087) grad_norm: 2.2244 (2.5036) time: 0.6291 [2021-03-28 02:18:33 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 820/1251] eta: 0:04:33 lr: 0.000149 loss: 2.9726 (2.9080) grad_norm: 2.2356 (2.5060) time: 0.6282 [2021-03-28 02:18:39 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 830/1251] eta: 0:04:26 lr: 0.000149 loss: 2.9726 (2.9105) grad_norm: 2.2855 (2.5050) time: 0.6223 [2021-03-28 02:18:46 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 840/1251] eta: 0:04:20 lr: 0.000149 loss: 3.1941 (2.9133) grad_norm: 2.4136 (2.5039) time: 0.6227 [2021-03-28 02:18:52 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 850/1251] eta: 0:04:14 lr: 0.000149 loss: 3.2252 (2.9151) grad_norm: 2.3850 (2.5036) time: 0.6254 [2021-03-28 02:18:58 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 860/1251] eta: 0:04:07 lr: 0.000149 loss: 3.2296 (2.9167) grad_norm: 2.3742 (2.5022) time: 0.6278 [2021-03-28 02:19:04 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 870/1251] eta: 0:04:01 lr: 0.000149 loss: 3.2296 (2.9192) grad_norm: 2.4364 (2.5036) time: 0.6278 [2021-03-28 02:19:11 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 880/1251] eta: 0:03:54 lr: 0.000149 loss: 3.1849 (2.9186) grad_norm: 2.4364 (2.5062) time: 0.6312 [2021-03-28 02:19:17 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 890/1251] eta: 0:03:48 lr: 0.000149 loss: 3.1581 (2.9190) grad_norm: 2.4990 (2.5077) time: 0.6314 [2021-03-28 02:19:23 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 900/1251] eta: 0:03:42 lr: 0.000149 loss: 2.9936 (2.9205) grad_norm: 2.4441 (2.5067) time: 0.6236 [2021-03-28 02:19:30 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 910/1251] eta: 0:03:35 lr: 0.000149 loss: 3.0380 (2.9223) grad_norm: 2.2301 (2.5035) time: 0.6232 [2021-03-28 02:19:36 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 920/1251] eta: 0:03:29 lr: 0.000149 loss: 3.0362 (2.9203) grad_norm: 2.2301 (2.5053) time: 0.6246 [2021-03-28 02:19:42 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 930/1251] eta: 0:03:23 lr: 0.000149 loss: 2.9920 (2.9209) grad_norm: 2.3084 (2.5024) time: 0.6308 [2021-03-28 02:19:48 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 940/1251] eta: 0:03:16 lr: 0.000149 loss: 3.0218 (2.9209) grad_norm: 2.3501 (2.5038) time: 0.6288 [2021-03-28 02:19:55 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 950/1251] eta: 0:03:10 lr: 0.000149 loss: 2.9155 (2.9196) grad_norm: 2.3438 (2.5008) time: 0.6272 [2021-03-28 02:20:01 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 960/1251] eta: 0:03:04 lr: 0.000149 loss: 2.9126 (2.9197) grad_norm: 2.2155 (2.5009) time: 0.6328 [2021-03-28 02:20:07 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 970/1251] eta: 0:02:57 lr: 0.000149 loss: 2.9815 (2.9194) grad_norm: 2.2902 (2.4998) time: 0.6284 [2021-03-28 02:20:14 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 980/1251] eta: 0:02:51 lr: 0.000149 loss: 3.0054 (2.9202) grad_norm: 2.4037 (2.5051) time: 0.6248 [2021-03-28 02:20:20 swin_base_patch4_window7_224] INFO: Epoch: [226] [ 990/1251] eta: 0:02:45 lr: 0.000148 loss: 2.9437 (2.9205) grad_norm: 2.3398 (2.5044) time: 0.6274 [2021-03-28 02:20:26 swin_base_patch4_window7_224] INFO: Epoch: [226] [1000/1251] eta: 0:02:38 lr: 0.000148 loss: 2.9264 (2.9191) grad_norm: 2.3398 (2.5080) time: 0.6273 [2021-03-28 02:20:32 swin_base_patch4_window7_224] INFO: Epoch: [226] [1010/1251] eta: 0:02:32 lr: 0.000148 loss: 2.9152 (2.9189) grad_norm: 2.5025 (2.5081) time: 0.6305 [2021-03-28 02:20:39 swin_base_patch4_window7_224] INFO: Epoch: [226] [1020/1251] eta: 0:02:26 lr: 0.000148 loss: 2.8980 (2.9184) grad_norm: 2.4233 (2.5082) time: 0.6320 [2021-03-28 02:20:45 swin_base_patch4_window7_224] INFO: Epoch: [226] [1030/1251] eta: 0:02:19 lr: 0.000148 loss: 2.8318 (2.9178) grad_norm: 2.3102 (2.5065) time: 0.6249 [2021-03-28 02:20:51 swin_base_patch4_window7_224] INFO: Epoch: [226] [1040/1251] eta: 0:02:13 lr: 0.000148 loss: 2.9898 (2.9193) grad_norm: 2.4327 (2.5071) time: 0.6224 [2021-03-28 02:20:57 swin_base_patch4_window7_224] INFO: Epoch: [226] [1050/1251] eta: 0:02:07 lr: 0.000148 loss: 3.0419 (2.9192) grad_norm: 2.3539 (2.5055) time: 0.6230 [2021-03-28 02:21:04 swin_base_patch4_window7_224] INFO: Epoch: [226] [1060/1251] eta: 0:02:00 lr: 0.000148 loss: 3.1259 (2.9196) grad_norm: 2.5463 (2.5099) time: 0.6251 [2021-03-28 02:21:10 swin_base_patch4_window7_224] INFO: Epoch: [226] [1070/1251] eta: 0:01:54 lr: 0.000148 loss: 2.9504 (2.9180) grad_norm: 2.4013 (2.5078) time: 0.6283 [2021-03-28 02:21:16 swin_base_patch4_window7_224] INFO: Epoch: [226] [1080/1251] eta: 0:01:48 lr: 0.000148 loss: 2.9391 (2.9175) grad_norm: 2.3618 (2.5079) time: 0.6263 [2021-03-28 02:21:22 swin_base_patch4_window7_224] INFO: Epoch: [226] [1090/1251] eta: 0:01:41 lr: 0.000148 loss: 2.9317 (2.9177) grad_norm: 2.4892 (2.5088) time: 0.6232 [2021-03-28 02:21:29 swin_base_patch4_window7_224] INFO: Epoch: [226] [1100/1251] eta: 0:01:35 lr: 0.000148 loss: 2.8746 (2.9180) grad_norm: 2.5426 (inf) time: 0.6231 [2021-03-28 02:21:35 swin_base_patch4_window7_224] INFO: Epoch: [226] [1110/1251] eta: 0:01:29 lr: 0.000148 loss: 3.0303 (2.9187) grad_norm: 2.5426 (inf) time: 0.6209 [2021-03-28 02:21:41 swin_base_patch4_window7_224] INFO: Epoch: [226] [1120/1251] eta: 0:01:22 lr: 0.000148 loss: 3.0570 (2.9189) grad_norm: 2.2744 (inf) time: 0.6232 [2021-03-28 02:21:47 swin_base_patch4_window7_224] INFO: Epoch: [226] [1130/1251] eta: 0:01:16 lr: 0.000148 loss: 3.0499 (2.9188) grad_norm: 2.2001 (inf) time: 0.6302 [2021-03-28 02:21:54 swin_base_patch4_window7_224] INFO: Epoch: [226] [1140/1251] eta: 0:01:10 lr: 0.000148 loss: 3.0275 (2.9190) grad_norm: 2.4067 (inf) time: 0.6273 [2021-03-28 02:22:00 swin_base_patch4_window7_224] INFO: Epoch: [226] [1150/1251] eta: 0:01:03 lr: 0.000148 loss: 2.9475 (2.9186) grad_norm: 2.3952 (inf) time: 0.6211 [2021-03-28 02:22:06 swin_base_patch4_window7_224] INFO: Epoch: [226] [1160/1251] eta: 0:00:57 lr: 0.000148 loss: 2.8962 (2.9186) grad_norm: 2.3952 (inf) time: 0.6324 [2021-03-28 02:22:13 swin_base_patch4_window7_224] INFO: Epoch: [226] [1170/1251] eta: 0:00:51 lr: 0.000148 loss: 2.9510 (2.9184) grad_norm: 2.4822 (inf) time: 0.6313 [2021-03-28 02:22:19 swin_base_patch4_window7_224] INFO: Epoch: [226] [1180/1251] eta: 0:00:44 lr: 0.000148 loss: 3.1172 (2.9203) grad_norm: 2.4084 (inf) time: 0.6270 [2021-03-28 02:22:25 swin_base_patch4_window7_224] INFO: Epoch: [226] [1190/1251] eta: 0:00:38 lr: 0.000148 loss: 3.0290 (2.9196) grad_norm: 2.5903 (inf) time: 0.6302 [2021-03-28 02:22:31 swin_base_patch4_window7_224] INFO: Epoch: [226] [1200/1251] eta: 0:00:32 lr: 0.000148 loss: 2.9333 (2.9198) grad_norm: 2.5705 (inf) time: 0.6286 [2021-03-28 02:22:38 swin_base_patch4_window7_224] INFO: Epoch: [226] [1210/1251] eta: 0:00:25 lr: 0.000148 loss: 2.9333 (2.9188) grad_norm: 2.3942 (inf) time: 0.6340 [2021-03-28 02:22:44 swin_base_patch4_window7_224] INFO: Epoch: [226] [1220/1251] eta: 0:00:19 lr: 0.000148 loss: 3.0973 (2.9205) grad_norm: 2.4800 (inf) time: 0.6390 [2021-03-28 02:22:50 swin_base_patch4_window7_224] INFO: Epoch: [226] [1230/1251] eta: 0:00:13 lr: 0.000148 loss: 3.0973 (2.9204) grad_norm: 2.5045 (inf) time: 0.6306 [2021-03-28 02:22:57 swin_base_patch4_window7_224] INFO: Epoch: [226] [1240/1251] eta: 0:00:06 lr: 0.000148 loss: 2.9659 (2.9206) grad_norm: 2.4170 (inf) time: 0.6206 [2021-03-28 02:23:03 swin_base_patch4_window7_224] INFO: Epoch: [226] [1250/1251] eta: 0:00:00 lr: 0.000148 loss: 3.0175 (2.9210) grad_norm: 2.3976 (inf) time: 0.6283 [2021-03-28 02:23:15 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:21 loss: 0.4877 (0.4877) acc1: 89.0625 (89.0625) acc5: 98.4375 (98.4375) [2021-03-28 02:23:17 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8198 (0.7944) acc1: 79.6875 (81.1080) acc5: 96.8750 (96.1648) [2021-03-28 02:23:19 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.8002 (0.8265) acc1: 79.6875 (80.5804) acc5: 96.8750 (96.3542) [2021-03-28 02:23:21 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7579 (0.8068) acc1: 81.2500 (81.3508) acc5: 95.3125 (96.1190) [2021-03-28 02:23:22 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6999 (0.7877) acc1: 84.3750 (81.7835) acc5: 95.3125 (96.2652) [2021-03-28 02:23:23 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7245 (0.7870) acc1: 84.3750 (81.7600) acc5: 96.8750 (96.2880) [2021-03-28 02:23:40 swin_base_patch4_window7_224] INFO: * Acc@1 82.080 Acc@5 96.064 loss 0.775 [2021-03-28 02:23:40 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.1% [2021-03-28 02:23:40 swin_base_patch4_window7_224] INFO: Max accuracy: 82.08% [2021-03-28 02:23:44 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 0/1251] eta: 1:38:05 lr: 0.000148 loss: 2.1691 (2.1691) grad_norm: 2.3987 (2.3987) time: 4.7049 [2021-03-28 02:23:51 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 10/1251] eta: 0:20:43 lr: 0.000148 loss: 2.8075 (2.7582) grad_norm: 2.3987 (2.5385) time: 1.0017 [2021-03-28 02:23:57 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 20/1251] eta: 0:16:58 lr: 0.000148 loss: 2.9518 (2.9205) grad_norm: 2.2954 (2.4272) time: 0.6332 [2021-03-28 02:24:03 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 30/1251] eta: 0:15:38 lr: 0.000148 loss: 3.0776 (2.9452) grad_norm: 2.3685 (2.4972) time: 0.6406 [2021-03-28 02:24:10 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 40/1251] eta: 0:14:52 lr: 0.000148 loss: 2.9937 (2.9302) grad_norm: 2.4089 (2.4732) time: 0.6427 [2021-03-28 02:24:16 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 50/1251] eta: 0:14:19 lr: 0.000148 loss: 2.8511 (2.8951) grad_norm: 2.2767 (2.4525) time: 0.6330 [2021-03-28 02:24:22 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 60/1251] eta: 0:13:55 lr: 0.000148 loss: 2.9074 (2.9077) grad_norm: 2.2815 (2.4248) time: 0.6292 [2021-03-28 02:24:29 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 70/1251] eta: 0:13:37 lr: 0.000148 loss: 3.1347 (2.9370) grad_norm: 2.3577 (2.4462) time: 0.6330 [2021-03-28 02:24:35 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 80/1251] eta: 0:13:21 lr: 0.000147 loss: 3.0803 (2.9414) grad_norm: 2.4024 (2.4379) time: 0.6315 [2021-03-28 02:24:41 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 90/1251] eta: 0:13:07 lr: 0.000147 loss: 2.8293 (2.9303) grad_norm: 2.2519 (2.4781) time: 0.6299 [2021-03-28 02:24:48 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 100/1251] eta: 0:12:54 lr: 0.000147 loss: 2.6250 (2.9094) grad_norm: 2.5205 (2.4908) time: 0.6277 [2021-03-28 02:24:54 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 110/1251] eta: 0:12:42 lr: 0.000147 loss: 3.0686 (2.9245) grad_norm: 2.3295 (2.4763) time: 0.6232 [2021-03-28 02:25:00 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 120/1251] eta: 0:12:32 lr: 0.000147 loss: 3.0686 (2.9360) grad_norm: 2.2672 (2.4576) time: 0.6268 [2021-03-28 02:25:06 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 130/1251] eta: 0:12:23 lr: 0.000147 loss: 3.0113 (2.9200) grad_norm: 2.1985 (2.4675) time: 0.6354 [2021-03-28 02:25:13 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 140/1251] eta: 0:12:14 lr: 0.000147 loss: 2.9249 (2.9194) grad_norm: 2.3605 (2.4691) time: 0.6357 [2021-03-28 02:25:19 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 150/1251] eta: 0:12:05 lr: 0.000147 loss: 3.0634 (2.9338) grad_norm: 2.3394 (2.4559) time: 0.6299 [2021-03-28 02:25:25 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 160/1251] eta: 0:11:56 lr: 0.000147 loss: 3.1064 (2.9287) grad_norm: 2.2537 (2.4498) time: 0.6275 [2021-03-28 02:25:32 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 170/1251] eta: 0:11:49 lr: 0.000147 loss: 2.8992 (2.9306) grad_norm: 2.3266 (2.4521) time: 0.6331 [2021-03-28 02:25:38 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 180/1251] eta: 0:11:41 lr: 0.000147 loss: 3.0255 (2.9351) grad_norm: 2.3266 (2.4504) time: 0.6340 [2021-03-28 02:25:44 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 190/1251] eta: 0:11:32 lr: 0.000147 loss: 3.0366 (2.9388) grad_norm: 2.3312 (2.4423) time: 0.6278 [2021-03-28 02:25:51 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 200/1251] eta: 0:11:25 lr: 0.000147 loss: 2.9946 (2.9366) grad_norm: 2.3873 (2.4458) time: 0.6322 [2021-03-28 02:25:57 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 210/1251] eta: 0:11:18 lr: 0.000147 loss: 2.9853 (2.9260) grad_norm: 2.3336 (2.4421) time: 0.6368 [2021-03-28 02:26:03 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 220/1251] eta: 0:11:10 lr: 0.000147 loss: 2.8943 (2.9270) grad_norm: 2.3048 (2.4437) time: 0.6304 [2021-03-28 02:26:10 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 230/1251] eta: 0:11:02 lr: 0.000147 loss: 2.8287 (2.9185) grad_norm: 2.3687 (2.4513) time: 0.6251 [2021-03-28 02:26:16 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 240/1251] eta: 0:10:56 lr: 0.000147 loss: 2.9989 (2.9172) grad_norm: 2.4081 (2.4522) time: 0.6335 [2021-03-28 02:26:22 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 250/1251] eta: 0:10:48 lr: 0.000147 loss: 2.8265 (2.9140) grad_norm: 2.3952 (2.4571) time: 0.6345 [2021-03-28 02:26:29 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 260/1251] eta: 0:10:41 lr: 0.000147 loss: 2.8450 (2.9133) grad_norm: 2.3132 (2.4517) time: 0.6335 [2021-03-28 02:26:35 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 270/1251] eta: 0:10:34 lr: 0.000147 loss: 2.9234 (2.9147) grad_norm: 2.3204 (2.4517) time: 0.6371 [2021-03-28 02:26:41 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 280/1251] eta: 0:10:27 lr: 0.000147 loss: 2.7581 (2.9089) grad_norm: 2.3097 (2.4474) time: 0.6333 [2021-03-28 02:26:48 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 290/1251] eta: 0:10:21 lr: 0.000147 loss: 2.6760 (2.9049) grad_norm: 2.2536 (2.4453) time: 0.6326 [2021-03-28 02:26:54 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 300/1251] eta: 0:10:14 lr: 0.000147 loss: 2.9591 (2.9100) grad_norm: 2.1957 (2.4426) time: 0.6313 [2021-03-28 02:27:00 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 310/1251] eta: 0:10:07 lr: 0.000147 loss: 2.9873 (2.9109) grad_norm: 2.2612 (2.4447) time: 0.6295 [2021-03-28 02:27:06 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 320/1251] eta: 0:09:59 lr: 0.000147 loss: 2.8004 (2.9074) grad_norm: 2.4678 (2.4544) time: 0.6255 [2021-03-28 02:27:13 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 330/1251] eta: 0:09:53 lr: 0.000147 loss: 2.8004 (2.9102) grad_norm: 2.4274 (2.4485) time: 0.6258 [2021-03-28 02:27:19 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 340/1251] eta: 0:09:46 lr: 0.000147 loss: 3.1490 (2.9129) grad_norm: 2.1982 (2.4445) time: 0.6358 [2021-03-28 02:27:25 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 350/1251] eta: 0:09:39 lr: 0.000147 loss: 3.1028 (2.9132) grad_norm: 2.2673 (2.4452) time: 0.6330 [2021-03-28 02:27:32 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 360/1251] eta: 0:09:32 lr: 0.000147 loss: 2.9830 (2.9124) grad_norm: 2.3088 (2.4461) time: 0.6259 [2021-03-28 02:27:38 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 370/1251] eta: 0:09:26 lr: 0.000147 loss: 2.9830 (2.9104) grad_norm: 2.2944 (2.4456) time: 0.6321 [2021-03-28 02:27:44 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 380/1251] eta: 0:09:19 lr: 0.000147 loss: 2.7710 (2.9038) grad_norm: 2.3232 (2.4470) time: 0.6352 [2021-03-28 02:27:51 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 390/1251] eta: 0:09:12 lr: 0.000147 loss: 2.7710 (2.9048) grad_norm: 2.3478 (2.4494) time: 0.6282 [2021-03-28 02:27:57 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 400/1251] eta: 0:09:06 lr: 0.000147 loss: 2.7686 (2.8969) grad_norm: 2.3750 (2.4461) time: 0.6291 [2021-03-28 02:28:03 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 410/1251] eta: 0:08:59 lr: 0.000147 loss: 2.5932 (2.8922) grad_norm: 2.3218 (2.4502) time: 0.6321 [2021-03-28 02:28:10 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 420/1251] eta: 0:08:52 lr: 0.000147 loss: 2.8738 (2.8975) grad_norm: 2.4980 (2.4590) time: 0.6269 [2021-03-28 02:28:16 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 430/1251] eta: 0:08:46 lr: 0.000146 loss: 3.0912 (2.9009) grad_norm: 2.3663 (2.4587) time: 0.6283 [2021-03-28 02:28:22 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 440/1251] eta: 0:08:39 lr: 0.000146 loss: 3.0548 (2.9016) grad_norm: 2.3592 (inf) time: 0.6256 [2021-03-28 02:28:28 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 450/1251] eta: 0:08:32 lr: 0.000146 loss: 2.9200 (2.9022) grad_norm: 2.3347 (inf) time: 0.6228 [2021-03-28 02:28:35 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 460/1251] eta: 0:08:26 lr: 0.000146 loss: 3.0830 (2.9066) grad_norm: 2.2252 (inf) time: 0.6284 [2021-03-28 02:28:41 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 470/1251] eta: 0:08:19 lr: 0.000146 loss: 3.0533 (2.9028) grad_norm: 2.2252 (inf) time: 0.6284 [2021-03-28 02:28:47 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 480/1251] eta: 0:08:12 lr: 0.000146 loss: 2.8483 (2.9033) grad_norm: 2.4292 (inf) time: 0.6258 [2021-03-28 02:28:54 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 490/1251] eta: 0:08:06 lr: 0.000146 loss: 2.7814 (2.8991) grad_norm: 2.4615 (inf) time: 0.6312 [2021-03-28 02:29:00 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 500/1251] eta: 0:07:59 lr: 0.000146 loss: 2.6461 (2.8967) grad_norm: 2.4297 (inf) time: 0.6314 [2021-03-28 02:29:06 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 510/1251] eta: 0:07:53 lr: 0.000146 loss: 2.8265 (2.8958) grad_norm: 2.3697 (inf) time: 0.6295 [2021-03-28 02:29:12 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 520/1251] eta: 0:07:47 lr: 0.000146 loss: 2.9832 (2.8943) grad_norm: 2.5210 (inf) time: 0.6352 [2021-03-28 02:29:19 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 530/1251] eta: 0:07:40 lr: 0.000146 loss: 3.0143 (2.8962) grad_norm: 2.5244 (inf) time: 0.6359 [2021-03-28 02:29:25 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 540/1251] eta: 0:07:34 lr: 0.000146 loss: 3.1099 (2.8955) grad_norm: 2.3731 (inf) time: 0.6321 [2021-03-28 02:29:32 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 550/1251] eta: 0:07:27 lr: 0.000146 loss: 2.7693 (2.8945) grad_norm: 2.4158 (inf) time: 0.6374 [2021-03-28 02:29:38 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 560/1251] eta: 0:07:21 lr: 0.000146 loss: 3.0777 (2.8942) grad_norm: 2.4634 (inf) time: 0.6396 [2021-03-28 02:29:44 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 570/1251] eta: 0:07:14 lr: 0.000146 loss: 3.1227 (2.8970) grad_norm: 2.3762 (inf) time: 0.6314 [2021-03-28 02:29:51 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 580/1251] eta: 0:07:08 lr: 0.000146 loss: 3.0686 (2.8974) grad_norm: 2.3367 (inf) time: 0.6312 [2021-03-28 02:29:57 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 590/1251] eta: 0:07:02 lr: 0.000146 loss: 2.8645 (2.8932) grad_norm: 2.2434 (inf) time: 0.6381 [2021-03-28 02:30:03 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 600/1251] eta: 0:06:55 lr: 0.000146 loss: 2.7569 (2.8932) grad_norm: 2.2434 (inf) time: 0.6324 [2021-03-28 02:30:10 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 610/1251] eta: 0:06:49 lr: 0.000146 loss: 3.0417 (2.8930) grad_norm: 2.2868 (inf) time: 0.6285 [2021-03-28 02:30:16 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 620/1251] eta: 0:06:42 lr: 0.000146 loss: 2.9275 (2.8933) grad_norm: 2.2868 (inf) time: 0.6389 [2021-03-28 02:30:22 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 630/1251] eta: 0:06:36 lr: 0.000146 loss: 2.9275 (2.8935) grad_norm: 2.4713 (inf) time: 0.6322 [2021-03-28 02:30:29 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 640/1251] eta: 0:06:29 lr: 0.000146 loss: 3.0116 (2.8942) grad_norm: 2.4713 (inf) time: 0.6304 [2021-03-28 02:30:35 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 650/1251] eta: 0:06:23 lr: 0.000146 loss: 3.0483 (2.8962) grad_norm: 2.4323 (inf) time: 0.6375 [2021-03-28 02:30:41 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 660/1251] eta: 0:06:16 lr: 0.000146 loss: 3.0483 (2.8966) grad_norm: 2.4864 (inf) time: 0.6288 [2021-03-28 02:30:47 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 670/1251] eta: 0:06:10 lr: 0.000146 loss: 2.9431 (2.8945) grad_norm: 2.3024 (inf) time: 0.6262 [2021-03-28 02:30:54 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 680/1251] eta: 0:06:04 lr: 0.000146 loss: 2.8395 (2.8934) grad_norm: 2.4855 (inf) time: 0.6308 [2021-03-28 02:31:00 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 690/1251] eta: 0:05:57 lr: 0.000146 loss: 2.8443 (2.8942) grad_norm: 2.6750 (inf) time: 0.6331 [2021-03-28 02:31:06 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 700/1251] eta: 0:05:51 lr: 0.000146 loss: 3.0125 (2.8957) grad_norm: 2.5892 (inf) time: 0.6289 [2021-03-28 02:31:13 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 710/1251] eta: 0:05:44 lr: 0.000146 loss: 3.0862 (2.8946) grad_norm: 2.3825 (inf) time: 0.6341 [2021-03-28 02:31:19 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 720/1251] eta: 0:05:38 lr: 0.000146 loss: 2.8116 (2.8908) grad_norm: 2.4273 (inf) time: 0.6356 [2021-03-28 02:31:25 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 730/1251] eta: 0:05:32 lr: 0.000146 loss: 2.9052 (2.8929) grad_norm: 2.2900 (inf) time: 0.6341 [2021-03-28 02:31:32 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 740/1251] eta: 0:05:25 lr: 0.000146 loss: 2.9980 (2.8942) grad_norm: 2.3418 (inf) time: 0.6420 [2021-03-28 02:31:38 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 750/1251] eta: 0:05:19 lr: 0.000146 loss: 2.9620 (2.8953) grad_norm: 2.5084 (inf) time: 0.6460 [2021-03-28 02:31:45 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 760/1251] eta: 0:05:12 lr: 0.000146 loss: 2.9620 (2.8957) grad_norm: 2.4470 (inf) time: 0.6405 [2021-03-28 02:31:51 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 770/1251] eta: 0:05:06 lr: 0.000146 loss: 2.9753 (2.8980) grad_norm: 2.4982 (inf) time: 0.6309 [2021-03-28 02:31:57 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 780/1251] eta: 0:05:00 lr: 0.000145 loss: 3.1226 (2.9009) grad_norm: 2.5690 (inf) time: 0.6336 [2021-03-28 02:32:04 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 790/1251] eta: 0:04:53 lr: 0.000145 loss: 3.0104 (2.9005) grad_norm: 2.5571 (inf) time: 0.6393 [2021-03-28 02:32:10 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 800/1251] eta: 0:04:47 lr: 0.000145 loss: 2.8422 (2.9007) grad_norm: 2.3090 (inf) time: 0.6344 [2021-03-28 02:32:16 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 810/1251] eta: 0:04:40 lr: 0.000145 loss: 3.0263 (2.9020) grad_norm: 2.4340 (inf) time: 0.6269 [2021-03-28 02:32:23 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 820/1251] eta: 0:04:34 lr: 0.000145 loss: 3.1148 (2.9020) grad_norm: 2.4748 (inf) time: 0.6297 [2021-03-28 02:32:29 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 830/1251] eta: 0:04:28 lr: 0.000145 loss: 3.1214 (2.9059) grad_norm: 2.5937 (inf) time: 0.6311 [2021-03-28 02:32:35 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 840/1251] eta: 0:04:21 lr: 0.000145 loss: 3.0764 (2.9051) grad_norm: 2.4783 (inf) time: 0.6333 [2021-03-28 02:32:42 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 850/1251] eta: 0:04:15 lr: 0.000145 loss: 2.8567 (2.9022) grad_norm: 2.4050 (inf) time: 0.6318 [2021-03-28 02:32:48 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 860/1251] eta: 0:04:08 lr: 0.000145 loss: 2.9475 (2.9038) grad_norm: 2.3960 (inf) time: 0.6238 [2021-03-28 02:32:54 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 870/1251] eta: 0:04:02 lr: 0.000145 loss: 2.9321 (2.9004) grad_norm: 2.4514 (inf) time: 0.6233 [2021-03-28 02:33:00 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 880/1251] eta: 0:03:56 lr: 0.000145 loss: 2.6130 (2.9002) grad_norm: 2.5086 (inf) time: 0.6261 [2021-03-28 02:33:07 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 890/1251] eta: 0:03:49 lr: 0.000145 loss: 3.0069 (2.9012) grad_norm: 2.4394 (inf) time: 0.6247 [2021-03-28 02:33:13 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 900/1251] eta: 0:03:43 lr: 0.000145 loss: 3.0723 (2.9019) grad_norm: 2.4098 (inf) time: 0.6244 [2021-03-28 02:33:19 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 910/1251] eta: 0:03:36 lr: 0.000145 loss: 3.0611 (2.9010) grad_norm: 2.4604 (inf) time: 0.6270 [2021-03-28 02:33:25 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 920/1251] eta: 0:03:30 lr: 0.000145 loss: 2.8000 (2.8985) grad_norm: 2.4571 (inf) time: 0.6301 [2021-03-28 02:33:32 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 930/1251] eta: 0:03:24 lr: 0.000145 loss: 3.0132 (2.9012) grad_norm: 2.4436 (inf) time: 0.6277 [2021-03-28 02:33:38 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 940/1251] eta: 0:03:17 lr: 0.000145 loss: 2.7944 (2.8985) grad_norm: 2.5557 (inf) time: 0.6299 [2021-03-28 02:33:44 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 950/1251] eta: 0:03:11 lr: 0.000145 loss: 2.5734 (2.8962) grad_norm: 2.3897 (inf) time: 0.6318 [2021-03-28 02:33:51 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 960/1251] eta: 0:03:05 lr: 0.000145 loss: 2.3585 (2.8940) grad_norm: 2.4344 (inf) time: 0.6302 [2021-03-28 02:33:57 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 970/1251] eta: 0:02:58 lr: 0.000145 loss: 2.9919 (2.8941) grad_norm: 2.7031 (inf) time: 0.6308 [2021-03-28 02:34:03 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 980/1251] eta: 0:02:52 lr: 0.000145 loss: 2.9959 (2.8929) grad_norm: 2.2934 (inf) time: 0.6301 [2021-03-28 02:34:10 swin_base_patch4_window7_224] INFO: Epoch: [227] [ 990/1251] eta: 0:02:45 lr: 0.000145 loss: 2.8695 (2.8920) grad_norm: 2.2934 (inf) time: 0.6325 [2021-03-28 02:34:16 swin_base_patch4_window7_224] INFO: Epoch: [227] [1000/1251] eta: 0:02:39 lr: 0.000145 loss: 3.0350 (2.8938) grad_norm: 2.6371 (inf) time: 0.6280 [2021-03-28 02:34:22 swin_base_patch4_window7_224] INFO: Epoch: [227] [1010/1251] eta: 0:02:33 lr: 0.000145 loss: 3.0932 (2.8933) grad_norm: 2.5605 (inf) time: 0.6294 [2021-03-28 02:34:28 swin_base_patch4_window7_224] INFO: Epoch: [227] [1020/1251] eta: 0:02:26 lr: 0.000145 loss: 2.7818 (2.8928) grad_norm: 2.4798 (inf) time: 0.6301 [2021-03-28 02:34:35 swin_base_patch4_window7_224] INFO: Epoch: [227] [1030/1251] eta: 0:02:20 lr: 0.000145 loss: 2.9827 (2.8939) grad_norm: 2.4436 (inf) time: 0.6278 [2021-03-28 02:34:41 swin_base_patch4_window7_224] INFO: Epoch: [227] [1040/1251] eta: 0:02:14 lr: 0.000145 loss: 3.0570 (2.8962) grad_norm: 2.4170 (inf) time: 0.6337 [2021-03-28 02:34:47 swin_base_patch4_window7_224] INFO: Epoch: [227] [1050/1251] eta: 0:02:07 lr: 0.000145 loss: 3.1316 (2.8985) grad_norm: 2.3375 (inf) time: 0.6320 [2021-03-28 02:34:54 swin_base_patch4_window7_224] INFO: Epoch: [227] [1060/1251] eta: 0:02:01 lr: 0.000145 loss: 3.1133 (2.8964) grad_norm: 2.2408 (inf) time: 0.6286 [2021-03-28 02:35:00 swin_base_patch4_window7_224] INFO: Epoch: [227] [1070/1251] eta: 0:01:54 lr: 0.000145 loss: 2.9469 (2.8970) grad_norm: 2.2693 (inf) time: 0.6317 [2021-03-28 02:35:06 swin_base_patch4_window7_224] INFO: Epoch: [227] [1080/1251] eta: 0:01:48 lr: 0.000145 loss: 2.9759 (2.8961) grad_norm: 2.4428 (inf) time: 0.6331 [2021-03-28 02:35:13 swin_base_patch4_window7_224] INFO: Epoch: [227] [1090/1251] eta: 0:01:42 lr: 0.000145 loss: 2.9354 (2.8966) grad_norm: 2.4652 (inf) time: 0.6358 [2021-03-28 02:35:19 swin_base_patch4_window7_224] INFO: Epoch: [227] [1100/1251] eta: 0:01:35 lr: 0.000145 loss: 2.8741 (2.8959) grad_norm: 2.4818 (inf) time: 0.6362 [2021-03-28 02:35:25 swin_base_patch4_window7_224] INFO: Epoch: [227] [1110/1251] eta: 0:01:29 lr: 0.000145 loss: 2.8338 (2.8940) grad_norm: 2.4527 (inf) time: 0.6329 [2021-03-28 02:35:32 swin_base_patch4_window7_224] INFO: Epoch: [227] [1120/1251] eta: 0:01:23 lr: 0.000145 loss: 2.8338 (2.8920) grad_norm: 2.4527 (inf) time: 0.6323 [2021-03-28 02:35:38 swin_base_patch4_window7_224] INFO: Epoch: [227] [1130/1251] eta: 0:01:16 lr: 0.000145 loss: 2.8847 (2.8925) grad_norm: 2.3479 (inf) time: 0.6350 [2021-03-28 02:35:44 swin_base_patch4_window7_224] INFO: Epoch: [227] [1140/1251] eta: 0:01:10 lr: 0.000144 loss: 2.9776 (2.8941) grad_norm: 2.3512 (inf) time: 0.6334 [2021-03-28 02:35:51 swin_base_patch4_window7_224] INFO: Epoch: [227] [1150/1251] eta: 0:01:04 lr: 0.000144 loss: 3.0029 (2.8938) grad_norm: 2.2821 (inf) time: 0.6268 [2021-03-28 02:35:57 swin_base_patch4_window7_224] INFO: Epoch: [227] [1160/1251] eta: 0:00:57 lr: 0.000144 loss: 3.0029 (2.8937) grad_norm: 2.1744 (inf) time: 0.6271 [2021-03-28 02:36:03 swin_base_patch4_window7_224] INFO: Epoch: [227] [1170/1251] eta: 0:00:51 lr: 0.000144 loss: 2.9909 (2.8943) grad_norm: 2.4707 (inf) time: 0.6284 [2021-03-28 02:36:10 swin_base_patch4_window7_224] INFO: Epoch: [227] [1180/1251] eta: 0:00:45 lr: 0.000144 loss: 2.9909 (2.8946) grad_norm: 2.4707 (inf) time: 0.6293 [2021-03-28 02:36:16 swin_base_patch4_window7_224] INFO: Epoch: [227] [1190/1251] eta: 0:00:38 lr: 0.000144 loss: 3.0889 (2.8958) grad_norm: 2.2698 (inf) time: 0.6259 [2021-03-28 02:36:22 swin_base_patch4_window7_224] INFO: Epoch: [227] [1200/1251] eta: 0:00:32 lr: 0.000144 loss: 3.0291 (2.8946) grad_norm: 2.2556 (inf) time: 0.6260 [2021-03-28 02:36:28 swin_base_patch4_window7_224] INFO: Epoch: [227] [1210/1251] eta: 0:00:26 lr: 0.000144 loss: 2.8178 (2.8935) grad_norm: 2.4998 (inf) time: 0.6317 [2021-03-28 02:36:35 swin_base_patch4_window7_224] INFO: Epoch: [227] [1220/1251] eta: 0:00:19 lr: 0.000144 loss: 2.8468 (2.8935) grad_norm: 2.4807 (inf) time: 0.6345 [2021-03-28 02:36:41 swin_base_patch4_window7_224] INFO: Epoch: [227] [1230/1251] eta: 0:00:13 lr: 0.000144 loss: 2.7363 (2.8920) grad_norm: 2.4341 (inf) time: 0.6325 [2021-03-28 02:36:47 swin_base_patch4_window7_224] INFO: Epoch: [227] [1240/1251] eta: 0:00:06 lr: 0.000144 loss: 2.5718 (2.8902) grad_norm: 2.4829 (inf) time: 0.6279 [2021-03-28 02:36:54 swin_base_patch4_window7_224] INFO: Epoch: [227] [1250/1251] eta: 0:00:00 lr: 0.000144 loss: 2.6847 (2.8893) grad_norm: 2.3846 (inf) time: 0.6256 [2021-03-28 02:37:06 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:27 loss: 0.9995 (0.9995) acc1: 76.5625 (76.5625) acc5: 93.7500 (93.7500) [2021-03-28 02:37:08 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.7777 (0.7658) acc1: 81.2500 (81.5341) acc5: 96.8750 (96.7330) [2021-03-28 02:37:10 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7426 (0.7667) acc1: 81.2500 (81.3988) acc5: 96.8750 (96.5030) [2021-03-28 02:37:12 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7330 (0.7608) acc1: 84.3750 (81.8044) acc5: 96.8750 (96.9254) [2021-03-28 02:37:14 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8471 (0.7851) acc1: 81.2500 (81.1738) acc5: 96.8750 (96.7226) [2021-03-28 02:37:15 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8544 (0.7931) acc1: 79.6875 (81.2800) acc5: 96.8750 (96.5440) [2021-03-28 02:37:27 swin_base_patch4_window7_224] INFO: * Acc@1 82.150 Acc@5 96.118 loss 0.777 [2021-03-28 02:37:27 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.2% [2021-03-28 02:37:27 swin_base_patch4_window7_224] INFO: Max accuracy: 82.15% [2021-03-28 02:37:31 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 0/1251] eta: 1:28:08 lr: 0.000144 loss: 3.5095 (3.5095) grad_norm: 2.2092 (2.2092) time: 4.2277 [2021-03-28 02:37:38 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 10/1251] eta: 0:20:23 lr: 0.000144 loss: 2.8607 (2.9121) grad_norm: 2.2092 (2.2828) time: 0.9861 [2021-03-28 02:37:44 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 20/1251] eta: 0:16:40 lr: 0.000144 loss: 2.8607 (2.9283) grad_norm: 2.2293 (2.3459) time: 0.6418 [2021-03-28 02:37:51 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 30/1251] eta: 0:15:19 lr: 0.000144 loss: 2.9640 (2.9421) grad_norm: 2.3164 (2.3841) time: 0.6247 [2021-03-28 02:37:57 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 40/1251] eta: 0:14:37 lr: 0.000144 loss: 2.9945 (2.9299) grad_norm: 2.4183 (2.4196) time: 0.6330 [2021-03-28 02:38:03 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 50/1251] eta: 0:14:08 lr: 0.000144 loss: 3.0459 (2.9113) grad_norm: 2.3921 (2.4123) time: 0.6351 [2021-03-28 02:38:10 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 60/1251] eta: 0:13:47 lr: 0.000144 loss: 3.0459 (2.9353) grad_norm: 2.3553 (2.4018) time: 0.6330 [2021-03-28 02:38:16 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 70/1251] eta: 0:13:29 lr: 0.000144 loss: 2.9611 (2.9018) grad_norm: 2.3553 (2.4060) time: 0.6301 [2021-03-28 02:38:22 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 80/1251] eta: 0:13:13 lr: 0.000144 loss: 2.9611 (2.9094) grad_norm: 2.3598 (2.4103) time: 0.6262 [2021-03-28 02:38:28 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 90/1251] eta: 0:13:01 lr: 0.000144 loss: 2.9696 (2.9007) grad_norm: 2.3690 (2.5287) time: 0.6289 [2021-03-28 02:38:35 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 100/1251] eta: 0:12:48 lr: 0.000144 loss: 2.9812 (2.9271) grad_norm: 2.2379 (2.5125) time: 0.6272 [2021-03-28 02:38:41 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 110/1251] eta: 0:12:38 lr: 0.000144 loss: 2.9451 (2.9105) grad_norm: 2.2744 (2.5033) time: 0.6270 [2021-03-28 02:38:47 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 120/1251] eta: 0:12:28 lr: 0.000144 loss: 2.9248 (2.9176) grad_norm: 2.3386 (2.4932) time: 0.6330 [2021-03-28 02:38:54 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 130/1251] eta: 0:12:20 lr: 0.000144 loss: 3.0819 (2.9248) grad_norm: 2.2857 (2.5289) time: 0.6407 [2021-03-28 02:39:00 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 140/1251] eta: 0:12:12 lr: 0.000144 loss: 2.8831 (2.9020) grad_norm: 2.3658 (2.5277) time: 0.6413 [2021-03-28 02:39:06 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 150/1251] eta: 0:12:03 lr: 0.000144 loss: 2.7389 (2.8961) grad_norm: 2.4054 (2.5417) time: 0.6333 [2021-03-28 02:39:13 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 160/1251] eta: 0:11:55 lr: 0.000144 loss: 2.9591 (2.8942) grad_norm: 2.4334 (2.5381) time: 0.6310 [2021-03-28 02:39:19 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 170/1251] eta: 0:11:47 lr: 0.000144 loss: 2.9591 (2.8971) grad_norm: 2.3390 (2.5234) time: 0.6331 [2021-03-28 02:39:25 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 180/1251] eta: 0:11:39 lr: 0.000144 loss: 2.8377 (2.8837) grad_norm: 2.3321 (2.5332) time: 0.6321 [2021-03-28 02:39:32 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 190/1251] eta: 0:11:31 lr: 0.000144 loss: 2.6407 (2.8753) grad_norm: 2.2493 (2.5158) time: 0.6307 [2021-03-28 02:39:38 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 200/1251] eta: 0:11:24 lr: 0.000144 loss: 2.8182 (2.8873) grad_norm: 2.2235 (2.5057) time: 0.6340 [2021-03-28 02:39:44 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 210/1251] eta: 0:11:16 lr: 0.000144 loss: 3.0184 (2.8868) grad_norm: 2.2974 (2.5280) time: 0.6349 [2021-03-28 02:39:51 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 220/1251] eta: 0:11:09 lr: 0.000144 loss: 2.9049 (2.8938) grad_norm: 2.3479 (2.5170) time: 0.6295 [2021-03-28 02:39:57 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 230/1251] eta: 0:11:01 lr: 0.000144 loss: 2.9049 (2.8967) grad_norm: 2.3479 (2.5134) time: 0.6254 [2021-03-28 02:40:03 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 240/1251] eta: 0:10:54 lr: 0.000143 loss: 3.0316 (2.9051) grad_norm: 2.4101 (2.5133) time: 0.6279 [2021-03-28 02:40:10 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 250/1251] eta: 0:10:47 lr: 0.000143 loss: 3.0973 (2.9017) grad_norm: 2.4468 (2.5120) time: 0.6277 [2021-03-28 02:40:16 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 260/1251] eta: 0:10:39 lr: 0.000143 loss: 2.7476 (2.8991) grad_norm: 2.4199 (2.5078) time: 0.6262 [2021-03-28 02:40:22 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 270/1251] eta: 0:10:33 lr: 0.000143 loss: 2.8973 (2.9030) grad_norm: 2.4264 (2.5097) time: 0.6312 [2021-03-28 02:40:29 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 280/1251] eta: 0:10:26 lr: 0.000143 loss: 3.2266 (2.9101) grad_norm: 2.3200 (2.5026) time: 0.6355 [2021-03-28 02:40:35 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 290/1251] eta: 0:10:19 lr: 0.000143 loss: 3.0525 (2.9066) grad_norm: 2.2013 (2.4993) time: 0.6304 [2021-03-28 02:40:41 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 300/1251] eta: 0:10:12 lr: 0.000143 loss: 3.0525 (2.9119) grad_norm: 2.2792 (2.4963) time: 0.6306 [2021-03-28 02:40:47 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 310/1251] eta: 0:10:05 lr: 0.000143 loss: 3.0370 (2.9147) grad_norm: 2.2953 (2.4907) time: 0.6308 [2021-03-28 02:40:54 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 320/1251] eta: 0:09:58 lr: 0.000143 loss: 2.9317 (2.9124) grad_norm: 2.2631 (2.4865) time: 0.6280 [2021-03-28 02:41:00 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 330/1251] eta: 0:09:51 lr: 0.000143 loss: 2.9317 (2.9114) grad_norm: 2.2631 (2.4846) time: 0.6311 [2021-03-28 02:41:06 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 340/1251] eta: 0:09:45 lr: 0.000143 loss: 2.8370 (2.9057) grad_norm: 2.4396 (2.4945) time: 0.6286 [2021-03-28 02:41:13 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 350/1251] eta: 0:09:38 lr: 0.000143 loss: 2.8537 (2.9085) grad_norm: 2.5686 (2.5035) time: 0.6267 [2021-03-28 02:41:19 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 360/1251] eta: 0:09:31 lr: 0.000143 loss: 3.0355 (2.9100) grad_norm: 2.3951 (2.5014) time: 0.6295 [2021-03-28 02:41:25 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 370/1251] eta: 0:09:24 lr: 0.000143 loss: 3.0658 (2.9112) grad_norm: 2.3118 (2.4943) time: 0.6320 [2021-03-28 02:41:31 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 380/1251] eta: 0:09:18 lr: 0.000143 loss: 3.0698 (2.9139) grad_norm: 2.2643 (2.4947) time: 0.6281 [2021-03-28 02:41:38 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 390/1251] eta: 0:09:11 lr: 0.000143 loss: 3.0293 (2.9114) grad_norm: 2.2508 (2.4909) time: 0.6266 [2021-03-28 02:41:44 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 400/1251] eta: 0:09:05 lr: 0.000143 loss: 2.8041 (2.9071) grad_norm: 2.1606 (2.4853) time: 0.6347 [2021-03-28 02:41:50 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 410/1251] eta: 0:08:58 lr: 0.000143 loss: 2.7640 (2.9021) grad_norm: 2.2316 (2.4791) time: 0.6346 [2021-03-28 02:41:57 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 420/1251] eta: 0:08:51 lr: 0.000143 loss: 2.9645 (2.9014) grad_norm: 2.3195 (2.4845) time: 0.6282 [2021-03-28 02:42:03 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 430/1251] eta: 0:08:45 lr: 0.000143 loss: 2.9645 (2.8997) grad_norm: 2.5134 (2.4911) time: 0.6263 [2021-03-28 02:42:09 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 440/1251] eta: 0:08:38 lr: 0.000143 loss: 2.9832 (2.9035) grad_norm: 2.4068 (2.4918) time: 0.6275 [2021-03-28 02:42:16 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 450/1251] eta: 0:08:31 lr: 0.000143 loss: 2.8567 (2.9012) grad_norm: 2.3586 (2.4886) time: 0.6299 [2021-03-28 02:42:22 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 460/1251] eta: 0:08:25 lr: 0.000143 loss: 2.8567 (2.9027) grad_norm: 2.4476 (2.4913) time: 0.6281 [2021-03-28 02:42:28 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 470/1251] eta: 0:08:18 lr: 0.000143 loss: 3.0201 (2.9054) grad_norm: 2.5881 (2.5098) time: 0.6279 [2021-03-28 02:42:34 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 480/1251] eta: 0:08:12 lr: 0.000143 loss: 3.0131 (2.9038) grad_norm: 2.3456 (2.5076) time: 0.6288 [2021-03-28 02:42:41 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 490/1251] eta: 0:08:05 lr: 0.000143 loss: 2.7473 (2.9004) grad_norm: 2.3146 (2.5049) time: 0.6263 [2021-03-28 02:42:47 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 500/1251] eta: 0:07:59 lr: 0.000143 loss: 2.7882 (2.9030) grad_norm: 2.5180 (2.5103) time: 0.6264 [2021-03-28 02:42:53 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 510/1251] eta: 0:07:52 lr: 0.000143 loss: 3.1955 (2.9075) grad_norm: 2.5282 (2.5114) time: 0.6261 [2021-03-28 02:42:59 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 520/1251] eta: 0:07:46 lr: 0.000143 loss: 3.1116 (2.9025) grad_norm: 2.3031 (2.5084) time: 0.6258 [2021-03-28 02:43:06 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 530/1251] eta: 0:07:39 lr: 0.000143 loss: 2.8322 (2.9021) grad_norm: 2.2972 (2.5061) time: 0.6282 [2021-03-28 02:43:12 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 540/1251] eta: 0:07:33 lr: 0.000143 loss: 2.9531 (2.9027) grad_norm: 2.3667 (2.5073) time: 0.6297 [2021-03-28 02:43:18 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 550/1251] eta: 0:07:26 lr: 0.000143 loss: 2.9549 (2.9037) grad_norm: 2.3671 (2.5072) time: 0.6352 [2021-03-28 02:43:25 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 560/1251] eta: 0:07:20 lr: 0.000143 loss: 2.8890 (2.8993) grad_norm: 2.5826 (2.5119) time: 0.6462 [2021-03-28 02:43:31 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 570/1251] eta: 0:07:14 lr: 0.000143 loss: 2.5951 (2.8970) grad_norm: 2.3903 (2.5103) time: 0.6405 [2021-03-28 02:43:38 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 580/1251] eta: 0:07:07 lr: 0.000143 loss: 2.9582 (2.8981) grad_norm: 2.3585 (2.5296) time: 0.6321 [2021-03-28 02:43:44 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 590/1251] eta: 0:07:01 lr: 0.000142 loss: 3.0784 (2.9006) grad_norm: 2.3622 (2.5257) time: 0.6397 [2021-03-28 02:43:50 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 600/1251] eta: 0:06:54 lr: 0.000142 loss: 3.1566 (2.9049) grad_norm: 2.2980 (2.5267) time: 0.6407 [2021-03-28 02:43:57 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 610/1251] eta: 0:06:48 lr: 0.000142 loss: 3.1530 (2.9047) grad_norm: 2.4502 (2.5840) time: 0.6380 [2021-03-28 02:44:03 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 620/1251] eta: 0:06:42 lr: 0.000142 loss: 3.0441 (2.9070) grad_norm: 2.4762 (2.5838) time: 0.6371 [2021-03-28 02:44:10 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 630/1251] eta: 0:06:35 lr: 0.000142 loss: 2.8687 (2.9054) grad_norm: 2.3401 (2.5799) time: 0.6362 [2021-03-28 02:44:16 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 640/1251] eta: 0:06:29 lr: 0.000142 loss: 2.8687 (2.9073) grad_norm: 2.3579 (2.5778) time: 0.6283 [2021-03-28 02:44:22 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 650/1251] eta: 0:06:22 lr: 0.000142 loss: 3.0985 (2.9081) grad_norm: 2.3640 (2.5802) time: 0.6242 [2021-03-28 02:44:28 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 660/1251] eta: 0:06:16 lr: 0.000142 loss: 3.0985 (2.9106) grad_norm: 2.4114 (2.5795) time: 0.6284 [2021-03-28 02:44:35 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 670/1251] eta: 0:06:09 lr: 0.000142 loss: 3.0206 (2.9071) grad_norm: 2.4114 (2.5790) time: 0.6293 [2021-03-28 02:44:41 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 680/1251] eta: 0:06:03 lr: 0.000142 loss: 2.7653 (2.9073) grad_norm: 2.2810 (2.5757) time: 0.6388 [2021-03-28 02:44:47 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 690/1251] eta: 0:05:57 lr: 0.000142 loss: 3.1373 (2.9092) grad_norm: 2.5019 (2.5794) time: 0.6361 [2021-03-28 02:44:54 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 700/1251] eta: 0:05:50 lr: 0.000142 loss: 2.9883 (2.9101) grad_norm: 2.5030 (2.5783) time: 0.6321 [2021-03-28 02:45:00 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 710/1251] eta: 0:05:44 lr: 0.000142 loss: 2.8968 (2.9080) grad_norm: 2.3179 (2.5756) time: 0.6342 [2021-03-28 02:45:06 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 720/1251] eta: 0:05:38 lr: 0.000142 loss: 2.8968 (2.9111) grad_norm: 2.2404 (2.5710) time: 0.6285 [2021-03-28 02:45:13 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 730/1251] eta: 0:05:31 lr: 0.000142 loss: 3.1822 (2.9128) grad_norm: 2.2766 (2.5689) time: 0.6262 [2021-03-28 02:45:19 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 740/1251] eta: 0:05:25 lr: 0.000142 loss: 3.0646 (2.9134) grad_norm: 2.2974 (2.5704) time: 0.6308 [2021-03-28 02:45:25 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 750/1251] eta: 0:05:18 lr: 0.000142 loss: 2.8738 (2.9112) grad_norm: 2.3455 (2.5690) time: 0.6391 [2021-03-28 02:45:32 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 760/1251] eta: 0:05:12 lr: 0.000142 loss: 2.7513 (2.9087) grad_norm: 2.4441 (2.5690) time: 0.6360 [2021-03-28 02:45:38 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 770/1251] eta: 0:05:06 lr: 0.000142 loss: 3.0262 (2.9101) grad_norm: 2.3762 (2.5665) time: 0.6362 [2021-03-28 02:45:44 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 780/1251] eta: 0:04:59 lr: 0.000142 loss: 3.0047 (2.9080) grad_norm: 2.3695 (2.5662) time: 0.6336 [2021-03-28 02:45:51 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 790/1251] eta: 0:04:53 lr: 0.000142 loss: 2.5524 (2.9031) grad_norm: 2.5882 (2.5684) time: 0.6272 [2021-03-28 02:45:57 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 800/1251] eta: 0:04:46 lr: 0.000142 loss: 2.5604 (2.9014) grad_norm: 2.5495 (2.5669) time: 0.6308 [2021-03-28 02:46:03 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 810/1251] eta: 0:04:40 lr: 0.000142 loss: 2.8327 (2.9019) grad_norm: 2.4880 (2.5690) time: 0.6331 [2021-03-28 02:46:10 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 820/1251] eta: 0:04:34 lr: 0.000142 loss: 2.9469 (2.9025) grad_norm: 2.4880 (2.5680) time: 0.6320 [2021-03-28 02:46:16 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 830/1251] eta: 0:04:27 lr: 0.000142 loss: 2.8294 (2.9019) grad_norm: 2.5504 (2.5680) time: 0.6267 [2021-03-28 02:46:22 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 840/1251] eta: 0:04:21 lr: 0.000142 loss: 2.8742 (2.9049) grad_norm: 2.5504 (2.5678) time: 0.6258 [2021-03-28 02:46:28 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 850/1251] eta: 0:04:14 lr: 0.000142 loss: 2.9197 (2.9054) grad_norm: 2.3653 (2.5664) time: 0.6266 [2021-03-28 02:46:35 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 860/1251] eta: 0:04:08 lr: 0.000142 loss: 2.9197 (2.9044) grad_norm: 2.4180 (2.5703) time: 0.6278 [2021-03-28 02:46:41 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 870/1251] eta: 0:04:02 lr: 0.000142 loss: 3.0916 (2.9067) grad_norm: 2.5203 (2.5693) time: 0.6295 [2021-03-28 02:46:47 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 880/1251] eta: 0:03:55 lr: 0.000142 loss: 3.0459 (2.9067) grad_norm: 2.4665 (2.5690) time: 0.6293 [2021-03-28 02:46:54 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 890/1251] eta: 0:03:49 lr: 0.000142 loss: 2.7568 (2.9026) grad_norm: 2.5312 (2.5712) time: 0.6309 [2021-03-28 02:47:00 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 900/1251] eta: 0:03:43 lr: 0.000142 loss: 2.6174 (2.9021) grad_norm: 2.5341 (2.5707) time: 0.6296 [2021-03-28 02:47:06 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 910/1251] eta: 0:03:36 lr: 0.000142 loss: 2.9774 (2.9028) grad_norm: 2.5341 (2.5739) time: 0.6259 [2021-03-28 02:47:12 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 920/1251] eta: 0:03:30 lr: 0.000142 loss: 3.0682 (2.9045) grad_norm: 2.3583 (2.5727) time: 0.6232 [2021-03-28 02:47:19 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 930/1251] eta: 0:03:23 lr: 0.000142 loss: 3.0623 (2.9049) grad_norm: 2.3873 (2.5723) time: 0.6279 [2021-03-28 02:47:25 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 940/1251] eta: 0:03:17 lr: 0.000142 loss: 2.8838 (2.9050) grad_norm: 2.4674 (2.5707) time: 0.6363 [2021-03-28 02:47:31 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 950/1251] eta: 0:03:11 lr: 0.000141 loss: 2.7900 (2.9008) grad_norm: 2.5042 (2.5720) time: 0.6337 [2021-03-28 02:47:38 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 960/1251] eta: 0:03:04 lr: 0.000141 loss: 2.9844 (2.9028) grad_norm: 2.3790 (2.5694) time: 0.6269 [2021-03-28 02:47:44 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 970/1251] eta: 0:02:58 lr: 0.000141 loss: 3.1347 (2.9040) grad_norm: 2.3031 (2.5665) time: 0.6281 [2021-03-28 02:47:50 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 980/1251] eta: 0:02:52 lr: 0.000141 loss: 3.1787 (2.9066) grad_norm: 2.2680 (2.5661) time: 0.6327 [2021-03-28 02:47:57 swin_base_patch4_window7_224] INFO: Epoch: [228] [ 990/1251] eta: 0:02:45 lr: 0.000141 loss: 3.1415 (2.9079) grad_norm: 2.3661 (2.5652) time: 0.6347 [2021-03-28 02:48:03 swin_base_patch4_window7_224] INFO: Epoch: [228] [1000/1251] eta: 0:02:39 lr: 0.000141 loss: 3.0331 (2.9065) grad_norm: 2.4287 (2.5664) time: 0.6322 [2021-03-28 02:48:09 swin_base_patch4_window7_224] INFO: Epoch: [228] [1010/1251] eta: 0:02:32 lr: 0.000141 loss: 3.0534 (2.9092) grad_norm: 2.8166 (2.5693) time: 0.6295 [2021-03-28 02:48:15 swin_base_patch4_window7_224] INFO: Epoch: [228] [1020/1251] eta: 0:02:26 lr: 0.000141 loss: 3.2279 (2.9100) grad_norm: 2.5965 (2.5689) time: 0.6281 [2021-03-28 02:48:22 swin_base_patch4_window7_224] INFO: Epoch: [228] [1030/1251] eta: 0:02:20 lr: 0.000141 loss: 3.1423 (2.9113) grad_norm: 2.3838 (2.5682) time: 0.6286 [2021-03-28 02:48:28 swin_base_patch4_window7_224] INFO: Epoch: [228] [1040/1251] eta: 0:02:13 lr: 0.000141 loss: 3.0379 (2.9119) grad_norm: 2.3988 (2.5689) time: 0.6295 [2021-03-28 02:48:34 swin_base_patch4_window7_224] INFO: Epoch: [228] [1050/1251] eta: 0:02:07 lr: 0.000141 loss: 2.9720 (2.9108) grad_norm: 2.4702 (2.5685) time: 0.6272 [2021-03-28 02:48:41 swin_base_patch4_window7_224] INFO: Epoch: [228] [1060/1251] eta: 0:02:01 lr: 0.000141 loss: 2.9747 (2.9094) grad_norm: 2.2946 (2.5660) time: 0.6306 [2021-03-28 02:48:47 swin_base_patch4_window7_224] INFO: Epoch: [228] [1070/1251] eta: 0:01:54 lr: 0.000141 loss: 3.0357 (2.9120) grad_norm: 2.3336 (2.5647) time: 0.6308 [2021-03-28 02:48:53 swin_base_patch4_window7_224] INFO: Epoch: [228] [1080/1251] eta: 0:01:48 lr: 0.000141 loss: 3.0357 (2.9115) grad_norm: 2.5163 (2.5663) time: 0.6291 [2021-03-28 02:49:00 swin_base_patch4_window7_224] INFO: Epoch: [228] [1090/1251] eta: 0:01:42 lr: 0.000141 loss: 3.0359 (2.9122) grad_norm: 2.6027 (2.5668) time: 0.6301 [2021-03-28 02:49:06 swin_base_patch4_window7_224] INFO: Epoch: [228] [1100/1251] eta: 0:01:35 lr: 0.000141 loss: 3.1595 (2.9143) grad_norm: 2.4669 (2.5667) time: 0.6273 [2021-03-28 02:49:12 swin_base_patch4_window7_224] INFO: Epoch: [228] [1110/1251] eta: 0:01:29 lr: 0.000141 loss: 3.1595 (2.9145) grad_norm: 2.4637 (2.5658) time: 0.6283 [2021-03-28 02:49:19 swin_base_patch4_window7_224] INFO: Epoch: [228] [1120/1251] eta: 0:01:23 lr: 0.000141 loss: 3.1253 (2.9160) grad_norm: 2.5242 (2.5671) time: 0.6341 [2021-03-28 02:49:25 swin_base_patch4_window7_224] INFO: Epoch: [228] [1130/1251] eta: 0:01:16 lr: 0.000141 loss: 3.1253 (2.9153) grad_norm: 2.5242 (2.5679) time: 0.6339 [2021-03-28 02:49:31 swin_base_patch4_window7_224] INFO: Epoch: [228] [1140/1251] eta: 0:01:10 lr: 0.000141 loss: 2.4634 (2.9136) grad_norm: 2.3680 (2.5658) time: 0.6285 [2021-03-28 02:49:37 swin_base_patch4_window7_224] INFO: Epoch: [228] [1150/1251] eta: 0:01:04 lr: 0.000141 loss: 2.8156 (2.9127) grad_norm: 2.3919 (2.5665) time: 0.6285 [2021-03-28 02:49:44 swin_base_patch4_window7_224] INFO: Epoch: [228] [1160/1251] eta: 0:00:57 lr: 0.000141 loss: 2.9784 (2.9132) grad_norm: 2.5700 (2.5735) time: 0.6267 [2021-03-28 02:49:50 swin_base_patch4_window7_224] INFO: Epoch: [228] [1170/1251] eta: 0:00:51 lr: 0.000141 loss: 3.0462 (2.9148) grad_norm: 2.6512 (2.5730) time: 0.6256 [2021-03-28 02:49:56 swin_base_patch4_window7_224] INFO: Epoch: [228] [1180/1251] eta: 0:00:45 lr: 0.000141 loss: 3.0280 (2.9149) grad_norm: 2.6368 (2.5734) time: 0.6316 [2021-03-28 02:50:03 swin_base_patch4_window7_224] INFO: Epoch: [228] [1190/1251] eta: 0:00:38 lr: 0.000141 loss: 2.9053 (2.9144) grad_norm: 2.5910 (2.5731) time: 0.6340 [2021-03-28 02:50:09 swin_base_patch4_window7_224] INFO: Epoch: [228] [1200/1251] eta: 0:00:32 lr: 0.000141 loss: 2.9418 (2.9142) grad_norm: 2.4028 (2.5722) time: 0.6300 [2021-03-28 02:50:15 swin_base_patch4_window7_224] INFO: Epoch: [228] [1210/1251] eta: 0:00:25 lr: 0.000141 loss: 2.9466 (2.9149) grad_norm: 2.5162 (2.5722) time: 0.6334 [2021-03-28 02:50:21 swin_base_patch4_window7_224] INFO: Epoch: [228] [1220/1251] eta: 0:00:19 lr: 0.000141 loss: 2.9127 (2.9121) grad_norm: 2.4118 (2.5708) time: 0.6321 [2021-03-28 02:50:28 swin_base_patch4_window7_224] INFO: Epoch: [228] [1230/1251] eta: 0:00:13 lr: 0.000141 loss: 2.7523 (2.9109) grad_norm: 2.3751 (2.5712) time: 0.6238 [2021-03-28 02:50:34 swin_base_patch4_window7_224] INFO: Epoch: [228] [1240/1251] eta: 0:00:06 lr: 0.000141 loss: 2.8599 (2.9107) grad_norm: 2.2864 (2.5693) time: 0.6263 [2021-03-28 02:50:40 swin_base_patch4_window7_224] INFO: Epoch: [228] [1250/1251] eta: 0:00:00 lr: 0.000141 loss: 2.8599 (2.9081) grad_norm: 2.4067 (2.5713) time: 0.6314 [2021-03-28 02:50:52 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:04 loss: 0.7439 (0.7439) acc1: 87.5000 (87.5000) acc5: 92.1875 (92.1875) [2021-03-28 02:50:54 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8200 (0.8867) acc1: 81.2500 (80.9659) acc5: 95.3125 (95.0284) [2021-03-28 02:50:56 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7641 (0.7978) acc1: 82.8125 (81.5476) acc5: 95.3125 (95.8333) [2021-03-28 02:50:58 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7037 (0.8118) acc1: 82.8125 (81.7540) acc5: 95.3125 (95.6149) [2021-03-28 02:51:00 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7473 (0.7881) acc1: 82.8125 (81.7073) acc5: 96.8750 (95.8841) [2021-03-28 02:51:01 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7707 (0.7960) acc1: 81.2500 (81.2480) acc5: 96.8750 (95.8720) [2021-03-28 02:51:15 swin_base_patch4_window7_224] INFO: * Acc@1 81.966 Acc@5 96.020 loss 0.777 [2021-03-28 02:51:15 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.0% [2021-03-28 02:51:15 swin_base_patch4_window7_224] INFO: Max accuracy: 82.15% [2021-03-28 02:51:20 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 0/1251] eta: 1:29:50 lr: 0.000141 loss: 2.0599 (2.0599) grad_norm: 2.3295 (2.3295) time: 4.3092 [2021-03-28 02:51:26 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 10/1251] eta: 0:20:07 lr: 0.000141 loss: 2.9994 (2.8052) grad_norm: 2.4435 (2.4243) time: 0.9727 [2021-03-28 02:51:32 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 20/1251] eta: 0:16:35 lr: 0.000141 loss: 2.8059 (2.7957) grad_norm: 2.2966 (2.7443) time: 0.6335 [2021-03-28 02:51:39 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 30/1251] eta: 0:15:19 lr: 0.000141 loss: 2.8038 (2.7899) grad_norm: 2.3131 (2.6956) time: 0.6324 [2021-03-28 02:51:45 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 40/1251] eta: 0:14:39 lr: 0.000141 loss: 2.8435 (2.8000) grad_norm: 2.3131 (2.6286) time: 0.6404 [2021-03-28 02:51:51 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 50/1251] eta: 0:14:08 lr: 0.000140 loss: 2.9276 (2.7907) grad_norm: 2.3025 (2.5798) time: 0.6350 [2021-03-28 02:51:58 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 60/1251] eta: 0:13:47 lr: 0.000140 loss: 2.9275 (2.7926) grad_norm: 2.4738 (2.5882) time: 0.6288 [2021-03-28 02:52:04 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 70/1251] eta: 0:13:29 lr: 0.000140 loss: 2.6845 (2.7823) grad_norm: 2.5326 (2.5805) time: 0.6318 [2021-03-28 02:52:10 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 80/1251] eta: 0:13:15 lr: 0.000140 loss: 2.9004 (2.8043) grad_norm: 2.4523 (2.5693) time: 0.6327 [2021-03-28 02:52:17 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 90/1251] eta: 0:13:02 lr: 0.000140 loss: 2.8951 (2.8025) grad_norm: 2.4134 (2.5600) time: 0.6322 [2021-03-28 02:52:23 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 100/1251] eta: 0:12:52 lr: 0.000140 loss: 2.8726 (2.8217) grad_norm: 2.3463 (2.5637) time: 0.6380 [2021-03-28 02:52:29 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 110/1251] eta: 0:12:41 lr: 0.000140 loss: 2.9657 (2.8326) grad_norm: 2.4422 (2.5688) time: 0.6369 [2021-03-28 02:52:36 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 120/1251] eta: 0:12:31 lr: 0.000140 loss: 2.8307 (2.8215) grad_norm: 2.7199 (2.5890) time: 0.6308 [2021-03-28 02:52:42 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 130/1251] eta: 0:12:21 lr: 0.000140 loss: 2.8218 (2.8238) grad_norm: 2.7057 (2.5943) time: 0.6295 [2021-03-28 02:52:48 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 140/1251] eta: 0:12:12 lr: 0.000140 loss: 3.0206 (2.8217) grad_norm: 2.5414 (2.5886) time: 0.6278 [2021-03-28 02:52:55 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 150/1251] eta: 0:12:03 lr: 0.000140 loss: 2.9612 (2.8186) grad_norm: 2.4279 (2.5842) time: 0.6270 [2021-03-28 02:53:01 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 160/1251] eta: 0:11:54 lr: 0.000140 loss: 3.1085 (2.8449) grad_norm: 2.3473 (2.5742) time: 0.6272 [2021-03-28 02:53:07 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 170/1251] eta: 0:11:46 lr: 0.000140 loss: 3.1085 (2.8538) grad_norm: 2.3884 (2.5648) time: 0.6309 [2021-03-28 02:53:14 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 180/1251] eta: 0:11:39 lr: 0.000140 loss: 3.0384 (2.8706) grad_norm: 2.3884 (2.5673) time: 0.6350 [2021-03-28 02:53:20 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 190/1251] eta: 0:11:31 lr: 0.000140 loss: 3.0384 (2.8547) grad_norm: 2.4614 (2.5716) time: 0.6346 [2021-03-28 02:53:26 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 200/1251] eta: 0:11:24 lr: 0.000140 loss: 2.7041 (2.8574) grad_norm: 2.4614 (2.5671) time: 0.6315 [2021-03-28 02:53:32 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 210/1251] eta: 0:11:16 lr: 0.000140 loss: 2.9000 (2.8535) grad_norm: 2.4564 (2.5680) time: 0.6275 [2021-03-28 02:53:39 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 220/1251] eta: 0:11:09 lr: 0.000140 loss: 3.1217 (2.8642) grad_norm: 2.3790 (2.5726) time: 0.6298 [2021-03-28 02:53:45 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 230/1251] eta: 0:11:02 lr: 0.000140 loss: 3.1450 (2.8636) grad_norm: 2.2632 (2.5605) time: 0.6376 [2021-03-28 02:53:52 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 240/1251] eta: 0:10:55 lr: 0.000140 loss: 2.8778 (2.8644) grad_norm: 2.1696 (2.5464) time: 0.6410 [2021-03-28 02:53:58 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 250/1251] eta: 0:10:48 lr: 0.000140 loss: 2.8778 (2.8635) grad_norm: 2.2046 (2.5503) time: 0.6360 [2021-03-28 02:54:04 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 260/1251] eta: 0:10:41 lr: 0.000140 loss: 2.8725 (2.8627) grad_norm: 2.3603 (2.5619) time: 0.6309 [2021-03-28 02:54:11 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 270/1251] eta: 0:10:34 lr: 0.000140 loss: 2.8405 (2.8636) grad_norm: 2.5322 (2.5628) time: 0.6354 [2021-03-28 02:54:17 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 280/1251] eta: 0:10:27 lr: 0.000140 loss: 2.9003 (2.8616) grad_norm: 2.4082 (2.5558) time: 0.6321 [2021-03-28 02:54:23 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 290/1251] eta: 0:10:20 lr: 0.000140 loss: 3.0959 (2.8724) grad_norm: 2.3699 (2.5604) time: 0.6287 [2021-03-28 02:54:29 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 300/1251] eta: 0:10:13 lr: 0.000140 loss: 3.0846 (2.8727) grad_norm: 2.5647 (2.5621) time: 0.6268 [2021-03-28 02:54:36 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 310/1251] eta: 0:10:06 lr: 0.000140 loss: 3.0314 (2.8696) grad_norm: 2.5419 (2.5624) time: 0.6263 [2021-03-28 02:54:42 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 320/1251] eta: 0:09:59 lr: 0.000140 loss: 2.7967 (2.8643) grad_norm: 2.5419 (2.5652) time: 0.6315 [2021-03-28 02:54:48 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 330/1251] eta: 0:09:52 lr: 0.000140 loss: 2.8096 (2.8642) grad_norm: 2.4990 (2.5645) time: 0.6275 [2021-03-28 02:54:55 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 340/1251] eta: 0:09:45 lr: 0.000140 loss: 3.1234 (2.8726) grad_norm: 2.4766 (2.5850) time: 0.6226 [2021-03-28 02:55:01 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 350/1251] eta: 0:09:38 lr: 0.000140 loss: 3.1111 (2.8721) grad_norm: 2.5015 (2.5887) time: 0.6231 [2021-03-28 02:55:07 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 360/1251] eta: 0:09:31 lr: 0.000140 loss: 2.9097 (2.8739) grad_norm: 2.4100 (2.5864) time: 0.6265 [2021-03-28 02:55:13 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 370/1251] eta: 0:09:25 lr: 0.000140 loss: 3.0655 (2.8762) grad_norm: 2.3764 (2.5884) time: 0.6339 [2021-03-28 02:55:20 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 380/1251] eta: 0:09:18 lr: 0.000140 loss: 2.9016 (2.8681) grad_norm: 2.4102 (2.5840) time: 0.6348 [2021-03-28 02:55:26 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 390/1251] eta: 0:09:11 lr: 0.000140 loss: 2.4567 (2.8627) grad_norm: 2.4164 (2.5916) time: 0.6299 [2021-03-28 02:55:32 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 400/1251] eta: 0:09:05 lr: 0.000140 loss: 2.7064 (2.8607) grad_norm: 2.4389 (2.6035) time: 0.6302 [2021-03-28 02:55:39 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 410/1251] eta: 0:08:58 lr: 0.000139 loss: 2.8920 (2.8619) grad_norm: 2.4389 (2.6026) time: 0.6316 [2021-03-28 02:55:45 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 420/1251] eta: 0:08:52 lr: 0.000139 loss: 2.9017 (2.8570) grad_norm: 2.3798 (2.5994) time: 0.6311 [2021-03-28 02:55:51 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 430/1251] eta: 0:08:45 lr: 0.000139 loss: 2.6846 (2.8512) grad_norm: 2.3798 (2.5977) time: 0.6290 [2021-03-28 02:55:58 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 440/1251] eta: 0:08:38 lr: 0.000139 loss: 2.6846 (2.8492) grad_norm: 2.4587 (2.5933) time: 0.6263 [2021-03-28 02:56:04 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 450/1251] eta: 0:08:32 lr: 0.000139 loss: 2.7502 (2.8445) grad_norm: 2.3984 (2.5923) time: 0.6290 [2021-03-28 02:56:10 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 460/1251] eta: 0:08:25 lr: 0.000139 loss: 2.9512 (2.8492) grad_norm: 2.3659 (2.5900) time: 0.6280 [2021-03-28 02:56:16 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 470/1251] eta: 0:08:18 lr: 0.000139 loss: 3.0309 (2.8524) grad_norm: 2.3432 (2.5855) time: 0.6256 [2021-03-28 02:56:23 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 480/1251] eta: 0:08:12 lr: 0.000139 loss: 3.0114 (2.8556) grad_norm: 2.3737 (2.5867) time: 0.6250 [2021-03-28 02:56:29 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 490/1251] eta: 0:08:05 lr: 0.000139 loss: 2.9758 (2.8591) grad_norm: 2.5103 (2.5840) time: 0.6268 [2021-03-28 02:56:35 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 500/1251] eta: 0:07:59 lr: 0.000139 loss: 2.9091 (2.8552) grad_norm: 2.3040 (2.5880) time: 0.6338 [2021-03-28 02:56:42 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 510/1251] eta: 0:07:52 lr: 0.000139 loss: 2.7982 (2.8567) grad_norm: 2.2681 (2.5845) time: 0.6308 [2021-03-28 02:56:48 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 520/1251] eta: 0:07:46 lr: 0.000139 loss: 3.0196 (2.8593) grad_norm: 2.2600 (2.5809) time: 0.6239 [2021-03-28 02:56:54 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 530/1251] eta: 0:07:39 lr: 0.000139 loss: 3.0270 (2.8594) grad_norm: 2.3414 (2.5799) time: 0.6266 [2021-03-28 02:57:00 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 540/1251] eta: 0:07:33 lr: 0.000139 loss: 2.8990 (2.8643) grad_norm: 2.3369 (2.5764) time: 0.6275 [2021-03-28 02:57:07 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 550/1251] eta: 0:07:26 lr: 0.000139 loss: 2.9118 (2.8677) grad_norm: 2.2891 (2.5731) time: 0.6303 [2021-03-28 02:57:13 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 560/1251] eta: 0:07:20 lr: 0.000139 loss: 3.1115 (2.8705) grad_norm: 2.3801 (2.5718) time: 0.6318 [2021-03-28 02:57:19 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 570/1251] eta: 0:07:14 lr: 0.000139 loss: 3.1746 (2.8754) grad_norm: 2.2540 (2.5682) time: 0.6342 [2021-03-28 02:57:26 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 580/1251] eta: 0:07:07 lr: 0.000139 loss: 3.0801 (2.8726) grad_norm: 2.3888 (2.5676) time: 0.6356 [2021-03-28 02:57:32 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 590/1251] eta: 0:07:01 lr: 0.000139 loss: 2.7853 (2.8707) grad_norm: 2.4696 (2.5650) time: 0.6340 [2021-03-28 02:57:38 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 600/1251] eta: 0:06:54 lr: 0.000139 loss: 2.7178 (2.8653) grad_norm: 2.4014 (2.5636) time: 0.6332 [2021-03-28 02:57:45 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 610/1251] eta: 0:06:48 lr: 0.000139 loss: 2.8603 (2.8681) grad_norm: 2.5245 (2.5686) time: 0.6266 [2021-03-28 02:57:51 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 620/1251] eta: 0:06:41 lr: 0.000139 loss: 3.0815 (2.8680) grad_norm: 2.6295 (2.5690) time: 0.6258 [2021-03-28 02:57:57 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 630/1251] eta: 0:06:35 lr: 0.000139 loss: 3.0782 (2.8714) grad_norm: 2.6295 (2.5701) time: 0.6283 [2021-03-28 02:58:03 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 640/1251] eta: 0:06:28 lr: 0.000139 loss: 3.0699 (2.8732) grad_norm: 2.5238 (2.5712) time: 0.6292 [2021-03-28 02:58:10 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 650/1251] eta: 0:06:22 lr: 0.000139 loss: 3.0679 (2.8731) grad_norm: 2.4895 (2.5691) time: 0.6281 [2021-03-28 02:58:16 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 660/1251] eta: 0:06:15 lr: 0.000139 loss: 3.0178 (2.8745) grad_norm: 2.5474 (2.5899) time: 0.6265 [2021-03-28 02:58:22 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 670/1251] eta: 0:06:09 lr: 0.000139 loss: 2.9441 (2.8745) grad_norm: 2.5566 (2.5875) time: 0.6317 [2021-03-28 02:58:29 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 680/1251] eta: 0:06:03 lr: 0.000139 loss: 2.8958 (2.8725) grad_norm: 2.3178 (2.5871) time: 0.6334 [2021-03-28 02:58:35 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 690/1251] eta: 0:05:56 lr: 0.000139 loss: 2.8623 (2.8730) grad_norm: 2.4735 (2.5910) time: 0.6316 [2021-03-28 02:58:41 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 700/1251] eta: 0:05:50 lr: 0.000139 loss: 2.9456 (2.8729) grad_norm: 2.5878 (2.5959) time: 0.6327 [2021-03-28 02:58:48 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 710/1251] eta: 0:05:44 lr: 0.000139 loss: 2.9236 (2.8711) grad_norm: 2.5192 (2.5978) time: 0.6343 [2021-03-28 02:58:54 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 720/1251] eta: 0:05:37 lr: 0.000139 loss: 2.9366 (2.8729) grad_norm: 2.5645 (2.5971) time: 0.6303 [2021-03-28 02:59:00 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 730/1251] eta: 0:05:31 lr: 0.000139 loss: 2.9366 (2.8714) grad_norm: 2.3593 (2.5930) time: 0.6279 [2021-03-28 02:59:07 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 740/1251] eta: 0:05:24 lr: 0.000139 loss: 2.6777 (2.8705) grad_norm: 2.3437 (2.5935) time: 0.6371 [2021-03-28 02:59:13 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 750/1251] eta: 0:05:18 lr: 0.000139 loss: 2.8171 (2.8686) grad_norm: 2.4631 (2.5973) time: 0.6501 [2021-03-28 02:59:20 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 760/1251] eta: 0:05:12 lr: 0.000139 loss: 2.9067 (2.8668) grad_norm: 2.3882 (2.5936) time: 0.6448 [2021-03-28 02:59:26 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 770/1251] eta: 0:05:05 lr: 0.000138 loss: 2.7652 (2.8652) grad_norm: 2.3375 (2.5941) time: 0.6302 [2021-03-28 02:59:32 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 780/1251] eta: 0:04:59 lr: 0.000138 loss: 2.7399 (2.8640) grad_norm: 2.3650 (2.5905) time: 0.6302 [2021-03-28 02:59:39 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 790/1251] eta: 0:04:53 lr: 0.000138 loss: 2.5995 (2.8583) grad_norm: 2.2890 (2.5886) time: 0.6312 [2021-03-28 02:59:45 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 800/1251] eta: 0:04:46 lr: 0.000138 loss: 2.6344 (2.8578) grad_norm: 2.5979 (2.5895) time: 0.6324 [2021-03-28 02:59:51 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 810/1251] eta: 0:04:40 lr: 0.000138 loss: 2.8493 (2.8579) grad_norm: 2.6605 (2.5941) time: 0.6286 [2021-03-28 02:59:57 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 820/1251] eta: 0:04:33 lr: 0.000138 loss: 2.9531 (2.8583) grad_norm: 2.5103 (2.5922) time: 0.6240 [2021-03-28 03:00:04 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 830/1251] eta: 0:04:27 lr: 0.000138 loss: 2.9531 (2.8583) grad_norm: 2.4180 (2.5926) time: 0.6305 [2021-03-28 03:00:10 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 840/1251] eta: 0:04:21 lr: 0.000138 loss: 3.0171 (2.8611) grad_norm: 2.4486 (2.5948) time: 0.6301 [2021-03-28 03:00:16 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 850/1251] eta: 0:04:14 lr: 0.000138 loss: 2.9815 (2.8593) grad_norm: 2.3398 (2.5911) time: 0.6288 [2021-03-28 03:00:23 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 860/1251] eta: 0:04:08 lr: 0.000138 loss: 2.8600 (2.8588) grad_norm: 2.2585 (2.5871) time: 0.6306 [2021-03-28 03:00:29 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 870/1251] eta: 0:04:02 lr: 0.000138 loss: 2.8601 (2.8582) grad_norm: 2.3486 (2.5858) time: 0.6297 [2021-03-28 03:00:35 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 880/1251] eta: 0:03:55 lr: 0.000138 loss: 2.7160 (2.8567) grad_norm: 2.4584 (2.5859) time: 0.6354 [2021-03-28 03:00:42 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 890/1251] eta: 0:03:49 lr: 0.000138 loss: 2.7498 (2.8577) grad_norm: 2.4594 (2.5849) time: 0.6335 [2021-03-28 03:00:48 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 900/1251] eta: 0:03:42 lr: 0.000138 loss: 2.8679 (2.8586) grad_norm: 2.4360 (2.5826) time: 0.6347 [2021-03-28 03:00:54 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 910/1251] eta: 0:03:36 lr: 0.000138 loss: 2.8679 (2.8582) grad_norm: 2.4044 (2.5840) time: 0.6316 [2021-03-28 03:01:01 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 920/1251] eta: 0:03:30 lr: 0.000138 loss: 2.8931 (2.8568) grad_norm: 2.4437 (2.5843) time: 0.6265 [2021-03-28 03:01:07 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 930/1251] eta: 0:03:23 lr: 0.000138 loss: 2.8931 (2.8564) grad_norm: 2.4530 (2.5838) time: 0.6330 [2021-03-28 03:01:13 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 940/1251] eta: 0:03:17 lr: 0.000138 loss: 2.9051 (2.8564) grad_norm: 2.3658 (2.5819) time: 0.6376 [2021-03-28 03:01:20 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 950/1251] eta: 0:03:11 lr: 0.000138 loss: 2.9166 (2.8564) grad_norm: 2.3846 (2.5810) time: 0.6322 [2021-03-28 03:01:26 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 960/1251] eta: 0:03:04 lr: 0.000138 loss: 2.9415 (2.8577) grad_norm: 2.4366 (2.5800) time: 0.6232 [2021-03-28 03:01:32 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 970/1251] eta: 0:02:58 lr: 0.000138 loss: 3.1130 (2.8585) grad_norm: 2.4400 (2.5790) time: 0.6302 [2021-03-28 03:01:38 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 980/1251] eta: 0:02:52 lr: 0.000138 loss: 2.9307 (2.8571) grad_norm: 2.5224 (2.5846) time: 0.6375 [2021-03-28 03:01:45 swin_base_patch4_window7_224] INFO: Epoch: [229] [ 990/1251] eta: 0:02:45 lr: 0.000138 loss: 2.6904 (2.8550) grad_norm: 2.3022 (2.5820) time: 0.6299 [2021-03-28 03:01:51 swin_base_patch4_window7_224] INFO: Epoch: [229] [1000/1251] eta: 0:02:39 lr: 0.000138 loss: 2.8356 (2.8563) grad_norm: 2.3022 (2.5806) time: 0.6313 [2021-03-28 03:01:57 swin_base_patch4_window7_224] INFO: Epoch: [229] [1010/1251] eta: 0:02:32 lr: 0.000138 loss: 2.8909 (2.8558) grad_norm: 2.3361 (2.5795) time: 0.6313 [2021-03-28 03:02:04 swin_base_patch4_window7_224] INFO: Epoch: [229] [1020/1251] eta: 0:02:26 lr: 0.000138 loss: 3.0876 (2.8577) grad_norm: 2.4818 (2.5809) time: 0.6274 [2021-03-28 03:02:10 swin_base_patch4_window7_224] INFO: Epoch: [229] [1030/1251] eta: 0:02:20 lr: 0.000138 loss: 3.0960 (2.8589) grad_norm: 2.5066 (2.5778) time: 0.6307 [2021-03-28 03:02:16 swin_base_patch4_window7_224] INFO: Epoch: [229] [1040/1251] eta: 0:02:13 lr: 0.000138 loss: 2.9136 (2.8580) grad_norm: 2.2938 (2.5770) time: 0.6325 [2021-03-28 03:02:23 swin_base_patch4_window7_224] INFO: Epoch: [229] [1050/1251] eta: 0:02:07 lr: 0.000138 loss: 2.9807 (2.8600) grad_norm: 2.5677 (2.5789) time: 0.6302 [2021-03-28 03:02:29 swin_base_patch4_window7_224] INFO: Epoch: [229] [1060/1251] eta: 0:02:01 lr: 0.000138 loss: 3.0268 (2.8604) grad_norm: 2.6161 (2.5789) time: 0.6311 [2021-03-28 03:02:35 swin_base_patch4_window7_224] INFO: Epoch: [229] [1070/1251] eta: 0:01:54 lr: 0.000138 loss: 2.9687 (2.8601) grad_norm: 2.6404 (2.5816) time: 0.6342 [2021-03-28 03:02:42 swin_base_patch4_window7_224] INFO: Epoch: [229] [1080/1251] eta: 0:01:48 lr: 0.000138 loss: 3.1082 (2.8635) grad_norm: 2.4744 (2.5820) time: 0.6293 [2021-03-28 03:02:48 swin_base_patch4_window7_224] INFO: Epoch: [229] [1090/1251] eta: 0:01:42 lr: 0.000138 loss: 3.1082 (2.8642) grad_norm: 2.4083 (2.5810) time: 0.6275 [2021-03-28 03:02:54 swin_base_patch4_window7_224] INFO: Epoch: [229] [1100/1251] eta: 0:01:35 lr: 0.000138 loss: 3.0066 (2.8650) grad_norm: 2.5101 (2.5835) time: 0.6272 [2021-03-28 03:03:00 swin_base_patch4_window7_224] INFO: Epoch: [229] [1110/1251] eta: 0:01:29 lr: 0.000138 loss: 2.8995 (2.8649) grad_norm: 2.6074 (2.5838) time: 0.6284 [2021-03-28 03:03:07 swin_base_patch4_window7_224] INFO: Epoch: [229] [1120/1251] eta: 0:01:23 lr: 0.000138 loss: 2.7693 (2.8655) grad_norm: 2.4721 (2.5834) time: 0.6344 [2021-03-28 03:03:13 swin_base_patch4_window7_224] INFO: Epoch: [229] [1130/1251] eta: 0:01:16 lr: 0.000137 loss: 2.8753 (2.8662) grad_norm: 2.4726 (2.5836) time: 0.6319 [2021-03-28 03:03:19 swin_base_patch4_window7_224] INFO: Epoch: [229] [1140/1251] eta: 0:01:10 lr: 0.000137 loss: 2.8195 (2.8645) grad_norm: 2.5824 (2.5830) time: 0.6257 [2021-03-28 03:03:26 swin_base_patch4_window7_224] INFO: Epoch: [229] [1150/1251] eta: 0:01:04 lr: 0.000137 loss: 2.8195 (2.8649) grad_norm: 2.2927 (2.5815) time: 0.6332 [2021-03-28 03:03:32 swin_base_patch4_window7_224] INFO: Epoch: [229] [1160/1251] eta: 0:00:57 lr: 0.000137 loss: 3.2079 (2.8679) grad_norm: 2.3195 (2.5808) time: 0.6356 [2021-03-28 03:03:38 swin_base_patch4_window7_224] INFO: Epoch: [229] [1170/1251] eta: 0:00:51 lr: 0.000137 loss: 3.1923 (2.8699) grad_norm: 2.3490 (2.5849) time: 0.6331 [2021-03-28 03:03:45 swin_base_patch4_window7_224] INFO: Epoch: [229] [1180/1251] eta: 0:00:45 lr: 0.000137 loss: 3.0312 (2.8697) grad_norm: 2.2461 (2.5839) time: 0.6369 [2021-03-28 03:03:51 swin_base_patch4_window7_224] INFO: Epoch: [229] [1190/1251] eta: 0:00:38 lr: 0.000137 loss: 2.9286 (2.8701) grad_norm: 2.4793 (2.5858) time: 0.6321 [2021-03-28 03:03:57 swin_base_patch4_window7_224] INFO: Epoch: [229] [1200/1251] eta: 0:00:32 lr: 0.000137 loss: 3.0261 (2.8724) grad_norm: 2.4565 (2.5850) time: 0.6297 [2021-03-28 03:04:04 swin_base_patch4_window7_224] INFO: Epoch: [229] [1210/1251] eta: 0:00:26 lr: 0.000137 loss: 3.0160 (2.8723) grad_norm: 2.4316 (2.5837) time: 0.6315 [2021-03-28 03:04:10 swin_base_patch4_window7_224] INFO: Epoch: [229] [1220/1251] eta: 0:00:19 lr: 0.000137 loss: 2.8311 (2.8706) grad_norm: 2.4598 (2.5881) time: 0.6287 [2021-03-28 03:04:16 swin_base_patch4_window7_224] INFO: Epoch: [229] [1230/1251] eta: 0:00:13 lr: 0.000137 loss: 2.9681 (2.8710) grad_norm: 2.4521 (2.5888) time: 0.6330 [2021-03-28 03:04:23 swin_base_patch4_window7_224] INFO: Epoch: [229] [1240/1251] eta: 0:00:06 lr: 0.000137 loss: 2.9695 (2.8720) grad_norm: 2.3935 (2.5882) time: 0.6303 [2021-03-28 03:04:29 swin_base_patch4_window7_224] INFO: Epoch: [229] [1250/1251] eta: 0:00:00 lr: 0.000137 loss: 2.8110 (2.8713) grad_norm: 2.4089 (2.5881) time: 0.6257 [2021-03-28 03:04:38 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:05 loss: 0.8587 (0.8587) acc1: 78.1250 (78.1250) acc5: 93.7500 (93.7500) [2021-03-28 03:04:42 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7543 (0.7614) acc1: 82.8125 (80.3977) acc5: 96.8750 (96.4489) [2021-03-28 03:04:44 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7987 (0.7973) acc1: 81.2500 (81.0268) acc5: 96.8750 (96.4286) [2021-03-28 03:04:46 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8369 (0.7979) acc1: 81.2500 (81.3004) acc5: 95.3125 (96.4718) [2021-03-28 03:04:48 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7200 (0.7751) acc1: 82.8125 (81.7073) acc5: 95.3125 (96.5701) [2021-03-28 03:04:49 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7389 (0.7892) acc1: 81.2500 (81.5360) acc5: 95.3125 (96.3200) [2021-03-28 03:05:03 swin_base_patch4_window7_224] INFO: * Acc@1 82.076 Acc@5 96.134 loss 0.775 [2021-03-28 03:05:03 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.1% [2021-03-28 03:05:03 swin_base_patch4_window7_224] INFO: Max accuracy: 82.15% [2021-03-28 03:05:07 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 0/1251] eta: 1:28:08 lr: 0.000137 loss: 3.3618 (3.3618) grad_norm: 2.4071 (2.4071) time: 4.2275 [2021-03-28 03:05:13 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 10/1251] eta: 0:19:46 lr: 0.000137 loss: 3.1107 (2.9689) grad_norm: 2.6512 (3.2328) time: 0.9560 [2021-03-28 03:05:20 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 20/1251] eta: 0:16:27 lr: 0.000137 loss: 2.9987 (2.8135) grad_norm: 2.5810 (3.0330) time: 0.6308 [2021-03-28 03:05:26 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 30/1251] eta: 0:15:10 lr: 0.000137 loss: 2.8191 (2.8043) grad_norm: 2.3806 (2.8526) time: 0.6300 [2021-03-28 03:05:32 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 40/1251] eta: 0:14:30 lr: 0.000137 loss: 2.9788 (2.8135) grad_norm: 2.5188 (2.8235) time: 0.6308 [2021-03-28 03:05:38 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 50/1251] eta: 0:14:02 lr: 0.000137 loss: 2.9877 (2.8393) grad_norm: 2.5854 (2.7906) time: 0.6327 [2021-03-28 03:05:45 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 60/1251] eta: 0:13:43 lr: 0.000137 loss: 2.7760 (2.8119) grad_norm: 2.4283 (2.7464) time: 0.6363 [2021-03-28 03:05:51 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 70/1251] eta: 0:13:24 lr: 0.000137 loss: 2.6780 (2.7856) grad_norm: 2.3612 (2.7150) time: 0.6313 [2021-03-28 03:05:57 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 80/1251] eta: 0:13:10 lr: 0.000137 loss: 2.8173 (2.7807) grad_norm: 2.2374 (2.6727) time: 0.6263 [2021-03-28 03:06:04 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 90/1251] eta: 0:12:58 lr: 0.000137 loss: 2.9220 (2.7986) grad_norm: 2.3144 (2.6370) time: 0.6323 [2021-03-28 03:06:10 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 100/1251] eta: 0:12:48 lr: 0.000137 loss: 3.0082 (2.8004) grad_norm: 2.3565 (2.6073) time: 0.6350 [2021-03-28 03:06:16 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 110/1251] eta: 0:12:38 lr: 0.000137 loss: 2.9585 (2.7975) grad_norm: 2.3424 (2.6114) time: 0.6351 [2021-03-28 03:06:23 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 120/1251] eta: 0:12:28 lr: 0.000137 loss: 2.8697 (2.8053) grad_norm: 2.3862 (2.6271) time: 0.6312 [2021-03-28 03:06:29 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 130/1251] eta: 0:12:19 lr: 0.000137 loss: 2.8697 (2.8045) grad_norm: 2.4307 (2.6171) time: 0.6325 [2021-03-28 03:06:36 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 140/1251] eta: 0:12:11 lr: 0.000137 loss: 2.8903 (2.8138) grad_norm: 2.4892 (2.6312) time: 0.6415 [2021-03-28 03:06:42 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 150/1251] eta: 0:12:02 lr: 0.000137 loss: 2.9339 (2.8211) grad_norm: 2.4762 (2.6234) time: 0.6360 [2021-03-28 03:06:48 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 160/1251] eta: 0:11:54 lr: 0.000137 loss: 2.8889 (2.8207) grad_norm: 2.4346 (2.6251) time: 0.6251 [2021-03-28 03:06:54 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 170/1251] eta: 0:11:45 lr: 0.000137 loss: 2.7835 (2.8172) grad_norm: 2.4346 (2.6165) time: 0.6263 [2021-03-28 03:07:01 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 180/1251] eta: 0:11:37 lr: 0.000137 loss: 2.7835 (2.8026) grad_norm: 2.4416 (2.6093) time: 0.6273 [2021-03-28 03:07:07 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 190/1251] eta: 0:11:29 lr: 0.000137 loss: 2.7277 (2.7949) grad_norm: 2.5548 (2.6154) time: 0.6257 [2021-03-28 03:07:13 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 200/1251] eta: 0:11:22 lr: 0.000137 loss: 2.8194 (2.8035) grad_norm: 2.6134 (2.6096) time: 0.6347 [2021-03-28 03:07:20 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 210/1251] eta: 0:11:15 lr: 0.000137 loss: 3.0662 (2.8122) grad_norm: 2.5109 (2.6113) time: 0.6376 [2021-03-28 03:07:26 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 220/1251] eta: 0:11:08 lr: 0.000137 loss: 2.9591 (2.8105) grad_norm: 2.6199 (2.6159) time: 0.6302 [2021-03-28 03:07:32 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 230/1251] eta: 0:11:01 lr: 0.000137 loss: 2.6061 (2.7988) grad_norm: 2.5196 (2.6065) time: 0.6336 [2021-03-28 03:07:39 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 240/1251] eta: 0:10:53 lr: 0.000136 loss: 2.5411 (2.7960) grad_norm: 2.3596 (2.5985) time: 0.6322 [2021-03-28 03:07:45 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 250/1251] eta: 0:10:46 lr: 0.000136 loss: 2.6082 (2.7947) grad_norm: 2.4211 (2.5982) time: 0.6267 [2021-03-28 03:07:51 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 260/1251] eta: 0:10:39 lr: 0.000136 loss: 2.7532 (2.7919) grad_norm: 2.3264 (2.5874) time: 0.6266 [2021-03-28 03:07:57 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 270/1251] eta: 0:10:32 lr: 0.000136 loss: 2.7879 (2.7946) grad_norm: 2.2566 (2.5740) time: 0.6266 [2021-03-28 03:08:04 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 280/1251] eta: 0:10:25 lr: 0.000136 loss: 3.0285 (2.8008) grad_norm: 2.2566 (2.5688) time: 0.6300 [2021-03-28 03:08:10 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 290/1251] eta: 0:10:18 lr: 0.000136 loss: 3.0216 (2.8000) grad_norm: 2.2458 (2.5582) time: 0.6331 [2021-03-28 03:08:16 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 300/1251] eta: 0:10:11 lr: 0.000136 loss: 2.8213 (2.7969) grad_norm: 2.3935 (2.5628) time: 0.6293 [2021-03-28 03:08:23 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 310/1251] eta: 0:10:05 lr: 0.000136 loss: 2.8213 (2.7964) grad_norm: 2.5590 (2.5666) time: 0.6347 [2021-03-28 03:08:29 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 320/1251] eta: 0:09:58 lr: 0.000136 loss: 2.8762 (2.7993) grad_norm: 2.5619 (2.5743) time: 0.6395 [2021-03-28 03:08:36 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 330/1251] eta: 0:09:52 lr: 0.000136 loss: 2.8631 (2.7926) grad_norm: 2.5094 (2.5700) time: 0.6393 [2021-03-28 03:08:42 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 340/1251] eta: 0:09:45 lr: 0.000136 loss: 2.8433 (2.7995) grad_norm: 2.3777 (2.5614) time: 0.6394 [2021-03-28 03:08:48 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 350/1251] eta: 0:09:38 lr: 0.000136 loss: 2.9618 (2.7998) grad_norm: 2.2215 (2.5523) time: 0.6375 [2021-03-28 03:08:55 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 360/1251] eta: 0:09:32 lr: 0.000136 loss: 2.6634 (2.7974) grad_norm: 2.3586 (2.5563) time: 0.6354 [2021-03-28 03:09:01 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 370/1251] eta: 0:09:25 lr: 0.000136 loss: 2.6634 (2.8000) grad_norm: 2.4009 (2.5502) time: 0.6282 [2021-03-28 03:09:07 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 380/1251] eta: 0:09:18 lr: 0.000136 loss: 2.7533 (2.8017) grad_norm: 2.3629 (2.5615) time: 0.6300 [2021-03-28 03:09:13 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 390/1251] eta: 0:09:11 lr: 0.000136 loss: 2.8713 (2.8014) grad_norm: 2.4883 (2.5609) time: 0.6282 [2021-03-28 03:09:20 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 400/1251] eta: 0:09:05 lr: 0.000136 loss: 2.9391 (2.8043) grad_norm: 2.4883 (2.5635) time: 0.6256 [2021-03-28 03:09:26 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 410/1251] eta: 0:08:58 lr: 0.000136 loss: 2.9607 (2.8026) grad_norm: 2.3978 (2.5622) time: 0.6293 [2021-03-28 03:09:32 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 420/1251] eta: 0:08:51 lr: 0.000136 loss: 2.8323 (2.8034) grad_norm: 2.2868 (2.5604) time: 0.6269 [2021-03-28 03:09:39 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 430/1251] eta: 0:08:45 lr: 0.000136 loss: 2.9550 (2.8015) grad_norm: 2.3611 (2.5569) time: 0.6299 [2021-03-28 03:09:45 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 440/1251] eta: 0:08:38 lr: 0.000136 loss: 2.8279 (2.8000) grad_norm: 2.4785 (2.5637) time: 0.6299 [2021-03-28 03:09:51 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 450/1251] eta: 0:08:32 lr: 0.000136 loss: 2.8279 (2.7993) grad_norm: 2.6250 (2.5656) time: 0.6237 [2021-03-28 03:09:57 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 460/1251] eta: 0:08:25 lr: 0.000136 loss: 2.9430 (2.7996) grad_norm: 2.3950 (2.5635) time: 0.6251 [2021-03-28 03:10:04 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 470/1251] eta: 0:08:18 lr: 0.000136 loss: 2.9821 (2.8037) grad_norm: 2.3649 (2.5619) time: 0.6274 [2021-03-28 03:10:10 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 480/1251] eta: 0:08:12 lr: 0.000136 loss: 3.0212 (2.8055) grad_norm: 2.4307 (2.5595) time: 0.6331 [2021-03-28 03:10:16 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 490/1251] eta: 0:08:05 lr: 0.000136 loss: 2.8235 (2.8058) grad_norm: 2.5730 (2.5693) time: 0.6345 [2021-03-28 03:10:23 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 500/1251] eta: 0:07:59 lr: 0.000136 loss: 3.0301 (2.8111) grad_norm: 2.5488 (2.5659) time: 0.6288 [2021-03-28 03:10:29 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 510/1251] eta: 0:07:52 lr: 0.000136 loss: 3.0835 (2.8146) grad_norm: 2.4483 (2.5668) time: 0.6302 [2021-03-28 03:10:35 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 520/1251] eta: 0:07:46 lr: 0.000136 loss: 3.0156 (2.8163) grad_norm: 2.5030 (2.5653) time: 0.6277 [2021-03-28 03:10:42 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 530/1251] eta: 0:07:40 lr: 0.000136 loss: 2.8443 (2.8183) grad_norm: 2.5030 (2.5666) time: 0.6311 [2021-03-28 03:10:48 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 540/1251] eta: 0:07:33 lr: 0.000136 loss: 2.8899 (2.8171) grad_norm: 2.4559 (2.5662) time: 0.6329 [2021-03-28 03:10:54 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 550/1251] eta: 0:07:27 lr: 0.000136 loss: 2.9738 (2.8192) grad_norm: 2.3767 (2.5631) time: 0.6358 [2021-03-28 03:11:01 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 560/1251] eta: 0:07:20 lr: 0.000136 loss: 2.9854 (2.8230) grad_norm: 2.2241 (2.5595) time: 0.6370 [2021-03-28 03:11:07 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 570/1251] eta: 0:07:14 lr: 0.000136 loss: 3.1401 (2.8270) grad_norm: 2.2001 (2.5580) time: 0.6303 [2021-03-28 03:11:13 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 580/1251] eta: 0:07:07 lr: 0.000136 loss: 3.0104 (2.8281) grad_norm: 2.3926 (2.5555) time: 0.6293 [2021-03-28 03:11:19 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 590/1251] eta: 0:07:01 lr: 0.000136 loss: 2.9427 (2.8283) grad_norm: 2.2251 (2.5537) time: 0.6284 [2021-03-28 03:11:26 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 600/1251] eta: 0:06:54 lr: 0.000135 loss: 3.0008 (2.8289) grad_norm: 2.2481 (2.5586) time: 0.6257 [2021-03-28 03:11:32 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 610/1251] eta: 0:06:48 lr: 0.000135 loss: 2.9897 (2.8295) grad_norm: 2.4395 (2.5585) time: 0.6234 [2021-03-28 03:11:38 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 620/1251] eta: 0:06:41 lr: 0.000135 loss: 2.7404 (2.8279) grad_norm: 2.3409 (2.5577) time: 0.6240 [2021-03-28 03:11:44 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 630/1251] eta: 0:06:35 lr: 0.000135 loss: 2.7527 (2.8283) grad_norm: 2.3792 (2.5568) time: 0.6276 [2021-03-28 03:11:51 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 640/1251] eta: 0:06:28 lr: 0.000135 loss: 2.9362 (2.8291) grad_norm: 2.3731 (2.5557) time: 0.6288 [2021-03-28 03:11:57 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 650/1251] eta: 0:06:22 lr: 0.000135 loss: 2.9821 (2.8299) grad_norm: 2.4363 (2.5543) time: 0.6233 [2021-03-28 03:12:03 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 660/1251] eta: 0:06:15 lr: 0.000135 loss: 2.9249 (2.8264) grad_norm: 2.4130 (2.5556) time: 0.6234 [2021-03-28 03:12:09 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 670/1251] eta: 0:06:09 lr: 0.000135 loss: 2.7902 (2.8284) grad_norm: 2.3539 (2.5540) time: 0.6262 [2021-03-28 03:12:16 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 680/1251] eta: 0:06:03 lr: 0.000135 loss: 2.7902 (2.8260) grad_norm: 2.3539 (2.5537) time: 0.6284 [2021-03-28 03:12:22 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 690/1251] eta: 0:05:56 lr: 0.000135 loss: 2.6420 (2.8238) grad_norm: 2.2946 (2.5503) time: 0.6295 [2021-03-28 03:12:28 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 700/1251] eta: 0:05:50 lr: 0.000135 loss: 2.8119 (2.8257) grad_norm: 2.3160 (2.5493) time: 0.6262 [2021-03-28 03:12:35 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 710/1251] eta: 0:05:43 lr: 0.000135 loss: 3.0654 (2.8295) grad_norm: 2.4107 (2.5482) time: 0.6256 [2021-03-28 03:12:41 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 720/1251] eta: 0:05:37 lr: 0.000135 loss: 3.0733 (2.8328) grad_norm: 2.5020 (2.5476) time: 0.6257 [2021-03-28 03:12:47 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 730/1251] eta: 0:05:30 lr: 0.000135 loss: 3.0809 (2.8347) grad_norm: 2.3121 (2.5445) time: 0.6293 [2021-03-28 03:12:54 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 740/1251] eta: 0:05:24 lr: 0.000135 loss: 2.9609 (2.8346) grad_norm: 2.3121 (2.5440) time: 0.6348 [2021-03-28 03:13:00 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 750/1251] eta: 0:05:18 lr: 0.000135 loss: 3.0631 (2.8367) grad_norm: 2.3637 (2.5429) time: 0.6335 [2021-03-28 03:13:06 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 760/1251] eta: 0:05:11 lr: 0.000135 loss: 2.9198 (2.8335) grad_norm: 2.2772 (2.5406) time: 0.6298 [2021-03-28 03:13:12 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 770/1251] eta: 0:05:05 lr: 0.000135 loss: 2.6837 (2.8350) grad_norm: 2.2679 (2.5377) time: 0.6331 [2021-03-28 03:13:19 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 780/1251] eta: 0:04:59 lr: 0.000135 loss: 2.7961 (2.8324) grad_norm: 2.3421 (2.5366) time: 0.6406 [2021-03-28 03:13:25 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 790/1251] eta: 0:04:52 lr: 0.000135 loss: 2.7399 (2.8311) grad_norm: 2.4422 (inf) time: 0.6303 [2021-03-28 03:13:31 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 800/1251] eta: 0:04:46 lr: 0.000135 loss: 2.7399 (2.8316) grad_norm: 2.3415 (inf) time: 0.6265 [2021-03-28 03:13:38 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 810/1251] eta: 0:04:40 lr: 0.000135 loss: 2.7197 (2.8285) grad_norm: 2.3415 (inf) time: 0.6304 [2021-03-28 03:13:44 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 820/1251] eta: 0:04:33 lr: 0.000135 loss: 2.6662 (2.8295) grad_norm: 2.4074 (inf) time: 0.6279 [2021-03-28 03:13:50 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 830/1251] eta: 0:04:27 lr: 0.000135 loss: 2.6662 (2.8267) grad_norm: 2.4580 (inf) time: 0.6343 [2021-03-28 03:13:57 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 840/1251] eta: 0:04:20 lr: 0.000135 loss: 2.8351 (2.8286) grad_norm: 2.5152 (inf) time: 0.6315 [2021-03-28 03:14:03 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 850/1251] eta: 0:04:14 lr: 0.000135 loss: 3.1800 (2.8323) grad_norm: 2.4804 (inf) time: 0.6284 [2021-03-28 03:14:09 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 860/1251] eta: 0:04:08 lr: 0.000135 loss: 3.0773 (2.8335) grad_norm: 2.4222 (inf) time: 0.6276 [2021-03-28 03:14:16 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 870/1251] eta: 0:04:01 lr: 0.000135 loss: 2.7374 (2.8310) grad_norm: 2.4763 (inf) time: 0.6332 [2021-03-28 03:14:22 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 880/1251] eta: 0:03:55 lr: 0.000135 loss: 2.7973 (2.8317) grad_norm: 2.4484 (inf) time: 0.6315 [2021-03-28 03:14:28 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 890/1251] eta: 0:03:49 lr: 0.000135 loss: 3.0267 (2.8340) grad_norm: 2.4323 (inf) time: 0.6316 [2021-03-28 03:14:35 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 900/1251] eta: 0:03:42 lr: 0.000135 loss: 3.0267 (2.8318) grad_norm: 2.3252 (inf) time: 0.6355 [2021-03-28 03:14:41 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 910/1251] eta: 0:03:36 lr: 0.000135 loss: 2.8893 (2.8322) grad_norm: 2.3252 (inf) time: 0.6259 [2021-03-28 03:14:47 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 920/1251] eta: 0:03:30 lr: 0.000135 loss: 2.9850 (2.8341) grad_norm: 2.3551 (inf) time: 0.6294 [2021-03-28 03:14:53 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 930/1251] eta: 0:03:23 lr: 0.000135 loss: 2.9027 (2.8333) grad_norm: 2.3731 (inf) time: 0.6317 [2021-03-28 03:15:00 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 940/1251] eta: 0:03:17 lr: 0.000135 loss: 3.0145 (2.8369) grad_norm: 2.2471 (inf) time: 0.6296 [2021-03-28 03:15:06 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 950/1251] eta: 0:03:10 lr: 0.000135 loss: 3.0665 (2.8364) grad_norm: 2.2722 (inf) time: 0.6279 [2021-03-28 03:15:12 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 960/1251] eta: 0:03:04 lr: 0.000134 loss: 2.9018 (2.8363) grad_norm: 2.4137 (inf) time: 0.6274 [2021-03-28 03:15:19 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 970/1251] eta: 0:02:58 lr: 0.000134 loss: 2.9052 (2.8363) grad_norm: 2.4263 (inf) time: 0.6289 [2021-03-28 03:15:25 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 980/1251] eta: 0:02:51 lr: 0.000134 loss: 2.9052 (2.8363) grad_norm: 2.4234 (inf) time: 0.6303 [2021-03-28 03:15:31 swin_base_patch4_window7_224] INFO: Epoch: [230] [ 990/1251] eta: 0:02:45 lr: 0.000134 loss: 3.0183 (2.8386) grad_norm: 2.3444 (inf) time: 0.6289 [2021-03-28 03:15:37 swin_base_patch4_window7_224] INFO: Epoch: [230] [1000/1251] eta: 0:02:39 lr: 0.000134 loss: 3.1469 (2.8412) grad_norm: 2.3444 (inf) time: 0.6268 [2021-03-28 03:15:44 swin_base_patch4_window7_224] INFO: Epoch: [230] [1010/1251] eta: 0:02:32 lr: 0.000134 loss: 3.0300 (2.8413) grad_norm: 2.3455 (inf) time: 0.6259 [2021-03-28 03:15:50 swin_base_patch4_window7_224] INFO: Epoch: [230] [1020/1251] eta: 0:02:26 lr: 0.000134 loss: 2.9441 (2.8433) grad_norm: 2.3928 (inf) time: 0.6271 [2021-03-28 03:15:56 swin_base_patch4_window7_224] INFO: Epoch: [230] [1030/1251] eta: 0:02:20 lr: 0.000134 loss: 3.1360 (2.8457) grad_norm: 2.5517 (inf) time: 0.6284 [2021-03-28 03:16:02 swin_base_patch4_window7_224] INFO: Epoch: [230] [1040/1251] eta: 0:02:13 lr: 0.000134 loss: 2.9020 (2.8425) grad_norm: 2.4881 (inf) time: 0.6253 [2021-03-28 03:16:09 swin_base_patch4_window7_224] INFO: Epoch: [230] [1050/1251] eta: 0:02:07 lr: 0.000134 loss: 2.8514 (2.8422) grad_norm: 2.4754 (inf) time: 0.6301 [2021-03-28 03:16:15 swin_base_patch4_window7_224] INFO: Epoch: [230] [1060/1251] eta: 0:02:01 lr: 0.000134 loss: 2.9104 (2.8436) grad_norm: 2.3391 (inf) time: 0.6364 [2021-03-28 03:16:22 swin_base_patch4_window7_224] INFO: Epoch: [230] [1070/1251] eta: 0:01:54 lr: 0.000134 loss: 2.9596 (2.8436) grad_norm: 2.3479 (inf) time: 0.6403 [2021-03-28 03:16:28 swin_base_patch4_window7_224] INFO: Epoch: [230] [1080/1251] eta: 0:01:48 lr: 0.000134 loss: 2.9025 (2.8426) grad_norm: 2.3838 (inf) time: 0.6379 [2021-03-28 03:16:34 swin_base_patch4_window7_224] INFO: Epoch: [230] [1090/1251] eta: 0:01:42 lr: 0.000134 loss: 2.7339 (2.8414) grad_norm: 2.4441 (inf) time: 0.6282 [2021-03-28 03:16:41 swin_base_patch4_window7_224] INFO: Epoch: [230] [1100/1251] eta: 0:01:35 lr: 0.000134 loss: 2.8664 (2.8427) grad_norm: 2.3284 (inf) time: 0.6263 [2021-03-28 03:16:47 swin_base_patch4_window7_224] INFO: Epoch: [230] [1110/1251] eta: 0:01:29 lr: 0.000134 loss: 2.8664 (2.8423) grad_norm: 2.3121 (inf) time: 0.6326 [2021-03-28 03:16:53 swin_base_patch4_window7_224] INFO: Epoch: [230] [1120/1251] eta: 0:01:23 lr: 0.000134 loss: 2.7445 (2.8407) grad_norm: 2.2858 (inf) time: 0.6386 [2021-03-28 03:17:00 swin_base_patch4_window7_224] INFO: Epoch: [230] [1130/1251] eta: 0:01:16 lr: 0.000134 loss: 2.6600 (2.8387) grad_norm: 2.2832 (inf) time: 0.6326 [2021-03-28 03:17:06 swin_base_patch4_window7_224] INFO: Epoch: [230] [1140/1251] eta: 0:01:10 lr: 0.000134 loss: 2.9449 (2.8399) grad_norm: 2.2832 (inf) time: 0.6276 [2021-03-28 03:17:12 swin_base_patch4_window7_224] INFO: Epoch: [230] [1150/1251] eta: 0:01:03 lr: 0.000134 loss: 2.9811 (2.8410) grad_norm: 2.2787 (inf) time: 0.6264 [2021-03-28 03:17:18 swin_base_patch4_window7_224] INFO: Epoch: [230] [1160/1251] eta: 0:00:57 lr: 0.000134 loss: 2.9634 (2.8404) grad_norm: 2.3928 (inf) time: 0.6268 [2021-03-28 03:17:25 swin_base_patch4_window7_224] INFO: Epoch: [230] [1170/1251] eta: 0:00:51 lr: 0.000134 loss: 3.0473 (2.8418) grad_norm: 2.4052 (inf) time: 0.6289 [2021-03-28 03:17:31 swin_base_patch4_window7_224] INFO: Epoch: [230] [1180/1251] eta: 0:00:44 lr: 0.000134 loss: 3.0607 (2.8418) grad_norm: 2.3260 (inf) time: 0.6279 [2021-03-28 03:17:37 swin_base_patch4_window7_224] INFO: Epoch: [230] [1190/1251] eta: 0:00:38 lr: 0.000134 loss: 2.9870 (2.8432) grad_norm: 2.2981 (inf) time: 0.6256 [2021-03-28 03:17:44 swin_base_patch4_window7_224] INFO: Epoch: [230] [1200/1251] eta: 0:00:32 lr: 0.000134 loss: 2.9658 (2.8429) grad_norm: 2.3417 (inf) time: 0.6297 [2021-03-28 03:17:50 swin_base_patch4_window7_224] INFO: Epoch: [230] [1210/1251] eta: 0:00:25 lr: 0.000134 loss: 2.8956 (2.8430) grad_norm: 2.3730 (inf) time: 0.6341 [2021-03-28 03:17:56 swin_base_patch4_window7_224] INFO: Epoch: [230] [1220/1251] eta: 0:00:19 lr: 0.000134 loss: 3.0202 (2.8447) grad_norm: 2.3496 (inf) time: 0.6281 [2021-03-28 03:18:02 swin_base_patch4_window7_224] INFO: Epoch: [230] [1230/1251] eta: 0:00:13 lr: 0.000134 loss: 3.0202 (2.8457) grad_norm: 2.3445 (inf) time: 0.6271 [2021-03-28 03:18:09 swin_base_patch4_window7_224] INFO: Epoch: [230] [1240/1251] eta: 0:00:06 lr: 0.000134 loss: 2.9208 (2.8457) grad_norm: 2.2666 (inf) time: 0.6293 [2021-03-28 03:18:15 swin_base_patch4_window7_224] INFO: Epoch: [230] [1250/1251] eta: 0:00:00 lr: 0.000134 loss: 3.0290 (2.8481) grad_norm: 2.3078 (inf) time: 0.6266 [2021-03-28 03:19:33 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.6491 (0.6491) acc1: 81.2500 (81.2500) acc5: 100.0000 (100.0000) [2021-03-28 03:19:34 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7578 (0.8119) acc1: 78.1250 (80.5398) acc5: 96.8750 (96.4489) [2021-03-28 03:19:36 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7578 (0.8065) acc1: 78.1250 (80.4315) acc5: 96.8750 (96.5030) [2021-03-28 03:19:37 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7474 (0.8015) acc1: 81.2500 (81.3004) acc5: 95.3125 (95.9677) [2021-03-28 03:19:39 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7656 (0.7946) acc1: 81.2500 (81.1357) acc5: 95.3125 (95.8841) [2021-03-28 03:19:40 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7678 (0.7910) acc1: 81.2500 (81.1840) acc5: 96.8750 (96.0640) [2021-03-28 03:19:50 swin_base_patch4_window7_224] INFO: * Acc@1 82.258 Acc@5 96.100 loss 0.772 [2021-03-28 03:19:50 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.3% [2021-03-28 03:19:50 swin_base_patch4_window7_224] INFO: Max accuracy: 82.26% [2021-03-28 03:19:54 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 0/1251] eta: 1:29:15 lr: 0.000134 loss: 2.3769 (2.3769) grad_norm: 2.2701 (2.2701) time: 4.2808 [2021-03-28 03:20:01 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 10/1251] eta: 0:19:57 lr: 0.000134 loss: 3.1381 (3.0044) grad_norm: 2.3760 (2.3856) time: 0.9649 [2021-03-28 03:20:07 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 20/1251] eta: 0:16:28 lr: 0.000134 loss: 3.0933 (2.9921) grad_norm: 2.4410 (2.4229) time: 0.6290 [2021-03-28 03:20:13 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 30/1251] eta: 0:15:09 lr: 0.000134 loss: 2.9767 (2.9088) grad_norm: 2.3718 (2.4613) time: 0.6243 [2021-03-28 03:20:19 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 40/1251] eta: 0:14:28 lr: 0.000134 loss: 2.8001 (2.9047) grad_norm: 2.2408 (2.4367) time: 0.6266 [2021-03-28 03:20:26 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 50/1251] eta: 0:14:01 lr: 0.000134 loss: 2.8001 (2.8901) grad_norm: 2.2916 (2.4655) time: 0.6327 [2021-03-28 03:20:32 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 60/1251] eta: 0:13:40 lr: 0.000134 loss: 3.0576 (2.9360) grad_norm: 2.2916 (2.4400) time: 0.6320 [2021-03-28 03:20:38 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 70/1251] eta: 0:13:24 lr: 0.000134 loss: 3.1613 (2.9516) grad_norm: 2.2816 (2.5059) time: 0.6292 [2021-03-28 03:20:45 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 80/1251] eta: 0:13:09 lr: 0.000133 loss: 2.9776 (2.9485) grad_norm: 2.4721 (2.5304) time: 0.6303 [2021-03-28 03:20:51 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 90/1251] eta: 0:12:58 lr: 0.000133 loss: 2.8642 (2.9316) grad_norm: 2.3540 (2.5180) time: 0.6342 [2021-03-28 03:20:57 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 100/1251] eta: 0:12:47 lr: 0.000133 loss: 2.8917 (2.9421) grad_norm: 2.3101 (2.5356) time: 0.6353 [2021-03-28 03:21:04 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 110/1251] eta: 0:12:37 lr: 0.000133 loss: 2.8917 (2.9283) grad_norm: 2.2892 (2.5176) time: 0.6346 [2021-03-28 03:21:10 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 120/1251] eta: 0:12:27 lr: 0.000133 loss: 2.6645 (2.9067) grad_norm: 2.3333 (2.5138) time: 0.6305 [2021-03-28 03:21:16 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 130/1251] eta: 0:12:18 lr: 0.000133 loss: 2.8477 (2.8998) grad_norm: 2.4517 (2.5088) time: 0.6273 [2021-03-28 03:21:22 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 140/1251] eta: 0:12:08 lr: 0.000133 loss: 2.9667 (2.9089) grad_norm: 2.4377 (2.5060) time: 0.6270 [2021-03-28 03:21:29 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 150/1251] eta: 0:12:01 lr: 0.000133 loss: 3.0246 (2.9152) grad_norm: 2.4863 (2.5144) time: 0.6339 [2021-03-28 03:21:35 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 160/1251] eta: 0:11:52 lr: 0.000133 loss: 3.0474 (2.9184) grad_norm: 2.4705 (2.5083) time: 0.6337 [2021-03-28 03:21:41 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 170/1251] eta: 0:11:44 lr: 0.000133 loss: 3.0474 (2.9150) grad_norm: 2.3105 (2.5051) time: 0.6253 [2021-03-28 03:21:48 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 180/1251] eta: 0:11:36 lr: 0.000133 loss: 3.0308 (2.9102) grad_norm: 2.3409 (2.5011) time: 0.6281 [2021-03-28 03:21:54 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 190/1251] eta: 0:11:29 lr: 0.000133 loss: 3.0308 (2.9166) grad_norm: 2.4523 (2.5080) time: 0.6309 [2021-03-28 03:22:00 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 200/1251] eta: 0:11:22 lr: 0.000133 loss: 2.9938 (2.9175) grad_norm: 2.4228 (2.5088) time: 0.6383 [2021-03-28 03:22:07 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 210/1251] eta: 0:11:15 lr: 0.000133 loss: 2.9280 (2.9084) grad_norm: 2.4368 (2.5092) time: 0.6445 [2021-03-28 03:22:13 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 220/1251] eta: 0:11:07 lr: 0.000133 loss: 2.9775 (2.9131) grad_norm: 2.3632 (2.5031) time: 0.6342 [2021-03-28 03:22:19 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 230/1251] eta: 0:11:00 lr: 0.000133 loss: 3.0986 (2.9193) grad_norm: 2.3405 (2.5037) time: 0.6269 [2021-03-28 03:22:26 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 240/1251] eta: 0:10:53 lr: 0.000133 loss: 2.9824 (2.9061) grad_norm: 2.4559 (2.5005) time: 0.6342 [2021-03-28 03:22:32 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 250/1251] eta: 0:10:46 lr: 0.000133 loss: 2.5958 (2.8974) grad_norm: 2.4269 (2.4993) time: 0.6293 [2021-03-28 03:22:38 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 260/1251] eta: 0:10:39 lr: 0.000133 loss: 2.8108 (2.8965) grad_norm: 2.4269 (2.4984) time: 0.6272 [2021-03-28 03:22:45 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 270/1251] eta: 0:10:32 lr: 0.000133 loss: 2.9183 (2.8916) grad_norm: 2.5621 (2.5061) time: 0.6306 [2021-03-28 03:22:51 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 280/1251] eta: 0:10:25 lr: 0.000133 loss: 2.9201 (2.8917) grad_norm: 2.5621 (2.5088) time: 0.6294 [2021-03-28 03:22:57 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 290/1251] eta: 0:10:18 lr: 0.000133 loss: 2.7972 (2.8812) grad_norm: 2.4107 (2.5193) time: 0.6325 [2021-03-28 03:23:04 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 300/1251] eta: 0:10:11 lr: 0.000133 loss: 2.8137 (2.8844) grad_norm: 2.4257 (2.5181) time: 0.6303 [2021-03-28 03:23:10 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 310/1251] eta: 0:10:04 lr: 0.000133 loss: 2.9384 (2.8840) grad_norm: 2.4427 (2.5193) time: 0.6293 [2021-03-28 03:23:16 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 320/1251] eta: 0:09:57 lr: 0.000133 loss: 2.9682 (2.8889) grad_norm: 2.3619 (2.5151) time: 0.6265 [2021-03-28 03:23:22 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 330/1251] eta: 0:09:50 lr: 0.000133 loss: 2.9667 (2.8852) grad_norm: 2.2807 (2.5173) time: 0.6224 [2021-03-28 03:23:29 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 340/1251] eta: 0:09:44 lr: 0.000133 loss: 2.8045 (2.8820) grad_norm: 2.3027 (2.5240) time: 0.6254 [2021-03-28 03:23:35 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 350/1251] eta: 0:09:37 lr: 0.000133 loss: 2.7865 (2.8787) grad_norm: 2.5293 (2.5231) time: 0.6280 [2021-03-28 03:23:41 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 360/1251] eta: 0:09:30 lr: 0.000133 loss: 2.7865 (2.8773) grad_norm: 2.4686 (2.5270) time: 0.6269 [2021-03-28 03:23:47 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 370/1251] eta: 0:09:23 lr: 0.000133 loss: 3.0270 (2.8787) grad_norm: 2.4392 (2.5353) time: 0.6264 [2021-03-28 03:23:54 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 380/1251] eta: 0:09:17 lr: 0.000133 loss: 3.0270 (2.8796) grad_norm: 2.3889 (2.5347) time: 0.6266 [2021-03-28 03:24:00 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 390/1251] eta: 0:09:10 lr: 0.000133 loss: 3.1263 (2.8873) grad_norm: 2.3641 (2.5334) time: 0.6297 [2021-03-28 03:24:06 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 400/1251] eta: 0:09:04 lr: 0.000133 loss: 3.1333 (2.8897) grad_norm: 2.4404 (2.5488) time: 0.6332 [2021-03-28 03:24:13 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 410/1251] eta: 0:08:57 lr: 0.000133 loss: 3.0527 (2.8908) grad_norm: 2.6557 (2.5528) time: 0.6318 [2021-03-28 03:24:19 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 420/1251] eta: 0:08:50 lr: 0.000133 loss: 2.8725 (2.8923) grad_norm: 2.6128 (2.5570) time: 0.6263 [2021-03-28 03:24:25 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 430/1251] eta: 0:08:44 lr: 0.000133 loss: 2.8075 (2.8834) grad_norm: 2.4365 (2.5554) time: 0.6253 [2021-03-28 03:24:31 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 440/1251] eta: 0:08:37 lr: 0.000132 loss: 2.8707 (2.8863) grad_norm: 2.4194 (2.5549) time: 0.6279 [2021-03-28 03:24:38 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 450/1251] eta: 0:08:31 lr: 0.000132 loss: 2.9246 (2.8887) grad_norm: 2.4513 (2.5591) time: 0.6290 [2021-03-28 03:24:44 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 460/1251] eta: 0:08:24 lr: 0.000132 loss: 3.0006 (2.8917) grad_norm: 2.4308 (2.5570) time: 0.6303 [2021-03-28 03:24:50 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 470/1251] eta: 0:08:17 lr: 0.000132 loss: 3.0792 (2.8909) grad_norm: 2.4308 (2.5558) time: 0.6272 [2021-03-28 03:24:57 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 480/1251] eta: 0:08:11 lr: 0.000132 loss: 2.8911 (2.8888) grad_norm: 2.4076 (2.5512) time: 0.6247 [2021-03-28 03:25:03 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 490/1251] eta: 0:08:04 lr: 0.000132 loss: 2.8911 (2.8888) grad_norm: 2.2549 (2.5479) time: 0.6293 [2021-03-28 03:25:09 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 500/1251] eta: 0:07:58 lr: 0.000132 loss: 2.9434 (2.8899) grad_norm: 2.3632 (2.5512) time: 0.6346 [2021-03-28 03:25:16 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 510/1251] eta: 0:07:52 lr: 0.000132 loss: 2.9434 (2.8887) grad_norm: 2.3632 (2.5520) time: 0.6324 [2021-03-28 03:25:22 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 520/1251] eta: 0:07:45 lr: 0.000132 loss: 3.0116 (2.8900) grad_norm: 2.3141 (2.5488) time: 0.6259 [2021-03-28 03:25:28 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 530/1251] eta: 0:07:39 lr: 0.000132 loss: 3.1354 (2.8949) grad_norm: 2.3141 (2.5447) time: 0.6301 [2021-03-28 03:25:34 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 540/1251] eta: 0:07:32 lr: 0.000132 loss: 3.1354 (2.8958) grad_norm: 2.2780 (2.5414) time: 0.6336 [2021-03-28 03:25:41 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 550/1251] eta: 0:07:26 lr: 0.000132 loss: 2.8869 (2.8945) grad_norm: 2.3983 (2.5428) time: 0.6383 [2021-03-28 03:25:47 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 560/1251] eta: 0:07:20 lr: 0.000132 loss: 2.7520 (2.8904) grad_norm: 2.5179 (2.5434) time: 0.6483 [2021-03-28 03:25:54 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 570/1251] eta: 0:07:13 lr: 0.000132 loss: 2.5135 (2.8853) grad_norm: 2.3541 (2.5411) time: 0.6381 [2021-03-28 03:26:00 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 580/1251] eta: 0:07:07 lr: 0.000132 loss: 2.8131 (2.8846) grad_norm: 2.3517 (2.5445) time: 0.6274 [2021-03-28 03:26:06 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 590/1251] eta: 0:07:00 lr: 0.000132 loss: 2.7856 (2.8832) grad_norm: 2.3199 (2.5404) time: 0.6255 [2021-03-28 03:26:13 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 600/1251] eta: 0:06:54 lr: 0.000132 loss: 2.8053 (2.8850) grad_norm: 2.1598 (2.5361) time: 0.6310 [2021-03-28 03:26:19 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 610/1251] eta: 0:06:48 lr: 0.000132 loss: 2.9949 (2.8859) grad_norm: 2.2596 (2.5386) time: 0.6362 [2021-03-28 03:26:25 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 620/1251] eta: 0:06:41 lr: 0.000132 loss: 3.0679 (2.8896) grad_norm: 2.5233 (2.5454) time: 0.6305 [2021-03-28 03:26:31 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 630/1251] eta: 0:06:35 lr: 0.000132 loss: 3.0679 (2.8849) grad_norm: 2.4400 (2.5419) time: 0.6266 [2021-03-28 03:26:38 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 640/1251] eta: 0:06:28 lr: 0.000132 loss: 2.8607 (2.8853) grad_norm: 2.4411 (2.5412) time: 0.6240 [2021-03-28 03:26:44 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 650/1251] eta: 0:06:22 lr: 0.000132 loss: 3.0739 (2.8869) grad_norm: 2.4735 (2.5404) time: 0.6371 [2021-03-28 03:26:50 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 660/1251] eta: 0:06:15 lr: 0.000132 loss: 3.0953 (2.8904) grad_norm: 2.3749 (2.5382) time: 0.6382 [2021-03-28 03:26:57 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 670/1251] eta: 0:06:09 lr: 0.000132 loss: 3.0485 (2.8872) grad_norm: 2.3049 (2.5348) time: 0.6224 [2021-03-28 03:27:03 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 680/1251] eta: 0:06:02 lr: 0.000132 loss: 2.7782 (2.8847) grad_norm: 2.3139 (2.5336) time: 0.6238 [2021-03-28 03:27:09 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 690/1251] eta: 0:05:56 lr: 0.000132 loss: 2.7874 (2.8838) grad_norm: 2.3317 (2.5309) time: 0.6322 [2021-03-28 03:27:16 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 700/1251] eta: 0:05:50 lr: 0.000132 loss: 2.8344 (2.8814) grad_norm: 2.2953 (2.5297) time: 0.6341 [2021-03-28 03:27:22 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 710/1251] eta: 0:05:43 lr: 0.000132 loss: 3.0547 (2.8848) grad_norm: 2.2761 (2.5300) time: 0.6318 [2021-03-28 03:27:28 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 720/1251] eta: 0:05:37 lr: 0.000132 loss: 3.1186 (2.8868) grad_norm: 2.3700 (2.5319) time: 0.6299 [2021-03-28 03:27:34 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 730/1251] eta: 0:05:30 lr: 0.000132 loss: 3.0815 (2.8908) grad_norm: 2.4453 (2.5320) time: 0.6239 [2021-03-28 03:27:41 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 740/1251] eta: 0:05:24 lr: 0.000132 loss: 3.0264 (2.8883) grad_norm: 2.3878 (2.5285) time: 0.6325 [2021-03-28 03:27:47 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 750/1251] eta: 0:05:18 lr: 0.000132 loss: 2.6715 (2.8869) grad_norm: 2.3515 (2.5268) time: 0.6481 [2021-03-28 03:27:54 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 760/1251] eta: 0:05:12 lr: 0.000132 loss: 2.8030 (2.8867) grad_norm: 2.4737 (2.5268) time: 0.6420 [2021-03-28 03:28:00 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 770/1251] eta: 0:05:05 lr: 0.000132 loss: 2.9632 (2.8877) grad_norm: 2.4306 (2.5252) time: 0.6264 [2021-03-28 03:28:06 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 780/1251] eta: 0:04:59 lr: 0.000132 loss: 2.8181 (2.8877) grad_norm: 2.3342 (2.5254) time: 0.6241 [2021-03-28 03:28:13 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 790/1251] eta: 0:04:52 lr: 0.000132 loss: 2.8181 (2.8894) grad_norm: 2.3342 (2.5225) time: 0.6292 [2021-03-28 03:28:19 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 800/1251] eta: 0:04:46 lr: 0.000132 loss: 3.0375 (2.8915) grad_norm: 2.4122 (2.5231) time: 0.6294 [2021-03-28 03:28:25 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 810/1251] eta: 0:04:40 lr: 0.000131 loss: 3.0262 (2.8928) grad_norm: 2.3158 (2.5206) time: 0.6257 [2021-03-28 03:28:31 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 820/1251] eta: 0:04:33 lr: 0.000131 loss: 2.8430 (2.8887) grad_norm: 2.2347 (2.5204) time: 0.6284 [2021-03-28 03:28:38 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 830/1251] eta: 0:04:27 lr: 0.000131 loss: 2.6122 (2.8887) grad_norm: 2.3259 (2.5184) time: 0.6329 [2021-03-28 03:28:44 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 840/1251] eta: 0:04:20 lr: 0.000131 loss: 2.9373 (2.8888) grad_norm: 2.3966 (2.5167) time: 0.6318 [2021-03-28 03:28:50 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 850/1251] eta: 0:04:14 lr: 0.000131 loss: 2.9358 (2.8887) grad_norm: 2.4254 (2.5164) time: 0.6269 [2021-03-28 03:28:57 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 860/1251] eta: 0:04:08 lr: 0.000131 loss: 2.8419 (2.8867) grad_norm: 2.3862 (2.5151) time: 0.6256 [2021-03-28 03:29:03 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 870/1251] eta: 0:04:01 lr: 0.000131 loss: 2.6260 (2.8840) grad_norm: 2.4259 (2.5153) time: 0.6306 [2021-03-28 03:29:09 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 880/1251] eta: 0:03:55 lr: 0.000131 loss: 2.8463 (2.8853) grad_norm: 2.4392 (2.5153) time: 0.6343 [2021-03-28 03:29:15 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 890/1251] eta: 0:03:49 lr: 0.000131 loss: 2.7484 (2.8816) grad_norm: 2.5854 (2.5180) time: 0.6303 [2021-03-28 03:29:22 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 900/1251] eta: 0:03:42 lr: 0.000131 loss: 2.7097 (2.8833) grad_norm: 2.5538 (2.5186) time: 0.6313 [2021-03-28 03:29:28 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 910/1251] eta: 0:03:36 lr: 0.000131 loss: 3.0202 (2.8831) grad_norm: 2.5106 (2.5202) time: 0.6288 [2021-03-28 03:29:34 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 920/1251] eta: 0:03:29 lr: 0.000131 loss: 2.9558 (2.8814) grad_norm: 2.4403 (2.5196) time: 0.6244 [2021-03-28 03:29:41 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 930/1251] eta: 0:03:23 lr: 0.000131 loss: 2.8061 (2.8785) grad_norm: 2.3606 (2.5197) time: 0.6265 [2021-03-28 03:29:47 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 940/1251] eta: 0:03:17 lr: 0.000131 loss: 2.9165 (2.8798) grad_norm: 2.3606 (2.5181) time: 0.6270 [2021-03-28 03:29:53 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 950/1251] eta: 0:03:10 lr: 0.000131 loss: 3.0249 (2.8816) grad_norm: 2.3780 (2.5183) time: 0.6324 [2021-03-28 03:30:00 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 960/1251] eta: 0:03:04 lr: 0.000131 loss: 2.8364 (2.8801) grad_norm: 2.4074 (2.5170) time: 0.6322 [2021-03-28 03:30:06 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 970/1251] eta: 0:02:58 lr: 0.000131 loss: 2.5342 (2.8778) grad_norm: 2.4074 (2.5165) time: 0.6303 [2021-03-28 03:30:12 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 980/1251] eta: 0:02:51 lr: 0.000131 loss: 2.8285 (2.8791) grad_norm: 2.4986 (2.5180) time: 0.6286 [2021-03-28 03:30:18 swin_base_patch4_window7_224] INFO: Epoch: [231] [ 990/1251] eta: 0:02:45 lr: 0.000131 loss: 3.1011 (2.8801) grad_norm: 2.5754 (2.5182) time: 0.6289 [2021-03-28 03:30:25 swin_base_patch4_window7_224] INFO: Epoch: [231] [1000/1251] eta: 0:02:39 lr: 0.000131 loss: 2.9904 (2.8800) grad_norm: 2.4754 (2.5170) time: 0.6309 [2021-03-28 03:30:31 swin_base_patch4_window7_224] INFO: Epoch: [231] [1010/1251] eta: 0:02:32 lr: 0.000131 loss: 2.7991 (2.8793) grad_norm: 2.4288 (2.5183) time: 0.6338 [2021-03-28 03:30:37 swin_base_patch4_window7_224] INFO: Epoch: [231] [1020/1251] eta: 0:02:26 lr: 0.000131 loss: 2.7102 (2.8769) grad_norm: 2.4702 (2.5194) time: 0.6307 [2021-03-28 03:30:44 swin_base_patch4_window7_224] INFO: Epoch: [231] [1030/1251] eta: 0:02:20 lr: 0.000131 loss: 2.8192 (2.8778) grad_norm: 2.4740 (2.5186) time: 0.6238 [2021-03-28 03:30:50 swin_base_patch4_window7_224] INFO: Epoch: [231] [1040/1251] eta: 0:02:13 lr: 0.000131 loss: 2.9872 (2.8773) grad_norm: 2.4740 (2.5186) time: 0.6275 [2021-03-28 03:30:56 swin_base_patch4_window7_224] INFO: Epoch: [231] [1050/1251] eta: 0:02:07 lr: 0.000131 loss: 2.9208 (2.8764) grad_norm: 2.3763 (2.5201) time: 0.6329 [2021-03-28 03:31:02 swin_base_patch4_window7_224] INFO: Epoch: [231] [1060/1251] eta: 0:02:01 lr: 0.000131 loss: 2.8631 (2.8773) grad_norm: 2.3763 (2.5210) time: 0.6303 [2021-03-28 03:31:09 swin_base_patch4_window7_224] INFO: Epoch: [231] [1070/1251] eta: 0:01:54 lr: 0.000131 loss: 3.1571 (2.8804) grad_norm: 2.2956 (2.5192) time: 0.6270 [2021-03-28 03:31:15 swin_base_patch4_window7_224] INFO: Epoch: [231] [1080/1251] eta: 0:01:48 lr: 0.000131 loss: 3.1511 (2.8790) grad_norm: 2.3215 (2.5177) time: 0.6274 [2021-03-28 03:31:21 swin_base_patch4_window7_224] INFO: Epoch: [231] [1090/1251] eta: 0:01:42 lr: 0.000131 loss: 2.7150 (2.8787) grad_norm: 2.3729 (2.5169) time: 0.6279 [2021-03-28 03:31:28 swin_base_patch4_window7_224] INFO: Epoch: [231] [1100/1251] eta: 0:01:35 lr: 0.000131 loss: 2.8131 (2.8774) grad_norm: 2.3217 (2.5143) time: 0.6327 [2021-03-28 03:31:34 swin_base_patch4_window7_224] INFO: Epoch: [231] [1110/1251] eta: 0:01:29 lr: 0.000131 loss: 2.7617 (2.8757) grad_norm: 2.2969 (2.5142) time: 0.6338 [2021-03-28 03:31:40 swin_base_patch4_window7_224] INFO: Epoch: [231] [1120/1251] eta: 0:01:22 lr: 0.000131 loss: 3.0458 (2.8783) grad_norm: 2.3175 (2.5141) time: 0.6286 [2021-03-28 03:31:47 swin_base_patch4_window7_224] INFO: Epoch: [231] [1130/1251] eta: 0:01:16 lr: 0.000131 loss: 3.2319 (2.8790) grad_norm: 2.3936 (2.5221) time: 0.6243 [2021-03-28 03:31:53 swin_base_patch4_window7_224] INFO: Epoch: [231] [1140/1251] eta: 0:01:10 lr: 0.000131 loss: 3.0441 (2.8790) grad_norm: 2.3756 (2.5225) time: 0.6248 [2021-03-28 03:31:59 swin_base_patch4_window7_224] INFO: Epoch: [231] [1150/1251] eta: 0:01:03 lr: 0.000131 loss: 3.0277 (2.8790) grad_norm: 2.3756 (2.5222) time: 0.6328 [2021-03-28 03:32:05 swin_base_patch4_window7_224] INFO: Epoch: [231] [1160/1251] eta: 0:00:57 lr: 0.000131 loss: 2.8845 (2.8791) grad_norm: 2.3866 (2.5227) time: 0.6335 [2021-03-28 03:32:12 swin_base_patch4_window7_224] INFO: Epoch: [231] [1170/1251] eta: 0:00:51 lr: 0.000131 loss: 2.8323 (2.8787) grad_norm: 2.5183 (2.5232) time: 0.6326 [2021-03-28 03:32:18 swin_base_patch4_window7_224] INFO: Epoch: [231] [1180/1251] eta: 0:00:44 lr: 0.000130 loss: 2.8697 (2.8788) grad_norm: 2.5183 (2.5254) time: 0.6324 [2021-03-28 03:32:24 swin_base_patch4_window7_224] INFO: Epoch: [231] [1190/1251] eta: 0:00:38 lr: 0.000130 loss: 2.9506 (2.8786) grad_norm: 2.5099 (2.5272) time: 0.6277 [2021-03-28 03:32:31 swin_base_patch4_window7_224] INFO: Epoch: [231] [1200/1251] eta: 0:00:32 lr: 0.000130 loss: 3.1079 (2.8805) grad_norm: 2.5014 (2.5279) time: 0.6278 [2021-03-28 03:32:37 swin_base_patch4_window7_224] INFO: Epoch: [231] [1210/1251] eta: 0:00:25 lr: 0.000130 loss: 3.0079 (2.8799) grad_norm: 2.5014 (2.5306) time: 0.6303 [2021-03-28 03:32:43 swin_base_patch4_window7_224] INFO: Epoch: [231] [1220/1251] eta: 0:00:19 lr: 0.000130 loss: 2.9014 (2.8783) grad_norm: 2.5872 (2.5331) time: 0.6297 [2021-03-28 03:32:49 swin_base_patch4_window7_224] INFO: Epoch: [231] [1230/1251] eta: 0:00:13 lr: 0.000130 loss: 2.9918 (2.8792) grad_norm: 2.4679 (2.5324) time: 0.6250 [2021-03-28 03:32:56 swin_base_patch4_window7_224] INFO: Epoch: [231] [1240/1251] eta: 0:00:06 lr: 0.000130 loss: 2.9970 (2.8789) grad_norm: 2.4699 (2.5328) time: 0.6252 [2021-03-28 03:33:02 swin_base_patch4_window7_224] INFO: Epoch: [231] [1250/1251] eta: 0:00:00 lr: 0.000130 loss: 3.0120 (2.8807) grad_norm: 2.4708 (2.5328) time: 0.6240 [2021-03-28 03:33:15 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:10 loss: 0.9601 (0.9601) acc1: 79.6875 (79.6875) acc5: 96.8750 (96.8750) [2021-03-28 03:33:17 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7962 (0.8002) acc1: 81.2500 (82.2443) acc5: 96.8750 (96.0227) [2021-03-28 03:33:19 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7371 (0.7811) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.7262) [2021-03-28 03:33:21 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7483 (0.7774) acc1: 81.2500 (81.9052) acc5: 96.8750 (96.5222) [2021-03-28 03:33:23 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7647 (0.7659) acc1: 81.2500 (82.0122) acc5: 95.3125 (96.5701) [2021-03-28 03:33:24 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8174 (0.7940) acc1: 81.2500 (81.4720) acc5: 95.3125 (96.2240) [2021-03-28 03:33:40 swin_base_patch4_window7_224] INFO: * Acc@1 82.254 Acc@5 96.122 loss 0.774 [2021-03-28 03:33:40 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.3% [2021-03-28 03:33:40 swin_base_patch4_window7_224] INFO: Max accuracy: 82.26% [2021-03-28 03:33:44 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 0/1251] eta: 1:30:17 lr: 0.000130 loss: 2.7056 (2.7056) grad_norm: 3.1808 (3.1808) time: 4.3307 [2021-03-28 03:33:51 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 10/1251] eta: 0:20:03 lr: 0.000130 loss: 2.9745 (2.9373) grad_norm: 2.5665 (2.6645) time: 0.9694 [2021-03-28 03:33:57 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 20/1251] eta: 0:16:32 lr: 0.000130 loss: 3.0162 (2.9371) grad_norm: 2.4325 (2.5557) time: 0.6301 [2021-03-28 03:34:03 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 30/1251] eta: 0:15:18 lr: 0.000130 loss: 3.0215 (2.9679) grad_norm: 2.3954 (2.5169) time: 0.6324 [2021-03-28 03:34:10 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 40/1251] eta: 0:14:34 lr: 0.000130 loss: 3.0650 (2.9867) grad_norm: 2.4065 (2.5314) time: 0.6332 [2021-03-28 03:34:16 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 50/1251] eta: 0:14:04 lr: 0.000130 loss: 3.0333 (2.9495) grad_norm: 2.3970 (2.4921) time: 0.6282 [2021-03-28 03:34:22 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 60/1251] eta: 0:13:42 lr: 0.000130 loss: 3.0333 (2.9486) grad_norm: 2.3763 (2.4765) time: 0.6261 [2021-03-28 03:34:28 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 70/1251] eta: 0:13:24 lr: 0.000130 loss: 2.8743 (2.9139) grad_norm: 2.3809 (2.4785) time: 0.6249 [2021-03-28 03:34:35 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 80/1251] eta: 0:13:10 lr: 0.000130 loss: 2.7674 (2.9117) grad_norm: 2.4831 (2.4729) time: 0.6288 [2021-03-28 03:34:41 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 90/1251] eta: 0:12:59 lr: 0.000130 loss: 3.0083 (2.9115) grad_norm: 2.4513 (2.4711) time: 0.6368 [2021-03-28 03:34:47 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 100/1251] eta: 0:12:47 lr: 0.000130 loss: 2.8739 (2.9021) grad_norm: 2.4513 (2.4666) time: 0.6325 [2021-03-28 03:34:54 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 110/1251] eta: 0:12:37 lr: 0.000130 loss: 2.9152 (2.9096) grad_norm: 2.5101 (2.4742) time: 0.6275 [2021-03-28 03:35:00 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 120/1251] eta: 0:12:27 lr: 0.000130 loss: 2.9152 (2.9046) grad_norm: 2.3230 (2.4566) time: 0.6327 [2021-03-28 03:35:07 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 130/1251] eta: 0:12:20 lr: 0.000130 loss: 2.6947 (2.8891) grad_norm: 2.3230 (2.4656) time: 0.6420 [2021-03-28 03:35:13 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 140/1251] eta: 0:12:10 lr: 0.000130 loss: 2.7150 (2.8864) grad_norm: 2.6109 (2.4861) time: 0.6379 [2021-03-28 03:35:19 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 150/1251] eta: 0:12:02 lr: 0.000130 loss: 2.8938 (2.8799) grad_norm: 2.4412 (2.4928) time: 0.6295 [2021-03-28 03:35:25 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 160/1251] eta: 0:11:53 lr: 0.000130 loss: 2.6792 (2.8696) grad_norm: 2.6397 (2.5224) time: 0.6277 [2021-03-28 03:35:32 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 170/1251] eta: 0:11:45 lr: 0.000130 loss: 2.5908 (2.8652) grad_norm: 2.6822 (2.5225) time: 0.6251 [2021-03-28 03:35:38 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 180/1251] eta: 0:11:37 lr: 0.000130 loss: 2.9094 (2.8591) grad_norm: 2.4675 (2.5242) time: 0.6302 [2021-03-28 03:35:44 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 190/1251] eta: 0:11:29 lr: 0.000130 loss: 3.0599 (2.8696) grad_norm: 2.4675 (2.5255) time: 0.6306 [2021-03-28 03:35:51 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 200/1251] eta: 0:11:22 lr: 0.000130 loss: 3.1602 (2.8812) grad_norm: 2.5217 (2.5369) time: 0.6311 [2021-03-28 03:35:57 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 210/1251] eta: 0:11:16 lr: 0.000130 loss: 3.1602 (2.8797) grad_norm: 2.5779 (2.5447) time: 0.6419 [2021-03-28 03:36:04 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 220/1251] eta: 0:11:08 lr: 0.000130 loss: 3.0387 (2.8827) grad_norm: 2.5455 (2.5500) time: 0.6424 [2021-03-28 03:36:10 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 230/1251] eta: 0:11:01 lr: 0.000130 loss: 2.9261 (2.8791) grad_norm: 2.5013 (2.5471) time: 0.6319 [2021-03-28 03:36:16 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 240/1251] eta: 0:10:54 lr: 0.000130 loss: 2.9311 (2.8793) grad_norm: 2.4500 (2.5522) time: 0.6320 [2021-03-28 03:36:22 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 250/1251] eta: 0:10:47 lr: 0.000130 loss: 3.0579 (2.8862) grad_norm: 2.5947 (2.5561) time: 0.6317 [2021-03-28 03:36:29 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 260/1251] eta: 0:10:40 lr: 0.000130 loss: 3.1146 (2.8889) grad_norm: 2.5947 (2.5576) time: 0.6280 [2021-03-28 03:36:35 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 270/1251] eta: 0:10:33 lr: 0.000130 loss: 3.0722 (2.8890) grad_norm: 2.5555 (2.5594) time: 0.6277 [2021-03-28 03:36:41 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 280/1251] eta: 0:10:26 lr: 0.000130 loss: 2.9701 (2.8935) grad_norm: 2.3835 (2.5609) time: 0.6322 [2021-03-28 03:36:48 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 290/1251] eta: 0:10:19 lr: 0.000130 loss: 2.7715 (2.8853) grad_norm: 2.3835 (2.5576) time: 0.6382 [2021-03-28 03:36:54 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 300/1251] eta: 0:10:12 lr: 0.000129 loss: 2.7715 (2.8851) grad_norm: 2.4444 (2.5528) time: 0.6387 [2021-03-28 03:37:00 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 310/1251] eta: 0:10:06 lr: 0.000129 loss: 2.8298 (2.8728) grad_norm: 2.4688 (2.5503) time: 0.6341 [2021-03-28 03:37:07 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 320/1251] eta: 0:09:59 lr: 0.000129 loss: 2.7551 (2.8678) grad_norm: 2.4688 (2.5476) time: 0.6343 [2021-03-28 03:37:13 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 330/1251] eta: 0:09:52 lr: 0.000129 loss: 2.8794 (2.8706) grad_norm: 2.3505 (2.5430) time: 0.6312 [2021-03-28 03:37:19 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 340/1251] eta: 0:09:45 lr: 0.000129 loss: 2.9953 (2.8726) grad_norm: 2.2984 (2.5361) time: 0.6294 [2021-03-28 03:37:26 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 350/1251] eta: 0:09:39 lr: 0.000129 loss: 2.8911 (2.8680) grad_norm: 2.3399 (2.5333) time: 0.6323 [2021-03-28 03:37:32 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 360/1251] eta: 0:09:32 lr: 0.000129 loss: 3.0621 (2.8723) grad_norm: 2.4392 (2.5342) time: 0.6287 [2021-03-28 03:37:38 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 370/1251] eta: 0:09:25 lr: 0.000129 loss: 3.1451 (2.8753) grad_norm: 2.5725 (2.5429) time: 0.6309 [2021-03-28 03:37:45 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 380/1251] eta: 0:09:19 lr: 0.000129 loss: 3.0631 (2.8758) grad_norm: 2.6396 (2.5428) time: 0.6347 [2021-03-28 03:37:51 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 390/1251] eta: 0:09:12 lr: 0.000129 loss: 2.8429 (2.8698) grad_norm: 2.4377 (2.5403) time: 0.6365 [2021-03-28 03:37:57 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 400/1251] eta: 0:09:05 lr: 0.000129 loss: 2.8147 (2.8708) grad_norm: 2.3533 (2.5447) time: 0.6303 [2021-03-28 03:38:04 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 410/1251] eta: 0:08:59 lr: 0.000129 loss: 2.8944 (2.8691) grad_norm: 2.3759 (2.5435) time: 0.6286 [2021-03-28 03:38:10 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 420/1251] eta: 0:08:52 lr: 0.000129 loss: 3.0381 (2.8747) grad_norm: 2.3872 (2.5439) time: 0.6284 [2021-03-28 03:38:16 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 430/1251] eta: 0:08:45 lr: 0.000129 loss: 3.0852 (2.8743) grad_norm: 2.3662 (2.5401) time: 0.6252 [2021-03-28 03:38:22 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 440/1251] eta: 0:08:39 lr: 0.000129 loss: 2.8064 (2.8698) grad_norm: 2.3328 (2.5373) time: 0.6268 [2021-03-28 03:38:29 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 450/1251] eta: 0:08:32 lr: 0.000129 loss: 2.7001 (2.8695) grad_norm: 2.3903 (2.5405) time: 0.6288 [2021-03-28 03:38:35 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 460/1251] eta: 0:08:25 lr: 0.000129 loss: 2.8790 (2.8706) grad_norm: 2.4996 (2.5457) time: 0.6303 [2021-03-28 03:38:41 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 470/1251] eta: 0:08:19 lr: 0.000129 loss: 2.9821 (2.8697) grad_norm: 2.7902 (2.5479) time: 0.6290 [2021-03-28 03:38:48 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 480/1251] eta: 0:08:12 lr: 0.000129 loss: 2.9143 (2.8642) grad_norm: 2.4310 (2.5445) time: 0.6303 [2021-03-28 03:38:54 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 490/1251] eta: 0:08:06 lr: 0.000129 loss: 2.7853 (2.8644) grad_norm: 2.4341 (2.5482) time: 0.6286 [2021-03-28 03:39:00 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 500/1251] eta: 0:07:59 lr: 0.000129 loss: 3.0928 (2.8682) grad_norm: 2.5430 (2.5492) time: 0.6244 [2021-03-28 03:39:06 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 510/1251] eta: 0:07:53 lr: 0.000129 loss: 3.0478 (2.8683) grad_norm: 2.5430 (2.5482) time: 0.6262 [2021-03-28 03:39:13 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 520/1251] eta: 0:07:46 lr: 0.000129 loss: 3.0478 (2.8730) grad_norm: 2.4882 (2.5491) time: 0.6323 [2021-03-28 03:39:19 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 530/1251] eta: 0:07:40 lr: 0.000129 loss: 3.1352 (2.8749) grad_norm: 2.4882 (2.5486) time: 0.6300 [2021-03-28 03:39:25 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 540/1251] eta: 0:07:33 lr: 0.000129 loss: 2.9184 (2.8746) grad_norm: 2.4934 (2.5483) time: 0.6327 [2021-03-28 03:39:32 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 550/1251] eta: 0:07:27 lr: 0.000129 loss: 2.8995 (2.8745) grad_norm: 2.4475 (2.5465) time: 0.6372 [2021-03-28 03:39:38 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 560/1251] eta: 0:07:20 lr: 0.000129 loss: 2.9823 (2.8734) grad_norm: 2.4475 (2.5473) time: 0.6339 [2021-03-28 03:39:45 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 570/1251] eta: 0:07:14 lr: 0.000129 loss: 2.6787 (2.8685) grad_norm: 2.5095 (2.5464) time: 0.6368 [2021-03-28 03:39:51 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 580/1251] eta: 0:07:08 lr: 0.000129 loss: 2.7839 (2.8727) grad_norm: 2.4223 (2.5429) time: 0.6353 [2021-03-28 03:39:57 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 590/1251] eta: 0:07:01 lr: 0.000129 loss: 3.0120 (2.8697) grad_norm: 2.3496 (2.5415) time: 0.6309 [2021-03-28 03:40:03 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 600/1251] eta: 0:06:55 lr: 0.000129 loss: 3.0106 (2.8713) grad_norm: 2.3496 (2.5382) time: 0.6320 [2021-03-28 03:40:10 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 610/1251] eta: 0:06:48 lr: 0.000129 loss: 3.0106 (2.8708) grad_norm: 2.4024 (2.5396) time: 0.6305 [2021-03-28 03:40:16 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 620/1251] eta: 0:06:42 lr: 0.000129 loss: 2.9397 (2.8689) grad_norm: 2.5860 (2.5385) time: 0.6338 [2021-03-28 03:40:22 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 630/1251] eta: 0:06:35 lr: 0.000129 loss: 2.9670 (2.8682) grad_norm: 2.5039 (2.5399) time: 0.6347 [2021-03-28 03:40:29 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 640/1251] eta: 0:06:29 lr: 0.000129 loss: 2.9207 (2.8681) grad_norm: 2.2786 (2.5372) time: 0.6330 [2021-03-28 03:40:35 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 650/1251] eta: 0:06:23 lr: 0.000129 loss: 3.0298 (2.8716) grad_norm: 2.3647 (2.5354) time: 0.6332 [2021-03-28 03:40:41 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 660/1251] eta: 0:06:16 lr: 0.000129 loss: 3.0517 (2.8720) grad_norm: 2.3581 (2.5343) time: 0.6284 [2021-03-28 03:40:48 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 670/1251] eta: 0:06:10 lr: 0.000128 loss: 2.9343 (2.8737) grad_norm: 2.3581 (2.5325) time: 0.6299 [2021-03-28 03:40:54 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 680/1251] eta: 0:06:03 lr: 0.000128 loss: 3.0622 (2.8724) grad_norm: 2.4801 (2.5353) time: 0.6374 [2021-03-28 03:41:01 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 690/1251] eta: 0:05:57 lr: 0.000128 loss: 3.0490 (2.8740) grad_norm: 2.5479 (2.5338) time: 0.6405 [2021-03-28 03:41:07 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 700/1251] eta: 0:05:50 lr: 0.000128 loss: 3.0921 (2.8763) grad_norm: 2.4431 (2.5353) time: 0.6302 [2021-03-28 03:41:13 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 710/1251] eta: 0:05:44 lr: 0.000128 loss: 2.9717 (2.8703) grad_norm: 2.6859 (2.5399) time: 0.6285 [2021-03-28 03:41:19 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 720/1251] eta: 0:05:38 lr: 0.000128 loss: 2.7870 (2.8726) grad_norm: 2.3335 (2.5395) time: 0.6307 [2021-03-28 03:41:26 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 730/1251] eta: 0:05:31 lr: 0.000128 loss: 2.9585 (2.8703) grad_norm: 2.5462 (2.5444) time: 0.6275 [2021-03-28 03:41:32 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 740/1251] eta: 0:05:25 lr: 0.000128 loss: 2.6309 (2.8690) grad_norm: 2.5462 (2.5461) time: 0.6316 [2021-03-28 03:41:38 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 750/1251] eta: 0:05:19 lr: 0.000128 loss: 2.9361 (2.8708) grad_norm: 2.3816 (2.5451) time: 0.6384 [2021-03-28 03:41:45 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 760/1251] eta: 0:05:12 lr: 0.000128 loss: 3.0068 (2.8726) grad_norm: 2.3955 (2.5437) time: 0.6385 [2021-03-28 03:41:51 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 770/1251] eta: 0:05:06 lr: 0.000128 loss: 2.8985 (2.8701) grad_norm: 2.3955 (2.5452) time: 0.6371 [2021-03-28 03:41:57 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 780/1251] eta: 0:04:59 lr: 0.000128 loss: 2.5493 (2.8686) grad_norm: 2.4694 (2.5435) time: 0.6308 [2021-03-28 03:42:04 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 790/1251] eta: 0:04:53 lr: 0.000128 loss: 2.8672 (2.8682) grad_norm: 2.3810 (2.5447) time: 0.6252 [2021-03-28 03:42:10 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 800/1251] eta: 0:04:47 lr: 0.000128 loss: 2.9862 (2.8679) grad_norm: 2.4129 (2.5434) time: 0.6281 [2021-03-28 03:42:16 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 810/1251] eta: 0:04:40 lr: 0.000128 loss: 2.9430 (2.8664) grad_norm: 2.4547 (2.5474) time: 0.6284 [2021-03-28 03:42:23 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 820/1251] eta: 0:04:34 lr: 0.000128 loss: 2.8898 (2.8662) grad_norm: 2.5225 (nan) time: 0.6287 [2021-03-28 03:42:29 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 830/1251] eta: 0:04:27 lr: 0.000128 loss: 2.9602 (2.8673) grad_norm: 2.4548 (nan) time: 0.6262 [2021-03-28 03:42:35 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 840/1251] eta: 0:04:21 lr: 0.000128 loss: 2.9376 (2.8637) grad_norm: 2.3751 (nan) time: 0.6276 [2021-03-28 03:42:41 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 850/1251] eta: 0:04:14 lr: 0.000128 loss: 2.8006 (2.8635) grad_norm: 2.3751 (nan) time: 0.6289 [2021-03-28 03:42:48 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 860/1251] eta: 0:04:08 lr: 0.000128 loss: 2.8867 (2.8638) grad_norm: 2.4325 (nan) time: 0.6260 [2021-03-28 03:42:54 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 870/1251] eta: 0:04:02 lr: 0.000128 loss: 2.9421 (2.8614) grad_norm: 2.4031 (nan) time: 0.6284 [2021-03-28 03:43:00 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 880/1251] eta: 0:03:55 lr: 0.000128 loss: 2.9421 (2.8592) grad_norm: 2.3776 (nan) time: 0.6314 [2021-03-28 03:43:07 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 890/1251] eta: 0:03:49 lr: 0.000128 loss: 2.8291 (2.8571) grad_norm: 2.3761 (nan) time: 0.6312 [2021-03-28 03:43:13 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 900/1251] eta: 0:03:43 lr: 0.000128 loss: 2.8734 (2.8567) grad_norm: 2.3974 (nan) time: 0.6287 [2021-03-28 03:43:19 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 910/1251] eta: 0:03:36 lr: 0.000128 loss: 2.9448 (2.8569) grad_norm: 2.5071 (nan) time: 0.6251 [2021-03-28 03:43:25 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 920/1251] eta: 0:03:30 lr: 0.000128 loss: 2.8852 (2.8564) grad_norm: 2.5517 (nan) time: 0.6274 [2021-03-28 03:43:32 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 930/1251] eta: 0:03:23 lr: 0.000128 loss: 2.8875 (2.8580) grad_norm: 2.5944 (nan) time: 0.6313 [2021-03-28 03:43:38 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 940/1251] eta: 0:03:17 lr: 0.000128 loss: 3.1144 (2.8614) grad_norm: 2.4067 (nan) time: 0.6290 [2021-03-28 03:43:44 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 950/1251] eta: 0:03:11 lr: 0.000128 loss: 3.2036 (2.8651) grad_norm: 2.4067 (nan) time: 0.6259 [2021-03-28 03:43:51 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 960/1251] eta: 0:03:04 lr: 0.000128 loss: 3.0584 (2.8645) grad_norm: 2.3043 (nan) time: 0.6287 [2021-03-28 03:43:57 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 970/1251] eta: 0:02:58 lr: 0.000128 loss: 2.9004 (2.8633) grad_norm: 2.4680 (nan) time: 0.6320 [2021-03-28 03:44:03 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 980/1251] eta: 0:02:52 lr: 0.000128 loss: 2.9500 (2.8650) grad_norm: 2.4680 (nan) time: 0.6355 [2021-03-28 03:44:10 swin_base_patch4_window7_224] INFO: Epoch: [232] [ 990/1251] eta: 0:02:45 lr: 0.000128 loss: 3.0320 (2.8664) grad_norm: 2.4723 (nan) time: 0.6359 [2021-03-28 03:44:16 swin_base_patch4_window7_224] INFO: Epoch: [232] [1000/1251] eta: 0:02:39 lr: 0.000128 loss: 3.0391 (2.8658) grad_norm: 2.5345 (nan) time: 0.6313 [2021-03-28 03:44:22 swin_base_patch4_window7_224] INFO: Epoch: [232] [1010/1251] eta: 0:02:33 lr: 0.000128 loss: 3.0291 (2.8668) grad_norm: 2.5502 (nan) time: 0.6284 [2021-03-28 03:44:28 swin_base_patch4_window7_224] INFO: Epoch: [232] [1020/1251] eta: 0:02:26 lr: 0.000128 loss: 3.0525 (2.8678) grad_norm: 2.5053 (nan) time: 0.6279 [2021-03-28 03:44:35 swin_base_patch4_window7_224] INFO: Epoch: [232] [1030/1251] eta: 0:02:20 lr: 0.000128 loss: 3.0698 (2.8685) grad_norm: 2.4421 (nan) time: 0.6326 [2021-03-28 03:44:41 swin_base_patch4_window7_224] INFO: Epoch: [232] [1040/1251] eta: 0:02:13 lr: 0.000127 loss: 2.9724 (2.8690) grad_norm: 2.5036 (nan) time: 0.6372 [2021-03-28 03:44:47 swin_base_patch4_window7_224] INFO: Epoch: [232] [1050/1251] eta: 0:02:07 lr: 0.000127 loss: 2.9724 (2.8682) grad_norm: 2.4901 (nan) time: 0.6308 [2021-03-28 03:44:54 swin_base_patch4_window7_224] INFO: Epoch: [232] [1060/1251] eta: 0:02:01 lr: 0.000127 loss: 2.9027 (2.8679) grad_norm: 2.4153 (nan) time: 0.6305 [2021-03-28 03:45:00 swin_base_patch4_window7_224] INFO: Epoch: [232] [1070/1251] eta: 0:01:54 lr: 0.000127 loss: 2.9047 (2.8686) grad_norm: 2.3723 (nan) time: 0.6301 [2021-03-28 03:45:06 swin_base_patch4_window7_224] INFO: Epoch: [232] [1080/1251] eta: 0:01:48 lr: 0.000127 loss: 2.9706 (2.8683) grad_norm: 2.4592 (nan) time: 0.6267 [2021-03-28 03:45:13 swin_base_patch4_window7_224] INFO: Epoch: [232] [1090/1251] eta: 0:01:42 lr: 0.000127 loss: 2.8850 (2.8673) grad_norm: 2.5211 (nan) time: 0.6259 [2021-03-28 03:45:19 swin_base_patch4_window7_224] INFO: Epoch: [232] [1100/1251] eta: 0:01:35 lr: 0.000127 loss: 2.6709 (2.8645) grad_norm: 2.4856 (nan) time: 0.6260 [2021-03-28 03:45:25 swin_base_patch4_window7_224] INFO: Epoch: [232] [1110/1251] eta: 0:01:29 lr: 0.000127 loss: 2.7019 (2.8649) grad_norm: 2.4253 (nan) time: 0.6282 [2021-03-28 03:45:31 swin_base_patch4_window7_224] INFO: Epoch: [232] [1120/1251] eta: 0:01:23 lr: 0.000127 loss: 3.0252 (2.8672) grad_norm: 2.3288 (nan) time: 0.6282 [2021-03-28 03:45:38 swin_base_patch4_window7_224] INFO: Epoch: [232] [1130/1251] eta: 0:01:16 lr: 0.000127 loss: 3.0252 (2.8660) grad_norm: 2.4040 (nan) time: 0.6339 [2021-03-28 03:45:44 swin_base_patch4_window7_224] INFO: Epoch: [232] [1140/1251] eta: 0:01:10 lr: 0.000127 loss: 2.8762 (2.8662) grad_norm: 2.4183 (nan) time: 0.6341 [2021-03-28 03:45:50 swin_base_patch4_window7_224] INFO: Epoch: [232] [1150/1251] eta: 0:01:04 lr: 0.000127 loss: 2.8435 (2.8652) grad_norm: 2.4987 (nan) time: 0.6299 [2021-03-28 03:45:57 swin_base_patch4_window7_224] INFO: Epoch: [232] [1160/1251] eta: 0:00:57 lr: 0.000127 loss: 2.8034 (2.8646) grad_norm: 2.4271 (nan) time: 0.6274 [2021-03-28 03:46:03 swin_base_patch4_window7_224] INFO: Epoch: [232] [1170/1251] eta: 0:00:51 lr: 0.000127 loss: 2.7898 (2.8637) grad_norm: 2.3939 (nan) time: 0.6289 [2021-03-28 03:46:09 swin_base_patch4_window7_224] INFO: Epoch: [232] [1180/1251] eta: 0:00:45 lr: 0.000127 loss: 2.7272 (2.8622) grad_norm: 2.4489 (nan) time: 0.6371 [2021-03-28 03:46:16 swin_base_patch4_window7_224] INFO: Epoch: [232] [1190/1251] eta: 0:00:38 lr: 0.000127 loss: 2.7272 (2.8611) grad_norm: 2.5566 (nan) time: 0.6383 [2021-03-28 03:46:22 swin_base_patch4_window7_224] INFO: Epoch: [232] [1200/1251] eta: 0:00:32 lr: 0.000127 loss: 2.9823 (2.8611) grad_norm: 2.5313 (nan) time: 0.6321 [2021-03-28 03:46:28 swin_base_patch4_window7_224] INFO: Epoch: [232] [1210/1251] eta: 0:00:26 lr: 0.000127 loss: 3.0636 (2.8621) grad_norm: 2.4192 (nan) time: 0.6277 [2021-03-28 03:46:35 swin_base_patch4_window7_224] INFO: Epoch: [232] [1220/1251] eta: 0:00:19 lr: 0.000127 loss: 3.0583 (2.8622) grad_norm: 2.5748 (nan) time: 0.6299 [2021-03-28 03:46:41 swin_base_patch4_window7_224] INFO: Epoch: [232] [1230/1251] eta: 0:00:13 lr: 0.000127 loss: 2.7808 (2.8616) grad_norm: 2.5225 (nan) time: 0.6339 [2021-03-28 03:46:47 swin_base_patch4_window7_224] INFO: Epoch: [232] [1240/1251] eta: 0:00:06 lr: 0.000127 loss: 2.8452 (2.8624) grad_norm: 2.4011 (nan) time: 0.6339 [2021-03-28 03:46:54 swin_base_patch4_window7_224] INFO: Epoch: [232] [1250/1251] eta: 0:00:00 lr: 0.000127 loss: 3.0133 (2.8649) grad_norm: 2.3271 (nan) time: 0.6253 [2021-03-28 03:47:05 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:23 loss: 0.7726 (0.7726) acc1: 87.5000 (87.5000) acc5: 96.8750 (96.8750) [2021-03-28 03:47:08 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7295 (0.7198) acc1: 82.8125 (83.3807) acc5: 98.4375 (97.7273) [2021-03-28 03:47:10 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7129 (0.7341) acc1: 81.2500 (82.2917) acc5: 98.4375 (97.3214) [2021-03-28 03:47:13 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7824 (0.7706) acc1: 79.6875 (81.6028) acc5: 96.8750 (96.5222) [2021-03-28 03:47:14 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7554 (0.7609) acc1: 79.6875 (81.6311) acc5: 95.3125 (96.3415) [2021-03-28 03:47:16 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7508 (0.7744) acc1: 81.2500 (81.5040) acc5: 95.3125 (96.1280) [2021-03-28 03:47:32 swin_base_patch4_window7_224] INFO: * Acc@1 82.128 Acc@5 96.156 loss 0.769 [2021-03-28 03:47:32 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.1% [2021-03-28 03:47:32 swin_base_patch4_window7_224] INFO: Max accuracy: 82.26% [2021-03-28 03:47:37 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 0/1251] eta: 1:30:42 lr: 0.000127 loss: 2.8277 (2.8277) grad_norm: 2.0213 (2.0213) time: 4.3502 [2021-03-28 03:47:43 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 10/1251] eta: 0:20:00 lr: 0.000127 loss: 3.1394 (2.9438) grad_norm: 2.3474 (2.4812) time: 0.9675 [2021-03-28 03:47:49 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 20/1251] eta: 0:16:35 lr: 0.000127 loss: 3.0209 (2.9776) grad_norm: 2.3474 (2.4617) time: 0.6317 [2021-03-28 03:47:56 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 30/1251] eta: 0:15:22 lr: 0.000127 loss: 2.9992 (2.9645) grad_norm: 2.4974 (2.5447) time: 0.6383 [2021-03-28 03:48:02 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 40/1251] eta: 0:14:37 lr: 0.000127 loss: 2.9954 (2.9504) grad_norm: 2.4404 (2.5133) time: 0.6370 [2021-03-28 03:48:08 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 50/1251] eta: 0:14:07 lr: 0.000127 loss: 3.0186 (2.9658) grad_norm: 2.3980 (2.5314) time: 0.6298 [2021-03-28 03:48:15 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 60/1251] eta: 0:13:44 lr: 0.000127 loss: 2.9381 (2.9571) grad_norm: 2.3971 (2.5270) time: 0.6262 [2021-03-28 03:48:21 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 70/1251] eta: 0:13:29 lr: 0.000127 loss: 3.0026 (2.9701) grad_norm: 2.5245 (2.5313) time: 0.6338 [2021-03-28 03:48:27 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 80/1251] eta: 0:13:14 lr: 0.000127 loss: 3.1067 (2.9746) grad_norm: 2.5159 (2.5177) time: 0.6356 [2021-03-28 03:48:34 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 90/1251] eta: 0:13:01 lr: 0.000127 loss: 3.0463 (2.9744) grad_norm: 2.4994 (2.5356) time: 0.6267 [2021-03-28 03:48:40 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 100/1251] eta: 0:12:49 lr: 0.000127 loss: 2.7472 (2.9223) grad_norm: 2.5319 (2.5626) time: 0.6292 [2021-03-28 03:48:46 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 110/1251] eta: 0:12:39 lr: 0.000127 loss: 2.9153 (2.9362) grad_norm: 2.5319 (2.5644) time: 0.6339 [2021-03-28 03:48:53 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 120/1251] eta: 0:12:30 lr: 0.000127 loss: 3.0361 (2.9287) grad_norm: 2.5181 (2.5674) time: 0.6365 [2021-03-28 03:48:59 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 130/1251] eta: 0:12:20 lr: 0.000127 loss: 2.7883 (2.9282) grad_norm: 2.4159 (2.6323) time: 0.6321 [2021-03-28 03:49:05 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 140/1251] eta: 0:12:11 lr: 0.000127 loss: 3.1118 (2.9435) grad_norm: 2.5430 (2.6504) time: 0.6279 [2021-03-28 03:49:12 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 150/1251] eta: 0:12:03 lr: 0.000127 loss: 3.1118 (2.9492) grad_norm: 2.5430 (2.6581) time: 0.6315 [2021-03-28 03:49:18 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 160/1251] eta: 0:11:54 lr: 0.000126 loss: 2.9973 (2.9462) grad_norm: 2.3739 (2.6394) time: 0.6312 [2021-03-28 03:49:24 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 170/1251] eta: 0:11:46 lr: 0.000126 loss: 2.9228 (2.9468) grad_norm: 2.4065 (2.6302) time: 0.6314 [2021-03-28 03:49:31 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 180/1251] eta: 0:11:39 lr: 0.000126 loss: 2.9203 (2.9351) grad_norm: 2.4345 (2.6164) time: 0.6338 [2021-03-28 03:49:37 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 190/1251] eta: 0:11:31 lr: 0.000126 loss: 2.9228 (2.9323) grad_norm: 2.4345 (2.6536) time: 0.6303 [2021-03-28 03:49:43 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 200/1251] eta: 0:11:23 lr: 0.000126 loss: 3.0203 (2.9308) grad_norm: 2.5109 (2.6494) time: 0.6301 [2021-03-28 03:49:50 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 210/1251] eta: 0:11:16 lr: 0.000126 loss: 3.0203 (2.9350) grad_norm: 2.4883 (2.6515) time: 0.6315 [2021-03-28 03:49:56 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 220/1251] eta: 0:11:08 lr: 0.000126 loss: 2.9010 (2.9340) grad_norm: 2.3577 (2.6423) time: 0.6288 [2021-03-28 03:50:02 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 230/1251] eta: 0:11:01 lr: 0.000126 loss: 3.0827 (2.9456) grad_norm: 2.5770 (2.6533) time: 0.6312 [2021-03-28 03:50:08 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 240/1251] eta: 0:10:54 lr: 0.000126 loss: 3.0106 (2.9290) grad_norm: 2.6076 (2.6791) time: 0.6318 [2021-03-28 03:50:15 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 250/1251] eta: 0:10:47 lr: 0.000126 loss: 2.7560 (2.9179) grad_norm: 2.4948 (2.6754) time: 0.6319 [2021-03-28 03:50:21 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 260/1251] eta: 0:10:40 lr: 0.000126 loss: 2.8018 (2.9189) grad_norm: 2.4512 (2.6688) time: 0.6361 [2021-03-28 03:50:28 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 270/1251] eta: 0:10:33 lr: 0.000126 loss: 2.9485 (2.9165) grad_norm: 2.4184 (2.6651) time: 0.6376 [2021-03-28 03:50:34 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 280/1251] eta: 0:10:26 lr: 0.000126 loss: 2.7873 (2.9115) grad_norm: 2.3957 (2.6637) time: 0.6356 [2021-03-28 03:50:40 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 290/1251] eta: 0:10:19 lr: 0.000126 loss: 2.7378 (2.9011) grad_norm: 2.3957 (2.6649) time: 0.6313 [2021-03-28 03:50:46 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 300/1251] eta: 0:10:12 lr: 0.000126 loss: 2.8554 (2.9004) grad_norm: 2.3523 (2.6523) time: 0.6271 [2021-03-28 03:50:53 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 310/1251] eta: 0:10:05 lr: 0.000126 loss: 3.0113 (2.9019) grad_norm: 2.3631 (2.6506) time: 0.6277 [2021-03-28 03:50:59 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 320/1251] eta: 0:09:58 lr: 0.000126 loss: 2.7870 (2.8956) grad_norm: 2.6443 (2.6577) time: 0.6267 [2021-03-28 03:51:05 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 330/1251] eta: 0:09:51 lr: 0.000126 loss: 2.8515 (2.8992) grad_norm: 2.7605 (2.6706) time: 0.6243 [2021-03-28 03:51:12 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 340/1251] eta: 0:09:45 lr: 0.000126 loss: 3.0061 (2.9016) grad_norm: 2.6679 (2.6673) time: 0.6312 [2021-03-28 03:51:18 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 350/1251] eta: 0:09:38 lr: 0.000126 loss: 3.0147 (2.9067) grad_norm: 2.4450 (2.6668) time: 0.6326 [2021-03-28 03:51:24 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 360/1251] eta: 0:09:31 lr: 0.000126 loss: 3.0147 (2.9125) grad_norm: 2.4741 (2.6732) time: 0.6264 [2021-03-28 03:51:30 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 370/1251] eta: 0:09:24 lr: 0.000126 loss: 2.9507 (2.9095) grad_norm: 2.5334 (2.6750) time: 0.6261 [2021-03-28 03:51:37 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 380/1251] eta: 0:09:18 lr: 0.000126 loss: 2.9650 (2.9077) grad_norm: 2.7055 (2.6808) time: 0.6302 [2021-03-28 03:51:43 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 390/1251] eta: 0:09:11 lr: 0.000126 loss: 2.9650 (2.9041) grad_norm: 2.6823 (2.6764) time: 0.6354 [2021-03-28 03:51:49 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 400/1251] eta: 0:09:05 lr: 0.000126 loss: 3.0673 (2.9129) grad_norm: 2.6014 (2.6914) time: 0.6370 [2021-03-28 03:51:56 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 410/1251] eta: 0:08:58 lr: 0.000126 loss: 3.1456 (2.9170) grad_norm: 2.5790 (2.6865) time: 0.6294 [2021-03-28 03:52:02 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 420/1251] eta: 0:08:52 lr: 0.000126 loss: 3.0370 (2.9167) grad_norm: 2.5409 (2.6998) time: 0.6292 [2021-03-28 03:52:08 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 430/1251] eta: 0:08:45 lr: 0.000126 loss: 2.9744 (2.9193) grad_norm: 2.4410 (2.7041) time: 0.6299 [2021-03-28 03:52:15 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 440/1251] eta: 0:08:38 lr: 0.000126 loss: 2.8639 (2.9140) grad_norm: 2.3381 (2.6976) time: 0.6271 [2021-03-28 03:52:21 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 450/1251] eta: 0:08:32 lr: 0.000126 loss: 2.7060 (2.9127) grad_norm: 2.4378 (2.6935) time: 0.6266 [2021-03-28 03:52:27 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 460/1251] eta: 0:08:25 lr: 0.000126 loss: 2.9743 (2.9124) grad_norm: 2.4156 (2.6887) time: 0.6242 [2021-03-28 03:52:33 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 470/1251] eta: 0:08:18 lr: 0.000126 loss: 3.0075 (2.9134) grad_norm: 2.4156 (2.6941) time: 0.6260 [2021-03-28 03:52:40 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 480/1251] eta: 0:08:12 lr: 0.000126 loss: 3.0133 (2.9129) grad_norm: 2.4426 (2.6905) time: 0.6317 [2021-03-28 03:52:46 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 490/1251] eta: 0:08:05 lr: 0.000126 loss: 2.9151 (2.9116) grad_norm: 2.4426 (2.6927) time: 0.6293 [2021-03-28 03:52:52 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 500/1251] eta: 0:07:59 lr: 0.000126 loss: 2.8739 (2.9104) grad_norm: 2.6085 (2.6911) time: 0.6251 [2021-03-28 03:52:58 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 510/1251] eta: 0:07:52 lr: 0.000126 loss: 2.9235 (2.9139) grad_norm: 2.4836 (2.6884) time: 0.6243 [2021-03-28 03:53:05 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 520/1251] eta: 0:07:46 lr: 0.000126 loss: 2.9602 (2.9149) grad_norm: 2.4218 (2.6829) time: 0.6270 [2021-03-28 03:53:11 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 530/1251] eta: 0:07:39 lr: 0.000126 loss: 2.9602 (2.9173) grad_norm: 2.4932 (2.6850) time: 0.6313 [2021-03-28 03:53:17 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 540/1251] eta: 0:07:33 lr: 0.000125 loss: 2.9607 (2.9174) grad_norm: 2.4623 (2.6805) time: 0.6245 [2021-03-28 03:53:24 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 550/1251] eta: 0:07:26 lr: 0.000125 loss: 2.9399 (2.9171) grad_norm: 2.6030 (2.6828) time: 0.6263 [2021-03-28 03:53:30 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 560/1251] eta: 0:07:20 lr: 0.000125 loss: 2.9117 (2.9135) grad_norm: 2.6251 (2.6807) time: 0.6327 [2021-03-28 03:53:36 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 570/1251] eta: 0:07:13 lr: 0.000125 loss: 2.8927 (2.9177) grad_norm: 2.4540 (2.6791) time: 0.6289 [2021-03-28 03:53:42 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 580/1251] eta: 0:07:07 lr: 0.000125 loss: 2.8717 (2.9137) grad_norm: 2.6229 (2.6774) time: 0.6278 [2021-03-28 03:53:49 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 590/1251] eta: 0:07:00 lr: 0.000125 loss: 2.6550 (2.9099) grad_norm: 2.6405 (2.6759) time: 0.6254 [2021-03-28 03:53:55 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 600/1251] eta: 0:06:54 lr: 0.000125 loss: 2.8383 (2.9089) grad_norm: 2.6405 (2.6742) time: 0.6241 [2021-03-28 03:54:01 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 610/1251] eta: 0:06:47 lr: 0.000125 loss: 2.8962 (2.9048) grad_norm: 2.5062 (2.6736) time: 0.6277 [2021-03-28 03:54:08 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 620/1251] eta: 0:06:41 lr: 0.000125 loss: 2.7875 (2.9036) grad_norm: 2.4001 (2.6706) time: 0.6283 [2021-03-28 03:54:14 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 630/1251] eta: 0:06:34 lr: 0.000125 loss: 3.0147 (2.9063) grad_norm: 2.3846 (2.6776) time: 0.6301 [2021-03-28 03:54:20 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 640/1251] eta: 0:06:28 lr: 0.000125 loss: 3.0972 (2.9054) grad_norm: 2.5911 (2.6774) time: 0.6286 [2021-03-28 03:54:26 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 650/1251] eta: 0:06:22 lr: 0.000125 loss: 2.9391 (2.9016) grad_norm: 2.4522 (2.6739) time: 0.6287 [2021-03-28 03:54:33 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 660/1251] eta: 0:06:15 lr: 0.000125 loss: 2.7329 (2.9021) grad_norm: 2.4403 (2.6717) time: 0.6344 [2021-03-28 03:54:39 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 670/1251] eta: 0:06:09 lr: 0.000125 loss: 2.7746 (2.8999) grad_norm: 2.5028 (2.6692) time: 0.6332 [2021-03-28 03:54:45 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 680/1251] eta: 0:06:02 lr: 0.000125 loss: 2.8564 (2.9010) grad_norm: 2.3995 (2.6657) time: 0.6253 [2021-03-28 03:54:52 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 690/1251] eta: 0:05:56 lr: 0.000125 loss: 2.8800 (2.9005) grad_norm: 2.3990 (2.6641) time: 0.6217 [2021-03-28 03:54:58 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 700/1251] eta: 0:05:50 lr: 0.000125 loss: 2.7834 (2.9001) grad_norm: 2.4041 (2.6618) time: 0.6268 [2021-03-28 03:55:04 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 710/1251] eta: 0:05:43 lr: 0.000125 loss: 2.8497 (2.9002) grad_norm: 2.3360 (2.6590) time: 0.6307 [2021-03-28 03:55:10 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 720/1251] eta: 0:05:37 lr: 0.000125 loss: 2.8448 (2.8961) grad_norm: 2.3255 (2.6566) time: 0.6266 [2021-03-28 03:55:17 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 730/1251] eta: 0:05:30 lr: 0.000125 loss: 2.9255 (2.8983) grad_norm: 2.4367 (2.6549) time: 0.6310 [2021-03-28 03:55:23 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 740/1251] eta: 0:05:24 lr: 0.000125 loss: 3.0983 (2.9009) grad_norm: 2.5156 (2.6547) time: 0.6400 [2021-03-28 03:55:30 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 750/1251] eta: 0:05:18 lr: 0.000125 loss: 2.9695 (2.8995) grad_norm: 2.6466 (2.6564) time: 0.6408 [2021-03-28 03:55:36 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 760/1251] eta: 0:05:11 lr: 0.000125 loss: 2.7056 (2.8973) grad_norm: 2.5354 (2.6565) time: 0.6336 [2021-03-28 03:55:42 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 770/1251] eta: 0:05:05 lr: 0.000125 loss: 2.7056 (2.8943) grad_norm: 2.3723 (2.6528) time: 0.6299 [2021-03-28 03:55:48 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 780/1251] eta: 0:04:59 lr: 0.000125 loss: 2.6740 (2.8903) grad_norm: 2.2825 (2.6490) time: 0.6292 [2021-03-28 03:55:55 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 790/1251] eta: 0:04:52 lr: 0.000125 loss: 2.7600 (2.8914) grad_norm: 2.2915 (2.6487) time: 0.6268 [2021-03-28 03:56:01 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 800/1251] eta: 0:04:46 lr: 0.000125 loss: 3.0824 (2.8904) grad_norm: 2.3249 (2.6453) time: 0.6258 [2021-03-28 03:56:07 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 810/1251] eta: 0:04:39 lr: 0.000125 loss: 3.1069 (2.8938) grad_norm: 2.3235 (2.6445) time: 0.6261 [2021-03-28 03:56:14 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 820/1251] eta: 0:04:33 lr: 0.000125 loss: 3.1229 (2.8949) grad_norm: 2.3942 (2.6450) time: 0.6351 [2021-03-28 03:56:20 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 830/1251] eta: 0:04:27 lr: 0.000125 loss: 2.8793 (2.8927) grad_norm: 2.6129 (2.6518) time: 0.6334 [2021-03-28 03:56:26 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 840/1251] eta: 0:04:20 lr: 0.000125 loss: 2.8787 (2.8944) grad_norm: 2.6898 (2.6532) time: 0.6225 [2021-03-28 03:56:32 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 850/1251] eta: 0:04:14 lr: 0.000125 loss: 3.0180 (2.8945) grad_norm: 2.4588 (2.6533) time: 0.6257 [2021-03-28 03:56:39 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 860/1251] eta: 0:04:08 lr: 0.000125 loss: 2.9868 (2.8952) grad_norm: 2.4248 (2.6589) time: 0.6400 [2021-03-28 03:56:45 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 870/1251] eta: 0:04:01 lr: 0.000125 loss: 2.7726 (2.8903) grad_norm: 2.4248 (2.6603) time: 0.6400 [2021-03-28 03:56:52 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 880/1251] eta: 0:03:55 lr: 0.000125 loss: 2.8466 (2.8918) grad_norm: 2.3942 (2.6592) time: 0.6352 [2021-03-28 03:56:58 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 890/1251] eta: 0:03:49 lr: 0.000125 loss: 3.0699 (2.8901) grad_norm: 2.3918 (2.6570) time: 0.6313 [2021-03-28 03:57:04 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 900/1251] eta: 0:03:42 lr: 0.000125 loss: 2.6930 (2.8889) grad_norm: 2.2245 (2.6552) time: 0.6289 [2021-03-28 03:57:10 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 910/1251] eta: 0:03:36 lr: 0.000124 loss: 2.8577 (2.8907) grad_norm: 2.5352 (2.6571) time: 0.6300 [2021-03-28 03:57:17 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 920/1251] eta: 0:03:29 lr: 0.000124 loss: 3.0058 (2.8909) grad_norm: 2.5352 (2.6539) time: 0.6288 [2021-03-28 03:57:23 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 930/1251] eta: 0:03:23 lr: 0.000124 loss: 3.0389 (2.8923) grad_norm: 2.3956 (2.6540) time: 0.6350 [2021-03-28 03:57:30 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 940/1251] eta: 0:03:17 lr: 0.000124 loss: 3.0389 (2.8924) grad_norm: 2.4865 (2.6513) time: 0.6345 [2021-03-28 03:57:36 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 950/1251] eta: 0:03:10 lr: 0.000124 loss: 2.9690 (2.8902) grad_norm: 2.3306 (2.6480) time: 0.6326 [2021-03-28 03:57:42 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 960/1251] eta: 0:03:04 lr: 0.000124 loss: 2.8001 (2.8900) grad_norm: 2.3306 (2.6464) time: 0.6326 [2021-03-28 03:57:49 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 970/1251] eta: 0:02:58 lr: 0.000124 loss: 3.0980 (2.8910) grad_norm: 2.4303 (2.6466) time: 0.6339 [2021-03-28 03:57:55 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 980/1251] eta: 0:02:51 lr: 0.000124 loss: 3.0907 (2.8919) grad_norm: 2.4304 (2.6468) time: 0.6320 [2021-03-28 03:58:01 swin_base_patch4_window7_224] INFO: Epoch: [233] [ 990/1251] eta: 0:02:45 lr: 0.000124 loss: 3.0565 (2.8934) grad_norm: 2.5015 (2.6455) time: 0.6295 [2021-03-28 03:58:07 swin_base_patch4_window7_224] INFO: Epoch: [233] [1000/1251] eta: 0:02:39 lr: 0.000124 loss: 2.8393 (2.8930) grad_norm: 2.5015 (2.6463) time: 0.6314 [2021-03-28 03:58:14 swin_base_patch4_window7_224] INFO: Epoch: [233] [1010/1251] eta: 0:02:32 lr: 0.000124 loss: 2.8772 (2.8935) grad_norm: 2.3448 (2.6434) time: 0.6266 [2021-03-28 03:58:20 swin_base_patch4_window7_224] INFO: Epoch: [233] [1020/1251] eta: 0:02:26 lr: 0.000124 loss: 2.9383 (2.8934) grad_norm: 2.3016 (2.6422) time: 0.6258 [2021-03-28 03:58:26 swin_base_patch4_window7_224] INFO: Epoch: [233] [1030/1251] eta: 0:02:20 lr: 0.000124 loss: 2.9322 (2.8943) grad_norm: 2.2806 (2.6405) time: 0.6288 [2021-03-28 03:58:32 swin_base_patch4_window7_224] INFO: Epoch: [233] [1040/1251] eta: 0:02:13 lr: 0.000124 loss: 3.0353 (2.8947) grad_norm: 2.4909 (2.6416) time: 0.6258 [2021-03-28 03:58:39 swin_base_patch4_window7_224] INFO: Epoch: [233] [1050/1251] eta: 0:02:07 lr: 0.000124 loss: 3.0882 (2.8959) grad_norm: 2.3540 (2.6389) time: 0.6244 [2021-03-28 03:58:45 swin_base_patch4_window7_224] INFO: Epoch: [233] [1060/1251] eta: 0:02:01 lr: 0.000124 loss: 3.0162 (2.8964) grad_norm: 2.4609 (2.6389) time: 0.6299 [2021-03-28 03:58:51 swin_base_patch4_window7_224] INFO: Epoch: [233] [1070/1251] eta: 0:01:54 lr: 0.000124 loss: 2.9962 (2.8966) grad_norm: 2.6082 (2.6380) time: 0.6310 [2021-03-28 03:58:58 swin_base_patch4_window7_224] INFO: Epoch: [233] [1080/1251] eta: 0:01:48 lr: 0.000124 loss: 2.8273 (2.8945) grad_norm: 2.5037 (2.6375) time: 0.6273 [2021-03-28 03:59:04 swin_base_patch4_window7_224] INFO: Epoch: [233] [1090/1251] eta: 0:01:42 lr: 0.000124 loss: 2.8273 (2.8946) grad_norm: 2.5669 (2.6383) time: 0.6266 [2021-03-28 03:59:10 swin_base_patch4_window7_224] INFO: Epoch: [233] [1100/1251] eta: 0:01:35 lr: 0.000124 loss: 3.1405 (2.8959) grad_norm: 2.5669 (2.6400) time: 0.6267 [2021-03-28 03:59:16 swin_base_patch4_window7_224] INFO: Epoch: [233] [1110/1251] eta: 0:01:29 lr: 0.000124 loss: 3.0862 (2.8963) grad_norm: 2.5593 (2.6421) time: 0.6232 [2021-03-28 03:59:23 swin_base_patch4_window7_224] INFO: Epoch: [233] [1120/1251] eta: 0:01:22 lr: 0.000124 loss: 3.0501 (2.8967) grad_norm: 2.4523 (2.6420) time: 0.6244 [2021-03-28 03:59:29 swin_base_patch4_window7_224] INFO: Epoch: [233] [1130/1251] eta: 0:01:16 lr: 0.000124 loss: 3.0131 (2.8964) grad_norm: 2.3978 (2.6422) time: 0.6280 [2021-03-28 03:59:35 swin_base_patch4_window7_224] INFO: Epoch: [233] [1140/1251] eta: 0:01:10 lr: 0.000124 loss: 2.7899 (2.8942) grad_norm: 2.4264 (2.6401) time: 0.6278 [2021-03-28 03:59:41 swin_base_patch4_window7_224] INFO: Epoch: [233] [1150/1251] eta: 0:01:03 lr: 0.000124 loss: 2.9176 (2.8947) grad_norm: 2.4730 (2.6396) time: 0.6265 [2021-03-28 03:59:48 swin_base_patch4_window7_224] INFO: Epoch: [233] [1160/1251] eta: 0:00:57 lr: 0.000124 loss: 2.9351 (2.8940) grad_norm: 2.5171 (2.6382) time: 0.6236 [2021-03-28 03:59:54 swin_base_patch4_window7_224] INFO: Epoch: [233] [1170/1251] eta: 0:00:51 lr: 0.000124 loss: 2.9415 (2.8951) grad_norm: 2.5117 (2.6374) time: 0.6278 [2021-03-28 04:00:00 swin_base_patch4_window7_224] INFO: Epoch: [233] [1180/1251] eta: 0:00:44 lr: 0.000124 loss: 3.0761 (2.8966) grad_norm: 2.6145 (2.6369) time: 0.6289 [2021-03-28 04:00:07 swin_base_patch4_window7_224] INFO: Epoch: [233] [1190/1251] eta: 0:00:38 lr: 0.000124 loss: 2.9744 (2.8964) grad_norm: 2.4364 (2.6357) time: 0.6293 [2021-03-28 04:00:13 swin_base_patch4_window7_224] INFO: Epoch: [233] [1200/1251] eta: 0:00:32 lr: 0.000124 loss: 2.8581 (2.8967) grad_norm: 2.4272 (2.6346) time: 0.6311 [2021-03-28 04:00:19 swin_base_patch4_window7_224] INFO: Epoch: [233] [1210/1251] eta: 0:00:25 lr: 0.000124 loss: 2.8215 (2.8966) grad_norm: 2.4573 (2.6339) time: 0.6283 [2021-03-28 04:00:25 swin_base_patch4_window7_224] INFO: Epoch: [233] [1220/1251] eta: 0:00:19 lr: 0.000124 loss: 2.7747 (2.8972) grad_norm: 2.4238 (2.6331) time: 0.6287 [2021-03-28 04:00:32 swin_base_patch4_window7_224] INFO: Epoch: [233] [1230/1251] eta: 0:00:13 lr: 0.000124 loss: 2.8073 (2.8950) grad_norm: 2.3226 (2.6310) time: 0.6313 [2021-03-28 04:00:38 swin_base_patch4_window7_224] INFO: Epoch: [233] [1240/1251] eta: 0:00:06 lr: 0.000124 loss: 2.9262 (2.8975) grad_norm: 2.2500 (2.6285) time: 0.6318 [2021-03-28 04:00:44 swin_base_patch4_window7_224] INFO: Epoch: [233] [1250/1251] eta: 0:00:00 lr: 0.000124 loss: 3.1330 (2.8990) grad_norm: 2.3612 (2.6267) time: 0.6222 [2021-03-28 04:00:54 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:48 loss: 1.2921 (1.2921) acc1: 75.0000 (75.0000) acc5: 92.1875 (92.1875) [2021-03-28 04:00:56 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7653 (0.8551) acc1: 82.8125 (80.6818) acc5: 96.8750 (95.5966) [2021-03-28 04:00:58 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7653 (0.8262) acc1: 82.8125 (80.9524) acc5: 95.3125 (95.5357) [2021-03-28 04:01:00 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7734 (0.7908) acc1: 82.8125 (81.6532) acc5: 95.3125 (95.8165) [2021-03-28 04:01:02 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7438 (0.7832) acc1: 82.8125 (81.7454) acc5: 96.8750 (96.1128) [2021-03-28 04:01:03 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7513 (0.7871) acc1: 82.8125 (81.6640) acc5: 96.8750 (96.0960) [2021-03-28 04:01:20 swin_base_patch4_window7_224] INFO: * Acc@1 82.282 Acc@5 96.158 loss 0.767 [2021-03-28 04:01:20 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.3% [2021-03-28 04:01:20 swin_base_patch4_window7_224] INFO: Max accuracy: 82.28% [2021-03-28 04:01:25 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 0/1251] eta: 1:29:55 lr: 0.000124 loss: 3.3817 (3.3817) grad_norm: 1.9110 (1.9110) time: 4.3126 [2021-03-28 04:01:31 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 10/1251] eta: 0:20:04 lr: 0.000124 loss: 3.1592 (3.1279) grad_norm: 2.3880 (2.5220) time: 0.9704 [2021-03-28 04:01:38 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 20/1251] eta: 0:16:43 lr: 0.000124 loss: 3.1402 (3.1253) grad_norm: 2.3880 (2.5102) time: 0.6404 [2021-03-28 04:01:44 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 30/1251] eta: 0:15:26 lr: 0.000124 loss: 2.9355 (2.9829) grad_norm: 2.4317 (2.5732) time: 0.6431 [2021-03-28 04:01:50 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 40/1251] eta: 0:14:43 lr: 0.000123 loss: 2.8943 (3.0028) grad_norm: 2.3934 (2.5173) time: 0.6396 [2021-03-28 04:01:57 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 50/1251] eta: 0:14:10 lr: 0.000123 loss: 3.1195 (3.0274) grad_norm: 2.2825 (2.5011) time: 0.6298 [2021-03-28 04:02:03 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 60/1251] eta: 0:13:47 lr: 0.000123 loss: 2.9703 (2.9563) grad_norm: 2.3567 (2.4868) time: 0.6240 [2021-03-28 04:02:09 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 70/1251] eta: 0:13:29 lr: 0.000123 loss: 2.9330 (2.9631) grad_norm: 2.4021 (2.5080) time: 0.6278 [2021-03-28 04:02:16 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 80/1251] eta: 0:13:15 lr: 0.000123 loss: 3.0050 (2.9776) grad_norm: 2.6550 (2.5432) time: 0.6317 [2021-03-28 04:02:22 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 90/1251] eta: 0:13:02 lr: 0.000123 loss: 3.0742 (2.9772) grad_norm: 2.7220 (2.5404) time: 0.6312 [2021-03-28 04:02:28 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 100/1251] eta: 0:12:50 lr: 0.000123 loss: 3.0565 (2.9718) grad_norm: 2.5221 (2.5303) time: 0.6294 [2021-03-28 04:02:35 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 110/1251] eta: 0:12:40 lr: 0.000123 loss: 2.9670 (2.9472) grad_norm: 2.5611 (2.6078) time: 0.6358 [2021-03-28 04:02:41 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 120/1251] eta: 0:12:31 lr: 0.000123 loss: 2.9586 (2.9395) grad_norm: 2.4271 (2.6018) time: 0.6411 [2021-03-28 04:02:47 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 130/1251] eta: 0:12:22 lr: 0.000123 loss: 2.9075 (2.9251) grad_norm: 2.4350 (2.6077) time: 0.6342 [2021-03-28 04:02:54 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 140/1251] eta: 0:12:13 lr: 0.000123 loss: 2.7796 (2.9155) grad_norm: 2.4209 (2.5897) time: 0.6324 [2021-03-28 04:03:00 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 150/1251] eta: 0:12:04 lr: 0.000123 loss: 2.6700 (2.9032) grad_norm: 2.2664 (2.5802) time: 0.6348 [2021-03-28 04:03:06 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 160/1251] eta: 0:11:55 lr: 0.000123 loss: 2.6079 (2.8928) grad_norm: 2.3588 (2.5776) time: 0.6275 [2021-03-28 04:03:12 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 170/1251] eta: 0:11:47 lr: 0.000123 loss: 2.8548 (2.8813) grad_norm: 2.3588 (2.5678) time: 0.6272 [2021-03-28 04:03:19 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 180/1251] eta: 0:11:40 lr: 0.000123 loss: 2.9171 (2.8921) grad_norm: 2.3101 (2.5643) time: 0.6387 [2021-03-28 04:03:25 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 190/1251] eta: 0:11:32 lr: 0.000123 loss: 2.9099 (2.8882) grad_norm: 2.3028 (2.5531) time: 0.6382 [2021-03-28 04:03:32 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 200/1251] eta: 0:11:25 lr: 0.000123 loss: 2.8718 (2.8800) grad_norm: 2.3472 (2.5532) time: 0.6366 [2021-03-28 04:03:38 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 210/1251] eta: 0:11:18 lr: 0.000123 loss: 2.6151 (2.8651) grad_norm: 2.5360 (2.5636) time: 0.6407 [2021-03-28 04:03:44 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 220/1251] eta: 0:11:10 lr: 0.000123 loss: 2.9096 (2.8649) grad_norm: 2.4584 (2.5620) time: 0.6343 [2021-03-28 04:03:51 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 230/1251] eta: 0:11:03 lr: 0.000123 loss: 2.9495 (2.8673) grad_norm: 2.3673 (2.5602) time: 0.6276 [2021-03-28 04:03:57 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 240/1251] eta: 0:10:55 lr: 0.000123 loss: 2.9643 (2.8656) grad_norm: 2.4412 (2.5589) time: 0.6265 [2021-03-28 04:04:03 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 250/1251] eta: 0:10:49 lr: 0.000123 loss: 2.9643 (2.8693) grad_norm: 2.4695 (2.5626) time: 0.6351 [2021-03-28 04:04:10 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 260/1251] eta: 0:10:41 lr: 0.000123 loss: 2.9721 (2.8665) grad_norm: 2.4461 (2.5642) time: 0.6307 [2021-03-28 04:04:16 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 270/1251] eta: 0:10:34 lr: 0.000123 loss: 2.8311 (2.8681) grad_norm: 2.5035 (2.5809) time: 0.6247 [2021-03-28 04:04:22 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 280/1251] eta: 0:10:27 lr: 0.000123 loss: 2.8311 (2.8632) grad_norm: 2.5624 (2.5993) time: 0.6305 [2021-03-28 04:04:29 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 290/1251] eta: 0:10:20 lr: 0.000123 loss: 2.8043 (2.8616) grad_norm: 2.5624 (2.6138) time: 0.6349 [2021-03-28 04:04:35 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 300/1251] eta: 0:10:13 lr: 0.000123 loss: 2.8797 (2.8640) grad_norm: 2.5646 (2.6138) time: 0.6356 [2021-03-28 04:04:41 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 310/1251] eta: 0:10:07 lr: 0.000123 loss: 3.0005 (2.8690) grad_norm: 2.5059 (2.6159) time: 0.6323 [2021-03-28 04:04:47 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 320/1251] eta: 0:09:59 lr: 0.000123 loss: 3.0454 (2.8677) grad_norm: 2.3939 (2.6085) time: 0.6291 [2021-03-28 04:04:54 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 330/1251] eta: 0:09:53 lr: 0.000123 loss: 3.2768 (2.8757) grad_norm: 2.3699 (2.6063) time: 0.6281 [2021-03-28 04:05:00 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 340/1251] eta: 0:09:46 lr: 0.000123 loss: 3.0675 (2.8770) grad_norm: 2.5560 (2.6051) time: 0.6249 [2021-03-28 04:05:06 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 350/1251] eta: 0:09:39 lr: 0.000123 loss: 2.7615 (2.8676) grad_norm: 2.4449 (2.5991) time: 0.6275 [2021-03-28 04:05:12 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 360/1251] eta: 0:09:32 lr: 0.000123 loss: 2.5400 (2.8599) grad_norm: 2.4302 (2.6036) time: 0.6286 [2021-03-28 04:05:19 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 370/1251] eta: 0:09:25 lr: 0.000123 loss: 2.9791 (2.8628) grad_norm: 2.4758 (inf) time: 0.6201 [2021-03-28 04:05:25 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 380/1251] eta: 0:09:18 lr: 0.000123 loss: 3.0797 (2.8633) grad_norm: 2.5077 (inf) time: 0.6275 [2021-03-28 04:05:31 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 390/1251] eta: 0:09:12 lr: 0.000123 loss: 2.9927 (2.8657) grad_norm: 2.5030 (inf) time: 0.6284 [2021-03-28 04:05:38 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 400/1251] eta: 0:09:05 lr: 0.000123 loss: 2.8799 (2.8659) grad_norm: 2.4270 (inf) time: 0.6231 [2021-03-28 04:05:44 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 410/1251] eta: 0:08:58 lr: 0.000123 loss: 2.7899 (2.8640) grad_norm: 2.4270 (inf) time: 0.6297 [2021-03-28 04:05:50 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 420/1251] eta: 0:08:52 lr: 0.000122 loss: 2.7080 (2.8607) grad_norm: 2.5588 (inf) time: 0.6348 [2021-03-28 04:05:57 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 430/1251] eta: 0:08:45 lr: 0.000122 loss: 2.7080 (2.8581) grad_norm: 2.4160 (inf) time: 0.6381 [2021-03-28 04:06:03 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 440/1251] eta: 0:08:39 lr: 0.000122 loss: 2.6490 (2.8531) grad_norm: 2.4160 (inf) time: 0.6374 [2021-03-28 04:06:09 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 450/1251] eta: 0:08:32 lr: 0.000122 loss: 2.9337 (2.8538) grad_norm: 2.7004 (inf) time: 0.6327 [2021-03-28 04:06:16 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 460/1251] eta: 0:08:26 lr: 0.000122 loss: 3.0034 (2.8510) grad_norm: 2.4952 (inf) time: 0.6273 [2021-03-28 04:06:22 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 470/1251] eta: 0:08:19 lr: 0.000122 loss: 2.9501 (2.8497) grad_norm: 2.3440 (inf) time: 0.6319 [2021-03-28 04:06:28 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 480/1251] eta: 0:08:13 lr: 0.000122 loss: 2.9501 (2.8492) grad_norm: 2.4361 (inf) time: 0.6408 [2021-03-28 04:06:35 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 490/1251] eta: 0:08:06 lr: 0.000122 loss: 2.9399 (2.8498) grad_norm: 2.3935 (inf) time: 0.6356 [2021-03-28 04:06:41 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 500/1251] eta: 0:08:00 lr: 0.000122 loss: 3.0024 (2.8536) grad_norm: 2.5325 (inf) time: 0.6278 [2021-03-28 04:06:47 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 510/1251] eta: 0:07:53 lr: 0.000122 loss: 3.0024 (2.8564) grad_norm: 2.6299 (inf) time: 0.6222 [2021-03-28 04:06:53 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 520/1251] eta: 0:07:46 lr: 0.000122 loss: 2.8563 (2.8548) grad_norm: 2.4542 (inf) time: 0.6244 [2021-03-28 04:07:00 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 530/1251] eta: 0:07:40 lr: 0.000122 loss: 2.8283 (2.8552) grad_norm: 2.4180 (inf) time: 0.6287 [2021-03-28 04:07:06 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 540/1251] eta: 0:07:34 lr: 0.000122 loss: 2.9145 (2.8568) grad_norm: 2.4180 (inf) time: 0.6330 [2021-03-28 04:07:12 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 550/1251] eta: 0:07:27 lr: 0.000122 loss: 2.9166 (2.8572) grad_norm: 2.4504 (inf) time: 0.6352 [2021-03-28 04:07:19 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 560/1251] eta: 0:07:21 lr: 0.000122 loss: 2.9167 (2.8580) grad_norm: 2.3837 (inf) time: 0.6327 [2021-03-28 04:07:25 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 570/1251] eta: 0:07:14 lr: 0.000122 loss: 2.9467 (2.8611) grad_norm: 2.4333 (inf) time: 0.6269 [2021-03-28 04:07:31 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 580/1251] eta: 0:07:08 lr: 0.000122 loss: 2.9745 (2.8597) grad_norm: 2.5228 (inf) time: 0.6240 [2021-03-28 04:07:38 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 590/1251] eta: 0:07:01 lr: 0.000122 loss: 2.7640 (2.8576) grad_norm: 2.4785 (inf) time: 0.6334 [2021-03-28 04:07:44 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 600/1251] eta: 0:06:55 lr: 0.000122 loss: 2.8385 (2.8581) grad_norm: 2.5099 (inf) time: 0.6354 [2021-03-28 04:07:50 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 610/1251] eta: 0:06:48 lr: 0.000122 loss: 3.0063 (2.8591) grad_norm: 2.5483 (inf) time: 0.6335 [2021-03-28 04:07:57 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 620/1251] eta: 0:06:42 lr: 0.000122 loss: 3.0084 (2.8583) grad_norm: 2.4583 (inf) time: 0.6344 [2021-03-28 04:08:03 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 630/1251] eta: 0:06:35 lr: 0.000122 loss: 2.8967 (2.8575) grad_norm: 2.4785 (inf) time: 0.6333 [2021-03-28 04:08:09 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 640/1251] eta: 0:06:29 lr: 0.000122 loss: 2.9126 (2.8553) grad_norm: 2.4828 (inf) time: 0.6345 [2021-03-28 04:08:16 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 650/1251] eta: 0:06:23 lr: 0.000122 loss: 2.8709 (2.8567) grad_norm: 2.5049 (inf) time: 0.6366 [2021-03-28 04:08:22 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 660/1251] eta: 0:06:16 lr: 0.000122 loss: 2.9691 (2.8587) grad_norm: 2.5283 (inf) time: 0.6302 [2021-03-28 04:08:28 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 670/1251] eta: 0:06:10 lr: 0.000122 loss: 2.9523 (2.8589) grad_norm: 2.4976 (inf) time: 0.6222 [2021-03-28 04:08:34 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 680/1251] eta: 0:06:03 lr: 0.000122 loss: 2.8835 (2.8585) grad_norm: 2.5990 (inf) time: 0.6227 [2021-03-28 04:08:41 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 690/1251] eta: 0:05:57 lr: 0.000122 loss: 2.7487 (2.8574) grad_norm: 2.5628 (inf) time: 0.6340 [2021-03-28 04:08:47 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 700/1251] eta: 0:05:50 lr: 0.000122 loss: 2.8263 (2.8557) grad_norm: 2.3315 (inf) time: 0.6344 [2021-03-28 04:08:53 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 710/1251] eta: 0:05:44 lr: 0.000122 loss: 2.9457 (2.8574) grad_norm: 2.2942 (inf) time: 0.6294 [2021-03-28 04:09:00 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 720/1251] eta: 0:05:38 lr: 0.000122 loss: 3.0290 (2.8568) grad_norm: 2.3543 (inf) time: 0.6317 [2021-03-28 04:09:06 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 730/1251] eta: 0:05:31 lr: 0.000122 loss: 3.0252 (2.8583) grad_norm: 2.3385 (inf) time: 0.6339 [2021-03-28 04:09:12 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 740/1251] eta: 0:05:25 lr: 0.000122 loss: 3.0187 (2.8577) grad_norm: 2.4151 (inf) time: 0.6342 [2021-03-28 04:09:19 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 750/1251] eta: 0:05:18 lr: 0.000122 loss: 2.9490 (2.8570) grad_norm: 2.4095 (inf) time: 0.6311 [2021-03-28 04:09:25 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 760/1251] eta: 0:05:12 lr: 0.000122 loss: 2.9641 (2.8589) grad_norm: 2.3329 (inf) time: 0.6270 [2021-03-28 04:09:31 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 770/1251] eta: 0:05:06 lr: 0.000122 loss: 2.9682 (2.8604) grad_norm: 2.4038 (inf) time: 0.6239 [2021-03-28 04:09:38 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 780/1251] eta: 0:04:59 lr: 0.000122 loss: 2.9741 (2.8628) grad_norm: 2.5323 (inf) time: 0.6296 [2021-03-28 04:09:44 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 790/1251] eta: 0:04:53 lr: 0.000122 loss: 3.1237 (2.8642) grad_norm: 2.5172 (inf) time: 0.6344 [2021-03-28 04:09:50 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 800/1251] eta: 0:04:46 lr: 0.000121 loss: 2.9447 (2.8632) grad_norm: 2.4680 (inf) time: 0.6332 [2021-03-28 04:09:56 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 810/1251] eta: 0:04:40 lr: 0.000121 loss: 2.9447 (2.8641) grad_norm: 2.4680 (inf) time: 0.6274 [2021-03-28 04:10:03 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 820/1251] eta: 0:04:34 lr: 0.000121 loss: 2.9840 (2.8635) grad_norm: 2.5279 (inf) time: 0.6278 [2021-03-28 04:10:09 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 830/1251] eta: 0:04:27 lr: 0.000121 loss: 2.7715 (2.8641) grad_norm: 2.5214 (inf) time: 0.6375 [2021-03-28 04:10:15 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 840/1251] eta: 0:04:21 lr: 0.000121 loss: 2.7715 (2.8634) grad_norm: 2.4587 (inf) time: 0.6346 [2021-03-28 04:10:22 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 850/1251] eta: 0:04:14 lr: 0.000121 loss: 2.7905 (2.8623) grad_norm: 2.3593 (inf) time: 0.6297 [2021-03-28 04:10:28 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 860/1251] eta: 0:04:08 lr: 0.000121 loss: 2.9082 (2.8633) grad_norm: 2.3593 (inf) time: 0.6347 [2021-03-28 04:10:35 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 870/1251] eta: 0:04:02 lr: 0.000121 loss: 2.9082 (2.8630) grad_norm: 2.7436 (inf) time: 0.6371 [2021-03-28 04:10:41 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 880/1251] eta: 0:03:55 lr: 0.000121 loss: 2.8049 (2.8625) grad_norm: 2.4758 (inf) time: 0.6333 [2021-03-28 04:10:47 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 890/1251] eta: 0:03:49 lr: 0.000121 loss: 2.8479 (2.8630) grad_norm: 2.4781 (inf) time: 0.6344 [2021-03-28 04:10:54 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 900/1251] eta: 0:03:43 lr: 0.000121 loss: 2.9578 (2.8646) grad_norm: 2.3003 (inf) time: 0.6392 [2021-03-28 04:11:00 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 910/1251] eta: 0:03:36 lr: 0.000121 loss: 2.9818 (2.8653) grad_norm: 2.3003 (inf) time: 0.6308 [2021-03-28 04:11:06 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 920/1251] eta: 0:03:30 lr: 0.000121 loss: 2.9818 (2.8654) grad_norm: 2.5197 (inf) time: 0.6265 [2021-03-28 04:11:12 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 930/1251] eta: 0:03:24 lr: 0.000121 loss: 2.8187 (2.8643) grad_norm: 2.4834 (inf) time: 0.6292 [2021-03-28 04:11:19 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 940/1251] eta: 0:03:17 lr: 0.000121 loss: 2.9892 (2.8652) grad_norm: 2.4786 (inf) time: 0.6264 [2021-03-28 04:11:25 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 950/1251] eta: 0:03:11 lr: 0.000121 loss: 2.8775 (2.8637) grad_norm: 2.4404 (inf) time: 0.6284 [2021-03-28 04:11:31 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 960/1251] eta: 0:03:04 lr: 0.000121 loss: 2.7833 (2.8612) grad_norm: 2.3354 (inf) time: 0.6305 [2021-03-28 04:11:38 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 970/1251] eta: 0:02:58 lr: 0.000121 loss: 2.8036 (2.8608) grad_norm: 2.4232 (inf) time: 0.6329 [2021-03-28 04:11:44 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 980/1251] eta: 0:02:52 lr: 0.000121 loss: 2.8845 (2.8614) grad_norm: 2.5080 (inf) time: 0.6338 [2021-03-28 04:11:50 swin_base_patch4_window7_224] INFO: Epoch: [234] [ 990/1251] eta: 0:02:45 lr: 0.000121 loss: 3.0072 (2.8612) grad_norm: 2.3979 (inf) time: 0.6301 [2021-03-28 04:11:57 swin_base_patch4_window7_224] INFO: Epoch: [234] [1000/1251] eta: 0:02:39 lr: 0.000121 loss: 2.9361 (2.8615) grad_norm: 2.4273 (inf) time: 0.6359 [2021-03-28 04:12:03 swin_base_patch4_window7_224] INFO: Epoch: [234] [1010/1251] eta: 0:02:33 lr: 0.000121 loss: 2.9745 (2.8606) grad_norm: 2.4757 (inf) time: 0.6347 [2021-03-28 04:12:09 swin_base_patch4_window7_224] INFO: Epoch: [234] [1020/1251] eta: 0:02:26 lr: 0.000121 loss: 2.7380 (2.8598) grad_norm: 2.8150 (inf) time: 0.6284 [2021-03-28 04:12:15 swin_base_patch4_window7_224] INFO: Epoch: [234] [1030/1251] eta: 0:02:20 lr: 0.000121 loss: 3.0645 (2.8609) grad_norm: 2.6011 (inf) time: 0.6247 [2021-03-28 04:12:22 swin_base_patch4_window7_224] INFO: Epoch: [234] [1040/1251] eta: 0:02:13 lr: 0.000121 loss: 2.9639 (2.8591) grad_norm: 2.4784 (inf) time: 0.6262 [2021-03-28 04:12:28 swin_base_patch4_window7_224] INFO: Epoch: [234] [1050/1251] eta: 0:02:07 lr: 0.000121 loss: 2.7736 (2.8601) grad_norm: 2.5919 (inf) time: 0.6315 [2021-03-28 04:12:34 swin_base_patch4_window7_224] INFO: Epoch: [234] [1060/1251] eta: 0:02:01 lr: 0.000121 loss: 2.9109 (2.8601) grad_norm: 2.4826 (inf) time: 0.6360 [2021-03-28 04:12:41 swin_base_patch4_window7_224] INFO: Epoch: [234] [1070/1251] eta: 0:01:54 lr: 0.000121 loss: 3.0363 (2.8627) grad_norm: 2.4826 (inf) time: 0.6349 [2021-03-28 04:12:47 swin_base_patch4_window7_224] INFO: Epoch: [234] [1080/1251] eta: 0:01:48 lr: 0.000121 loss: 2.9193 (2.8603) grad_norm: 2.5561 (inf) time: 0.6364 [2021-03-28 04:12:54 swin_base_patch4_window7_224] INFO: Epoch: [234] [1090/1251] eta: 0:01:42 lr: 0.000121 loss: 2.8789 (2.8605) grad_norm: 2.4534 (inf) time: 0.6377 [2021-03-28 04:13:00 swin_base_patch4_window7_224] INFO: Epoch: [234] [1100/1251] eta: 0:01:35 lr: 0.000121 loss: 2.8992 (2.8600) grad_norm: 2.4534 (inf) time: 0.6320 [2021-03-28 04:13:06 swin_base_patch4_window7_224] INFO: Epoch: [234] [1110/1251] eta: 0:01:29 lr: 0.000121 loss: 2.9128 (2.8607) grad_norm: 2.6663 (inf) time: 0.6295 [2021-03-28 04:13:12 swin_base_patch4_window7_224] INFO: Epoch: [234] [1120/1251] eta: 0:01:23 lr: 0.000121 loss: 2.9376 (2.8602) grad_norm: 2.4073 (inf) time: 0.6259 [2021-03-28 04:13:19 swin_base_patch4_window7_224] INFO: Epoch: [234] [1130/1251] eta: 0:01:16 lr: 0.000121 loss: 2.6443 (2.8569) grad_norm: 2.3309 (inf) time: 0.6258 [2021-03-28 04:13:25 swin_base_patch4_window7_224] INFO: Epoch: [234] [1140/1251] eta: 0:01:10 lr: 0.000121 loss: 2.7093 (2.8577) grad_norm: 2.7087 (inf) time: 0.6308 [2021-03-28 04:13:31 swin_base_patch4_window7_224] INFO: Epoch: [234] [1150/1251] eta: 0:01:04 lr: 0.000121 loss: 3.0002 (2.8567) grad_norm: 2.6706 (inf) time: 0.6322 [2021-03-28 04:13:38 swin_base_patch4_window7_224] INFO: Epoch: [234] [1160/1251] eta: 0:00:57 lr: 0.000121 loss: 2.9659 (2.8569) grad_norm: 2.5480 (inf) time: 0.6275 [2021-03-28 04:13:44 swin_base_patch4_window7_224] INFO: Epoch: [234] [1170/1251] eta: 0:00:51 lr: 0.000121 loss: 3.0004 (2.8574) grad_norm: 2.3656 (inf) time: 0.6259 [2021-03-28 04:13:50 swin_base_patch4_window7_224] INFO: Epoch: [234] [1180/1251] eta: 0:00:45 lr: 0.000120 loss: 2.7175 (2.8565) grad_norm: 2.4453 (inf) time: 0.6242 [2021-03-28 04:13:56 swin_base_patch4_window7_224] INFO: Epoch: [234] [1190/1251] eta: 0:00:38 lr: 0.000120 loss: 2.6879 (2.8560) grad_norm: 2.5135 (inf) time: 0.6291 [2021-03-28 04:14:03 swin_base_patch4_window7_224] INFO: Epoch: [234] [1200/1251] eta: 0:00:32 lr: 0.000120 loss: 2.8892 (2.8573) grad_norm: 2.4499 (inf) time: 0.6329 [2021-03-28 04:14:09 swin_base_patch4_window7_224] INFO: Epoch: [234] [1210/1251] eta: 0:00:26 lr: 0.000120 loss: 2.9622 (2.8566) grad_norm: 2.3703 (inf) time: 0.6269 [2021-03-28 04:14:15 swin_base_patch4_window7_224] INFO: Epoch: [234] [1220/1251] eta: 0:00:19 lr: 0.000120 loss: 2.6253 (2.8545) grad_norm: 2.3833 (inf) time: 0.6241 [2021-03-28 04:14:22 swin_base_patch4_window7_224] INFO: Epoch: [234] [1230/1251] eta: 0:00:13 lr: 0.000120 loss: 2.7948 (2.8545) grad_norm: 2.4568 (inf) time: 0.6287 [2021-03-28 04:14:28 swin_base_patch4_window7_224] INFO: Epoch: [234] [1240/1251] eta: 0:00:06 lr: 0.000120 loss: 2.8908 (2.8549) grad_norm: 2.5903 (inf) time: 0.6262 [2021-03-28 04:14:34 swin_base_patch4_window7_224] INFO: Epoch: [234] [1250/1251] eta: 0:00:00 lr: 0.000120 loss: 2.9839 (2.8564) grad_norm: 2.5556 (inf) time: 0.6250 [2021-03-28 04:14:47 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:30 loss: 0.7657 (0.7657) acc1: 84.3750 (84.3750) acc5: 95.3125 (95.3125) [2021-03-28 04:14:49 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7434 (0.7621) acc1: 81.2500 (81.3920) acc5: 96.8750 (97.1591) [2021-03-28 04:14:50 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7025 (0.7150) acc1: 81.2500 (81.7708) acc5: 96.8750 (97.3958) [2021-03-28 04:14:52 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7263 (0.7606) acc1: 81.2500 (81.1996) acc5: 96.8750 (96.7238) [2021-03-28 04:14:55 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8412 (0.7753) acc1: 81.2500 (81.3643) acc5: 95.3125 (96.3034) [2021-03-28 04:14:56 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7491 (0.7768) acc1: 81.2500 (81.1520) acc5: 96.8750 (96.4160) [2021-03-28 04:15:10 swin_base_patch4_window7_224] INFO: * Acc@1 82.274 Acc@5 96.132 loss 0.767 [2021-03-28 04:15:10 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.3% [2021-03-28 04:15:10 swin_base_patch4_window7_224] INFO: Max accuracy: 82.28% [2021-03-28 04:15:15 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 0/1251] eta: 1:29:29 lr: 0.000120 loss: 3.0245 (3.0245) grad_norm: 2.5036 (2.5036) time: 4.2921 [2021-03-28 04:15:21 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 10/1251] eta: 0:20:18 lr: 0.000120 loss: 3.1038 (2.9546) grad_norm: 2.3880 (2.3547) time: 0.9816 [2021-03-28 04:15:27 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 20/1251] eta: 0:16:44 lr: 0.000120 loss: 2.9198 (2.8502) grad_norm: 2.3880 (2.5059) time: 0.6419 [2021-03-28 04:15:34 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 30/1251] eta: 0:15:19 lr: 0.000120 loss: 2.7764 (2.8493) grad_norm: 2.5499 (2.5329) time: 0.6277 [2021-03-28 04:15:40 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 40/1251] eta: 0:14:38 lr: 0.000120 loss: 2.8187 (2.8844) grad_norm: 2.4587 (2.4947) time: 0.6302 [2021-03-28 04:15:46 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 50/1251] eta: 0:14:07 lr: 0.000120 loss: 3.0984 (2.8848) grad_norm: 2.3917 (2.5018) time: 0.6322 [2021-03-28 04:15:53 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 60/1251] eta: 0:13:46 lr: 0.000120 loss: 2.8904 (2.8519) grad_norm: 2.3917 (2.4901) time: 0.6288 [2021-03-28 04:15:59 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 70/1251] eta: 0:13:29 lr: 0.000120 loss: 2.8904 (2.8698) grad_norm: 2.4348 (2.5711) time: 0.6347 [2021-03-28 04:16:05 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 80/1251] eta: 0:13:15 lr: 0.000120 loss: 2.9786 (2.8420) grad_norm: 2.3995 (2.5549) time: 0.6365 [2021-03-28 04:16:12 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 90/1251] eta: 0:13:02 lr: 0.000120 loss: 2.7944 (2.8420) grad_norm: 2.3315 (2.5849) time: 0.6338 [2021-03-28 04:16:18 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 100/1251] eta: 0:12:51 lr: 0.000120 loss: 2.7895 (2.8178) grad_norm: 2.3872 (2.5663) time: 0.6315 [2021-03-28 04:16:24 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 110/1251] eta: 0:12:39 lr: 0.000120 loss: 2.2999 (2.8001) grad_norm: 2.3671 (2.6724) time: 0.6276 [2021-03-28 04:16:31 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 120/1251] eta: 0:12:30 lr: 0.000120 loss: 2.8081 (2.8085) grad_norm: 2.4930 (2.6665) time: 0.6304 [2021-03-28 04:16:37 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 130/1251] eta: 0:12:21 lr: 0.000120 loss: 2.9015 (2.8127) grad_norm: 2.5253 (2.6499) time: 0.6363 [2021-03-28 04:16:43 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 140/1251] eta: 0:12:12 lr: 0.000120 loss: 2.9493 (2.8174) grad_norm: 2.4895 (2.6399) time: 0.6352 [2021-03-28 04:16:50 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 150/1251] eta: 0:12:05 lr: 0.000120 loss: 2.8249 (2.8125) grad_norm: 2.4927 (2.6385) time: 0.6407 [2021-03-28 04:16:56 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 160/1251] eta: 0:11:56 lr: 0.000120 loss: 2.7409 (2.8070) grad_norm: 2.5360 (2.6445) time: 0.6372 [2021-03-28 04:17:02 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 170/1251] eta: 0:11:48 lr: 0.000120 loss: 2.9953 (2.8258) grad_norm: 2.5164 (2.6700) time: 0.6288 [2021-03-28 04:17:09 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 180/1251] eta: 0:11:40 lr: 0.000120 loss: 3.0760 (2.8312) grad_norm: 2.4283 (2.6581) time: 0.6327 [2021-03-28 04:17:15 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 190/1251] eta: 0:11:32 lr: 0.000120 loss: 3.0603 (2.8390) grad_norm: 2.4283 (2.6525) time: 0.6288 [2021-03-28 04:17:21 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 200/1251] eta: 0:11:24 lr: 0.000120 loss: 2.9825 (2.8486) grad_norm: 2.5908 (2.6500) time: 0.6263 [2021-03-28 04:17:28 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 210/1251] eta: 0:11:17 lr: 0.000120 loss: 2.9401 (2.8491) grad_norm: 2.6031 (2.6554) time: 0.6320 [2021-03-28 04:17:34 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 220/1251] eta: 0:11:09 lr: 0.000120 loss: 2.9677 (2.8482) grad_norm: 2.4959 (2.6433) time: 0.6280 [2021-03-28 04:17:40 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 230/1251] eta: 0:11:01 lr: 0.000120 loss: 2.9392 (2.8387) grad_norm: 2.2842 (2.6318) time: 0.6232 [2021-03-28 04:17:46 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 240/1251] eta: 0:10:54 lr: 0.000120 loss: 2.9392 (2.8405) grad_norm: 2.4868 (2.6270) time: 0.6288 [2021-03-28 04:17:53 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 250/1251] eta: 0:10:48 lr: 0.000120 loss: 2.9659 (2.8369) grad_norm: 2.4901 (2.6256) time: 0.6404 [2021-03-28 04:17:59 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 260/1251] eta: 0:10:40 lr: 0.000120 loss: 2.9610 (2.8432) grad_norm: 2.5407 (2.6217) time: 0.6374 [2021-03-28 04:18:05 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 270/1251] eta: 0:10:34 lr: 0.000120 loss: 3.0922 (2.8463) grad_norm: 2.5319 (2.6232) time: 0.6322 [2021-03-28 04:18:12 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 280/1251] eta: 0:10:27 lr: 0.000120 loss: 3.0412 (2.8506) grad_norm: 2.5228 (2.6388) time: 0.6349 [2021-03-28 04:18:18 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 290/1251] eta: 0:10:20 lr: 0.000120 loss: 3.1220 (2.8511) grad_norm: 2.5159 (2.6362) time: 0.6294 [2021-03-28 04:18:24 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 300/1251] eta: 0:10:12 lr: 0.000120 loss: 3.1220 (2.8562) grad_norm: 2.4221 (2.6482) time: 0.6259 [2021-03-28 04:18:31 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 310/1251] eta: 0:10:06 lr: 0.000120 loss: 3.0494 (2.8545) grad_norm: 2.3939 (2.6421) time: 0.6281 [2021-03-28 04:18:37 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 320/1251] eta: 0:09:59 lr: 0.000119 loss: 3.0494 (2.8580) grad_norm: 2.4239 (2.6355) time: 0.6330 [2021-03-28 04:18:43 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 330/1251] eta: 0:09:52 lr: 0.000119 loss: 2.8805 (2.8574) grad_norm: 2.4941 (2.6333) time: 0.6337 [2021-03-28 04:18:50 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 340/1251] eta: 0:09:45 lr: 0.000119 loss: 2.8761 (2.8566) grad_norm: 2.5167 (2.6337) time: 0.6333 [2021-03-28 04:18:56 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 350/1251] eta: 0:09:39 lr: 0.000119 loss: 2.7817 (2.8463) grad_norm: 2.4795 (2.6341) time: 0.6353 [2021-03-28 04:19:02 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 360/1251] eta: 0:09:32 lr: 0.000119 loss: 2.7591 (2.8490) grad_norm: 2.3962 (2.6274) time: 0.6333 [2021-03-28 04:19:09 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 370/1251] eta: 0:09:25 lr: 0.000119 loss: 2.9422 (2.8518) grad_norm: 2.3962 (2.6229) time: 0.6295 [2021-03-28 04:19:15 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 380/1251] eta: 0:09:19 lr: 0.000119 loss: 2.8250 (2.8517) grad_norm: 2.2752 (2.6138) time: 0.6288 [2021-03-28 04:19:21 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 390/1251] eta: 0:09:12 lr: 0.000119 loss: 2.8785 (2.8497) grad_norm: 2.2845 (2.6106) time: 0.6270 [2021-03-28 04:19:27 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 400/1251] eta: 0:09:05 lr: 0.000119 loss: 2.7645 (2.8461) grad_norm: 2.5073 (2.6127) time: 0.6286 [2021-03-28 04:19:34 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 410/1251] eta: 0:08:59 lr: 0.000119 loss: 2.7288 (2.8437) grad_norm: 2.6881 (2.6306) time: 0.6362 [2021-03-28 04:19:40 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 420/1251] eta: 0:08:52 lr: 0.000119 loss: 2.8533 (2.8432) grad_norm: 2.5853 (2.6277) time: 0.6359 [2021-03-28 04:19:47 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 430/1251] eta: 0:08:46 lr: 0.000119 loss: 2.9107 (2.8449) grad_norm: 2.3780 (2.6293) time: 0.6334 [2021-03-28 04:19:53 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 440/1251] eta: 0:08:39 lr: 0.000119 loss: 2.9468 (2.8482) grad_norm: 2.4234 (2.6267) time: 0.6366 [2021-03-28 04:19:59 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 450/1251] eta: 0:08:32 lr: 0.000119 loss: 2.9468 (2.8502) grad_norm: 2.5480 (2.6357) time: 0.6303 [2021-03-28 04:20:06 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 460/1251] eta: 0:08:26 lr: 0.000119 loss: 2.9321 (2.8487) grad_norm: 2.4593 (2.6286) time: 0.6311 [2021-03-28 04:20:12 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 470/1251] eta: 0:08:20 lr: 0.000119 loss: 2.9321 (2.8489) grad_norm: 2.3841 (2.6317) time: 0.6371 [2021-03-28 04:20:18 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 480/1251] eta: 0:08:13 lr: 0.000119 loss: 2.7293 (2.8439) grad_norm: 2.4657 (2.6345) time: 0.6324 [2021-03-28 04:20:24 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 490/1251] eta: 0:08:06 lr: 0.000119 loss: 2.7293 (2.8441) grad_norm: 2.4657 (2.6328) time: 0.6267 [2021-03-28 04:20:31 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 500/1251] eta: 0:08:00 lr: 0.000119 loss: 2.7701 (2.8416) grad_norm: 2.5452 (2.6362) time: 0.6299 [2021-03-28 04:20:37 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 510/1251] eta: 0:07:53 lr: 0.000119 loss: 2.8170 (2.8405) grad_norm: 2.4947 (2.6358) time: 0.6343 [2021-03-28 04:20:43 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 520/1251] eta: 0:07:47 lr: 0.000119 loss: 2.8286 (2.8399) grad_norm: 2.6656 (2.6377) time: 0.6288 [2021-03-28 04:20:50 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 530/1251] eta: 0:07:40 lr: 0.000119 loss: 2.9863 (2.8426) grad_norm: 2.5447 (2.6338) time: 0.6308 [2021-03-28 04:20:56 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 540/1251] eta: 0:07:34 lr: 0.000119 loss: 3.0437 (2.8454) grad_norm: 2.3148 (2.6304) time: 0.6316 [2021-03-28 04:21:02 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 550/1251] eta: 0:07:27 lr: 0.000119 loss: 3.1592 (2.8504) grad_norm: 2.2842 (2.6274) time: 0.6336 [2021-03-28 04:21:09 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 560/1251] eta: 0:07:21 lr: 0.000119 loss: 3.1286 (2.8496) grad_norm: 2.4484 (2.6323) time: 0.6426 [2021-03-28 04:21:15 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 570/1251] eta: 0:07:15 lr: 0.000119 loss: 2.9822 (2.8498) grad_norm: 2.5732 (2.6329) time: 0.6391 [2021-03-28 04:21:21 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 580/1251] eta: 0:07:08 lr: 0.000119 loss: 2.7680 (2.8460) grad_norm: 2.4973 (2.6327) time: 0.6314 [2021-03-28 04:21:28 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 590/1251] eta: 0:07:02 lr: 0.000119 loss: 2.7897 (2.8464) grad_norm: 2.4355 (2.6304) time: 0.6332 [2021-03-28 04:21:34 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 600/1251] eta: 0:06:55 lr: 0.000119 loss: 3.0342 (2.8522) grad_norm: 2.4002 (2.6274) time: 0.6413 [2021-03-28 04:21:41 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 610/1251] eta: 0:06:49 lr: 0.000119 loss: 3.1111 (2.8504) grad_norm: 2.5748 (2.6295) time: 0.6369 [2021-03-28 04:21:47 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 620/1251] eta: 0:06:42 lr: 0.000119 loss: 2.9917 (2.8526) grad_norm: 2.6567 (2.6347) time: 0.6288 [2021-03-28 04:21:53 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 630/1251] eta: 0:06:36 lr: 0.000119 loss: 2.9296 (2.8532) grad_norm: 2.6127 (2.6330) time: 0.6306 [2021-03-28 04:21:59 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 640/1251] eta: 0:06:29 lr: 0.000119 loss: 3.0631 (2.8559) grad_norm: 2.5633 (2.6309) time: 0.6280 [2021-03-28 04:22:06 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 650/1251] eta: 0:06:23 lr: 0.000119 loss: 2.9723 (2.8543) grad_norm: 2.3177 (2.6263) time: 0.6300 [2021-03-28 04:22:12 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 660/1251] eta: 0:06:17 lr: 0.000119 loss: 2.7879 (2.8550) grad_norm: 2.3720 (2.6273) time: 0.6322 [2021-03-28 04:22:18 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 670/1251] eta: 0:06:10 lr: 0.000119 loss: 2.7759 (2.8530) grad_norm: 2.5462 (2.6269) time: 0.6281 [2021-03-28 04:22:25 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 680/1251] eta: 0:06:04 lr: 0.000119 loss: 2.7540 (2.8524) grad_norm: 2.5075 (2.6268) time: 0.6240 [2021-03-28 04:22:31 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 690/1251] eta: 0:05:57 lr: 0.000119 loss: 2.7822 (2.8521) grad_norm: 2.5253 (2.6319) time: 0.6260 [2021-03-28 04:22:37 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 700/1251] eta: 0:05:51 lr: 0.000118 loss: 2.9999 (2.8543) grad_norm: 2.4532 (2.6282) time: 0.6295 [2021-03-28 04:22:44 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 710/1251] eta: 0:05:44 lr: 0.000118 loss: 2.9217 (2.8551) grad_norm: 2.3895 (2.6262) time: 0.6297 [2021-03-28 04:22:50 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 720/1251] eta: 0:05:38 lr: 0.000118 loss: 2.8545 (2.8545) grad_norm: 2.3943 (2.6244) time: 0.6313 [2021-03-28 04:22:56 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 730/1251] eta: 0:05:31 lr: 0.000118 loss: 2.6844 (2.8513) grad_norm: 2.3289 (2.6229) time: 0.6298 [2021-03-28 04:23:02 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 740/1251] eta: 0:05:25 lr: 0.000118 loss: 2.7657 (2.8504) grad_norm: 2.4090 (2.6237) time: 0.6307 [2021-03-28 04:23:09 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 750/1251] eta: 0:05:19 lr: 0.000118 loss: 2.8987 (2.8491) grad_norm: 2.5235 (2.6218) time: 0.6272 [2021-03-28 04:23:15 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 760/1251] eta: 0:05:12 lr: 0.000118 loss: 2.8987 (2.8497) grad_norm: 2.4296 (2.6216) time: 0.6267 [2021-03-28 04:23:21 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 770/1251] eta: 0:05:06 lr: 0.000118 loss: 3.0000 (2.8515) grad_norm: 2.5025 (2.6219) time: 0.6328 [2021-03-28 04:23:28 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 780/1251] eta: 0:04:59 lr: 0.000118 loss: 2.8718 (2.8508) grad_norm: 2.4901 (2.6232) time: 0.6277 [2021-03-28 04:23:34 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 790/1251] eta: 0:04:53 lr: 0.000118 loss: 2.9012 (2.8519) grad_norm: 2.4530 (2.6239) time: 0.6263 [2021-03-28 04:23:40 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 800/1251] eta: 0:04:46 lr: 0.000118 loss: 2.9469 (2.8525) grad_norm: 2.4530 (2.6225) time: 0.6271 [2021-03-28 04:23:46 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 810/1251] eta: 0:04:40 lr: 0.000118 loss: 2.9469 (2.8522) grad_norm: 2.5681 (2.6251) time: 0.6296 [2021-03-28 04:23:53 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 820/1251] eta: 0:04:34 lr: 0.000118 loss: 3.0064 (2.8531) grad_norm: 2.5938 (2.6255) time: 0.6377 [2021-03-28 04:23:59 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 830/1251] eta: 0:04:27 lr: 0.000118 loss: 3.1825 (2.8548) grad_norm: 2.4928 (2.6235) time: 0.6379 [2021-03-28 04:24:06 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 840/1251] eta: 0:04:21 lr: 0.000118 loss: 2.9871 (2.8557) grad_norm: 2.5336 (2.6248) time: 0.6333 [2021-03-28 04:24:12 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 850/1251] eta: 0:04:15 lr: 0.000118 loss: 2.9871 (2.8582) grad_norm: 2.6409 (2.6275) time: 0.6268 [2021-03-28 04:24:18 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 860/1251] eta: 0:04:08 lr: 0.000118 loss: 3.0248 (2.8599) grad_norm: 2.4534 (2.6253) time: 0.6289 [2021-03-28 04:24:24 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 870/1251] eta: 0:04:02 lr: 0.000118 loss: 2.9538 (2.8600) grad_norm: 2.4073 (2.6237) time: 0.6341 [2021-03-28 04:24:31 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 880/1251] eta: 0:03:56 lr: 0.000118 loss: 2.9362 (2.8587) grad_norm: 2.3138 (2.6237) time: 0.6365 [2021-03-28 04:24:37 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 890/1251] eta: 0:03:49 lr: 0.000118 loss: 2.9858 (2.8560) grad_norm: 2.5817 (2.6238) time: 0.6367 [2021-03-28 04:24:43 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 900/1251] eta: 0:03:43 lr: 0.000118 loss: 3.0412 (2.8575) grad_norm: 2.5817 (2.6240) time: 0.6329 [2021-03-28 04:24:50 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 910/1251] eta: 0:03:36 lr: 0.000118 loss: 2.8995 (2.8558) grad_norm: 2.5101 (2.6239) time: 0.6285 [2021-03-28 04:24:56 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 920/1251] eta: 0:03:30 lr: 0.000118 loss: 2.8964 (2.8564) grad_norm: 2.5101 (2.6244) time: 0.6240 [2021-03-28 04:25:02 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 930/1251] eta: 0:03:24 lr: 0.000118 loss: 2.8964 (2.8549) grad_norm: 2.4793 (2.6246) time: 0.6235 [2021-03-28 04:25:09 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 940/1251] eta: 0:03:17 lr: 0.000118 loss: 2.9373 (2.8547) grad_norm: 2.4793 (2.6241) time: 0.6299 [2021-03-28 04:25:15 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 950/1251] eta: 0:03:11 lr: 0.000118 loss: 2.9373 (2.8536) grad_norm: 2.3507 (2.6249) time: 0.6320 [2021-03-28 04:25:21 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 960/1251] eta: 0:03:04 lr: 0.000118 loss: 2.8026 (2.8524) grad_norm: 2.3515 (2.6250) time: 0.6317 [2021-03-28 04:25:28 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 970/1251] eta: 0:02:58 lr: 0.000118 loss: 2.8708 (2.8553) grad_norm: 2.6558 (2.6261) time: 0.6328 [2021-03-28 04:25:34 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 980/1251] eta: 0:02:52 lr: 0.000118 loss: 3.1578 (2.8567) grad_norm: 2.5110 (2.6251) time: 0.6303 [2021-03-28 04:25:40 swin_base_patch4_window7_224] INFO: Epoch: [235] [ 990/1251] eta: 0:02:45 lr: 0.000118 loss: 2.9500 (2.8589) grad_norm: 2.5110 (2.6257) time: 0.6375 [2021-03-28 04:25:47 swin_base_patch4_window7_224] INFO: Epoch: [235] [1000/1251] eta: 0:02:39 lr: 0.000118 loss: 2.8739 (2.8584) grad_norm: 2.5690 (2.6257) time: 0.6383 [2021-03-28 04:25:53 swin_base_patch4_window7_224] INFO: Epoch: [235] [1010/1251] eta: 0:02:33 lr: 0.000118 loss: 2.8739 (2.8585) grad_norm: 2.4871 (2.6238) time: 0.6296 [2021-03-28 04:25:59 swin_base_patch4_window7_224] INFO: Epoch: [235] [1020/1251] eta: 0:02:26 lr: 0.000118 loss: 2.8866 (2.8573) grad_norm: 2.3679 (2.6208) time: 0.6271 [2021-03-28 04:26:05 swin_base_patch4_window7_224] INFO: Epoch: [235] [1030/1251] eta: 0:02:20 lr: 0.000118 loss: 2.7823 (2.8583) grad_norm: 2.5224 (2.6235) time: 0.6285 [2021-03-28 04:26:12 swin_base_patch4_window7_224] INFO: Epoch: [235] [1040/1251] eta: 0:02:14 lr: 0.000118 loss: 3.1056 (2.8607) grad_norm: 2.5538 (2.6224) time: 0.6251 [2021-03-28 04:26:18 swin_base_patch4_window7_224] INFO: Epoch: [235] [1050/1251] eta: 0:02:07 lr: 0.000118 loss: 3.0792 (2.8610) grad_norm: 2.5538 (2.6250) time: 0.6199 [2021-03-28 04:26:24 swin_base_patch4_window7_224] INFO: Epoch: [235] [1060/1251] eta: 0:02:01 lr: 0.000118 loss: 3.0374 (2.8618) grad_norm: 2.5673 (2.6237) time: 0.6221 [2021-03-28 04:26:30 swin_base_patch4_window7_224] INFO: Epoch: [235] [1070/1251] eta: 0:01:54 lr: 0.000118 loss: 2.8687 (2.8612) grad_norm: 2.5673 (2.6257) time: 0.6251 [2021-03-28 04:26:37 swin_base_patch4_window7_224] INFO: Epoch: [235] [1080/1251] eta: 0:01:48 lr: 0.000118 loss: 2.8687 (2.8616) grad_norm: 2.5850 (2.6249) time: 0.6321 [2021-03-28 04:26:43 swin_base_patch4_window7_224] INFO: Epoch: [235] [1090/1251] eta: 0:01:42 lr: 0.000117 loss: 2.9092 (2.8601) grad_norm: 2.5463 (2.6253) time: 0.6383 [2021-03-28 04:26:49 swin_base_patch4_window7_224] INFO: Epoch: [235] [1100/1251] eta: 0:01:35 lr: 0.000117 loss: 2.8730 (2.8599) grad_norm: 2.6880 (2.6272) time: 0.6364 [2021-03-28 04:26:56 swin_base_patch4_window7_224] INFO: Epoch: [235] [1110/1251] eta: 0:01:29 lr: 0.000117 loss: 2.8546 (2.8599) grad_norm: 2.6690 (2.6284) time: 0.6277 [2021-03-28 04:27:02 swin_base_patch4_window7_224] INFO: Epoch: [235] [1120/1251] eta: 0:01:23 lr: 0.000117 loss: 2.8546 (2.8603) grad_norm: 2.8088 (2.6302) time: 0.6246 [2021-03-28 04:27:08 swin_base_patch4_window7_224] INFO: Epoch: [235] [1130/1251] eta: 0:01:16 lr: 0.000117 loss: 2.9177 (2.8592) grad_norm: 2.4123 (2.6264) time: 0.6242 [2021-03-28 04:27:15 swin_base_patch4_window7_224] INFO: Epoch: [235] [1140/1251] eta: 0:01:10 lr: 0.000117 loss: 2.9510 (2.8584) grad_norm: 2.3773 (2.6257) time: 0.6315 [2021-03-28 04:27:21 swin_base_patch4_window7_224] INFO: Epoch: [235] [1150/1251] eta: 0:01:04 lr: 0.000117 loss: 2.8731 (2.8567) grad_norm: 2.4989 (2.6250) time: 0.6328 [2021-03-28 04:27:27 swin_base_patch4_window7_224] INFO: Epoch: [235] [1160/1251] eta: 0:00:57 lr: 0.000117 loss: 2.8731 (2.8571) grad_norm: 2.4989 (2.6257) time: 0.6295 [2021-03-28 04:27:33 swin_base_patch4_window7_224] INFO: Epoch: [235] [1170/1251] eta: 0:00:51 lr: 0.000117 loss: 2.8913 (2.8573) grad_norm: 2.4741 (2.6241) time: 0.6319 [2021-03-28 04:27:40 swin_base_patch4_window7_224] INFO: Epoch: [235] [1180/1251] eta: 0:00:45 lr: 0.000117 loss: 2.8761 (2.8574) grad_norm: 2.4608 (2.6242) time: 0.6313 [2021-03-28 04:27:46 swin_base_patch4_window7_224] INFO: Epoch: [235] [1190/1251] eta: 0:00:38 lr: 0.000117 loss: 2.8714 (2.8570) grad_norm: 2.5356 (2.6248) time: 0.6287 [2021-03-28 04:27:52 swin_base_patch4_window7_224] INFO: Epoch: [235] [1200/1251] eta: 0:00:32 lr: 0.000117 loss: 2.8482 (2.8559) grad_norm: 2.4727 (2.6247) time: 0.6240 [2021-03-28 04:27:59 swin_base_patch4_window7_224] INFO: Epoch: [235] [1210/1251] eta: 0:00:26 lr: 0.000117 loss: 2.4977 (2.8530) grad_norm: 2.5329 (2.6246) time: 0.6297 [2021-03-28 04:28:05 swin_base_patch4_window7_224] INFO: Epoch: [235] [1220/1251] eta: 0:00:19 lr: 0.000117 loss: 2.7734 (2.8530) grad_norm: 2.5870 (2.6245) time: 0.6321 [2021-03-28 04:28:11 swin_base_patch4_window7_224] INFO: Epoch: [235] [1230/1251] eta: 0:00:13 lr: 0.000117 loss: 2.7847 (2.8504) grad_norm: 2.5974 (2.6250) time: 0.6294 [2021-03-28 04:28:18 swin_base_patch4_window7_224] INFO: Epoch: [235] [1240/1251] eta: 0:00:06 lr: 0.000117 loss: 2.7398 (2.8502) grad_norm: 2.4042 (2.6234) time: 0.6342 [2021-03-28 04:28:24 swin_base_patch4_window7_224] INFO: Epoch: [235] [1250/1251] eta: 0:00:00 lr: 0.000117 loss: 2.9579 (2.8510) grad_norm: 2.3855 (2.6229) time: 0.6282 [2021-03-28 04:29:42 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.5583 (0.5583) acc1: 79.6875 (79.6875) acc5: 98.4375 (98.4375) [2021-03-28 04:29:43 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7739 (0.7930) acc1: 79.6875 (81.1080) acc5: 96.8750 (95.8807) [2021-03-28 04:29:45 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.8274 (0.8057) acc1: 79.6875 (80.9524) acc5: 95.3125 (96.0565) [2021-03-28 04:29:46 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8153 (0.7923) acc1: 81.2500 (81.1492) acc5: 95.3125 (96.0685) [2021-03-28 04:29:48 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8153 (0.7923) acc1: 81.2500 (81.2119) acc5: 95.3125 (96.0747) [2021-03-28 04:29:49 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7029 (0.7770) acc1: 81.2500 (81.3760) acc5: 96.8750 (96.2880) [2021-03-28 04:30:02 swin_base_patch4_window7_224] INFO: * Acc@1 82.580 Acc@5 96.198 loss 0.757 [2021-03-28 04:30:02 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.6% [2021-03-28 04:30:02 swin_base_patch4_window7_224] INFO: Max accuracy: 82.58% [2021-03-28 04:30:07 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 0/1251] eta: 1:29:28 lr: 0.000117 loss: 3.5407 (3.5407) grad_norm: 3.4204 (3.4204) time: 4.2912 [2021-03-28 04:30:13 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 10/1251] eta: 0:20:07 lr: 0.000117 loss: 3.1532 (3.1674) grad_norm: 2.8077 (3.1778) time: 0.9733 [2021-03-28 04:30:19 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 20/1251] eta: 0:16:31 lr: 0.000117 loss: 2.9502 (2.9618) grad_norm: 2.5424 (2.8656) time: 0.6313 [2021-03-28 04:30:26 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 30/1251] eta: 0:15:17 lr: 0.000117 loss: 2.7669 (2.9607) grad_norm: 2.4036 (2.7328) time: 0.6297 [2021-03-28 04:30:32 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 40/1251] eta: 0:14:32 lr: 0.000117 loss: 2.9183 (2.9642) grad_norm: 2.2787 (2.6429) time: 0.6305 [2021-03-28 04:30:38 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 50/1251] eta: 0:14:03 lr: 0.000117 loss: 2.8893 (2.9316) grad_norm: 2.2787 (2.6142) time: 0.6270 [2021-03-28 04:30:44 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 60/1251] eta: 0:13:42 lr: 0.000117 loss: 2.8534 (2.9321) grad_norm: 2.3394 (2.5781) time: 0.6287 [2021-03-28 04:30:51 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 70/1251] eta: 0:13:25 lr: 0.000117 loss: 3.0190 (2.9122) grad_norm: 2.3394 (2.5589) time: 0.6304 [2021-03-28 04:30:57 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 80/1251] eta: 0:13:11 lr: 0.000117 loss: 2.9051 (2.9109) grad_norm: 2.3833 (2.5352) time: 0.6322 [2021-03-28 04:31:03 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 90/1251] eta: 0:12:59 lr: 0.000117 loss: 2.8302 (2.9028) grad_norm: 2.4241 (2.5468) time: 0.6309 [2021-03-28 04:31:10 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 100/1251] eta: 0:12:47 lr: 0.000117 loss: 2.8302 (2.8913) grad_norm: 2.5985 (2.5748) time: 0.6308 [2021-03-28 04:31:16 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 110/1251] eta: 0:12:36 lr: 0.000117 loss: 2.7676 (2.8791) grad_norm: 2.5895 (2.5836) time: 0.6264 [2021-03-28 04:31:22 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 120/1251] eta: 0:12:27 lr: 0.000117 loss: 2.9369 (2.8912) grad_norm: 2.4536 (2.5769) time: 0.6308 [2021-03-28 04:31:28 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 130/1251] eta: 0:12:17 lr: 0.000117 loss: 3.0123 (2.8973) grad_norm: 2.4694 (2.5979) time: 0.6321 [2021-03-28 04:31:35 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 140/1251] eta: 0:12:09 lr: 0.000117 loss: 2.8963 (2.8937) grad_norm: 2.7581 (2.6246) time: 0.6305 [2021-03-28 04:31:41 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 150/1251] eta: 0:12:01 lr: 0.000117 loss: 2.8716 (2.8943) grad_norm: 2.5701 (2.6107) time: 0.6338 [2021-03-28 04:31:48 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 160/1251] eta: 0:11:53 lr: 0.000117 loss: 2.8130 (2.8787) grad_norm: 2.4101 (2.6642) time: 0.6364 [2021-03-28 04:31:54 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 170/1251] eta: 0:11:45 lr: 0.000117 loss: 2.7257 (2.8766) grad_norm: 2.5013 (2.6570) time: 0.6328 [2021-03-28 04:32:00 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 180/1251] eta: 0:11:37 lr: 0.000117 loss: 2.8735 (2.8730) grad_norm: 2.5095 (2.6653) time: 0.6324 [2021-03-28 04:32:07 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 190/1251] eta: 0:11:30 lr: 0.000117 loss: 2.8601 (2.8698) grad_norm: 2.4753 (2.6557) time: 0.6390 [2021-03-28 04:32:13 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 200/1251] eta: 0:11:23 lr: 0.000117 loss: 3.0908 (2.8740) grad_norm: 2.4373 (2.6496) time: 0.6378 [2021-03-28 04:32:19 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 210/1251] eta: 0:11:15 lr: 0.000117 loss: 3.1206 (2.8793) grad_norm: 2.3393 (2.6459) time: 0.6323 [2021-03-28 04:32:26 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 220/1251] eta: 0:11:08 lr: 0.000117 loss: 3.0138 (2.8704) grad_norm: 2.4376 (2.6560) time: 0.6318 [2021-03-28 04:32:32 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 230/1251] eta: 0:11:01 lr: 0.000116 loss: 2.8683 (2.8695) grad_norm: 2.6639 (2.6596) time: 0.6321 [2021-03-28 04:32:38 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 240/1251] eta: 0:10:53 lr: 0.000116 loss: 2.8178 (2.8585) grad_norm: 2.5456 (2.6489) time: 0.6243 [2021-03-28 04:32:44 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 250/1251] eta: 0:10:46 lr: 0.000116 loss: 2.5486 (2.8442) grad_norm: 2.4612 (2.6402) time: 0.6265 [2021-03-28 04:32:51 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 260/1251] eta: 0:10:39 lr: 0.000116 loss: 2.3848 (2.8350) grad_norm: 2.4155 (2.6376) time: 0.6320 [2021-03-28 04:32:57 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 270/1251] eta: 0:10:33 lr: 0.000116 loss: 2.8207 (2.8333) grad_norm: 2.4250 (2.6347) time: 0.6351 [2021-03-28 04:33:04 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 280/1251] eta: 0:10:26 lr: 0.000116 loss: 3.0310 (2.8343) grad_norm: 2.6686 (2.6396) time: 0.6406 [2021-03-28 04:33:10 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 290/1251] eta: 0:10:19 lr: 0.000116 loss: 3.0850 (2.8430) grad_norm: 2.6325 (2.6343) time: 0.6346 [2021-03-28 04:33:16 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 300/1251] eta: 0:10:12 lr: 0.000116 loss: 3.1362 (2.8517) grad_norm: 2.4045 (2.6357) time: 0.6258 [2021-03-28 04:33:22 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 310/1251] eta: 0:10:05 lr: 0.000116 loss: 2.9445 (2.8517) grad_norm: 2.4256 (2.6352) time: 0.6296 [2021-03-28 04:33:29 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 320/1251] eta: 0:09:58 lr: 0.000116 loss: 2.9423 (2.8569) grad_norm: 2.4256 (2.6296) time: 0.6307 [2021-03-28 04:33:35 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 330/1251] eta: 0:09:51 lr: 0.000116 loss: 3.0013 (2.8579) grad_norm: 2.5266 (2.6347) time: 0.6304 [2021-03-28 04:33:41 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 340/1251] eta: 0:09:45 lr: 0.000116 loss: 2.8394 (2.8520) grad_norm: 2.7085 (2.6363) time: 0.6325 [2021-03-28 04:33:48 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 350/1251] eta: 0:09:38 lr: 0.000116 loss: 2.8025 (2.8501) grad_norm: 2.3940 (2.6239) time: 0.6314 [2021-03-28 04:33:54 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 360/1251] eta: 0:09:31 lr: 0.000116 loss: 2.8640 (2.8480) grad_norm: 2.3363 (2.6275) time: 0.6282 [2021-03-28 04:34:00 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 370/1251] eta: 0:09:24 lr: 0.000116 loss: 2.9926 (2.8485) grad_norm: 2.4383 (2.6264) time: 0.6246 [2021-03-28 04:34:07 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 380/1251] eta: 0:09:18 lr: 0.000116 loss: 2.8118 (2.8447) grad_norm: 2.4764 (2.6293) time: 0.6329 [2021-03-28 04:34:13 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 390/1251] eta: 0:09:11 lr: 0.000116 loss: 2.9466 (2.8496) grad_norm: 2.3622 (2.6255) time: 0.6315 [2021-03-28 04:34:19 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 400/1251] eta: 0:09:04 lr: 0.000116 loss: 2.9466 (2.8461) grad_norm: 2.3100 (2.6218) time: 0.6237 [2021-03-28 04:34:25 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 410/1251] eta: 0:08:58 lr: 0.000116 loss: 2.9150 (2.8462) grad_norm: 2.5997 (2.6246) time: 0.6273 [2021-03-28 04:34:32 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 420/1251] eta: 0:08:51 lr: 0.000116 loss: 3.0417 (2.8509) grad_norm: 2.6839 (2.6235) time: 0.6252 [2021-03-28 04:34:38 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 430/1251] eta: 0:08:44 lr: 0.000116 loss: 2.9012 (2.8453) grad_norm: 2.5531 (2.6239) time: 0.6235 [2021-03-28 04:34:44 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 440/1251] eta: 0:08:38 lr: 0.000116 loss: 2.9837 (2.8494) grad_norm: 2.6129 (2.6278) time: 0.6236 [2021-03-28 04:34:50 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 450/1251] eta: 0:08:31 lr: 0.000116 loss: 2.9930 (2.8505) grad_norm: 2.5575 (2.6233) time: 0.6247 [2021-03-28 04:34:57 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 460/1251] eta: 0:08:25 lr: 0.000116 loss: 2.8567 (2.8501) grad_norm: 2.4741 (2.6236) time: 0.6321 [2021-03-28 04:35:03 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 470/1251] eta: 0:08:18 lr: 0.000116 loss: 2.8698 (2.8476) grad_norm: 2.6832 (2.6289) time: 0.6323 [2021-03-28 04:35:09 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 480/1251] eta: 0:08:12 lr: 0.000116 loss: 2.9400 (2.8477) grad_norm: 2.6561 (2.6289) time: 0.6287 [2021-03-28 04:35:16 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 490/1251] eta: 0:08:05 lr: 0.000116 loss: 2.9807 (2.8494) grad_norm: 2.5556 (2.6270) time: 0.6288 [2021-03-28 04:35:22 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 500/1251] eta: 0:07:59 lr: 0.000116 loss: 2.9735 (2.8483) grad_norm: 2.4742 (2.6247) time: 0.6304 [2021-03-28 04:35:28 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 510/1251] eta: 0:07:52 lr: 0.000116 loss: 2.8863 (2.8468) grad_norm: 2.4291 (2.6229) time: 0.6269 [2021-03-28 04:35:34 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 520/1251] eta: 0:07:45 lr: 0.000116 loss: 2.8863 (2.8460) grad_norm: 2.3931 (2.6187) time: 0.6239 [2021-03-28 04:35:41 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 530/1251] eta: 0:07:39 lr: 0.000116 loss: 2.9863 (2.8469) grad_norm: 2.5093 (2.6268) time: 0.6250 [2021-03-28 04:35:47 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 540/1251] eta: 0:07:32 lr: 0.000116 loss: 3.1525 (2.8524) grad_norm: 2.6171 (2.6311) time: 0.6293 [2021-03-28 04:35:53 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 550/1251] eta: 0:07:26 lr: 0.000116 loss: 3.0557 (2.8520) grad_norm: 2.4065 (2.6272) time: 0.6398 [2021-03-28 04:36:00 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 560/1251] eta: 0:07:20 lr: 0.000116 loss: 2.7602 (2.8479) grad_norm: 2.3832 (2.6255) time: 0.6351 [2021-03-28 04:36:06 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 570/1251] eta: 0:07:13 lr: 0.000116 loss: 2.7602 (2.8461) grad_norm: 2.4010 (2.6216) time: 0.6275 [2021-03-28 04:36:12 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 580/1251] eta: 0:07:07 lr: 0.000116 loss: 2.8239 (2.8449) grad_norm: 2.2663 (2.6163) time: 0.6333 [2021-03-28 04:36:19 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 590/1251] eta: 0:07:00 lr: 0.000116 loss: 2.9575 (2.8468) grad_norm: 2.3727 (2.6188) time: 0.6325 [2021-03-28 04:36:25 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 600/1251] eta: 0:06:54 lr: 0.000116 loss: 2.9696 (2.8460) grad_norm: 2.4960 (2.6163) time: 0.6333 [2021-03-28 04:36:31 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 610/1251] eta: 0:06:47 lr: 0.000116 loss: 2.8560 (2.8454) grad_norm: 2.3871 (2.6130) time: 0.6315 [2021-03-28 04:36:37 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 620/1251] eta: 0:06:41 lr: 0.000115 loss: 2.9139 (2.8471) grad_norm: 2.3316 (2.6122) time: 0.6238 [2021-03-28 04:36:44 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 630/1251] eta: 0:06:35 lr: 0.000115 loss: 2.9867 (2.8483) grad_norm: 2.3197 (2.6135) time: 0.6317 [2021-03-28 04:36:50 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 640/1251] eta: 0:06:28 lr: 0.000115 loss: 2.9290 (2.8463) grad_norm: 2.3967 (2.6128) time: 0.6296 [2021-03-28 04:36:56 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 650/1251] eta: 0:06:22 lr: 0.000115 loss: 2.9061 (2.8463) grad_norm: 2.4279 (2.6119) time: 0.6216 [2021-03-28 04:37:03 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 660/1251] eta: 0:06:15 lr: 0.000115 loss: 2.9828 (2.8489) grad_norm: 2.3446 (2.6110) time: 0.6252 [2021-03-28 04:37:09 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 670/1251] eta: 0:06:09 lr: 0.000115 loss: 2.8510 (2.8449) grad_norm: 2.3887 (2.6136) time: 0.6291 [2021-03-28 04:37:15 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 680/1251] eta: 0:06:02 lr: 0.000115 loss: 2.4852 (2.8401) grad_norm: 2.3284 (2.6094) time: 0.6286 [2021-03-28 04:37:21 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 690/1251] eta: 0:05:56 lr: 0.000115 loss: 2.9053 (2.8428) grad_norm: 2.3209 (2.6093) time: 0.6283 [2021-03-28 04:37:28 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 700/1251] eta: 0:05:50 lr: 0.000115 loss: 3.0354 (2.8424) grad_norm: 2.3974 (2.6075) time: 0.6317 [2021-03-28 04:37:34 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 710/1251] eta: 0:05:43 lr: 0.000115 loss: 2.9146 (2.8437) grad_norm: 2.3652 (2.6066) time: 0.6302 [2021-03-28 04:37:40 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 720/1251] eta: 0:05:37 lr: 0.000115 loss: 2.8833 (2.8438) grad_norm: 2.3506 (2.6042) time: 0.6295 [2021-03-28 04:37:47 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 730/1251] eta: 0:05:31 lr: 0.000115 loss: 2.9643 (2.8472) grad_norm: 2.3862 (2.6013) time: 0.6366 [2021-03-28 04:37:53 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 740/1251] eta: 0:05:24 lr: 0.000115 loss: 2.9567 (2.8459) grad_norm: 2.5419 (2.6029) time: 0.6403 [2021-03-28 04:38:00 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 750/1251] eta: 0:05:18 lr: 0.000115 loss: 2.8709 (2.8468) grad_norm: 2.7643 (2.6075) time: 0.6364 [2021-03-28 04:38:06 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 760/1251] eta: 0:05:11 lr: 0.000115 loss: 2.9246 (2.8476) grad_norm: 2.4230 (2.6062) time: 0.6310 [2021-03-28 04:38:12 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 770/1251] eta: 0:05:05 lr: 0.000115 loss: 2.7984 (2.8470) grad_norm: 2.3928 (2.6035) time: 0.6322 [2021-03-28 04:38:19 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 780/1251] eta: 0:04:59 lr: 0.000115 loss: 2.7506 (2.8461) grad_norm: 2.3717 (2.6068) time: 0.6386 [2021-03-28 04:38:25 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 790/1251] eta: 0:04:52 lr: 0.000115 loss: 2.9742 (2.8473) grad_norm: 2.5653 (2.6074) time: 0.6375 [2021-03-28 04:38:31 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 800/1251] eta: 0:04:46 lr: 0.000115 loss: 2.9426 (2.8467) grad_norm: 2.6093 (2.6088) time: 0.6329 [2021-03-28 04:38:37 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 810/1251] eta: 0:04:40 lr: 0.000115 loss: 2.8224 (2.8470) grad_norm: 2.5342 (2.6067) time: 0.6270 [2021-03-28 04:38:44 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 820/1251] eta: 0:04:33 lr: 0.000115 loss: 2.7770 (2.8459) grad_norm: 2.3877 (2.6058) time: 0.6339 [2021-03-28 04:38:50 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 830/1251] eta: 0:04:27 lr: 0.000115 loss: 2.7357 (2.8454) grad_norm: 2.5625 (2.6063) time: 0.6354 [2021-03-28 04:38:57 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 840/1251] eta: 0:04:21 lr: 0.000115 loss: 2.7731 (2.8440) grad_norm: 2.6303 (2.6075) time: 0.6304 [2021-03-28 04:39:03 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 850/1251] eta: 0:04:14 lr: 0.000115 loss: 2.9133 (2.8457) grad_norm: 2.5970 (2.6080) time: 0.6342 [2021-03-28 04:39:09 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 860/1251] eta: 0:04:08 lr: 0.000115 loss: 2.9653 (2.8438) grad_norm: 2.5970 (2.6080) time: 0.6318 [2021-03-28 04:39:16 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 870/1251] eta: 0:04:01 lr: 0.000115 loss: 2.7246 (2.8429) grad_norm: 2.6004 (2.6089) time: 0.6335 [2021-03-28 04:39:22 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 880/1251] eta: 0:03:55 lr: 0.000115 loss: 2.9456 (2.8432) grad_norm: 2.4685 (2.6075) time: 0.6295 [2021-03-28 04:39:28 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 890/1251] eta: 0:03:49 lr: 0.000115 loss: 2.9438 (2.8430) grad_norm: 2.5942 (2.6120) time: 0.6314 [2021-03-28 04:39:34 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 900/1251] eta: 0:03:42 lr: 0.000115 loss: 2.8160 (2.8417) grad_norm: 2.6129 (2.6125) time: 0.6346 [2021-03-28 04:39:41 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 910/1251] eta: 0:03:36 lr: 0.000115 loss: 2.9251 (2.8428) grad_norm: 2.5901 (2.6127) time: 0.6271 [2021-03-28 04:39:47 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 920/1251] eta: 0:03:30 lr: 0.000115 loss: 2.9425 (2.8431) grad_norm: 2.5546 (2.6110) time: 0.6246 [2021-03-28 04:39:53 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 930/1251] eta: 0:03:23 lr: 0.000115 loss: 2.8874 (2.8421) grad_norm: 2.3965 (2.6122) time: 0.6289 [2021-03-28 04:40:00 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 940/1251] eta: 0:03:17 lr: 0.000115 loss: 2.8725 (2.8416) grad_norm: 2.3597 (2.6105) time: 0.6316 [2021-03-28 04:40:06 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 950/1251] eta: 0:03:10 lr: 0.000115 loss: 2.9682 (2.8430) grad_norm: 2.5407 (2.6107) time: 0.6266 [2021-03-28 04:40:12 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 960/1251] eta: 0:03:04 lr: 0.000115 loss: 3.0097 (2.8425) grad_norm: 2.5851 (2.6116) time: 0.6246 [2021-03-28 04:40:18 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 970/1251] eta: 0:02:58 lr: 0.000115 loss: 2.8542 (2.8420) grad_norm: 2.4758 (2.6097) time: 0.6264 [2021-03-28 04:40:25 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 980/1251] eta: 0:02:51 lr: 0.000115 loss: 2.8333 (2.8407) grad_norm: 2.4758 (2.6101) time: 0.6274 [2021-03-28 04:40:31 swin_base_patch4_window7_224] INFO: Epoch: [236] [ 990/1251] eta: 0:02:45 lr: 0.000115 loss: 2.8549 (2.8410) grad_norm: 2.6559 (2.6121) time: 0.6318 [2021-03-28 04:40:37 swin_base_patch4_window7_224] INFO: Epoch: [236] [1000/1251] eta: 0:02:39 lr: 0.000115 loss: 2.8571 (2.8397) grad_norm: 2.5318 (2.6139) time: 0.6375 [2021-03-28 04:40:44 swin_base_patch4_window7_224] INFO: Epoch: [236] [1010/1251] eta: 0:02:32 lr: 0.000114 loss: 2.8571 (2.8398) grad_norm: 2.5202 (2.6140) time: 0.6337 [2021-03-28 04:40:50 swin_base_patch4_window7_224] INFO: Epoch: [236] [1020/1251] eta: 0:02:26 lr: 0.000114 loss: 3.0014 (2.8422) grad_norm: 2.5202 (2.6148) time: 0.6286 [2021-03-28 04:40:56 swin_base_patch4_window7_224] INFO: Epoch: [236] [1030/1251] eta: 0:02:20 lr: 0.000114 loss: 2.9919 (2.8409) grad_norm: 2.4981 (2.6142) time: 0.6284 [2021-03-28 04:41:03 swin_base_patch4_window7_224] INFO: Epoch: [236] [1040/1251] eta: 0:02:13 lr: 0.000114 loss: 2.8438 (2.8408) grad_norm: 2.5036 (2.6149) time: 0.6299 [2021-03-28 04:41:09 swin_base_patch4_window7_224] INFO: Epoch: [236] [1050/1251] eta: 0:02:07 lr: 0.000114 loss: 2.8903 (2.8412) grad_norm: 2.5356 (2.6150) time: 0.6262 [2021-03-28 04:41:15 swin_base_patch4_window7_224] INFO: Epoch: [236] [1060/1251] eta: 0:02:01 lr: 0.000114 loss: 2.7511 (2.8391) grad_norm: 2.5358 (2.6151) time: 0.6230 [2021-03-28 04:41:21 swin_base_patch4_window7_224] INFO: Epoch: [236] [1070/1251] eta: 0:01:54 lr: 0.000114 loss: 2.6944 (2.8388) grad_norm: 2.4570 (2.6129) time: 0.6257 [2021-03-28 04:41:28 swin_base_patch4_window7_224] INFO: Epoch: [236] [1080/1251] eta: 0:01:48 lr: 0.000114 loss: 3.0122 (2.8398) grad_norm: 2.4570 (2.6117) time: 0.6283 [2021-03-28 04:41:34 swin_base_patch4_window7_224] INFO: Epoch: [236] [1090/1251] eta: 0:01:42 lr: 0.000114 loss: 3.1182 (2.8421) grad_norm: 2.4737 (inf) time: 0.6244 [2021-03-28 04:41:40 swin_base_patch4_window7_224] INFO: Epoch: [236] [1100/1251] eta: 0:01:35 lr: 0.000114 loss: 3.1104 (2.8420) grad_norm: 2.3420 (inf) time: 0.6234 [2021-03-28 04:41:46 swin_base_patch4_window7_224] INFO: Epoch: [236] [1110/1251] eta: 0:01:29 lr: 0.000114 loss: 2.7826 (2.8410) grad_norm: 2.3915 (inf) time: 0.6254 [2021-03-28 04:41:53 swin_base_patch4_window7_224] INFO: Epoch: [236] [1120/1251] eta: 0:01:23 lr: 0.000114 loss: 2.9408 (2.8417) grad_norm: 2.5225 (inf) time: 0.6299 [2021-03-28 04:41:59 swin_base_patch4_window7_224] INFO: Epoch: [236] [1130/1251] eta: 0:01:16 lr: 0.000114 loss: 2.9408 (2.8405) grad_norm: 2.4772 (inf) time: 0.6365 [2021-03-28 04:42:05 swin_base_patch4_window7_224] INFO: Epoch: [236] [1140/1251] eta: 0:01:10 lr: 0.000114 loss: 2.8351 (2.8408) grad_norm: 2.3242 (inf) time: 0.6358 [2021-03-28 04:42:12 swin_base_patch4_window7_224] INFO: Epoch: [236] [1150/1251] eta: 0:01:03 lr: 0.000114 loss: 3.0058 (2.8420) grad_norm: 2.3942 (inf) time: 0.6318 [2021-03-28 04:42:18 swin_base_patch4_window7_224] INFO: Epoch: [236] [1160/1251] eta: 0:00:57 lr: 0.000114 loss: 3.0479 (2.8416) grad_norm: 2.4885 (inf) time: 0.6282 [2021-03-28 04:42:24 swin_base_patch4_window7_224] INFO: Epoch: [236] [1170/1251] eta: 0:00:51 lr: 0.000114 loss: 2.9196 (2.8415) grad_norm: 2.5949 (inf) time: 0.6268 [2021-03-28 04:42:30 swin_base_patch4_window7_224] INFO: Epoch: [236] [1180/1251] eta: 0:00:44 lr: 0.000114 loss: 2.9196 (2.8407) grad_norm: 2.5872 (inf) time: 0.6251 [2021-03-28 04:42:37 swin_base_patch4_window7_224] INFO: Epoch: [236] [1190/1251] eta: 0:00:38 lr: 0.000114 loss: 2.9236 (2.8420) grad_norm: 2.5529 (inf) time: 0.6288 [2021-03-28 04:42:43 swin_base_patch4_window7_224] INFO: Epoch: [236] [1200/1251] eta: 0:00:32 lr: 0.000114 loss: 2.9251 (2.8424) grad_norm: 2.4915 (inf) time: 0.6273 [2021-03-28 04:42:49 swin_base_patch4_window7_224] INFO: Epoch: [236] [1210/1251] eta: 0:00:25 lr: 0.000114 loss: 2.9596 (2.8440) grad_norm: 2.3740 (inf) time: 0.6260 [2021-03-28 04:42:56 swin_base_patch4_window7_224] INFO: Epoch: [236] [1220/1251] eta: 0:00:19 lr: 0.000114 loss: 2.9100 (2.8429) grad_norm: 2.4771 (inf) time: 0.6350 [2021-03-28 04:43:02 swin_base_patch4_window7_224] INFO: Epoch: [236] [1230/1251] eta: 0:00:13 lr: 0.000114 loss: 3.0495 (2.8455) grad_norm: 2.4771 (inf) time: 0.6329 [2021-03-28 04:43:08 swin_base_patch4_window7_224] INFO: Epoch: [236] [1240/1251] eta: 0:00:06 lr: 0.000114 loss: 3.1314 (2.8468) grad_norm: 2.4681 (inf) time: 0.6307 [2021-03-28 04:43:15 swin_base_patch4_window7_224] INFO: Epoch: [236] [1250/1251] eta: 0:00:00 lr: 0.000114 loss: 3.0773 (2.8466) grad_norm: 2.5853 (inf) time: 0.6312 [2021-03-28 04:43:28 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:10 loss: 0.7987 (0.7987) acc1: 75.0000 (75.0000) acc5: 98.4375 (98.4375) [2021-03-28 04:43:30 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7987 (0.7873) acc1: 81.2500 (80.8239) acc5: 96.8750 (96.5909) [2021-03-28 04:43:33 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7486 (0.8067) acc1: 81.2500 (80.2827) acc5: 95.3125 (95.9821) [2021-03-28 04:43:35 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7685 (0.7975) acc1: 81.2500 (80.5444) acc5: 95.3125 (95.8165) [2021-03-28 04:43:37 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7392 (0.7820) acc1: 82.8125 (81.0976) acc5: 95.3125 (96.1128) [2021-03-28 04:43:38 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7392 (0.7763) acc1: 82.8125 (81.2800) acc5: 96.8750 (96.2560) [2021-03-28 04:43:50 swin_base_patch4_window7_224] INFO: * Acc@1 82.470 Acc@5 96.186 loss 0.758 [2021-03-28 04:43:50 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.5% [2021-03-28 04:43:50 swin_base_patch4_window7_224] INFO: Max accuracy: 82.58% [2021-03-28 04:43:55 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 0/1251] eta: 1:45:39 lr: 0.000114 loss: 2.8430 (2.8430) grad_norm: 3.1326 (3.1326) time: 5.0675 [2021-03-28 04:44:01 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 10/1251] eta: 0:21:41 lr: 0.000114 loss: 2.9351 (2.9686) grad_norm: 2.4800 (2.5573) time: 1.0491 [2021-03-28 04:44:08 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 20/1251] eta: 0:17:32 lr: 0.000114 loss: 2.7543 (2.7487) grad_norm: 2.3205 (2.4576) time: 0.6445 [2021-03-28 04:44:14 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 30/1251] eta: 0:15:55 lr: 0.000114 loss: 2.7543 (2.7789) grad_norm: 2.3558 (2.5226) time: 0.6360 [2021-03-28 04:44:20 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 40/1251] eta: 0:15:03 lr: 0.000114 loss: 2.9963 (2.8047) grad_norm: 2.5558 (2.5319) time: 0.6309 [2021-03-28 04:44:27 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 50/1251] eta: 0:14:27 lr: 0.000114 loss: 2.9245 (2.8195) grad_norm: 2.4259 (2.5489) time: 0.6285 [2021-03-28 04:44:33 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 60/1251] eta: 0:14:04 lr: 0.000114 loss: 2.8651 (2.7857) grad_norm: 2.4760 (2.5482) time: 0.6334 [2021-03-28 04:44:39 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 70/1251] eta: 0:13:44 lr: 0.000114 loss: 2.7717 (2.7955) grad_norm: 2.4760 (2.5856) time: 0.6382 [2021-03-28 04:44:46 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 80/1251] eta: 0:13:28 lr: 0.000114 loss: 2.8147 (2.7684) grad_norm: 2.4580 (2.5674) time: 0.6355 [2021-03-28 04:44:52 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 90/1251] eta: 0:13:14 lr: 0.000114 loss: 2.9251 (2.7805) grad_norm: 2.3787 (2.5511) time: 0.6346 [2021-03-28 04:44:58 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 100/1251] eta: 0:13:02 lr: 0.000114 loss: 2.9182 (2.7724) grad_norm: 2.4045 (2.5762) time: 0.6356 [2021-03-28 04:45:05 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 110/1251] eta: 0:12:51 lr: 0.000114 loss: 2.6695 (2.7680) grad_norm: 2.6069 (2.5846) time: 0.6375 [2021-03-28 04:45:11 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 120/1251] eta: 0:12:40 lr: 0.000114 loss: 2.8000 (2.7796) grad_norm: 2.6497 (2.5925) time: 0.6358 [2021-03-28 04:45:17 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 130/1251] eta: 0:12:29 lr: 0.000114 loss: 2.7244 (2.7473) grad_norm: 2.5756 (2.6117) time: 0.6290 [2021-03-28 04:45:24 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 140/1251] eta: 0:12:20 lr: 0.000114 loss: 2.3937 (2.7313) grad_norm: 2.5721 (2.6290) time: 0.6271 [2021-03-28 04:45:30 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 150/1251] eta: 0:12:10 lr: 0.000113 loss: 2.8209 (2.7496) grad_norm: 2.5736 (2.6339) time: 0.6261 [2021-03-28 04:45:36 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 160/1251] eta: 0:12:01 lr: 0.000113 loss: 2.9751 (2.7546) grad_norm: 2.3819 (2.6391) time: 0.6289 [2021-03-28 04:45:43 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 170/1251] eta: 0:11:52 lr: 0.000113 loss: 2.9467 (2.7658) grad_norm: 2.2938 (2.6240) time: 0.6284 [2021-03-28 04:45:49 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 180/1251] eta: 0:11:44 lr: 0.000113 loss: 2.9878 (2.7805) grad_norm: 2.3566 (2.6112) time: 0.6260 [2021-03-28 04:45:55 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 190/1251] eta: 0:11:35 lr: 0.000113 loss: 2.9878 (2.7911) grad_norm: 2.3960 (2.6225) time: 0.6293 [2021-03-28 04:46:02 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 200/1251] eta: 0:11:28 lr: 0.000113 loss: 2.8477 (2.7871) grad_norm: 2.4527 (2.6257) time: 0.6337 [2021-03-28 04:46:08 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 210/1251] eta: 0:11:20 lr: 0.000113 loss: 2.5251 (2.7792) grad_norm: 2.4527 (2.6238) time: 0.6336 [2021-03-28 04:46:14 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 220/1251] eta: 0:11:12 lr: 0.000113 loss: 2.4505 (2.7737) grad_norm: 2.4523 (2.6245) time: 0.6250 [2021-03-28 04:46:20 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 230/1251] eta: 0:11:05 lr: 0.000113 loss: 2.8470 (2.7821) grad_norm: 2.6015 (2.6308) time: 0.6288 [2021-03-28 04:46:27 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 240/1251] eta: 0:10:57 lr: 0.000113 loss: 3.0222 (2.7897) grad_norm: 2.6015 (2.6293) time: 0.6314 [2021-03-28 04:46:33 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 250/1251] eta: 0:10:50 lr: 0.000113 loss: 3.1052 (2.7968) grad_norm: 2.5752 (2.6333) time: 0.6308 [2021-03-28 04:46:39 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 260/1251] eta: 0:10:43 lr: 0.000113 loss: 3.1175 (2.8037) grad_norm: 2.4188 (2.6239) time: 0.6333 [2021-03-28 04:46:46 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 270/1251] eta: 0:10:36 lr: 0.000113 loss: 2.9238 (2.8022) grad_norm: 2.4066 (2.6218) time: 0.6353 [2021-03-28 04:46:52 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 280/1251] eta: 0:10:29 lr: 0.000113 loss: 2.7904 (2.8028) grad_norm: 2.5267 (2.6196) time: 0.6304 [2021-03-28 04:46:58 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 290/1251] eta: 0:10:21 lr: 0.000113 loss: 2.7464 (2.7957) grad_norm: 2.5383 (2.6140) time: 0.6231 [2021-03-28 04:47:04 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 300/1251] eta: 0:10:14 lr: 0.000113 loss: 2.7502 (2.7998) grad_norm: 2.5119 (2.6153) time: 0.6242 [2021-03-28 04:47:11 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 310/1251] eta: 0:10:08 lr: 0.000113 loss: 3.0737 (2.8040) grad_norm: 2.4237 (2.6079) time: 0.6323 [2021-03-28 04:47:17 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 320/1251] eta: 0:10:00 lr: 0.000113 loss: 3.0366 (2.8093) grad_norm: 2.4600 (2.6273) time: 0.6301 [2021-03-28 04:47:23 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 330/1251] eta: 0:09:53 lr: 0.000113 loss: 2.9210 (2.8047) grad_norm: 2.5417 (2.6278) time: 0.6217 [2021-03-28 04:47:30 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 340/1251] eta: 0:09:46 lr: 0.000113 loss: 2.7237 (2.8019) grad_norm: 2.6185 (2.6290) time: 0.6253 [2021-03-28 04:47:36 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 350/1251] eta: 0:09:40 lr: 0.000113 loss: 2.7237 (2.7998) grad_norm: 2.4950 (2.6296) time: 0.6302 [2021-03-28 04:47:42 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 360/1251] eta: 0:09:33 lr: 0.000113 loss: 2.8222 (2.8067) grad_norm: 2.5177 (2.6354) time: 0.6302 [2021-03-28 04:47:49 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 370/1251] eta: 0:09:26 lr: 0.000113 loss: 2.9658 (2.8086) grad_norm: 2.5177 (2.6369) time: 0.6364 [2021-03-28 04:47:55 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 380/1251] eta: 0:09:20 lr: 0.000113 loss: 2.8149 (2.8087) grad_norm: 2.4561 (2.6328) time: 0.6374 [2021-03-28 04:48:01 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 390/1251] eta: 0:09:13 lr: 0.000113 loss: 2.8124 (2.8071) grad_norm: 2.4561 (2.6360) time: 0.6321 [2021-03-28 04:48:08 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 400/1251] eta: 0:09:06 lr: 0.000113 loss: 2.9370 (2.8113) grad_norm: 2.3554 (2.6369) time: 0.6324 [2021-03-28 04:48:14 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 410/1251] eta: 0:09:00 lr: 0.000113 loss: 2.9370 (2.8112) grad_norm: 2.6058 (2.6388) time: 0.6342 [2021-03-28 04:48:20 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 420/1251] eta: 0:08:53 lr: 0.000113 loss: 3.0309 (2.8158) grad_norm: 2.4957 (2.6342) time: 0.6379 [2021-03-28 04:48:27 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 430/1251] eta: 0:08:47 lr: 0.000113 loss: 2.8797 (2.8151) grad_norm: 2.4956 (2.6333) time: 0.6309 [2021-03-28 04:48:33 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 440/1251] eta: 0:08:40 lr: 0.000113 loss: 2.8775 (2.8150) grad_norm: 2.4956 (2.6343) time: 0.6291 [2021-03-28 04:48:39 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 450/1251] eta: 0:08:33 lr: 0.000113 loss: 2.8945 (2.8183) grad_norm: 2.4568 (2.6326) time: 0.6324 [2021-03-28 04:48:45 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 460/1251] eta: 0:08:27 lr: 0.000113 loss: 2.8244 (2.8170) grad_norm: 2.4254 (2.6291) time: 0.6285 [2021-03-28 04:48:52 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 470/1251] eta: 0:08:20 lr: 0.000113 loss: 2.8244 (2.8142) grad_norm: 2.4243 (2.6267) time: 0.6255 [2021-03-28 04:48:58 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 480/1251] eta: 0:08:13 lr: 0.000113 loss: 2.8167 (2.8160) grad_norm: 2.4104 (2.6273) time: 0.6234 [2021-03-28 04:49:04 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 490/1251] eta: 0:08:07 lr: 0.000113 loss: 2.8904 (2.8157) grad_norm: 2.4104 (2.6254) time: 0.6227 [2021-03-28 04:49:10 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 500/1251] eta: 0:08:00 lr: 0.000113 loss: 2.8904 (2.8171) grad_norm: 2.3777 (2.6198) time: 0.6247 [2021-03-28 04:49:17 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 510/1251] eta: 0:07:53 lr: 0.000113 loss: 2.8087 (2.8149) grad_norm: 2.3515 (2.6162) time: 0.6252 [2021-03-28 04:49:23 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 520/1251] eta: 0:07:47 lr: 0.000113 loss: 2.8459 (2.8181) grad_norm: 2.4727 (2.6214) time: 0.6253 [2021-03-28 04:49:29 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 530/1251] eta: 0:07:40 lr: 0.000113 loss: 2.8720 (2.8177) grad_norm: 2.5177 (2.6194) time: 0.6259 [2021-03-28 04:49:36 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 540/1251] eta: 0:07:34 lr: 0.000113 loss: 2.9640 (2.8205) grad_norm: 2.4875 (2.6180) time: 0.6280 [2021-03-28 04:49:42 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 550/1251] eta: 0:07:27 lr: 0.000112 loss: 2.8557 (2.8175) grad_norm: 2.4206 (2.6144) time: 0.6410 [2021-03-28 04:49:48 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 560/1251] eta: 0:07:21 lr: 0.000112 loss: 2.8199 (2.8175) grad_norm: 2.5185 (2.6175) time: 0.6445 [2021-03-28 04:49:55 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 570/1251] eta: 0:07:15 lr: 0.000112 loss: 2.8882 (2.8191) grad_norm: 2.6064 (2.6203) time: 0.6398 [2021-03-28 04:50:01 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 580/1251] eta: 0:07:08 lr: 0.000112 loss: 3.0128 (2.8223) grad_norm: 2.3771 (2.6150) time: 0.6357 [2021-03-28 04:50:07 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 590/1251] eta: 0:07:02 lr: 0.000112 loss: 3.0283 (2.8251) grad_norm: 2.2278 (2.6141) time: 0.6286 [2021-03-28 04:50:14 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 600/1251] eta: 0:06:55 lr: 0.000112 loss: 3.0283 (2.8257) grad_norm: 2.4708 (2.6198) time: 0.6262 [2021-03-28 04:50:20 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 610/1251] eta: 0:06:49 lr: 0.000112 loss: 2.8520 (2.8255) grad_norm: 2.5705 (2.6303) time: 0.6243 [2021-03-28 04:50:26 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 620/1251] eta: 0:06:42 lr: 0.000112 loss: 2.9819 (2.8298) grad_norm: 2.5362 (2.6281) time: 0.6258 [2021-03-28 04:50:32 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 630/1251] eta: 0:06:36 lr: 0.000112 loss: 3.0487 (2.8299) grad_norm: 2.4291 (2.6266) time: 0.6255 [2021-03-28 04:50:39 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 640/1251] eta: 0:06:29 lr: 0.000112 loss: 2.9917 (2.8289) grad_norm: 2.6373 (2.6295) time: 0.6249 [2021-03-28 04:50:45 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 650/1251] eta: 0:06:23 lr: 0.000112 loss: 2.7847 (2.8269) grad_norm: 2.6373 (2.6298) time: 0.6302 [2021-03-28 04:50:51 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 660/1251] eta: 0:06:16 lr: 0.000112 loss: 2.8636 (2.8275) grad_norm: 2.5770 (2.6294) time: 0.6333 [2021-03-28 04:50:58 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 670/1251] eta: 0:06:10 lr: 0.000112 loss: 2.8636 (2.8283) grad_norm: 2.5770 (2.6279) time: 0.6344 [2021-03-28 04:51:04 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 680/1251] eta: 0:06:03 lr: 0.000112 loss: 2.7741 (2.8275) grad_norm: 2.3281 (2.6267) time: 0.6316 [2021-03-28 04:51:10 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 690/1251] eta: 0:05:57 lr: 0.000112 loss: 2.7782 (2.8264) grad_norm: 2.4627 (2.6286) time: 0.6275 [2021-03-28 04:51:17 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 700/1251] eta: 0:05:51 lr: 0.000112 loss: 2.8404 (2.8281) grad_norm: 2.4059 (2.6265) time: 0.6304 [2021-03-28 04:51:23 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 710/1251] eta: 0:05:44 lr: 0.000112 loss: 2.9743 (2.8279) grad_norm: 2.3917 (2.6234) time: 0.6322 [2021-03-28 04:51:29 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 720/1251] eta: 0:05:38 lr: 0.000112 loss: 2.9197 (2.8274) grad_norm: 2.5209 (2.6237) time: 0.6283 [2021-03-28 04:51:36 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 730/1251] eta: 0:05:31 lr: 0.000112 loss: 2.8167 (2.8272) grad_norm: 2.5270 (2.6242) time: 0.6308 [2021-03-28 04:51:42 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 740/1251] eta: 0:05:25 lr: 0.000112 loss: 2.9216 (2.8268) grad_norm: 2.5861 (2.6260) time: 0.6383 [2021-03-28 04:51:48 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 750/1251] eta: 0:05:19 lr: 0.000112 loss: 2.9727 (2.8270) grad_norm: 2.5152 (2.6229) time: 0.6377 [2021-03-28 04:51:55 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 760/1251] eta: 0:05:12 lr: 0.000112 loss: 2.9585 (2.8256) grad_norm: 2.3964 (2.6224) time: 0.6385 [2021-03-28 04:52:01 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 770/1251] eta: 0:05:06 lr: 0.000112 loss: 2.9497 (2.8270) grad_norm: 2.4245 (2.6209) time: 0.6420 [2021-03-28 04:52:07 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 780/1251] eta: 0:05:00 lr: 0.000112 loss: 2.9497 (2.8268) grad_norm: 2.4501 (2.6199) time: 0.6337 [2021-03-28 04:52:14 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 790/1251] eta: 0:04:53 lr: 0.000112 loss: 2.9305 (2.8273) grad_norm: 2.4501 (2.6178) time: 0.6260 [2021-03-28 04:52:20 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 800/1251] eta: 0:04:47 lr: 0.000112 loss: 3.0730 (2.8289) grad_norm: 2.3254 (2.6150) time: 0.6313 [2021-03-28 04:52:26 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 810/1251] eta: 0:04:40 lr: 0.000112 loss: 3.0410 (2.8312) grad_norm: 2.3097 (2.6119) time: 0.6302 [2021-03-28 04:52:33 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 820/1251] eta: 0:04:34 lr: 0.000112 loss: 2.9806 (2.8299) grad_norm: 2.3851 (2.6108) time: 0.6286 [2021-03-28 04:52:39 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 830/1251] eta: 0:04:28 lr: 0.000112 loss: 2.9034 (2.8320) grad_norm: 2.2926 (2.6067) time: 0.6341 [2021-03-28 04:52:45 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 840/1251] eta: 0:04:21 lr: 0.000112 loss: 2.9034 (2.8305) grad_norm: 2.2926 (2.6076) time: 0.6344 [2021-03-28 04:52:52 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 850/1251] eta: 0:04:15 lr: 0.000112 loss: 2.8131 (2.8313) grad_norm: 2.4562 (2.6077) time: 0.6326 [2021-03-28 04:52:58 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 860/1251] eta: 0:04:08 lr: 0.000112 loss: 2.9315 (2.8321) grad_norm: 2.3898 (2.6050) time: 0.6335 [2021-03-28 04:53:04 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 870/1251] eta: 0:04:02 lr: 0.000112 loss: 2.9315 (2.8330) grad_norm: 2.3872 (2.6039) time: 0.6386 [2021-03-28 04:53:11 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 880/1251] eta: 0:03:56 lr: 0.000112 loss: 2.8646 (2.8312) grad_norm: 2.5572 (2.6040) time: 0.6375 [2021-03-28 04:53:17 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 890/1251] eta: 0:03:49 lr: 0.000112 loss: 2.8624 (2.8316) grad_norm: 2.5197 (2.6019) time: 0.6280 [2021-03-28 04:53:23 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 900/1251] eta: 0:03:43 lr: 0.000112 loss: 3.0341 (2.8315) grad_norm: 2.3567 (2.6037) time: 0.6249 [2021-03-28 04:53:29 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 910/1251] eta: 0:03:36 lr: 0.000112 loss: 2.9698 (2.8312) grad_norm: 2.3800 (2.6021) time: 0.6274 [2021-03-28 04:53:36 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 920/1251] eta: 0:03:30 lr: 0.000112 loss: 2.9698 (2.8303) grad_norm: 2.3800 (2.6021) time: 0.6247 [2021-03-28 04:53:42 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 930/1251] eta: 0:03:24 lr: 0.000112 loss: 2.8907 (2.8311) grad_norm: 2.3683 (2.6023) time: 0.6275 [2021-03-28 04:53:48 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 940/1251] eta: 0:03:17 lr: 0.000111 loss: 2.7379 (2.8291) grad_norm: 2.4325 (2.6018) time: 0.6361 [2021-03-28 04:53:55 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 950/1251] eta: 0:03:11 lr: 0.000111 loss: 2.8434 (2.8316) grad_norm: 2.4384 (2.6002) time: 0.6377 [2021-03-28 04:54:01 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 960/1251] eta: 0:03:05 lr: 0.000111 loss: 3.0344 (2.8315) grad_norm: 2.5232 (2.5998) time: 0.6311 [2021-03-28 04:54:07 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 970/1251] eta: 0:02:58 lr: 0.000111 loss: 2.7819 (2.8298) grad_norm: 2.5356 (2.6023) time: 0.6331 [2021-03-28 04:54:14 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 980/1251] eta: 0:02:52 lr: 0.000111 loss: 2.9757 (2.8306) grad_norm: 2.4473 (2.6011) time: 0.6311 [2021-03-28 04:54:20 swin_base_patch4_window7_224] INFO: Epoch: [237] [ 990/1251] eta: 0:02:45 lr: 0.000111 loss: 3.0012 (2.8319) grad_norm: 2.4848 (2.6014) time: 0.6223 [2021-03-28 04:54:26 swin_base_patch4_window7_224] INFO: Epoch: [237] [1000/1251] eta: 0:02:39 lr: 0.000111 loss: 2.9890 (2.8329) grad_norm: 2.5572 (2.5998) time: 0.6272 [2021-03-28 04:54:33 swin_base_patch4_window7_224] INFO: Epoch: [237] [1010/1251] eta: 0:02:33 lr: 0.000111 loss: 2.9412 (2.8326) grad_norm: 2.4492 (2.5981) time: 0.6344 [2021-03-28 04:54:39 swin_base_patch4_window7_224] INFO: Epoch: [237] [1020/1251] eta: 0:02:26 lr: 0.000111 loss: 2.9258 (2.8337) grad_norm: 2.4492 (2.5981) time: 0.6362 [2021-03-28 04:54:45 swin_base_patch4_window7_224] INFO: Epoch: [237] [1030/1251] eta: 0:02:20 lr: 0.000111 loss: 2.8201 (2.8308) grad_norm: 2.5345 (2.6027) time: 0.6348 [2021-03-28 04:54:52 swin_base_patch4_window7_224] INFO: Epoch: [237] [1040/1251] eta: 0:02:14 lr: 0.000111 loss: 2.8201 (2.8322) grad_norm: 2.4136 (2.5993) time: 0.6318 [2021-03-28 04:54:58 swin_base_patch4_window7_224] INFO: Epoch: [237] [1050/1251] eta: 0:02:07 lr: 0.000111 loss: 3.0685 (2.8342) grad_norm: 2.1917 (2.5960) time: 0.6286 [2021-03-28 04:55:04 swin_base_patch4_window7_224] INFO: Epoch: [237] [1060/1251] eta: 0:02:01 lr: 0.000111 loss: 2.8751 (2.8327) grad_norm: 2.2644 (2.5947) time: 0.6289 [2021-03-28 04:55:10 swin_base_patch4_window7_224] INFO: Epoch: [237] [1070/1251] eta: 0:01:54 lr: 0.000111 loss: 2.8751 (2.8332) grad_norm: 2.5470 (2.5952) time: 0.6261 [2021-03-28 04:55:17 swin_base_patch4_window7_224] INFO: Epoch: [237] [1080/1251] eta: 0:01:48 lr: 0.000111 loss: 2.9508 (2.8307) grad_norm: 2.5041 (2.5965) time: 0.6238 [2021-03-28 04:55:23 swin_base_patch4_window7_224] INFO: Epoch: [237] [1090/1251] eta: 0:01:42 lr: 0.000111 loss: 2.9202 (2.8323) grad_norm: 2.5041 (2.5970) time: 0.6320 [2021-03-28 04:55:29 swin_base_patch4_window7_224] INFO: Epoch: [237] [1100/1251] eta: 0:01:35 lr: 0.000111 loss: 2.9202 (2.8326) grad_norm: 2.4601 (2.5950) time: 0.6381 [2021-03-28 04:55:36 swin_base_patch4_window7_224] INFO: Epoch: [237] [1110/1251] eta: 0:01:29 lr: 0.000111 loss: 2.9895 (2.8338) grad_norm: 2.3864 (2.5959) time: 0.6381 [2021-03-28 04:55:42 swin_base_patch4_window7_224] INFO: Epoch: [237] [1120/1251] eta: 0:01:23 lr: 0.000111 loss: 2.9831 (2.8341) grad_norm: 2.5342 (2.5954) time: 0.6321 [2021-03-28 04:55:48 swin_base_patch4_window7_224] INFO: Epoch: [237] [1130/1251] eta: 0:01:16 lr: 0.000111 loss: 2.8682 (2.8330) grad_norm: 2.4577 (2.5946) time: 0.6258 [2021-03-28 04:55:55 swin_base_patch4_window7_224] INFO: Epoch: [237] [1140/1251] eta: 0:01:10 lr: 0.000111 loss: 2.7970 (2.8315) grad_norm: 2.4234 (2.5951) time: 0.6273 [2021-03-28 04:56:01 swin_base_patch4_window7_224] INFO: Epoch: [237] [1150/1251] eta: 0:01:04 lr: 0.000111 loss: 2.7970 (2.8306) grad_norm: 2.5198 (2.5943) time: 0.6269 [2021-03-28 04:56:07 swin_base_patch4_window7_224] INFO: Epoch: [237] [1160/1251] eta: 0:00:57 lr: 0.000111 loss: 2.8855 (2.8308) grad_norm: 2.5663 (2.5959) time: 0.6271 [2021-03-28 04:56:13 swin_base_patch4_window7_224] INFO: Epoch: [237] [1170/1251] eta: 0:00:51 lr: 0.000111 loss: 2.8875 (2.8315) grad_norm: 2.5437 (2.5963) time: 0.6306 [2021-03-28 04:56:20 swin_base_patch4_window7_224] INFO: Epoch: [237] [1180/1251] eta: 0:00:45 lr: 0.000111 loss: 2.9125 (2.8311) grad_norm: 2.4676 (2.6006) time: 0.6271 [2021-03-28 04:56:26 swin_base_patch4_window7_224] INFO: Epoch: [237] [1190/1251] eta: 0:00:38 lr: 0.000111 loss: 2.8721 (2.8311) grad_norm: 2.4951 (2.5994) time: 0.6278 [2021-03-28 04:56:32 swin_base_patch4_window7_224] INFO: Epoch: [237] [1200/1251] eta: 0:00:32 lr: 0.000111 loss: 2.8233 (2.8307) grad_norm: 2.4770 (2.5991) time: 0.6286 [2021-03-28 04:56:39 swin_base_patch4_window7_224] INFO: Epoch: [237] [1210/1251] eta: 0:00:26 lr: 0.000111 loss: 2.9302 (2.8327) grad_norm: 2.5341 (2.5992) time: 0.6236 [2021-03-28 04:56:45 swin_base_patch4_window7_224] INFO: Epoch: [237] [1220/1251] eta: 0:00:19 lr: 0.000111 loss: 3.0992 (2.8328) grad_norm: 2.5344 (2.5991) time: 0.6247 [2021-03-28 04:56:51 swin_base_patch4_window7_224] INFO: Epoch: [237] [1230/1251] eta: 0:00:13 lr: 0.000111 loss: 2.9027 (2.8337) grad_norm: 2.4444 (2.5990) time: 0.6253 [2021-03-28 04:56:57 swin_base_patch4_window7_224] INFO: Epoch: [237] [1240/1251] eta: 0:00:06 lr: 0.000111 loss: 3.1724 (2.8357) grad_norm: 2.4444 (2.5982) time: 0.6261 [2021-03-28 04:57:04 swin_base_patch4_window7_224] INFO: Epoch: [237] [1250/1251] eta: 0:00:00 lr: 0.000111 loss: 2.9691 (2.8360) grad_norm: 2.5109 (2.6027) time: 0.6282 [2021-03-28 04:57:13 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:54 loss: 0.5749 (0.5749) acc1: 87.5000 (87.5000) acc5: 98.4375 (98.4375) [2021-03-28 04:57:15 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8724 (0.8027) acc1: 81.2500 (80.8239) acc5: 96.8750 (96.4489) [2021-03-28 04:57:18 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8454 (0.7508) acc1: 81.2500 (82.2917) acc5: 96.8750 (96.6518) [2021-03-28 04:57:19 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8027 (0.7828) acc1: 81.2500 (81.6532) acc5: 96.8750 (96.3710) [2021-03-28 04:57:21 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8268 (0.7844) acc1: 81.2500 (81.7454) acc5: 95.3125 (96.1128) [2021-03-28 04:57:22 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8371 (0.7862) acc1: 81.2500 (81.7920) acc5: 95.3125 (96.0960) [2021-03-28 04:57:36 swin_base_patch4_window7_224] INFO: * Acc@1 82.506 Acc@5 96.174 loss 0.773 [2021-03-28 04:57:36 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.5% [2021-03-28 04:57:36 swin_base_patch4_window7_224] INFO: Max accuracy: 82.58% [2021-03-28 04:57:40 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 0/1251] eta: 1:27:36 lr: 0.000111 loss: 3.0047 (3.0047) grad_norm: 2.1838 (2.1838) time: 4.2022 [2021-03-28 04:57:46 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 10/1251] eta: 0:19:45 lr: 0.000111 loss: 2.9565 (2.7614) grad_norm: 2.5444 (2.5360) time: 0.9556 [2021-03-28 04:57:53 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 20/1251] eta: 0:16:21 lr: 0.000111 loss: 2.9565 (2.8872) grad_norm: 2.4518 (2.4769) time: 0.6270 [2021-03-28 04:57:59 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 30/1251] eta: 0:15:07 lr: 0.000111 loss: 2.8959 (2.8931) grad_norm: 2.2632 (2.4258) time: 0.6271 [2021-03-28 04:58:05 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 40/1251] eta: 0:14:25 lr: 0.000111 loss: 3.0219 (2.9214) grad_norm: 2.2881 (2.4544) time: 0.6279 [2021-03-28 04:58:11 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 50/1251] eta: 0:13:59 lr: 0.000111 loss: 3.0591 (2.9210) grad_norm: 2.2631 (2.4129) time: 0.6291 [2021-03-28 04:58:18 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 60/1251] eta: 0:13:37 lr: 0.000111 loss: 2.9904 (2.9095) grad_norm: 2.3996 (2.4869) time: 0.6281 [2021-03-28 04:58:24 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 70/1251] eta: 0:13:21 lr: 0.000111 loss: 2.9904 (2.9030) grad_norm: 2.4842 (2.5171) time: 0.6263 [2021-03-28 04:58:30 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 80/1251] eta: 0:13:06 lr: 0.000111 loss: 2.9992 (2.9100) grad_norm: 2.5173 (2.5612) time: 0.6258 [2021-03-28 04:58:36 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 90/1251] eta: 0:12:53 lr: 0.000110 loss: 2.8717 (2.8989) grad_norm: 2.7714 (2.6503) time: 0.6244 [2021-03-28 04:58:43 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 100/1251] eta: 0:12:43 lr: 0.000110 loss: 2.8670 (2.9051) grad_norm: 2.4847 (2.6270) time: 0.6298 [2021-03-28 04:58:49 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 110/1251] eta: 0:12:33 lr: 0.000110 loss: 2.8631 (2.8797) grad_norm: 2.4679 (2.6280) time: 0.6331 [2021-03-28 04:58:55 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 120/1251] eta: 0:12:24 lr: 0.000110 loss: 2.8579 (2.8702) grad_norm: 2.6131 (2.6519) time: 0.6324 [2021-03-28 04:59:02 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 130/1251] eta: 0:12:15 lr: 0.000110 loss: 2.9445 (2.8667) grad_norm: 2.6786 (2.6631) time: 0.6322 [2021-03-28 04:59:08 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 140/1251] eta: 0:12:07 lr: 0.000110 loss: 3.0084 (2.8753) grad_norm: 2.6786 (2.6615) time: 0.6331 [2021-03-28 04:59:15 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 150/1251] eta: 0:11:59 lr: 0.000110 loss: 2.9538 (2.8751) grad_norm: 2.5300 (2.6554) time: 0.6367 [2021-03-28 04:59:21 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 160/1251] eta: 0:11:51 lr: 0.000110 loss: 3.0115 (2.8868) grad_norm: 2.5164 (2.7168) time: 0.6356 [2021-03-28 04:59:27 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 170/1251] eta: 0:11:43 lr: 0.000110 loss: 3.1409 (2.8884) grad_norm: 2.6390 (2.7298) time: 0.6305 [2021-03-28 04:59:33 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 180/1251] eta: 0:11:35 lr: 0.000110 loss: 3.0622 (2.8968) grad_norm: 2.8145 (2.7553) time: 0.6273 [2021-03-28 04:59:40 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 190/1251] eta: 0:11:28 lr: 0.000110 loss: 2.9977 (2.8997) grad_norm: 2.5119 (2.7428) time: 0.6343 [2021-03-28 04:59:46 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 200/1251] eta: 0:11:21 lr: 0.000110 loss: 2.8668 (2.8940) grad_norm: 2.3840 (2.7341) time: 0.6378 [2021-03-28 04:59:52 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 210/1251] eta: 0:11:13 lr: 0.000110 loss: 2.9850 (2.8968) grad_norm: 2.4079 (2.7240) time: 0.6290 [2021-03-28 04:59:59 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 220/1251] eta: 0:11:06 lr: 0.000110 loss: 3.0723 (2.9008) grad_norm: 2.3240 (2.7098) time: 0.6264 [2021-03-28 05:00:05 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 230/1251] eta: 0:10:58 lr: 0.000110 loss: 2.9749 (2.8926) grad_norm: 2.3516 (2.7082) time: 0.6264 [2021-03-28 05:00:11 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 240/1251] eta: 0:10:51 lr: 0.000110 loss: 2.9749 (2.8982) grad_norm: 2.6042 (2.7063) time: 0.6264 [2021-03-28 05:00:17 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 250/1251] eta: 0:10:44 lr: 0.000110 loss: 2.7925 (2.8939) grad_norm: 2.5982 (2.7053) time: 0.6260 [2021-03-28 05:00:24 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 260/1251] eta: 0:10:37 lr: 0.000110 loss: 2.7603 (2.8929) grad_norm: 2.5252 (2.7030) time: 0.6294 [2021-03-28 05:00:30 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 270/1251] eta: 0:10:30 lr: 0.000110 loss: 2.7573 (2.8795) grad_norm: 2.5450 (2.7055) time: 0.6298 [2021-03-28 05:00:36 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 280/1251] eta: 0:10:23 lr: 0.000110 loss: 2.7784 (2.8829) grad_norm: 2.6443 (2.7014) time: 0.6256 [2021-03-28 05:00:43 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 290/1251] eta: 0:10:16 lr: 0.000110 loss: 3.0857 (2.8876) grad_norm: 2.6443 (2.7007) time: 0.6245 [2021-03-28 05:00:49 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 300/1251] eta: 0:10:10 lr: 0.000110 loss: 3.0717 (2.8827) grad_norm: 2.6200 (2.7021) time: 0.6320 [2021-03-28 05:00:55 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 310/1251] eta: 0:10:03 lr: 0.000110 loss: 2.9140 (2.8830) grad_norm: 2.4932 (2.6957) time: 0.6299 [2021-03-28 05:01:01 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 320/1251] eta: 0:09:56 lr: 0.000110 loss: 3.0206 (2.8831) grad_norm: 2.3717 (2.6879) time: 0.6211 [2021-03-28 05:01:08 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 330/1251] eta: 0:09:49 lr: 0.000110 loss: 3.0608 (2.8854) grad_norm: 2.3696 (2.6900) time: 0.6248 [2021-03-28 05:01:14 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 340/1251] eta: 0:09:42 lr: 0.000110 loss: 2.9078 (2.8770) grad_norm: 2.4604 (2.6869) time: 0.6304 [2021-03-28 05:01:20 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 350/1251] eta: 0:09:36 lr: 0.000110 loss: 2.9078 (2.8822) grad_norm: 2.4604 (2.6861) time: 0.6349 [2021-03-28 05:01:27 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 360/1251] eta: 0:09:29 lr: 0.000110 loss: 2.9870 (2.8819) grad_norm: 2.5536 (2.6882) time: 0.6354 [2021-03-28 05:01:33 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 370/1251] eta: 0:09:22 lr: 0.000110 loss: 2.9870 (2.8806) grad_norm: 2.5707 (2.6912) time: 0.6276 [2021-03-28 05:01:39 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 380/1251] eta: 0:09:16 lr: 0.000110 loss: 2.9239 (2.8831) grad_norm: 2.6746 (2.6921) time: 0.6266 [2021-03-28 05:01:46 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 390/1251] eta: 0:09:09 lr: 0.000110 loss: 2.8844 (2.8838) grad_norm: 2.6781 (2.6942) time: 0.6354 [2021-03-28 05:01:52 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 400/1251] eta: 0:09:03 lr: 0.000110 loss: 2.8712 (2.8861) grad_norm: 2.6934 (2.6974) time: 0.6406 [2021-03-28 05:01:58 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 410/1251] eta: 0:08:57 lr: 0.000110 loss: 2.7183 (2.8746) grad_norm: 2.5912 (2.6954) time: 0.6356 [2021-03-28 05:02:05 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 420/1251] eta: 0:08:50 lr: 0.000110 loss: 2.5232 (2.8700) grad_norm: 2.5179 (2.6965) time: 0.6278 [2021-03-28 05:02:11 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 430/1251] eta: 0:08:43 lr: 0.000110 loss: 2.8497 (2.8714) grad_norm: 2.4590 (2.6920) time: 0.6297 [2021-03-28 05:02:17 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 440/1251] eta: 0:08:37 lr: 0.000110 loss: 2.8915 (2.8681) grad_norm: 2.5748 (2.6879) time: 0.6292 [2021-03-28 05:02:23 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 450/1251] eta: 0:08:30 lr: 0.000110 loss: 3.0610 (2.8711) grad_norm: 2.3601 (2.6819) time: 0.6264 [2021-03-28 05:02:30 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 460/1251] eta: 0:08:24 lr: 0.000110 loss: 2.8450 (2.8663) grad_norm: 2.4635 (2.6842) time: 0.6254 [2021-03-28 05:02:36 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 470/1251] eta: 0:08:17 lr: 0.000110 loss: 2.7140 (2.8672) grad_norm: 2.4144 (2.6768) time: 0.6295 [2021-03-28 05:02:42 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 480/1251] eta: 0:08:11 lr: 0.000110 loss: 3.0027 (2.8667) grad_norm: 2.5738 (2.6806) time: 0.6305 [2021-03-28 05:02:49 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 490/1251] eta: 0:08:04 lr: 0.000109 loss: 2.5997 (2.8564) grad_norm: 2.5738 (2.6805) time: 0.6287 [2021-03-28 05:02:55 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 500/1251] eta: 0:07:58 lr: 0.000109 loss: 2.5997 (2.8545) grad_norm: 2.3380 (2.6751) time: 0.6286 [2021-03-28 05:03:01 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 510/1251] eta: 0:07:51 lr: 0.000109 loss: 3.0062 (2.8576) grad_norm: 2.3380 (2.6819) time: 0.6262 [2021-03-28 05:03:07 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 520/1251] eta: 0:07:45 lr: 0.000109 loss: 2.9311 (2.8602) grad_norm: 2.6216 (2.6789) time: 0.6253 [2021-03-28 05:03:14 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 530/1251] eta: 0:07:38 lr: 0.000109 loss: 2.9274 (2.8614) grad_norm: 2.4916 (2.6777) time: 0.6253 [2021-03-28 05:03:20 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 540/1251] eta: 0:07:32 lr: 0.000109 loss: 2.9175 (2.8612) grad_norm: 2.5044 (2.6782) time: 0.6329 [2021-03-28 05:03:27 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 550/1251] eta: 0:07:26 lr: 0.000109 loss: 2.7266 (2.8588) grad_norm: 2.5666 (2.6769) time: 0.6430 [2021-03-28 05:03:33 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 560/1251] eta: 0:07:19 lr: 0.000109 loss: 2.7410 (2.8572) grad_norm: 2.4926 (2.6722) time: 0.6363 [2021-03-28 05:03:39 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 570/1251] eta: 0:07:13 lr: 0.000109 loss: 2.9492 (2.8572) grad_norm: 2.4268 (2.6721) time: 0.6269 [2021-03-28 05:03:45 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 580/1251] eta: 0:07:06 lr: 0.000109 loss: 2.8939 (2.8554) grad_norm: 2.8967 (2.6868) time: 0.6260 [2021-03-28 05:03:52 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 590/1251] eta: 0:07:00 lr: 0.000109 loss: 2.8939 (2.8585) grad_norm: 2.8172 (2.6863) time: 0.6238 [2021-03-28 05:03:58 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 600/1251] eta: 0:06:53 lr: 0.000109 loss: 2.8386 (2.8563) grad_norm: 2.4344 (2.6821) time: 0.6247 [2021-03-28 05:04:04 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 610/1251] eta: 0:06:47 lr: 0.000109 loss: 2.8386 (2.8568) grad_norm: 2.3822 (2.6810) time: 0.6257 [2021-03-28 05:04:10 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 620/1251] eta: 0:06:40 lr: 0.000109 loss: 2.9301 (2.8571) grad_norm: 2.3822 (2.6817) time: 0.6273 [2021-03-28 05:04:17 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 630/1251] eta: 0:06:34 lr: 0.000109 loss: 2.8737 (2.8592) grad_norm: 2.3265 (2.6773) time: 0.6331 [2021-03-28 05:04:23 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 640/1251] eta: 0:06:28 lr: 0.000109 loss: 2.8254 (2.8571) grad_norm: 2.4242 (2.6789) time: 0.6351 [2021-03-28 05:04:29 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 650/1251] eta: 0:06:21 lr: 0.000109 loss: 2.7356 (2.8579) grad_norm: 2.6024 (2.6780) time: 0.6332 [2021-03-28 05:04:36 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 660/1251] eta: 0:06:15 lr: 0.000109 loss: 2.7356 (2.8549) grad_norm: 2.7438 (2.6847) time: 0.6285 [2021-03-28 05:04:42 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 670/1251] eta: 0:06:08 lr: 0.000109 loss: 2.8232 (2.8562) grad_norm: 2.7153 (2.6828) time: 0.6277 [2021-03-28 05:04:48 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 680/1251] eta: 0:06:02 lr: 0.000109 loss: 2.9058 (2.8529) grad_norm: 2.5265 (2.6817) time: 0.6306 [2021-03-28 05:04:55 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 690/1251] eta: 0:05:56 lr: 0.000109 loss: 2.7684 (2.8519) grad_norm: 2.5265 (2.6825) time: 0.6285 [2021-03-28 05:05:01 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 700/1251] eta: 0:05:49 lr: 0.000109 loss: 3.0049 (2.8523) grad_norm: 2.6031 (2.6836) time: 0.6340 [2021-03-28 05:05:07 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 710/1251] eta: 0:05:43 lr: 0.000109 loss: 3.0049 (2.8546) grad_norm: 2.6031 (2.6861) time: 0.6375 [2021-03-28 05:05:14 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 720/1251] eta: 0:05:37 lr: 0.000109 loss: 2.8547 (2.8541) grad_norm: 2.5618 (2.6858) time: 0.6374 [2021-03-28 05:05:20 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 730/1251] eta: 0:05:30 lr: 0.000109 loss: 2.9779 (2.8565) grad_norm: 2.4698 (nan) time: 0.6303 [2021-03-28 05:05:26 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 740/1251] eta: 0:05:24 lr: 0.000109 loss: 2.7759 (2.8510) grad_norm: 2.4790 (nan) time: 0.6398 [2021-03-28 05:05:33 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 750/1251] eta: 0:05:18 lr: 0.000109 loss: 2.7652 (2.8527) grad_norm: 2.6085 (nan) time: 0.6479 [2021-03-28 05:05:39 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 760/1251] eta: 0:05:11 lr: 0.000109 loss: 2.8190 (2.8518) grad_norm: 2.6032 (nan) time: 0.6335 [2021-03-28 05:05:45 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 770/1251] eta: 0:05:05 lr: 0.000109 loss: 2.8654 (2.8531) grad_norm: 2.4204 (nan) time: 0.6264 [2021-03-28 05:05:52 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 780/1251] eta: 0:04:59 lr: 0.000109 loss: 3.0931 (2.8560) grad_norm: 2.4204 (nan) time: 0.6290 [2021-03-28 05:05:58 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 790/1251] eta: 0:04:52 lr: 0.000109 loss: 3.1250 (2.8593) grad_norm: 2.5104 (nan) time: 0.6332 [2021-03-28 05:06:04 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 800/1251] eta: 0:04:46 lr: 0.000109 loss: 2.9795 (2.8574) grad_norm: 2.6748 (nan) time: 0.6333 [2021-03-28 05:06:11 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 810/1251] eta: 0:04:39 lr: 0.000109 loss: 2.6214 (2.8556) grad_norm: 2.7052 (nan) time: 0.6281 [2021-03-28 05:06:17 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 820/1251] eta: 0:04:33 lr: 0.000109 loss: 2.6214 (2.8540) grad_norm: 2.6334 (nan) time: 0.6223 [2021-03-28 05:06:23 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 830/1251] eta: 0:04:27 lr: 0.000109 loss: 2.5311 (2.8524) grad_norm: 2.6236 (nan) time: 0.6257 [2021-03-28 05:06:29 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 840/1251] eta: 0:04:20 lr: 0.000109 loss: 2.9674 (2.8547) grad_norm: 2.5915 (nan) time: 0.6253 [2021-03-28 05:06:36 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 850/1251] eta: 0:04:14 lr: 0.000109 loss: 2.9852 (2.8553) grad_norm: 2.7633 (nan) time: 0.6244 [2021-03-28 05:06:42 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 860/1251] eta: 0:04:07 lr: 0.000109 loss: 2.9336 (2.8552) grad_norm: 2.5358 (nan) time: 0.6273 [2021-03-28 05:06:48 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 870/1251] eta: 0:04:01 lr: 0.000109 loss: 2.7693 (2.8544) grad_norm: 2.3391 (nan) time: 0.6258 [2021-03-28 05:06:54 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 880/1251] eta: 0:03:55 lr: 0.000109 loss: 2.6926 (2.8517) grad_norm: 2.4400 (nan) time: 0.6266 [2021-03-28 05:07:01 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 890/1251] eta: 0:03:48 lr: 0.000108 loss: 2.7248 (2.8505) grad_norm: 2.6355 (nan) time: 0.6342 [2021-03-28 05:07:07 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 900/1251] eta: 0:03:42 lr: 0.000108 loss: 2.9785 (2.8535) grad_norm: 2.6008 (nan) time: 0.6312 [2021-03-28 05:07:13 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 910/1251] eta: 0:03:36 lr: 0.000108 loss: 3.1144 (2.8547) grad_norm: 2.6723 (nan) time: 0.6303 [2021-03-28 05:07:20 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 920/1251] eta: 0:03:29 lr: 0.000108 loss: 2.9938 (2.8552) grad_norm: 2.7242 (nan) time: 0.6294 [2021-03-28 05:07:26 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 930/1251] eta: 0:03:23 lr: 0.000108 loss: 2.8308 (2.8545) grad_norm: 2.4992 (nan) time: 0.6263 [2021-03-28 05:07:32 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 940/1251] eta: 0:03:17 lr: 0.000108 loss: 2.8792 (2.8554) grad_norm: 2.3978 (nan) time: 0.6338 [2021-03-28 05:07:39 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 950/1251] eta: 0:03:10 lr: 0.000108 loss: 3.0072 (2.8565) grad_norm: 2.3851 (nan) time: 0.6357 [2021-03-28 05:07:45 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 960/1251] eta: 0:03:04 lr: 0.000108 loss: 3.0188 (2.8582) grad_norm: 2.3008 (nan) time: 0.6347 [2021-03-28 05:07:51 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 970/1251] eta: 0:02:58 lr: 0.000108 loss: 3.0180 (2.8565) grad_norm: 2.4200 (nan) time: 0.6362 [2021-03-28 05:07:58 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 980/1251] eta: 0:02:51 lr: 0.000108 loss: 3.0354 (2.8584) grad_norm: 2.5836 (nan) time: 0.6303 [2021-03-28 05:08:04 swin_base_patch4_window7_224] INFO: Epoch: [238] [ 990/1251] eta: 0:02:45 lr: 0.000108 loss: 3.0672 (2.8593) grad_norm: 2.5903 (nan) time: 0.6305 [2021-03-28 05:08:10 swin_base_patch4_window7_224] INFO: Epoch: [238] [1000/1251] eta: 0:02:39 lr: 0.000108 loss: 2.9560 (2.8576) grad_norm: 2.6079 (nan) time: 0.6365 [2021-03-28 05:08:17 swin_base_patch4_window7_224] INFO: Epoch: [238] [1010/1251] eta: 0:02:32 lr: 0.000108 loss: 2.9116 (2.8579) grad_norm: 2.6188 (nan) time: 0.6330 [2021-03-28 05:08:23 swin_base_patch4_window7_224] INFO: Epoch: [238] [1020/1251] eta: 0:02:26 lr: 0.000108 loss: 2.9116 (2.8602) grad_norm: 2.4698 (nan) time: 0.6286 [2021-03-28 05:08:29 swin_base_patch4_window7_224] INFO: Epoch: [238] [1030/1251] eta: 0:02:20 lr: 0.000108 loss: 2.9472 (2.8600) grad_norm: 2.3705 (nan) time: 0.6258 [2021-03-28 05:08:36 swin_base_patch4_window7_224] INFO: Epoch: [238] [1040/1251] eta: 0:02:13 lr: 0.000108 loss: 2.8632 (2.8597) grad_norm: 2.3916 (nan) time: 0.6289 [2021-03-28 05:08:42 swin_base_patch4_window7_224] INFO: Epoch: [238] [1050/1251] eta: 0:02:07 lr: 0.000108 loss: 2.9313 (2.8603) grad_norm: 2.4015 (nan) time: 0.6274 [2021-03-28 05:08:48 swin_base_patch4_window7_224] INFO: Epoch: [238] [1060/1251] eta: 0:02:00 lr: 0.000108 loss: 2.8521 (2.8584) grad_norm: 2.4088 (nan) time: 0.6227 [2021-03-28 05:08:54 swin_base_patch4_window7_224] INFO: Epoch: [238] [1070/1251] eta: 0:01:54 lr: 0.000108 loss: 2.8544 (2.8577) grad_norm: 2.3939 (nan) time: 0.6245 [2021-03-28 05:09:01 swin_base_patch4_window7_224] INFO: Epoch: [238] [1080/1251] eta: 0:01:48 lr: 0.000108 loss: 3.0297 (2.8601) grad_norm: 2.4762 (nan) time: 0.6306 [2021-03-28 05:09:07 swin_base_patch4_window7_224] INFO: Epoch: [238] [1090/1251] eta: 0:01:41 lr: 0.000108 loss: 2.6942 (2.8577) grad_norm: 2.4762 (nan) time: 0.6350 [2021-03-28 05:09:13 swin_base_patch4_window7_224] INFO: Epoch: [238] [1100/1251] eta: 0:01:35 lr: 0.000108 loss: 2.6942 (2.8581) grad_norm: 2.4169 (nan) time: 0.6335 [2021-03-28 05:09:20 swin_base_patch4_window7_224] INFO: Epoch: [238] [1110/1251] eta: 0:01:29 lr: 0.000108 loss: 2.7714 (2.8565) grad_norm: 2.6729 (nan) time: 0.6350 [2021-03-28 05:09:26 swin_base_patch4_window7_224] INFO: Epoch: [238] [1120/1251] eta: 0:01:22 lr: 0.000108 loss: 2.7946 (2.8568) grad_norm: 2.5284 (nan) time: 0.6363 [2021-03-28 05:09:32 swin_base_patch4_window7_224] INFO: Epoch: [238] [1130/1251] eta: 0:01:16 lr: 0.000108 loss: 2.9942 (2.8568) grad_norm: 2.4514 (nan) time: 0.6371 [2021-03-28 05:09:39 swin_base_patch4_window7_224] INFO: Epoch: [238] [1140/1251] eta: 0:01:10 lr: 0.000108 loss: 3.0061 (2.8558) grad_norm: 2.5934 (nan) time: 0.6329 [2021-03-28 05:09:45 swin_base_patch4_window7_224] INFO: Epoch: [238] [1150/1251] eta: 0:01:03 lr: 0.000108 loss: 2.9448 (2.8564) grad_norm: 2.5477 (nan) time: 0.6351 [2021-03-28 05:09:51 swin_base_patch4_window7_224] INFO: Epoch: [238] [1160/1251] eta: 0:00:57 lr: 0.000108 loss: 3.0374 (2.8580) grad_norm: 2.3462 (nan) time: 0.6366 [2021-03-28 05:09:58 swin_base_patch4_window7_224] INFO: Epoch: [238] [1170/1251] eta: 0:00:51 lr: 0.000108 loss: 2.8855 (2.8569) grad_norm: 2.5195 (nan) time: 0.6333 [2021-03-28 05:10:04 swin_base_patch4_window7_224] INFO: Epoch: [238] [1180/1251] eta: 0:00:44 lr: 0.000108 loss: 2.7902 (2.8557) grad_norm: 2.6153 (nan) time: 0.6327 [2021-03-28 05:10:10 swin_base_patch4_window7_224] INFO: Epoch: [238] [1190/1251] eta: 0:00:38 lr: 0.000108 loss: 2.9217 (2.8569) grad_norm: 2.6309 (nan) time: 0.6328 [2021-03-28 05:10:17 swin_base_patch4_window7_224] INFO: Epoch: [238] [1200/1251] eta: 0:00:32 lr: 0.000108 loss: 2.9453 (2.8569) grad_norm: 2.4755 (nan) time: 0.6306 [2021-03-28 05:10:23 swin_base_patch4_window7_224] INFO: Epoch: [238] [1210/1251] eta: 0:00:25 lr: 0.000108 loss: 2.8727 (2.8564) grad_norm: 2.4481 (nan) time: 0.6255 [2021-03-28 05:10:29 swin_base_patch4_window7_224] INFO: Epoch: [238] [1220/1251] eta: 0:00:19 lr: 0.000108 loss: 2.7507 (2.8549) grad_norm: 2.6887 (nan) time: 0.6285 [2021-03-28 05:10:36 swin_base_patch4_window7_224] INFO: Epoch: [238] [1230/1251] eta: 0:00:13 lr: 0.000108 loss: 2.7471 (2.8534) grad_norm: 2.7233 (nan) time: 0.6345 [2021-03-28 05:10:42 swin_base_patch4_window7_224] INFO: Epoch: [238] [1240/1251] eta: 0:00:06 lr: 0.000108 loss: 2.9409 (2.8541) grad_norm: 2.7258 (nan) time: 0.6295 [2021-03-28 05:10:48 swin_base_patch4_window7_224] INFO: Epoch: [238] [1250/1251] eta: 0:00:00 lr: 0.000108 loss: 3.0395 (2.8555) grad_norm: 2.5021 (nan) time: 0.6172 [2021-03-28 05:11:01 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:23 loss: 0.7515 (0.7515) acc1: 81.2500 (81.2500) acc5: 98.4375 (98.4375) [2021-03-28 05:11:03 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7515 (0.7697) acc1: 82.8125 (82.9545) acc5: 95.3125 (95.7386) [2021-03-28 05:11:05 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8248 (0.8126) acc1: 82.8125 (81.7708) acc5: 95.3125 (95.2381) [2021-03-28 05:11:08 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8080 (0.8069) acc1: 81.2500 (81.7036) acc5: 96.8750 (95.8165) [2021-03-28 05:11:10 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7131 (0.7713) acc1: 82.8125 (82.2790) acc5: 98.4375 (96.4939) [2021-03-28 05:11:11 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6606 (0.7728) acc1: 82.8125 (82.3040) acc5: 98.4375 (96.4480) [2021-03-28 05:11:26 swin_base_patch4_window7_224] INFO: * Acc@1 82.604 Acc@5 96.232 loss 0.762 [2021-03-28 05:11:26 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.6% [2021-03-28 05:11:26 swin_base_patch4_window7_224] INFO: Max accuracy: 82.60% [2021-03-28 05:11:30 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 0/1251] eta: 1:28:39 lr: 0.000108 loss: 2.9532 (2.9532) grad_norm: 2.5992 (2.5992) time: 4.2522 [2021-03-28 05:11:37 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 10/1251] eta: 0:19:59 lr: 0.000108 loss: 2.7629 (2.7966) grad_norm: 2.4938 (2.5253) time: 0.9662 [2021-03-28 05:11:43 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 20/1251] eta: 0:16:35 lr: 0.000108 loss: 2.9058 (2.7603) grad_norm: 2.4976 (2.6183) time: 0.6366 [2021-03-28 05:11:49 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 30/1251] eta: 0:15:18 lr: 0.000108 loss: 2.8343 (2.6825) grad_norm: 2.5334 (2.6528) time: 0.6347 [2021-03-28 05:11:56 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 40/1251] eta: 0:14:33 lr: 0.000108 loss: 2.7505 (2.7485) grad_norm: 2.5557 (2.6910) time: 0.6288 [2021-03-28 05:12:02 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 50/1251] eta: 0:14:03 lr: 0.000107 loss: 3.0649 (2.7988) grad_norm: 2.6106 (2.6776) time: 0.6252 [2021-03-28 05:12:08 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 60/1251] eta: 0:13:42 lr: 0.000107 loss: 3.0509 (2.7973) grad_norm: 2.5798 (2.6979) time: 0.6274 [2021-03-28 05:12:14 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 70/1251] eta: 0:13:25 lr: 0.000107 loss: 2.9085 (2.7796) grad_norm: 2.4999 (2.6646) time: 0.6290 [2021-03-28 05:12:21 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 80/1251] eta: 0:13:11 lr: 0.000107 loss: 2.6494 (2.7626) grad_norm: 2.3844 (2.6704) time: 0.6309 [2021-03-28 05:12:27 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 90/1251] eta: 0:12:58 lr: 0.000107 loss: 2.7319 (2.7666) grad_norm: 2.5390 (2.7457) time: 0.6294 [2021-03-28 05:12:33 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 100/1251] eta: 0:12:46 lr: 0.000107 loss: 2.8483 (2.7728) grad_norm: 2.4462 (2.7170) time: 0.6286 [2021-03-28 05:12:40 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 110/1251] eta: 0:12:37 lr: 0.000107 loss: 2.8483 (2.7630) grad_norm: 2.3698 (2.7170) time: 0.6334 [2021-03-28 05:12:46 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 120/1251] eta: 0:12:26 lr: 0.000107 loss: 2.8887 (2.7701) grad_norm: 2.5398 (2.7089) time: 0.6295 [2021-03-28 05:12:52 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 130/1251] eta: 0:12:17 lr: 0.000107 loss: 3.0248 (2.7882) grad_norm: 2.5571 (2.7015) time: 0.6268 [2021-03-28 05:12:59 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 140/1251] eta: 0:12:08 lr: 0.000107 loss: 2.9963 (2.7940) grad_norm: 2.5801 (2.7060) time: 0.6276 [2021-03-28 05:13:05 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 150/1251] eta: 0:12:00 lr: 0.000107 loss: 3.0363 (2.8086) grad_norm: 2.5680 (2.7012) time: 0.6296 [2021-03-28 05:13:11 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 160/1251] eta: 0:11:52 lr: 0.000107 loss: 2.9765 (2.8113) grad_norm: 2.4550 (2.7116) time: 0.6316 [2021-03-28 05:13:17 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 170/1251] eta: 0:11:44 lr: 0.000107 loss: 2.9411 (2.8211) grad_norm: 2.3527 (2.6963) time: 0.6288 [2021-03-28 05:13:24 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 180/1251] eta: 0:11:36 lr: 0.000107 loss: 2.9411 (2.8211) grad_norm: 2.4053 (2.7125) time: 0.6332 [2021-03-28 05:13:30 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 190/1251] eta: 0:11:29 lr: 0.000107 loss: 2.8868 (2.8257) grad_norm: 2.4783 (2.6989) time: 0.6381 [2021-03-28 05:13:37 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 200/1251] eta: 0:11:22 lr: 0.000107 loss: 3.0543 (2.8339) grad_norm: 2.4820 (2.6958) time: 0.6381 [2021-03-28 05:13:43 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 210/1251] eta: 0:11:15 lr: 0.000107 loss: 2.9097 (2.8339) grad_norm: 2.5361 (2.6933) time: 0.6360 [2021-03-28 05:13:49 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 220/1251] eta: 0:11:07 lr: 0.000107 loss: 2.8998 (2.8400) grad_norm: 2.4303 (2.6853) time: 0.6323 [2021-03-28 05:13:55 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 230/1251] eta: 0:11:00 lr: 0.000107 loss: 2.8998 (2.8387) grad_norm: 2.4809 (2.6820) time: 0.6280 [2021-03-28 05:14:02 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 240/1251] eta: 0:10:53 lr: 0.000107 loss: 2.9653 (2.8475) grad_norm: 2.4809 (2.6725) time: 0.6296 [2021-03-28 05:14:08 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 250/1251] eta: 0:10:45 lr: 0.000107 loss: 2.9671 (2.8482) grad_norm: 2.3573 (2.6682) time: 0.6284 [2021-03-28 05:14:14 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 260/1251] eta: 0:10:38 lr: 0.000107 loss: 2.9163 (2.8409) grad_norm: 2.3573 (2.6577) time: 0.6268 [2021-03-28 05:14:21 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 270/1251] eta: 0:10:32 lr: 0.000107 loss: 2.6731 (2.8360) grad_norm: 2.4307 (2.6524) time: 0.6325 [2021-03-28 05:14:27 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 280/1251] eta: 0:10:25 lr: 0.000107 loss: 2.8194 (2.8435) grad_norm: 2.3984 (2.6412) time: 0.6363 [2021-03-28 05:14:33 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 290/1251] eta: 0:10:18 lr: 0.000107 loss: 3.0644 (2.8458) grad_norm: 2.4096 (2.6402) time: 0.6330 [2021-03-28 05:14:40 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 300/1251] eta: 0:10:12 lr: 0.000107 loss: 2.8487 (2.8456) grad_norm: 2.4096 (2.6323) time: 0.6387 [2021-03-28 05:14:46 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 310/1251] eta: 0:10:05 lr: 0.000107 loss: 2.8604 (2.8461) grad_norm: 2.3966 (2.6342) time: 0.6416 [2021-03-28 05:14:53 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 320/1251] eta: 0:09:58 lr: 0.000107 loss: 2.8779 (2.8420) grad_norm: 2.6301 (2.6339) time: 0.6376 [2021-03-28 05:14:59 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 330/1251] eta: 0:09:52 lr: 0.000107 loss: 2.8779 (2.8468) grad_norm: 2.4583 (2.6289) time: 0.6382 [2021-03-28 05:15:05 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 340/1251] eta: 0:09:45 lr: 0.000107 loss: 3.0991 (2.8484) grad_norm: 2.3549 (2.6268) time: 0.6345 [2021-03-28 05:15:12 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 350/1251] eta: 0:09:38 lr: 0.000107 loss: 2.9910 (2.8508) grad_norm: 2.3399 (2.6196) time: 0.6276 [2021-03-28 05:15:18 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 360/1251] eta: 0:09:31 lr: 0.000107 loss: 3.0009 (2.8511) grad_norm: 2.4422 (2.6226) time: 0.6262 [2021-03-28 05:15:24 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 370/1251] eta: 0:09:25 lr: 0.000107 loss: 2.9281 (2.8465) grad_norm: 2.5423 (2.6235) time: 0.6282 [2021-03-28 05:15:30 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 380/1251] eta: 0:09:18 lr: 0.000107 loss: 2.9281 (2.8483) grad_norm: 2.4965 (2.6239) time: 0.6301 [2021-03-28 05:15:37 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 390/1251] eta: 0:09:11 lr: 0.000107 loss: 2.9517 (2.8483) grad_norm: 2.4498 (2.6306) time: 0.6337 [2021-03-28 05:15:43 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 400/1251] eta: 0:09:05 lr: 0.000107 loss: 3.0849 (2.8578) grad_norm: 2.5465 (2.6317) time: 0.6319 [2021-03-28 05:15:49 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 410/1251] eta: 0:08:58 lr: 0.000107 loss: 3.0757 (2.8605) grad_norm: 2.5465 (2.6333) time: 0.6268 [2021-03-28 05:15:56 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 420/1251] eta: 0:08:51 lr: 0.000107 loss: 2.8152 (2.8558) grad_norm: 2.4872 (2.6301) time: 0.6248 [2021-03-28 05:16:02 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 430/1251] eta: 0:08:45 lr: 0.000107 loss: 2.8152 (2.8547) grad_norm: 2.3880 (2.6264) time: 0.6272 [2021-03-28 05:16:08 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 440/1251] eta: 0:08:38 lr: 0.000107 loss: 3.1201 (2.8563) grad_norm: 2.3892 (2.6354) time: 0.6266 [2021-03-28 05:16:14 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 450/1251] eta: 0:08:31 lr: 0.000106 loss: 2.9510 (2.8546) grad_norm: 2.7849 (2.6397) time: 0.6250 [2021-03-28 05:16:21 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 460/1251] eta: 0:08:25 lr: 0.000106 loss: 3.0198 (2.8623) grad_norm: 2.7156 (2.6390) time: 0.6253 [2021-03-28 05:16:27 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 470/1251] eta: 0:08:18 lr: 0.000106 loss: 3.0049 (2.8650) grad_norm: 2.3928 (2.6379) time: 0.6286 [2021-03-28 05:16:33 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 480/1251] eta: 0:08:12 lr: 0.000106 loss: 2.6514 (2.8540) grad_norm: 2.3837 (2.6382) time: 0.6345 [2021-03-28 05:16:40 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 490/1251] eta: 0:08:05 lr: 0.000106 loss: 2.5772 (2.8524) grad_norm: 2.5922 (2.6403) time: 0.6342 [2021-03-28 05:16:46 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 500/1251] eta: 0:07:59 lr: 0.000106 loss: 2.9026 (2.8552) grad_norm: 2.6176 (2.6374) time: 0.6287 [2021-03-28 05:16:52 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 510/1251] eta: 0:07:52 lr: 0.000106 loss: 2.9574 (2.8551) grad_norm: 2.5419 (2.6377) time: 0.6293 [2021-03-28 05:16:59 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 520/1251] eta: 0:07:46 lr: 0.000106 loss: 2.8893 (2.8558) grad_norm: 2.5419 (2.6418) time: 0.6298 [2021-03-28 05:17:05 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 530/1251] eta: 0:07:39 lr: 0.000106 loss: 2.8670 (2.8542) grad_norm: 2.5545 (2.6546) time: 0.6302 [2021-03-28 05:17:11 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 540/1251] eta: 0:07:33 lr: 0.000106 loss: 2.6383 (2.8512) grad_norm: 2.3862 (2.6506) time: 0.6316 [2021-03-28 05:17:17 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 550/1251] eta: 0:07:26 lr: 0.000106 loss: 2.7847 (2.8520) grad_norm: 2.3862 (2.6484) time: 0.6306 [2021-03-28 05:17:24 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 560/1251] eta: 0:07:20 lr: 0.000106 loss: 2.9676 (2.8564) grad_norm: 2.4928 (2.6515) time: 0.6239 [2021-03-28 05:17:30 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 570/1251] eta: 0:07:13 lr: 0.000106 loss: 3.0164 (2.8585) grad_norm: 2.6168 (2.6551) time: 0.6272 [2021-03-28 05:17:36 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 580/1251] eta: 0:07:07 lr: 0.000106 loss: 2.9488 (2.8555) grad_norm: 2.4848 (2.6517) time: 0.6346 [2021-03-28 05:17:43 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 590/1251] eta: 0:07:01 lr: 0.000106 loss: 2.7906 (2.8540) grad_norm: 2.4397 (2.6496) time: 0.6332 [2021-03-28 05:17:49 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 600/1251] eta: 0:06:54 lr: 0.000106 loss: 2.9168 (2.8591) grad_norm: 2.4373 (2.6476) time: 0.6308 [2021-03-28 05:17:55 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 610/1251] eta: 0:06:48 lr: 0.000106 loss: 3.1050 (2.8609) grad_norm: 2.3740 (2.6442) time: 0.6247 [2021-03-28 05:18:02 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 620/1251] eta: 0:06:41 lr: 0.000106 loss: 3.1050 (2.8637) grad_norm: 2.4475 (2.6515) time: 0.6310 [2021-03-28 05:18:08 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 630/1251] eta: 0:06:35 lr: 0.000106 loss: 2.8944 (2.8580) grad_norm: 2.5408 (2.6492) time: 0.6340 [2021-03-28 05:18:14 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 640/1251] eta: 0:06:28 lr: 0.000106 loss: 2.7026 (2.8572) grad_norm: 2.2988 (2.6439) time: 0.6286 [2021-03-28 05:18:20 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 650/1251] eta: 0:06:22 lr: 0.000106 loss: 3.0320 (2.8584) grad_norm: 2.3598 (2.6454) time: 0.6305 [2021-03-28 05:18:27 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 660/1251] eta: 0:06:16 lr: 0.000106 loss: 3.0873 (2.8604) grad_norm: 2.5760 (2.6443) time: 0.6292 [2021-03-28 05:18:33 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 670/1251] eta: 0:06:09 lr: 0.000106 loss: 2.9746 (2.8566) grad_norm: 2.4773 (2.6426) time: 0.6277 [2021-03-28 05:18:39 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 680/1251] eta: 0:06:03 lr: 0.000106 loss: 2.7009 (2.8563) grad_norm: 2.4381 (2.6400) time: 0.6275 [2021-03-28 05:18:46 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 690/1251] eta: 0:05:56 lr: 0.000106 loss: 2.8244 (2.8539) grad_norm: 2.5229 (2.6398) time: 0.6250 [2021-03-28 05:18:52 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 700/1251] eta: 0:05:50 lr: 0.000106 loss: 2.8830 (2.8548) grad_norm: 2.5889 (2.6386) time: 0.6275 [2021-03-28 05:18:58 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 710/1251] eta: 0:05:43 lr: 0.000106 loss: 2.9130 (2.8532) grad_norm: 2.5889 (2.6517) time: 0.6257 [2021-03-28 05:19:04 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 720/1251] eta: 0:05:37 lr: 0.000106 loss: 2.8196 (2.8545) grad_norm: 2.4740 (2.6575) time: 0.6272 [2021-03-28 05:19:11 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 730/1251] eta: 0:05:31 lr: 0.000106 loss: 2.8556 (2.8541) grad_norm: 2.4754 (2.6562) time: 0.6385 [2021-03-28 05:19:17 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 740/1251] eta: 0:05:24 lr: 0.000106 loss: 2.8170 (2.8535) grad_norm: 2.4754 (2.6566) time: 0.6404 [2021-03-28 05:19:24 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 750/1251] eta: 0:05:18 lr: 0.000106 loss: 2.8258 (2.8564) grad_norm: 2.4053 (2.6571) time: 0.6381 [2021-03-28 05:19:30 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 760/1251] eta: 0:05:12 lr: 0.000106 loss: 3.0739 (2.8578) grad_norm: 2.4088 (2.6568) time: 0.6339 [2021-03-28 05:19:36 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 770/1251] eta: 0:05:05 lr: 0.000106 loss: 3.0330 (2.8594) grad_norm: 2.5401 (2.6566) time: 0.6310 [2021-03-28 05:19:42 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 780/1251] eta: 0:04:59 lr: 0.000106 loss: 2.9521 (2.8575) grad_norm: 2.5401 (2.6560) time: 0.6310 [2021-03-28 05:19:49 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 790/1251] eta: 0:04:52 lr: 0.000106 loss: 2.8232 (2.8585) grad_norm: 2.3998 (2.6517) time: 0.6288 [2021-03-28 05:19:55 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 800/1251] eta: 0:04:46 lr: 0.000106 loss: 2.6633 (2.8536) grad_norm: 2.3404 (2.6522) time: 0.6280 [2021-03-28 05:20:01 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 810/1251] eta: 0:04:40 lr: 0.000106 loss: 2.5979 (2.8532) grad_norm: 2.4625 (2.6508) time: 0.6252 [2021-03-28 05:20:08 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 820/1251] eta: 0:04:33 lr: 0.000106 loss: 2.8676 (2.8502) grad_norm: 2.5528 (2.6519) time: 0.6263 [2021-03-28 05:20:14 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 830/1251] eta: 0:04:27 lr: 0.000106 loss: 2.9449 (2.8510) grad_norm: 2.4670 (2.6497) time: 0.6313 [2021-03-28 05:20:20 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 840/1251] eta: 0:04:20 lr: 0.000106 loss: 3.0161 (2.8520) grad_norm: 2.6514 (2.6516) time: 0.6263 [2021-03-28 05:20:26 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 850/1251] eta: 0:04:14 lr: 0.000106 loss: 2.9926 (2.8522) grad_norm: 2.7218 (2.6527) time: 0.6236 [2021-03-28 05:20:33 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 860/1251] eta: 0:04:08 lr: 0.000105 loss: 2.8219 (2.8498) grad_norm: 2.4699 (2.6497) time: 0.6266 [2021-03-28 05:20:39 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 870/1251] eta: 0:04:01 lr: 0.000105 loss: 2.8197 (2.8484) grad_norm: 2.4619 (2.6508) time: 0.6238 [2021-03-28 05:20:45 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 880/1251] eta: 0:03:55 lr: 0.000105 loss: 2.8178 (2.8487) grad_norm: 2.4835 (2.6525) time: 0.6268 [2021-03-28 05:20:51 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 890/1251] eta: 0:03:49 lr: 0.000105 loss: 2.9432 (2.8485) grad_norm: 2.4592 (2.6519) time: 0.6297 [2021-03-28 05:20:58 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 900/1251] eta: 0:03:42 lr: 0.000105 loss: 2.8193 (2.8466) grad_norm: 2.4172 (2.6542) time: 0.6257 [2021-03-28 05:21:04 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 910/1251] eta: 0:03:36 lr: 0.000105 loss: 2.7683 (2.8465) grad_norm: 2.4172 (2.6511) time: 0.6266 [2021-03-28 05:21:10 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 920/1251] eta: 0:03:29 lr: 0.000105 loss: 2.7683 (2.8451) grad_norm: 2.2804 (2.6509) time: 0.6274 [2021-03-28 05:21:17 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 930/1251] eta: 0:03:23 lr: 0.000105 loss: 2.6580 (2.8426) grad_norm: 2.7463 (2.6524) time: 0.6303 [2021-03-28 05:21:23 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 940/1251] eta: 0:03:17 lr: 0.000105 loss: 2.7294 (2.8442) grad_norm: 2.5777 (2.6509) time: 0.6330 [2021-03-28 05:21:29 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 950/1251] eta: 0:03:10 lr: 0.000105 loss: 2.8755 (2.8432) grad_norm: 2.4896 (2.6506) time: 0.6281 [2021-03-28 05:21:35 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 960/1251] eta: 0:03:04 lr: 0.000105 loss: 2.7242 (2.8416) grad_norm: 2.5846 (2.6502) time: 0.6231 [2021-03-28 05:21:42 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 970/1251] eta: 0:02:58 lr: 0.000105 loss: 2.7713 (2.8410) grad_norm: 2.6091 (2.6488) time: 0.6281 [2021-03-28 05:21:48 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 980/1251] eta: 0:02:51 lr: 0.000105 loss: 2.7547 (2.8380) grad_norm: 2.4419 (2.6492) time: 0.6309 [2021-03-28 05:21:54 swin_base_patch4_window7_224] INFO: Epoch: [239] [ 990/1251] eta: 0:02:45 lr: 0.000105 loss: 2.3972 (2.8339) grad_norm: 2.5203 (2.6484) time: 0.6267 [2021-03-28 05:22:01 swin_base_patch4_window7_224] INFO: Epoch: [239] [1000/1251] eta: 0:02:39 lr: 0.000105 loss: 2.6837 (2.8342) grad_norm: 2.5665 (2.6496) time: 0.6285 [2021-03-28 05:22:07 swin_base_patch4_window7_224] INFO: Epoch: [239] [1010/1251] eta: 0:02:32 lr: 0.000105 loss: 2.9206 (2.8355) grad_norm: 2.5957 (2.6542) time: 0.6293 [2021-03-28 05:22:13 swin_base_patch4_window7_224] INFO: Epoch: [239] [1020/1251] eta: 0:02:26 lr: 0.000105 loss: 2.9533 (2.8344) grad_norm: 2.6446 (2.6561) time: 0.6311 [2021-03-28 05:22:20 swin_base_patch4_window7_224] INFO: Epoch: [239] [1030/1251] eta: 0:02:20 lr: 0.000105 loss: 2.8111 (2.8325) grad_norm: 2.6446 (2.6595) time: 0.6325 [2021-03-28 05:22:26 swin_base_patch4_window7_224] INFO: Epoch: [239] [1040/1251] eta: 0:02:13 lr: 0.000105 loss: 2.8499 (2.8338) grad_norm: 2.7221 (2.6597) time: 0.6290 [2021-03-28 05:22:32 swin_base_patch4_window7_224] INFO: Epoch: [239] [1050/1251] eta: 0:02:07 lr: 0.000105 loss: 2.9206 (2.8327) grad_norm: 2.6477 (2.6582) time: 0.6308 [2021-03-28 05:22:38 swin_base_patch4_window7_224] INFO: Epoch: [239] [1060/1251] eta: 0:02:01 lr: 0.000105 loss: 2.9206 (2.8329) grad_norm: 2.6584 (2.6609) time: 0.6332 [2021-03-28 05:22:45 swin_base_patch4_window7_224] INFO: Epoch: [239] [1070/1251] eta: 0:01:54 lr: 0.000105 loss: 2.9401 (2.8340) grad_norm: 2.5123 (2.6589) time: 0.6312 [2021-03-28 05:22:51 swin_base_patch4_window7_224] INFO: Epoch: [239] [1080/1251] eta: 0:01:48 lr: 0.000105 loss: 3.0622 (2.8343) grad_norm: 2.4845 (2.6637) time: 0.6305 [2021-03-28 05:22:57 swin_base_patch4_window7_224] INFO: Epoch: [239] [1090/1251] eta: 0:01:41 lr: 0.000105 loss: 2.8921 (2.8332) grad_norm: 2.6201 (2.6633) time: 0.6302 [2021-03-28 05:23:04 swin_base_patch4_window7_224] INFO: Epoch: [239] [1100/1251] eta: 0:01:35 lr: 0.000105 loss: 2.8921 (2.8338) grad_norm: 2.5377 (2.6796) time: 0.6296 [2021-03-28 05:23:10 swin_base_patch4_window7_224] INFO: Epoch: [239] [1110/1251] eta: 0:01:29 lr: 0.000105 loss: 2.9690 (2.8343) grad_norm: 2.5377 (2.6781) time: 0.6272 [2021-03-28 05:23:16 swin_base_patch4_window7_224] INFO: Epoch: [239] [1120/1251] eta: 0:01:22 lr: 0.000105 loss: 3.0362 (2.8370) grad_norm: 2.5574 (2.6802) time: 0.6277 [2021-03-28 05:23:23 swin_base_patch4_window7_224] INFO: Epoch: [239] [1130/1251] eta: 0:01:16 lr: 0.000105 loss: 2.9306 (2.8372) grad_norm: 2.5746 (2.6798) time: 0.6318 [2021-03-28 05:23:29 swin_base_patch4_window7_224] INFO: Epoch: [239] [1140/1251] eta: 0:01:10 lr: 0.000105 loss: 2.8513 (2.8378) grad_norm: 2.6621 (2.6804) time: 0.6311 [2021-03-28 05:23:35 swin_base_patch4_window7_224] INFO: Epoch: [239] [1150/1251] eta: 0:01:03 lr: 0.000105 loss: 2.8513 (2.8379) grad_norm: 2.5103 (2.6824) time: 0.6257 [2021-03-28 05:23:41 swin_base_patch4_window7_224] INFO: Epoch: [239] [1160/1251] eta: 0:00:57 lr: 0.000105 loss: 3.0669 (2.8395) grad_norm: 2.4651 (2.6819) time: 0.6245 [2021-03-28 05:23:48 swin_base_patch4_window7_224] INFO: Epoch: [239] [1170/1251] eta: 0:00:51 lr: 0.000105 loss: 2.8816 (2.8379) grad_norm: 2.4868 (2.6823) time: 0.6320 [2021-03-28 05:23:54 swin_base_patch4_window7_224] INFO: Epoch: [239] [1180/1251] eta: 0:00:44 lr: 0.000105 loss: 2.8713 (2.8388) grad_norm: 2.4618 (2.6817) time: 0.6315 [2021-03-28 05:24:00 swin_base_patch4_window7_224] INFO: Epoch: [239] [1190/1251] eta: 0:00:38 lr: 0.000105 loss: 3.0221 (2.8392) grad_norm: 2.4121 (2.6803) time: 0.6302 [2021-03-28 05:24:07 swin_base_patch4_window7_224] INFO: Epoch: [239] [1200/1251] eta: 0:00:32 lr: 0.000105 loss: 3.0221 (2.8392) grad_norm: 2.5417 (2.6814) time: 0.6327 [2021-03-28 05:24:13 swin_base_patch4_window7_224] INFO: Epoch: [239] [1210/1251] eta: 0:00:25 lr: 0.000105 loss: 3.0380 (2.8397) grad_norm: 2.6498 (2.6809) time: 0.6311 [2021-03-28 05:24:19 swin_base_patch4_window7_224] INFO: Epoch: [239] [1220/1251] eta: 0:00:19 lr: 0.000105 loss: 3.0380 (2.8402) grad_norm: 2.6658 (2.6831) time: 0.6277 [2021-03-28 05:24:25 swin_base_patch4_window7_224] INFO: Epoch: [239] [1230/1251] eta: 0:00:13 lr: 0.000105 loss: 3.0246 (2.8404) grad_norm: 2.6658 (2.6835) time: 0.6257 [2021-03-28 05:24:32 swin_base_patch4_window7_224] INFO: Epoch: [239] [1240/1251] eta: 0:00:06 lr: 0.000105 loss: 3.0618 (2.8413) grad_norm: 2.4447 (2.6868) time: 0.6295 [2021-03-28 05:24:38 swin_base_patch4_window7_224] INFO: Epoch: [239] [1250/1251] eta: 0:00:00 lr: 0.000105 loss: 2.9442 (2.8407) grad_norm: 2.7609 (2.6897) time: 0.6273 [2021-03-28 05:24:49 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:12 loss: 0.8434 (0.8434) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-28 05:24:52 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.7234 (0.7696) acc1: 82.8125 (81.5341) acc5: 96.8750 (96.4489) [2021-03-28 05:24:55 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7234 (0.7416) acc1: 82.8125 (81.9940) acc5: 96.8750 (96.7262) [2021-03-28 05:24:57 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7546 (0.7628) acc1: 81.2500 (81.1492) acc5: 96.8750 (96.5726) [2021-03-28 05:24:59 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7689 (0.7706) acc1: 81.2500 (81.4787) acc5: 95.3125 (96.4558) [2021-03-28 05:25:00 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7689 (0.7730) acc1: 82.8125 (81.5680) acc5: 96.8750 (96.4160) [2021-03-28 05:25:13 swin_base_patch4_window7_224] INFO: * Acc@1 82.466 Acc@5 96.232 loss 0.765 [2021-03-28 05:25:13 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.5% [2021-03-28 05:25:13 swin_base_patch4_window7_224] INFO: Max accuracy: 82.60% [2021-03-28 05:25:17 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 0/1251] eta: 1:25:46 lr: 0.000105 loss: 2.2127 (2.2127) grad_norm: 2.3774 (2.3774) time: 4.1139 [2021-03-28 05:25:24 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 10/1251] eta: 0:19:57 lr: 0.000105 loss: 2.5144 (2.6070) grad_norm: 2.7158 (2.8906) time: 0.9650 [2021-03-28 05:25:30 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 20/1251] eta: 0:16:27 lr: 0.000104 loss: 2.9285 (2.7704) grad_norm: 2.7075 (2.7664) time: 0.6364 [2021-03-28 05:25:36 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 30/1251] eta: 0:15:10 lr: 0.000104 loss: 3.0189 (2.8237) grad_norm: 2.6051 (2.8581) time: 0.6255 [2021-03-28 05:25:43 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 40/1251] eta: 0:14:30 lr: 0.000104 loss: 2.8557 (2.8023) grad_norm: 2.7340 (2.8439) time: 0.6311 [2021-03-28 05:25:49 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 50/1251] eta: 0:14:03 lr: 0.000104 loss: 2.8557 (2.7967) grad_norm: 2.5379 (2.7603) time: 0.6346 [2021-03-28 05:25:55 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 60/1251] eta: 0:13:42 lr: 0.000104 loss: 3.0237 (2.8223) grad_norm: 2.4018 (2.7393) time: 0.6332 [2021-03-28 05:26:02 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 70/1251] eta: 0:13:25 lr: 0.000104 loss: 2.9060 (2.8204) grad_norm: 2.4648 (2.7223) time: 0.6295 [2021-03-28 05:26:08 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 80/1251] eta: 0:13:12 lr: 0.000104 loss: 2.8683 (2.8122) grad_norm: 2.5459 (2.7114) time: 0.6330 [2021-03-28 05:26:14 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 90/1251] eta: 0:13:00 lr: 0.000104 loss: 2.7506 (2.8123) grad_norm: 2.5086 (2.6952) time: 0.6397 [2021-03-28 05:26:21 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 100/1251] eta: 0:12:49 lr: 0.000104 loss: 2.7743 (2.8221) grad_norm: 2.7052 (2.7188) time: 0.6358 [2021-03-28 05:26:27 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 110/1251] eta: 0:12:38 lr: 0.000104 loss: 2.9644 (2.8291) grad_norm: 2.7095 (2.7183) time: 0.6317 [2021-03-28 05:26:34 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 120/1251] eta: 0:12:29 lr: 0.000104 loss: 2.9644 (2.8384) grad_norm: 2.3970 (2.6898) time: 0.6365 [2021-03-28 05:26:40 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 130/1251] eta: 0:12:21 lr: 0.000104 loss: 2.9106 (2.8336) grad_norm: 2.3370 (2.6898) time: 0.6391 [2021-03-28 05:26:46 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 140/1251] eta: 0:12:11 lr: 0.000104 loss: 2.9530 (2.8390) grad_norm: 2.5692 (2.6786) time: 0.6331 [2021-03-28 05:26:53 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 150/1251] eta: 0:12:03 lr: 0.000104 loss: 2.9972 (2.8348) grad_norm: 2.4765 (2.6925) time: 0.6325 [2021-03-28 05:26:59 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 160/1251] eta: 0:11:55 lr: 0.000104 loss: 2.7794 (2.8285) grad_norm: 2.7419 (2.7080) time: 0.6330 [2021-03-28 05:27:05 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 170/1251] eta: 0:11:47 lr: 0.000104 loss: 2.6976 (2.8253) grad_norm: 2.8584 (2.7126) time: 0.6318 [2021-03-28 05:27:12 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 180/1251] eta: 0:11:39 lr: 0.000104 loss: 2.6968 (2.8125) grad_norm: 2.5829 (2.7090) time: 0.6332 [2021-03-28 05:27:18 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 190/1251] eta: 0:11:31 lr: 0.000104 loss: 2.6446 (2.8057) grad_norm: 2.4861 (2.7080) time: 0.6304 [2021-03-28 05:27:24 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 200/1251] eta: 0:11:23 lr: 0.000104 loss: 2.8267 (2.8109) grad_norm: 2.6283 (2.7258) time: 0.6294 [2021-03-28 05:27:30 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 210/1251] eta: 0:11:16 lr: 0.000104 loss: 2.8267 (2.8070) grad_norm: 2.6283 (2.7239) time: 0.6313 [2021-03-28 05:27:37 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 220/1251] eta: 0:11:09 lr: 0.000104 loss: 2.8610 (2.8123) grad_norm: 2.4666 (2.7178) time: 0.6350 [2021-03-28 05:27:43 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 230/1251] eta: 0:11:01 lr: 0.000104 loss: 2.9979 (2.8187) grad_norm: 2.4352 (2.7196) time: 0.6316 [2021-03-28 05:27:49 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 240/1251] eta: 0:10:54 lr: 0.000104 loss: 2.8470 (2.8229) grad_norm: 2.4838 (2.7339) time: 0.6296 [2021-03-28 05:27:56 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 250/1251] eta: 0:10:47 lr: 0.000104 loss: 2.9411 (2.8193) grad_norm: 2.4780 (2.7235) time: 0.6338 [2021-03-28 05:28:02 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 260/1251] eta: 0:10:40 lr: 0.000104 loss: 2.8506 (2.8176) grad_norm: 2.5134 (2.7291) time: 0.6331 [2021-03-28 05:28:08 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 270/1251] eta: 0:10:33 lr: 0.000104 loss: 2.8506 (2.8202) grad_norm: 2.5227 (2.7141) time: 0.6346 [2021-03-28 05:28:15 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 280/1251] eta: 0:10:26 lr: 0.000104 loss: 2.8894 (2.8182) grad_norm: 2.3598 (2.7009) time: 0.6326 [2021-03-28 05:28:21 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 290/1251] eta: 0:10:19 lr: 0.000104 loss: 2.9061 (2.8234) grad_norm: 2.5399 (2.7092) time: 0.6301 [2021-03-28 05:28:27 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 300/1251] eta: 0:10:12 lr: 0.000104 loss: 2.9122 (2.8255) grad_norm: 2.8020 (2.7104) time: 0.6279 [2021-03-28 05:28:34 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 310/1251] eta: 0:10:05 lr: 0.000104 loss: 2.9666 (2.8261) grad_norm: 2.7781 (2.7327) time: 0.6264 [2021-03-28 05:28:40 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 320/1251] eta: 0:09:59 lr: 0.000104 loss: 2.8961 (2.8248) grad_norm: 2.6310 (2.7316) time: 0.6351 [2021-03-28 05:28:46 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 330/1251] eta: 0:09:52 lr: 0.000104 loss: 2.8812 (2.8243) grad_norm: 2.5921 (2.7294) time: 0.6334 [2021-03-28 05:28:53 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 340/1251] eta: 0:09:45 lr: 0.000104 loss: 2.9262 (2.8235) grad_norm: 2.5799 (2.7287) time: 0.6277 [2021-03-28 05:28:59 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 350/1251] eta: 0:09:39 lr: 0.000104 loss: 2.8492 (2.8221) grad_norm: 2.5182 (2.7232) time: 0.6320 [2021-03-28 05:29:05 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 360/1251] eta: 0:09:32 lr: 0.000104 loss: 2.7679 (2.8185) grad_norm: 2.4801 (2.7156) time: 0.6323 [2021-03-28 05:29:11 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 370/1251] eta: 0:09:25 lr: 0.000104 loss: 2.9456 (2.8234) grad_norm: 2.5444 (2.7110) time: 0.6282 [2021-03-28 05:29:18 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 380/1251] eta: 0:09:18 lr: 0.000104 loss: 2.9694 (2.8242) grad_norm: 2.5444 (2.7081) time: 0.6280 [2021-03-28 05:29:24 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 390/1251] eta: 0:09:12 lr: 0.000104 loss: 2.8712 (2.8235) grad_norm: 2.5365 (2.7075) time: 0.6292 [2021-03-28 05:29:30 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 400/1251] eta: 0:09:05 lr: 0.000104 loss: 2.8846 (2.8239) grad_norm: 2.6061 (2.7052) time: 0.6281 [2021-03-28 05:29:37 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 410/1251] eta: 0:08:58 lr: 0.000104 loss: 3.0414 (2.8261) grad_norm: 2.6200 (2.7079) time: 0.6266 [2021-03-28 05:29:43 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 420/1251] eta: 0:08:51 lr: 0.000104 loss: 2.8056 (2.8250) grad_norm: 2.5081 (2.7066) time: 0.6259 [2021-03-28 05:29:49 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 430/1251] eta: 0:08:45 lr: 0.000103 loss: 2.8056 (2.8249) grad_norm: 2.7029 (2.7091) time: 0.6256 [2021-03-28 05:29:55 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 440/1251] eta: 0:08:38 lr: 0.000103 loss: 2.9912 (2.8218) grad_norm: 2.7416 (2.7065) time: 0.6274 [2021-03-28 05:30:02 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 450/1251] eta: 0:08:32 lr: 0.000103 loss: 2.9811 (2.8242) grad_norm: 2.7778 (2.7152) time: 0.6282 [2021-03-28 05:30:08 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 460/1251] eta: 0:08:25 lr: 0.000103 loss: 2.8205 (2.8186) grad_norm: 2.7680 (2.7187) time: 0.6276 [2021-03-28 05:30:14 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 470/1251] eta: 0:08:18 lr: 0.000103 loss: 2.7298 (2.8170) grad_norm: 2.9204 (inf) time: 0.6262 [2021-03-28 05:30:21 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 480/1251] eta: 0:08:12 lr: 0.000103 loss: 2.9069 (2.8191) grad_norm: 2.7109 (inf) time: 0.6283 [2021-03-28 05:30:27 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 490/1251] eta: 0:08:05 lr: 0.000103 loss: 3.0919 (2.8245) grad_norm: 2.5568 (inf) time: 0.6287 [2021-03-28 05:30:33 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 500/1251] eta: 0:07:59 lr: 0.000103 loss: 3.0919 (2.8286) grad_norm: 2.7540 (inf) time: 0.6234 [2021-03-28 05:30:39 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 510/1251] eta: 0:07:52 lr: 0.000103 loss: 2.8719 (2.8244) grad_norm: 3.1687 (inf) time: 0.6254 [2021-03-28 05:30:46 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 520/1251] eta: 0:07:46 lr: 0.000103 loss: 2.7589 (2.8220) grad_norm: 2.8793 (inf) time: 0.6293 [2021-03-28 05:30:52 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 530/1251] eta: 0:07:39 lr: 0.000103 loss: 2.8148 (2.8208) grad_norm: 2.4857 (inf) time: 0.6272 [2021-03-28 05:30:58 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 540/1251] eta: 0:07:33 lr: 0.000103 loss: 2.8989 (2.8223) grad_norm: 2.4951 (inf) time: 0.6273 [2021-03-28 05:31:05 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 550/1251] eta: 0:07:26 lr: 0.000103 loss: 3.0761 (2.8235) grad_norm: 2.6392 (inf) time: 0.6357 [2021-03-28 05:31:11 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 560/1251] eta: 0:07:20 lr: 0.000103 loss: 2.9405 (2.8232) grad_norm: 2.6928 (inf) time: 0.6431 [2021-03-28 05:31:17 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 570/1251] eta: 0:07:14 lr: 0.000103 loss: 2.9405 (2.8225) grad_norm: 2.5808 (inf) time: 0.6381 [2021-03-28 05:31:24 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 580/1251] eta: 0:07:07 lr: 0.000103 loss: 2.9819 (2.8244) grad_norm: 2.5329 (inf) time: 0.6307 [2021-03-28 05:31:30 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 590/1251] eta: 0:07:01 lr: 0.000103 loss: 2.9943 (2.8237) grad_norm: 2.6228 (inf) time: 0.6312 [2021-03-28 05:31:36 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 600/1251] eta: 0:06:54 lr: 0.000103 loss: 2.7834 (2.8199) grad_norm: 2.7328 (inf) time: 0.6320 [2021-03-28 05:31:42 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 610/1251] eta: 0:06:48 lr: 0.000103 loss: 2.7787 (2.8201) grad_norm: 2.4413 (inf) time: 0.6265 [2021-03-28 05:31:49 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 620/1251] eta: 0:06:41 lr: 0.000103 loss: 2.9393 (2.8201) grad_norm: 2.4830 (inf) time: 0.6259 [2021-03-28 05:31:55 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 630/1251] eta: 0:06:35 lr: 0.000103 loss: 2.9773 (2.8227) grad_norm: 2.7411 (inf) time: 0.6276 [2021-03-28 05:32:01 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 640/1251] eta: 0:06:28 lr: 0.000103 loss: 3.0979 (2.8268) grad_norm: 2.8269 (inf) time: 0.6302 [2021-03-28 05:32:08 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 650/1251] eta: 0:06:22 lr: 0.000103 loss: 3.0284 (2.8255) grad_norm: 2.5445 (inf) time: 0.6375 [2021-03-28 05:32:14 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 660/1251] eta: 0:06:16 lr: 0.000103 loss: 2.7421 (2.8254) grad_norm: 2.5496 (inf) time: 0.6326 [2021-03-28 05:32:20 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 670/1251] eta: 0:06:09 lr: 0.000103 loss: 2.9000 (2.8268) grad_norm: 2.5920 (inf) time: 0.6234 [2021-03-28 05:32:27 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 680/1251] eta: 0:06:03 lr: 0.000103 loss: 3.0099 (2.8285) grad_norm: 2.6562 (inf) time: 0.6243 [2021-03-28 05:32:33 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 690/1251] eta: 0:05:56 lr: 0.000103 loss: 2.9329 (2.8271) grad_norm: 2.5789 (inf) time: 0.6308 [2021-03-28 05:32:39 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 700/1251] eta: 0:05:50 lr: 0.000103 loss: 2.7343 (2.8274) grad_norm: 2.6231 (inf) time: 0.6360 [2021-03-28 05:32:46 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 710/1251] eta: 0:05:44 lr: 0.000103 loss: 2.7090 (2.8246) grad_norm: 2.7047 (inf) time: 0.6384 [2021-03-28 05:32:52 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 720/1251] eta: 0:05:37 lr: 0.000103 loss: 2.7498 (2.8238) grad_norm: 2.4913 (inf) time: 0.6346 [2021-03-28 05:32:58 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 730/1251] eta: 0:05:31 lr: 0.000103 loss: 2.8655 (2.8240) grad_norm: 2.5475 (inf) time: 0.6356 [2021-03-28 05:33:05 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 740/1251] eta: 0:05:25 lr: 0.000103 loss: 2.8655 (2.8228) grad_norm: 2.6110 (inf) time: 0.6423 [2021-03-28 05:33:11 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 750/1251] eta: 0:05:18 lr: 0.000103 loss: 2.9129 (2.8246) grad_norm: 2.5370 (inf) time: 0.6430 [2021-03-28 05:33:18 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 760/1251] eta: 0:05:12 lr: 0.000103 loss: 2.9129 (2.8242) grad_norm: 2.5244 (inf) time: 0.6413 [2021-03-28 05:33:24 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 770/1251] eta: 0:05:06 lr: 0.000103 loss: 2.7810 (2.8242) grad_norm: 2.3676 (inf) time: 0.6362 [2021-03-28 05:33:30 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 780/1251] eta: 0:04:59 lr: 0.000103 loss: 3.0790 (2.8255) grad_norm: 2.5096 (inf) time: 0.6261 [2021-03-28 05:33:37 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 790/1251] eta: 0:04:53 lr: 0.000103 loss: 2.9797 (2.8260) grad_norm: 2.5241 (inf) time: 0.6281 [2021-03-28 05:33:43 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 800/1251] eta: 0:04:46 lr: 0.000103 loss: 2.9014 (2.8243) grad_norm: 2.4730 (inf) time: 0.6373 [2021-03-28 05:33:49 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 810/1251] eta: 0:04:40 lr: 0.000103 loss: 2.9014 (2.8237) grad_norm: 2.4664 (inf) time: 0.6316 [2021-03-28 05:33:56 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 820/1251] eta: 0:04:34 lr: 0.000103 loss: 2.9158 (2.8256) grad_norm: 2.4563 (inf) time: 0.6299 [2021-03-28 05:34:02 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 830/1251] eta: 0:04:27 lr: 0.000103 loss: 2.9383 (2.8270) grad_norm: 2.5893 (inf) time: 0.6330 [2021-03-28 05:34:08 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 840/1251] eta: 0:04:21 lr: 0.000103 loss: 2.9659 (2.8288) grad_norm: 2.4613 (inf) time: 0.6342 [2021-03-28 05:34:14 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 850/1251] eta: 0:04:14 lr: 0.000102 loss: 2.9981 (2.8302) grad_norm: 2.4076 (inf) time: 0.6342 [2021-03-28 05:34:21 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 860/1251] eta: 0:04:08 lr: 0.000102 loss: 2.8305 (2.8304) grad_norm: 2.4076 (inf) time: 0.6264 [2021-03-28 05:34:27 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 870/1251] eta: 0:04:02 lr: 0.000102 loss: 2.8299 (2.8310) grad_norm: 2.5163 (inf) time: 0.6301 [2021-03-28 05:34:33 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 880/1251] eta: 0:03:55 lr: 0.000102 loss: 3.0197 (2.8321) grad_norm: 2.6645 (inf) time: 0.6371 [2021-03-28 05:34:40 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 890/1251] eta: 0:03:49 lr: 0.000102 loss: 3.1232 (2.8340) grad_norm: 2.6629 (inf) time: 0.6294 [2021-03-28 05:34:46 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 900/1251] eta: 0:03:43 lr: 0.000102 loss: 2.9720 (2.8346) grad_norm: 2.6332 (inf) time: 0.6261 [2021-03-28 05:34:52 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 910/1251] eta: 0:03:36 lr: 0.000102 loss: 2.9561 (2.8342) grad_norm: 2.7474 (inf) time: 0.6303 [2021-03-28 05:34:59 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 920/1251] eta: 0:03:30 lr: 0.000102 loss: 2.6711 (2.8322) grad_norm: 2.7204 (inf) time: 0.6279 [2021-03-28 05:35:05 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 930/1251] eta: 0:03:23 lr: 0.000102 loss: 2.6031 (2.8303) grad_norm: 2.5520 (inf) time: 0.6306 [2021-03-28 05:35:11 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 940/1251] eta: 0:03:17 lr: 0.000102 loss: 2.6989 (2.8308) grad_norm: 2.5367 (inf) time: 0.6376 [2021-03-28 05:35:18 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 950/1251] eta: 0:03:11 lr: 0.000102 loss: 2.7451 (2.8293) grad_norm: 2.5367 (inf) time: 0.6306 [2021-03-28 05:35:24 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 960/1251] eta: 0:03:04 lr: 0.000102 loss: 2.7451 (2.8283) grad_norm: 2.6505 (inf) time: 0.6229 [2021-03-28 05:35:30 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 970/1251] eta: 0:02:58 lr: 0.000102 loss: 2.9656 (2.8300) grad_norm: 2.5488 (inf) time: 0.6265 [2021-03-28 05:35:36 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 980/1251] eta: 0:02:52 lr: 0.000102 loss: 2.9388 (2.8293) grad_norm: 2.5428 (inf) time: 0.6280 [2021-03-28 05:35:43 swin_base_patch4_window7_224] INFO: Epoch: [240] [ 990/1251] eta: 0:02:45 lr: 0.000102 loss: 2.9388 (2.8318) grad_norm: 2.5007 (inf) time: 0.6254 [2021-03-28 05:35:49 swin_base_patch4_window7_224] INFO: Epoch: [240] [1000/1251] eta: 0:02:39 lr: 0.000102 loss: 3.0614 (2.8334) grad_norm: 2.5556 (inf) time: 0.6294 [2021-03-28 05:35:55 swin_base_patch4_window7_224] INFO: Epoch: [240] [1010/1251] eta: 0:02:32 lr: 0.000102 loss: 3.0424 (2.8348) grad_norm: 2.5582 (inf) time: 0.6328 [2021-03-28 05:36:02 swin_base_patch4_window7_224] INFO: Epoch: [240] [1020/1251] eta: 0:02:26 lr: 0.000102 loss: 3.0036 (2.8336) grad_norm: 2.5679 (inf) time: 0.6343 [2021-03-28 05:36:08 swin_base_patch4_window7_224] INFO: Epoch: [240] [1030/1251] eta: 0:02:20 lr: 0.000102 loss: 2.8951 (2.8327) grad_norm: 2.6818 (inf) time: 0.6336 [2021-03-28 05:36:14 swin_base_patch4_window7_224] INFO: Epoch: [240] [1040/1251] eta: 0:02:13 lr: 0.000102 loss: 2.9043 (2.8331) grad_norm: 2.5248 (inf) time: 0.6328 [2021-03-28 05:36:21 swin_base_patch4_window7_224] INFO: Epoch: [240] [1050/1251] eta: 0:02:07 lr: 0.000102 loss: 2.9043 (2.8334) grad_norm: 2.5796 (inf) time: 0.6371 [2021-03-28 05:36:27 swin_base_patch4_window7_224] INFO: Epoch: [240] [1060/1251] eta: 0:02:01 lr: 0.000102 loss: 2.7945 (2.8331) grad_norm: 2.6224 (inf) time: 0.6336 [2021-03-28 05:36:33 swin_base_patch4_window7_224] INFO: Epoch: [240] [1070/1251] eta: 0:01:54 lr: 0.000102 loss: 2.7808 (2.8314) grad_norm: 2.5297 (inf) time: 0.6283 [2021-03-28 05:36:40 swin_base_patch4_window7_224] INFO: Epoch: [240] [1080/1251] eta: 0:01:48 lr: 0.000102 loss: 2.4980 (2.8278) grad_norm: 2.6242 (inf) time: 0.6300 [2021-03-28 05:36:46 swin_base_patch4_window7_224] INFO: Epoch: [240] [1090/1251] eta: 0:01:42 lr: 0.000102 loss: 2.5145 (2.8276) grad_norm: 2.5847 (inf) time: 0.6275 [2021-03-28 05:36:52 swin_base_patch4_window7_224] INFO: Epoch: [240] [1100/1251] eta: 0:01:35 lr: 0.000102 loss: 2.8909 (2.8275) grad_norm: 2.5372 (inf) time: 0.6231 [2021-03-28 05:36:58 swin_base_patch4_window7_224] INFO: Epoch: [240] [1110/1251] eta: 0:01:29 lr: 0.000102 loss: 2.7266 (2.8271) grad_norm: 2.5065 (inf) time: 0.6307 [2021-03-28 05:37:05 swin_base_patch4_window7_224] INFO: Epoch: [240] [1120/1251] eta: 0:01:23 lr: 0.000102 loss: 2.6859 (2.8254) grad_norm: 2.5065 (inf) time: 0.6330 [2021-03-28 05:37:11 swin_base_patch4_window7_224] INFO: Epoch: [240] [1130/1251] eta: 0:01:16 lr: 0.000102 loss: 2.7982 (2.8252) grad_norm: 2.5436 (inf) time: 0.6265 [2021-03-28 05:37:17 swin_base_patch4_window7_224] INFO: Epoch: [240] [1140/1251] eta: 0:01:10 lr: 0.000102 loss: 2.7982 (2.8253) grad_norm: 2.5436 (inf) time: 0.6228 [2021-03-28 05:37:23 swin_base_patch4_window7_224] INFO: Epoch: [240] [1150/1251] eta: 0:01:04 lr: 0.000102 loss: 2.8317 (2.8252) grad_norm: 2.7023 (inf) time: 0.6232 [2021-03-28 05:37:30 swin_base_patch4_window7_224] INFO: Epoch: [240] [1160/1251] eta: 0:00:57 lr: 0.000102 loss: 2.9236 (2.8258) grad_norm: 2.6744 (inf) time: 0.6245 [2021-03-28 05:37:36 swin_base_patch4_window7_224] INFO: Epoch: [240] [1170/1251] eta: 0:00:51 lr: 0.000102 loss: 2.9236 (2.8261) grad_norm: 2.5546 (inf) time: 0.6265 [2021-03-28 05:37:42 swin_base_patch4_window7_224] INFO: Epoch: [240] [1180/1251] eta: 0:00:45 lr: 0.000102 loss: 2.9737 (2.8262) grad_norm: 2.5096 (inf) time: 0.6249 [2021-03-28 05:37:48 swin_base_patch4_window7_224] INFO: Epoch: [240] [1190/1251] eta: 0:00:38 lr: 0.000102 loss: 2.9737 (2.8267) grad_norm: 2.5096 (inf) time: 0.6253 [2021-03-28 05:37:55 swin_base_patch4_window7_224] INFO: Epoch: [240] [1200/1251] eta: 0:00:32 lr: 0.000102 loss: 2.9108 (2.8264) grad_norm: 2.4686 (inf) time: 0.6340 [2021-03-28 05:38:01 swin_base_patch4_window7_224] INFO: Epoch: [240] [1210/1251] eta: 0:00:25 lr: 0.000102 loss: 2.8383 (2.8264) grad_norm: 2.4299 (inf) time: 0.6365 [2021-03-28 05:38:07 swin_base_patch4_window7_224] INFO: Epoch: [240] [1220/1251] eta: 0:00:19 lr: 0.000102 loss: 2.6464 (2.8245) grad_norm: 2.5126 (inf) time: 0.6283 [2021-03-28 05:38:14 swin_base_patch4_window7_224] INFO: Epoch: [240] [1230/1251] eta: 0:00:13 lr: 0.000102 loss: 2.9825 (2.8262) grad_norm: 2.5962 (inf) time: 0.6230 [2021-03-28 05:38:20 swin_base_patch4_window7_224] INFO: Epoch: [240] [1240/1251] eta: 0:00:06 lr: 0.000102 loss: 3.1419 (2.8273) grad_norm: 2.6100 (inf) time: 0.6200 [2021-03-28 05:38:26 swin_base_patch4_window7_224] INFO: Epoch: [240] [1250/1251] eta: 0:00:00 lr: 0.000102 loss: 2.9413 (2.8270) grad_norm: 2.5173 (inf) time: 0.6202 [2021-03-28 05:39:48 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:01 loss: 0.6674 (0.6674) acc1: 81.2500 (81.2500) acc5: 100.0000 (100.0000) [2021-03-28 05:39:49 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7798 (0.8290) acc1: 81.2500 (81.3920) acc5: 96.8750 (95.8807) [2021-03-28 05:39:51 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7609 (0.8161) acc1: 81.2500 (81.3988) acc5: 96.8750 (95.9077) [2021-03-28 05:39:52 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7492 (0.8126) acc1: 81.2500 (81.0988) acc5: 96.8750 (96.0181) [2021-03-28 05:39:53 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7137 (0.7817) acc1: 81.2500 (81.7835) acc5: 96.8750 (96.1890) [2021-03-28 05:39:55 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6614 (0.7751) acc1: 82.8125 (81.9840) acc5: 96.8750 (96.3200) [2021-03-28 05:40:09 swin_base_patch4_window7_224] INFO: * Acc@1 82.746 Acc@5 96.294 loss 0.762 [2021-03-28 05:40:09 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.7% [2021-03-28 05:40:09 swin_base_patch4_window7_224] INFO: Max accuracy: 82.75% [2021-03-28 05:40:13 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 0/1251] eta: 1:31:14 lr: 0.000102 loss: 2.8915 (2.8915) grad_norm: 2.3342 (2.3342) time: 4.3759 [2021-03-28 05:40:20 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 10/1251] eta: 0:20:23 lr: 0.000101 loss: 2.5144 (2.5869) grad_norm: 2.6328 (2.6434) time: 0.9855 [2021-03-28 05:40:26 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 20/1251] eta: 0:16:44 lr: 0.000101 loss: 2.6364 (2.7083) grad_norm: 2.5663 (2.5603) time: 0.6376 [2021-03-28 05:40:32 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 30/1251] eta: 0:15:24 lr: 0.000101 loss: 3.1260 (2.7928) grad_norm: 2.5181 (2.6410) time: 0.6321 [2021-03-28 05:40:39 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 40/1251] eta: 0:14:41 lr: 0.000101 loss: 2.9838 (2.7762) grad_norm: 2.6078 (2.6758) time: 0.6350 [2021-03-28 05:40:45 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 50/1251] eta: 0:14:12 lr: 0.000101 loss: 2.8009 (2.7850) grad_norm: 2.4980 (2.6380) time: 0.6362 [2021-03-28 05:40:51 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 60/1251] eta: 0:13:50 lr: 0.000101 loss: 2.9358 (2.7930) grad_norm: 2.5882 (2.6501) time: 0.6359 [2021-03-28 05:40:58 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 70/1251] eta: 0:13:31 lr: 0.000101 loss: 2.9358 (2.7925) grad_norm: 2.6103 (2.6766) time: 0.6298 [2021-03-28 05:41:04 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 80/1251] eta: 0:13:15 lr: 0.000101 loss: 2.6007 (2.7817) grad_norm: 2.6103 (2.6822) time: 0.6243 [2021-03-28 05:41:10 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 90/1251] eta: 0:13:01 lr: 0.000101 loss: 2.9376 (2.8009) grad_norm: 2.5749 (2.6723) time: 0.6233 [2021-03-28 05:41:16 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 100/1251] eta: 0:12:49 lr: 0.000101 loss: 2.9711 (2.8101) grad_norm: 2.3638 (2.6823) time: 0.6262 [2021-03-28 05:41:23 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 110/1251] eta: 0:12:39 lr: 0.000101 loss: 3.0109 (2.8264) grad_norm: 2.7315 (2.7258) time: 0.6329 [2021-03-28 05:41:29 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 120/1251] eta: 0:12:29 lr: 0.000101 loss: 2.8726 (2.8183) grad_norm: 2.8088 (2.7223) time: 0.6311 [2021-03-28 05:41:35 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 130/1251] eta: 0:12:19 lr: 0.000101 loss: 2.8826 (2.8269) grad_norm: 2.8664 (2.7762) time: 0.6269 [2021-03-28 05:41:42 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 140/1251] eta: 0:12:11 lr: 0.000101 loss: 2.8976 (2.8221) grad_norm: 2.9313 (2.7716) time: 0.6332 [2021-03-28 05:41:48 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 150/1251] eta: 0:12:02 lr: 0.000101 loss: 2.9497 (2.8270) grad_norm: 2.6050 (2.7565) time: 0.6334 [2021-03-28 05:41:54 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 160/1251] eta: 0:11:53 lr: 0.000101 loss: 2.9511 (2.8342) grad_norm: 2.5832 (2.7535) time: 0.6248 [2021-03-28 05:42:00 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 170/1251] eta: 0:11:46 lr: 0.000101 loss: 2.9512 (2.8341) grad_norm: 2.4677 (2.7514) time: 0.6281 [2021-03-28 05:42:07 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 180/1251] eta: 0:11:38 lr: 0.000101 loss: 3.0115 (2.8388) grad_norm: 2.4984 (2.7356) time: 0.6367 [2021-03-28 05:42:13 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 190/1251] eta: 0:11:30 lr: 0.000101 loss: 2.9899 (2.8331) grad_norm: 2.5871 (2.7570) time: 0.6334 [2021-03-28 05:42:19 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 200/1251] eta: 0:11:23 lr: 0.000101 loss: 2.8724 (2.8283) grad_norm: 2.5871 (2.7646) time: 0.6298 [2021-03-28 05:42:26 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 210/1251] eta: 0:11:15 lr: 0.000101 loss: 2.8985 (2.8367) grad_norm: 2.6278 (2.7691) time: 0.6289 [2021-03-28 05:42:32 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 220/1251] eta: 0:11:08 lr: 0.000101 loss: 2.9321 (2.8361) grad_norm: 2.7130 (2.7673) time: 0.6300 [2021-03-28 05:42:39 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 230/1251] eta: 0:11:01 lr: 0.000101 loss: 2.9244 (2.8348) grad_norm: 2.6091 (2.7620) time: 0.6397 [2021-03-28 05:42:45 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 240/1251] eta: 0:10:54 lr: 0.000101 loss: 2.9244 (2.8360) grad_norm: 2.4129 (2.7529) time: 0.6404 [2021-03-28 05:42:51 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 250/1251] eta: 0:10:47 lr: 0.000101 loss: 2.9164 (2.8359) grad_norm: 2.5640 (2.7485) time: 0.6369 [2021-03-28 05:42:58 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 260/1251] eta: 0:10:41 lr: 0.000101 loss: 2.8562 (2.8383) grad_norm: 2.5130 (2.7372) time: 0.6397 [2021-03-28 05:43:04 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 270/1251] eta: 0:10:33 lr: 0.000101 loss: 2.8659 (2.8382) grad_norm: 2.4461 (2.7318) time: 0.6285 [2021-03-28 05:43:10 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 280/1251] eta: 0:10:26 lr: 0.000101 loss: 2.6871 (2.8313) grad_norm: 2.3225 (2.7215) time: 0.6249 [2021-03-28 05:43:17 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 290/1251] eta: 0:10:19 lr: 0.000101 loss: 2.8788 (2.8326) grad_norm: 2.4371 (2.7325) time: 0.6341 [2021-03-28 05:43:23 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 300/1251] eta: 0:10:13 lr: 0.000101 loss: 2.9601 (2.8306) grad_norm: 2.5313 (2.7261) time: 0.6336 [2021-03-28 05:43:29 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 310/1251] eta: 0:10:06 lr: 0.000101 loss: 2.8294 (2.8275) grad_norm: 2.5313 (2.7187) time: 0.6339 [2021-03-28 05:43:36 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 320/1251] eta: 0:09:59 lr: 0.000101 loss: 2.8294 (2.8272) grad_norm: 2.5960 (2.7179) time: 0.6341 [2021-03-28 05:43:42 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 330/1251] eta: 0:09:52 lr: 0.000101 loss: 2.7112 (2.8251) grad_norm: 2.5960 (2.7169) time: 0.6339 [2021-03-28 05:43:48 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 340/1251] eta: 0:09:46 lr: 0.000101 loss: 2.8463 (2.8214) grad_norm: 2.5334 (2.7158) time: 0.6317 [2021-03-28 05:43:54 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 350/1251] eta: 0:09:39 lr: 0.000101 loss: 2.8955 (2.8221) grad_norm: 2.3936 (2.7056) time: 0.6288 [2021-03-28 05:44:01 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 360/1251] eta: 0:09:32 lr: 0.000101 loss: 2.8242 (2.8238) grad_norm: 2.3076 (2.7011) time: 0.6295 [2021-03-28 05:44:07 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 370/1251] eta: 0:09:25 lr: 0.000101 loss: 2.9679 (2.8215) grad_norm: 2.3391 (2.6946) time: 0.6293 [2021-03-28 05:44:13 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 380/1251] eta: 0:09:19 lr: 0.000101 loss: 3.0407 (2.8262) grad_norm: 2.4102 (2.6925) time: 0.6321 [2021-03-28 05:44:20 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 390/1251] eta: 0:09:12 lr: 0.000101 loss: 2.9362 (2.8284) grad_norm: 2.3669 (2.6844) time: 0.6306 [2021-03-28 05:44:26 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 400/1251] eta: 0:09:05 lr: 0.000101 loss: 2.9759 (2.8281) grad_norm: 2.3588 (2.6801) time: 0.6308 [2021-03-28 05:44:32 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 410/1251] eta: 0:08:59 lr: 0.000101 loss: 2.9104 (2.8285) grad_norm: 2.4942 (2.6790) time: 0.6329 [2021-03-28 05:44:39 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 420/1251] eta: 0:08:52 lr: 0.000101 loss: 2.9104 (2.8306) grad_norm: 2.4634 (2.6733) time: 0.6303 [2021-03-28 05:44:45 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 430/1251] eta: 0:08:45 lr: 0.000100 loss: 2.9285 (2.8306) grad_norm: 2.3084 (2.6669) time: 0.6303 [2021-03-28 05:44:51 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 440/1251] eta: 0:08:39 lr: 0.000100 loss: 3.0211 (2.8354) grad_norm: 2.4070 (2.6653) time: 0.6364 [2021-03-28 05:44:58 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 450/1251] eta: 0:08:33 lr: 0.000100 loss: 3.0544 (2.8377) grad_norm: 2.5746 (2.6741) time: 0.6385 [2021-03-28 05:45:04 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 460/1251] eta: 0:08:26 lr: 0.000100 loss: 3.0056 (2.8405) grad_norm: 2.5364 (2.6694) time: 0.6382 [2021-03-28 05:45:10 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 470/1251] eta: 0:08:20 lr: 0.000100 loss: 2.9075 (2.8401) grad_norm: 2.4720 (2.6663) time: 0.6349 [2021-03-28 05:45:17 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 480/1251] eta: 0:08:13 lr: 0.000100 loss: 2.7930 (2.8379) grad_norm: 2.4060 (2.6627) time: 0.6263 [2021-03-28 05:45:23 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 490/1251] eta: 0:08:06 lr: 0.000100 loss: 2.8573 (2.8431) grad_norm: 2.5013 (2.6727) time: 0.6274 [2021-03-28 05:45:29 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 500/1251] eta: 0:08:00 lr: 0.000100 loss: 2.8573 (2.8399) grad_norm: 2.5013 (2.6700) time: 0.6292 [2021-03-28 05:45:36 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 510/1251] eta: 0:07:53 lr: 0.000100 loss: 2.7313 (2.8377) grad_norm: 2.4076 (2.6657) time: 0.6296 [2021-03-28 05:45:42 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 520/1251] eta: 0:07:47 lr: 0.000100 loss: 2.7762 (2.8357) grad_norm: 2.6009 (2.6660) time: 0.6293 [2021-03-28 05:45:48 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 530/1251] eta: 0:07:40 lr: 0.000100 loss: 2.9497 (2.8358) grad_norm: 2.6012 (2.6692) time: 0.6295 [2021-03-28 05:45:55 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 540/1251] eta: 0:07:34 lr: 0.000100 loss: 2.6794 (2.8321) grad_norm: 2.6046 (2.6737) time: 0.6389 [2021-03-28 05:46:01 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 550/1251] eta: 0:07:28 lr: 0.000100 loss: 2.7235 (2.8309) grad_norm: 2.7291 (2.6762) time: 0.6445 [2021-03-28 05:46:07 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 560/1251] eta: 0:07:21 lr: 0.000100 loss: 2.9460 (2.8354) grad_norm: 2.5853 (2.6762) time: 0.6372 [2021-03-28 05:46:14 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 570/1251] eta: 0:07:15 lr: 0.000100 loss: 2.9460 (2.8347) grad_norm: 2.5521 (2.6797) time: 0.6324 [2021-03-28 05:46:20 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 580/1251] eta: 0:07:08 lr: 0.000100 loss: 2.8643 (2.8315) grad_norm: 2.5660 (2.6821) time: 0.6313 [2021-03-28 05:46:26 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 590/1251] eta: 0:07:02 lr: 0.000100 loss: 2.8643 (2.8327) grad_norm: 2.5660 (2.6813) time: 0.6338 [2021-03-28 05:46:33 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 600/1251] eta: 0:06:55 lr: 0.000100 loss: 2.9880 (2.8350) grad_norm: 2.6444 (2.6958) time: 0.6317 [2021-03-28 05:46:39 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 610/1251] eta: 0:06:49 lr: 0.000100 loss: 2.8923 (2.8362) grad_norm: 2.5840 (2.6931) time: 0.6303 [2021-03-28 05:46:45 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 620/1251] eta: 0:06:42 lr: 0.000100 loss: 2.8842 (2.8363) grad_norm: 2.5130 (2.6972) time: 0.6301 [2021-03-28 05:46:52 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 630/1251] eta: 0:06:36 lr: 0.000100 loss: 2.9226 (2.8355) grad_norm: 2.5211 (2.6961) time: 0.6288 [2021-03-28 05:46:58 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 640/1251] eta: 0:06:29 lr: 0.000100 loss: 2.8347 (2.8340) grad_norm: 2.4301 (2.6926) time: 0.6314 [2021-03-28 05:47:04 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 650/1251] eta: 0:06:23 lr: 0.000100 loss: 2.6488 (2.8302) grad_norm: 2.4602 (2.6942) time: 0.6314 [2021-03-28 05:47:10 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 660/1251] eta: 0:06:16 lr: 0.000100 loss: 2.7931 (2.8321) grad_norm: 2.5591 (2.6917) time: 0.6291 [2021-03-28 05:47:17 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 670/1251] eta: 0:06:10 lr: 0.000100 loss: 3.0193 (2.8357) grad_norm: 2.5591 (2.6918) time: 0.6249 [2021-03-28 05:47:23 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 680/1251] eta: 0:06:04 lr: 0.000100 loss: 2.9447 (2.8332) grad_norm: 2.7198 (2.6922) time: 0.6307 [2021-03-28 05:47:29 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 690/1251] eta: 0:05:57 lr: 0.000100 loss: 2.5865 (2.8302) grad_norm: 2.5240 (2.6901) time: 0.6365 [2021-03-28 05:47:36 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 700/1251] eta: 0:05:51 lr: 0.000100 loss: 2.4797 (2.8277) grad_norm: 2.5240 (2.6873) time: 0.6380 [2021-03-28 05:47:42 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 710/1251] eta: 0:05:44 lr: 0.000100 loss: 2.9562 (2.8297) grad_norm: 2.5242 (2.6893) time: 0.6304 [2021-03-28 05:47:48 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 720/1251] eta: 0:05:38 lr: 0.000100 loss: 3.0244 (2.8304) grad_norm: 2.5353 (2.6906) time: 0.6244 [2021-03-28 05:47:55 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 730/1251] eta: 0:05:31 lr: 0.000100 loss: 2.7975 (2.8298) grad_norm: 2.6120 (2.6933) time: 0.6292 [2021-03-28 05:48:01 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 740/1251] eta: 0:05:25 lr: 0.000100 loss: 2.8872 (2.8303) grad_norm: 2.5749 (2.6940) time: 0.6296 [2021-03-28 05:48:07 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 750/1251] eta: 0:05:19 lr: 0.000100 loss: 2.9628 (2.8333) grad_norm: 2.5182 (2.6948) time: 0.6291 [2021-03-28 05:48:14 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 760/1251] eta: 0:05:12 lr: 0.000100 loss: 3.0616 (2.8331) grad_norm: 2.4186 (2.6904) time: 0.6327 [2021-03-28 05:48:20 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 770/1251] eta: 0:05:06 lr: 0.000100 loss: 2.9535 (2.8341) grad_norm: 2.3524 (2.6909) time: 0.6338 [2021-03-28 05:48:26 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 780/1251] eta: 0:04:59 lr: 0.000100 loss: 2.9442 (2.8327) grad_norm: 2.5207 (2.6914) time: 0.6314 [2021-03-28 05:48:33 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 790/1251] eta: 0:04:53 lr: 0.000100 loss: 2.8991 (2.8310) grad_norm: 2.5657 (2.6888) time: 0.6313 [2021-03-28 05:48:39 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 800/1251] eta: 0:04:47 lr: 0.000100 loss: 2.8991 (2.8339) grad_norm: 2.4895 (2.6941) time: 0.6361 [2021-03-28 05:48:45 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 810/1251] eta: 0:04:40 lr: 0.000100 loss: 2.9160 (2.8315) grad_norm: 2.6459 (2.6941) time: 0.6348 [2021-03-28 05:48:51 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 820/1251] eta: 0:04:34 lr: 0.000100 loss: 2.7523 (2.8301) grad_norm: 2.6459 (2.6967) time: 0.6284 [2021-03-28 05:48:58 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 830/1251] eta: 0:04:27 lr: 0.000100 loss: 2.7042 (2.8300) grad_norm: 2.6110 (2.6973) time: 0.6273 [2021-03-28 05:49:04 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 840/1251] eta: 0:04:21 lr: 0.000100 loss: 2.6421 (2.8265) grad_norm: 2.6623 (2.7090) time: 0.6285 [2021-03-28 05:49:10 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 850/1251] eta: 0:04:15 lr: 0.000099 loss: 2.7626 (2.8281) grad_norm: 2.6270 (2.7078) time: 0.6278 [2021-03-28 05:49:17 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 860/1251] eta: 0:04:08 lr: 0.000099 loss: 3.0887 (2.8322) grad_norm: 2.6270 (2.7080) time: 0.6305 [2021-03-28 05:49:23 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 870/1251] eta: 0:04:02 lr: 0.000099 loss: 3.0460 (2.8336) grad_norm: 2.6291 (2.7061) time: 0.6348 [2021-03-28 05:49:29 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 880/1251] eta: 0:03:55 lr: 0.000099 loss: 2.9960 (2.8355) grad_norm: 2.4238 (2.7044) time: 0.6306 [2021-03-28 05:49:36 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 890/1251] eta: 0:03:49 lr: 0.000099 loss: 2.9256 (2.8338) grad_norm: 2.4748 (2.7068) time: 0.6318 [2021-03-28 05:49:42 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 900/1251] eta: 0:03:43 lr: 0.000099 loss: 2.8963 (2.8349) grad_norm: 2.5833 (2.7078) time: 0.6339 [2021-03-28 05:49:48 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 910/1251] eta: 0:03:36 lr: 0.000099 loss: 2.9362 (2.8355) grad_norm: 2.5352 (2.7064) time: 0.6279 [2021-03-28 05:49:55 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 920/1251] eta: 0:03:30 lr: 0.000099 loss: 2.9538 (2.8365) grad_norm: 2.5600 (2.7067) time: 0.6291 [2021-03-28 05:50:01 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 930/1251] eta: 0:03:24 lr: 0.000099 loss: 2.9846 (2.8384) grad_norm: 2.7365 (2.7080) time: 0.6294 [2021-03-28 05:50:07 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 940/1251] eta: 0:03:17 lr: 0.000099 loss: 3.0688 (2.8389) grad_norm: 2.6918 (2.7093) time: 0.6275 [2021-03-28 05:50:13 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 950/1251] eta: 0:03:11 lr: 0.000099 loss: 2.7204 (2.8370) grad_norm: 2.6894 (2.7134) time: 0.6268 [2021-03-28 05:50:20 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 960/1251] eta: 0:03:04 lr: 0.000099 loss: 2.7204 (2.8361) grad_norm: 2.6894 (2.7127) time: 0.6294 [2021-03-28 05:50:26 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 970/1251] eta: 0:02:58 lr: 0.000099 loss: 2.9340 (2.8352) grad_norm: 2.4355 (2.7102) time: 0.6391 [2021-03-28 05:50:32 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 980/1251] eta: 0:02:52 lr: 0.000099 loss: 2.9467 (2.8365) grad_norm: 2.4526 (2.7109) time: 0.6376 [2021-03-28 05:50:39 swin_base_patch4_window7_224] INFO: Epoch: [241] [ 990/1251] eta: 0:02:45 lr: 0.000099 loss: 3.0256 (2.8351) grad_norm: 2.7004 (2.7105) time: 0.6362 [2021-03-28 05:50:45 swin_base_patch4_window7_224] INFO: Epoch: [241] [1000/1251] eta: 0:02:39 lr: 0.000099 loss: 2.7446 (2.8351) grad_norm: 2.6107 (2.7104) time: 0.6376 [2021-03-28 05:50:52 swin_base_patch4_window7_224] INFO: Epoch: [241] [1010/1251] eta: 0:02:33 lr: 0.000099 loss: 2.7446 (2.8337) grad_norm: 2.5201 (2.7096) time: 0.6339 [2021-03-28 05:50:58 swin_base_patch4_window7_224] INFO: Epoch: [241] [1020/1251] eta: 0:02:26 lr: 0.000099 loss: 2.8221 (2.8339) grad_norm: 2.5382 (2.7094) time: 0.6294 [2021-03-28 05:51:04 swin_base_patch4_window7_224] INFO: Epoch: [241] [1030/1251] eta: 0:02:20 lr: 0.000099 loss: 2.8221 (2.8341) grad_norm: 2.5909 (2.7097) time: 0.6274 [2021-03-28 05:51:10 swin_base_patch4_window7_224] INFO: Epoch: [241] [1040/1251] eta: 0:02:14 lr: 0.000099 loss: 2.9376 (2.8351) grad_norm: 2.5909 (2.7081) time: 0.6276 [2021-03-28 05:51:17 swin_base_patch4_window7_224] INFO: Epoch: [241] [1050/1251] eta: 0:02:07 lr: 0.000099 loss: 2.9918 (2.8362) grad_norm: 2.7422 (2.7089) time: 0.6234 [2021-03-28 05:51:23 swin_base_patch4_window7_224] INFO: Epoch: [241] [1060/1251] eta: 0:02:01 lr: 0.000099 loss: 2.9636 (2.8350) grad_norm: 2.7665 (2.7090) time: 0.6230 [2021-03-28 05:51:29 swin_base_patch4_window7_224] INFO: Epoch: [241] [1070/1251] eta: 0:01:54 lr: 0.000099 loss: 2.7517 (2.8348) grad_norm: 2.7871 (2.7134) time: 0.6265 [2021-03-28 05:51:35 swin_base_patch4_window7_224] INFO: Epoch: [241] [1080/1251] eta: 0:01:48 lr: 0.000099 loss: 2.8955 (2.8353) grad_norm: 2.5123 (2.7101) time: 0.6285 [2021-03-28 05:51:42 swin_base_patch4_window7_224] INFO: Epoch: [241] [1090/1251] eta: 0:01:42 lr: 0.000099 loss: 2.8504 (2.8347) grad_norm: 2.4900 (2.7101) time: 0.6293 [2021-03-28 05:51:48 swin_base_patch4_window7_224] INFO: Epoch: [241] [1100/1251] eta: 0:01:35 lr: 0.000099 loss: 2.6473 (2.8329) grad_norm: 2.5398 (2.7087) time: 0.6309 [2021-03-28 05:51:54 swin_base_patch4_window7_224] INFO: Epoch: [241] [1110/1251] eta: 0:01:29 lr: 0.000099 loss: 2.6473 (2.8324) grad_norm: 2.5867 (2.7101) time: 0.6270 [2021-03-28 05:52:01 swin_base_patch4_window7_224] INFO: Epoch: [241] [1120/1251] eta: 0:01:23 lr: 0.000099 loss: 2.8576 (2.8337) grad_norm: 2.6403 (2.7100) time: 0.6244 [2021-03-28 05:52:07 swin_base_patch4_window7_224] INFO: Epoch: [241] [1130/1251] eta: 0:01:16 lr: 0.000099 loss: 2.9417 (2.8324) grad_norm: 2.4299 (2.7135) time: 0.6280 [2021-03-28 05:52:13 swin_base_patch4_window7_224] INFO: Epoch: [241] [1140/1251] eta: 0:01:10 lr: 0.000099 loss: 2.7953 (2.8317) grad_norm: 2.3826 (2.7115) time: 0.6284 [2021-03-28 05:52:19 swin_base_patch4_window7_224] INFO: Epoch: [241] [1150/1251] eta: 0:01:04 lr: 0.000099 loss: 2.8341 (2.8312) grad_norm: 2.6226 (2.7136) time: 0.6265 [2021-03-28 05:52:26 swin_base_patch4_window7_224] INFO: Epoch: [241] [1160/1251] eta: 0:00:57 lr: 0.000099 loss: 2.9584 (2.8318) grad_norm: 2.7700 (2.7141) time: 0.6283 [2021-03-28 05:52:32 swin_base_patch4_window7_224] INFO: Epoch: [241] [1170/1251] eta: 0:00:51 lr: 0.000099 loss: 2.9971 (2.8331) grad_norm: 2.7436 (2.7148) time: 0.6284 [2021-03-28 05:52:38 swin_base_patch4_window7_224] INFO: Epoch: [241] [1180/1251] eta: 0:00:45 lr: 0.000099 loss: 2.9950 (2.8334) grad_norm: 2.6372 (2.7142) time: 0.6283 [2021-03-28 05:52:45 swin_base_patch4_window7_224] INFO: Epoch: [241] [1190/1251] eta: 0:00:38 lr: 0.000099 loss: 2.9871 (2.8352) grad_norm: 2.7751 (2.7169) time: 0.6296 [2021-03-28 05:52:51 swin_base_patch4_window7_224] INFO: Epoch: [241] [1200/1251] eta: 0:00:32 lr: 0.000099 loss: 2.9871 (2.8339) grad_norm: 2.6949 (2.7166) time: 0.6284 [2021-03-28 05:52:57 swin_base_patch4_window7_224] INFO: Epoch: [241] [1210/1251] eta: 0:00:26 lr: 0.000099 loss: 2.8944 (2.8344) grad_norm: 2.5906 (2.7150) time: 0.6283 [2021-03-28 05:53:03 swin_base_patch4_window7_224] INFO: Epoch: [241] [1220/1251] eta: 0:00:19 lr: 0.000099 loss: 2.8944 (2.8347) grad_norm: 2.5906 (2.7153) time: 0.6307 [2021-03-28 05:53:10 swin_base_patch4_window7_224] INFO: Epoch: [241] [1230/1251] eta: 0:00:13 lr: 0.000099 loss: 2.7647 (2.8332) grad_norm: 2.5133 (2.7136) time: 0.6292 [2021-03-28 05:53:16 swin_base_patch4_window7_224] INFO: Epoch: [241] [1240/1251] eta: 0:00:06 lr: 0.000099 loss: 2.7832 (2.8345) grad_norm: 2.5158 (2.7135) time: 0.6243 [2021-03-28 05:53:22 swin_base_patch4_window7_224] INFO: Epoch: [241] [1250/1251] eta: 0:00:00 lr: 0.000099 loss: 3.0113 (2.8360) grad_norm: 2.5560 (2.7137) time: 0.6177 [2021-03-28 05:53:34 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:09 loss: 0.9323 (0.9323) acc1: 75.0000 (75.0000) acc5: 95.3125 (95.3125) [2021-03-28 05:53:36 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7870 (0.8026) acc1: 82.8125 (81.5341) acc5: 95.3125 (95.8807) [2021-03-28 05:53:39 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8036 (0.8166) acc1: 81.2500 (81.5476) acc5: 95.3125 (95.6845) [2021-03-28 05:53:41 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8098 (0.7917) acc1: 81.2500 (82.1069) acc5: 96.8750 (96.0685) [2021-03-28 05:53:43 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7315 (0.7720) acc1: 81.2500 (82.0503) acc5: 96.8750 (96.1509) [2021-03-28 05:53:44 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7092 (0.7665) acc1: 82.8125 (82.0800) acc5: 96.8750 (96.2560) [2021-03-28 05:53:56 swin_base_patch4_window7_224] INFO: * Acc@1 82.664 Acc@5 96.228 loss 0.757 [2021-03-28 05:53:56 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.7% [2021-03-28 05:53:56 swin_base_patch4_window7_224] INFO: Max accuracy: 82.75% [2021-03-28 05:54:01 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 0/1251] eta: 1:31:04 lr: 0.000099 loss: 2.8998 (2.8998) grad_norm: 2.3868 (2.3868) time: 4.3683 [2021-03-28 05:54:07 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 10/1251] eta: 0:20:32 lr: 0.000099 loss: 2.6097 (2.6288) grad_norm: 2.8073 (2.8202) time: 0.9931 [2021-03-28 05:54:13 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 20/1251] eta: 0:16:45 lr: 0.000098 loss: 2.6450 (2.7245) grad_norm: 2.7875 (2.7977) time: 0.6392 [2021-03-28 05:54:20 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 30/1251] eta: 0:15:27 lr: 0.000098 loss: 2.8287 (2.7745) grad_norm: 2.6152 (2.7734) time: 0.6318 [2021-03-28 05:54:26 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 40/1251] eta: 0:14:38 lr: 0.000098 loss: 2.8287 (2.7703) grad_norm: 2.5159 (2.7111) time: 0.6303 [2021-03-28 05:54:32 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 50/1251] eta: 0:14:10 lr: 0.000098 loss: 2.7417 (2.7266) grad_norm: 2.4839 (2.7833) time: 0.6280 [2021-03-28 05:54:39 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 60/1251] eta: 0:13:48 lr: 0.000098 loss: 2.5659 (2.6951) grad_norm: 2.6055 (2.7962) time: 0.6334 [2021-03-28 05:54:45 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 70/1251] eta: 0:13:30 lr: 0.000098 loss: 2.8779 (2.7324) grad_norm: 2.5297 (2.7542) time: 0.6313 [2021-03-28 05:54:51 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 80/1251] eta: 0:13:17 lr: 0.000098 loss: 2.9786 (2.7640) grad_norm: 2.5576 (2.7537) time: 0.6355 [2021-03-28 05:54:58 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 90/1251] eta: 0:13:04 lr: 0.000098 loss: 3.0901 (2.7834) grad_norm: 2.5524 (2.7205) time: 0.6375 [2021-03-28 05:55:04 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 100/1251] eta: 0:12:52 lr: 0.000098 loss: 3.0826 (2.7821) grad_norm: 2.4324 (2.7113) time: 0.6308 [2021-03-28 05:55:10 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 110/1251] eta: 0:12:40 lr: 0.000098 loss: 2.9834 (2.7909) grad_norm: 2.5960 (2.7162) time: 0.6262 [2021-03-28 05:55:17 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 120/1251] eta: 0:12:30 lr: 0.000098 loss: 3.1112 (2.7996) grad_norm: 2.5960 (2.7211) time: 0.6252 [2021-03-28 05:55:23 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 130/1251] eta: 0:12:22 lr: 0.000098 loss: 3.1754 (2.8042) grad_norm: 2.5394 (2.7158) time: 0.6347 [2021-03-28 05:55:29 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 140/1251] eta: 0:12:12 lr: 0.000098 loss: 2.8319 (2.7928) grad_norm: 2.5534 (2.7098) time: 0.6331 [2021-03-28 05:55:36 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 150/1251] eta: 0:12:03 lr: 0.000098 loss: 2.8285 (2.7916) grad_norm: 2.6483 (2.7082) time: 0.6275 [2021-03-28 05:55:42 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 160/1251] eta: 0:11:55 lr: 0.000098 loss: 2.9630 (2.7983) grad_norm: 2.4069 (2.6908) time: 0.6312 [2021-03-28 05:55:48 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 170/1251] eta: 0:11:46 lr: 0.000098 loss: 2.9944 (2.8062) grad_norm: 2.4828 (2.6893) time: 0.6275 [2021-03-28 05:55:55 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 180/1251] eta: 0:11:39 lr: 0.000098 loss: 2.8136 (2.7976) grad_norm: 2.6742 (2.7143) time: 0.6335 [2021-03-28 05:56:01 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 190/1251] eta: 0:11:31 lr: 0.000098 loss: 2.7442 (2.7924) grad_norm: 2.6521 (2.7192) time: 0.6340 [2021-03-28 05:56:07 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 200/1251] eta: 0:11:24 lr: 0.000098 loss: 2.8293 (2.7955) grad_norm: 2.5733 (2.7104) time: 0.6335 [2021-03-28 05:56:14 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 210/1251] eta: 0:11:16 lr: 0.000098 loss: 2.8414 (2.7970) grad_norm: 2.5222 (2.7153) time: 0.6358 [2021-03-28 05:56:20 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 220/1251] eta: 0:11:09 lr: 0.000098 loss: 2.9468 (2.8112) grad_norm: 2.6565 (2.7113) time: 0.6278 [2021-03-28 05:56:26 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 230/1251] eta: 0:11:01 lr: 0.000098 loss: 3.1089 (2.8162) grad_norm: 2.6953 (2.7132) time: 0.6275 [2021-03-28 05:56:32 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 240/1251] eta: 0:10:54 lr: 0.000098 loss: 2.5750 (2.7976) grad_norm: 2.4532 (2.7010) time: 0.6328 [2021-03-28 05:56:39 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 250/1251] eta: 0:10:47 lr: 0.000098 loss: 2.7491 (2.8051) grad_norm: 2.4321 (2.7044) time: 0.6334 [2021-03-28 05:56:45 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 260/1251] eta: 0:10:41 lr: 0.000098 loss: 2.9952 (2.8086) grad_norm: 2.6439 (2.7004) time: 0.6372 [2021-03-28 05:56:51 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 270/1251] eta: 0:10:33 lr: 0.000098 loss: 2.7542 (2.8053) grad_norm: 2.5053 (2.6959) time: 0.6348 [2021-03-28 05:56:58 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 280/1251] eta: 0:10:27 lr: 0.000098 loss: 2.7542 (2.8078) grad_norm: 2.4980 (2.6923) time: 0.6326 [2021-03-28 05:57:04 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 290/1251] eta: 0:10:20 lr: 0.000098 loss: 2.7634 (2.8054) grad_norm: 2.5198 (2.6908) time: 0.6335 [2021-03-28 05:57:10 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 300/1251] eta: 0:10:13 lr: 0.000098 loss: 2.7891 (2.8034) grad_norm: 2.5814 (2.6926) time: 0.6328 [2021-03-28 05:57:17 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 310/1251] eta: 0:10:06 lr: 0.000098 loss: 2.7322 (2.7956) grad_norm: 2.8029 (2.6951) time: 0.6347 [2021-03-28 05:57:23 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 320/1251] eta: 0:09:59 lr: 0.000098 loss: 2.7357 (2.8016) grad_norm: 2.6712 (2.6929) time: 0.6307 [2021-03-28 05:57:29 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 330/1251] eta: 0:09:52 lr: 0.000098 loss: 2.9537 (2.8044) grad_norm: 2.4782 (2.6900) time: 0.6311 [2021-03-28 05:57:36 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 340/1251] eta: 0:09:46 lr: 0.000098 loss: 2.9808 (2.8111) grad_norm: 2.4677 (2.6877) time: 0.6406 [2021-03-28 05:57:42 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 350/1251] eta: 0:09:39 lr: 0.000098 loss: 2.9019 (2.8072) grad_norm: 2.6208 (2.6889) time: 0.6342 [2021-03-28 05:57:49 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 360/1251] eta: 0:09:33 lr: 0.000098 loss: 2.8362 (2.8055) grad_norm: 2.6303 (2.6867) time: 0.6332 [2021-03-28 05:57:55 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 370/1251] eta: 0:09:26 lr: 0.000098 loss: 2.8079 (2.8020) grad_norm: 2.4651 (2.6792) time: 0.6335 [2021-03-28 05:58:01 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 380/1251] eta: 0:09:19 lr: 0.000098 loss: 2.7626 (2.8030) grad_norm: 2.4464 (2.6801) time: 0.6236 [2021-03-28 05:58:07 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 390/1251] eta: 0:09:12 lr: 0.000098 loss: 2.6223 (2.8013) grad_norm: 2.5235 (2.6795) time: 0.6238 [2021-03-28 05:58:14 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 400/1251] eta: 0:09:06 lr: 0.000098 loss: 2.8396 (2.8003) grad_norm: 2.5235 (2.6801) time: 0.6295 [2021-03-28 05:58:20 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 410/1251] eta: 0:08:59 lr: 0.000098 loss: 2.8699 (2.8030) grad_norm: 2.7469 (2.6869) time: 0.6310 [2021-03-28 05:58:26 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 420/1251] eta: 0:08:52 lr: 0.000098 loss: 2.9728 (2.8084) grad_norm: 2.7212 (2.6851) time: 0.6269 [2021-03-28 05:58:32 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 430/1251] eta: 0:08:45 lr: 0.000098 loss: 2.8493 (2.8088) grad_norm: 2.4745 (2.6831) time: 0.6279 [2021-03-28 05:58:39 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 440/1251] eta: 0:08:39 lr: 0.000097 loss: 2.8232 (2.8113) grad_norm: 2.6264 (2.6929) time: 0.6307 [2021-03-28 05:58:45 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 450/1251] eta: 0:08:32 lr: 0.000097 loss: 3.0372 (2.8155) grad_norm: 2.6868 (2.7048) time: 0.6282 [2021-03-28 05:58:51 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 460/1251] eta: 0:08:26 lr: 0.000097 loss: 2.9265 (2.8126) grad_norm: 2.5107 (2.6982) time: 0.6271 [2021-03-28 05:58:58 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 470/1251] eta: 0:08:19 lr: 0.000097 loss: 2.8918 (2.8141) grad_norm: 2.4999 (2.6982) time: 0.6287 [2021-03-28 05:59:04 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 480/1251] eta: 0:08:12 lr: 0.000097 loss: 2.9264 (2.8139) grad_norm: 2.4999 (2.6980) time: 0.6271 [2021-03-28 05:59:10 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 490/1251] eta: 0:08:06 lr: 0.000097 loss: 2.9252 (2.8131) grad_norm: 2.6032 (2.6985) time: 0.6310 [2021-03-28 05:59:17 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 500/1251] eta: 0:07:59 lr: 0.000097 loss: 2.8613 (2.8106) grad_norm: 2.7393 (2.6984) time: 0.6330 [2021-03-28 05:59:23 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 510/1251] eta: 0:07:53 lr: 0.000097 loss: 2.8587 (2.8138) grad_norm: 2.7671 (2.7021) time: 0.6294 [2021-03-28 05:59:29 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 520/1251] eta: 0:07:46 lr: 0.000097 loss: 2.8587 (2.8164) grad_norm: 2.7671 (2.7068) time: 0.6285 [2021-03-28 05:59:35 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 530/1251] eta: 0:07:40 lr: 0.000097 loss: 2.9780 (2.8202) grad_norm: 2.5581 (2.7051) time: 0.6292 [2021-03-28 05:59:42 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 540/1251] eta: 0:07:33 lr: 0.000097 loss: 2.9424 (2.8183) grad_norm: 2.3688 (2.7001) time: 0.6283 [2021-03-28 05:59:48 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 550/1251] eta: 0:07:27 lr: 0.000097 loss: 2.7933 (2.8162) grad_norm: 2.5884 (2.7067) time: 0.6419 [2021-03-28 05:59:54 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 560/1251] eta: 0:07:21 lr: 0.000097 loss: 2.9125 (2.8176) grad_norm: 2.5884 (2.7075) time: 0.6389 [2021-03-28 06:00:01 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 570/1251] eta: 0:07:14 lr: 0.000097 loss: 2.9044 (2.8180) grad_norm: 2.5913 (2.7116) time: 0.6255 [2021-03-28 06:00:07 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 580/1251] eta: 0:07:08 lr: 0.000097 loss: 2.8666 (2.8179) grad_norm: 2.5976 (2.7083) time: 0.6278 [2021-03-28 06:00:13 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 590/1251] eta: 0:07:01 lr: 0.000097 loss: 2.9369 (2.8198) grad_norm: 2.4543 (2.7035) time: 0.6294 [2021-03-28 06:00:20 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 600/1251] eta: 0:06:55 lr: 0.000097 loss: 2.7759 (2.8172) grad_norm: 2.4305 (2.7037) time: 0.6267 [2021-03-28 06:00:26 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 610/1251] eta: 0:06:48 lr: 0.000097 loss: 2.7040 (2.8183) grad_norm: 2.5878 (2.7025) time: 0.6258 [2021-03-28 06:00:32 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 620/1251] eta: 0:06:42 lr: 0.000097 loss: 3.1399 (2.8206) grad_norm: 2.6334 (2.7043) time: 0.6290 [2021-03-28 06:00:38 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 630/1251] eta: 0:06:35 lr: 0.000097 loss: 2.9831 (2.8216) grad_norm: 2.6334 (2.7054) time: 0.6281 [2021-03-28 06:00:45 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 640/1251] eta: 0:06:29 lr: 0.000097 loss: 2.7886 (2.8179) grad_norm: 2.5040 (2.7065) time: 0.6312 [2021-03-28 06:00:51 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 650/1251] eta: 0:06:22 lr: 0.000097 loss: 2.7631 (2.8177) grad_norm: 2.7087 (2.7099) time: 0.6313 [2021-03-28 06:00:57 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 660/1251] eta: 0:06:16 lr: 0.000097 loss: 2.8659 (2.8183) grad_norm: 2.7087 (2.7101) time: 0.6247 [2021-03-28 06:01:04 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 670/1251] eta: 0:06:09 lr: 0.000097 loss: 2.9184 (2.8207) grad_norm: 2.6374 (2.7114) time: 0.6247 [2021-03-28 06:01:10 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 680/1251] eta: 0:06:03 lr: 0.000097 loss: 2.9184 (2.8189) grad_norm: 2.7584 (2.7130) time: 0.6371 [2021-03-28 06:01:16 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 690/1251] eta: 0:05:57 lr: 0.000097 loss: 2.8206 (2.8167) grad_norm: 2.7650 (2.7123) time: 0.6400 [2021-03-28 06:01:23 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 700/1251] eta: 0:05:50 lr: 0.000097 loss: 2.6143 (2.8167) grad_norm: 2.6699 (2.7177) time: 0.6289 [2021-03-28 06:01:29 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 710/1251] eta: 0:05:44 lr: 0.000097 loss: 2.6143 (2.8123) grad_norm: 2.5694 (2.7169) time: 0.6272 [2021-03-28 06:01:35 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 720/1251] eta: 0:05:37 lr: 0.000097 loss: 2.6003 (2.8109) grad_norm: 2.4641 (2.7145) time: 0.6306 [2021-03-28 06:01:42 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 730/1251] eta: 0:05:31 lr: 0.000097 loss: 2.9434 (2.8137) grad_norm: 2.6049 (2.7154) time: 0.6335 [2021-03-28 06:01:48 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 740/1251] eta: 0:05:25 lr: 0.000097 loss: 2.9219 (2.8120) grad_norm: 2.6146 (2.7162) time: 0.6461 [2021-03-28 06:01:54 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 750/1251] eta: 0:05:18 lr: 0.000097 loss: 2.9071 (2.8149) grad_norm: 2.6231 (2.7170) time: 0.6419 [2021-03-28 06:02:01 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 760/1251] eta: 0:05:12 lr: 0.000097 loss: 2.9293 (2.8172) grad_norm: 2.8451 (2.7210) time: 0.6336 [2021-03-28 06:02:07 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 770/1251] eta: 0:05:06 lr: 0.000097 loss: 2.9293 (2.8193) grad_norm: 2.7621 (2.7215) time: 0.6327 [2021-03-28 06:02:13 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 780/1251] eta: 0:04:59 lr: 0.000097 loss: 2.8976 (2.8193) grad_norm: 2.6726 (2.7197) time: 0.6311 [2021-03-28 06:02:20 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 790/1251] eta: 0:04:53 lr: 0.000097 loss: 2.8389 (2.8196) grad_norm: 2.5284 (2.7168) time: 0.6357 [2021-03-28 06:02:26 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 800/1251] eta: 0:04:46 lr: 0.000097 loss: 2.8328 (2.8204) grad_norm: 2.5265 (2.7182) time: 0.6339 [2021-03-28 06:02:32 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 810/1251] eta: 0:04:40 lr: 0.000097 loss: 2.8884 (2.8216) grad_norm: 2.5733 (2.7180) time: 0.6309 [2021-03-28 06:02:39 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 820/1251] eta: 0:04:34 lr: 0.000097 loss: 2.8513 (2.8198) grad_norm: 2.4787 (2.7161) time: 0.6273 [2021-03-28 06:02:45 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 830/1251] eta: 0:04:27 lr: 0.000097 loss: 2.7987 (2.8201) grad_norm: 2.4447 (2.7168) time: 0.6275 [2021-03-28 06:02:51 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 840/1251] eta: 0:04:21 lr: 0.000097 loss: 2.9014 (2.8196) grad_norm: 2.4839 (2.7147) time: 0.6261 [2021-03-28 06:02:57 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 850/1251] eta: 0:04:14 lr: 0.000097 loss: 2.8436 (2.8171) grad_norm: 2.4839 (2.7144) time: 0.6232 [2021-03-28 06:03:04 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 860/1251] eta: 0:04:08 lr: 0.000097 loss: 2.9276 (2.8178) grad_norm: 2.5221 (2.7124) time: 0.6274 [2021-03-28 06:03:10 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 870/1251] eta: 0:04:02 lr: 0.000096 loss: 2.7719 (2.8151) grad_norm: 2.5496 (2.7125) time: 0.6302 [2021-03-28 06:03:16 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 880/1251] eta: 0:03:55 lr: 0.000096 loss: 2.5955 (2.8150) grad_norm: 2.7206 (2.7125) time: 0.6327 [2021-03-28 06:03:23 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 890/1251] eta: 0:03:49 lr: 0.000096 loss: 2.8466 (2.8145) grad_norm: 2.6148 (2.7115) time: 0.6293 [2021-03-28 06:03:29 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 900/1251] eta: 0:03:43 lr: 0.000096 loss: 2.7771 (2.8137) grad_norm: 2.5087 (2.7096) time: 0.6324 [2021-03-28 06:03:35 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 910/1251] eta: 0:03:36 lr: 0.000096 loss: 2.8973 (2.8148) grad_norm: 2.5654 (2.7083) time: 0.6366 [2021-03-28 06:03:42 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 920/1251] eta: 0:03:30 lr: 0.000096 loss: 3.0027 (2.8140) grad_norm: 2.5767 (2.7096) time: 0.6368 [2021-03-28 06:03:48 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 930/1251] eta: 0:03:24 lr: 0.000096 loss: 2.9146 (2.8144) grad_norm: 2.5862 (2.7088) time: 0.6371 [2021-03-28 06:03:54 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 940/1251] eta: 0:03:17 lr: 0.000096 loss: 2.7311 (2.8121) grad_norm: 2.5310 (2.7123) time: 0.6279 [2021-03-28 06:04:01 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 950/1251] eta: 0:03:11 lr: 0.000096 loss: 2.6736 (2.8118) grad_norm: 2.6880 (2.7129) time: 0.6275 [2021-03-28 06:04:07 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 960/1251] eta: 0:03:04 lr: 0.000096 loss: 3.0892 (2.8142) grad_norm: 2.6711 (2.7137) time: 0.6268 [2021-03-28 06:04:13 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 970/1251] eta: 0:02:58 lr: 0.000096 loss: 3.0133 (2.8152) grad_norm: 2.5075 (2.7127) time: 0.6254 [2021-03-28 06:04:19 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 980/1251] eta: 0:02:52 lr: 0.000096 loss: 2.7808 (2.8137) grad_norm: 2.5075 (2.7158) time: 0.6280 [2021-03-28 06:04:26 swin_base_patch4_window7_224] INFO: Epoch: [242] [ 990/1251] eta: 0:02:45 lr: 0.000096 loss: 2.7808 (2.8132) grad_norm: 2.7047 (2.7194) time: 0.6270 [2021-03-28 06:04:32 swin_base_patch4_window7_224] INFO: Epoch: [242] [1000/1251] eta: 0:02:39 lr: 0.000096 loss: 2.8767 (2.8141) grad_norm: 2.7142 (2.7199) time: 0.6244 [2021-03-28 06:04:38 swin_base_patch4_window7_224] INFO: Epoch: [242] [1010/1251] eta: 0:02:33 lr: 0.000096 loss: 2.8404 (2.8133) grad_norm: 2.5006 (2.7181) time: 0.6319 [2021-03-28 06:04:45 swin_base_patch4_window7_224] INFO: Epoch: [242] [1020/1251] eta: 0:02:26 lr: 0.000096 loss: 2.7294 (2.8123) grad_norm: 2.4461 (2.7166) time: 0.6384 [2021-03-28 06:04:51 swin_base_patch4_window7_224] INFO: Epoch: [242] [1030/1251] eta: 0:02:20 lr: 0.000096 loss: 2.8253 (2.8120) grad_norm: 2.5553 (2.7180) time: 0.6343 [2021-03-28 06:04:57 swin_base_patch4_window7_224] INFO: Epoch: [242] [1040/1251] eta: 0:02:13 lr: 0.000096 loss: 2.9136 (2.8117) grad_norm: 2.7254 (2.7174) time: 0.6298 [2021-03-28 06:05:04 swin_base_patch4_window7_224] INFO: Epoch: [242] [1050/1251] eta: 0:02:07 lr: 0.000096 loss: 2.7111 (2.8090) grad_norm: 2.3411 (2.7159) time: 0.6289 [2021-03-28 06:05:10 swin_base_patch4_window7_224] INFO: Epoch: [242] [1060/1251] eta: 0:02:01 lr: 0.000096 loss: 2.7441 (2.8077) grad_norm: 2.5408 (2.7146) time: 0.6296 [2021-03-28 06:05:16 swin_base_patch4_window7_224] INFO: Epoch: [242] [1070/1251] eta: 0:01:54 lr: 0.000096 loss: 2.8536 (2.8074) grad_norm: 2.6370 (2.7142) time: 0.6255 [2021-03-28 06:05:22 swin_base_patch4_window7_224] INFO: Epoch: [242] [1080/1251] eta: 0:01:48 lr: 0.000096 loss: 2.8536 (2.8085) grad_norm: 2.5297 (2.7121) time: 0.6245 [2021-03-28 06:05:29 swin_base_patch4_window7_224] INFO: Epoch: [242] [1090/1251] eta: 0:01:42 lr: 0.000096 loss: 2.8467 (2.8085) grad_norm: 2.5557 (2.7128) time: 0.6325 [2021-03-28 06:05:35 swin_base_patch4_window7_224] INFO: Epoch: [242] [1100/1251] eta: 0:01:35 lr: 0.000096 loss: 2.6013 (2.8059) grad_norm: 2.6315 (2.7134) time: 0.6367 [2021-03-28 06:05:42 swin_base_patch4_window7_224] INFO: Epoch: [242] [1110/1251] eta: 0:01:29 lr: 0.000096 loss: 2.6013 (2.8049) grad_norm: 2.6645 (2.7126) time: 0.6382 [2021-03-28 06:05:48 swin_base_patch4_window7_224] INFO: Epoch: [242] [1120/1251] eta: 0:01:23 lr: 0.000096 loss: 2.7177 (2.8038) grad_norm: 2.5605 (2.7117) time: 0.6402 [2021-03-28 06:05:54 swin_base_patch4_window7_224] INFO: Epoch: [242] [1130/1251] eta: 0:01:16 lr: 0.000096 loss: 2.7367 (2.8027) grad_norm: 2.4199 (2.7082) time: 0.6397 [2021-03-28 06:06:01 swin_base_patch4_window7_224] INFO: Epoch: [242] [1140/1251] eta: 0:01:10 lr: 0.000096 loss: 2.7661 (2.8009) grad_norm: 2.2929 (2.7081) time: 0.6357 [2021-03-28 06:06:07 swin_base_patch4_window7_224] INFO: Epoch: [242] [1150/1251] eta: 0:01:04 lr: 0.000096 loss: 2.7075 (2.8003) grad_norm: 2.5195 (2.7079) time: 0.6300 [2021-03-28 06:06:13 swin_base_patch4_window7_224] INFO: Epoch: [242] [1160/1251] eta: 0:00:57 lr: 0.000096 loss: 2.8189 (2.8004) grad_norm: 2.5195 (2.7075) time: 0.6296 [2021-03-28 06:06:20 swin_base_patch4_window7_224] INFO: Epoch: [242] [1170/1251] eta: 0:00:51 lr: 0.000096 loss: 2.8397 (2.7996) grad_norm: 2.7203 (2.7091) time: 0.6275 [2021-03-28 06:06:26 swin_base_patch4_window7_224] INFO: Epoch: [242] [1180/1251] eta: 0:00:45 lr: 0.000096 loss: 2.7726 (2.7992) grad_norm: 2.6650 (2.7086) time: 0.6293 [2021-03-28 06:06:32 swin_base_patch4_window7_224] INFO: Epoch: [242] [1190/1251] eta: 0:00:38 lr: 0.000096 loss: 2.7726 (2.7992) grad_norm: 2.6650 (2.7091) time: 0.6345 [2021-03-28 06:06:39 swin_base_patch4_window7_224] INFO: Epoch: [242] [1200/1251] eta: 0:00:32 lr: 0.000096 loss: 2.7690 (2.7977) grad_norm: 2.7381 (2.7084) time: 0.6342 [2021-03-28 06:06:45 swin_base_patch4_window7_224] INFO: Epoch: [242] [1210/1251] eta: 0:00:26 lr: 0.000096 loss: 2.9522 (2.7986) grad_norm: 2.5519 (2.7073) time: 0.6266 [2021-03-28 06:06:51 swin_base_patch4_window7_224] INFO: Epoch: [242] [1220/1251] eta: 0:00:19 lr: 0.000096 loss: 2.9522 (2.7995) grad_norm: 2.4704 (2.7052) time: 0.6241 [2021-03-28 06:06:57 swin_base_patch4_window7_224] INFO: Epoch: [242] [1230/1251] eta: 0:00:13 lr: 0.000096 loss: 2.8182 (2.7998) grad_norm: 2.5682 (2.7062) time: 0.6281 [2021-03-28 06:07:04 swin_base_patch4_window7_224] INFO: Epoch: [242] [1240/1251] eta: 0:00:06 lr: 0.000096 loss: 2.6826 (2.7983) grad_norm: 2.5953 (2.7050) time: 0.6239 [2021-03-28 06:07:10 swin_base_patch4_window7_224] INFO: Epoch: [242] [1250/1251] eta: 0:00:00 lr: 0.000096 loss: 2.6145 (2.7968) grad_norm: 2.6250 (2.7056) time: 0.6206 [2021-03-28 06:07:21 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:25 loss: 0.6711 (0.6711) acc1: 79.6875 (79.6875) acc5: 98.4375 (98.4375) [2021-03-28 06:07:23 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:13 loss: 0.7256 (0.7828) acc1: 81.2500 (82.1023) acc5: 96.8750 (96.7330) [2021-03-28 06:07:25 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7770 (0.7898) acc1: 82.8125 (82.2173) acc5: 96.8750 (96.5774) [2021-03-28 06:07:27 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.7770 (0.7805) acc1: 82.8125 (82.5605) acc5: 96.8750 (96.3710) [2021-03-28 06:07:29 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7996 (0.7766) acc1: 81.2500 (82.6982) acc5: 96.8750 (96.3796) [2021-03-28 06:07:31 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8008 (0.7814) acc1: 79.6875 (82.3680) acc5: 96.8750 (96.3840) [2021-03-28 06:07:45 swin_base_patch4_window7_224] INFO: * Acc@1 82.604 Acc@5 96.248 loss 0.770 [2021-03-28 06:07:45 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.6% [2021-03-28 06:07:45 swin_base_patch4_window7_224] INFO: Max accuracy: 82.75% [2021-03-28 06:07:50 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 0/1251] eta: 1:28:39 lr: 0.000096 loss: 2.6355 (2.6355) grad_norm: 4.7211 (4.7211) time: 4.2523 [2021-03-28 06:07:56 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 10/1251] eta: 0:20:18 lr: 0.000096 loss: 3.0558 (2.9997) grad_norm: 2.8640 (2.9020) time: 0.9818 [2021-03-28 06:08:03 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 20/1251] eta: 0:16:48 lr: 0.000096 loss: 3.0751 (3.0577) grad_norm: 2.6056 (2.7939) time: 0.6477 [2021-03-28 06:08:09 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 30/1251] eta: 0:15:26 lr: 0.000096 loss: 3.0524 (3.0150) grad_norm: 2.4684 (2.7352) time: 0.6356 [2021-03-28 06:08:15 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 40/1251] eta: 0:14:40 lr: 0.000096 loss: 2.7250 (2.9473) grad_norm: 2.5092 (2.7308) time: 0.6298 [2021-03-28 06:08:21 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 50/1251] eta: 0:14:10 lr: 0.000095 loss: 2.8890 (2.9628) grad_norm: 2.5092 (2.6890) time: 0.6292 [2021-03-28 06:08:28 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 60/1251] eta: 0:13:47 lr: 0.000095 loss: 3.0041 (2.9432) grad_norm: 2.5336 (2.6870) time: 0.6279 [2021-03-28 06:08:34 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 70/1251] eta: 0:13:30 lr: 0.000095 loss: 2.7590 (2.8872) grad_norm: 2.5139 (2.6591) time: 0.6315 [2021-03-28 06:08:40 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 80/1251] eta: 0:13:14 lr: 0.000095 loss: 2.8501 (2.8850) grad_norm: 2.5741 (2.6871) time: 0.6302 [2021-03-28 06:08:47 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 90/1251] eta: 0:13:01 lr: 0.000095 loss: 2.8508 (2.8723) grad_norm: 2.6946 (2.6902) time: 0.6281 [2021-03-28 06:08:53 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 100/1251] eta: 0:12:49 lr: 0.000095 loss: 2.9147 (2.8852) grad_norm: 2.6881 (2.7353) time: 0.6297 [2021-03-28 06:08:59 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 110/1251] eta: 0:12:39 lr: 0.000095 loss: 2.8639 (2.8665) grad_norm: 2.6247 (2.7396) time: 0.6320 [2021-03-28 06:09:06 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 120/1251] eta: 0:12:29 lr: 0.000095 loss: 2.7429 (2.8578) grad_norm: 2.5056 (2.7273) time: 0.6314 [2021-03-28 06:09:12 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 130/1251] eta: 0:12:19 lr: 0.000095 loss: 2.7787 (2.8613) grad_norm: 2.5056 (2.7248) time: 0.6258 [2021-03-28 06:09:18 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 140/1251] eta: 0:12:10 lr: 0.000095 loss: 2.8544 (2.8640) grad_norm: 2.7556 (2.7375) time: 0.6244 [2021-03-28 06:09:24 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 150/1251] eta: 0:12:01 lr: 0.000095 loss: 2.8672 (2.8566) grad_norm: 2.5611 (2.7216) time: 0.6282 [2021-03-28 06:09:31 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 160/1251] eta: 0:11:53 lr: 0.000095 loss: 2.9479 (2.8538) grad_norm: 2.5872 (2.7460) time: 0.6295 [2021-03-28 06:09:37 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 170/1251] eta: 0:11:45 lr: 0.000095 loss: 2.7825 (2.8511) grad_norm: 2.6242 (2.7396) time: 0.6282 [2021-03-28 06:09:43 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 180/1251] eta: 0:11:37 lr: 0.000095 loss: 2.7921 (2.8471) grad_norm: 2.5052 (2.7322) time: 0.6318 [2021-03-28 06:09:50 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 190/1251] eta: 0:11:29 lr: 0.000095 loss: 2.8915 (2.8480) grad_norm: 2.6374 (2.7394) time: 0.6317 [2021-03-28 06:09:56 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 200/1251] eta: 0:11:22 lr: 0.000095 loss: 2.8915 (2.8483) grad_norm: 2.5791 (2.7281) time: 0.6284 [2021-03-28 06:10:02 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 210/1251] eta: 0:11:14 lr: 0.000095 loss: 3.0058 (2.8565) grad_norm: 2.5139 (2.7206) time: 0.6251 [2021-03-28 06:10:08 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 220/1251] eta: 0:11:07 lr: 0.000095 loss: 3.0365 (2.8572) grad_norm: 2.5957 (2.7180) time: 0.6276 [2021-03-28 06:10:15 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 230/1251] eta: 0:11:00 lr: 0.000095 loss: 2.7964 (2.8481) grad_norm: 2.5588 (2.7093) time: 0.6328 [2021-03-28 06:10:21 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 240/1251] eta: 0:10:53 lr: 0.000095 loss: 2.6567 (2.8424) grad_norm: 2.5373 (2.7122) time: 0.6353 [2021-03-28 06:10:27 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 250/1251] eta: 0:10:45 lr: 0.000095 loss: 2.9188 (2.8455) grad_norm: 2.5655 (2.7080) time: 0.6288 [2021-03-28 06:10:34 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 260/1251] eta: 0:10:38 lr: 0.000095 loss: 2.9619 (2.8447) grad_norm: 2.7168 (2.7169) time: 0.6249 [2021-03-28 06:10:40 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 270/1251] eta: 0:10:31 lr: 0.000095 loss: 2.9827 (2.8475) grad_norm: 2.9073 (2.7246) time: 0.6260 [2021-03-28 06:10:46 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 280/1251] eta: 0:10:24 lr: 0.000095 loss: 2.9827 (2.8424) grad_norm: 2.6436 (2.7361) time: 0.6284 [2021-03-28 06:10:52 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 290/1251] eta: 0:10:17 lr: 0.000095 loss: 2.9335 (2.8461) grad_norm: 2.5059 (2.7401) time: 0.6291 [2021-03-28 06:10:59 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 300/1251] eta: 0:10:10 lr: 0.000095 loss: 2.9327 (2.8477) grad_norm: 2.5832 (2.7408) time: 0.6282 [2021-03-28 06:11:05 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 310/1251] eta: 0:10:04 lr: 0.000095 loss: 2.9179 (2.8489) grad_norm: 2.5261 (2.7393) time: 0.6345 [2021-03-28 06:11:11 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 320/1251] eta: 0:09:57 lr: 0.000095 loss: 2.8820 (2.8473) grad_norm: 2.5835 (2.7716) time: 0.6339 [2021-03-28 06:11:18 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 330/1251] eta: 0:09:50 lr: 0.000095 loss: 2.9041 (2.8510) grad_norm: 2.4705 (2.7744) time: 0.6289 [2021-03-28 06:11:24 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 340/1251] eta: 0:09:44 lr: 0.000095 loss: 2.9270 (2.8462) grad_norm: 2.3763 (2.7665) time: 0.6293 [2021-03-28 06:11:30 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 350/1251] eta: 0:09:37 lr: 0.000095 loss: 2.8816 (2.8456) grad_norm: 2.3763 (2.7640) time: 0.6324 [2021-03-28 06:11:37 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 360/1251] eta: 0:09:30 lr: 0.000095 loss: 2.8283 (2.8432) grad_norm: 2.4657 (2.7581) time: 0.6277 [2021-03-28 06:11:43 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 370/1251] eta: 0:09:23 lr: 0.000095 loss: 2.7111 (2.8450) grad_norm: 2.3780 (2.7510) time: 0.6265 [2021-03-28 06:11:49 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 380/1251] eta: 0:09:17 lr: 0.000095 loss: 3.0298 (2.8485) grad_norm: 2.6134 (2.7541) time: 0.6305 [2021-03-28 06:11:56 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 390/1251] eta: 0:09:10 lr: 0.000095 loss: 2.9489 (2.8516) grad_norm: 2.7234 (2.7560) time: 0.6281 [2021-03-28 06:12:02 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 400/1251] eta: 0:09:04 lr: 0.000095 loss: 3.0227 (2.8570) grad_norm: 2.7943 (2.7600) time: 0.6335 [2021-03-28 06:12:08 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 410/1251] eta: 0:08:57 lr: 0.000095 loss: 3.0017 (2.8587) grad_norm: 2.7946 (2.7665) time: 0.6383 [2021-03-28 06:12:14 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 420/1251] eta: 0:08:51 lr: 0.000095 loss: 2.8384 (2.8531) grad_norm: 2.5274 (2.7590) time: 0.6289 [2021-03-28 06:12:21 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 430/1251] eta: 0:08:44 lr: 0.000095 loss: 2.6845 (2.8523) grad_norm: 2.5774 (2.7586) time: 0.6251 [2021-03-28 06:12:27 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 440/1251] eta: 0:08:37 lr: 0.000095 loss: 2.6693 (2.8440) grad_norm: 2.6302 (2.7561) time: 0.6266 [2021-03-28 06:12:33 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 450/1251] eta: 0:08:31 lr: 0.000095 loss: 2.7086 (2.8403) grad_norm: 2.5811 (2.7532) time: 0.6327 [2021-03-28 06:12:40 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 460/1251] eta: 0:08:24 lr: 0.000095 loss: 2.7836 (2.8390) grad_norm: 2.5903 (2.7498) time: 0.6369 [2021-03-28 06:12:46 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 470/1251] eta: 0:08:18 lr: 0.000095 loss: 2.8830 (2.8379) grad_norm: 2.5724 (2.7508) time: 0.6300 [2021-03-28 06:12:52 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 480/1251] eta: 0:08:11 lr: 0.000094 loss: 2.8821 (2.8350) grad_norm: 2.6575 (2.7488) time: 0.6289 [2021-03-28 06:12:59 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 490/1251] eta: 0:08:05 lr: 0.000094 loss: 2.8821 (2.8368) grad_norm: 2.6448 (2.7474) time: 0.6278 [2021-03-28 06:13:05 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 500/1251] eta: 0:07:58 lr: 0.000094 loss: 3.0001 (2.8389) grad_norm: 2.5913 (2.7443) time: 0.6266 [2021-03-28 06:13:11 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 510/1251] eta: 0:07:52 lr: 0.000094 loss: 2.9574 (2.8407) grad_norm: 2.6096 (2.7537) time: 0.6325 [2021-03-28 06:13:18 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 520/1251] eta: 0:07:45 lr: 0.000094 loss: 2.9284 (2.8410) grad_norm: 2.7126 (2.7559) time: 0.6354 [2021-03-28 06:13:24 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 530/1251] eta: 0:07:39 lr: 0.000094 loss: 2.8532 (2.8406) grad_norm: 2.6839 (2.7542) time: 0.6300 [2021-03-28 06:13:30 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 540/1251] eta: 0:07:32 lr: 0.000094 loss: 2.9390 (2.8435) grad_norm: 2.6839 (2.7549) time: 0.6253 [2021-03-28 06:13:37 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 550/1251] eta: 0:07:26 lr: 0.000094 loss: 3.0505 (2.8433) grad_norm: 2.7634 (2.7553) time: 0.6334 [2021-03-28 06:13:43 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 560/1251] eta: 0:07:20 lr: 0.000094 loss: 2.6524 (2.8403) grad_norm: 2.7634 (2.7693) time: 0.6365 [2021-03-28 06:13:49 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 570/1251] eta: 0:07:13 lr: 0.000094 loss: 2.6759 (2.8375) grad_norm: 2.8490 (2.7695) time: 0.6335 [2021-03-28 06:13:56 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 580/1251] eta: 0:07:07 lr: 0.000094 loss: 2.8484 (2.8384) grad_norm: 2.7568 (2.7679) time: 0.6386 [2021-03-28 06:14:02 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 590/1251] eta: 0:07:01 lr: 0.000094 loss: 2.9833 (2.8389) grad_norm: 2.7258 (2.7794) time: 0.6394 [2021-03-28 06:14:08 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 600/1251] eta: 0:06:54 lr: 0.000094 loss: 2.8275 (2.8384) grad_norm: 2.6184 (2.7765) time: 0.6384 [2021-03-28 06:14:15 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 610/1251] eta: 0:06:48 lr: 0.000094 loss: 2.8139 (2.8373) grad_norm: 2.4821 (2.7750) time: 0.6317 [2021-03-28 06:14:21 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 620/1251] eta: 0:06:41 lr: 0.000094 loss: 2.9798 (2.8403) grad_norm: 2.4948 (2.7760) time: 0.6229 [2021-03-28 06:14:27 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 630/1251] eta: 0:06:35 lr: 0.000094 loss: 2.9638 (2.8398) grad_norm: 2.7376 (2.7768) time: 0.6215 [2021-03-28 06:14:33 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 640/1251] eta: 0:06:28 lr: 0.000094 loss: 2.8245 (2.8372) grad_norm: 2.6645 (2.7756) time: 0.6250 [2021-03-28 06:14:40 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 650/1251] eta: 0:06:22 lr: 0.000094 loss: 2.8513 (2.8357) grad_norm: 2.7405 (2.7834) time: 0.6301 [2021-03-28 06:14:46 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 660/1251] eta: 0:06:16 lr: 0.000094 loss: 2.8046 (2.8328) grad_norm: 2.7935 (2.7824) time: 0.6346 [2021-03-28 06:14:52 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 670/1251] eta: 0:06:09 lr: 0.000094 loss: 2.9832 (2.8351) grad_norm: 2.7895 (2.7887) time: 0.6347 [2021-03-28 06:14:59 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 680/1251] eta: 0:06:03 lr: 0.000094 loss: 2.9835 (2.8338) grad_norm: 2.8824 (2.7902) time: 0.6280 [2021-03-28 06:15:05 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 690/1251] eta: 0:05:56 lr: 0.000094 loss: 2.8278 (2.8333) grad_norm: 2.6689 (2.7897) time: 0.6248 [2021-03-28 06:15:11 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 700/1251] eta: 0:05:50 lr: 0.000094 loss: 2.8013 (2.8312) grad_norm: 2.5538 (2.7876) time: 0.6278 [2021-03-28 06:15:18 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 710/1251] eta: 0:05:43 lr: 0.000094 loss: 2.6992 (2.8287) grad_norm: 2.5538 (2.7845) time: 0.6364 [2021-03-28 06:15:24 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 720/1251] eta: 0:05:37 lr: 0.000094 loss: 2.7448 (2.8284) grad_norm: 2.5590 (2.7832) time: 0.6350 [2021-03-28 06:15:30 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 730/1251] eta: 0:05:31 lr: 0.000094 loss: 2.8986 (2.8295) grad_norm: 2.5617 (2.7840) time: 0.6275 [2021-03-28 06:15:36 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 740/1251] eta: 0:05:24 lr: 0.000094 loss: 2.8986 (2.8250) grad_norm: 2.5229 (2.7813) time: 0.6267 [2021-03-28 06:15:43 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 750/1251] eta: 0:05:18 lr: 0.000094 loss: 2.5280 (2.8229) grad_norm: 2.5229 (2.7812) time: 0.6328 [2021-03-28 06:15:49 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 760/1251] eta: 0:05:12 lr: 0.000094 loss: 2.7844 (2.8223) grad_norm: 2.7078 (2.7806) time: 0.6334 [2021-03-28 06:15:55 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 770/1251] eta: 0:05:05 lr: 0.000094 loss: 2.9879 (2.8237) grad_norm: 2.6485 (2.7806) time: 0.6308 [2021-03-28 06:16:02 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 780/1251] eta: 0:04:59 lr: 0.000094 loss: 2.9638 (2.8210) grad_norm: 2.5845 (2.7769) time: 0.6296 [2021-03-28 06:16:08 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 790/1251] eta: 0:04:52 lr: 0.000094 loss: 2.9499 (2.8224) grad_norm: 2.5026 (2.7754) time: 0.6310 [2021-03-28 06:16:14 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 800/1251] eta: 0:04:46 lr: 0.000094 loss: 3.0486 (2.8237) grad_norm: 2.5734 (2.7729) time: 0.6333 [2021-03-28 06:16:21 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 810/1251] eta: 0:04:40 lr: 0.000094 loss: 2.9589 (2.8234) grad_norm: 2.6200 (2.7726) time: 0.6281 [2021-03-28 06:16:27 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 820/1251] eta: 0:04:33 lr: 0.000094 loss: 2.7730 (2.8211) grad_norm: 2.6195 (2.7714) time: 0.6309 [2021-03-28 06:16:33 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 830/1251] eta: 0:04:27 lr: 0.000094 loss: 2.7468 (2.8206) grad_norm: 2.6052 (2.7737) time: 0.6322 [2021-03-28 06:16:40 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 840/1251] eta: 0:04:20 lr: 0.000094 loss: 2.8599 (2.8208) grad_norm: 2.5547 (2.7724) time: 0.6305 [2021-03-28 06:16:46 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 850/1251] eta: 0:04:14 lr: 0.000094 loss: 2.8599 (2.8217) grad_norm: 2.5968 (2.7720) time: 0.6321 [2021-03-28 06:16:52 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 860/1251] eta: 0:04:08 lr: 0.000094 loss: 2.7535 (2.8193) grad_norm: 2.5060 (2.7691) time: 0.6266 [2021-03-28 06:16:58 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 870/1251] eta: 0:04:01 lr: 0.000094 loss: 2.7132 (2.8185) grad_norm: 2.5060 (2.7680) time: 0.6233 [2021-03-28 06:17:05 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 880/1251] eta: 0:03:55 lr: 0.000094 loss: 2.7095 (2.8172) grad_norm: 2.7002 (2.7671) time: 0.6290 [2021-03-28 06:17:11 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 890/1251] eta: 0:03:49 lr: 0.000094 loss: 2.7973 (2.8196) grad_norm: 2.6046 (2.7668) time: 0.6308 [2021-03-28 06:17:17 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 900/1251] eta: 0:03:42 lr: 0.000094 loss: 2.9623 (2.8184) grad_norm: 2.6046 (2.7653) time: 0.6255 [2021-03-28 06:17:24 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 910/1251] eta: 0:03:36 lr: 0.000093 loss: 3.0227 (2.8221) grad_norm: 2.6196 (2.7670) time: 0.6254 [2021-03-28 06:17:30 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 920/1251] eta: 0:03:29 lr: 0.000093 loss: 3.0853 (2.8233) grad_norm: 2.9228 (2.7703) time: 0.6273 [2021-03-28 06:17:36 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 930/1251] eta: 0:03:23 lr: 0.000093 loss: 2.9955 (2.8243) grad_norm: 2.6142 (2.7683) time: 0.6261 [2021-03-28 06:17:42 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 940/1251] eta: 0:03:17 lr: 0.000093 loss: 2.9610 (2.8264) grad_norm: 2.6142 (2.7691) time: 0.6317 [2021-03-28 06:17:49 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 950/1251] eta: 0:03:10 lr: 0.000093 loss: 2.9677 (2.8252) grad_norm: 2.6809 (2.7704) time: 0.6379 [2021-03-28 06:17:55 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 960/1251] eta: 0:03:04 lr: 0.000093 loss: 3.0101 (2.8261) grad_norm: 2.7090 (2.7743) time: 0.6322 [2021-03-28 06:18:01 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 970/1251] eta: 0:02:58 lr: 0.000093 loss: 2.9041 (2.8254) grad_norm: 2.6935 (2.7741) time: 0.6293 [2021-03-28 06:18:08 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 980/1251] eta: 0:02:51 lr: 0.000093 loss: 2.8793 (2.8258) grad_norm: 2.5768 (2.7729) time: 0.6324 [2021-03-28 06:18:14 swin_base_patch4_window7_224] INFO: Epoch: [243] [ 990/1251] eta: 0:02:45 lr: 0.000093 loss: 2.8372 (2.8276) grad_norm: 2.7884 (2.7787) time: 0.6317 [2021-03-28 06:18:20 swin_base_patch4_window7_224] INFO: Epoch: [243] [1000/1251] eta: 0:02:39 lr: 0.000093 loss: 2.8359 (2.8276) grad_norm: 2.8820 (2.7776) time: 0.6312 [2021-03-28 06:18:27 swin_base_patch4_window7_224] INFO: Epoch: [243] [1010/1251] eta: 0:02:32 lr: 0.000093 loss: 2.9232 (2.8273) grad_norm: 2.6675 (2.7768) time: 0.6306 [2021-03-28 06:18:33 swin_base_patch4_window7_224] INFO: Epoch: [243] [1020/1251] eta: 0:02:26 lr: 0.000093 loss: 2.9540 (2.8281) grad_norm: 2.5762 (2.7752) time: 0.6340 [2021-03-28 06:18:39 swin_base_patch4_window7_224] INFO: Epoch: [243] [1030/1251] eta: 0:02:20 lr: 0.000093 loss: 2.9650 (2.8299) grad_norm: 2.5580 (2.7734) time: 0.6317 [2021-03-28 06:18:46 swin_base_patch4_window7_224] INFO: Epoch: [243] [1040/1251] eta: 0:02:13 lr: 0.000093 loss: 3.0631 (2.8316) grad_norm: 2.5627 (2.7716) time: 0.6253 [2021-03-28 06:18:52 swin_base_patch4_window7_224] INFO: Epoch: [243] [1050/1251] eta: 0:02:07 lr: 0.000093 loss: 2.8746 (2.8313) grad_norm: 2.4813 (2.7692) time: 0.6253 [2021-03-28 06:18:58 swin_base_patch4_window7_224] INFO: Epoch: [243] [1060/1251] eta: 0:02:01 lr: 0.000093 loss: 2.7983 (2.8301) grad_norm: 2.4691 (2.7674) time: 0.6290 [2021-03-28 06:19:04 swin_base_patch4_window7_224] INFO: Epoch: [243] [1070/1251] eta: 0:01:54 lr: 0.000093 loss: 2.9232 (2.8312) grad_norm: 2.5593 (2.7693) time: 0.6310 [2021-03-28 06:19:11 swin_base_patch4_window7_224] INFO: Epoch: [243] [1080/1251] eta: 0:01:48 lr: 0.000093 loss: 3.0091 (2.8326) grad_norm: 2.6380 (2.7725) time: 0.6291 [2021-03-28 06:19:17 swin_base_patch4_window7_224] INFO: Epoch: [243] [1090/1251] eta: 0:01:42 lr: 0.000093 loss: 2.9942 (2.8325) grad_norm: 2.9641 (2.7726) time: 0.6263 [2021-03-28 06:19:23 swin_base_patch4_window7_224] INFO: Epoch: [243] [1100/1251] eta: 0:01:35 lr: 0.000093 loss: 2.9496 (2.8316) grad_norm: 2.6868 (2.7733) time: 0.6259 [2021-03-28 06:19:30 swin_base_patch4_window7_224] INFO: Epoch: [243] [1110/1251] eta: 0:01:29 lr: 0.000093 loss: 2.9496 (2.8321) grad_norm: 2.6868 (2.7726) time: 0.6307 [2021-03-28 06:19:36 swin_base_patch4_window7_224] INFO: Epoch: [243] [1120/1251] eta: 0:01:23 lr: 0.000093 loss: 2.7817 (2.8284) grad_norm: 2.5963 (2.7721) time: 0.6371 [2021-03-28 06:19:42 swin_base_patch4_window7_224] INFO: Epoch: [243] [1130/1251] eta: 0:01:16 lr: 0.000093 loss: 2.7817 (2.8298) grad_norm: 2.5963 (2.7718) time: 0.6358 [2021-03-28 06:19:49 swin_base_patch4_window7_224] INFO: Epoch: [243] [1140/1251] eta: 0:01:10 lr: 0.000093 loss: 3.0126 (2.8290) grad_norm: 2.6924 (2.7720) time: 0.6325 [2021-03-28 06:19:55 swin_base_patch4_window7_224] INFO: Epoch: [243] [1150/1251] eta: 0:01:03 lr: 0.000093 loss: 2.9714 (2.8284) grad_norm: 2.6924 (inf) time: 0.6247 [2021-03-28 06:20:01 swin_base_patch4_window7_224] INFO: Epoch: [243] [1160/1251] eta: 0:00:57 lr: 0.000093 loss: 2.6619 (2.8259) grad_norm: 2.6470 (inf) time: 0.6239 [2021-03-28 06:20:07 swin_base_patch4_window7_224] INFO: Epoch: [243] [1170/1251] eta: 0:00:51 lr: 0.000093 loss: 2.4959 (2.8236) grad_norm: 2.7743 (inf) time: 0.6270 [2021-03-28 06:20:14 swin_base_patch4_window7_224] INFO: Epoch: [243] [1180/1251] eta: 0:00:44 lr: 0.000093 loss: 2.6207 (2.8228) grad_norm: 2.7573 (inf) time: 0.6280 [2021-03-28 06:20:20 swin_base_patch4_window7_224] INFO: Epoch: [243] [1190/1251] eta: 0:00:38 lr: 0.000093 loss: 2.5747 (2.8202) grad_norm: 2.5732 (inf) time: 0.6295 [2021-03-28 06:20:26 swin_base_patch4_window7_224] INFO: Epoch: [243] [1200/1251] eta: 0:00:32 lr: 0.000093 loss: 2.3643 (2.8181) grad_norm: 2.5223 (inf) time: 0.6299 [2021-03-28 06:20:33 swin_base_patch4_window7_224] INFO: Epoch: [243] [1210/1251] eta: 0:00:25 lr: 0.000093 loss: 2.6285 (2.8172) grad_norm: 2.4410 (inf) time: 0.6309 [2021-03-28 06:20:39 swin_base_patch4_window7_224] INFO: Epoch: [243] [1220/1251] eta: 0:00:19 lr: 0.000093 loss: 2.8312 (2.8177) grad_norm: 2.4410 (inf) time: 0.6263 [2021-03-28 06:20:45 swin_base_patch4_window7_224] INFO: Epoch: [243] [1230/1251] eta: 0:00:13 lr: 0.000093 loss: 2.8737 (2.8189) grad_norm: 2.6988 (inf) time: 0.6251 [2021-03-28 06:20:51 swin_base_patch4_window7_224] INFO: Epoch: [243] [1240/1251] eta: 0:00:06 lr: 0.000093 loss: 2.8737 (2.8174) grad_norm: 2.6988 (inf) time: 0.6275 [2021-03-28 06:20:58 swin_base_patch4_window7_224] INFO: Epoch: [243] [1250/1251] eta: 0:00:00 lr: 0.000093 loss: 2.7467 (2.8170) grad_norm: 2.6732 (inf) time: 0.6255 [2021-03-28 06:21:11 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:42 loss: 1.0353 (1.0353) acc1: 75.0000 (75.0000) acc5: 95.3125 (95.3125) [2021-03-28 06:21:13 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7357 (0.7367) acc1: 81.2500 (81.8182) acc5: 98.4375 (97.1591) [2021-03-28 06:21:14 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8026 (0.7882) acc1: 81.2500 (81.7708) acc5: 96.8750 (96.2054) [2021-03-28 06:21:17 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7530 (0.7535) acc1: 81.2500 (82.2581) acc5: 96.8750 (96.5222) [2021-03-28 06:21:19 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7315 (0.7725) acc1: 81.2500 (82.0503) acc5: 96.8750 (96.1890) [2021-03-28 06:21:20 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7928 (0.7752) acc1: 79.6875 (82.0160) acc5: 95.3125 (96.1280) [2021-03-28 06:21:33 swin_base_patch4_window7_224] INFO: * Acc@1 82.782 Acc@5 96.220 loss 0.758 [2021-03-28 06:21:33 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.8% [2021-03-28 06:21:33 swin_base_patch4_window7_224] INFO: Max accuracy: 82.78% [2021-03-28 06:21:38 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 0/1251] eta: 1:31:22 lr: 0.000093 loss: 2.4189 (2.4189) grad_norm: 2.8076 (2.8076) time: 4.3826 [2021-03-28 06:21:44 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 10/1251] eta: 0:20:12 lr: 0.000093 loss: 2.8780 (2.8465) grad_norm: 2.7151 (3.1924) time: 0.9773 [2021-03-28 06:21:50 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 20/1251] eta: 0:16:36 lr: 0.000093 loss: 2.9557 (2.8717) grad_norm: 2.6453 (3.0341) time: 0.6311 [2021-03-28 06:21:56 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 30/1251] eta: 0:15:14 lr: 0.000093 loss: 3.0230 (2.8991) grad_norm: 2.6453 (2.9179) time: 0.6239 [2021-03-28 06:22:03 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 40/1251] eta: 0:14:37 lr: 0.000093 loss: 3.0343 (2.8828) grad_norm: 2.6591 (2.9047) time: 0.6355 [2021-03-28 06:22:09 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 50/1251] eta: 0:14:08 lr: 0.000093 loss: 2.9001 (2.8430) grad_norm: 2.7916 (2.9458) time: 0.6401 [2021-03-28 06:22:16 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 60/1251] eta: 0:13:47 lr: 0.000093 loss: 2.9001 (2.8800) grad_norm: 2.9247 (2.9387) time: 0.6323 [2021-03-28 06:22:22 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 70/1251] eta: 0:13:28 lr: 0.000093 loss: 3.0042 (2.8962) grad_norm: 3.0461 (2.9674) time: 0.6277 [2021-03-28 06:22:28 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 80/1251] eta: 0:13:14 lr: 0.000093 loss: 3.0042 (2.8957) grad_norm: 2.9517 (2.9719) time: 0.6297 [2021-03-28 06:22:34 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 90/1251] eta: 0:13:01 lr: 0.000092 loss: 2.9981 (2.8720) grad_norm: 2.5123 (2.9301) time: 0.6340 [2021-03-28 06:22:41 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 100/1251] eta: 0:12:49 lr: 0.000092 loss: 2.9360 (2.8722) grad_norm: 2.4683 (2.9082) time: 0.6281 [2021-03-28 06:22:47 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 110/1251] eta: 0:12:39 lr: 0.000092 loss: 3.0039 (2.8811) grad_norm: 2.5676 (2.8855) time: 0.6306 [2021-03-28 06:22:53 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 120/1251] eta: 0:12:29 lr: 0.000092 loss: 2.9973 (2.8732) grad_norm: 2.5719 (2.8645) time: 0.6311 [2021-03-28 06:23:00 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 130/1251] eta: 0:12:20 lr: 0.000092 loss: 2.9738 (2.8726) grad_norm: 2.5882 (2.8533) time: 0.6313 [2021-03-28 06:23:06 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 140/1251] eta: 0:12:11 lr: 0.000092 loss: 2.8420 (2.8538) grad_norm: 2.6417 (2.8386) time: 0.6337 [2021-03-28 06:23:12 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 150/1251] eta: 0:12:02 lr: 0.000092 loss: 2.7202 (2.8476) grad_norm: 2.6027 (2.8340) time: 0.6325 [2021-03-28 06:23:19 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 160/1251] eta: 0:11:55 lr: 0.000092 loss: 2.8322 (2.8492) grad_norm: 2.6634 (2.8264) time: 0.6370 [2021-03-28 06:23:25 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 170/1251] eta: 0:11:47 lr: 0.000092 loss: 2.8676 (2.8544) grad_norm: 2.6634 (2.8265) time: 0.6366 [2021-03-28 06:23:31 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 180/1251] eta: 0:11:39 lr: 0.000092 loss: 2.8676 (2.8494) grad_norm: 2.8220 (2.8431) time: 0.6363 [2021-03-28 06:23:38 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 190/1251] eta: 0:11:32 lr: 0.000092 loss: 2.6230 (2.8382) grad_norm: 2.8089 (2.8403) time: 0.6345 [2021-03-28 06:23:44 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 200/1251] eta: 0:11:24 lr: 0.000092 loss: 2.6046 (2.8291) grad_norm: 2.5887 (2.8246) time: 0.6341 [2021-03-28 06:23:50 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 210/1251] eta: 0:11:16 lr: 0.000092 loss: 2.7523 (2.8324) grad_norm: 2.5611 (2.9085) time: 0.6322 [2021-03-28 06:23:57 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 220/1251] eta: 0:11:09 lr: 0.000092 loss: 2.7523 (2.8233) grad_norm: 2.5611 (2.9040) time: 0.6281 [2021-03-28 06:24:03 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 230/1251] eta: 0:11:02 lr: 0.000092 loss: 2.6858 (2.8138) grad_norm: 2.9007 (2.9032) time: 0.6310 [2021-03-28 06:24:09 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 240/1251] eta: 0:10:54 lr: 0.000092 loss: 2.7617 (2.8171) grad_norm: 2.6648 (2.8954) time: 0.6287 [2021-03-28 06:24:16 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 250/1251] eta: 0:10:47 lr: 0.000092 loss: 3.0087 (2.8165) grad_norm: 2.6898 (2.9130) time: 0.6270 [2021-03-28 06:24:22 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 260/1251] eta: 0:10:40 lr: 0.000092 loss: 2.8716 (2.8141) grad_norm: 2.8485 (2.9180) time: 0.6287 [2021-03-28 06:24:28 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 270/1251] eta: 0:10:33 lr: 0.000092 loss: 2.9437 (2.8202) grad_norm: 2.5422 (2.9084) time: 0.6276 [2021-03-28 06:24:34 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 280/1251] eta: 0:10:26 lr: 0.000092 loss: 2.8995 (2.8143) grad_norm: 2.7414 (2.9110) time: 0.6269 [2021-03-28 06:24:41 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 290/1251] eta: 0:10:18 lr: 0.000092 loss: 2.8995 (2.8219) grad_norm: 2.7968 (2.9073) time: 0.6242 [2021-03-28 06:24:47 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 300/1251] eta: 0:10:12 lr: 0.000092 loss: 3.0300 (2.8236) grad_norm: 2.7668 (2.9088) time: 0.6292 [2021-03-28 06:24:53 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 310/1251] eta: 0:10:05 lr: 0.000092 loss: 2.9389 (2.8238) grad_norm: 2.5637 (2.8959) time: 0.6348 [2021-03-28 06:25:00 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 320/1251] eta: 0:09:58 lr: 0.000092 loss: 2.9961 (2.8279) grad_norm: 2.5517 (2.8902) time: 0.6329 [2021-03-28 06:25:06 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 330/1251] eta: 0:09:51 lr: 0.000092 loss: 2.8125 (2.8213) grad_norm: 2.6893 (2.9040) time: 0.6316 [2021-03-28 06:25:12 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 340/1251] eta: 0:09:44 lr: 0.000092 loss: 2.7205 (2.8195) grad_norm: 2.6446 (2.8981) time: 0.6264 [2021-03-28 06:25:18 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 350/1251] eta: 0:09:38 lr: 0.000092 loss: 2.7205 (2.8162) grad_norm: 2.6432 (2.8924) time: 0.6235 [2021-03-28 06:25:25 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 360/1251] eta: 0:09:31 lr: 0.000092 loss: 2.9639 (2.8240) grad_norm: 2.6265 (2.8898) time: 0.6326 [2021-03-28 06:25:31 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 370/1251] eta: 0:09:25 lr: 0.000092 loss: 2.9256 (2.8144) grad_norm: 2.6265 (2.8859) time: 0.6372 [2021-03-28 06:25:37 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 380/1251] eta: 0:09:18 lr: 0.000092 loss: 2.7831 (2.8185) grad_norm: 2.6322 (2.8906) time: 0.6287 [2021-03-28 06:25:44 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 390/1251] eta: 0:09:11 lr: 0.000092 loss: 3.0389 (2.8149) grad_norm: 2.8677 (2.8913) time: 0.6279 [2021-03-28 06:25:50 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 400/1251] eta: 0:09:05 lr: 0.000092 loss: 2.6248 (2.8111) grad_norm: 2.9384 (2.8988) time: 0.6328 [2021-03-28 06:25:56 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 410/1251] eta: 0:08:58 lr: 0.000092 loss: 2.9030 (2.8161) grad_norm: 2.8770 (2.8938) time: 0.6298 [2021-03-28 06:26:03 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 420/1251] eta: 0:08:51 lr: 0.000092 loss: 2.8471 (2.8141) grad_norm: 2.6081 (2.8920) time: 0.6266 [2021-03-28 06:26:09 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 430/1251] eta: 0:08:45 lr: 0.000092 loss: 3.0302 (2.8219) grad_norm: 2.6208 (2.8911) time: 0.6291 [2021-03-28 06:26:15 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 440/1251] eta: 0:08:38 lr: 0.000092 loss: 3.0986 (2.8204) grad_norm: 2.8155 (2.8878) time: 0.6262 [2021-03-28 06:26:21 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 450/1251] eta: 0:08:31 lr: 0.000092 loss: 2.5363 (2.8130) grad_norm: 2.8155 (2.8956) time: 0.6256 [2021-03-28 06:26:28 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 460/1251] eta: 0:08:25 lr: 0.000092 loss: 2.6656 (2.8125) grad_norm: 2.7923 (2.8928) time: 0.6309 [2021-03-28 06:26:34 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 470/1251] eta: 0:08:18 lr: 0.000092 loss: 2.6656 (2.8112) grad_norm: 2.6009 (2.8855) time: 0.6326 [2021-03-28 06:26:40 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 480/1251] eta: 0:08:12 lr: 0.000092 loss: 2.9180 (2.8148) grad_norm: 2.5227 (2.8805) time: 0.6323 [2021-03-28 06:26:47 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 490/1251] eta: 0:08:05 lr: 0.000092 loss: 2.9517 (2.8124) grad_norm: 2.7170 (2.8775) time: 0.6334 [2021-03-28 06:26:53 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 500/1251] eta: 0:07:59 lr: 0.000092 loss: 2.6527 (2.8093) grad_norm: 2.5997 (2.8737) time: 0.6333 [2021-03-28 06:26:59 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 510/1251] eta: 0:07:52 lr: 0.000092 loss: 2.9391 (2.8140) grad_norm: 2.5638 (2.8684) time: 0.6309 [2021-03-28 06:27:06 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 520/1251] eta: 0:07:46 lr: 0.000092 loss: 3.1080 (2.8129) grad_norm: 2.4975 (2.8639) time: 0.6384 [2021-03-28 06:27:12 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 530/1251] eta: 0:07:40 lr: 0.000091 loss: 2.8778 (2.8116) grad_norm: 2.6224 (2.8588) time: 0.6383 [2021-03-28 06:27:18 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 540/1251] eta: 0:07:33 lr: 0.000091 loss: 2.7494 (2.8078) grad_norm: 2.6224 (2.8545) time: 0.6251 [2021-03-28 06:27:25 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 550/1251] eta: 0:07:27 lr: 0.000091 loss: 2.7748 (2.8082) grad_norm: 2.3909 (2.8471) time: 0.6325 [2021-03-28 06:27:31 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 560/1251] eta: 0:07:20 lr: 0.000091 loss: 2.7258 (2.8048) grad_norm: 2.4672 (2.8447) time: 0.6385 [2021-03-28 06:27:38 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 570/1251] eta: 0:07:14 lr: 0.000091 loss: 2.7495 (2.8071) grad_norm: 2.5517 (2.8399) time: 0.6374 [2021-03-28 06:27:44 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 580/1251] eta: 0:07:08 lr: 0.000091 loss: 2.8579 (2.8045) grad_norm: 2.6936 (2.8419) time: 0.6425 [2021-03-28 06:27:50 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 590/1251] eta: 0:07:01 lr: 0.000091 loss: 2.6943 (2.8034) grad_norm: 2.6936 (2.8377) time: 0.6343 [2021-03-28 06:27:57 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 600/1251] eta: 0:06:55 lr: 0.000091 loss: 2.9295 (2.8069) grad_norm: 2.5538 (2.8352) time: 0.6319 [2021-03-28 06:28:03 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 610/1251] eta: 0:06:48 lr: 0.000091 loss: 2.9295 (2.8051) grad_norm: 2.8279 (2.8376) time: 0.6383 [2021-03-28 06:28:09 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 620/1251] eta: 0:06:42 lr: 0.000091 loss: 2.9168 (2.8076) grad_norm: 2.8279 (2.8335) time: 0.6366 [2021-03-28 06:28:16 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 630/1251] eta: 0:06:36 lr: 0.000091 loss: 2.8765 (2.8053) grad_norm: 2.6471 (2.8313) time: 0.6368 [2021-03-28 06:28:22 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 640/1251] eta: 0:06:29 lr: 0.000091 loss: 2.7367 (2.8020) grad_norm: 2.7615 (2.8319) time: 0.6355 [2021-03-28 06:28:28 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 650/1251] eta: 0:06:23 lr: 0.000091 loss: 2.5146 (2.7997) grad_norm: 2.7609 (2.8319) time: 0.6281 [2021-03-28 06:28:35 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 660/1251] eta: 0:06:16 lr: 0.000091 loss: 2.7547 (2.8000) grad_norm: 2.7292 (2.8310) time: 0.6261 [2021-03-28 06:28:41 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 670/1251] eta: 0:06:10 lr: 0.000091 loss: 2.6349 (2.7986) grad_norm: 2.8184 (2.8321) time: 0.6276 [2021-03-28 06:28:47 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 680/1251] eta: 0:06:03 lr: 0.000091 loss: 2.7405 (2.7990) grad_norm: 2.8184 (2.8334) time: 0.6282 [2021-03-28 06:28:54 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 690/1251] eta: 0:05:57 lr: 0.000091 loss: 2.9116 (2.7992) grad_norm: 2.7275 (2.8379) time: 0.6312 [2021-03-28 06:29:00 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 700/1251] eta: 0:05:50 lr: 0.000091 loss: 2.8784 (2.7990) grad_norm: 2.7275 (2.8400) time: 0.6277 [2021-03-28 06:29:06 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 710/1251] eta: 0:05:44 lr: 0.000091 loss: 2.8503 (2.7980) grad_norm: 2.6849 (2.8393) time: 0.6264 [2021-03-28 06:29:12 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 720/1251] eta: 0:05:38 lr: 0.000091 loss: 2.9058 (2.7973) grad_norm: 2.7093 (2.8382) time: 0.6291 [2021-03-28 06:29:19 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 730/1251] eta: 0:05:31 lr: 0.000091 loss: 2.9386 (2.7940) grad_norm: 2.6343 (2.8378) time: 0.6313 [2021-03-28 06:29:25 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 740/1251] eta: 0:05:25 lr: 0.000091 loss: 2.5985 (2.7900) grad_norm: 2.5549 (2.8322) time: 0.6315 [2021-03-28 06:29:31 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 750/1251] eta: 0:05:18 lr: 0.000091 loss: 2.6776 (2.7885) grad_norm: 2.6294 (2.8347) time: 0.6319 [2021-03-28 06:29:38 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 760/1251] eta: 0:05:12 lr: 0.000091 loss: 2.7763 (2.7865) grad_norm: 2.7664 (2.8479) time: 0.6352 [2021-03-28 06:29:44 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 770/1251] eta: 0:05:06 lr: 0.000091 loss: 2.7797 (2.7877) grad_norm: 2.6325 (2.8458) time: 0.6337 [2021-03-28 06:29:50 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 780/1251] eta: 0:04:59 lr: 0.000091 loss: 2.9270 (2.7886) grad_norm: 2.5668 (2.8439) time: 0.6291 [2021-03-28 06:29:57 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 790/1251] eta: 0:04:53 lr: 0.000091 loss: 2.9389 (2.7915) grad_norm: 2.5234 (2.8448) time: 0.6302 [2021-03-28 06:30:03 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 800/1251] eta: 0:04:46 lr: 0.000091 loss: 2.9569 (2.7923) grad_norm: 2.5775 (2.8448) time: 0.6300 [2021-03-28 06:30:09 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 810/1251] eta: 0:04:40 lr: 0.000091 loss: 2.7722 (2.7927) grad_norm: 2.6485 (2.8456) time: 0.6235 [2021-03-28 06:30:15 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 820/1251] eta: 0:04:34 lr: 0.000091 loss: 2.7776 (2.7925) grad_norm: 2.6917 (2.8457) time: 0.6275 [2021-03-28 06:30:22 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 830/1251] eta: 0:04:27 lr: 0.000091 loss: 2.9446 (2.7954) grad_norm: 2.6811 (2.8442) time: 0.6256 [2021-03-28 06:30:28 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 840/1251] eta: 0:04:21 lr: 0.000091 loss: 2.9827 (2.7964) grad_norm: 2.6453 (2.8431) time: 0.6183 [2021-03-28 06:30:34 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 850/1251] eta: 0:04:14 lr: 0.000091 loss: 2.9827 (2.7957) grad_norm: 2.6453 (2.8406) time: 0.6199 [2021-03-28 06:30:40 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 860/1251] eta: 0:04:08 lr: 0.000091 loss: 2.9380 (2.7971) grad_norm: 2.5860 (2.8404) time: 0.6280 [2021-03-28 06:30:47 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 870/1251] eta: 0:04:02 lr: 0.000091 loss: 2.9380 (2.7965) grad_norm: 2.6840 (2.8384) time: 0.6293 [2021-03-28 06:30:53 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 880/1251] eta: 0:03:55 lr: 0.000091 loss: 2.8198 (2.7959) grad_norm: 2.7178 (2.8451) time: 0.6255 [2021-03-28 06:30:59 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 890/1251] eta: 0:03:49 lr: 0.000091 loss: 2.7644 (2.7926) grad_norm: 2.5291 (2.8419) time: 0.6236 [2021-03-28 06:31:05 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 900/1251] eta: 0:03:42 lr: 0.000091 loss: 2.8009 (2.7945) grad_norm: 2.5846 (2.8419) time: 0.6248 [2021-03-28 06:31:12 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 910/1251] eta: 0:03:36 lr: 0.000091 loss: 3.0499 (2.7970) grad_norm: 2.6459 (2.8401) time: 0.6330 [2021-03-28 06:31:18 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 920/1251] eta: 0:03:30 lr: 0.000091 loss: 3.0235 (2.7961) grad_norm: 2.5685 (2.8394) time: 0.6320 [2021-03-28 06:31:24 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 930/1251] eta: 0:03:23 lr: 0.000091 loss: 2.9090 (2.7982) grad_norm: 2.5579 (2.8371) time: 0.6277 [2021-03-28 06:31:31 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 940/1251] eta: 0:03:17 lr: 0.000091 loss: 3.0867 (2.7992) grad_norm: 2.4857 (2.8402) time: 0.6368 [2021-03-28 06:31:37 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 950/1251] eta: 0:03:11 lr: 0.000091 loss: 2.8330 (2.7977) grad_norm: 2.6469 (2.8408) time: 0.6344 [2021-03-28 06:31:43 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 960/1251] eta: 0:03:04 lr: 0.000091 loss: 2.8330 (2.7983) grad_norm: 2.7499 (2.8413) time: 0.6236 [2021-03-28 06:31:49 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 970/1251] eta: 0:02:58 lr: 0.000090 loss: 2.8502 (2.7982) grad_norm: 2.7499 (2.8466) time: 0.6252 [2021-03-28 06:31:56 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 980/1251] eta: 0:02:51 lr: 0.000090 loss: 2.8502 (2.7982) grad_norm: 2.6734 (2.8449) time: 0.6336 [2021-03-28 06:32:02 swin_base_patch4_window7_224] INFO: Epoch: [244] [ 990/1251] eta: 0:02:45 lr: 0.000090 loss: 3.0344 (2.8004) grad_norm: 2.5486 (2.8429) time: 0.6319 [2021-03-28 06:32:08 swin_base_patch4_window7_224] INFO: Epoch: [244] [1000/1251] eta: 0:02:39 lr: 0.000090 loss: 3.0344 (2.8004) grad_norm: 2.5913 (2.8407) time: 0.6228 [2021-03-28 06:32:15 swin_base_patch4_window7_224] INFO: Epoch: [244] [1010/1251] eta: 0:02:32 lr: 0.000090 loss: 2.7589 (2.7989) grad_norm: 2.6978 (2.8394) time: 0.6231 [2021-03-28 06:32:21 swin_base_patch4_window7_224] INFO: Epoch: [244] [1020/1251] eta: 0:02:26 lr: 0.000090 loss: 2.8541 (2.8000) grad_norm: 2.6309 (2.8363) time: 0.6257 [2021-03-28 06:32:27 swin_base_patch4_window7_224] INFO: Epoch: [244] [1030/1251] eta: 0:02:20 lr: 0.000090 loss: 2.8808 (2.7991) grad_norm: 2.4330 (2.8334) time: 0.6291 [2021-03-28 06:32:33 swin_base_patch4_window7_224] INFO: Epoch: [244] [1040/1251] eta: 0:02:13 lr: 0.000090 loss: 2.8118 (2.7981) grad_norm: 2.7897 (2.8333) time: 0.6305 [2021-03-28 06:32:40 swin_base_patch4_window7_224] INFO: Epoch: [244] [1050/1251] eta: 0:02:07 lr: 0.000090 loss: 2.7648 (2.7971) grad_norm: 2.7655 (2.8323) time: 0.6346 [2021-03-28 06:32:46 swin_base_patch4_window7_224] INFO: Epoch: [244] [1060/1251] eta: 0:02:01 lr: 0.000090 loss: 2.8221 (2.7983) grad_norm: 2.8377 (2.8419) time: 0.6384 [2021-03-28 06:32:53 swin_base_patch4_window7_224] INFO: Epoch: [244] [1070/1251] eta: 0:01:54 lr: 0.000090 loss: 2.9510 (2.7999) grad_norm: 2.8987 (2.8429) time: 0.6361 [2021-03-28 06:32:59 swin_base_patch4_window7_224] INFO: Epoch: [244] [1080/1251] eta: 0:01:48 lr: 0.000090 loss: 2.9267 (2.7998) grad_norm: 2.7902 (2.8439) time: 0.6290 [2021-03-28 06:33:05 swin_base_patch4_window7_224] INFO: Epoch: [244] [1090/1251] eta: 0:01:42 lr: 0.000090 loss: 2.5912 (2.7974) grad_norm: 2.7388 (2.8450) time: 0.6266 [2021-03-28 06:33:11 swin_base_patch4_window7_224] INFO: Epoch: [244] [1100/1251] eta: 0:01:35 lr: 0.000090 loss: 2.9374 (2.7991) grad_norm: 2.7976 (2.8467) time: 0.6332 [2021-03-28 06:33:18 swin_base_patch4_window7_224] INFO: Epoch: [244] [1110/1251] eta: 0:01:29 lr: 0.000090 loss: 3.0295 (2.7991) grad_norm: 2.7976 (2.8473) time: 0.6350 [2021-03-28 06:33:24 swin_base_patch4_window7_224] INFO: Epoch: [244] [1120/1251] eta: 0:01:23 lr: 0.000090 loss: 2.9332 (2.8001) grad_norm: 2.7365 (2.8454) time: 0.6269 [2021-03-28 06:33:30 swin_base_patch4_window7_224] INFO: Epoch: [244] [1130/1251] eta: 0:01:16 lr: 0.000090 loss: 3.0995 (2.8032) grad_norm: 2.6177 (2.8441) time: 0.6239 [2021-03-28 06:33:37 swin_base_patch4_window7_224] INFO: Epoch: [244] [1140/1251] eta: 0:01:10 lr: 0.000090 loss: 3.0995 (2.8034) grad_norm: 2.8243 (2.8449) time: 0.6282 [2021-03-28 06:33:43 swin_base_patch4_window7_224] INFO: Epoch: [244] [1150/1251] eta: 0:01:04 lr: 0.000090 loss: 2.8281 (2.8011) grad_norm: 2.8243 (2.8438) time: 0.6244 [2021-03-28 06:33:49 swin_base_patch4_window7_224] INFO: Epoch: [244] [1160/1251] eta: 0:00:57 lr: 0.000090 loss: 2.8343 (2.8008) grad_norm: 2.6735 (2.8418) time: 0.6229 [2021-03-28 06:33:55 swin_base_patch4_window7_224] INFO: Epoch: [244] [1170/1251] eta: 0:00:51 lr: 0.000090 loss: 2.9294 (2.8024) grad_norm: 2.8121 (2.8422) time: 0.6237 [2021-03-28 06:34:02 swin_base_patch4_window7_224] INFO: Epoch: [244] [1180/1251] eta: 0:00:44 lr: 0.000090 loss: 2.8816 (2.8021) grad_norm: 2.7219 (2.8417) time: 0.6252 [2021-03-28 06:34:08 swin_base_patch4_window7_224] INFO: Epoch: [244] [1190/1251] eta: 0:00:38 lr: 0.000090 loss: 2.7954 (2.8024) grad_norm: 2.5166 (2.8398) time: 0.6309 [2021-03-28 06:34:14 swin_base_patch4_window7_224] INFO: Epoch: [244] [1200/1251] eta: 0:00:32 lr: 0.000090 loss: 2.8095 (2.8021) grad_norm: 2.4756 (2.8382) time: 0.6304 [2021-03-28 06:34:21 swin_base_patch4_window7_224] INFO: Epoch: [244] [1210/1251] eta: 0:00:25 lr: 0.000090 loss: 2.7203 (2.8010) grad_norm: 2.4925 (2.8362) time: 0.6311 [2021-03-28 06:34:27 swin_base_patch4_window7_224] INFO: Epoch: [244] [1220/1251] eta: 0:00:19 lr: 0.000090 loss: 2.8173 (2.8032) grad_norm: 2.6344 (2.8383) time: 0.6356 [2021-03-28 06:34:33 swin_base_patch4_window7_224] INFO: Epoch: [244] [1230/1251] eta: 0:00:13 lr: 0.000090 loss: 2.9917 (2.8040) grad_norm: 2.6327 (2.8369) time: 0.6297 [2021-03-28 06:34:39 swin_base_patch4_window7_224] INFO: Epoch: [244] [1240/1251] eta: 0:00:06 lr: 0.000090 loss: 2.9876 (2.8042) grad_norm: 2.5047 (2.8345) time: 0.6280 [2021-03-28 06:34:46 swin_base_patch4_window7_224] INFO: Epoch: [244] [1250/1251] eta: 0:00:00 lr: 0.000090 loss: 2.8979 (2.8041) grad_norm: 2.4798 (2.8369) time: 0.6276 [2021-03-28 06:34:56 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:45 loss: 1.1136 (1.1136) acc1: 73.4375 (73.4375) acc5: 93.7500 (93.7500) [2021-03-28 06:34:58 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.8038 (0.8124) acc1: 79.6875 (81.5341) acc5: 96.8750 (96.3068) [2021-03-28 06:35:01 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7484 (0.7960) acc1: 82.8125 (81.5476) acc5: 96.8750 (96.3542) [2021-03-28 06:35:04 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7083 (0.7738) acc1: 84.3750 (82.1573) acc5: 96.8750 (96.2702) [2021-03-28 06:35:06 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7083 (0.7802) acc1: 82.8125 (82.0122) acc5: 95.3125 (96.0747) [2021-03-28 06:35:07 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7119 (0.7700) acc1: 81.2500 (82.0160) acc5: 95.3125 (96.1280) [2021-03-28 06:35:20 swin_base_patch4_window7_224] INFO: * Acc@1 82.726 Acc@5 96.254 loss 0.762 [2021-03-28 06:35:20 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.7% [2021-03-28 06:35:20 swin_base_patch4_window7_224] INFO: Max accuracy: 82.78% [2021-03-28 06:35:26 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 0/1251] eta: 1:45:32 lr: 0.000090 loss: 2.6462 (2.6462) grad_norm: 2.3113 (2.3113) time: 5.0620 [2021-03-28 06:35:32 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 10/1251] eta: 0:21:28 lr: 0.000090 loss: 3.0706 (2.8378) grad_norm: 2.7924 (3.1110) time: 1.0385 [2021-03-28 06:35:38 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 20/1251] eta: 0:17:17 lr: 0.000090 loss: 2.8574 (2.8359) grad_norm: 2.7924 (2.9379) time: 0.6317 [2021-03-28 06:35:45 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 30/1251] eta: 0:15:47 lr: 0.000090 loss: 2.7491 (2.8347) grad_norm: 2.4389 (2.8067) time: 0.6317 [2021-03-28 06:35:51 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 40/1251] eta: 0:14:58 lr: 0.000090 loss: 2.7491 (2.8257) grad_norm: 2.4389 (3.0645) time: 0.6353 [2021-03-28 06:35:57 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 50/1251] eta: 0:14:25 lr: 0.000090 loss: 3.1261 (2.8856) grad_norm: 2.5808 (3.0317) time: 0.6337 [2021-03-28 06:36:04 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 60/1251] eta: 0:14:00 lr: 0.000090 loss: 3.0738 (2.8626) grad_norm: 2.7971 (3.0181) time: 0.6310 [2021-03-28 06:36:10 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 70/1251] eta: 0:13:39 lr: 0.000090 loss: 2.7439 (2.8523) grad_norm: 2.8416 (2.9915) time: 0.6269 [2021-03-28 06:36:16 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 80/1251] eta: 0:13:24 lr: 0.000090 loss: 2.8002 (2.8439) grad_norm: 2.7639 (2.9892) time: 0.6302 [2021-03-28 06:36:22 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 90/1251] eta: 0:13:10 lr: 0.000090 loss: 2.9529 (2.8612) grad_norm: 2.5558 (2.9425) time: 0.6356 [2021-03-28 06:36:29 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 100/1251] eta: 0:12:58 lr: 0.000090 loss: 2.9420 (2.8531) grad_norm: 2.5563 (2.9366) time: 0.6323 [2021-03-28 06:36:35 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 110/1251] eta: 0:12:45 lr: 0.000090 loss: 2.9051 (2.8191) grad_norm: 2.5830 (2.8975) time: 0.6267 [2021-03-28 06:36:41 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 120/1251] eta: 0:12:35 lr: 0.000090 loss: 2.5525 (2.8078) grad_norm: 2.6640 (3.0159) time: 0.6279 [2021-03-28 06:36:48 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 130/1251] eta: 0:12:24 lr: 0.000090 loss: 2.8479 (2.8148) grad_norm: 2.9805 (3.0300) time: 0.6269 [2021-03-28 06:36:54 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 140/1251] eta: 0:12:15 lr: 0.000090 loss: 2.9215 (2.8140) grad_norm: 2.6511 (3.0093) time: 0.6243 [2021-03-28 06:37:00 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 150/1251] eta: 0:12:06 lr: 0.000090 loss: 2.8102 (2.8037) grad_norm: 2.6830 (3.0006) time: 0.6286 [2021-03-28 06:37:06 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 160/1251] eta: 0:11:57 lr: 0.000089 loss: 2.7927 (2.8005) grad_norm: 2.7016 (3.0015) time: 0.6281 [2021-03-28 06:37:13 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 170/1251] eta: 0:11:49 lr: 0.000089 loss: 2.9638 (2.8154) grad_norm: 2.7539 (2.9956) time: 0.6339 [2021-03-28 06:37:19 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 180/1251] eta: 0:11:41 lr: 0.000089 loss: 2.9638 (2.8034) grad_norm: 2.6768 (2.9766) time: 0.6359 [2021-03-28 06:37:26 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 190/1251] eta: 0:11:34 lr: 0.000089 loss: 2.7676 (2.8016) grad_norm: 2.5715 (2.9600) time: 0.6339 [2021-03-28 06:37:32 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 200/1251] eta: 0:11:26 lr: 0.000089 loss: 2.8338 (2.8021) grad_norm: 2.4498 (2.9400) time: 0.6339 [2021-03-28 06:37:38 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 210/1251] eta: 0:11:19 lr: 0.000089 loss: 2.9733 (2.8066) grad_norm: 2.4585 (2.9232) time: 0.6326 [2021-03-28 06:37:44 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 220/1251] eta: 0:11:11 lr: 0.000089 loss: 2.9733 (2.8048) grad_norm: 2.6437 (2.9246) time: 0.6316 [2021-03-28 06:37:51 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 230/1251] eta: 0:11:04 lr: 0.000089 loss: 2.8282 (2.8080) grad_norm: 2.7670 (2.9261) time: 0.6302 [2021-03-28 06:37:57 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 240/1251] eta: 0:10:56 lr: 0.000089 loss: 2.6381 (2.7999) grad_norm: 2.9870 (2.9416) time: 0.6292 [2021-03-28 06:38:03 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 250/1251] eta: 0:10:48 lr: 0.000089 loss: 2.4296 (2.7810) grad_norm: 2.9175 (2.9324) time: 0.6228 [2021-03-28 06:38:10 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 260/1251] eta: 0:10:41 lr: 0.000089 loss: 2.5380 (2.7844) grad_norm: 2.6798 (2.9346) time: 0.6247 [2021-03-28 06:38:16 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 270/1251] eta: 0:10:34 lr: 0.000089 loss: 2.7883 (2.7833) grad_norm: 2.6135 (2.9367) time: 0.6303 [2021-03-28 06:38:22 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 280/1251] eta: 0:10:27 lr: 0.000089 loss: 2.6950 (2.7817) grad_norm: 2.4876 (2.9192) time: 0.6296 [2021-03-28 06:38:29 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 290/1251] eta: 0:10:20 lr: 0.000089 loss: 2.7639 (2.7845) grad_norm: 2.4916 (2.9099) time: 0.6357 [2021-03-28 06:38:35 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 300/1251] eta: 0:10:14 lr: 0.000089 loss: 2.9954 (2.7918) grad_norm: 2.6084 (2.9008) time: 0.6394 [2021-03-28 06:38:41 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 310/1251] eta: 0:10:07 lr: 0.000089 loss: 2.9954 (2.7870) grad_norm: 2.6194 (2.9157) time: 0.6353 [2021-03-28 06:38:48 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 320/1251] eta: 0:10:00 lr: 0.000089 loss: 2.8605 (2.7932) grad_norm: 2.8431 (2.9192) time: 0.6323 [2021-03-28 06:38:54 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 330/1251] eta: 0:09:53 lr: 0.000089 loss: 2.8745 (2.7884) grad_norm: 2.6752 (2.9161) time: 0.6355 [2021-03-28 06:39:00 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 340/1251] eta: 0:09:46 lr: 0.000089 loss: 2.8752 (2.7857) grad_norm: 2.7276 (2.9171) time: 0.6353 [2021-03-28 06:39:07 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 350/1251] eta: 0:09:40 lr: 0.000089 loss: 2.8752 (2.7834) grad_norm: 2.8262 (2.9146) time: 0.6285 [2021-03-28 06:39:13 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 360/1251] eta: 0:09:33 lr: 0.000089 loss: 2.8411 (2.7869) grad_norm: 2.7395 (2.9093) time: 0.6320 [2021-03-28 06:39:19 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 370/1251] eta: 0:09:26 lr: 0.000089 loss: 2.7706 (2.7840) grad_norm: 2.6532 (2.9117) time: 0.6330 [2021-03-28 06:39:26 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 380/1251] eta: 0:09:20 lr: 0.000089 loss: 2.7334 (2.7813) grad_norm: 2.5740 (2.9030) time: 0.6341 [2021-03-28 06:39:32 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 390/1251] eta: 0:09:13 lr: 0.000089 loss: 2.8816 (2.7828) grad_norm: 2.6032 (2.9074) time: 0.6353 [2021-03-28 06:39:38 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 400/1251] eta: 0:09:06 lr: 0.000089 loss: 2.8573 (2.7842) grad_norm: 2.5813 (2.8991) time: 0.6304 [2021-03-28 06:39:45 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 410/1251] eta: 0:09:00 lr: 0.000089 loss: 2.8573 (2.7848) grad_norm: 2.5956 (2.8954) time: 0.6307 [2021-03-28 06:39:51 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 420/1251] eta: 0:08:53 lr: 0.000089 loss: 2.8948 (2.7849) grad_norm: 2.6860 (2.8981) time: 0.6258 [2021-03-28 06:39:57 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 430/1251] eta: 0:08:46 lr: 0.000089 loss: 2.6079 (2.7765) grad_norm: 2.6860 (2.8971) time: 0.6223 [2021-03-28 06:40:03 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 440/1251] eta: 0:08:39 lr: 0.000089 loss: 2.6380 (2.7796) grad_norm: 2.8671 (2.8956) time: 0.6253 [2021-03-28 06:40:09 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 450/1251] eta: 0:08:33 lr: 0.000089 loss: 3.0122 (2.7803) grad_norm: 2.7034 (2.8958) time: 0.6247 [2021-03-28 06:40:16 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 460/1251] eta: 0:08:26 lr: 0.000089 loss: 2.8953 (2.7830) grad_norm: 2.6839 (2.8931) time: 0.6219 [2021-03-28 06:40:22 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 470/1251] eta: 0:08:19 lr: 0.000089 loss: 2.8694 (2.7809) grad_norm: 2.6188 (2.8884) time: 0.6213 [2021-03-28 06:40:28 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 480/1251] eta: 0:08:13 lr: 0.000089 loss: 2.7450 (2.7805) grad_norm: 2.6188 (2.8890) time: 0.6271 [2021-03-28 06:40:34 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 490/1251] eta: 0:08:06 lr: 0.000089 loss: 2.8418 (2.7805) grad_norm: 2.6706 (2.8868) time: 0.6278 [2021-03-28 06:40:41 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 500/1251] eta: 0:07:59 lr: 0.000089 loss: 3.0092 (2.7845) grad_norm: 2.6855 (2.8840) time: 0.6258 [2021-03-28 06:40:47 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 510/1251] eta: 0:07:53 lr: 0.000089 loss: 3.0169 (2.7803) grad_norm: 2.7017 (2.8837) time: 0.6247 [2021-03-28 06:40:53 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 520/1251] eta: 0:07:46 lr: 0.000089 loss: 2.8924 (2.7837) grad_norm: 2.7689 (2.8878) time: 0.6243 [2021-03-28 06:40:59 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 530/1251] eta: 0:07:40 lr: 0.000089 loss: 2.7937 (2.7773) grad_norm: 2.6524 (2.8869) time: 0.6226 [2021-03-28 06:41:06 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 540/1251] eta: 0:07:33 lr: 0.000089 loss: 2.6539 (2.7771) grad_norm: 2.6292 (2.8824) time: 0.6229 [2021-03-28 06:41:12 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 550/1251] eta: 0:07:27 lr: 0.000089 loss: 2.8163 (2.7781) grad_norm: 2.7096 (2.8802) time: 0.6348 [2021-03-28 06:41:19 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 560/1251] eta: 0:07:20 lr: 0.000089 loss: 2.8159 (2.7789) grad_norm: 2.8783 (2.9015) time: 0.6419 [2021-03-28 06:41:25 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 570/1251] eta: 0:07:14 lr: 0.000089 loss: 2.7875 (2.7793) grad_norm: 2.9323 (2.8991) time: 0.6385 [2021-03-28 06:41:31 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 580/1251] eta: 0:07:07 lr: 0.000089 loss: 2.8244 (2.7770) grad_norm: 2.6807 (2.8981) time: 0.6282 [2021-03-28 06:41:37 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 590/1251] eta: 0:07:01 lr: 0.000089 loss: 2.8244 (2.7783) grad_norm: 2.5761 (2.8929) time: 0.6284 [2021-03-28 06:41:44 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 600/1251] eta: 0:06:55 lr: 0.000089 loss: 2.7717 (2.7788) grad_norm: 2.5989 (2.8921) time: 0.6396 [2021-03-28 06:41:50 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 610/1251] eta: 0:06:48 lr: 0.000088 loss: 2.6524 (2.7763) grad_norm: 2.5989 (2.8935) time: 0.6379 [2021-03-28 06:41:57 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 620/1251] eta: 0:06:42 lr: 0.000088 loss: 2.7131 (2.7771) grad_norm: 2.6969 (2.8931) time: 0.6384 [2021-03-28 06:42:03 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 630/1251] eta: 0:06:35 lr: 0.000088 loss: 2.7509 (2.7758) grad_norm: 2.6801 (2.8897) time: 0.6369 [2021-03-28 06:42:09 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 640/1251] eta: 0:06:29 lr: 0.000088 loss: 2.7834 (2.7791) grad_norm: 2.5876 (2.8849) time: 0.6320 [2021-03-28 06:42:16 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 650/1251] eta: 0:06:23 lr: 0.000088 loss: 2.8888 (2.7819) grad_norm: 2.5970 (2.8852) time: 0.6298 [2021-03-28 06:42:22 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 660/1251] eta: 0:06:16 lr: 0.000088 loss: 2.9333 (2.7850) grad_norm: 2.8017 (2.8824) time: 0.6289 [2021-03-28 06:42:28 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 670/1251] eta: 0:06:10 lr: 0.000088 loss: 2.8621 (2.7854) grad_norm: 2.4196 (2.8798) time: 0.6293 [2021-03-28 06:42:34 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 680/1251] eta: 0:06:03 lr: 0.000088 loss: 2.8621 (2.7854) grad_norm: 2.4615 (2.8765) time: 0.6269 [2021-03-28 06:42:41 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 690/1251] eta: 0:05:57 lr: 0.000088 loss: 2.8976 (2.7868) grad_norm: 2.6409 (2.8813) time: 0.6295 [2021-03-28 06:42:47 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 700/1251] eta: 0:05:50 lr: 0.000088 loss: 3.0482 (2.7924) grad_norm: 2.6409 (2.8788) time: 0.6302 [2021-03-28 06:42:53 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 710/1251] eta: 0:05:44 lr: 0.000088 loss: 3.0289 (2.7900) grad_norm: 2.6070 (2.8760) time: 0.6275 [2021-03-28 06:43:00 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 720/1251] eta: 0:05:38 lr: 0.000088 loss: 2.8875 (2.7920) grad_norm: 2.6537 (2.8773) time: 0.6379 [2021-03-28 06:43:06 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 730/1251] eta: 0:05:31 lr: 0.000088 loss: 3.1716 (2.7959) grad_norm: 2.8954 (2.8782) time: 0.6412 [2021-03-28 06:43:13 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 740/1251] eta: 0:05:25 lr: 0.000088 loss: 3.1716 (2.7960) grad_norm: 2.6189 (2.8730) time: 0.6344 [2021-03-28 06:43:19 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 750/1251] eta: 0:05:19 lr: 0.000088 loss: 2.9876 (2.7966) grad_norm: 2.4714 (2.8677) time: 0.6360 [2021-03-28 06:43:25 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 760/1251] eta: 0:05:12 lr: 0.000088 loss: 2.9719 (2.7975) grad_norm: 2.5645 (2.8661) time: 0.6332 [2021-03-28 06:43:31 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 770/1251] eta: 0:05:06 lr: 0.000088 loss: 2.6359 (2.7944) grad_norm: 2.4861 (2.8618) time: 0.6276 [2021-03-28 06:43:38 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 780/1251] eta: 0:04:59 lr: 0.000088 loss: 2.5673 (2.7912) grad_norm: 2.6010 (2.8681) time: 0.6245 [2021-03-28 06:43:44 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 790/1251] eta: 0:04:53 lr: 0.000088 loss: 2.5627 (2.7891) grad_norm: 2.8684 (2.8679) time: 0.6281 [2021-03-28 06:43:50 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 800/1251] eta: 0:04:46 lr: 0.000088 loss: 2.5576 (2.7857) grad_norm: 2.7489 (2.8652) time: 0.6326 [2021-03-28 06:43:57 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 810/1251] eta: 0:04:40 lr: 0.000088 loss: 2.5741 (2.7858) grad_norm: 2.7542 (2.8759) time: 0.6281 [2021-03-28 06:44:03 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 820/1251] eta: 0:04:34 lr: 0.000088 loss: 2.8451 (2.7858) grad_norm: 2.8333 (2.8764) time: 0.6276 [2021-03-28 06:44:09 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 830/1251] eta: 0:04:27 lr: 0.000088 loss: 2.8222 (2.7854) grad_norm: 2.6775 (2.8790) time: 0.6298 [2021-03-28 06:44:15 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 840/1251] eta: 0:04:21 lr: 0.000088 loss: 2.7919 (2.7852) grad_norm: 2.5714 (2.8745) time: 0.6290 [2021-03-28 06:44:22 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 850/1251] eta: 0:04:15 lr: 0.000088 loss: 2.8625 (2.7860) grad_norm: 2.6413 (2.8730) time: 0.6339 [2021-03-28 06:44:28 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 860/1251] eta: 0:04:08 lr: 0.000088 loss: 2.7125 (2.7827) grad_norm: 2.7008 (2.8704) time: 0.6313 [2021-03-28 06:44:34 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 870/1251] eta: 0:04:02 lr: 0.000088 loss: 2.7803 (2.7827) grad_norm: 2.7233 (2.8766) time: 0.6294 [2021-03-28 06:44:41 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 880/1251] eta: 0:03:55 lr: 0.000088 loss: 2.8620 (2.7840) grad_norm: 2.5473 (2.8723) time: 0.6328 [2021-03-28 06:44:47 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 890/1251] eta: 0:03:49 lr: 0.000088 loss: 2.9745 (2.7859) grad_norm: 2.4435 (2.8698) time: 0.6291 [2021-03-28 06:44:53 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 900/1251] eta: 0:03:43 lr: 0.000088 loss: 2.9668 (2.7842) grad_norm: 2.7089 (2.8719) time: 0.6305 [2021-03-28 06:45:00 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 910/1251] eta: 0:03:36 lr: 0.000088 loss: 2.9108 (2.7860) grad_norm: 2.6387 (2.8686) time: 0.6374 [2021-03-28 06:45:06 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 920/1251] eta: 0:03:30 lr: 0.000088 loss: 3.0380 (2.7855) grad_norm: 2.5533 (2.8676) time: 0.6343 [2021-03-28 06:45:12 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 930/1251] eta: 0:03:24 lr: 0.000088 loss: 2.9678 (2.7883) grad_norm: 2.6736 (2.8669) time: 0.6317 [2021-03-28 06:45:19 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 940/1251] eta: 0:03:17 lr: 0.000088 loss: 2.8243 (2.7866) grad_norm: 2.6835 (2.8675) time: 0.6349 [2021-03-28 06:45:25 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 950/1251] eta: 0:03:11 lr: 0.000088 loss: 2.7055 (2.7865) grad_norm: 2.6321 (2.8647) time: 0.6288 [2021-03-28 06:45:31 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 960/1251] eta: 0:03:04 lr: 0.000088 loss: 2.7672 (2.7858) grad_norm: 2.6321 (2.8658) time: 0.6281 [2021-03-28 06:45:38 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 970/1251] eta: 0:02:58 lr: 0.000088 loss: 2.8252 (2.7851) grad_norm: 2.7700 (2.8654) time: 0.6297 [2021-03-28 06:45:44 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 980/1251] eta: 0:02:52 lr: 0.000088 loss: 2.7228 (2.7840) grad_norm: 2.5822 (2.8624) time: 0.6262 [2021-03-28 06:45:50 swin_base_patch4_window7_224] INFO: Epoch: [245] [ 990/1251] eta: 0:02:45 lr: 0.000088 loss: 2.7560 (2.7858) grad_norm: 2.5715 (2.8628) time: 0.6268 [2021-03-28 06:45:56 swin_base_patch4_window7_224] INFO: Epoch: [245] [1000/1251] eta: 0:02:39 lr: 0.000088 loss: 2.8861 (2.7855) grad_norm: 2.6352 (2.8603) time: 0.6246 [2021-03-28 06:46:03 swin_base_patch4_window7_224] INFO: Epoch: [245] [1010/1251] eta: 0:02:33 lr: 0.000088 loss: 2.8588 (2.7857) grad_norm: 2.6352 (2.8588) time: 0.6242 [2021-03-28 06:46:09 swin_base_patch4_window7_224] INFO: Epoch: [245] [1020/1251] eta: 0:02:26 lr: 0.000088 loss: 2.8588 (2.7870) grad_norm: 2.6912 (2.8571) time: 0.6260 [2021-03-28 06:46:15 swin_base_patch4_window7_224] INFO: Epoch: [245] [1030/1251] eta: 0:02:20 lr: 0.000088 loss: 3.0363 (2.7877) grad_norm: 2.5454 (2.8547) time: 0.6292 [2021-03-28 06:46:22 swin_base_patch4_window7_224] INFO: Epoch: [245] [1040/1251] eta: 0:02:13 lr: 0.000088 loss: 2.9782 (2.7896) grad_norm: 2.5622 (2.8569) time: 0.6330 [2021-03-28 06:46:28 swin_base_patch4_window7_224] INFO: Epoch: [245] [1050/1251] eta: 0:02:07 lr: 0.000088 loss: 2.9039 (2.7901) grad_norm: 2.6384 (2.8548) time: 0.6294 [2021-03-28 06:46:34 swin_base_patch4_window7_224] INFO: Epoch: [245] [1060/1251] eta: 0:02:01 lr: 0.000087 loss: 2.8365 (2.7899) grad_norm: 2.5548 (2.8526) time: 0.6270 [2021-03-28 06:46:40 swin_base_patch4_window7_224] INFO: Epoch: [245] [1070/1251] eta: 0:01:54 lr: 0.000087 loss: 2.8741 (2.7900) grad_norm: 2.6045 (2.8500) time: 0.6325 [2021-03-28 06:46:47 swin_base_patch4_window7_224] INFO: Epoch: [245] [1080/1251] eta: 0:01:48 lr: 0.000087 loss: 2.8899 (2.7877) grad_norm: 2.5850 (2.8467) time: 0.6338 [2021-03-28 06:46:53 swin_base_patch4_window7_224] INFO: Epoch: [245] [1090/1251] eta: 0:01:42 lr: 0.000087 loss: 2.8034 (2.7898) grad_norm: 2.5451 (2.8457) time: 0.6297 [2021-03-28 06:46:59 swin_base_patch4_window7_224] INFO: Epoch: [245] [1100/1251] eta: 0:01:35 lr: 0.000087 loss: 2.7854 (2.7877) grad_norm: 2.6161 (2.8444) time: 0.6274 [2021-03-28 06:47:06 swin_base_patch4_window7_224] INFO: Epoch: [245] [1110/1251] eta: 0:01:29 lr: 0.000087 loss: 2.8759 (2.7881) grad_norm: 2.5121 (2.8442) time: 0.6273 [2021-03-28 06:47:12 swin_base_patch4_window7_224] INFO: Epoch: [245] [1120/1251] eta: 0:01:23 lr: 0.000087 loss: 2.9006 (2.7884) grad_norm: 2.5107 (2.8442) time: 0.6322 [2021-03-28 06:47:18 swin_base_patch4_window7_224] INFO: Epoch: [245] [1130/1251] eta: 0:01:16 lr: 0.000087 loss: 2.9006 (2.7878) grad_norm: 2.7283 (2.8435) time: 0.6340 [2021-03-28 06:47:25 swin_base_patch4_window7_224] INFO: Epoch: [245] [1140/1251] eta: 0:01:10 lr: 0.000087 loss: 2.9213 (2.7882) grad_norm: 2.7353 (2.8451) time: 0.6326 [2021-03-28 06:47:31 swin_base_patch4_window7_224] INFO: Epoch: [245] [1150/1251] eta: 0:01:04 lr: 0.000087 loss: 2.9213 (2.7876) grad_norm: 2.7054 (2.8441) time: 0.6311 [2021-03-28 06:47:37 swin_base_patch4_window7_224] INFO: Epoch: [245] [1160/1251] eta: 0:00:57 lr: 0.000087 loss: 2.9015 (2.7887) grad_norm: 2.7054 (2.8451) time: 0.6315 [2021-03-28 06:47:44 swin_base_patch4_window7_224] INFO: Epoch: [245] [1170/1251] eta: 0:00:51 lr: 0.000087 loss: 2.9468 (2.7890) grad_norm: 2.7798 (2.8441) time: 0.6327 [2021-03-28 06:47:50 swin_base_patch4_window7_224] INFO: Epoch: [245] [1180/1251] eta: 0:00:45 lr: 0.000087 loss: 2.9517 (2.7897) grad_norm: 2.7964 (2.8426) time: 0.6286 [2021-03-28 06:47:56 swin_base_patch4_window7_224] INFO: Epoch: [245] [1190/1251] eta: 0:00:38 lr: 0.000087 loss: 2.7899 (2.7885) grad_norm: 2.7363 (2.8432) time: 0.6269 [2021-03-28 06:48:02 swin_base_patch4_window7_224] INFO: Epoch: [245] [1200/1251] eta: 0:00:32 lr: 0.000087 loss: 2.7899 (2.7896) grad_norm: 2.6866 (2.8416) time: 0.6313 [2021-03-28 06:48:09 swin_base_patch4_window7_224] INFO: Epoch: [245] [1210/1251] eta: 0:00:26 lr: 0.000087 loss: 2.9343 (2.7903) grad_norm: 2.7440 (2.8429) time: 0.6319 [2021-03-28 06:48:15 swin_base_patch4_window7_224] INFO: Epoch: [245] [1220/1251] eta: 0:00:19 lr: 0.000087 loss: 3.2523 (2.7933) grad_norm: 2.8232 (inf) time: 0.6287 [2021-03-28 06:48:21 swin_base_patch4_window7_224] INFO: Epoch: [245] [1230/1251] eta: 0:00:13 lr: 0.000087 loss: 3.0405 (2.7930) grad_norm: 2.6605 (inf) time: 0.6310 [2021-03-28 06:48:28 swin_base_patch4_window7_224] INFO: Epoch: [245] [1240/1251] eta: 0:00:06 lr: 0.000087 loss: 2.7397 (2.7931) grad_norm: 2.8693 (inf) time: 0.6289 [2021-03-28 06:48:34 swin_base_patch4_window7_224] INFO: Epoch: [245] [1250/1251] eta: 0:00:00 lr: 0.000087 loss: 2.8312 (2.7930) grad_norm: 2.8693 (inf) time: 0.6235 [2021-03-28 06:49:41 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.7446 (0.7446) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-28 06:49:43 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7413 (0.7338) acc1: 82.8125 (82.3864) acc5: 96.8750 (96.5909) [2021-03-28 06:49:44 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7828 (0.8244) acc1: 79.6875 (79.5387) acc5: 95.3125 (96.0565) [2021-03-28 06:49:46 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8407 (0.8121) acc1: 79.6875 (80.2923) acc5: 95.3125 (95.9173) [2021-03-28 06:49:47 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7474 (0.7941) acc1: 81.2500 (81.0213) acc5: 96.8750 (96.1509) [2021-03-28 06:49:48 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6955 (0.7846) acc1: 82.8125 (81.3440) acc5: 96.8750 (96.1280) [2021-03-28 06:50:01 swin_base_patch4_window7_224] INFO: * Acc@1 82.678 Acc@5 96.210 loss 0.768 [2021-03-28 06:50:01 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.7% [2021-03-28 06:50:01 swin_base_patch4_window7_224] INFO: Max accuracy: 82.78% [2021-03-28 06:50:05 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 0/1251] eta: 1:31:58 lr: 0.000087 loss: 3.1892 (3.1892) grad_norm: 2.2224 (2.2224) time: 4.4112 [2021-03-28 06:50:12 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 10/1251] eta: 0:20:03 lr: 0.000087 loss: 2.9491 (2.9704) grad_norm: 3.0860 (2.9709) time: 0.9695 [2021-03-28 06:50:18 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 20/1251] eta: 0:16:36 lr: 0.000087 loss: 2.8922 (2.8227) grad_norm: 3.2196 (3.1664) time: 0.6296 [2021-03-28 06:50:25 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 30/1251] eta: 0:15:21 lr: 0.000087 loss: 2.9050 (2.8914) grad_norm: 2.9496 (3.0175) time: 0.6370 [2021-03-28 06:50:31 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 40/1251] eta: 0:14:40 lr: 0.000087 loss: 2.9129 (2.8393) grad_norm: 2.8114 (2.9905) time: 0.6404 [2021-03-28 06:50:37 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 50/1251] eta: 0:14:10 lr: 0.000087 loss: 2.9021 (2.8396) grad_norm: 2.8176 (2.9718) time: 0.6365 [2021-03-28 06:50:44 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 60/1251] eta: 0:13:48 lr: 0.000087 loss: 2.9021 (2.8562) grad_norm: 2.6476 (2.9378) time: 0.6306 [2021-03-28 06:50:50 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 70/1251] eta: 0:13:30 lr: 0.000087 loss: 2.9411 (2.8525) grad_norm: 2.5965 (2.9381) time: 0.6281 [2021-03-28 06:50:56 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 80/1251] eta: 0:13:15 lr: 0.000087 loss: 2.8832 (2.8400) grad_norm: 2.4738 (2.9085) time: 0.6315 [2021-03-28 06:51:03 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 90/1251] eta: 0:13:03 lr: 0.000087 loss: 2.5903 (2.7919) grad_norm: 2.5043 (2.8851) time: 0.6347 [2021-03-28 06:51:09 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 100/1251] eta: 0:12:52 lr: 0.000087 loss: 2.6592 (2.8050) grad_norm: 2.6092 (2.9144) time: 0.6348 [2021-03-28 06:51:15 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 110/1251] eta: 0:12:41 lr: 0.000087 loss: 2.9137 (2.8054) grad_norm: 2.6077 (2.8947) time: 0.6339 [2021-03-28 06:51:22 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 120/1251] eta: 0:12:31 lr: 0.000087 loss: 2.8779 (2.8006) grad_norm: 2.6353 (2.9119) time: 0.6313 [2021-03-28 06:51:28 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 130/1251] eta: 0:12:20 lr: 0.000087 loss: 2.8870 (2.8011) grad_norm: 2.7137 (2.8887) time: 0.6251 [2021-03-28 06:51:34 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 140/1251] eta: 0:12:11 lr: 0.000087 loss: 2.6439 (2.7902) grad_norm: 2.5570 (2.8800) time: 0.6226 [2021-03-28 06:51:40 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 150/1251] eta: 0:12:02 lr: 0.000087 loss: 2.5995 (2.7812) grad_norm: 2.5570 (2.8603) time: 0.6283 [2021-03-28 06:51:47 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 160/1251] eta: 0:11:54 lr: 0.000087 loss: 2.8761 (2.7908) grad_norm: 2.5015 (2.8501) time: 0.6273 [2021-03-28 06:51:53 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 170/1251] eta: 0:11:46 lr: 0.000087 loss: 2.8171 (2.7755) grad_norm: 2.7385 (2.8568) time: 0.6272 [2021-03-28 06:51:59 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 180/1251] eta: 0:11:38 lr: 0.000087 loss: 2.7196 (2.7785) grad_norm: 2.7385 (2.8449) time: 0.6315 [2021-03-28 06:52:05 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 190/1251] eta: 0:11:30 lr: 0.000087 loss: 2.7984 (2.7795) grad_norm: 2.5218 (2.8401) time: 0.6328 [2021-03-28 06:52:12 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 200/1251] eta: 0:11:23 lr: 0.000087 loss: 2.8503 (2.7811) grad_norm: 2.5735 (2.8355) time: 0.6335 [2021-03-28 06:52:18 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 210/1251] eta: 0:11:16 lr: 0.000087 loss: 2.9661 (2.7836) grad_norm: 2.6586 (2.8307) time: 0.6343 [2021-03-28 06:52:25 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 220/1251] eta: 0:11:08 lr: 0.000087 loss: 2.9661 (2.7871) grad_norm: 2.6088 (2.8250) time: 0.6365 [2021-03-28 06:52:31 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 230/1251] eta: 0:11:01 lr: 0.000087 loss: 2.9408 (2.7912) grad_norm: 2.7348 (2.8247) time: 0.6337 [2021-03-28 06:52:37 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 240/1251] eta: 0:10:54 lr: 0.000087 loss: 2.9217 (2.7900) grad_norm: 2.8372 (2.8288) time: 0.6331 [2021-03-28 06:52:44 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 250/1251] eta: 0:10:48 lr: 0.000087 loss: 2.9688 (2.7951) grad_norm: 2.8678 (2.8331) time: 0.6408 [2021-03-28 06:52:50 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 260/1251] eta: 0:10:40 lr: 0.000086 loss: 3.0071 (2.7967) grad_norm: 2.8186 (2.8298) time: 0.6337 [2021-03-28 06:52:56 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 270/1251] eta: 0:10:33 lr: 0.000086 loss: 2.6353 (2.7859) grad_norm: 2.7311 (2.8310) time: 0.6253 [2021-03-28 06:53:02 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 280/1251] eta: 0:10:26 lr: 0.000086 loss: 2.8001 (2.7969) grad_norm: 2.7228 (2.8279) time: 0.6282 [2021-03-28 06:53:09 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 290/1251] eta: 0:10:19 lr: 0.000086 loss: 2.8875 (2.7974) grad_norm: 2.5892 (2.8213) time: 0.6291 [2021-03-28 06:53:15 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 300/1251] eta: 0:10:12 lr: 0.000086 loss: 2.7378 (2.7928) grad_norm: 2.6215 (2.8168) time: 0.6307 [2021-03-28 06:53:21 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 310/1251] eta: 0:10:05 lr: 0.000086 loss: 2.8516 (2.7985) grad_norm: 2.6615 (2.8285) time: 0.6287 [2021-03-28 06:53:28 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 320/1251] eta: 0:09:58 lr: 0.000086 loss: 2.9336 (2.8004) grad_norm: 2.6254 (2.8199) time: 0.6299 [2021-03-28 06:53:34 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 330/1251] eta: 0:09:52 lr: 0.000086 loss: 3.0295 (2.8021) grad_norm: 2.6254 (2.8230) time: 0.6320 [2021-03-28 06:53:40 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 340/1251] eta: 0:09:45 lr: 0.000086 loss: 2.9781 (2.8058) grad_norm: 2.8152 (2.8236) time: 0.6311 [2021-03-28 06:53:47 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 350/1251] eta: 0:09:38 lr: 0.000086 loss: 2.8461 (2.8039) grad_norm: 2.5440 (2.8195) time: 0.6330 [2021-03-28 06:53:53 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 360/1251] eta: 0:09:31 lr: 0.000086 loss: 2.8087 (2.8108) grad_norm: 2.5387 (2.8140) time: 0.6308 [2021-03-28 06:53:59 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 370/1251] eta: 0:09:25 lr: 0.000086 loss: 2.9854 (2.8149) grad_norm: 2.5387 (2.8094) time: 0.6320 [2021-03-28 06:54:06 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 380/1251] eta: 0:09:18 lr: 0.000086 loss: 2.9839 (2.8158) grad_norm: 2.5615 (2.8082) time: 0.6309 [2021-03-28 06:54:12 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 390/1251] eta: 0:09:11 lr: 0.000086 loss: 2.9668 (2.8145) grad_norm: 2.6233 (2.8079) time: 0.6272 [2021-03-28 06:54:18 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 400/1251] eta: 0:09:05 lr: 0.000086 loss: 2.7438 (2.8114) grad_norm: 2.6233 (2.8018) time: 0.6270 [2021-03-28 06:54:24 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 410/1251] eta: 0:08:58 lr: 0.000086 loss: 3.0089 (2.8157) grad_norm: 2.4843 (2.7962) time: 0.6307 [2021-03-28 06:54:31 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 420/1251] eta: 0:08:52 lr: 0.000086 loss: 3.0089 (2.8123) grad_norm: 2.4803 (2.7946) time: 0.6361 [2021-03-28 06:54:37 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 430/1251] eta: 0:08:45 lr: 0.000086 loss: 2.9619 (2.8144) grad_norm: 2.4803 (2.7896) time: 0.6318 [2021-03-28 06:54:43 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 440/1251] eta: 0:08:38 lr: 0.000086 loss: 2.9193 (2.8150) grad_norm: 2.5131 (2.7883) time: 0.6276 [2021-03-28 06:54:50 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 450/1251] eta: 0:08:32 lr: 0.000086 loss: 2.9193 (2.8191) grad_norm: 2.6502 (2.7933) time: 0.6323 [2021-03-28 06:54:56 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 460/1251] eta: 0:08:25 lr: 0.000086 loss: 2.9088 (2.8206) grad_norm: 2.5652 (2.7899) time: 0.6308 [2021-03-28 06:55:02 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 470/1251] eta: 0:08:19 lr: 0.000086 loss: 2.9088 (2.8227) grad_norm: 2.4978 (2.7985) time: 0.6287 [2021-03-28 06:55:09 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 480/1251] eta: 0:08:12 lr: 0.000086 loss: 3.0055 (2.8272) grad_norm: 2.5800 (2.8000) time: 0.6288 [2021-03-28 06:55:15 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 490/1251] eta: 0:08:06 lr: 0.000086 loss: 3.1048 (2.8305) grad_norm: 2.9045 (2.8056) time: 0.6253 [2021-03-28 06:55:21 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 500/1251] eta: 0:07:59 lr: 0.000086 loss: 2.9389 (2.8273) grad_norm: 2.9045 (2.8042) time: 0.6304 [2021-03-28 06:55:28 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 510/1251] eta: 0:07:53 lr: 0.000086 loss: 2.7380 (2.8267) grad_norm: 2.5892 (2.8024) time: 0.6381 [2021-03-28 06:55:34 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 520/1251] eta: 0:07:46 lr: 0.000086 loss: 2.7380 (2.8233) grad_norm: 2.5892 (2.8004) time: 0.6354 [2021-03-28 06:55:40 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 530/1251] eta: 0:07:40 lr: 0.000086 loss: 2.7456 (2.8195) grad_norm: 2.5687 (2.7971) time: 0.6289 [2021-03-28 06:55:46 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 540/1251] eta: 0:07:33 lr: 0.000086 loss: 2.6614 (2.8159) grad_norm: 2.7813 (2.7985) time: 0.6253 [2021-03-28 06:55:53 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 550/1251] eta: 0:07:27 lr: 0.000086 loss: 2.6975 (2.8166) grad_norm: 2.8303 (2.8107) time: 0.6357 [2021-03-28 06:55:59 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 560/1251] eta: 0:07:21 lr: 0.000086 loss: 2.6854 (2.8118) grad_norm: 2.8864 (2.8138) time: 0.6449 [2021-03-28 06:56:06 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 570/1251] eta: 0:07:14 lr: 0.000086 loss: 2.6879 (2.8120) grad_norm: 2.8737 (2.8200) time: 0.6346 [2021-03-28 06:56:12 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 580/1251] eta: 0:07:08 lr: 0.000086 loss: 2.8219 (2.8117) grad_norm: 2.6711 (2.8206) time: 0.6274 [2021-03-28 06:56:18 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 590/1251] eta: 0:07:01 lr: 0.000086 loss: 2.6491 (2.8069) grad_norm: 2.5717 (2.8177) time: 0.6273 [2021-03-28 06:56:25 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 600/1251] eta: 0:06:55 lr: 0.000086 loss: 2.3257 (2.8047) grad_norm: 2.6736 (2.8165) time: 0.6334 [2021-03-28 06:56:31 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 610/1251] eta: 0:06:48 lr: 0.000086 loss: 2.8683 (2.8069) grad_norm: 2.6976 (2.8188) time: 0.6386 [2021-03-28 06:56:37 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 620/1251] eta: 0:06:42 lr: 0.000086 loss: 3.0406 (2.8116) grad_norm: 2.7302 (2.8220) time: 0.6359 [2021-03-28 06:56:43 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 630/1251] eta: 0:06:35 lr: 0.000086 loss: 2.9694 (2.8098) grad_norm: 2.6445 (2.8195) time: 0.6291 [2021-03-28 06:56:50 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 640/1251] eta: 0:06:29 lr: 0.000086 loss: 2.7819 (2.8085) grad_norm: 2.7995 (2.8391) time: 0.6277 [2021-03-28 06:56:56 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 650/1251] eta: 0:06:23 lr: 0.000086 loss: 2.8229 (2.8116) grad_norm: 2.7995 (2.8361) time: 0.6316 [2021-03-28 06:57:02 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 660/1251] eta: 0:06:16 lr: 0.000086 loss: 2.6963 (2.8043) grad_norm: 2.6947 (2.8425) time: 0.6270 [2021-03-28 06:57:09 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 670/1251] eta: 0:06:10 lr: 0.000086 loss: 2.5093 (2.8025) grad_norm: 2.9925 (2.8463) time: 0.6278 [2021-03-28 06:57:15 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 680/1251] eta: 0:06:03 lr: 0.000086 loss: 2.7872 (2.7995) grad_norm: 2.7259 (2.8449) time: 0.6306 [2021-03-28 06:57:21 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 690/1251] eta: 0:05:57 lr: 0.000086 loss: 2.7962 (2.7951) grad_norm: 2.6724 (2.8432) time: 0.6266 [2021-03-28 06:57:28 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 700/1251] eta: 0:05:50 lr: 0.000086 loss: 2.6952 (2.7913) grad_norm: 2.7093 (2.8446) time: 0.6284 [2021-03-28 06:57:34 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 710/1251] eta: 0:05:44 lr: 0.000085 loss: 2.2159 (2.7861) grad_norm: 2.7616 (2.8452) time: 0.6343 [2021-03-28 06:57:40 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 720/1251] eta: 0:05:38 lr: 0.000085 loss: 2.6856 (2.7860) grad_norm: 2.7295 (2.8446) time: 0.6335 [2021-03-28 06:57:47 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 730/1251] eta: 0:05:31 lr: 0.000085 loss: 2.7907 (2.7847) grad_norm: 2.7049 (2.8420) time: 0.6320 [2021-03-28 06:57:53 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 740/1251] eta: 0:05:25 lr: 0.000085 loss: 2.8307 (2.7867) grad_norm: 2.7049 (2.8414) time: 0.6305 [2021-03-28 06:57:59 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 750/1251] eta: 0:05:18 lr: 0.000085 loss: 2.8321 (2.7847) grad_norm: 2.7845 (2.8410) time: 0.6364 [2021-03-28 06:58:06 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 760/1251] eta: 0:05:12 lr: 0.000085 loss: 2.7628 (2.7842) grad_norm: 2.8144 (2.8446) time: 0.6369 [2021-03-28 06:58:12 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 770/1251] eta: 0:05:06 lr: 0.000085 loss: 2.8722 (2.7851) grad_norm: 2.7102 (2.8430) time: 0.6362 [2021-03-28 06:58:18 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 780/1251] eta: 0:04:59 lr: 0.000085 loss: 2.7714 (2.7838) grad_norm: 2.5357 (2.8430) time: 0.6408 [2021-03-28 06:58:25 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 790/1251] eta: 0:04:53 lr: 0.000085 loss: 2.7961 (2.7849) grad_norm: 2.7190 (2.8509) time: 0.6355 [2021-03-28 06:58:31 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 800/1251] eta: 0:04:47 lr: 0.000085 loss: 2.9313 (2.7865) grad_norm: 2.7563 (2.8497) time: 0.6317 [2021-03-28 06:58:37 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 810/1251] eta: 0:04:40 lr: 0.000085 loss: 2.8408 (2.7865) grad_norm: 2.8709 (2.8524) time: 0.6295 [2021-03-28 06:58:44 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 820/1251] eta: 0:04:34 lr: 0.000085 loss: 2.8943 (2.7881) grad_norm: 2.7524 (2.8528) time: 0.6287 [2021-03-28 06:58:50 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 830/1251] eta: 0:04:27 lr: 0.000085 loss: 2.6816 (2.7837) grad_norm: 2.7524 (2.8560) time: 0.6276 [2021-03-28 06:58:56 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 840/1251] eta: 0:04:21 lr: 0.000085 loss: 2.8192 (2.7857) grad_norm: 2.7107 (2.8537) time: 0.6244 [2021-03-28 06:59:02 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 850/1251] eta: 0:04:15 lr: 0.000085 loss: 2.8671 (2.7854) grad_norm: 2.6374 (2.8612) time: 0.6292 [2021-03-28 06:59:09 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 860/1251] eta: 0:04:08 lr: 0.000085 loss: 2.7536 (2.7876) grad_norm: 2.7210 (2.8608) time: 0.6375 [2021-03-28 06:59:15 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 870/1251] eta: 0:04:02 lr: 0.000085 loss: 2.8921 (2.7894) grad_norm: 2.4708 (2.8601) time: 0.6380 [2021-03-28 06:59:21 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 880/1251] eta: 0:03:55 lr: 0.000085 loss: 2.9144 (2.7899) grad_norm: 2.8351 (2.8640) time: 0.6308 [2021-03-28 06:59:28 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 890/1251] eta: 0:03:49 lr: 0.000085 loss: 2.9145 (2.7897) grad_norm: 2.8351 (2.8648) time: 0.6243 [2021-03-28 06:59:34 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 900/1251] eta: 0:03:43 lr: 0.000085 loss: 2.7816 (2.7896) grad_norm: 2.6853 (2.8648) time: 0.6294 [2021-03-28 06:59:40 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 910/1251] eta: 0:03:36 lr: 0.000085 loss: 2.7568 (2.7907) grad_norm: 2.6504 (2.8634) time: 0.6311 [2021-03-28 06:59:47 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 920/1251] eta: 0:03:30 lr: 0.000085 loss: 2.9273 (2.7910) grad_norm: 2.6593 (2.8623) time: 0.6243 [2021-03-28 06:59:53 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 930/1251] eta: 0:03:23 lr: 0.000085 loss: 2.9485 (2.7933) grad_norm: 2.7601 (2.8623) time: 0.6264 [2021-03-28 06:59:59 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 940/1251] eta: 0:03:17 lr: 0.000085 loss: 2.9019 (2.7934) grad_norm: 2.7439 (2.8611) time: 0.6348 [2021-03-28 07:00:06 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 950/1251] eta: 0:03:11 lr: 0.000085 loss: 2.7598 (2.7939) grad_norm: 2.6281 (2.8583) time: 0.6324 [2021-03-28 07:00:12 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 960/1251] eta: 0:03:04 lr: 0.000085 loss: 2.8774 (2.7941) grad_norm: 2.4949 (2.8563) time: 0.6264 [2021-03-28 07:00:18 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 970/1251] eta: 0:02:58 lr: 0.000085 loss: 2.9578 (2.7946) grad_norm: 2.5293 (2.8577) time: 0.6258 [2021-03-28 07:00:24 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 980/1251] eta: 0:02:52 lr: 0.000085 loss: 2.9578 (2.7945) grad_norm: 2.5804 (2.8555) time: 0.6243 [2021-03-28 07:00:31 swin_base_patch4_window7_224] INFO: Epoch: [246] [ 990/1251] eta: 0:02:45 lr: 0.000085 loss: 3.0625 (2.7968) grad_norm: 2.7006 (2.8553) time: 0.6267 [2021-03-28 07:00:37 swin_base_patch4_window7_224] INFO: Epoch: [246] [1000/1251] eta: 0:02:39 lr: 0.000085 loss: 2.8525 (2.7953) grad_norm: 2.8807 (2.8569) time: 0.6281 [2021-03-28 07:00:43 swin_base_patch4_window7_224] INFO: Epoch: [246] [1010/1251] eta: 0:02:32 lr: 0.000085 loss: 2.7713 (2.7958) grad_norm: 2.7864 (2.8611) time: 0.6259 [2021-03-28 07:00:49 swin_base_patch4_window7_224] INFO: Epoch: [246] [1020/1251] eta: 0:02:26 lr: 0.000085 loss: 2.8474 (2.7954) grad_norm: 2.6776 (2.8625) time: 0.6261 [2021-03-28 07:00:56 swin_base_patch4_window7_224] INFO: Epoch: [246] [1030/1251] eta: 0:02:20 lr: 0.000085 loss: 2.9647 (2.7973) grad_norm: 2.6115 (2.8612) time: 0.6250 [2021-03-28 07:01:02 swin_base_patch4_window7_224] INFO: Epoch: [246] [1040/1251] eta: 0:02:13 lr: 0.000085 loss: 2.9268 (2.7952) grad_norm: 2.5624 (2.8587) time: 0.6286 [2021-03-28 07:01:08 swin_base_patch4_window7_224] INFO: Epoch: [246] [1050/1251] eta: 0:02:07 lr: 0.000085 loss: 2.6657 (2.7958) grad_norm: 2.5624 (2.8571) time: 0.6284 [2021-03-28 07:01:15 swin_base_patch4_window7_224] INFO: Epoch: [246] [1060/1251] eta: 0:02:01 lr: 0.000085 loss: 2.8009 (2.7965) grad_norm: 2.7119 (2.8556) time: 0.6298 [2021-03-28 07:01:21 swin_base_patch4_window7_224] INFO: Epoch: [246] [1070/1251] eta: 0:01:54 lr: 0.000085 loss: 2.7963 (2.7951) grad_norm: 2.5656 (2.8527) time: 0.6325 [2021-03-28 07:01:27 swin_base_patch4_window7_224] INFO: Epoch: [246] [1080/1251] eta: 0:01:48 lr: 0.000085 loss: 2.7211 (2.7933) grad_norm: 2.5168 (2.8511) time: 0.6337 [2021-03-28 07:01:34 swin_base_patch4_window7_224] INFO: Epoch: [246] [1090/1251] eta: 0:01:42 lr: 0.000085 loss: 2.5922 (2.7928) grad_norm: 2.6292 (2.8501) time: 0.6340 [2021-03-28 07:01:40 swin_base_patch4_window7_224] INFO: Epoch: [246] [1100/1251] eta: 0:01:35 lr: 0.000085 loss: 2.5922 (2.7907) grad_norm: 2.7135 (2.8515) time: 0.6312 [2021-03-28 07:01:46 swin_base_patch4_window7_224] INFO: Epoch: [246] [1110/1251] eta: 0:01:29 lr: 0.000085 loss: 2.6766 (2.7905) grad_norm: 2.6474 (2.8490) time: 0.6331 [2021-03-28 07:01:52 swin_base_patch4_window7_224] INFO: Epoch: [246] [1120/1251] eta: 0:01:23 lr: 0.000085 loss: 2.9522 (2.7925) grad_norm: 2.6474 (2.8496) time: 0.6290 [2021-03-28 07:01:59 swin_base_patch4_window7_224] INFO: Epoch: [246] [1130/1251] eta: 0:01:16 lr: 0.000085 loss: 3.0144 (2.7947) grad_norm: 2.8524 (2.8518) time: 0.6245 [2021-03-28 07:02:05 swin_base_patch4_window7_224] INFO: Epoch: [246] [1140/1251] eta: 0:01:10 lr: 0.000085 loss: 3.0056 (2.7957) grad_norm: 2.7851 (2.8504) time: 0.6268 [2021-03-28 07:02:11 swin_base_patch4_window7_224] INFO: Epoch: [246] [1150/1251] eta: 0:01:04 lr: 0.000085 loss: 2.8549 (2.7947) grad_norm: 2.7203 (2.8504) time: 0.6312 [2021-03-28 07:02:18 swin_base_patch4_window7_224] INFO: Epoch: [246] [1160/1251] eta: 0:00:57 lr: 0.000085 loss: 2.8549 (2.7943) grad_norm: 2.5972 (2.8487) time: 0.6306 [2021-03-28 07:02:24 swin_base_patch4_window7_224] INFO: Epoch: [246] [1170/1251] eta: 0:00:51 lr: 0.000084 loss: 2.9484 (2.7951) grad_norm: 2.5983 (2.8489) time: 0.6256 [2021-03-28 07:02:30 swin_base_patch4_window7_224] INFO: Epoch: [246] [1180/1251] eta: 0:00:45 lr: 0.000084 loss: 2.9231 (2.7969) grad_norm: 2.6765 (2.8481) time: 0.6234 [2021-03-28 07:02:36 swin_base_patch4_window7_224] INFO: Epoch: [246] [1190/1251] eta: 0:00:38 lr: 0.000084 loss: 2.9099 (2.7961) grad_norm: 2.7007 (2.8483) time: 0.6271 [2021-03-28 07:02:43 swin_base_patch4_window7_224] INFO: Epoch: [246] [1200/1251] eta: 0:00:32 lr: 0.000084 loss: 2.9099 (2.7967) grad_norm: 2.8651 (2.8499) time: 0.6284 [2021-03-28 07:02:49 swin_base_patch4_window7_224] INFO: Epoch: [246] [1210/1251] eta: 0:00:25 lr: 0.000084 loss: 2.8404 (2.7951) grad_norm: 2.7942 (2.8517) time: 0.6278 [2021-03-28 07:02:55 swin_base_patch4_window7_224] INFO: Epoch: [246] [1220/1251] eta: 0:00:19 lr: 0.000084 loss: 2.7471 (2.7949) grad_norm: 2.5408 (2.8510) time: 0.6298 [2021-03-28 07:03:01 swin_base_patch4_window7_224] INFO: Epoch: [246] [1230/1251] eta: 0:00:13 lr: 0.000084 loss: 2.9330 (2.7941) grad_norm: 2.4906 (2.8483) time: 0.6271 [2021-03-28 07:03:08 swin_base_patch4_window7_224] INFO: Epoch: [246] [1240/1251] eta: 0:00:06 lr: 0.000084 loss: 2.9574 (2.7955) grad_norm: 2.5256 (2.8484) time: 0.6256 [2021-03-28 07:03:14 swin_base_patch4_window7_224] INFO: Epoch: [246] [1250/1251] eta: 0:00:00 lr: 0.000084 loss: 2.9596 (2.7966) grad_norm: 2.6554 (2.8569) time: 0.6208 [2021-03-28 07:03:25 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:42 loss: 0.7318 (0.7318) acc1: 85.9375 (85.9375) acc5: 95.3125 (95.3125) [2021-03-28 07:03:28 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7129 (0.7103) acc1: 84.3750 (83.9489) acc5: 95.3125 (95.7386) [2021-03-28 07:03:30 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7129 (0.7475) acc1: 81.2500 (81.8452) acc5: 95.3125 (96.3542) [2021-03-28 07:03:32 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7680 (0.7497) acc1: 79.6875 (81.9556) acc5: 96.8750 (96.4718) [2021-03-28 07:03:34 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7680 (0.7739) acc1: 79.6875 (81.3643) acc5: 96.8750 (96.1509) [2021-03-28 07:03:35 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7708 (0.7619) acc1: 79.6875 (81.8240) acc5: 95.3125 (96.2240) [2021-03-28 07:03:48 swin_base_patch4_window7_224] INFO: * Acc@1 82.776 Acc@5 96.326 loss 0.750 [2021-03-28 07:03:48 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.8% [2021-03-28 07:03:48 swin_base_patch4_window7_224] INFO: Max accuracy: 82.78% [2021-03-28 07:03:53 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 0/1251] eta: 1:36:00 lr: 0.000084 loss: 2.6149 (2.6149) grad_norm: 2.5589 (2.5589) time: 4.6050 [2021-03-28 07:03:59 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 10/1251] eta: 0:20:28 lr: 0.000084 loss: 2.8361 (2.9383) grad_norm: 2.7282 (2.8677) time: 0.9903 [2021-03-28 07:04:05 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 20/1251] eta: 0:16:47 lr: 0.000084 loss: 2.9404 (2.9676) grad_norm: 2.7282 (2.8230) time: 0.6295 [2021-03-28 07:04:12 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 30/1251] eta: 0:15:30 lr: 0.000084 loss: 2.8843 (2.8774) grad_norm: 2.6879 (2.8544) time: 0.6361 [2021-03-28 07:04:18 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 40/1251] eta: 0:14:44 lr: 0.000084 loss: 2.5749 (2.8271) grad_norm: 2.6871 (2.8003) time: 0.6379 [2021-03-28 07:04:24 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 50/1251] eta: 0:14:15 lr: 0.000084 loss: 2.6443 (2.7768) grad_norm: 2.6771 (2.8334) time: 0.6356 [2021-03-28 07:04:31 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 60/1251] eta: 0:13:54 lr: 0.000084 loss: 2.7970 (2.7689) grad_norm: 2.6771 (2.8549) time: 0.6384 [2021-03-28 07:04:37 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 70/1251] eta: 0:13:35 lr: 0.000084 loss: 2.8941 (2.7687) grad_norm: 2.5982 (2.9099) time: 0.6348 [2021-03-28 07:04:43 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 80/1251] eta: 0:13:20 lr: 0.000084 loss: 2.6927 (2.7582) grad_norm: 2.6497 (2.9041) time: 0.6310 [2021-03-28 07:04:50 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 90/1251] eta: 0:13:07 lr: 0.000084 loss: 2.6096 (2.7465) grad_norm: 2.6506 (2.8875) time: 0.6333 [2021-03-28 07:04:56 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 100/1251] eta: 0:12:54 lr: 0.000084 loss: 2.6371 (2.7560) grad_norm: 2.7409 (2.8966) time: 0.6314 [2021-03-28 07:05:02 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 110/1251] eta: 0:12:43 lr: 0.000084 loss: 2.9165 (2.7672) grad_norm: 2.9994 (2.9052) time: 0.6294 [2021-03-28 07:05:08 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 120/1251] eta: 0:12:33 lr: 0.000084 loss: 2.5446 (2.7499) grad_norm: 2.8525 (2.9058) time: 0.6296 [2021-03-28 07:05:15 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 130/1251] eta: 0:12:22 lr: 0.000084 loss: 2.5970 (2.7461) grad_norm: 2.6184 (2.8848) time: 0.6241 [2021-03-28 07:05:21 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 140/1251] eta: 0:12:13 lr: 0.000084 loss: 2.7905 (2.7584) grad_norm: 2.6212 (2.8758) time: 0.6263 [2021-03-28 07:05:27 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 150/1251] eta: 0:12:04 lr: 0.000084 loss: 2.7662 (2.7641) grad_norm: 2.6212 (2.8777) time: 0.6312 [2021-03-28 07:05:34 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 160/1251] eta: 0:11:55 lr: 0.000084 loss: 2.7406 (2.7587) grad_norm: 2.5579 (2.8560) time: 0.6273 [2021-03-28 07:05:40 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 170/1251] eta: 0:11:47 lr: 0.000084 loss: 2.7348 (2.7637) grad_norm: 2.4372 (2.8414) time: 0.6249 [2021-03-28 07:05:46 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 180/1251] eta: 0:11:39 lr: 0.000084 loss: 2.9135 (2.7779) grad_norm: 2.5264 (2.8385) time: 0.6330 [2021-03-28 07:05:52 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 190/1251] eta: 0:11:31 lr: 0.000084 loss: 2.8834 (2.7690) grad_norm: 2.6231 (2.8249) time: 0.6320 [2021-03-28 07:05:59 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 200/1251] eta: 0:11:23 lr: 0.000084 loss: 2.7386 (2.7637) grad_norm: 2.4823 (2.8082) time: 0.6225 [2021-03-28 07:06:05 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 210/1251] eta: 0:11:15 lr: 0.000084 loss: 2.7561 (2.7524) grad_norm: 2.4566 (2.8040) time: 0.6245 [2021-03-28 07:06:11 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 220/1251] eta: 0:11:08 lr: 0.000084 loss: 2.8129 (2.7652) grad_norm: 2.6267 (2.8083) time: 0.6322 [2021-03-28 07:06:18 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 230/1251] eta: 0:11:01 lr: 0.000084 loss: 2.9050 (2.7685) grad_norm: 2.6862 (2.8135) time: 0.6322 [2021-03-28 07:06:24 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 240/1251] eta: 0:10:54 lr: 0.000084 loss: 2.8179 (2.7668) grad_norm: 2.6197 (2.8041) time: 0.6291 [2021-03-28 07:06:30 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 250/1251] eta: 0:10:47 lr: 0.000084 loss: 2.8179 (2.7629) grad_norm: 2.6039 (2.7997) time: 0.6324 [2021-03-28 07:06:37 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 260/1251] eta: 0:10:40 lr: 0.000084 loss: 2.8862 (2.7663) grad_norm: 2.7268 (2.8012) time: 0.6319 [2021-03-28 07:06:43 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 270/1251] eta: 0:10:33 lr: 0.000084 loss: 2.8911 (2.7668) grad_norm: 2.7268 (2.7985) time: 0.6299 [2021-03-28 07:06:49 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 280/1251] eta: 0:10:26 lr: 0.000084 loss: 2.9513 (2.7643) grad_norm: 2.5420 (2.7972) time: 0.6276 [2021-03-28 07:06:55 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 290/1251] eta: 0:10:18 lr: 0.000084 loss: 2.9318 (2.7650) grad_norm: 2.7206 (2.7988) time: 0.6237 [2021-03-28 07:07:02 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 300/1251] eta: 0:10:11 lr: 0.000084 loss: 2.8670 (2.7679) grad_norm: 2.7623 (2.8026) time: 0.6238 [2021-03-28 07:07:08 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 310/1251] eta: 0:10:04 lr: 0.000084 loss: 2.8972 (2.7734) grad_norm: 2.7604 (2.8133) time: 0.6285 [2021-03-28 07:07:14 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 320/1251] eta: 0:09:58 lr: 0.000084 loss: 2.8972 (2.7764) grad_norm: 2.7604 (2.8192) time: 0.6291 [2021-03-28 07:07:21 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 330/1251] eta: 0:09:51 lr: 0.000084 loss: 2.8840 (2.7812) grad_norm: 2.8516 (2.8244) time: 0.6301 [2021-03-28 07:07:27 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 340/1251] eta: 0:09:44 lr: 0.000084 loss: 2.8842 (2.7824) grad_norm: 2.5105 (2.8132) time: 0.6285 [2021-03-28 07:07:33 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 350/1251] eta: 0:09:37 lr: 0.000084 loss: 2.9481 (2.7836) grad_norm: 2.5528 (2.8212) time: 0.6289 [2021-03-28 07:07:39 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 360/1251] eta: 0:09:31 lr: 0.000084 loss: 2.7234 (2.7819) grad_norm: 2.6304 (2.8200) time: 0.6310 [2021-03-28 07:07:46 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 370/1251] eta: 0:09:24 lr: 0.000083 loss: 2.6904 (2.7770) grad_norm: 2.5599 (2.8149) time: 0.6329 [2021-03-28 07:07:52 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 380/1251] eta: 0:09:18 lr: 0.000083 loss: 2.6904 (2.7771) grad_norm: 2.6579 (2.8140) time: 0.6375 [2021-03-28 07:07:59 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 390/1251] eta: 0:09:11 lr: 0.000083 loss: 2.8703 (2.7761) grad_norm: 2.7354 (2.8166) time: 0.6389 [2021-03-28 07:08:05 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 400/1251] eta: 0:09:04 lr: 0.000083 loss: 2.8169 (2.7774) grad_norm: 2.7453 (2.8201) time: 0.6314 [2021-03-28 07:08:11 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 410/1251] eta: 0:08:58 lr: 0.000083 loss: 2.8169 (2.7804) grad_norm: 2.6658 (2.8238) time: 0.6297 [2021-03-28 07:08:17 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 420/1251] eta: 0:08:51 lr: 0.000083 loss: 2.7481 (2.7741) grad_norm: 2.6505 (2.8236) time: 0.6306 [2021-03-28 07:08:24 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 430/1251] eta: 0:08:45 lr: 0.000083 loss: 2.4965 (2.7723) grad_norm: 2.5381 (2.8207) time: 0.6256 [2021-03-28 07:08:30 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 440/1251] eta: 0:08:38 lr: 0.000083 loss: 2.8143 (2.7712) grad_norm: 2.5101 (2.8146) time: 0.6231 [2021-03-28 07:08:36 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 450/1251] eta: 0:08:31 lr: 0.000083 loss: 2.6978 (2.7667) grad_norm: 2.4836 (2.8080) time: 0.6205 [2021-03-28 07:08:42 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 460/1251] eta: 0:08:25 lr: 0.000083 loss: 2.6692 (2.7637) grad_norm: 2.4111 (2.8039) time: 0.6233 [2021-03-28 07:08:49 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 470/1251] eta: 0:08:18 lr: 0.000083 loss: 2.6877 (2.7604) grad_norm: 2.6090 (2.8035) time: 0.6252 [2021-03-28 07:08:55 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 480/1251] eta: 0:08:12 lr: 0.000083 loss: 2.7336 (2.7619) grad_norm: 2.5922 (2.8018) time: 0.6314 [2021-03-28 07:09:01 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 490/1251] eta: 0:08:05 lr: 0.000083 loss: 2.9306 (2.7635) grad_norm: 2.5663 (2.8034) time: 0.6338 [2021-03-28 07:09:08 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 500/1251] eta: 0:07:59 lr: 0.000083 loss: 2.9306 (2.7618) grad_norm: 2.6442 (2.8014) time: 0.6308 [2021-03-28 07:09:14 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 510/1251] eta: 0:07:52 lr: 0.000083 loss: 2.7503 (2.7626) grad_norm: 2.5874 (2.8049) time: 0.6290 [2021-03-28 07:09:20 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 520/1251] eta: 0:07:45 lr: 0.000083 loss: 2.7082 (2.7613) grad_norm: 2.6798 (2.8060) time: 0.6251 [2021-03-28 07:09:26 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 530/1251] eta: 0:07:39 lr: 0.000083 loss: 2.8888 (2.7642) grad_norm: 2.8203 (2.8186) time: 0.6249 [2021-03-28 07:09:33 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 540/1251] eta: 0:07:32 lr: 0.000083 loss: 3.0105 (2.7658) grad_norm: 2.9117 (2.8200) time: 0.6300 [2021-03-28 07:09:39 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 550/1251] eta: 0:07:26 lr: 0.000083 loss: 3.0105 (2.7702) grad_norm: 2.9037 (2.8231) time: 0.6411 [2021-03-28 07:09:46 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 560/1251] eta: 0:07:20 lr: 0.000083 loss: 2.9819 (2.7709) grad_norm: 2.7700 (2.8232) time: 0.6430 [2021-03-28 07:09:52 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 570/1251] eta: 0:07:13 lr: 0.000083 loss: 2.7869 (2.7697) grad_norm: 2.8064 (2.8239) time: 0.6331 [2021-03-28 07:09:58 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 580/1251] eta: 0:07:07 lr: 0.000083 loss: 2.9023 (2.7736) grad_norm: 2.7457 (2.8220) time: 0.6307 [2021-03-28 07:10:05 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 590/1251] eta: 0:07:01 lr: 0.000083 loss: 2.8699 (2.7732) grad_norm: 2.5878 (2.8193) time: 0.6349 [2021-03-28 07:10:11 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 600/1251] eta: 0:06:54 lr: 0.000083 loss: 2.8699 (2.7750) grad_norm: 2.6614 (2.8250) time: 0.6375 [2021-03-28 07:10:17 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 610/1251] eta: 0:06:48 lr: 0.000083 loss: 2.9141 (2.7766) grad_norm: 2.9095 (2.8272) time: 0.6423 [2021-03-28 07:10:24 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 620/1251] eta: 0:06:42 lr: 0.000083 loss: 2.8124 (2.7767) grad_norm: 2.7848 (2.8283) time: 0.6430 [2021-03-28 07:10:30 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 630/1251] eta: 0:06:35 lr: 0.000083 loss: 2.8124 (2.7755) grad_norm: 2.7362 (2.8402) time: 0.6354 [2021-03-28 07:10:36 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 640/1251] eta: 0:06:29 lr: 0.000083 loss: 2.8307 (2.7743) grad_norm: 2.7246 (2.8369) time: 0.6339 [2021-03-28 07:10:43 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 650/1251] eta: 0:06:22 lr: 0.000083 loss: 2.8032 (2.7750) grad_norm: 2.6613 (2.8353) time: 0.6333 [2021-03-28 07:10:49 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 660/1251] eta: 0:06:16 lr: 0.000083 loss: 2.8442 (2.7760) grad_norm: 2.7072 (2.8394) time: 0.6294 [2021-03-28 07:10:55 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 670/1251] eta: 0:06:09 lr: 0.000083 loss: 2.9221 (2.7770) grad_norm: 2.8136 (2.8418) time: 0.6258 [2021-03-28 07:11:02 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 680/1251] eta: 0:06:03 lr: 0.000083 loss: 2.8601 (2.7738) grad_norm: 2.8136 (2.8414) time: 0.6238 [2021-03-28 07:11:08 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 690/1251] eta: 0:05:57 lr: 0.000083 loss: 2.8097 (2.7741) grad_norm: 2.6819 (2.8406) time: 0.6271 [2021-03-28 07:11:14 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 700/1251] eta: 0:05:50 lr: 0.000083 loss: 2.8101 (2.7732) grad_norm: 2.7135 (2.8400) time: 0.6292 [2021-03-28 07:11:20 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 710/1251] eta: 0:05:44 lr: 0.000083 loss: 2.8238 (2.7735) grad_norm: 2.7953 (2.8398) time: 0.6305 [2021-03-28 07:11:27 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 720/1251] eta: 0:05:37 lr: 0.000083 loss: 2.8256 (2.7743) grad_norm: 2.6299 (2.8399) time: 0.6274 [2021-03-28 07:11:33 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 730/1251] eta: 0:05:31 lr: 0.000083 loss: 2.9828 (2.7774) grad_norm: 2.6525 (2.8379) time: 0.6273 [2021-03-28 07:11:39 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 740/1251] eta: 0:05:25 lr: 0.000083 loss: 2.9588 (2.7782) grad_norm: 2.6966 (2.8380) time: 0.6334 [2021-03-28 07:11:46 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 750/1251] eta: 0:05:18 lr: 0.000083 loss: 2.8810 (2.7785) grad_norm: 2.7861 (2.8379) time: 0.6305 [2021-03-28 07:11:52 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 760/1251] eta: 0:05:12 lr: 0.000083 loss: 2.9267 (2.7800) grad_norm: 2.6604 (2.8433) time: 0.6289 [2021-03-28 07:11:58 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 770/1251] eta: 0:05:05 lr: 0.000083 loss: 2.9487 (2.7816) grad_norm: 2.6620 (2.8485) time: 0.6295 [2021-03-28 07:12:05 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 780/1251] eta: 0:04:59 lr: 0.000083 loss: 2.9648 (2.7837) grad_norm: 2.6801 (2.8461) time: 0.6336 [2021-03-28 07:12:11 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 790/1251] eta: 0:04:53 lr: 0.000083 loss: 2.9808 (2.7865) grad_norm: 2.7284 (2.8531) time: 0.6352 [2021-03-28 07:12:17 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 800/1251] eta: 0:04:46 lr: 0.000083 loss: 2.9808 (2.7848) grad_norm: 2.8465 (2.8554) time: 0.6353 [2021-03-28 07:12:24 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 810/1251] eta: 0:04:40 lr: 0.000083 loss: 2.6288 (2.7846) grad_norm: 2.7848 (2.8547) time: 0.6395 [2021-03-28 07:12:30 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 820/1251] eta: 0:04:33 lr: 0.000083 loss: 2.9177 (2.7844) grad_norm: 2.8087 (2.8547) time: 0.6327 [2021-03-28 07:12:36 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 830/1251] eta: 0:04:27 lr: 0.000083 loss: 2.9334 (2.7864) grad_norm: 2.8489 (2.8550) time: 0.6284 [2021-03-28 07:12:43 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 840/1251] eta: 0:04:21 lr: 0.000082 loss: 3.0561 (2.7878) grad_norm: 2.6695 (2.8531) time: 0.6279 [2021-03-28 07:12:49 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 850/1251] eta: 0:04:14 lr: 0.000082 loss: 2.9234 (2.7886) grad_norm: 2.8075 (2.8595) time: 0.6323 [2021-03-28 07:12:55 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 860/1251] eta: 0:04:08 lr: 0.000082 loss: 2.9687 (2.7908) grad_norm: 2.8517 (2.8584) time: 0.6350 [2021-03-28 07:13:02 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 870/1251] eta: 0:04:02 lr: 0.000082 loss: 2.9687 (2.7918) grad_norm: 2.7275 (2.8587) time: 0.6311 [2021-03-28 07:13:08 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 880/1251] eta: 0:03:55 lr: 0.000082 loss: 3.0154 (2.7946) grad_norm: 2.8369 (2.8661) time: 0.6285 [2021-03-28 07:13:14 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 890/1251] eta: 0:03:49 lr: 0.000082 loss: 3.0154 (2.7954) grad_norm: 2.8447 (2.8648) time: 0.6316 [2021-03-28 07:13:20 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 900/1251] eta: 0:03:42 lr: 0.000082 loss: 2.7278 (2.7949) grad_norm: 2.8075 (2.8649) time: 0.6294 [2021-03-28 07:13:27 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 910/1251] eta: 0:03:36 lr: 0.000082 loss: 2.7229 (2.7953) grad_norm: 2.6667 (2.8642) time: 0.6250 [2021-03-28 07:13:33 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 920/1251] eta: 0:03:30 lr: 0.000082 loss: 3.0141 (2.7984) grad_norm: 2.6888 (2.8632) time: 0.6263 [2021-03-28 07:13:39 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 930/1251] eta: 0:03:23 lr: 0.000082 loss: 2.9422 (2.7983) grad_norm: 2.7085 (2.8661) time: 0.6289 [2021-03-28 07:13:46 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 940/1251] eta: 0:03:17 lr: 0.000082 loss: 2.7749 (2.7978) grad_norm: 2.6826 (2.8656) time: 0.6303 [2021-03-28 07:13:52 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 950/1251] eta: 0:03:11 lr: 0.000082 loss: 2.7367 (2.7977) grad_norm: 2.6587 (2.8671) time: 0.6277 [2021-03-28 07:13:58 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 960/1251] eta: 0:03:04 lr: 0.000082 loss: 2.9749 (2.8006) grad_norm: 2.6909 (2.8664) time: 0.6303 [2021-03-28 07:14:04 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 970/1251] eta: 0:02:58 lr: 0.000082 loss: 2.8825 (2.7986) grad_norm: 2.6409 (2.8673) time: 0.6317 [2021-03-28 07:14:11 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 980/1251] eta: 0:02:52 lr: 0.000082 loss: 2.8318 (2.8002) grad_norm: 2.5894 (2.8653) time: 0.6326 [2021-03-28 07:14:17 swin_base_patch4_window7_224] INFO: Epoch: [247] [ 990/1251] eta: 0:02:45 lr: 0.000082 loss: 2.9198 (2.7971) grad_norm: 2.6216 (2.8652) time: 0.6321 [2021-03-28 07:14:23 swin_base_patch4_window7_224] INFO: Epoch: [247] [1000/1251] eta: 0:02:39 lr: 0.000082 loss: 2.5158 (2.7954) grad_norm: 2.6216 (2.8643) time: 0.6277 [2021-03-28 07:14:30 swin_base_patch4_window7_224] INFO: Epoch: [247] [1010/1251] eta: 0:02:32 lr: 0.000082 loss: 2.7044 (2.7955) grad_norm: 2.6026 (2.8663) time: 0.6252 [2021-03-28 07:14:36 swin_base_patch4_window7_224] INFO: Epoch: [247] [1020/1251] eta: 0:02:26 lr: 0.000082 loss: 2.8617 (2.7957) grad_norm: 2.5938 (2.8637) time: 0.6240 [2021-03-28 07:14:42 swin_base_patch4_window7_224] INFO: Epoch: [247] [1030/1251] eta: 0:02:20 lr: 0.000082 loss: 2.7959 (2.7952) grad_norm: 2.5741 (2.8630) time: 0.6256 [2021-03-28 07:14:48 swin_base_patch4_window7_224] INFO: Epoch: [247] [1040/1251] eta: 0:02:13 lr: 0.000082 loss: 2.8478 (2.7971) grad_norm: 2.6746 (2.8653) time: 0.6287 [2021-03-28 07:14:55 swin_base_patch4_window7_224] INFO: Epoch: [247] [1050/1251] eta: 0:02:07 lr: 0.000082 loss: 2.9646 (2.7990) grad_norm: 2.9213 (2.8653) time: 0.6304 [2021-03-28 07:15:01 swin_base_patch4_window7_224] INFO: Epoch: [247] [1060/1251] eta: 0:02:01 lr: 0.000082 loss: 2.9646 (2.7993) grad_norm: 2.7164 (2.8647) time: 0.6274 [2021-03-28 07:15:07 swin_base_patch4_window7_224] INFO: Epoch: [247] [1070/1251] eta: 0:01:54 lr: 0.000082 loss: 2.9445 (2.7996) grad_norm: 2.7137 (2.8637) time: 0.6261 [2021-03-28 07:15:14 swin_base_patch4_window7_224] INFO: Epoch: [247] [1080/1251] eta: 0:01:48 lr: 0.000082 loss: 2.8680 (2.7994) grad_norm: 2.7137 (2.8632) time: 0.6287 [2021-03-28 07:15:20 swin_base_patch4_window7_224] INFO: Epoch: [247] [1090/1251] eta: 0:01:42 lr: 0.000082 loss: 2.6641 (2.7965) grad_norm: 2.7711 (2.8622) time: 0.6260 [2021-03-28 07:15:26 swin_base_patch4_window7_224] INFO: Epoch: [247] [1100/1251] eta: 0:01:35 lr: 0.000082 loss: 2.7679 (2.7975) grad_norm: 2.7711 (nan) time: 0.6208 [2021-03-28 07:15:32 swin_base_patch4_window7_224] INFO: Epoch: [247] [1110/1251] eta: 0:01:29 lr: 0.000082 loss: 3.0684 (2.7998) grad_norm: 2.6512 (nan) time: 0.6225 [2021-03-28 07:15:39 swin_base_patch4_window7_224] INFO: Epoch: [247] [1120/1251] eta: 0:01:23 lr: 0.000082 loss: 2.9840 (2.7993) grad_norm: 2.8664 (nan) time: 0.6272 [2021-03-28 07:15:45 swin_base_patch4_window7_224] INFO: Epoch: [247] [1130/1251] eta: 0:01:16 lr: 0.000082 loss: 2.8811 (2.7991) grad_norm: 2.8734 (nan) time: 0.6264 [2021-03-28 07:15:51 swin_base_patch4_window7_224] INFO: Epoch: [247] [1140/1251] eta: 0:01:10 lr: 0.000082 loss: 2.9164 (2.7976) grad_norm: 2.5217 (nan) time: 0.6277 [2021-03-28 07:15:57 swin_base_patch4_window7_224] INFO: Epoch: [247] [1150/1251] eta: 0:01:03 lr: 0.000082 loss: 2.9164 (2.7961) grad_norm: 2.5934 (nan) time: 0.6313 [2021-03-28 07:16:04 swin_base_patch4_window7_224] INFO: Epoch: [247] [1160/1251] eta: 0:00:57 lr: 0.000082 loss: 2.8063 (2.7946) grad_norm: 2.6079 (nan) time: 0.6329 [2021-03-28 07:16:10 swin_base_patch4_window7_224] INFO: Epoch: [247] [1170/1251] eta: 0:00:51 lr: 0.000082 loss: 2.8003 (2.7942) grad_norm: 2.6495 (nan) time: 0.6300 [2021-03-28 07:16:16 swin_base_patch4_window7_224] INFO: Epoch: [247] [1180/1251] eta: 0:00:44 lr: 0.000082 loss: 2.7386 (2.7922) grad_norm: 2.6841 (nan) time: 0.6287 [2021-03-28 07:16:23 swin_base_patch4_window7_224] INFO: Epoch: [247] [1190/1251] eta: 0:00:38 lr: 0.000082 loss: 2.7386 (2.7931) grad_norm: 2.6841 (nan) time: 0.6261 [2021-03-28 07:16:29 swin_base_patch4_window7_224] INFO: Epoch: [247] [1200/1251] eta: 0:00:32 lr: 0.000082 loss: 2.8543 (2.7948) grad_norm: 2.5412 (nan) time: 0.6243 [2021-03-28 07:16:35 swin_base_patch4_window7_224] INFO: Epoch: [247] [1210/1251] eta: 0:00:25 lr: 0.000082 loss: 2.9285 (2.7959) grad_norm: 2.3590 (nan) time: 0.6249 [2021-03-28 07:16:41 swin_base_patch4_window7_224] INFO: Epoch: [247] [1220/1251] eta: 0:00:19 lr: 0.000082 loss: 2.9956 (2.7968) grad_norm: 2.4171 (nan) time: 0.6244 [2021-03-28 07:16:48 swin_base_patch4_window7_224] INFO: Epoch: [247] [1230/1251] eta: 0:00:13 lr: 0.000082 loss: 3.0041 (2.7970) grad_norm: 2.6571 (nan) time: 0.6255 [2021-03-28 07:16:54 swin_base_patch4_window7_224] INFO: Epoch: [247] [1240/1251] eta: 0:00:06 lr: 0.000082 loss: 2.8995 (2.7967) grad_norm: 2.7710 (nan) time: 0.6282 [2021-03-28 07:17:00 swin_base_patch4_window7_224] INFO: Epoch: [247] [1250/1251] eta: 0:00:00 lr: 0.000082 loss: 2.8068 (2.7968) grad_norm: 2.7635 (nan) time: 0.6217 [2021-03-28 07:17:11 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:51 loss: 0.7784 (0.7784) acc1: 79.6875 (79.6875) acc5: 95.3125 (95.3125) [2021-03-28 07:17:14 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7784 (0.8107) acc1: 79.6875 (81.3920) acc5: 95.3125 (95.7386) [2021-03-28 07:17:16 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7675 (0.7596) acc1: 81.2500 (82.5149) acc5: 96.8750 (96.3542) [2021-03-28 07:17:18 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7547 (0.7693) acc1: 81.2500 (82.1573) acc5: 96.8750 (96.0685) [2021-03-28 07:17:20 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7547 (0.7603) acc1: 82.8125 (82.3552) acc5: 95.3125 (96.1509) [2021-03-28 07:17:22 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7291 (0.7681) acc1: 82.8125 (82.0160) acc5: 95.3125 (96.1600) [2021-03-28 07:17:33 swin_base_patch4_window7_224] INFO: * Acc@1 82.776 Acc@5 96.314 loss 0.751 [2021-03-28 07:17:33 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.8% [2021-03-28 07:17:33 swin_base_patch4_window7_224] INFO: Max accuracy: 82.78% [2021-03-28 07:17:37 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 0/1251] eta: 1:32:50 lr: 0.000082 loss: 1.9762 (1.9762) grad_norm: 2.3342 (2.3342) time: 4.4528 [2021-03-28 07:17:44 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 10/1251] eta: 0:20:30 lr: 0.000082 loss: 2.8944 (2.7414) grad_norm: 2.5780 (2.6624) time: 0.9915 [2021-03-28 07:17:50 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 20/1251] eta: 0:16:50 lr: 0.000082 loss: 2.9113 (2.8264) grad_norm: 2.5603 (2.6256) time: 0.6393 [2021-03-28 07:17:57 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 30/1251] eta: 0:15:30 lr: 0.000082 loss: 2.9113 (2.8220) grad_norm: 2.6603 (2.7201) time: 0.6358 [2021-03-28 07:18:03 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 40/1251] eta: 0:14:43 lr: 0.000082 loss: 2.7339 (2.8214) grad_norm: 2.9933 (2.8044) time: 0.6341 [2021-03-28 07:18:09 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 50/1251] eta: 0:14:12 lr: 0.000081 loss: 2.6370 (2.7757) grad_norm: 2.7906 (2.7771) time: 0.6296 [2021-03-28 07:18:16 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 60/1251] eta: 0:13:49 lr: 0.000081 loss: 2.7205 (2.7531) grad_norm: 2.6983 (2.7792) time: 0.6280 [2021-03-28 07:18:22 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 70/1251] eta: 0:13:31 lr: 0.000081 loss: 2.8793 (2.7704) grad_norm: 2.8878 (2.8090) time: 0.6300 [2021-03-28 07:18:28 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 80/1251] eta: 0:13:15 lr: 0.000081 loss: 2.8261 (2.7809) grad_norm: 2.5954 (2.7789) time: 0.6274 [2021-03-28 07:18:34 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 90/1251] eta: 0:13:01 lr: 0.000081 loss: 2.9289 (2.8086) grad_norm: 2.5605 (2.8105) time: 0.6214 [2021-03-28 07:18:41 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 100/1251] eta: 0:12:49 lr: 0.000081 loss: 2.9963 (2.7908) grad_norm: 2.7351 (2.8197) time: 0.6248 [2021-03-28 07:18:47 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 110/1251] eta: 0:12:39 lr: 0.000081 loss: 2.7702 (2.7872) grad_norm: 2.7679 (2.8264) time: 0.6303 [2021-03-28 07:18:53 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 120/1251] eta: 0:12:28 lr: 0.000081 loss: 2.7834 (2.7717) grad_norm: 2.7113 (2.8359) time: 0.6302 [2021-03-28 07:18:59 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 130/1251] eta: 0:12:18 lr: 0.000081 loss: 2.7232 (2.7526) grad_norm: 2.6967 (2.8383) time: 0.6249 [2021-03-28 07:19:06 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 140/1251] eta: 0:12:09 lr: 0.000081 loss: 2.8115 (2.7608) grad_norm: 2.8194 (2.8452) time: 0.6230 [2021-03-28 07:19:12 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 150/1251] eta: 0:12:00 lr: 0.000081 loss: 2.9087 (2.7673) grad_norm: 2.7650 (2.8472) time: 0.6234 [2021-03-28 07:19:18 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 160/1251] eta: 0:11:52 lr: 0.000081 loss: 2.9596 (2.7745) grad_norm: 2.8581 (2.9107) time: 0.6268 [2021-03-28 07:19:24 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 170/1251] eta: 0:11:44 lr: 0.000081 loss: 2.9792 (2.7829) grad_norm: 2.8135 (2.8990) time: 0.6313 [2021-03-28 07:19:31 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 180/1251] eta: 0:11:36 lr: 0.000081 loss: 2.9566 (2.7885) grad_norm: 2.7108 (2.9077) time: 0.6331 [2021-03-28 07:19:37 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 190/1251] eta: 0:11:29 lr: 0.000081 loss: 3.0224 (2.7978) grad_norm: 2.7427 (2.9081) time: 0.6327 [2021-03-28 07:19:44 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 200/1251] eta: 0:11:22 lr: 0.000081 loss: 3.0422 (2.8023) grad_norm: 2.6134 (2.8969) time: 0.6371 [2021-03-28 07:19:50 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 210/1251] eta: 0:11:15 lr: 0.000081 loss: 3.0358 (2.8068) grad_norm: 2.7727 (2.9086) time: 0.6378 [2021-03-28 07:19:56 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 220/1251] eta: 0:11:07 lr: 0.000081 loss: 2.9748 (2.8087) grad_norm: 2.8142 (2.9177) time: 0.6301 [2021-03-28 07:20:02 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 230/1251] eta: 0:11:00 lr: 0.000081 loss: 2.7870 (2.7998) grad_norm: 2.7110 (2.9113) time: 0.6285 [2021-03-28 07:20:09 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 240/1251] eta: 0:10:53 lr: 0.000081 loss: 2.6708 (2.7982) grad_norm: 2.7110 (2.9086) time: 0.6296 [2021-03-28 07:20:15 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 250/1251] eta: 0:10:45 lr: 0.000081 loss: 2.7285 (2.7996) grad_norm: 2.8052 (2.9142) time: 0.6272 [2021-03-28 07:20:21 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 260/1251] eta: 0:10:38 lr: 0.000081 loss: 2.8212 (2.7973) grad_norm: 2.8996 (2.9171) time: 0.6235 [2021-03-28 07:20:28 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 270/1251] eta: 0:10:31 lr: 0.000081 loss: 2.7418 (2.7919) grad_norm: 2.6809 (2.9165) time: 0.6242 [2021-03-28 07:20:34 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 280/1251] eta: 0:10:24 lr: 0.000081 loss: 2.7418 (2.7941) grad_norm: 2.4266 (2.9064) time: 0.6333 [2021-03-28 07:20:40 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 290/1251] eta: 0:10:17 lr: 0.000081 loss: 2.6976 (2.7902) grad_norm: 2.5674 (2.9029) time: 0.6318 [2021-03-28 07:20:47 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 300/1251] eta: 0:10:11 lr: 0.000081 loss: 2.6660 (2.7842) grad_norm: 2.5900 (2.8931) time: 0.6333 [2021-03-28 07:20:53 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 310/1251] eta: 0:10:04 lr: 0.000081 loss: 2.7941 (2.7833) grad_norm: 2.5900 (2.8971) time: 0.6369 [2021-03-28 07:20:59 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 320/1251] eta: 0:09:57 lr: 0.000081 loss: 2.8550 (2.7877) grad_norm: 2.7342 (2.8891) time: 0.6270 [2021-03-28 07:21:05 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 330/1251] eta: 0:09:50 lr: 0.000081 loss: 2.9130 (2.7829) grad_norm: 2.6875 (2.8872) time: 0.6243 [2021-03-28 07:21:12 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 340/1251] eta: 0:09:43 lr: 0.000081 loss: 2.9225 (2.7858) grad_norm: 2.7676 (2.8845) time: 0.6251 [2021-03-28 07:21:18 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 350/1251] eta: 0:09:37 lr: 0.000081 loss: 2.9136 (2.7834) grad_norm: 2.8485 (2.8914) time: 0.6257 [2021-03-28 07:21:24 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 360/1251] eta: 0:09:30 lr: 0.000081 loss: 2.6852 (2.7776) grad_norm: 2.8391 (2.8940) time: 0.6241 [2021-03-28 07:21:30 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 370/1251] eta: 0:09:23 lr: 0.000081 loss: 2.8117 (2.7772) grad_norm: 2.7877 (2.8963) time: 0.6258 [2021-03-28 07:21:37 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 380/1251] eta: 0:09:16 lr: 0.000081 loss: 2.9474 (2.7836) grad_norm: 2.7152 (2.8950) time: 0.6282 [2021-03-28 07:21:43 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 390/1251] eta: 0:09:10 lr: 0.000081 loss: 2.9885 (2.7889) grad_norm: 2.6629 (2.8925) time: 0.6294 [2021-03-28 07:21:49 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 400/1251] eta: 0:09:03 lr: 0.000081 loss: 2.8612 (2.7885) grad_norm: 2.6629 (2.8875) time: 0.6309 [2021-03-28 07:21:56 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 410/1251] eta: 0:08:57 lr: 0.000081 loss: 2.6600 (2.7877) grad_norm: 2.6810 (2.8848) time: 0.6277 [2021-03-28 07:22:02 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 420/1251] eta: 0:08:50 lr: 0.000081 loss: 2.7234 (2.7905) grad_norm: 2.6922 (2.8878) time: 0.6269 [2021-03-28 07:22:08 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 430/1251] eta: 0:08:43 lr: 0.000081 loss: 3.0033 (2.7956) grad_norm: 2.6404 (2.8904) time: 0.6287 [2021-03-28 07:22:15 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 440/1251] eta: 0:08:37 lr: 0.000081 loss: 2.9401 (2.7948) grad_norm: 2.6042 (2.9012) time: 0.6329 [2021-03-28 07:22:21 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 450/1251] eta: 0:08:31 lr: 0.000081 loss: 2.7654 (2.7928) grad_norm: 3.0352 (2.9068) time: 0.6367 [2021-03-28 07:22:27 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 460/1251] eta: 0:08:24 lr: 0.000081 loss: 2.6593 (2.7891) grad_norm: 2.8993 (2.9053) time: 0.6312 [2021-03-28 07:22:33 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 470/1251] eta: 0:08:17 lr: 0.000081 loss: 2.7833 (2.7896) grad_norm: 2.7790 (2.9092) time: 0.6244 [2021-03-28 07:22:40 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 480/1251] eta: 0:08:11 lr: 0.000081 loss: 2.8245 (2.7899) grad_norm: 2.7795 (2.9073) time: 0.6257 [2021-03-28 07:22:46 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 490/1251] eta: 0:08:04 lr: 0.000081 loss: 2.9545 (2.7953) grad_norm: 2.7615 (2.9034) time: 0.6275 [2021-03-28 07:22:52 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 500/1251] eta: 0:07:58 lr: 0.000081 loss: 3.0735 (2.7992) grad_norm: 2.7473 (2.9016) time: 0.6243 [2021-03-28 07:22:58 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 510/1251] eta: 0:07:51 lr: 0.000081 loss: 2.9985 (2.7991) grad_norm: 2.8078 (2.8994) time: 0.6258 [2021-03-28 07:23:05 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 520/1251] eta: 0:07:45 lr: 0.000080 loss: 2.9985 (2.8011) grad_norm: 2.6485 (2.8988) time: 0.6321 [2021-03-28 07:23:11 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 530/1251] eta: 0:07:38 lr: 0.000080 loss: 2.8988 (2.8011) grad_norm: 2.6382 (2.9000) time: 0.6299 [2021-03-28 07:23:17 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 540/1251] eta: 0:07:32 lr: 0.000080 loss: 2.8945 (2.8046) grad_norm: 2.6903 (2.8973) time: 0.6253 [2021-03-28 07:23:24 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 550/1251] eta: 0:07:26 lr: 0.000080 loss: 2.8948 (2.8048) grad_norm: 2.6695 (2.8959) time: 0.6344 [2021-03-28 07:23:30 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 560/1251] eta: 0:07:19 lr: 0.000080 loss: 2.7835 (2.8040) grad_norm: 2.6695 (2.8958) time: 0.6386 [2021-03-28 07:23:36 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 570/1251] eta: 0:07:13 lr: 0.000080 loss: 2.7976 (2.8060) grad_norm: 2.8269 (2.8961) time: 0.6334 [2021-03-28 07:23:43 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 580/1251] eta: 0:07:06 lr: 0.000080 loss: 2.9299 (2.8083) grad_norm: 2.6883 (2.8929) time: 0.6330 [2021-03-28 07:23:49 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 590/1251] eta: 0:07:00 lr: 0.000080 loss: 2.9125 (2.8093) grad_norm: 2.7274 (2.8999) time: 0.6327 [2021-03-28 07:23:55 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 600/1251] eta: 0:06:54 lr: 0.000080 loss: 2.8983 (2.8083) grad_norm: 2.7723 (2.9002) time: 0.6320 [2021-03-28 07:24:02 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 610/1251] eta: 0:06:47 lr: 0.000080 loss: 2.8535 (2.8055) grad_norm: 2.7723 (2.8988) time: 0.6276 [2021-03-28 07:24:08 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 620/1251] eta: 0:06:41 lr: 0.000080 loss: 2.9782 (2.8074) grad_norm: 2.6235 (2.8928) time: 0.6308 [2021-03-28 07:24:14 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 630/1251] eta: 0:06:34 lr: 0.000080 loss: 2.9081 (2.8043) grad_norm: 2.5966 (2.8934) time: 0.6381 [2021-03-28 07:24:21 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 640/1251] eta: 0:06:28 lr: 0.000080 loss: 2.6198 (2.8056) grad_norm: 2.8070 (2.8924) time: 0.6351 [2021-03-28 07:24:27 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 650/1251] eta: 0:06:22 lr: 0.000080 loss: 3.0184 (2.8075) grad_norm: 2.9171 (2.8986) time: 0.6288 [2021-03-28 07:24:33 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 660/1251] eta: 0:06:15 lr: 0.000080 loss: 2.8148 (2.8054) grad_norm: 2.8664 (2.8971) time: 0.6274 [2021-03-28 07:24:39 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 670/1251] eta: 0:06:09 lr: 0.000080 loss: 2.6421 (2.8012) grad_norm: 2.7293 (2.8980) time: 0.6243 [2021-03-28 07:24:46 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 680/1251] eta: 0:06:02 lr: 0.000080 loss: 2.7921 (2.8023) grad_norm: 2.7642 (2.9022) time: 0.6251 [2021-03-28 07:24:52 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 690/1251] eta: 0:05:56 lr: 0.000080 loss: 2.8688 (2.8029) grad_norm: 2.7699 (2.9011) time: 0.6286 [2021-03-28 07:24:58 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 700/1251] eta: 0:05:49 lr: 0.000080 loss: 2.8530 (2.8036) grad_norm: 2.6479 (2.9012) time: 0.6264 [2021-03-28 07:25:05 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 710/1251] eta: 0:05:43 lr: 0.000080 loss: 2.9711 (2.8025) grad_norm: 2.9254 (2.9012) time: 0.6289 [2021-03-28 07:25:11 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 720/1251] eta: 0:05:37 lr: 0.000080 loss: 2.7556 (2.8001) grad_norm: 2.7904 (2.8968) time: 0.6346 [2021-03-28 07:25:17 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 730/1251] eta: 0:05:30 lr: 0.000080 loss: 2.5690 (2.7952) grad_norm: 2.7904 (2.8991) time: 0.6422 [2021-03-28 07:25:24 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 740/1251] eta: 0:05:24 lr: 0.000080 loss: 2.6237 (2.7909) grad_norm: 2.9473 (2.9065) time: 0.6439 [2021-03-28 07:25:30 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 750/1251] eta: 0:05:18 lr: 0.000080 loss: 2.6565 (2.7909) grad_norm: 2.6762 (2.9051) time: 0.6392 [2021-03-28 07:25:37 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 760/1251] eta: 0:05:11 lr: 0.000080 loss: 2.8907 (2.7913) grad_norm: 2.6677 (2.9040) time: 0.6358 [2021-03-28 07:25:43 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 770/1251] eta: 0:05:05 lr: 0.000080 loss: 2.8907 (2.7905) grad_norm: 2.7407 (2.9011) time: 0.6445 [2021-03-28 07:25:49 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 780/1251] eta: 0:04:59 lr: 0.000080 loss: 2.7719 (2.7893) grad_norm: 2.5039 (2.8982) time: 0.6453 [2021-03-28 07:25:56 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 790/1251] eta: 0:04:52 lr: 0.000080 loss: 2.7719 (2.7899) grad_norm: 2.7208 (2.8989) time: 0.6329 [2021-03-28 07:26:02 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 800/1251] eta: 0:04:46 lr: 0.000080 loss: 2.8574 (2.7885) grad_norm: 2.7648 (2.9010) time: 0.6303 [2021-03-28 07:26:08 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 810/1251] eta: 0:04:40 lr: 0.000080 loss: 2.8574 (2.7882) grad_norm: 2.7926 (2.9024) time: 0.6285 [2021-03-28 07:26:15 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 820/1251] eta: 0:04:33 lr: 0.000080 loss: 2.7263 (2.7877) grad_norm: 2.8449 (2.9015) time: 0.6229 [2021-03-28 07:26:21 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 830/1251] eta: 0:04:27 lr: 0.000080 loss: 2.7263 (2.7870) grad_norm: 2.7536 (2.8994) time: 0.6240 [2021-03-28 07:26:27 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 840/1251] eta: 0:04:20 lr: 0.000080 loss: 2.6269 (2.7858) grad_norm: 2.6273 (2.9002) time: 0.6283 [2021-03-28 07:26:33 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 850/1251] eta: 0:04:14 lr: 0.000080 loss: 2.9123 (2.7897) grad_norm: 2.7283 (2.9000) time: 0.6290 [2021-03-28 07:26:40 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 860/1251] eta: 0:04:08 lr: 0.000080 loss: 3.0259 (2.7893) grad_norm: 2.7283 (2.8992) time: 0.6302 [2021-03-28 07:26:46 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 870/1251] eta: 0:04:01 lr: 0.000080 loss: 2.6643 (2.7885) grad_norm: 2.6944 (2.8983) time: 0.6295 [2021-03-28 07:26:52 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 880/1251] eta: 0:03:55 lr: 0.000080 loss: 2.6393 (2.7884) grad_norm: 2.6944 (2.8962) time: 0.6315 [2021-03-28 07:26:59 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 890/1251] eta: 0:03:49 lr: 0.000080 loss: 2.6247 (2.7855) grad_norm: 2.6784 (2.8971) time: 0.6320 [2021-03-28 07:27:05 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 900/1251] eta: 0:03:42 lr: 0.000080 loss: 2.5135 (2.7863) grad_norm: 2.5834 (2.8951) time: 0.6273 [2021-03-28 07:27:11 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 910/1251] eta: 0:03:36 lr: 0.000080 loss: 2.8681 (2.7860) grad_norm: 2.5834 (2.8908) time: 0.6294 [2021-03-28 07:27:18 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 920/1251] eta: 0:03:30 lr: 0.000080 loss: 2.8757 (2.7867) grad_norm: 2.4236 (2.8914) time: 0.6318 [2021-03-28 07:27:24 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 930/1251] eta: 0:03:23 lr: 0.000080 loss: 2.9094 (2.7854) grad_norm: 2.8338 (2.8916) time: 0.6301 [2021-03-28 07:27:30 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 940/1251] eta: 0:03:17 lr: 0.000080 loss: 2.6794 (2.7851) grad_norm: 2.8157 (2.8913) time: 0.6330 [2021-03-28 07:27:37 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 950/1251] eta: 0:03:10 lr: 0.000080 loss: 2.7573 (2.7849) grad_norm: 2.7406 (2.8906) time: 0.6342 [2021-03-28 07:27:43 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 960/1251] eta: 0:03:04 lr: 0.000080 loss: 2.9574 (2.7864) grad_norm: 2.5618 (2.8891) time: 0.6426 [2021-03-28 07:27:49 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 970/1251] eta: 0:02:58 lr: 0.000080 loss: 2.9512 (2.7837) grad_norm: 2.5900 (2.8873) time: 0.6368 [2021-03-28 07:27:56 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 980/1251] eta: 0:02:51 lr: 0.000080 loss: 2.9412 (2.7860) grad_norm: 2.6244 (2.8847) time: 0.6239 [2021-03-28 07:28:02 swin_base_patch4_window7_224] INFO: Epoch: [248] [ 990/1251] eta: 0:02:45 lr: 0.000079 loss: 2.9579 (2.7867) grad_norm: 2.5862 (2.8819) time: 0.6312 [2021-03-28 07:28:08 swin_base_patch4_window7_224] INFO: Epoch: [248] [1000/1251] eta: 0:02:39 lr: 0.000079 loss: 2.9128 (2.7891) grad_norm: 2.6704 (2.8843) time: 0.6332 [2021-03-28 07:28:15 swin_base_patch4_window7_224] INFO: Epoch: [248] [1010/1251] eta: 0:02:32 lr: 0.000079 loss: 3.1159 (2.7910) grad_norm: 2.6704 (2.8826) time: 0.6290 [2021-03-28 07:28:21 swin_base_patch4_window7_224] INFO: Epoch: [248] [1020/1251] eta: 0:02:26 lr: 0.000079 loss: 2.7905 (2.7902) grad_norm: 2.6450 (2.8812) time: 0.6320 [2021-03-28 07:28:27 swin_base_patch4_window7_224] INFO: Epoch: [248] [1030/1251] eta: 0:02:20 lr: 0.000079 loss: 2.7356 (2.7899) grad_norm: 2.7257 (2.8796) time: 0.6317 [2021-03-28 07:28:33 swin_base_patch4_window7_224] INFO: Epoch: [248] [1040/1251] eta: 0:02:13 lr: 0.000079 loss: 2.8911 (2.7908) grad_norm: 2.8106 (2.8802) time: 0.6291 [2021-03-28 07:28:40 swin_base_patch4_window7_224] INFO: Epoch: [248] [1050/1251] eta: 0:02:07 lr: 0.000079 loss: 2.9629 (2.7928) grad_norm: 2.8106 (2.8793) time: 0.6299 [2021-03-28 07:28:46 swin_base_patch4_window7_224] INFO: Epoch: [248] [1060/1251] eta: 0:02:01 lr: 0.000079 loss: 3.0219 (2.7937) grad_norm: 2.5752 (2.8851) time: 0.6319 [2021-03-28 07:28:52 swin_base_patch4_window7_224] INFO: Epoch: [248] [1070/1251] eta: 0:01:54 lr: 0.000079 loss: 2.8161 (2.7939) grad_norm: 2.5752 (2.8838) time: 0.6325 [2021-03-28 07:28:59 swin_base_patch4_window7_224] INFO: Epoch: [248] [1080/1251] eta: 0:01:48 lr: 0.000079 loss: 2.9779 (2.7964) grad_norm: 2.5863 (2.8962) time: 0.6256 [2021-03-28 07:29:05 swin_base_patch4_window7_224] INFO: Epoch: [248] [1090/1251] eta: 0:01:42 lr: 0.000079 loss: 3.0856 (2.7992) grad_norm: 2.7305 (2.8940) time: 0.6274 [2021-03-28 07:29:11 swin_base_patch4_window7_224] INFO: Epoch: [248] [1100/1251] eta: 0:01:35 lr: 0.000079 loss: 3.1464 (2.8023) grad_norm: 2.6911 (2.8931) time: 0.6348 [2021-03-28 07:29:18 swin_base_patch4_window7_224] INFO: Epoch: [248] [1110/1251] eta: 0:01:29 lr: 0.000079 loss: 3.0767 (2.8015) grad_norm: 2.8198 (2.8934) time: 0.6297 [2021-03-28 07:29:24 swin_base_patch4_window7_224] INFO: Epoch: [248] [1120/1251] eta: 0:01:23 lr: 0.000079 loss: 2.9685 (2.8031) grad_norm: 2.7323 (2.8910) time: 0.6262 [2021-03-28 07:29:30 swin_base_patch4_window7_224] INFO: Epoch: [248] [1130/1251] eta: 0:01:16 lr: 0.000079 loss: 2.9672 (2.8031) grad_norm: 2.6053 (2.8905) time: 0.6308 [2021-03-28 07:29:37 swin_base_patch4_window7_224] INFO: Epoch: [248] [1140/1251] eta: 0:01:10 lr: 0.000079 loss: 2.6208 (2.8025) grad_norm: 2.5440 (2.8888) time: 0.6341 [2021-03-28 07:29:43 swin_base_patch4_window7_224] INFO: Epoch: [248] [1150/1251] eta: 0:01:04 lr: 0.000079 loss: 2.9074 (2.8029) grad_norm: 2.7632 (2.8883) time: 0.6292 [2021-03-28 07:29:49 swin_base_patch4_window7_224] INFO: Epoch: [248] [1160/1251] eta: 0:00:57 lr: 0.000079 loss: 2.7279 (2.8000) grad_norm: 2.7744 (2.8886) time: 0.6247 [2021-03-28 07:29:55 swin_base_patch4_window7_224] INFO: Epoch: [248] [1170/1251] eta: 0:00:51 lr: 0.000079 loss: 2.6254 (2.7992) grad_norm: 2.7220 (2.8881) time: 0.6260 [2021-03-28 07:30:02 swin_base_patch4_window7_224] INFO: Epoch: [248] [1180/1251] eta: 0:00:44 lr: 0.000079 loss: 2.6669 (2.7986) grad_norm: 2.6301 (2.8869) time: 0.6271 [2021-03-28 07:30:08 swin_base_patch4_window7_224] INFO: Epoch: [248] [1190/1251] eta: 0:00:38 lr: 0.000079 loss: 2.7018 (2.7965) grad_norm: 2.6876 (2.8856) time: 0.6310 [2021-03-28 07:30:14 swin_base_patch4_window7_224] INFO: Epoch: [248] [1200/1251] eta: 0:00:32 lr: 0.000079 loss: 2.7057 (2.7959) grad_norm: 2.7257 (2.8860) time: 0.6301 [2021-03-28 07:30:20 swin_base_patch4_window7_224] INFO: Epoch: [248] [1210/1251] eta: 0:00:25 lr: 0.000079 loss: 2.8122 (2.7968) grad_norm: 2.6787 (2.8855) time: 0.6275 [2021-03-28 07:30:27 swin_base_patch4_window7_224] INFO: Epoch: [248] [1220/1251] eta: 0:00:19 lr: 0.000079 loss: 2.8768 (2.7969) grad_norm: 2.5896 (2.8837) time: 0.6281 [2021-03-28 07:30:33 swin_base_patch4_window7_224] INFO: Epoch: [248] [1230/1251] eta: 0:00:13 lr: 0.000079 loss: 2.9388 (2.7985) grad_norm: 2.6396 (2.8828) time: 0.6277 [2021-03-28 07:30:39 swin_base_patch4_window7_224] INFO: Epoch: [248] [1240/1251] eta: 0:00:06 lr: 0.000079 loss: 2.9362 (2.7994) grad_norm: 2.6679 (2.8822) time: 0.6274 [2021-03-28 07:30:46 swin_base_patch4_window7_224] INFO: Epoch: [248] [1250/1251] eta: 0:00:00 lr: 0.000079 loss: 2.7513 (2.7985) grad_norm: 2.6052 (2.8806) time: 0.6305 [2021-03-28 07:30:57 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:23 loss: 1.0842 (1.0842) acc1: 71.8750 (71.8750) acc5: 92.1875 (92.1875) [2021-03-28 07:31:00 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8734 (0.8368) acc1: 81.2500 (80.6818) acc5: 95.3125 (95.7386) [2021-03-28 07:31:02 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8110 (0.8089) acc1: 81.2500 (80.8036) acc5: 96.8750 (95.9821) [2021-03-28 07:31:04 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7412 (0.7961) acc1: 81.2500 (81.0988) acc5: 96.8750 (96.1694) [2021-03-28 07:31:06 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7518 (0.7848) acc1: 82.8125 (81.5168) acc5: 96.8750 (96.2271) [2021-03-28 07:31:08 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7181 (0.7664) acc1: 82.8125 (81.7920) acc5: 96.8750 (96.3840) [2021-03-28 07:31:23 swin_base_patch4_window7_224] INFO: * Acc@1 82.770 Acc@5 96.256 loss 0.758 [2021-03-28 07:31:23 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.8% [2021-03-28 07:31:23 swin_base_patch4_window7_224] INFO: Max accuracy: 82.78% [2021-03-28 07:31:28 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 0/1251] eta: 1:26:30 lr: 0.000079 loss: 2.4401 (2.4401) grad_norm: 2.6422 (2.6422) time: 4.1490 [2021-03-28 07:31:34 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 10/1251] eta: 0:20:08 lr: 0.000079 loss: 2.7274 (2.7039) grad_norm: 2.5623 (2.6113) time: 0.9740 [2021-03-28 07:31:40 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 20/1251] eta: 0:16:35 lr: 0.000079 loss: 2.7353 (2.6584) grad_norm: 2.5915 (2.8468) time: 0.6420 [2021-03-28 07:31:47 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 30/1251] eta: 0:15:23 lr: 0.000079 loss: 2.7655 (2.6926) grad_norm: 2.7595 (2.9112) time: 0.6368 [2021-03-28 07:31:53 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 40/1251] eta: 0:14:39 lr: 0.000079 loss: 2.7509 (2.6888) grad_norm: 2.7595 (2.9526) time: 0.6402 [2021-03-28 07:32:00 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 50/1251] eta: 0:14:08 lr: 0.000079 loss: 2.4992 (2.6595) grad_norm: 2.5985 (3.0010) time: 0.6301 [2021-03-28 07:32:06 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 60/1251] eta: 0:13:48 lr: 0.000079 loss: 2.7783 (2.6731) grad_norm: 2.5745 (2.9723) time: 0.6314 [2021-03-28 07:32:12 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 70/1251] eta: 0:13:29 lr: 0.000079 loss: 2.7783 (2.6574) grad_norm: 2.5245 (2.9277) time: 0.6305 [2021-03-28 07:32:18 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 80/1251] eta: 0:13:15 lr: 0.000079 loss: 2.5522 (2.6614) grad_norm: 2.6781 (2.9202) time: 0.6287 [2021-03-28 07:32:25 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 90/1251] eta: 0:13:01 lr: 0.000079 loss: 2.6899 (2.6737) grad_norm: 2.8917 (2.9105) time: 0.6280 [2021-03-28 07:32:31 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 100/1251] eta: 0:12:48 lr: 0.000079 loss: 2.8336 (2.6762) grad_norm: 2.7741 (2.8912) time: 0.6228 [2021-03-28 07:32:37 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 110/1251] eta: 0:12:39 lr: 0.000079 loss: 2.5363 (2.6644) grad_norm: 2.8465 (2.8974) time: 0.6313 [2021-03-28 07:32:44 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 120/1251] eta: 0:12:28 lr: 0.000079 loss: 2.6761 (2.6616) grad_norm: 2.7114 (2.8794) time: 0.6323 [2021-03-28 07:32:50 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 130/1251] eta: 0:12:19 lr: 0.000079 loss: 2.6761 (2.6543) grad_norm: 2.5510 (2.8612) time: 0.6263 [2021-03-28 07:32:56 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 140/1251] eta: 0:12:10 lr: 0.000079 loss: 2.7470 (2.6637) grad_norm: 2.5510 (2.8643) time: 0.6296 [2021-03-28 07:33:03 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 150/1251] eta: 0:12:02 lr: 0.000079 loss: 2.7470 (2.6604) grad_norm: 2.7101 (2.8783) time: 0.6359 [2021-03-28 07:33:09 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 160/1251] eta: 0:11:54 lr: 0.000079 loss: 2.8512 (2.6695) grad_norm: 2.7101 (2.8769) time: 0.6367 [2021-03-28 07:33:15 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 170/1251] eta: 0:11:46 lr: 0.000079 loss: 2.8183 (2.6656) grad_norm: 2.6732 (2.8716) time: 0.6336 [2021-03-28 07:33:22 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 180/1251] eta: 0:11:38 lr: 0.000079 loss: 2.8183 (2.6765) grad_norm: 2.6555 (2.8905) time: 0.6348 [2021-03-28 07:33:28 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 190/1251] eta: 0:11:31 lr: 0.000079 loss: 2.9826 (2.6911) grad_norm: 2.7478 (2.8935) time: 0.6320 [2021-03-28 07:33:34 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 200/1251] eta: 0:11:23 lr: 0.000079 loss: 2.9826 (2.7008) grad_norm: 2.7259 (2.8798) time: 0.6287 [2021-03-28 07:33:40 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 210/1251] eta: 0:11:15 lr: 0.000078 loss: 2.8681 (2.7014) grad_norm: 2.6650 (2.8853) time: 0.6286 [2021-03-28 07:33:47 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 220/1251] eta: 0:11:08 lr: 0.000078 loss: 2.9453 (2.7135) grad_norm: 2.6160 (2.8744) time: 0.6321 [2021-03-28 07:33:53 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 230/1251] eta: 0:11:01 lr: 0.000078 loss: 2.8310 (2.7142) grad_norm: 2.7475 (2.8806) time: 0.6367 [2021-03-28 07:33:59 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 240/1251] eta: 0:10:54 lr: 0.000078 loss: 2.9114 (2.7232) grad_norm: 2.7105 (2.8695) time: 0.6305 [2021-03-28 07:34:06 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 250/1251] eta: 0:10:46 lr: 0.000078 loss: 2.9521 (2.7225) grad_norm: 2.5502 (2.8644) time: 0.6244 [2021-03-28 07:34:12 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 260/1251] eta: 0:10:39 lr: 0.000078 loss: 2.6837 (2.7174) grad_norm: 2.5852 (2.8571) time: 0.6304 [2021-03-28 07:34:19 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 270/1251] eta: 0:10:33 lr: 0.000078 loss: 2.5062 (2.7126) grad_norm: 2.7250 (2.8627) time: 0.6402 [2021-03-28 07:34:25 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 280/1251] eta: 0:10:26 lr: 0.000078 loss: 3.0086 (2.7191) grad_norm: 2.8510 (2.8701) time: 0.6420 [2021-03-28 07:34:31 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 290/1251] eta: 0:10:19 lr: 0.000078 loss: 2.8949 (2.7260) grad_norm: 2.8825 (2.8852) time: 0.6352 [2021-03-28 07:34:37 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 300/1251] eta: 0:10:12 lr: 0.000078 loss: 2.7231 (2.7206) grad_norm: 2.7409 (2.8863) time: 0.6280 [2021-03-28 07:34:44 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 310/1251] eta: 0:10:06 lr: 0.000078 loss: 2.6291 (2.7196) grad_norm: 2.8007 (2.8938) time: 0.6332 [2021-03-28 07:34:50 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 320/1251] eta: 0:09:59 lr: 0.000078 loss: 2.8819 (2.7216) grad_norm: 2.7282 (2.8888) time: 0.6383 [2021-03-28 07:34:57 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 330/1251] eta: 0:09:52 lr: 0.000078 loss: 2.9462 (2.7263) grad_norm: 2.5722 (2.8800) time: 0.6318 [2021-03-28 07:35:03 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 340/1251] eta: 0:09:46 lr: 0.000078 loss: 2.9204 (2.7270) grad_norm: 2.5953 (2.9006) time: 0.6339 [2021-03-28 07:35:09 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 350/1251] eta: 0:09:39 lr: 0.000078 loss: 2.7864 (2.7290) grad_norm: 2.7796 (2.8976) time: 0.6343 [2021-03-28 07:35:16 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 360/1251] eta: 0:09:32 lr: 0.000078 loss: 2.7918 (2.7276) grad_norm: 2.5494 (2.8867) time: 0.6344 [2021-03-28 07:35:22 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 370/1251] eta: 0:09:26 lr: 0.000078 loss: 2.6409 (2.7227) grad_norm: 2.5494 (2.8827) time: 0.6331 [2021-03-28 07:35:28 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 380/1251] eta: 0:09:19 lr: 0.000078 loss: 2.6926 (2.7230) grad_norm: 2.6659 (2.8800) time: 0.6236 [2021-03-28 07:35:34 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 390/1251] eta: 0:09:12 lr: 0.000078 loss: 2.8382 (2.7209) grad_norm: 2.8162 (2.8791) time: 0.6256 [2021-03-28 07:35:41 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 400/1251] eta: 0:09:05 lr: 0.000078 loss: 2.7524 (2.7225) grad_norm: 2.8162 (2.8749) time: 0.6312 [2021-03-28 07:35:47 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 410/1251] eta: 0:08:59 lr: 0.000078 loss: 2.9084 (2.7223) grad_norm: 2.7243 (2.8832) time: 0.6349 [2021-03-28 07:35:53 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 420/1251] eta: 0:08:52 lr: 0.000078 loss: 2.8680 (2.7213) grad_norm: 3.0811 (2.8888) time: 0.6348 [2021-03-28 07:36:00 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 430/1251] eta: 0:08:46 lr: 0.000078 loss: 2.7462 (2.7235) grad_norm: 2.8128 (2.8873) time: 0.6348 [2021-03-28 07:36:06 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 440/1251] eta: 0:08:39 lr: 0.000078 loss: 2.7001 (2.7173) grad_norm: 2.6497 (2.8827) time: 0.6302 [2021-03-28 07:36:12 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 450/1251] eta: 0:08:32 lr: 0.000078 loss: 2.7786 (2.7231) grad_norm: 2.6834 (2.8860) time: 0.6264 [2021-03-28 07:36:19 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 460/1251] eta: 0:08:26 lr: 0.000078 loss: 2.9580 (2.7263) grad_norm: 2.8825 (2.8867) time: 0.6283 [2021-03-28 07:36:25 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 470/1251] eta: 0:08:19 lr: 0.000078 loss: 3.0937 (2.7322) grad_norm: 2.7089 (2.8896) time: 0.6330 [2021-03-28 07:36:31 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 480/1251] eta: 0:08:13 lr: 0.000078 loss: 2.9999 (2.7355) grad_norm: 2.7089 (2.8893) time: 0.6361 [2021-03-28 07:36:38 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 490/1251] eta: 0:08:06 lr: 0.000078 loss: 2.9065 (2.7334) grad_norm: 2.7683 (2.8963) time: 0.6305 [2021-03-28 07:36:44 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 500/1251] eta: 0:08:00 lr: 0.000078 loss: 2.8910 (2.7314) grad_norm: 2.7977 (2.8954) time: 0.6314 [2021-03-28 07:36:50 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 510/1251] eta: 0:07:53 lr: 0.000078 loss: 2.8910 (2.7330) grad_norm: 2.8688 (2.9002) time: 0.6301 [2021-03-28 07:36:57 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 520/1251] eta: 0:07:47 lr: 0.000078 loss: 2.9579 (2.7395) grad_norm: 2.6750 (2.8945) time: 0.6307 [2021-03-28 07:37:03 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 530/1251] eta: 0:07:40 lr: 0.000078 loss: 2.9419 (2.7410) grad_norm: 2.6168 (2.8892) time: 0.6322 [2021-03-28 07:37:09 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 540/1251] eta: 0:07:34 lr: 0.000078 loss: 2.9155 (2.7439) grad_norm: 2.6410 (2.8893) time: 0.6300 [2021-03-28 07:37:16 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 550/1251] eta: 0:07:28 lr: 0.000078 loss: 2.7956 (2.7440) grad_norm: 2.6812 (2.8956) time: 0.6441 [2021-03-28 07:37:22 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 560/1251] eta: 0:07:21 lr: 0.000078 loss: 2.7629 (2.7448) grad_norm: 2.6364 (2.8981) time: 0.6458 [2021-03-28 07:37:28 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 570/1251] eta: 0:07:15 lr: 0.000078 loss: 2.6775 (2.7419) grad_norm: 2.6364 (2.8956) time: 0.6367 [2021-03-28 07:37:35 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 580/1251] eta: 0:07:08 lr: 0.000078 loss: 2.8368 (2.7453) grad_norm: 2.6761 (2.8965) time: 0.6299 [2021-03-28 07:37:41 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 590/1251] eta: 0:07:02 lr: 0.000078 loss: 2.9626 (2.7488) grad_norm: 2.7972 (2.9045) time: 0.6247 [2021-03-28 07:37:47 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 600/1251] eta: 0:06:55 lr: 0.000078 loss: 2.9894 (2.7520) grad_norm: 2.7831 (2.9014) time: 0.6316 [2021-03-28 07:37:54 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 610/1251] eta: 0:06:49 lr: 0.000078 loss: 2.9909 (2.7520) grad_norm: 2.7939 (2.9048) time: 0.6318 [2021-03-28 07:38:00 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 620/1251] eta: 0:06:42 lr: 0.000078 loss: 2.7910 (2.7530) grad_norm: 2.6898 (2.9011) time: 0.6306 [2021-03-28 07:38:06 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 630/1251] eta: 0:06:36 lr: 0.000078 loss: 2.7910 (2.7533) grad_norm: 2.6078 (2.8996) time: 0.6329 [2021-03-28 07:38:13 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 640/1251] eta: 0:06:29 lr: 0.000078 loss: 2.7578 (2.7505) grad_norm: 2.7409 (2.8984) time: 0.6300 [2021-03-28 07:38:19 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 650/1251] eta: 0:06:23 lr: 0.000078 loss: 2.6658 (2.7487) grad_norm: 2.7317 (2.8979) time: 0.6292 [2021-03-28 07:38:25 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 660/1251] eta: 0:06:16 lr: 0.000078 loss: 2.7956 (2.7511) grad_norm: 2.7978 (2.9078) time: 0.6281 [2021-03-28 07:38:31 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 670/1251] eta: 0:06:10 lr: 0.000078 loss: 2.7918 (2.7520) grad_norm: 2.8779 (2.9092) time: 0.6268 [2021-03-28 07:38:38 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 680/1251] eta: 0:06:04 lr: 0.000078 loss: 2.9524 (2.7533) grad_norm: 2.8109 (2.9115) time: 0.6297 [2021-03-28 07:38:44 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 690/1251] eta: 0:05:57 lr: 0.000077 loss: 2.9791 (2.7550) grad_norm: 2.8109 (2.9128) time: 0.6323 [2021-03-28 07:38:50 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 700/1251] eta: 0:05:51 lr: 0.000077 loss: 2.9891 (2.7577) grad_norm: 2.9014 (2.9138) time: 0.6327 [2021-03-28 07:38:57 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 710/1251] eta: 0:05:44 lr: 0.000077 loss: 2.9143 (2.7591) grad_norm: 2.9014 (2.9144) time: 0.6316 [2021-03-28 07:39:03 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 720/1251] eta: 0:05:38 lr: 0.000077 loss: 2.7705 (2.7579) grad_norm: 2.5923 (2.9125) time: 0.6294 [2021-03-28 07:39:09 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 730/1251] eta: 0:05:31 lr: 0.000077 loss: 2.8553 (2.7610) grad_norm: 2.7264 (2.9128) time: 0.6339 [2021-03-28 07:39:16 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 740/1251] eta: 0:05:25 lr: 0.000077 loss: 2.8553 (2.7611) grad_norm: 2.8934 (2.9152) time: 0.6463 [2021-03-28 07:39:22 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 750/1251] eta: 0:05:19 lr: 0.000077 loss: 2.7426 (2.7614) grad_norm: 2.7318 (2.9151) time: 0.6402 [2021-03-28 07:39:28 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 760/1251] eta: 0:05:12 lr: 0.000077 loss: 2.8990 (2.7628) grad_norm: 2.6701 (2.9114) time: 0.6289 [2021-03-28 07:39:35 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 770/1251] eta: 0:05:06 lr: 0.000077 loss: 2.9685 (2.7653) grad_norm: 2.7043 (2.9083) time: 0.6299 [2021-03-28 07:39:41 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 780/1251] eta: 0:05:00 lr: 0.000077 loss: 2.8637 (2.7638) grad_norm: 2.7043 (2.9070) time: 0.6329 [2021-03-28 07:39:47 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 790/1251] eta: 0:04:53 lr: 0.000077 loss: 2.7264 (2.7639) grad_norm: 2.7194 (2.9070) time: 0.6293 [2021-03-28 07:39:54 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 800/1251] eta: 0:04:47 lr: 0.000077 loss: 2.8162 (2.7625) grad_norm: 2.7800 (2.9043) time: 0.6280 [2021-03-28 07:40:00 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 810/1251] eta: 0:04:40 lr: 0.000077 loss: 2.8810 (2.7632) grad_norm: 2.6906 (2.9010) time: 0.6320 [2021-03-28 07:40:06 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 820/1251] eta: 0:04:34 lr: 0.000077 loss: 2.8927 (2.7655) grad_norm: 2.6397 (2.8984) time: 0.6304 [2021-03-28 07:40:13 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 830/1251] eta: 0:04:27 lr: 0.000077 loss: 2.6530 (2.7628) grad_norm: 2.7791 (2.8994) time: 0.6296 [2021-03-28 07:40:19 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 840/1251] eta: 0:04:21 lr: 0.000077 loss: 2.6425 (2.7634) grad_norm: 2.7084 (2.8991) time: 0.6352 [2021-03-28 07:40:25 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 850/1251] eta: 0:04:15 lr: 0.000077 loss: 2.8268 (2.7632) grad_norm: 2.6763 (2.8970) time: 0.6353 [2021-03-28 07:40:32 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 860/1251] eta: 0:04:08 lr: 0.000077 loss: 2.8268 (2.7624) grad_norm: 2.7710 (2.8996) time: 0.6307 [2021-03-28 07:40:38 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 870/1251] eta: 0:04:02 lr: 0.000077 loss: 2.8231 (2.7630) grad_norm: 2.7907 (2.8976) time: 0.6286 [2021-03-28 07:40:44 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 880/1251] eta: 0:03:56 lr: 0.000077 loss: 2.8231 (2.7649) grad_norm: 2.5931 (2.8978) time: 0.6293 [2021-03-28 07:40:51 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 890/1251] eta: 0:03:49 lr: 0.000077 loss: 2.9168 (2.7647) grad_norm: 2.5954 (2.9005) time: 0.6435 [2021-03-28 07:40:57 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 900/1251] eta: 0:03:43 lr: 0.000077 loss: 2.9168 (2.7660) grad_norm: 2.9915 (2.9037) time: 0.6436 [2021-03-28 07:41:03 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 910/1251] eta: 0:03:37 lr: 0.000077 loss: 2.7710 (2.7652) grad_norm: 3.0133 (2.9035) time: 0.6339 [2021-03-28 07:41:10 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 920/1251] eta: 0:03:30 lr: 0.000077 loss: 2.8410 (2.7675) grad_norm: 2.9504 (2.9055) time: 0.6299 [2021-03-28 07:41:16 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 930/1251] eta: 0:03:24 lr: 0.000077 loss: 3.0519 (2.7717) grad_norm: 2.9545 (2.9065) time: 0.6315 [2021-03-28 07:41:22 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 940/1251] eta: 0:03:17 lr: 0.000077 loss: 3.0314 (2.7714) grad_norm: 2.9345 (2.9059) time: 0.6343 [2021-03-28 07:41:29 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 950/1251] eta: 0:03:11 lr: 0.000077 loss: 2.7794 (2.7714) grad_norm: 2.9112 (inf) time: 0.6247 [2021-03-28 07:41:35 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 960/1251] eta: 0:03:05 lr: 0.000077 loss: 2.8356 (2.7723) grad_norm: 2.9112 (inf) time: 0.6248 [2021-03-28 07:41:41 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 970/1251] eta: 0:02:58 lr: 0.000077 loss: 2.7728 (2.7693) grad_norm: 2.6048 (inf) time: 0.6295 [2021-03-28 07:41:47 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 980/1251] eta: 0:02:52 lr: 0.000077 loss: 2.1458 (2.7649) grad_norm: 2.6048 (inf) time: 0.6260 [2021-03-28 07:41:54 swin_base_patch4_window7_224] INFO: Epoch: [249] [ 990/1251] eta: 0:02:45 lr: 0.000077 loss: 2.5245 (2.7649) grad_norm: 2.7419 (inf) time: 0.6246 [2021-03-28 07:42:00 swin_base_patch4_window7_224] INFO: Epoch: [249] [1000/1251] eta: 0:02:39 lr: 0.000077 loss: 2.7390 (2.7624) grad_norm: 2.7419 (inf) time: 0.6258 [2021-03-28 07:42:06 swin_base_patch4_window7_224] INFO: Epoch: [249] [1010/1251] eta: 0:02:33 lr: 0.000077 loss: 2.6942 (2.7629) grad_norm: 2.8717 (inf) time: 0.6267 [2021-03-28 07:42:12 swin_base_patch4_window7_224] INFO: Epoch: [249] [1020/1251] eta: 0:02:26 lr: 0.000077 loss: 2.8286 (2.7652) grad_norm: 2.8772 (inf) time: 0.6232 [2021-03-28 07:42:19 swin_base_patch4_window7_224] INFO: Epoch: [249] [1030/1251] eta: 0:02:20 lr: 0.000077 loss: 2.8286 (2.7653) grad_norm: 2.7163 (inf) time: 0.6208 [2021-03-28 07:42:25 swin_base_patch4_window7_224] INFO: Epoch: [249] [1040/1251] eta: 0:02:14 lr: 0.000077 loss: 2.7973 (2.7649) grad_norm: 2.9629 (inf) time: 0.6275 [2021-03-28 07:42:31 swin_base_patch4_window7_224] INFO: Epoch: [249] [1050/1251] eta: 0:02:07 lr: 0.000077 loss: 2.8872 (2.7644) grad_norm: 3.0371 (inf) time: 0.6309 [2021-03-28 07:42:37 swin_base_patch4_window7_224] INFO: Epoch: [249] [1060/1251] eta: 0:02:01 lr: 0.000077 loss: 2.8027 (2.7645) grad_norm: 2.8021 (inf) time: 0.6249 [2021-03-28 07:42:44 swin_base_patch4_window7_224] INFO: Epoch: [249] [1070/1251] eta: 0:01:54 lr: 0.000077 loss: 2.7674 (2.7642) grad_norm: 2.6359 (inf) time: 0.6245 [2021-03-28 07:42:50 swin_base_patch4_window7_224] INFO: Epoch: [249] [1080/1251] eta: 0:01:48 lr: 0.000077 loss: 2.8592 (2.7663) grad_norm: 2.7288 (inf) time: 0.6277 [2021-03-28 07:42:56 swin_base_patch4_window7_224] INFO: Epoch: [249] [1090/1251] eta: 0:01:42 lr: 0.000077 loss: 2.8592 (2.7650) grad_norm: 2.7450 (inf) time: 0.6283 [2021-03-28 07:43:03 swin_base_patch4_window7_224] INFO: Epoch: [249] [1100/1251] eta: 0:01:35 lr: 0.000077 loss: 2.7064 (2.7653) grad_norm: 2.9508 (inf) time: 0.6358 [2021-03-28 07:43:09 swin_base_patch4_window7_224] INFO: Epoch: [249] [1110/1251] eta: 0:01:29 lr: 0.000077 loss: 2.9305 (2.7658) grad_norm: 2.6477 (inf) time: 0.6382 [2021-03-28 07:43:15 swin_base_patch4_window7_224] INFO: Epoch: [249] [1120/1251] eta: 0:01:23 lr: 0.000077 loss: 3.0458 (2.7659) grad_norm: 2.5306 (inf) time: 0.6316 [2021-03-28 07:43:22 swin_base_patch4_window7_224] INFO: Epoch: [249] [1130/1251] eta: 0:01:16 lr: 0.000077 loss: 2.8845 (2.7648) grad_norm: 2.7027 (inf) time: 0.6271 [2021-03-28 07:43:28 swin_base_patch4_window7_224] INFO: Epoch: [249] [1140/1251] eta: 0:01:10 lr: 0.000077 loss: 2.9196 (2.7657) grad_norm: 3.0615 (inf) time: 0.6258 [2021-03-28 07:43:34 swin_base_patch4_window7_224] INFO: Epoch: [249] [1150/1251] eta: 0:01:04 lr: 0.000077 loss: 2.9176 (2.7640) grad_norm: 2.9815 (inf) time: 0.6272 [2021-03-28 07:43:40 swin_base_patch4_window7_224] INFO: Epoch: [249] [1160/1251] eta: 0:00:57 lr: 0.000077 loss: 2.7229 (2.7634) grad_norm: 2.8369 (inf) time: 0.6274 [2021-03-28 07:43:47 swin_base_patch4_window7_224] INFO: Epoch: [249] [1170/1251] eta: 0:00:51 lr: 0.000076 loss: 2.7965 (2.7649) grad_norm: 2.7218 (inf) time: 0.6295 [2021-03-28 07:43:53 swin_base_patch4_window7_224] INFO: Epoch: [249] [1180/1251] eta: 0:00:45 lr: 0.000076 loss: 2.7030 (2.7632) grad_norm: 2.6855 (inf) time: 0.6306 [2021-03-28 07:43:59 swin_base_patch4_window7_224] INFO: Epoch: [249] [1190/1251] eta: 0:00:38 lr: 0.000076 loss: 2.7030 (2.7644) grad_norm: 2.7511 (inf) time: 0.6286 [2021-03-28 07:44:06 swin_base_patch4_window7_224] INFO: Epoch: [249] [1200/1251] eta: 0:00:32 lr: 0.000076 loss: 2.8080 (2.7634) grad_norm: 2.6820 (inf) time: 0.6247 [2021-03-28 07:44:12 swin_base_patch4_window7_224] INFO: Epoch: [249] [1210/1251] eta: 0:00:26 lr: 0.000076 loss: 2.8080 (2.7639) grad_norm: 2.6820 (inf) time: 0.6259 [2021-03-28 07:44:18 swin_base_patch4_window7_224] INFO: Epoch: [249] [1220/1251] eta: 0:00:19 lr: 0.000076 loss: 2.9716 (2.7659) grad_norm: 2.8632 (inf) time: 0.6268 [2021-03-28 07:44:24 swin_base_patch4_window7_224] INFO: Epoch: [249] [1230/1251] eta: 0:00:13 lr: 0.000076 loss: 2.9585 (2.7654) grad_norm: 2.7890 (inf) time: 0.6230 [2021-03-28 07:44:31 swin_base_patch4_window7_224] INFO: Epoch: [249] [1240/1251] eta: 0:00:06 lr: 0.000076 loss: 2.5989 (2.7627) grad_norm: 2.7890 (inf) time: 0.6229 [2021-03-28 07:44:37 swin_base_patch4_window7_224] INFO: Epoch: [249] [1250/1251] eta: 0:00:00 lr: 0.000076 loss: 2.5989 (2.7630) grad_norm: 2.7672 (inf) time: 0.6241 [2021-03-28 07:44:51 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:18 loss: 0.5862 (0.5862) acc1: 85.9375 (85.9375) acc5: 98.4375 (98.4375) [2021-03-28 07:44:53 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7356 (0.8272) acc1: 81.2500 (80.8239) acc5: 95.3125 (96.1648) [2021-03-28 07:44:56 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7477 (0.8015) acc1: 81.2500 (81.2500) acc5: 95.3125 (96.2054) [2021-03-28 07:44:58 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7176 (0.7679) acc1: 82.8125 (81.5524) acc5: 96.8750 (96.5222) [2021-03-28 07:45:00 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7600 (0.7711) acc1: 82.8125 (81.7835) acc5: 96.8750 (96.3415) [2021-03-28 07:45:01 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7600 (0.7617) acc1: 82.8125 (82.0800) acc5: 96.8750 (96.3840) [2021-03-28 07:45:15 swin_base_patch4_window7_224] INFO: * Acc@1 82.852 Acc@5 96.274 loss 0.752 [2021-03-28 07:45:15 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.9% [2021-03-28 07:45:15 swin_base_patch4_window7_224] INFO: Max accuracy: 82.85% [2021-03-28 07:45:19 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 0/1251] eta: 1:26:06 lr: 0.000076 loss: 1.9957 (1.9957) grad_norm: 2.5094 (2.5094) time: 4.1303 [2021-03-28 07:45:26 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 10/1251] eta: 0:19:46 lr: 0.000076 loss: 2.7027 (2.5870) grad_norm: 2.5094 (2.6311) time: 0.9564 [2021-03-28 07:45:32 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 20/1251] eta: 0:16:23 lr: 0.000076 loss: 2.7799 (2.6446) grad_norm: 2.6475 (2.6629) time: 0.6321 [2021-03-28 07:45:38 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 30/1251] eta: 0:15:06 lr: 0.000076 loss: 2.8825 (2.7281) grad_norm: 2.6475 (2.7696) time: 0.6250 [2021-03-28 07:45:44 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 40/1251] eta: 0:14:26 lr: 0.000076 loss: 2.8252 (2.7089) grad_norm: 2.6293 (2.9538) time: 0.6290 [2021-03-28 07:45:51 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 50/1251] eta: 0:13:58 lr: 0.000076 loss: 2.8894 (2.7139) grad_norm: 2.9909 (2.9814) time: 0.6301 [2021-03-28 07:45:57 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 60/1251] eta: 0:13:36 lr: 0.000076 loss: 2.8816 (2.6799) grad_norm: 2.8360 (3.0319) time: 0.6238 [2021-03-28 07:46:03 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 70/1251] eta: 0:13:21 lr: 0.000076 loss: 2.7367 (2.6901) grad_norm: 2.9078 (3.0933) time: 0.6288 [2021-03-28 07:46:10 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 80/1251] eta: 0:13:08 lr: 0.000076 loss: 2.8085 (2.7163) grad_norm: 3.1796 (3.0820) time: 0.6342 [2021-03-28 07:46:16 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 90/1251] eta: 0:12:57 lr: 0.000076 loss: 2.9404 (2.7263) grad_norm: 2.9702 (3.0882) time: 0.6372 [2021-03-28 07:46:22 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 100/1251] eta: 0:12:45 lr: 0.000076 loss: 2.6964 (2.7136) grad_norm: 3.1331 (3.1025) time: 0.6346 [2021-03-28 07:46:29 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 110/1251] eta: 0:12:34 lr: 0.000076 loss: 2.7561 (2.7434) grad_norm: 3.1702 (3.1183) time: 0.6251 [2021-03-28 07:46:35 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 120/1251] eta: 0:12:25 lr: 0.000076 loss: 2.9342 (2.7480) grad_norm: 3.0389 (3.1000) time: 0.6264 [2021-03-28 07:46:41 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 130/1251] eta: 0:12:16 lr: 0.000076 loss: 2.7748 (2.7465) grad_norm: 2.6728 (3.0609) time: 0.6294 [2021-03-28 07:46:47 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 140/1251] eta: 0:12:07 lr: 0.000076 loss: 2.7748 (2.7421) grad_norm: 2.5329 (3.0495) time: 0.6271 [2021-03-28 07:46:54 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 150/1251] eta: 0:11:59 lr: 0.000076 loss: 2.9520 (2.7532) grad_norm: 2.5821 (3.0202) time: 0.6316 [2021-03-28 07:47:00 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 160/1251] eta: 0:11:51 lr: 0.000076 loss: 3.0219 (2.7598) grad_norm: 2.7539 (3.0150) time: 0.6326 [2021-03-28 07:47:06 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 170/1251] eta: 0:11:42 lr: 0.000076 loss: 2.9162 (2.7637) grad_norm: 2.8511 (3.0180) time: 0.6243 [2021-03-28 07:47:13 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 180/1251] eta: 0:11:35 lr: 0.000076 loss: 3.0205 (2.7780) grad_norm: 2.7831 (3.0145) time: 0.6318 [2021-03-28 07:47:19 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 190/1251] eta: 0:11:28 lr: 0.000076 loss: 2.9515 (2.7784) grad_norm: 2.6632 (3.0093) time: 0.6364 [2021-03-28 07:47:25 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 200/1251] eta: 0:11:20 lr: 0.000076 loss: 2.8141 (2.7757) grad_norm: 2.6632 (2.9903) time: 0.6317 [2021-03-28 07:47:32 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 210/1251] eta: 0:11:13 lr: 0.000076 loss: 2.8141 (2.7815) grad_norm: 2.5851 (2.9843) time: 0.6276 [2021-03-28 07:47:38 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 220/1251] eta: 0:11:06 lr: 0.000076 loss: 2.7946 (2.7829) grad_norm: 2.7065 (2.9974) time: 0.6285 [2021-03-28 07:47:44 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 230/1251] eta: 0:10:58 lr: 0.000076 loss: 2.6830 (2.7763) grad_norm: 3.0514 (3.0230) time: 0.6312 [2021-03-28 07:47:50 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 240/1251] eta: 0:10:51 lr: 0.000076 loss: 2.7306 (2.7760) grad_norm: 3.0434 (3.0195) time: 0.6284 [2021-03-28 07:47:57 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 250/1251] eta: 0:10:44 lr: 0.000076 loss: 2.6264 (2.7682) grad_norm: 2.7847 (3.0095) time: 0.6272 [2021-03-28 07:48:03 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 260/1251] eta: 0:10:37 lr: 0.000076 loss: 2.6264 (2.7671) grad_norm: 2.6984 (3.0040) time: 0.6286 [2021-03-28 07:48:09 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 270/1251] eta: 0:10:30 lr: 0.000076 loss: 2.9468 (2.7723) grad_norm: 2.8041 (2.9923) time: 0.6327 [2021-03-28 07:48:16 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 280/1251] eta: 0:10:24 lr: 0.000076 loss: 2.8875 (2.7722) grad_norm: 2.6164 (2.9892) time: 0.6417 [2021-03-28 07:48:22 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 290/1251] eta: 0:10:17 lr: 0.000076 loss: 2.8635 (2.7755) grad_norm: 2.6327 (2.9819) time: 0.6418 [2021-03-28 07:48:28 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 300/1251] eta: 0:10:10 lr: 0.000076 loss: 2.8838 (2.7739) grad_norm: 2.7670 (2.9836) time: 0.6288 [2021-03-28 07:48:35 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 310/1251] eta: 0:10:04 lr: 0.000076 loss: 2.8032 (2.7753) grad_norm: 2.8671 (3.0082) time: 0.6268 [2021-03-28 07:48:41 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 320/1251] eta: 0:09:57 lr: 0.000076 loss: 2.7885 (2.7682) grad_norm: 2.7375 (3.0024) time: 0.6337 [2021-03-28 07:48:47 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 330/1251] eta: 0:09:50 lr: 0.000076 loss: 2.7361 (2.7694) grad_norm: 2.5695 (2.9914) time: 0.6370 [2021-03-28 07:48:54 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 340/1251] eta: 0:09:44 lr: 0.000076 loss: 2.8070 (2.7706) grad_norm: 2.4638 (2.9853) time: 0.6307 [2021-03-28 07:49:00 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 350/1251] eta: 0:09:37 lr: 0.000076 loss: 2.8208 (2.7692) grad_norm: 2.6153 (2.9876) time: 0.6273 [2021-03-28 07:49:06 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 360/1251] eta: 0:09:30 lr: 0.000076 loss: 2.8514 (2.7739) grad_norm: 2.8537 (2.9899) time: 0.6358 [2021-03-28 07:49:13 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 370/1251] eta: 0:09:24 lr: 0.000076 loss: 2.7951 (2.7692) grad_norm: 2.8739 (2.9910) time: 0.6350 [2021-03-28 07:49:19 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 380/1251] eta: 0:09:17 lr: 0.000076 loss: 2.7951 (2.7748) grad_norm: 2.7300 (2.9888) time: 0.6279 [2021-03-28 07:49:25 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 390/1251] eta: 0:09:10 lr: 0.000076 loss: 2.9725 (2.7763) grad_norm: 2.7021 (2.9809) time: 0.6280 [2021-03-28 07:49:32 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 400/1251] eta: 0:09:04 lr: 0.000075 loss: 2.9725 (2.7761) grad_norm: 2.7036 (2.9873) time: 0.6317 [2021-03-28 07:49:38 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 410/1251] eta: 0:08:57 lr: 0.000075 loss: 2.9813 (2.7784) grad_norm: 2.7042 (3.0157) time: 0.6299 [2021-03-28 07:49:44 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 420/1251] eta: 0:08:51 lr: 0.000075 loss: 2.8256 (2.7781) grad_norm: 2.6926 (3.0130) time: 0.6287 [2021-03-28 07:49:51 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 430/1251] eta: 0:08:44 lr: 0.000075 loss: 2.9018 (2.7795) grad_norm: 2.8473 (3.0103) time: 0.6310 [2021-03-28 07:49:57 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 440/1251] eta: 0:08:38 lr: 0.000075 loss: 2.9111 (2.7765) grad_norm: 2.6984 (2.9996) time: 0.6315 [2021-03-28 07:50:03 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 450/1251] eta: 0:08:31 lr: 0.000075 loss: 2.9110 (2.7801) grad_norm: 2.5453 (2.9987) time: 0.6305 [2021-03-28 07:50:09 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 460/1251] eta: 0:08:24 lr: 0.000075 loss: 2.9110 (2.7818) grad_norm: 2.7732 (2.9963) time: 0.6242 [2021-03-28 07:50:16 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 470/1251] eta: 0:08:18 lr: 0.000075 loss: 2.8055 (2.7803) grad_norm: 2.7685 (3.0064) time: 0.6282 [2021-03-28 07:50:22 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 480/1251] eta: 0:08:11 lr: 0.000075 loss: 2.8388 (2.7805) grad_norm: 2.7355 (3.0034) time: 0.6320 [2021-03-28 07:50:28 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 490/1251] eta: 0:08:05 lr: 0.000075 loss: 2.8188 (2.7769) grad_norm: 2.6661 (2.9971) time: 0.6278 [2021-03-28 07:50:35 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 500/1251] eta: 0:07:58 lr: 0.000075 loss: 2.8785 (2.7822) grad_norm: 2.6088 (3.0043) time: 0.6296 [2021-03-28 07:50:41 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 510/1251] eta: 0:07:52 lr: 0.000075 loss: 2.8862 (2.7776) grad_norm: 2.5622 (2.9987) time: 0.6290 [2021-03-28 07:50:47 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 520/1251] eta: 0:07:45 lr: 0.000075 loss: 2.4876 (2.7750) grad_norm: 2.6797 (2.9988) time: 0.6244 [2021-03-28 07:50:53 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 530/1251] eta: 0:07:39 lr: 0.000075 loss: 2.7099 (2.7733) grad_norm: 2.6315 (2.9932) time: 0.6237 [2021-03-28 07:51:00 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 540/1251] eta: 0:07:32 lr: 0.000075 loss: 2.8260 (2.7770) grad_norm: 2.6210 (3.0030) time: 0.6264 [2021-03-28 07:51:06 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 550/1251] eta: 0:07:26 lr: 0.000075 loss: 2.8806 (2.7759) grad_norm: 2.7107 (2.9973) time: 0.6366 [2021-03-28 07:51:12 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 560/1251] eta: 0:07:19 lr: 0.000075 loss: 2.9055 (2.7818) grad_norm: 2.5133 (3.0271) time: 0.6370 [2021-03-28 07:51:19 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 570/1251] eta: 0:07:13 lr: 0.000075 loss: 2.9437 (2.7781) grad_norm: 2.7517 (3.0248) time: 0.6287 [2021-03-28 07:51:25 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 580/1251] eta: 0:07:07 lr: 0.000075 loss: 2.8513 (2.7805) grad_norm: 2.7742 (3.0239) time: 0.6288 [2021-03-28 07:51:31 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 590/1251] eta: 0:07:00 lr: 0.000075 loss: 2.9478 (2.7810) grad_norm: 2.6101 (3.0179) time: 0.6315 [2021-03-28 07:51:38 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 600/1251] eta: 0:06:54 lr: 0.000075 loss: 2.8569 (2.7816) grad_norm: 2.5985 (3.0120) time: 0.6340 [2021-03-28 07:51:44 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 610/1251] eta: 0:06:47 lr: 0.000075 loss: 2.8997 (2.7840) grad_norm: 2.6138 (3.0074) time: 0.6304 [2021-03-28 07:51:50 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 620/1251] eta: 0:06:41 lr: 0.000075 loss: 2.9698 (2.7823) grad_norm: 2.6150 (3.0047) time: 0.6279 [2021-03-28 07:51:56 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 630/1251] eta: 0:06:34 lr: 0.000075 loss: 3.0200 (2.7872) grad_norm: 2.6923 (3.0012) time: 0.6248 [2021-03-28 07:52:03 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 640/1251] eta: 0:06:28 lr: 0.000075 loss: 3.0303 (2.7882) grad_norm: 2.6923 (3.0052) time: 0.6297 [2021-03-28 07:52:09 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 650/1251] eta: 0:06:22 lr: 0.000075 loss: 2.9552 (2.7889) grad_norm: 2.6511 (2.9998) time: 0.6379 [2021-03-28 07:52:15 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 660/1251] eta: 0:06:15 lr: 0.000075 loss: 2.9753 (2.7904) grad_norm: 2.7459 (3.0002) time: 0.6309 [2021-03-28 07:52:22 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 670/1251] eta: 0:06:09 lr: 0.000075 loss: 2.8333 (2.7933) grad_norm: 2.8030 (3.0022) time: 0.6284 [2021-03-28 07:52:28 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 680/1251] eta: 0:06:02 lr: 0.000075 loss: 2.8123 (2.7923) grad_norm: 2.8030 (2.9987) time: 0.6279 [2021-03-28 07:52:34 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 690/1251] eta: 0:05:56 lr: 0.000075 loss: 2.7988 (2.7927) grad_norm: 2.7639 (2.9942) time: 0.6280 [2021-03-28 07:52:41 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 700/1251] eta: 0:05:50 lr: 0.000075 loss: 2.7721 (2.7892) grad_norm: 2.6647 (2.9926) time: 0.6344 [2021-03-28 07:52:47 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 710/1251] eta: 0:05:43 lr: 0.000075 loss: 2.4860 (2.7866) grad_norm: 2.6552 (2.9909) time: 0.6347 [2021-03-28 07:52:53 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 720/1251] eta: 0:05:37 lr: 0.000075 loss: 2.5425 (2.7868) grad_norm: 3.0956 (2.9965) time: 0.6292 [2021-03-28 07:53:00 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 730/1251] eta: 0:05:31 lr: 0.000075 loss: 2.7500 (2.7874) grad_norm: 2.8562 (2.9937) time: 0.6337 [2021-03-28 07:53:06 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 740/1251] eta: 0:05:24 lr: 0.000075 loss: 2.7226 (2.7860) grad_norm: 2.6268 (2.9907) time: 0.6424 [2021-03-28 07:53:13 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 750/1251] eta: 0:05:18 lr: 0.000075 loss: 2.6539 (2.7846) grad_norm: 2.5949 (2.9888) time: 0.6438 [2021-03-28 07:53:19 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 760/1251] eta: 0:05:12 lr: 0.000075 loss: 2.9202 (2.7871) grad_norm: 2.7382 (2.9904) time: 0.6412 [2021-03-28 07:53:25 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 770/1251] eta: 0:05:05 lr: 0.000075 loss: 2.9212 (2.7880) grad_norm: 2.8258 (3.0036) time: 0.6318 [2021-03-28 07:53:31 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 780/1251] eta: 0:04:59 lr: 0.000075 loss: 2.8892 (2.7905) grad_norm: 2.9753 (3.0059) time: 0.6242 [2021-03-28 07:53:38 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 790/1251] eta: 0:04:52 lr: 0.000075 loss: 2.8877 (2.7884) grad_norm: 2.9251 (3.0074) time: 0.6295 [2021-03-28 07:53:44 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 800/1251] eta: 0:04:46 lr: 0.000075 loss: 2.7889 (2.7907) grad_norm: 2.8102 (3.0053) time: 0.6364 [2021-03-28 07:53:50 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 810/1251] eta: 0:04:40 lr: 0.000075 loss: 3.0076 (2.7908) grad_norm: 2.8102 (3.0041) time: 0.6296 [2021-03-28 07:53:57 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 820/1251] eta: 0:04:33 lr: 0.000075 loss: 2.9348 (2.7905) grad_norm: 2.7024 (3.0068) time: 0.6255 [2021-03-28 07:54:03 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 830/1251] eta: 0:04:27 lr: 0.000075 loss: 2.7331 (2.7886) grad_norm: 2.7912 (3.0078) time: 0.6315 [2021-03-28 07:54:09 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 840/1251] eta: 0:04:21 lr: 0.000075 loss: 2.7983 (2.7903) grad_norm: 2.9823 (3.0090) time: 0.6319 [2021-03-28 07:54:16 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 850/1251] eta: 0:04:14 lr: 0.000075 loss: 3.0738 (2.7921) grad_norm: 2.9823 (3.0125) time: 0.6299 [2021-03-28 07:54:22 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 860/1251] eta: 0:04:08 lr: 0.000075 loss: 2.9271 (2.7921) grad_norm: 2.7791 (3.0097) time: 0.6331 [2021-03-28 07:54:28 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 870/1251] eta: 0:04:01 lr: 0.000075 loss: 2.8118 (2.7923) grad_norm: 2.6646 (3.0069) time: 0.6299 [2021-03-28 07:54:34 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 880/1251] eta: 0:03:55 lr: 0.000075 loss: 2.8764 (2.7920) grad_norm: 2.6646 (3.0043) time: 0.6232 [2021-03-28 07:54:41 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 890/1251] eta: 0:03:49 lr: 0.000074 loss: 2.9553 (2.7938) grad_norm: 2.8982 (3.0074) time: 0.6229 [2021-03-28 07:54:47 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 900/1251] eta: 0:03:42 lr: 0.000074 loss: 2.9553 (2.7935) grad_norm: 3.1128 (3.0127) time: 0.6249 [2021-03-28 07:54:53 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 910/1251] eta: 0:03:36 lr: 0.000074 loss: 2.8365 (2.7937) grad_norm: 2.8747 (3.0112) time: 0.6293 [2021-03-28 07:55:00 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 920/1251] eta: 0:03:30 lr: 0.000074 loss: 2.8196 (2.7924) grad_norm: 2.6052 (3.0074) time: 0.6351 [2021-03-28 07:55:06 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 930/1251] eta: 0:03:23 lr: 0.000074 loss: 2.8196 (2.7928) grad_norm: 2.5752 (3.0037) time: 0.6396 [2021-03-28 07:55:12 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 940/1251] eta: 0:03:17 lr: 0.000074 loss: 2.8166 (2.7932) grad_norm: 2.6108 (3.0014) time: 0.6361 [2021-03-28 07:55:19 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 950/1251] eta: 0:03:10 lr: 0.000074 loss: 2.8085 (2.7934) grad_norm: 2.7005 (3.0009) time: 0.6271 [2021-03-28 07:55:25 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 960/1251] eta: 0:03:04 lr: 0.000074 loss: 2.7920 (2.7909) grad_norm: 2.9158 (2.9992) time: 0.6284 [2021-03-28 07:55:31 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 970/1251] eta: 0:02:58 lr: 0.000074 loss: 2.8266 (2.7918) grad_norm: 2.9128 (2.9988) time: 0.6318 [2021-03-28 07:55:37 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 980/1251] eta: 0:02:51 lr: 0.000074 loss: 2.8442 (2.7903) grad_norm: 2.9128 (3.0031) time: 0.6284 [2021-03-28 07:55:44 swin_base_patch4_window7_224] INFO: Epoch: [250] [ 990/1251] eta: 0:02:45 lr: 0.000074 loss: 2.5508 (2.7883) grad_norm: 2.7636 (3.0033) time: 0.6301 [2021-03-28 07:55:50 swin_base_patch4_window7_224] INFO: Epoch: [250] [1000/1251] eta: 0:02:39 lr: 0.000074 loss: 2.7357 (2.7881) grad_norm: 2.8606 (3.0040) time: 0.6335 [2021-03-28 07:55:56 swin_base_patch4_window7_224] INFO: Epoch: [250] [1010/1251] eta: 0:02:32 lr: 0.000074 loss: 2.7625 (2.7868) grad_norm: 2.8710 (3.0043) time: 0.6274 [2021-03-28 07:56:03 swin_base_patch4_window7_224] INFO: Epoch: [250] [1020/1251] eta: 0:02:26 lr: 0.000074 loss: 2.5498 (2.7842) grad_norm: 2.9846 (3.0055) time: 0.6290 [2021-03-28 07:56:09 swin_base_patch4_window7_224] INFO: Epoch: [250] [1030/1251] eta: 0:02:20 lr: 0.000074 loss: 2.5970 (2.7833) grad_norm: 2.8207 (3.0063) time: 0.6381 [2021-03-28 07:56:15 swin_base_patch4_window7_224] INFO: Epoch: [250] [1040/1251] eta: 0:02:13 lr: 0.000074 loss: 2.7578 (2.7829) grad_norm: 2.7661 (3.0044) time: 0.6309 [2021-03-28 07:56:22 swin_base_patch4_window7_224] INFO: Epoch: [250] [1050/1251] eta: 0:02:07 lr: 0.000074 loss: 2.7578 (2.7826) grad_norm: 2.6739 (3.0045) time: 0.6243 [2021-03-28 07:56:28 swin_base_patch4_window7_224] INFO: Epoch: [250] [1060/1251] eta: 0:02:01 lr: 0.000074 loss: 2.7873 (2.7837) grad_norm: 2.9857 (3.0121) time: 0.6252 [2021-03-28 07:56:34 swin_base_patch4_window7_224] INFO: Epoch: [250] [1070/1251] eta: 0:01:54 lr: 0.000074 loss: 2.7415 (2.7823) grad_norm: 3.4555 (3.0162) time: 0.6291 [2021-03-28 07:56:41 swin_base_patch4_window7_224] INFO: Epoch: [250] [1080/1251] eta: 0:01:48 lr: 0.000074 loss: 2.6047 (2.7806) grad_norm: 3.2145 (3.0197) time: 0.6312 [2021-03-28 07:56:47 swin_base_patch4_window7_224] INFO: Epoch: [250] [1090/1251] eta: 0:01:42 lr: 0.000074 loss: 2.6421 (2.7804) grad_norm: 2.8788 (3.0190) time: 0.6278 [2021-03-28 07:56:53 swin_base_patch4_window7_224] INFO: Epoch: [250] [1100/1251] eta: 0:01:35 lr: 0.000074 loss: 2.7117 (2.7814) grad_norm: 2.8052 (3.0214) time: 0.6276 [2021-03-28 07:56:59 swin_base_patch4_window7_224] INFO: Epoch: [250] [1110/1251] eta: 0:01:29 lr: 0.000074 loss: 2.8975 (2.7822) grad_norm: 2.9543 (3.0211) time: 0.6312 [2021-03-28 07:57:06 swin_base_patch4_window7_224] INFO: Epoch: [250] [1120/1251] eta: 0:01:23 lr: 0.000074 loss: 2.8858 (2.7827) grad_norm: 2.8964 (3.0197) time: 0.6335 [2021-03-28 07:57:12 swin_base_patch4_window7_224] INFO: Epoch: [250] [1130/1251] eta: 0:01:16 lr: 0.000074 loss: 2.8537 (2.7827) grad_norm: 3.0233 (3.0228) time: 0.6295 [2021-03-28 07:57:18 swin_base_patch4_window7_224] INFO: Epoch: [250] [1140/1251] eta: 0:01:10 lr: 0.000074 loss: 2.8342 (2.7825) grad_norm: 3.0416 (3.0220) time: 0.6293 [2021-03-28 07:57:25 swin_base_patch4_window7_224] INFO: Epoch: [250] [1150/1251] eta: 0:01:04 lr: 0.000074 loss: 2.7935 (2.7825) grad_norm: 2.6562 (3.0219) time: 0.6298 [2021-03-28 07:57:31 swin_base_patch4_window7_224] INFO: Epoch: [250] [1160/1251] eta: 0:00:57 lr: 0.000074 loss: 2.7935 (2.7821) grad_norm: 2.7150 (3.0234) time: 0.6305 [2021-03-28 07:57:37 swin_base_patch4_window7_224] INFO: Epoch: [250] [1170/1251] eta: 0:00:51 lr: 0.000074 loss: 2.8191 (2.7819) grad_norm: 2.9007 (3.0237) time: 0.6277 [2021-03-28 07:57:43 swin_base_patch4_window7_224] INFO: Epoch: [250] [1180/1251] eta: 0:00:44 lr: 0.000074 loss: 2.8191 (2.7822) grad_norm: 2.9930 (3.0248) time: 0.6240 [2021-03-28 07:57:50 swin_base_patch4_window7_224] INFO: Epoch: [250] [1190/1251] eta: 0:00:38 lr: 0.000074 loss: 2.8565 (2.7824) grad_norm: 2.9235 (3.0264) time: 0.6242 [2021-03-28 07:57:56 swin_base_patch4_window7_224] INFO: Epoch: [250] [1200/1251] eta: 0:00:32 lr: 0.000074 loss: 2.4415 (2.7792) grad_norm: 2.8278 (3.0236) time: 0.6269 [2021-03-28 07:58:02 swin_base_patch4_window7_224] INFO: Epoch: [250] [1210/1251] eta: 0:00:25 lr: 0.000074 loss: 2.5646 (2.7784) grad_norm: 2.6927 (3.0216) time: 0.6308 [2021-03-28 07:58:09 swin_base_patch4_window7_224] INFO: Epoch: [250] [1220/1251] eta: 0:00:19 lr: 0.000074 loss: 2.6476 (2.7769) grad_norm: 2.9111 (3.0233) time: 0.6316 [2021-03-28 07:58:15 swin_base_patch4_window7_224] INFO: Epoch: [250] [1230/1251] eta: 0:00:13 lr: 0.000074 loss: 2.8452 (2.7775) grad_norm: 2.8692 (3.0215) time: 0.6289 [2021-03-28 07:58:21 swin_base_patch4_window7_224] INFO: Epoch: [250] [1240/1251] eta: 0:00:06 lr: 0.000074 loss: 2.9381 (2.7796) grad_norm: 2.6101 (3.0183) time: 0.6324 [2021-03-28 07:58:28 swin_base_patch4_window7_224] INFO: Epoch: [250] [1250/1251] eta: 0:00:00 lr: 0.000074 loss: 2.8909 (2.7785) grad_norm: 2.6737 (3.0168) time: 0.6340 [2021-03-28 07:59:35 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:05 loss: 0.7669 (0.7669) acc1: 84.3750 (84.3750) acc5: 96.8750 (96.8750) [2021-03-28 07:59:37 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.8147 (0.8331) acc1: 81.2500 (80.8239) acc5: 96.8750 (96.1648) [2021-03-28 07:59:38 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7902 (0.8048) acc1: 81.2500 (81.0268) acc5: 96.8750 (96.2798) [2021-03-28 07:59:40 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7242 (0.7645) acc1: 82.8125 (82.3085) acc5: 95.3125 (96.4214) [2021-03-28 07:59:41 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7219 (0.7627) acc1: 82.8125 (82.3552) acc5: 95.3125 (96.2652) [2021-03-28 07:59:42 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7012 (0.7685) acc1: 81.2500 (82.1120) acc5: 95.3125 (96.3520) [2021-03-28 07:59:52 swin_base_patch4_window7_224] INFO: * Acc@1 82.888 Acc@5 96.322 loss 0.748 [2021-03-28 07:59:52 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.9% [2021-03-28 07:59:52 swin_base_patch4_window7_224] INFO: Max accuracy: 82.89% [2021-03-28 07:59:57 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 0/1251] eta: 1:30:11 lr: 0.000074 loss: 3.2716 (3.2716) grad_norm: 2.7263 (2.7263) time: 4.3261 [2021-03-28 08:00:03 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 10/1251] eta: 0:20:01 lr: 0.000074 loss: 2.9679 (2.7610) grad_norm: 2.8017 (2.7894) time: 0.9682 [2021-03-28 08:00:09 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 20/1251] eta: 0:16:30 lr: 0.000074 loss: 2.8779 (2.7687) grad_norm: 2.7703 (2.8478) time: 0.6284 [2021-03-28 08:00:16 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 30/1251] eta: 0:15:13 lr: 0.000074 loss: 2.8779 (2.7172) grad_norm: 2.7148 (2.8092) time: 0.6272 [2021-03-28 08:00:22 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 40/1251] eta: 0:14:32 lr: 0.000074 loss: 2.8385 (2.6899) grad_norm: 2.7985 (2.8547) time: 0.6322 [2021-03-28 08:00:28 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 50/1251] eta: 0:14:05 lr: 0.000074 loss: 2.7896 (2.7128) grad_norm: 3.0041 (2.9244) time: 0.6366 [2021-03-28 08:00:35 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 60/1251] eta: 0:13:43 lr: 0.000074 loss: 2.5954 (2.6734) grad_norm: 2.9096 (2.9278) time: 0.6326 [2021-03-28 08:00:41 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 70/1251] eta: 0:13:26 lr: 0.000074 loss: 2.6548 (2.6901) grad_norm: 2.7558 (2.9811) time: 0.6281 [2021-03-28 08:00:47 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 80/1251] eta: 0:13:11 lr: 0.000074 loss: 2.7282 (2.6896) grad_norm: 2.7572 (2.9673) time: 0.6291 [2021-03-28 08:00:54 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 90/1251] eta: 0:12:59 lr: 0.000074 loss: 2.7119 (2.6717) grad_norm: 2.8275 (2.9681) time: 0.6288 [2021-03-28 08:01:00 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 100/1251] eta: 0:12:47 lr: 0.000074 loss: 2.6944 (2.6820) grad_norm: 2.8810 (2.9988) time: 0.6294 [2021-03-28 08:01:06 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 110/1251] eta: 0:12:36 lr: 0.000074 loss: 2.7694 (2.6847) grad_norm: 2.8162 (2.9791) time: 0.6280 [2021-03-28 08:01:12 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 120/1251] eta: 0:12:27 lr: 0.000074 loss: 2.7097 (2.6836) grad_norm: 2.6708 (2.9600) time: 0.6287 [2021-03-28 08:01:19 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 130/1251] eta: 0:12:17 lr: 0.000073 loss: 2.7387 (2.7019) grad_norm: 2.6725 (2.9497) time: 0.6282 [2021-03-28 08:01:25 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 140/1251] eta: 0:12:09 lr: 0.000073 loss: 2.8441 (2.6942) grad_norm: 2.6920 (2.9434) time: 0.6300 [2021-03-28 08:01:31 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 150/1251] eta: 0:12:00 lr: 0.000073 loss: 2.7955 (2.6943) grad_norm: 2.8308 (2.9415) time: 0.6346 [2021-03-28 08:01:38 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 160/1251] eta: 0:11:52 lr: 0.000073 loss: 2.7955 (2.6921) grad_norm: 2.7846 (2.9923) time: 0.6319 [2021-03-28 08:01:44 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 170/1251] eta: 0:11:44 lr: 0.000073 loss: 2.8408 (2.7089) grad_norm: 2.7679 (2.9801) time: 0.6295 [2021-03-28 08:01:50 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 180/1251] eta: 0:11:37 lr: 0.000073 loss: 2.9775 (2.7152) grad_norm: 2.7953 (2.9788) time: 0.6310 [2021-03-28 08:01:57 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 190/1251] eta: 0:11:29 lr: 0.000073 loss: 2.9181 (2.7197) grad_norm: 2.7884 (2.9803) time: 0.6338 [2021-03-28 08:02:03 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 200/1251] eta: 0:11:22 lr: 0.000073 loss: 2.8844 (2.7202) grad_norm: 2.8386 (2.9759) time: 0.6390 [2021-03-28 08:02:09 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 210/1251] eta: 0:11:15 lr: 0.000073 loss: 2.7219 (2.7123) grad_norm: 2.9260 (2.9729) time: 0.6381 [2021-03-28 08:02:16 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 220/1251] eta: 0:11:07 lr: 0.000073 loss: 2.6326 (2.7096) grad_norm: 2.9379 (2.9745) time: 0.6289 [2021-03-28 08:02:22 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 230/1251] eta: 0:11:00 lr: 0.000073 loss: 2.7375 (2.7172) grad_norm: 2.8225 (2.9765) time: 0.6220 [2021-03-28 08:02:28 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 240/1251] eta: 0:10:52 lr: 0.000073 loss: 2.7236 (2.7060) grad_norm: 2.7945 (3.0295) time: 0.6230 [2021-03-28 08:02:34 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 250/1251] eta: 0:10:45 lr: 0.000073 loss: 2.6072 (2.6989) grad_norm: 2.8015 (3.0272) time: 0.6304 [2021-03-28 08:02:41 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 260/1251] eta: 0:10:38 lr: 0.000073 loss: 2.8588 (2.7063) grad_norm: 2.7935 (3.0400) time: 0.6284 [2021-03-28 08:02:47 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 270/1251] eta: 0:10:31 lr: 0.000073 loss: 2.9244 (2.7145) grad_norm: 2.7935 (3.0409) time: 0.6255 [2021-03-28 08:02:53 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 280/1251] eta: 0:10:24 lr: 0.000073 loss: 2.9017 (2.7158) grad_norm: 2.8987 (3.0430) time: 0.6256 [2021-03-28 08:03:00 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 290/1251] eta: 0:10:17 lr: 0.000073 loss: 2.7521 (2.7154) grad_norm: 2.8987 (3.0386) time: 0.6259 [2021-03-28 08:03:06 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 300/1251] eta: 0:10:10 lr: 0.000073 loss: 2.7976 (2.7182) grad_norm: 2.8530 (3.0504) time: 0.6273 [2021-03-28 08:03:12 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 310/1251] eta: 0:10:03 lr: 0.000073 loss: 2.8226 (2.7161) grad_norm: 2.6444 (3.0435) time: 0.6295 [2021-03-28 08:03:18 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 320/1251] eta: 0:09:57 lr: 0.000073 loss: 2.8379 (2.7188) grad_norm: 2.7942 (3.0422) time: 0.6348 [2021-03-28 08:03:25 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 330/1251] eta: 0:09:50 lr: 0.000073 loss: 2.9554 (2.7227) grad_norm: 2.7942 (3.0353) time: 0.6351 [2021-03-28 08:03:31 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 340/1251] eta: 0:09:43 lr: 0.000073 loss: 2.7764 (2.7165) grad_norm: 2.8330 (3.0437) time: 0.6298 [2021-03-28 08:03:37 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 350/1251] eta: 0:09:37 lr: 0.000073 loss: 2.7092 (2.7203) grad_norm: 2.9439 (3.0465) time: 0.6255 [2021-03-28 08:03:44 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 360/1251] eta: 0:09:30 lr: 0.000073 loss: 2.9973 (2.7289) grad_norm: 2.6432 (3.0403) time: 0.6282 [2021-03-28 08:03:50 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 370/1251] eta: 0:09:23 lr: 0.000073 loss: 2.9744 (2.7292) grad_norm: 2.6407 (3.0352) time: 0.6292 [2021-03-28 08:03:56 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 380/1251] eta: 0:09:16 lr: 0.000073 loss: 2.7064 (2.7259) grad_norm: 2.6328 (3.0256) time: 0.6254 [2021-03-28 08:04:02 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 390/1251] eta: 0:09:10 lr: 0.000073 loss: 2.6591 (2.7244) grad_norm: 2.7411 (3.0210) time: 0.6229 [2021-03-28 08:04:09 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 400/1251] eta: 0:09:03 lr: 0.000073 loss: 2.8215 (2.7268) grad_norm: 2.6886 (3.0138) time: 0.6267 [2021-03-28 08:04:15 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 410/1251] eta: 0:08:57 lr: 0.000073 loss: 2.9101 (2.7301) grad_norm: 2.6766 (3.0122) time: 0.6311 [2021-03-28 08:04:21 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 420/1251] eta: 0:08:50 lr: 0.000073 loss: 2.9101 (2.7351) grad_norm: 2.6795 (3.0053) time: 0.6318 [2021-03-28 08:04:28 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 430/1251] eta: 0:08:44 lr: 0.000073 loss: 2.8330 (2.7352) grad_norm: 2.5982 (3.0024) time: 0.6321 [2021-03-28 08:04:34 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 440/1251] eta: 0:08:37 lr: 0.000073 loss: 2.7658 (2.7339) grad_norm: 2.7547 (3.0009) time: 0.6297 [2021-03-28 08:04:40 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 450/1251] eta: 0:08:30 lr: 0.000073 loss: 2.7748 (2.7369) grad_norm: 2.6872 (2.9949) time: 0.6285 [2021-03-28 08:04:47 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 460/1251] eta: 0:08:24 lr: 0.000073 loss: 2.7748 (2.7368) grad_norm: 2.6872 (2.9961) time: 0.6301 [2021-03-28 08:04:53 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 470/1251] eta: 0:08:17 lr: 0.000073 loss: 2.7735 (2.7390) grad_norm: 2.7619 (2.9897) time: 0.6313 [2021-03-28 08:04:59 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 480/1251] eta: 0:08:11 lr: 0.000073 loss: 2.6891 (2.7379) grad_norm: 2.7619 (2.9916) time: 0.6312 [2021-03-28 08:05:05 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 490/1251] eta: 0:08:04 lr: 0.000073 loss: 2.6891 (2.7375) grad_norm: 2.7875 (2.9903) time: 0.6300 [2021-03-28 08:05:12 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 500/1251] eta: 0:07:58 lr: 0.000073 loss: 2.6955 (2.7353) grad_norm: 2.7875 (2.9965) time: 0.6285 [2021-03-28 08:05:18 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 510/1251] eta: 0:07:51 lr: 0.000073 loss: 2.7907 (2.7389) grad_norm: 2.9214 (2.9973) time: 0.6288 [2021-03-28 08:05:24 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 520/1251] eta: 0:07:45 lr: 0.000073 loss: 2.9115 (2.7417) grad_norm: 2.7123 (2.9923) time: 0.6269 [2021-03-28 08:05:31 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 530/1251] eta: 0:07:39 lr: 0.000073 loss: 2.7450 (2.7409) grad_norm: 2.6397 (3.0109) time: 0.6314 [2021-03-28 08:05:37 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 540/1251] eta: 0:07:32 lr: 0.000073 loss: 2.7449 (2.7402) grad_norm: 2.5846 (3.0039) time: 0.6354 [2021-03-28 08:05:43 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 550/1251] eta: 0:07:26 lr: 0.000073 loss: 2.9093 (2.7428) grad_norm: 2.6050 (3.0051) time: 0.6401 [2021-03-28 08:05:50 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 560/1251] eta: 0:07:19 lr: 0.000073 loss: 2.9600 (2.7417) grad_norm: 2.7736 (3.0006) time: 0.6389 [2021-03-28 08:05:56 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 570/1251] eta: 0:07:13 lr: 0.000073 loss: 2.8162 (2.7376) grad_norm: 2.5972 (2.9927) time: 0.6376 [2021-03-28 08:06:03 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 580/1251] eta: 0:07:07 lr: 0.000073 loss: 2.7637 (2.7390) grad_norm: 2.6186 (2.9914) time: 0.6412 [2021-03-28 08:06:09 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 590/1251] eta: 0:07:00 lr: 0.000073 loss: 2.7637 (2.7389) grad_norm: 2.8058 (2.9913) time: 0.6309 [2021-03-28 08:06:15 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 600/1251] eta: 0:06:54 lr: 0.000073 loss: 2.9400 (2.7426) grad_norm: 2.8695 (2.9929) time: 0.6371 [2021-03-28 08:06:22 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 610/1251] eta: 0:06:48 lr: 0.000073 loss: 2.9400 (2.7448) grad_norm: 3.0665 (2.9947) time: 0.6440 [2021-03-28 08:06:28 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 620/1251] eta: 0:06:41 lr: 0.000072 loss: 2.7953 (2.7421) grad_norm: 2.8365 (2.9928) time: 0.6325 [2021-03-28 08:06:34 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 630/1251] eta: 0:06:35 lr: 0.000072 loss: 2.7170 (2.7429) grad_norm: 2.7685 (2.9947) time: 0.6296 [2021-03-28 08:06:41 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 640/1251] eta: 0:06:28 lr: 0.000072 loss: 2.7209 (2.7405) grad_norm: 2.7567 (2.9903) time: 0.6293 [2021-03-28 08:06:47 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 650/1251] eta: 0:06:22 lr: 0.000072 loss: 2.7687 (2.7417) grad_norm: 2.8114 (2.9922) time: 0.6292 [2021-03-28 08:06:53 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 660/1251] eta: 0:06:16 lr: 0.000072 loss: 2.8440 (2.7420) grad_norm: 3.0177 (2.9919) time: 0.6334 [2021-03-28 08:06:59 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 670/1251] eta: 0:06:09 lr: 0.000072 loss: 2.7377 (2.7426) grad_norm: 2.6938 (2.9860) time: 0.6270 [2021-03-28 08:07:06 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 680/1251] eta: 0:06:03 lr: 0.000072 loss: 2.8606 (2.7431) grad_norm: 2.6316 (2.9846) time: 0.6222 [2021-03-28 08:07:12 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 690/1251] eta: 0:05:56 lr: 0.000072 loss: 2.8613 (2.7424) grad_norm: 2.9103 (2.9873) time: 0.6284 [2021-03-28 08:07:19 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 700/1251] eta: 0:05:50 lr: 0.000072 loss: 2.8613 (2.7426) grad_norm: 3.0329 (2.9965) time: 0.6430 [2021-03-28 08:07:25 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 710/1251] eta: 0:05:44 lr: 0.000072 loss: 2.8991 (2.7434) grad_norm: 2.6494 (2.9938) time: 0.6433 [2021-03-28 08:07:31 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 720/1251] eta: 0:05:37 lr: 0.000072 loss: 2.7435 (2.7425) grad_norm: 2.6494 (2.9908) time: 0.6299 [2021-03-28 08:07:38 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 730/1251] eta: 0:05:31 lr: 0.000072 loss: 2.6465 (2.7414) grad_norm: 2.8521 (2.9898) time: 0.6315 [2021-03-28 08:07:44 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 740/1251] eta: 0:05:25 lr: 0.000072 loss: 2.8655 (2.7437) grad_norm: 2.9845 (2.9940) time: 0.6404 [2021-03-28 08:07:50 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 750/1251] eta: 0:05:18 lr: 0.000072 loss: 2.7388 (2.7406) grad_norm: 2.7768 (2.9890) time: 0.6362 [2021-03-28 08:07:57 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 760/1251] eta: 0:05:12 lr: 0.000072 loss: 2.7571 (2.7439) grad_norm: 2.7248 (2.9859) time: 0.6346 [2021-03-28 08:08:03 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 770/1251] eta: 0:05:05 lr: 0.000072 loss: 2.9246 (2.7434) grad_norm: 2.7454 (2.9850) time: 0.6363 [2021-03-28 08:08:09 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 780/1251] eta: 0:04:59 lr: 0.000072 loss: 2.7353 (2.7423) grad_norm: 2.7049 (2.9874) time: 0.6263 [2021-03-28 08:08:15 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 790/1251] eta: 0:04:53 lr: 0.000072 loss: 2.8270 (2.7424) grad_norm: 2.7451 (2.9850) time: 0.6234 [2021-03-28 08:08:22 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 800/1251] eta: 0:04:46 lr: 0.000072 loss: 2.9074 (2.7438) grad_norm: 2.7050 (2.9851) time: 0.6308 [2021-03-28 08:08:28 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 810/1251] eta: 0:04:40 lr: 0.000072 loss: 2.9074 (2.7456) grad_norm: 2.7050 (2.9824) time: 0.6350 [2021-03-28 08:08:35 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 820/1251] eta: 0:04:34 lr: 0.000072 loss: 2.8398 (2.7475) grad_norm: 2.7520 (2.9826) time: 0.6408 [2021-03-28 08:08:41 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 830/1251] eta: 0:04:27 lr: 0.000072 loss: 2.9712 (2.7507) grad_norm: 2.9414 (2.9824) time: 0.6380 [2021-03-28 08:08:47 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 840/1251] eta: 0:04:21 lr: 0.000072 loss: 2.9141 (2.7484) grad_norm: 2.8807 (2.9825) time: 0.6295 [2021-03-28 08:08:53 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 850/1251] eta: 0:04:14 lr: 0.000072 loss: 2.8680 (2.7510) grad_norm: 2.6943 (2.9794) time: 0.6285 [2021-03-28 08:09:00 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 860/1251] eta: 0:04:08 lr: 0.000072 loss: 2.8680 (2.7502) grad_norm: 2.6885 (2.9784) time: 0.6270 [2021-03-28 08:09:06 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 870/1251] eta: 0:04:02 lr: 0.000072 loss: 2.7253 (2.7512) grad_norm: 2.7950 (2.9790) time: 0.6313 [2021-03-28 08:09:12 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 880/1251] eta: 0:03:55 lr: 0.000072 loss: 2.7253 (2.7483) grad_norm: 2.8408 (2.9792) time: 0.6330 [2021-03-28 08:09:19 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 890/1251] eta: 0:03:49 lr: 0.000072 loss: 2.6941 (2.7484) grad_norm: 2.8408 (2.9873) time: 0.6298 [2021-03-28 08:09:25 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 900/1251] eta: 0:03:42 lr: 0.000072 loss: 2.9223 (2.7498) grad_norm: 2.8321 (2.9961) time: 0.6264 [2021-03-28 08:09:31 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 910/1251] eta: 0:03:36 lr: 0.000072 loss: 2.8435 (2.7463) grad_norm: 2.7320 (2.9947) time: 0.6280 [2021-03-28 08:09:38 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 920/1251] eta: 0:03:30 lr: 0.000072 loss: 2.6670 (2.7464) grad_norm: 2.7614 (2.9999) time: 0.6341 [2021-03-28 08:09:44 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 930/1251] eta: 0:03:23 lr: 0.000072 loss: 2.8283 (2.7471) grad_norm: 2.7634 (2.9984) time: 0.6351 [2021-03-28 08:09:50 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 940/1251] eta: 0:03:17 lr: 0.000072 loss: 2.7778 (2.7470) grad_norm: 2.8048 (2.9962) time: 0.6303 [2021-03-28 08:09:57 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 950/1251] eta: 0:03:11 lr: 0.000072 loss: 2.6694 (2.7449) grad_norm: 2.8048 (2.9947) time: 0.6300 [2021-03-28 08:10:03 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 960/1251] eta: 0:03:04 lr: 0.000072 loss: 2.8016 (2.7454) grad_norm: 2.7351 (inf) time: 0.6271 [2021-03-28 08:10:09 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 970/1251] eta: 0:02:58 lr: 0.000072 loss: 2.8241 (2.7453) grad_norm: 2.7351 (inf) time: 0.6241 [2021-03-28 08:10:15 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 980/1251] eta: 0:02:52 lr: 0.000072 loss: 2.8091 (2.7448) grad_norm: 2.9339 (inf) time: 0.6265 [2021-03-28 08:10:22 swin_base_patch4_window7_224] INFO: Epoch: [251] [ 990/1251] eta: 0:02:45 lr: 0.000072 loss: 2.8091 (2.7470) grad_norm: 3.0627 (inf) time: 0.6253 [2021-03-28 08:10:28 swin_base_patch4_window7_224] INFO: Epoch: [251] [1000/1251] eta: 0:02:39 lr: 0.000072 loss: 2.7433 (2.7454) grad_norm: 2.7936 (inf) time: 0.6278 [2021-03-28 08:10:34 swin_base_patch4_window7_224] INFO: Epoch: [251] [1010/1251] eta: 0:02:32 lr: 0.000072 loss: 2.8787 (2.7467) grad_norm: 2.7966 (inf) time: 0.6363 [2021-03-28 08:10:41 swin_base_patch4_window7_224] INFO: Epoch: [251] [1020/1251] eta: 0:02:26 lr: 0.000072 loss: 2.8845 (2.7458) grad_norm: 2.7338 (inf) time: 0.6325 [2021-03-28 08:10:47 swin_base_patch4_window7_224] INFO: Epoch: [251] [1030/1251] eta: 0:02:20 lr: 0.000072 loss: 2.7953 (2.7458) grad_norm: 2.6665 (inf) time: 0.6265 [2021-03-28 08:10:53 swin_base_patch4_window7_224] INFO: Epoch: [251] [1040/1251] eta: 0:02:13 lr: 0.000072 loss: 2.7941 (2.7466) grad_norm: 2.5849 (inf) time: 0.6291 [2021-03-28 08:10:59 swin_base_patch4_window7_224] INFO: Epoch: [251] [1050/1251] eta: 0:02:07 lr: 0.000072 loss: 2.7805 (2.7459) grad_norm: 2.6638 (inf) time: 0.6287 [2021-03-28 08:11:06 swin_base_patch4_window7_224] INFO: Epoch: [251] [1060/1251] eta: 0:02:01 lr: 0.000072 loss: 2.9059 (2.7484) grad_norm: 2.8789 (inf) time: 0.6280 [2021-03-28 08:11:12 swin_base_patch4_window7_224] INFO: Epoch: [251] [1070/1251] eta: 0:01:54 lr: 0.000072 loss: 2.9059 (2.7478) grad_norm: 2.6135 (inf) time: 0.6251 [2021-03-28 08:11:18 swin_base_patch4_window7_224] INFO: Epoch: [251] [1080/1251] eta: 0:01:48 lr: 0.000072 loss: 2.8918 (2.7472) grad_norm: 2.6135 (inf) time: 0.6275 [2021-03-28 08:11:25 swin_base_patch4_window7_224] INFO: Epoch: [251] [1090/1251] eta: 0:01:42 lr: 0.000072 loss: 2.8770 (2.7485) grad_norm: 2.9428 (inf) time: 0.6356 [2021-03-28 08:11:31 swin_base_patch4_window7_224] INFO: Epoch: [251] [1100/1251] eta: 0:01:35 lr: 0.000072 loss: 2.9616 (2.7500) grad_norm: 2.6811 (inf) time: 0.6346 [2021-03-28 08:11:37 swin_base_patch4_window7_224] INFO: Epoch: [251] [1110/1251] eta: 0:01:29 lr: 0.000072 loss: 2.8572 (2.7504) grad_norm: 2.6085 (inf) time: 0.6291 [2021-03-28 08:11:43 swin_base_patch4_window7_224] INFO: Epoch: [251] [1120/1251] eta: 0:01:23 lr: 0.000071 loss: 2.9257 (2.7518) grad_norm: 2.9549 (inf) time: 0.6246 [2021-03-28 08:11:50 swin_base_patch4_window7_224] INFO: Epoch: [251] [1130/1251] eta: 0:01:16 lr: 0.000071 loss: 2.9257 (2.7516) grad_norm: 3.0205 (inf) time: 0.6274 [2021-03-28 08:11:56 swin_base_patch4_window7_224] INFO: Epoch: [251] [1140/1251] eta: 0:01:10 lr: 0.000071 loss: 2.8807 (2.7515) grad_norm: 3.0331 (inf) time: 0.6321 [2021-03-28 08:12:02 swin_base_patch4_window7_224] INFO: Epoch: [251] [1150/1251] eta: 0:01:04 lr: 0.000071 loss: 2.8349 (2.7520) grad_norm: 2.7265 (inf) time: 0.6274 [2021-03-28 08:12:09 swin_base_patch4_window7_224] INFO: Epoch: [251] [1160/1251] eta: 0:00:57 lr: 0.000071 loss: 2.8926 (2.7512) grad_norm: 2.6064 (inf) time: 0.6254 [2021-03-28 08:12:15 swin_base_patch4_window7_224] INFO: Epoch: [251] [1170/1251] eta: 0:00:51 lr: 0.000071 loss: 2.7698 (2.7502) grad_norm: 2.8186 (inf) time: 0.6267 [2021-03-28 08:12:21 swin_base_patch4_window7_224] INFO: Epoch: [251] [1180/1251] eta: 0:00:44 lr: 0.000071 loss: 2.5496 (2.7475) grad_norm: 2.8186 (inf) time: 0.6292 [2021-03-28 08:12:27 swin_base_patch4_window7_224] INFO: Epoch: [251] [1190/1251] eta: 0:00:38 lr: 0.000071 loss: 2.7117 (2.7476) grad_norm: 2.7976 (inf) time: 0.6294 [2021-03-28 08:12:34 swin_base_patch4_window7_224] INFO: Epoch: [251] [1200/1251] eta: 0:00:32 lr: 0.000071 loss: 2.8632 (2.7477) grad_norm: 2.6490 (inf) time: 0.6263 [2021-03-28 08:12:40 swin_base_patch4_window7_224] INFO: Epoch: [251] [1210/1251] eta: 0:00:25 lr: 0.000071 loss: 2.7544 (2.7452) grad_norm: 2.7364 (inf) time: 0.6230 [2021-03-28 08:12:46 swin_base_patch4_window7_224] INFO: Epoch: [251] [1220/1251] eta: 0:00:19 lr: 0.000071 loss: 2.7938 (2.7462) grad_norm: 2.8783 (inf) time: 0.6246 [2021-03-28 08:12:53 swin_base_patch4_window7_224] INFO: Epoch: [251] [1230/1251] eta: 0:00:13 lr: 0.000071 loss: 2.9473 (2.7459) grad_norm: 2.8783 (inf) time: 0.6294 [2021-03-28 08:12:59 swin_base_patch4_window7_224] INFO: Epoch: [251] [1240/1251] eta: 0:00:06 lr: 0.000071 loss: 2.3288 (2.7434) grad_norm: 2.9152 (inf) time: 0.6326 [2021-03-28 08:13:05 swin_base_patch4_window7_224] INFO: Epoch: [251] [1250/1251] eta: 0:00:00 lr: 0.000071 loss: 2.3554 (2.7437) grad_norm: 2.8879 (inf) time: 0.6297 [2021-03-28 08:13:16 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:14 loss: 0.7026 (0.7026) acc1: 81.2500 (81.2500) acc5: 98.4375 (98.4375) [2021-03-28 08:13:18 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7517 (0.8214) acc1: 81.2500 (80.5398) acc5: 96.8750 (96.3068) [2021-03-28 08:13:20 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7515 (0.8068) acc1: 79.6875 (80.2827) acc5: 96.8750 (96.5774) [2021-03-28 08:13:23 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6581 (0.7742) acc1: 81.2500 (81.3508) acc5: 96.8750 (96.6230) [2021-03-28 08:13:25 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7353 (0.7763) acc1: 82.8125 (81.4787) acc5: 96.8750 (96.6845) [2021-03-28 08:13:26 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7490 (0.7719) acc1: 82.8125 (81.6640) acc5: 96.8750 (96.7680) [2021-03-28 08:13:39 swin_base_patch4_window7_224] INFO: * Acc@1 82.834 Acc@5 96.328 loss 0.762 [2021-03-28 08:13:39 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.8% [2021-03-28 08:13:39 swin_base_patch4_window7_224] INFO: Max accuracy: 82.89% [2021-03-28 08:13:44 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 0/1251] eta: 1:39:33 lr: 0.000071 loss: 3.2637 (3.2637) grad_norm: 2.7116 (2.7116) time: 4.7750 [2021-03-28 08:13:51 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 10/1251] eta: 0:20:52 lr: 0.000071 loss: 3.0305 (2.6485) grad_norm: 2.9119 (3.3760) time: 1.0097 [2021-03-28 08:13:57 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 20/1251] eta: 0:17:00 lr: 0.000071 loss: 2.7039 (2.6707) grad_norm: 2.9507 (3.2157) time: 0.6314 [2021-03-28 08:14:03 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 30/1251] eta: 0:15:37 lr: 0.000071 loss: 2.7039 (2.6909) grad_norm: 2.9507 (3.1783) time: 0.6342 [2021-03-28 08:14:10 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 40/1251] eta: 0:14:47 lr: 0.000071 loss: 2.6983 (2.7004) grad_norm: 2.7638 (3.1012) time: 0.6321 [2021-03-28 08:14:16 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 50/1251] eta: 0:14:16 lr: 0.000071 loss: 2.6395 (2.6574) grad_norm: 2.7469 (3.1131) time: 0.6290 [2021-03-28 08:14:22 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 60/1251] eta: 0:13:53 lr: 0.000071 loss: 2.6978 (2.6646) grad_norm: 2.9020 (3.2135) time: 0.6319 [2021-03-28 08:14:28 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 70/1251] eta: 0:13:33 lr: 0.000071 loss: 2.6978 (2.6458) grad_norm: 3.0855 (3.2267) time: 0.6272 [2021-03-28 08:14:35 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 80/1251] eta: 0:13:19 lr: 0.000071 loss: 3.0247 (2.6968) grad_norm: 3.0302 (3.1751) time: 0.6308 [2021-03-28 08:14:41 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 90/1251] eta: 0:13:06 lr: 0.000071 loss: 3.0700 (2.7123) grad_norm: 2.7327 (3.1742) time: 0.6365 [2021-03-28 08:14:48 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 100/1251] eta: 0:12:54 lr: 0.000071 loss: 2.9462 (2.7377) grad_norm: 3.0390 (3.1888) time: 0.6344 [2021-03-28 08:14:54 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 110/1251] eta: 0:12:43 lr: 0.000071 loss: 2.9378 (2.7464) grad_norm: 3.0390 (3.1793) time: 0.6322 [2021-03-28 08:15:00 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 120/1251] eta: 0:12:33 lr: 0.000071 loss: 2.7387 (2.7542) grad_norm: 2.8162 (3.1657) time: 0.6340 [2021-03-28 08:15:06 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 130/1251] eta: 0:12:23 lr: 0.000071 loss: 2.7797 (2.7562) grad_norm: 2.6678 (3.1250) time: 0.6286 [2021-03-28 08:15:13 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 140/1251] eta: 0:12:14 lr: 0.000071 loss: 2.7684 (2.7510) grad_norm: 2.7098 (3.1508) time: 0.6267 [2021-03-28 08:15:19 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 150/1251] eta: 0:12:05 lr: 0.000071 loss: 2.6376 (2.7405) grad_norm: 2.7098 (3.1217) time: 0.6340 [2021-03-28 08:15:25 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 160/1251] eta: 0:11:57 lr: 0.000071 loss: 2.6575 (2.7422) grad_norm: 2.7529 (3.1252) time: 0.6344 [2021-03-28 08:15:32 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 170/1251] eta: 0:11:49 lr: 0.000071 loss: 2.9700 (2.7465) grad_norm: 2.9984 (3.1467) time: 0.6336 [2021-03-28 08:15:38 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 180/1251] eta: 0:11:41 lr: 0.000071 loss: 3.0132 (2.7649) grad_norm: 2.9984 (3.1542) time: 0.6355 [2021-03-28 08:15:44 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 190/1251] eta: 0:11:33 lr: 0.000071 loss: 3.0132 (2.7726) grad_norm: 2.9360 (3.1497) time: 0.6326 [2021-03-28 08:15:51 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 200/1251] eta: 0:11:26 lr: 0.000071 loss: 2.9563 (2.7788) grad_norm: 2.9134 (3.1409) time: 0.6317 [2021-03-28 08:15:57 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 210/1251] eta: 0:11:18 lr: 0.000071 loss: 2.9839 (2.7763) grad_norm: 2.8740 (3.1350) time: 0.6284 [2021-03-28 08:16:03 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 220/1251] eta: 0:11:10 lr: 0.000071 loss: 2.8883 (2.7759) grad_norm: 2.8740 (3.1423) time: 0.6246 [2021-03-28 08:16:10 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 230/1251] eta: 0:11:03 lr: 0.000071 loss: 2.8883 (2.7725) grad_norm: 2.8332 (3.1345) time: 0.6308 [2021-03-28 08:16:16 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 240/1251] eta: 0:10:55 lr: 0.000071 loss: 2.7343 (2.7662) grad_norm: 2.9833 (3.1394) time: 0.6310 [2021-03-28 08:16:22 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 250/1251] eta: 0:10:48 lr: 0.000071 loss: 2.6541 (2.7584) grad_norm: 2.9833 (3.1291) time: 0.6301 [2021-03-28 08:16:29 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 260/1251] eta: 0:10:41 lr: 0.000071 loss: 2.8025 (2.7642) grad_norm: 2.8084 (3.1162) time: 0.6311 [2021-03-28 08:16:35 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 270/1251] eta: 0:10:34 lr: 0.000071 loss: 2.9120 (2.7659) grad_norm: 2.8084 (3.1166) time: 0.6315 [2021-03-28 08:16:41 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 280/1251] eta: 0:10:27 lr: 0.000071 loss: 2.8977 (2.7652) grad_norm: 2.9047 (3.1157) time: 0.6295 [2021-03-28 08:16:47 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 290/1251] eta: 0:10:20 lr: 0.000071 loss: 2.8444 (2.7671) grad_norm: 2.8308 (3.1107) time: 0.6236 [2021-03-28 08:16:54 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 300/1251] eta: 0:10:13 lr: 0.000071 loss: 2.8977 (2.7695) grad_norm: 2.8731 (3.1145) time: 0.6284 [2021-03-28 08:17:00 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 310/1251] eta: 0:10:06 lr: 0.000071 loss: 2.9576 (2.7734) grad_norm: 2.7688 (3.1022) time: 0.6366 [2021-03-28 08:17:06 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 320/1251] eta: 0:09:59 lr: 0.000071 loss: 2.9657 (2.7769) grad_norm: 2.7688 (3.1009) time: 0.6292 [2021-03-28 08:17:13 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 330/1251] eta: 0:09:52 lr: 0.000071 loss: 2.7851 (2.7718) grad_norm: 2.9643 (3.0981) time: 0.6261 [2021-03-28 08:17:19 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 340/1251] eta: 0:09:45 lr: 0.000071 loss: 2.7717 (2.7734) grad_norm: 2.9750 (3.0961) time: 0.6268 [2021-03-28 08:17:25 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 350/1251] eta: 0:09:38 lr: 0.000071 loss: 2.8187 (2.7749) grad_norm: 2.8788 (3.0900) time: 0.6264 [2021-03-28 08:17:31 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 360/1251] eta: 0:09:32 lr: 0.000071 loss: 2.7152 (2.7724) grad_norm: 2.8378 (3.0936) time: 0.6277 [2021-03-28 08:17:38 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 370/1251] eta: 0:09:25 lr: 0.000070 loss: 2.7152 (2.7661) grad_norm: 2.9216 (3.0990) time: 0.6272 [2021-03-28 08:17:44 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 380/1251] eta: 0:09:18 lr: 0.000070 loss: 2.5803 (2.7645) grad_norm: 3.0007 (3.1030) time: 0.6290 [2021-03-28 08:17:50 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 390/1251] eta: 0:09:12 lr: 0.000070 loss: 2.8659 (2.7683) grad_norm: 2.8830 (3.0935) time: 0.6312 [2021-03-28 08:17:57 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 400/1251] eta: 0:09:05 lr: 0.000070 loss: 3.0298 (2.7715) grad_norm: 2.6548 (3.0831) time: 0.6303 [2021-03-28 08:18:03 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 410/1251] eta: 0:08:58 lr: 0.000070 loss: 2.7429 (2.7629) grad_norm: 2.6839 (3.0826) time: 0.6241 [2021-03-28 08:18:09 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 420/1251] eta: 0:08:51 lr: 0.000070 loss: 2.7429 (2.7665) grad_norm: 2.8200 (3.0868) time: 0.6231 [2021-03-28 08:18:15 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 430/1251] eta: 0:08:45 lr: 0.000070 loss: 2.9830 (2.7682) grad_norm: 3.0613 (3.0933) time: 0.6247 [2021-03-28 08:18:22 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 440/1251] eta: 0:08:38 lr: 0.000070 loss: 2.7892 (2.7680) grad_norm: 3.1213 (3.0963) time: 0.6236 [2021-03-28 08:18:28 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 450/1251] eta: 0:08:31 lr: 0.000070 loss: 2.7768 (2.7692) grad_norm: 3.0592 (3.0962) time: 0.6246 [2021-03-28 08:18:34 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 460/1251] eta: 0:08:25 lr: 0.000070 loss: 2.5586 (2.7659) grad_norm: 2.8005 (3.1125) time: 0.6255 [2021-03-28 08:18:40 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 470/1251] eta: 0:08:18 lr: 0.000070 loss: 2.6630 (2.7667) grad_norm: 2.6975 (3.1162) time: 0.6254 [2021-03-28 08:18:47 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 480/1251] eta: 0:08:12 lr: 0.000070 loss: 2.7373 (2.7653) grad_norm: 2.9128 (3.1196) time: 0.6271 [2021-03-28 08:18:53 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 490/1251] eta: 0:08:05 lr: 0.000070 loss: 2.6768 (2.7626) grad_norm: 2.7725 (3.1162) time: 0.6317 [2021-03-28 08:18:59 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 500/1251] eta: 0:07:59 lr: 0.000070 loss: 2.7435 (2.7641) grad_norm: 2.7725 (3.1192) time: 0.6315 [2021-03-28 08:19:05 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 510/1251] eta: 0:07:52 lr: 0.000070 loss: 2.9327 (2.7679) grad_norm: 2.8706 (3.1155) time: 0.6286 [2021-03-28 08:19:12 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 520/1251] eta: 0:07:46 lr: 0.000070 loss: 2.9786 (2.7710) grad_norm: 2.8463 (3.1102) time: 0.6290 [2021-03-28 08:19:18 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 530/1251] eta: 0:07:39 lr: 0.000070 loss: 2.7637 (2.7668) grad_norm: 2.7581 (3.1071) time: 0.6270 [2021-03-28 08:19:24 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 540/1251] eta: 0:07:33 lr: 0.000070 loss: 2.4531 (2.7620) grad_norm: 2.7536 (3.1012) time: 0.6299 [2021-03-28 08:19:31 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 550/1251] eta: 0:07:26 lr: 0.000070 loss: 2.8426 (2.7655) grad_norm: 2.9501 (3.1063) time: 0.6414 [2021-03-28 08:19:37 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 560/1251] eta: 0:07:20 lr: 0.000070 loss: 2.8595 (2.7620) grad_norm: 3.0366 (3.1104) time: 0.6457 [2021-03-28 08:19:44 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 570/1251] eta: 0:07:14 lr: 0.000070 loss: 2.8037 (2.7626) grad_norm: 2.8009 (3.1047) time: 0.6365 [2021-03-28 08:19:50 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 580/1251] eta: 0:07:07 lr: 0.000070 loss: 2.9752 (2.7633) grad_norm: 2.8716 (3.1078) time: 0.6362 [2021-03-28 08:19:56 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 590/1251] eta: 0:07:01 lr: 0.000070 loss: 2.9149 (2.7608) grad_norm: 2.7984 (3.1024) time: 0.6356 [2021-03-28 08:20:03 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 600/1251] eta: 0:06:54 lr: 0.000070 loss: 2.7501 (2.7595) grad_norm: 2.7883 (3.1061) time: 0.6294 [2021-03-28 08:20:09 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 610/1251] eta: 0:06:48 lr: 0.000070 loss: 2.7612 (2.7604) grad_norm: 2.8538 (3.1113) time: 0.6311 [2021-03-28 08:20:15 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 620/1251] eta: 0:06:41 lr: 0.000070 loss: 2.5599 (2.7567) grad_norm: 2.8502 (3.1113) time: 0.6271 [2021-03-28 08:20:21 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 630/1251] eta: 0:06:35 lr: 0.000070 loss: 2.4483 (2.7537) grad_norm: 2.8120 (3.1049) time: 0.6281 [2021-03-28 08:20:28 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 640/1251] eta: 0:06:29 lr: 0.000070 loss: 2.8915 (2.7567) grad_norm: 2.6837 (3.0965) time: 0.6324 [2021-03-28 08:20:34 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 650/1251] eta: 0:06:22 lr: 0.000070 loss: 2.9057 (2.7578) grad_norm: 2.7190 (3.0988) time: 0.6352 [2021-03-28 08:20:40 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 660/1251] eta: 0:06:16 lr: 0.000070 loss: 2.7808 (2.7559) grad_norm: 2.7282 (3.0928) time: 0.6314 [2021-03-28 08:20:47 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 670/1251] eta: 0:06:09 lr: 0.000070 loss: 2.8087 (2.7565) grad_norm: 2.6201 (3.0872) time: 0.6267 [2021-03-28 08:20:53 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 680/1251] eta: 0:06:03 lr: 0.000070 loss: 2.8087 (2.7547) grad_norm: 2.6697 (3.0831) time: 0.6248 [2021-03-28 08:20:59 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 690/1251] eta: 0:05:56 lr: 0.000070 loss: 2.7112 (2.7539) grad_norm: 2.7971 (3.0830) time: 0.6216 [2021-03-28 08:21:06 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 700/1251] eta: 0:05:50 lr: 0.000070 loss: 2.6753 (2.7527) grad_norm: 2.9018 (3.0876) time: 0.6283 [2021-03-28 08:21:12 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 710/1251] eta: 0:05:44 lr: 0.000070 loss: 2.6753 (2.7550) grad_norm: 2.7685 (3.0816) time: 0.6318 [2021-03-28 08:21:18 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 720/1251] eta: 0:05:37 lr: 0.000070 loss: 2.8466 (2.7562) grad_norm: 2.8016 (3.0805) time: 0.6315 [2021-03-28 08:21:25 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 730/1251] eta: 0:05:31 lr: 0.000070 loss: 2.6585 (2.7530) grad_norm: 2.8501 (3.0822) time: 0.6383 [2021-03-28 08:21:31 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 740/1251] eta: 0:05:24 lr: 0.000070 loss: 2.7415 (2.7544) grad_norm: 2.9857 (3.0829) time: 0.6376 [2021-03-28 08:21:37 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 750/1251] eta: 0:05:18 lr: 0.000070 loss: 3.0084 (2.7571) grad_norm: 2.9747 (3.1002) time: 0.6360 [2021-03-28 08:21:44 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 760/1251] eta: 0:05:12 lr: 0.000070 loss: 2.9212 (2.7555) grad_norm: 2.9529 (3.0986) time: 0.6310 [2021-03-28 08:21:50 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 770/1251] eta: 0:05:05 lr: 0.000070 loss: 2.9581 (2.7599) grad_norm: 2.8581 (3.0943) time: 0.6277 [2021-03-28 08:21:56 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 780/1251] eta: 0:04:59 lr: 0.000070 loss: 3.1664 (2.7637) grad_norm: 2.7454 (3.0892) time: 0.6365 [2021-03-28 08:22:03 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 790/1251] eta: 0:04:53 lr: 0.000070 loss: 2.8377 (2.7612) grad_norm: 2.7416 (3.0848) time: 0.6333 [2021-03-28 08:22:09 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 800/1251] eta: 0:04:46 lr: 0.000070 loss: 2.6396 (2.7615) grad_norm: 2.7129 (3.0822) time: 0.6305 [2021-03-28 08:22:15 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 810/1251] eta: 0:04:40 lr: 0.000070 loss: 2.8091 (2.7630) grad_norm: 2.6224 (3.0814) time: 0.6302 [2021-03-28 08:22:21 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 820/1251] eta: 0:04:33 lr: 0.000070 loss: 2.7648 (2.7618) grad_norm: 2.5905 (3.0774) time: 0.6284 [2021-03-28 08:22:28 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 830/1251] eta: 0:04:27 lr: 0.000070 loss: 2.7483 (2.7643) grad_norm: 2.5905 (3.0739) time: 0.6290 [2021-03-28 08:22:34 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 840/1251] eta: 0:04:21 lr: 0.000070 loss: 3.1125 (2.7668) grad_norm: 2.9234 (3.0739) time: 0.6354 [2021-03-28 08:22:40 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 850/1251] eta: 0:04:14 lr: 0.000070 loss: 2.9578 (2.7675) grad_norm: 2.8836 (3.0757) time: 0.6377 [2021-03-28 08:22:47 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 860/1251] eta: 0:04:08 lr: 0.000070 loss: 2.8724 (2.7691) grad_norm: 2.7595 (3.0729) time: 0.6291 [2021-03-28 08:22:53 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 870/1251] eta: 0:04:02 lr: 0.000070 loss: 2.8393 (2.7699) grad_norm: 2.7831 (3.0720) time: 0.6318 [2021-03-28 08:22:59 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 880/1251] eta: 0:03:55 lr: 0.000069 loss: 2.8332 (2.7691) grad_norm: 2.8440 (3.0744) time: 0.6356 [2021-03-28 08:23:06 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 890/1251] eta: 0:03:49 lr: 0.000069 loss: 2.7794 (2.7666) grad_norm: 2.8778 (3.0793) time: 0.6335 [2021-03-28 08:23:12 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 900/1251] eta: 0:03:43 lr: 0.000069 loss: 2.9520 (2.7693) grad_norm: 3.0496 (3.0780) time: 0.6318 [2021-03-28 08:23:18 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 910/1251] eta: 0:03:36 lr: 0.000069 loss: 2.8184 (2.7675) grad_norm: 2.9824 (3.0759) time: 0.6305 [2021-03-28 08:23:25 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 920/1251] eta: 0:03:30 lr: 0.000069 loss: 2.7526 (2.7682) grad_norm: 2.8671 (3.0751) time: 0.6322 [2021-03-28 08:23:31 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 930/1251] eta: 0:03:23 lr: 0.000069 loss: 2.8092 (2.7671) grad_norm: 2.9508 (3.0730) time: 0.6342 [2021-03-28 08:23:37 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 940/1251] eta: 0:03:17 lr: 0.000069 loss: 2.8092 (2.7658) grad_norm: 2.7170 (3.0696) time: 0.6319 [2021-03-28 08:23:44 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 950/1251] eta: 0:03:11 lr: 0.000069 loss: 2.7341 (2.7657) grad_norm: 2.6409 (3.0668) time: 0.6287 [2021-03-28 08:23:50 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 960/1251] eta: 0:03:04 lr: 0.000069 loss: 2.7907 (2.7670) grad_norm: 3.0074 (3.0721) time: 0.6255 [2021-03-28 08:23:56 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 970/1251] eta: 0:02:58 lr: 0.000069 loss: 2.8558 (2.7672) grad_norm: 2.9502 (3.0702) time: 0.6243 [2021-03-28 08:24:02 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 980/1251] eta: 0:02:52 lr: 0.000069 loss: 2.8483 (2.7679) grad_norm: 2.7373 (3.0690) time: 0.6295 [2021-03-28 08:24:09 swin_base_patch4_window7_224] INFO: Epoch: [252] [ 990/1251] eta: 0:02:45 lr: 0.000069 loss: 2.8373 (2.7678) grad_norm: 2.6295 (3.0653) time: 0.6312 [2021-03-28 08:24:15 swin_base_patch4_window7_224] INFO: Epoch: [252] [1000/1251] eta: 0:02:39 lr: 0.000069 loss: 2.7516 (2.7657) grad_norm: 2.6251 (3.0619) time: 0.6313 [2021-03-28 08:24:21 swin_base_patch4_window7_224] INFO: Epoch: [252] [1010/1251] eta: 0:02:32 lr: 0.000069 loss: 2.7040 (2.7636) grad_norm: 2.7213 (3.0613) time: 0.6283 [2021-03-28 08:24:28 swin_base_patch4_window7_224] INFO: Epoch: [252] [1020/1251] eta: 0:02:26 lr: 0.000069 loss: 2.8108 (2.7663) grad_norm: 2.7475 (3.0586) time: 0.6236 [2021-03-28 08:24:34 swin_base_patch4_window7_224] INFO: Epoch: [252] [1030/1251] eta: 0:02:20 lr: 0.000069 loss: 2.8768 (2.7669) grad_norm: 2.6448 (3.0562) time: 0.6274 [2021-03-28 08:24:40 swin_base_patch4_window7_224] INFO: Epoch: [252] [1040/1251] eta: 0:02:13 lr: 0.000069 loss: 2.8178 (2.7658) grad_norm: 2.7417 (3.0540) time: 0.6281 [2021-03-28 08:24:46 swin_base_patch4_window7_224] INFO: Epoch: [252] [1050/1251] eta: 0:02:07 lr: 0.000069 loss: 2.8178 (2.7666) grad_norm: 2.8390 (3.0564) time: 0.6267 [2021-03-28 08:24:53 swin_base_patch4_window7_224] INFO: Epoch: [252] [1060/1251] eta: 0:02:01 lr: 0.000069 loss: 2.8800 (2.7656) grad_norm: 2.7741 (3.0587) time: 0.6309 [2021-03-28 08:24:59 swin_base_patch4_window7_224] INFO: Epoch: [252] [1070/1251] eta: 0:01:54 lr: 0.000069 loss: 2.9207 (2.7673) grad_norm: 2.7464 (3.0623) time: 0.6352 [2021-03-28 08:25:06 swin_base_patch4_window7_224] INFO: Epoch: [252] [1080/1251] eta: 0:01:48 lr: 0.000069 loss: 2.8600 (2.7660) grad_norm: 2.6766 (3.0666) time: 0.6364 [2021-03-28 08:25:12 swin_base_patch4_window7_224] INFO: Epoch: [252] [1090/1251] eta: 0:01:42 lr: 0.000069 loss: 2.8600 (2.7680) grad_norm: 2.6502 (3.0637) time: 0.6309 [2021-03-28 08:25:18 swin_base_patch4_window7_224] INFO: Epoch: [252] [1100/1251] eta: 0:01:35 lr: 0.000069 loss: 2.9087 (2.7684) grad_norm: 2.7903 (3.0643) time: 0.6264 [2021-03-28 08:25:24 swin_base_patch4_window7_224] INFO: Epoch: [252] [1110/1251] eta: 0:01:29 lr: 0.000069 loss: 2.6646 (2.7670) grad_norm: 3.0666 (3.0661) time: 0.6261 [2021-03-28 08:25:31 swin_base_patch4_window7_224] INFO: Epoch: [252] [1120/1251] eta: 0:01:23 lr: 0.000069 loss: 2.6963 (2.7665) grad_norm: 2.9554 (3.0659) time: 0.6261 [2021-03-28 08:25:37 swin_base_patch4_window7_224] INFO: Epoch: [252] [1130/1251] eta: 0:01:16 lr: 0.000069 loss: 2.9709 (2.7676) grad_norm: 2.7297 (3.0639) time: 0.6325 [2021-03-28 08:25:43 swin_base_patch4_window7_224] INFO: Epoch: [252] [1140/1251] eta: 0:01:10 lr: 0.000069 loss: 2.9612 (2.7682) grad_norm: 2.7773 (3.0619) time: 0.6380 [2021-03-28 08:25:50 swin_base_patch4_window7_224] INFO: Epoch: [252] [1150/1251] eta: 0:01:04 lr: 0.000069 loss: 2.8734 (2.7685) grad_norm: 2.7773 (3.0594) time: 0.6311 [2021-03-28 08:25:56 swin_base_patch4_window7_224] INFO: Epoch: [252] [1160/1251] eta: 0:00:57 lr: 0.000069 loss: 2.8318 (2.7683) grad_norm: 2.7598 (3.0581) time: 0.6284 [2021-03-28 08:26:02 swin_base_patch4_window7_224] INFO: Epoch: [252] [1170/1251] eta: 0:00:51 lr: 0.000069 loss: 2.7452 (2.7675) grad_norm: 2.8185 (3.0575) time: 0.6303 [2021-03-28 08:26:08 swin_base_patch4_window7_224] INFO: Epoch: [252] [1180/1251] eta: 0:00:45 lr: 0.000069 loss: 2.8351 (2.7683) grad_norm: 2.8185 (inf) time: 0.6239 [2021-03-28 08:26:15 swin_base_patch4_window7_224] INFO: Epoch: [252] [1190/1251] eta: 0:00:38 lr: 0.000069 loss: 2.8538 (2.7680) grad_norm: 2.6933 (inf) time: 0.6269 [2021-03-28 08:26:21 swin_base_patch4_window7_224] INFO: Epoch: [252] [1200/1251] eta: 0:00:32 lr: 0.000069 loss: 2.7824 (2.7689) grad_norm: 2.6156 (inf) time: 0.6301 [2021-03-28 08:26:27 swin_base_patch4_window7_224] INFO: Epoch: [252] [1210/1251] eta: 0:00:25 lr: 0.000069 loss: 2.6535 (2.7650) grad_norm: 3.0470 (inf) time: 0.6284 [2021-03-28 08:26:34 swin_base_patch4_window7_224] INFO: Epoch: [252] [1220/1251] eta: 0:00:19 lr: 0.000069 loss: 2.4476 (2.7648) grad_norm: 2.9560 (inf) time: 0.6281 [2021-03-28 08:26:40 swin_base_patch4_window7_224] INFO: Epoch: [252] [1230/1251] eta: 0:00:13 lr: 0.000069 loss: 2.8438 (2.7645) grad_norm: 2.8028 (inf) time: 0.6241 [2021-03-28 08:26:46 swin_base_patch4_window7_224] INFO: Epoch: [252] [1240/1251] eta: 0:00:06 lr: 0.000069 loss: 2.9500 (2.7654) grad_norm: 2.9192 (inf) time: 0.6249 [2021-03-28 08:26:52 swin_base_patch4_window7_224] INFO: Epoch: [252] [1250/1251] eta: 0:00:00 lr: 0.000069 loss: 2.9500 (2.7662) grad_norm: 2.9055 (inf) time: 0.6303 [2021-03-28 08:27:06 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:22 loss: 0.3734 (0.3734) acc1: 92.1875 (92.1875) acc5: 98.4375 (98.4375) [2021-03-28 08:27:08 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.6860 (0.6934) acc1: 82.8125 (84.6591) acc5: 96.8750 (96.3068) [2021-03-28 08:27:12 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:12 loss: 0.6860 (0.7159) acc1: 81.2500 (83.4077) acc5: 95.3125 (96.2054) [2021-03-28 08:27:14 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7846 (0.7242) acc1: 79.6875 (82.6109) acc5: 96.8750 (96.5222) [2021-03-28 08:27:15 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8011 (0.7525) acc1: 79.6875 (81.9360) acc5: 96.8750 (96.3034) [2021-03-28 08:27:16 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8253 (0.7596) acc1: 79.6875 (81.7920) acc5: 96.8750 (96.3840) [2021-03-28 08:27:33 swin_base_patch4_window7_224] INFO: * Acc@1 82.904 Acc@5 96.282 loss 0.751 [2021-03-28 08:27:33 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.9% [2021-03-28 08:27:33 swin_base_patch4_window7_224] INFO: Max accuracy: 82.90% [2021-03-28 08:27:37 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 0/1251] eta: 1:32:13 lr: 0.000069 loss: 3.1595 (3.1595) grad_norm: 3.2245 (3.2245) time: 4.4234 [2021-03-28 08:27:43 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 10/1251] eta: 0:20:09 lr: 0.000069 loss: 2.6484 (2.6405) grad_norm: 2.6424 (2.9037) time: 0.9744 [2021-03-28 08:27:50 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 20/1251] eta: 0:16:36 lr: 0.000069 loss: 2.6584 (2.6955) grad_norm: 2.7748 (2.9393) time: 0.6285 [2021-03-28 08:27:56 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 30/1251] eta: 0:15:15 lr: 0.000069 loss: 2.8701 (2.7796) grad_norm: 2.7748 (2.8878) time: 0.6261 [2021-03-28 08:28:02 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 40/1251] eta: 0:14:33 lr: 0.000069 loss: 3.0388 (2.7717) grad_norm: 2.7404 (2.8930) time: 0.6294 [2021-03-28 08:28:09 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 50/1251] eta: 0:14:07 lr: 0.000069 loss: 2.7317 (2.7393) grad_norm: 2.8553 (2.9281) time: 0.6371 [2021-03-28 08:28:15 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 60/1251] eta: 0:13:47 lr: 0.000069 loss: 2.7573 (2.7702) grad_norm: 2.9625 (2.9254) time: 0.6391 [2021-03-28 08:28:21 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 70/1251] eta: 0:13:29 lr: 0.000069 loss: 2.9643 (2.7561) grad_norm: 2.9613 (2.9327) time: 0.6341 [2021-03-28 08:28:28 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 80/1251] eta: 0:13:14 lr: 0.000069 loss: 2.6730 (2.7290) grad_norm: 2.8936 (2.9331) time: 0.6289 [2021-03-28 08:28:34 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 90/1251] eta: 0:13:02 lr: 0.000069 loss: 2.8280 (2.7226) grad_norm: 2.8534 (2.9122) time: 0.6315 [2021-03-28 08:28:40 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 100/1251] eta: 0:12:50 lr: 0.000069 loss: 2.8280 (2.7219) grad_norm: 2.6804 (2.9203) time: 0.6352 [2021-03-28 08:28:47 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 110/1251] eta: 0:12:40 lr: 0.000069 loss: 3.0355 (2.7326) grad_norm: 2.6085 (2.9205) time: 0.6328 [2021-03-28 08:28:53 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 120/1251] eta: 0:12:30 lr: 0.000069 loss: 2.8808 (2.7235) grad_norm: 2.5954 (2.9053) time: 0.6330 [2021-03-28 08:28:59 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 130/1251] eta: 0:12:20 lr: 0.000069 loss: 2.8808 (2.7306) grad_norm: 2.8491 (2.9205) time: 0.6288 [2021-03-28 08:29:06 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 140/1251] eta: 0:12:11 lr: 0.000068 loss: 2.9359 (2.7357) grad_norm: 2.8536 (2.9179) time: 0.6287 [2021-03-28 08:29:12 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 150/1251] eta: 0:12:03 lr: 0.000068 loss: 2.8505 (2.7336) grad_norm: 2.6879 (2.9287) time: 0.6360 [2021-03-28 08:29:18 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 160/1251] eta: 0:11:55 lr: 0.000068 loss: 2.8582 (2.7372) grad_norm: 2.8818 (2.9326) time: 0.6368 [2021-03-28 08:29:25 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 170/1251] eta: 0:11:47 lr: 0.000068 loss: 2.7817 (2.7394) grad_norm: 2.6849 (2.9256) time: 0.6327 [2021-03-28 08:29:31 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 180/1251] eta: 0:11:39 lr: 0.000068 loss: 2.7817 (2.7386) grad_norm: 2.6849 (2.9178) time: 0.6329 [2021-03-28 08:29:37 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 190/1251] eta: 0:11:32 lr: 0.000068 loss: 2.9901 (2.7480) grad_norm: 2.7220 (2.9109) time: 0.6352 [2021-03-28 08:29:44 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 200/1251] eta: 0:11:24 lr: 0.000068 loss: 2.7627 (2.7354) grad_norm: 2.6646 (2.9032) time: 0.6316 [2021-03-28 08:29:50 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 210/1251] eta: 0:11:16 lr: 0.000068 loss: 2.6482 (2.7374) grad_norm: 2.6136 (2.9023) time: 0.6275 [2021-03-28 08:29:56 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 220/1251] eta: 0:11:09 lr: 0.000068 loss: 2.9677 (2.7385) grad_norm: 2.6829 (2.9066) time: 0.6263 [2021-03-28 08:30:02 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 230/1251] eta: 0:11:02 lr: 0.000068 loss: 2.9677 (2.7412) grad_norm: 2.6329 (2.9130) time: 0.6314 [2021-03-28 08:30:09 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 240/1251] eta: 0:10:54 lr: 0.000068 loss: 2.8067 (2.7422) grad_norm: 2.6326 (2.9092) time: 0.6342 [2021-03-28 08:30:15 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 250/1251] eta: 0:10:47 lr: 0.000068 loss: 2.7608 (2.7334) grad_norm: 2.6326 (2.8991) time: 0.6330 [2021-03-28 08:30:21 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 260/1251] eta: 0:10:40 lr: 0.000068 loss: 2.8697 (2.7417) grad_norm: 2.6233 (2.8930) time: 0.6328 [2021-03-28 08:30:28 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 270/1251] eta: 0:10:33 lr: 0.000068 loss: 3.0012 (2.7516) grad_norm: 2.6735 (2.8968) time: 0.6295 [2021-03-28 08:30:34 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 280/1251] eta: 0:10:26 lr: 0.000068 loss: 2.8208 (2.7453) grad_norm: 2.7347 (2.8988) time: 0.6291 [2021-03-28 08:30:40 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 290/1251] eta: 0:10:19 lr: 0.000068 loss: 2.7184 (2.7459) grad_norm: 2.6725 (2.8972) time: 0.6292 [2021-03-28 08:30:47 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 300/1251] eta: 0:10:12 lr: 0.000068 loss: 2.8756 (2.7525) grad_norm: 2.7245 (2.9042) time: 0.6247 [2021-03-28 08:30:53 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 310/1251] eta: 0:10:05 lr: 0.000068 loss: 2.9350 (2.7500) grad_norm: 2.9724 (2.9204) time: 0.6241 [2021-03-28 08:30:59 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 320/1251] eta: 0:09:58 lr: 0.000068 loss: 2.9454 (2.7570) grad_norm: 2.9724 (2.9222) time: 0.6285 [2021-03-28 08:31:06 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 330/1251] eta: 0:09:52 lr: 0.000068 loss: 2.6706 (2.7503) grad_norm: 2.9256 (2.9434) time: 0.6373 [2021-03-28 08:31:12 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 340/1251] eta: 0:09:45 lr: 0.000068 loss: 2.6635 (2.7535) grad_norm: 2.7873 (2.9468) time: 0.6376 [2021-03-28 08:31:18 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 350/1251] eta: 0:09:38 lr: 0.000068 loss: 2.8414 (2.7514) grad_norm: 2.7448 (2.9489) time: 0.6278 [2021-03-28 08:31:24 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 360/1251] eta: 0:09:31 lr: 0.000068 loss: 2.9166 (2.7594) grad_norm: 2.7435 (2.9407) time: 0.6281 [2021-03-28 08:31:31 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 370/1251] eta: 0:09:25 lr: 0.000068 loss: 3.0728 (2.7623) grad_norm: 2.6715 (2.9427) time: 0.6321 [2021-03-28 08:31:37 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 380/1251] eta: 0:09:18 lr: 0.000068 loss: 2.9418 (2.7617) grad_norm: 2.7064 (2.9392) time: 0.6308 [2021-03-28 08:31:43 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 390/1251] eta: 0:09:11 lr: 0.000068 loss: 2.8065 (2.7612) grad_norm: 2.8543 (2.9549) time: 0.6290 [2021-03-28 08:31:50 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 400/1251] eta: 0:09:05 lr: 0.000068 loss: 2.6368 (2.7588) grad_norm: 3.0044 (2.9595) time: 0.6294 [2021-03-28 08:31:56 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 410/1251] eta: 0:08:58 lr: 0.000068 loss: 2.8327 (2.7606) grad_norm: 2.9160 (2.9954) time: 0.6250 [2021-03-28 08:32:02 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 420/1251] eta: 0:08:51 lr: 0.000068 loss: 2.8764 (2.7624) grad_norm: 2.8873 (2.9954) time: 0.6286 [2021-03-28 08:32:09 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 430/1251] eta: 0:08:45 lr: 0.000068 loss: 2.8764 (2.7613) grad_norm: 2.8346 (2.9969) time: 0.6370 [2021-03-28 08:32:15 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 440/1251] eta: 0:08:38 lr: 0.000068 loss: 2.7208 (2.7598) grad_norm: 3.1940 (3.0144) time: 0.6355 [2021-03-28 08:32:21 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 450/1251] eta: 0:08:32 lr: 0.000068 loss: 2.8398 (2.7625) grad_norm: 2.8114 (3.0078) time: 0.6322 [2021-03-28 08:32:27 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 460/1251] eta: 0:08:25 lr: 0.000068 loss: 2.9104 (2.7632) grad_norm: 2.6956 (3.0044) time: 0.6241 [2021-03-28 08:32:34 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 470/1251] eta: 0:08:19 lr: 0.000068 loss: 2.8902 (2.7645) grad_norm: 2.7388 (3.0011) time: 0.6245 [2021-03-28 08:32:40 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 480/1251] eta: 0:08:12 lr: 0.000068 loss: 2.7504 (2.7630) grad_norm: 2.6998 (2.9969) time: 0.6263 [2021-03-28 08:32:46 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 490/1251] eta: 0:08:06 lr: 0.000068 loss: 2.7257 (2.7651) grad_norm: 2.7867 (2.9952) time: 0.6290 [2021-03-28 08:32:53 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 500/1251] eta: 0:07:59 lr: 0.000068 loss: 2.8028 (2.7655) grad_norm: 3.0479 (3.0031) time: 0.6317 [2021-03-28 08:32:59 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 510/1251] eta: 0:07:52 lr: 0.000068 loss: 2.8565 (2.7676) grad_norm: 3.0676 (3.0016) time: 0.6233 [2021-03-28 08:33:05 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 520/1251] eta: 0:07:46 lr: 0.000068 loss: 3.0015 (2.7692) grad_norm: 2.8172 (3.0053) time: 0.6292 [2021-03-28 08:33:11 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 530/1251] eta: 0:07:39 lr: 0.000068 loss: 2.7859 (2.7663) grad_norm: 2.8504 (3.0062) time: 0.6351 [2021-03-28 08:33:18 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 540/1251] eta: 0:07:33 lr: 0.000068 loss: 2.7764 (2.7649) grad_norm: 3.0782 (3.0384) time: 0.6276 [2021-03-28 08:33:24 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 550/1251] eta: 0:07:27 lr: 0.000068 loss: 2.8934 (2.7687) grad_norm: 2.9508 (3.0418) time: 0.6362 [2021-03-28 08:33:30 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 560/1251] eta: 0:07:20 lr: 0.000068 loss: 2.9922 (2.7707) grad_norm: 2.9837 (3.0553) time: 0.6361 [2021-03-28 08:33:37 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 570/1251] eta: 0:07:14 lr: 0.000068 loss: 3.0096 (2.7729) grad_norm: 3.0255 (3.0547) time: 0.6271 [2021-03-28 08:33:43 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 580/1251] eta: 0:07:07 lr: 0.000068 loss: 3.0096 (2.7749) grad_norm: 2.8262 (3.0531) time: 0.6252 [2021-03-28 08:33:49 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 590/1251] eta: 0:07:01 lr: 0.000068 loss: 2.9848 (2.7767) grad_norm: 2.8141 (3.0518) time: 0.6262 [2021-03-28 08:33:56 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 600/1251] eta: 0:06:54 lr: 0.000068 loss: 2.9848 (2.7768) grad_norm: 2.8141 (3.0509) time: 0.6288 [2021-03-28 08:34:02 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 610/1251] eta: 0:06:48 lr: 0.000068 loss: 2.7579 (2.7752) grad_norm: 2.7796 (3.0490) time: 0.6369 [2021-03-28 08:34:08 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 620/1251] eta: 0:06:41 lr: 0.000068 loss: 2.6779 (2.7752) grad_norm: 2.8948 (3.0517) time: 0.6380 [2021-03-28 08:34:15 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 630/1251] eta: 0:06:35 lr: 0.000068 loss: 2.8228 (2.7766) grad_norm: 2.9343 (3.0491) time: 0.6313 [2021-03-28 08:34:21 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 640/1251] eta: 0:06:29 lr: 0.000068 loss: 2.9611 (2.7785) grad_norm: 2.7424 (3.0491) time: 0.6368 [2021-03-28 08:34:27 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 650/1251] eta: 0:06:22 lr: 0.000067 loss: 2.8696 (2.7761) grad_norm: 2.9506 (3.0495) time: 0.6389 [2021-03-28 08:34:34 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 660/1251] eta: 0:06:16 lr: 0.000067 loss: 2.8368 (2.7771) grad_norm: 2.7336 (3.0471) time: 0.6385 [2021-03-28 08:34:40 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 670/1251] eta: 0:06:10 lr: 0.000067 loss: 2.9257 (2.7779) grad_norm: 2.6508 (3.0444) time: 0.6339 [2021-03-28 08:34:46 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 680/1251] eta: 0:06:03 lr: 0.000067 loss: 3.0321 (2.7811) grad_norm: 2.8488 (3.0461) time: 0.6326 [2021-03-28 08:34:53 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 690/1251] eta: 0:05:57 lr: 0.000067 loss: 2.8672 (2.7810) grad_norm: 2.8987 (3.0486) time: 0.6374 [2021-03-28 08:34:59 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 700/1251] eta: 0:05:50 lr: 0.000067 loss: 2.8668 (2.7821) grad_norm: 2.8266 (3.0473) time: 0.6411 [2021-03-28 08:35:06 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 710/1251] eta: 0:05:44 lr: 0.000067 loss: 2.9274 (2.7807) grad_norm: 2.8332 (3.0463) time: 0.6347 [2021-03-28 08:35:12 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 720/1251] eta: 0:05:38 lr: 0.000067 loss: 2.8204 (2.7794) grad_norm: 2.7490 (3.0445) time: 0.6259 [2021-03-28 08:35:18 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 730/1251] eta: 0:05:31 lr: 0.000067 loss: 2.8204 (2.7778) grad_norm: 2.7490 (3.0413) time: 0.6300 [2021-03-28 08:35:25 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 740/1251] eta: 0:05:25 lr: 0.000067 loss: 2.8363 (2.7762) grad_norm: 2.7812 (3.0398) time: 0.6355 [2021-03-28 08:35:31 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 750/1251] eta: 0:05:18 lr: 0.000067 loss: 2.9504 (2.7776) grad_norm: 2.8384 (3.0421) time: 0.6374 [2021-03-28 08:35:37 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 760/1251] eta: 0:05:12 lr: 0.000067 loss: 2.6931 (2.7713) grad_norm: 2.8708 (3.0441) time: 0.6309 [2021-03-28 08:35:43 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 770/1251] eta: 0:05:06 lr: 0.000067 loss: 2.6039 (2.7719) grad_norm: 2.8047 (3.0419) time: 0.6259 [2021-03-28 08:35:50 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 780/1251] eta: 0:04:59 lr: 0.000067 loss: 2.9332 (2.7722) grad_norm: 2.6573 (3.0387) time: 0.6242 [2021-03-28 08:35:56 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 790/1251] eta: 0:04:53 lr: 0.000067 loss: 3.0241 (2.7749) grad_norm: 2.8459 (3.0390) time: 0.6276 [2021-03-28 08:36:02 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 800/1251] eta: 0:04:46 lr: 0.000067 loss: 2.8350 (2.7717) grad_norm: 2.9471 (3.0447) time: 0.6340 [2021-03-28 08:36:09 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 810/1251] eta: 0:04:40 lr: 0.000067 loss: 2.7456 (2.7713) grad_norm: 2.9421 (3.0502) time: 0.6336 [2021-03-28 08:36:15 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 820/1251] eta: 0:04:34 lr: 0.000067 loss: 2.9050 (2.7722) grad_norm: 2.9421 (3.0493) time: 0.6346 [2021-03-28 08:36:21 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 830/1251] eta: 0:04:27 lr: 0.000067 loss: 2.9168 (2.7736) grad_norm: 2.8505 (3.0475) time: 0.6335 [2021-03-28 08:36:28 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 840/1251] eta: 0:04:21 lr: 0.000067 loss: 2.8751 (2.7739) grad_norm: 2.8733 (3.0471) time: 0.6341 [2021-03-28 08:36:34 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 850/1251] eta: 0:04:15 lr: 0.000067 loss: 2.9449 (2.7772) grad_norm: 2.8733 (3.0452) time: 0.6325 [2021-03-28 08:36:40 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 860/1251] eta: 0:04:08 lr: 0.000067 loss: 2.8394 (2.7750) grad_norm: 2.9027 (3.0489) time: 0.6335 [2021-03-28 08:36:47 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 870/1251] eta: 0:04:02 lr: 0.000067 loss: 2.6061 (2.7748) grad_norm: 2.8990 (3.0474) time: 0.6341 [2021-03-28 08:36:53 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 880/1251] eta: 0:03:55 lr: 0.000067 loss: 2.7694 (2.7760) grad_norm: 2.8219 (3.0458) time: 0.6356 [2021-03-28 08:36:59 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 890/1251] eta: 0:03:49 lr: 0.000067 loss: 2.7782 (2.7747) grad_norm: 2.6950 (3.0433) time: 0.6359 [2021-03-28 08:37:06 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 900/1251] eta: 0:03:43 lr: 0.000067 loss: 2.7514 (2.7744) grad_norm: 2.7153 (3.0432) time: 0.6298 [2021-03-28 08:37:12 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 910/1251] eta: 0:03:36 lr: 0.000067 loss: 2.8252 (2.7727) grad_norm: 2.7513 (3.0443) time: 0.6270 [2021-03-28 08:37:18 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 920/1251] eta: 0:03:30 lr: 0.000067 loss: 2.7778 (2.7704) grad_norm: 2.7513 (3.0420) time: 0.6242 [2021-03-28 08:37:24 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 930/1251] eta: 0:03:23 lr: 0.000067 loss: 2.6865 (2.7682) grad_norm: 2.7480 (3.0425) time: 0.6250 [2021-03-28 08:37:31 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 940/1251] eta: 0:03:17 lr: 0.000067 loss: 2.6467 (2.7675) grad_norm: 2.9069 (3.0464) time: 0.6257 [2021-03-28 08:37:37 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 950/1251] eta: 0:03:11 lr: 0.000067 loss: 2.8478 (2.7681) grad_norm: 2.8537 (3.0432) time: 0.6258 [2021-03-28 08:37:43 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 960/1251] eta: 0:03:04 lr: 0.000067 loss: 2.9377 (2.7683) grad_norm: 2.6987 (3.0404) time: 0.6257 [2021-03-28 08:37:49 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 970/1251] eta: 0:02:58 lr: 0.000067 loss: 2.8594 (2.7682) grad_norm: 2.6026 (3.0379) time: 0.6238 [2021-03-28 08:37:56 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 980/1251] eta: 0:02:52 lr: 0.000067 loss: 2.9253 (2.7703) grad_norm: 2.7741 (3.0396) time: 0.6245 [2021-03-28 08:38:02 swin_base_patch4_window7_224] INFO: Epoch: [253] [ 990/1251] eta: 0:02:45 lr: 0.000067 loss: 2.7562 (2.7690) grad_norm: 2.7741 (3.0363) time: 0.6260 [2021-03-28 08:38:08 swin_base_patch4_window7_224] INFO: Epoch: [253] [1000/1251] eta: 0:02:39 lr: 0.000067 loss: 2.7117 (2.7673) grad_norm: 2.7556 (3.0486) time: 0.6314 [2021-03-28 08:38:15 swin_base_patch4_window7_224] INFO: Epoch: [253] [1010/1251] eta: 0:02:33 lr: 0.000067 loss: 2.7304 (2.7669) grad_norm: 2.8043 (3.0495) time: 0.6346 [2021-03-28 08:38:21 swin_base_patch4_window7_224] INFO: Epoch: [253] [1020/1251] eta: 0:02:26 lr: 0.000067 loss: 2.9471 (2.7685) grad_norm: 2.8043 (3.0471) time: 0.6295 [2021-03-28 08:38:27 swin_base_patch4_window7_224] INFO: Epoch: [253] [1030/1251] eta: 0:02:20 lr: 0.000067 loss: 2.8953 (2.7685) grad_norm: 2.6856 (3.0443) time: 0.6265 [2021-03-28 08:38:34 swin_base_patch4_window7_224] INFO: Epoch: [253] [1040/1251] eta: 0:02:13 lr: 0.000067 loss: 2.9116 (2.7702) grad_norm: 2.6773 (3.0407) time: 0.6279 [2021-03-28 08:38:40 swin_base_patch4_window7_224] INFO: Epoch: [253] [1050/1251] eta: 0:02:07 lr: 0.000067 loss: 2.9495 (2.7694) grad_norm: 2.7508 (3.0411) time: 0.6237 [2021-03-28 08:38:46 swin_base_patch4_window7_224] INFO: Epoch: [253] [1060/1251] eta: 0:02:01 lr: 0.000067 loss: 2.5725 (2.7680) grad_norm: 2.7964 (3.0424) time: 0.6263 [2021-03-28 08:38:52 swin_base_patch4_window7_224] INFO: Epoch: [253] [1070/1251] eta: 0:01:54 lr: 0.000067 loss: 2.5725 (2.7678) grad_norm: 2.9232 (3.0427) time: 0.6301 [2021-03-28 08:38:59 swin_base_patch4_window7_224] INFO: Epoch: [253] [1080/1251] eta: 0:01:48 lr: 0.000067 loss: 2.9042 (2.7685) grad_norm: 3.0062 (3.0464) time: 0.6254 [2021-03-28 08:39:05 swin_base_patch4_window7_224] INFO: Epoch: [253] [1090/1251] eta: 0:01:42 lr: 0.000067 loss: 2.9042 (2.7679) grad_norm: 2.6862 (3.0429) time: 0.6262 [2021-03-28 08:39:11 swin_base_patch4_window7_224] INFO: Epoch: [253] [1100/1251] eta: 0:01:35 lr: 0.000067 loss: 2.8647 (2.7687) grad_norm: 2.6684 (3.0409) time: 0.6298 [2021-03-28 08:39:17 swin_base_patch4_window7_224] INFO: Epoch: [253] [1110/1251] eta: 0:01:29 lr: 0.000067 loss: 2.7645 (2.7667) grad_norm: 2.6858 (3.0388) time: 0.6282 [2021-03-28 08:39:24 swin_base_patch4_window7_224] INFO: Epoch: [253] [1120/1251] eta: 0:01:23 lr: 0.000067 loss: 2.8809 (2.7664) grad_norm: 2.8197 (3.0385) time: 0.6271 [2021-03-28 08:39:30 swin_base_patch4_window7_224] INFO: Epoch: [253] [1130/1251] eta: 0:01:16 lr: 0.000067 loss: 2.9444 (2.7667) grad_norm: 2.8623 (3.0370) time: 0.6269 [2021-03-28 08:39:36 swin_base_patch4_window7_224] INFO: Epoch: [253] [1140/1251] eta: 0:01:10 lr: 0.000067 loss: 2.6795 (2.7658) grad_norm: 2.9984 (3.0368) time: 0.6334 [2021-03-28 08:39:43 swin_base_patch4_window7_224] INFO: Epoch: [253] [1150/1251] eta: 0:01:04 lr: 0.000067 loss: 2.6795 (2.7649) grad_norm: 2.7998 (3.0342) time: 0.6377 [2021-03-28 08:39:49 swin_base_patch4_window7_224] INFO: Epoch: [253] [1160/1251] eta: 0:00:57 lr: 0.000067 loss: 2.8585 (2.7645) grad_norm: 2.6305 (3.0327) time: 0.6289 [2021-03-28 08:39:55 swin_base_patch4_window7_224] INFO: Epoch: [253] [1170/1251] eta: 0:00:51 lr: 0.000066 loss: 2.4948 (2.7641) grad_norm: 2.8240 (3.0346) time: 0.6226 [2021-03-28 08:40:02 swin_base_patch4_window7_224] INFO: Epoch: [253] [1180/1251] eta: 0:00:45 lr: 0.000066 loss: 2.9699 (2.7657) grad_norm: 2.7898 (3.0345) time: 0.6284 [2021-03-28 08:40:08 swin_base_patch4_window7_224] INFO: Epoch: [253] [1190/1251] eta: 0:00:38 lr: 0.000066 loss: 2.7171 (2.7634) grad_norm: 2.8815 (3.0338) time: 0.6329 [2021-03-28 08:40:14 swin_base_patch4_window7_224] INFO: Epoch: [253] [1200/1251] eta: 0:00:32 lr: 0.000066 loss: 2.5816 (2.7627) grad_norm: 2.8876 (3.0381) time: 0.6281 [2021-03-28 08:40:20 swin_base_patch4_window7_224] INFO: Epoch: [253] [1210/1251] eta: 0:00:25 lr: 0.000066 loss: 2.6499 (2.7620) grad_norm: 2.7033 (3.0363) time: 0.6259 [2021-03-28 08:40:27 swin_base_patch4_window7_224] INFO: Epoch: [253] [1220/1251] eta: 0:00:19 lr: 0.000066 loss: 2.7124 (2.7606) grad_norm: 2.6645 (3.0368) time: 0.6249 [2021-03-28 08:40:33 swin_base_patch4_window7_224] INFO: Epoch: [253] [1230/1251] eta: 0:00:13 lr: 0.000066 loss: 2.7881 (2.7608) grad_norm: 2.6717 (3.0368) time: 0.6313 [2021-03-28 08:40:39 swin_base_patch4_window7_224] INFO: Epoch: [253] [1240/1251] eta: 0:00:06 lr: 0.000066 loss: 2.7881 (2.7591) grad_norm: 2.7066 (3.0370) time: 0.6363 [2021-03-28 08:40:45 swin_base_patch4_window7_224] INFO: Epoch: [253] [1250/1251] eta: 0:00:00 lr: 0.000066 loss: 2.7245 (2.7587) grad_norm: 2.7536 (3.0349) time: 0.6221 [2021-03-28 08:40:58 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:37 loss: 0.8362 (0.8362) acc1: 84.3750 (84.3750) acc5: 93.7500 (93.7500) [2021-03-28 08:41:00 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.7541 (0.7716) acc1: 82.8125 (81.6761) acc5: 95.3125 (96.0227) [2021-03-28 08:41:02 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7541 (0.7985) acc1: 81.2500 (81.2500) acc5: 95.3125 (95.9821) [2021-03-28 08:41:04 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7649 (0.7865) acc1: 82.8125 (81.3508) acc5: 96.8750 (96.1694) [2021-03-28 08:41:07 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6429 (0.7537) acc1: 82.8125 (81.8216) acc5: 96.8750 (96.4177) [2021-03-28 08:41:08 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6429 (0.7619) acc1: 84.3750 (81.6640) acc5: 96.8750 (96.3520) [2021-03-28 08:41:22 swin_base_patch4_window7_224] INFO: * Acc@1 82.888 Acc@5 96.340 loss 0.751 [2021-03-28 08:41:22 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.9% [2021-03-28 08:41:22 swin_base_patch4_window7_224] INFO: Max accuracy: 82.90% [2021-03-28 08:41:27 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 0/1251] eta: 1:40:15 lr: 0.000066 loss: 3.3130 (3.3130) grad_norm: 3.8483 (3.8483) time: 4.8083 [2021-03-28 08:41:33 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 10/1251] eta: 0:20:59 lr: 0.000066 loss: 3.0298 (3.0308) grad_norm: 2.9837 (3.0473) time: 1.0145 [2021-03-28 08:41:40 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 20/1251] eta: 0:17:02 lr: 0.000066 loss: 2.9593 (2.9652) grad_norm: 2.9922 (3.5440) time: 0.6320 [2021-03-28 08:41:46 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 30/1251] eta: 0:15:32 lr: 0.000066 loss: 2.9027 (2.8800) grad_norm: 3.0463 (3.3836) time: 0.6259 [2021-03-28 08:41:52 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 40/1251] eta: 0:14:47 lr: 0.000066 loss: 2.8316 (2.8567) grad_norm: 3.0463 (3.2985) time: 0.6292 [2021-03-28 08:41:58 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 50/1251] eta: 0:14:15 lr: 0.000066 loss: 2.8084 (2.8422) grad_norm: 2.8046 (3.2153) time: 0.6330 [2021-03-28 08:42:05 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 60/1251] eta: 0:13:53 lr: 0.000066 loss: 2.8078 (2.8187) grad_norm: 2.9196 (3.2352) time: 0.6320 [2021-03-28 08:42:11 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 70/1251] eta: 0:13:34 lr: 0.000066 loss: 2.8302 (2.8294) grad_norm: 2.9605 (3.2481) time: 0.6302 [2021-03-28 08:42:17 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 80/1251] eta: 0:13:19 lr: 0.000066 loss: 2.9358 (2.8293) grad_norm: 2.9602 (3.2751) time: 0.6311 [2021-03-28 08:42:24 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 90/1251] eta: 0:13:06 lr: 0.000066 loss: 2.8886 (2.8149) grad_norm: 2.8544 (3.2635) time: 0.6335 [2021-03-28 08:42:30 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 100/1251] eta: 0:12:53 lr: 0.000066 loss: 2.8886 (2.8060) grad_norm: 2.8077 (3.2188) time: 0.6296 [2021-03-28 08:42:36 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 110/1251] eta: 0:12:41 lr: 0.000066 loss: 2.7825 (2.7795) grad_norm: 2.8628 (3.2188) time: 0.6249 [2021-03-28 08:42:43 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 120/1251] eta: 0:12:32 lr: 0.000066 loss: 2.8807 (2.7852) grad_norm: 2.8628 (3.1880) time: 0.6292 [2021-03-28 08:42:49 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 130/1251] eta: 0:12:23 lr: 0.000066 loss: 2.7783 (2.7640) grad_norm: 2.8226 (3.1690) time: 0.6366 [2021-03-28 08:42:55 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 140/1251] eta: 0:12:13 lr: 0.000066 loss: 2.7824 (2.7881) grad_norm: 2.8929 (3.1691) time: 0.6322 [2021-03-28 08:43:02 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 150/1251] eta: 0:12:04 lr: 0.000066 loss: 2.9470 (2.7880) grad_norm: 3.0167 (3.1912) time: 0.6271 [2021-03-28 08:43:08 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 160/1251] eta: 0:11:55 lr: 0.000066 loss: 2.7573 (2.7843) grad_norm: 2.8273 (3.1611) time: 0.6262 [2021-03-28 08:43:14 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 170/1251] eta: 0:11:47 lr: 0.000066 loss: 2.7267 (2.7689) grad_norm: 2.7894 (3.1668) time: 0.6285 [2021-03-28 08:43:20 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 180/1251] eta: 0:11:39 lr: 0.000066 loss: 2.5515 (2.7547) grad_norm: 2.8403 (3.1456) time: 0.6321 [2021-03-28 08:43:27 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 190/1251] eta: 0:11:32 lr: 0.000066 loss: 2.3847 (2.7445) grad_norm: 2.7277 (3.1289) time: 0.6324 [2021-03-28 08:43:33 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 200/1251] eta: 0:11:24 lr: 0.000066 loss: 2.5631 (2.7339) grad_norm: 2.8691 (3.2214) time: 0.6346 [2021-03-28 08:43:39 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 210/1251] eta: 0:11:17 lr: 0.000066 loss: 2.7129 (2.7363) grad_norm: 2.9063 (3.2137) time: 0.6341 [2021-03-28 08:43:46 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 220/1251] eta: 0:11:09 lr: 0.000066 loss: 2.7129 (2.7327) grad_norm: 3.1124 (3.2355) time: 0.6316 [2021-03-28 08:43:52 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 230/1251] eta: 0:11:02 lr: 0.000066 loss: 2.5144 (2.7225) grad_norm: 3.0531 (3.2313) time: 0.6282 [2021-03-28 08:43:58 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 240/1251] eta: 0:10:55 lr: 0.000066 loss: 2.4572 (2.7081) grad_norm: 2.9879 (3.2269) time: 0.6280 [2021-03-28 08:44:05 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 250/1251] eta: 0:10:48 lr: 0.000066 loss: 2.4759 (2.7023) grad_norm: 2.8356 (3.2098) time: 0.6386 [2021-03-28 08:44:11 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 260/1251] eta: 0:10:41 lr: 0.000066 loss: 2.7188 (2.7070) grad_norm: 2.8238 (3.2048) time: 0.6375 [2021-03-28 08:44:17 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 270/1251] eta: 0:10:34 lr: 0.000066 loss: 2.7633 (2.7051) grad_norm: 2.9176 (3.2009) time: 0.6274 [2021-03-28 08:44:24 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 280/1251] eta: 0:10:26 lr: 0.000066 loss: 2.7740 (2.7045) grad_norm: 2.9971 (3.1963) time: 0.6267 [2021-03-28 08:44:30 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 290/1251] eta: 0:10:19 lr: 0.000066 loss: 2.8372 (2.7072) grad_norm: 2.7424 (3.1832) time: 0.6263 [2021-03-28 08:44:36 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 300/1251] eta: 0:10:12 lr: 0.000066 loss: 2.8372 (2.7080) grad_norm: 2.7424 (3.1703) time: 0.6281 [2021-03-28 08:44:43 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 310/1251] eta: 0:10:06 lr: 0.000066 loss: 2.7036 (2.7040) grad_norm: 2.9816 (3.1704) time: 0.6340 [2021-03-28 08:44:49 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 320/1251] eta: 0:09:59 lr: 0.000066 loss: 2.6408 (2.7062) grad_norm: 2.9658 (3.1610) time: 0.6326 [2021-03-28 08:44:55 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 330/1251] eta: 0:09:52 lr: 0.000066 loss: 2.6714 (2.7090) grad_norm: 2.6178 (3.1590) time: 0.6307 [2021-03-28 08:45:02 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 340/1251] eta: 0:09:46 lr: 0.000066 loss: 2.7178 (2.7075) grad_norm: 2.7130 (3.1569) time: 0.6361 [2021-03-28 08:45:08 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 350/1251] eta: 0:09:39 lr: 0.000066 loss: 2.8615 (2.7129) grad_norm: 2.7413 (3.1497) time: 0.6345 [2021-03-28 08:45:14 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 360/1251] eta: 0:09:32 lr: 0.000066 loss: 2.8615 (2.7117) grad_norm: 2.6920 (3.1401) time: 0.6304 [2021-03-28 08:45:20 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 370/1251] eta: 0:09:25 lr: 0.000066 loss: 2.8813 (2.7175) grad_norm: 2.6877 (3.1426) time: 0.6290 [2021-03-28 08:45:27 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 380/1251] eta: 0:09:19 lr: 0.000066 loss: 2.7347 (2.7120) grad_norm: 2.7133 (3.1447) time: 0.6322 [2021-03-28 08:45:33 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 390/1251] eta: 0:09:12 lr: 0.000066 loss: 2.6683 (2.7155) grad_norm: 2.7734 (3.1437) time: 0.6365 [2021-03-28 08:45:40 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 400/1251] eta: 0:09:06 lr: 0.000066 loss: 2.8751 (2.7157) grad_norm: 2.6909 (3.1330) time: 0.6370 [2021-03-28 08:45:46 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 410/1251] eta: 0:08:59 lr: 0.000066 loss: 2.9089 (2.7219) grad_norm: 2.7222 (3.1264) time: 0.6311 [2021-03-28 08:45:52 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 420/1251] eta: 0:08:52 lr: 0.000066 loss: 2.9089 (2.7196) grad_norm: 2.7324 (3.1225) time: 0.6231 [2021-03-28 08:45:58 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 430/1251] eta: 0:08:45 lr: 0.000066 loss: 2.9119 (2.7242) grad_norm: 2.5192 (3.1136) time: 0.6234 [2021-03-28 08:46:05 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 440/1251] eta: 0:08:39 lr: 0.000065 loss: 2.7570 (2.7179) grad_norm: 2.8952 (3.1225) time: 0.6307 [2021-03-28 08:46:11 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 450/1251] eta: 0:08:32 lr: 0.000065 loss: 2.6918 (2.7153) grad_norm: 2.8524 (3.1143) time: 0.6333 [2021-03-28 08:46:17 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 460/1251] eta: 0:08:26 lr: 0.000065 loss: 2.6880 (2.7121) grad_norm: 2.7073 (3.1070) time: 0.6292 [2021-03-28 08:46:24 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 470/1251] eta: 0:08:19 lr: 0.000065 loss: 2.6774 (2.7090) grad_norm: 2.7436 (3.0991) time: 0.6297 [2021-03-28 08:46:30 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 480/1251] eta: 0:08:13 lr: 0.000065 loss: 2.8234 (2.7102) grad_norm: 2.8345 (3.1038) time: 0.6299 [2021-03-28 08:46:36 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 490/1251] eta: 0:08:06 lr: 0.000065 loss: 2.9502 (2.7142) grad_norm: 2.7237 (3.1001) time: 0.6283 [2021-03-28 08:46:42 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 500/1251] eta: 0:07:59 lr: 0.000065 loss: 2.8719 (2.7150) grad_norm: 2.5741 (3.0956) time: 0.6232 [2021-03-28 08:46:49 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 510/1251] eta: 0:07:53 lr: 0.000065 loss: 2.6726 (2.7115) grad_norm: 2.6150 (3.0873) time: 0.6264 [2021-03-28 08:46:55 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 520/1251] eta: 0:07:46 lr: 0.000065 loss: 2.6587 (2.7089) grad_norm: 2.7666 (3.0957) time: 0.6315 [2021-03-28 08:47:01 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 530/1251] eta: 0:07:40 lr: 0.000065 loss: 2.5717 (2.7085) grad_norm: 3.2650 (3.1033) time: 0.6342 [2021-03-28 08:47:08 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 540/1251] eta: 0:07:33 lr: 0.000065 loss: 2.8171 (2.7091) grad_norm: 3.2650 (3.1122) time: 0.6303 [2021-03-28 08:47:14 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 550/1251] eta: 0:07:27 lr: 0.000065 loss: 2.8171 (2.7110) grad_norm: 2.8537 (3.1079) time: 0.6368 [2021-03-28 08:47:20 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 560/1251] eta: 0:07:21 lr: 0.000065 loss: 3.0453 (2.7162) grad_norm: 2.7701 (3.1042) time: 0.6396 [2021-03-28 08:47:27 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 570/1251] eta: 0:07:14 lr: 0.000065 loss: 2.9994 (2.7170) grad_norm: 2.7701 (3.1007) time: 0.6287 [2021-03-28 08:47:33 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 580/1251] eta: 0:07:08 lr: 0.000065 loss: 2.7231 (2.7141) grad_norm: 2.7183 (3.0972) time: 0.6324 [2021-03-28 08:47:39 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 590/1251] eta: 0:07:01 lr: 0.000065 loss: 2.6826 (2.7123) grad_norm: 2.9357 (3.0974) time: 0.6363 [2021-03-28 08:47:46 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 600/1251] eta: 0:06:55 lr: 0.000065 loss: 2.8160 (2.7137) grad_norm: 2.9705 (3.0960) time: 0.6380 [2021-03-28 08:47:52 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 610/1251] eta: 0:06:48 lr: 0.000065 loss: 2.6371 (2.7095) grad_norm: 2.9803 (3.0993) time: 0.6323 [2021-03-28 08:47:58 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 620/1251] eta: 0:06:42 lr: 0.000065 loss: 2.5556 (2.7074) grad_norm: 2.7520 (3.0918) time: 0.6267 [2021-03-28 08:48:05 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 630/1251] eta: 0:06:36 lr: 0.000065 loss: 2.7832 (2.7110) grad_norm: 2.7289 (3.0903) time: 0.6304 [2021-03-28 08:48:11 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 640/1251] eta: 0:06:29 lr: 0.000065 loss: 2.9155 (2.7133) grad_norm: 2.7382 (3.0880) time: 0.6368 [2021-03-28 08:48:17 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 650/1251] eta: 0:06:23 lr: 0.000065 loss: 3.0368 (2.7151) grad_norm: 2.8243 (3.0882) time: 0.6343 [2021-03-28 08:48:24 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 660/1251] eta: 0:06:16 lr: 0.000065 loss: 2.7236 (2.7138) grad_norm: 2.8644 (3.0872) time: 0.6297 [2021-03-28 08:48:30 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 670/1251] eta: 0:06:10 lr: 0.000065 loss: 2.7345 (2.7154) grad_norm: 2.7469 (3.0853) time: 0.6328 [2021-03-28 08:48:36 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 680/1251] eta: 0:06:03 lr: 0.000065 loss: 2.8292 (2.7126) grad_norm: 2.9408 (3.0897) time: 0.6295 [2021-03-28 08:48:43 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 690/1251] eta: 0:05:57 lr: 0.000065 loss: 2.8787 (2.7155) grad_norm: 2.9408 (3.0884) time: 0.6320 [2021-03-28 08:48:49 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 700/1251] eta: 0:05:51 lr: 0.000065 loss: 2.8888 (2.7164) grad_norm: 2.8525 (3.0871) time: 0.6321 [2021-03-28 08:48:55 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 710/1251] eta: 0:05:44 lr: 0.000065 loss: 2.6532 (2.7153) grad_norm: 2.8724 (3.0888) time: 0.6283 [2021-03-28 08:49:02 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 720/1251] eta: 0:05:38 lr: 0.000065 loss: 2.6821 (2.7128) grad_norm: 2.7963 (3.0882) time: 0.6310 [2021-03-28 08:49:08 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 730/1251] eta: 0:05:31 lr: 0.000065 loss: 2.7444 (2.7127) grad_norm: 2.7428 (3.0849) time: 0.6354 [2021-03-28 08:49:14 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 740/1251] eta: 0:05:25 lr: 0.000065 loss: 2.7298 (2.7124) grad_norm: 2.8016 (3.0865) time: 0.6387 [2021-03-28 08:49:21 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 750/1251] eta: 0:05:19 lr: 0.000065 loss: 2.6584 (2.7114) grad_norm: 3.2142 (3.0888) time: 0.6344 [2021-03-28 08:49:27 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 760/1251] eta: 0:05:12 lr: 0.000065 loss: 2.8642 (2.7140) grad_norm: 3.1819 (3.0870) time: 0.6347 [2021-03-28 08:49:33 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 770/1251] eta: 0:05:06 lr: 0.000065 loss: 2.7004 (2.7085) grad_norm: 2.8574 (3.0827) time: 0.6364 [2021-03-28 08:49:40 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 780/1251] eta: 0:04:59 lr: 0.000065 loss: 2.6006 (2.7097) grad_norm: 2.7089 (3.0799) time: 0.6323 [2021-03-28 08:49:46 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 790/1251] eta: 0:04:53 lr: 0.000065 loss: 2.7548 (2.7091) grad_norm: 2.6030 (3.0738) time: 0.6295 [2021-03-28 08:49:52 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 800/1251] eta: 0:04:47 lr: 0.000065 loss: 2.9646 (2.7106) grad_norm: 2.6030 (3.0729) time: 0.6278 [2021-03-28 08:49:59 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 810/1251] eta: 0:04:40 lr: 0.000065 loss: 2.9701 (2.7126) grad_norm: 2.7201 (3.0706) time: 0.6304 [2021-03-28 08:50:05 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 820/1251] eta: 0:04:34 lr: 0.000065 loss: 2.8833 (2.7119) grad_norm: 2.6889 (3.0681) time: 0.6333 [2021-03-28 08:50:11 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 830/1251] eta: 0:04:27 lr: 0.000065 loss: 2.8064 (2.7099) grad_norm: 2.8501 (3.0662) time: 0.6301 [2021-03-28 08:50:17 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 840/1251] eta: 0:04:21 lr: 0.000065 loss: 2.8485 (2.7113) grad_norm: 2.8994 (3.0652) time: 0.6280 [2021-03-28 08:50:24 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 850/1251] eta: 0:04:15 lr: 0.000065 loss: 2.8485 (2.7119) grad_norm: 3.0726 (3.0706) time: 0.6266 [2021-03-28 08:50:30 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 860/1251] eta: 0:04:08 lr: 0.000065 loss: 2.8095 (2.7120) grad_norm: 3.0726 (3.0754) time: 0.6273 [2021-03-28 08:50:36 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 870/1251] eta: 0:04:02 lr: 0.000065 loss: 2.8115 (2.7132) grad_norm: 2.8864 (3.0780) time: 0.6349 [2021-03-28 08:50:43 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 880/1251] eta: 0:03:56 lr: 0.000065 loss: 2.8115 (2.7132) grad_norm: 2.9635 (3.0767) time: 0.6406 [2021-03-28 08:50:49 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 890/1251] eta: 0:03:49 lr: 0.000065 loss: 2.8937 (2.7163) grad_norm: 2.8278 (3.0747) time: 0.6385 [2021-03-28 08:50:55 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 900/1251] eta: 0:03:43 lr: 0.000065 loss: 3.0158 (2.7194) grad_norm: 2.8041 (3.0732) time: 0.6333 [2021-03-28 08:51:02 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 910/1251] eta: 0:03:36 lr: 0.000065 loss: 2.6769 (2.7169) grad_norm: 2.7766 (3.0702) time: 0.6314 [2021-03-28 08:51:08 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 920/1251] eta: 0:03:30 lr: 0.000065 loss: 2.8494 (2.7185) grad_norm: 2.7976 (3.0766) time: 0.6271 [2021-03-28 08:51:14 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 930/1251] eta: 0:03:24 lr: 0.000065 loss: 3.0059 (2.7205) grad_norm: 2.9152 (3.0760) time: 0.6254 [2021-03-28 08:51:21 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 940/1251] eta: 0:03:17 lr: 0.000065 loss: 2.9341 (2.7207) grad_norm: 3.0049 (3.0775) time: 0.6335 [2021-03-28 08:51:27 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 950/1251] eta: 0:03:11 lr: 0.000065 loss: 2.8824 (2.7223) grad_norm: 3.0254 (3.0768) time: 0.6339 [2021-03-28 08:51:33 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 960/1251] eta: 0:03:05 lr: 0.000065 loss: 2.9999 (2.7247) grad_norm: 2.8352 (3.0741) time: 0.6334 [2021-03-28 08:51:40 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 970/1251] eta: 0:02:58 lr: 0.000064 loss: 2.9977 (2.7260) grad_norm: 2.8644 (3.0732) time: 0.6328 [2021-03-28 08:51:46 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 980/1251] eta: 0:02:52 lr: 0.000064 loss: 2.8876 (2.7265) grad_norm: 2.8855 (3.0721) time: 0.6284 [2021-03-28 08:51:52 swin_base_patch4_window7_224] INFO: Epoch: [254] [ 990/1251] eta: 0:02:45 lr: 0.000064 loss: 2.8347 (2.7289) grad_norm: 3.1889 (3.0766) time: 0.6302 [2021-03-28 08:51:58 swin_base_patch4_window7_224] INFO: Epoch: [254] [1000/1251] eta: 0:02:39 lr: 0.000064 loss: 2.8791 (2.7294) grad_norm: 3.1889 (3.0796) time: 0.6277 [2021-03-28 08:52:05 swin_base_patch4_window7_224] INFO: Epoch: [254] [1010/1251] eta: 0:02:33 lr: 0.000064 loss: 2.9718 (2.7306) grad_norm: 2.9319 (3.0825) time: 0.6251 [2021-03-28 08:52:11 swin_base_patch4_window7_224] INFO: Epoch: [254] [1020/1251] eta: 0:02:26 lr: 0.000064 loss: 3.0163 (2.7323) grad_norm: 2.9555 (3.0813) time: 0.6270 [2021-03-28 08:52:17 swin_base_patch4_window7_224] INFO: Epoch: [254] [1030/1251] eta: 0:02:20 lr: 0.000064 loss: 2.7386 (2.7301) grad_norm: 2.9555 (3.0794) time: 0.6296 [2021-03-28 08:52:24 swin_base_patch4_window7_224] INFO: Epoch: [254] [1040/1251] eta: 0:02:14 lr: 0.000064 loss: 2.6247 (2.7310) grad_norm: 2.7302 (3.0774) time: 0.6323 [2021-03-28 08:52:30 swin_base_patch4_window7_224] INFO: Epoch: [254] [1050/1251] eta: 0:02:07 lr: 0.000064 loss: 2.8993 (2.7321) grad_norm: 2.7189 (3.0754) time: 0.6285 [2021-03-28 08:52:36 swin_base_patch4_window7_224] INFO: Epoch: [254] [1060/1251] eta: 0:02:01 lr: 0.000064 loss: 2.9216 (2.7323) grad_norm: 2.7921 (3.0752) time: 0.6314 [2021-03-28 08:52:43 swin_base_patch4_window7_224] INFO: Epoch: [254] [1070/1251] eta: 0:01:54 lr: 0.000064 loss: 2.9069 (2.7326) grad_norm: 2.8531 (3.0733) time: 0.6329 [2021-03-28 08:52:49 swin_base_patch4_window7_224] INFO: Epoch: [254] [1080/1251] eta: 0:01:48 lr: 0.000064 loss: 2.8505 (2.7321) grad_norm: 2.8248 (3.0724) time: 0.6302 [2021-03-28 08:52:55 swin_base_patch4_window7_224] INFO: Epoch: [254] [1090/1251] eta: 0:01:42 lr: 0.000064 loss: 2.8434 (2.7324) grad_norm: 2.8248 (3.0712) time: 0.6265 [2021-03-28 08:53:01 swin_base_patch4_window7_224] INFO: Epoch: [254] [1100/1251] eta: 0:01:35 lr: 0.000064 loss: 2.8434 (2.7322) grad_norm: 2.9024 (3.0700) time: 0.6254 [2021-03-28 08:53:08 swin_base_patch4_window7_224] INFO: Epoch: [254] [1110/1251] eta: 0:01:29 lr: 0.000064 loss: 2.7751 (2.7327) grad_norm: 2.9374 (3.0723) time: 0.6286 [2021-03-28 08:53:14 swin_base_patch4_window7_224] INFO: Epoch: [254] [1120/1251] eta: 0:01:23 lr: 0.000064 loss: 2.6698 (2.7326) grad_norm: 3.0254 (3.0720) time: 0.6260 [2021-03-28 08:53:20 swin_base_patch4_window7_224] INFO: Epoch: [254] [1130/1251] eta: 0:01:16 lr: 0.000064 loss: 2.7430 (2.7313) grad_norm: 2.8812 (3.0705) time: 0.6297 [2021-03-28 08:53:27 swin_base_patch4_window7_224] INFO: Epoch: [254] [1140/1251] eta: 0:01:10 lr: 0.000064 loss: 2.7430 (2.7319) grad_norm: 2.8007 (3.0695) time: 0.6281 [2021-03-28 08:53:33 swin_base_patch4_window7_224] INFO: Epoch: [254] [1150/1251] eta: 0:01:04 lr: 0.000064 loss: 2.7124 (2.7308) grad_norm: 2.8461 (3.0719) time: 0.6269 [2021-03-28 08:53:39 swin_base_patch4_window7_224] INFO: Epoch: [254] [1160/1251] eta: 0:00:57 lr: 0.000064 loss: 2.7042 (2.7298) grad_norm: 3.0275 (3.0714) time: 0.6273 [2021-03-28 08:53:45 swin_base_patch4_window7_224] INFO: Epoch: [254] [1170/1251] eta: 0:00:51 lr: 0.000064 loss: 2.7042 (2.7295) grad_norm: 2.8839 (3.0698) time: 0.6234 [2021-03-28 08:53:52 swin_base_patch4_window7_224] INFO: Epoch: [254] [1180/1251] eta: 0:00:45 lr: 0.000064 loss: 2.8439 (2.7301) grad_norm: 2.7257 (3.0670) time: 0.6288 [2021-03-28 08:53:58 swin_base_patch4_window7_224] INFO: Epoch: [254] [1190/1251] eta: 0:00:38 lr: 0.000064 loss: 2.9278 (2.7311) grad_norm: 2.7444 (3.0680) time: 0.6288 [2021-03-28 08:54:04 swin_base_patch4_window7_224] INFO: Epoch: [254] [1200/1251] eta: 0:00:32 lr: 0.000064 loss: 2.9104 (2.7312) grad_norm: 2.7862 (3.0674) time: 0.6323 [2021-03-28 08:54:11 swin_base_patch4_window7_224] INFO: Epoch: [254] [1210/1251] eta: 0:00:26 lr: 0.000064 loss: 2.8973 (2.7319) grad_norm: 2.7235 (3.0674) time: 0.6337 [2021-03-28 08:54:17 swin_base_patch4_window7_224] INFO: Epoch: [254] [1220/1251] eta: 0:00:19 lr: 0.000064 loss: 2.6921 (2.7312) grad_norm: 2.8802 (3.0668) time: 0.6269 [2021-03-28 08:54:23 swin_base_patch4_window7_224] INFO: Epoch: [254] [1230/1251] eta: 0:00:13 lr: 0.000064 loss: 2.6921 (2.7316) grad_norm: 2.7236 (3.0634) time: 0.6240 [2021-03-28 08:54:29 swin_base_patch4_window7_224] INFO: Epoch: [254] [1240/1251] eta: 0:00:06 lr: 0.000064 loss: 2.7888 (2.7321) grad_norm: 2.7236 (3.0650) time: 0.6260 [2021-03-28 08:54:36 swin_base_patch4_window7_224] INFO: Epoch: [254] [1250/1251] eta: 0:00:00 lr: 0.000064 loss: 2.7455 (2.7319) grad_norm: 2.8884 (3.0646) time: 0.6257 [2021-03-28 08:54:44 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:13 loss: 0.7463 (0.7463) acc1: 79.6875 (79.6875) acc5: 98.4375 (98.4375) [2021-03-28 08:54:46 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8035 (0.7995) acc1: 81.2500 (82.1023) acc5: 95.3125 (95.7386) [2021-03-28 08:54:48 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7849 (0.7651) acc1: 82.8125 (82.6637) acc5: 95.3125 (95.6845) [2021-03-28 08:54:50 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6293 (0.7431) acc1: 82.8125 (82.5605) acc5: 96.8750 (96.1694) [2021-03-28 08:54:52 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7033 (0.7604) acc1: 81.2500 (81.9360) acc5: 98.4375 (96.3796) [2021-03-28 08:54:53 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7033 (0.7574) acc1: 82.8125 (82.2080) acc5: 98.4375 (96.4160) [2021-03-28 08:55:07 swin_base_patch4_window7_224] INFO: * Acc@1 83.022 Acc@5 96.350 loss 0.749 [2021-03-28 08:55:07 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.0% [2021-03-28 08:55:07 swin_base_patch4_window7_224] INFO: Max accuracy: 83.02% [2021-03-28 08:55:11 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 0/1251] eta: 1:29:55 lr: 0.000064 loss: 3.3395 (3.3395) grad_norm: 2.4116 (2.4116) time: 4.3126 [2021-03-28 08:55:17 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 10/1251] eta: 0:20:01 lr: 0.000064 loss: 2.9038 (2.7715) grad_norm: 2.9033 (2.8749) time: 0.9680 [2021-03-28 08:55:24 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 20/1251] eta: 0:16:33 lr: 0.000064 loss: 2.9038 (2.8232) grad_norm: 2.9033 (3.0017) time: 0.6318 [2021-03-28 08:55:30 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 30/1251] eta: 0:15:15 lr: 0.000064 loss: 2.7674 (2.7637) grad_norm: 2.7552 (2.9942) time: 0.6295 [2021-03-28 08:55:36 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 40/1251] eta: 0:14:31 lr: 0.000064 loss: 2.6529 (2.7271) grad_norm: 2.8870 (3.0306) time: 0.6281 [2021-03-28 08:55:43 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 50/1251] eta: 0:14:04 lr: 0.000064 loss: 2.8663 (2.7458) grad_norm: 2.8293 (3.0869) time: 0.6319 [2021-03-28 08:55:49 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 60/1251] eta: 0:13:41 lr: 0.000064 loss: 2.8663 (2.7720) grad_norm: 2.7872 (inf) time: 0.6285 [2021-03-28 08:55:55 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 70/1251] eta: 0:13:27 lr: 0.000064 loss: 2.9465 (2.7997) grad_norm: 2.9200 (inf) time: 0.6328 [2021-03-28 08:56:02 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 80/1251] eta: 0:13:13 lr: 0.000064 loss: 2.8864 (2.7899) grad_norm: 2.9186 (inf) time: 0.6390 [2021-03-28 08:56:08 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 90/1251] eta: 0:13:00 lr: 0.000064 loss: 2.7085 (2.7891) grad_norm: 2.8131 (inf) time: 0.6324 [2021-03-28 08:56:14 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 100/1251] eta: 0:12:47 lr: 0.000064 loss: 2.7085 (2.7961) grad_norm: 2.9187 (inf) time: 0.6263 [2021-03-28 08:56:20 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 110/1251] eta: 0:12:36 lr: 0.000064 loss: 2.7506 (2.8008) grad_norm: 3.1483 (inf) time: 0.6208 [2021-03-28 08:56:27 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 120/1251] eta: 0:12:28 lr: 0.000064 loss: 2.8658 (2.8011) grad_norm: 2.9881 (inf) time: 0.6326 [2021-03-28 08:56:33 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 130/1251] eta: 0:12:18 lr: 0.000064 loss: 2.9286 (2.8103) grad_norm: 2.8205 (inf) time: 0.6378 [2021-03-28 08:56:40 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 140/1251] eta: 0:12:10 lr: 0.000064 loss: 2.9296 (2.8142) grad_norm: 2.9524 (inf) time: 0.6334 [2021-03-28 08:56:46 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 150/1251] eta: 0:12:01 lr: 0.000064 loss: 2.7296 (2.7996) grad_norm: 2.9749 (inf) time: 0.6301 [2021-03-28 08:56:52 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 160/1251] eta: 0:11:52 lr: 0.000064 loss: 2.7296 (2.7955) grad_norm: 2.6791 (inf) time: 0.6231 [2021-03-28 08:56:58 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 170/1251] eta: 0:11:44 lr: 0.000064 loss: 2.6270 (2.7811) grad_norm: 2.6017 (inf) time: 0.6233 [2021-03-28 08:57:05 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 180/1251] eta: 0:11:36 lr: 0.000064 loss: 2.6062 (2.7792) grad_norm: 2.6017 (inf) time: 0.6311 [2021-03-28 08:57:11 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 190/1251] eta: 0:11:29 lr: 0.000064 loss: 2.7979 (2.7781) grad_norm: 2.6540 (inf) time: 0.6321 [2021-03-28 08:57:17 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 200/1251] eta: 0:11:21 lr: 0.000064 loss: 2.6312 (2.7739) grad_norm: 2.8161 (inf) time: 0.6298 [2021-03-28 08:57:23 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 210/1251] eta: 0:11:14 lr: 0.000064 loss: 2.9817 (2.7832) grad_norm: 2.8161 (inf) time: 0.6295 [2021-03-28 08:57:30 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 220/1251] eta: 0:11:06 lr: 0.000064 loss: 2.7484 (2.7763) grad_norm: 2.9226 (inf) time: 0.6282 [2021-03-28 08:57:36 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 230/1251] eta: 0:10:59 lr: 0.000064 loss: 2.7151 (2.7731) grad_norm: 2.9420 (inf) time: 0.6307 [2021-03-28 08:57:42 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 240/1251] eta: 0:10:52 lr: 0.000064 loss: 2.7880 (2.7750) grad_norm: 2.8064 (inf) time: 0.6288 [2021-03-28 08:57:49 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 250/1251] eta: 0:10:45 lr: 0.000063 loss: 3.0153 (2.7766) grad_norm: 3.0215 (inf) time: 0.6240 [2021-03-28 08:57:55 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 260/1251] eta: 0:10:38 lr: 0.000063 loss: 2.7910 (2.7714) grad_norm: 3.0647 (inf) time: 0.6294 [2021-03-28 08:58:01 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 270/1251] eta: 0:10:31 lr: 0.000063 loss: 2.7910 (2.7705) grad_norm: 2.8461 (inf) time: 0.6321 [2021-03-28 08:58:08 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 280/1251] eta: 0:10:24 lr: 0.000063 loss: 2.8181 (2.7657) grad_norm: 2.8461 (inf) time: 0.6287 [2021-03-28 08:58:14 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 290/1251] eta: 0:10:17 lr: 0.000063 loss: 2.6364 (2.7586) grad_norm: 2.7590 (inf) time: 0.6276 [2021-03-28 08:58:20 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 300/1251] eta: 0:10:10 lr: 0.000063 loss: 2.6751 (2.7562) grad_norm: 2.8078 (inf) time: 0.6314 [2021-03-28 08:58:26 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 310/1251] eta: 0:10:04 lr: 0.000063 loss: 2.7346 (2.7561) grad_norm: 2.7677 (inf) time: 0.6346 [2021-03-28 08:58:33 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 320/1251] eta: 0:09:57 lr: 0.000063 loss: 2.8683 (2.7551) grad_norm: 2.7677 (inf) time: 0.6331 [2021-03-28 08:58:39 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 330/1251] eta: 0:09:50 lr: 0.000063 loss: 2.8439 (2.7575) grad_norm: 2.9080 (inf) time: 0.6344 [2021-03-28 08:58:45 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 340/1251] eta: 0:09:43 lr: 0.000063 loss: 2.8439 (2.7601) grad_norm: 2.8723 (inf) time: 0.6295 [2021-03-28 08:58:52 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 350/1251] eta: 0:09:37 lr: 0.000063 loss: 2.7847 (2.7619) grad_norm: 2.7490 (inf) time: 0.6239 [2021-03-28 08:58:58 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 360/1251] eta: 0:09:30 lr: 0.000063 loss: 2.7257 (2.7606) grad_norm: 2.8164 (inf) time: 0.6262 [2021-03-28 08:59:04 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 370/1251] eta: 0:09:23 lr: 0.000063 loss: 2.6835 (2.7596) grad_norm: 2.9540 (inf) time: 0.6316 [2021-03-28 08:59:11 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 380/1251] eta: 0:09:17 lr: 0.000063 loss: 2.6687 (2.7568) grad_norm: 2.7489 (inf) time: 0.6314 [2021-03-28 08:59:17 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 390/1251] eta: 0:09:10 lr: 0.000063 loss: 2.8892 (2.7604) grad_norm: 2.7137 (inf) time: 0.6249 [2021-03-28 08:59:23 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 400/1251] eta: 0:09:03 lr: 0.000063 loss: 2.9266 (2.7617) grad_norm: 2.9388 (inf) time: 0.6211 [2021-03-28 08:59:29 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 410/1251] eta: 0:08:56 lr: 0.000063 loss: 2.8130 (2.7624) grad_norm: 2.8105 (inf) time: 0.6211 [2021-03-28 08:59:36 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 420/1251] eta: 0:08:50 lr: 0.000063 loss: 2.6880 (2.7586) grad_norm: 2.8105 (inf) time: 0.6271 [2021-03-28 08:59:42 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 430/1251] eta: 0:08:44 lr: 0.000063 loss: 2.6918 (2.7536) grad_norm: 2.7819 (inf) time: 0.6369 [2021-03-28 08:59:48 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 440/1251] eta: 0:08:37 lr: 0.000063 loss: 2.5591 (2.7476) grad_norm: 2.7379 (inf) time: 0.6343 [2021-03-28 08:59:55 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 450/1251] eta: 0:08:30 lr: 0.000063 loss: 2.5591 (2.7451) grad_norm: 2.7983 (inf) time: 0.6297 [2021-03-28 09:00:01 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 460/1251] eta: 0:08:24 lr: 0.000063 loss: 2.7806 (2.7457) grad_norm: 2.7477 (inf) time: 0.6329 [2021-03-28 09:00:07 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 470/1251] eta: 0:08:17 lr: 0.000063 loss: 2.7806 (2.7441) grad_norm: 2.7489 (inf) time: 0.6319 [2021-03-28 09:00:14 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 480/1251] eta: 0:08:11 lr: 0.000063 loss: 2.7567 (2.7430) grad_norm: 2.8910 (inf) time: 0.6331 [2021-03-28 09:00:20 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 490/1251] eta: 0:08:04 lr: 0.000063 loss: 2.6647 (2.7394) grad_norm: 2.8230 (inf) time: 0.6276 [2021-03-28 09:00:26 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 500/1251] eta: 0:07:58 lr: 0.000063 loss: 2.7308 (2.7421) grad_norm: 2.8286 (inf) time: 0.6223 [2021-03-28 09:00:32 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 510/1251] eta: 0:07:51 lr: 0.000063 loss: 2.8020 (2.7427) grad_norm: 2.7912 (inf) time: 0.6238 [2021-03-28 09:00:39 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 520/1251] eta: 0:07:45 lr: 0.000063 loss: 2.8642 (2.7438) grad_norm: 2.8585 (inf) time: 0.6237 [2021-03-28 09:00:45 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 530/1251] eta: 0:07:38 lr: 0.000063 loss: 2.9413 (2.7460) grad_norm: 2.8585 (inf) time: 0.6267 [2021-03-28 09:00:51 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 540/1251] eta: 0:07:32 lr: 0.000063 loss: 2.7966 (2.7459) grad_norm: 2.6750 (inf) time: 0.6256 [2021-03-28 09:00:57 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 550/1251] eta: 0:07:25 lr: 0.000063 loss: 2.9619 (2.7513) grad_norm: 2.9622 (inf) time: 0.6308 [2021-03-28 09:01:04 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 560/1251] eta: 0:07:19 lr: 0.000063 loss: 2.9324 (2.7525) grad_norm: 2.8849 (inf) time: 0.6354 [2021-03-28 09:01:10 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 570/1251] eta: 0:07:13 lr: 0.000063 loss: 2.8274 (2.7500) grad_norm: 2.7524 (inf) time: 0.6293 [2021-03-28 09:01:16 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 580/1251] eta: 0:07:06 lr: 0.000063 loss: 2.7306 (2.7502) grad_norm: 2.7811 (inf) time: 0.6292 [2021-03-28 09:01:23 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 590/1251] eta: 0:07:00 lr: 0.000063 loss: 2.9179 (2.7537) grad_norm: 2.8474 (inf) time: 0.6314 [2021-03-28 09:01:29 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 600/1251] eta: 0:06:53 lr: 0.000063 loss: 2.8751 (2.7527) grad_norm: 2.9669 (inf) time: 0.6272 [2021-03-28 09:01:35 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 610/1251] eta: 0:06:47 lr: 0.000063 loss: 2.6131 (2.7475) grad_norm: 2.9401 (inf) time: 0.6260 [2021-03-28 09:01:41 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 620/1251] eta: 0:06:40 lr: 0.000063 loss: 2.6406 (2.7473) grad_norm: 2.8699 (inf) time: 0.6271 [2021-03-28 09:01:48 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 630/1251] eta: 0:06:34 lr: 0.000063 loss: 2.7834 (2.7467) grad_norm: 2.9187 (inf) time: 0.6270 [2021-03-28 09:01:54 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 640/1251] eta: 0:06:28 lr: 0.000063 loss: 2.7055 (2.7470) grad_norm: 2.9136 (inf) time: 0.6285 [2021-03-28 09:02:00 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 650/1251] eta: 0:06:21 lr: 0.000063 loss: 2.7969 (2.7470) grad_norm: 2.9545 (inf) time: 0.6301 [2021-03-28 09:02:07 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 660/1251] eta: 0:06:15 lr: 0.000063 loss: 2.6849 (2.7456) grad_norm: 2.8648 (inf) time: 0.6309 [2021-03-28 09:02:13 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 670/1251] eta: 0:06:08 lr: 0.000063 loss: 2.6308 (2.7464) grad_norm: 2.6980 (inf) time: 0.6299 [2021-03-28 09:02:19 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 680/1251] eta: 0:06:02 lr: 0.000063 loss: 2.9367 (2.7469) grad_norm: 2.6031 (inf) time: 0.6283 [2021-03-28 09:02:26 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 690/1251] eta: 0:05:56 lr: 0.000063 loss: 2.8560 (2.7451) grad_norm: 2.6031 (inf) time: 0.6336 [2021-03-28 09:02:32 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 700/1251] eta: 0:05:49 lr: 0.000063 loss: 2.7681 (2.7432) grad_norm: 2.7681 (inf) time: 0.6361 [2021-03-28 09:02:38 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 710/1251] eta: 0:05:43 lr: 0.000063 loss: 2.8190 (2.7437) grad_norm: 2.7147 (inf) time: 0.6345 [2021-03-28 09:02:45 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 720/1251] eta: 0:05:37 lr: 0.000063 loss: 3.0406 (2.7476) grad_norm: 2.6749 (inf) time: 0.6312 [2021-03-28 09:02:51 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 730/1251] eta: 0:05:30 lr: 0.000063 loss: 2.9483 (2.7485) grad_norm: 2.8614 (inf) time: 0.6321 [2021-03-28 09:02:57 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 740/1251] eta: 0:05:24 lr: 0.000063 loss: 2.8343 (2.7495) grad_norm: 3.0578 (inf) time: 0.6363 [2021-03-28 09:03:04 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 750/1251] eta: 0:05:18 lr: 0.000063 loss: 2.9170 (2.7501) grad_norm: 3.0050 (inf) time: 0.6426 [2021-03-28 09:03:10 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 760/1251] eta: 0:05:11 lr: 0.000063 loss: 2.8607 (2.7487) grad_norm: 2.7490 (inf) time: 0.6375 [2021-03-28 09:03:16 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 770/1251] eta: 0:05:05 lr: 0.000063 loss: 2.7940 (2.7479) grad_norm: 2.8375 (inf) time: 0.6264 [2021-03-28 09:03:23 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 780/1251] eta: 0:04:58 lr: 0.000062 loss: 2.8951 (2.7496) grad_norm: 2.9327 (inf) time: 0.6288 [2021-03-28 09:03:29 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 790/1251] eta: 0:04:52 lr: 0.000062 loss: 2.8951 (2.7495) grad_norm: 2.8914 (inf) time: 0.6283 [2021-03-28 09:03:35 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 800/1251] eta: 0:04:46 lr: 0.000062 loss: 2.5339 (2.7464) grad_norm: 2.8927 (inf) time: 0.6286 [2021-03-28 09:03:41 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 810/1251] eta: 0:04:39 lr: 0.000062 loss: 2.7757 (2.7472) grad_norm: 2.8367 (inf) time: 0.6265 [2021-03-28 09:03:48 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 820/1251] eta: 0:04:33 lr: 0.000062 loss: 2.8214 (2.7475) grad_norm: 2.8367 (inf) time: 0.6291 [2021-03-28 09:03:54 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 830/1251] eta: 0:04:27 lr: 0.000062 loss: 2.8214 (2.7477) grad_norm: 2.9663 (inf) time: 0.6297 [2021-03-28 09:04:00 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 840/1251] eta: 0:04:20 lr: 0.000062 loss: 2.6014 (2.7461) grad_norm: 2.7484 (inf) time: 0.6279 [2021-03-28 09:04:07 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 850/1251] eta: 0:04:14 lr: 0.000062 loss: 2.6521 (2.7449) grad_norm: 2.8570 (inf) time: 0.6346 [2021-03-28 09:04:13 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 860/1251] eta: 0:04:07 lr: 0.000062 loss: 2.6521 (2.7444) grad_norm: 2.8570 (inf) time: 0.6303 [2021-03-28 09:04:19 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 870/1251] eta: 0:04:01 lr: 0.000062 loss: 2.6192 (2.7428) grad_norm: 2.7775 (inf) time: 0.6342 [2021-03-28 09:04:26 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 880/1251] eta: 0:03:55 lr: 0.000062 loss: 2.7132 (2.7439) grad_norm: 2.9851 (inf) time: 0.6371 [2021-03-28 09:04:32 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 890/1251] eta: 0:03:48 lr: 0.000062 loss: 2.8157 (2.7450) grad_norm: 2.9680 (inf) time: 0.6357 [2021-03-28 09:04:38 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 900/1251] eta: 0:03:42 lr: 0.000062 loss: 2.9417 (2.7466) grad_norm: 2.7160 (inf) time: 0.6368 [2021-03-28 09:04:45 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 910/1251] eta: 0:03:36 lr: 0.000062 loss: 2.9466 (2.7494) grad_norm: 2.7460 (inf) time: 0.6278 [2021-03-28 09:04:51 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 920/1251] eta: 0:03:29 lr: 0.000062 loss: 2.9096 (2.7497) grad_norm: 2.7951 (inf) time: 0.6256 [2021-03-28 09:04:57 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 930/1251] eta: 0:03:23 lr: 0.000062 loss: 2.8028 (2.7493) grad_norm: 2.7848 (inf) time: 0.6319 [2021-03-28 09:05:04 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 940/1251] eta: 0:03:17 lr: 0.000062 loss: 2.8614 (2.7498) grad_norm: 2.7130 (inf) time: 0.6365 [2021-03-28 09:05:10 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 950/1251] eta: 0:03:10 lr: 0.000062 loss: 2.9321 (2.7506) grad_norm: 2.6791 (inf) time: 0.6333 [2021-03-28 09:05:16 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 960/1251] eta: 0:03:04 lr: 0.000062 loss: 2.9321 (2.7520) grad_norm: 2.7189 (inf) time: 0.6324 [2021-03-28 09:05:23 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 970/1251] eta: 0:02:58 lr: 0.000062 loss: 2.9101 (2.7539) grad_norm: 2.8187 (inf) time: 0.6327 [2021-03-28 09:05:29 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 980/1251] eta: 0:02:51 lr: 0.000062 loss: 2.9564 (2.7546) grad_norm: 3.0670 (inf) time: 0.6300 [2021-03-28 09:05:35 swin_base_patch4_window7_224] INFO: Epoch: [255] [ 990/1251] eta: 0:02:45 lr: 0.000062 loss: 2.6893 (2.7526) grad_norm: 2.9061 (inf) time: 0.6251 [2021-03-28 09:05:42 swin_base_patch4_window7_224] INFO: Epoch: [255] [1000/1251] eta: 0:02:39 lr: 0.000062 loss: 2.5607 (2.7517) grad_norm: 2.7575 (inf) time: 0.6323 [2021-03-28 09:05:48 swin_base_patch4_window7_224] INFO: Epoch: [255] [1010/1251] eta: 0:02:32 lr: 0.000062 loss: 2.6601 (2.7506) grad_norm: 2.8183 (inf) time: 0.6358 [2021-03-28 09:05:54 swin_base_patch4_window7_224] INFO: Epoch: [255] [1020/1251] eta: 0:02:26 lr: 0.000062 loss: 2.7378 (2.7502) grad_norm: 2.8761 (inf) time: 0.6270 [2021-03-28 09:06:00 swin_base_patch4_window7_224] INFO: Epoch: [255] [1030/1251] eta: 0:02:20 lr: 0.000062 loss: 2.8843 (2.7508) grad_norm: 2.8842 (inf) time: 0.6286 [2021-03-28 09:06:07 swin_base_patch4_window7_224] INFO: Epoch: [255] [1040/1251] eta: 0:02:13 lr: 0.000062 loss: 2.7470 (2.7497) grad_norm: 2.8099 (inf) time: 0.6292 [2021-03-28 09:06:13 swin_base_patch4_window7_224] INFO: Epoch: [255] [1050/1251] eta: 0:02:07 lr: 0.000062 loss: 2.7470 (2.7495) grad_norm: 2.8099 (inf) time: 0.6256 [2021-03-28 09:06:19 swin_base_patch4_window7_224] INFO: Epoch: [255] [1060/1251] eta: 0:02:01 lr: 0.000062 loss: 2.8688 (2.7496) grad_norm: 2.8799 (inf) time: 0.6230 [2021-03-28 09:06:25 swin_base_patch4_window7_224] INFO: Epoch: [255] [1070/1251] eta: 0:01:54 lr: 0.000062 loss: 2.7323 (2.7502) grad_norm: 2.9877 (inf) time: 0.6254 [2021-03-28 09:06:32 swin_base_patch4_window7_224] INFO: Epoch: [255] [1080/1251] eta: 0:01:48 lr: 0.000062 loss: 2.6653 (2.7481) grad_norm: 2.8949 (inf) time: 0.6309 [2021-03-28 09:06:38 swin_base_patch4_window7_224] INFO: Epoch: [255] [1090/1251] eta: 0:01:41 lr: 0.000062 loss: 2.8291 (2.7497) grad_norm: 2.8949 (inf) time: 0.6278 [2021-03-28 09:06:44 swin_base_patch4_window7_224] INFO: Epoch: [255] [1100/1251] eta: 0:01:35 lr: 0.000062 loss: 2.8745 (2.7487) grad_norm: 3.1301 (inf) time: 0.6236 [2021-03-28 09:06:51 swin_base_patch4_window7_224] INFO: Epoch: [255] [1110/1251] eta: 0:01:29 lr: 0.000062 loss: 2.6893 (2.7492) grad_norm: 3.0065 (inf) time: 0.6253 [2021-03-28 09:06:57 swin_base_patch4_window7_224] INFO: Epoch: [255] [1120/1251] eta: 0:01:22 lr: 0.000062 loss: 2.9061 (2.7510) grad_norm: 2.9521 (inf) time: 0.6252 [2021-03-28 09:07:03 swin_base_patch4_window7_224] INFO: Epoch: [255] [1130/1251] eta: 0:01:16 lr: 0.000062 loss: 2.9574 (2.7516) grad_norm: 2.8217 (inf) time: 0.6310 [2021-03-28 09:07:09 swin_base_patch4_window7_224] INFO: Epoch: [255] [1140/1251] eta: 0:01:10 lr: 0.000062 loss: 2.8561 (2.7522) grad_norm: 2.6774 (inf) time: 0.6356 [2021-03-28 09:07:16 swin_base_patch4_window7_224] INFO: Epoch: [255] [1150/1251] eta: 0:01:03 lr: 0.000062 loss: 2.7821 (2.7516) grad_norm: 2.9776 (inf) time: 0.6269 [2021-03-28 09:07:22 swin_base_patch4_window7_224] INFO: Epoch: [255] [1160/1251] eta: 0:00:57 lr: 0.000062 loss: 2.6339 (2.7513) grad_norm: 3.1073 (inf) time: 0.6309 [2021-03-28 09:07:28 swin_base_patch4_window7_224] INFO: Epoch: [255] [1170/1251] eta: 0:00:51 lr: 0.000062 loss: 2.8918 (2.7527) grad_norm: 2.9989 (inf) time: 0.6344 [2021-03-28 09:07:35 swin_base_patch4_window7_224] INFO: Epoch: [255] [1180/1251] eta: 0:00:44 lr: 0.000062 loss: 2.9406 (2.7541) grad_norm: 2.9989 (inf) time: 0.6260 [2021-03-28 09:07:41 swin_base_patch4_window7_224] INFO: Epoch: [255] [1190/1251] eta: 0:00:38 lr: 0.000062 loss: 3.0023 (2.7551) grad_norm: 2.8710 (inf) time: 0.6283 [2021-03-28 09:07:47 swin_base_patch4_window7_224] INFO: Epoch: [255] [1200/1251] eta: 0:00:32 lr: 0.000062 loss: 2.9591 (2.7549) grad_norm: 2.9684 (inf) time: 0.6326 [2021-03-28 09:07:54 swin_base_patch4_window7_224] INFO: Epoch: [255] [1210/1251] eta: 0:00:25 lr: 0.000062 loss: 2.5931 (2.7547) grad_norm: 2.8695 (inf) time: 0.6359 [2021-03-28 09:08:00 swin_base_patch4_window7_224] INFO: Epoch: [255] [1220/1251] eta: 0:00:19 lr: 0.000062 loss: 2.9399 (2.7547) grad_norm: 2.8592 (inf) time: 0.6314 [2021-03-28 09:08:06 swin_base_patch4_window7_224] INFO: Epoch: [255] [1230/1251] eta: 0:00:13 lr: 0.000062 loss: 2.8820 (2.7548) grad_norm: 2.8592 (inf) time: 0.6282 [2021-03-28 09:08:12 swin_base_patch4_window7_224] INFO: Epoch: [255] [1240/1251] eta: 0:00:06 lr: 0.000062 loss: 2.8820 (2.7546) grad_norm: 2.8105 (inf) time: 0.6281 [2021-03-28 09:08:19 swin_base_patch4_window7_224] INFO: Epoch: [255] [1250/1251] eta: 0:00:00 lr: 0.000062 loss: 2.9643 (2.7564) grad_norm: 2.8499 (inf) time: 0.6182 [2021-03-28 09:09:46 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:18 loss: 0.6023 (0.6023) acc1: 85.9375 (85.9375) acc5: 98.4375 (98.4375) [2021-03-28 09:09:47 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.7096 (0.6953) acc1: 82.8125 (83.2386) acc5: 96.8750 (97.3011) [2021-03-28 09:09:49 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:06 loss: 0.7422 (0.7449) acc1: 82.8125 (82.1429) acc5: 96.8750 (96.8006) [2021-03-28 09:09:50 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7718 (0.7453) acc1: 82.8125 (82.1069) acc5: 96.8750 (96.6734) [2021-03-28 09:09:51 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7105 (0.7391) acc1: 82.8125 (82.5076) acc5: 96.8750 (96.6082) [2021-03-28 09:09:52 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7221 (0.7676) acc1: 81.2500 (81.9520) acc5: 96.8750 (96.3840) [2021-03-28 09:10:03 swin_base_patch4_window7_224] INFO: * Acc@1 82.978 Acc@5 96.328 loss 0.758 [2021-03-28 09:10:03 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.0% [2021-03-28 09:10:03 swin_base_patch4_window7_224] INFO: Max accuracy: 83.02% [2021-03-28 09:10:07 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 0/1251] eta: 1:32:24 lr: 0.000062 loss: 3.5238 (3.5238) grad_norm: 2.7838 (2.7838) time: 4.4324 [2021-03-28 09:10:14 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 10/1251] eta: 0:20:16 lr: 0.000062 loss: 2.9144 (2.9715) grad_norm: 2.7167 (2.7930) time: 0.9807 [2021-03-28 09:10:20 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 20/1251] eta: 0:16:38 lr: 0.000062 loss: 2.8460 (2.8431) grad_norm: 2.6970 (3.0941) time: 0.6303 [2021-03-28 09:10:26 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 30/1251] eta: 0:15:18 lr: 0.000062 loss: 2.9116 (2.8501) grad_norm: 2.7626 (3.0295) time: 0.6271 [2021-03-28 09:10:33 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 40/1251] eta: 0:14:33 lr: 0.000062 loss: 2.8670 (2.8225) grad_norm: 2.7841 (3.0823) time: 0.6271 [2021-03-28 09:10:39 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 50/1251] eta: 0:14:06 lr: 0.000062 loss: 2.6965 (2.7395) grad_norm: 3.0911 (3.7498) time: 0.6316 [2021-03-28 09:10:45 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 60/1251] eta: 0:13:45 lr: 0.000062 loss: 2.5596 (2.7096) grad_norm: 3.1083 (3.6159) time: 0.6341 [2021-03-28 09:10:52 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 70/1251] eta: 0:13:28 lr: 0.000061 loss: 2.7472 (2.7106) grad_norm: 2.9495 (3.5348) time: 0.6333 [2021-03-28 09:10:58 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 80/1251] eta: 0:13:14 lr: 0.000061 loss: 2.9109 (2.7266) grad_norm: 2.9495 (3.4596) time: 0.6363 [2021-03-28 09:11:04 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 90/1251] eta: 0:13:01 lr: 0.000061 loss: 2.7656 (2.7149) grad_norm: 2.8232 (3.3989) time: 0.6316 [2021-03-28 09:11:11 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 100/1251] eta: 0:12:49 lr: 0.000061 loss: 2.7162 (2.6903) grad_norm: 2.7696 (3.3578) time: 0.6257 [2021-03-28 09:11:17 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 110/1251] eta: 0:12:39 lr: 0.000061 loss: 2.5958 (2.6940) grad_norm: 2.7525 (3.3352) time: 0.6296 [2021-03-28 09:11:23 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 120/1251] eta: 0:12:30 lr: 0.000061 loss: 2.9201 (2.6852) grad_norm: 2.9315 (3.3441) time: 0.6389 [2021-03-28 09:11:30 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 130/1251] eta: 0:12:22 lr: 0.000061 loss: 2.6440 (2.6878) grad_norm: 3.1073 (3.3311) time: 0.6442 [2021-03-28 09:11:36 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 140/1251] eta: 0:12:12 lr: 0.000061 loss: 2.8353 (2.7048) grad_norm: 2.8921 (3.3005) time: 0.6328 [2021-03-28 09:11:42 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 150/1251] eta: 0:12:03 lr: 0.000061 loss: 2.8854 (2.7148) grad_norm: 2.9122 (3.2882) time: 0.6274 [2021-03-28 09:11:49 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 160/1251] eta: 0:11:54 lr: 0.000061 loss: 2.8606 (2.7216) grad_norm: 3.0018 (3.2757) time: 0.6278 [2021-03-28 09:11:55 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 170/1251] eta: 0:11:47 lr: 0.000061 loss: 2.7814 (2.7228) grad_norm: 2.9991 (3.2550) time: 0.6294 [2021-03-28 09:12:01 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 180/1251] eta: 0:11:39 lr: 0.000061 loss: 2.7802 (2.7263) grad_norm: 2.9230 (3.2325) time: 0.6349 [2021-03-28 09:12:08 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 190/1251] eta: 0:11:31 lr: 0.000061 loss: 2.7802 (2.7281) grad_norm: 2.6046 (3.2000) time: 0.6346 [2021-03-28 09:12:14 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 200/1251] eta: 0:11:24 lr: 0.000061 loss: 2.8087 (2.7293) grad_norm: 2.6046 (3.1870) time: 0.6355 [2021-03-28 09:12:20 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 210/1251] eta: 0:11:16 lr: 0.000061 loss: 2.6946 (2.7233) grad_norm: 2.7922 (3.1657) time: 0.6314 [2021-03-28 09:12:27 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 220/1251] eta: 0:11:09 lr: 0.000061 loss: 2.7344 (2.7297) grad_norm: 2.6125 (3.1492) time: 0.6304 [2021-03-28 09:12:33 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 230/1251] eta: 0:11:02 lr: 0.000061 loss: 2.8728 (2.7350) grad_norm: 2.6256 (3.1762) time: 0.6302 [2021-03-28 09:12:39 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 240/1251] eta: 0:10:55 lr: 0.000061 loss: 2.8838 (2.7303) grad_norm: 2.7177 (3.1605) time: 0.6328 [2021-03-28 09:12:46 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 250/1251] eta: 0:10:48 lr: 0.000061 loss: 2.6608 (2.7200) grad_norm: 2.8845 (3.1498) time: 0.6352 [2021-03-28 09:12:52 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 260/1251] eta: 0:10:40 lr: 0.000061 loss: 2.7395 (2.7254) grad_norm: 2.9181 (3.1519) time: 0.6323 [2021-03-28 09:12:58 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 270/1251] eta: 0:10:34 lr: 0.000061 loss: 2.9068 (2.7215) grad_norm: 2.8253 (3.1468) time: 0.6321 [2021-03-28 09:13:05 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 280/1251] eta: 0:10:26 lr: 0.000061 loss: 2.8162 (2.7218) grad_norm: 2.7855 (3.1397) time: 0.6319 [2021-03-28 09:13:11 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 290/1251] eta: 0:10:20 lr: 0.000061 loss: 2.5802 (2.7184) grad_norm: 2.8224 (3.1285) time: 0.6307 [2021-03-28 09:13:17 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 300/1251] eta: 0:10:12 lr: 0.000061 loss: 2.7643 (2.7253) grad_norm: 2.6939 (3.1192) time: 0.6274 [2021-03-28 09:13:23 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 310/1251] eta: 0:10:06 lr: 0.000061 loss: 2.8247 (2.7259) grad_norm: 2.8107 (3.1122) time: 0.6285 [2021-03-28 09:13:30 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 320/1251] eta: 0:09:59 lr: 0.000061 loss: 2.8247 (2.7282) grad_norm: 2.8345 (3.1032) time: 0.6330 [2021-03-28 09:13:36 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 330/1251] eta: 0:09:52 lr: 0.000061 loss: 2.8646 (2.7308) grad_norm: 2.9701 (3.1038) time: 0.6297 [2021-03-28 09:13:42 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 340/1251] eta: 0:09:45 lr: 0.000061 loss: 2.9033 (2.7370) grad_norm: 2.9701 (3.0989) time: 0.6275 [2021-03-28 09:13:49 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 350/1251] eta: 0:09:38 lr: 0.000061 loss: 2.8618 (2.7419) grad_norm: 2.8141 (3.0947) time: 0.6240 [2021-03-28 09:13:55 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 360/1251] eta: 0:09:31 lr: 0.000061 loss: 2.8241 (2.7448) grad_norm: 2.9022 (3.0977) time: 0.6226 [2021-03-28 09:14:01 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 370/1251] eta: 0:09:25 lr: 0.000061 loss: 2.7815 (2.7446) grad_norm: 2.8392 (3.0949) time: 0.6283 [2021-03-28 09:14:07 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 380/1251] eta: 0:09:18 lr: 0.000061 loss: 2.8761 (2.7503) grad_norm: 2.7635 (3.0864) time: 0.6300 [2021-03-28 09:14:14 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 390/1251] eta: 0:09:11 lr: 0.000061 loss: 2.8229 (2.7456) grad_norm: 2.7337 (3.0815) time: 0.6306 [2021-03-28 09:14:20 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 400/1251] eta: 0:09:05 lr: 0.000061 loss: 2.6066 (2.7412) grad_norm: 2.7334 (3.0754) time: 0.6289 [2021-03-28 09:14:26 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 410/1251] eta: 0:08:58 lr: 0.000061 loss: 2.9437 (2.7432) grad_norm: 2.8835 (3.0915) time: 0.6330 [2021-03-28 09:14:33 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 420/1251] eta: 0:08:51 lr: 0.000061 loss: 2.9097 (2.7392) grad_norm: 2.8268 (3.0881) time: 0.6343 [2021-03-28 09:14:39 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 430/1251] eta: 0:08:45 lr: 0.000061 loss: 2.7986 (2.7411) grad_norm: 2.8134 (3.0851) time: 0.6269 [2021-03-28 09:14:45 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 440/1251] eta: 0:08:38 lr: 0.000061 loss: 2.8665 (2.7421) grad_norm: 2.8195 (3.0910) time: 0.6285 [2021-03-28 09:14:52 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 450/1251] eta: 0:08:32 lr: 0.000061 loss: 2.9266 (2.7463) grad_norm: 2.8658 (3.0854) time: 0.6356 [2021-03-28 09:14:58 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 460/1251] eta: 0:08:25 lr: 0.000061 loss: 2.7957 (2.7432) grad_norm: 2.8959 (3.0822) time: 0.6374 [2021-03-28 09:15:04 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 470/1251] eta: 0:08:19 lr: 0.000061 loss: 2.7957 (2.7472) grad_norm: 2.7944 (3.0779) time: 0.6286 [2021-03-28 09:15:11 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 480/1251] eta: 0:08:12 lr: 0.000061 loss: 2.8986 (2.7481) grad_norm: 2.7895 (3.0805) time: 0.6258 [2021-03-28 09:15:17 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 490/1251] eta: 0:08:06 lr: 0.000061 loss: 2.8867 (2.7497) grad_norm: 3.0325 (3.0847) time: 0.6322 [2021-03-28 09:15:23 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 500/1251] eta: 0:07:59 lr: 0.000061 loss: 2.9217 (2.7511) grad_norm: 2.8941 (3.0835) time: 0.6299 [2021-03-28 09:15:29 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 510/1251] eta: 0:07:52 lr: 0.000061 loss: 2.9397 (2.7504) grad_norm: 2.8941 (3.0845) time: 0.6239 [2021-03-28 09:15:36 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 520/1251] eta: 0:07:46 lr: 0.000061 loss: 2.8675 (2.7497) grad_norm: 2.8856 (3.0889) time: 0.6233 [2021-03-28 09:15:42 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 530/1251] eta: 0:07:39 lr: 0.000061 loss: 2.7583 (2.7499) grad_norm: 2.8083 (3.0891) time: 0.6234 [2021-03-28 09:15:48 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 540/1251] eta: 0:07:33 lr: 0.000061 loss: 2.7583 (2.7475) grad_norm: 2.8283 (3.0874) time: 0.6330 [2021-03-28 09:15:55 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 550/1251] eta: 0:07:27 lr: 0.000061 loss: 2.4685 (2.7429) grad_norm: 2.9114 (3.0868) time: 0.6364 [2021-03-28 09:16:01 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 560/1251] eta: 0:07:20 lr: 0.000061 loss: 2.4566 (2.7403) grad_norm: 2.9844 (3.0849) time: 0.6312 [2021-03-28 09:16:07 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 570/1251] eta: 0:07:14 lr: 0.000061 loss: 2.6180 (2.7363) grad_norm: 2.7813 (3.0802) time: 0.6266 [2021-03-28 09:16:13 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 580/1251] eta: 0:07:07 lr: 0.000061 loss: 2.7097 (2.7386) grad_norm: 2.6504 (3.0818) time: 0.6279 [2021-03-28 09:16:20 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 590/1251] eta: 0:07:01 lr: 0.000061 loss: 2.9444 (2.7403) grad_norm: 2.7058 (3.0771) time: 0.6315 [2021-03-28 09:16:26 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 600/1251] eta: 0:06:54 lr: 0.000061 loss: 2.9444 (2.7402) grad_norm: 2.6587 (3.0723) time: 0.6318 [2021-03-28 09:16:32 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 610/1251] eta: 0:06:48 lr: 0.000061 loss: 2.8660 (2.7393) grad_norm: 2.7790 (3.0704) time: 0.6338 [2021-03-28 09:16:39 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 620/1251] eta: 0:06:41 lr: 0.000060 loss: 2.9228 (2.7418) grad_norm: 2.8904 (3.0843) time: 0.6288 [2021-03-28 09:16:45 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 630/1251] eta: 0:06:35 lr: 0.000060 loss: 2.9594 (2.7456) grad_norm: 2.6392 (3.0800) time: 0.6355 [2021-03-28 09:16:51 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 640/1251] eta: 0:06:29 lr: 0.000060 loss: 2.9453 (2.7434) grad_norm: 2.8686 (3.1039) time: 0.6327 [2021-03-28 09:16:58 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 650/1251] eta: 0:06:22 lr: 0.000060 loss: 2.5318 (2.7409) grad_norm: 2.9835 (3.1013) time: 0.6251 [2021-03-28 09:17:04 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 660/1251] eta: 0:06:16 lr: 0.000060 loss: 2.6749 (2.7378) grad_norm: 2.9625 (3.1138) time: 0.6363 [2021-03-28 09:17:10 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 670/1251] eta: 0:06:09 lr: 0.000060 loss: 2.6926 (2.7366) grad_norm: 3.0134 (3.1130) time: 0.6389 [2021-03-28 09:17:17 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 680/1251] eta: 0:06:03 lr: 0.000060 loss: 2.8445 (2.7388) grad_norm: 3.0345 (3.1125) time: 0.6347 [2021-03-28 09:17:23 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 690/1251] eta: 0:05:57 lr: 0.000060 loss: 2.8351 (2.7387) grad_norm: 2.8129 (3.1085) time: 0.6343 [2021-03-28 09:17:29 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 700/1251] eta: 0:05:50 lr: 0.000060 loss: 2.6752 (2.7382) grad_norm: 2.7444 (3.1072) time: 0.6311 [2021-03-28 09:17:36 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 710/1251] eta: 0:05:44 lr: 0.000060 loss: 2.6752 (2.7396) grad_norm: 2.8928 (3.1129) time: 0.6262 [2021-03-28 09:17:42 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 720/1251] eta: 0:05:37 lr: 0.000060 loss: 2.6489 (2.7354) grad_norm: 2.8926 (3.1101) time: 0.6287 [2021-03-28 09:17:48 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 730/1251] eta: 0:05:31 lr: 0.000060 loss: 2.7071 (2.7363) grad_norm: 2.8952 (3.1199) time: 0.6380 [2021-03-28 09:17:55 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 740/1251] eta: 0:05:25 lr: 0.000060 loss: 2.9126 (2.7381) grad_norm: 2.8495 (3.1165) time: 0.6382 [2021-03-28 09:18:01 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 750/1251] eta: 0:05:18 lr: 0.000060 loss: 2.8541 (2.7382) grad_norm: 2.8336 (3.1169) time: 0.6317 [2021-03-28 09:18:07 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 760/1251] eta: 0:05:12 lr: 0.000060 loss: 2.8172 (2.7375) grad_norm: 2.8251 (3.1116) time: 0.6353 [2021-03-28 09:18:14 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 770/1251] eta: 0:05:06 lr: 0.000060 loss: 2.8358 (2.7376) grad_norm: 2.7486 (3.1113) time: 0.6391 [2021-03-28 09:18:20 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 780/1251] eta: 0:04:59 lr: 0.000060 loss: 2.8497 (2.7396) grad_norm: 2.7486 (3.1082) time: 0.6304 [2021-03-28 09:18:26 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 790/1251] eta: 0:04:53 lr: 0.000060 loss: 2.8352 (2.7379) grad_norm: 2.7640 (3.1099) time: 0.6215 [2021-03-28 09:18:33 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 800/1251] eta: 0:04:46 lr: 0.000060 loss: 2.6441 (2.7373) grad_norm: 2.8461 (3.1107) time: 0.6243 [2021-03-28 09:18:39 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 810/1251] eta: 0:04:40 lr: 0.000060 loss: 2.6441 (2.7361) grad_norm: 2.8038 (3.1087) time: 0.6244 [2021-03-28 09:18:45 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 820/1251] eta: 0:04:33 lr: 0.000060 loss: 2.8328 (2.7373) grad_norm: 2.8038 (3.1083) time: 0.6302 [2021-03-28 09:18:51 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 830/1251] eta: 0:04:27 lr: 0.000060 loss: 2.8795 (2.7377) grad_norm: 2.6586 (3.1045) time: 0.6349 [2021-03-28 09:18:58 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 840/1251] eta: 0:04:21 lr: 0.000060 loss: 2.7830 (2.7378) grad_norm: 2.6582 (3.1053) time: 0.6262 [2021-03-28 09:19:04 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 850/1251] eta: 0:04:14 lr: 0.000060 loss: 2.6745 (2.7355) grad_norm: 2.9009 (3.1026) time: 0.6273 [2021-03-28 09:19:10 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 860/1251] eta: 0:04:08 lr: 0.000060 loss: 2.6986 (2.7380) grad_norm: 2.9009 (3.1040) time: 0.6331 [2021-03-28 09:19:17 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 870/1251] eta: 0:04:02 lr: 0.000060 loss: 2.8866 (2.7379) grad_norm: 2.9499 (3.1043) time: 0.6356 [2021-03-28 09:19:23 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 880/1251] eta: 0:03:55 lr: 0.000060 loss: 2.8447 (2.7382) grad_norm: 2.8480 (3.1017) time: 0.6366 [2021-03-28 09:19:29 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 890/1251] eta: 0:03:49 lr: 0.000060 loss: 2.9021 (2.7393) grad_norm: 2.9697 (3.1123) time: 0.6344 [2021-03-28 09:19:36 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 900/1251] eta: 0:03:43 lr: 0.000060 loss: 2.9716 (2.7395) grad_norm: 3.1569 (3.1143) time: 0.6302 [2021-03-28 09:19:42 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 910/1251] eta: 0:03:36 lr: 0.000060 loss: 2.8829 (2.7393) grad_norm: 3.0937 (3.1165) time: 0.6323 [2021-03-28 09:19:48 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 920/1251] eta: 0:03:30 lr: 0.000060 loss: 2.5231 (2.7353) grad_norm: 3.0192 (3.1190) time: 0.6350 [2021-03-28 09:19:55 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 930/1251] eta: 0:03:23 lr: 0.000060 loss: 2.7440 (2.7361) grad_norm: 2.9659 (3.1183) time: 0.6279 [2021-03-28 09:20:01 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 940/1251] eta: 0:03:17 lr: 0.000060 loss: 2.8988 (2.7367) grad_norm: 2.8485 (3.1162) time: 0.6258 [2021-03-28 09:20:07 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 950/1251] eta: 0:03:11 lr: 0.000060 loss: 2.9162 (2.7381) grad_norm: 2.8313 (3.1135) time: 0.6299 [2021-03-28 09:20:14 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 960/1251] eta: 0:03:04 lr: 0.000060 loss: 2.9133 (2.7394) grad_norm: 2.8291 (3.1130) time: 0.6314 [2021-03-28 09:20:20 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 970/1251] eta: 0:02:58 lr: 0.000060 loss: 2.8870 (2.7392) grad_norm: 2.8291 (3.1098) time: 0.6264 [2021-03-28 09:20:26 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 980/1251] eta: 0:02:52 lr: 0.000060 loss: 2.9092 (2.7395) grad_norm: 2.8588 (3.1090) time: 0.6215 [2021-03-28 09:20:32 swin_base_patch4_window7_224] INFO: Epoch: [256] [ 990/1251] eta: 0:02:45 lr: 0.000060 loss: 2.9092 (2.7399) grad_norm: 2.8482 (3.1057) time: 0.6282 [2021-03-28 09:20:39 swin_base_patch4_window7_224] INFO: Epoch: [256] [1000/1251] eta: 0:02:39 lr: 0.000060 loss: 2.8589 (2.7411) grad_norm: 2.7820 (3.1028) time: 0.6377 [2021-03-28 09:20:45 swin_base_patch4_window7_224] INFO: Epoch: [256] [1010/1251] eta: 0:02:32 lr: 0.000060 loss: 2.8251 (2.7420) grad_norm: 2.7820 (3.1002) time: 0.6377 [2021-03-28 09:20:51 swin_base_patch4_window7_224] INFO: Epoch: [256] [1020/1251] eta: 0:02:26 lr: 0.000060 loss: 2.8749 (2.7430) grad_norm: 2.8820 (3.0998) time: 0.6378 [2021-03-28 09:20:58 swin_base_patch4_window7_224] INFO: Epoch: [256] [1030/1251] eta: 0:02:20 lr: 0.000060 loss: 2.8749 (2.7446) grad_norm: 2.6624 (3.0960) time: 0.6347 [2021-03-28 09:21:04 swin_base_patch4_window7_224] INFO: Epoch: [256] [1040/1251] eta: 0:02:13 lr: 0.000060 loss: 2.7833 (2.7448) grad_norm: 2.8671 (3.0973) time: 0.6275 [2021-03-28 09:21:10 swin_base_patch4_window7_224] INFO: Epoch: [256] [1050/1251] eta: 0:02:07 lr: 0.000060 loss: 2.7739 (2.7452) grad_norm: 3.0124 (3.0981) time: 0.6288 [2021-03-28 09:21:17 swin_base_patch4_window7_224] INFO: Epoch: [256] [1060/1251] eta: 0:02:01 lr: 0.000060 loss: 2.7739 (2.7445) grad_norm: 2.6241 (3.0967) time: 0.6284 [2021-03-28 09:21:23 swin_base_patch4_window7_224] INFO: Epoch: [256] [1070/1251] eta: 0:01:54 lr: 0.000060 loss: 2.8404 (2.7444) grad_norm: 2.7981 (3.0968) time: 0.6296 [2021-03-28 09:21:29 swin_base_patch4_window7_224] INFO: Epoch: [256] [1080/1251] eta: 0:01:48 lr: 0.000060 loss: 2.8751 (2.7455) grad_norm: 2.7863 (3.0944) time: 0.6274 [2021-03-28 09:21:35 swin_base_patch4_window7_224] INFO: Epoch: [256] [1090/1251] eta: 0:01:42 lr: 0.000060 loss: 2.9033 (2.7466) grad_norm: 2.7182 (3.0928) time: 0.6271 [2021-03-28 09:21:42 swin_base_patch4_window7_224] INFO: Epoch: [256] [1100/1251] eta: 0:01:35 lr: 0.000060 loss: 2.8946 (2.7468) grad_norm: 2.8553 (3.0930) time: 0.6295 [2021-03-28 09:21:48 swin_base_patch4_window7_224] INFO: Epoch: [256] [1110/1251] eta: 0:01:29 lr: 0.000060 loss: 2.7957 (2.7475) grad_norm: 2.7520 (3.0912) time: 0.6261 [2021-03-28 09:21:54 swin_base_patch4_window7_224] INFO: Epoch: [256] [1120/1251] eta: 0:01:23 lr: 0.000060 loss: 2.7957 (2.7473) grad_norm: 2.7359 (3.0900) time: 0.6280 [2021-03-28 09:22:01 swin_base_patch4_window7_224] INFO: Epoch: [256] [1130/1251] eta: 0:01:16 lr: 0.000060 loss: 2.7435 (2.7453) grad_norm: 2.8269 (3.0894) time: 0.6301 [2021-03-28 09:22:07 swin_base_patch4_window7_224] INFO: Epoch: [256] [1140/1251] eta: 0:01:10 lr: 0.000060 loss: 2.6762 (2.7445) grad_norm: 2.9967 (3.0879) time: 0.6255 [2021-03-28 09:22:13 swin_base_patch4_window7_224] INFO: Epoch: [256] [1150/1251] eta: 0:01:04 lr: 0.000060 loss: 2.6795 (2.7443) grad_norm: 2.9113 (3.0870) time: 0.6258 [2021-03-28 09:22:19 swin_base_patch4_window7_224] INFO: Epoch: [256] [1160/1251] eta: 0:00:57 lr: 0.000060 loss: 2.5774 (2.7417) grad_norm: 2.9113 (3.0952) time: 0.6287 [2021-03-28 09:22:26 swin_base_patch4_window7_224] INFO: Epoch: [256] [1170/1251] eta: 0:00:51 lr: 0.000059 loss: 2.7715 (2.7430) grad_norm: 2.7658 (3.0937) time: 0.6292 [2021-03-28 09:22:32 swin_base_patch4_window7_224] INFO: Epoch: [256] [1180/1251] eta: 0:00:45 lr: 0.000059 loss: 2.9090 (2.7436) grad_norm: 2.7882 (3.0937) time: 0.6315 [2021-03-28 09:22:38 swin_base_patch4_window7_224] INFO: Epoch: [256] [1190/1251] eta: 0:00:38 lr: 0.000059 loss: 2.8613 (2.7448) grad_norm: 2.8141 (3.0924) time: 0.6309 [2021-03-28 09:22:45 swin_base_patch4_window7_224] INFO: Epoch: [256] [1200/1251] eta: 0:00:32 lr: 0.000059 loss: 2.9586 (2.7461) grad_norm: 2.8456 (3.0913) time: 0.6330 [2021-03-28 09:22:51 swin_base_patch4_window7_224] INFO: Epoch: [256] [1210/1251] eta: 0:00:25 lr: 0.000059 loss: 2.9257 (2.7467) grad_norm: 2.8903 (3.0898) time: 0.6322 [2021-03-28 09:22:57 swin_base_patch4_window7_224] INFO: Epoch: [256] [1220/1251] eta: 0:00:19 lr: 0.000059 loss: 2.7829 (2.7469) grad_norm: 2.7161 (3.0877) time: 0.6354 [2021-03-28 09:23:04 swin_base_patch4_window7_224] INFO: Epoch: [256] [1230/1251] eta: 0:00:13 lr: 0.000059 loss: 2.9401 (2.7478) grad_norm: 2.7290 (3.0860) time: 0.6330 [2021-03-28 09:23:10 swin_base_patch4_window7_224] INFO: Epoch: [256] [1240/1251] eta: 0:00:06 lr: 0.000059 loss: 2.9401 (2.7485) grad_norm: 2.7557 (3.0846) time: 0.6276 [2021-03-28 09:23:16 swin_base_patch4_window7_224] INFO: Epoch: [256] [1250/1251] eta: 0:00:00 lr: 0.000059 loss: 2.8640 (2.7491) grad_norm: 2.8088 (3.0896) time: 0.6236 [2021-03-28 09:23:30 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:15 loss: 1.1819 (1.1819) acc1: 76.5625 (76.5625) acc5: 89.0625 (89.0625) [2021-03-28 09:23:32 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8506 (0.8712) acc1: 79.6875 (80.3977) acc5: 95.3125 (95.1705) [2021-03-28 09:23:35 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8123 (0.8261) acc1: 81.2500 (81.6220) acc5: 95.3125 (95.4613) [2021-03-28 09:23:37 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.6713 (0.7869) acc1: 82.8125 (82.1069) acc5: 96.8750 (96.1190) [2021-03-28 09:23:39 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6589 (0.7660) acc1: 84.3750 (82.6601) acc5: 96.8750 (96.4177) [2021-03-28 09:23:40 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7045 (0.7649) acc1: 82.8125 (82.6240) acc5: 96.8750 (96.4160) [2021-03-28 09:24:00 swin_base_patch4_window7_224] INFO: * Acc@1 83.134 Acc@5 96.356 loss 0.751 [2021-03-28 09:24:00 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-28 09:24:00 swin_base_patch4_window7_224] INFO: Max accuracy: 83.13% [2021-03-28 09:24:04 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 0/1251] eta: 1:28:53 lr: 0.000059 loss: 3.1054 (3.1054) grad_norm: 2.4741 (2.4741) time: 4.2633 [2021-03-28 09:24:10 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 10/1251] eta: 0:19:53 lr: 0.000059 loss: 2.8098 (2.8226) grad_norm: 2.6731 (2.7262) time: 0.9615 [2021-03-28 09:24:17 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 20/1251] eta: 0:16:35 lr: 0.000059 loss: 2.8098 (2.7125) grad_norm: 2.8489 (3.4674) time: 0.6358 [2021-03-28 09:24:23 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 30/1251] eta: 0:15:15 lr: 0.000059 loss: 2.8255 (2.7017) grad_norm: 3.0150 (3.3617) time: 0.6333 [2021-03-28 09:24:29 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 40/1251] eta: 0:14:29 lr: 0.000059 loss: 2.8255 (2.7147) grad_norm: 2.8475 (3.2108) time: 0.6237 [2021-03-28 09:24:35 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 50/1251] eta: 0:14:03 lr: 0.000059 loss: 2.6726 (2.7272) grad_norm: 2.7948 (3.1559) time: 0.6285 [2021-03-28 09:24:42 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 60/1251] eta: 0:13:43 lr: 0.000059 loss: 2.8822 (2.7352) grad_norm: 2.7948 (3.1011) time: 0.6375 [2021-03-28 09:24:48 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 70/1251] eta: 0:13:26 lr: 0.000059 loss: 2.8697 (2.7157) grad_norm: 2.6030 (3.0805) time: 0.6348 [2021-03-28 09:24:54 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 80/1251] eta: 0:13:11 lr: 0.000059 loss: 2.7424 (2.7246) grad_norm: 2.6931 (3.0814) time: 0.6271 [2021-03-28 09:25:01 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 90/1251] eta: 0:12:59 lr: 0.000059 loss: 2.6858 (2.7153) grad_norm: 2.9423 (3.0920) time: 0.6306 [2021-03-28 09:25:07 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 100/1251] eta: 0:12:48 lr: 0.000059 loss: 2.6176 (2.7176) grad_norm: 2.9462 (3.0888) time: 0.6340 [2021-03-28 09:25:13 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 110/1251] eta: 0:12:38 lr: 0.000059 loss: 2.6176 (2.7108) grad_norm: 2.9693 (3.1339) time: 0.6313 [2021-03-28 09:25:20 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 120/1251] eta: 0:12:28 lr: 0.000059 loss: 2.7448 (2.7112) grad_norm: 3.0590 (3.1557) time: 0.6306 [2021-03-28 09:25:26 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 130/1251] eta: 0:12:19 lr: 0.000059 loss: 2.8398 (2.7126) grad_norm: 3.1300 (3.1571) time: 0.6314 [2021-03-28 09:25:32 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 140/1251] eta: 0:12:10 lr: 0.000059 loss: 2.8688 (2.7251) grad_norm: 2.9474 (3.1478) time: 0.6339 [2021-03-28 09:25:39 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 150/1251] eta: 0:12:01 lr: 0.000059 loss: 2.8688 (2.7214) grad_norm: 2.9304 (3.1420) time: 0.6282 [2021-03-28 09:25:45 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 160/1251] eta: 0:11:53 lr: 0.000059 loss: 2.7297 (2.7202) grad_norm: 3.0245 (3.1455) time: 0.6256 [2021-03-28 09:25:51 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 170/1251] eta: 0:11:44 lr: 0.000059 loss: 2.8424 (2.7323) grad_norm: 2.8906 (3.1469) time: 0.6290 [2021-03-28 09:25:57 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 180/1251] eta: 0:11:36 lr: 0.000059 loss: 2.8313 (2.7317) grad_norm: 2.8630 (3.1436) time: 0.6267 [2021-03-28 09:26:04 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 190/1251] eta: 0:11:29 lr: 0.000059 loss: 2.7795 (2.7280) grad_norm: 2.8392 (3.1466) time: 0.6292 [2021-03-28 09:26:10 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 200/1251] eta: 0:11:22 lr: 0.000059 loss: 2.6377 (2.7195) grad_norm: 3.0913 (3.1487) time: 0.6353 [2021-03-28 09:26:17 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 210/1251] eta: 0:11:15 lr: 0.000059 loss: 2.6675 (2.7229) grad_norm: 2.8836 (3.1340) time: 0.6363 [2021-03-28 09:26:23 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 220/1251] eta: 0:11:07 lr: 0.000059 loss: 2.8549 (2.7279) grad_norm: 2.8157 (3.1258) time: 0.6292 [2021-03-28 09:26:29 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 230/1251] eta: 0:11:00 lr: 0.000059 loss: 2.6574 (2.7252) grad_norm: 2.8395 (3.1137) time: 0.6307 [2021-03-28 09:26:35 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 240/1251] eta: 0:10:53 lr: 0.000059 loss: 2.5564 (2.7234) grad_norm: 2.9452 (3.1157) time: 0.6343 [2021-03-28 09:26:42 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 250/1251] eta: 0:10:46 lr: 0.000059 loss: 2.5304 (2.7151) grad_norm: 3.0177 (3.1131) time: 0.6298 [2021-03-28 09:26:48 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 260/1251] eta: 0:10:39 lr: 0.000059 loss: 2.7004 (2.7155) grad_norm: 3.1457 (inf) time: 0.6285 [2021-03-28 09:26:54 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 270/1251] eta: 0:10:32 lr: 0.000059 loss: 2.7441 (2.7176) grad_norm: 3.0359 (inf) time: 0.6308 [2021-03-28 09:27:01 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 280/1251] eta: 0:10:25 lr: 0.000059 loss: 2.8739 (2.7228) grad_norm: 2.8373 (inf) time: 0.6317 [2021-03-28 09:27:07 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 290/1251] eta: 0:10:18 lr: 0.000059 loss: 2.6633 (2.7221) grad_norm: 3.0789 (inf) time: 0.6274 [2021-03-28 09:27:13 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 300/1251] eta: 0:10:11 lr: 0.000059 loss: 2.6870 (2.7286) grad_norm: 2.7815 (inf) time: 0.6261 [2021-03-28 09:27:20 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 310/1251] eta: 0:10:04 lr: 0.000059 loss: 2.9058 (2.7320) grad_norm: 2.7571 (inf) time: 0.6288 [2021-03-28 09:27:26 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 320/1251] eta: 0:09:57 lr: 0.000059 loss: 2.7894 (2.7310) grad_norm: 2.8151 (inf) time: 0.6272 [2021-03-28 09:27:32 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 330/1251] eta: 0:09:50 lr: 0.000059 loss: 2.8575 (2.7330) grad_norm: 2.8151 (inf) time: 0.6291 [2021-03-28 09:27:38 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 340/1251] eta: 0:09:44 lr: 0.000059 loss: 2.9063 (2.7317) grad_norm: 2.9806 (inf) time: 0.6315 [2021-03-28 09:27:45 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 350/1251] eta: 0:09:37 lr: 0.000059 loss: 2.7504 (2.7308) grad_norm: 2.8221 (inf) time: 0.6263 [2021-03-28 09:27:51 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 360/1251] eta: 0:09:30 lr: 0.000059 loss: 2.9592 (2.7314) grad_norm: 2.9553 (inf) time: 0.6255 [2021-03-28 09:27:57 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 370/1251] eta: 0:09:23 lr: 0.000059 loss: 2.7796 (2.7257) grad_norm: 3.0381 (inf) time: 0.6233 [2021-03-28 09:28:03 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 380/1251] eta: 0:09:17 lr: 0.000059 loss: 2.7119 (2.7301) grad_norm: 3.1060 (inf) time: 0.6260 [2021-03-28 09:28:10 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 390/1251] eta: 0:09:10 lr: 0.000059 loss: 2.7683 (2.7292) grad_norm: 3.3298 (inf) time: 0.6311 [2021-03-28 09:28:16 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 400/1251] eta: 0:09:03 lr: 0.000059 loss: 2.4986 (2.7227) grad_norm: 3.3513 (inf) time: 0.6268 [2021-03-28 09:28:22 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 410/1251] eta: 0:08:57 lr: 0.000059 loss: 2.6155 (2.7239) grad_norm: 2.8211 (inf) time: 0.6284 [2021-03-28 09:28:29 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 420/1251] eta: 0:08:50 lr: 0.000059 loss: 2.8421 (2.7254) grad_norm: 2.7913 (inf) time: 0.6311 [2021-03-28 09:28:35 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 430/1251] eta: 0:08:44 lr: 0.000059 loss: 2.7373 (2.7245) grad_norm: 2.7995 (inf) time: 0.6334 [2021-03-28 09:28:41 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 440/1251] eta: 0:08:37 lr: 0.000059 loss: 2.7141 (2.7243) grad_norm: 2.9023 (inf) time: 0.6374 [2021-03-28 09:28:48 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 450/1251] eta: 0:08:31 lr: 0.000059 loss: 2.8178 (2.7247) grad_norm: 2.8028 (inf) time: 0.6345 [2021-03-28 09:28:54 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 460/1251] eta: 0:08:24 lr: 0.000059 loss: 2.8178 (2.7234) grad_norm: 2.8120 (inf) time: 0.6302 [2021-03-28 09:29:00 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 470/1251] eta: 0:08:18 lr: 0.000058 loss: 2.8318 (2.7279) grad_norm: 2.9703 (inf) time: 0.6239 [2021-03-28 09:29:07 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 480/1251] eta: 0:08:11 lr: 0.000058 loss: 2.9445 (2.7294) grad_norm: 2.9318 (inf) time: 0.6276 [2021-03-28 09:29:13 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 490/1251] eta: 0:08:05 lr: 0.000058 loss: 2.7528 (2.7275) grad_norm: 2.8313 (inf) time: 0.6325 [2021-03-28 09:29:19 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 500/1251] eta: 0:07:58 lr: 0.000058 loss: 2.7528 (2.7288) grad_norm: 2.9115 (inf) time: 0.6307 [2021-03-28 09:29:25 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 510/1251] eta: 0:07:52 lr: 0.000058 loss: 2.9155 (2.7308) grad_norm: 2.8617 (inf) time: 0.6308 [2021-03-28 09:29:32 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 520/1251] eta: 0:07:45 lr: 0.000058 loss: 2.8547 (2.7326) grad_norm: 2.8035 (inf) time: 0.6299 [2021-03-28 09:29:38 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 530/1251] eta: 0:07:39 lr: 0.000058 loss: 2.8452 (2.7311) grad_norm: 2.7996 (inf) time: 0.6300 [2021-03-28 09:29:44 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 540/1251] eta: 0:07:32 lr: 0.000058 loss: 2.8452 (2.7306) grad_norm: 2.7996 (inf) time: 0.6311 [2021-03-28 09:29:51 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 550/1251] eta: 0:07:26 lr: 0.000058 loss: 2.9557 (2.7344) grad_norm: 3.0186 (inf) time: 0.6420 [2021-03-28 09:29:57 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 560/1251] eta: 0:07:20 lr: 0.000058 loss: 2.8832 (2.7341) grad_norm: 3.0380 (inf) time: 0.6508 [2021-03-28 09:30:04 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 570/1251] eta: 0:07:13 lr: 0.000058 loss: 2.8587 (2.7372) grad_norm: 3.0552 (inf) time: 0.6384 [2021-03-28 09:30:10 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 580/1251] eta: 0:07:07 lr: 0.000058 loss: 2.8587 (2.7355) grad_norm: 3.2834 (inf) time: 0.6281 [2021-03-28 09:30:16 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 590/1251] eta: 0:07:00 lr: 0.000058 loss: 2.5607 (2.7332) grad_norm: 2.9172 (inf) time: 0.6269 [2021-03-28 09:30:22 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 600/1251] eta: 0:06:54 lr: 0.000058 loss: 2.7362 (2.7333) grad_norm: 2.7444 (inf) time: 0.6268 [2021-03-28 09:30:29 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 610/1251] eta: 0:06:48 lr: 0.000058 loss: 2.5901 (2.7294) grad_norm: 2.7484 (inf) time: 0.6343 [2021-03-28 09:30:35 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 620/1251] eta: 0:06:41 lr: 0.000058 loss: 2.5889 (2.7283) grad_norm: 2.7979 (inf) time: 0.6326 [2021-03-28 09:30:41 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 630/1251] eta: 0:06:35 lr: 0.000058 loss: 2.7452 (2.7266) grad_norm: 2.7616 (inf) time: 0.6298 [2021-03-28 09:30:48 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 640/1251] eta: 0:06:28 lr: 0.000058 loss: 2.8995 (2.7294) grad_norm: 2.6980 (inf) time: 0.6314 [2021-03-28 09:30:54 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 650/1251] eta: 0:06:22 lr: 0.000058 loss: 2.9288 (2.7327) grad_norm: 2.7916 (inf) time: 0.6298 [2021-03-28 09:31:00 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 660/1251] eta: 0:06:16 lr: 0.000058 loss: 2.9706 (2.7365) grad_norm: 2.8880 (inf) time: 0.6310 [2021-03-28 09:31:07 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 670/1251] eta: 0:06:09 lr: 0.000058 loss: 2.8410 (2.7358) grad_norm: 3.1154 (inf) time: 0.6291 [2021-03-28 09:31:13 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 680/1251] eta: 0:06:03 lr: 0.000058 loss: 2.7538 (2.7357) grad_norm: 3.1154 (inf) time: 0.6356 [2021-03-28 09:31:20 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 690/1251] eta: 0:05:57 lr: 0.000058 loss: 2.9819 (2.7407) grad_norm: 2.8802 (inf) time: 0.6437 [2021-03-28 09:31:26 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 700/1251] eta: 0:05:50 lr: 0.000058 loss: 2.9117 (2.7412) grad_norm: 2.9240 (inf) time: 0.6397 [2021-03-28 09:31:32 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 710/1251] eta: 0:05:44 lr: 0.000058 loss: 2.7202 (2.7374) grad_norm: 2.8942 (inf) time: 0.6312 [2021-03-28 09:31:38 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 720/1251] eta: 0:05:37 lr: 0.000058 loss: 2.5508 (2.7369) grad_norm: 2.8942 (inf) time: 0.6267 [2021-03-28 09:31:45 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 730/1251] eta: 0:05:31 lr: 0.000058 loss: 2.7894 (2.7385) grad_norm: 2.9475 (inf) time: 0.6273 [2021-03-28 09:31:51 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 740/1251] eta: 0:05:25 lr: 0.000058 loss: 2.8973 (2.7419) grad_norm: 2.9314 (inf) time: 0.6335 [2021-03-28 09:31:58 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 750/1251] eta: 0:05:18 lr: 0.000058 loss: 2.8374 (2.7412) grad_norm: 2.9188 (inf) time: 0.6401 [2021-03-28 09:32:04 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 760/1251] eta: 0:05:12 lr: 0.000058 loss: 2.7685 (2.7424) grad_norm: 3.2578 (inf) time: 0.6414 [2021-03-28 09:32:10 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 770/1251] eta: 0:05:05 lr: 0.000058 loss: 2.8530 (2.7426) grad_norm: 3.2573 (inf) time: 0.6394 [2021-03-28 09:32:17 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 780/1251] eta: 0:04:59 lr: 0.000058 loss: 2.8226 (2.7447) grad_norm: 3.1996 (inf) time: 0.6330 [2021-03-28 09:32:23 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 790/1251] eta: 0:04:53 lr: 0.000058 loss: 2.8239 (2.7458) grad_norm: 3.1925 (inf) time: 0.6251 [2021-03-28 09:32:29 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 800/1251] eta: 0:04:46 lr: 0.000058 loss: 2.8474 (2.7463) grad_norm: 3.0769 (inf) time: 0.6299 [2021-03-28 09:32:35 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 810/1251] eta: 0:04:40 lr: 0.000058 loss: 2.9139 (2.7470) grad_norm: 2.9465 (inf) time: 0.6324 [2021-03-28 09:32:42 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 820/1251] eta: 0:04:34 lr: 0.000058 loss: 2.6603 (2.7447) grad_norm: 3.0064 (inf) time: 0.6307 [2021-03-28 09:32:48 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 830/1251] eta: 0:04:27 lr: 0.000058 loss: 2.7018 (2.7455) grad_norm: 3.0119 (inf) time: 0.6285 [2021-03-28 09:32:54 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 840/1251] eta: 0:04:21 lr: 0.000058 loss: 2.9092 (2.7477) grad_norm: 2.8225 (inf) time: 0.6268 [2021-03-28 09:33:01 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 850/1251] eta: 0:04:14 lr: 0.000058 loss: 2.8859 (2.7470) grad_norm: 2.8711 (inf) time: 0.6303 [2021-03-28 09:33:07 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 860/1251] eta: 0:04:08 lr: 0.000058 loss: 2.7409 (2.7459) grad_norm: 2.8711 (inf) time: 0.6328 [2021-03-28 09:33:13 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 870/1251] eta: 0:04:02 lr: 0.000058 loss: 2.8898 (2.7477) grad_norm: 2.9057 (inf) time: 0.6377 [2021-03-28 09:33:20 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 880/1251] eta: 0:03:55 lr: 0.000058 loss: 2.9394 (2.7485) grad_norm: 2.9553 (inf) time: 0.6405 [2021-03-28 09:33:26 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 890/1251] eta: 0:03:49 lr: 0.000058 loss: 2.9742 (2.7507) grad_norm: 2.9553 (inf) time: 0.6399 [2021-03-28 09:33:32 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 900/1251] eta: 0:03:43 lr: 0.000058 loss: 2.9742 (2.7515) grad_norm: 3.0787 (inf) time: 0.6321 [2021-03-28 09:33:39 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 910/1251] eta: 0:03:36 lr: 0.000058 loss: 2.8596 (2.7513) grad_norm: 2.8875 (inf) time: 0.6298 [2021-03-28 09:33:45 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 920/1251] eta: 0:03:30 lr: 0.000058 loss: 2.8596 (2.7525) grad_norm: 2.9408 (inf) time: 0.6318 [2021-03-28 09:33:51 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 930/1251] eta: 0:03:23 lr: 0.000058 loss: 2.8884 (2.7523) grad_norm: 2.9909 (inf) time: 0.6271 [2021-03-28 09:33:58 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 940/1251] eta: 0:03:17 lr: 0.000058 loss: 2.7881 (2.7521) grad_norm: 2.9344 (inf) time: 0.6237 [2021-03-28 09:34:04 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 950/1251] eta: 0:03:11 lr: 0.000058 loss: 2.7025 (2.7509) grad_norm: 2.9344 (inf) time: 0.6273 [2021-03-28 09:34:10 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 960/1251] eta: 0:03:04 lr: 0.000058 loss: 2.5546 (2.7486) grad_norm: 2.8788 (inf) time: 0.6294 [2021-03-28 09:34:16 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 970/1251] eta: 0:02:58 lr: 0.000058 loss: 2.7129 (2.7499) grad_norm: 2.8788 (inf) time: 0.6252 [2021-03-28 09:34:23 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 980/1251] eta: 0:02:52 lr: 0.000058 loss: 2.8940 (2.7481) grad_norm: 2.6843 (inf) time: 0.6309 [2021-03-28 09:34:29 swin_base_patch4_window7_224] INFO: Epoch: [257] [ 990/1251] eta: 0:02:45 lr: 0.000058 loss: 2.7473 (2.7468) grad_norm: 2.7823 (inf) time: 0.6373 [2021-03-28 09:34:36 swin_base_patch4_window7_224] INFO: Epoch: [257] [1000/1251] eta: 0:02:39 lr: 0.000058 loss: 2.7473 (2.7473) grad_norm: 2.8069 (inf) time: 0.6366 [2021-03-28 09:34:42 swin_base_patch4_window7_224] INFO: Epoch: [257] [1010/1251] eta: 0:02:33 lr: 0.000058 loss: 2.7304 (2.7468) grad_norm: 2.8929 (inf) time: 0.6313 [2021-03-28 09:34:48 swin_base_patch4_window7_224] INFO: Epoch: [257] [1020/1251] eta: 0:02:26 lr: 0.000058 loss: 2.6796 (2.7470) grad_norm: 2.9503 (inf) time: 0.6328 [2021-03-28 09:34:54 swin_base_patch4_window7_224] INFO: Epoch: [257] [1030/1251] eta: 0:02:20 lr: 0.000058 loss: 2.6796 (2.7465) grad_norm: 2.8317 (inf) time: 0.6313 [2021-03-28 09:35:01 swin_base_patch4_window7_224] INFO: Epoch: [257] [1040/1251] eta: 0:02:13 lr: 0.000057 loss: 2.7652 (2.7474) grad_norm: 2.8723 (inf) time: 0.6323 [2021-03-28 09:35:07 swin_base_patch4_window7_224] INFO: Epoch: [257] [1050/1251] eta: 0:02:07 lr: 0.000057 loss: 2.8280 (2.7467) grad_norm: 2.8723 (inf) time: 0.6340 [2021-03-28 09:35:13 swin_base_patch4_window7_224] INFO: Epoch: [257] [1060/1251] eta: 0:02:01 lr: 0.000057 loss: 2.7448 (2.7464) grad_norm: 2.7429 (inf) time: 0.6287 [2021-03-28 09:35:20 swin_base_patch4_window7_224] INFO: Epoch: [257] [1070/1251] eta: 0:01:54 lr: 0.000057 loss: 2.8466 (2.7465) grad_norm: 2.8005 (inf) time: 0.6294 [2021-03-28 09:35:26 swin_base_patch4_window7_224] INFO: Epoch: [257] [1080/1251] eta: 0:01:48 lr: 0.000057 loss: 2.8466 (2.7456) grad_norm: 2.8083 (inf) time: 0.6236 [2021-03-28 09:35:32 swin_base_patch4_window7_224] INFO: Epoch: [257] [1090/1251] eta: 0:01:42 lr: 0.000057 loss: 2.7009 (2.7452) grad_norm: 2.8083 (inf) time: 0.6223 [2021-03-28 09:35:38 swin_base_patch4_window7_224] INFO: Epoch: [257] [1100/1251] eta: 0:01:35 lr: 0.000057 loss: 2.7860 (2.7453) grad_norm: 2.8260 (inf) time: 0.6251 [2021-03-28 09:35:45 swin_base_patch4_window7_224] INFO: Epoch: [257] [1110/1251] eta: 0:01:29 lr: 0.000057 loss: 2.7201 (2.7426) grad_norm: 3.0872 (inf) time: 0.6321 [2021-03-28 09:35:51 swin_base_patch4_window7_224] INFO: Epoch: [257] [1120/1251] eta: 0:01:23 lr: 0.000057 loss: 2.6812 (2.7435) grad_norm: 3.2058 (inf) time: 0.6368 [2021-03-28 09:35:57 swin_base_patch4_window7_224] INFO: Epoch: [257] [1130/1251] eta: 0:01:16 lr: 0.000057 loss: 2.8128 (2.7428) grad_norm: 3.1129 (inf) time: 0.6326 [2021-03-28 09:36:04 swin_base_patch4_window7_224] INFO: Epoch: [257] [1140/1251] eta: 0:01:10 lr: 0.000057 loss: 2.7062 (2.7410) grad_norm: 2.7995 (inf) time: 0.6333 [2021-03-28 09:36:10 swin_base_patch4_window7_224] INFO: Epoch: [257] [1150/1251] eta: 0:01:04 lr: 0.000057 loss: 2.8947 (2.7432) grad_norm: 2.8115 (inf) time: 0.6375 [2021-03-28 09:36:16 swin_base_patch4_window7_224] INFO: Epoch: [257] [1160/1251] eta: 0:00:57 lr: 0.000057 loss: 2.9383 (2.7430) grad_norm: 2.9135 (inf) time: 0.6293 [2021-03-28 09:36:23 swin_base_patch4_window7_224] INFO: Epoch: [257] [1170/1251] eta: 0:00:51 lr: 0.000057 loss: 2.5591 (2.7420) grad_norm: 2.8870 (inf) time: 0.6280 [2021-03-28 09:36:29 swin_base_patch4_window7_224] INFO: Epoch: [257] [1180/1251] eta: 0:00:45 lr: 0.000057 loss: 2.7734 (2.7436) grad_norm: 3.1390 (inf) time: 0.6384 [2021-03-28 09:36:36 swin_base_patch4_window7_224] INFO: Epoch: [257] [1190/1251] eta: 0:00:38 lr: 0.000057 loss: 2.9561 (2.7455) grad_norm: 3.1390 (inf) time: 0.6375 [2021-03-28 09:36:42 swin_base_patch4_window7_224] INFO: Epoch: [257] [1200/1251] eta: 0:00:32 lr: 0.000057 loss: 3.1384 (2.7463) grad_norm: 2.9581 (inf) time: 0.6325 [2021-03-28 09:36:48 swin_base_patch4_window7_224] INFO: Epoch: [257] [1210/1251] eta: 0:00:26 lr: 0.000057 loss: 3.0366 (2.7482) grad_norm: 3.0420 (inf) time: 0.6265 [2021-03-28 09:36:54 swin_base_patch4_window7_224] INFO: Epoch: [257] [1220/1251] eta: 0:00:19 lr: 0.000057 loss: 2.9700 (2.7500) grad_norm: 3.0285 (inf) time: 0.6221 [2021-03-28 09:37:01 swin_base_patch4_window7_224] INFO: Epoch: [257] [1230/1251] eta: 0:00:13 lr: 0.000057 loss: 2.9641 (2.7512) grad_norm: 3.0478 (inf) time: 0.6256 [2021-03-28 09:37:07 swin_base_patch4_window7_224] INFO: Epoch: [257] [1240/1251] eta: 0:00:06 lr: 0.000057 loss: 2.7353 (2.7487) grad_norm: 3.0478 (inf) time: 0.6281 [2021-03-28 09:37:13 swin_base_patch4_window7_224] INFO: Epoch: [257] [1250/1251] eta: 0:00:00 lr: 0.000057 loss: 2.6725 (2.7484) grad_norm: 3.1321 (inf) time: 0.6267 [2021-03-28 09:37:27 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:51 loss: 0.5658 (0.5658) acc1: 89.0625 (89.0625) acc5: 98.4375 (98.4375) [2021-03-28 09:37:29 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8143 (0.7506) acc1: 81.2500 (82.9545) acc5: 96.8750 (96.4489) [2021-03-28 09:37:32 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7787 (0.7440) acc1: 81.2500 (83.1845) acc5: 96.8750 (96.5774) [2021-03-28 09:37:34 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7128 (0.7221) acc1: 81.2500 (83.5685) acc5: 96.8750 (96.7238) [2021-03-28 09:37:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7027 (0.7444) acc1: 81.2500 (83.0030) acc5: 96.8750 (96.3034) [2021-03-28 09:37:37 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7306 (0.7613) acc1: 81.2500 (82.2080) acc5: 96.8750 (96.3520) [2021-03-28 09:37:55 swin_base_patch4_window7_224] INFO: * Acc@1 83.078 Acc@5 96.284 loss 0.746 [2021-03-28 09:37:55 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-28 09:37:55 swin_base_patch4_window7_224] INFO: Max accuracy: 83.13% [2021-03-28 09:37:59 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 0/1251] eta: 1:32:19 lr: 0.000057 loss: 2.8414 (2.8414) grad_norm: 2.8161 (2.8161) time: 4.4279 [2021-03-28 09:38:06 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 10/1251] eta: 0:20:17 lr: 0.000057 loss: 2.7389 (2.7171) grad_norm: 2.8138 (2.7884) time: 0.9813 [2021-03-28 09:38:12 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 20/1251] eta: 0:16:47 lr: 0.000057 loss: 2.7389 (2.6712) grad_norm: 2.7480 (2.8341) time: 0.6379 [2021-03-28 09:38:18 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 30/1251] eta: 0:15:33 lr: 0.000057 loss: 2.8198 (2.7349) grad_norm: 2.8634 (2.9396) time: 0.6450 [2021-03-28 09:38:25 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 40/1251] eta: 0:14:46 lr: 0.000057 loss: 2.6086 (2.6954) grad_norm: 3.0062 (2.9107) time: 0.6409 [2021-03-28 09:38:31 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 50/1251] eta: 0:14:13 lr: 0.000057 loss: 2.6348 (2.7361) grad_norm: 3.0062 (3.6015) time: 0.6267 [2021-03-28 09:38:37 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 60/1251] eta: 0:13:48 lr: 0.000057 loss: 2.7863 (2.7240) grad_norm: 3.0174 (3.5271) time: 0.6215 [2021-03-28 09:38:44 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 70/1251] eta: 0:13:33 lr: 0.000057 loss: 2.6262 (2.6959) grad_norm: 2.8854 (3.4305) time: 0.6332 [2021-03-28 09:38:50 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 80/1251] eta: 0:13:19 lr: 0.000057 loss: 2.6649 (2.7020) grad_norm: 2.7962 (3.3536) time: 0.6431 [2021-03-28 09:38:56 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 90/1251] eta: 0:13:06 lr: 0.000057 loss: 2.6894 (2.6932) grad_norm: 2.8330 (3.3102) time: 0.6373 [2021-03-28 09:39:03 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 100/1251] eta: 0:12:53 lr: 0.000057 loss: 2.8627 (2.7107) grad_norm: 2.9059 (3.2808) time: 0.6311 [2021-03-28 09:39:09 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 110/1251] eta: 0:12:42 lr: 0.000057 loss: 2.9908 (2.7297) grad_norm: 2.8949 (3.2882) time: 0.6281 [2021-03-28 09:39:15 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 120/1251] eta: 0:12:32 lr: 0.000057 loss: 2.9018 (2.7223) grad_norm: 2.9596 (3.2906) time: 0.6278 [2021-03-28 09:39:22 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 130/1251] eta: 0:12:22 lr: 0.000057 loss: 2.8319 (2.7320) grad_norm: 2.9596 (3.2684) time: 0.6285 [2021-03-28 09:39:28 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 140/1251] eta: 0:12:12 lr: 0.000057 loss: 2.7730 (2.7193) grad_norm: 2.6937 (3.2350) time: 0.6261 [2021-03-28 09:39:34 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 150/1251] eta: 0:12:04 lr: 0.000057 loss: 2.8159 (2.7298) grad_norm: 2.6526 (3.2070) time: 0.6280 [2021-03-28 09:39:40 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 160/1251] eta: 0:11:56 lr: 0.000057 loss: 2.8776 (2.7312) grad_norm: 2.8015 (3.1959) time: 0.6334 [2021-03-28 09:39:47 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 170/1251] eta: 0:11:47 lr: 0.000057 loss: 2.8394 (2.7346) grad_norm: 2.9712 (3.1941) time: 0.6302 [2021-03-28 09:39:53 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 180/1251] eta: 0:11:40 lr: 0.000057 loss: 2.6595 (2.7231) grad_norm: 2.9608 (3.1883) time: 0.6335 [2021-03-28 09:39:59 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 190/1251] eta: 0:11:32 lr: 0.000057 loss: 2.5956 (2.7286) grad_norm: 2.9608 (3.1878) time: 0.6357 [2021-03-28 09:40:06 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 200/1251] eta: 0:11:24 lr: 0.000057 loss: 2.7759 (2.7354) grad_norm: 3.0063 (3.1914) time: 0.6305 [2021-03-28 09:40:12 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 210/1251] eta: 0:11:16 lr: 0.000057 loss: 2.9114 (2.7479) grad_norm: 2.9512 (3.1821) time: 0.6285 [2021-03-28 09:40:18 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 220/1251] eta: 0:11:09 lr: 0.000057 loss: 2.9934 (2.7485) grad_norm: 2.6987 (3.2497) time: 0.6297 [2021-03-28 09:40:25 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 230/1251] eta: 0:11:02 lr: 0.000057 loss: 2.6835 (2.7344) grad_norm: 2.8136 (3.2354) time: 0.6300 [2021-03-28 09:40:31 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 240/1251] eta: 0:10:54 lr: 0.000057 loss: 2.6961 (2.7382) grad_norm: 2.7914 (3.2360) time: 0.6236 [2021-03-28 09:40:37 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 250/1251] eta: 0:10:47 lr: 0.000057 loss: 2.8820 (2.7311) grad_norm: 2.7914 (3.2469) time: 0.6242 [2021-03-28 09:40:43 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 260/1251] eta: 0:10:39 lr: 0.000057 loss: 2.5068 (2.7290) grad_norm: 2.9297 (3.2440) time: 0.6256 [2021-03-28 09:40:50 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 270/1251] eta: 0:10:32 lr: 0.000057 loss: 2.5051 (2.7220) grad_norm: 2.9139 (3.2357) time: 0.6257 [2021-03-28 09:40:56 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 280/1251] eta: 0:10:25 lr: 0.000057 loss: 2.7698 (2.7249) grad_norm: 2.9139 (3.2514) time: 0.6281 [2021-03-28 09:41:02 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 290/1251] eta: 0:10:18 lr: 0.000057 loss: 2.9339 (2.7341) grad_norm: 2.9888 (3.2486) time: 0.6252 [2021-03-28 09:41:08 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 300/1251] eta: 0:10:11 lr: 0.000057 loss: 2.9339 (2.7317) grad_norm: 3.1865 (3.2503) time: 0.6250 [2021-03-28 09:41:15 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 310/1251] eta: 0:10:05 lr: 0.000057 loss: 2.8730 (2.7346) grad_norm: 3.3047 (3.2491) time: 0.6339 [2021-03-28 09:41:21 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 320/1251] eta: 0:09:58 lr: 0.000057 loss: 2.7717 (2.7292) grad_norm: 2.7067 (3.2431) time: 0.6374 [2021-03-28 09:41:27 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 330/1251] eta: 0:09:51 lr: 0.000057 loss: 2.9145 (2.7377) grad_norm: 2.7912 (3.2429) time: 0.6336 [2021-03-28 09:41:34 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 340/1251] eta: 0:09:45 lr: 0.000057 loss: 2.9145 (2.7371) grad_norm: 2.8500 (3.2355) time: 0.6326 [2021-03-28 09:41:40 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 350/1251] eta: 0:09:38 lr: 0.000056 loss: 2.6647 (2.7353) grad_norm: 2.7589 (3.2683) time: 0.6292 [2021-03-28 09:41:46 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 360/1251] eta: 0:09:31 lr: 0.000056 loss: 2.6643 (2.7320) grad_norm: 2.9275 (3.2924) time: 0.6275 [2021-03-28 09:41:53 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 370/1251] eta: 0:09:24 lr: 0.000056 loss: 2.6130 (2.7268) grad_norm: 3.1358 (3.2882) time: 0.6287 [2021-03-28 09:41:59 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 380/1251] eta: 0:09:18 lr: 0.000056 loss: 2.3873 (2.7221) grad_norm: 3.0300 (3.2842) time: 0.6292 [2021-03-28 09:42:05 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 390/1251] eta: 0:09:11 lr: 0.000056 loss: 2.7679 (2.7225) grad_norm: 3.0037 (3.2878) time: 0.6247 [2021-03-28 09:42:11 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 400/1251] eta: 0:09:04 lr: 0.000056 loss: 2.4319 (2.7121) grad_norm: 3.0387 (3.2866) time: 0.6229 [2021-03-28 09:42:18 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 410/1251] eta: 0:08:57 lr: 0.000056 loss: 2.7775 (2.7156) grad_norm: 3.0329 (3.2793) time: 0.6290 [2021-03-28 09:42:24 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 420/1251] eta: 0:08:51 lr: 0.000056 loss: 3.0453 (2.7219) grad_norm: 3.0190 (3.2826) time: 0.6291 [2021-03-28 09:42:30 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 430/1251] eta: 0:08:44 lr: 0.000056 loss: 2.6712 (2.7110) grad_norm: 2.8155 (3.2779) time: 0.6237 [2021-03-28 09:42:36 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 440/1251] eta: 0:08:37 lr: 0.000056 loss: 2.5929 (2.7125) grad_norm: 2.7869 (3.2741) time: 0.6232 [2021-03-28 09:42:43 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 450/1251] eta: 0:08:31 lr: 0.000056 loss: 2.7226 (2.7119) grad_norm: 3.0425 (3.2763) time: 0.6258 [2021-03-28 09:42:49 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 460/1251] eta: 0:08:24 lr: 0.000056 loss: 2.4795 (2.7075) grad_norm: 3.1195 (3.2718) time: 0.6281 [2021-03-28 09:42:55 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 470/1251] eta: 0:08:18 lr: 0.000056 loss: 2.6453 (2.7092) grad_norm: 3.1169 (3.2677) time: 0.6331 [2021-03-28 09:43:02 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 480/1251] eta: 0:08:11 lr: 0.000056 loss: 2.9719 (2.7147) grad_norm: 3.1914 (3.2716) time: 0.6305 [2021-03-28 09:43:08 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 490/1251] eta: 0:08:05 lr: 0.000056 loss: 2.9621 (2.7170) grad_norm: 3.2088 (3.2696) time: 0.6246 [2021-03-28 09:43:14 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 500/1251] eta: 0:07:58 lr: 0.000056 loss: 2.8260 (2.7146) grad_norm: 2.8720 (3.2663) time: 0.6253 [2021-03-28 09:43:20 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 510/1251] eta: 0:07:52 lr: 0.000056 loss: 2.7220 (2.7151) grad_norm: 2.8840 (3.2660) time: 0.6286 [2021-03-28 09:43:27 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 520/1251] eta: 0:07:45 lr: 0.000056 loss: 2.7599 (2.7149) grad_norm: 2.8840 (3.2661) time: 0.6276 [2021-03-28 09:43:33 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 530/1251] eta: 0:07:39 lr: 0.000056 loss: 2.7599 (2.7160) grad_norm: 2.9340 (3.2613) time: 0.6253 [2021-03-28 09:43:39 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 540/1251] eta: 0:07:32 lr: 0.000056 loss: 2.7732 (2.7179) grad_norm: 2.9466 (3.2613) time: 0.6280 [2021-03-28 09:43:46 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 550/1251] eta: 0:07:26 lr: 0.000056 loss: 2.7312 (2.7161) grad_norm: 2.9532 (3.2550) time: 0.6360 [2021-03-28 09:43:52 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 560/1251] eta: 0:07:20 lr: 0.000056 loss: 2.6281 (2.7147) grad_norm: 2.9532 (3.2510) time: 0.6415 [2021-03-28 09:43:58 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 570/1251] eta: 0:07:13 lr: 0.000056 loss: 2.6490 (2.7129) grad_norm: 3.0650 (3.2699) time: 0.6370 [2021-03-28 09:44:05 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 580/1251] eta: 0:07:07 lr: 0.000056 loss: 2.7678 (2.7126) grad_norm: 3.0406 (3.2700) time: 0.6287 [2021-03-28 09:44:11 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 590/1251] eta: 0:07:00 lr: 0.000056 loss: 2.9236 (2.7177) grad_norm: 3.1047 (3.2700) time: 0.6280 [2021-03-28 09:44:17 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 600/1251] eta: 0:06:54 lr: 0.000056 loss: 2.9236 (2.7189) grad_norm: 3.2670 (3.2707) time: 0.6305 [2021-03-28 09:44:24 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 610/1251] eta: 0:06:47 lr: 0.000056 loss: 2.7072 (2.7153) grad_norm: 3.1550 (3.2692) time: 0.6312 [2021-03-28 09:44:30 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 620/1251] eta: 0:06:41 lr: 0.000056 loss: 2.5411 (2.7138) grad_norm: 3.0427 (3.2669) time: 0.6335 [2021-03-28 09:44:36 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 630/1251] eta: 0:06:35 lr: 0.000056 loss: 2.9054 (2.7188) grad_norm: 2.9460 (3.2609) time: 0.6356 [2021-03-28 09:44:43 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 640/1251] eta: 0:06:28 lr: 0.000056 loss: 2.9967 (2.7221) grad_norm: 2.9460 (3.2570) time: 0.6333 [2021-03-28 09:44:49 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 650/1251] eta: 0:06:22 lr: 0.000056 loss: 2.9289 (2.7236) grad_norm: 2.9863 (3.2546) time: 0.6264 [2021-03-28 09:44:55 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 660/1251] eta: 0:06:15 lr: 0.000056 loss: 2.8741 (2.7248) grad_norm: 3.0800 (3.2530) time: 0.6248 [2021-03-28 09:45:01 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 670/1251] eta: 0:06:09 lr: 0.000056 loss: 2.8149 (2.7261) grad_norm: 2.8990 (3.2476) time: 0.6268 [2021-03-28 09:45:08 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 680/1251] eta: 0:06:02 lr: 0.000056 loss: 2.7167 (2.7233) grad_norm: 2.9279 (3.2464) time: 0.6265 [2021-03-28 09:45:14 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 690/1251] eta: 0:05:56 lr: 0.000056 loss: 2.7235 (2.7207) grad_norm: 3.1884 (3.2535) time: 0.6299 [2021-03-28 09:45:20 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 700/1251] eta: 0:05:50 lr: 0.000056 loss: 2.7620 (2.7201) grad_norm: 3.2826 (3.2563) time: 0.6309 [2021-03-28 09:45:27 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 710/1251] eta: 0:05:43 lr: 0.000056 loss: 2.7689 (2.7189) grad_norm: 3.0881 (3.2545) time: 0.6279 [2021-03-28 09:45:33 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 720/1251] eta: 0:05:37 lr: 0.000056 loss: 2.6438 (2.7184) grad_norm: 3.0860 (3.2519) time: 0.6317 [2021-03-28 09:45:39 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 730/1251] eta: 0:05:30 lr: 0.000056 loss: 2.6859 (2.7186) grad_norm: 3.1419 (3.2556) time: 0.6336 [2021-03-28 09:45:46 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 740/1251] eta: 0:05:24 lr: 0.000056 loss: 2.8743 (2.7192) grad_norm: 3.0446 (3.2558) time: 0.6411 [2021-03-28 09:45:52 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 750/1251] eta: 0:05:18 lr: 0.000056 loss: 2.8929 (2.7200) grad_norm: 2.9758 (3.2599) time: 0.6376 [2021-03-28 09:45:58 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 760/1251] eta: 0:05:11 lr: 0.000056 loss: 2.9410 (2.7215) grad_norm: 2.8828 (3.2542) time: 0.6329 [2021-03-28 09:46:05 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 770/1251] eta: 0:05:05 lr: 0.000056 loss: 2.9182 (2.7236) grad_norm: 2.9201 (3.2549) time: 0.6350 [2021-03-28 09:46:11 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 780/1251] eta: 0:04:59 lr: 0.000056 loss: 2.5858 (2.7183) grad_norm: 2.8971 (3.2501) time: 0.6252 [2021-03-28 09:46:17 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 790/1251] eta: 0:04:52 lr: 0.000056 loss: 2.6408 (2.7192) grad_norm: 2.8743 (3.2564) time: 0.6282 [2021-03-28 09:46:24 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 800/1251] eta: 0:04:46 lr: 0.000056 loss: 2.8852 (2.7205) grad_norm: 2.7910 (3.2551) time: 0.6318 [2021-03-28 09:46:30 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 810/1251] eta: 0:04:40 lr: 0.000056 loss: 2.9134 (2.7218) grad_norm: 2.7910 (3.2509) time: 0.6282 [2021-03-28 09:46:36 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 820/1251] eta: 0:04:33 lr: 0.000056 loss: 2.8155 (2.7206) grad_norm: 2.9014 (3.2483) time: 0.6246 [2021-03-28 09:46:42 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 830/1251] eta: 0:04:27 lr: 0.000056 loss: 2.6866 (2.7194) grad_norm: 3.1565 (3.2584) time: 0.6318 [2021-03-28 09:46:49 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 840/1251] eta: 0:04:20 lr: 0.000056 loss: 2.9074 (2.7218) grad_norm: 3.4824 (3.2642) time: 0.6341 [2021-03-28 09:46:55 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 850/1251] eta: 0:04:14 lr: 0.000056 loss: 2.9712 (2.7229) grad_norm: 3.1263 (3.2630) time: 0.6314 [2021-03-28 09:47:01 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 860/1251] eta: 0:04:08 lr: 0.000056 loss: 2.7507 (2.7224) grad_norm: 2.8297 (3.2651) time: 0.6315 [2021-03-28 09:47:08 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 870/1251] eta: 0:04:01 lr: 0.000056 loss: 2.7950 (2.7227) grad_norm: 2.9322 (3.2650) time: 0.6252 [2021-03-28 09:47:14 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 880/1251] eta: 0:03:55 lr: 0.000056 loss: 2.7950 (2.7222) grad_norm: 2.9242 (3.2616) time: 0.6268 [2021-03-28 09:47:20 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 890/1251] eta: 0:03:49 lr: 0.000056 loss: 2.7583 (2.7226) grad_norm: 2.7797 (3.2563) time: 0.6374 [2021-03-28 09:47:27 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 900/1251] eta: 0:03:42 lr: 0.000056 loss: 2.8928 (2.7243) grad_norm: 2.7797 (3.2531) time: 0.6356 [2021-03-28 09:47:33 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 910/1251] eta: 0:03:36 lr: 0.000056 loss: 2.7606 (2.7246) grad_norm: 2.9671 (3.2538) time: 0.6275 [2021-03-28 09:47:39 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 920/1251] eta: 0:03:29 lr: 0.000056 loss: 2.7606 (2.7243) grad_norm: 3.0304 (3.2557) time: 0.6300 [2021-03-28 09:47:45 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 930/1251] eta: 0:03:23 lr: 0.000055 loss: 3.0390 (2.7273) grad_norm: 3.0921 (3.2522) time: 0.6291 [2021-03-28 09:47:52 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 940/1251] eta: 0:03:17 lr: 0.000055 loss: 2.9839 (2.7277) grad_norm: 2.8638 (3.2497) time: 0.6279 [2021-03-28 09:47:58 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 950/1251] eta: 0:03:10 lr: 0.000055 loss: 2.7060 (2.7273) grad_norm: 2.8882 (3.2492) time: 0.6255 [2021-03-28 09:48:04 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 960/1251] eta: 0:03:04 lr: 0.000055 loss: 2.7237 (2.7292) grad_norm: 3.1727 (3.2485) time: 0.6217 [2021-03-28 09:48:11 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 970/1251] eta: 0:02:58 lr: 0.000055 loss: 2.8439 (2.7292) grad_norm: 3.0759 (3.2456) time: 0.6302 [2021-03-28 09:48:17 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 980/1251] eta: 0:02:51 lr: 0.000055 loss: 2.7609 (2.7289) grad_norm: 2.8542 (3.2436) time: 0.6339 [2021-03-28 09:48:23 swin_base_patch4_window7_224] INFO: Epoch: [258] [ 990/1251] eta: 0:02:45 lr: 0.000055 loss: 2.8810 (2.7297) grad_norm: 3.1091 (3.2482) time: 0.6314 [2021-03-28 09:48:30 swin_base_patch4_window7_224] INFO: Epoch: [258] [1000/1251] eta: 0:02:39 lr: 0.000055 loss: 2.7608 (2.7276) grad_norm: 3.2650 (3.2488) time: 0.6359 [2021-03-28 09:48:36 swin_base_patch4_window7_224] INFO: Epoch: [258] [1010/1251] eta: 0:02:32 lr: 0.000055 loss: 2.7608 (2.7285) grad_norm: 2.9948 (3.2478) time: 0.6335 [2021-03-28 09:48:42 swin_base_patch4_window7_224] INFO: Epoch: [258] [1020/1251] eta: 0:02:26 lr: 0.000055 loss: 2.8339 (2.7263) grad_norm: 2.9494 (3.2463) time: 0.6316 [2021-03-28 09:48:49 swin_base_patch4_window7_224] INFO: Epoch: [258] [1030/1251] eta: 0:02:20 lr: 0.000055 loss: 2.7342 (2.7265) grad_norm: 2.7631 (3.2447) time: 0.6326 [2021-03-28 09:48:55 swin_base_patch4_window7_224] INFO: Epoch: [258] [1040/1251] eta: 0:02:13 lr: 0.000055 loss: 2.6966 (2.7254) grad_norm: 2.8555 (3.2452) time: 0.6270 [2021-03-28 09:49:01 swin_base_patch4_window7_224] INFO: Epoch: [258] [1050/1251] eta: 0:02:07 lr: 0.000055 loss: 2.9125 (2.7286) grad_norm: 2.9131 (3.2484) time: 0.6241 [2021-03-28 09:49:07 swin_base_patch4_window7_224] INFO: Epoch: [258] [1060/1251] eta: 0:02:01 lr: 0.000055 loss: 2.9434 (2.7288) grad_norm: 2.9131 (3.2467) time: 0.6269 [2021-03-28 09:49:14 swin_base_patch4_window7_224] INFO: Epoch: [258] [1070/1251] eta: 0:01:54 lr: 0.000055 loss: 2.8431 (2.7297) grad_norm: 2.9846 (3.2434) time: 0.6242 [2021-03-28 09:49:20 swin_base_patch4_window7_224] INFO: Epoch: [258] [1080/1251] eta: 0:01:48 lr: 0.000055 loss: 2.7903 (2.7297) grad_norm: 2.8814 (3.2412) time: 0.6295 [2021-03-28 09:49:26 swin_base_patch4_window7_224] INFO: Epoch: [258] [1090/1251] eta: 0:01:42 lr: 0.000055 loss: 2.8567 (2.7314) grad_norm: 2.8495 (3.2372) time: 0.6355 [2021-03-28 09:49:33 swin_base_patch4_window7_224] INFO: Epoch: [258] [1100/1251] eta: 0:01:35 lr: 0.000055 loss: 2.8567 (2.7320) grad_norm: 2.8495 (3.2355) time: 0.6329 [2021-03-28 09:49:39 swin_base_patch4_window7_224] INFO: Epoch: [258] [1110/1251] eta: 0:01:29 lr: 0.000055 loss: 2.6475 (2.7305) grad_norm: 2.7771 (3.2313) time: 0.6248 [2021-03-28 09:49:45 swin_base_patch4_window7_224] INFO: Epoch: [258] [1120/1251] eta: 0:01:22 lr: 0.000055 loss: 2.8007 (2.7315) grad_norm: 2.7814 (3.2305) time: 0.6194 [2021-03-28 09:49:51 swin_base_patch4_window7_224] INFO: Epoch: [258] [1130/1251] eta: 0:01:16 lr: 0.000055 loss: 2.7281 (2.7305) grad_norm: 2.9197 (3.2275) time: 0.6247 [2021-03-28 09:49:58 swin_base_patch4_window7_224] INFO: Epoch: [258] [1140/1251] eta: 0:01:10 lr: 0.000055 loss: 2.7161 (2.7300) grad_norm: 2.9178 (3.2250) time: 0.6303 [2021-03-28 09:50:04 swin_base_patch4_window7_224] INFO: Epoch: [258] [1150/1251] eta: 0:01:03 lr: 0.000055 loss: 2.7450 (2.7288) grad_norm: 2.9604 (3.2244) time: 0.6319 [2021-03-28 09:50:10 swin_base_patch4_window7_224] INFO: Epoch: [258] [1160/1251] eta: 0:00:57 lr: 0.000055 loss: 2.7667 (2.7281) grad_norm: 2.8357 (3.2204) time: 0.6319 [2021-03-28 09:50:16 swin_base_patch4_window7_224] INFO: Epoch: [258] [1170/1251] eta: 0:00:51 lr: 0.000055 loss: 2.8275 (2.7282) grad_norm: 2.8083 (3.2200) time: 0.6292 [2021-03-28 09:50:23 swin_base_patch4_window7_224] INFO: Epoch: [258] [1180/1251] eta: 0:00:44 lr: 0.000055 loss: 2.8703 (2.7281) grad_norm: 2.8292 (3.2177) time: 0.6277 [2021-03-28 09:50:29 swin_base_patch4_window7_224] INFO: Epoch: [258] [1190/1251] eta: 0:00:38 lr: 0.000055 loss: 2.7608 (2.7266) grad_norm: 2.8246 (3.2179) time: 0.6257 [2021-03-28 09:50:35 swin_base_patch4_window7_224] INFO: Epoch: [258] [1200/1251] eta: 0:00:32 lr: 0.000055 loss: 2.7817 (2.7264) grad_norm: 2.8569 (3.2163) time: 0.6287 [2021-03-28 09:50:42 swin_base_patch4_window7_224] INFO: Epoch: [258] [1210/1251] eta: 0:00:25 lr: 0.000055 loss: 2.8192 (2.7264) grad_norm: 3.0304 (3.2161) time: 0.6351 [2021-03-28 09:50:48 swin_base_patch4_window7_224] INFO: Epoch: [258] [1220/1251] eta: 0:00:19 lr: 0.000055 loss: 2.8103 (2.7262) grad_norm: 2.7960 (3.2132) time: 0.6291 [2021-03-28 09:50:54 swin_base_patch4_window7_224] INFO: Epoch: [258] [1230/1251] eta: 0:00:13 lr: 0.000055 loss: 2.8103 (2.7264) grad_norm: 2.7960 (3.2141) time: 0.6248 [2021-03-28 09:51:01 swin_base_patch4_window7_224] INFO: Epoch: [258] [1240/1251] eta: 0:00:06 lr: 0.000055 loss: 2.9019 (2.7291) grad_norm: 3.1498 (3.2142) time: 0.6288 [2021-03-28 09:51:07 swin_base_patch4_window7_224] INFO: Epoch: [258] [1250/1251] eta: 0:00:00 lr: 0.000055 loss: 2.9944 (2.7302) grad_norm: 3.0463 (3.2118) time: 0.6267 [2021-03-28 09:51:16 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:36 loss: 0.9821 (0.9821) acc1: 73.4375 (73.4375) acc5: 93.7500 (93.7500) [2021-03-28 09:51:19 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.7634 (0.7153) acc1: 84.3750 (83.2386) acc5: 96.8750 (96.4489) [2021-03-28 09:51:21 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7196 (0.7288) acc1: 82.8125 (82.6637) acc5: 96.8750 (96.5030) [2021-03-28 09:51:23 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7196 (0.7400) acc1: 82.8125 (82.4597) acc5: 96.8750 (96.3206) [2021-03-28 09:51:25 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7276 (0.7446) acc1: 82.8125 (82.5457) acc5: 96.8750 (96.2652) [2021-03-28 09:51:26 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7521 (0.7534) acc1: 81.2500 (82.3680) acc5: 96.8750 (96.2560) [2021-03-28 09:51:41 swin_base_patch4_window7_224] INFO: * Acc@1 83.056 Acc@5 96.394 loss 0.742 [2021-03-28 09:51:41 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-28 09:51:41 swin_base_patch4_window7_224] INFO: Max accuracy: 83.13% [2021-03-28 09:51:45 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 0/1251] eta: 1:28:09 lr: 0.000055 loss: 2.0400 (2.0400) grad_norm: 2.4927 (2.4927) time: 4.2280 [2021-03-28 09:51:52 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 10/1251] eta: 0:20:08 lr: 0.000055 loss: 2.6700 (2.5686) grad_norm: 2.9597 (3.0019) time: 0.9740 [2021-03-28 09:51:58 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 20/1251] eta: 0:16:35 lr: 0.000055 loss: 2.5448 (2.6075) grad_norm: 2.8778 (2.9863) time: 0.6380 [2021-03-28 09:52:05 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 30/1251] eta: 0:15:18 lr: 0.000055 loss: 2.7646 (2.6811) grad_norm: 2.8202 (3.0030) time: 0.6302 [2021-03-28 09:52:11 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 40/1251] eta: 0:14:37 lr: 0.000055 loss: 2.8118 (2.6938) grad_norm: 2.8202 (2.9926) time: 0.6355 [2021-03-28 09:52:17 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 50/1251] eta: 0:14:09 lr: 0.000055 loss: 2.8003 (2.6907) grad_norm: 2.8260 (2.9845) time: 0.6371 [2021-03-28 09:52:24 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 60/1251] eta: 0:13:48 lr: 0.000055 loss: 2.7880 (2.6654) grad_norm: 2.9715 (2.9810) time: 0.6370 [2021-03-28 09:52:30 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 70/1251] eta: 0:13:31 lr: 0.000055 loss: 2.7880 (2.6844) grad_norm: 2.9304 (2.9892) time: 0.6372 [2021-03-28 09:52:36 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 80/1251] eta: 0:13:15 lr: 0.000055 loss: 2.9677 (2.7075) grad_norm: 2.8897 (2.9811) time: 0.6310 [2021-03-28 09:52:43 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 90/1251] eta: 0:13:02 lr: 0.000055 loss: 2.9677 (2.7339) grad_norm: 2.9405 (3.0031) time: 0.6249 [2021-03-28 09:52:49 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 100/1251] eta: 0:12:50 lr: 0.000055 loss: 2.7903 (2.7235) grad_norm: 2.9576 (3.0650) time: 0.6285 [2021-03-28 09:52:55 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 110/1251] eta: 0:12:40 lr: 0.000055 loss: 2.7545 (2.7282) grad_norm: 2.9207 (3.0669) time: 0.6350 [2021-03-28 09:53:01 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 120/1251] eta: 0:12:30 lr: 0.000055 loss: 2.9489 (2.7365) grad_norm: 2.7894 (3.0884) time: 0.6313 [2021-03-28 09:53:08 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 130/1251] eta: 0:12:20 lr: 0.000055 loss: 2.9456 (2.7430) grad_norm: 2.8357 (3.1042) time: 0.6295 [2021-03-28 09:53:14 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 140/1251] eta: 0:12:12 lr: 0.000055 loss: 2.9011 (2.7458) grad_norm: 2.9178 (3.0887) time: 0.6323 [2021-03-28 09:53:20 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 150/1251] eta: 0:12:03 lr: 0.000055 loss: 2.8091 (2.7439) grad_norm: 2.8113 (3.0787) time: 0.6318 [2021-03-28 09:53:27 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 160/1251] eta: 0:11:54 lr: 0.000055 loss: 2.7309 (2.7385) grad_norm: 3.0543 (3.0896) time: 0.6275 [2021-03-28 09:53:33 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 170/1251] eta: 0:11:46 lr: 0.000055 loss: 2.7649 (2.7386) grad_norm: 3.1598 (3.0988) time: 0.6274 [2021-03-28 09:53:39 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 180/1251] eta: 0:11:38 lr: 0.000055 loss: 2.8330 (2.7465) grad_norm: 3.1038 (3.0976) time: 0.6297 [2021-03-28 09:53:46 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 190/1251] eta: 0:11:30 lr: 0.000055 loss: 2.8159 (2.7453) grad_norm: 2.7847 (3.0822) time: 0.6306 [2021-03-28 09:53:52 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 200/1251] eta: 0:11:23 lr: 0.000055 loss: 2.6764 (2.7404) grad_norm: 2.8491 (3.0947) time: 0.6357 [2021-03-28 09:53:58 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 210/1251] eta: 0:11:16 lr: 0.000055 loss: 2.6212 (2.7278) grad_norm: 3.0563 (3.0989) time: 0.6367 [2021-03-28 09:54:05 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 220/1251] eta: 0:11:09 lr: 0.000055 loss: 2.6360 (2.7183) grad_norm: 3.0010 (3.0967) time: 0.6343 [2021-03-28 09:54:11 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 230/1251] eta: 0:11:01 lr: 0.000055 loss: 2.6621 (2.7196) grad_norm: 3.0837 (3.0968) time: 0.6295 [2021-03-28 09:54:17 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 240/1251] eta: 0:10:54 lr: 0.000055 loss: 2.8428 (2.7205) grad_norm: 3.0479 (3.1047) time: 0.6267 [2021-03-28 09:54:24 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 250/1251] eta: 0:10:47 lr: 0.000054 loss: 2.7391 (2.7205) grad_norm: 3.0479 (3.1130) time: 0.6280 [2021-03-28 09:54:30 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 260/1251] eta: 0:10:39 lr: 0.000054 loss: 2.9286 (2.7326) grad_norm: 2.8602 (3.1141) time: 0.6268 [2021-03-28 09:54:36 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 270/1251] eta: 0:10:33 lr: 0.000054 loss: 2.8185 (2.7239) grad_norm: 2.8348 (3.1064) time: 0.6300 [2021-03-28 09:54:43 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 280/1251] eta: 0:10:26 lr: 0.000054 loss: 2.5441 (2.7182) grad_norm: 2.9665 (3.1038) time: 0.6399 [2021-03-28 09:54:49 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 290/1251] eta: 0:10:19 lr: 0.000054 loss: 2.7189 (2.7204) grad_norm: 2.9947 (3.1240) time: 0.6371 [2021-03-28 09:54:55 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 300/1251] eta: 0:10:12 lr: 0.000054 loss: 2.7253 (2.7160) grad_norm: 3.1134 (3.1272) time: 0.6320 [2021-03-28 09:55:02 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 310/1251] eta: 0:10:06 lr: 0.000054 loss: 2.6537 (2.7091) grad_norm: 3.3046 (3.1316) time: 0.6345 [2021-03-28 09:55:08 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 320/1251] eta: 0:09:59 lr: 0.000054 loss: 2.7433 (2.7126) grad_norm: 3.1005 (3.1354) time: 0.6363 [2021-03-28 09:55:14 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 330/1251] eta: 0:09:52 lr: 0.000054 loss: 2.8082 (2.7134) grad_norm: 3.0321 (3.1533) time: 0.6352 [2021-03-28 09:55:21 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 340/1251] eta: 0:09:45 lr: 0.000054 loss: 2.9330 (2.7227) grad_norm: 3.1474 (3.1603) time: 0.6310 [2021-03-28 09:55:27 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 350/1251] eta: 0:09:39 lr: 0.000054 loss: 2.9435 (2.7252) grad_norm: 2.9093 (3.1589) time: 0.6283 [2021-03-28 09:55:33 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 360/1251] eta: 0:09:32 lr: 0.000054 loss: 2.6193 (2.7218) grad_norm: 2.8410 (3.1587) time: 0.6277 [2021-03-28 09:55:39 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 370/1251] eta: 0:09:25 lr: 0.000054 loss: 2.6193 (2.7201) grad_norm: 2.9353 (3.1562) time: 0.6325 [2021-03-28 09:55:46 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 380/1251] eta: 0:09:19 lr: 0.000054 loss: 2.6851 (2.7174) grad_norm: 2.9353 (3.1522) time: 0.6367 [2021-03-28 09:55:52 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 390/1251] eta: 0:09:12 lr: 0.000054 loss: 2.8392 (2.7178) grad_norm: 3.1485 (3.1520) time: 0.6340 [2021-03-28 09:55:58 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 400/1251] eta: 0:09:05 lr: 0.000054 loss: 2.8452 (2.7183) grad_norm: 3.0529 (3.1523) time: 0.6278 [2021-03-28 09:56:05 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 410/1251] eta: 0:08:58 lr: 0.000054 loss: 2.8442 (2.7143) grad_norm: 3.0198 (3.1550) time: 0.6238 [2021-03-28 09:56:11 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 420/1251] eta: 0:08:52 lr: 0.000054 loss: 2.6656 (2.7122) grad_norm: 3.0439 (3.1523) time: 0.6228 [2021-03-28 09:56:17 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 430/1251] eta: 0:08:45 lr: 0.000054 loss: 2.8984 (2.7207) grad_norm: 3.1141 (3.1776) time: 0.6267 [2021-03-28 09:56:23 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 440/1251] eta: 0:08:38 lr: 0.000054 loss: 2.9089 (2.7191) grad_norm: 2.9754 (3.1738) time: 0.6272 [2021-03-28 09:56:30 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 450/1251] eta: 0:08:32 lr: 0.000054 loss: 2.6793 (2.7159) grad_norm: 2.9112 (3.1795) time: 0.6237 [2021-03-28 09:56:36 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 460/1251] eta: 0:08:25 lr: 0.000054 loss: 2.6825 (2.7186) grad_norm: 2.9112 (3.1746) time: 0.6261 [2021-03-28 09:56:42 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 470/1251] eta: 0:08:19 lr: 0.000054 loss: 2.7846 (2.7208) grad_norm: 2.7679 (3.1741) time: 0.6304 [2021-03-28 09:56:49 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 480/1251] eta: 0:08:12 lr: 0.000054 loss: 2.7846 (2.7206) grad_norm: 2.8324 (3.1721) time: 0.6315 [2021-03-28 09:56:55 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 490/1251] eta: 0:08:05 lr: 0.000054 loss: 2.6467 (2.7166) grad_norm: 2.8645 (3.1690) time: 0.6265 [2021-03-28 09:57:01 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 500/1251] eta: 0:07:59 lr: 0.000054 loss: 2.6823 (2.7169) grad_norm: 2.9059 (3.1649) time: 0.6251 [2021-03-28 09:57:07 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 510/1251] eta: 0:07:52 lr: 0.000054 loss: 2.7101 (2.7151) grad_norm: 2.8788 (3.1607) time: 0.6269 [2021-03-28 09:57:14 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 520/1251] eta: 0:07:46 lr: 0.000054 loss: 2.6975 (2.7148) grad_norm: 2.8617 (3.1621) time: 0.6255 [2021-03-28 09:57:20 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 530/1251] eta: 0:07:39 lr: 0.000054 loss: 2.6812 (2.7155) grad_norm: 2.9286 (3.1615) time: 0.6253 [2021-03-28 09:57:26 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 540/1251] eta: 0:07:33 lr: 0.000054 loss: 2.7995 (2.7147) grad_norm: 2.9286 (3.1617) time: 0.6258 [2021-03-28 09:57:33 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 550/1251] eta: 0:07:27 lr: 0.000054 loss: 2.6027 (2.7118) grad_norm: 3.0582 (3.1648) time: 0.6422 [2021-03-28 09:57:39 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 560/1251] eta: 0:07:20 lr: 0.000054 loss: 2.6291 (2.7144) grad_norm: 3.0092 (3.1602) time: 0.6466 [2021-03-28 09:57:45 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 570/1251] eta: 0:07:14 lr: 0.000054 loss: 2.8011 (2.7129) grad_norm: 2.9567 (3.1688) time: 0.6305 [2021-03-28 09:57:52 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 580/1251] eta: 0:07:07 lr: 0.000054 loss: 2.7410 (2.7128) grad_norm: 2.8965 (3.1651) time: 0.6243 [2021-03-28 09:57:58 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 590/1251] eta: 0:07:01 lr: 0.000054 loss: 2.5647 (2.7095) grad_norm: 2.9660 (3.1718) time: 0.6275 [2021-03-28 09:58:04 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 600/1251] eta: 0:06:54 lr: 0.000054 loss: 2.6981 (2.7083) grad_norm: 3.0831 (3.1769) time: 0.6314 [2021-03-28 09:58:11 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 610/1251] eta: 0:06:48 lr: 0.000054 loss: 2.6981 (2.7054) grad_norm: 3.1829 (3.1764) time: 0.6324 [2021-03-28 09:58:17 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 620/1251] eta: 0:06:41 lr: 0.000054 loss: 2.5400 (2.7039) grad_norm: 3.0569 (3.1752) time: 0.6371 [2021-03-28 09:58:23 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 630/1251] eta: 0:06:35 lr: 0.000054 loss: 2.6504 (2.7038) grad_norm: 2.9558 (3.1712) time: 0.6398 [2021-03-28 09:58:30 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 640/1251] eta: 0:06:29 lr: 0.000054 loss: 2.6352 (2.7012) grad_norm: 2.9165 (3.1680) time: 0.6392 [2021-03-28 09:58:36 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 650/1251] eta: 0:06:22 lr: 0.000054 loss: 2.5735 (2.6988) grad_norm: 2.9406 (3.1760) time: 0.6388 [2021-03-28 09:58:42 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 660/1251] eta: 0:06:16 lr: 0.000054 loss: 2.6974 (2.7000) grad_norm: 2.7808 (3.1745) time: 0.6329 [2021-03-28 09:58:49 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 670/1251] eta: 0:06:09 lr: 0.000054 loss: 2.7696 (2.6981) grad_norm: 2.8925 (3.1759) time: 0.6252 [2021-03-28 09:58:55 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 680/1251] eta: 0:06:03 lr: 0.000054 loss: 2.8445 (2.7013) grad_norm: 3.0787 (3.1765) time: 0.6250 [2021-03-28 09:59:01 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 690/1251] eta: 0:05:57 lr: 0.000054 loss: 2.9581 (2.7044) grad_norm: 2.9387 (3.1800) time: 0.6278 [2021-03-28 09:59:07 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 700/1251] eta: 0:05:50 lr: 0.000054 loss: 2.9169 (2.7031) grad_norm: 2.7719 (3.1751) time: 0.6264 [2021-03-28 09:59:14 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 710/1251] eta: 0:05:44 lr: 0.000054 loss: 2.7968 (2.7045) grad_norm: 2.8275 (3.1730) time: 0.6241 [2021-03-28 09:59:20 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 720/1251] eta: 0:05:37 lr: 0.000054 loss: 2.7843 (2.7045) grad_norm: 2.8609 (3.1730) time: 0.6306 [2021-03-28 09:59:26 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 730/1251] eta: 0:05:31 lr: 0.000054 loss: 2.7666 (2.7021) grad_norm: 2.9608 (3.1737) time: 0.6291 [2021-03-28 09:59:33 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 740/1251] eta: 0:05:25 lr: 0.000054 loss: 2.5323 (2.7019) grad_norm: 3.0318 (3.1717) time: 0.6298 [2021-03-28 09:59:39 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 750/1251] eta: 0:05:18 lr: 0.000054 loss: 2.8746 (2.7048) grad_norm: 3.1137 (3.1788) time: 0.6408 [2021-03-28 09:59:45 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 760/1251] eta: 0:05:12 lr: 0.000054 loss: 2.8873 (2.7059) grad_norm: 3.3527 (3.1807) time: 0.6374 [2021-03-28 09:59:52 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 770/1251] eta: 0:05:05 lr: 0.000054 loss: 2.8608 (2.7047) grad_norm: 3.1220 (3.1788) time: 0.6263 [2021-03-28 09:59:58 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 780/1251] eta: 0:04:59 lr: 0.000054 loss: 2.7744 (2.7057) grad_norm: 3.1090 (3.1829) time: 0.6247 [2021-03-28 10:00:04 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 790/1251] eta: 0:04:53 lr: 0.000054 loss: 2.6939 (2.7033) grad_norm: 3.1539 (3.2005) time: 0.6305 [2021-03-28 10:00:10 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 800/1251] eta: 0:04:46 lr: 0.000054 loss: 2.4242 (2.7004) grad_norm: 3.2166 (3.2021) time: 0.6276 [2021-03-28 10:00:17 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 810/1251] eta: 0:04:40 lr: 0.000054 loss: 2.6549 (2.7009) grad_norm: 3.1735 (3.2007) time: 0.6224 [2021-03-28 10:00:23 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 820/1251] eta: 0:04:33 lr: 0.000054 loss: 2.8572 (2.7025) grad_norm: 3.0838 (3.2032) time: 0.6296 [2021-03-28 10:00:29 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 830/1251] eta: 0:04:27 lr: 0.000054 loss: 2.7896 (2.7022) grad_norm: 2.9447 (3.2091) time: 0.6321 [2021-03-28 10:00:36 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 840/1251] eta: 0:04:21 lr: 0.000053 loss: 2.6236 (2.7012) grad_norm: 2.9418 (3.2057) time: 0.6302 [2021-03-28 10:00:42 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 850/1251] eta: 0:04:14 lr: 0.000053 loss: 2.5485 (2.7010) grad_norm: 2.9005 (3.2031) time: 0.6308 [2021-03-28 10:00:48 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 860/1251] eta: 0:04:08 lr: 0.000053 loss: 2.5315 (2.6976) grad_norm: 2.9005 (3.2046) time: 0.6318 [2021-03-28 10:00:55 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 870/1251] eta: 0:04:02 lr: 0.000053 loss: 2.4278 (2.6961) grad_norm: 3.0561 (3.2025) time: 0.6371 [2021-03-28 10:01:01 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 880/1251] eta: 0:03:55 lr: 0.000053 loss: 2.8033 (2.6975) grad_norm: 3.0669 (3.2016) time: 0.6354 [2021-03-28 10:01:07 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 890/1251] eta: 0:03:49 lr: 0.000053 loss: 2.8430 (2.6997) grad_norm: 3.1184 (3.2015) time: 0.6316 [2021-03-28 10:01:14 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 900/1251] eta: 0:03:42 lr: 0.000053 loss: 2.8673 (2.6999) grad_norm: 3.0209 (3.2006) time: 0.6285 [2021-03-28 10:01:20 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 910/1251] eta: 0:03:36 lr: 0.000053 loss: 2.7248 (2.6995) grad_norm: 3.0209 (3.1993) time: 0.6257 [2021-03-28 10:01:26 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 920/1251] eta: 0:03:30 lr: 0.000053 loss: 2.7218 (2.6998) grad_norm: 2.8359 (3.1951) time: 0.6283 [2021-03-28 10:01:32 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 930/1251] eta: 0:03:23 lr: 0.000053 loss: 2.5539 (2.6986) grad_norm: 2.9604 (3.1968) time: 0.6333 [2021-03-28 10:01:39 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 940/1251] eta: 0:03:17 lr: 0.000053 loss: 2.5711 (2.6994) grad_norm: 3.0144 (3.2071) time: 0.6318 [2021-03-28 10:01:45 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 950/1251] eta: 0:03:11 lr: 0.000053 loss: 2.8593 (2.7011) grad_norm: 3.0232 (3.2100) time: 0.6267 [2021-03-28 10:01:51 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 960/1251] eta: 0:03:04 lr: 0.000053 loss: 2.9562 (2.7013) grad_norm: 3.1999 (3.2104) time: 0.6288 [2021-03-28 10:01:58 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 970/1251] eta: 0:02:58 lr: 0.000053 loss: 2.9380 (2.7044) grad_norm: 2.8911 (3.2088) time: 0.6303 [2021-03-28 10:02:04 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 980/1251] eta: 0:02:52 lr: 0.000053 loss: 2.9347 (2.7051) grad_norm: 2.9810 (3.2084) time: 0.6331 [2021-03-28 10:02:10 swin_base_patch4_window7_224] INFO: Epoch: [259] [ 990/1251] eta: 0:02:45 lr: 0.000053 loss: 2.8624 (2.7051) grad_norm: 2.9810 (inf) time: 0.6303 [2021-03-28 10:02:17 swin_base_patch4_window7_224] INFO: Epoch: [259] [1000/1251] eta: 0:02:39 lr: 0.000053 loss: 2.8624 (2.7065) grad_norm: 2.9284 (inf) time: 0.6287 [2021-03-28 10:02:23 swin_base_patch4_window7_224] INFO: Epoch: [259] [1010/1251] eta: 0:02:32 lr: 0.000053 loss: 2.9016 (2.7051) grad_norm: 2.8989 (inf) time: 0.6315 [2021-03-28 10:02:29 swin_base_patch4_window7_224] INFO: Epoch: [259] [1020/1251] eta: 0:02:26 lr: 0.000053 loss: 2.8840 (2.7056) grad_norm: 2.7413 (inf) time: 0.6289 [2021-03-28 10:02:36 swin_base_patch4_window7_224] INFO: Epoch: [259] [1030/1251] eta: 0:02:20 lr: 0.000053 loss: 2.8840 (2.7056) grad_norm: 2.9487 (inf) time: 0.6355 [2021-03-28 10:02:42 swin_base_patch4_window7_224] INFO: Epoch: [259] [1040/1251] eta: 0:02:13 lr: 0.000053 loss: 2.8532 (2.7064) grad_norm: 2.9487 (inf) time: 0.6347 [2021-03-28 10:02:48 swin_base_patch4_window7_224] INFO: Epoch: [259] [1050/1251] eta: 0:02:07 lr: 0.000053 loss: 2.8576 (2.7083) grad_norm: 2.9628 (inf) time: 0.6257 [2021-03-28 10:02:54 swin_base_patch4_window7_224] INFO: Epoch: [259] [1060/1251] eta: 0:02:01 lr: 0.000053 loss: 2.6975 (2.7072) grad_norm: 3.0056 (inf) time: 0.6255 [2021-03-28 10:03:01 swin_base_patch4_window7_224] INFO: Epoch: [259] [1070/1251] eta: 0:01:54 lr: 0.000053 loss: 2.5648 (2.7064) grad_norm: 3.0056 (inf) time: 0.6301 [2021-03-28 10:03:07 swin_base_patch4_window7_224] INFO: Epoch: [259] [1080/1251] eta: 0:01:48 lr: 0.000053 loss: 2.7706 (2.7065) grad_norm: 2.8722 (inf) time: 0.6332 [2021-03-28 10:03:13 swin_base_patch4_window7_224] INFO: Epoch: [259] [1090/1251] eta: 0:01:42 lr: 0.000053 loss: 2.8584 (2.7075) grad_norm: 2.9354 (inf) time: 0.6349 [2021-03-28 10:03:20 swin_base_patch4_window7_224] INFO: Epoch: [259] [1100/1251] eta: 0:01:35 lr: 0.000053 loss: 2.8590 (2.7079) grad_norm: 3.3752 (inf) time: 0.6347 [2021-03-28 10:03:26 swin_base_patch4_window7_224] INFO: Epoch: [259] [1110/1251] eta: 0:01:29 lr: 0.000053 loss: 2.8200 (2.7091) grad_norm: 3.4528 (inf) time: 0.6359 [2021-03-28 10:03:32 swin_base_patch4_window7_224] INFO: Epoch: [259] [1120/1251] eta: 0:01:23 lr: 0.000053 loss: 2.8043 (2.7096) grad_norm: 2.9453 (inf) time: 0.6374 [2021-03-28 10:03:39 swin_base_patch4_window7_224] INFO: Epoch: [259] [1130/1251] eta: 0:01:16 lr: 0.000053 loss: 2.8043 (2.7104) grad_norm: 3.0552 (inf) time: 0.6310 [2021-03-28 10:03:45 swin_base_patch4_window7_224] INFO: Epoch: [259] [1140/1251] eta: 0:01:10 lr: 0.000053 loss: 2.8380 (2.7105) grad_norm: 3.0840 (inf) time: 0.6304 [2021-03-28 10:03:51 swin_base_patch4_window7_224] INFO: Epoch: [259] [1150/1251] eta: 0:01:04 lr: 0.000053 loss: 2.8644 (2.7109) grad_norm: 2.8872 (inf) time: 0.6305 [2021-03-28 10:03:58 swin_base_patch4_window7_224] INFO: Epoch: [259] [1160/1251] eta: 0:00:57 lr: 0.000053 loss: 2.8644 (2.7113) grad_norm: 3.1198 (inf) time: 0.6266 [2021-03-28 10:04:04 swin_base_patch4_window7_224] INFO: Epoch: [259] [1170/1251] eta: 0:00:51 lr: 0.000053 loss: 2.8522 (2.7115) grad_norm: 3.1262 (inf) time: 0.6255 [2021-03-28 10:04:10 swin_base_patch4_window7_224] INFO: Epoch: [259] [1180/1251] eta: 0:00:45 lr: 0.000053 loss: 2.8868 (2.7130) grad_norm: 3.1078 (inf) time: 0.6325 [2021-03-28 10:04:16 swin_base_patch4_window7_224] INFO: Epoch: [259] [1190/1251] eta: 0:00:38 lr: 0.000053 loss: 2.9275 (2.7137) grad_norm: 3.1078 (inf) time: 0.6298 [2021-03-28 10:04:23 swin_base_patch4_window7_224] INFO: Epoch: [259] [1200/1251] eta: 0:00:32 lr: 0.000053 loss: 3.0005 (2.7151) grad_norm: 3.1697 (inf) time: 0.6215 [2021-03-28 10:04:29 swin_base_patch4_window7_224] INFO: Epoch: [259] [1210/1251] eta: 0:00:25 lr: 0.000053 loss: 2.7896 (2.7135) grad_norm: 2.9087 (inf) time: 0.6234 [2021-03-28 10:04:35 swin_base_patch4_window7_224] INFO: Epoch: [259] [1220/1251] eta: 0:00:19 lr: 0.000053 loss: 2.7076 (2.7136) grad_norm: 2.8553 (inf) time: 0.6261 [2021-03-28 10:04:42 swin_base_patch4_window7_224] INFO: Epoch: [259] [1230/1251] eta: 0:00:13 lr: 0.000053 loss: 2.8271 (2.7146) grad_norm: 2.9541 (inf) time: 0.6301 [2021-03-28 10:04:48 swin_base_patch4_window7_224] INFO: Epoch: [259] [1240/1251] eta: 0:00:06 lr: 0.000053 loss: 2.6918 (2.7127) grad_norm: 2.9607 (inf) time: 0.6248 [2021-03-28 10:04:54 swin_base_patch4_window7_224] INFO: Epoch: [259] [1250/1251] eta: 0:00:00 lr: 0.000053 loss: 2.6207 (2.7125) grad_norm: 2.9223 (inf) time: 0.6145 [2021-03-28 10:05:11 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:34 loss: 0.7638 (0.7638) acc1: 84.3750 (84.3750) acc5: 93.7500 (93.7500) [2021-03-28 10:05:14 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7004 (0.7215) acc1: 84.3750 (82.9545) acc5: 96.8750 (97.0170) [2021-03-28 10:05:16 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.6825 (0.7110) acc1: 84.3750 (83.6310) acc5: 96.8750 (96.8006) [2021-03-28 10:05:18 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7024 (0.7377) acc1: 84.3750 (82.8125) acc5: 96.8750 (96.8246) [2021-03-28 10:05:21 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7365 (0.7469) acc1: 82.8125 (82.6601) acc5: 96.8750 (96.4177) [2021-03-28 10:05:22 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7369 (0.7628) acc1: 82.8125 (82.3360) acc5: 95.3125 (96.2560) [2021-03-28 10:05:41 swin_base_patch4_window7_224] INFO: * Acc@1 83.010 Acc@5 96.296 loss 0.753 [2021-03-28 10:05:41 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.0% [2021-03-28 10:05:41 swin_base_patch4_window7_224] INFO: Max accuracy: 83.13% [2021-03-28 10:05:45 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 0/1251] eta: 1:29:42 lr: 0.000053 loss: 3.2700 (3.2700) grad_norm: 3.0479 (3.0479) time: 4.3030 [2021-03-28 10:05:52 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 10/1251] eta: 0:20:05 lr: 0.000053 loss: 2.9251 (2.7696) grad_norm: 2.7967 (3.3599) time: 0.9714 [2021-03-28 10:05:58 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 20/1251] eta: 0:16:32 lr: 0.000053 loss: 2.8547 (2.7445) grad_norm: 2.7967 (3.4433) time: 0.6311 [2021-03-28 10:06:04 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 30/1251] eta: 0:15:14 lr: 0.000053 loss: 3.0062 (2.8291) grad_norm: 2.9623 (3.3585) time: 0.6261 [2021-03-28 10:06:10 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 40/1251] eta: 0:14:29 lr: 0.000053 loss: 2.9504 (2.8041) grad_norm: 3.1035 (3.4396) time: 0.6264 [2021-03-28 10:06:17 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 50/1251] eta: 0:14:02 lr: 0.000053 loss: 2.7300 (2.7650) grad_norm: 2.8836 (3.3802) time: 0.6293 [2021-03-28 10:06:23 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 60/1251] eta: 0:13:42 lr: 0.000053 loss: 2.8005 (2.7856) grad_norm: 2.9571 (3.5163) time: 0.6344 [2021-03-28 10:06:29 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 70/1251] eta: 0:13:26 lr: 0.000053 loss: 2.8362 (2.7805) grad_norm: 2.9944 (3.4509) time: 0.6356 [2021-03-28 10:06:36 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 80/1251] eta: 0:13:11 lr: 0.000053 loss: 2.7477 (2.7739) grad_norm: 2.9944 (3.4181) time: 0.6316 [2021-03-28 10:06:42 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 90/1251] eta: 0:13:00 lr: 0.000053 loss: 2.7076 (2.7700) grad_norm: 2.9653 (3.6439) time: 0.6339 [2021-03-28 10:06:48 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 100/1251] eta: 0:12:49 lr: 0.000053 loss: 2.9078 (2.7786) grad_norm: 2.9458 (3.5907) time: 0.6360 [2021-03-28 10:06:55 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 110/1251] eta: 0:12:37 lr: 0.000053 loss: 2.8785 (2.7794) grad_norm: 2.8388 (3.5501) time: 0.6275 [2021-03-28 10:07:01 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 120/1251] eta: 0:12:28 lr: 0.000053 loss: 2.8785 (2.7941) grad_norm: 2.9636 (3.5419) time: 0.6281 [2021-03-28 10:07:07 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 130/1251] eta: 0:12:20 lr: 0.000053 loss: 2.9641 (2.7987) grad_norm: 2.9294 (3.5010) time: 0.6383 [2021-03-28 10:07:14 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 140/1251] eta: 0:12:11 lr: 0.000053 loss: 2.8707 (2.8002) grad_norm: 2.9946 (3.5050) time: 0.6369 [2021-03-28 10:07:20 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 150/1251] eta: 0:12:01 lr: 0.000053 loss: 2.8604 (2.7977) grad_norm: 2.9946 (3.4673) time: 0.6247 [2021-03-28 10:07:26 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 160/1251] eta: 0:11:53 lr: 0.000053 loss: 2.7590 (2.7918) grad_norm: 2.8914 (3.4925) time: 0.6238 [2021-03-28 10:07:32 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 170/1251] eta: 0:11:44 lr: 0.000053 loss: 2.4978 (2.7828) grad_norm: 2.9796 (3.4797) time: 0.6256 [2021-03-28 10:07:39 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 180/1251] eta: 0:11:37 lr: 0.000052 loss: 2.4559 (2.7808) grad_norm: 2.9899 (3.4663) time: 0.6275 [2021-03-28 10:07:45 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 190/1251] eta: 0:11:29 lr: 0.000052 loss: 2.6690 (2.7760) grad_norm: 3.1434 (3.4528) time: 0.6269 [2021-03-28 10:07:51 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 200/1251] eta: 0:11:21 lr: 0.000052 loss: 2.3781 (2.7611) grad_norm: 3.0819 (3.4417) time: 0.6264 [2021-03-28 10:07:57 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 210/1251] eta: 0:11:14 lr: 0.000052 loss: 2.6650 (2.7658) grad_norm: 2.9826 (3.4882) time: 0.6291 [2021-03-28 10:08:04 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 220/1251] eta: 0:11:06 lr: 0.000052 loss: 2.7387 (2.7554) grad_norm: 2.9642 (3.4831) time: 0.6255 [2021-03-28 10:08:10 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 230/1251] eta: 0:10:59 lr: 0.000052 loss: 2.7827 (2.7577) grad_norm: 2.8391 (3.4567) time: 0.6249 [2021-03-28 10:08:16 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 240/1251] eta: 0:10:52 lr: 0.000052 loss: 2.8267 (2.7586) grad_norm: 2.8391 (3.4644) time: 0.6283 [2021-03-28 10:08:23 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 250/1251] eta: 0:10:44 lr: 0.000052 loss: 2.8267 (2.7630) grad_norm: 3.1966 (3.4594) time: 0.6281 [2021-03-28 10:08:29 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 260/1251] eta: 0:10:37 lr: 0.000052 loss: 2.7397 (2.7550) grad_norm: 3.1068 (3.4807) time: 0.6267 [2021-03-28 10:08:35 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 270/1251] eta: 0:10:31 lr: 0.000052 loss: 2.7397 (2.7595) grad_norm: 2.9153 (3.4543) time: 0.6337 [2021-03-28 10:08:42 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 280/1251] eta: 0:10:24 lr: 0.000052 loss: 2.7867 (2.7553) grad_norm: 2.9115 (3.4377) time: 0.6354 [2021-03-28 10:08:48 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 290/1251] eta: 0:10:17 lr: 0.000052 loss: 2.6680 (2.7518) grad_norm: 2.9700 (3.4285) time: 0.6295 [2021-03-28 10:08:54 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 300/1251] eta: 0:10:10 lr: 0.000052 loss: 2.8337 (2.7509) grad_norm: 2.9770 (3.4282) time: 0.6302 [2021-03-28 10:09:00 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 310/1251] eta: 0:10:03 lr: 0.000052 loss: 2.7565 (2.7473) grad_norm: 2.9554 (3.4213) time: 0.6311 [2021-03-28 10:09:07 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 320/1251] eta: 0:09:57 lr: 0.000052 loss: 2.7565 (2.7464) grad_norm: 2.9383 (3.4109) time: 0.6291 [2021-03-28 10:09:13 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 330/1251] eta: 0:09:50 lr: 0.000052 loss: 2.7880 (2.7418) grad_norm: 2.8851 (3.4125) time: 0.6259 [2021-03-28 10:09:19 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 340/1251] eta: 0:09:43 lr: 0.000052 loss: 2.8010 (2.7427) grad_norm: 3.0011 (3.4020) time: 0.6281 [2021-03-28 10:09:26 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 350/1251] eta: 0:09:36 lr: 0.000052 loss: 2.8010 (2.7439) grad_norm: 3.0534 (3.4019) time: 0.6288 [2021-03-28 10:09:32 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 360/1251] eta: 0:09:29 lr: 0.000052 loss: 2.7070 (2.7418) grad_norm: 3.1822 (3.3933) time: 0.6264 [2021-03-28 10:09:38 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 370/1251] eta: 0:09:23 lr: 0.000052 loss: 2.9408 (2.7450) grad_norm: 2.9456 (3.3808) time: 0.6295 [2021-03-28 10:09:44 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 380/1251] eta: 0:09:16 lr: 0.000052 loss: 2.9146 (2.7459) grad_norm: 2.9020 (3.3788) time: 0.6274 [2021-03-28 10:09:51 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 390/1251] eta: 0:09:09 lr: 0.000052 loss: 2.6701 (2.7415) grad_norm: 2.9020 (3.3693) time: 0.6238 [2021-03-28 10:09:57 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 400/1251] eta: 0:09:03 lr: 0.000052 loss: 2.7984 (2.7456) grad_norm: 2.9777 (3.3639) time: 0.6258 [2021-03-28 10:10:03 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 410/1251] eta: 0:08:56 lr: 0.000052 loss: 2.8488 (2.7445) grad_norm: 3.0435 (3.3618) time: 0.6309 [2021-03-28 10:10:10 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 420/1251] eta: 0:08:50 lr: 0.000052 loss: 2.9178 (2.7488) grad_norm: 2.8791 (3.3514) time: 0.6311 [2021-03-28 10:10:16 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 430/1251] eta: 0:08:43 lr: 0.000052 loss: 2.9178 (2.7517) grad_norm: 2.8743 (3.3438) time: 0.6306 [2021-03-28 10:10:22 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 440/1251] eta: 0:08:37 lr: 0.000052 loss: 2.8829 (2.7524) grad_norm: 2.8535 (3.3358) time: 0.6320 [2021-03-28 10:10:28 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 450/1251] eta: 0:08:30 lr: 0.000052 loss: 2.7402 (2.7477) grad_norm: 2.7613 (3.3395) time: 0.6283 [2021-03-28 10:10:35 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 460/1251] eta: 0:08:24 lr: 0.000052 loss: 2.5885 (2.7435) grad_norm: 3.1360 (3.3315) time: 0.6304 [2021-03-28 10:10:41 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 470/1251] eta: 0:08:17 lr: 0.000052 loss: 2.7116 (2.7448) grad_norm: 3.1422 (3.3352) time: 0.6295 [2021-03-28 10:10:47 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 480/1251] eta: 0:08:11 lr: 0.000052 loss: 2.8098 (2.7451) grad_norm: 3.1422 (3.3305) time: 0.6272 [2021-03-28 10:10:54 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 490/1251] eta: 0:08:04 lr: 0.000052 loss: 2.8098 (2.7477) grad_norm: 3.1333 (3.3444) time: 0.6282 [2021-03-28 10:11:00 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 500/1251] eta: 0:07:58 lr: 0.000052 loss: 2.7421 (2.7457) grad_norm: 3.0920 (3.3401) time: 0.6287 [2021-03-28 10:11:06 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 510/1251] eta: 0:07:51 lr: 0.000052 loss: 2.6224 (2.7407) grad_norm: 3.0920 (3.3364) time: 0.6309 [2021-03-28 10:11:13 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 520/1251] eta: 0:07:45 lr: 0.000052 loss: 2.6591 (2.7398) grad_norm: 2.8371 (3.3251) time: 0.6347 [2021-03-28 10:11:19 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 530/1251] eta: 0:07:38 lr: 0.000052 loss: 2.7989 (2.7391) grad_norm: 2.7779 (3.3174) time: 0.6296 [2021-03-28 10:11:25 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 540/1251] eta: 0:07:32 lr: 0.000052 loss: 2.7989 (2.7397) grad_norm: 2.8884 (3.3089) time: 0.6272 [2021-03-28 10:11:32 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 550/1251] eta: 0:07:26 lr: 0.000052 loss: 2.8993 (2.7424) grad_norm: 2.6569 (3.3015) time: 0.6420 [2021-03-28 10:11:38 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 560/1251] eta: 0:07:19 lr: 0.000052 loss: 2.8220 (2.7424) grad_norm: 2.7839 (3.3003) time: 0.6477 [2021-03-28 10:11:44 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 570/1251] eta: 0:07:13 lr: 0.000052 loss: 2.6406 (2.7378) grad_norm: 2.8648 (3.2930) time: 0.6367 [2021-03-28 10:11:51 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 580/1251] eta: 0:07:07 lr: 0.000052 loss: 2.6308 (2.7373) grad_norm: 2.6949 (3.2830) time: 0.6273 [2021-03-28 10:11:57 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 590/1251] eta: 0:07:00 lr: 0.000052 loss: 2.8177 (2.7401) grad_norm: 2.7592 (3.2790) time: 0.6310 [2021-03-28 10:12:03 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 600/1251] eta: 0:06:54 lr: 0.000052 loss: 2.8648 (2.7418) grad_norm: 2.8692 (3.2805) time: 0.6363 [2021-03-28 10:12:10 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 610/1251] eta: 0:06:47 lr: 0.000052 loss: 2.8282 (2.7398) grad_norm: 2.9077 (3.2775) time: 0.6326 [2021-03-28 10:12:16 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 620/1251] eta: 0:06:41 lr: 0.000052 loss: 2.8282 (2.7400) grad_norm: 3.0234 (3.2743) time: 0.6308 [2021-03-28 10:12:22 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 630/1251] eta: 0:06:34 lr: 0.000052 loss: 2.6925 (2.7360) grad_norm: 2.8791 (3.2694) time: 0.6288 [2021-03-28 10:12:28 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 640/1251] eta: 0:06:28 lr: 0.000052 loss: 2.6555 (2.7350) grad_norm: 3.0089 (3.2669) time: 0.6249 [2021-03-28 10:12:35 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 650/1251] eta: 0:06:22 lr: 0.000052 loss: 2.7806 (2.7358) grad_norm: 3.1588 (3.2651) time: 0.6277 [2021-03-28 10:12:41 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 660/1251] eta: 0:06:15 lr: 0.000052 loss: 2.8436 (2.7381) grad_norm: 3.0659 (3.2668) time: 0.6298 [2021-03-28 10:12:47 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 670/1251] eta: 0:06:09 lr: 0.000052 loss: 2.8853 (2.7406) grad_norm: 2.9373 (3.2611) time: 0.6302 [2021-03-28 10:12:54 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 680/1251] eta: 0:06:02 lr: 0.000052 loss: 2.8853 (2.7412) grad_norm: 2.9412 (3.2560) time: 0.6287 [2021-03-28 10:13:00 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 690/1251] eta: 0:05:56 lr: 0.000052 loss: 2.9432 (2.7435) grad_norm: 2.8217 (3.2503) time: 0.6298 [2021-03-28 10:13:06 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 700/1251] eta: 0:05:50 lr: 0.000052 loss: 2.9432 (2.7450) grad_norm: 2.8444 (3.2473) time: 0.6320 [2021-03-28 10:13:13 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 710/1251] eta: 0:05:43 lr: 0.000052 loss: 2.7267 (2.7455) grad_norm: 2.9668 (3.2431) time: 0.6308 [2021-03-28 10:13:19 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 720/1251] eta: 0:05:37 lr: 0.000052 loss: 2.7267 (2.7453) grad_norm: 2.9099 (3.2481) time: 0.6295 [2021-03-28 10:13:25 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 730/1251] eta: 0:05:30 lr: 0.000052 loss: 2.8135 (2.7448) grad_norm: 2.8630 (3.2417) time: 0.6311 [2021-03-28 10:13:32 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 740/1251] eta: 0:05:24 lr: 0.000052 loss: 2.8135 (2.7461) grad_norm: 2.9208 (3.2436) time: 0.6399 [2021-03-28 10:13:38 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 750/1251] eta: 0:05:18 lr: 0.000052 loss: 2.6813 (2.7441) grad_norm: 3.2078 (3.2400) time: 0.6451 [2021-03-28 10:13:44 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 760/1251] eta: 0:05:11 lr: 0.000052 loss: 2.7553 (2.7464) grad_norm: 3.1370 (3.2420) time: 0.6380 [2021-03-28 10:13:51 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 770/1251] eta: 0:05:05 lr: 0.000052 loss: 2.7933 (2.7459) grad_norm: 3.2344 (3.2464) time: 0.6286 [2021-03-28 10:13:57 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 780/1251] eta: 0:04:59 lr: 0.000051 loss: 2.7729 (2.7444) grad_norm: 3.0150 (3.2451) time: 0.6268 [2021-03-28 10:14:03 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 790/1251] eta: 0:04:52 lr: 0.000051 loss: 2.7729 (2.7458) grad_norm: 2.8906 (3.2428) time: 0.6275 [2021-03-28 10:14:10 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 800/1251] eta: 0:04:46 lr: 0.000051 loss: 2.9593 (2.7486) grad_norm: 2.9635 (3.2408) time: 0.6273 [2021-03-28 10:14:16 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 810/1251] eta: 0:04:40 lr: 0.000051 loss: 2.9103 (2.7466) grad_norm: 3.0910 (3.2396) time: 0.6312 [2021-03-28 10:14:22 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 820/1251] eta: 0:04:33 lr: 0.000051 loss: 2.8017 (2.7479) grad_norm: 3.0107 (3.2419) time: 0.6281 [2021-03-28 10:14:28 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 830/1251] eta: 0:04:27 lr: 0.000051 loss: 2.9036 (2.7462) grad_norm: 3.0018 (3.2424) time: 0.6234 [2021-03-28 10:14:35 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 840/1251] eta: 0:04:20 lr: 0.000051 loss: 2.6787 (2.7464) grad_norm: 3.1159 (3.2410) time: 0.6252 [2021-03-28 10:14:41 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 850/1251] eta: 0:04:14 lr: 0.000051 loss: 2.9525 (2.7488) grad_norm: 3.1223 (3.2440) time: 0.6250 [2021-03-28 10:14:47 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 860/1251] eta: 0:04:08 lr: 0.000051 loss: 2.8226 (2.7461) grad_norm: 3.2395 (3.2440) time: 0.6298 [2021-03-28 10:14:54 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 870/1251] eta: 0:04:01 lr: 0.000051 loss: 2.6207 (2.7459) grad_norm: 3.0069 (3.2399) time: 0.6315 [2021-03-28 10:15:00 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 880/1251] eta: 0:03:55 lr: 0.000051 loss: 2.8114 (2.7457) grad_norm: 2.9742 (3.2410) time: 0.6300 [2021-03-28 10:15:06 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 890/1251] eta: 0:03:49 lr: 0.000051 loss: 2.8320 (2.7469) grad_norm: 2.9768 (3.2403) time: 0.6395 [2021-03-28 10:15:13 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 900/1251] eta: 0:03:42 lr: 0.000051 loss: 2.6348 (2.7434) grad_norm: 3.2091 (3.2419) time: 0.6354 [2021-03-28 10:15:19 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 910/1251] eta: 0:03:36 lr: 0.000051 loss: 2.5577 (2.7425) grad_norm: 3.1552 (3.2428) time: 0.6255 [2021-03-28 10:15:25 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 920/1251] eta: 0:03:29 lr: 0.000051 loss: 2.6909 (2.7411) grad_norm: 3.0097 (3.2427) time: 0.6267 [2021-03-28 10:15:31 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 930/1251] eta: 0:03:23 lr: 0.000051 loss: 2.7281 (2.7415) grad_norm: 2.9793 (3.2421) time: 0.6261 [2021-03-28 10:15:38 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 940/1251] eta: 0:03:17 lr: 0.000051 loss: 2.8883 (2.7423) grad_norm: 2.9793 (3.2395) time: 0.6293 [2021-03-28 10:15:44 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 950/1251] eta: 0:03:10 lr: 0.000051 loss: 2.8841 (2.7420) grad_norm: 2.8407 (3.2375) time: 0.6382 [2021-03-28 10:15:50 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 960/1251] eta: 0:03:04 lr: 0.000051 loss: 2.6826 (2.7382) grad_norm: 2.8503 (3.2385) time: 0.6402 [2021-03-28 10:15:57 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 970/1251] eta: 0:02:58 lr: 0.000051 loss: 2.6826 (2.7393) grad_norm: 2.9428 (3.2355) time: 0.6344 [2021-03-28 10:16:03 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 980/1251] eta: 0:02:51 lr: 0.000051 loss: 2.9172 (2.7371) grad_norm: 2.7868 (3.2322) time: 0.6286 [2021-03-28 10:16:09 swin_base_patch4_window7_224] INFO: Epoch: [260] [ 990/1251] eta: 0:02:45 lr: 0.000051 loss: 2.7356 (2.7375) grad_norm: 3.0447 (3.2351) time: 0.6331 [2021-03-28 10:16:16 swin_base_patch4_window7_224] INFO: Epoch: [260] [1000/1251] eta: 0:02:39 lr: 0.000051 loss: 2.7356 (2.7368) grad_norm: 3.0236 (3.2338) time: 0.6349 [2021-03-28 10:16:22 swin_base_patch4_window7_224] INFO: Epoch: [260] [1010/1251] eta: 0:02:32 lr: 0.000051 loss: 2.6374 (2.7368) grad_norm: 3.1167 (3.2379) time: 0.6311 [2021-03-28 10:16:28 swin_base_patch4_window7_224] INFO: Epoch: [260] [1020/1251] eta: 0:02:26 lr: 0.000051 loss: 2.6771 (2.7362) grad_norm: 3.1413 (3.2378) time: 0.6329 [2021-03-28 10:16:35 swin_base_patch4_window7_224] INFO: Epoch: [260] [1030/1251] eta: 0:02:20 lr: 0.000051 loss: 2.8638 (2.7377) grad_norm: 3.0043 (3.2348) time: 0.6275 [2021-03-28 10:16:41 swin_base_patch4_window7_224] INFO: Epoch: [260] [1040/1251] eta: 0:02:13 lr: 0.000051 loss: 2.8890 (2.7389) grad_norm: 2.9795 (3.2337) time: 0.6300 [2021-03-28 10:16:47 swin_base_patch4_window7_224] INFO: Epoch: [260] [1050/1251] eta: 0:02:07 lr: 0.000051 loss: 2.8743 (2.7388) grad_norm: 2.9928 (3.2340) time: 0.6343 [2021-03-28 10:16:54 swin_base_patch4_window7_224] INFO: Epoch: [260] [1060/1251] eta: 0:02:01 lr: 0.000051 loss: 2.8743 (2.7386) grad_norm: 3.1586 (3.2362) time: 0.6283 [2021-03-28 10:17:00 swin_base_patch4_window7_224] INFO: Epoch: [260] [1070/1251] eta: 0:01:54 lr: 0.000051 loss: 2.8150 (2.7374) grad_norm: 2.9787 (3.2379) time: 0.6271 [2021-03-28 10:17:06 swin_base_patch4_window7_224] INFO: Epoch: [260] [1080/1251] eta: 0:01:48 lr: 0.000051 loss: 2.7443 (2.7362) grad_norm: 2.9135 (3.2363) time: 0.6333 [2021-03-28 10:17:13 swin_base_patch4_window7_224] INFO: Epoch: [260] [1090/1251] eta: 0:01:42 lr: 0.000051 loss: 2.6709 (2.7346) grad_norm: 3.1853 (3.2378) time: 0.6356 [2021-03-28 10:17:19 swin_base_patch4_window7_224] INFO: Epoch: [260] [1100/1251] eta: 0:01:35 lr: 0.000051 loss: 2.7960 (2.7362) grad_norm: 3.1837 (3.2364) time: 0.6348 [2021-03-28 10:17:25 swin_base_patch4_window7_224] INFO: Epoch: [260] [1110/1251] eta: 0:01:29 lr: 0.000051 loss: 2.6383 (2.7342) grad_norm: 3.1690 (3.2358) time: 0.6312 [2021-03-28 10:17:32 swin_base_patch4_window7_224] INFO: Epoch: [260] [1120/1251] eta: 0:01:23 lr: 0.000051 loss: 2.6383 (2.7336) grad_norm: 3.1754 (3.2398) time: 0.6302 [2021-03-28 10:17:38 swin_base_patch4_window7_224] INFO: Epoch: [260] [1130/1251] eta: 0:01:16 lr: 0.000051 loss: 2.8191 (2.7341) grad_norm: 3.1548 (3.2387) time: 0.6337 [2021-03-28 10:17:44 swin_base_patch4_window7_224] INFO: Epoch: [260] [1140/1251] eta: 0:01:10 lr: 0.000051 loss: 2.8278 (2.7351) grad_norm: 2.9899 (3.2385) time: 0.6349 [2021-03-28 10:17:51 swin_base_patch4_window7_224] INFO: Epoch: [260] [1150/1251] eta: 0:01:04 lr: 0.000051 loss: 2.8278 (2.7349) grad_norm: 2.7815 (3.2363) time: 0.6345 [2021-03-28 10:17:57 swin_base_patch4_window7_224] INFO: Epoch: [260] [1160/1251] eta: 0:00:57 lr: 0.000051 loss: 2.8841 (2.7358) grad_norm: 2.6985 (3.2334) time: 0.6328 [2021-03-28 10:18:03 swin_base_patch4_window7_224] INFO: Epoch: [260] [1170/1251] eta: 0:00:51 lr: 0.000051 loss: 2.9505 (2.7372) grad_norm: 2.8284 (3.2351) time: 0.6293 [2021-03-28 10:18:10 swin_base_patch4_window7_224] INFO: Epoch: [260] [1180/1251] eta: 0:00:45 lr: 0.000051 loss: 2.7784 (2.7339) grad_norm: 3.0766 (3.2360) time: 0.6354 [2021-03-28 10:18:16 swin_base_patch4_window7_224] INFO: Epoch: [260] [1190/1251] eta: 0:00:38 lr: 0.000051 loss: 2.5956 (2.7347) grad_norm: 3.1786 (3.2359) time: 0.6368 [2021-03-28 10:18:22 swin_base_patch4_window7_224] INFO: Epoch: [260] [1200/1251] eta: 0:00:32 lr: 0.000051 loss: 2.8343 (2.7349) grad_norm: 3.2722 (3.2368) time: 0.6260 [2021-03-28 10:18:28 swin_base_patch4_window7_224] INFO: Epoch: [260] [1210/1251] eta: 0:00:25 lr: 0.000051 loss: 2.8586 (2.7354) grad_norm: 3.2134 (3.2414) time: 0.6256 [2021-03-28 10:18:35 swin_base_patch4_window7_224] INFO: Epoch: [260] [1220/1251] eta: 0:00:19 lr: 0.000051 loss: 2.9664 (2.7359) grad_norm: 2.8697 (3.2391) time: 0.6288 [2021-03-28 10:18:41 swin_base_patch4_window7_224] INFO: Epoch: [260] [1230/1251] eta: 0:00:13 lr: 0.000051 loss: 2.9726 (2.7375) grad_norm: 2.8019 (3.2355) time: 0.6279 [2021-03-28 10:18:47 swin_base_patch4_window7_224] INFO: Epoch: [260] [1240/1251] eta: 0:00:06 lr: 0.000051 loss: 2.8134 (2.7372) grad_norm: 2.7852 (3.2323) time: 0.6249 [2021-03-28 10:18:54 swin_base_patch4_window7_224] INFO: Epoch: [260] [1250/1251] eta: 0:00:00 lr: 0.000051 loss: 2.4768 (2.7347) grad_norm: 2.7821 (3.2291) time: 0.6252 [2021-03-28 10:20:10 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:04 loss: 0.7692 (0.7692) acc1: 81.2500 (81.2500) acc5: 93.7500 (93.7500) [2021-03-28 10:20:11 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7692 (0.7655) acc1: 82.8125 (82.3864) acc5: 96.8750 (96.0227) [2021-03-28 10:20:12 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7555 (0.7525) acc1: 81.2500 (81.9940) acc5: 96.8750 (96.3542) [2021-03-28 10:20:14 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7555 (0.7710) acc1: 81.2500 (81.6028) acc5: 95.3125 (95.8669) [2021-03-28 10:20:15 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7457 (0.7645) acc1: 81.2500 (81.7835) acc5: 96.8750 (96.2652) [2021-03-28 10:20:16 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7483 (0.7522) acc1: 82.8125 (82.0160) acc5: 96.8750 (96.4160) [2021-03-28 10:20:29 swin_base_patch4_window7_224] INFO: * Acc@1 83.148 Acc@5 96.354 loss 0.738 [2021-03-28 10:20:29 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-28 10:20:29 swin_base_patch4_window7_224] INFO: Max accuracy: 83.15% [2021-03-28 10:20:33 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 0/1251] eta: 1:30:23 lr: 0.000051 loss: 3.3679 (3.3679) grad_norm: 2.6961 (2.6961) time: 4.3355 [2021-03-28 10:20:40 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 10/1251] eta: 0:20:13 lr: 0.000051 loss: 2.9503 (2.7844) grad_norm: 2.9428 (3.1970) time: 0.9779 [2021-03-28 10:20:46 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 20/1251] eta: 0:16:38 lr: 0.000051 loss: 2.8658 (2.8079) grad_norm: 2.9428 (3.1958) time: 0.6346 [2021-03-28 10:20:53 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 30/1251] eta: 0:15:24 lr: 0.000051 loss: 2.8658 (2.7801) grad_norm: 3.0420 (3.2276) time: 0.6353 [2021-03-28 10:20:59 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 40/1251] eta: 0:14:39 lr: 0.000051 loss: 2.6572 (2.7754) grad_norm: 3.0420 (3.1795) time: 0.6371 [2021-03-28 10:21:05 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 50/1251] eta: 0:14:11 lr: 0.000051 loss: 2.6572 (2.7376) grad_norm: 3.1664 (3.2912) time: 0.6353 [2021-03-28 10:21:12 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 60/1251] eta: 0:13:48 lr: 0.000051 loss: 2.7121 (2.7081) grad_norm: 3.2740 (3.2950) time: 0.6338 [2021-03-28 10:21:18 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 70/1251] eta: 0:13:29 lr: 0.000051 loss: 2.7262 (2.7103) grad_norm: 3.1004 (3.2936) time: 0.6263 [2021-03-28 10:21:24 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 80/1251] eta: 0:13:15 lr: 0.000051 loss: 2.6318 (2.6721) grad_norm: 2.9788 (3.2842) time: 0.6296 [2021-03-28 10:21:30 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 90/1251] eta: 0:13:03 lr: 0.000051 loss: 2.6141 (2.6883) grad_norm: 3.2941 (3.3175) time: 0.6339 [2021-03-28 10:21:37 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 100/1251] eta: 0:12:52 lr: 0.000051 loss: 2.8007 (2.6803) grad_norm: 3.2304 (3.2888) time: 0.6355 [2021-03-28 10:21:43 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 110/1251] eta: 0:12:41 lr: 0.000051 loss: 2.8007 (2.6863) grad_norm: 2.9832 (3.2848) time: 0.6356 [2021-03-28 10:21:50 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 120/1251] eta: 0:12:32 lr: 0.000051 loss: 2.7640 (2.6852) grad_norm: 2.9832 (3.2495) time: 0.6362 [2021-03-28 10:21:56 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 130/1251] eta: 0:12:22 lr: 0.000050 loss: 2.8279 (2.6969) grad_norm: 2.7434 (3.2258) time: 0.6343 [2021-03-28 10:22:02 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 140/1251] eta: 0:12:13 lr: 0.000050 loss: 2.7734 (2.6885) grad_norm: 2.8050 (3.2096) time: 0.6332 [2021-03-28 10:22:09 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 150/1251] eta: 0:12:05 lr: 0.000050 loss: 2.7711 (2.7000) grad_norm: 2.8425 (3.1961) time: 0.6335 [2021-03-28 10:22:15 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 160/1251] eta: 0:11:56 lr: 0.000050 loss: 2.8756 (2.7073) grad_norm: 2.9266 (3.1965) time: 0.6272 [2021-03-28 10:22:21 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 170/1251] eta: 0:11:48 lr: 0.000050 loss: 2.7809 (2.7023) grad_norm: 2.9331 (3.1894) time: 0.6282 [2021-03-28 10:22:27 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 180/1251] eta: 0:11:40 lr: 0.000050 loss: 2.6642 (2.7039) grad_norm: 2.9711 (3.1784) time: 0.6339 [2021-03-28 10:22:34 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 190/1251] eta: 0:11:32 lr: 0.000050 loss: 2.7472 (2.7087) grad_norm: 3.0262 (3.1915) time: 0.6302 [2021-03-28 10:22:40 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 200/1251] eta: 0:11:25 lr: 0.000050 loss: 2.7983 (2.7070) grad_norm: 3.1000 (3.1889) time: 0.6348 [2021-03-28 10:22:46 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 210/1251] eta: 0:11:17 lr: 0.000050 loss: 2.5935 (2.7020) grad_norm: 3.0866 (3.1927) time: 0.6347 [2021-03-28 10:22:53 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 220/1251] eta: 0:11:10 lr: 0.000050 loss: 3.0297 (2.7189) grad_norm: 3.0114 (3.2086) time: 0.6290 [2021-03-28 10:22:59 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 230/1251] eta: 0:11:02 lr: 0.000050 loss: 2.9402 (2.7153) grad_norm: 2.9472 (3.1959) time: 0.6328 [2021-03-28 10:23:05 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 240/1251] eta: 0:10:55 lr: 0.000050 loss: 2.7815 (2.7148) grad_norm: 2.9683 (3.1968) time: 0.6334 [2021-03-28 10:23:12 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 250/1251] eta: 0:10:48 lr: 0.000050 loss: 2.7815 (2.7084) grad_norm: 2.9257 (3.1995) time: 0.6350 [2021-03-28 10:23:18 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 260/1251] eta: 0:10:41 lr: 0.000050 loss: 2.5414 (2.7012) grad_norm: 2.8949 (3.1992) time: 0.6311 [2021-03-28 10:23:24 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 270/1251] eta: 0:10:34 lr: 0.000050 loss: 2.7202 (2.7023) grad_norm: 2.9920 (3.2117) time: 0.6259 [2021-03-28 10:23:30 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 280/1251] eta: 0:10:26 lr: 0.000050 loss: 2.7202 (2.7025) grad_norm: 3.0321 (3.2089) time: 0.6235 [2021-03-28 10:23:37 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 290/1251] eta: 0:10:19 lr: 0.000050 loss: 2.7516 (2.7083) grad_norm: 2.8105 (3.2029) time: 0.6250 [2021-03-28 10:23:43 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 300/1251] eta: 0:10:12 lr: 0.000050 loss: 2.8011 (2.7099) grad_norm: 2.8271 (3.1964) time: 0.6285 [2021-03-28 10:23:49 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 310/1251] eta: 0:10:06 lr: 0.000050 loss: 2.7959 (2.7109) grad_norm: 2.8955 (3.1918) time: 0.6327 [2021-03-28 10:23:56 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 320/1251] eta: 0:09:59 lr: 0.000050 loss: 2.7959 (2.7115) grad_norm: 2.9060 (3.1874) time: 0.6349 [2021-03-28 10:24:02 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 330/1251] eta: 0:09:52 lr: 0.000050 loss: 2.7334 (2.7142) grad_norm: 3.0503 (3.1905) time: 0.6332 [2021-03-28 10:24:08 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 340/1251] eta: 0:09:45 lr: 0.000050 loss: 2.7328 (2.7082) grad_norm: 3.1765 (3.1889) time: 0.6288 [2021-03-28 10:24:15 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 350/1251] eta: 0:09:39 lr: 0.000050 loss: 2.7394 (2.7119) grad_norm: 3.1702 (3.1913) time: 0.6309 [2021-03-28 10:24:21 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 360/1251] eta: 0:09:32 lr: 0.000050 loss: 2.7189 (2.7081) grad_norm: 3.1343 (3.1930) time: 0.6347 [2021-03-28 10:24:27 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 370/1251] eta: 0:09:25 lr: 0.000050 loss: 2.7189 (2.7086) grad_norm: 3.0781 (3.1889) time: 0.6308 [2021-03-28 10:24:34 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 380/1251] eta: 0:09:18 lr: 0.000050 loss: 2.7858 (2.7099) grad_norm: 3.1826 (3.1931) time: 0.6291 [2021-03-28 10:24:40 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 390/1251] eta: 0:09:12 lr: 0.000050 loss: 2.6329 (2.7025) grad_norm: 3.1239 (3.1883) time: 0.6288 [2021-03-28 10:24:46 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 400/1251] eta: 0:09:05 lr: 0.000050 loss: 2.7899 (2.7082) grad_norm: 3.0423 (3.1895) time: 0.6253 [2021-03-28 10:24:52 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 410/1251] eta: 0:08:58 lr: 0.000050 loss: 2.8491 (2.7033) grad_norm: 3.0526 (3.1930) time: 0.6251 [2021-03-28 10:24:59 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 420/1251] eta: 0:08:52 lr: 0.000050 loss: 2.8450 (2.7055) grad_norm: 3.1432 (3.2008) time: 0.6268 [2021-03-28 10:25:05 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 430/1251] eta: 0:08:45 lr: 0.000050 loss: 2.8450 (2.7058) grad_norm: 3.1432 (3.2025) time: 0.6248 [2021-03-28 10:25:11 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 440/1251] eta: 0:08:38 lr: 0.000050 loss: 2.8215 (2.7040) grad_norm: 2.9282 (3.1970) time: 0.6264 [2021-03-28 10:25:17 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 450/1251] eta: 0:08:32 lr: 0.000050 loss: 2.7010 (2.7050) grad_norm: 2.9540 (3.1982) time: 0.6270 [2021-03-28 10:25:24 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 460/1251] eta: 0:08:25 lr: 0.000050 loss: 2.6709 (2.7016) grad_norm: 2.9540 (3.1943) time: 0.6275 [2021-03-28 10:25:30 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 470/1251] eta: 0:08:19 lr: 0.000050 loss: 2.7365 (2.7023) grad_norm: 2.8762 (3.1881) time: 0.6302 [2021-03-28 10:25:37 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 480/1251] eta: 0:08:12 lr: 0.000050 loss: 2.8319 (2.7031) grad_norm: 2.8953 (3.1857) time: 0.6371 [2021-03-28 10:25:43 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 490/1251] eta: 0:08:06 lr: 0.000050 loss: 2.7921 (2.7012) grad_norm: 3.2238 (3.1905) time: 0.6397 [2021-03-28 10:25:49 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 500/1251] eta: 0:07:59 lr: 0.000050 loss: 2.7461 (2.7017) grad_norm: 3.2309 (3.1901) time: 0.6384 [2021-03-28 10:25:56 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 510/1251] eta: 0:07:53 lr: 0.000050 loss: 2.7100 (2.6985) grad_norm: 3.0872 (3.1953) time: 0.6340 [2021-03-28 10:26:02 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 520/1251] eta: 0:07:46 lr: 0.000050 loss: 2.7100 (2.6998) grad_norm: 2.8384 (3.1955) time: 0.6270 [2021-03-28 10:26:08 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 530/1251] eta: 0:07:40 lr: 0.000050 loss: 2.9095 (2.7035) grad_norm: 2.7982 (3.1895) time: 0.6261 [2021-03-28 10:26:14 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 540/1251] eta: 0:07:33 lr: 0.000050 loss: 2.8042 (2.7020) grad_norm: 3.0277 (3.1923) time: 0.6286 [2021-03-28 10:26:21 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 550/1251] eta: 0:07:27 lr: 0.000050 loss: 2.6365 (2.7011) grad_norm: 2.9519 (3.1902) time: 0.6390 [2021-03-28 10:26:27 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 560/1251] eta: 0:07:21 lr: 0.000050 loss: 2.8203 (2.7005) grad_norm: 2.9900 (3.1917) time: 0.6460 [2021-03-28 10:26:34 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 570/1251] eta: 0:07:14 lr: 0.000050 loss: 2.7855 (2.7015) grad_norm: 3.0492 (3.1881) time: 0.6387 [2021-03-28 10:26:40 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 580/1251] eta: 0:07:08 lr: 0.000050 loss: 2.7445 (2.6999) grad_norm: 3.0320 (3.1913) time: 0.6309 [2021-03-28 10:26:46 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 590/1251] eta: 0:07:01 lr: 0.000050 loss: 2.7469 (2.6995) grad_norm: 2.9762 (3.1874) time: 0.6312 [2021-03-28 10:26:53 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 600/1251] eta: 0:06:55 lr: 0.000050 loss: 2.8601 (2.7034) grad_norm: 2.9466 (3.1872) time: 0.6331 [2021-03-28 10:26:59 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 610/1251] eta: 0:06:48 lr: 0.000050 loss: 2.9007 (2.7034) grad_norm: 3.0548 (3.1892) time: 0.6294 [2021-03-28 10:27:05 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 620/1251] eta: 0:06:42 lr: 0.000050 loss: 2.8977 (2.7053) grad_norm: 3.0548 (3.1874) time: 0.6274 [2021-03-28 10:27:11 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 630/1251] eta: 0:06:35 lr: 0.000050 loss: 2.8804 (2.7058) grad_norm: 3.0142 (3.1910) time: 0.6273 [2021-03-28 10:27:18 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 640/1251] eta: 0:06:29 lr: 0.000050 loss: 2.8259 (2.7071) grad_norm: 2.9175 (3.1909) time: 0.6243 [2021-03-28 10:27:24 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 650/1251] eta: 0:06:22 lr: 0.000050 loss: 2.7380 (2.7057) grad_norm: 2.8601 (3.1881) time: 0.6225 [2021-03-28 10:27:30 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 660/1251] eta: 0:06:16 lr: 0.000050 loss: 2.7064 (2.7031) grad_norm: 2.9445 (3.1955) time: 0.6245 [2021-03-28 10:27:36 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 670/1251] eta: 0:06:09 lr: 0.000050 loss: 2.7117 (2.7039) grad_norm: 2.9379 (3.1907) time: 0.6283 [2021-03-28 10:27:43 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 680/1251] eta: 0:06:03 lr: 0.000050 loss: 2.7139 (2.7041) grad_norm: 2.9773 (3.1914) time: 0.6323 [2021-03-28 10:27:49 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 690/1251] eta: 0:05:57 lr: 0.000050 loss: 2.5796 (2.7043) grad_norm: 3.1516 (3.1972) time: 0.6338 [2021-03-28 10:27:55 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 700/1251] eta: 0:05:50 lr: 0.000050 loss: 2.8598 (2.7073) grad_norm: 3.2159 (3.1993) time: 0.6283 [2021-03-28 10:28:02 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 710/1251] eta: 0:05:44 lr: 0.000050 loss: 2.9592 (2.7083) grad_norm: 3.2201 (3.2005) time: 0.6273 [2021-03-28 10:28:08 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 720/1251] eta: 0:05:37 lr: 0.000050 loss: 2.8916 (2.7106) grad_norm: 3.2065 (3.2069) time: 0.6334 [2021-03-28 10:28:14 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 730/1251] eta: 0:05:31 lr: 0.000050 loss: 2.8614 (2.7123) grad_norm: 3.1428 (3.2055) time: 0.6392 [2021-03-28 10:28:21 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 740/1251] eta: 0:05:25 lr: 0.000050 loss: 2.8151 (2.7126) grad_norm: 3.0561 (3.2043) time: 0.6407 [2021-03-28 10:28:27 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 750/1251] eta: 0:05:18 lr: 0.000049 loss: 2.7701 (2.7102) grad_norm: 2.9216 (3.2020) time: 0.6367 [2021-03-28 10:28:34 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 760/1251] eta: 0:05:12 lr: 0.000049 loss: 2.7038 (2.7085) grad_norm: 2.9371 (3.2024) time: 0.6370 [2021-03-28 10:28:40 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 770/1251] eta: 0:05:06 lr: 0.000049 loss: 2.4735 (2.7069) grad_norm: 2.8885 (3.2003) time: 0.6304 [2021-03-28 10:28:46 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 780/1251] eta: 0:04:59 lr: 0.000049 loss: 2.7165 (2.7090) grad_norm: 2.8701 (3.1990) time: 0.6298 [2021-03-28 10:28:53 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 790/1251] eta: 0:04:53 lr: 0.000049 loss: 2.8152 (2.7096) grad_norm: 2.8781 (3.1978) time: 0.6349 [2021-03-28 10:28:59 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 800/1251] eta: 0:04:46 lr: 0.000049 loss: 2.8152 (2.7091) grad_norm: 3.0209 (3.1949) time: 0.6309 [2021-03-28 10:29:05 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 810/1251] eta: 0:04:40 lr: 0.000049 loss: 2.8192 (2.7100) grad_norm: 2.9885 (3.1931) time: 0.6298 [2021-03-28 10:29:11 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 820/1251] eta: 0:04:34 lr: 0.000049 loss: 2.8192 (2.7105) grad_norm: 3.0171 (3.1935) time: 0.6266 [2021-03-28 10:29:18 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 830/1251] eta: 0:04:27 lr: 0.000049 loss: 2.8208 (2.7121) grad_norm: 3.3641 (3.1974) time: 0.6221 [2021-03-28 10:29:24 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 840/1251] eta: 0:04:21 lr: 0.000049 loss: 2.8792 (2.7135) grad_norm: 3.3407 (3.1962) time: 0.6272 [2021-03-28 10:29:30 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 850/1251] eta: 0:04:14 lr: 0.000049 loss: 2.9234 (2.7159) grad_norm: 2.8147 (3.1945) time: 0.6295 [2021-03-28 10:29:37 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 860/1251] eta: 0:04:08 lr: 0.000049 loss: 2.9936 (2.7132) grad_norm: 2.9009 (3.1919) time: 0.6330 [2021-03-28 10:29:43 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 870/1251] eta: 0:04:02 lr: 0.000049 loss: 2.6627 (2.7136) grad_norm: 3.0942 (3.1957) time: 0.6365 [2021-03-28 10:29:49 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 880/1251] eta: 0:03:55 lr: 0.000049 loss: 2.6627 (2.7127) grad_norm: 3.0976 (3.1938) time: 0.6360 [2021-03-28 10:29:56 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 890/1251] eta: 0:03:49 lr: 0.000049 loss: 2.5965 (2.7120) grad_norm: 2.9127 (3.1910) time: 0.6345 [2021-03-28 10:30:02 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 900/1251] eta: 0:03:43 lr: 0.000049 loss: 2.9283 (2.7152) grad_norm: 3.0044 (3.1927) time: 0.6327 [2021-03-28 10:30:08 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 910/1251] eta: 0:03:36 lr: 0.000049 loss: 2.8508 (2.7161) grad_norm: 3.0174 (3.1913) time: 0.6358 [2021-03-28 10:30:15 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 920/1251] eta: 0:03:30 lr: 0.000049 loss: 2.8056 (2.7146) grad_norm: 2.9018 (3.1964) time: 0.6288 [2021-03-28 10:30:21 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 930/1251] eta: 0:03:23 lr: 0.000049 loss: 2.8366 (2.7155) grad_norm: 2.9414 (3.2045) time: 0.6275 [2021-03-28 10:30:27 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 940/1251] eta: 0:03:17 lr: 0.000049 loss: 2.8920 (2.7172) grad_norm: 3.0034 (3.2061) time: 0.6314 [2021-03-28 10:30:34 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 950/1251] eta: 0:03:11 lr: 0.000049 loss: 2.8663 (2.7171) grad_norm: 3.1035 (3.2081) time: 0.6345 [2021-03-28 10:30:40 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 960/1251] eta: 0:03:04 lr: 0.000049 loss: 2.8886 (2.7185) grad_norm: 3.0887 (3.2073) time: 0.6343 [2021-03-28 10:30:46 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 970/1251] eta: 0:02:58 lr: 0.000049 loss: 2.8766 (2.7190) grad_norm: 3.2942 (3.2084) time: 0.6330 [2021-03-28 10:30:53 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 980/1251] eta: 0:02:52 lr: 0.000049 loss: 2.7541 (2.7182) grad_norm: 3.0033 (3.2098) time: 0.6331 [2021-03-28 10:30:59 swin_base_patch4_window7_224] INFO: Epoch: [261] [ 990/1251] eta: 0:02:45 lr: 0.000049 loss: 2.7573 (2.7190) grad_norm: 3.0065 (3.2092) time: 0.6304 [2021-03-28 10:31:05 swin_base_patch4_window7_224] INFO: Epoch: [261] [1000/1251] eta: 0:02:39 lr: 0.000049 loss: 2.8508 (2.7198) grad_norm: 3.0545 (3.2079) time: 0.6251 [2021-03-28 10:31:11 swin_base_patch4_window7_224] INFO: Epoch: [261] [1010/1251] eta: 0:02:33 lr: 0.000049 loss: 2.8508 (2.7193) grad_norm: 3.0545 (3.2090) time: 0.6210 [2021-03-28 10:31:18 swin_base_patch4_window7_224] INFO: Epoch: [261] [1020/1251] eta: 0:02:26 lr: 0.000049 loss: 2.7293 (2.7192) grad_norm: 3.0768 (3.2146) time: 0.6262 [2021-03-28 10:31:24 swin_base_patch4_window7_224] INFO: Epoch: [261] [1030/1251] eta: 0:02:20 lr: 0.000049 loss: 2.8842 (2.7197) grad_norm: 3.0411 (inf) time: 0.6247 [2021-03-28 10:31:30 swin_base_patch4_window7_224] INFO: Epoch: [261] [1040/1251] eta: 0:02:13 lr: 0.000049 loss: 2.8450 (2.7191) grad_norm: 3.0411 (inf) time: 0.6226 [2021-03-28 10:31:36 swin_base_patch4_window7_224] INFO: Epoch: [261] [1050/1251] eta: 0:02:07 lr: 0.000049 loss: 2.8450 (2.7194) grad_norm: 3.0072 (inf) time: 0.6275 [2021-03-28 10:31:43 swin_base_patch4_window7_224] INFO: Epoch: [261] [1060/1251] eta: 0:02:01 lr: 0.000049 loss: 2.9546 (2.7207) grad_norm: 3.1283 (inf) time: 0.6266 [2021-03-28 10:31:49 swin_base_patch4_window7_224] INFO: Epoch: [261] [1070/1251] eta: 0:01:54 lr: 0.000049 loss: 2.8485 (2.7215) grad_norm: 3.1162 (inf) time: 0.6320 [2021-03-28 10:31:55 swin_base_patch4_window7_224] INFO: Epoch: [261] [1080/1251] eta: 0:01:48 lr: 0.000049 loss: 2.8485 (2.7236) grad_norm: 3.1658 (inf) time: 0.6357 [2021-03-28 10:32:01 swin_base_patch4_window7_224] INFO: Epoch: [261] [1090/1251] eta: 0:01:42 lr: 0.000049 loss: 2.8247 (2.7218) grad_norm: 3.0323 (inf) time: 0.6270 [2021-03-28 10:32:08 swin_base_patch4_window7_224] INFO: Epoch: [261] [1100/1251] eta: 0:01:35 lr: 0.000049 loss: 2.7173 (2.7223) grad_norm: 3.0921 (inf) time: 0.6248 [2021-03-28 10:32:14 swin_base_patch4_window7_224] INFO: Epoch: [261] [1110/1251] eta: 0:01:29 lr: 0.000049 loss: 2.8401 (2.7223) grad_norm: 3.2541 (inf) time: 0.6331 [2021-03-28 10:32:21 swin_base_patch4_window7_224] INFO: Epoch: [261] [1120/1251] eta: 0:01:23 lr: 0.000049 loss: 2.7500 (2.7214) grad_norm: 3.0225 (inf) time: 0.6387 [2021-03-28 10:32:27 swin_base_patch4_window7_224] INFO: Epoch: [261] [1130/1251] eta: 0:01:16 lr: 0.000049 loss: 2.7500 (2.7228) grad_norm: 2.8080 (inf) time: 0.6318 [2021-03-28 10:32:33 swin_base_patch4_window7_224] INFO: Epoch: [261] [1140/1251] eta: 0:01:10 lr: 0.000049 loss: 2.8694 (2.7227) grad_norm: 2.8532 (inf) time: 0.6286 [2021-03-28 10:32:39 swin_base_patch4_window7_224] INFO: Epoch: [261] [1150/1251] eta: 0:01:04 lr: 0.000049 loss: 2.8306 (2.7232) grad_norm: 2.9662 (inf) time: 0.6349 [2021-03-28 10:32:46 swin_base_patch4_window7_224] INFO: Epoch: [261] [1160/1251] eta: 0:00:57 lr: 0.000049 loss: 2.9158 (2.7242) grad_norm: 3.1380 (inf) time: 0.6355 [2021-03-28 10:32:52 swin_base_patch4_window7_224] INFO: Epoch: [261] [1170/1251] eta: 0:00:51 lr: 0.000049 loss: 2.8438 (2.7245) grad_norm: 3.1651 (inf) time: 0.6277 [2021-03-28 10:32:58 swin_base_patch4_window7_224] INFO: Epoch: [261] [1180/1251] eta: 0:00:45 lr: 0.000049 loss: 2.8438 (2.7260) grad_norm: 3.3122 (inf) time: 0.6262 [2021-03-28 10:33:05 swin_base_patch4_window7_224] INFO: Epoch: [261] [1190/1251] eta: 0:00:38 lr: 0.000049 loss: 2.8732 (2.7268) grad_norm: 3.1443 (inf) time: 0.6295 [2021-03-28 10:33:11 swin_base_patch4_window7_224] INFO: Epoch: [261] [1200/1251] eta: 0:00:32 lr: 0.000049 loss: 2.8332 (2.7257) grad_norm: 3.0578 (inf) time: 0.6285 [2021-03-28 10:33:17 swin_base_patch4_window7_224] INFO: Epoch: [261] [1210/1251] eta: 0:00:25 lr: 0.000049 loss: 2.6892 (2.7244) grad_norm: 2.9676 (inf) time: 0.6249 [2021-03-28 10:33:23 swin_base_patch4_window7_224] INFO: Epoch: [261] [1220/1251] eta: 0:00:19 lr: 0.000049 loss: 2.9147 (2.7261) grad_norm: 3.0483 (inf) time: 0.6277 [2021-03-28 10:33:30 swin_base_patch4_window7_224] INFO: Epoch: [261] [1230/1251] eta: 0:00:13 lr: 0.000049 loss: 2.9147 (2.7260) grad_norm: 3.0878 (inf) time: 0.6306 [2021-03-28 10:33:36 swin_base_patch4_window7_224] INFO: Epoch: [261] [1240/1251] eta: 0:00:06 lr: 0.000049 loss: 2.8644 (2.7271) grad_norm: 3.2053 (inf) time: 0.6228 [2021-03-28 10:33:42 swin_base_patch4_window7_224] INFO: Epoch: [261] [1250/1251] eta: 0:00:00 lr: 0.000049 loss: 2.8226 (2.7275) grad_norm: 3.1440 (inf) time: 0.6129 [2021-03-28 10:33:56 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:54 loss: 0.8857 (0.8857) acc1: 79.6875 (79.6875) acc5: 92.1875 (92.1875) [2021-03-28 10:33:59 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8526 (0.8545) acc1: 79.6875 (79.4034) acc5: 95.3125 (95.3125) [2021-03-28 10:34:01 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8178 (0.8052) acc1: 81.2500 (80.8036) acc5: 95.3125 (95.7589) [2021-03-28 10:34:03 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6888 (0.7750) acc1: 82.8125 (81.6028) acc5: 95.3125 (95.9173) [2021-03-28 10:34:06 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6965 (0.7659) acc1: 82.8125 (81.7073) acc5: 96.8750 (96.0747) [2021-03-28 10:34:07 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7110 (0.7572) acc1: 81.2500 (81.9840) acc5: 96.8750 (96.0960) [2021-03-28 10:34:22 swin_base_patch4_window7_224] INFO: * Acc@1 83.056 Acc@5 96.244 loss 0.743 [2021-03-28 10:34:22 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-28 10:34:22 swin_base_patch4_window7_224] INFO: Max accuracy: 83.15% [2021-03-28 10:34:26 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 0/1251] eta: 1:25:52 lr: 0.000049 loss: 2.7192 (2.7192) grad_norm: 2.9134 (2.9134) time: 4.1187 [2021-03-28 10:34:33 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 10/1251] eta: 0:19:39 lr: 0.000049 loss: 2.7947 (2.6453) grad_norm: 2.8550 (2.9050) time: 0.9504 [2021-03-28 10:34:39 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 20/1251] eta: 0:16:22 lr: 0.000049 loss: 2.7947 (2.6343) grad_norm: 2.8976 (3.1463) time: 0.6320 [2021-03-28 10:34:45 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 30/1251] eta: 0:15:09 lr: 0.000049 loss: 2.7850 (2.6961) grad_norm: 3.2442 (3.2481) time: 0.6323 [2021-03-28 10:34:52 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 40/1251] eta: 0:14:30 lr: 0.000049 loss: 2.8203 (2.7221) grad_norm: 3.1027 (3.2024) time: 0.6357 [2021-03-28 10:34:58 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 50/1251] eta: 0:14:04 lr: 0.000049 loss: 2.9902 (2.7285) grad_norm: 2.9014 (3.1372) time: 0.6376 [2021-03-28 10:35:04 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 60/1251] eta: 0:13:43 lr: 0.000049 loss: 2.6514 (2.7006) grad_norm: 2.9014 (3.1426) time: 0.6355 [2021-03-28 10:35:11 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 70/1251] eta: 0:13:27 lr: 0.000049 loss: 2.6642 (2.7091) grad_norm: 2.9023 (3.1210) time: 0.6352 [2021-03-28 10:35:17 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 80/1251] eta: 0:13:12 lr: 0.000049 loss: 2.6642 (2.6786) grad_norm: 2.8912 (3.1268) time: 0.6313 [2021-03-28 10:35:23 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 90/1251] eta: 0:12:59 lr: 0.000049 loss: 2.7873 (2.6886) grad_norm: 2.8642 (3.1147) time: 0.6286 [2021-03-28 10:35:30 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 100/1251] eta: 0:12:49 lr: 0.000049 loss: 2.8716 (2.6891) grad_norm: 2.9008 (3.1038) time: 0.6378 [2021-03-28 10:35:36 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 110/1251] eta: 0:12:38 lr: 0.000049 loss: 2.5907 (2.6646) grad_norm: 2.9008 (3.1021) time: 0.6337 [2021-03-28 10:35:42 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 120/1251] eta: 0:12:28 lr: 0.000048 loss: 2.5928 (2.6635) grad_norm: 2.8405 (3.0854) time: 0.6275 [2021-03-28 10:35:48 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 130/1251] eta: 0:12:19 lr: 0.000048 loss: 2.7175 (2.6762) grad_norm: 2.9179 (3.1022) time: 0.6300 [2021-03-28 10:35:55 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 140/1251] eta: 0:12:10 lr: 0.000048 loss: 2.6693 (2.6664) grad_norm: 2.9897 (3.1122) time: 0.6279 [2021-03-28 10:36:01 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 150/1251] eta: 0:12:01 lr: 0.000048 loss: 2.6693 (2.6711) grad_norm: 3.0274 (3.1180) time: 0.6294 [2021-03-28 10:36:07 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 160/1251] eta: 0:11:53 lr: 0.000048 loss: 2.8002 (2.6778) grad_norm: 3.1244 (3.1365) time: 0.6310 [2021-03-28 10:36:14 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 170/1251] eta: 0:11:44 lr: 0.000048 loss: 2.8124 (2.6787) grad_norm: 3.2080 (3.1556) time: 0.6259 [2021-03-28 10:36:20 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 180/1251] eta: 0:11:37 lr: 0.000048 loss: 2.8655 (2.6934) grad_norm: 3.2735 (3.1543) time: 0.6265 [2021-03-28 10:36:26 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 190/1251] eta: 0:11:29 lr: 0.000048 loss: 2.8897 (2.7012) grad_norm: 3.1464 (3.1654) time: 0.6349 [2021-03-28 10:36:33 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 200/1251] eta: 0:11:22 lr: 0.000048 loss: 2.8818 (2.7030) grad_norm: 3.1464 (3.1834) time: 0.6324 [2021-03-28 10:36:39 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 210/1251] eta: 0:11:14 lr: 0.000048 loss: 2.6740 (2.6957) grad_norm: 2.9132 (3.1851) time: 0.6301 [2021-03-28 10:36:45 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 220/1251] eta: 0:11:07 lr: 0.000048 loss: 2.5118 (2.6921) grad_norm: 2.9132 (3.1772) time: 0.6283 [2021-03-28 10:36:51 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 230/1251] eta: 0:11:00 lr: 0.000048 loss: 2.5022 (2.6883) grad_norm: 2.8353 (3.1643) time: 0.6282 [2021-03-28 10:36:58 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 240/1251] eta: 0:10:52 lr: 0.000048 loss: 2.6190 (2.6898) grad_norm: 2.7897 (3.1562) time: 0.6299 [2021-03-28 10:37:04 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 250/1251] eta: 0:10:45 lr: 0.000048 loss: 2.6806 (2.6850) grad_norm: 2.7922 (3.1545) time: 0.6299 [2021-03-28 10:37:10 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 260/1251] eta: 0:10:39 lr: 0.000048 loss: 2.7982 (2.6854) grad_norm: 2.8458 (3.1497) time: 0.6360 [2021-03-28 10:37:17 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 270/1251] eta: 0:10:31 lr: 0.000048 loss: 2.9166 (2.6976) grad_norm: 3.0150 (3.1450) time: 0.6307 [2021-03-28 10:37:23 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 280/1251] eta: 0:10:24 lr: 0.000048 loss: 2.9895 (2.6968) grad_norm: 2.9247 (3.1385) time: 0.6235 [2021-03-28 10:37:29 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 290/1251] eta: 0:10:18 lr: 0.000048 loss: 2.7078 (2.6961) grad_norm: 2.9079 (3.1449) time: 0.6281 [2021-03-28 10:37:36 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 300/1251] eta: 0:10:11 lr: 0.000048 loss: 2.7078 (2.6972) grad_norm: 3.0223 (3.1484) time: 0.6283 [2021-03-28 10:37:42 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 310/1251] eta: 0:10:04 lr: 0.000048 loss: 2.8558 (2.6984) grad_norm: 3.0697 (3.1666) time: 0.6259 [2021-03-28 10:37:48 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 320/1251] eta: 0:09:57 lr: 0.000048 loss: 2.8558 (2.6940) grad_norm: 3.1764 (3.1654) time: 0.6261 [2021-03-28 10:37:54 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 330/1251] eta: 0:09:50 lr: 0.000048 loss: 2.6811 (2.6917) grad_norm: 3.0084 (3.1635) time: 0.6267 [2021-03-28 10:38:01 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 340/1251] eta: 0:09:43 lr: 0.000048 loss: 2.6412 (2.6886) grad_norm: 3.0084 (3.1646) time: 0.6273 [2021-03-28 10:38:07 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 350/1251] eta: 0:09:36 lr: 0.000048 loss: 2.8070 (2.6952) grad_norm: 2.9235 (3.1607) time: 0.6272 [2021-03-28 10:38:13 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 360/1251] eta: 0:09:30 lr: 0.000048 loss: 2.7171 (2.6884) grad_norm: 2.8363 (3.1520) time: 0.6301 [2021-03-28 10:38:19 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 370/1251] eta: 0:09:23 lr: 0.000048 loss: 2.7202 (2.6938) grad_norm: 3.1221 (3.1603) time: 0.6302 [2021-03-28 10:38:26 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 380/1251] eta: 0:09:17 lr: 0.000048 loss: 2.8162 (2.6945) grad_norm: 3.1615 (3.1578) time: 0.6311 [2021-03-28 10:38:32 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 390/1251] eta: 0:09:10 lr: 0.000048 loss: 2.8796 (2.6980) grad_norm: 3.0073 (3.1540) time: 0.6314 [2021-03-28 10:38:38 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 400/1251] eta: 0:09:03 lr: 0.000048 loss: 2.8796 (2.6955) grad_norm: 2.9311 (3.1513) time: 0.6307 [2021-03-28 10:38:45 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 410/1251] eta: 0:08:57 lr: 0.000048 loss: 3.0553 (2.7047) grad_norm: 2.8519 (3.1453) time: 0.6276 [2021-03-28 10:38:51 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 420/1251] eta: 0:08:50 lr: 0.000048 loss: 2.9740 (2.7059) grad_norm: 2.7269 (3.1402) time: 0.6300 [2021-03-28 10:38:57 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 430/1251] eta: 0:08:44 lr: 0.000048 loss: 2.9110 (2.7104) grad_norm: 2.7327 (3.1349) time: 0.6332 [2021-03-28 10:39:04 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 440/1251] eta: 0:08:37 lr: 0.000048 loss: 3.0053 (2.7102) grad_norm: 2.9488 (3.1413) time: 0.6340 [2021-03-28 10:39:10 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 450/1251] eta: 0:08:31 lr: 0.000048 loss: 2.8465 (2.7110) grad_norm: 3.2467 (3.1432) time: 0.6376 [2021-03-28 10:39:16 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 460/1251] eta: 0:08:24 lr: 0.000048 loss: 2.8439 (2.7132) grad_norm: 3.0833 (3.1402) time: 0.6370 [2021-03-28 10:39:23 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 470/1251] eta: 0:08:18 lr: 0.000048 loss: 2.6697 (2.7078) grad_norm: 2.9339 (3.1373) time: 0.6311 [2021-03-28 10:39:29 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 480/1251] eta: 0:08:11 lr: 0.000048 loss: 2.6173 (2.7074) grad_norm: 2.7552 (3.1312) time: 0.6239 [2021-03-28 10:39:35 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 490/1251] eta: 0:08:05 lr: 0.000048 loss: 2.7807 (2.7091) grad_norm: 2.8389 (3.1424) time: 0.6227 [2021-03-28 10:39:41 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 500/1251] eta: 0:07:58 lr: 0.000048 loss: 2.8079 (2.7105) grad_norm: 2.9038 (3.1379) time: 0.6276 [2021-03-28 10:39:48 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 510/1251] eta: 0:07:52 lr: 0.000048 loss: 2.8514 (2.7124) grad_norm: 2.8738 (3.1349) time: 0.6309 [2021-03-28 10:39:54 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 520/1251] eta: 0:07:45 lr: 0.000048 loss: 2.8076 (2.7125) grad_norm: 2.9859 (3.1359) time: 0.6271 [2021-03-28 10:40:00 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 530/1251] eta: 0:07:39 lr: 0.000048 loss: 2.9176 (2.7140) grad_norm: 3.0689 (3.1346) time: 0.6231 [2021-03-28 10:40:07 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 540/1251] eta: 0:07:32 lr: 0.000048 loss: 2.8032 (2.7122) grad_norm: 3.0065 (3.1316) time: 0.6293 [2021-03-28 10:40:13 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 550/1251] eta: 0:07:26 lr: 0.000048 loss: 2.6530 (2.7094) grad_norm: 3.0282 (3.1297) time: 0.6474 [2021-03-28 10:40:20 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 560/1251] eta: 0:07:20 lr: 0.000048 loss: 2.5622 (2.7078) grad_norm: 3.0468 (3.1310) time: 0.6442 [2021-03-28 10:40:26 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 570/1251] eta: 0:07:13 lr: 0.000048 loss: 2.7882 (2.7108) grad_norm: 2.9653 (3.1292) time: 0.6316 [2021-03-28 10:40:32 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 580/1251] eta: 0:07:07 lr: 0.000048 loss: 2.9368 (2.7130) grad_norm: 2.9653 (3.1276) time: 0.6280 [2021-03-28 10:40:38 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 590/1251] eta: 0:07:00 lr: 0.000048 loss: 2.9541 (2.7128) grad_norm: 3.0515 (3.1367) time: 0.6283 [2021-03-28 10:40:45 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 600/1251] eta: 0:06:54 lr: 0.000048 loss: 2.8418 (2.7163) grad_norm: 2.9957 (3.1331) time: 0.6372 [2021-03-28 10:40:51 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 610/1251] eta: 0:06:48 lr: 0.000048 loss: 2.8430 (2.7201) grad_norm: 2.9957 (3.1448) time: 0.6379 [2021-03-28 10:40:57 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 620/1251] eta: 0:06:41 lr: 0.000048 loss: 2.8430 (2.7218) grad_norm: 3.2165 (3.1453) time: 0.6291 [2021-03-28 10:41:04 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 630/1251] eta: 0:06:35 lr: 0.000048 loss: 2.8307 (2.7214) grad_norm: 2.8463 (3.1406) time: 0.6255 [2021-03-28 10:41:10 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 640/1251] eta: 0:06:28 lr: 0.000048 loss: 2.7304 (2.7196) grad_norm: 2.8480 (3.1375) time: 0.6296 [2021-03-28 10:41:16 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 650/1251] eta: 0:06:22 lr: 0.000048 loss: 2.4852 (2.7138) grad_norm: 2.8891 (3.1368) time: 0.6332 [2021-03-28 10:41:23 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 660/1251] eta: 0:06:15 lr: 0.000048 loss: 2.4910 (2.7131) grad_norm: 3.0434 (3.1481) time: 0.6284 [2021-03-28 10:41:29 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 670/1251] eta: 0:06:09 lr: 0.000048 loss: 2.7531 (2.7145) grad_norm: 3.1932 (3.1499) time: 0.6229 [2021-03-28 10:41:35 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 680/1251] eta: 0:06:03 lr: 0.000048 loss: 2.7531 (2.7156) grad_norm: 2.9457 (3.1461) time: 0.6278 [2021-03-28 10:41:41 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 690/1251] eta: 0:05:56 lr: 0.000048 loss: 2.7176 (2.7161) grad_norm: 2.8969 (3.1438) time: 0.6321 [2021-03-28 10:41:48 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 700/1251] eta: 0:05:50 lr: 0.000048 loss: 2.6328 (2.7127) grad_norm: 2.9923 (3.1431) time: 0.6257 [2021-03-28 10:41:54 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 710/1251] eta: 0:05:43 lr: 0.000048 loss: 2.4582 (2.7117) grad_norm: 2.9623 (3.1449) time: 0.6239 [2021-03-28 10:42:00 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 720/1251] eta: 0:05:37 lr: 0.000048 loss: 2.7395 (2.7095) grad_norm: 3.0555 (3.1711) time: 0.6264 [2021-03-28 10:42:07 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 730/1251] eta: 0:05:30 lr: 0.000048 loss: 2.8924 (2.7112) grad_norm: 3.1142 (3.1743) time: 0.6283 [2021-03-28 10:42:13 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 740/1251] eta: 0:05:24 lr: 0.000047 loss: 2.8358 (2.7093) grad_norm: 3.1405 (3.1764) time: 0.6384 [2021-03-28 10:42:19 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 750/1251] eta: 0:05:18 lr: 0.000047 loss: 2.6168 (2.7076) grad_norm: 2.8974 (3.1761) time: 0.6453 [2021-03-28 10:42:26 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 760/1251] eta: 0:05:11 lr: 0.000047 loss: 2.7427 (2.7099) grad_norm: 2.8964 (3.1756) time: 0.6367 [2021-03-28 10:42:32 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 770/1251] eta: 0:05:05 lr: 0.000047 loss: 2.8460 (2.7099) grad_norm: 2.8323 (3.1718) time: 0.6259 [2021-03-28 10:42:38 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 780/1251] eta: 0:04:59 lr: 0.000047 loss: 2.7294 (2.7113) grad_norm: 2.7914 (3.2018) time: 0.6286 [2021-03-28 10:42:45 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 790/1251] eta: 0:04:52 lr: 0.000047 loss: 2.7068 (2.7118) grad_norm: 2.8091 (3.1998) time: 0.6297 [2021-03-28 10:42:51 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 800/1251] eta: 0:04:46 lr: 0.000047 loss: 2.7068 (2.7131) grad_norm: 2.9508 (3.2006) time: 0.6280 [2021-03-28 10:42:57 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 810/1251] eta: 0:04:39 lr: 0.000047 loss: 2.7636 (2.7135) grad_norm: 3.1215 (3.1992) time: 0.6284 [2021-03-28 10:43:03 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 820/1251] eta: 0:04:33 lr: 0.000047 loss: 2.9387 (2.7159) grad_norm: 3.0238 (3.1976) time: 0.6285 [2021-03-28 10:43:10 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 830/1251] eta: 0:04:27 lr: 0.000047 loss: 2.9890 (2.7179) grad_norm: 3.0715 (3.1979) time: 0.6293 [2021-03-28 10:43:16 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 840/1251] eta: 0:04:20 lr: 0.000047 loss: 2.8662 (2.7156) grad_norm: 3.0300 (3.1995) time: 0.6276 [2021-03-28 10:43:22 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 850/1251] eta: 0:04:14 lr: 0.000047 loss: 2.9713 (2.7178) grad_norm: 3.0582 (3.2017) time: 0.6311 [2021-03-28 10:43:29 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 860/1251] eta: 0:04:08 lr: 0.000047 loss: 2.9793 (2.7183) grad_norm: 3.1482 (3.2001) time: 0.6292 [2021-03-28 10:43:35 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 870/1251] eta: 0:04:01 lr: 0.000047 loss: 2.8390 (2.7183) grad_norm: 2.9203 (3.1972) time: 0.6247 [2021-03-28 10:43:41 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 880/1251] eta: 0:03:55 lr: 0.000047 loss: 2.7585 (2.7183) grad_norm: 2.8048 (3.2000) time: 0.6299 [2021-03-28 10:43:47 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 890/1251] eta: 0:03:49 lr: 0.000047 loss: 2.8287 (2.7178) grad_norm: 3.1139 (3.2008) time: 0.6309 [2021-03-28 10:43:54 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 900/1251] eta: 0:03:42 lr: 0.000047 loss: 2.8598 (2.7196) grad_norm: 3.0897 (3.1999) time: 0.6289 [2021-03-28 10:44:00 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 910/1251] eta: 0:03:36 lr: 0.000047 loss: 2.8458 (2.7198) grad_norm: 2.9915 (3.2036) time: 0.6293 [2021-03-28 10:44:06 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 920/1251] eta: 0:03:29 lr: 0.000047 loss: 2.8256 (2.7219) grad_norm: 2.7962 (3.1983) time: 0.6275 [2021-03-28 10:44:13 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 930/1251] eta: 0:03:23 lr: 0.000047 loss: 2.8859 (2.7241) grad_norm: 2.8185 (3.1988) time: 0.6259 [2021-03-28 10:44:19 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 940/1251] eta: 0:03:17 lr: 0.000047 loss: 2.7846 (2.7230) grad_norm: 3.0087 (3.1985) time: 0.6288 [2021-03-28 10:44:25 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 950/1251] eta: 0:03:10 lr: 0.000047 loss: 2.8775 (2.7253) grad_norm: 3.1550 (3.1992) time: 0.6293 [2021-03-28 10:44:31 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 960/1251] eta: 0:03:04 lr: 0.000047 loss: 2.8856 (2.7269) grad_norm: 3.1545 (3.2013) time: 0.6265 [2021-03-28 10:44:38 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 970/1251] eta: 0:02:58 lr: 0.000047 loss: 2.6493 (2.7265) grad_norm: 2.9710 (3.2012) time: 0.6292 [2021-03-28 10:44:44 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 980/1251] eta: 0:02:51 lr: 0.000047 loss: 2.7137 (2.7277) grad_norm: 2.9710 (3.2040) time: 0.6290 [2021-03-28 10:44:50 swin_base_patch4_window7_224] INFO: Epoch: [262] [ 990/1251] eta: 0:02:45 lr: 0.000047 loss: 2.7049 (2.7254) grad_norm: 3.2088 (3.2044) time: 0.6292 [2021-03-28 10:44:57 swin_base_patch4_window7_224] INFO: Epoch: [262] [1000/1251] eta: 0:02:39 lr: 0.000047 loss: 2.7145 (2.7260) grad_norm: 3.2784 (3.2037) time: 0.6311 [2021-03-28 10:45:03 swin_base_patch4_window7_224] INFO: Epoch: [262] [1010/1251] eta: 0:02:32 lr: 0.000047 loss: 2.8717 (2.7282) grad_norm: 2.8304 (3.2008) time: 0.6336 [2021-03-28 10:45:09 swin_base_patch4_window7_224] INFO: Epoch: [262] [1020/1251] eta: 0:02:26 lr: 0.000047 loss: 3.0349 (2.7310) grad_norm: 2.8587 (3.2063) time: 0.6401 [2021-03-28 10:45:16 swin_base_patch4_window7_224] INFO: Epoch: [262] [1030/1251] eta: 0:02:20 lr: 0.000047 loss: 3.0349 (2.7317) grad_norm: 3.2421 (3.2064) time: 0.6393 [2021-03-28 10:45:22 swin_base_patch4_window7_224] INFO: Epoch: [262] [1040/1251] eta: 0:02:13 lr: 0.000047 loss: 2.9431 (2.7337) grad_norm: 2.9258 (3.2026) time: 0.6343 [2021-03-28 10:45:28 swin_base_patch4_window7_224] INFO: Epoch: [262] [1050/1251] eta: 0:02:07 lr: 0.000047 loss: 2.8973 (2.7326) grad_norm: 2.8536 (3.1999) time: 0.6299 [2021-03-28 10:45:35 swin_base_patch4_window7_224] INFO: Epoch: [262] [1060/1251] eta: 0:02:01 lr: 0.000047 loss: 2.6641 (2.7321) grad_norm: 2.7852 (3.1964) time: 0.6285 [2021-03-28 10:45:41 swin_base_patch4_window7_224] INFO: Epoch: [262] [1070/1251] eta: 0:01:54 lr: 0.000047 loss: 2.6842 (2.7304) grad_norm: 2.8764 (3.1948) time: 0.6350 [2021-03-28 10:45:47 swin_base_patch4_window7_224] INFO: Epoch: [262] [1080/1251] eta: 0:01:48 lr: 0.000047 loss: 2.5000 (2.7274) grad_norm: 3.0566 (3.1971) time: 0.6317 [2021-03-28 10:45:54 swin_base_patch4_window7_224] INFO: Epoch: [262] [1090/1251] eta: 0:01:42 lr: 0.000047 loss: 2.6189 (2.7265) grad_norm: 3.0526 (3.1969) time: 0.6256 [2021-03-28 10:46:00 swin_base_patch4_window7_224] INFO: Epoch: [262] [1100/1251] eta: 0:01:35 lr: 0.000047 loss: 2.7217 (2.7260) grad_norm: 2.9785 (3.1966) time: 0.6314 [2021-03-28 10:46:06 swin_base_patch4_window7_224] INFO: Epoch: [262] [1110/1251] eta: 0:01:29 lr: 0.000047 loss: 2.7467 (2.7255) grad_norm: 2.8183 (3.1923) time: 0.6356 [2021-03-28 10:46:13 swin_base_patch4_window7_224] INFO: Epoch: [262] [1120/1251] eta: 0:01:23 lr: 0.000047 loss: 2.9281 (2.7269) grad_norm: 2.8233 (3.1935) time: 0.6388 [2021-03-28 10:46:19 swin_base_patch4_window7_224] INFO: Epoch: [262] [1130/1251] eta: 0:01:16 lr: 0.000047 loss: 2.9468 (2.7274) grad_norm: 2.8851 (3.1921) time: 0.6347 [2021-03-28 10:46:25 swin_base_patch4_window7_224] INFO: Epoch: [262] [1140/1251] eta: 0:01:10 lr: 0.000047 loss: 2.8394 (2.7276) grad_norm: 2.8717 (3.1929) time: 0.6297 [2021-03-28 10:46:32 swin_base_patch4_window7_224] INFO: Epoch: [262] [1150/1251] eta: 0:01:03 lr: 0.000047 loss: 2.8249 (2.7271) grad_norm: 3.2169 (3.1944) time: 0.6274 [2021-03-28 10:46:38 swin_base_patch4_window7_224] INFO: Epoch: [262] [1160/1251] eta: 0:00:57 lr: 0.000047 loss: 2.7790 (2.7273) grad_norm: 3.0028 (3.1926) time: 0.6281 [2021-03-28 10:46:44 swin_base_patch4_window7_224] INFO: Epoch: [262] [1170/1251] eta: 0:00:51 lr: 0.000047 loss: 2.7790 (2.7268) grad_norm: 2.8675 (3.1916) time: 0.6257 [2021-03-28 10:46:50 swin_base_patch4_window7_224] INFO: Epoch: [262] [1180/1251] eta: 0:00:44 lr: 0.000047 loss: 2.7834 (2.7266) grad_norm: 2.9593 (3.1924) time: 0.6275 [2021-03-28 10:46:57 swin_base_patch4_window7_224] INFO: Epoch: [262] [1190/1251] eta: 0:00:38 lr: 0.000047 loss: 2.8131 (2.7265) grad_norm: 2.8158 (3.1892) time: 0.6297 [2021-03-28 10:47:03 swin_base_patch4_window7_224] INFO: Epoch: [262] [1200/1251] eta: 0:00:32 lr: 0.000047 loss: 2.8131 (2.7262) grad_norm: 2.8651 (3.1883) time: 0.6279 [2021-03-28 10:47:09 swin_base_patch4_window7_224] INFO: Epoch: [262] [1210/1251] eta: 0:00:25 lr: 0.000047 loss: 2.6908 (2.7255) grad_norm: 2.8669 (3.1898) time: 0.6311 [2021-03-28 10:47:16 swin_base_patch4_window7_224] INFO: Epoch: [262] [1220/1251] eta: 0:00:19 lr: 0.000047 loss: 2.6623 (2.7246) grad_norm: 2.8251 (3.1877) time: 0.6256 [2021-03-28 10:47:22 swin_base_patch4_window7_224] INFO: Epoch: [262] [1230/1251] eta: 0:00:13 lr: 0.000047 loss: 2.6832 (2.7255) grad_norm: 2.9344 (3.1877) time: 0.6225 [2021-03-28 10:47:28 swin_base_patch4_window7_224] INFO: Epoch: [262] [1240/1251] eta: 0:00:06 lr: 0.000047 loss: 2.7870 (2.7260) grad_norm: 3.0081 (3.1882) time: 0.6270 [2021-03-28 10:47:34 swin_base_patch4_window7_224] INFO: Epoch: [262] [1250/1251] eta: 0:00:00 lr: 0.000047 loss: 2.7870 (2.7256) grad_norm: 2.9340 (3.1856) time: 0.6270 [2021-03-28 10:47:46 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:38 loss: 0.8681 (0.8681) acc1: 81.2500 (81.2500) acc5: 93.7500 (93.7500) [2021-03-28 10:47:50 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7459 (0.7221) acc1: 81.2500 (81.8182) acc5: 95.3125 (96.0227) [2021-03-28 10:47:52 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7296 (0.7401) acc1: 81.2500 (81.4732) acc5: 96.8750 (96.8750) [2021-03-28 10:47:54 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7198 (0.7370) acc1: 82.8125 (81.9052) acc5: 96.8750 (96.5222) [2021-03-28 10:47:56 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7489 (0.7553) acc1: 82.8125 (81.7454) acc5: 95.3125 (96.3415) [2021-03-28 10:47:57 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7489 (0.7532) acc1: 82.8125 (82.0160) acc5: 96.8750 (96.2560) [2021-03-28 10:48:09 swin_base_patch4_window7_224] INFO: * Acc@1 83.136 Acc@5 96.344 loss 0.742 [2021-03-28 10:48:09 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-28 10:48:09 swin_base_patch4_window7_224] INFO: Max accuracy: 83.15% [2021-03-28 10:48:14 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 0/1251] eta: 1:31:48 lr: 0.000047 loss: 3.0186 (3.0186) grad_norm: 2.7243 (2.7243) time: 4.4032 [2021-03-28 10:48:20 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 10/1251] eta: 0:20:22 lr: 0.000047 loss: 2.8783 (2.6041) grad_norm: 2.7405 (2.9635) time: 0.9851 [2021-03-28 10:48:27 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 20/1251] eta: 0:16:44 lr: 0.000047 loss: 2.8806 (2.7427) grad_norm: 2.8848 (2.9514) time: 0.6369 [2021-03-28 10:48:33 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 30/1251] eta: 0:15:24 lr: 0.000047 loss: 3.0195 (2.7586) grad_norm: 2.8937 (3.0142) time: 0.6314 [2021-03-28 10:48:39 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 40/1251] eta: 0:14:37 lr: 0.000047 loss: 2.9117 (2.7785) grad_norm: 3.0052 (3.0698) time: 0.6281 [2021-03-28 10:48:46 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 50/1251] eta: 0:14:10 lr: 0.000047 loss: 2.8697 (2.7669) grad_norm: 3.0542 (3.0450) time: 0.6328 [2021-03-28 10:48:52 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 60/1251] eta: 0:13:47 lr: 0.000047 loss: 2.7675 (2.7424) grad_norm: 2.7985 (3.0045) time: 0.6331 [2021-03-28 10:48:58 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 70/1251] eta: 0:13:29 lr: 0.000047 loss: 2.7200 (2.7193) grad_norm: 2.7882 (3.0219) time: 0.6273 [2021-03-28 10:49:04 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 80/1251] eta: 0:13:15 lr: 0.000047 loss: 2.7654 (2.7259) grad_norm: 2.9523 (3.0434) time: 0.6347 [2021-03-28 10:49:11 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 90/1251] eta: 0:13:01 lr: 0.000047 loss: 2.9001 (2.7130) grad_norm: 3.3022 (3.1433) time: 0.6286 [2021-03-28 10:49:17 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 100/1251] eta: 0:12:48 lr: 0.000047 loss: 2.8099 (2.7195) grad_norm: 3.0559 (3.1425) time: 0.6200 [2021-03-28 10:49:23 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 110/1251] eta: 0:12:37 lr: 0.000047 loss: 2.8099 (2.7255) grad_norm: 3.0757 (3.1598) time: 0.6245 [2021-03-28 10:49:29 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 120/1251] eta: 0:12:27 lr: 0.000047 loss: 2.6204 (2.7204) grad_norm: 3.0025 (3.1686) time: 0.6264 [2021-03-28 10:49:36 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 130/1251] eta: 0:12:18 lr: 0.000046 loss: 2.6150 (2.7124) grad_norm: 2.9688 (3.1595) time: 0.6275 [2021-03-28 10:49:42 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 140/1251] eta: 0:12:09 lr: 0.000046 loss: 2.7244 (2.7063) grad_norm: 3.0268 (3.1515) time: 0.6310 [2021-03-28 10:49:48 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 150/1251] eta: 0:12:00 lr: 0.000046 loss: 2.6371 (2.6964) grad_norm: 3.0607 (3.1568) time: 0.6290 [2021-03-28 10:49:55 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 160/1251] eta: 0:11:52 lr: 0.000046 loss: 2.6298 (2.6961) grad_norm: 3.0460 (3.1600) time: 0.6261 [2021-03-28 10:50:01 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 170/1251] eta: 0:11:44 lr: 0.000046 loss: 2.8183 (2.7002) grad_norm: 3.0283 (3.1474) time: 0.6291 [2021-03-28 10:50:07 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 180/1251] eta: 0:11:36 lr: 0.000046 loss: 2.7351 (2.6941) grad_norm: 2.9400 (3.1374) time: 0.6302 [2021-03-28 10:50:13 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 190/1251] eta: 0:11:28 lr: 0.000046 loss: 2.7190 (2.6955) grad_norm: 2.9605 (3.1351) time: 0.6267 [2021-03-28 10:50:20 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 200/1251] eta: 0:11:21 lr: 0.000046 loss: 2.8858 (2.7038) grad_norm: 2.9634 (3.1306) time: 0.6255 [2021-03-28 10:50:26 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 210/1251] eta: 0:11:13 lr: 0.000046 loss: 2.7342 (2.7029) grad_norm: 2.8125 (3.1255) time: 0.6306 [2021-03-28 10:50:32 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 220/1251] eta: 0:11:06 lr: 0.000046 loss: 2.8334 (2.7078) grad_norm: 2.8520 (3.1163) time: 0.6331 [2021-03-28 10:50:39 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 230/1251] eta: 0:10:59 lr: 0.000046 loss: 2.8923 (2.7070) grad_norm: 3.2315 (3.1636) time: 0.6312 [2021-03-28 10:50:45 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 240/1251] eta: 0:10:52 lr: 0.000046 loss: 2.8707 (2.7046) grad_norm: 3.2396 (3.1584) time: 0.6303 [2021-03-28 10:50:51 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 250/1251] eta: 0:10:45 lr: 0.000046 loss: 2.7410 (2.6997) grad_norm: 2.7722 (3.1450) time: 0.6277 [2021-03-28 10:50:57 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 260/1251] eta: 0:10:37 lr: 0.000046 loss: 2.7410 (2.6918) grad_norm: 2.7798 (3.1342) time: 0.6231 [2021-03-28 10:51:04 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 270/1251] eta: 0:10:30 lr: 0.000046 loss: 2.7302 (2.6895) grad_norm: 2.9504 (3.1307) time: 0.6259 [2021-03-28 10:51:10 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 280/1251] eta: 0:10:23 lr: 0.000046 loss: 2.8688 (2.6989) grad_norm: 3.0021 (3.1388) time: 0.6264 [2021-03-28 10:51:16 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 290/1251] eta: 0:10:16 lr: 0.000046 loss: 2.9763 (2.7021) grad_norm: 2.9466 (3.1423) time: 0.6268 [2021-03-28 10:51:23 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 300/1251] eta: 0:10:10 lr: 0.000046 loss: 2.7579 (2.7015) grad_norm: 2.8430 (3.1339) time: 0.6324 [2021-03-28 10:51:29 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 310/1251] eta: 0:10:03 lr: 0.000046 loss: 2.6581 (2.7024) grad_norm: 2.9506 (3.1314) time: 0.6295 [2021-03-28 10:51:35 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 320/1251] eta: 0:09:56 lr: 0.000046 loss: 2.9884 (2.7048) grad_norm: 3.0520 (3.1329) time: 0.6312 [2021-03-28 10:51:41 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 330/1251] eta: 0:09:49 lr: 0.000046 loss: 2.9904 (2.7076) grad_norm: 2.9829 (3.1283) time: 0.6307 [2021-03-28 10:51:48 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 340/1251] eta: 0:09:43 lr: 0.000046 loss: 2.8862 (2.7119) grad_norm: 2.9129 (3.1239) time: 0.6290 [2021-03-28 10:51:54 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 350/1251] eta: 0:09:36 lr: 0.000046 loss: 2.7868 (2.7130) grad_norm: 2.9129 (3.1349) time: 0.6313 [2021-03-28 10:52:01 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 360/1251] eta: 0:09:30 lr: 0.000046 loss: 2.7633 (2.7141) grad_norm: 3.0878 (3.1504) time: 0.6342 [2021-03-28 10:52:07 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 370/1251] eta: 0:09:23 lr: 0.000046 loss: 2.6983 (2.7142) grad_norm: 2.9914 (3.1475) time: 0.6307 [2021-03-28 10:52:13 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 380/1251] eta: 0:09:16 lr: 0.000046 loss: 2.5391 (2.7095) grad_norm: 2.6970 (3.1332) time: 0.6285 [2021-03-28 10:52:19 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 390/1251] eta: 0:09:10 lr: 0.000046 loss: 2.6305 (2.7087) grad_norm: 2.7907 (3.1376) time: 0.6314 [2021-03-28 10:52:26 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 400/1251] eta: 0:09:03 lr: 0.000046 loss: 2.8034 (2.7119) grad_norm: 2.9506 (3.1363) time: 0.6297 [2021-03-28 10:52:32 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 410/1251] eta: 0:08:57 lr: 0.000046 loss: 2.7867 (2.7078) grad_norm: 2.9889 (3.1337) time: 0.6294 [2021-03-28 10:52:38 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 420/1251] eta: 0:08:50 lr: 0.000046 loss: 2.5050 (2.7034) grad_norm: 2.9714 (3.1290) time: 0.6264 [2021-03-28 10:52:44 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 430/1251] eta: 0:08:43 lr: 0.000046 loss: 2.8005 (2.7064) grad_norm: 2.9329 (3.1241) time: 0.6245 [2021-03-28 10:52:51 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 440/1251] eta: 0:08:37 lr: 0.000046 loss: 2.8806 (2.7073) grad_norm: 2.8519 (3.1262) time: 0.6248 [2021-03-28 10:52:57 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 450/1251] eta: 0:08:30 lr: 0.000046 loss: 2.7943 (2.7053) grad_norm: 2.8124 (3.1221) time: 0.6246 [2021-03-28 10:53:03 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 460/1251] eta: 0:08:23 lr: 0.000046 loss: 2.6988 (2.7011) grad_norm: 2.7864 (3.1156) time: 0.6233 [2021-03-28 10:53:09 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 470/1251] eta: 0:08:17 lr: 0.000046 loss: 2.6988 (2.7017) grad_norm: 2.9179 (3.1209) time: 0.6265 [2021-03-28 10:53:16 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 480/1251] eta: 0:08:10 lr: 0.000046 loss: 2.7667 (2.7024) grad_norm: 3.1710 (3.1263) time: 0.6257 [2021-03-28 10:53:22 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 490/1251] eta: 0:08:04 lr: 0.000046 loss: 2.8019 (2.7071) grad_norm: 3.2558 (3.1330) time: 0.6200 [2021-03-28 10:53:28 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 500/1251] eta: 0:07:57 lr: 0.000046 loss: 2.8324 (2.7061) grad_norm: 3.2591 (3.1420) time: 0.6239 [2021-03-28 10:53:35 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 510/1251] eta: 0:07:51 lr: 0.000046 loss: 2.8395 (2.7094) grad_norm: 3.2116 (3.1415) time: 0.6332 [2021-03-28 10:53:41 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 520/1251] eta: 0:07:44 lr: 0.000046 loss: 2.8955 (2.7076) grad_norm: 3.0739 (3.1426) time: 0.6309 [2021-03-28 10:53:47 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 530/1251] eta: 0:07:38 lr: 0.000046 loss: 2.7140 (2.7055) grad_norm: 2.8305 (3.1365) time: 0.6262 [2021-03-28 10:53:53 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 540/1251] eta: 0:07:31 lr: 0.000046 loss: 2.7321 (2.7030) grad_norm: 2.9399 (3.1460) time: 0.6266 [2021-03-28 10:54:00 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 550/1251] eta: 0:07:25 lr: 0.000046 loss: 2.7195 (2.7007) grad_norm: 2.9607 (3.1445) time: 0.6424 [2021-03-28 10:54:06 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 560/1251] eta: 0:07:19 lr: 0.000046 loss: 2.7951 (2.7030) grad_norm: 3.1245 (3.1470) time: 0.6471 [2021-03-28 10:54:13 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 570/1251] eta: 0:07:13 lr: 0.000046 loss: 2.8920 (2.7060) grad_norm: 3.0546 (3.1432) time: 0.6383 [2021-03-28 10:54:19 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 580/1251] eta: 0:07:06 lr: 0.000046 loss: 2.8523 (2.7052) grad_norm: 2.9291 (3.1406) time: 0.6415 [2021-03-28 10:54:25 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 590/1251] eta: 0:07:00 lr: 0.000046 loss: 2.8476 (2.7077) grad_norm: 3.0319 (3.1390) time: 0.6328 [2021-03-28 10:54:32 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 600/1251] eta: 0:06:53 lr: 0.000046 loss: 2.7310 (2.7031) grad_norm: 3.0368 (3.1427) time: 0.6272 [2021-03-28 10:54:38 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 610/1251] eta: 0:06:47 lr: 0.000046 loss: 2.7310 (2.7031) grad_norm: 2.9834 (3.1399) time: 0.6292 [2021-03-28 10:54:44 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 620/1251] eta: 0:06:41 lr: 0.000046 loss: 2.9063 (2.7046) grad_norm: 2.9834 (3.1373) time: 0.6299 [2021-03-28 10:54:51 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 630/1251] eta: 0:06:34 lr: 0.000046 loss: 2.6867 (2.7021) grad_norm: 3.0584 (3.1404) time: 0.6305 [2021-03-28 10:54:57 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 640/1251] eta: 0:06:28 lr: 0.000046 loss: 2.6867 (2.7016) grad_norm: 2.8917 (3.1382) time: 0.6329 [2021-03-28 10:55:03 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 650/1251] eta: 0:06:21 lr: 0.000046 loss: 2.9154 (2.7063) grad_norm: 2.9427 (3.1424) time: 0.6316 [2021-03-28 10:55:10 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 660/1251] eta: 0:06:15 lr: 0.000046 loss: 2.9088 (2.7057) grad_norm: 3.0772 (3.1542) time: 0.6339 [2021-03-28 10:55:16 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 670/1251] eta: 0:06:09 lr: 0.000046 loss: 2.8636 (2.7093) grad_norm: 3.0956 (3.1665) time: 0.6341 [2021-03-28 10:55:22 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 680/1251] eta: 0:06:02 lr: 0.000046 loss: 3.0268 (2.7126) grad_norm: 2.9254 (3.1652) time: 0.6387 [2021-03-28 10:55:29 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 690/1251] eta: 0:05:56 lr: 0.000046 loss: 3.0166 (2.7141) grad_norm: 2.8917 (3.1649) time: 0.6478 [2021-03-28 10:55:35 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 700/1251] eta: 0:05:50 lr: 0.000046 loss: 2.8333 (2.7144) grad_norm: 2.8706 (3.1606) time: 0.6362 [2021-03-28 10:55:41 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 710/1251] eta: 0:05:43 lr: 0.000046 loss: 2.6508 (2.7129) grad_norm: 2.8706 (3.1577) time: 0.6297 [2021-03-28 10:55:48 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 720/1251] eta: 0:05:37 lr: 0.000046 loss: 2.5957 (2.7105) grad_norm: 2.9090 (3.1555) time: 0.6292 [2021-03-28 10:55:54 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 730/1251] eta: 0:05:31 lr: 0.000046 loss: 2.7459 (2.7129) grad_norm: 3.0997 (3.1545) time: 0.6296 [2021-03-28 10:56:00 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 740/1251] eta: 0:05:24 lr: 0.000046 loss: 2.8544 (2.7145) grad_norm: 3.3048 (3.1620) time: 0.6376 [2021-03-28 10:56:07 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 750/1251] eta: 0:05:18 lr: 0.000046 loss: 2.8389 (2.7164) grad_norm: 3.2224 (3.1592) time: 0.6438 [2021-03-28 10:56:13 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 760/1251] eta: 0:05:12 lr: 0.000046 loss: 2.8290 (2.7157) grad_norm: 2.8994 (3.1577) time: 0.6464 [2021-03-28 10:56:20 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 770/1251] eta: 0:05:05 lr: 0.000045 loss: 2.8290 (2.7162) grad_norm: 2.9735 (3.1568) time: 0.6367 [2021-03-28 10:56:26 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 780/1251] eta: 0:04:59 lr: 0.000045 loss: 2.7979 (2.7171) grad_norm: 2.9449 (3.1551) time: 0.6282 [2021-03-28 10:56:32 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 790/1251] eta: 0:04:52 lr: 0.000045 loss: 2.7632 (2.7156) grad_norm: 3.0252 (3.1547) time: 0.6267 [2021-03-28 10:56:39 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 800/1251] eta: 0:04:46 lr: 0.000045 loss: 2.6650 (2.7153) grad_norm: 3.0535 (3.1528) time: 0.6276 [2021-03-28 10:56:45 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 810/1251] eta: 0:04:40 lr: 0.000045 loss: 2.6650 (2.7158) grad_norm: 3.1444 (3.1560) time: 0.6279 [2021-03-28 10:56:51 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 820/1251] eta: 0:04:33 lr: 0.000045 loss: 2.6367 (2.7125) grad_norm: 3.1107 (3.1583) time: 0.6263 [2021-03-28 10:56:57 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 830/1251] eta: 0:04:27 lr: 0.000045 loss: 2.4222 (2.7090) grad_norm: 2.9847 (3.1629) time: 0.6308 [2021-03-28 10:57:04 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 840/1251] eta: 0:04:21 lr: 0.000045 loss: 2.8654 (2.7095) grad_norm: 3.1083 (3.1635) time: 0.6307 [2021-03-28 10:57:10 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 850/1251] eta: 0:04:14 lr: 0.000045 loss: 2.8347 (2.7080) grad_norm: 3.0945 (3.1696) time: 0.6309 [2021-03-28 10:57:16 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 860/1251] eta: 0:04:08 lr: 0.000045 loss: 2.8347 (2.7084) grad_norm: 2.9923 (3.1673) time: 0.6292 [2021-03-28 10:57:23 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 870/1251] eta: 0:04:01 lr: 0.000045 loss: 2.7729 (2.7091) grad_norm: 3.0390 (3.1708) time: 0.6254 [2021-03-28 10:57:29 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 880/1251] eta: 0:03:55 lr: 0.000045 loss: 2.7729 (2.7101) grad_norm: 3.0449 (3.1714) time: 0.6318 [2021-03-28 10:57:35 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 890/1251] eta: 0:03:49 lr: 0.000045 loss: 2.7181 (2.7081) grad_norm: 3.0408 (3.1730) time: 0.6334 [2021-03-28 10:57:42 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 900/1251] eta: 0:03:42 lr: 0.000045 loss: 2.7718 (2.7083) grad_norm: 3.2837 (3.1747) time: 0.6363 [2021-03-28 10:57:48 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 910/1251] eta: 0:03:36 lr: 0.000045 loss: 2.8587 (2.7069) grad_norm: 3.2947 (3.1762) time: 0.6373 [2021-03-28 10:57:54 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 920/1251] eta: 0:03:30 lr: 0.000045 loss: 2.8289 (2.7073) grad_norm: 3.0680 (3.1779) time: 0.6264 [2021-03-28 10:58:00 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 930/1251] eta: 0:03:23 lr: 0.000045 loss: 2.8316 (2.7086) grad_norm: 3.1579 (3.1786) time: 0.6245 [2021-03-28 10:58:07 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 940/1251] eta: 0:03:17 lr: 0.000045 loss: 2.8548 (2.7089) grad_norm: 3.2212 (3.1826) time: 0.6270 [2021-03-28 10:58:13 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 950/1251] eta: 0:03:11 lr: 0.000045 loss: 2.8638 (2.7105) grad_norm: 3.2400 (3.1844) time: 0.6316 [2021-03-28 10:58:19 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 960/1251] eta: 0:03:04 lr: 0.000045 loss: 2.8511 (2.7118) grad_norm: 3.3501 (3.1925) time: 0.6295 [2021-03-28 10:58:26 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 970/1251] eta: 0:02:58 lr: 0.000045 loss: 2.7380 (2.7105) grad_norm: 3.1011 (3.1907) time: 0.6248 [2021-03-28 10:58:32 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 980/1251] eta: 0:02:51 lr: 0.000045 loss: 2.7050 (2.7105) grad_norm: 2.8723 (3.1884) time: 0.6338 [2021-03-28 10:58:38 swin_base_patch4_window7_224] INFO: Epoch: [263] [ 990/1251] eta: 0:02:45 lr: 0.000045 loss: 2.7066 (2.7113) grad_norm: 2.8871 (3.1923) time: 0.6354 [2021-03-28 10:58:45 swin_base_patch4_window7_224] INFO: Epoch: [263] [1000/1251] eta: 0:02:39 lr: 0.000045 loss: 2.9576 (2.7119) grad_norm: 2.9093 (3.1914) time: 0.6276 [2021-03-28 10:58:51 swin_base_patch4_window7_224] INFO: Epoch: [263] [1010/1251] eta: 0:02:32 lr: 0.000045 loss: 2.7774 (2.7106) grad_norm: 2.7859 (3.1906) time: 0.6302 [2021-03-28 10:58:57 swin_base_patch4_window7_224] INFO: Epoch: [263] [1020/1251] eta: 0:02:26 lr: 0.000045 loss: 2.6755 (2.7107) grad_norm: 2.8329 (3.1904) time: 0.6284 [2021-03-28 10:59:03 swin_base_patch4_window7_224] INFO: Epoch: [263] [1030/1251] eta: 0:02:20 lr: 0.000045 loss: 2.7398 (2.7108) grad_norm: 3.0320 (3.1903) time: 0.6247 [2021-03-28 10:59:10 swin_base_patch4_window7_224] INFO: Epoch: [263] [1040/1251] eta: 0:02:13 lr: 0.000045 loss: 2.7992 (2.7119) grad_norm: 3.0320 (3.1972) time: 0.6260 [2021-03-28 10:59:16 swin_base_patch4_window7_224] INFO: Epoch: [263] [1050/1251] eta: 0:02:07 lr: 0.000045 loss: 2.3696 (2.7082) grad_norm: 2.9142 (3.1977) time: 0.6279 [2021-03-28 10:59:22 swin_base_patch4_window7_224] INFO: Epoch: [263] [1060/1251] eta: 0:02:01 lr: 0.000045 loss: 2.6408 (2.7077) grad_norm: 2.8950 (3.1965) time: 0.6303 [2021-03-28 10:59:29 swin_base_patch4_window7_224] INFO: Epoch: [263] [1070/1251] eta: 0:01:54 lr: 0.000045 loss: 2.6635 (2.7080) grad_norm: 3.1098 (3.1974) time: 0.6298 [2021-03-28 10:59:35 swin_base_patch4_window7_224] INFO: Epoch: [263] [1080/1251] eta: 0:01:48 lr: 0.000045 loss: 2.9527 (2.7107) grad_norm: 3.1649 (3.1985) time: 0.6321 [2021-03-28 10:59:41 swin_base_patch4_window7_224] INFO: Epoch: [263] [1090/1251] eta: 0:01:42 lr: 0.000045 loss: 2.9572 (2.7100) grad_norm: 2.8189 (3.1978) time: 0.6281 [2021-03-28 10:59:47 swin_base_patch4_window7_224] INFO: Epoch: [263] [1100/1251] eta: 0:01:35 lr: 0.000045 loss: 2.8822 (2.7111) grad_norm: 3.2050 (3.2012) time: 0.6268 [2021-03-28 10:59:54 swin_base_patch4_window7_224] INFO: Epoch: [263] [1110/1251] eta: 0:01:29 lr: 0.000045 loss: 2.7031 (2.7101) grad_norm: 3.2302 (3.2011) time: 0.6300 [2021-03-28 11:00:00 swin_base_patch4_window7_224] INFO: Epoch: [263] [1120/1251] eta: 0:01:23 lr: 0.000045 loss: 2.6492 (2.7095) grad_norm: 2.9769 (3.2016) time: 0.6264 [2021-03-28 11:00:06 swin_base_patch4_window7_224] INFO: Epoch: [263] [1130/1251] eta: 0:01:16 lr: 0.000045 loss: 2.6492 (2.7081) grad_norm: 3.0896 (3.2015) time: 0.6284 [2021-03-28 11:00:13 swin_base_patch4_window7_224] INFO: Epoch: [263] [1140/1251] eta: 0:01:10 lr: 0.000045 loss: 2.6685 (2.7073) grad_norm: 3.1564 (3.2024) time: 0.6321 [2021-03-28 11:00:19 swin_base_patch4_window7_224] INFO: Epoch: [263] [1150/1251] eta: 0:01:03 lr: 0.000045 loss: 2.4734 (2.7046) grad_norm: 3.2792 (3.2032) time: 0.6307 [2021-03-28 11:00:25 swin_base_patch4_window7_224] INFO: Epoch: [263] [1160/1251] eta: 0:00:57 lr: 0.000045 loss: 2.5694 (2.7039) grad_norm: 2.9735 (3.1996) time: 0.6270 [2021-03-28 11:00:31 swin_base_patch4_window7_224] INFO: Epoch: [263] [1170/1251] eta: 0:00:51 lr: 0.000045 loss: 2.6678 (2.7032) grad_norm: 2.8047 (3.2014) time: 0.6266 [2021-03-28 11:00:38 swin_base_patch4_window7_224] INFO: Epoch: [263] [1180/1251] eta: 0:00:44 lr: 0.000045 loss: 2.8778 (2.7051) grad_norm: 2.9967 (3.2061) time: 0.6295 [2021-03-28 11:00:44 swin_base_patch4_window7_224] INFO: Epoch: [263] [1190/1251] eta: 0:00:38 lr: 0.000045 loss: 2.9494 (2.7052) grad_norm: 2.8821 (3.2107) time: 0.6297 [2021-03-28 11:00:50 swin_base_patch4_window7_224] INFO: Epoch: [263] [1200/1251] eta: 0:00:32 lr: 0.000045 loss: 2.9010 (2.7061) grad_norm: 2.8821 (3.2096) time: 0.6261 [2021-03-28 11:00:57 swin_base_patch4_window7_224] INFO: Epoch: [263] [1210/1251] eta: 0:00:25 lr: 0.000045 loss: 2.8438 (2.7059) grad_norm: 2.9892 (3.2102) time: 0.6246 [2021-03-28 11:01:03 swin_base_patch4_window7_224] INFO: Epoch: [263] [1220/1251] eta: 0:00:19 lr: 0.000045 loss: 2.6648 (2.7042) grad_norm: 2.9599 (3.2094) time: 0.6275 [2021-03-28 11:01:09 swin_base_patch4_window7_224] INFO: Epoch: [263] [1230/1251] eta: 0:00:13 lr: 0.000045 loss: 2.8343 (2.7049) grad_norm: 3.0257 (3.2083) time: 0.6273 [2021-03-28 11:01:15 swin_base_patch4_window7_224] INFO: Epoch: [263] [1240/1251] eta: 0:00:06 lr: 0.000045 loss: 2.8796 (2.7076) grad_norm: 3.1666 (3.2112) time: 0.6231 [2021-03-28 11:01:21 swin_base_patch4_window7_224] INFO: Epoch: [263] [1250/1251] eta: 0:00:00 lr: 0.000045 loss: 2.9506 (2.7085) grad_norm: 3.1803 (3.2099) time: 0.6157 [2021-03-28 11:01:32 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:49 loss: 0.9473 (0.9473) acc1: 73.4375 (73.4375) acc5: 96.8750 (96.8750) [2021-03-28 11:01:34 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:13 loss: 0.7006 (0.7234) acc1: 84.3750 (82.8125) acc5: 96.8750 (96.5909) [2021-03-28 11:01:37 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7457 (0.7710) acc1: 82.8125 (82.0685) acc5: 95.3125 (96.1310) [2021-03-28 11:01:39 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8083 (0.7975) acc1: 81.2500 (81.3508) acc5: 95.3125 (95.8669) [2021-03-28 11:01:41 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7387 (0.7667) acc1: 81.2500 (81.9360) acc5: 96.8750 (96.1890) [2021-03-28 11:01:42 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7387 (0.7538) acc1: 82.8125 (82.3360) acc5: 96.8750 (96.3520) [2021-03-28 11:01:57 swin_base_patch4_window7_224] INFO: * Acc@1 83.172 Acc@5 96.410 loss 0.745 [2021-03-28 11:01:57 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.2% [2021-03-28 11:01:57 swin_base_patch4_window7_224] INFO: Max accuracy: 83.17% [2021-03-28 11:02:01 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 0/1251] eta: 1:28:33 lr: 0.000045 loss: 2.9680 (2.9680) grad_norm: 4.2366 (4.2366) time: 4.2470 [2021-03-28 11:02:07 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 10/1251] eta: 0:19:54 lr: 0.000045 loss: 2.8290 (2.7716) grad_norm: 3.2058 (3.2650) time: 0.9625 [2021-03-28 11:02:14 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 20/1251] eta: 0:16:34 lr: 0.000045 loss: 2.7048 (2.6973) grad_norm: 2.9948 (3.1808) time: 0.6362 [2021-03-28 11:02:20 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 30/1251] eta: 0:15:18 lr: 0.000045 loss: 2.6277 (2.6272) grad_norm: 3.0259 (3.2060) time: 0.6365 [2021-03-28 11:02:26 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 40/1251] eta: 0:14:35 lr: 0.000045 loss: 2.6438 (2.6270) grad_norm: 3.2965 (3.2665) time: 0.6340 [2021-03-28 11:02:33 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 50/1251] eta: 0:14:09 lr: 0.000045 loss: 2.7573 (2.6649) grad_norm: 3.3874 (3.3080) time: 0.6369 [2021-03-28 11:02:39 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 60/1251] eta: 0:13:46 lr: 0.000045 loss: 2.7076 (2.6309) grad_norm: 2.9724 (3.2381) time: 0.6336 [2021-03-28 11:02:45 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 70/1251] eta: 0:13:28 lr: 0.000045 loss: 2.6893 (2.6284) grad_norm: 2.8905 (3.2636) time: 0.6272 [2021-03-28 11:02:51 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 80/1251] eta: 0:13:12 lr: 0.000045 loss: 2.7777 (2.6582) grad_norm: 3.2183 (3.2780) time: 0.6254 [2021-03-28 11:02:58 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 90/1251] eta: 0:12:58 lr: 0.000045 loss: 2.9849 (2.6986) grad_norm: 2.8811 (3.3202) time: 0.6222 [2021-03-28 11:03:04 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 100/1251] eta: 0:12:47 lr: 0.000045 loss: 2.9849 (2.7016) grad_norm: 2.8746 (3.3408) time: 0.6258 [2021-03-28 11:03:10 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 110/1251] eta: 0:12:37 lr: 0.000045 loss: 2.5882 (2.7002) grad_norm: 3.0240 (3.4078) time: 0.6330 [2021-03-28 11:03:17 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 120/1251] eta: 0:12:29 lr: 0.000045 loss: 2.5930 (2.6887) grad_norm: 3.2708 (3.3902) time: 0.6397 [2021-03-28 11:03:23 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 130/1251] eta: 0:12:20 lr: 0.000045 loss: 2.5930 (2.6867) grad_norm: 3.2600 (3.3842) time: 0.6419 [2021-03-28 11:03:29 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 140/1251] eta: 0:12:11 lr: 0.000045 loss: 2.7450 (2.6910) grad_norm: 3.0506 (3.3620) time: 0.6325 [2021-03-28 11:03:36 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 150/1251] eta: 0:12:02 lr: 0.000045 loss: 2.8506 (2.7002) grad_norm: 2.8804 (3.3563) time: 0.6272 [2021-03-28 11:03:42 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 160/1251] eta: 0:11:54 lr: 0.000045 loss: 2.7360 (2.6928) grad_norm: 2.9367 (3.3393) time: 0.6306 [2021-03-28 11:03:48 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 170/1251] eta: 0:11:46 lr: 0.000045 loss: 2.7939 (2.7024) grad_norm: 2.9397 (3.3344) time: 0.6319 [2021-03-28 11:03:55 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 180/1251] eta: 0:11:38 lr: 0.000044 loss: 2.8788 (2.7089) grad_norm: 3.1222 (3.3504) time: 0.6348 [2021-03-28 11:04:01 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 190/1251] eta: 0:11:30 lr: 0.000044 loss: 2.8156 (2.7104) grad_norm: 3.2275 (3.3699) time: 0.6320 [2021-03-28 11:04:07 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 200/1251] eta: 0:11:23 lr: 0.000044 loss: 2.5721 (2.7079) grad_norm: 3.1948 (3.3579) time: 0.6327 [2021-03-28 11:04:14 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 210/1251] eta: 0:11:16 lr: 0.000044 loss: 2.3830 (2.7041) grad_norm: 3.1943 (3.3778) time: 0.6335 [2021-03-28 11:04:20 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 220/1251] eta: 0:11:08 lr: 0.000044 loss: 2.7779 (2.7043) grad_norm: 3.1943 (3.3836) time: 0.6259 [2021-03-28 11:04:26 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 230/1251] eta: 0:11:01 lr: 0.000044 loss: 2.7808 (2.7037) grad_norm: 2.9574 (3.3710) time: 0.6300 [2021-03-28 11:04:33 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 240/1251] eta: 0:10:54 lr: 0.000044 loss: 2.6817 (2.7019) grad_norm: 2.9140 (3.3663) time: 0.6345 [2021-03-28 11:04:39 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 250/1251] eta: 0:10:47 lr: 0.000044 loss: 2.7879 (2.7118) grad_norm: 3.0230 (3.3626) time: 0.6353 [2021-03-28 11:04:45 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 260/1251] eta: 0:10:40 lr: 0.000044 loss: 2.8365 (2.7109) grad_norm: 2.9102 (3.3447) time: 0.6329 [2021-03-28 11:04:52 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 270/1251] eta: 0:10:33 lr: 0.000044 loss: 2.7862 (2.7106) grad_norm: 2.9623 (3.3545) time: 0.6296 [2021-03-28 11:04:58 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 280/1251] eta: 0:10:26 lr: 0.000044 loss: 2.8639 (2.7079) grad_norm: 3.1472 (3.3461) time: 0.6328 [2021-03-28 11:05:04 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 290/1251] eta: 0:10:19 lr: 0.000044 loss: 2.7301 (2.7062) grad_norm: 2.9548 (3.3445) time: 0.6315 [2021-03-28 11:05:11 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 300/1251] eta: 0:10:12 lr: 0.000044 loss: 2.7301 (2.7054) grad_norm: 3.0603 (3.3540) time: 0.6284 [2021-03-28 11:05:17 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 310/1251] eta: 0:10:05 lr: 0.000044 loss: 2.7436 (2.7054) grad_norm: 3.1413 (3.3822) time: 0.6323 [2021-03-28 11:05:23 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 320/1251] eta: 0:09:58 lr: 0.000044 loss: 2.7971 (2.7092) grad_norm: 3.1186 (3.3850) time: 0.6337 [2021-03-28 11:05:29 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 330/1251] eta: 0:09:52 lr: 0.000044 loss: 2.7720 (2.7074) grad_norm: 2.9950 (3.4209) time: 0.6307 [2021-03-28 11:05:36 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 340/1251] eta: 0:09:45 lr: 0.000044 loss: 2.7425 (2.7096) grad_norm: 2.9018 (3.4126) time: 0.6259 [2021-03-28 11:05:42 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 350/1251] eta: 0:09:38 lr: 0.000044 loss: 2.7465 (2.7075) grad_norm: 2.9845 (3.4201) time: 0.6212 [2021-03-28 11:05:48 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 360/1251] eta: 0:09:31 lr: 0.000044 loss: 2.6917 (2.7083) grad_norm: 3.1669 (3.4364) time: 0.6250 [2021-03-28 11:05:54 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 370/1251] eta: 0:09:24 lr: 0.000044 loss: 2.8835 (2.7118) grad_norm: 3.1806 (3.4476) time: 0.6275 [2021-03-28 11:06:01 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 380/1251] eta: 0:09:17 lr: 0.000044 loss: 2.8884 (2.7156) grad_norm: 3.2157 (3.4448) time: 0.6242 [2021-03-28 11:06:07 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 390/1251] eta: 0:09:11 lr: 0.000044 loss: 2.8805 (2.7176) grad_norm: 3.1242 (3.4311) time: 0.6307 [2021-03-28 11:06:13 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 400/1251] eta: 0:09:04 lr: 0.000044 loss: 2.8937 (2.7193) grad_norm: 2.7487 (3.4212) time: 0.6352 [2021-03-28 11:06:20 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 410/1251] eta: 0:08:58 lr: 0.000044 loss: 2.8694 (2.7180) grad_norm: 3.2161 (3.4277) time: 0.6263 [2021-03-28 11:06:26 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 420/1251] eta: 0:08:51 lr: 0.000044 loss: 2.5916 (2.7175) grad_norm: 3.2161 (3.4192) time: 0.6238 [2021-03-28 11:06:32 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 430/1251] eta: 0:08:44 lr: 0.000044 loss: 2.8776 (2.7237) grad_norm: 3.0531 (3.4130) time: 0.6224 [2021-03-28 11:06:38 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 440/1251] eta: 0:08:37 lr: 0.000044 loss: 2.7431 (2.7166) grad_norm: 3.0792 (3.4074) time: 0.6235 [2021-03-28 11:06:45 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 450/1251] eta: 0:08:31 lr: 0.000044 loss: 2.7164 (2.7197) grad_norm: 3.1059 (3.4067) time: 0.6293 [2021-03-28 11:06:51 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 460/1251] eta: 0:08:24 lr: 0.000044 loss: 2.8907 (2.7217) grad_norm: 3.1289 (3.4021) time: 0.6317 [2021-03-28 11:06:57 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 470/1251] eta: 0:08:18 lr: 0.000044 loss: 2.8760 (2.7237) grad_norm: 2.9845 (3.3956) time: 0.6354 [2021-03-28 11:07:04 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 480/1251] eta: 0:08:12 lr: 0.000044 loss: 2.6773 (2.7163) grad_norm: 2.9401 (3.3923) time: 0.6351 [2021-03-28 11:07:10 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 490/1251] eta: 0:08:05 lr: 0.000044 loss: 2.0882 (2.7074) grad_norm: 2.9401 (3.3863) time: 0.6283 [2021-03-28 11:07:16 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 500/1251] eta: 0:07:58 lr: 0.000044 loss: 2.4795 (2.7071) grad_norm: 2.7726 (3.3828) time: 0.6247 [2021-03-28 11:07:22 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 510/1251] eta: 0:07:52 lr: 0.000044 loss: 2.7461 (2.7093) grad_norm: 2.8720 (3.3754) time: 0.6276 [2021-03-28 11:07:29 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 520/1251] eta: 0:07:45 lr: 0.000044 loss: 2.7461 (2.7083) grad_norm: 2.8851 (3.3673) time: 0.6287 [2021-03-28 11:07:35 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 530/1251] eta: 0:07:39 lr: 0.000044 loss: 2.6915 (2.7065) grad_norm: 2.9267 (3.3694) time: 0.6269 [2021-03-28 11:07:41 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 540/1251] eta: 0:07:32 lr: 0.000044 loss: 2.6593 (2.7061) grad_norm: 3.2141 (3.3680) time: 0.6264 [2021-03-28 11:07:48 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 550/1251] eta: 0:07:26 lr: 0.000044 loss: 2.5962 (2.7044) grad_norm: 3.0727 (3.3629) time: 0.6388 [2021-03-28 11:07:54 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 560/1251] eta: 0:07:20 lr: 0.000044 loss: 2.7785 (2.7073) grad_norm: 3.0727 (3.3645) time: 0.6444 [2021-03-28 11:08:01 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 570/1251] eta: 0:07:13 lr: 0.000044 loss: 2.7382 (2.7045) grad_norm: 3.4136 (3.3690) time: 0.6369 [2021-03-28 11:08:07 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 580/1251] eta: 0:07:07 lr: 0.000044 loss: 2.7940 (2.7090) grad_norm: 3.0109 (3.3602) time: 0.6398 [2021-03-28 11:08:13 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 590/1251] eta: 0:07:01 lr: 0.000044 loss: 2.8674 (2.7085) grad_norm: 2.8765 (3.3585) time: 0.6384 [2021-03-28 11:08:20 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 600/1251] eta: 0:06:54 lr: 0.000044 loss: 2.7848 (2.7062) grad_norm: 2.8765 (3.3533) time: 0.6292 [2021-03-28 11:08:26 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 610/1251] eta: 0:06:48 lr: 0.000044 loss: 2.7274 (2.7072) grad_norm: 3.3156 (3.3573) time: 0.6263 [2021-03-28 11:08:32 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 620/1251] eta: 0:06:41 lr: 0.000044 loss: 2.8367 (2.7061) grad_norm: 3.3011 (3.3574) time: 0.6277 [2021-03-28 11:08:38 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 630/1251] eta: 0:06:35 lr: 0.000044 loss: 2.8367 (2.7068) grad_norm: 3.0967 (3.3526) time: 0.6279 [2021-03-28 11:08:45 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 640/1251] eta: 0:06:28 lr: 0.000044 loss: 2.9236 (2.7082) grad_norm: 2.8104 (3.3501) time: 0.6307 [2021-03-28 11:08:51 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 650/1251] eta: 0:06:22 lr: 0.000044 loss: 2.8124 (2.7087) grad_norm: 2.8423 (3.3463) time: 0.6367 [2021-03-28 11:08:57 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 660/1251] eta: 0:06:16 lr: 0.000044 loss: 2.5806 (2.7022) grad_norm: 3.0656 (3.3468) time: 0.6308 [2021-03-28 11:09:04 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 670/1251] eta: 0:06:09 lr: 0.000044 loss: 2.6221 (2.7039) grad_norm: 3.1723 (3.3446) time: 0.6250 [2021-03-28 11:09:10 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 680/1251] eta: 0:06:03 lr: 0.000044 loss: 2.7939 (2.7037) grad_norm: 3.0390 (3.3400) time: 0.6268 [2021-03-28 11:09:16 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 690/1251] eta: 0:05:56 lr: 0.000044 loss: 2.6956 (2.7021) grad_norm: 3.0235 (3.3397) time: 0.6285 [2021-03-28 11:09:23 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 700/1251] eta: 0:05:50 lr: 0.000044 loss: 2.7769 (2.7050) grad_norm: 3.2302 (3.3571) time: 0.6310 [2021-03-28 11:09:29 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 710/1251] eta: 0:05:43 lr: 0.000044 loss: 2.8828 (2.7028) grad_norm: 3.1318 (3.3569) time: 0.6272 [2021-03-28 11:09:35 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 720/1251] eta: 0:05:37 lr: 0.000044 loss: 2.8140 (2.7047) grad_norm: 3.0480 (3.3646) time: 0.6250 [2021-03-28 11:09:41 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 730/1251] eta: 0:05:31 lr: 0.000044 loss: 2.7947 (2.7038) grad_norm: 3.1432 (3.3603) time: 0.6278 [2021-03-28 11:09:48 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 740/1251] eta: 0:05:24 lr: 0.000044 loss: 2.7045 (2.7028) grad_norm: 3.2174 (3.3626) time: 0.6298 [2021-03-28 11:09:54 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 750/1251] eta: 0:05:18 lr: 0.000044 loss: 2.5717 (2.7004) grad_norm: 3.3136 (3.3623) time: 0.6389 [2021-03-28 11:10:00 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 760/1251] eta: 0:05:12 lr: 0.000044 loss: 2.6354 (2.6987) grad_norm: 3.1377 (3.3797) time: 0.6396 [2021-03-28 11:10:07 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 770/1251] eta: 0:05:05 lr: 0.000044 loss: 2.6564 (2.6997) grad_norm: 2.8157 (3.3745) time: 0.6354 [2021-03-28 11:10:13 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 780/1251] eta: 0:04:59 lr: 0.000044 loss: 2.6764 (2.6989) grad_norm: 3.1260 (3.3763) time: 0.6328 [2021-03-28 11:10:20 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 790/1251] eta: 0:04:53 lr: 0.000044 loss: 2.5926 (2.6974) grad_norm: 3.2144 (3.3757) time: 0.6350 [2021-03-28 11:10:26 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 800/1251] eta: 0:04:46 lr: 0.000044 loss: 2.7394 (2.6970) grad_norm: 3.2175 (3.3872) time: 0.6351 [2021-03-28 11:10:32 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 810/1251] eta: 0:04:40 lr: 0.000044 loss: 2.8049 (2.6994) grad_norm: 2.9554 (3.3925) time: 0.6247 [2021-03-28 11:10:38 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 820/1251] eta: 0:04:33 lr: 0.000044 loss: 2.7314 (2.6968) grad_norm: 3.1454 (3.3914) time: 0.6300 [2021-03-28 11:10:45 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 830/1251] eta: 0:04:27 lr: 0.000044 loss: 2.6424 (2.6962) grad_norm: 3.1454 (3.3898) time: 0.6308 [2021-03-28 11:10:51 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 840/1251] eta: 0:04:21 lr: 0.000043 loss: 2.6424 (2.6954) grad_norm: 3.0814 (3.3885) time: 0.6263 [2021-03-28 11:10:57 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 850/1251] eta: 0:04:14 lr: 0.000043 loss: 2.8343 (2.6970) grad_norm: 3.1774 (3.3962) time: 0.6287 [2021-03-28 11:11:04 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 860/1251] eta: 0:04:08 lr: 0.000043 loss: 2.8343 (2.6959) grad_norm: 3.1774 (3.3990) time: 0.6343 [2021-03-28 11:11:10 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 870/1251] eta: 0:04:01 lr: 0.000043 loss: 2.5949 (2.6953) grad_norm: 3.0695 (3.3983) time: 0.6374 [2021-03-28 11:11:16 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 880/1251] eta: 0:03:55 lr: 0.000043 loss: 2.9003 (2.6980) grad_norm: 2.9865 (3.3947) time: 0.6318 [2021-03-28 11:11:23 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 890/1251] eta: 0:03:49 lr: 0.000043 loss: 2.8416 (2.6974) grad_norm: 2.8940 (3.3946) time: 0.6273 [2021-03-28 11:11:29 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 900/1251] eta: 0:03:42 lr: 0.000043 loss: 2.7262 (2.7000) grad_norm: 2.9151 (3.3896) time: 0.6293 [2021-03-28 11:11:35 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 910/1251] eta: 0:03:36 lr: 0.000043 loss: 2.9308 (2.7015) grad_norm: 2.9430 (3.3880) time: 0.6301 [2021-03-28 11:11:41 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 920/1251] eta: 0:03:30 lr: 0.000043 loss: 2.9308 (2.7038) grad_norm: 3.1098 (3.3836) time: 0.6300 [2021-03-28 11:11:48 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 930/1251] eta: 0:03:23 lr: 0.000043 loss: 2.8052 (2.7042) grad_norm: 3.0544 (3.3865) time: 0.6299 [2021-03-28 11:11:54 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 940/1251] eta: 0:03:17 lr: 0.000043 loss: 2.7609 (2.7037) grad_norm: 3.0491 (3.3826) time: 0.6288 [2021-03-28 11:12:01 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 950/1251] eta: 0:03:11 lr: 0.000043 loss: 2.7980 (2.7048) grad_norm: 2.9333 (3.3801) time: 0.6402 [2021-03-28 11:12:07 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 960/1251] eta: 0:03:04 lr: 0.000043 loss: 2.6892 (2.7030) grad_norm: 2.9984 (3.3788) time: 0.6400 [2021-03-28 11:12:13 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 970/1251] eta: 0:02:58 lr: 0.000043 loss: 2.6892 (2.7036) grad_norm: 3.2541 (3.3779) time: 0.6286 [2021-03-28 11:12:19 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 980/1251] eta: 0:02:51 lr: 0.000043 loss: 2.8402 (2.7056) grad_norm: 3.3553 (3.3814) time: 0.6263 [2021-03-28 11:12:26 swin_base_patch4_window7_224] INFO: Epoch: [264] [ 990/1251] eta: 0:02:45 lr: 0.000043 loss: 2.7071 (2.7037) grad_norm: 3.2455 (3.3774) time: 0.6231 [2021-03-28 11:12:32 swin_base_patch4_window7_224] INFO: Epoch: [264] [1000/1251] eta: 0:02:39 lr: 0.000043 loss: 2.6299 (2.7044) grad_norm: 2.9119 (3.3749) time: 0.6221 [2021-03-28 11:12:38 swin_base_patch4_window7_224] INFO: Epoch: [264] [1010/1251] eta: 0:02:32 lr: 0.000043 loss: 2.6299 (2.7026) grad_norm: 3.0505 (3.3727) time: 0.6252 [2021-03-28 11:12:44 swin_base_patch4_window7_224] INFO: Epoch: [264] [1020/1251] eta: 0:02:26 lr: 0.000043 loss: 2.4194 (2.7009) grad_norm: 3.0732 (3.3695) time: 0.6292 [2021-03-28 11:12:51 swin_base_patch4_window7_224] INFO: Epoch: [264] [1030/1251] eta: 0:02:20 lr: 0.000043 loss: 2.6899 (2.6999) grad_norm: 3.0166 (3.3672) time: 0.6293 [2021-03-28 11:12:57 swin_base_patch4_window7_224] INFO: Epoch: [264] [1040/1251] eta: 0:02:13 lr: 0.000043 loss: 2.8733 (2.7014) grad_norm: 3.0728 (3.3668) time: 0.6323 [2021-03-28 11:13:03 swin_base_patch4_window7_224] INFO: Epoch: [264] [1050/1251] eta: 0:02:07 lr: 0.000043 loss: 2.9286 (2.7028) grad_norm: 3.1775 (3.3728) time: 0.6385 [2021-03-28 11:13:10 swin_base_patch4_window7_224] INFO: Epoch: [264] [1060/1251] eta: 0:02:01 lr: 0.000043 loss: 2.9351 (2.7036) grad_norm: 3.1775 (3.3765) time: 0.6338 [2021-03-28 11:13:16 swin_base_patch4_window7_224] INFO: Epoch: [264] [1070/1251] eta: 0:01:54 lr: 0.000043 loss: 2.8229 (2.7038) grad_norm: 2.9007 (3.3744) time: 0.6259 [2021-03-28 11:13:22 swin_base_patch4_window7_224] INFO: Epoch: [264] [1080/1251] eta: 0:01:48 lr: 0.000043 loss: 2.7486 (2.7032) grad_norm: 2.9007 (3.3721) time: 0.6251 [2021-03-28 11:13:29 swin_base_patch4_window7_224] INFO: Epoch: [264] [1090/1251] eta: 0:01:42 lr: 0.000043 loss: 2.6878 (2.7031) grad_norm: 3.0262 (3.3693) time: 0.6259 [2021-03-28 11:13:35 swin_base_patch4_window7_224] INFO: Epoch: [264] [1100/1251] eta: 0:01:35 lr: 0.000043 loss: 2.7777 (2.7039) grad_norm: 3.1179 (inf) time: 0.6283 [2021-03-28 11:13:41 swin_base_patch4_window7_224] INFO: Epoch: [264] [1110/1251] eta: 0:01:29 lr: 0.000043 loss: 2.8373 (2.7050) grad_norm: 3.1713 (inf) time: 0.6309 [2021-03-28 11:13:47 swin_base_patch4_window7_224] INFO: Epoch: [264] [1120/1251] eta: 0:01:23 lr: 0.000043 loss: 2.7198 (2.7048) grad_norm: 3.2012 (inf) time: 0.6278 [2021-03-28 11:13:54 swin_base_patch4_window7_224] INFO: Epoch: [264] [1130/1251] eta: 0:01:16 lr: 0.000043 loss: 2.7198 (2.7048) grad_norm: 2.9488 (inf) time: 0.6304 [2021-03-28 11:14:00 swin_base_patch4_window7_224] INFO: Epoch: [264] [1140/1251] eta: 0:01:10 lr: 0.000043 loss: 2.6015 (2.7043) grad_norm: 2.9488 (inf) time: 0.6299 [2021-03-28 11:14:06 swin_base_patch4_window7_224] INFO: Epoch: [264] [1150/1251] eta: 0:01:04 lr: 0.000043 loss: 2.7469 (2.7056) grad_norm: 2.9471 (inf) time: 0.6297 [2021-03-28 11:14:13 swin_base_patch4_window7_224] INFO: Epoch: [264] [1160/1251] eta: 0:00:57 lr: 0.000043 loss: 2.7603 (2.7062) grad_norm: 2.9077 (inf) time: 0.6302 [2021-03-28 11:14:19 swin_base_patch4_window7_224] INFO: Epoch: [264] [1170/1251] eta: 0:00:51 lr: 0.000043 loss: 2.7358 (2.7059) grad_norm: 2.9472 (inf) time: 0.6220 [2021-03-28 11:14:25 swin_base_patch4_window7_224] INFO: Epoch: [264] [1180/1251] eta: 0:00:44 lr: 0.000043 loss: 2.8631 (2.7062) grad_norm: 3.1395 (inf) time: 0.6235 [2021-03-28 11:14:31 swin_base_patch4_window7_224] INFO: Epoch: [264] [1190/1251] eta: 0:00:38 lr: 0.000043 loss: 2.8631 (2.7064) grad_norm: 3.0289 (inf) time: 0.6262 [2021-03-28 11:14:38 swin_base_patch4_window7_224] INFO: Epoch: [264] [1200/1251] eta: 0:00:32 lr: 0.000043 loss: 2.8583 (2.7060) grad_norm: 2.9458 (inf) time: 0.6280 [2021-03-28 11:14:44 swin_base_patch4_window7_224] INFO: Epoch: [264] [1210/1251] eta: 0:00:25 lr: 0.000043 loss: 2.7762 (2.7045) grad_norm: 2.9747 (inf) time: 0.6275 [2021-03-28 11:14:50 swin_base_patch4_window7_224] INFO: Epoch: [264] [1220/1251] eta: 0:00:19 lr: 0.000043 loss: 2.7651 (2.7055) grad_norm: 2.9878 (inf) time: 0.6238 [2021-03-28 11:14:56 swin_base_patch4_window7_224] INFO: Epoch: [264] [1230/1251] eta: 0:00:13 lr: 0.000043 loss: 2.8144 (2.7052) grad_norm: 2.8825 (inf) time: 0.6289 [2021-03-28 11:15:03 swin_base_patch4_window7_224] INFO: Epoch: [264] [1240/1251] eta: 0:00:06 lr: 0.000043 loss: 2.9629 (2.7064) grad_norm: 3.0536 (inf) time: 0.6315 [2021-03-28 11:15:09 swin_base_patch4_window7_224] INFO: Epoch: [264] [1250/1251] eta: 0:00:00 lr: 0.000043 loss: 3.0064 (2.7070) grad_norm: 3.1012 (inf) time: 0.6222 [2021-03-28 11:15:22 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:41 loss: 0.5668 (0.5668) acc1: 89.0625 (89.0625) acc5: 98.4375 (98.4375) [2021-03-28 11:15:24 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7669 (0.7732) acc1: 79.6875 (81.5341) acc5: 96.8750 (96.3068) [2021-03-28 11:15:26 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7447 (0.7471) acc1: 81.2500 (82.4405) acc5: 96.8750 (96.6518) [2021-03-28 11:15:28 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.6761 (0.7409) acc1: 82.8125 (82.6109) acc5: 96.8750 (96.5726) [2021-03-28 11:15:31 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7380 (0.7497) acc1: 81.2500 (82.4695) acc5: 96.8750 (96.6463) [2021-03-28 11:15:32 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7380 (0.7572) acc1: 82.8125 (82.4320) acc5: 96.8750 (96.6400) [2021-03-28 11:15:46 swin_base_patch4_window7_224] INFO: * Acc@1 83.270 Acc@5 96.382 loss 0.743 [2021-03-28 11:15:46 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.3% [2021-03-28 11:15:46 swin_base_patch4_window7_224] INFO: Max accuracy: 83.27% [2021-03-28 11:15:50 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 0/1251] eta: 1:32:23 lr: 0.000043 loss: 3.1275 (3.1275) grad_norm: 2.7612 (2.7612) time: 4.4311 [2021-03-28 11:15:57 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 10/1251] eta: 0:20:32 lr: 0.000043 loss: 2.9813 (2.8893) grad_norm: 3.3453 (3.8015) time: 0.9931 [2021-03-28 11:16:03 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 20/1251] eta: 0:16:49 lr: 0.000043 loss: 2.8205 (2.8209) grad_norm: 3.0351 (3.4357) time: 0.6391 [2021-03-28 11:16:09 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 30/1251] eta: 0:15:26 lr: 0.000043 loss: 2.8205 (2.8215) grad_norm: 2.9598 (3.3303) time: 0.6303 [2021-03-28 11:16:16 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 40/1251] eta: 0:14:43 lr: 0.000043 loss: 2.8454 (2.8148) grad_norm: 3.0412 (3.3777) time: 0.6354 [2021-03-28 11:16:22 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 50/1251] eta: 0:14:12 lr: 0.000043 loss: 2.7592 (2.7820) grad_norm: 3.3715 (3.4772) time: 0.6328 [2021-03-28 11:16:28 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 60/1251] eta: 0:13:49 lr: 0.000043 loss: 2.7548 (2.7841) grad_norm: 3.1571 (3.4096) time: 0.6280 [2021-03-28 11:16:35 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 70/1251] eta: 0:13:31 lr: 0.000043 loss: 2.7987 (2.7656) grad_norm: 3.0790 (3.3974) time: 0.6300 [2021-03-28 11:16:41 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 80/1251] eta: 0:13:15 lr: 0.000043 loss: 2.6044 (2.7210) grad_norm: 2.9058 (3.3361) time: 0.6258 [2021-03-28 11:16:47 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 90/1251] eta: 0:13:02 lr: 0.000043 loss: 2.6085 (2.7400) grad_norm: 3.1166 (3.3628) time: 0.6254 [2021-03-28 11:16:53 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 100/1251] eta: 0:12:49 lr: 0.000043 loss: 2.7866 (2.7300) grad_norm: 3.1166 (3.3526) time: 0.6281 [2021-03-28 11:17:00 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 110/1251] eta: 0:12:39 lr: 0.000043 loss: 2.6272 (2.7328) grad_norm: 2.9793 (3.3285) time: 0.6320 [2021-03-28 11:17:06 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 120/1251] eta: 0:12:30 lr: 0.000043 loss: 2.7769 (2.7356) grad_norm: 2.9400 (3.3452) time: 0.6358 [2021-03-28 11:17:12 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 130/1251] eta: 0:12:21 lr: 0.000043 loss: 2.7929 (2.7405) grad_norm: 3.2603 (3.3502) time: 0.6368 [2021-03-28 11:17:19 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 140/1251] eta: 0:12:13 lr: 0.000043 loss: 2.8458 (2.7324) grad_norm: 3.1968 (3.3404) time: 0.6416 [2021-03-28 11:17:25 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 150/1251] eta: 0:12:05 lr: 0.000043 loss: 2.3972 (2.7145) grad_norm: 2.9881 (3.4334) time: 0.6400 [2021-03-28 11:17:32 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 160/1251] eta: 0:11:56 lr: 0.000043 loss: 2.5497 (2.7126) grad_norm: 2.7359 (3.4156) time: 0.6336 [2021-03-28 11:17:38 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 170/1251] eta: 0:11:48 lr: 0.000043 loss: 2.7082 (2.6951) grad_norm: 2.7359 (3.4025) time: 0.6315 [2021-03-28 11:17:44 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 180/1251] eta: 0:11:41 lr: 0.000043 loss: 2.7158 (2.6977) grad_norm: 2.9325 (3.3912) time: 0.6373 [2021-03-28 11:17:51 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 190/1251] eta: 0:11:33 lr: 0.000043 loss: 2.7761 (2.6986) grad_norm: 3.0190 (3.3725) time: 0.6353 [2021-03-28 11:17:57 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 200/1251] eta: 0:11:25 lr: 0.000043 loss: 2.8298 (2.6977) grad_norm: 3.0190 (3.3610) time: 0.6301 [2021-03-28 11:18:03 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 210/1251] eta: 0:11:18 lr: 0.000043 loss: 2.7434 (2.6959) grad_norm: 3.0160 (3.3810) time: 0.6358 [2021-03-28 11:18:10 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 220/1251] eta: 0:11:11 lr: 0.000043 loss: 2.8287 (2.6995) grad_norm: 3.1077 (3.3733) time: 0.6387 [2021-03-28 11:18:16 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 230/1251] eta: 0:11:03 lr: 0.000043 loss: 2.8741 (2.6981) grad_norm: 2.9669 (3.3594) time: 0.6310 [2021-03-28 11:18:22 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 240/1251] eta: 0:10:56 lr: 0.000043 loss: 2.5858 (2.6940) grad_norm: 2.9476 (3.3548) time: 0.6258 [2021-03-28 11:18:29 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 250/1251] eta: 0:10:49 lr: 0.000043 loss: 2.7923 (2.6979) grad_norm: 2.9702 (3.3486) time: 0.6313 [2021-03-28 11:18:35 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 260/1251] eta: 0:10:41 lr: 0.000042 loss: 2.7923 (2.6988) grad_norm: 2.9868 (3.3410) time: 0.6328 [2021-03-28 11:18:41 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 270/1251] eta: 0:10:34 lr: 0.000042 loss: 2.8438 (2.7104) grad_norm: 2.9802 (3.3269) time: 0.6265 [2021-03-28 11:18:47 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 280/1251] eta: 0:10:27 lr: 0.000042 loss: 2.8406 (2.7078) grad_norm: 2.9802 (3.3184) time: 0.6271 [2021-03-28 11:18:54 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 290/1251] eta: 0:10:20 lr: 0.000042 loss: 2.7521 (2.7075) grad_norm: 2.9637 (3.3068) time: 0.6280 [2021-03-28 11:19:00 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 300/1251] eta: 0:10:13 lr: 0.000042 loss: 2.7703 (2.7089) grad_norm: 3.0245 (3.3105) time: 0.6288 [2021-03-28 11:19:06 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 310/1251] eta: 0:10:06 lr: 0.000042 loss: 2.7444 (2.7017) grad_norm: 3.1545 (3.3090) time: 0.6363 [2021-03-28 11:19:13 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 320/1251] eta: 0:10:00 lr: 0.000042 loss: 2.8195 (2.7070) grad_norm: 3.1949 (3.3143) time: 0.6359 [2021-03-28 11:19:19 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 330/1251] eta: 0:09:53 lr: 0.000042 loss: 2.7936 (2.7036) grad_norm: 3.0357 (3.3125) time: 0.6359 [2021-03-28 11:19:25 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 340/1251] eta: 0:09:46 lr: 0.000042 loss: 2.7936 (2.7047) grad_norm: 3.0261 (3.3038) time: 0.6384 [2021-03-28 11:19:32 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 350/1251] eta: 0:09:40 lr: 0.000042 loss: 2.8051 (2.7035) grad_norm: 2.9246 (3.2959) time: 0.6379 [2021-03-28 11:19:38 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 360/1251] eta: 0:09:33 lr: 0.000042 loss: 2.8070 (2.7055) grad_norm: 2.9720 (3.2862) time: 0.6367 [2021-03-28 11:19:45 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 370/1251] eta: 0:09:26 lr: 0.000042 loss: 2.8654 (2.7076) grad_norm: 3.1661 (3.2918) time: 0.6317 [2021-03-28 11:19:51 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 380/1251] eta: 0:09:20 lr: 0.000042 loss: 2.8859 (2.7095) grad_norm: 3.2993 (3.2972) time: 0.6279 [2021-03-28 11:19:57 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 390/1251] eta: 0:09:13 lr: 0.000042 loss: 2.8001 (2.7143) grad_norm: 3.1638 (3.3110) time: 0.6244 [2021-03-28 11:20:03 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 400/1251] eta: 0:09:06 lr: 0.000042 loss: 2.8418 (2.7155) grad_norm: 3.2456 (3.3125) time: 0.6262 [2021-03-28 11:20:10 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 410/1251] eta: 0:09:00 lr: 0.000042 loss: 2.7385 (2.7104) grad_norm: 3.3090 (3.3093) time: 0.6364 [2021-03-28 11:20:16 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 420/1251] eta: 0:08:53 lr: 0.000042 loss: 2.3858 (2.7039) grad_norm: 3.2805 (3.3184) time: 0.6399 [2021-03-28 11:20:22 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 430/1251] eta: 0:08:46 lr: 0.000042 loss: 2.4195 (2.6997) grad_norm: 3.1939 (3.3196) time: 0.6332 [2021-03-28 11:20:29 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 440/1251] eta: 0:08:40 lr: 0.000042 loss: 2.6748 (2.7007) grad_norm: 3.1144 (3.3267) time: 0.6327 [2021-03-28 11:20:35 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 450/1251] eta: 0:08:33 lr: 0.000042 loss: 2.6748 (2.6994) grad_norm: 3.1154 (3.3285) time: 0.6320 [2021-03-28 11:20:41 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 460/1251] eta: 0:08:27 lr: 0.000042 loss: 2.5627 (2.6971) grad_norm: 3.2537 (3.3326) time: 0.6287 [2021-03-28 11:20:48 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 470/1251] eta: 0:08:20 lr: 0.000042 loss: 2.6136 (2.6941) grad_norm: 3.0708 (3.3256) time: 0.6295 [2021-03-28 11:20:54 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 480/1251] eta: 0:08:13 lr: 0.000042 loss: 2.4970 (2.6878) grad_norm: 2.8781 (3.3225) time: 0.6302 [2021-03-28 11:21:00 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 490/1251] eta: 0:08:07 lr: 0.000042 loss: 2.7821 (2.6905) grad_norm: 2.9201 (3.3163) time: 0.6294 [2021-03-28 11:21:07 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 500/1251] eta: 0:08:00 lr: 0.000042 loss: 2.7843 (2.6904) grad_norm: 3.1152 (3.3164) time: 0.6301 [2021-03-28 11:21:13 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 510/1251] eta: 0:07:54 lr: 0.000042 loss: 2.6864 (2.6884) grad_norm: 3.2141 (3.3251) time: 0.6299 [2021-03-28 11:21:19 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 520/1251] eta: 0:07:47 lr: 0.000042 loss: 2.5473 (2.6856) grad_norm: 3.1248 (3.3246) time: 0.6314 [2021-03-28 11:21:25 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 530/1251] eta: 0:07:41 lr: 0.000042 loss: 2.7691 (2.6869) grad_norm: 3.0827 (3.3225) time: 0.6299 [2021-03-28 11:21:32 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 540/1251] eta: 0:07:34 lr: 0.000042 loss: 2.7970 (2.6866) grad_norm: 3.1221 (3.3268) time: 0.6267 [2021-03-28 11:21:38 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 550/1251] eta: 0:07:28 lr: 0.000042 loss: 2.5884 (2.6845) grad_norm: 3.2873 (3.3288) time: 0.6443 [2021-03-28 11:21:45 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 560/1251] eta: 0:07:22 lr: 0.000042 loss: 2.5686 (2.6827) grad_norm: 3.1238 (3.3243) time: 0.6505 [2021-03-28 11:21:51 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 570/1251] eta: 0:07:15 lr: 0.000042 loss: 2.6592 (2.6843) grad_norm: 3.0180 (3.3241) time: 0.6408 [2021-03-28 11:21:57 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 580/1251] eta: 0:07:09 lr: 0.000042 loss: 2.7491 (2.6841) grad_norm: 3.2045 (3.3360) time: 0.6370 [2021-03-28 11:22:04 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 590/1251] eta: 0:07:02 lr: 0.000042 loss: 2.7319 (2.6824) grad_norm: 3.6445 (3.3463) time: 0.6313 [2021-03-28 11:22:10 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 600/1251] eta: 0:06:56 lr: 0.000042 loss: 2.7411 (2.6847) grad_norm: 3.2616 (3.3410) time: 0.6378 [2021-03-28 11:22:17 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 610/1251] eta: 0:06:49 lr: 0.000042 loss: 2.7408 (2.6855) grad_norm: 3.1411 (3.3424) time: 0.6390 [2021-03-28 11:22:23 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 620/1251] eta: 0:06:43 lr: 0.000042 loss: 2.5582 (2.6832) grad_norm: 3.4492 (3.3910) time: 0.6298 [2021-03-28 11:22:29 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 630/1251] eta: 0:06:36 lr: 0.000042 loss: 2.7844 (2.6859) grad_norm: 3.4937 (3.3913) time: 0.6300 [2021-03-28 11:22:35 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 640/1251] eta: 0:06:30 lr: 0.000042 loss: 2.9940 (2.6864) grad_norm: 3.1229 (3.3840) time: 0.6311 [2021-03-28 11:22:42 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 650/1251] eta: 0:06:23 lr: 0.000042 loss: 2.9596 (2.6871) grad_norm: 2.7688 (3.3765) time: 0.6319 [2021-03-28 11:22:48 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 660/1251] eta: 0:06:17 lr: 0.000042 loss: 2.8900 (2.6889) grad_norm: 2.8241 (3.3708) time: 0.6323 [2021-03-28 11:22:55 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 670/1251] eta: 0:06:11 lr: 0.000042 loss: 2.8640 (2.6882) grad_norm: 3.0456 (3.3916) time: 0.6346 [2021-03-28 11:23:01 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 680/1251] eta: 0:06:04 lr: 0.000042 loss: 2.9038 (2.6888) grad_norm: 3.1317 (3.3885) time: 0.6329 [2021-03-28 11:23:07 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 690/1251] eta: 0:05:58 lr: 0.000042 loss: 2.7565 (2.6850) grad_norm: 3.3240 (3.3898) time: 0.6300 [2021-03-28 11:23:13 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 700/1251] eta: 0:05:51 lr: 0.000042 loss: 2.6320 (2.6872) grad_norm: 3.2163 (3.3871) time: 0.6277 [2021-03-28 11:23:20 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 710/1251] eta: 0:05:45 lr: 0.000042 loss: 2.7948 (2.6864) grad_norm: 3.1085 (3.3822) time: 0.6246 [2021-03-28 11:23:26 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 720/1251] eta: 0:05:38 lr: 0.000042 loss: 2.6882 (2.6867) grad_norm: 2.8741 (3.3806) time: 0.6264 [2021-03-28 11:23:32 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 730/1251] eta: 0:05:32 lr: 0.000042 loss: 2.5857 (2.6844) grad_norm: 2.9886 (3.3795) time: 0.6250 [2021-03-28 11:23:39 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 740/1251] eta: 0:05:25 lr: 0.000042 loss: 2.6213 (2.6844) grad_norm: 3.0120 (3.3787) time: 0.6357 [2021-03-28 11:23:45 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 750/1251] eta: 0:05:19 lr: 0.000042 loss: 2.7214 (2.6859) grad_norm: 3.0120 (3.3749) time: 0.6482 [2021-03-28 11:23:51 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 760/1251] eta: 0:05:13 lr: 0.000042 loss: 2.5863 (2.6833) grad_norm: 3.0864 (3.3724) time: 0.6394 [2021-03-28 11:23:58 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 770/1251] eta: 0:05:06 lr: 0.000042 loss: 2.6535 (2.6850) grad_norm: 3.0571 (3.3694) time: 0.6280 [2021-03-28 11:24:04 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 780/1251] eta: 0:05:00 lr: 0.000042 loss: 2.6759 (2.6826) grad_norm: 3.0433 (3.3660) time: 0.6250 [2021-03-28 11:24:10 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 790/1251] eta: 0:04:53 lr: 0.000042 loss: 2.7086 (2.6828) grad_norm: 3.0154 (3.3631) time: 0.6348 [2021-03-28 11:24:17 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 800/1251] eta: 0:04:47 lr: 0.000042 loss: 2.8763 (2.6819) grad_norm: 2.9285 (3.3595) time: 0.6327 [2021-03-28 11:24:23 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 810/1251] eta: 0:04:41 lr: 0.000042 loss: 2.7936 (2.6841) grad_norm: 3.0306 (3.3630) time: 0.6251 [2021-03-28 11:24:29 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 820/1251] eta: 0:04:34 lr: 0.000042 loss: 2.8589 (2.6839) grad_norm: 3.0306 (3.3583) time: 0.6337 [2021-03-28 11:24:36 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 830/1251] eta: 0:04:28 lr: 0.000042 loss: 2.7073 (2.6836) grad_norm: 3.0033 (3.3615) time: 0.6332 [2021-03-28 11:24:42 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 840/1251] eta: 0:04:21 lr: 0.000042 loss: 2.6978 (2.6849) grad_norm: 2.9684 (3.3600) time: 0.6315 [2021-03-28 11:24:48 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 850/1251] eta: 0:04:15 lr: 0.000042 loss: 2.8663 (2.6845) grad_norm: 2.8966 (3.3586) time: 0.6314 [2021-03-28 11:24:54 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 860/1251] eta: 0:04:09 lr: 0.000042 loss: 2.9220 (2.6870) grad_norm: 3.0330 (3.3569) time: 0.6242 [2021-03-28 11:25:01 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 870/1251] eta: 0:04:02 lr: 0.000042 loss: 2.9047 (2.6861) grad_norm: 3.0051 (3.3537) time: 0.6250 [2021-03-28 11:25:07 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 880/1251] eta: 0:03:56 lr: 0.000042 loss: 2.6836 (2.6870) grad_norm: 3.0051 (3.3508) time: 0.6312 [2021-03-28 11:25:13 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 890/1251] eta: 0:03:49 lr: 0.000042 loss: 2.7543 (2.6873) grad_norm: 2.9972 (3.3486) time: 0.6353 [2021-03-28 11:25:20 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 900/1251] eta: 0:03:43 lr: 0.000042 loss: 2.6071 (2.6845) grad_norm: 2.9578 (3.3460) time: 0.6318 [2021-03-28 11:25:26 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 910/1251] eta: 0:03:37 lr: 0.000042 loss: 2.6071 (2.6847) grad_norm: 2.9711 (3.3454) time: 0.6263 [2021-03-28 11:25:32 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 920/1251] eta: 0:03:30 lr: 0.000042 loss: 2.7703 (2.6839) grad_norm: 3.0299 (3.3432) time: 0.6260 [2021-03-28 11:25:39 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 930/1251] eta: 0:03:24 lr: 0.000042 loss: 2.6514 (2.6817) grad_norm: 3.0090 (3.3412) time: 0.6323 [2021-03-28 11:25:45 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 940/1251] eta: 0:03:17 lr: 0.000041 loss: 2.7978 (2.6840) grad_norm: 2.9413 (3.3417) time: 0.6324 [2021-03-28 11:25:51 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 950/1251] eta: 0:03:11 lr: 0.000041 loss: 2.9981 (2.6858) grad_norm: 2.8858 (3.3400) time: 0.6307 [2021-03-28 11:25:57 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 960/1251] eta: 0:03:05 lr: 0.000041 loss: 2.8565 (2.6859) grad_norm: 2.8992 (3.3391) time: 0.6318 [2021-03-28 11:26:04 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 970/1251] eta: 0:02:58 lr: 0.000041 loss: 2.7899 (2.6869) grad_norm: 2.9917 (3.3419) time: 0.6269 [2021-03-28 11:26:10 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 980/1251] eta: 0:02:52 lr: 0.000041 loss: 2.9489 (2.6885) grad_norm: 3.0104 (3.3394) time: 0.6317 [2021-03-28 11:26:16 swin_base_patch4_window7_224] INFO: Epoch: [265] [ 990/1251] eta: 0:02:46 lr: 0.000041 loss: 2.8569 (2.6892) grad_norm: 3.0104 (3.3392) time: 0.6338 [2021-03-28 11:26:23 swin_base_patch4_window7_224] INFO: Epoch: [265] [1000/1251] eta: 0:02:39 lr: 0.000041 loss: 2.7795 (2.6897) grad_norm: 3.0007 (3.3359) time: 0.6327 [2021-03-28 11:26:29 swin_base_patch4_window7_224] INFO: Epoch: [265] [1010/1251] eta: 0:02:33 lr: 0.000041 loss: 2.7505 (2.6894) grad_norm: 3.0007 (3.3353) time: 0.6310 [2021-03-28 11:26:35 swin_base_patch4_window7_224] INFO: Epoch: [265] [1020/1251] eta: 0:02:26 lr: 0.000041 loss: 2.7952 (2.6910) grad_norm: 2.8774 (3.3330) time: 0.6278 [2021-03-28 11:26:42 swin_base_patch4_window7_224] INFO: Epoch: [265] [1030/1251] eta: 0:02:20 lr: 0.000041 loss: 2.7862 (2.6892) grad_norm: 2.8830 (3.3299) time: 0.6273 [2021-03-28 11:26:48 swin_base_patch4_window7_224] INFO: Epoch: [265] [1040/1251] eta: 0:02:14 lr: 0.000041 loss: 2.5751 (2.6882) grad_norm: 2.9839 (3.3340) time: 0.6243 [2021-03-28 11:26:54 swin_base_patch4_window7_224] INFO: Epoch: [265] [1050/1251] eta: 0:02:07 lr: 0.000041 loss: 2.8296 (2.6905) grad_norm: 3.2708 (3.3388) time: 0.6258 [2021-03-28 11:27:00 swin_base_patch4_window7_224] INFO: Epoch: [265] [1060/1251] eta: 0:02:01 lr: 0.000041 loss: 2.8563 (2.6915) grad_norm: 3.1313 (3.3373) time: 0.6266 [2021-03-28 11:27:07 swin_base_patch4_window7_224] INFO: Epoch: [265] [1070/1251] eta: 0:01:55 lr: 0.000041 loss: 2.9294 (2.6922) grad_norm: 3.2398 (3.3365) time: 0.6265 [2021-03-28 11:27:13 swin_base_patch4_window7_224] INFO: Epoch: [265] [1080/1251] eta: 0:01:48 lr: 0.000041 loss: 2.7473 (2.6924) grad_norm: 3.3636 (3.3367) time: 0.6317 [2021-03-28 11:27:19 swin_base_patch4_window7_224] INFO: Epoch: [265] [1090/1251] eta: 0:01:42 lr: 0.000041 loss: 2.7473 (2.6928) grad_norm: 3.2844 (3.3371) time: 0.6334 [2021-03-28 11:27:26 swin_base_patch4_window7_224] INFO: Epoch: [265] [1100/1251] eta: 0:01:35 lr: 0.000041 loss: 2.8370 (2.6938) grad_norm: 3.1693 (3.3355) time: 0.6298 [2021-03-28 11:27:32 swin_base_patch4_window7_224] INFO: Epoch: [265] [1110/1251] eta: 0:01:29 lr: 0.000041 loss: 2.9834 (2.6946) grad_norm: 3.0170 (3.3326) time: 0.6305 [2021-03-28 11:27:38 swin_base_patch4_window7_224] INFO: Epoch: [265] [1120/1251] eta: 0:01:23 lr: 0.000041 loss: 2.8890 (2.6961) grad_norm: 2.9170 (3.3317) time: 0.6293 [2021-03-28 11:27:44 swin_base_patch4_window7_224] INFO: Epoch: [265] [1130/1251] eta: 0:01:16 lr: 0.000041 loss: 2.8855 (2.6962) grad_norm: 2.9354 (3.3281) time: 0.6254 [2021-03-28 11:27:51 swin_base_patch4_window7_224] INFO: Epoch: [265] [1140/1251] eta: 0:01:10 lr: 0.000041 loss: 2.8992 (2.6967) grad_norm: 3.0817 (3.3307) time: 0.6272 [2021-03-28 11:27:57 swin_base_patch4_window7_224] INFO: Epoch: [265] [1150/1251] eta: 0:01:04 lr: 0.000041 loss: 2.7000 (2.6947) grad_norm: 3.2628 (3.3284) time: 0.6291 [2021-03-28 11:28:03 swin_base_patch4_window7_224] INFO: Epoch: [265] [1160/1251] eta: 0:00:57 lr: 0.000041 loss: 2.6663 (2.6956) grad_norm: 3.1447 (3.3342) time: 0.6251 [2021-03-28 11:28:10 swin_base_patch4_window7_224] INFO: Epoch: [265] [1170/1251] eta: 0:00:51 lr: 0.000041 loss: 2.8080 (2.6946) grad_norm: 3.1447 (3.3336) time: 0.6295 [2021-03-28 11:28:16 swin_base_patch4_window7_224] INFO: Epoch: [265] [1180/1251] eta: 0:00:45 lr: 0.000041 loss: 2.8080 (2.6951) grad_norm: 3.0417 (3.3343) time: 0.6331 [2021-03-28 11:28:22 swin_base_patch4_window7_224] INFO: Epoch: [265] [1190/1251] eta: 0:00:38 lr: 0.000041 loss: 2.8350 (2.6962) grad_norm: 3.0414 (3.3332) time: 0.6337 [2021-03-28 11:28:29 swin_base_patch4_window7_224] INFO: Epoch: [265] [1200/1251] eta: 0:00:32 lr: 0.000041 loss: 2.9105 (2.6977) grad_norm: 3.0154 (3.3321) time: 0.6350 [2021-03-28 11:28:35 swin_base_patch4_window7_224] INFO: Epoch: [265] [1210/1251] eta: 0:00:26 lr: 0.000041 loss: 2.8667 (2.6971) grad_norm: 3.1221 (3.3316) time: 0.6329 [2021-03-28 11:28:41 swin_base_patch4_window7_224] INFO: Epoch: [265] [1220/1251] eta: 0:00:19 lr: 0.000041 loss: 2.7561 (2.6972) grad_norm: 3.3547 (3.3333) time: 0.6343 [2021-03-28 11:28:47 swin_base_patch4_window7_224] INFO: Epoch: [265] [1230/1251] eta: 0:00:13 lr: 0.000041 loss: 2.8378 (2.6982) grad_norm: 3.3603 (3.3327) time: 0.6291 [2021-03-28 11:28:54 swin_base_patch4_window7_224] INFO: Epoch: [265] [1240/1251] eta: 0:00:06 lr: 0.000041 loss: 2.7683 (2.6977) grad_norm: 3.0975 (3.3329) time: 0.6237 [2021-03-28 11:29:00 swin_base_patch4_window7_224] INFO: Epoch: [265] [1250/1251] eta: 0:00:00 lr: 0.000041 loss: 2.6613 (2.6975) grad_norm: 3.0518 (3.3322) time: 0.6299 [2021-03-28 11:30:18 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 1.2434 (1.2434) acc1: 76.5625 (76.5625) acc5: 92.1875 (92.1875) [2021-03-28 11:30:20 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7199 (0.7676) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.5909) [2021-03-28 11:30:21 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.6972 (0.7543) acc1: 81.2500 (82.1429) acc5: 96.8750 (96.6518) [2021-03-28 11:30:23 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7036 (0.7789) acc1: 81.2500 (81.7036) acc5: 96.8750 (96.2198) [2021-03-28 11:30:24 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7355 (0.7579) acc1: 82.8125 (82.2027) acc5: 96.8750 (96.3034) [2021-03-28 11:30:25 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7172 (0.7526) acc1: 84.3750 (82.5920) acc5: 96.8750 (96.3840) [2021-03-28 11:30:38 swin_base_patch4_window7_224] INFO: * Acc@1 83.234 Acc@5 96.362 loss 0.743 [2021-03-28 11:30:38 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.2% [2021-03-28 11:30:38 swin_base_patch4_window7_224] INFO: Max accuracy: 83.27% [2021-03-28 11:30:42 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 0/1251] eta: 1:26:28 lr: 0.000041 loss: 3.0294 (3.0294) grad_norm: 3.3728 (3.3728) time: 4.1478 [2021-03-28 11:30:49 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 10/1251] eta: 0:19:43 lr: 0.000041 loss: 2.9231 (2.8911) grad_norm: 3.1416 (3.6930) time: 0.9537 [2021-03-28 11:30:55 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 20/1251] eta: 0:16:29 lr: 0.000041 loss: 2.9022 (2.8852) grad_norm: 3.1416 (3.5784) time: 0.6367 [2021-03-28 11:31:01 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 30/1251] eta: 0:15:11 lr: 0.000041 loss: 2.8449 (2.7761) grad_norm: 3.2587 (3.5488) time: 0.6330 [2021-03-28 11:31:08 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 40/1251] eta: 0:14:29 lr: 0.000041 loss: 2.5818 (2.7285) grad_norm: 3.2438 (3.4641) time: 0.6270 [2021-03-28 11:31:14 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 50/1251] eta: 0:14:02 lr: 0.000041 loss: 2.7748 (2.7578) grad_norm: 3.1599 (3.4075) time: 0.6315 [2021-03-28 11:31:20 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 60/1251] eta: 0:13:41 lr: 0.000041 loss: 2.9388 (2.7763) grad_norm: 3.1143 (3.3837) time: 0.6327 [2021-03-28 11:31:27 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 70/1251] eta: 0:13:24 lr: 0.000041 loss: 2.7269 (2.7233) grad_norm: 3.1143 (3.3486) time: 0.6288 [2021-03-28 11:31:33 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 80/1251] eta: 0:13:10 lr: 0.000041 loss: 2.4989 (2.7117) grad_norm: 3.3187 (3.4394) time: 0.6308 [2021-03-28 11:31:39 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 90/1251] eta: 0:12:58 lr: 0.000041 loss: 2.6535 (2.7143) grad_norm: 3.4817 (3.4585) time: 0.6318 [2021-03-28 11:31:46 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 100/1251] eta: 0:12:46 lr: 0.000041 loss: 2.8393 (2.7145) grad_norm: 3.3389 (3.4761) time: 0.6288 [2021-03-28 11:31:52 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 110/1251] eta: 0:12:36 lr: 0.000041 loss: 2.8272 (2.7078) grad_norm: 3.3389 (3.4785) time: 0.6281 [2021-03-28 11:31:58 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 120/1251] eta: 0:12:27 lr: 0.000041 loss: 2.7914 (2.7199) grad_norm: 3.3201 (3.4939) time: 0.6344 [2021-03-28 11:32:05 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 130/1251] eta: 0:12:19 lr: 0.000041 loss: 2.7271 (2.7112) grad_norm: 3.3217 (3.4854) time: 0.6439 [2021-03-28 11:32:11 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 140/1251] eta: 0:12:11 lr: 0.000041 loss: 2.8488 (2.7194) grad_norm: 3.1285 (3.4586) time: 0.6447 [2021-03-28 11:32:18 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 150/1251] eta: 0:12:03 lr: 0.000041 loss: 2.9168 (2.7340) grad_norm: 3.0314 (3.4445) time: 0.6379 [2021-03-28 11:32:24 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 160/1251] eta: 0:11:54 lr: 0.000041 loss: 2.9168 (2.7369) grad_norm: 3.1266 (3.4426) time: 0.6329 [2021-03-28 11:32:30 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 170/1251] eta: 0:11:47 lr: 0.000041 loss: 2.7907 (2.7370) grad_norm: 3.0269 (3.4162) time: 0.6326 [2021-03-28 11:32:36 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 180/1251] eta: 0:11:39 lr: 0.000041 loss: 2.6843 (2.7324) grad_norm: 3.0269 (3.4261) time: 0.6334 [2021-03-28 11:32:43 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 190/1251] eta: 0:11:31 lr: 0.000041 loss: 2.6843 (2.7372) grad_norm: 3.2231 (3.4404) time: 0.6316 [2021-03-28 11:32:49 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 200/1251] eta: 0:11:23 lr: 0.000041 loss: 2.6790 (2.7324) grad_norm: 3.2231 (3.4675) time: 0.6290 [2021-03-28 11:32:55 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 210/1251] eta: 0:11:16 lr: 0.000041 loss: 2.5906 (2.7230) grad_norm: 3.4915 (3.4792) time: 0.6277 [2021-03-28 11:33:02 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 220/1251] eta: 0:11:08 lr: 0.000041 loss: 2.7970 (2.7281) grad_norm: 3.2800 (3.4844) time: 0.6307 [2021-03-28 11:33:08 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 230/1251] eta: 0:11:01 lr: 0.000041 loss: 2.7970 (2.7261) grad_norm: 2.9248 (3.4746) time: 0.6304 [2021-03-28 11:33:14 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 240/1251] eta: 0:10:54 lr: 0.000041 loss: 2.8819 (2.7331) grad_norm: 3.1843 (3.4749) time: 0.6278 [2021-03-28 11:33:21 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 250/1251] eta: 0:10:47 lr: 0.000041 loss: 2.9107 (2.7397) grad_norm: 3.1843 (3.4600) time: 0.6322 [2021-03-28 11:33:27 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 260/1251] eta: 0:10:40 lr: 0.000041 loss: 2.8846 (2.7420) grad_norm: 3.0061 (3.4420) time: 0.6324 [2021-03-28 11:33:33 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 270/1251] eta: 0:10:33 lr: 0.000041 loss: 2.8024 (2.7502) grad_norm: 3.0108 (3.4295) time: 0.6298 [2021-03-28 11:33:40 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 280/1251] eta: 0:10:26 lr: 0.000041 loss: 2.7868 (2.7400) grad_norm: 3.0772 (3.4203) time: 0.6306 [2021-03-28 11:33:46 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 290/1251] eta: 0:10:19 lr: 0.000041 loss: 2.7693 (2.7407) grad_norm: 2.9763 (3.4070) time: 0.6306 [2021-03-28 11:33:52 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 300/1251] eta: 0:10:11 lr: 0.000041 loss: 2.4593 (2.7280) grad_norm: 3.2848 (3.4129) time: 0.6257 [2021-03-28 11:33:58 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 310/1251] eta: 0:10:05 lr: 0.000041 loss: 2.4593 (2.7298) grad_norm: 3.2848 (3.4016) time: 0.6270 [2021-03-28 11:34:05 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 320/1251] eta: 0:09:58 lr: 0.000041 loss: 2.9819 (2.7357) grad_norm: 3.2330 (3.4106) time: 0.6314 [2021-03-28 11:34:11 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 330/1251] eta: 0:09:51 lr: 0.000041 loss: 2.8418 (2.7343) grad_norm: 3.5102 (3.4114) time: 0.6300 [2021-03-28 11:34:17 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 340/1251] eta: 0:09:44 lr: 0.000041 loss: 2.6993 (2.7347) grad_norm: 3.0914 (3.4064) time: 0.6285 [2021-03-28 11:34:24 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 350/1251] eta: 0:09:38 lr: 0.000041 loss: 2.6993 (2.7310) grad_norm: 3.0913 (3.4054) time: 0.6283 [2021-03-28 11:34:30 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 360/1251] eta: 0:09:31 lr: 0.000041 loss: 2.7644 (2.7320) grad_norm: 3.0877 (3.3936) time: 0.6276 [2021-03-28 11:34:36 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 370/1251] eta: 0:09:24 lr: 0.000041 loss: 2.8137 (2.7263) grad_norm: 3.1080 (3.3882) time: 0.6255 [2021-03-28 11:34:42 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 380/1251] eta: 0:09:17 lr: 0.000040 loss: 2.8184 (2.7325) grad_norm: 2.9960 (3.3788) time: 0.6273 [2021-03-28 11:34:49 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 390/1251] eta: 0:09:11 lr: 0.000040 loss: 2.9073 (2.7343) grad_norm: 2.9253 (3.3729) time: 0.6265 [2021-03-28 11:34:55 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 400/1251] eta: 0:09:04 lr: 0.000040 loss: 2.8464 (2.7344) grad_norm: 3.0239 (3.3687) time: 0.6250 [2021-03-28 11:35:01 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 410/1251] eta: 0:08:58 lr: 0.000040 loss: 2.7710 (2.7343) grad_norm: 3.2375 (3.3745) time: 0.6348 [2021-03-28 11:35:08 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 420/1251] eta: 0:08:51 lr: 0.000040 loss: 2.7331 (2.7337) grad_norm: 3.2002 (3.3688) time: 0.6346 [2021-03-28 11:35:14 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 430/1251] eta: 0:08:44 lr: 0.000040 loss: 2.7878 (2.7337) grad_norm: 3.0200 (3.3688) time: 0.6283 [2021-03-28 11:35:20 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 440/1251] eta: 0:08:38 lr: 0.000040 loss: 2.9269 (2.7384) grad_norm: 3.0905 (3.3655) time: 0.6319 [2021-03-28 11:35:27 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 450/1251] eta: 0:08:31 lr: 0.000040 loss: 2.9244 (2.7401) grad_norm: 3.2769 (3.3638) time: 0.6345 [2021-03-28 11:35:33 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 460/1251] eta: 0:08:25 lr: 0.000040 loss: 2.8231 (2.7361) grad_norm: 3.3864 (3.3638) time: 0.6355 [2021-03-28 11:35:39 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 470/1251] eta: 0:08:18 lr: 0.000040 loss: 2.6544 (2.7307) grad_norm: 3.3864 (3.3693) time: 0.6357 [2021-03-28 11:35:46 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 480/1251] eta: 0:08:12 lr: 0.000040 loss: 2.6433 (2.7269) grad_norm: 3.0349 (3.3666) time: 0.6343 [2021-03-28 11:35:52 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 490/1251] eta: 0:08:05 lr: 0.000040 loss: 2.1931 (2.7171) grad_norm: 3.0193 (3.3632) time: 0.6270 [2021-03-28 11:35:58 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 500/1251] eta: 0:07:59 lr: 0.000040 loss: 2.3149 (2.7164) grad_norm: 2.8002 (3.3563) time: 0.6234 [2021-03-28 11:36:04 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 510/1251] eta: 0:07:52 lr: 0.000040 loss: 2.6934 (2.7123) grad_norm: 3.0149 (3.3582) time: 0.6321 [2021-03-28 11:36:11 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 520/1251] eta: 0:07:46 lr: 0.000040 loss: 2.7216 (2.7125) grad_norm: 3.0859 (3.3566) time: 0.6353 [2021-03-28 11:36:17 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 530/1251] eta: 0:07:39 lr: 0.000040 loss: 2.7103 (2.7095) grad_norm: 3.0859 (3.3530) time: 0.6267 [2021-03-28 11:36:23 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 540/1251] eta: 0:07:33 lr: 0.000040 loss: 2.6552 (2.7085) grad_norm: 3.2838 (3.3566) time: 0.6275 [2021-03-28 11:36:30 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 550/1251] eta: 0:07:27 lr: 0.000040 loss: 2.5523 (2.7073) grad_norm: 3.1375 (3.3482) time: 0.6413 [2021-03-28 11:36:36 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 560/1251] eta: 0:07:20 lr: 0.000040 loss: 2.5112 (2.7038) grad_norm: 2.9018 (3.3540) time: 0.6406 [2021-03-28 11:36:42 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 570/1251] eta: 0:07:14 lr: 0.000040 loss: 2.4961 (2.7031) grad_norm: 3.4250 (3.3576) time: 0.6280 [2021-03-28 11:36:49 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 580/1251] eta: 0:07:07 lr: 0.000040 loss: 2.9045 (2.7050) grad_norm: 3.3535 (3.3701) time: 0.6247 [2021-03-28 11:36:55 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 590/1251] eta: 0:07:01 lr: 0.000040 loss: 2.7896 (2.7021) grad_norm: 3.1039 (3.3659) time: 0.6249 [2021-03-28 11:37:01 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 600/1251] eta: 0:06:54 lr: 0.000040 loss: 2.6721 (2.6995) grad_norm: 3.1768 (3.3710) time: 0.6246 [2021-03-28 11:37:07 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 610/1251] eta: 0:06:48 lr: 0.000040 loss: 2.7902 (2.7010) grad_norm: 3.2302 (3.3751) time: 0.6275 [2021-03-28 11:37:14 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 620/1251] eta: 0:06:41 lr: 0.000040 loss: 2.6022 (2.6958) grad_norm: 3.2634 (3.3761) time: 0.6325 [2021-03-28 11:37:20 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 630/1251] eta: 0:06:35 lr: 0.000040 loss: 2.6194 (2.6963) grad_norm: 3.2634 (3.3765) time: 0.6324 [2021-03-28 11:37:26 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 640/1251] eta: 0:06:28 lr: 0.000040 loss: 2.7823 (2.6942) grad_norm: 3.1540 (3.3754) time: 0.6308 [2021-03-28 11:37:33 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 650/1251] eta: 0:06:22 lr: 0.000040 loss: 2.7336 (2.6935) grad_norm: 3.0964 (3.3711) time: 0.6314 [2021-03-28 11:37:39 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 660/1251] eta: 0:06:16 lr: 0.000040 loss: 2.6478 (2.6889) grad_norm: 3.1056 (3.3685) time: 0.6285 [2021-03-28 11:37:45 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 670/1251] eta: 0:06:09 lr: 0.000040 loss: 2.8040 (2.6937) grad_norm: 3.2572 (3.3720) time: 0.6288 [2021-03-28 11:37:52 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 680/1251] eta: 0:06:03 lr: 0.000040 loss: 2.8421 (2.6940) grad_norm: 3.4085 (3.3779) time: 0.6297 [2021-03-28 11:37:58 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 690/1251] eta: 0:05:56 lr: 0.000040 loss: 2.8421 (2.6927) grad_norm: 3.4085 (3.3969) time: 0.6328 [2021-03-28 11:38:04 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 700/1251] eta: 0:05:50 lr: 0.000040 loss: 2.6816 (2.6901) grad_norm: 3.2177 (3.4008) time: 0.6340 [2021-03-28 11:38:11 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 710/1251] eta: 0:05:44 lr: 0.000040 loss: 2.7200 (2.6944) grad_norm: 3.1397 (3.3955) time: 0.6279 [2021-03-28 11:38:17 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 720/1251] eta: 0:05:37 lr: 0.000040 loss: 2.7200 (2.6903) grad_norm: 2.8857 (3.3919) time: 0.6308 [2021-03-28 11:38:23 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 730/1251] eta: 0:05:31 lr: 0.000040 loss: 2.4369 (2.6893) grad_norm: 2.9646 (3.3890) time: 0.6325 [2021-03-28 11:38:30 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 740/1251] eta: 0:05:24 lr: 0.000040 loss: 2.7214 (2.6897) grad_norm: 3.0611 (3.3872) time: 0.6393 [2021-03-28 11:38:36 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 750/1251] eta: 0:05:18 lr: 0.000040 loss: 2.7518 (2.6914) grad_norm: 2.9962 (3.3845) time: 0.6409 [2021-03-28 11:38:42 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 760/1251] eta: 0:05:12 lr: 0.000040 loss: 2.8686 (2.6923) grad_norm: 2.9231 (3.3874) time: 0.6287 [2021-03-28 11:38:49 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 770/1251] eta: 0:05:05 lr: 0.000040 loss: 2.5752 (2.6895) grad_norm: 3.1464 (3.3911) time: 0.6308 [2021-03-28 11:38:55 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 780/1251] eta: 0:04:59 lr: 0.000040 loss: 2.5499 (2.6867) grad_norm: 3.1464 (3.3891) time: 0.6334 [2021-03-28 11:39:01 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 790/1251] eta: 0:04:53 lr: 0.000040 loss: 2.6853 (2.6874) grad_norm: 2.9376 (3.3845) time: 0.6287 [2021-03-28 11:39:08 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 800/1251] eta: 0:04:46 lr: 0.000040 loss: 2.6853 (2.6853) grad_norm: 3.0400 (3.3822) time: 0.6313 [2021-03-28 11:39:14 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 810/1251] eta: 0:04:40 lr: 0.000040 loss: 2.7435 (2.6851) grad_norm: 3.1102 (3.3821) time: 0.6293 [2021-03-28 11:39:20 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 820/1251] eta: 0:04:33 lr: 0.000040 loss: 2.6761 (2.6838) grad_norm: 3.1239 (3.3843) time: 0.6276 [2021-03-28 11:39:26 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 830/1251] eta: 0:04:27 lr: 0.000040 loss: 2.6761 (2.6856) grad_norm: 3.2493 (3.3848) time: 0.6283 [2021-03-28 11:39:33 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 840/1251] eta: 0:04:21 lr: 0.000040 loss: 2.8989 (2.6879) grad_norm: 3.2979 (3.3826) time: 0.6274 [2021-03-28 11:39:39 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 850/1251] eta: 0:04:14 lr: 0.000040 loss: 2.9202 (2.6890) grad_norm: 3.0682 (3.3792) time: 0.6273 [2021-03-28 11:39:45 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 860/1251] eta: 0:04:08 lr: 0.000040 loss: 2.8178 (2.6890) grad_norm: 2.8875 (3.3783) time: 0.6283 [2021-03-28 11:39:52 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 870/1251] eta: 0:04:01 lr: 0.000040 loss: 2.7635 (2.6896) grad_norm: 3.0249 (3.3775) time: 0.6365 [2021-03-28 11:39:58 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 880/1251] eta: 0:03:55 lr: 0.000040 loss: 2.9215 (2.6903) grad_norm: 3.1177 (3.3754) time: 0.6393 [2021-03-28 11:40:04 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 890/1251] eta: 0:03:49 lr: 0.000040 loss: 2.9250 (2.6920) grad_norm: 3.1602 (3.3740) time: 0.6344 [2021-03-28 11:40:11 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 900/1251] eta: 0:03:42 lr: 0.000040 loss: 2.9329 (2.6939) grad_norm: 3.1787 (3.3721) time: 0.6306 [2021-03-28 11:40:17 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 910/1251] eta: 0:03:36 lr: 0.000040 loss: 2.8965 (2.6958) grad_norm: 3.1955 (3.3713) time: 0.6260 [2021-03-28 11:40:23 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 920/1251] eta: 0:03:30 lr: 0.000040 loss: 2.8459 (2.6958) grad_norm: 3.1955 (3.3740) time: 0.6243 [2021-03-28 11:40:29 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 930/1251] eta: 0:03:23 lr: 0.000040 loss: 2.7784 (2.6970) grad_norm: 3.3062 (3.3727) time: 0.6261 [2021-03-28 11:40:36 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 940/1251] eta: 0:03:17 lr: 0.000040 loss: 2.8100 (2.6980) grad_norm: 3.3221 (3.3929) time: 0.6244 [2021-03-28 11:40:42 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 950/1251] eta: 0:03:10 lr: 0.000040 loss: 2.7545 (2.6973) grad_norm: 3.2980 (3.3977) time: 0.6251 [2021-03-28 11:40:48 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 960/1251] eta: 0:03:04 lr: 0.000040 loss: 2.7951 (2.6983) grad_norm: 3.1629 (3.3980) time: 0.6283 [2021-03-28 11:40:54 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 970/1251] eta: 0:02:58 lr: 0.000040 loss: 2.7984 (2.6989) grad_norm: 3.1023 (3.3965) time: 0.6300 [2021-03-28 11:41:01 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 980/1251] eta: 0:02:51 lr: 0.000040 loss: 2.6535 (2.6967) grad_norm: 3.0903 (3.3930) time: 0.6282 [2021-03-28 11:41:07 swin_base_patch4_window7_224] INFO: Epoch: [266] [ 990/1251] eta: 0:02:45 lr: 0.000040 loss: 2.6380 (2.6961) grad_norm: 3.0968 (3.3949) time: 0.6249 [2021-03-28 11:41:13 swin_base_patch4_window7_224] INFO: Epoch: [266] [1000/1251] eta: 0:02:39 lr: 0.000040 loss: 2.6586 (2.6946) grad_norm: 3.2886 (3.3944) time: 0.6280 [2021-03-28 11:41:20 swin_base_patch4_window7_224] INFO: Epoch: [266] [1010/1251] eta: 0:02:32 lr: 0.000040 loss: 2.5794 (2.6941) grad_norm: 2.9434 (3.3899) time: 0.6273 [2021-03-28 11:41:26 swin_base_patch4_window7_224] INFO: Epoch: [266] [1020/1251] eta: 0:02:26 lr: 0.000040 loss: 2.6314 (2.6934) grad_norm: 2.8434 (3.3862) time: 0.6228 [2021-03-28 11:41:32 swin_base_patch4_window7_224] INFO: Epoch: [266] [1030/1251] eta: 0:02:20 lr: 0.000040 loss: 2.5960 (2.6918) grad_norm: 2.7709 (3.3834) time: 0.6296 [2021-03-28 11:41:38 swin_base_patch4_window7_224] INFO: Epoch: [266] [1040/1251] eta: 0:02:13 lr: 0.000040 loss: 2.6488 (2.6934) grad_norm: 3.0851 (3.3823) time: 0.6337 [2021-03-28 11:41:45 swin_base_patch4_window7_224] INFO: Epoch: [266] [1050/1251] eta: 0:02:07 lr: 0.000040 loss: 2.8253 (2.6944) grad_norm: 3.1629 (3.3815) time: 0.6299 [2021-03-28 11:41:51 swin_base_patch4_window7_224] INFO: Epoch: [266] [1060/1251] eta: 0:02:01 lr: 0.000040 loss: 2.8253 (2.6965) grad_norm: 3.1791 (3.3829) time: 0.6293 [2021-03-28 11:41:57 swin_base_patch4_window7_224] INFO: Epoch: [266] [1070/1251] eta: 0:01:54 lr: 0.000040 loss: 2.8549 (2.6968) grad_norm: 3.3215 (3.3829) time: 0.6330 [2021-03-28 11:42:04 swin_base_patch4_window7_224] INFO: Epoch: [266] [1080/1251] eta: 0:01:48 lr: 0.000040 loss: 2.8494 (2.6983) grad_norm: 3.3215 (3.3826) time: 0.6357 [2021-03-28 11:42:10 swin_base_patch4_window7_224] INFO: Epoch: [266] [1090/1251] eta: 0:01:42 lr: 0.000039 loss: 2.7471 (2.6973) grad_norm: 3.2476 (3.3830) time: 0.6318 [2021-03-28 11:42:16 swin_base_patch4_window7_224] INFO: Epoch: [266] [1100/1251] eta: 0:01:35 lr: 0.000039 loss: 2.7152 (2.6967) grad_norm: 3.1857 (3.3801) time: 0.6272 [2021-03-28 11:42:22 swin_base_patch4_window7_224] INFO: Epoch: [266] [1110/1251] eta: 0:01:29 lr: 0.000039 loss: 2.7280 (2.6978) grad_norm: 3.1737 (3.3888) time: 0.6226 [2021-03-28 11:42:29 swin_base_patch4_window7_224] INFO: Epoch: [266] [1120/1251] eta: 0:01:23 lr: 0.000039 loss: 2.7336 (2.6984) grad_norm: 3.3144 (3.3911) time: 0.6251 [2021-03-28 11:42:35 swin_base_patch4_window7_224] INFO: Epoch: [266] [1130/1251] eta: 0:01:16 lr: 0.000039 loss: 2.7039 (2.6975) grad_norm: 3.1591 (3.3896) time: 0.6286 [2021-03-28 11:42:41 swin_base_patch4_window7_224] INFO: Epoch: [266] [1140/1251] eta: 0:01:10 lr: 0.000039 loss: 2.7377 (2.6976) grad_norm: 3.3608 (3.3904) time: 0.6288 [2021-03-28 11:42:48 swin_base_patch4_window7_224] INFO: Epoch: [266] [1150/1251] eta: 0:01:03 lr: 0.000039 loss: 2.7741 (2.6982) grad_norm: 3.4325 (3.3906) time: 0.6331 [2021-03-28 11:42:54 swin_base_patch4_window7_224] INFO: Epoch: [266] [1160/1251] eta: 0:00:57 lr: 0.000039 loss: 2.7747 (2.6984) grad_norm: 3.0976 (3.3878) time: 0.6322 [2021-03-28 11:43:00 swin_base_patch4_window7_224] INFO: Epoch: [266] [1170/1251] eta: 0:00:51 lr: 0.000039 loss: 2.8163 (2.6991) grad_norm: 3.0976 (3.3874) time: 0.6315 [2021-03-28 11:43:07 swin_base_patch4_window7_224] INFO: Epoch: [266] [1180/1251] eta: 0:00:44 lr: 0.000039 loss: 2.6315 (2.6977) grad_norm: 3.0970 (3.3845) time: 0.6321 [2021-03-28 11:43:13 swin_base_patch4_window7_224] INFO: Epoch: [266] [1190/1251] eta: 0:00:38 lr: 0.000039 loss: 2.8873 (2.7004) grad_norm: 3.0141 (3.3821) time: 0.6315 [2021-03-28 11:43:19 swin_base_patch4_window7_224] INFO: Epoch: [266] [1200/1251] eta: 0:00:32 lr: 0.000039 loss: 2.9444 (2.7016) grad_norm: 2.9904 (3.3790) time: 0.6306 [2021-03-28 11:43:26 swin_base_patch4_window7_224] INFO: Epoch: [266] [1210/1251] eta: 0:00:25 lr: 0.000039 loss: 2.9219 (2.7035) grad_norm: 3.0180 (3.3785) time: 0.6264 [2021-03-28 11:43:32 swin_base_patch4_window7_224] INFO: Epoch: [266] [1220/1251] eta: 0:00:19 lr: 0.000039 loss: 2.8069 (2.7019) grad_norm: 3.1724 (3.3789) time: 0.6251 [2021-03-28 11:43:38 swin_base_patch4_window7_224] INFO: Epoch: [266] [1230/1251] eta: 0:00:13 lr: 0.000039 loss: 2.6826 (2.7020) grad_norm: 3.0460 (3.3782) time: 0.6282 [2021-03-28 11:43:44 swin_base_patch4_window7_224] INFO: Epoch: [266] [1240/1251] eta: 0:00:06 lr: 0.000039 loss: 2.7819 (2.7010) grad_norm: 3.0460 (3.3784) time: 0.6290 [2021-03-28 11:43:51 swin_base_patch4_window7_224] INFO: Epoch: [266] [1250/1251] eta: 0:00:00 lr: 0.000039 loss: 2.6507 (2.7003) grad_norm: 3.1609 (3.3766) time: 0.6200 [2021-03-28 11:44:03 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:34 loss: 0.9693 (0.9693) acc1: 76.5625 (76.5625) acc5: 95.3125 (95.3125) [2021-03-28 11:44:06 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8330 (0.7814) acc1: 79.6875 (80.9659) acc5: 95.3125 (96.0227) [2021-03-28 11:44:08 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7317 (0.7755) acc1: 81.2500 (81.9196) acc5: 95.3125 (95.7589) [2021-03-28 11:44:10 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7151 (0.7528) acc1: 82.8125 (82.3085) acc5: 96.8750 (96.5726) [2021-03-28 11:44:12 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6937 (0.7635) acc1: 84.3750 (82.2409) acc5: 96.8750 (96.3796) [2021-03-28 11:44:13 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7252 (0.7543) acc1: 84.3750 (82.4000) acc5: 96.2264 (96.3520) [2021-03-28 11:44:30 swin_base_patch4_window7_224] INFO: * Acc@1 83.212 Acc@5 96.370 loss 0.741 [2021-03-28 11:44:30 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.2% [2021-03-28 11:44:30 swin_base_patch4_window7_224] INFO: Max accuracy: 83.27% [2021-03-28 11:44:34 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 0/1251] eta: 1:29:09 lr: 0.000039 loss: 2.8973 (2.8973) grad_norm: 3.1514 (3.1514) time: 4.2763 [2021-03-28 11:44:40 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 10/1251] eta: 0:19:48 lr: 0.000039 loss: 2.8973 (2.6865) grad_norm: 3.0393 (3.1319) time: 0.9576 [2021-03-28 11:44:46 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 20/1251] eta: 0:16:25 lr: 0.000039 loss: 2.7935 (2.7255) grad_norm: 3.0303 (3.1521) time: 0.6268 [2021-03-28 11:44:53 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 30/1251] eta: 0:15:16 lr: 0.000039 loss: 2.7935 (2.7046) grad_norm: 3.0699 (3.1917) time: 0.6364 [2021-03-28 11:44:59 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 40/1251] eta: 0:14:34 lr: 0.000039 loss: 2.6910 (2.6757) grad_norm: 3.1568 (3.3988) time: 0.6395 [2021-03-28 11:45:06 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 50/1251] eta: 0:14:06 lr: 0.000039 loss: 2.7061 (2.6830) grad_norm: 3.3045 (3.4282) time: 0.6333 [2021-03-28 11:45:12 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 60/1251] eta: 0:13:45 lr: 0.000039 loss: 2.7570 (2.7076) grad_norm: 3.2754 (3.3884) time: 0.6330 [2021-03-28 11:45:18 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 70/1251] eta: 0:13:27 lr: 0.000039 loss: 2.7576 (2.6966) grad_norm: 3.4938 (3.4135) time: 0.6309 [2021-03-28 11:45:25 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 80/1251] eta: 0:13:13 lr: 0.000039 loss: 2.7700 (2.7138) grad_norm: 3.6539 (3.4271) time: 0.6316 [2021-03-28 11:45:31 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 90/1251] eta: 0:12:59 lr: 0.000039 loss: 2.7879 (2.7140) grad_norm: 3.2739 (3.4078) time: 0.6293 [2021-03-28 11:45:37 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 100/1251] eta: 0:12:48 lr: 0.000039 loss: 2.9049 (2.7345) grad_norm: 3.0692 (3.3941) time: 0.6265 [2021-03-28 11:45:43 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 110/1251] eta: 0:12:37 lr: 0.000039 loss: 2.8229 (2.7094) grad_norm: 3.2680 (3.4060) time: 0.6292 [2021-03-28 11:45:50 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 120/1251] eta: 0:12:28 lr: 0.000039 loss: 2.4558 (2.7032) grad_norm: 3.4062 (3.4127) time: 0.6342 [2021-03-28 11:45:56 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 130/1251] eta: 0:12:19 lr: 0.000039 loss: 2.7633 (2.7044) grad_norm: 3.6457 (3.4450) time: 0.6379 [2021-03-28 11:46:02 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 140/1251] eta: 0:12:11 lr: 0.000039 loss: 2.8250 (2.7101) grad_norm: 3.6481 (3.4556) time: 0.6350 [2021-03-28 11:46:09 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 150/1251] eta: 0:12:02 lr: 0.000039 loss: 2.8810 (2.7234) grad_norm: 3.2360 (3.4309) time: 0.6312 [2021-03-28 11:46:15 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 160/1251] eta: 0:11:53 lr: 0.000039 loss: 2.7884 (2.7227) grad_norm: 3.0337 (3.4034) time: 0.6275 [2021-03-28 11:46:21 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 170/1251] eta: 0:11:45 lr: 0.000039 loss: 2.7813 (2.7214) grad_norm: 3.1946 (3.4084) time: 0.6266 [2021-03-28 11:46:28 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 180/1251] eta: 0:11:38 lr: 0.000039 loss: 2.7571 (2.7144) grad_norm: 3.2867 (3.4111) time: 0.6322 [2021-03-28 11:46:34 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 190/1251] eta: 0:11:30 lr: 0.000039 loss: 2.8029 (2.7243) grad_norm: 3.1928 (3.3963) time: 0.6349 [2021-03-28 11:46:40 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 200/1251] eta: 0:11:22 lr: 0.000039 loss: 2.8518 (2.7173) grad_norm: 3.1328 (3.4369) time: 0.6297 [2021-03-28 11:46:47 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 210/1251] eta: 0:11:15 lr: 0.000039 loss: 2.6237 (2.7129) grad_norm: 3.5856 (3.4366) time: 0.6266 [2021-03-28 11:46:53 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 220/1251] eta: 0:11:07 lr: 0.000039 loss: 2.8582 (2.7241) grad_norm: 3.0700 (3.4279) time: 0.6285 [2021-03-28 11:46:59 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 230/1251] eta: 0:11:00 lr: 0.000039 loss: 2.9104 (2.7284) grad_norm: 2.8355 (3.4185) time: 0.6293 [2021-03-28 11:47:05 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 240/1251] eta: 0:10:53 lr: 0.000039 loss: 2.8817 (2.7258) grad_norm: 3.1187 (3.4196) time: 0.6266 [2021-03-28 11:47:12 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 250/1251] eta: 0:10:46 lr: 0.000039 loss: 2.8303 (2.7282) grad_norm: 3.1714 (3.4112) time: 0.6289 [2021-03-28 11:47:18 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 260/1251] eta: 0:10:39 lr: 0.000039 loss: 2.7357 (2.7253) grad_norm: 3.0233 (3.4032) time: 0.6366 [2021-03-28 11:47:25 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 270/1251] eta: 0:10:32 lr: 0.000039 loss: 2.7357 (2.7229) grad_norm: 3.0210 (3.3931) time: 0.6396 [2021-03-28 11:47:31 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 280/1251] eta: 0:10:25 lr: 0.000039 loss: 2.9011 (2.7253) grad_norm: 3.0571 (3.3919) time: 0.6327 [2021-03-28 11:47:37 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 290/1251] eta: 0:10:18 lr: 0.000039 loss: 2.6715 (2.7119) grad_norm: 3.2248 (3.3879) time: 0.6287 [2021-03-28 11:47:43 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 300/1251] eta: 0:10:11 lr: 0.000039 loss: 2.6552 (2.7112) grad_norm: 3.2248 (3.3838) time: 0.6309 [2021-03-28 11:47:50 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 310/1251] eta: 0:10:05 lr: 0.000039 loss: 2.7085 (2.7117) grad_norm: 3.2470 (3.3910) time: 0.6290 [2021-03-28 11:47:56 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 320/1251] eta: 0:09:58 lr: 0.000039 loss: 2.6774 (2.7076) grad_norm: 3.0760 (3.3808) time: 0.6256 [2021-03-28 11:48:02 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 330/1251] eta: 0:09:51 lr: 0.000039 loss: 2.6151 (2.7015) grad_norm: 3.0005 (3.3808) time: 0.6263 [2021-03-28 11:48:09 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 340/1251] eta: 0:09:44 lr: 0.000039 loss: 2.6944 (2.7037) grad_norm: 3.1887 (3.3761) time: 0.6293 [2021-03-28 11:48:15 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 350/1251] eta: 0:09:37 lr: 0.000039 loss: 2.7697 (2.7058) grad_norm: 3.1887 (3.3760) time: 0.6287 [2021-03-28 11:48:21 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 360/1251] eta: 0:09:30 lr: 0.000039 loss: 2.6800 (2.6990) grad_norm: 3.0194 (3.3693) time: 0.6236 [2021-03-28 11:48:27 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 370/1251] eta: 0:09:24 lr: 0.000039 loss: 2.6800 (2.6991) grad_norm: 3.0394 (3.3751) time: 0.6228 [2021-03-28 11:48:34 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 380/1251] eta: 0:09:17 lr: 0.000039 loss: 2.6646 (2.6918) grad_norm: 3.6857 (3.3866) time: 0.6342 [2021-03-28 11:48:40 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 390/1251] eta: 0:09:11 lr: 0.000039 loss: 2.5476 (2.6879) grad_norm: 3.4107 (3.3999) time: 0.6371 [2021-03-28 11:48:46 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 400/1251] eta: 0:09:04 lr: 0.000039 loss: 2.6790 (2.6836) grad_norm: 3.2443 (3.3983) time: 0.6262 [2021-03-28 11:48:53 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 410/1251] eta: 0:08:57 lr: 0.000039 loss: 2.6725 (2.6805) grad_norm: 3.2109 (3.3941) time: 0.6291 [2021-03-28 11:48:59 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 420/1251] eta: 0:08:51 lr: 0.000039 loss: 2.7139 (2.6801) grad_norm: 3.2109 (3.4075) time: 0.6374 [2021-03-28 11:49:05 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 430/1251] eta: 0:08:44 lr: 0.000039 loss: 2.8491 (2.6816) grad_norm: 3.3619 (3.4105) time: 0.6329 [2021-03-28 11:49:12 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 440/1251] eta: 0:08:38 lr: 0.000039 loss: 2.7331 (2.6830) grad_norm: 3.0564 (3.4041) time: 0.6302 [2021-03-28 11:49:18 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 450/1251] eta: 0:08:31 lr: 0.000039 loss: 2.7671 (2.6844) grad_norm: 2.9679 (3.4013) time: 0.6345 [2021-03-28 11:49:24 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 460/1251] eta: 0:08:25 lr: 0.000039 loss: 2.7951 (2.6851) grad_norm: 3.1701 (3.4140) time: 0.6327 [2021-03-28 11:49:31 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 470/1251] eta: 0:08:18 lr: 0.000039 loss: 2.7102 (2.6785) grad_norm: 3.2783 (3.4221) time: 0.6302 [2021-03-28 11:49:37 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 480/1251] eta: 0:08:12 lr: 0.000039 loss: 2.7173 (2.6783) grad_norm: 3.4635 (3.4365) time: 0.6257 [2021-03-28 11:49:43 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 490/1251] eta: 0:08:05 lr: 0.000039 loss: 2.6680 (2.6771) grad_norm: 3.4635 (3.4500) time: 0.6263 [2021-03-28 11:49:50 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 500/1251] eta: 0:07:59 lr: 0.000039 loss: 2.6154 (2.6787) grad_norm: 3.2092 (3.4449) time: 0.6390 [2021-03-28 11:49:56 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 510/1251] eta: 0:07:52 lr: 0.000039 loss: 2.7862 (2.6797) grad_norm: 3.2092 (3.4415) time: 0.6381 [2021-03-28 11:50:02 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 520/1251] eta: 0:07:46 lr: 0.000039 loss: 2.8922 (2.6857) grad_norm: 3.4127 (3.4481) time: 0.6286 [2021-03-28 11:50:08 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 530/1251] eta: 0:07:39 lr: 0.000039 loss: 2.8950 (2.6906) grad_norm: 3.3606 (3.4421) time: 0.6262 [2021-03-28 11:50:15 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 540/1251] eta: 0:07:33 lr: 0.000039 loss: 2.7500 (2.6887) grad_norm: 3.3609 (3.4546) time: 0.6315 [2021-03-28 11:50:21 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 550/1251] eta: 0:07:27 lr: 0.000038 loss: 2.7389 (2.6932) grad_norm: 3.4038 (3.4554) time: 0.6385 [2021-03-28 11:50:28 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 560/1251] eta: 0:07:20 lr: 0.000038 loss: 2.8591 (2.6932) grad_norm: 3.1094 (3.4494) time: 0.6386 [2021-03-28 11:50:34 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 570/1251] eta: 0:07:14 lr: 0.000038 loss: 2.8591 (2.6956) grad_norm: 3.1112 (3.4798) time: 0.6369 [2021-03-28 11:50:40 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 580/1251] eta: 0:07:07 lr: 0.000038 loss: 2.7377 (2.6947) grad_norm: 3.5514 (3.4807) time: 0.6376 [2021-03-28 11:50:47 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 590/1251] eta: 0:07:01 lr: 0.000038 loss: 2.8400 (2.6997) grad_norm: 3.3563 (3.4881) time: 0.6331 [2021-03-28 11:50:53 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 600/1251] eta: 0:06:55 lr: 0.000038 loss: 3.0032 (2.7035) grad_norm: 3.3563 (3.4939) time: 0.6337 [2021-03-28 11:50:59 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 610/1251] eta: 0:06:48 lr: 0.000038 loss: 3.0032 (2.7066) grad_norm: 3.0156 (3.4862) time: 0.6400 [2021-03-28 11:51:06 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 620/1251] eta: 0:06:42 lr: 0.000038 loss: 2.7569 (2.7056) grad_norm: 2.9596 (3.4809) time: 0.6321 [2021-03-28 11:51:12 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 630/1251] eta: 0:06:35 lr: 0.000038 loss: 2.7569 (2.7078) grad_norm: 3.2005 (3.4780) time: 0.6241 [2021-03-28 11:51:18 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 640/1251] eta: 0:06:29 lr: 0.000038 loss: 2.7870 (2.7069) grad_norm: 3.2005 (3.4764) time: 0.6271 [2021-03-28 11:51:24 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 650/1251] eta: 0:06:22 lr: 0.000038 loss: 2.5237 (2.7041) grad_norm: 3.2227 (3.4755) time: 0.6287 [2021-03-28 11:51:31 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 660/1251] eta: 0:06:16 lr: 0.000038 loss: 2.6955 (2.7040) grad_norm: 3.4014 (3.4763) time: 0.6297 [2021-03-28 11:51:37 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 670/1251] eta: 0:06:09 lr: 0.000038 loss: 2.7072 (2.7004) grad_norm: 3.2322 (3.4769) time: 0.6295 [2021-03-28 11:51:43 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 680/1251] eta: 0:06:03 lr: 0.000038 loss: 2.6669 (2.7016) grad_norm: 3.1799 (3.4745) time: 0.6287 [2021-03-28 11:51:50 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 690/1251] eta: 0:05:57 lr: 0.000038 loss: 2.9293 (2.7063) grad_norm: 3.0764 (3.4697) time: 0.6311 [2021-03-28 11:51:56 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 700/1251] eta: 0:05:50 lr: 0.000038 loss: 2.8826 (2.7092) grad_norm: 3.0265 (3.4802) time: 0.6283 [2021-03-28 11:52:02 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 710/1251] eta: 0:05:44 lr: 0.000038 loss: 2.7866 (2.7078) grad_norm: 3.1117 (3.4787) time: 0.6322 [2021-03-28 11:52:09 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 720/1251] eta: 0:05:37 lr: 0.000038 loss: 2.5718 (2.7069) grad_norm: 3.1737 (3.4837) time: 0.6361 [2021-03-28 11:52:15 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 730/1251] eta: 0:05:31 lr: 0.000038 loss: 2.6682 (2.7052) grad_norm: 3.3918 (3.4829) time: 0.6338 [2021-03-28 11:52:21 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 740/1251] eta: 0:05:25 lr: 0.000038 loss: 2.6682 (2.7040) grad_norm: 3.2175 (3.4844) time: 0.6344 [2021-03-28 11:52:28 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 750/1251] eta: 0:05:18 lr: 0.000038 loss: 2.7868 (2.7043) grad_norm: 3.1605 (3.4851) time: 0.6349 [2021-03-28 11:52:34 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 760/1251] eta: 0:05:12 lr: 0.000038 loss: 2.8424 (2.7066) grad_norm: 3.3240 (3.4807) time: 0.6364 [2021-03-28 11:52:40 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 770/1251] eta: 0:05:06 lr: 0.000038 loss: 2.7935 (2.7041) grad_norm: 3.1542 (3.4771) time: 0.6356 [2021-03-28 11:52:47 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 780/1251] eta: 0:04:59 lr: 0.000038 loss: 2.7501 (2.7071) grad_norm: 3.1354 (3.4771) time: 0.6338 [2021-03-28 11:52:53 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 790/1251] eta: 0:04:53 lr: 0.000038 loss: 2.8303 (2.7084) grad_norm: 3.2574 (3.4782) time: 0.6301 [2021-03-28 11:52:59 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 800/1251] eta: 0:04:46 lr: 0.000038 loss: 2.8282 (2.7088) grad_norm: 3.3565 (3.4876) time: 0.6291 [2021-03-28 11:53:06 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 810/1251] eta: 0:04:40 lr: 0.000038 loss: 2.8555 (2.7102) grad_norm: 3.1856 (3.4874) time: 0.6301 [2021-03-28 11:53:12 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 820/1251] eta: 0:04:34 lr: 0.000038 loss: 2.8270 (2.7097) grad_norm: 3.4002 (3.4874) time: 0.6320 [2021-03-28 11:53:18 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 830/1251] eta: 0:04:27 lr: 0.000038 loss: 2.8038 (2.7101) grad_norm: 3.1720 (3.4828) time: 0.6288 [2021-03-28 11:53:24 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 840/1251] eta: 0:04:21 lr: 0.000038 loss: 2.8159 (2.7113) grad_norm: 3.0246 (3.4781) time: 0.6236 [2021-03-28 11:53:31 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 850/1251] eta: 0:04:14 lr: 0.000038 loss: 2.9384 (2.7135) grad_norm: 3.0316 (3.4757) time: 0.6271 [2021-03-28 11:53:37 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 860/1251] eta: 0:04:08 lr: 0.000038 loss: 2.9145 (2.7115) grad_norm: 3.1197 (3.4793) time: 0.6298 [2021-03-28 11:53:43 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 870/1251] eta: 0:04:02 lr: 0.000038 loss: 2.7371 (2.7117) grad_norm: 2.9981 (3.4729) time: 0.6314 [2021-03-28 11:53:50 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 880/1251] eta: 0:03:55 lr: 0.000038 loss: 2.8526 (2.7118) grad_norm: 3.0322 (3.4764) time: 0.6322 [2021-03-28 11:53:56 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 890/1251] eta: 0:03:49 lr: 0.000038 loss: 2.8038 (2.7113) grad_norm: 3.1779 (3.4725) time: 0.6279 [2021-03-28 11:54:02 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 900/1251] eta: 0:03:42 lr: 0.000038 loss: 2.7134 (2.7110) grad_norm: 3.1391 (3.4706) time: 0.6233 [2021-03-28 11:54:08 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 910/1251] eta: 0:03:36 lr: 0.000038 loss: 2.7198 (2.7110) grad_norm: 3.3179 (3.4720) time: 0.6289 [2021-03-28 11:54:15 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 920/1251] eta: 0:03:30 lr: 0.000038 loss: 2.7511 (2.7114) grad_norm: 3.3957 (3.4706) time: 0.6286 [2021-03-28 11:54:21 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 930/1251] eta: 0:03:23 lr: 0.000038 loss: 2.8507 (2.7112) grad_norm: 3.2295 (3.4697) time: 0.6298 [2021-03-28 11:54:27 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 940/1251] eta: 0:03:17 lr: 0.000038 loss: 2.5711 (2.7096) grad_norm: 3.2928 (3.4816) time: 0.6349 [2021-03-28 11:54:34 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 950/1251] eta: 0:03:11 lr: 0.000038 loss: 2.7528 (2.7107) grad_norm: 3.3918 (3.4839) time: 0.6305 [2021-03-28 11:54:40 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 960/1251] eta: 0:03:04 lr: 0.000038 loss: 2.8215 (2.7112) grad_norm: 3.2620 (3.4810) time: 0.6269 [2021-03-28 11:54:46 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 970/1251] eta: 0:02:58 lr: 0.000038 loss: 2.9179 (2.7124) grad_norm: 3.1597 (3.4810) time: 0.6321 [2021-03-28 11:54:53 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 980/1251] eta: 0:02:52 lr: 0.000038 loss: 2.7193 (2.7099) grad_norm: 3.2321 (3.4835) time: 0.6324 [2021-03-28 11:54:59 swin_base_patch4_window7_224] INFO: Epoch: [267] [ 990/1251] eta: 0:02:45 lr: 0.000038 loss: 2.6376 (2.7100) grad_norm: 3.2844 (3.4830) time: 0.6260 [2021-03-28 11:55:05 swin_base_patch4_window7_224] INFO: Epoch: [267] [1000/1251] eta: 0:02:39 lr: 0.000038 loss: 2.8769 (2.7116) grad_norm: 3.3731 (3.4882) time: 0.6290 [2021-03-28 11:55:12 swin_base_patch4_window7_224] INFO: Epoch: [267] [1010/1251] eta: 0:02:32 lr: 0.000038 loss: 3.0003 (2.7138) grad_norm: 3.3511 (3.4859) time: 0.6392 [2021-03-28 11:55:18 swin_base_patch4_window7_224] INFO: Epoch: [267] [1020/1251] eta: 0:02:26 lr: 0.000038 loss: 2.9532 (2.7159) grad_norm: 3.1339 (3.4830) time: 0.6385 [2021-03-28 11:55:24 swin_base_patch4_window7_224] INFO: Epoch: [267] [1030/1251] eta: 0:02:20 lr: 0.000038 loss: 2.9712 (2.7174) grad_norm: 3.2058 (3.4821) time: 0.6279 [2021-03-28 11:55:31 swin_base_patch4_window7_224] INFO: Epoch: [267] [1040/1251] eta: 0:02:13 lr: 0.000038 loss: 2.9703 (2.7177) grad_norm: 3.4144 (3.4834) time: 0.6280 [2021-03-28 11:55:37 swin_base_patch4_window7_224] INFO: Epoch: [267] [1050/1251] eta: 0:02:07 lr: 0.000038 loss: 2.8980 (2.7181) grad_norm: 3.1752 (3.4796) time: 0.6287 [2021-03-28 11:55:43 swin_base_patch4_window7_224] INFO: Epoch: [267] [1060/1251] eta: 0:02:01 lr: 0.000038 loss: 2.7144 (2.7174) grad_norm: 2.9732 (3.4766) time: 0.6255 [2021-03-28 11:55:49 swin_base_patch4_window7_224] INFO: Epoch: [267] [1070/1251] eta: 0:01:54 lr: 0.000038 loss: 2.6981 (2.7178) grad_norm: 3.2229 (3.4799) time: 0.6287 [2021-03-28 11:55:56 swin_base_patch4_window7_224] INFO: Epoch: [267] [1080/1251] eta: 0:01:48 lr: 0.000038 loss: 2.6088 (2.7162) grad_norm: 3.3722 (3.4836) time: 0.6307 [2021-03-28 11:56:02 swin_base_patch4_window7_224] INFO: Epoch: [267] [1090/1251] eta: 0:01:42 lr: 0.000038 loss: 2.6082 (2.7157) grad_norm: 3.2830 (3.4814) time: 0.6290 [2021-03-28 11:56:08 swin_base_patch4_window7_224] INFO: Epoch: [267] [1100/1251] eta: 0:01:35 lr: 0.000038 loss: 2.7439 (2.7153) grad_norm: 3.1754 (3.4844) time: 0.6274 [2021-03-28 11:56:14 swin_base_patch4_window7_224] INFO: Epoch: [267] [1110/1251] eta: 0:01:29 lr: 0.000038 loss: 2.6611 (2.7152) grad_norm: 3.1893 (3.4853) time: 0.6272 [2021-03-28 11:56:21 swin_base_patch4_window7_224] INFO: Epoch: [267] [1120/1251] eta: 0:01:23 lr: 0.000038 loss: 2.7712 (2.7144) grad_norm: 3.1984 (3.4836) time: 0.6313 [2021-03-28 11:56:27 swin_base_patch4_window7_224] INFO: Epoch: [267] [1130/1251] eta: 0:01:16 lr: 0.000038 loss: 2.5593 (2.7128) grad_norm: 3.0258 (3.4800) time: 0.6300 [2021-03-28 11:56:33 swin_base_patch4_window7_224] INFO: Epoch: [267] [1140/1251] eta: 0:01:10 lr: 0.000038 loss: 2.5180 (2.7117) grad_norm: 3.0355 (3.4790) time: 0.6293 [2021-03-28 11:56:40 swin_base_patch4_window7_224] INFO: Epoch: [267] [1150/1251] eta: 0:01:04 lr: 0.000038 loss: 2.8189 (2.7121) grad_norm: 3.0431 (3.4758) time: 0.6271 [2021-03-28 11:56:46 swin_base_patch4_window7_224] INFO: Epoch: [267] [1160/1251] eta: 0:00:57 lr: 0.000038 loss: 2.7834 (2.7107) grad_norm: 2.9592 (3.4725) time: 0.6268 [2021-03-28 11:56:52 swin_base_patch4_window7_224] INFO: Epoch: [267] [1170/1251] eta: 0:00:51 lr: 0.000038 loss: 2.6903 (2.7105) grad_norm: 2.9592 (3.4853) time: 0.6360 [2021-03-28 11:56:59 swin_base_patch4_window7_224] INFO: Epoch: [267] [1180/1251] eta: 0:00:45 lr: 0.000038 loss: 2.8443 (2.7111) grad_norm: 3.1948 (3.4886) time: 0.6395 [2021-03-28 11:57:05 swin_base_patch4_window7_224] INFO: Epoch: [267] [1190/1251] eta: 0:00:38 lr: 0.000038 loss: 2.8564 (2.7119) grad_norm: 3.2777 (3.4896) time: 0.6365 [2021-03-28 11:57:11 swin_base_patch4_window7_224] INFO: Epoch: [267] [1200/1251] eta: 0:00:32 lr: 0.000038 loss: 2.9125 (2.7132) grad_norm: 3.2074 (3.4914) time: 0.6361 [2021-03-28 11:57:18 swin_base_patch4_window7_224] INFO: Epoch: [267] [1210/1251] eta: 0:00:25 lr: 0.000038 loss: 2.7924 (2.7108) grad_norm: 3.2720 (3.4910) time: 0.6315 [2021-03-28 11:57:24 swin_base_patch4_window7_224] INFO: Epoch: [267] [1220/1251] eta: 0:00:19 lr: 0.000038 loss: 2.7049 (2.7113) grad_norm: 3.2720 (3.4899) time: 0.6265 [2021-03-28 11:57:30 swin_base_patch4_window7_224] INFO: Epoch: [267] [1230/1251] eta: 0:00:13 lr: 0.000038 loss: 2.9519 (2.7118) grad_norm: 3.3970 (3.4930) time: 0.6260 [2021-03-28 11:57:36 swin_base_patch4_window7_224] INFO: Epoch: [267] [1240/1251] eta: 0:00:06 lr: 0.000038 loss: 2.7372 (2.7106) grad_norm: 3.4112 (3.4922) time: 0.6194 [2021-03-28 11:57:43 swin_base_patch4_window7_224] INFO: Epoch: [267] [1250/1251] eta: 0:00:00 lr: 0.000038 loss: 2.7628 (2.7109) grad_norm: 3.2004 (3.4905) time: 0.6128 [2021-03-28 11:57:52 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:58 loss: 0.8717 (0.8717) acc1: 79.6875 (79.6875) acc5: 92.1875 (92.1875) [2021-03-28 11:57:54 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.7926 (0.8173) acc1: 81.2500 (81.9602) acc5: 95.3125 (95.5966) [2021-03-28 11:57:57 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7207 (0.7711) acc1: 81.2500 (81.9196) acc5: 96.8750 (96.5030) [2021-03-28 11:57:59 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6712 (0.7581) acc1: 82.8125 (82.1069) acc5: 96.8750 (96.4718) [2021-03-28 11:58:01 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6487 (0.7440) acc1: 82.8125 (82.2027) acc5: 96.8750 (96.7607) [2021-03-28 11:58:03 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7255 (0.7661) acc1: 82.8125 (81.9840) acc5: 96.8750 (96.5120) [2021-03-28 11:58:18 swin_base_patch4_window7_224] INFO: * Acc@1 83.178 Acc@5 96.374 loss 0.746 [2021-03-28 11:58:18 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.2% [2021-03-28 11:58:18 swin_base_patch4_window7_224] INFO: Max accuracy: 83.27% [2021-03-28 11:58:22 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 0/1251] eta: 1:30:52 lr: 0.000038 loss: 2.8482 (2.8482) grad_norm: 2.7502 (2.7502) time: 4.3583 [2021-03-28 11:58:28 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 10/1251] eta: 0:20:13 lr: 0.000038 loss: 2.8335 (2.7108) grad_norm: 3.5097 (3.2987) time: 0.9775 [2021-03-28 11:58:35 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 20/1251] eta: 0:16:40 lr: 0.000038 loss: 2.8335 (2.7734) grad_norm: 3.2897 (3.3772) time: 0.6359 [2021-03-28 11:58:41 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 30/1251] eta: 0:15:21 lr: 0.000037 loss: 2.8458 (2.7306) grad_norm: 3.1682 (3.4787) time: 0.6327 [2021-03-28 11:58:47 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 40/1251] eta: 0:14:36 lr: 0.000037 loss: 2.7833 (2.7184) grad_norm: 3.4246 (3.5109) time: 0.6303 [2021-03-28 11:58:54 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 50/1251] eta: 0:14:07 lr: 0.000037 loss: 2.7035 (2.7005) grad_norm: 3.3347 (3.8687) time: 0.6294 [2021-03-28 11:59:00 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 60/1251] eta: 0:13:46 lr: 0.000037 loss: 2.7037 (2.7018) grad_norm: 3.2361 (3.7862) time: 0.6328 [2021-03-28 11:59:06 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 70/1251] eta: 0:13:30 lr: 0.000037 loss: 2.7308 (2.6977) grad_norm: 3.2675 (3.7605) time: 0.6364 [2021-03-28 11:59:13 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 80/1251] eta: 0:13:15 lr: 0.000037 loss: 2.7308 (2.6997) grad_norm: 3.2269 (3.7273) time: 0.6348 [2021-03-28 11:59:19 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 90/1251] eta: 0:13:01 lr: 0.000037 loss: 2.7508 (2.6933) grad_norm: 2.9523 (3.6664) time: 0.6279 [2021-03-28 11:59:25 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 100/1251] eta: 0:12:50 lr: 0.000037 loss: 2.4702 (2.6509) grad_norm: 2.9544 (3.6071) time: 0.6305 [2021-03-28 11:59:32 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 110/1251] eta: 0:12:41 lr: 0.000037 loss: 2.5854 (2.6761) grad_norm: 3.0167 (3.5755) time: 0.6395 [2021-03-28 11:59:38 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 120/1251] eta: 0:12:30 lr: 0.000037 loss: 2.7877 (2.6756) grad_norm: 3.0257 (3.5482) time: 0.6339 [2021-03-28 11:59:44 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 130/1251] eta: 0:12:22 lr: 0.000037 loss: 2.8093 (2.6938) grad_norm: 3.1401 (3.6138) time: 0.6333 [2021-03-28 11:59:51 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 140/1251] eta: 0:12:13 lr: 0.000037 loss: 2.8093 (2.6872) grad_norm: 3.1401 (3.5883) time: 0.6405 [2021-03-28 11:59:57 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 150/1251] eta: 0:12:05 lr: 0.000037 loss: 2.5294 (2.6769) grad_norm: 3.1669 (3.6234) time: 0.6350 [2021-03-28 12:00:03 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 160/1251] eta: 0:11:57 lr: 0.000037 loss: 2.7758 (2.6896) grad_norm: 3.3106 (3.6176) time: 0.6380 [2021-03-28 12:00:10 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 170/1251] eta: 0:11:49 lr: 0.000037 loss: 2.7747 (2.6850) grad_norm: 3.2599 (3.6100) time: 0.6393 [2021-03-28 12:00:16 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 180/1251] eta: 0:11:41 lr: 0.000037 loss: 2.5555 (2.6786) grad_norm: 3.2291 (3.6012) time: 0.6329 [2021-03-28 12:00:22 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 190/1251] eta: 0:11:33 lr: 0.000037 loss: 2.7867 (2.6917) grad_norm: 3.2148 (3.5872) time: 0.6326 [2021-03-28 12:00:29 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 200/1251] eta: 0:11:26 lr: 0.000037 loss: 2.8628 (2.6810) grad_norm: 3.3367 (nan) time: 0.6370 [2021-03-28 12:00:35 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 210/1251] eta: 0:11:18 lr: 0.000037 loss: 2.5474 (2.6811) grad_norm: 3.3282 (nan) time: 0.6324 [2021-03-28 12:00:41 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 220/1251] eta: 0:11:10 lr: 0.000037 loss: 2.6409 (2.6794) grad_norm: 3.2807 (nan) time: 0.6230 [2021-03-28 12:00:48 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 230/1251] eta: 0:11:03 lr: 0.000037 loss: 2.7046 (2.6863) grad_norm: 3.1371 (nan) time: 0.6284 [2021-03-28 12:00:54 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 240/1251] eta: 0:10:56 lr: 0.000037 loss: 2.7947 (2.6850) grad_norm: 3.2091 (nan) time: 0.6354 [2021-03-28 12:01:00 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 250/1251] eta: 0:10:48 lr: 0.000037 loss: 2.5710 (2.6777) grad_norm: 3.3251 (nan) time: 0.6311 [2021-03-28 12:01:07 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 260/1251] eta: 0:10:41 lr: 0.000037 loss: 2.5940 (2.6795) grad_norm: 3.2607 (nan) time: 0.6300 [2021-03-28 12:01:13 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 270/1251] eta: 0:10:34 lr: 0.000037 loss: 2.7542 (2.6781) grad_norm: 3.1335 (nan) time: 0.6307 [2021-03-28 12:01:19 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 280/1251] eta: 0:10:27 lr: 0.000037 loss: 2.8410 (2.6837) grad_norm: 3.2616 (nan) time: 0.6251 [2021-03-28 12:01:26 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 290/1251] eta: 0:10:20 lr: 0.000037 loss: 2.7441 (2.6781) grad_norm: 3.4282 (nan) time: 0.6277 [2021-03-28 12:01:32 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 300/1251] eta: 0:10:13 lr: 0.000037 loss: 2.8515 (2.6857) grad_norm: 3.1131 (nan) time: 0.6355 [2021-03-28 12:01:38 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 310/1251] eta: 0:10:06 lr: 0.000037 loss: 2.7803 (2.6757) grad_norm: 3.2890 (nan) time: 0.6364 [2021-03-28 12:01:45 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 320/1251] eta: 0:10:00 lr: 0.000037 loss: 2.8374 (2.6822) grad_norm: 3.3608 (nan) time: 0.6344 [2021-03-28 12:01:51 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 330/1251] eta: 0:09:53 lr: 0.000037 loss: 2.8934 (2.6861) grad_norm: 3.2613 (nan) time: 0.6289 [2021-03-28 12:01:57 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 340/1251] eta: 0:09:46 lr: 0.000037 loss: 2.8613 (2.6912) grad_norm: 3.1378 (nan) time: 0.6255 [2021-03-28 12:02:03 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 350/1251] eta: 0:09:39 lr: 0.000037 loss: 2.7665 (2.6924) grad_norm: 3.2749 (nan) time: 0.6286 [2021-03-28 12:02:10 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 360/1251] eta: 0:09:32 lr: 0.000037 loss: 2.7563 (2.6867) grad_norm: 3.3184 (nan) time: 0.6308 [2021-03-28 12:02:16 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 370/1251] eta: 0:09:26 lr: 0.000037 loss: 2.8695 (2.6901) grad_norm: 3.3337 (nan) time: 0.6299 [2021-03-28 12:02:22 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 380/1251] eta: 0:09:19 lr: 0.000037 loss: 2.8766 (2.6920) grad_norm: 3.1813 (nan) time: 0.6266 [2021-03-28 12:02:28 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 390/1251] eta: 0:09:12 lr: 0.000037 loss: 2.9004 (2.6968) grad_norm: 3.1577 (nan) time: 0.6244 [2021-03-28 12:02:35 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 400/1251] eta: 0:09:05 lr: 0.000037 loss: 2.9743 (2.7049) grad_norm: 3.0503 (nan) time: 0.6268 [2021-03-28 12:02:41 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 410/1251] eta: 0:08:59 lr: 0.000037 loss: 2.9262 (2.7024) grad_norm: 3.0725 (nan) time: 0.6299 [2021-03-28 12:02:47 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 420/1251] eta: 0:08:52 lr: 0.000037 loss: 2.6683 (2.7036) grad_norm: 3.0426 (nan) time: 0.6294 [2021-03-28 12:02:54 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 430/1251] eta: 0:08:45 lr: 0.000037 loss: 2.7270 (2.7073) grad_norm: 3.0327 (nan) time: 0.6280 [2021-03-28 12:03:00 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 440/1251] eta: 0:08:39 lr: 0.000037 loss: 2.6888 (2.7064) grad_norm: 3.3542 (nan) time: 0.6258 [2021-03-28 12:03:06 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 450/1251] eta: 0:08:32 lr: 0.000037 loss: 2.4361 (2.6962) grad_norm: 3.2095 (nan) time: 0.6257 [2021-03-28 12:03:13 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 460/1251] eta: 0:08:26 lr: 0.000037 loss: 2.4457 (2.6996) grad_norm: 3.0873 (nan) time: 0.6328 [2021-03-28 12:03:19 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 470/1251] eta: 0:08:19 lr: 0.000037 loss: 2.6899 (2.6940) grad_norm: 3.0572 (nan) time: 0.6367 [2021-03-28 12:03:25 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 480/1251] eta: 0:08:13 lr: 0.000037 loss: 2.5718 (2.6912) grad_norm: 3.1651 (nan) time: 0.6392 [2021-03-28 12:03:32 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 490/1251] eta: 0:08:06 lr: 0.000037 loss: 2.8092 (2.6933) grad_norm: 3.3171 (nan) time: 0.6383 [2021-03-28 12:03:38 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 500/1251] eta: 0:08:00 lr: 0.000037 loss: 2.8235 (2.6957) grad_norm: 3.4383 (nan) time: 0.6337 [2021-03-28 12:03:44 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 510/1251] eta: 0:07:53 lr: 0.000037 loss: 2.7365 (2.6956) grad_norm: 3.2651 (nan) time: 0.6343 [2021-03-28 12:03:51 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 520/1251] eta: 0:07:47 lr: 0.000037 loss: 2.7860 (2.6987) grad_norm: 3.2605 (nan) time: 0.6330 [2021-03-28 12:03:57 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 530/1251] eta: 0:07:40 lr: 0.000037 loss: 2.7860 (2.6955) grad_norm: 3.0594 (nan) time: 0.6286 [2021-03-28 12:04:03 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 540/1251] eta: 0:07:34 lr: 0.000037 loss: 2.7126 (2.6985) grad_norm: 2.9640 (nan) time: 0.6301 [2021-03-28 12:04:10 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 550/1251] eta: 0:07:27 lr: 0.000037 loss: 2.8006 (2.6994) grad_norm: 3.2769 (nan) time: 0.6411 [2021-03-28 12:04:16 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 560/1251] eta: 0:07:21 lr: 0.000037 loss: 2.8138 (2.6997) grad_norm: 3.2808 (nan) time: 0.6443 [2021-03-28 12:04:22 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 570/1251] eta: 0:07:15 lr: 0.000037 loss: 2.8354 (2.6993) grad_norm: 3.0769 (nan) time: 0.6333 [2021-03-28 12:04:29 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 580/1251] eta: 0:07:08 lr: 0.000037 loss: 2.7168 (2.6989) grad_norm: 3.1346 (nan) time: 0.6302 [2021-03-28 12:04:35 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 590/1251] eta: 0:07:02 lr: 0.000037 loss: 2.7168 (2.6983) grad_norm: 3.1579 (nan) time: 0.6298 [2021-03-28 12:04:41 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 600/1251] eta: 0:06:55 lr: 0.000037 loss: 2.6774 (2.6955) grad_norm: 3.0507 (nan) time: 0.6267 [2021-03-28 12:04:48 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 610/1251] eta: 0:06:49 lr: 0.000037 loss: 2.6908 (2.6961) grad_norm: 3.1364 (nan) time: 0.6281 [2021-03-28 12:04:54 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 620/1251] eta: 0:06:42 lr: 0.000037 loss: 2.8670 (2.6980) grad_norm: 3.2209 (nan) time: 0.6274 [2021-03-28 12:05:00 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 630/1251] eta: 0:06:36 lr: 0.000037 loss: 2.8642 (2.7003) grad_norm: 2.9486 (nan) time: 0.6363 [2021-03-28 12:05:07 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 640/1251] eta: 0:06:29 lr: 0.000037 loss: 2.9248 (2.7006) grad_norm: 3.0930 (nan) time: 0.6367 [2021-03-28 12:05:13 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 650/1251] eta: 0:06:23 lr: 0.000037 loss: 2.9779 (2.7029) grad_norm: 3.1466 (nan) time: 0.6282 [2021-03-28 12:05:19 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 660/1251] eta: 0:06:16 lr: 0.000037 loss: 2.8582 (2.7028) grad_norm: 3.1146 (nan) time: 0.6255 [2021-03-28 12:05:25 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 670/1251] eta: 0:06:10 lr: 0.000037 loss: 2.8582 (2.7019) grad_norm: 3.1820 (nan) time: 0.6271 [2021-03-28 12:05:32 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 680/1251] eta: 0:06:03 lr: 0.000037 loss: 2.5797 (2.6983) grad_norm: 3.1302 (nan) time: 0.6289 [2021-03-28 12:05:38 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 690/1251] eta: 0:05:57 lr: 0.000037 loss: 2.6186 (2.6984) grad_norm: 3.1186 (nan) time: 0.6317 [2021-03-28 12:05:44 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 700/1251] eta: 0:05:51 lr: 0.000037 loss: 2.8096 (2.6988) grad_norm: 3.2808 (nan) time: 0.6373 [2021-03-28 12:05:51 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 710/1251] eta: 0:05:44 lr: 0.000037 loss: 2.8236 (2.7005) grad_norm: 3.1469 (nan) time: 0.6335 [2021-03-28 12:05:57 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 720/1251] eta: 0:05:38 lr: 0.000037 loss: 2.9121 (2.7028) grad_norm: 3.1093 (nan) time: 0.6320 [2021-03-28 12:06:03 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 730/1251] eta: 0:05:31 lr: 0.000037 loss: 3.0295 (2.7070) grad_norm: 3.3451 (nan) time: 0.6328 [2021-03-28 12:06:10 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 740/1251] eta: 0:05:25 lr: 0.000037 loss: 3.0417 (2.7087) grad_norm: 3.4796 (nan) time: 0.6336 [2021-03-28 12:06:16 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 750/1251] eta: 0:05:19 lr: 0.000037 loss: 2.5869 (2.7080) grad_norm: 3.1830 (nan) time: 0.6334 [2021-03-28 12:06:22 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 760/1251] eta: 0:05:12 lr: 0.000037 loss: 2.5869 (2.7078) grad_norm: 3.1588 (nan) time: 0.6343 [2021-03-28 12:06:29 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 770/1251] eta: 0:05:06 lr: 0.000036 loss: 2.6108 (2.7056) grad_norm: 3.1044 (nan) time: 0.6341 [2021-03-28 12:06:35 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 780/1251] eta: 0:04:59 lr: 0.000036 loss: 2.8435 (2.7081) grad_norm: 3.1044 (nan) time: 0.6335 [2021-03-28 12:06:42 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 790/1251] eta: 0:04:53 lr: 0.000036 loss: 2.8205 (2.7044) grad_norm: 3.0800 (nan) time: 0.6371 [2021-03-28 12:06:48 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 800/1251] eta: 0:04:47 lr: 0.000036 loss: 2.9289 (2.7075) grad_norm: 3.0800 (nan) time: 0.6357 [2021-03-28 12:06:54 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 810/1251] eta: 0:04:40 lr: 0.000036 loss: 2.9608 (2.7083) grad_norm: 3.1845 (nan) time: 0.6317 [2021-03-28 12:07:00 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 820/1251] eta: 0:04:34 lr: 0.000036 loss: 2.8458 (2.7075) grad_norm: 3.2515 (nan) time: 0.6294 [2021-03-28 12:07:07 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 830/1251] eta: 0:04:27 lr: 0.000036 loss: 2.7603 (2.7063) grad_norm: 3.0678 (nan) time: 0.6266 [2021-03-28 12:07:13 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 840/1251] eta: 0:04:21 lr: 0.000036 loss: 2.4645 (2.7024) grad_norm: 3.0051 (nan) time: 0.6262 [2021-03-28 12:07:19 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 850/1251] eta: 0:04:15 lr: 0.000036 loss: 2.6062 (2.7028) grad_norm: 3.0057 (nan) time: 0.6358 [2021-03-28 12:07:26 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 860/1251] eta: 0:04:08 lr: 0.000036 loss: 2.6916 (2.7009) grad_norm: 2.9675 (nan) time: 0.6366 [2021-03-28 12:07:32 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 870/1251] eta: 0:04:02 lr: 0.000036 loss: 2.6056 (2.6993) grad_norm: 3.0118 (nan) time: 0.6284 [2021-03-28 12:07:38 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 880/1251] eta: 0:03:56 lr: 0.000036 loss: 2.7234 (2.6991) grad_norm: 3.0118 (nan) time: 0.6322 [2021-03-28 12:07:45 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 890/1251] eta: 0:03:49 lr: 0.000036 loss: 2.7771 (2.7002) grad_norm: 3.0788 (nan) time: 0.6364 [2021-03-28 12:07:51 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 900/1251] eta: 0:03:43 lr: 0.000036 loss: 2.8058 (2.7005) grad_norm: 3.2634 (nan) time: 0.6380 [2021-03-28 12:07:58 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 910/1251] eta: 0:03:37 lr: 0.000036 loss: 2.7844 (2.6998) grad_norm: 3.0909 (nan) time: 0.6402 [2021-03-28 12:08:04 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 920/1251] eta: 0:03:30 lr: 0.000036 loss: 2.7125 (2.6976) grad_norm: 3.0453 (nan) time: 0.6397 [2021-03-28 12:08:10 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 930/1251] eta: 0:03:24 lr: 0.000036 loss: 2.5159 (2.6958) grad_norm: 3.2205 (nan) time: 0.6356 [2021-03-28 12:08:16 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 940/1251] eta: 0:03:17 lr: 0.000036 loss: 2.5159 (2.6952) grad_norm: 3.1442 (nan) time: 0.6267 [2021-03-28 12:08:23 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 950/1251] eta: 0:03:11 lr: 0.000036 loss: 2.7859 (2.6955) grad_norm: 2.9814 (nan) time: 0.6316 [2021-03-28 12:08:29 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 960/1251] eta: 0:03:05 lr: 0.000036 loss: 2.7965 (2.6959) grad_norm: 3.0283 (nan) time: 0.6329 [2021-03-28 12:08:36 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 970/1251] eta: 0:02:58 lr: 0.000036 loss: 2.7182 (2.6950) grad_norm: 2.9761 (nan) time: 0.6325 [2021-03-28 12:08:42 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 980/1251] eta: 0:02:52 lr: 0.000036 loss: 2.6969 (2.6940) grad_norm: 2.9761 (nan) time: 0.6355 [2021-03-28 12:08:48 swin_base_patch4_window7_224] INFO: Epoch: [268] [ 990/1251] eta: 0:02:46 lr: 0.000036 loss: 2.7171 (2.6933) grad_norm: 3.1729 (nan) time: 0.6304 [2021-03-28 12:08:54 swin_base_patch4_window7_224] INFO: Epoch: [268] [1000/1251] eta: 0:02:39 lr: 0.000036 loss: 2.7495 (2.6931) grad_norm: 3.1026 (nan) time: 0.6272 [2021-03-28 12:09:01 swin_base_patch4_window7_224] INFO: Epoch: [268] [1010/1251] eta: 0:02:33 lr: 0.000036 loss: 2.7495 (2.6928) grad_norm: 3.3790 (nan) time: 0.6324 [2021-03-28 12:09:07 swin_base_patch4_window7_224] INFO: Epoch: [268] [1020/1251] eta: 0:02:26 lr: 0.000036 loss: 2.7228 (2.6951) grad_norm: 3.3790 (nan) time: 0.6355 [2021-03-28 12:09:13 swin_base_patch4_window7_224] INFO: Epoch: [268] [1030/1251] eta: 0:02:20 lr: 0.000036 loss: 2.8394 (2.6959) grad_norm: 3.0772 (nan) time: 0.6340 [2021-03-28 12:09:20 swin_base_patch4_window7_224] INFO: Epoch: [268] [1040/1251] eta: 0:02:14 lr: 0.000036 loss: 2.7881 (2.6944) grad_norm: 3.0772 (nan) time: 0.6325 [2021-03-28 12:09:26 swin_base_patch4_window7_224] INFO: Epoch: [268] [1050/1251] eta: 0:02:07 lr: 0.000036 loss: 2.8109 (2.6960) grad_norm: 3.0877 (nan) time: 0.6269 [2021-03-28 12:09:32 swin_base_patch4_window7_224] INFO: Epoch: [268] [1060/1251] eta: 0:02:01 lr: 0.000036 loss: 2.8328 (2.6975) grad_norm: 3.0936 (nan) time: 0.6284 [2021-03-28 12:09:39 swin_base_patch4_window7_224] INFO: Epoch: [268] [1070/1251] eta: 0:01:55 lr: 0.000036 loss: 2.8023 (2.6984) grad_norm: 3.1486 (nan) time: 0.6349 [2021-03-28 12:09:45 swin_base_patch4_window7_224] INFO: Epoch: [268] [1080/1251] eta: 0:01:48 lr: 0.000036 loss: 2.8228 (2.6986) grad_norm: 3.3889 (nan) time: 0.6319 [2021-03-28 12:09:51 swin_base_patch4_window7_224] INFO: Epoch: [268] [1090/1251] eta: 0:01:42 lr: 0.000036 loss: 2.7837 (2.6976) grad_norm: 3.3441 (nan) time: 0.6242 [2021-03-28 12:09:57 swin_base_patch4_window7_224] INFO: Epoch: [268] [1100/1251] eta: 0:01:35 lr: 0.000036 loss: 2.6552 (2.6957) grad_norm: 2.8996 (nan) time: 0.6249 [2021-03-28 12:10:04 swin_base_patch4_window7_224] INFO: Epoch: [268] [1110/1251] eta: 0:01:29 lr: 0.000036 loss: 2.7570 (2.6957) grad_norm: 3.0639 (nan) time: 0.6250 [2021-03-28 12:10:10 swin_base_patch4_window7_224] INFO: Epoch: [268] [1120/1251] eta: 0:01:23 lr: 0.000036 loss: 2.8830 (2.6963) grad_norm: 3.1083 (nan) time: 0.6304 [2021-03-28 12:10:16 swin_base_patch4_window7_224] INFO: Epoch: [268] [1130/1251] eta: 0:01:16 lr: 0.000036 loss: 2.9020 (2.6980) grad_norm: 3.1083 (nan) time: 0.6345 [2021-03-28 12:10:23 swin_base_patch4_window7_224] INFO: Epoch: [268] [1140/1251] eta: 0:01:10 lr: 0.000036 loss: 2.8984 (2.6988) grad_norm: 3.4330 (nan) time: 0.6327 [2021-03-28 12:10:29 swin_base_patch4_window7_224] INFO: Epoch: [268] [1150/1251] eta: 0:01:04 lr: 0.000036 loss: 2.7878 (2.6979) grad_norm: 3.5137 (nan) time: 0.6374 [2021-03-28 12:10:36 swin_base_patch4_window7_224] INFO: Epoch: [268] [1160/1251] eta: 0:00:57 lr: 0.000036 loss: 2.5646 (2.6958) grad_norm: 3.5659 (nan) time: 0.6401 [2021-03-28 12:10:42 swin_base_patch4_window7_224] INFO: Epoch: [268] [1170/1251] eta: 0:00:51 lr: 0.000036 loss: 2.5469 (2.6958) grad_norm: 3.4275 (nan) time: 0.6361 [2021-03-28 12:10:48 swin_base_patch4_window7_224] INFO: Epoch: [268] [1180/1251] eta: 0:00:45 lr: 0.000036 loss: 2.6835 (2.6954) grad_norm: 3.2956 (nan) time: 0.6319 [2021-03-28 12:10:54 swin_base_patch4_window7_224] INFO: Epoch: [268] [1190/1251] eta: 0:00:38 lr: 0.000036 loss: 2.7359 (2.6957) grad_norm: 3.2956 (nan) time: 0.6246 [2021-03-28 12:11:01 swin_base_patch4_window7_224] INFO: Epoch: [268] [1200/1251] eta: 0:00:32 lr: 0.000036 loss: 2.7716 (2.6938) grad_norm: 2.9814 (nan) time: 0.6277 [2021-03-28 12:11:07 swin_base_patch4_window7_224] INFO: Epoch: [268] [1210/1251] eta: 0:00:26 lr: 0.000036 loss: 2.6334 (2.6936) grad_norm: 3.1506 (nan) time: 0.6307 [2021-03-28 12:11:13 swin_base_patch4_window7_224] INFO: Epoch: [268] [1220/1251] eta: 0:00:19 lr: 0.000036 loss: 2.5752 (2.6924) grad_norm: 3.1446 (nan) time: 0.6245 [2021-03-28 12:11:19 swin_base_patch4_window7_224] INFO: Epoch: [268] [1230/1251] eta: 0:00:13 lr: 0.000036 loss: 2.6977 (2.6926) grad_norm: 3.0137 (nan) time: 0.6241 [2021-03-28 12:11:26 swin_base_patch4_window7_224] INFO: Epoch: [268] [1240/1251] eta: 0:00:06 lr: 0.000036 loss: 2.8256 (2.6933) grad_norm: 3.1640 (nan) time: 0.6261 [2021-03-28 12:11:32 swin_base_patch4_window7_224] INFO: Epoch: [268] [1250/1251] eta: 0:00:00 lr: 0.000036 loss: 2.7714 (2.6936) grad_norm: 3.1636 (nan) time: 0.6251 [2021-03-28 12:11:44 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:51 loss: 0.8287 (0.8287) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-28 12:11:46 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.8142 (0.7718) acc1: 81.2500 (82.1023) acc5: 96.8750 (96.4489) [2021-03-28 12:11:48 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7797 (0.7698) acc1: 79.6875 (80.9524) acc5: 96.8750 (96.8006) [2021-03-28 12:11:52 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7536 (0.7590) acc1: 79.6875 (81.5020) acc5: 96.8750 (96.6734) [2021-03-28 12:11:54 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7536 (0.7559) acc1: 81.2500 (81.5930) acc5: 96.8750 (96.6082) [2021-03-28 12:11:55 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7670 (0.7575) acc1: 82.8125 (81.9200) acc5: 96.8750 (96.5760) [2021-03-28 12:12:10 swin_base_patch4_window7_224] INFO: * Acc@1 83.284 Acc@5 96.364 loss 0.739 [2021-03-28 12:12:10 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.3% [2021-03-28 12:12:10 swin_base_patch4_window7_224] INFO: Max accuracy: 83.28% [2021-03-28 12:12:14 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 0/1251] eta: 1:29:11 lr: 0.000036 loss: 2.8409 (2.8409) grad_norm: 2.8572 (2.8572) time: 4.2780 [2021-03-28 12:12:20 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 10/1251] eta: 0:20:00 lr: 0.000036 loss: 2.4469 (2.5023) grad_norm: 3.2233 (3.6427) time: 0.9670 [2021-03-28 12:12:26 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 20/1251] eta: 0:16:30 lr: 0.000036 loss: 2.8482 (2.7211) grad_norm: 3.2134 (3.8101) time: 0.6309 [2021-03-28 12:12:33 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 30/1251] eta: 0:15:15 lr: 0.000036 loss: 2.9622 (2.7624) grad_norm: 3.0865 (3.5821) time: 0.6297 [2021-03-28 12:12:39 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 40/1251] eta: 0:14:33 lr: 0.000036 loss: 2.9353 (2.7770) grad_norm: 3.0939 (3.5062) time: 0.6344 [2021-03-28 12:12:45 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 50/1251] eta: 0:14:04 lr: 0.000036 loss: 2.7574 (2.7457) grad_norm: 3.5288 (3.6416) time: 0.6319 [2021-03-28 12:12:52 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 60/1251] eta: 0:13:43 lr: 0.000036 loss: 2.7340 (2.7366) grad_norm: 3.5288 (3.5858) time: 0.6298 [2021-03-28 12:12:58 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 70/1251] eta: 0:13:25 lr: 0.000036 loss: 2.5932 (2.7025) grad_norm: 3.3718 (3.6583) time: 0.6291 [2021-03-28 12:13:04 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 80/1251] eta: 0:13:12 lr: 0.000036 loss: 2.5752 (2.6986) grad_norm: 3.3448 (3.6203) time: 0.6328 [2021-03-28 12:13:11 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 90/1251] eta: 0:12:58 lr: 0.000036 loss: 2.6720 (2.6818) grad_norm: 3.2295 (3.6215) time: 0.6299 [2021-03-28 12:13:17 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 100/1251] eta: 0:12:47 lr: 0.000036 loss: 2.7570 (2.6864) grad_norm: 3.0918 (3.5731) time: 0.6255 [2021-03-28 12:13:23 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 110/1251] eta: 0:12:37 lr: 0.000036 loss: 2.8052 (2.6907) grad_norm: 3.0918 (3.5294) time: 0.6331 [2021-03-28 12:13:30 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 120/1251] eta: 0:12:27 lr: 0.000036 loss: 2.7652 (2.6938) grad_norm: 3.1125 (3.5135) time: 0.6336 [2021-03-28 12:13:36 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 130/1251] eta: 0:12:18 lr: 0.000036 loss: 2.7530 (2.7067) grad_norm: 3.1115 (3.4929) time: 0.6300 [2021-03-28 12:13:42 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 140/1251] eta: 0:12:09 lr: 0.000036 loss: 2.7433 (2.7076) grad_norm: 3.2738 (3.4898) time: 0.6314 [2021-03-28 12:13:48 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 150/1251] eta: 0:12:01 lr: 0.000036 loss: 2.7622 (2.7056) grad_norm: 3.2738 (3.4822) time: 0.6294 [2021-03-28 12:13:55 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 160/1251] eta: 0:11:53 lr: 0.000036 loss: 2.7622 (2.7062) grad_norm: 3.0337 (3.4754) time: 0.6333 [2021-03-28 12:14:01 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 170/1251] eta: 0:11:45 lr: 0.000036 loss: 2.7847 (2.6998) grad_norm: 3.0891 (3.4672) time: 0.6385 [2021-03-28 12:14:07 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 180/1251] eta: 0:11:37 lr: 0.000036 loss: 2.5505 (2.6911) grad_norm: 3.1493 (3.4647) time: 0.6290 [2021-03-28 12:14:14 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 190/1251] eta: 0:11:29 lr: 0.000036 loss: 2.6233 (2.6987) grad_norm: 3.1287 (3.4642) time: 0.6247 [2021-03-28 12:14:20 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 200/1251] eta: 0:11:22 lr: 0.000036 loss: 2.7051 (2.6994) grad_norm: 3.1030 (3.4675) time: 0.6272 [2021-03-28 12:14:26 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 210/1251] eta: 0:11:14 lr: 0.000036 loss: 2.8101 (2.6990) grad_norm: 3.0546 (3.4511) time: 0.6305 [2021-03-28 12:14:33 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 220/1251] eta: 0:11:07 lr: 0.000036 loss: 2.8167 (2.7055) grad_norm: 2.9952 (3.4417) time: 0.6291 [2021-03-28 12:14:39 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 230/1251] eta: 0:11:00 lr: 0.000036 loss: 2.7992 (2.7038) grad_norm: 3.2386 (3.4390) time: 0.6327 [2021-03-28 12:14:45 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 240/1251] eta: 0:10:53 lr: 0.000036 loss: 2.7054 (2.7112) grad_norm: 3.3227 (3.5311) time: 0.6377 [2021-03-28 12:14:52 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 250/1251] eta: 0:10:46 lr: 0.000036 loss: 2.8177 (2.7146) grad_norm: 3.1534 (3.5248) time: 0.6361 [2021-03-28 12:14:58 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 260/1251] eta: 0:10:39 lr: 0.000036 loss: 2.7007 (2.7159) grad_norm: 3.1788 (3.5277) time: 0.6333 [2021-03-28 12:15:04 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 270/1251] eta: 0:10:32 lr: 0.000035 loss: 2.7640 (2.7164) grad_norm: 3.2717 (3.5206) time: 0.6300 [2021-03-28 12:15:11 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 280/1251] eta: 0:10:25 lr: 0.000035 loss: 2.5438 (2.7000) grad_norm: 3.3679 (3.5235) time: 0.6319 [2021-03-28 12:15:17 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 290/1251] eta: 0:10:19 lr: 0.000035 loss: 2.0273 (2.6843) grad_norm: 3.1940 (3.5105) time: 0.6349 [2021-03-28 12:15:23 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 300/1251] eta: 0:10:11 lr: 0.000035 loss: 2.3837 (2.6791) grad_norm: 3.0210 (3.5230) time: 0.6291 [2021-03-28 12:15:30 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 310/1251] eta: 0:10:05 lr: 0.000035 loss: 2.6809 (2.6764) grad_norm: 3.0761 (3.5183) time: 0.6272 [2021-03-28 12:15:36 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 320/1251] eta: 0:09:58 lr: 0.000035 loss: 2.7422 (2.6800) grad_norm: 3.0761 (3.5204) time: 0.6293 [2021-03-28 12:15:42 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 330/1251] eta: 0:09:51 lr: 0.000035 loss: 2.6934 (2.6748) grad_norm: 3.1625 (3.5176) time: 0.6278 [2021-03-28 12:15:48 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 340/1251] eta: 0:09:44 lr: 0.000035 loss: 2.6262 (2.6749) grad_norm: 3.2412 (3.5116) time: 0.6288 [2021-03-28 12:15:55 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 350/1251] eta: 0:09:37 lr: 0.000035 loss: 2.4876 (2.6664) grad_norm: 3.0449 (3.5030) time: 0.6290 [2021-03-28 12:16:01 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 360/1251] eta: 0:09:31 lr: 0.000035 loss: 2.4059 (2.6670) grad_norm: 3.1183 (3.4946) time: 0.6287 [2021-03-28 12:16:07 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 370/1251] eta: 0:09:24 lr: 0.000035 loss: 2.9514 (2.6714) grad_norm: 3.1427 (3.4889) time: 0.6288 [2021-03-28 12:16:14 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 380/1251] eta: 0:09:17 lr: 0.000035 loss: 2.7223 (2.6683) grad_norm: 3.2397 (3.4890) time: 0.6270 [2021-03-28 12:16:20 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 390/1251] eta: 0:09:11 lr: 0.000035 loss: 2.5533 (2.6690) grad_norm: 3.0301 (3.4775) time: 0.6264 [2021-03-28 12:16:26 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 400/1251] eta: 0:09:04 lr: 0.000035 loss: 2.4908 (2.6626) grad_norm: 3.2078 (3.4834) time: 0.6335 [2021-03-28 12:16:32 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 410/1251] eta: 0:08:57 lr: 0.000035 loss: 2.4908 (2.6625) grad_norm: 3.2964 (3.4813) time: 0.6323 [2021-03-28 12:16:39 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 420/1251] eta: 0:08:51 lr: 0.000035 loss: 2.7513 (2.6628) grad_norm: 3.0122 (3.4765) time: 0.6253 [2021-03-28 12:16:45 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 430/1251] eta: 0:08:44 lr: 0.000035 loss: 2.7765 (2.6677) grad_norm: 3.1045 (3.4705) time: 0.6290 [2021-03-28 12:16:51 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 440/1251] eta: 0:08:38 lr: 0.000035 loss: 2.8384 (2.6673) grad_norm: 3.0334 (3.4595) time: 0.6329 [2021-03-28 12:16:58 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 450/1251] eta: 0:08:31 lr: 0.000035 loss: 2.7017 (2.6687) grad_norm: 2.9541 (3.4535) time: 0.6297 [2021-03-28 12:17:04 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 460/1251] eta: 0:08:24 lr: 0.000035 loss: 2.7370 (2.6716) grad_norm: 3.2582 (3.4560) time: 0.6273 [2021-03-28 12:17:10 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 470/1251] eta: 0:08:18 lr: 0.000035 loss: 2.7899 (2.6722) grad_norm: 3.3867 (3.4556) time: 0.6291 [2021-03-28 12:17:17 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 480/1251] eta: 0:08:11 lr: 0.000035 loss: 2.8561 (2.6764) grad_norm: 3.1878 (3.4536) time: 0.6306 [2021-03-28 12:17:23 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 490/1251] eta: 0:08:05 lr: 0.000035 loss: 2.8561 (2.6747) grad_norm: 3.3574 (3.4777) time: 0.6315 [2021-03-28 12:17:29 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 500/1251] eta: 0:07:58 lr: 0.000035 loss: 2.5775 (2.6717) grad_norm: 4.0258 (3.4970) time: 0.6299 [2021-03-28 12:17:35 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 510/1251] eta: 0:07:52 lr: 0.000035 loss: 2.6527 (2.6757) grad_norm: 3.4422 (3.4932) time: 0.6286 [2021-03-28 12:17:42 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 520/1251] eta: 0:07:45 lr: 0.000035 loss: 2.7836 (2.6727) grad_norm: 3.1187 (3.4886) time: 0.6262 [2021-03-28 12:17:48 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 530/1251] eta: 0:07:39 lr: 0.000035 loss: 2.6327 (2.6724) grad_norm: 3.0265 (3.4882) time: 0.6258 [2021-03-28 12:17:54 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 540/1251] eta: 0:07:32 lr: 0.000035 loss: 2.6327 (2.6682) grad_norm: 3.1405 (3.4854) time: 0.6261 [2021-03-28 12:18:01 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 550/1251] eta: 0:07:26 lr: 0.000035 loss: 2.4986 (2.6702) grad_norm: 3.0914 (3.4879) time: 0.6341 [2021-03-28 12:18:07 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 560/1251] eta: 0:07:20 lr: 0.000035 loss: 2.8311 (2.6737) grad_norm: 3.2199 (3.4916) time: 0.6480 [2021-03-28 12:18:13 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 570/1251] eta: 0:07:13 lr: 0.000035 loss: 2.9320 (2.6793) grad_norm: 3.4102 (3.4985) time: 0.6406 [2021-03-28 12:18:20 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 580/1251] eta: 0:07:07 lr: 0.000035 loss: 2.8608 (2.6756) grad_norm: 3.4102 (3.4991) time: 0.6342 [2021-03-28 12:18:26 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 590/1251] eta: 0:07:01 lr: 0.000035 loss: 2.6018 (2.6752) grad_norm: 3.1351 (3.4966) time: 0.6348 [2021-03-28 12:18:32 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 600/1251] eta: 0:06:54 lr: 0.000035 loss: 2.7010 (2.6755) grad_norm: 2.9502 (3.4889) time: 0.6302 [2021-03-28 12:18:39 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 610/1251] eta: 0:06:48 lr: 0.000035 loss: 2.6094 (2.6736) grad_norm: 3.0858 (3.4881) time: 0.6313 [2021-03-28 12:18:45 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 620/1251] eta: 0:06:41 lr: 0.000035 loss: 2.8285 (2.6778) grad_norm: 3.2266 (3.4908) time: 0.6360 [2021-03-28 12:18:51 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 630/1251] eta: 0:06:35 lr: 0.000035 loss: 2.8887 (2.6803) grad_norm: 3.2662 (3.4906) time: 0.6301 [2021-03-28 12:18:58 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 640/1251] eta: 0:06:28 lr: 0.000035 loss: 2.7953 (2.6818) grad_norm: 3.2677 (3.4935) time: 0.6261 [2021-03-28 12:19:04 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 650/1251] eta: 0:06:22 lr: 0.000035 loss: 2.7953 (2.6841) grad_norm: 3.1966 (3.4941) time: 0.6357 [2021-03-28 12:19:10 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 660/1251] eta: 0:06:16 lr: 0.000035 loss: 2.8293 (2.6839) grad_norm: 3.5047 (3.4983) time: 0.6362 [2021-03-28 12:19:17 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 670/1251] eta: 0:06:09 lr: 0.000035 loss: 2.7003 (2.6840) grad_norm: 3.2928 (3.4955) time: 0.6316 [2021-03-28 12:19:23 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 680/1251] eta: 0:06:03 lr: 0.000035 loss: 2.7087 (2.6856) grad_norm: 3.1802 (3.4935) time: 0.6326 [2021-03-28 12:19:29 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 690/1251] eta: 0:05:56 lr: 0.000035 loss: 2.9845 (2.6876) grad_norm: 3.3037 (3.4981) time: 0.6282 [2021-03-28 12:19:36 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 700/1251] eta: 0:05:50 lr: 0.000035 loss: 2.8504 (2.6892) grad_norm: 3.6798 (3.5231) time: 0.6271 [2021-03-28 12:19:42 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 710/1251] eta: 0:05:44 lr: 0.000035 loss: 2.8504 (2.6915) grad_norm: 3.3210 (3.5198) time: 0.6331 [2021-03-28 12:19:48 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 720/1251] eta: 0:05:37 lr: 0.000035 loss: 2.8129 (2.6939) grad_norm: 2.9688 (3.5142) time: 0.6316 [2021-03-28 12:19:55 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 730/1251] eta: 0:05:31 lr: 0.000035 loss: 2.8030 (2.6941) grad_norm: 2.9771 (3.5079) time: 0.6291 [2021-03-28 12:20:01 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 740/1251] eta: 0:05:25 lr: 0.000035 loss: 2.8202 (2.6939) grad_norm: 3.0141 (3.5043) time: 0.6354 [2021-03-28 12:20:07 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 750/1251] eta: 0:05:18 lr: 0.000035 loss: 2.8794 (2.6944) grad_norm: 3.0033 (3.5003) time: 0.6379 [2021-03-28 12:20:14 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 760/1251] eta: 0:05:12 lr: 0.000035 loss: 2.7721 (2.6941) grad_norm: 3.0864 (3.4978) time: 0.6300 [2021-03-28 12:20:20 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 770/1251] eta: 0:05:05 lr: 0.000035 loss: 2.8258 (2.6936) grad_norm: 3.1980 (3.4946) time: 0.6258 [2021-03-28 12:20:26 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 780/1251] eta: 0:04:59 lr: 0.000035 loss: 2.7226 (2.6926) grad_norm: 3.1579 (3.4932) time: 0.6299 [2021-03-28 12:20:33 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 790/1251] eta: 0:04:53 lr: 0.000035 loss: 2.7226 (2.6923) grad_norm: 3.2883 (3.4943) time: 0.6325 [2021-03-28 12:20:39 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 800/1251] eta: 0:04:46 lr: 0.000035 loss: 2.5694 (2.6888) grad_norm: 3.1580 (3.4891) time: 0.6362 [2021-03-28 12:20:45 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 810/1251] eta: 0:04:40 lr: 0.000035 loss: 2.8642 (2.6913) grad_norm: 3.0977 (3.4874) time: 0.6365 [2021-03-28 12:20:52 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 820/1251] eta: 0:04:33 lr: 0.000035 loss: 2.9767 (2.6954) grad_norm: 3.3205 (3.4883) time: 0.6292 [2021-03-28 12:20:58 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 830/1251] eta: 0:04:27 lr: 0.000035 loss: 2.9340 (2.6943) grad_norm: 3.2220 (3.4881) time: 0.6316 [2021-03-28 12:21:04 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 840/1251] eta: 0:04:21 lr: 0.000035 loss: 2.5636 (2.6916) grad_norm: 3.1403 (3.4839) time: 0.6320 [2021-03-28 12:21:10 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 850/1251] eta: 0:04:14 lr: 0.000035 loss: 2.5636 (2.6889) grad_norm: 3.0577 (3.4836) time: 0.6279 [2021-03-28 12:21:17 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 860/1251] eta: 0:04:08 lr: 0.000035 loss: 2.7998 (2.6904) grad_norm: 3.1534 (3.4823) time: 0.6328 [2021-03-28 12:21:23 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 870/1251] eta: 0:04:02 lr: 0.000035 loss: 2.8196 (2.6914) grad_norm: 3.1166 (3.4798) time: 0.6373 [2021-03-28 12:21:30 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 880/1251] eta: 0:03:55 lr: 0.000035 loss: 2.8062 (2.6913) grad_norm: 3.1517 (3.4851) time: 0.6372 [2021-03-28 12:21:36 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 890/1251] eta: 0:03:49 lr: 0.000035 loss: 2.5703 (2.6886) grad_norm: 3.3061 (3.4848) time: 0.6336 [2021-03-28 12:21:42 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 900/1251] eta: 0:03:43 lr: 0.000035 loss: 2.5703 (2.6881) grad_norm: 3.3193 (3.4863) time: 0.6307 [2021-03-28 12:21:48 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 910/1251] eta: 0:03:36 lr: 0.000035 loss: 2.7725 (2.6876) grad_norm: 3.1968 (3.4949) time: 0.6271 [2021-03-28 12:21:55 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 920/1251] eta: 0:03:30 lr: 0.000035 loss: 2.8331 (2.6887) grad_norm: 3.3948 (3.4971) time: 0.6278 [2021-03-28 12:22:01 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 930/1251] eta: 0:03:23 lr: 0.000035 loss: 2.9046 (2.6916) grad_norm: 3.5053 (3.4998) time: 0.6338 [2021-03-28 12:22:07 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 940/1251] eta: 0:03:17 lr: 0.000035 loss: 2.9046 (2.6927) grad_norm: 3.1792 (3.4967) time: 0.6323 [2021-03-28 12:22:14 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 950/1251] eta: 0:03:11 lr: 0.000035 loss: 2.8738 (2.6918) grad_norm: 3.1466 (3.4944) time: 0.6319 [2021-03-28 12:22:20 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 960/1251] eta: 0:03:04 lr: 0.000035 loss: 2.7486 (2.6927) grad_norm: 3.2639 (3.4947) time: 0.6349 [2021-03-28 12:22:26 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 970/1251] eta: 0:02:58 lr: 0.000035 loss: 2.6763 (2.6914) grad_norm: 3.2881 (3.4933) time: 0.6301 [2021-03-28 12:22:33 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 980/1251] eta: 0:02:52 lr: 0.000035 loss: 2.6086 (2.6911) grad_norm: 3.2614 (3.4978) time: 0.6350 [2021-03-28 12:22:39 swin_base_patch4_window7_224] INFO: Epoch: [269] [ 990/1251] eta: 0:02:45 lr: 0.000035 loss: 2.6849 (2.6902) grad_norm: 3.3337 (3.4976) time: 0.6369 [2021-03-28 12:22:45 swin_base_patch4_window7_224] INFO: Epoch: [269] [1000/1251] eta: 0:02:39 lr: 0.000035 loss: 2.3635 (2.6878) grad_norm: 3.2520 (3.4994) time: 0.6295 [2021-03-28 12:22:52 swin_base_patch4_window7_224] INFO: Epoch: [269] [1010/1251] eta: 0:02:33 lr: 0.000035 loss: 2.5701 (2.6878) grad_norm: 3.2520 (3.5006) time: 0.6286 [2021-03-28 12:22:58 swin_base_patch4_window7_224] INFO: Epoch: [269] [1020/1251] eta: 0:02:26 lr: 0.000035 loss: 2.7442 (2.6873) grad_norm: 3.2150 (3.4979) time: 0.6311 [2021-03-28 12:23:04 swin_base_patch4_window7_224] INFO: Epoch: [269] [1030/1251] eta: 0:02:20 lr: 0.000035 loss: 2.7957 (2.6888) grad_norm: 3.0785 (3.4970) time: 0.6337 [2021-03-28 12:23:11 swin_base_patch4_window7_224] INFO: Epoch: [269] [1040/1251] eta: 0:02:13 lr: 0.000034 loss: 2.8210 (2.6886) grad_norm: 3.0492 (3.4945) time: 0.6305 [2021-03-28 12:23:17 swin_base_patch4_window7_224] INFO: Epoch: [269] [1050/1251] eta: 0:02:07 lr: 0.000034 loss: 2.6699 (2.6875) grad_norm: 3.1602 (3.4930) time: 0.6292 [2021-03-28 12:23:23 swin_base_patch4_window7_224] INFO: Epoch: [269] [1060/1251] eta: 0:02:01 lr: 0.000034 loss: 2.7257 (2.6882) grad_norm: 3.1890 (3.4914) time: 0.6343 [2021-03-28 12:23:30 swin_base_patch4_window7_224] INFO: Epoch: [269] [1070/1251] eta: 0:01:54 lr: 0.000034 loss: 2.8131 (2.6884) grad_norm: 3.1692 (3.4907) time: 0.6324 [2021-03-28 12:23:36 swin_base_patch4_window7_224] INFO: Epoch: [269] [1080/1251] eta: 0:01:48 lr: 0.000034 loss: 2.9267 (2.6904) grad_norm: 3.0929 (3.4891) time: 0.6310 [2021-03-28 12:23:42 swin_base_patch4_window7_224] INFO: Epoch: [269] [1090/1251] eta: 0:01:42 lr: 0.000034 loss: 2.9111 (2.6914) grad_norm: 3.2931 (3.4940) time: 0.6288 [2021-03-28 12:23:48 swin_base_patch4_window7_224] INFO: Epoch: [269] [1100/1251] eta: 0:01:35 lr: 0.000034 loss: 2.8438 (2.6923) grad_norm: 3.2931 (3.4911) time: 0.6229 [2021-03-28 12:23:55 swin_base_patch4_window7_224] INFO: Epoch: [269] [1110/1251] eta: 0:01:29 lr: 0.000034 loss: 2.7708 (2.6916) grad_norm: 3.0650 (3.4906) time: 0.6240 [2021-03-28 12:24:01 swin_base_patch4_window7_224] INFO: Epoch: [269] [1120/1251] eta: 0:01:23 lr: 0.000034 loss: 2.6297 (2.6901) grad_norm: 3.0589 (3.4878) time: 0.6284 [2021-03-28 12:24:07 swin_base_patch4_window7_224] INFO: Epoch: [269] [1130/1251] eta: 0:01:16 lr: 0.000034 loss: 2.5786 (2.6884) grad_norm: 3.2044 (3.4889) time: 0.6299 [2021-03-28 12:24:14 swin_base_patch4_window7_224] INFO: Epoch: [269] [1140/1251] eta: 0:01:10 lr: 0.000034 loss: 2.6307 (2.6888) grad_norm: 3.2045 (3.4873) time: 0.6314 [2021-03-28 12:24:20 swin_base_patch4_window7_224] INFO: Epoch: [269] [1150/1251] eta: 0:01:04 lr: 0.000034 loss: 2.7530 (2.6888) grad_norm: 3.2032 (3.4848) time: 0.6327 [2021-03-28 12:24:26 swin_base_patch4_window7_224] INFO: Epoch: [269] [1160/1251] eta: 0:00:57 lr: 0.000034 loss: 2.7530 (2.6893) grad_norm: 3.3831 (3.4836) time: 0.6287 [2021-03-28 12:24:32 swin_base_patch4_window7_224] INFO: Epoch: [269] [1170/1251] eta: 0:00:51 lr: 0.000034 loss: 2.8988 (2.6919) grad_norm: 3.4074 (3.4839) time: 0.6248 [2021-03-28 12:24:39 swin_base_patch4_window7_224] INFO: Epoch: [269] [1180/1251] eta: 0:00:45 lr: 0.000034 loss: 2.7001 (2.6903) grad_norm: 3.0805 (3.4814) time: 0.6292 [2021-03-28 12:24:45 swin_base_patch4_window7_224] INFO: Epoch: [269] [1190/1251] eta: 0:00:38 lr: 0.000034 loss: 2.6470 (2.6903) grad_norm: 2.9954 (3.4820) time: 0.6382 [2021-03-28 12:24:51 swin_base_patch4_window7_224] INFO: Epoch: [269] [1200/1251] eta: 0:00:32 lr: 0.000034 loss: 2.7425 (2.6910) grad_norm: 3.5099 (3.4895) time: 0.6341 [2021-03-28 12:24:58 swin_base_patch4_window7_224] INFO: Epoch: [269] [1210/1251] eta: 0:00:26 lr: 0.000034 loss: 2.9751 (2.6931) grad_norm: 3.3280 (3.4868) time: 0.6268 [2021-03-28 12:25:04 swin_base_patch4_window7_224] INFO: Epoch: [269] [1220/1251] eta: 0:00:19 lr: 0.000034 loss: 2.8238 (2.6918) grad_norm: 3.2596 (3.4865) time: 0.6301 [2021-03-28 12:25:10 swin_base_patch4_window7_224] INFO: Epoch: [269] [1230/1251] eta: 0:00:13 lr: 0.000034 loss: 2.8238 (2.6928) grad_norm: 3.3320 (3.4847) time: 0.6287 [2021-03-28 12:25:17 swin_base_patch4_window7_224] INFO: Epoch: [269] [1240/1251] eta: 0:00:06 lr: 0.000034 loss: 2.8783 (2.6926) grad_norm: 3.1690 (3.4863) time: 0.6263 [2021-03-28 12:25:23 swin_base_patch4_window7_224] INFO: Epoch: [269] [1250/1251] eta: 0:00:00 lr: 0.000034 loss: 2.8033 (2.6941) grad_norm: 3.6114 (3.4879) time: 0.6239 [2021-03-28 12:25:36 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:00 loss: 0.6740 (0.6740) acc1: 85.9375 (85.9375) acc5: 100.0000 (100.0000) [2021-03-28 12:25:38 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7031 (0.7465) acc1: 81.2500 (81.8182) acc5: 96.8750 (96.4489) [2021-03-28 12:25:40 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7031 (0.7365) acc1: 81.2500 (82.3661) acc5: 96.8750 (96.4286) [2021-03-28 12:25:43 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7192 (0.7424) acc1: 82.8125 (82.5101) acc5: 96.8750 (96.5222) [2021-03-28 12:25:45 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7264 (0.7494) acc1: 81.2500 (82.4314) acc5: 96.8750 (96.4558) [2021-03-28 12:25:46 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7682 (0.7581) acc1: 81.2500 (82.1440) acc5: 96.8750 (96.3520) [2021-03-28 12:26:02 swin_base_patch4_window7_224] INFO: * Acc@1 83.172 Acc@5 96.342 loss 0.742 [2021-03-28 12:26:02 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.2% [2021-03-28 12:26:02 swin_base_patch4_window7_224] INFO: Max accuracy: 83.28% [2021-03-28 12:26:07 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 0/1251] eta: 1:39:09 lr: 0.000034 loss: 3.0373 (3.0373) grad_norm: 4.6179 (4.6179) time: 4.7554 [2021-03-28 12:26:14 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 10/1251] eta: 0:20:52 lr: 0.000034 loss: 2.8634 (2.7354) grad_norm: 3.3466 (3.4048) time: 1.0090 [2021-03-28 12:26:20 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 20/1251] eta: 0:17:04 lr: 0.000034 loss: 2.8784 (2.8136) grad_norm: 3.0696 (3.6905) time: 0.6360 [2021-03-28 12:26:26 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 30/1251] eta: 0:15:37 lr: 0.000034 loss: 2.9193 (2.8201) grad_norm: 3.0275 (3.5860) time: 0.6355 [2021-03-28 12:26:33 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 40/1251] eta: 0:14:49 lr: 0.000034 loss: 2.7763 (2.7747) grad_norm: 3.1982 (3.5541) time: 0.6325 [2021-03-28 12:26:39 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 50/1251] eta: 0:14:20 lr: 0.000034 loss: 2.6939 (2.7585) grad_norm: 3.1252 (3.4903) time: 0.6361 [2021-03-28 12:26:45 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 60/1251] eta: 0:13:55 lr: 0.000034 loss: 2.7610 (2.7747) grad_norm: 3.1873 (3.5079) time: 0.6322 [2021-03-28 12:26:52 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 70/1251] eta: 0:13:36 lr: 0.000034 loss: 2.7572 (2.7417) grad_norm: 3.1809 (3.4605) time: 0.6290 [2021-03-28 12:26:58 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 80/1251] eta: 0:13:19 lr: 0.000034 loss: 2.7220 (2.7306) grad_norm: 3.0981 (3.4218) time: 0.6265 [2021-03-28 12:27:04 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 90/1251] eta: 0:13:05 lr: 0.000034 loss: 2.6251 (2.7174) grad_norm: 2.8829 (3.3835) time: 0.6239 [2021-03-28 12:27:10 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 100/1251] eta: 0:12:53 lr: 0.000034 loss: 2.6210 (2.7116) grad_norm: 3.2822 (3.4237) time: 0.6301 [2021-03-28 12:27:17 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 110/1251] eta: 0:12:43 lr: 0.000034 loss: 2.6163 (2.7028) grad_norm: 3.3714 (3.4438) time: 0.6341 [2021-03-28 12:27:23 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 120/1251] eta: 0:12:32 lr: 0.000034 loss: 2.7595 (2.7084) grad_norm: 3.1198 (3.4480) time: 0.6328 [2021-03-28 12:27:29 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 130/1251] eta: 0:12:23 lr: 0.000034 loss: 2.6651 (2.6895) grad_norm: 3.3970 (3.4938) time: 0.6330 [2021-03-28 12:27:36 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 140/1251] eta: 0:12:15 lr: 0.000034 loss: 2.6759 (2.6940) grad_norm: 3.5443 (3.5002) time: 0.6365 [2021-03-28 12:27:42 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 150/1251] eta: 0:12:07 lr: 0.000034 loss: 2.8264 (2.6932) grad_norm: 3.0109 (3.4737) time: 0.6420 [2021-03-28 12:27:49 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 160/1251] eta: 0:11:58 lr: 0.000034 loss: 2.8258 (2.6991) grad_norm: 3.1384 (3.4811) time: 0.6364 [2021-03-28 12:27:55 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 170/1251] eta: 0:11:50 lr: 0.000034 loss: 2.8162 (2.7043) grad_norm: 3.2461 (3.4928) time: 0.6307 [2021-03-28 12:28:01 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 180/1251] eta: 0:11:42 lr: 0.000034 loss: 2.8617 (2.7116) grad_norm: 3.3820 (3.4902) time: 0.6343 [2021-03-28 12:28:08 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 190/1251] eta: 0:11:34 lr: 0.000034 loss: 2.7658 (2.6998) grad_norm: 3.3384 (3.4656) time: 0.6317 [2021-03-28 12:28:14 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 200/1251] eta: 0:11:26 lr: 0.000034 loss: 2.6926 (2.7072) grad_norm: 3.0669 (3.4770) time: 0.6335 [2021-03-28 12:28:20 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 210/1251] eta: 0:11:19 lr: 0.000034 loss: 2.7719 (2.6992) grad_norm: 3.1989 (3.4739) time: 0.6310 [2021-03-28 12:28:27 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 220/1251] eta: 0:11:11 lr: 0.000034 loss: 2.5061 (2.6884) grad_norm: 3.2927 (3.4702) time: 0.6308 [2021-03-28 12:28:33 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 230/1251] eta: 0:11:04 lr: 0.000034 loss: 2.5938 (2.6875) grad_norm: 3.2745 (3.4610) time: 0.6386 [2021-03-28 12:28:39 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 240/1251] eta: 0:10:57 lr: 0.000034 loss: 2.7718 (2.6898) grad_norm: 3.2684 (3.4910) time: 0.6369 [2021-03-28 12:28:46 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 250/1251] eta: 0:10:49 lr: 0.000034 loss: 2.7718 (2.6884) grad_norm: 3.4110 (3.5031) time: 0.6281 [2021-03-28 12:28:52 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 260/1251] eta: 0:10:42 lr: 0.000034 loss: 2.8239 (2.6906) grad_norm: 3.4110 (3.4967) time: 0.6305 [2021-03-28 12:28:58 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 270/1251] eta: 0:10:35 lr: 0.000034 loss: 2.7886 (2.6939) grad_norm: 3.0749 (3.4848) time: 0.6358 [2021-03-28 12:29:04 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 280/1251] eta: 0:10:28 lr: 0.000034 loss: 2.7886 (2.7015) grad_norm: 3.0247 (3.4811) time: 0.6266 [2021-03-28 12:29:11 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 290/1251] eta: 0:10:21 lr: 0.000034 loss: 2.7028 (2.6921) grad_norm: 3.2269 (3.4778) time: 0.6252 [2021-03-28 12:29:17 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 300/1251] eta: 0:10:14 lr: 0.000034 loss: 2.6733 (2.6929) grad_norm: 3.3553 (3.5249) time: 0.6298 [2021-03-28 12:29:23 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 310/1251] eta: 0:10:07 lr: 0.000034 loss: 2.8697 (2.7030) grad_norm: 3.4508 (3.5296) time: 0.6278 [2021-03-28 12:29:30 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 320/1251] eta: 0:10:00 lr: 0.000034 loss: 2.8618 (2.6966) grad_norm: 3.4800 (3.5470) time: 0.6333 [2021-03-28 12:29:36 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 330/1251] eta: 0:09:54 lr: 0.000034 loss: 2.6135 (2.6896) grad_norm: 3.5022 (3.5423) time: 0.6368 [2021-03-28 12:29:42 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 340/1251] eta: 0:09:47 lr: 0.000034 loss: 2.6969 (2.6880) grad_norm: 3.2268 (3.5341) time: 0.6370 [2021-03-28 12:29:49 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 350/1251] eta: 0:09:40 lr: 0.000034 loss: 2.6969 (2.6855) grad_norm: 3.0827 (3.5214) time: 0.6331 [2021-03-28 12:29:55 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 360/1251] eta: 0:09:33 lr: 0.000034 loss: 2.7495 (2.6879) grad_norm: 3.1888 (3.5241) time: 0.6285 [2021-03-28 12:30:01 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 370/1251] eta: 0:09:26 lr: 0.000034 loss: 2.8240 (2.6904) grad_norm: 3.3386 (3.5201) time: 0.6311 [2021-03-28 12:30:08 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 380/1251] eta: 0:09:20 lr: 0.000034 loss: 2.7253 (2.6902) grad_norm: 3.4311 (3.5254) time: 0.6323 [2021-03-28 12:30:14 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 390/1251] eta: 0:09:13 lr: 0.000034 loss: 2.6477 (2.6910) grad_norm: 3.2241 (3.5323) time: 0.6310 [2021-03-28 12:30:20 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 400/1251] eta: 0:09:06 lr: 0.000034 loss: 2.8001 (2.6973) grad_norm: 3.2422 (3.5320) time: 0.6319 [2021-03-28 12:30:27 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 410/1251] eta: 0:09:00 lr: 0.000034 loss: 2.8001 (2.6974) grad_norm: 3.2422 (3.5234) time: 0.6283 [2021-03-28 12:30:33 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 420/1251] eta: 0:08:53 lr: 0.000034 loss: 2.7237 (2.6954) grad_norm: 3.0881 (3.5163) time: 0.6299 [2021-03-28 12:30:39 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 430/1251] eta: 0:08:46 lr: 0.000034 loss: 2.8148 (2.6978) grad_norm: 3.1318 (3.5223) time: 0.6338 [2021-03-28 12:30:46 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 440/1251] eta: 0:08:40 lr: 0.000034 loss: 2.6890 (2.6969) grad_norm: 3.6284 (3.5296) time: 0.6354 [2021-03-28 12:30:52 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 450/1251] eta: 0:08:33 lr: 0.000034 loss: 2.6428 (2.6973) grad_norm: 3.0774 (3.5228) time: 0.6372 [2021-03-28 12:30:58 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 460/1251] eta: 0:08:27 lr: 0.000034 loss: 2.6350 (2.6925) grad_norm: 3.0774 (3.5156) time: 0.6325 [2021-03-28 12:31:05 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 470/1251] eta: 0:08:20 lr: 0.000034 loss: 2.6350 (2.6894) grad_norm: 3.0031 (3.5059) time: 0.6311 [2021-03-28 12:31:11 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 480/1251] eta: 0:08:14 lr: 0.000034 loss: 2.7272 (2.6870) grad_norm: 2.9724 (3.5024) time: 0.6299 [2021-03-28 12:31:17 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 490/1251] eta: 0:08:07 lr: 0.000034 loss: 2.8330 (2.6899) grad_norm: 3.0141 (3.4958) time: 0.6280 [2021-03-28 12:31:23 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 500/1251] eta: 0:08:00 lr: 0.000034 loss: 2.7259 (2.6886) grad_norm: 3.1124 (3.4883) time: 0.6262 [2021-03-28 12:31:30 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 510/1251] eta: 0:07:54 lr: 0.000034 loss: 2.6258 (2.6836) grad_norm: 3.1124 (3.4842) time: 0.6262 [2021-03-28 12:31:36 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 520/1251] eta: 0:07:47 lr: 0.000034 loss: 2.6338 (2.6811) grad_norm: 3.1558 (3.4897) time: 0.6327 [2021-03-28 12:31:42 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 530/1251] eta: 0:07:41 lr: 0.000034 loss: 2.6906 (2.6816) grad_norm: 3.0863 (3.4817) time: 0.6333 [2021-03-28 12:31:49 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 540/1251] eta: 0:07:34 lr: 0.000034 loss: 2.6874 (2.6762) grad_norm: 3.0878 (3.4887) time: 0.6293 [2021-03-28 12:31:55 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 550/1251] eta: 0:07:28 lr: 0.000034 loss: 2.5705 (2.6754) grad_norm: 3.3173 (3.4868) time: 0.6415 [2021-03-28 12:32:01 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 560/1251] eta: 0:07:21 lr: 0.000034 loss: 2.9409 (2.6813) grad_norm: 3.2563 (3.4818) time: 0.6396 [2021-03-28 12:32:08 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 570/1251] eta: 0:07:15 lr: 0.000034 loss: 2.7921 (2.6806) grad_norm: 3.2835 (3.4896) time: 0.6339 [2021-03-28 12:32:14 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 580/1251] eta: 0:07:09 lr: 0.000033 loss: 2.7719 (2.6823) grad_norm: 3.2167 (3.4843) time: 0.6369 [2021-03-28 12:32:20 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 590/1251] eta: 0:07:02 lr: 0.000033 loss: 2.7091 (2.6812) grad_norm: 3.2005 (3.4817) time: 0.6315 [2021-03-28 12:32:27 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 600/1251] eta: 0:06:56 lr: 0.000033 loss: 2.7091 (2.6824) grad_norm: 3.2545 (3.5093) time: 0.6283 [2021-03-28 12:32:33 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 610/1251] eta: 0:06:49 lr: 0.000033 loss: 2.7782 (2.6824) grad_norm: 3.1825 (3.5061) time: 0.6320 [2021-03-28 12:32:39 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 620/1251] eta: 0:06:43 lr: 0.000033 loss: 2.6879 (2.6831) grad_norm: 3.1825 (3.5240) time: 0.6342 [2021-03-28 12:32:46 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 630/1251] eta: 0:06:36 lr: 0.000033 loss: 2.8000 (2.6860) grad_norm: 3.1284 (3.5219) time: 0.6295 [2021-03-28 12:32:52 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 640/1251] eta: 0:06:30 lr: 0.000033 loss: 2.9019 (2.6899) grad_norm: 3.0818 (3.5159) time: 0.6293 [2021-03-28 12:32:58 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 650/1251] eta: 0:06:23 lr: 0.000033 loss: 2.8729 (2.6890) grad_norm: 3.0879 (3.5123) time: 0.6304 [2021-03-28 12:33:05 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 660/1251] eta: 0:06:17 lr: 0.000033 loss: 2.7541 (2.6889) grad_norm: 3.0879 (3.5065) time: 0.6302 [2021-03-28 12:33:11 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 670/1251] eta: 0:06:10 lr: 0.000033 loss: 2.6274 (2.6845) grad_norm: 3.1846 (3.5062) time: 0.6260 [2021-03-28 12:33:17 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 680/1251] eta: 0:06:04 lr: 0.000033 loss: 2.6274 (2.6851) grad_norm: 3.4074 (3.5049) time: 0.6267 [2021-03-28 12:33:23 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 690/1251] eta: 0:05:57 lr: 0.000033 loss: 2.9053 (2.6886) grad_norm: 3.2219 (3.5076) time: 0.6277 [2021-03-28 12:33:30 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 700/1251] eta: 0:05:51 lr: 0.000033 loss: 2.7097 (2.6860) grad_norm: 3.0144 (3.5032) time: 0.6324 [2021-03-28 12:33:36 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 710/1251] eta: 0:05:45 lr: 0.000033 loss: 2.6488 (2.6869) grad_norm: 3.1033 (3.5086) time: 0.6343 [2021-03-28 12:33:42 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 720/1251] eta: 0:05:38 lr: 0.000033 loss: 2.7358 (2.6887) grad_norm: 3.0920 (3.5041) time: 0.6275 [2021-03-28 12:33:49 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 730/1251] eta: 0:05:32 lr: 0.000033 loss: 2.7358 (2.6883) grad_norm: 3.0920 (3.5018) time: 0.6296 [2021-03-28 12:33:55 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 740/1251] eta: 0:05:25 lr: 0.000033 loss: 2.8466 (2.6901) grad_norm: 3.1330 (3.4970) time: 0.6378 [2021-03-28 12:34:01 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 750/1251] eta: 0:05:19 lr: 0.000033 loss: 2.8722 (2.6918) grad_norm: 3.1271 (3.4931) time: 0.6363 [2021-03-28 12:34:08 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 760/1251] eta: 0:05:12 lr: 0.000033 loss: 2.8472 (2.6923) grad_norm: 3.2278 (3.4930) time: 0.6305 [2021-03-28 12:34:14 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 770/1251] eta: 0:05:06 lr: 0.000033 loss: 2.6830 (2.6886) grad_norm: 3.3748 (3.4896) time: 0.6280 [2021-03-28 12:34:20 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 780/1251] eta: 0:05:00 lr: 0.000033 loss: 2.6682 (2.6886) grad_norm: 3.2915 (3.4933) time: 0.6276 [2021-03-28 12:34:27 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 790/1251] eta: 0:04:53 lr: 0.000033 loss: 2.9265 (2.6913) grad_norm: 3.0314 (3.4872) time: 0.6267 [2021-03-28 12:34:33 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 800/1251] eta: 0:04:47 lr: 0.000033 loss: 2.8936 (2.6930) grad_norm: 3.0498 (3.4935) time: 0.6258 [2021-03-28 12:34:39 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 810/1251] eta: 0:04:40 lr: 0.000033 loss: 2.8393 (2.6942) grad_norm: 3.1538 (3.4908) time: 0.6252 [2021-03-28 12:34:45 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 820/1251] eta: 0:04:34 lr: 0.000033 loss: 2.8743 (2.6951) grad_norm: 3.1638 (3.4895) time: 0.6300 [2021-03-28 12:34:52 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 830/1251] eta: 0:04:27 lr: 0.000033 loss: 2.8799 (2.6969) grad_norm: 3.1643 (3.4847) time: 0.6294 [2021-03-28 12:34:58 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 840/1251] eta: 0:04:21 lr: 0.000033 loss: 2.9147 (2.6980) grad_norm: 3.1512 (3.4883) time: 0.6272 [2021-03-28 12:35:04 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 850/1251] eta: 0:04:15 lr: 0.000033 loss: 2.5961 (2.6952) grad_norm: 3.2818 (3.4867) time: 0.6329 [2021-03-28 12:35:11 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 860/1251] eta: 0:04:08 lr: 0.000033 loss: 2.4829 (2.6934) grad_norm: 3.2134 (3.4831) time: 0.6293 [2021-03-28 12:35:17 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 870/1251] eta: 0:04:02 lr: 0.000033 loss: 2.7512 (2.6938) grad_norm: 3.1087 (3.4813) time: 0.6291 [2021-03-28 12:35:23 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 880/1251] eta: 0:03:56 lr: 0.000033 loss: 2.7512 (2.6952) grad_norm: 3.1089 (3.4812) time: 0.6388 [2021-03-28 12:35:30 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 890/1251] eta: 0:03:49 lr: 0.000033 loss: 2.7678 (2.6962) grad_norm: 3.1465 (3.4869) time: 0.6369 [2021-03-28 12:35:36 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 900/1251] eta: 0:03:43 lr: 0.000033 loss: 2.7008 (2.6950) grad_norm: 3.0897 (3.4833) time: 0.6250 [2021-03-28 12:35:42 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 910/1251] eta: 0:03:36 lr: 0.000033 loss: 2.6267 (2.6943) grad_norm: 2.9915 (3.4847) time: 0.6267 [2021-03-28 12:35:48 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 920/1251] eta: 0:03:30 lr: 0.000033 loss: 2.7858 (2.6947) grad_norm: 3.2215 (3.4843) time: 0.6264 [2021-03-28 12:35:55 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 930/1251] eta: 0:03:24 lr: 0.000033 loss: 2.7156 (2.6933) grad_norm: 3.2341 (3.4945) time: 0.6246 [2021-03-28 12:36:01 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 940/1251] eta: 0:03:17 lr: 0.000033 loss: 2.7156 (2.6946) grad_norm: 3.2234 (3.4925) time: 0.6285 [2021-03-28 12:36:07 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 950/1251] eta: 0:03:11 lr: 0.000033 loss: 2.7450 (2.6957) grad_norm: 3.1799 (3.5016) time: 0.6301 [2021-03-28 12:36:14 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 960/1251] eta: 0:03:04 lr: 0.000033 loss: 2.6855 (2.6960) grad_norm: 3.0491 (3.4989) time: 0.6285 [2021-03-28 12:36:20 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 970/1251] eta: 0:02:58 lr: 0.000033 loss: 2.5967 (2.6935) grad_norm: 3.1306 (3.5003) time: 0.6260 [2021-03-28 12:36:26 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 980/1251] eta: 0:02:52 lr: 0.000033 loss: 2.5967 (2.6919) grad_norm: 3.2197 (3.4984) time: 0.6299 [2021-03-28 12:36:32 swin_base_patch4_window7_224] INFO: Epoch: [270] [ 990/1251] eta: 0:02:45 lr: 0.000033 loss: 2.6478 (2.6922) grad_norm: 3.2869 (3.4990) time: 0.6294 [2021-03-28 12:36:39 swin_base_patch4_window7_224] INFO: Epoch: [270] [1000/1251] eta: 0:02:39 lr: 0.000033 loss: 2.7787 (2.6911) grad_norm: 3.1487 (3.4972) time: 0.6261 [2021-03-28 12:36:45 swin_base_patch4_window7_224] INFO: Epoch: [270] [1010/1251] eta: 0:02:33 lr: 0.000033 loss: 2.7519 (2.6926) grad_norm: 3.1265 (3.5044) time: 0.6320 [2021-03-28 12:36:51 swin_base_patch4_window7_224] INFO: Epoch: [270] [1020/1251] eta: 0:02:26 lr: 0.000033 loss: 2.6311 (2.6905) grad_norm: 3.2362 (3.5047) time: 0.6308 [2021-03-28 12:36:58 swin_base_patch4_window7_224] INFO: Epoch: [270] [1030/1251] eta: 0:02:20 lr: 0.000033 loss: 2.7609 (2.6929) grad_norm: 3.2925 (3.5040) time: 0.6282 [2021-03-28 12:37:04 swin_base_patch4_window7_224] INFO: Epoch: [270] [1040/1251] eta: 0:02:14 lr: 0.000033 loss: 2.9448 (2.6915) grad_norm: 3.3419 (3.5085) time: 0.6291 [2021-03-28 12:37:10 swin_base_patch4_window7_224] INFO: Epoch: [270] [1050/1251] eta: 0:02:07 lr: 0.000033 loss: 2.7217 (2.6926) grad_norm: 3.1945 (3.5087) time: 0.6293 [2021-03-28 12:37:16 swin_base_patch4_window7_224] INFO: Epoch: [270] [1060/1251] eta: 0:02:01 lr: 0.000033 loss: 2.8757 (2.6938) grad_norm: 3.1945 (3.5110) time: 0.6312 [2021-03-28 12:37:23 swin_base_patch4_window7_224] INFO: Epoch: [270] [1070/1251] eta: 0:01:54 lr: 0.000033 loss: 2.7855 (2.6934) grad_norm: 3.4171 (3.5098) time: 0.6303 [2021-03-28 12:37:29 swin_base_patch4_window7_224] INFO: Epoch: [270] [1080/1251] eta: 0:01:48 lr: 0.000033 loss: 2.7629 (2.6934) grad_norm: 3.5388 (3.5119) time: 0.6318 [2021-03-28 12:37:35 swin_base_patch4_window7_224] INFO: Epoch: [270] [1090/1251] eta: 0:01:42 lr: 0.000033 loss: 2.7629 (2.6935) grad_norm: 3.7242 (3.5169) time: 0.6310 [2021-03-28 12:37:42 swin_base_patch4_window7_224] INFO: Epoch: [270] [1100/1251] eta: 0:01:35 lr: 0.000033 loss: 2.7246 (2.6943) grad_norm: 3.7307 (3.5176) time: 0.6282 [2021-03-28 12:37:48 swin_base_patch4_window7_224] INFO: Epoch: [270] [1110/1251] eta: 0:01:29 lr: 0.000033 loss: 2.8299 (2.6961) grad_norm: 3.2458 (3.5155) time: 0.6281 [2021-03-28 12:37:54 swin_base_patch4_window7_224] INFO: Epoch: [270] [1120/1251] eta: 0:01:23 lr: 0.000033 loss: 2.8121 (2.6969) grad_norm: 3.0186 (3.5150) time: 0.6253 [2021-03-28 12:38:01 swin_base_patch4_window7_224] INFO: Epoch: [270] [1130/1251] eta: 0:01:16 lr: 0.000033 loss: 2.7701 (2.6962) grad_norm: 3.0742 (3.5188) time: 0.6301 [2021-03-28 12:38:07 swin_base_patch4_window7_224] INFO: Epoch: [270] [1140/1251] eta: 0:01:10 lr: 0.000033 loss: 2.6815 (2.6962) grad_norm: 3.2186 (3.5194) time: 0.6358 [2021-03-28 12:38:13 swin_base_patch4_window7_224] INFO: Epoch: [270] [1150/1251] eta: 0:01:04 lr: 0.000033 loss: 2.6252 (2.6951) grad_norm: 3.3016 (3.5210) time: 0.6356 [2021-03-28 12:38:20 swin_base_patch4_window7_224] INFO: Epoch: [270] [1160/1251] eta: 0:00:57 lr: 0.000033 loss: 2.8279 (2.6961) grad_norm: 3.4642 (3.5219) time: 0.6373 [2021-03-28 12:38:26 swin_base_patch4_window7_224] INFO: Epoch: [270] [1170/1251] eta: 0:00:51 lr: 0.000033 loss: 2.7842 (2.6957) grad_norm: 3.1939 (3.5225) time: 0.6320 [2021-03-28 12:38:32 swin_base_patch4_window7_224] INFO: Epoch: [270] [1180/1251] eta: 0:00:45 lr: 0.000033 loss: 2.7271 (2.6947) grad_norm: 3.2581 (3.5225) time: 0.6277 [2021-03-28 12:38:39 swin_base_patch4_window7_224] INFO: Epoch: [270] [1190/1251] eta: 0:00:38 lr: 0.000033 loss: 2.6663 (2.6936) grad_norm: 3.3089 (3.5209) time: 0.6284 [2021-03-28 12:38:45 swin_base_patch4_window7_224] INFO: Epoch: [270] [1200/1251] eta: 0:00:32 lr: 0.000033 loss: 2.7407 (2.6944) grad_norm: 3.2915 (3.5185) time: 0.6335 [2021-03-28 12:38:51 swin_base_patch4_window7_224] INFO: Epoch: [270] [1210/1251] eta: 0:00:26 lr: 0.000033 loss: 2.6878 (2.6924) grad_norm: 2.9798 (3.5159) time: 0.6372 [2021-03-28 12:38:58 swin_base_patch4_window7_224] INFO: Epoch: [270] [1220/1251] eta: 0:00:19 lr: 0.000033 loss: 2.4608 (2.6922) grad_norm: 2.9697 (3.5150) time: 0.6313 [2021-03-28 12:39:04 swin_base_patch4_window7_224] INFO: Epoch: [270] [1230/1251] eta: 0:00:13 lr: 0.000033 loss: 2.8088 (2.6924) grad_norm: 3.0578 (3.5122) time: 0.6260 [2021-03-28 12:39:10 swin_base_patch4_window7_224] INFO: Epoch: [270] [1240/1251] eta: 0:00:06 lr: 0.000033 loss: 2.8656 (2.6931) grad_norm: 2.9990 (3.5102) time: 0.6262 [2021-03-28 12:39:16 swin_base_patch4_window7_224] INFO: Epoch: [270] [1250/1251] eta: 0:00:00 lr: 0.000033 loss: 2.9946 (2.6946) grad_norm: 3.2553 (3.5091) time: 0.6193 [2021-03-28 12:40:45 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:55 loss: 0.5352 (0.5352) acc1: 87.5000 (87.5000) acc5: 98.4375 (98.4375) [2021-03-28 12:40:46 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:13 loss: 0.7953 (0.7907) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.5966) [2021-03-28 12:40:47 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:07 loss: 0.7885 (0.7892) acc1: 81.2500 (81.6964) acc5: 95.3125 (96.0565) [2021-03-28 12:40:49 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.7692 (0.7763) acc1: 79.6875 (81.8548) acc5: 96.8750 (96.1694) [2021-03-28 12:40:50 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.6743 (0.7528) acc1: 84.3750 (82.4314) acc5: 96.8750 (96.4939) [2021-03-28 12:40:51 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6616 (0.7470) acc1: 84.3750 (82.6560) acc5: 96.8750 (96.6400) [2021-03-28 12:41:03 swin_base_patch4_window7_224] INFO: * Acc@1 83.200 Acc@5 96.358 loss 0.743 [2021-03-28 12:41:03 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.2% [2021-03-28 12:41:03 swin_base_patch4_window7_224] INFO: Max accuracy: 83.28% [2021-03-28 12:41:08 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 0/1251] eta: 1:29:01 lr: 0.000033 loss: 2.6942 (2.6942) grad_norm: 3.3589 (3.3589) time: 4.2694 [2021-03-28 12:41:14 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 10/1251] eta: 0:19:59 lr: 0.000033 loss: 2.6942 (2.6178) grad_norm: 3.5743 (3.7003) time: 0.9666 [2021-03-28 12:41:20 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 20/1251] eta: 0:16:39 lr: 0.000033 loss: 2.7309 (2.6657) grad_norm: 3.5743 (3.7158) time: 0.6391 [2021-03-28 12:41:27 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 30/1251] eta: 0:15:20 lr: 0.000033 loss: 2.7055 (2.6576) grad_norm: 3.1828 (3.5181) time: 0.6365 [2021-03-28 12:41:33 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 40/1251] eta: 0:14:39 lr: 0.000033 loss: 2.5432 (2.6713) grad_norm: 2.9406 (3.4244) time: 0.6363 [2021-03-28 12:41:40 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 50/1251] eta: 0:14:10 lr: 0.000033 loss: 2.6763 (2.6609) grad_norm: 2.9820 (3.3991) time: 0.6372 [2021-03-28 12:41:46 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 60/1251] eta: 0:13:47 lr: 0.000033 loss: 2.6544 (2.6376) grad_norm: 3.1285 (3.4128) time: 0.6292 [2021-03-28 12:41:52 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 70/1251] eta: 0:13:29 lr: 0.000033 loss: 2.6767 (2.6332) grad_norm: 3.1645 (3.4698) time: 0.6269 [2021-03-28 12:41:58 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 80/1251] eta: 0:13:15 lr: 0.000033 loss: 2.6767 (2.6404) grad_norm: 3.1743 (3.4411) time: 0.6338 [2021-03-28 12:42:05 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 90/1251] eta: 0:13:02 lr: 0.000033 loss: 2.8501 (2.6515) grad_norm: 3.0254 (3.4203) time: 0.6360 [2021-03-28 12:42:11 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 100/1251] eta: 0:12:50 lr: 0.000033 loss: 2.8612 (2.6665) grad_norm: 3.0254 (3.4498) time: 0.6300 [2021-03-28 12:42:17 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 110/1251] eta: 0:12:39 lr: 0.000033 loss: 2.7192 (2.6580) grad_norm: 3.3822 (3.4690) time: 0.6282 [2021-03-28 12:42:24 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 120/1251] eta: 0:12:30 lr: 0.000033 loss: 2.6818 (2.6658) grad_norm: 3.4052 (3.4603) time: 0.6331 [2021-03-28 12:42:30 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 130/1251] eta: 0:12:20 lr: 0.000032 loss: 2.8903 (2.6853) grad_norm: 3.0984 (3.4377) time: 0.6305 [2021-03-28 12:42:36 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 140/1251] eta: 0:12:12 lr: 0.000032 loss: 2.8896 (2.6917) grad_norm: 3.0278 (3.4244) time: 0.6302 [2021-03-28 12:42:43 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 150/1251] eta: 0:12:03 lr: 0.000032 loss: 2.8445 (2.6970) grad_norm: 3.2055 (3.4517) time: 0.6368 [2021-03-28 12:42:49 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 160/1251] eta: 0:11:55 lr: 0.000032 loss: 2.8445 (2.7035) grad_norm: 3.4717 (3.4898) time: 0.6376 [2021-03-28 12:42:55 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 170/1251] eta: 0:11:48 lr: 0.000032 loss: 2.7364 (2.7019) grad_norm: 3.3385 (3.4947) time: 0.6371 [2021-03-28 12:43:02 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 180/1251] eta: 0:11:40 lr: 0.000032 loss: 2.6734 (2.6950) grad_norm: 3.2991 (3.5215) time: 0.6406 [2021-03-28 12:43:08 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 190/1251] eta: 0:11:33 lr: 0.000032 loss: 2.5475 (2.6855) grad_norm: 3.3397 (3.5102) time: 0.6390 [2021-03-28 12:43:15 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 200/1251] eta: 0:11:25 lr: 0.000032 loss: 2.7063 (2.6931) grad_norm: 3.3034 (3.5471) time: 0.6291 [2021-03-28 12:43:21 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 210/1251] eta: 0:11:17 lr: 0.000032 loss: 2.9228 (2.6973) grad_norm: 3.1250 (3.5303) time: 0.6238 [2021-03-28 12:43:27 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 220/1251] eta: 0:11:09 lr: 0.000032 loss: 2.7269 (2.6918) grad_norm: 3.0675 (3.5438) time: 0.6256 [2021-03-28 12:43:33 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 230/1251] eta: 0:11:02 lr: 0.000032 loss: 2.7627 (2.6932) grad_norm: 3.1012 (3.5354) time: 0.6299 [2021-03-28 12:43:40 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 240/1251] eta: 0:10:55 lr: 0.000032 loss: 2.7627 (2.6915) grad_norm: 3.1012 (3.5322) time: 0.6304 [2021-03-28 12:43:46 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 250/1251] eta: 0:10:48 lr: 0.000032 loss: 2.7698 (2.6921) grad_norm: 3.1945 (3.5269) time: 0.6327 [2021-03-28 12:43:52 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 260/1251] eta: 0:10:40 lr: 0.000032 loss: 2.7978 (2.6877) grad_norm: 3.2917 (3.5228) time: 0.6312 [2021-03-28 12:43:59 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 270/1251] eta: 0:10:33 lr: 0.000032 loss: 2.5255 (2.6814) grad_norm: 3.3107 (3.5357) time: 0.6280 [2021-03-28 12:44:05 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 280/1251] eta: 0:10:26 lr: 0.000032 loss: 2.5290 (2.6780) grad_norm: 3.3545 (3.5260) time: 0.6290 [2021-03-28 12:44:11 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 290/1251] eta: 0:10:19 lr: 0.000032 loss: 2.7125 (2.6732) grad_norm: 3.3545 (3.5286) time: 0.6309 [2021-03-28 12:44:18 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 300/1251] eta: 0:10:13 lr: 0.000032 loss: 2.7360 (2.6732) grad_norm: 3.3552 (3.5203) time: 0.6350 [2021-03-28 12:44:24 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 310/1251] eta: 0:10:06 lr: 0.000032 loss: 2.7417 (2.6704) grad_norm: 3.2908 (3.5153) time: 0.6324 [2021-03-28 12:44:30 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 320/1251] eta: 0:09:59 lr: 0.000032 loss: 2.7939 (2.6749) grad_norm: 3.0627 (3.5001) time: 0.6335 [2021-03-28 12:44:37 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 330/1251] eta: 0:09:52 lr: 0.000032 loss: 2.8343 (2.6762) grad_norm: 3.2281 (3.5149) time: 0.6348 [2021-03-28 12:44:43 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 340/1251] eta: 0:09:46 lr: 0.000032 loss: 2.7668 (2.6759) grad_norm: 3.2787 (3.5093) time: 0.6325 [2021-03-28 12:44:49 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 350/1251] eta: 0:09:39 lr: 0.000032 loss: 2.6410 (2.6756) grad_norm: 3.2691 (3.5089) time: 0.6320 [2021-03-28 12:44:56 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 360/1251] eta: 0:09:32 lr: 0.000032 loss: 2.7623 (2.6786) grad_norm: 3.2691 (3.5050) time: 0.6351 [2021-03-28 12:45:02 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 370/1251] eta: 0:09:25 lr: 0.000032 loss: 2.6461 (2.6747) grad_norm: 3.2652 (3.4984) time: 0.6318 [2021-03-28 12:45:08 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 380/1251] eta: 0:09:19 lr: 0.000032 loss: 2.6416 (2.6707) grad_norm: 3.1742 (3.4839) time: 0.6254 [2021-03-28 12:45:14 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 390/1251] eta: 0:09:12 lr: 0.000032 loss: 2.6361 (2.6688) grad_norm: 3.1167 (3.4867) time: 0.6261 [2021-03-28 12:45:21 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 400/1251] eta: 0:09:05 lr: 0.000032 loss: 2.7026 (2.6685) grad_norm: 3.3209 (3.4974) time: 0.6253 [2021-03-28 12:45:27 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 410/1251] eta: 0:08:58 lr: 0.000032 loss: 2.7466 (2.6711) grad_norm: 3.3588 (3.5041) time: 0.6269 [2021-03-28 12:45:33 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 420/1251] eta: 0:08:52 lr: 0.000032 loss: 2.8393 (2.6707) grad_norm: 3.4081 (3.5072) time: 0.6285 [2021-03-28 12:45:40 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 430/1251] eta: 0:08:45 lr: 0.000032 loss: 2.7734 (2.6750) grad_norm: 3.6351 (3.5214) time: 0.6333 [2021-03-28 12:45:46 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 440/1251] eta: 0:08:39 lr: 0.000032 loss: 2.7734 (2.6745) grad_norm: 3.4727 (3.5197) time: 0.6335 [2021-03-28 12:45:52 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 450/1251] eta: 0:08:32 lr: 0.000032 loss: 2.7072 (2.6725) grad_norm: 3.3608 (3.5153) time: 0.6270 [2021-03-28 12:45:59 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 460/1251] eta: 0:08:26 lr: 0.000032 loss: 2.7691 (2.6723) grad_norm: 3.3608 (3.5146) time: 0.6330 [2021-03-28 12:46:05 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 470/1251] eta: 0:08:19 lr: 0.000032 loss: 2.7691 (2.6716) grad_norm: 3.1185 (3.5086) time: 0.6360 [2021-03-28 12:46:11 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 480/1251] eta: 0:08:13 lr: 0.000032 loss: 2.6471 (2.6710) grad_norm: 2.9924 (3.4974) time: 0.6314 [2021-03-28 12:46:17 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 490/1251] eta: 0:08:06 lr: 0.000032 loss: 2.6591 (2.6683) grad_norm: 2.9462 (3.4897) time: 0.6257 [2021-03-28 12:46:24 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 500/1251] eta: 0:07:59 lr: 0.000032 loss: 2.6898 (2.6655) grad_norm: 3.1803 (3.4893) time: 0.6272 [2021-03-28 12:46:30 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 510/1251] eta: 0:07:53 lr: 0.000032 loss: 2.7970 (2.6695) grad_norm: 3.1992 (3.4861) time: 0.6371 [2021-03-28 12:46:36 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 520/1251] eta: 0:07:47 lr: 0.000032 loss: 2.8198 (2.6715) grad_norm: 3.1992 (3.4812) time: 0.6375 [2021-03-28 12:46:43 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 530/1251] eta: 0:07:40 lr: 0.000032 loss: 2.7321 (2.6742) grad_norm: 3.2237 (3.4819) time: 0.6395 [2021-03-28 12:46:49 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 540/1251] eta: 0:07:34 lr: 0.000032 loss: 2.7402 (2.6744) grad_norm: 3.2259 (3.4792) time: 0.6396 [2021-03-28 12:46:56 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 550/1251] eta: 0:07:28 lr: 0.000032 loss: 2.6473 (2.6724) grad_norm: 3.1251 (3.4790) time: 0.6427 [2021-03-28 12:47:02 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 560/1251] eta: 0:07:21 lr: 0.000032 loss: 2.8502 (2.6762) grad_norm: 3.1686 (3.4803) time: 0.6431 [2021-03-28 12:47:08 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 570/1251] eta: 0:07:15 lr: 0.000032 loss: 2.9329 (2.6783) grad_norm: 3.2247 (3.4739) time: 0.6374 [2021-03-28 12:47:15 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 580/1251] eta: 0:07:08 lr: 0.000032 loss: 2.7541 (2.6784) grad_norm: 3.1723 (3.4756) time: 0.6305 [2021-03-28 12:47:21 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 590/1251] eta: 0:07:02 lr: 0.000032 loss: 2.7541 (2.6812) grad_norm: 3.3439 (3.4857) time: 0.6257 [2021-03-28 12:47:27 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 600/1251] eta: 0:06:55 lr: 0.000032 loss: 2.8450 (2.6810) grad_norm: 3.3375 (3.4903) time: 0.6295 [2021-03-28 12:47:34 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 610/1251] eta: 0:06:49 lr: 0.000032 loss: 2.6898 (2.6784) grad_norm: 3.2587 (3.5011) time: 0.6301 [2021-03-28 12:47:40 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 620/1251] eta: 0:06:42 lr: 0.000032 loss: 2.5755 (2.6756) grad_norm: 3.2549 (3.5044) time: 0.6291 [2021-03-28 12:47:46 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 630/1251] eta: 0:06:36 lr: 0.000032 loss: 2.7238 (2.6745) grad_norm: 3.1802 (3.4959) time: 0.6345 [2021-03-28 12:47:53 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 640/1251] eta: 0:06:29 lr: 0.000032 loss: 2.7755 (2.6777) grad_norm: 3.0530 (3.4944) time: 0.6329 [2021-03-28 12:47:59 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 650/1251] eta: 0:06:23 lr: 0.000032 loss: 2.9280 (2.6801) grad_norm: 3.3156 (3.4916) time: 0.6299 [2021-03-28 12:48:05 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 660/1251] eta: 0:06:16 lr: 0.000032 loss: 2.9280 (2.6813) grad_norm: 3.2957 (3.4890) time: 0.6301 [2021-03-28 12:48:12 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 670/1251] eta: 0:06:10 lr: 0.000032 loss: 2.8597 (2.6855) grad_norm: 3.5889 (3.5138) time: 0.6308 [2021-03-28 12:48:18 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 680/1251] eta: 0:06:04 lr: 0.000032 loss: 2.8422 (2.6868) grad_norm: 3.4743 (3.5292) time: 0.6301 [2021-03-28 12:48:24 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 690/1251] eta: 0:05:57 lr: 0.000032 loss: 2.7878 (2.6891) grad_norm: 3.1621 (3.5292) time: 0.6312 [2021-03-28 12:48:30 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 700/1251] eta: 0:05:51 lr: 0.000032 loss: 2.8279 (2.6904) grad_norm: 3.2397 (3.5289) time: 0.6352 [2021-03-28 12:48:37 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 710/1251] eta: 0:05:44 lr: 0.000032 loss: 3.0132 (2.6938) grad_norm: 3.3195 (3.5279) time: 0.6341 [2021-03-28 12:48:43 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 720/1251] eta: 0:05:38 lr: 0.000032 loss: 2.7415 (2.6913) grad_norm: 3.3649 (3.5270) time: 0.6349 [2021-03-28 12:48:50 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 730/1251] eta: 0:05:32 lr: 0.000032 loss: 2.7186 (2.6919) grad_norm: 3.2400 (3.5222) time: 0.6423 [2021-03-28 12:48:56 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 740/1251] eta: 0:05:25 lr: 0.000032 loss: 2.7060 (2.6900) grad_norm: 3.2400 (3.5247) time: 0.6437 [2021-03-28 12:49:02 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 750/1251] eta: 0:05:19 lr: 0.000032 loss: 2.4791 (2.6869) grad_norm: 3.3424 (3.5220) time: 0.6387 [2021-03-28 12:49:09 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 760/1251] eta: 0:05:13 lr: 0.000032 loss: 2.5426 (2.6866) grad_norm: 3.1634 (3.5168) time: 0.6388 [2021-03-28 12:49:15 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 770/1251] eta: 0:05:06 lr: 0.000032 loss: 2.6627 (2.6867) grad_norm: 3.1531 (3.5147) time: 0.6384 [2021-03-28 12:49:22 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 780/1251] eta: 0:05:00 lr: 0.000032 loss: 2.6661 (2.6865) grad_norm: 3.1707 (3.5133) time: 0.6382 [2021-03-28 12:49:28 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 790/1251] eta: 0:04:53 lr: 0.000032 loss: 2.6661 (2.6852) grad_norm: 3.1641 (3.5095) time: 0.6358 [2021-03-28 12:49:34 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 800/1251] eta: 0:04:47 lr: 0.000032 loss: 2.7771 (2.6860) grad_norm: 3.1532 (3.5070) time: 0.6299 [2021-03-28 12:49:41 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 810/1251] eta: 0:04:41 lr: 0.000032 loss: 2.6196 (2.6834) grad_norm: 3.1779 (3.5081) time: 0.6302 [2021-03-28 12:49:47 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 820/1251] eta: 0:04:34 lr: 0.000032 loss: 2.9288 (2.6884) grad_norm: 3.3126 (3.5137) time: 0.6308 [2021-03-28 12:49:53 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 830/1251] eta: 0:04:28 lr: 0.000032 loss: 2.9478 (2.6878) grad_norm: 3.2976 (3.5144) time: 0.6334 [2021-03-28 12:50:00 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 840/1251] eta: 0:04:21 lr: 0.000032 loss: 2.6902 (2.6878) grad_norm: 3.2976 (3.5145) time: 0.6362 [2021-03-28 12:50:06 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 850/1251] eta: 0:04:15 lr: 0.000032 loss: 2.6780 (2.6883) grad_norm: 3.1778 (3.5133) time: 0.6339 [2021-03-28 12:50:12 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 860/1251] eta: 0:04:09 lr: 0.000032 loss: 2.5845 (2.6865) grad_norm: 3.3903 (3.5162) time: 0.6360 [2021-03-28 12:50:19 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 870/1251] eta: 0:04:02 lr: 0.000032 loss: 2.6705 (2.6846) grad_norm: 3.3568 (3.5157) time: 0.6361 [2021-03-28 12:50:25 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 880/1251] eta: 0:03:56 lr: 0.000032 loss: 2.6297 (2.6821) grad_norm: 3.3430 (3.5196) time: 0.6334 [2021-03-28 12:50:31 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 890/1251] eta: 0:03:49 lr: 0.000032 loss: 2.6337 (2.6833) grad_norm: 3.2220 (3.5191) time: 0.6300 [2021-03-28 12:50:38 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 900/1251] eta: 0:03:43 lr: 0.000032 loss: 2.7442 (2.6843) grad_norm: 3.0232 (3.5205) time: 0.6316 [2021-03-28 12:50:44 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 910/1251] eta: 0:03:37 lr: 0.000032 loss: 2.6080 (2.6826) grad_norm: 3.5475 (3.5272) time: 0.6353 [2021-03-28 12:50:50 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 920/1251] eta: 0:03:30 lr: 0.000032 loss: 2.6080 (2.6830) grad_norm: 3.3488 (3.5247) time: 0.6324 [2021-03-28 12:50:57 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 930/1251] eta: 0:03:24 lr: 0.000032 loss: 2.7259 (2.6815) grad_norm: 3.2648 (3.5276) time: 0.6361 [2021-03-28 12:51:03 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 940/1251] eta: 0:03:18 lr: 0.000032 loss: 2.6096 (2.6812) grad_norm: 3.5269 (3.5264) time: 0.6401 [2021-03-28 12:51:09 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 950/1251] eta: 0:03:11 lr: 0.000031 loss: 2.6821 (2.6836) grad_norm: 3.3477 (3.5240) time: 0.6308 [2021-03-28 12:51:16 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 960/1251] eta: 0:03:05 lr: 0.000031 loss: 2.6682 (2.6813) grad_norm: 3.2610 (3.5210) time: 0.6269 [2021-03-28 12:51:22 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 970/1251] eta: 0:02:58 lr: 0.000031 loss: 2.6266 (2.6816) grad_norm: 3.3471 (3.5204) time: 0.6320 [2021-03-28 12:51:28 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 980/1251] eta: 0:02:52 lr: 0.000031 loss: 2.8538 (2.6812) grad_norm: 3.3697 (3.5195) time: 0.6355 [2021-03-28 12:51:35 swin_base_patch4_window7_224] INFO: Epoch: [271] [ 990/1251] eta: 0:02:46 lr: 0.000031 loss: 2.5350 (2.6794) grad_norm: 3.2189 (3.5179) time: 0.6321 [2021-03-28 12:51:41 swin_base_patch4_window7_224] INFO: Epoch: [271] [1000/1251] eta: 0:02:39 lr: 0.000031 loss: 2.3308 (2.6770) grad_norm: 3.2215 (3.5189) time: 0.6354 [2021-03-28 12:51:47 swin_base_patch4_window7_224] INFO: Epoch: [271] [1010/1251] eta: 0:02:33 lr: 0.000031 loss: 2.6830 (2.6768) grad_norm: 3.3173 (3.5180) time: 0.6393 [2021-03-28 12:51:54 swin_base_patch4_window7_224] INFO: Epoch: [271] [1020/1251] eta: 0:02:27 lr: 0.000031 loss: 2.7440 (2.6753) grad_norm: 3.3173 (3.5237) time: 0.6337 [2021-03-28 12:52:00 swin_base_patch4_window7_224] INFO: Epoch: [271] [1030/1251] eta: 0:02:20 lr: 0.000031 loss: 2.6222 (2.6731) grad_norm: 3.3171 (3.5269) time: 0.6286 [2021-03-28 12:52:06 swin_base_patch4_window7_224] INFO: Epoch: [271] [1040/1251] eta: 0:02:14 lr: 0.000031 loss: 2.6504 (2.6730) grad_norm: 3.3468 (3.5300) time: 0.6308 [2021-03-28 12:52:13 swin_base_patch4_window7_224] INFO: Epoch: [271] [1050/1251] eta: 0:02:07 lr: 0.000031 loss: 2.7659 (2.6743) grad_norm: 3.2768 (3.5277) time: 0.6354 [2021-03-28 12:52:19 swin_base_patch4_window7_224] INFO: Epoch: [271] [1060/1251] eta: 0:02:01 lr: 0.000031 loss: 2.8603 (2.6739) grad_norm: 3.3063 (3.5287) time: 0.6354 [2021-03-28 12:52:25 swin_base_patch4_window7_224] INFO: Epoch: [271] [1070/1251] eta: 0:01:55 lr: 0.000031 loss: 2.6963 (2.6737) grad_norm: 3.3834 (3.5289) time: 0.6334 [2021-03-28 12:52:32 swin_base_patch4_window7_224] INFO: Epoch: [271] [1080/1251] eta: 0:01:48 lr: 0.000031 loss: 2.6963 (2.6743) grad_norm: 3.2764 (3.5267) time: 0.6322 [2021-03-28 12:52:38 swin_base_patch4_window7_224] INFO: Epoch: [271] [1090/1251] eta: 0:01:42 lr: 0.000031 loss: 2.7055 (2.6747) grad_norm: 3.0574 (3.5238) time: 0.6302 [2021-03-28 12:52:44 swin_base_patch4_window7_224] INFO: Epoch: [271] [1100/1251] eta: 0:01:36 lr: 0.000031 loss: 2.8215 (2.6766) grad_norm: 3.3954 (3.5260) time: 0.6326 [2021-03-28 12:52:51 swin_base_patch4_window7_224] INFO: Epoch: [271] [1110/1251] eta: 0:01:29 lr: 0.000031 loss: 2.7930 (2.6767) grad_norm: 3.5343 (3.5253) time: 0.6319 [2021-03-28 12:52:57 swin_base_patch4_window7_224] INFO: Epoch: [271] [1120/1251] eta: 0:01:23 lr: 0.000031 loss: 2.7634 (2.6760) grad_norm: 3.5805 (3.5258) time: 0.6271 [2021-03-28 12:53:03 swin_base_patch4_window7_224] INFO: Epoch: [271] [1130/1251] eta: 0:01:16 lr: 0.000031 loss: 2.8404 (2.6775) grad_norm: 3.5573 (3.5275) time: 0.6260 [2021-03-28 12:53:09 swin_base_patch4_window7_224] INFO: Epoch: [271] [1140/1251] eta: 0:01:10 lr: 0.000031 loss: 2.8404 (2.6775) grad_norm: 3.2138 (3.5250) time: 0.6254 [2021-03-28 12:53:16 swin_base_patch4_window7_224] INFO: Epoch: [271] [1150/1251] eta: 0:01:04 lr: 0.000031 loss: 2.4259 (2.6748) grad_norm: 3.1331 (3.5260) time: 0.6286 [2021-03-28 12:53:22 swin_base_patch4_window7_224] INFO: Epoch: [271] [1160/1251] eta: 0:00:57 lr: 0.000031 loss: 2.4057 (2.6735) grad_norm: 3.1813 (3.5231) time: 0.6277 [2021-03-28 12:53:28 swin_base_patch4_window7_224] INFO: Epoch: [271] [1170/1251] eta: 0:00:51 lr: 0.000031 loss: 2.6157 (2.6733) grad_norm: 3.3887 (3.5224) time: 0.6322 [2021-03-28 12:53:35 swin_base_patch4_window7_224] INFO: Epoch: [271] [1180/1251] eta: 0:00:45 lr: 0.000031 loss: 2.5278 (2.6718) grad_norm: 3.4016 (3.5296) time: 0.6342 [2021-03-28 12:53:41 swin_base_patch4_window7_224] INFO: Epoch: [271] [1190/1251] eta: 0:00:38 lr: 0.000031 loss: 2.5117 (2.6712) grad_norm: 3.3365 (3.5288) time: 0.6341 [2021-03-28 12:53:47 swin_base_patch4_window7_224] INFO: Epoch: [271] [1200/1251] eta: 0:00:32 lr: 0.000031 loss: 2.7143 (2.6716) grad_norm: 3.1897 (3.5289) time: 0.6379 [2021-03-28 12:53:54 swin_base_patch4_window7_224] INFO: Epoch: [271] [1210/1251] eta: 0:00:26 lr: 0.000031 loss: 2.7212 (2.6708) grad_norm: 3.2396 (3.5283) time: 0.6461 [2021-03-28 12:54:00 swin_base_patch4_window7_224] INFO: Epoch: [271] [1220/1251] eta: 0:00:19 lr: 0.000031 loss: 2.7703 (2.6727) grad_norm: 3.2902 (3.5283) time: 0.6454 [2021-03-28 12:54:07 swin_base_patch4_window7_224] INFO: Epoch: [271] [1230/1251] eta: 0:00:13 lr: 0.000031 loss: 2.7554 (2.6724) grad_norm: 3.1750 (3.5275) time: 0.6352 [2021-03-28 12:54:13 swin_base_patch4_window7_224] INFO: Epoch: [271] [1240/1251] eta: 0:00:06 lr: 0.000031 loss: 2.5570 (2.6699) grad_norm: 3.1411 (3.5267) time: 0.6254 [2021-03-28 12:54:19 swin_base_patch4_window7_224] INFO: Epoch: [271] [1250/1251] eta: 0:00:00 lr: 0.000031 loss: 2.6772 (2.6707) grad_norm: 3.3839 (3.5275) time: 0.6144 [2021-03-28 12:54:31 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:13 loss: 0.6380 (0.6380) acc1: 84.3750 (84.3750) acc5: 95.3125 (95.3125) [2021-03-28 12:54:34 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.6410 (0.7106) acc1: 84.3750 (82.2443) acc5: 96.8750 (97.0170) [2021-03-28 12:54:36 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7135 (0.7257) acc1: 82.8125 (82.6637) acc5: 96.8750 (96.8006) [2021-03-28 12:54:39 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7312 (0.7432) acc1: 81.2500 (82.3085) acc5: 96.8750 (96.6230) [2021-03-28 12:54:41 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7589 (0.7619) acc1: 81.2500 (81.9360) acc5: 96.8750 (96.6082) [2021-03-28 12:54:42 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7546 (0.7537) acc1: 81.2500 (82.1760) acc5: 96.8750 (96.5440) [2021-03-28 12:55:01 swin_base_patch4_window7_224] INFO: * Acc@1 83.156 Acc@5 96.358 loss 0.741 [2021-03-28 12:55:01 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.2% [2021-03-28 12:55:01 swin_base_patch4_window7_224] INFO: Max accuracy: 83.28% [2021-03-28 12:55:05 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 0/1251] eta: 1:29:08 lr: 0.000031 loss: 2.8302 (2.8302) grad_norm: 5.9636 (5.9636) time: 4.2757 [2021-03-28 12:55:12 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 10/1251] eta: 0:19:54 lr: 0.000031 loss: 2.7897 (2.6961) grad_norm: 3.3555 (3.5624) time: 0.9629 [2021-03-28 12:55:18 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 20/1251] eta: 0:16:28 lr: 0.000031 loss: 2.7306 (2.6957) grad_norm: 3.3555 (3.4611) time: 0.6296 [2021-03-28 12:55:24 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 30/1251] eta: 0:15:12 lr: 0.000031 loss: 2.7183 (2.6408) grad_norm: 3.1052 (3.3836) time: 0.6292 [2021-03-28 12:55:31 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 40/1251] eta: 0:14:33 lr: 0.000031 loss: 2.7183 (2.7082) grad_norm: 3.2301 (3.6694) time: 0.6352 [2021-03-28 12:55:37 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 50/1251] eta: 0:14:06 lr: 0.000031 loss: 2.7180 (2.6692) grad_norm: 3.6735 (3.6623) time: 0.6388 [2021-03-28 12:55:43 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 60/1251] eta: 0:13:45 lr: 0.000031 loss: 2.5017 (2.6490) grad_norm: 3.2303 (3.5789) time: 0.6348 [2021-03-28 12:55:50 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 70/1251] eta: 0:13:30 lr: 0.000031 loss: 2.6161 (2.6451) grad_norm: 3.3267 (3.6006) time: 0.6373 [2021-03-28 12:55:56 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 80/1251] eta: 0:13:15 lr: 0.000031 loss: 2.6529 (2.6530) grad_norm: 3.7081 (3.6394) time: 0.6373 [2021-03-28 12:56:02 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 90/1251] eta: 0:13:02 lr: 0.000031 loss: 2.4989 (2.6219) grad_norm: 3.2717 (3.5784) time: 0.6315 [2021-03-28 12:56:09 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 100/1251] eta: 0:12:50 lr: 0.000031 loss: 2.6615 (2.6469) grad_norm: 3.1773 (3.5503) time: 0.6307 [2021-03-28 12:56:15 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 110/1251] eta: 0:12:39 lr: 0.000031 loss: 2.8291 (2.6529) grad_norm: 3.3925 (3.5909) time: 0.6299 [2021-03-28 12:56:21 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 120/1251] eta: 0:12:30 lr: 0.000031 loss: 2.8302 (2.6691) grad_norm: 3.3896 (3.6108) time: 0.6313 [2021-03-28 12:56:28 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 130/1251] eta: 0:12:20 lr: 0.000031 loss: 2.9630 (2.6917) grad_norm: 3.2359 (3.5863) time: 0.6321 [2021-03-28 12:56:34 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 140/1251] eta: 0:12:11 lr: 0.000031 loss: 2.7198 (2.6720) grad_norm: 2.9930 (3.5598) time: 0.6305 [2021-03-28 12:56:40 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 150/1251] eta: 0:12:03 lr: 0.000031 loss: 2.5003 (2.6611) grad_norm: 3.2843 (3.5696) time: 0.6318 [2021-03-28 12:56:47 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 160/1251] eta: 0:11:55 lr: 0.000031 loss: 2.6525 (2.6684) grad_norm: 3.2843 (3.5748) time: 0.6349 [2021-03-28 12:56:53 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 170/1251] eta: 0:11:48 lr: 0.000031 loss: 2.7006 (2.6724) grad_norm: 3.1440 (3.5810) time: 0.6405 [2021-03-28 12:57:00 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 180/1251] eta: 0:11:40 lr: 0.000031 loss: 2.7006 (2.6698) grad_norm: 3.1440 (3.5860) time: 0.6426 [2021-03-28 12:57:06 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 190/1251] eta: 0:11:33 lr: 0.000031 loss: 2.5744 (2.6629) grad_norm: 3.3773 (3.5875) time: 0.6385 [2021-03-28 12:57:12 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 200/1251] eta: 0:11:25 lr: 0.000031 loss: 2.6577 (2.6636) grad_norm: 3.3471 (3.5768) time: 0.6377 [2021-03-28 12:57:19 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 210/1251] eta: 0:11:18 lr: 0.000031 loss: 2.7908 (2.6734) grad_norm: 3.2793 (3.5954) time: 0.6416 [2021-03-28 12:57:25 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 220/1251] eta: 0:11:11 lr: 0.000031 loss: 2.8786 (2.6768) grad_norm: 3.3116 (3.5851) time: 0.6360 [2021-03-28 12:57:31 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 230/1251] eta: 0:11:03 lr: 0.000031 loss: 2.6926 (2.6803) grad_norm: 3.1700 (3.5734) time: 0.6287 [2021-03-28 12:57:38 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 240/1251] eta: 0:10:56 lr: 0.000031 loss: 2.8105 (2.6866) grad_norm: 3.4114 (3.5883) time: 0.6291 [2021-03-28 12:57:44 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 250/1251] eta: 0:10:49 lr: 0.000031 loss: 2.7408 (2.6837) grad_norm: 3.6184 (3.5940) time: 0.6278 [2021-03-28 12:57:50 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 260/1251] eta: 0:10:42 lr: 0.000031 loss: 2.7516 (2.6883) grad_norm: 3.6595 (3.6076) time: 0.6347 [2021-03-28 12:57:57 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 270/1251] eta: 0:10:35 lr: 0.000031 loss: 2.8157 (2.6838) grad_norm: 3.4286 (3.6146) time: 0.6396 [2021-03-28 12:58:03 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 280/1251] eta: 0:10:28 lr: 0.000031 loss: 2.6110 (2.6840) grad_norm: 3.2454 (3.5977) time: 0.6399 [2021-03-28 12:58:09 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 290/1251] eta: 0:10:21 lr: 0.000031 loss: 2.7480 (2.6805) grad_norm: 3.2786 (3.5950) time: 0.6392 [2021-03-28 12:58:16 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 300/1251] eta: 0:10:14 lr: 0.000031 loss: 2.6466 (2.6760) grad_norm: 3.5265 (3.5953) time: 0.6322 [2021-03-28 12:58:22 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 310/1251] eta: 0:10:08 lr: 0.000031 loss: 2.7667 (2.6761) grad_norm: 3.4398 (3.6035) time: 0.6327 [2021-03-28 12:58:28 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 320/1251] eta: 0:10:00 lr: 0.000031 loss: 2.7927 (2.6793) grad_norm: 3.3632 (3.5964) time: 0.6299 [2021-03-28 12:58:35 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 330/1251] eta: 0:09:54 lr: 0.000031 loss: 2.8501 (2.6810) grad_norm: 3.3632 (3.6029) time: 0.6311 [2021-03-28 12:58:41 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 340/1251] eta: 0:09:47 lr: 0.000031 loss: 2.8248 (2.6829) grad_norm: 3.1799 (3.6080) time: 0.6344 [2021-03-28 12:58:47 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 350/1251] eta: 0:09:40 lr: 0.000031 loss: 2.8085 (2.6870) grad_norm: 3.1557 (3.6202) time: 0.6289 [2021-03-28 12:58:54 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 360/1251] eta: 0:09:33 lr: 0.000031 loss: 2.8085 (2.6898) grad_norm: 3.0798 (3.6112) time: 0.6332 [2021-03-28 12:59:00 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 370/1251] eta: 0:09:27 lr: 0.000031 loss: 2.8314 (2.6912) grad_norm: 3.1994 (3.6098) time: 0.6353 [2021-03-28 12:59:06 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 380/1251] eta: 0:09:20 lr: 0.000031 loss: 2.8395 (2.6921) grad_norm: 3.6906 (3.6232) time: 0.6371 [2021-03-28 12:59:13 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 390/1251] eta: 0:09:13 lr: 0.000031 loss: 2.5541 (2.6848) grad_norm: 3.6841 (3.6305) time: 0.6345 [2021-03-28 12:59:19 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 400/1251] eta: 0:09:07 lr: 0.000031 loss: 2.5524 (2.6815) grad_norm: 3.5152 (3.6380) time: 0.6343 [2021-03-28 12:59:25 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 410/1251] eta: 0:09:00 lr: 0.000031 loss: 2.6668 (2.6797) grad_norm: 3.4246 (3.6446) time: 0.6372 [2021-03-28 12:59:32 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 420/1251] eta: 0:08:53 lr: 0.000031 loss: 2.7508 (2.6828) grad_norm: 3.1177 (3.6466) time: 0.6267 [2021-03-28 12:59:38 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 430/1251] eta: 0:08:47 lr: 0.000031 loss: 2.6141 (2.6766) grad_norm: 3.3715 (3.6536) time: 0.6277 [2021-03-28 12:59:44 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 440/1251] eta: 0:08:40 lr: 0.000031 loss: 2.5796 (2.6765) grad_norm: 3.3715 (3.6493) time: 0.6360 [2021-03-28 12:59:51 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 450/1251] eta: 0:08:34 lr: 0.000031 loss: 2.8323 (2.6805) grad_norm: 3.2706 (3.6520) time: 0.6380 [2021-03-28 12:59:57 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 460/1251] eta: 0:08:27 lr: 0.000031 loss: 2.8684 (2.6805) grad_norm: 3.4588 (3.6571) time: 0.6364 [2021-03-28 13:00:03 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 470/1251] eta: 0:08:21 lr: 0.000031 loss: 2.8452 (2.6791) grad_norm: 3.2706 (3.6523) time: 0.6311 [2021-03-28 13:00:10 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 480/1251] eta: 0:08:14 lr: 0.000031 loss: 2.7073 (2.6795) grad_norm: 3.2706 (3.6498) time: 0.6357 [2021-03-28 13:00:16 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 490/1251] eta: 0:08:08 lr: 0.000031 loss: 2.8394 (2.6849) grad_norm: 3.5269 (3.6512) time: 0.6340 [2021-03-28 13:00:22 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 500/1251] eta: 0:08:01 lr: 0.000031 loss: 2.8911 (2.6871) grad_norm: 3.4042 (3.6471) time: 0.6273 [2021-03-28 13:00:29 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 510/1251] eta: 0:07:55 lr: 0.000031 loss: 2.7612 (2.6850) grad_norm: 3.1655 (3.6476) time: 0.6352 [2021-03-28 13:00:35 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 520/1251] eta: 0:07:48 lr: 0.000031 loss: 2.7485 (2.6837) grad_norm: 3.3261 (3.6426) time: 0.6342 [2021-03-28 13:00:41 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 530/1251] eta: 0:07:41 lr: 0.000030 loss: 2.6995 (2.6834) grad_norm: 3.2064 (3.6340) time: 0.6305 [2021-03-28 13:00:48 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 540/1251] eta: 0:07:35 lr: 0.000030 loss: 2.6879 (2.6836) grad_norm: 3.2606 (3.6515) time: 0.6329 [2021-03-28 13:00:54 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 550/1251] eta: 0:07:29 lr: 0.000030 loss: 2.6440 (2.6818) grad_norm: 3.2606 (3.6457) time: 0.6392 [2021-03-28 13:01:00 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 560/1251] eta: 0:07:22 lr: 0.000030 loss: 2.6259 (2.6821) grad_norm: 3.1062 (inf) time: 0.6389 [2021-03-28 13:01:07 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 570/1251] eta: 0:07:16 lr: 0.000030 loss: 2.7824 (2.6819) grad_norm: 3.1752 (inf) time: 0.6298 [2021-03-28 13:01:13 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 580/1251] eta: 0:07:09 lr: 0.000030 loss: 2.7050 (2.6837) grad_norm: 3.0276 (inf) time: 0.6298 [2021-03-28 13:01:19 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 590/1251] eta: 0:07:03 lr: 0.000030 loss: 2.7496 (2.6871) grad_norm: 3.1691 (inf) time: 0.6298 [2021-03-28 13:01:26 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 600/1251] eta: 0:06:56 lr: 0.000030 loss: 2.7196 (2.6847) grad_norm: 3.1691 (inf) time: 0.6334 [2021-03-28 13:01:32 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 610/1251] eta: 0:06:50 lr: 0.000030 loss: 2.6925 (2.6843) grad_norm: 3.4688 (inf) time: 0.6351 [2021-03-28 13:01:38 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 620/1251] eta: 0:06:43 lr: 0.000030 loss: 2.8143 (2.6847) grad_norm: 3.2884 (inf) time: 0.6319 [2021-03-28 13:01:45 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 630/1251] eta: 0:06:37 lr: 0.000030 loss: 2.8508 (2.6856) grad_norm: 3.4057 (inf) time: 0.6303 [2021-03-28 13:01:51 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 640/1251] eta: 0:06:30 lr: 0.000030 loss: 2.7671 (2.6872) grad_norm: 3.4547 (inf) time: 0.6339 [2021-03-28 13:01:57 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 650/1251] eta: 0:06:24 lr: 0.000030 loss: 2.6745 (2.6850) grad_norm: 3.3915 (inf) time: 0.6385 [2021-03-28 13:02:04 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 660/1251] eta: 0:06:17 lr: 0.000030 loss: 2.5800 (2.6838) grad_norm: 3.3143 (inf) time: 0.6388 [2021-03-28 13:02:10 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 670/1251] eta: 0:06:11 lr: 0.000030 loss: 2.6559 (2.6835) grad_norm: 3.1833 (inf) time: 0.6363 [2021-03-28 13:02:17 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 680/1251] eta: 0:06:05 lr: 0.000030 loss: 2.6653 (2.6827) grad_norm: 3.1833 (inf) time: 0.6350 [2021-03-28 13:02:23 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 690/1251] eta: 0:05:58 lr: 0.000030 loss: 2.7236 (2.6848) grad_norm: 3.2661 (inf) time: 0.6364 [2021-03-28 13:02:29 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 700/1251] eta: 0:05:52 lr: 0.000030 loss: 2.7236 (2.6831) grad_norm: 3.2656 (inf) time: 0.6325 [2021-03-28 13:02:36 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 710/1251] eta: 0:05:45 lr: 0.000030 loss: 2.6191 (2.6814) grad_norm: 3.2656 (inf) time: 0.6293 [2021-03-28 13:02:42 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 720/1251] eta: 0:05:39 lr: 0.000030 loss: 2.6191 (2.6828) grad_norm: 3.2523 (inf) time: 0.6317 [2021-03-28 13:02:48 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 730/1251] eta: 0:05:32 lr: 0.000030 loss: 2.6976 (2.6802) grad_norm: 3.5267 (inf) time: 0.6340 [2021-03-28 13:02:55 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 740/1251] eta: 0:05:26 lr: 0.000030 loss: 2.8383 (2.6822) grad_norm: 3.4368 (inf) time: 0.6362 [2021-03-28 13:03:01 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 750/1251] eta: 0:05:20 lr: 0.000030 loss: 2.7786 (2.6790) grad_norm: 3.3778 (inf) time: 0.6354 [2021-03-28 13:03:07 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 760/1251] eta: 0:05:13 lr: 0.000030 loss: 2.6735 (2.6790) grad_norm: 3.5465 (inf) time: 0.6341 [2021-03-28 13:03:14 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 770/1251] eta: 0:05:07 lr: 0.000030 loss: 2.7891 (2.6774) grad_norm: 3.4136 (inf) time: 0.6358 [2021-03-28 13:03:20 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 780/1251] eta: 0:05:00 lr: 0.000030 loss: 2.5985 (2.6764) grad_norm: 3.4136 (inf) time: 0.6290 [2021-03-28 13:03:26 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 790/1251] eta: 0:04:54 lr: 0.000030 loss: 2.5656 (2.6756) grad_norm: 3.0661 (inf) time: 0.6347 [2021-03-28 13:03:33 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 800/1251] eta: 0:04:47 lr: 0.000030 loss: 2.6829 (2.6751) grad_norm: 3.2979 (inf) time: 0.6349 [2021-03-28 13:03:39 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 810/1251] eta: 0:04:41 lr: 0.000030 loss: 2.6994 (2.6733) grad_norm: 3.3290 (inf) time: 0.6298 [2021-03-28 13:03:45 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 820/1251] eta: 0:04:35 lr: 0.000030 loss: 2.6614 (2.6715) grad_norm: 3.0742 (inf) time: 0.6313 [2021-03-28 13:03:51 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 830/1251] eta: 0:04:28 lr: 0.000030 loss: 2.6338 (2.6718) grad_norm: 3.3040 (inf) time: 0.6282 [2021-03-28 13:03:58 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 840/1251] eta: 0:04:22 lr: 0.000030 loss: 2.5950 (2.6709) grad_norm: 3.4108 (inf) time: 0.6284 [2021-03-28 13:04:04 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 850/1251] eta: 0:04:15 lr: 0.000030 loss: 2.6644 (2.6720) grad_norm: 3.3604 (inf) time: 0.6262 [2021-03-28 13:04:10 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 860/1251] eta: 0:04:09 lr: 0.000030 loss: 2.7920 (2.6748) grad_norm: 3.1581 (inf) time: 0.6303 [2021-03-28 13:04:17 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 870/1251] eta: 0:04:02 lr: 0.000030 loss: 2.9556 (2.6759) grad_norm: 3.1752 (inf) time: 0.6342 [2021-03-28 13:04:23 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 880/1251] eta: 0:03:56 lr: 0.000030 loss: 2.8111 (2.6762) grad_norm: 3.4404 (inf) time: 0.6323 [2021-03-28 13:04:29 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 890/1251] eta: 0:03:50 lr: 0.000030 loss: 2.6889 (2.6712) grad_norm: 3.2527 (inf) time: 0.6337 [2021-03-28 13:04:36 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 900/1251] eta: 0:03:43 lr: 0.000030 loss: 2.5661 (2.6702) grad_norm: 3.2527 (inf) time: 0.6363 [2021-03-28 13:04:42 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 910/1251] eta: 0:03:37 lr: 0.000030 loss: 2.8255 (2.6721) grad_norm: 3.1194 (inf) time: 0.6373 [2021-03-28 13:04:49 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 920/1251] eta: 0:03:31 lr: 0.000030 loss: 2.6542 (2.6709) grad_norm: 3.1194 (inf) time: 0.6404 [2021-03-28 13:04:55 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 930/1251] eta: 0:03:24 lr: 0.000030 loss: 2.6542 (2.6702) grad_norm: 3.2352 (inf) time: 0.6382 [2021-03-28 13:05:01 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 940/1251] eta: 0:03:18 lr: 0.000030 loss: 2.7401 (2.6721) grad_norm: 3.2142 (inf) time: 0.6357 [2021-03-28 13:05:08 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 950/1251] eta: 0:03:11 lr: 0.000030 loss: 2.8984 (2.6727) grad_norm: 3.3201 (inf) time: 0.6365 [2021-03-28 13:05:14 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 960/1251] eta: 0:03:05 lr: 0.000030 loss: 2.7287 (2.6702) grad_norm: 3.3355 (inf) time: 0.6293 [2021-03-28 13:05:20 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 970/1251] eta: 0:02:59 lr: 0.000030 loss: 2.5228 (2.6691) grad_norm: 3.2487 (inf) time: 0.6256 [2021-03-28 13:05:26 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 980/1251] eta: 0:02:52 lr: 0.000030 loss: 2.6636 (2.6713) grad_norm: 3.2765 (inf) time: 0.6291 [2021-03-28 13:05:33 swin_base_patch4_window7_224] INFO: Epoch: [272] [ 990/1251] eta: 0:02:46 lr: 0.000030 loss: 2.8928 (2.6716) grad_norm: 3.5508 (inf) time: 0.6282 [2021-03-28 13:05:39 swin_base_patch4_window7_224] INFO: Epoch: [272] [1000/1251] eta: 0:02:39 lr: 0.000030 loss: 2.7449 (2.6717) grad_norm: 3.5278 (inf) time: 0.6332 [2021-03-28 13:05:45 swin_base_patch4_window7_224] INFO: Epoch: [272] [1010/1251] eta: 0:02:33 lr: 0.000030 loss: 2.7129 (2.6704) grad_norm: 3.2805 (inf) time: 0.6379 [2021-03-28 13:05:52 swin_base_patch4_window7_224] INFO: Epoch: [272] [1020/1251] eta: 0:02:27 lr: 0.000030 loss: 2.7268 (2.6714) grad_norm: 3.2805 (inf) time: 0.6378 [2021-03-28 13:05:58 swin_base_patch4_window7_224] INFO: Epoch: [272] [1030/1251] eta: 0:02:20 lr: 0.000030 loss: 2.7268 (2.6702) grad_norm: 3.2724 (inf) time: 0.6338 [2021-03-28 13:06:04 swin_base_patch4_window7_224] INFO: Epoch: [272] [1040/1251] eta: 0:02:14 lr: 0.000030 loss: 2.7175 (2.6711) grad_norm: 3.5376 (inf) time: 0.6264 [2021-03-28 13:06:11 swin_base_patch4_window7_224] INFO: Epoch: [272] [1050/1251] eta: 0:02:08 lr: 0.000030 loss: 2.7990 (2.6723) grad_norm: 3.5376 (inf) time: 0.6276 [2021-03-28 13:06:17 swin_base_patch4_window7_224] INFO: Epoch: [272] [1060/1251] eta: 0:02:01 lr: 0.000030 loss: 2.6677 (2.6711) grad_norm: 3.2824 (inf) time: 0.6324 [2021-03-28 13:06:23 swin_base_patch4_window7_224] INFO: Epoch: [272] [1070/1251] eta: 0:01:55 lr: 0.000030 loss: 2.4958 (2.6700) grad_norm: 3.1423 (inf) time: 0.6377 [2021-03-28 13:06:30 swin_base_patch4_window7_224] INFO: Epoch: [272] [1080/1251] eta: 0:01:48 lr: 0.000030 loss: 2.6571 (2.6719) grad_norm: 3.1709 (inf) time: 0.6377 [2021-03-28 13:06:36 swin_base_patch4_window7_224] INFO: Epoch: [272] [1090/1251] eta: 0:01:42 lr: 0.000030 loss: 2.8167 (2.6720) grad_norm: 3.5312 (inf) time: 0.6332 [2021-03-28 13:06:42 swin_base_patch4_window7_224] INFO: Epoch: [272] [1100/1251] eta: 0:01:36 lr: 0.000030 loss: 2.7153 (2.6720) grad_norm: 3.6790 (inf) time: 0.6310 [2021-03-28 13:06:49 swin_base_patch4_window7_224] INFO: Epoch: [272] [1110/1251] eta: 0:01:29 lr: 0.000030 loss: 2.8388 (2.6734) grad_norm: 3.3712 (inf) time: 0.6316 [2021-03-28 13:06:55 swin_base_patch4_window7_224] INFO: Epoch: [272] [1120/1251] eta: 0:01:23 lr: 0.000030 loss: 2.8503 (2.6749) grad_norm: 3.1723 (inf) time: 0.6322 [2021-03-28 13:07:01 swin_base_patch4_window7_224] INFO: Epoch: [272] [1130/1251] eta: 0:01:17 lr: 0.000030 loss: 2.6356 (2.6733) grad_norm: 3.1409 (inf) time: 0.6329 [2021-03-28 13:07:08 swin_base_patch4_window7_224] INFO: Epoch: [272] [1140/1251] eta: 0:01:10 lr: 0.000030 loss: 2.4833 (2.6716) grad_norm: 3.0043 (inf) time: 0.6381 [2021-03-28 13:07:14 swin_base_patch4_window7_224] INFO: Epoch: [272] [1150/1251] eta: 0:01:04 lr: 0.000030 loss: 2.4768 (2.6700) grad_norm: 3.0686 (inf) time: 0.6377 [2021-03-28 13:07:20 swin_base_patch4_window7_224] INFO: Epoch: [272] [1160/1251] eta: 0:00:57 lr: 0.000030 loss: 2.7596 (2.6700) grad_norm: 3.2586 (inf) time: 0.6282 [2021-03-28 13:07:27 swin_base_patch4_window7_224] INFO: Epoch: [272] [1170/1251] eta: 0:00:51 lr: 0.000030 loss: 2.6744 (2.6692) grad_norm: 3.1518 (inf) time: 0.6289 [2021-03-28 13:07:33 swin_base_patch4_window7_224] INFO: Epoch: [272] [1180/1251] eta: 0:00:45 lr: 0.000030 loss: 2.6431 (2.6692) grad_norm: 3.1518 (inf) time: 0.6361 [2021-03-28 13:07:39 swin_base_patch4_window7_224] INFO: Epoch: [272] [1190/1251] eta: 0:00:38 lr: 0.000030 loss: 2.6385 (2.6689) grad_norm: 3.2788 (inf) time: 0.6321 [2021-03-28 13:07:46 swin_base_patch4_window7_224] INFO: Epoch: [272] [1200/1251] eta: 0:00:32 lr: 0.000030 loss: 2.7106 (2.6689) grad_norm: 3.2840 (inf) time: 0.6327 [2021-03-28 13:07:52 swin_base_patch4_window7_224] INFO: Epoch: [272] [1210/1251] eta: 0:00:26 lr: 0.000030 loss: 2.5644 (2.6674) grad_norm: 3.2534 (inf) time: 0.6364 [2021-03-28 13:07:58 swin_base_patch4_window7_224] INFO: Epoch: [272] [1220/1251] eta: 0:00:19 lr: 0.000030 loss: 2.5809 (2.6684) grad_norm: 3.3812 (inf) time: 0.6320 [2021-03-28 13:08:05 swin_base_patch4_window7_224] INFO: Epoch: [272] [1230/1251] eta: 0:00:13 lr: 0.000030 loss: 2.6991 (2.6667) grad_norm: 3.3432 (inf) time: 0.6346 [2021-03-28 13:08:11 swin_base_patch4_window7_224] INFO: Epoch: [272] [1240/1251] eta: 0:00:07 lr: 0.000030 loss: 2.5112 (2.6668) grad_norm: 3.3169 (inf) time: 0.6346 [2021-03-28 13:08:17 swin_base_patch4_window7_224] INFO: Epoch: [272] [1250/1251] eta: 0:00:00 lr: 0.000030 loss: 2.6527 (2.6674) grad_norm: 3.4257 (inf) time: 0.6292 [2021-03-28 13:08:29 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:46 loss: 0.7941 (0.7941) acc1: 79.6875 (79.6875) acc5: 98.4375 (98.4375) [2021-03-28 13:08:31 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.6958 (0.6759) acc1: 84.3750 (83.5227) acc5: 96.8750 (96.7330) [2021-03-28 13:08:32 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7250 (0.7375) acc1: 81.2500 (82.2173) acc5: 96.8750 (96.6518) [2021-03-28 13:08:36 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7250 (0.7245) acc1: 81.2500 (82.6109) acc5: 96.8750 (96.6734) [2021-03-28 13:08:38 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7238 (0.7342) acc1: 84.3750 (82.6220) acc5: 95.3125 (96.4939) [2021-03-28 13:08:39 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7550 (0.7538) acc1: 81.2500 (82.2400) acc5: 95.3125 (96.3840) [2021-03-28 13:08:57 swin_base_patch4_window7_224] INFO: * Acc@1 83.336 Acc@5 96.400 loss 0.739 [2021-03-28 13:08:57 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.3% [2021-03-28 13:08:57 swin_base_patch4_window7_224] INFO: Max accuracy: 83.34% [2021-03-28 13:09:02 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 0/1251] eta: 1:34:06 lr: 0.000030 loss: 3.0869 (3.0869) grad_norm: 2.9948 (2.9948) time: 4.5138 [2021-03-28 13:09:08 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 10/1251] eta: 0:20:37 lr: 0.000030 loss: 2.7820 (2.6061) grad_norm: 3.4700 (3.4377) time: 0.9976 [2021-03-28 13:09:15 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 20/1251] eta: 0:17:00 lr: 0.000030 loss: 2.7359 (2.6401) grad_norm: 3.2788 (3.4562) time: 0.6445 [2021-03-28 13:09:21 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 30/1251] eta: 0:15:35 lr: 0.000030 loss: 2.7564 (2.6935) grad_norm: 3.2788 (3.5387) time: 0.6387 [2021-03-28 13:09:27 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 40/1251] eta: 0:14:47 lr: 0.000030 loss: 2.7564 (2.6609) grad_norm: 3.3790 (3.5586) time: 0.6325 [2021-03-28 13:09:34 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 50/1251] eta: 0:14:16 lr: 0.000030 loss: 2.5075 (2.6254) grad_norm: 3.4254 (3.6315) time: 0.6316 [2021-03-28 13:09:40 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 60/1251] eta: 0:13:53 lr: 0.000030 loss: 2.6834 (2.6501) grad_norm: 3.5020 (3.7110) time: 0.6315 [2021-03-28 13:09:46 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 70/1251] eta: 0:13:35 lr: 0.000030 loss: 2.8201 (2.6470) grad_norm: 3.2929 (3.7611) time: 0.6321 [2021-03-28 13:09:53 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 80/1251] eta: 0:13:20 lr: 0.000030 loss: 2.8032 (2.6614) grad_norm: 3.2885 (3.7190) time: 0.6340 [2021-03-28 13:09:59 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 90/1251] eta: 0:13:07 lr: 0.000030 loss: 2.7654 (2.6626) grad_norm: 3.3654 (3.7196) time: 0.6358 [2021-03-28 13:10:05 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 100/1251] eta: 0:12:56 lr: 0.000030 loss: 2.4930 (2.6432) grad_norm: 3.6107 (3.7058) time: 0.6402 [2021-03-28 13:10:12 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 110/1251] eta: 0:12:46 lr: 0.000030 loss: 2.4662 (2.6253) grad_norm: 3.4611 (3.6838) time: 0.6426 [2021-03-28 13:10:18 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 120/1251] eta: 0:12:37 lr: 0.000030 loss: 2.5731 (2.6373) grad_norm: 3.5151 (3.7026) time: 0.6424 [2021-03-28 13:10:24 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 130/1251] eta: 0:12:26 lr: 0.000030 loss: 2.5429 (2.6175) grad_norm: 3.5766 (3.6913) time: 0.6339 [2021-03-28 13:10:31 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 140/1251] eta: 0:12:17 lr: 0.000029 loss: 2.6380 (2.6229) grad_norm: 3.5166 (3.7192) time: 0.6305 [2021-03-28 13:10:37 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 150/1251] eta: 0:12:09 lr: 0.000029 loss: 2.8034 (2.6382) grad_norm: 3.4194 (3.7098) time: 0.6377 [2021-03-28 13:10:44 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 160/1251] eta: 0:12:01 lr: 0.000029 loss: 2.6896 (2.6273) grad_norm: 3.2569 (3.6972) time: 0.6408 [2021-03-28 13:10:50 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 170/1251] eta: 0:11:53 lr: 0.000029 loss: 2.4683 (2.6319) grad_norm: 3.4760 (3.6821) time: 0.6414 [2021-03-28 13:10:56 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 180/1251] eta: 0:11:44 lr: 0.000029 loss: 2.4683 (2.6218) grad_norm: 3.2142 (3.7130) time: 0.6347 [2021-03-28 13:11:03 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 190/1251] eta: 0:11:37 lr: 0.000029 loss: 2.4658 (2.6193) grad_norm: 3.3319 (3.7090) time: 0.6322 [2021-03-28 13:11:09 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 200/1251] eta: 0:11:29 lr: 0.000029 loss: 2.8055 (2.6223) grad_norm: 3.2836 (3.6910) time: 0.6373 [2021-03-28 13:11:15 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 210/1251] eta: 0:11:21 lr: 0.000029 loss: 2.8327 (2.6334) grad_norm: 3.2836 (3.7029) time: 0.6370 [2021-03-28 13:11:22 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 220/1251] eta: 0:11:14 lr: 0.000029 loss: 2.9460 (2.6325) grad_norm: 3.5127 (3.7117) time: 0.6318 [2021-03-28 13:11:28 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 230/1251] eta: 0:11:06 lr: 0.000029 loss: 2.7018 (2.6356) grad_norm: 3.3529 (3.7148) time: 0.6283 [2021-03-28 13:11:34 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 240/1251] eta: 0:10:58 lr: 0.000029 loss: 2.7985 (2.6444) grad_norm: 3.3529 (3.7309) time: 0.6251 [2021-03-28 13:11:41 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 250/1251] eta: 0:10:51 lr: 0.000029 loss: 2.7985 (2.6394) grad_norm: 3.3314 (3.7324) time: 0.6325 [2021-03-28 13:11:47 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 260/1251] eta: 0:10:44 lr: 0.000029 loss: 2.7569 (2.6452) grad_norm: 3.1744 (3.7175) time: 0.6330 [2021-03-28 13:11:53 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 270/1251] eta: 0:10:37 lr: 0.000029 loss: 2.7919 (2.6522) grad_norm: 3.2157 (3.7216) time: 0.6276 [2021-03-28 13:11:59 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 280/1251] eta: 0:10:29 lr: 0.000029 loss: 2.8088 (2.6521) grad_norm: 3.5511 (inf) time: 0.6285 [2021-03-28 13:12:06 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 290/1251] eta: 0:10:22 lr: 0.000029 loss: 2.8469 (2.6510) grad_norm: 3.6102 (inf) time: 0.6287 [2021-03-28 13:12:12 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 300/1251] eta: 0:10:15 lr: 0.000029 loss: 2.8469 (2.6487) grad_norm: 3.2401 (inf) time: 0.6314 [2021-03-28 13:12:18 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 310/1251] eta: 0:10:08 lr: 0.000029 loss: 2.8492 (2.6554) grad_norm: 3.2423 (inf) time: 0.6313 [2021-03-28 13:12:25 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 320/1251] eta: 0:10:01 lr: 0.000029 loss: 2.6887 (2.6547) grad_norm: 3.4408 (inf) time: 0.6255 [2021-03-28 13:12:31 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 330/1251] eta: 0:09:54 lr: 0.000029 loss: 2.6604 (2.6521) grad_norm: 3.2387 (inf) time: 0.6203 [2021-03-28 13:12:37 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 340/1251] eta: 0:09:47 lr: 0.000029 loss: 2.6659 (2.6543) grad_norm: 3.1432 (inf) time: 0.6281 [2021-03-28 13:12:43 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 350/1251] eta: 0:09:40 lr: 0.000029 loss: 2.6800 (2.6575) grad_norm: 3.4153 (inf) time: 0.6327 [2021-03-28 13:12:50 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 360/1251] eta: 0:09:33 lr: 0.000029 loss: 2.6724 (2.6527) grad_norm: 3.2643 (inf) time: 0.6255 [2021-03-28 13:12:56 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 370/1251] eta: 0:09:27 lr: 0.000029 loss: 2.6071 (2.6475) grad_norm: 3.2248 (inf) time: 0.6280 [2021-03-28 13:13:02 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 380/1251] eta: 0:09:20 lr: 0.000029 loss: 2.6266 (2.6447) grad_norm: 3.6000 (inf) time: 0.6302 [2021-03-28 13:13:09 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 390/1251] eta: 0:09:13 lr: 0.000029 loss: 2.7025 (2.6505) grad_norm: 3.8382 (inf) time: 0.6303 [2021-03-28 13:13:15 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 400/1251] eta: 0:09:06 lr: 0.000029 loss: 2.7163 (2.6497) grad_norm: 3.3920 (inf) time: 0.6328 [2021-03-28 13:13:21 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 410/1251] eta: 0:09:00 lr: 0.000029 loss: 2.6535 (2.6485) grad_norm: 3.2767 (inf) time: 0.6279 [2021-03-28 13:13:27 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 420/1251] eta: 0:08:53 lr: 0.000029 loss: 2.4648 (2.6439) grad_norm: 3.1685 (inf) time: 0.6265 [2021-03-28 13:13:34 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 430/1251] eta: 0:08:46 lr: 0.000029 loss: 2.4343 (2.6434) grad_norm: 3.2317 (inf) time: 0.6269 [2021-03-28 13:13:40 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 440/1251] eta: 0:08:40 lr: 0.000029 loss: 2.6620 (2.6460) grad_norm: 3.2566 (inf) time: 0.6349 [2021-03-28 13:13:47 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 450/1251] eta: 0:08:33 lr: 0.000029 loss: 2.6737 (2.6446) grad_norm: 3.1908 (inf) time: 0.6417 [2021-03-28 13:13:53 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 460/1251] eta: 0:08:27 lr: 0.000029 loss: 2.8604 (2.6462) grad_norm: 3.3098 (inf) time: 0.6345 [2021-03-28 13:13:59 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 470/1251] eta: 0:08:20 lr: 0.000029 loss: 2.6686 (2.6470) grad_norm: 3.4074 (inf) time: 0.6309 [2021-03-28 13:14:06 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 480/1251] eta: 0:08:14 lr: 0.000029 loss: 2.7987 (2.6501) grad_norm: 3.1548 (inf) time: 0.6367 [2021-03-28 13:14:12 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 490/1251] eta: 0:08:07 lr: 0.000029 loss: 2.7987 (2.6502) grad_norm: 3.1397 (inf) time: 0.6352 [2021-03-28 13:14:18 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 500/1251] eta: 0:08:01 lr: 0.000029 loss: 2.7619 (2.6531) grad_norm: 3.0993 (inf) time: 0.6357 [2021-03-28 13:14:25 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 510/1251] eta: 0:07:54 lr: 0.000029 loss: 2.8940 (2.6577) grad_norm: 3.3268 (inf) time: 0.6353 [2021-03-28 13:14:31 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 520/1251] eta: 0:07:48 lr: 0.000029 loss: 2.8940 (2.6597) grad_norm: 3.4011 (inf) time: 0.6330 [2021-03-28 13:14:37 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 530/1251] eta: 0:07:41 lr: 0.000029 loss: 2.6355 (2.6559) grad_norm: 3.4011 (inf) time: 0.6329 [2021-03-28 13:14:44 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 540/1251] eta: 0:07:35 lr: 0.000029 loss: 2.6355 (2.6554) grad_norm: 3.3528 (inf) time: 0.6336 [2021-03-28 13:14:50 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 550/1251] eta: 0:07:29 lr: 0.000029 loss: 2.7421 (2.6548) grad_norm: 3.3528 (inf) time: 0.6443 [2021-03-28 13:14:57 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 560/1251] eta: 0:07:22 lr: 0.000029 loss: 2.7792 (2.6588) grad_norm: 3.6051 (inf) time: 0.6489 [2021-03-28 13:15:03 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 570/1251] eta: 0:07:16 lr: 0.000029 loss: 2.6946 (2.6530) grad_norm: 3.3704 (inf) time: 0.6355 [2021-03-28 13:15:09 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 580/1251] eta: 0:07:09 lr: 0.000029 loss: 2.4303 (2.6526) grad_norm: 3.2453 (inf) time: 0.6240 [2021-03-28 13:15:15 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 590/1251] eta: 0:07:03 lr: 0.000029 loss: 2.7180 (2.6542) grad_norm: 3.2569 (inf) time: 0.6284 [2021-03-28 13:15:22 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 600/1251] eta: 0:06:56 lr: 0.000029 loss: 2.7180 (2.6516) grad_norm: 3.3374 (inf) time: 0.6328 [2021-03-28 13:15:28 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 610/1251] eta: 0:06:50 lr: 0.000029 loss: 2.7831 (2.6542) grad_norm: 3.3374 (inf) time: 0.6306 [2021-03-28 13:15:34 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 620/1251] eta: 0:06:43 lr: 0.000029 loss: 2.8044 (2.6532) grad_norm: 3.3195 (inf) time: 0.6338 [2021-03-28 13:15:41 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 630/1251] eta: 0:06:37 lr: 0.000029 loss: 2.5649 (2.6507) grad_norm: 3.3010 (inf) time: 0.6353 [2021-03-28 13:15:47 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 640/1251] eta: 0:06:30 lr: 0.000029 loss: 2.5678 (2.6509) grad_norm: 3.1861 (inf) time: 0.6326 [2021-03-28 13:15:53 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 650/1251] eta: 0:06:24 lr: 0.000029 loss: 2.7935 (2.6532) grad_norm: 3.3817 (inf) time: 0.6329 [2021-03-28 13:16:00 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 660/1251] eta: 0:06:17 lr: 0.000029 loss: 2.6757 (2.6519) grad_norm: 3.3616 (inf) time: 0.6354 [2021-03-28 13:16:06 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 670/1251] eta: 0:06:11 lr: 0.000029 loss: 2.6757 (2.6547) grad_norm: 3.3732 (inf) time: 0.6391 [2021-03-28 13:16:13 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 680/1251] eta: 0:06:05 lr: 0.000029 loss: 2.8969 (2.6565) grad_norm: 3.2526 (inf) time: 0.6393 [2021-03-28 13:16:19 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 690/1251] eta: 0:05:58 lr: 0.000029 loss: 2.6611 (2.6547) grad_norm: 3.1693 (inf) time: 0.6325 [2021-03-28 13:16:25 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 700/1251] eta: 0:05:52 lr: 0.000029 loss: 2.5763 (2.6515) grad_norm: 3.5450 (inf) time: 0.6319 [2021-03-28 13:16:32 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 710/1251] eta: 0:05:45 lr: 0.000029 loss: 2.7656 (2.6535) grad_norm: 3.4162 (inf) time: 0.6324 [2021-03-28 13:16:38 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 720/1251] eta: 0:05:39 lr: 0.000029 loss: 2.9433 (2.6543) grad_norm: 3.2527 (inf) time: 0.6316 [2021-03-28 13:16:44 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 730/1251] eta: 0:05:32 lr: 0.000029 loss: 2.8587 (2.6548) grad_norm: 3.4294 (inf) time: 0.6319 [2021-03-28 13:16:51 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 740/1251] eta: 0:05:26 lr: 0.000029 loss: 2.5691 (2.6513) grad_norm: 3.5573 (inf) time: 0.6311 [2021-03-28 13:16:57 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 750/1251] eta: 0:05:19 lr: 0.000029 loss: 2.5708 (2.6514) grad_norm: 3.5407 (inf) time: 0.6388 [2021-03-28 13:17:03 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 760/1251] eta: 0:05:13 lr: 0.000029 loss: 2.6499 (2.6503) grad_norm: 3.5538 (inf) time: 0.6366 [2021-03-28 13:17:10 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 770/1251] eta: 0:05:07 lr: 0.000029 loss: 2.5130 (2.6490) grad_norm: 3.3789 (inf) time: 0.6334 [2021-03-28 13:17:16 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 780/1251] eta: 0:05:00 lr: 0.000029 loss: 2.7128 (2.6488) grad_norm: 3.3236 (inf) time: 0.6332 [2021-03-28 13:17:22 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 790/1251] eta: 0:04:54 lr: 0.000029 loss: 2.7270 (2.6509) grad_norm: 3.2868 (inf) time: 0.6310 [2021-03-28 13:17:29 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 800/1251] eta: 0:04:47 lr: 0.000029 loss: 2.7211 (2.6482) grad_norm: 3.2692 (inf) time: 0.6347 [2021-03-28 13:17:35 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 810/1251] eta: 0:04:41 lr: 0.000029 loss: 2.5094 (2.6475) grad_norm: 3.3465 (inf) time: 0.6350 [2021-03-28 13:17:41 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 820/1251] eta: 0:04:35 lr: 0.000029 loss: 2.5455 (2.6485) grad_norm: 3.2717 (inf) time: 0.6283 [2021-03-28 13:17:48 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 830/1251] eta: 0:04:28 lr: 0.000029 loss: 2.5455 (2.6471) grad_norm: 3.2024 (inf) time: 0.6294 [2021-03-28 13:17:54 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 840/1251] eta: 0:04:22 lr: 0.000029 loss: 2.6639 (2.6478) grad_norm: 3.5013 (inf) time: 0.6345 [2021-03-28 13:18:00 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 850/1251] eta: 0:04:15 lr: 0.000029 loss: 2.8310 (2.6488) grad_norm: 3.5013 (inf) time: 0.6321 [2021-03-28 13:18:07 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 860/1251] eta: 0:04:09 lr: 0.000029 loss: 2.8324 (2.6500) grad_norm: 3.2777 (inf) time: 0.6335 [2021-03-28 13:18:13 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 870/1251] eta: 0:04:03 lr: 0.000029 loss: 2.8369 (2.6517) grad_norm: 3.3594 (inf) time: 0.6346 [2021-03-28 13:18:19 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 880/1251] eta: 0:03:56 lr: 0.000029 loss: 2.8827 (2.6548) grad_norm: 3.3314 (inf) time: 0.6279 [2021-03-28 13:18:25 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 890/1251] eta: 0:03:50 lr: 0.000029 loss: 2.8827 (2.6557) grad_norm: 3.3548 (inf) time: 0.6265 [2021-03-28 13:18:32 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 900/1251] eta: 0:03:43 lr: 0.000029 loss: 2.8493 (2.6571) grad_norm: 3.3583 (inf) time: 0.6280 [2021-03-28 13:18:38 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 910/1251] eta: 0:03:37 lr: 0.000029 loss: 2.7275 (2.6574) grad_norm: 3.2523 (inf) time: 0.6295 [2021-03-28 13:18:44 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 920/1251] eta: 0:03:31 lr: 0.000029 loss: 2.6667 (2.6579) grad_norm: 3.4520 (inf) time: 0.6379 [2021-03-28 13:18:51 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 930/1251] eta: 0:03:24 lr: 0.000029 loss: 2.6667 (2.6573) grad_norm: 3.0955 (inf) time: 0.6390 [2021-03-28 13:18:57 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 940/1251] eta: 0:03:18 lr: 0.000029 loss: 2.7250 (2.6581) grad_norm: 3.1545 (inf) time: 0.6315 [2021-03-28 13:19:03 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 950/1251] eta: 0:03:11 lr: 0.000029 loss: 2.8442 (2.6605) grad_norm: 3.2697 (inf) time: 0.6325 [2021-03-28 13:19:10 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 960/1251] eta: 0:03:05 lr: 0.000029 loss: 2.7491 (2.6584) grad_norm: 3.5656 (inf) time: 0.6376 [2021-03-28 13:19:16 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 970/1251] eta: 0:02:59 lr: 0.000029 loss: 2.3536 (2.6559) grad_norm: 3.5807 (inf) time: 0.6373 [2021-03-28 13:19:23 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 980/1251] eta: 0:02:52 lr: 0.000029 loss: 2.7636 (2.6585) grad_norm: 3.5618 (inf) time: 0.6349 [2021-03-28 13:19:29 swin_base_patch4_window7_224] INFO: Epoch: [273] [ 990/1251] eta: 0:02:46 lr: 0.000029 loss: 2.8553 (2.6591) grad_norm: 3.8311 (inf) time: 0.6304 [2021-03-28 13:19:35 swin_base_patch4_window7_224] INFO: Epoch: [273] [1000/1251] eta: 0:02:39 lr: 0.000029 loss: 2.8000 (2.6598) grad_norm: 3.6833 (inf) time: 0.6302 [2021-03-28 13:19:42 swin_base_patch4_window7_224] INFO: Epoch: [273] [1010/1251] eta: 0:02:33 lr: 0.000029 loss: 2.7522 (2.6594) grad_norm: 3.1828 (inf) time: 0.6345 [2021-03-28 13:19:48 swin_base_patch4_window7_224] INFO: Epoch: [273] [1020/1251] eta: 0:02:27 lr: 0.000028 loss: 2.6103 (2.6576) grad_norm: 3.5155 (inf) time: 0.6351 [2021-03-28 13:19:54 swin_base_patch4_window7_224] INFO: Epoch: [273] [1030/1251] eta: 0:02:20 lr: 0.000028 loss: 2.5731 (2.6562) grad_norm: 3.6025 (inf) time: 0.6382 [2021-03-28 13:20:01 swin_base_patch4_window7_224] INFO: Epoch: [273] [1040/1251] eta: 0:02:14 lr: 0.000028 loss: 2.5899 (2.6557) grad_norm: 3.2775 (inf) time: 0.6435 [2021-03-28 13:20:07 swin_base_patch4_window7_224] INFO: Epoch: [273] [1050/1251] eta: 0:02:08 lr: 0.000028 loss: 2.8119 (2.6565) grad_norm: 3.1578 (inf) time: 0.6422 [2021-03-28 13:20:14 swin_base_patch4_window7_224] INFO: Epoch: [273] [1060/1251] eta: 0:02:01 lr: 0.000028 loss: 2.8314 (2.6573) grad_norm: 3.1578 (inf) time: 0.6408 [2021-03-28 13:20:20 swin_base_patch4_window7_224] INFO: Epoch: [273] [1070/1251] eta: 0:01:55 lr: 0.000028 loss: 2.7038 (2.6559) grad_norm: 3.2087 (inf) time: 0.6318 [2021-03-28 13:20:26 swin_base_patch4_window7_224] INFO: Epoch: [273] [1080/1251] eta: 0:01:48 lr: 0.000028 loss: 2.6483 (2.6581) grad_norm: 3.3561 (inf) time: 0.6298 [2021-03-28 13:20:32 swin_base_patch4_window7_224] INFO: Epoch: [273] [1090/1251] eta: 0:01:42 lr: 0.000028 loss: 2.7559 (2.6580) grad_norm: 3.3390 (inf) time: 0.6335 [2021-03-28 13:20:39 swin_base_patch4_window7_224] INFO: Epoch: [273] [1100/1251] eta: 0:01:36 lr: 0.000028 loss: 2.7559 (2.6587) grad_norm: 3.3894 (inf) time: 0.6311 [2021-03-28 13:20:45 swin_base_patch4_window7_224] INFO: Epoch: [273] [1110/1251] eta: 0:01:29 lr: 0.000028 loss: 2.5671 (2.6563) grad_norm: 3.3894 (inf) time: 0.6305 [2021-03-28 13:20:51 swin_base_patch4_window7_224] INFO: Epoch: [273] [1120/1251] eta: 0:01:23 lr: 0.000028 loss: 2.4677 (2.6545) grad_norm: 3.2388 (inf) time: 0.6267 [2021-03-28 13:20:58 swin_base_patch4_window7_224] INFO: Epoch: [273] [1130/1251] eta: 0:01:17 lr: 0.000028 loss: 2.5513 (2.6540) grad_norm: 3.3493 (inf) time: 0.6251 [2021-03-28 13:21:04 swin_base_patch4_window7_224] INFO: Epoch: [273] [1140/1251] eta: 0:01:10 lr: 0.000028 loss: 2.9221 (2.6562) grad_norm: 3.5325 (inf) time: 0.6287 [2021-03-28 13:21:10 swin_base_patch4_window7_224] INFO: Epoch: [273] [1150/1251] eta: 0:01:04 lr: 0.000028 loss: 2.6685 (2.6544) grad_norm: 3.4471 (inf) time: 0.6304 [2021-03-28 13:21:16 swin_base_patch4_window7_224] INFO: Epoch: [273] [1160/1251] eta: 0:00:57 lr: 0.000028 loss: 2.7512 (2.6559) grad_norm: 3.2868 (inf) time: 0.6292 [2021-03-28 13:21:23 swin_base_patch4_window7_224] INFO: Epoch: [273] [1170/1251] eta: 0:00:51 lr: 0.000028 loss: 2.8745 (2.6564) grad_norm: 3.3352 (inf) time: 0.6296 [2021-03-28 13:21:29 swin_base_patch4_window7_224] INFO: Epoch: [273] [1180/1251] eta: 0:00:45 lr: 0.000028 loss: 2.7599 (2.6563) grad_norm: 3.5035 (inf) time: 0.6237 [2021-03-28 13:21:35 swin_base_patch4_window7_224] INFO: Epoch: [273] [1190/1251] eta: 0:00:38 lr: 0.000028 loss: 2.5000 (2.6547) grad_norm: 3.2686 (inf) time: 0.6278 [2021-03-28 13:21:42 swin_base_patch4_window7_224] INFO: Epoch: [273] [1200/1251] eta: 0:00:32 lr: 0.000028 loss: 2.6625 (2.6568) grad_norm: 3.1265 (inf) time: 0.6371 [2021-03-28 13:21:48 swin_base_patch4_window7_224] INFO: Epoch: [273] [1210/1251] eta: 0:00:26 lr: 0.000028 loss: 2.7728 (2.6580) grad_norm: 3.2661 (inf) time: 0.6325 [2021-03-28 13:21:54 swin_base_patch4_window7_224] INFO: Epoch: [273] [1220/1251] eta: 0:00:19 lr: 0.000028 loss: 2.6976 (2.6586) grad_norm: 3.2661 (inf) time: 0.6320 [2021-03-28 13:22:01 swin_base_patch4_window7_224] INFO: Epoch: [273] [1230/1251] eta: 0:00:13 lr: 0.000028 loss: 2.6976 (2.6600) grad_norm: 3.4874 (inf) time: 0.6348 [2021-03-28 13:22:07 swin_base_patch4_window7_224] INFO: Epoch: [273] [1240/1251] eta: 0:00:06 lr: 0.000028 loss: 2.7101 (2.6603) grad_norm: 3.2791 (inf) time: 0.6323 [2021-03-28 13:22:13 swin_base_patch4_window7_224] INFO: Epoch: [273] [1250/1251] eta: 0:00:00 lr: 0.000028 loss: 2.7283 (2.6619) grad_norm: 3.5671 (inf) time: 0.6237 [2021-03-28 13:22:27 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:46 loss: 1.0861 (1.0861) acc1: 73.4375 (73.4375) acc5: 90.6250 (90.6250) [2021-03-28 13:22:29 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8332 (0.8546) acc1: 81.2500 (80.6818) acc5: 93.7500 (94.7443) [2021-03-28 13:22:32 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7900 (0.7850) acc1: 81.2500 (81.9196) acc5: 95.3125 (95.8333) [2021-03-28 13:22:34 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6857 (0.7741) acc1: 82.8125 (81.8548) acc5: 96.8750 (96.2702) [2021-03-28 13:22:36 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6734 (0.7598) acc1: 82.8125 (82.1646) acc5: 96.8750 (96.3796) [2021-03-28 13:22:37 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6725 (0.7515) acc1: 84.3750 (82.3680) acc5: 96.8750 (96.3200) [2021-03-28 13:22:54 swin_base_patch4_window7_224] INFO: * Acc@1 83.238 Acc@5 96.390 loss 0.739 [2021-03-28 13:22:54 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.2% [2021-03-28 13:22:54 swin_base_patch4_window7_224] INFO: Max accuracy: 83.34% [2021-03-28 13:22:58 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 0/1251] eta: 1:30:03 lr: 0.000028 loss: 3.1258 (3.1258) grad_norm: 4.3393 (4.3393) time: 4.3190 [2021-03-28 13:23:05 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 10/1251] eta: 0:20:17 lr: 0.000028 loss: 2.8035 (2.6138) grad_norm: 3.5441 (3.5669) time: 0.9807 [2021-03-28 13:23:11 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 20/1251] eta: 0:16:45 lr: 0.000028 loss: 2.8035 (2.6348) grad_norm: 3.2910 (3.4789) time: 0.6421 [2021-03-28 13:23:17 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 30/1251] eta: 0:15:26 lr: 0.000028 loss: 2.7296 (2.6421) grad_norm: 3.1656 (3.4731) time: 0.6364 [2021-03-28 13:23:24 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 40/1251] eta: 0:14:43 lr: 0.000028 loss: 2.4899 (2.5910) grad_norm: 3.3228 (3.4458) time: 0.6373 [2021-03-28 13:23:30 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 50/1251] eta: 0:14:12 lr: 0.000028 loss: 2.6511 (2.6286) grad_norm: 3.2714 (3.4764) time: 0.6348 [2021-03-28 13:23:36 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 60/1251] eta: 0:13:48 lr: 0.000028 loss: 2.7710 (2.6365) grad_norm: 3.2523 (3.6098) time: 0.6269 [2021-03-28 13:23:42 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 70/1251] eta: 0:13:30 lr: 0.000028 loss: 2.7199 (2.6361) grad_norm: 3.2197 (3.5537) time: 0.6248 [2021-03-28 13:23:49 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 80/1251] eta: 0:13:15 lr: 0.000028 loss: 2.4997 (2.6024) grad_norm: 3.2930 (3.5563) time: 0.6303 [2021-03-28 13:23:55 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 90/1251] eta: 0:13:02 lr: 0.000028 loss: 2.5557 (2.6142) grad_norm: 3.3808 (3.5375) time: 0.6332 [2021-03-28 13:24:01 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 100/1251] eta: 0:12:51 lr: 0.000028 loss: 2.7410 (2.6387) grad_norm: 3.5197 (3.5772) time: 0.6328 [2021-03-28 13:24:08 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 110/1251] eta: 0:12:40 lr: 0.000028 loss: 2.7544 (2.6342) grad_norm: 3.6392 (3.5773) time: 0.6323 [2021-03-28 13:24:14 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 120/1251] eta: 0:12:32 lr: 0.000028 loss: 2.7536 (2.6275) grad_norm: 3.3132 (3.5622) time: 0.6379 [2021-03-28 13:24:21 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 130/1251] eta: 0:12:23 lr: 0.000028 loss: 2.4933 (2.6153) grad_norm: 3.2605 (3.5367) time: 0.6411 [2021-03-28 13:24:27 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 140/1251] eta: 0:12:15 lr: 0.000028 loss: 2.5619 (2.6258) grad_norm: 3.2605 (3.5305) time: 0.6408 [2021-03-28 13:24:33 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 150/1251] eta: 0:12:06 lr: 0.000028 loss: 2.8333 (2.6284) grad_norm: 3.3332 (3.5216) time: 0.6381 [2021-03-28 13:24:40 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 160/1251] eta: 0:11:57 lr: 0.000028 loss: 2.9536 (2.6377) grad_norm: 3.3332 (3.5384) time: 0.6319 [2021-03-28 13:24:46 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 170/1251] eta: 0:11:49 lr: 0.000028 loss: 2.6572 (2.6221) grad_norm: 3.3015 (3.5599) time: 0.6331 [2021-03-28 13:24:52 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 180/1251] eta: 0:11:41 lr: 0.000028 loss: 2.2989 (2.6209) grad_norm: 3.1513 (3.5416) time: 0.6337 [2021-03-28 13:24:59 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 190/1251] eta: 0:11:34 lr: 0.000028 loss: 2.5528 (2.6269) grad_norm: 3.1513 (3.5332) time: 0.6380 [2021-03-28 13:25:05 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 200/1251] eta: 0:11:27 lr: 0.000028 loss: 2.6114 (2.6243) grad_norm: 3.2377 (3.5684) time: 0.6399 [2021-03-28 13:25:12 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 210/1251] eta: 0:11:19 lr: 0.000028 loss: 2.7716 (2.6320) grad_norm: 3.2683 (3.5615) time: 0.6379 [2021-03-28 13:25:18 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 220/1251] eta: 0:11:12 lr: 0.000028 loss: 2.9700 (2.6382) grad_norm: 3.2856 (3.6320) time: 0.6352 [2021-03-28 13:25:24 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 230/1251] eta: 0:11:04 lr: 0.000028 loss: 2.9451 (2.6433) grad_norm: 3.3765 (3.6200) time: 0.6336 [2021-03-28 13:25:31 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 240/1251] eta: 0:10:57 lr: 0.000028 loss: 2.7755 (2.6429) grad_norm: 3.3706 (3.6305) time: 0.6305 [2021-03-28 13:25:37 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 250/1251] eta: 0:10:50 lr: 0.000028 loss: 2.8020 (2.6549) grad_norm: 3.1783 (3.6169) time: 0.6304 [2021-03-28 13:25:43 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 260/1251] eta: 0:10:42 lr: 0.000028 loss: 2.7529 (2.6458) grad_norm: 3.1994 (3.6123) time: 0.6298 [2021-03-28 13:25:49 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 270/1251] eta: 0:10:35 lr: 0.000028 loss: 2.5690 (2.6509) grad_norm: 3.4694 (3.6353) time: 0.6241 [2021-03-28 13:25:56 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 280/1251] eta: 0:10:28 lr: 0.000028 loss: 2.6714 (2.6489) grad_norm: 3.4694 (3.6336) time: 0.6237 [2021-03-28 13:26:02 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 290/1251] eta: 0:10:21 lr: 0.000028 loss: 2.7006 (2.6485) grad_norm: 3.2846 (3.6201) time: 0.6251 [2021-03-28 13:26:08 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 300/1251] eta: 0:10:14 lr: 0.000028 loss: 2.7507 (2.6550) grad_norm: 3.4061 (3.6222) time: 0.6294 [2021-03-28 13:26:14 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 310/1251] eta: 0:10:07 lr: 0.000028 loss: 2.6931 (2.6479) grad_norm: 3.5514 (3.6165) time: 0.6306 [2021-03-28 13:26:21 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 320/1251] eta: 0:10:00 lr: 0.000028 loss: 2.6998 (2.6559) grad_norm: 3.1115 (3.6014) time: 0.6364 [2021-03-28 13:26:27 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 330/1251] eta: 0:09:53 lr: 0.000028 loss: 2.8005 (2.6588) grad_norm: 3.3747 (3.6123) time: 0.6346 [2021-03-28 13:26:34 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 340/1251] eta: 0:09:46 lr: 0.000028 loss: 2.7688 (2.6624) grad_norm: 3.4489 (3.6085) time: 0.6299 [2021-03-28 13:26:40 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 350/1251] eta: 0:09:40 lr: 0.000028 loss: 2.9559 (2.6713) grad_norm: 3.2698 (3.6109) time: 0.6335 [2021-03-28 13:26:46 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 360/1251] eta: 0:09:33 lr: 0.000028 loss: 2.9301 (2.6759) grad_norm: 3.3022 (3.6153) time: 0.6318 [2021-03-28 13:26:52 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 370/1251] eta: 0:09:26 lr: 0.000028 loss: 2.7739 (2.6783) grad_norm: 3.2794 (3.6197) time: 0.6279 [2021-03-28 13:26:59 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 380/1251] eta: 0:09:19 lr: 0.000028 loss: 2.8753 (2.6790) grad_norm: 3.2151 (3.6290) time: 0.6248 [2021-03-28 13:27:05 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 390/1251] eta: 0:09:13 lr: 0.000028 loss: 2.7138 (2.6809) grad_norm: 3.1691 (3.6243) time: 0.6315 [2021-03-28 13:27:11 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 400/1251] eta: 0:09:06 lr: 0.000028 loss: 2.7138 (2.6823) grad_norm: 3.5786 (3.6310) time: 0.6339 [2021-03-28 13:27:18 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 410/1251] eta: 0:08:59 lr: 0.000028 loss: 2.7107 (2.6828) grad_norm: 3.8137 (3.6361) time: 0.6260 [2021-03-28 13:27:24 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 420/1251] eta: 0:08:52 lr: 0.000028 loss: 2.7533 (2.6851) grad_norm: 3.4948 (3.6368) time: 0.6248 [2021-03-28 13:27:30 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 430/1251] eta: 0:08:46 lr: 0.000028 loss: 2.6957 (2.6828) grad_norm: 3.3020 (3.6337) time: 0.6269 [2021-03-28 13:27:36 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 440/1251] eta: 0:08:39 lr: 0.000028 loss: 2.6364 (2.6842) grad_norm: 3.2977 (3.6392) time: 0.6293 [2021-03-28 13:27:43 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 450/1251] eta: 0:08:33 lr: 0.000028 loss: 2.7015 (2.6832) grad_norm: 3.5779 (3.6383) time: 0.6352 [2021-03-28 13:27:49 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 460/1251] eta: 0:08:26 lr: 0.000028 loss: 2.5895 (2.6828) grad_norm: 3.2641 (3.6297) time: 0.6334 [2021-03-28 13:27:55 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 470/1251] eta: 0:08:20 lr: 0.000028 loss: 2.7207 (2.6853) grad_norm: 3.4603 (3.6341) time: 0.6302 [2021-03-28 13:28:02 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 480/1251] eta: 0:08:13 lr: 0.000028 loss: 2.8843 (2.6851) grad_norm: 3.1712 (3.6316) time: 0.6300 [2021-03-28 13:28:08 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 490/1251] eta: 0:08:06 lr: 0.000028 loss: 2.8954 (2.6869) grad_norm: 3.0299 (3.6286) time: 0.6269 [2021-03-28 13:28:14 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 500/1251] eta: 0:08:00 lr: 0.000028 loss: 2.8435 (2.6862) grad_norm: 3.3590 (3.6331) time: 0.6301 [2021-03-28 13:28:21 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 510/1251] eta: 0:07:53 lr: 0.000028 loss: 2.8435 (2.6889) grad_norm: 3.4502 (3.6269) time: 0.6303 [2021-03-28 13:28:27 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 520/1251] eta: 0:07:47 lr: 0.000028 loss: 2.8225 (2.6880) grad_norm: 3.2996 (3.6315) time: 0.6307 [2021-03-28 13:28:33 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 530/1251] eta: 0:07:40 lr: 0.000028 loss: 2.5744 (2.6868) grad_norm: 3.5308 (3.6288) time: 0.6306 [2021-03-28 13:28:40 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 540/1251] eta: 0:07:34 lr: 0.000028 loss: 2.7058 (2.6876) grad_norm: 3.3973 (3.6390) time: 0.6338 [2021-03-28 13:28:46 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 550/1251] eta: 0:07:28 lr: 0.000028 loss: 2.8292 (2.6901) grad_norm: 3.1034 (3.6370) time: 0.6482 [2021-03-28 13:28:52 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 560/1251] eta: 0:07:21 lr: 0.000028 loss: 2.6347 (2.6877) grad_norm: 3.1034 (3.6360) time: 0.6448 [2021-03-28 13:28:59 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 570/1251] eta: 0:07:15 lr: 0.000028 loss: 2.6063 (2.6878) grad_norm: 3.0956 (3.6341) time: 0.6355 [2021-03-28 13:29:05 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 580/1251] eta: 0:07:08 lr: 0.000028 loss: 2.7163 (2.6880) grad_norm: 3.3701 (3.6384) time: 0.6358 [2021-03-28 13:29:11 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 590/1251] eta: 0:07:02 lr: 0.000028 loss: 2.6857 (2.6875) grad_norm: 3.6198 (3.6665) time: 0.6301 [2021-03-28 13:29:18 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 600/1251] eta: 0:06:55 lr: 0.000028 loss: 2.6091 (2.6848) grad_norm: 3.6051 (3.6712) time: 0.6251 [2021-03-28 13:29:24 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 610/1251] eta: 0:06:49 lr: 0.000028 loss: 2.6556 (2.6840) grad_norm: 3.5780 (3.6703) time: 0.6270 [2021-03-28 13:29:30 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 620/1251] eta: 0:06:42 lr: 0.000028 loss: 2.6606 (2.6827) grad_norm: 3.4651 (3.6698) time: 0.6303 [2021-03-28 13:29:37 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 630/1251] eta: 0:06:36 lr: 0.000028 loss: 2.6947 (2.6841) grad_norm: 3.4053 (3.6658) time: 0.6337 [2021-03-28 13:29:43 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 640/1251] eta: 0:06:29 lr: 0.000028 loss: 2.5563 (2.6809) grad_norm: 3.2936 (3.6586) time: 0.6296 [2021-03-28 13:29:49 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 650/1251] eta: 0:06:23 lr: 0.000028 loss: 2.4706 (2.6798) grad_norm: 3.2063 (3.6583) time: 0.6255 [2021-03-28 13:29:55 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 660/1251] eta: 0:06:16 lr: 0.000028 loss: 2.7032 (2.6793) grad_norm: 3.1812 (3.6525) time: 0.6275 [2021-03-28 13:30:02 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 670/1251] eta: 0:06:10 lr: 0.000027 loss: 2.6558 (2.6785) grad_norm: 3.1094 (3.6522) time: 0.6307 [2021-03-28 13:30:08 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 680/1251] eta: 0:06:04 lr: 0.000027 loss: 2.6554 (2.6804) grad_norm: 3.2582 (3.6475) time: 0.6286 [2021-03-28 13:30:14 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 690/1251] eta: 0:05:57 lr: 0.000027 loss: 2.7896 (2.6788) grad_norm: 3.2925 (3.6429) time: 0.6280 [2021-03-28 13:30:21 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 700/1251] eta: 0:05:51 lr: 0.000027 loss: 2.7896 (2.6781) grad_norm: 3.3763 (3.6500) time: 0.6274 [2021-03-28 13:30:27 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 710/1251] eta: 0:05:44 lr: 0.000027 loss: 2.7522 (2.6770) grad_norm: 3.5143 (3.6555) time: 0.6293 [2021-03-28 13:30:33 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 720/1251] eta: 0:05:38 lr: 0.000027 loss: 2.7132 (2.6789) grad_norm: 3.7040 (3.6560) time: 0.6334 [2021-03-28 13:30:40 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 730/1251] eta: 0:05:31 lr: 0.000027 loss: 2.9160 (2.6835) grad_norm: 3.4432 (3.6604) time: 0.6329 [2021-03-28 13:30:46 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 740/1251] eta: 0:05:25 lr: 0.000027 loss: 2.9582 (2.6823) grad_norm: 3.4185 (3.6569) time: 0.6423 [2021-03-28 13:30:52 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 750/1251] eta: 0:05:19 lr: 0.000027 loss: 2.8807 (2.6837) grad_norm: 3.5084 (3.6535) time: 0.6430 [2021-03-28 13:30:59 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 760/1251] eta: 0:05:12 lr: 0.000027 loss: 2.8807 (2.6847) grad_norm: 3.4562 (3.6494) time: 0.6394 [2021-03-28 13:31:05 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 770/1251] eta: 0:05:06 lr: 0.000027 loss: 2.7579 (2.6858) grad_norm: 3.2544 (3.6518) time: 0.6401 [2021-03-28 13:31:12 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 780/1251] eta: 0:05:00 lr: 0.000027 loss: 2.6996 (2.6838) grad_norm: 3.0820 (3.6487) time: 0.6356 [2021-03-28 13:31:18 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 790/1251] eta: 0:04:53 lr: 0.000027 loss: 2.9133 (2.6864) grad_norm: 3.1348 (3.6413) time: 0.6326 [2021-03-28 13:31:24 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 800/1251] eta: 0:04:47 lr: 0.000027 loss: 2.9133 (2.6880) grad_norm: 3.0327 (3.6356) time: 0.6315 [2021-03-28 13:31:31 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 810/1251] eta: 0:04:40 lr: 0.000027 loss: 2.9453 (2.6897) grad_norm: 3.0765 (3.6625) time: 0.6278 [2021-03-28 13:31:37 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 820/1251] eta: 0:04:34 lr: 0.000027 loss: 2.8707 (2.6902) grad_norm: 3.6016 (3.6590) time: 0.6286 [2021-03-28 13:31:43 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 830/1251] eta: 0:04:28 lr: 0.000027 loss: 2.8010 (2.6906) grad_norm: 3.4153 (3.6631) time: 0.6365 [2021-03-28 13:31:50 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 840/1251] eta: 0:04:21 lr: 0.000027 loss: 2.7556 (2.6910) grad_norm: 3.6073 (3.6672) time: 0.6375 [2021-03-28 13:31:56 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 850/1251] eta: 0:04:15 lr: 0.000027 loss: 2.6936 (2.6902) grad_norm: 3.2785 (3.6623) time: 0.6363 [2021-03-28 13:32:02 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 860/1251] eta: 0:04:09 lr: 0.000027 loss: 2.7561 (2.6917) grad_norm: 3.2070 (3.6613) time: 0.6366 [2021-03-28 13:32:09 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 870/1251] eta: 0:04:02 lr: 0.000027 loss: 2.7970 (2.6922) grad_norm: 3.2485 (3.6711) time: 0.6381 [2021-03-28 13:32:15 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 880/1251] eta: 0:03:56 lr: 0.000027 loss: 2.7619 (2.6916) grad_norm: 3.1097 (3.6648) time: 0.6392 [2021-03-28 13:32:21 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 890/1251] eta: 0:03:49 lr: 0.000027 loss: 2.7262 (2.6914) grad_norm: 3.1621 (3.6607) time: 0.6345 [2021-03-28 13:32:28 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 900/1251] eta: 0:03:43 lr: 0.000027 loss: 2.5256 (2.6904) grad_norm: 3.2425 (3.6689) time: 0.6279 [2021-03-28 13:32:34 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 910/1251] eta: 0:03:37 lr: 0.000027 loss: 2.5615 (2.6908) grad_norm: 3.3203 (3.6717) time: 0.6246 [2021-03-28 13:32:40 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 920/1251] eta: 0:03:30 lr: 0.000027 loss: 2.7638 (2.6904) grad_norm: 3.2974 (3.6762) time: 0.6252 [2021-03-28 13:32:47 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 930/1251] eta: 0:03:24 lr: 0.000027 loss: 2.7638 (2.6910) grad_norm: 3.2563 (3.6761) time: 0.6309 [2021-03-28 13:32:53 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 940/1251] eta: 0:03:17 lr: 0.000027 loss: 2.6803 (2.6894) grad_norm: 3.9659 (3.6825) time: 0.6350 [2021-03-28 13:32:59 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 950/1251] eta: 0:03:11 lr: 0.000027 loss: 2.7376 (2.6899) grad_norm: 3.9659 (3.6824) time: 0.6317 [2021-03-28 13:33:06 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 960/1251] eta: 0:03:05 lr: 0.000027 loss: 2.8293 (2.6907) grad_norm: 3.3869 (3.6801) time: 0.6323 [2021-03-28 13:33:12 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 970/1251] eta: 0:02:58 lr: 0.000027 loss: 2.8293 (2.6914) grad_norm: 3.4177 (3.6859) time: 0.6351 [2021-03-28 13:33:18 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 980/1251] eta: 0:02:52 lr: 0.000027 loss: 2.7770 (2.6911) grad_norm: 3.3634 (3.6823) time: 0.6370 [2021-03-28 13:33:25 swin_base_patch4_window7_224] INFO: Epoch: [274] [ 990/1251] eta: 0:02:46 lr: 0.000027 loss: 2.7354 (2.6902) grad_norm: 3.2448 (3.6840) time: 0.6395 [2021-03-28 13:33:31 swin_base_patch4_window7_224] INFO: Epoch: [274] [1000/1251] eta: 0:02:39 lr: 0.000027 loss: 2.7401 (2.6902) grad_norm: 3.3013 (3.6797) time: 0.6392 [2021-03-28 13:33:37 swin_base_patch4_window7_224] INFO: Epoch: [274] [1010/1251] eta: 0:02:33 lr: 0.000027 loss: 2.7401 (2.6893) grad_norm: 3.3824 (3.6787) time: 0.6290 [2021-03-28 13:33:44 swin_base_patch4_window7_224] INFO: Epoch: [274] [1020/1251] eta: 0:02:26 lr: 0.000027 loss: 2.6094 (2.6889) grad_norm: 3.6261 (3.6782) time: 0.6278 [2021-03-28 13:33:50 swin_base_patch4_window7_224] INFO: Epoch: [274] [1030/1251] eta: 0:02:20 lr: 0.000027 loss: 2.8448 (2.6902) grad_norm: 3.6261 (3.6779) time: 0.6336 [2021-03-28 13:33:56 swin_base_patch4_window7_224] INFO: Epoch: [274] [1040/1251] eta: 0:02:14 lr: 0.000027 loss: 2.8627 (2.6914) grad_norm: 3.2819 (3.6761) time: 0.6329 [2021-03-28 13:34:03 swin_base_patch4_window7_224] INFO: Epoch: [274] [1050/1251] eta: 0:02:07 lr: 0.000027 loss: 2.7510 (2.6916) grad_norm: 3.1860 (3.6717) time: 0.6287 [2021-03-28 13:34:09 swin_base_patch4_window7_224] INFO: Epoch: [274] [1060/1251] eta: 0:02:01 lr: 0.000027 loss: 2.7053 (2.6913) grad_norm: 3.5405 (3.6770) time: 0.6263 [2021-03-28 13:34:15 swin_base_patch4_window7_224] INFO: Epoch: [274] [1070/1251] eta: 0:01:55 lr: 0.000027 loss: 2.8967 (2.6938) grad_norm: 3.5405 (3.6737) time: 0.6351 [2021-03-28 13:34:22 swin_base_patch4_window7_224] INFO: Epoch: [274] [1080/1251] eta: 0:01:48 lr: 0.000027 loss: 2.8207 (2.6903) grad_norm: 3.4141 (3.6704) time: 0.6345 [2021-03-28 13:34:28 swin_base_patch4_window7_224] INFO: Epoch: [274] [1090/1251] eta: 0:01:42 lr: 0.000027 loss: 2.6572 (2.6902) grad_norm: 3.1297 (3.6664) time: 0.6256 [2021-03-28 13:34:34 swin_base_patch4_window7_224] INFO: Epoch: [274] [1100/1251] eta: 0:01:36 lr: 0.000027 loss: 2.5255 (2.6867) grad_norm: 3.1462 (3.6630) time: 0.6283 [2021-03-28 13:34:40 swin_base_patch4_window7_224] INFO: Epoch: [274] [1110/1251] eta: 0:01:29 lr: 0.000027 loss: 2.4758 (2.6855) grad_norm: 3.3838 (inf) time: 0.6298 [2021-03-28 13:34:47 swin_base_patch4_window7_224] INFO: Epoch: [274] [1120/1251] eta: 0:01:23 lr: 0.000027 loss: 2.6180 (2.6843) grad_norm: 3.4043 (inf) time: 0.6325 [2021-03-28 13:34:53 swin_base_patch4_window7_224] INFO: Epoch: [274] [1130/1251] eta: 0:01:16 lr: 0.000027 loss: 2.6780 (2.6855) grad_norm: 3.3304 (inf) time: 0.6339 [2021-03-28 13:34:59 swin_base_patch4_window7_224] INFO: Epoch: [274] [1140/1251] eta: 0:01:10 lr: 0.000027 loss: 2.8088 (2.6845) grad_norm: 3.5446 (inf) time: 0.6247 [2021-03-28 13:35:06 swin_base_patch4_window7_224] INFO: Epoch: [274] [1150/1251] eta: 0:01:04 lr: 0.000027 loss: 2.6249 (2.6822) grad_norm: 3.4987 (inf) time: 0.6242 [2021-03-28 13:35:12 swin_base_patch4_window7_224] INFO: Epoch: [274] [1160/1251] eta: 0:00:57 lr: 0.000027 loss: 2.6569 (2.6831) grad_norm: 3.3043 (inf) time: 0.6318 [2021-03-28 13:35:18 swin_base_patch4_window7_224] INFO: Epoch: [274] [1170/1251] eta: 0:00:51 lr: 0.000027 loss: 2.6993 (2.6829) grad_norm: 3.3043 (inf) time: 0.6336 [2021-03-28 13:35:25 swin_base_patch4_window7_224] INFO: Epoch: [274] [1180/1251] eta: 0:00:45 lr: 0.000027 loss: 2.6751 (2.6811) grad_norm: 3.4958 (inf) time: 0.6331 [2021-03-28 13:35:31 swin_base_patch4_window7_224] INFO: Epoch: [274] [1190/1251] eta: 0:00:38 lr: 0.000027 loss: 2.6972 (2.6821) grad_norm: 3.3433 (inf) time: 0.6334 [2021-03-28 13:35:37 swin_base_patch4_window7_224] INFO: Epoch: [274] [1200/1251] eta: 0:00:32 lr: 0.000027 loss: 2.6775 (2.6816) grad_norm: 3.3433 (inf) time: 0.6297 [2021-03-28 13:35:43 swin_base_patch4_window7_224] INFO: Epoch: [274] [1210/1251] eta: 0:00:26 lr: 0.000027 loss: 2.6687 (2.6821) grad_norm: 3.2254 (inf) time: 0.6286 [2021-03-28 13:35:50 swin_base_patch4_window7_224] INFO: Epoch: [274] [1220/1251] eta: 0:00:19 lr: 0.000027 loss: 2.9300 (2.6828) grad_norm: 3.2108 (inf) time: 0.6318 [2021-03-28 13:35:56 swin_base_patch4_window7_224] INFO: Epoch: [274] [1230/1251] eta: 0:00:13 lr: 0.000027 loss: 2.8110 (2.6826) grad_norm: 3.2108 (inf) time: 0.6330 [2021-03-28 13:36:02 swin_base_patch4_window7_224] INFO: Epoch: [274] [1240/1251] eta: 0:00:06 lr: 0.000027 loss: 2.8110 (2.6849) grad_norm: 3.0443 (inf) time: 0.6334 [2021-03-28 13:36:09 swin_base_patch4_window7_224] INFO: Epoch: [274] [1250/1251] eta: 0:00:00 lr: 0.000027 loss: 2.9071 (2.6844) grad_norm: 3.0966 (inf) time: 0.6307 [2021-03-28 13:36:23 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:58 loss: 0.7452 (0.7452) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-28 13:36:27 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.7491 (0.7513) acc1: 84.3750 (82.8125) acc5: 95.3125 (95.4545) [2021-03-28 13:36:29 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.6532 (0.7312) acc1: 84.3750 (82.3661) acc5: 96.8750 (96.2798) [2021-03-28 13:36:31 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7475 (0.7602) acc1: 82.8125 (82.2581) acc5: 96.8750 (95.9677) [2021-03-28 13:36:33 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7802 (0.7655) acc1: 81.2500 (82.1265) acc5: 96.8750 (96.3796) [2021-03-28 13:36:34 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7461 (0.7577) acc1: 79.6875 (82.1120) acc5: 98.4375 (96.5440) [2021-03-28 13:36:49 swin_base_patch4_window7_224] INFO: * Acc@1 83.280 Acc@5 96.332 loss 0.745 [2021-03-28 13:36:49 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.3% [2021-03-28 13:36:49 swin_base_patch4_window7_224] INFO: Max accuracy: 83.34% [2021-03-28 13:36:53 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 0/1251] eta: 1:28:04 lr: 0.000027 loss: 2.8745 (2.8745) grad_norm: 3.4987 (3.4987) time: 4.2241 [2021-03-28 13:37:00 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 10/1251] eta: 0:19:44 lr: 0.000027 loss: 2.7592 (2.6900) grad_norm: 3.4987 (3.5666) time: 0.9548 [2021-03-28 13:37:06 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 20/1251] eta: 0:16:26 lr: 0.000027 loss: 2.6534 (2.6656) grad_norm: 3.4885 (3.4831) time: 0.6303 [2021-03-28 13:37:12 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 30/1251] eta: 0:15:14 lr: 0.000027 loss: 2.6106 (2.6970) grad_norm: 3.3977 (3.5407) time: 0.6358 [2021-03-28 13:37:19 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 40/1251] eta: 0:14:35 lr: 0.000027 loss: 2.8270 (2.7072) grad_norm: 3.2857 (3.5077) time: 0.6407 [2021-03-28 13:37:25 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 50/1251] eta: 0:14:07 lr: 0.000027 loss: 2.8638 (2.7391) grad_norm: 3.0783 (3.4353) time: 0.6375 [2021-03-28 13:37:31 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 60/1251] eta: 0:13:44 lr: 0.000027 loss: 2.7878 (2.7451) grad_norm: 3.0462 (3.3997) time: 0.6287 [2021-03-28 13:37:38 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 70/1251] eta: 0:13:27 lr: 0.000027 loss: 2.7878 (2.7465) grad_norm: 3.2639 (3.4988) time: 0.6289 [2021-03-28 13:37:44 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 80/1251] eta: 0:13:12 lr: 0.000027 loss: 2.7950 (2.7182) grad_norm: 3.4962 (3.5301) time: 0.6313 [2021-03-28 13:37:50 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 90/1251] eta: 0:12:59 lr: 0.000027 loss: 2.6047 (2.7067) grad_norm: 3.3801 (3.5096) time: 0.6258 [2021-03-28 13:37:56 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 100/1251] eta: 0:12:48 lr: 0.000027 loss: 2.7331 (2.7108) grad_norm: 3.2774 (3.5273) time: 0.6303 [2021-03-28 13:38:03 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 110/1251] eta: 0:12:38 lr: 0.000027 loss: 2.6654 (2.7103) grad_norm: 3.2977 (3.5125) time: 0.6347 [2021-03-28 13:38:09 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 120/1251] eta: 0:12:28 lr: 0.000027 loss: 2.6274 (2.7027) grad_norm: 3.3335 (3.5166) time: 0.6322 [2021-03-28 13:38:16 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 130/1251] eta: 0:12:19 lr: 0.000027 loss: 2.5381 (2.6935) grad_norm: 3.1878 (3.5182) time: 0.6356 [2021-03-28 13:38:22 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 140/1251] eta: 0:12:11 lr: 0.000027 loss: 2.4097 (2.6666) grad_norm: 3.1528 (3.4920) time: 0.6387 [2021-03-28 13:38:28 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 150/1251] eta: 0:12:03 lr: 0.000027 loss: 2.5162 (2.6598) grad_norm: 3.0815 (3.4723) time: 0.6359 [2021-03-28 13:38:35 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 160/1251] eta: 0:11:55 lr: 0.000027 loss: 2.6050 (2.6544) grad_norm: 3.3562 (3.4700) time: 0.6347 [2021-03-28 13:38:41 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 170/1251] eta: 0:11:47 lr: 0.000027 loss: 2.6623 (2.6573) grad_norm: 3.3562 (3.4864) time: 0.6362 [2021-03-28 13:38:47 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 180/1251] eta: 0:11:39 lr: 0.000027 loss: 2.8323 (2.6604) grad_norm: 3.4613 (3.5188) time: 0.6323 [2021-03-28 13:38:54 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 190/1251] eta: 0:11:31 lr: 0.000027 loss: 2.8323 (2.6580) grad_norm: 3.5577 (3.5209) time: 0.6296 [2021-03-28 13:39:00 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 200/1251] eta: 0:11:24 lr: 0.000027 loss: 2.8846 (2.6684) grad_norm: 3.2541 (3.5125) time: 0.6355 [2021-03-28 13:39:06 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 210/1251] eta: 0:11:17 lr: 0.000027 loss: 2.8443 (2.6682) grad_norm: 3.0851 (3.6440) time: 0.6388 [2021-03-28 13:39:13 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 220/1251] eta: 0:11:09 lr: 0.000027 loss: 2.7732 (2.6696) grad_norm: 3.1845 (3.6420) time: 0.6329 [2021-03-28 13:39:19 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 230/1251] eta: 0:11:02 lr: 0.000027 loss: 2.7114 (2.6643) grad_norm: 3.2047 (3.6428) time: 0.6283 [2021-03-28 13:39:25 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 240/1251] eta: 0:10:55 lr: 0.000027 loss: 2.7114 (2.6652) grad_norm: 3.4634 (3.6465) time: 0.6283 [2021-03-28 13:39:32 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 250/1251] eta: 0:10:48 lr: 0.000027 loss: 2.8384 (2.6700) grad_norm: 3.4040 (3.6322) time: 0.6340 [2021-03-28 13:39:38 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 260/1251] eta: 0:10:41 lr: 0.000027 loss: 2.7162 (2.6633) grad_norm: 3.3346 (3.6202) time: 0.6346 [2021-03-28 13:39:44 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 270/1251] eta: 0:10:33 lr: 0.000027 loss: 2.6763 (2.6626) grad_norm: 3.0957 (3.6086) time: 0.6268 [2021-03-28 13:39:50 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 280/1251] eta: 0:10:26 lr: 0.000027 loss: 2.6504 (2.6610) grad_norm: 3.1513 (3.5983) time: 0.6241 [2021-03-28 13:39:57 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 290/1251] eta: 0:10:19 lr: 0.000027 loss: 2.6268 (2.6604) grad_norm: 3.2800 (3.5901) time: 0.6303 [2021-03-28 13:40:03 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 300/1251] eta: 0:10:12 lr: 0.000027 loss: 2.6405 (2.6581) grad_norm: 3.3440 (3.5883) time: 0.6291 [2021-03-28 13:40:09 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 310/1251] eta: 0:10:06 lr: 0.000027 loss: 2.7601 (2.6592) grad_norm: 3.4226 (3.6031) time: 0.6317 [2021-03-28 13:40:16 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 320/1251] eta: 0:09:59 lr: 0.000027 loss: 2.6002 (2.6533) grad_norm: 3.3677 (3.5939) time: 0.6336 [2021-03-28 13:40:22 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 330/1251] eta: 0:09:52 lr: 0.000027 loss: 2.6002 (2.6534) grad_norm: 3.2707 (3.5928) time: 0.6333 [2021-03-28 13:40:28 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 340/1251] eta: 0:09:45 lr: 0.000027 loss: 2.6890 (2.6519) grad_norm: 3.2924 (3.5860) time: 0.6312 [2021-03-28 13:40:35 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 350/1251] eta: 0:09:38 lr: 0.000026 loss: 2.6156 (2.6525) grad_norm: 3.3867 (3.5811) time: 0.6289 [2021-03-28 13:40:41 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 360/1251] eta: 0:09:32 lr: 0.000026 loss: 2.6156 (2.6513) grad_norm: 3.3973 (3.5759) time: 0.6333 [2021-03-28 13:40:47 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 370/1251] eta: 0:09:25 lr: 0.000026 loss: 2.6894 (2.6544) grad_norm: 3.4712 (3.6004) time: 0.6355 [2021-03-28 13:40:54 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 380/1251] eta: 0:09:19 lr: 0.000026 loss: 2.7223 (2.6549) grad_norm: 3.7645 (3.6048) time: 0.6355 [2021-03-28 13:41:00 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 390/1251] eta: 0:09:12 lr: 0.000026 loss: 2.7440 (2.6600) grad_norm: 3.3424 (3.6014) time: 0.6292 [2021-03-28 13:41:06 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 400/1251] eta: 0:09:05 lr: 0.000026 loss: 2.8217 (2.6618) grad_norm: 3.2951 (3.6008) time: 0.6276 [2021-03-28 13:41:13 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 410/1251] eta: 0:08:59 lr: 0.000026 loss: 2.8754 (2.6623) grad_norm: 3.3941 (3.5971) time: 0.6321 [2021-03-28 13:41:19 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 420/1251] eta: 0:08:52 lr: 0.000026 loss: 2.9069 (2.6670) grad_norm: 3.4056 (3.5923) time: 0.6293 [2021-03-28 13:41:25 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 430/1251] eta: 0:08:45 lr: 0.000026 loss: 2.7545 (2.6640) grad_norm: 3.1209 (3.5860) time: 0.6239 [2021-03-28 13:41:31 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 440/1251] eta: 0:08:39 lr: 0.000026 loss: 2.5099 (2.6639) grad_norm: 3.1085 (3.5881) time: 0.6274 [2021-03-28 13:41:38 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 450/1251] eta: 0:08:32 lr: 0.000026 loss: 2.7175 (2.6651) grad_norm: 3.4892 (3.6077) time: 0.6302 [2021-03-28 13:41:44 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 460/1251] eta: 0:08:25 lr: 0.000026 loss: 2.7175 (2.6653) grad_norm: 3.2658 (3.6000) time: 0.6306 [2021-03-28 13:41:50 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 470/1251] eta: 0:08:19 lr: 0.000026 loss: 2.6860 (2.6649) grad_norm: 3.1641 (3.5972) time: 0.6317 [2021-03-28 13:41:57 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 480/1251] eta: 0:08:12 lr: 0.000026 loss: 2.6772 (2.6655) grad_norm: 3.4205 (3.6011) time: 0.6315 [2021-03-28 13:42:03 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 490/1251] eta: 0:08:06 lr: 0.000026 loss: 2.6772 (2.6629) grad_norm: 3.4047 (3.6015) time: 0.6282 [2021-03-28 13:42:09 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 500/1251] eta: 0:07:59 lr: 0.000026 loss: 2.3796 (2.6567) grad_norm: 3.6892 (3.6122) time: 0.6272 [2021-03-28 13:42:15 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 510/1251] eta: 0:07:53 lr: 0.000026 loss: 2.5141 (2.6593) grad_norm: 3.8908 (3.6191) time: 0.6294 [2021-03-28 13:42:22 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 520/1251] eta: 0:07:46 lr: 0.000026 loss: 2.9110 (2.6612) grad_norm: 3.4294 (3.6201) time: 0.6299 [2021-03-28 13:42:28 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 530/1251] eta: 0:07:40 lr: 0.000026 loss: 2.8555 (2.6601) grad_norm: 3.3021 (3.6150) time: 0.6291 [2021-03-28 13:42:34 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 540/1251] eta: 0:07:33 lr: 0.000026 loss: 2.7315 (2.6597) grad_norm: 3.1615 (3.6130) time: 0.6335 [2021-03-28 13:42:41 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 550/1251] eta: 0:07:27 lr: 0.000026 loss: 2.7315 (2.6612) grad_norm: 3.2083 (3.6209) time: 0.6419 [2021-03-28 13:42:47 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 560/1251] eta: 0:07:21 lr: 0.000026 loss: 2.8421 (2.6630) grad_norm: 3.5316 (3.6345) time: 0.6366 [2021-03-28 13:42:54 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 570/1251] eta: 0:07:14 lr: 0.000026 loss: 2.8741 (2.6667) grad_norm: 3.2866 (3.6398) time: 0.6307 [2021-03-28 13:43:00 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 580/1251] eta: 0:07:08 lr: 0.000026 loss: 2.7494 (2.6653) grad_norm: 3.2238 (3.6366) time: 0.6298 [2021-03-28 13:43:06 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 590/1251] eta: 0:07:01 lr: 0.000026 loss: 2.7303 (2.6657) grad_norm: 3.1493 (3.6417) time: 0.6373 [2021-03-28 13:43:13 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 600/1251] eta: 0:06:55 lr: 0.000026 loss: 2.6950 (2.6617) grad_norm: 3.4923 (3.6399) time: 0.6473 [2021-03-28 13:43:19 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 610/1251] eta: 0:06:49 lr: 0.000026 loss: 2.5737 (2.6596) grad_norm: 3.4923 (3.6390) time: 0.6400 [2021-03-28 13:43:25 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 620/1251] eta: 0:06:42 lr: 0.000026 loss: 2.7636 (2.6602) grad_norm: 3.4112 (inf) time: 0.6277 [2021-03-28 13:43:32 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 630/1251] eta: 0:06:36 lr: 0.000026 loss: 2.7922 (2.6597) grad_norm: 3.1753 (inf) time: 0.6285 [2021-03-28 13:43:38 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 640/1251] eta: 0:06:29 lr: 0.000026 loss: 2.6404 (2.6578) grad_norm: 3.1412 (inf) time: 0.6328 [2021-03-28 13:43:44 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 650/1251] eta: 0:06:23 lr: 0.000026 loss: 2.6484 (2.6605) grad_norm: 3.3848 (inf) time: 0.6262 [2021-03-28 13:43:50 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 660/1251] eta: 0:06:16 lr: 0.000026 loss: 2.7157 (2.6583) grad_norm: 3.5559 (inf) time: 0.6265 [2021-03-28 13:43:57 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 670/1251] eta: 0:06:10 lr: 0.000026 loss: 2.6368 (2.6586) grad_norm: 3.3262 (inf) time: 0.6292 [2021-03-28 13:44:03 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 680/1251] eta: 0:06:03 lr: 0.000026 loss: 2.7391 (2.6584) grad_norm: 3.4741 (inf) time: 0.6297 [2021-03-28 13:44:10 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 690/1251] eta: 0:05:57 lr: 0.000026 loss: 2.7676 (2.6572) grad_norm: 3.4598 (inf) time: 0.6371 [2021-03-28 13:44:16 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 700/1251] eta: 0:05:51 lr: 0.000026 loss: 2.8339 (2.6578) grad_norm: 3.2992 (inf) time: 0.6365 [2021-03-28 13:44:22 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 710/1251] eta: 0:05:44 lr: 0.000026 loss: 2.8354 (2.6577) grad_norm: 3.4155 (inf) time: 0.6301 [2021-03-28 13:44:29 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 720/1251] eta: 0:05:38 lr: 0.000026 loss: 2.8354 (2.6608) grad_norm: 3.4155 (inf) time: 0.6369 [2021-03-28 13:44:35 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 730/1251] eta: 0:05:31 lr: 0.000026 loss: 2.8232 (2.6620) grad_norm: 3.1801 (inf) time: 0.6399 [2021-03-28 13:44:41 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 740/1251] eta: 0:05:25 lr: 0.000026 loss: 2.8232 (2.6643) grad_norm: 3.4887 (inf) time: 0.6398 [2021-03-28 13:44:48 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 750/1251] eta: 0:05:19 lr: 0.000026 loss: 2.8157 (2.6634) grad_norm: 3.3478 (inf) time: 0.6443 [2021-03-28 13:44:54 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 760/1251] eta: 0:05:12 lr: 0.000026 loss: 2.7673 (2.6625) grad_norm: 3.1992 (inf) time: 0.6379 [2021-03-28 13:45:00 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 770/1251] eta: 0:05:06 lr: 0.000026 loss: 2.8741 (2.6661) grad_norm: 3.2184 (inf) time: 0.6334 [2021-03-28 13:45:07 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 780/1251] eta: 0:05:00 lr: 0.000026 loss: 2.8307 (2.6656) grad_norm: 3.3036 (inf) time: 0.6334 [2021-03-28 13:45:13 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 790/1251] eta: 0:04:53 lr: 0.000026 loss: 2.6990 (2.6649) grad_norm: 3.2441 (inf) time: 0.6326 [2021-03-28 13:45:19 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 800/1251] eta: 0:04:47 lr: 0.000026 loss: 2.7305 (2.6664) grad_norm: 3.2408 (inf) time: 0.6298 [2021-03-28 13:45:26 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 810/1251] eta: 0:04:40 lr: 0.000026 loss: 2.7078 (2.6687) grad_norm: 3.2926 (inf) time: 0.6296 [2021-03-28 13:45:32 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 820/1251] eta: 0:04:34 lr: 0.000026 loss: 2.7078 (2.6687) grad_norm: 3.2684 (inf) time: 0.6353 [2021-03-28 13:45:38 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 830/1251] eta: 0:04:28 lr: 0.000026 loss: 2.7338 (2.6686) grad_norm: 3.6298 (inf) time: 0.6326 [2021-03-28 13:45:45 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 840/1251] eta: 0:04:21 lr: 0.000026 loss: 2.6832 (2.6683) grad_norm: 3.6922 (inf) time: 0.6312 [2021-03-28 13:45:51 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 850/1251] eta: 0:04:15 lr: 0.000026 loss: 2.6221 (2.6664) grad_norm: 3.2002 (inf) time: 0.6415 [2021-03-28 13:45:58 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 860/1251] eta: 0:04:09 lr: 0.000026 loss: 2.5999 (2.6655) grad_norm: 3.3866 (inf) time: 0.6447 [2021-03-28 13:46:04 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 870/1251] eta: 0:04:02 lr: 0.000026 loss: 2.7543 (2.6657) grad_norm: 3.3175 (inf) time: 0.6423 [2021-03-28 13:46:10 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 880/1251] eta: 0:03:56 lr: 0.000026 loss: 2.7938 (2.6649) grad_norm: 3.2330 (inf) time: 0.6376 [2021-03-28 13:46:17 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 890/1251] eta: 0:03:49 lr: 0.000026 loss: 2.7996 (2.6665) grad_norm: 3.3349 (inf) time: 0.6342 [2021-03-28 13:46:23 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 900/1251] eta: 0:03:43 lr: 0.000026 loss: 2.7664 (2.6674) grad_norm: 3.4762 (inf) time: 0.6399 [2021-03-28 13:46:29 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 910/1251] eta: 0:03:37 lr: 0.000026 loss: 2.7137 (2.6686) grad_norm: 3.4164 (inf) time: 0.6354 [2021-03-28 13:46:36 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 920/1251] eta: 0:03:30 lr: 0.000026 loss: 2.6859 (2.6680) grad_norm: 3.3218 (inf) time: 0.6304 [2021-03-28 13:46:42 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 930/1251] eta: 0:03:24 lr: 0.000026 loss: 2.7333 (2.6686) grad_norm: 3.2551 (inf) time: 0.6321 [2021-03-28 13:46:48 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 940/1251] eta: 0:03:18 lr: 0.000026 loss: 2.7333 (2.6699) grad_norm: 3.4222 (inf) time: 0.6323 [2021-03-28 13:46:55 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 950/1251] eta: 0:03:11 lr: 0.000026 loss: 2.7012 (2.6695) grad_norm: 3.3482 (inf) time: 0.6321 [2021-03-28 13:47:01 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 960/1251] eta: 0:03:05 lr: 0.000026 loss: 2.7793 (2.6707) grad_norm: 3.4162 (inf) time: 0.6304 [2021-03-28 13:47:07 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 970/1251] eta: 0:02:58 lr: 0.000026 loss: 2.7793 (2.6694) grad_norm: 3.2908 (inf) time: 0.6316 [2021-03-28 13:47:14 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 980/1251] eta: 0:02:52 lr: 0.000026 loss: 2.7556 (2.6686) grad_norm: 3.1904 (inf) time: 0.6323 [2021-03-28 13:47:20 swin_base_patch4_window7_224] INFO: Epoch: [275] [ 990/1251] eta: 0:02:46 lr: 0.000026 loss: 2.6370 (2.6691) grad_norm: 3.2261 (inf) time: 0.6307 [2021-03-28 13:47:26 swin_base_patch4_window7_224] INFO: Epoch: [275] [1000/1251] eta: 0:02:39 lr: 0.000026 loss: 2.6370 (2.6686) grad_norm: 3.1097 (inf) time: 0.6348 [2021-03-28 13:47:33 swin_base_patch4_window7_224] INFO: Epoch: [275] [1010/1251] eta: 0:02:33 lr: 0.000026 loss: 2.5959 (2.6681) grad_norm: 3.3112 (inf) time: 0.6376 [2021-03-28 13:47:39 swin_base_patch4_window7_224] INFO: Epoch: [275] [1020/1251] eta: 0:02:27 lr: 0.000026 loss: 2.9152 (2.6708) grad_norm: 3.3251 (inf) time: 0.6338 [2021-03-28 13:47:45 swin_base_patch4_window7_224] INFO: Epoch: [275] [1030/1251] eta: 0:02:20 lr: 0.000026 loss: 2.9152 (2.6705) grad_norm: 3.3026 (inf) time: 0.6265 [2021-03-28 13:47:52 swin_base_patch4_window7_224] INFO: Epoch: [275] [1040/1251] eta: 0:02:14 lr: 0.000026 loss: 2.8063 (2.6713) grad_norm: 3.1551 (inf) time: 0.6306 [2021-03-28 13:47:58 swin_base_patch4_window7_224] INFO: Epoch: [275] [1050/1251] eta: 0:02:07 lr: 0.000026 loss: 2.5217 (2.6692) grad_norm: 3.1317 (inf) time: 0.6403 [2021-03-28 13:48:05 swin_base_patch4_window7_224] INFO: Epoch: [275] [1060/1251] eta: 0:02:01 lr: 0.000026 loss: 2.6365 (2.6705) grad_norm: 3.2802 (inf) time: 0.6406 [2021-03-28 13:48:11 swin_base_patch4_window7_224] INFO: Epoch: [275] [1070/1251] eta: 0:01:55 lr: 0.000026 loss: 2.7868 (2.6715) grad_norm: 3.4869 (inf) time: 0.6371 [2021-03-28 13:48:17 swin_base_patch4_window7_224] INFO: Epoch: [275] [1080/1251] eta: 0:01:48 lr: 0.000026 loss: 2.7088 (2.6705) grad_norm: 3.3137 (inf) time: 0.6336 [2021-03-28 13:48:23 swin_base_patch4_window7_224] INFO: Epoch: [275] [1090/1251] eta: 0:01:42 lr: 0.000026 loss: 2.7968 (2.6726) grad_norm: 3.3165 (inf) time: 0.6311 [2021-03-28 13:48:30 swin_base_patch4_window7_224] INFO: Epoch: [275] [1100/1251] eta: 0:01:36 lr: 0.000026 loss: 2.9028 (2.6743) grad_norm: 3.5769 (inf) time: 0.6321 [2021-03-28 13:48:36 swin_base_patch4_window7_224] INFO: Epoch: [275] [1110/1251] eta: 0:01:29 lr: 0.000026 loss: 2.7998 (2.6741) grad_norm: 3.5966 (inf) time: 0.6396 [2021-03-28 13:48:43 swin_base_patch4_window7_224] INFO: Epoch: [275] [1120/1251] eta: 0:01:23 lr: 0.000026 loss: 2.7479 (2.6736) grad_norm: 3.1756 (inf) time: 0.6439 [2021-03-28 13:48:49 swin_base_patch4_window7_224] INFO: Epoch: [275] [1130/1251] eta: 0:01:16 lr: 0.000026 loss: 2.6186 (2.6725) grad_norm: 3.1336 (inf) time: 0.6343 [2021-03-28 13:48:55 swin_base_patch4_window7_224] INFO: Epoch: [275] [1140/1251] eta: 0:01:10 lr: 0.000026 loss: 2.5957 (2.6719) grad_norm: 3.1503 (inf) time: 0.6238 [2021-03-28 13:49:02 swin_base_patch4_window7_224] INFO: Epoch: [275] [1150/1251] eta: 0:01:04 lr: 0.000026 loss: 2.9226 (2.6742) grad_norm: 3.4476 (inf) time: 0.6293 [2021-03-28 13:49:08 swin_base_patch4_window7_224] INFO: Epoch: [275] [1160/1251] eta: 0:00:57 lr: 0.000026 loss: 2.9126 (2.6749) grad_norm: 3.3464 (inf) time: 0.6368 [2021-03-28 13:49:14 swin_base_patch4_window7_224] INFO: Epoch: [275] [1170/1251] eta: 0:00:51 lr: 0.000026 loss: 2.8467 (2.6748) grad_norm: 3.2291 (inf) time: 0.6389 [2021-03-28 13:49:21 swin_base_patch4_window7_224] INFO: Epoch: [275] [1180/1251] eta: 0:00:45 lr: 0.000026 loss: 2.8210 (2.6760) grad_norm: 3.3912 (inf) time: 0.6408 [2021-03-28 13:49:27 swin_base_patch4_window7_224] INFO: Epoch: [275] [1190/1251] eta: 0:00:38 lr: 0.000026 loss: 2.7788 (2.6754) grad_norm: 3.3509 (inf) time: 0.6339 [2021-03-28 13:49:33 swin_base_patch4_window7_224] INFO: Epoch: [275] [1200/1251] eta: 0:00:32 lr: 0.000026 loss: 2.5830 (2.6756) grad_norm: 3.1167 (inf) time: 0.6301 [2021-03-28 13:49:40 swin_base_patch4_window7_224] INFO: Epoch: [275] [1210/1251] eta: 0:00:26 lr: 0.000026 loss: 2.5830 (2.6753) grad_norm: 3.2317 (inf) time: 0.6339 [2021-03-28 13:49:46 swin_base_patch4_window7_224] INFO: Epoch: [275] [1220/1251] eta: 0:00:19 lr: 0.000026 loss: 2.5201 (2.6730) grad_norm: 3.3643 (inf) time: 0.6327 [2021-03-28 13:49:52 swin_base_patch4_window7_224] INFO: Epoch: [275] [1230/1251] eta: 0:00:13 lr: 0.000026 loss: 2.5201 (2.6731) grad_norm: 3.4493 (inf) time: 0.6294 [2021-03-28 13:49:59 swin_base_patch4_window7_224] INFO: Epoch: [275] [1240/1251] eta: 0:00:06 lr: 0.000026 loss: 2.6740 (2.6725) grad_norm: 3.3065 (inf) time: 0.6334 [2021-03-28 13:50:05 swin_base_patch4_window7_224] INFO: Epoch: [275] [1250/1251] eta: 0:00:00 lr: 0.000026 loss: 2.6439 (2.6714) grad_norm: 3.3065 (inf) time: 0.6368 [2021-03-28 13:51:29 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:05 loss: 0.4989 (0.4989) acc1: 89.0625 (89.0625) acc5: 98.4375 (98.4375) [2021-03-28 13:51:31 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.6822 (0.7019) acc1: 85.9375 (84.3750) acc5: 96.8750 (96.5909) [2021-03-28 13:51:32 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7227 (0.7136) acc1: 84.3750 (83.6310) acc5: 96.8750 (96.5774) [2021-03-28 13:51:34 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7717 (0.7485) acc1: 79.6875 (82.4597) acc5: 96.8750 (96.5222) [2021-03-28 13:51:35 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7993 (0.7452) acc1: 81.2500 (82.4314) acc5: 95.3125 (96.4939) [2021-03-28 13:51:36 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7440 (0.7572) acc1: 79.6875 (82.0800) acc5: 96.2264 (96.5120) [2021-03-28 13:51:51 swin_base_patch4_window7_224] INFO: * Acc@1 83.212 Acc@5 96.378 loss 0.741 [2021-03-28 13:51:51 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.2% [2021-03-28 13:51:51 swin_base_patch4_window7_224] INFO: Max accuracy: 83.34% [2021-03-28 13:51:55 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 0/1251] eta: 1:23:46 lr: 0.000026 loss: 3.1202 (3.1202) grad_norm: 2.6262 (2.6262) time: 4.0182 [2021-03-28 13:52:02 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 10/1251] eta: 0:19:39 lr: 0.000026 loss: 2.4910 (2.6143) grad_norm: 3.5221 (3.4780) time: 0.9505 [2021-03-28 13:52:08 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 20/1251] eta: 0:16:21 lr: 0.000026 loss: 2.4557 (2.5564) grad_norm: 3.2975 (3.3700) time: 0.6367 [2021-03-28 13:52:14 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 30/1251] eta: 0:15:10 lr: 0.000026 loss: 2.7849 (2.6388) grad_norm: 3.2780 (3.4011) time: 0.6329 [2021-03-28 13:52:21 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 40/1251] eta: 0:14:27 lr: 0.000026 loss: 2.8470 (2.6985) grad_norm: 3.3591 (3.6358) time: 0.6316 [2021-03-28 13:52:27 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 50/1251] eta: 0:14:02 lr: 0.000025 loss: 2.9713 (2.7244) grad_norm: 3.3641 (3.6194) time: 0.6337 [2021-03-28 13:52:33 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 60/1251] eta: 0:13:42 lr: 0.000025 loss: 2.6869 (2.6823) grad_norm: 3.1435 (3.5883) time: 0.6377 [2021-03-28 13:52:40 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 70/1251] eta: 0:13:25 lr: 0.000025 loss: 2.5565 (2.6774) grad_norm: 3.1333 (3.8957) time: 0.6316 [2021-03-28 13:52:46 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 80/1251] eta: 0:13:10 lr: 0.000025 loss: 2.7775 (2.6814) grad_norm: 3.3536 (3.8464) time: 0.6277 [2021-03-28 13:52:52 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 90/1251] eta: 0:12:58 lr: 0.000025 loss: 2.7622 (2.6897) grad_norm: 3.3693 (3.9051) time: 0.6283 [2021-03-28 13:52:59 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 100/1251] eta: 0:12:47 lr: 0.000025 loss: 2.6877 (2.6948) grad_norm: 3.3975 (3.8926) time: 0.6337 [2021-03-28 13:53:05 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 110/1251] eta: 0:12:37 lr: 0.000025 loss: 2.6176 (2.6835) grad_norm: 3.1471 (3.8163) time: 0.6360 [2021-03-28 13:53:11 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 120/1251] eta: 0:12:28 lr: 0.000025 loss: 2.5416 (2.6776) grad_norm: 3.2792 (3.8434) time: 0.6351 [2021-03-28 13:53:18 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 130/1251] eta: 0:12:18 lr: 0.000025 loss: 2.6430 (2.6780) grad_norm: 3.4277 (3.8100) time: 0.6292 [2021-03-28 13:53:24 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 140/1251] eta: 0:12:09 lr: 0.000025 loss: 2.7914 (2.6873) grad_norm: 3.3165 (3.8040) time: 0.6233 [2021-03-28 13:53:30 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 150/1251] eta: 0:12:00 lr: 0.000025 loss: 2.6606 (2.6721) grad_norm: 3.1855 (3.8147) time: 0.6276 [2021-03-28 13:53:36 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 160/1251] eta: 0:11:52 lr: 0.000025 loss: 2.6606 (2.6800) grad_norm: 3.1855 (3.7822) time: 0.6326 [2021-03-28 13:53:43 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 170/1251] eta: 0:11:45 lr: 0.000025 loss: 2.7588 (2.6818) grad_norm: 3.3970 (3.7987) time: 0.6363 [2021-03-28 13:53:49 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 180/1251] eta: 0:11:37 lr: 0.000025 loss: 2.5600 (2.6775) grad_norm: 3.6578 (3.7905) time: 0.6360 [2021-03-28 13:53:55 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 190/1251] eta: 0:11:29 lr: 0.000025 loss: 2.6453 (2.6750) grad_norm: 3.5681 (3.7750) time: 0.6324 [2021-03-28 13:54:02 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 200/1251] eta: 0:11:22 lr: 0.000025 loss: 2.7513 (2.6825) grad_norm: 3.6631 (3.7747) time: 0.6302 [2021-03-28 13:54:08 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 210/1251] eta: 0:11:15 lr: 0.000025 loss: 2.7268 (2.6765) grad_norm: 3.6631 (3.7733) time: 0.6312 [2021-03-28 13:54:14 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 220/1251] eta: 0:11:07 lr: 0.000025 loss: 2.7276 (2.6835) grad_norm: 3.5987 (3.7660) time: 0.6276 [2021-03-28 13:54:21 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 230/1251] eta: 0:11:00 lr: 0.000025 loss: 2.8922 (2.6911) grad_norm: 3.5108 (3.7541) time: 0.6250 [2021-03-28 13:54:27 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 240/1251] eta: 0:10:52 lr: 0.000025 loss: 2.8922 (2.6918) grad_norm: 3.5070 (3.7495) time: 0.6285 [2021-03-28 13:54:33 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 250/1251] eta: 0:10:46 lr: 0.000025 loss: 2.7281 (2.6869) grad_norm: 3.5750 (3.7395) time: 0.6365 [2021-03-28 13:54:40 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 260/1251] eta: 0:10:39 lr: 0.000025 loss: 2.7866 (2.6931) grad_norm: 3.6461 (3.7486) time: 0.6399 [2021-03-28 13:54:46 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 270/1251] eta: 0:10:32 lr: 0.000025 loss: 2.7407 (2.6815) grad_norm: 3.6143 (3.7381) time: 0.6341 [2021-03-28 13:54:52 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 280/1251] eta: 0:10:25 lr: 0.000025 loss: 2.3692 (2.6723) grad_norm: 3.2443 (3.7154) time: 0.6334 [2021-03-28 13:54:59 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 290/1251] eta: 0:10:19 lr: 0.000025 loss: 2.4530 (2.6656) grad_norm: 3.1753 (3.7070) time: 0.6358 [2021-03-28 13:55:05 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 300/1251] eta: 0:10:12 lr: 0.000025 loss: 2.6820 (2.6682) grad_norm: 3.1753 (3.6889) time: 0.6345 [2021-03-28 13:55:11 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 310/1251] eta: 0:10:05 lr: 0.000025 loss: 2.8389 (2.6718) grad_norm: 3.1959 (3.6852) time: 0.6337 [2021-03-28 13:55:18 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 320/1251] eta: 0:09:58 lr: 0.000025 loss: 2.7169 (2.6731) grad_norm: 3.3852 (3.6860) time: 0.6302 [2021-03-28 13:55:24 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 330/1251] eta: 0:09:52 lr: 0.000025 loss: 2.7393 (2.6763) grad_norm: 3.3852 (3.6948) time: 0.6331 [2021-03-28 13:55:30 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 340/1251] eta: 0:09:45 lr: 0.000025 loss: 2.8077 (2.6769) grad_norm: 3.2860 (3.6873) time: 0.6383 [2021-03-28 13:55:37 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 350/1251] eta: 0:09:38 lr: 0.000025 loss: 2.9202 (2.6872) grad_norm: 3.4378 (3.6920) time: 0.6286 [2021-03-28 13:55:43 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 360/1251] eta: 0:09:31 lr: 0.000025 loss: 2.8684 (2.6855) grad_norm: 3.4081 (3.6920) time: 0.6230 [2021-03-28 13:55:49 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 370/1251] eta: 0:09:25 lr: 0.000025 loss: 2.6596 (2.6841) grad_norm: 3.3827 (3.6926) time: 0.6294 [2021-03-28 13:55:56 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 380/1251] eta: 0:09:18 lr: 0.000025 loss: 2.7616 (2.6875) grad_norm: 3.3827 (3.6882) time: 0.6352 [2021-03-28 13:56:02 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 390/1251] eta: 0:09:11 lr: 0.000025 loss: 2.7110 (2.6822) grad_norm: 3.5058 (3.6972) time: 0.6314 [2021-03-28 13:56:08 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 400/1251] eta: 0:09:05 lr: 0.000025 loss: 2.6156 (2.6798) grad_norm: 3.5058 (3.7019) time: 0.6273 [2021-03-28 13:56:14 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 410/1251] eta: 0:08:58 lr: 0.000025 loss: 2.7310 (2.6826) grad_norm: 3.2475 (3.6900) time: 0.6308 [2021-03-28 13:56:21 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 420/1251] eta: 0:08:51 lr: 0.000025 loss: 2.7480 (2.6793) grad_norm: 3.2374 (3.6909) time: 0.6307 [2021-03-28 13:56:27 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 430/1251] eta: 0:08:45 lr: 0.000025 loss: 2.6668 (2.6792) grad_norm: 3.2754 (3.6852) time: 0.6322 [2021-03-28 13:56:33 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 440/1251] eta: 0:08:38 lr: 0.000025 loss: 2.7880 (2.6813) grad_norm: 3.4018 (3.6840) time: 0.6324 [2021-03-28 13:56:40 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 450/1251] eta: 0:08:32 lr: 0.000025 loss: 2.8105 (2.6840) grad_norm: 3.6053 (3.6866) time: 0.6294 [2021-03-28 13:56:46 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 460/1251] eta: 0:08:25 lr: 0.000025 loss: 2.8047 (2.6847) grad_norm: 3.3002 (3.6778) time: 0.6365 [2021-03-28 13:56:53 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 470/1251] eta: 0:08:19 lr: 0.000025 loss: 2.6877 (2.6798) grad_norm: 3.1168 (3.6687) time: 0.6429 [2021-03-28 13:56:59 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 480/1251] eta: 0:08:12 lr: 0.000025 loss: 2.6023 (2.6780) grad_norm: 3.2739 (3.6766) time: 0.6335 [2021-03-28 13:57:05 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 490/1251] eta: 0:08:06 lr: 0.000025 loss: 2.7080 (2.6779) grad_norm: 3.4261 (3.6792) time: 0.6241 [2021-03-28 13:57:11 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 500/1251] eta: 0:07:59 lr: 0.000025 loss: 2.7080 (2.6753) grad_norm: 3.4261 (3.6770) time: 0.6330 [2021-03-28 13:57:18 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 510/1251] eta: 0:07:53 lr: 0.000025 loss: 2.4544 (2.6721) grad_norm: 3.4748 (3.6855) time: 0.6344 [2021-03-28 13:57:24 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 520/1251] eta: 0:07:46 lr: 0.000025 loss: 2.7346 (2.6731) grad_norm: 3.4748 (3.6816) time: 0.6318 [2021-03-28 13:57:30 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 530/1251] eta: 0:07:40 lr: 0.000025 loss: 2.7484 (2.6735) grad_norm: 3.4566 (3.6774) time: 0.6330 [2021-03-28 13:57:37 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 540/1251] eta: 0:07:34 lr: 0.000025 loss: 2.7406 (2.6777) grad_norm: 3.1665 (3.6683) time: 0.6396 [2021-03-28 13:57:43 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 550/1251] eta: 0:07:27 lr: 0.000025 loss: 2.7227 (2.6760) grad_norm: 3.1665 (3.6690) time: 0.6459 [2021-03-28 13:57:50 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 560/1251] eta: 0:07:21 lr: 0.000025 loss: 2.5981 (2.6765) grad_norm: 3.4880 (3.6715) time: 0.6394 [2021-03-28 13:57:56 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 570/1251] eta: 0:07:14 lr: 0.000025 loss: 2.7850 (2.6794) grad_norm: 3.5227 (3.6704) time: 0.6332 [2021-03-28 13:58:02 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 580/1251] eta: 0:07:08 lr: 0.000025 loss: 2.8444 (2.6820) grad_norm: 3.5716 (3.6757) time: 0.6373 [2021-03-28 13:58:09 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 590/1251] eta: 0:07:02 lr: 0.000025 loss: 2.7644 (2.6791) grad_norm: 3.6172 (3.6826) time: 0.6388 [2021-03-28 13:58:15 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 600/1251] eta: 0:06:55 lr: 0.000025 loss: 2.4486 (2.6790) grad_norm: 3.8043 (3.6918) time: 0.6337 [2021-03-28 13:58:21 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 610/1251] eta: 0:06:49 lr: 0.000025 loss: 2.6636 (2.6760) grad_norm: 3.8624 (3.7062) time: 0.6308 [2021-03-28 13:58:28 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 620/1251] eta: 0:06:42 lr: 0.000025 loss: 2.6542 (2.6742) grad_norm: 3.4070 (3.6987) time: 0.6333 [2021-03-28 13:58:34 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 630/1251] eta: 0:06:36 lr: 0.000025 loss: 2.6660 (2.6753) grad_norm: 3.3461 (3.6973) time: 0.6384 [2021-03-28 13:58:40 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 640/1251] eta: 0:06:29 lr: 0.000025 loss: 2.7575 (2.6755) grad_norm: 3.3834 (3.6933) time: 0.6307 [2021-03-28 13:58:47 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 650/1251] eta: 0:06:23 lr: 0.000025 loss: 2.5374 (2.6711) grad_norm: 3.2689 (3.6911) time: 0.6238 [2021-03-28 13:58:53 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 660/1251] eta: 0:06:16 lr: 0.000025 loss: 2.8998 (2.6748) grad_norm: 3.2689 (3.6889) time: 0.6242 [2021-03-28 13:58:59 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 670/1251] eta: 0:06:10 lr: 0.000025 loss: 2.7252 (2.6741) grad_norm: 3.2736 (3.6877) time: 0.6301 [2021-03-28 13:59:06 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 680/1251] eta: 0:06:04 lr: 0.000025 loss: 2.6296 (2.6723) grad_norm: 3.3935 (3.7072) time: 0.6354 [2021-03-28 13:59:12 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 690/1251] eta: 0:05:57 lr: 0.000025 loss: 2.5983 (2.6722) grad_norm: 3.3556 (3.7049) time: 0.6304 [2021-03-28 13:59:18 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 700/1251] eta: 0:05:51 lr: 0.000025 loss: 2.7502 (2.6731) grad_norm: 3.1948 (3.6987) time: 0.6353 [2021-03-28 13:59:25 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 710/1251] eta: 0:05:44 lr: 0.000025 loss: 2.8692 (2.6758) grad_norm: 3.4276 (3.7013) time: 0.6385 [2021-03-28 13:59:31 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 720/1251] eta: 0:05:38 lr: 0.000025 loss: 2.8576 (2.6773) grad_norm: 3.3536 (3.6960) time: 0.6277 [2021-03-28 13:59:37 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 730/1251] eta: 0:05:32 lr: 0.000025 loss: 2.8600 (2.6800) grad_norm: 3.3220 (3.6960) time: 0.6359 [2021-03-28 13:59:44 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 740/1251] eta: 0:05:25 lr: 0.000025 loss: 2.8360 (2.6815) grad_norm: 3.3220 (3.6924) time: 0.6457 [2021-03-28 13:59:50 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 750/1251] eta: 0:05:19 lr: 0.000025 loss: 2.7716 (2.6811) grad_norm: 3.2879 (3.6925) time: 0.6377 [2021-03-28 13:59:56 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 760/1251] eta: 0:05:13 lr: 0.000025 loss: 2.7118 (2.6809) grad_norm: 3.3859 (3.7110) time: 0.6326 [2021-03-28 14:00:03 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 770/1251] eta: 0:05:06 lr: 0.000025 loss: 2.7193 (2.6823) grad_norm: 3.4278 (3.7076) time: 0.6355 [2021-03-28 14:00:09 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 780/1251] eta: 0:05:00 lr: 0.000025 loss: 2.6915 (2.6809) grad_norm: 3.4152 (3.7029) time: 0.6368 [2021-03-28 14:00:16 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 790/1251] eta: 0:04:53 lr: 0.000025 loss: 2.8941 (2.6844) grad_norm: 3.4152 (3.7055) time: 0.6361 [2021-03-28 14:00:22 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 800/1251] eta: 0:04:47 lr: 0.000025 loss: 2.9492 (2.6841) grad_norm: 3.5646 (3.7052) time: 0.6325 [2021-03-28 14:00:28 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 810/1251] eta: 0:04:40 lr: 0.000025 loss: 2.7115 (2.6854) grad_norm: 3.4928 (3.7001) time: 0.6247 [2021-03-28 14:00:34 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 820/1251] eta: 0:04:34 lr: 0.000025 loss: 2.6210 (2.6829) grad_norm: 3.1730 (3.6955) time: 0.6225 [2021-03-28 14:00:41 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 830/1251] eta: 0:04:28 lr: 0.000025 loss: 2.3922 (2.6819) grad_norm: 3.1371 (3.6916) time: 0.6272 [2021-03-28 14:00:47 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 840/1251] eta: 0:04:21 lr: 0.000025 loss: 2.5860 (2.6813) grad_norm: 3.4592 (3.6983) time: 0.6328 [2021-03-28 14:00:53 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 850/1251] eta: 0:04:15 lr: 0.000025 loss: 2.8157 (2.6829) grad_norm: 3.6933 (3.7003) time: 0.6283 [2021-03-28 14:00:59 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 860/1251] eta: 0:04:08 lr: 0.000025 loss: 2.7767 (2.6844) grad_norm: 3.3898 (3.6954) time: 0.6209 [2021-03-28 14:01:06 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 870/1251] eta: 0:04:02 lr: 0.000025 loss: 2.7767 (2.6843) grad_norm: 3.2910 (3.6936) time: 0.6277 [2021-03-28 14:01:12 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 880/1251] eta: 0:03:56 lr: 0.000025 loss: 2.8558 (2.6868) grad_norm: 3.4495 (3.6952) time: 0.6396 [2021-03-28 14:01:19 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 890/1251] eta: 0:03:49 lr: 0.000025 loss: 2.9056 (2.6877) grad_norm: 3.4041 (3.6969) time: 0.6416 [2021-03-28 14:01:25 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 900/1251] eta: 0:03:43 lr: 0.000025 loss: 2.7970 (2.6879) grad_norm: 3.3884 (3.6953) time: 0.6383 [2021-03-28 14:01:31 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 910/1251] eta: 0:03:37 lr: 0.000025 loss: 2.7646 (2.6874) grad_norm: 3.3294 (3.6907) time: 0.6339 [2021-03-28 14:01:38 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 920/1251] eta: 0:03:30 lr: 0.000025 loss: 2.7646 (2.6867) grad_norm: 3.3529 (3.6932) time: 0.6291 [2021-03-28 14:01:44 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 930/1251] eta: 0:03:24 lr: 0.000025 loss: 2.6325 (2.6843) grad_norm: 3.3635 (3.6918) time: 0.6282 [2021-03-28 14:01:50 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 940/1251] eta: 0:03:17 lr: 0.000025 loss: 2.6661 (2.6831) grad_norm: 3.2365 (3.6955) time: 0.6315 [2021-03-28 14:01:56 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 950/1251] eta: 0:03:11 lr: 0.000025 loss: 2.7689 (2.6844) grad_norm: 3.6891 (3.6959) time: 0.6331 [2021-03-28 14:02:03 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 960/1251] eta: 0:03:05 lr: 0.000025 loss: 2.7728 (2.6837) grad_norm: 3.4799 (3.6930) time: 0.6272 [2021-03-28 14:02:09 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 970/1251] eta: 0:02:58 lr: 0.000025 loss: 2.7783 (2.6826) grad_norm: 3.2134 (3.6915) time: 0.6269 [2021-03-28 14:02:15 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 980/1251] eta: 0:02:52 lr: 0.000025 loss: 2.8382 (2.6846) grad_norm: 3.5409 (3.6912) time: 0.6320 [2021-03-28 14:02:22 swin_base_patch4_window7_224] INFO: Epoch: [276] [ 990/1251] eta: 0:02:45 lr: 0.000025 loss: 2.7681 (2.6832) grad_norm: 3.4442 (3.6921) time: 0.6301 [2021-03-28 14:02:28 swin_base_patch4_window7_224] INFO: Epoch: [276] [1000/1251] eta: 0:02:39 lr: 0.000025 loss: 2.6852 (2.6836) grad_norm: 3.2915 (3.6887) time: 0.6358 [2021-03-28 14:02:34 swin_base_patch4_window7_224] INFO: Epoch: [276] [1010/1251] eta: 0:02:33 lr: 0.000025 loss: 2.8708 (2.6852) grad_norm: 3.4620 (3.6893) time: 0.6352 [2021-03-28 14:02:41 swin_base_patch4_window7_224] INFO: Epoch: [276] [1020/1251] eta: 0:02:26 lr: 0.000025 loss: 2.8031 (2.6856) grad_norm: 3.4887 (3.6878) time: 0.6297 [2021-03-28 14:02:47 swin_base_patch4_window7_224] INFO: Epoch: [276] [1030/1251] eta: 0:02:20 lr: 0.000025 loss: 2.7379 (2.6860) grad_norm: 3.4696 (3.6860) time: 0.6270 [2021-03-28 14:02:53 swin_base_patch4_window7_224] INFO: Epoch: [276] [1040/1251] eta: 0:02:14 lr: 0.000024 loss: 2.7759 (2.6857) grad_norm: 3.3348 (3.6851) time: 0.6245 [2021-03-28 14:03:00 swin_base_patch4_window7_224] INFO: Epoch: [276] [1050/1251] eta: 0:02:07 lr: 0.000024 loss: 2.4815 (2.6840) grad_norm: 3.4282 (3.6841) time: 0.6321 [2021-03-28 14:03:06 swin_base_patch4_window7_224] INFO: Epoch: [276] [1060/1251] eta: 0:02:01 lr: 0.000024 loss: 2.7340 (2.6845) grad_norm: 3.5280 (3.6842) time: 0.6333 [2021-03-28 14:03:12 swin_base_patch4_window7_224] INFO: Epoch: [276] [1070/1251] eta: 0:01:55 lr: 0.000024 loss: 2.7276 (2.6830) grad_norm: 3.4370 (3.6814) time: 0.6325 [2021-03-28 14:03:19 swin_base_patch4_window7_224] INFO: Epoch: [276] [1080/1251] eta: 0:01:48 lr: 0.000024 loss: 2.5925 (2.6825) grad_norm: 3.2052 (3.6819) time: 0.6341 [2021-03-28 14:03:25 swin_base_patch4_window7_224] INFO: Epoch: [276] [1090/1251] eta: 0:01:42 lr: 0.000024 loss: 2.6189 (2.6831) grad_norm: 3.5246 (3.6875) time: 0.6373 [2021-03-28 14:03:31 swin_base_patch4_window7_224] INFO: Epoch: [276] [1100/1251] eta: 0:01:35 lr: 0.000024 loss: 2.6189 (2.6819) grad_norm: 3.5246 (3.6955) time: 0.6397 [2021-03-28 14:03:38 swin_base_patch4_window7_224] INFO: Epoch: [276] [1110/1251] eta: 0:01:29 lr: 0.000024 loss: 2.5948 (2.6820) grad_norm: 3.3744 (3.6921) time: 0.6384 [2021-03-28 14:03:44 swin_base_patch4_window7_224] INFO: Epoch: [276] [1120/1251] eta: 0:01:23 lr: 0.000024 loss: 2.8475 (2.6833) grad_norm: 3.1628 (3.6905) time: 0.6371 [2021-03-28 14:03:50 swin_base_patch4_window7_224] INFO: Epoch: [276] [1130/1251] eta: 0:01:16 lr: 0.000024 loss: 2.8797 (2.6824) grad_norm: 2.9949 (3.6855) time: 0.6311 [2021-03-28 14:03:57 swin_base_patch4_window7_224] INFO: Epoch: [276] [1140/1251] eta: 0:01:10 lr: 0.000024 loss: 2.8385 (2.6837) grad_norm: 3.0049 (3.6820) time: 0.6307 [2021-03-28 14:04:03 swin_base_patch4_window7_224] INFO: Epoch: [276] [1150/1251] eta: 0:01:04 lr: 0.000024 loss: 2.7336 (2.6822) grad_norm: 3.4282 (3.6828) time: 0.6358 [2021-03-28 14:04:09 swin_base_patch4_window7_224] INFO: Epoch: [276] [1160/1251] eta: 0:00:57 lr: 0.000024 loss: 2.6818 (2.6812) grad_norm: 3.7531 (3.6846) time: 0.6344 [2021-03-28 14:04:16 swin_base_patch4_window7_224] INFO: Epoch: [276] [1170/1251] eta: 0:00:51 lr: 0.000024 loss: 2.7021 (2.6809) grad_norm: 3.7744 (3.6905) time: 0.6290 [2021-03-28 14:04:22 swin_base_patch4_window7_224] INFO: Epoch: [276] [1180/1251] eta: 0:00:45 lr: 0.000024 loss: 2.5871 (2.6793) grad_norm: 3.7649 (3.6924) time: 0.6278 [2021-03-28 14:04:28 swin_base_patch4_window7_224] INFO: Epoch: [276] [1190/1251] eta: 0:00:38 lr: 0.000024 loss: 2.6733 (2.6802) grad_norm: 3.6924 (3.6918) time: 0.6346 [2021-03-28 14:04:35 swin_base_patch4_window7_224] INFO: Epoch: [276] [1200/1251] eta: 0:00:32 lr: 0.000024 loss: 3.0019 (2.6804) grad_norm: 3.2579 (3.6870) time: 0.6333 [2021-03-28 14:04:41 swin_base_patch4_window7_224] INFO: Epoch: [276] [1210/1251] eta: 0:00:26 lr: 0.000024 loss: 2.6521 (2.6794) grad_norm: 3.2512 (3.6889) time: 0.6276 [2021-03-28 14:04:47 swin_base_patch4_window7_224] INFO: Epoch: [276] [1220/1251] eta: 0:00:19 lr: 0.000024 loss: 2.7653 (2.6813) grad_norm: 3.3126 (3.6904) time: 0.6260 [2021-03-28 14:04:53 swin_base_patch4_window7_224] INFO: Epoch: [276] [1230/1251] eta: 0:00:13 lr: 0.000024 loss: 2.7895 (2.6816) grad_norm: 3.3727 (3.6897) time: 0.6266 [2021-03-28 14:05:00 swin_base_patch4_window7_224] INFO: Epoch: [276] [1240/1251] eta: 0:00:06 lr: 0.000024 loss: 2.5658 (2.6798) grad_norm: 3.0982 (3.6861) time: 0.6226 [2021-03-28 14:05:06 swin_base_patch4_window7_224] INFO: Epoch: [276] [1250/1251] eta: 0:00:00 lr: 0.000024 loss: 2.4793 (2.6786) grad_norm: 3.2321 (3.6845) time: 0.6180 [2021-03-28 14:05:19 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:05 loss: 0.5481 (0.5481) acc1: 85.9375 (85.9375) acc5: 98.4375 (98.4375) [2021-03-28 14:05:21 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.6128 (0.7027) acc1: 84.3750 (84.5170) acc5: 98.4375 (97.0170) [2021-03-28 14:05:23 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.6916 (0.7124) acc1: 81.2500 (83.2589) acc5: 96.8750 (97.0982) [2021-03-28 14:05:26 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7025 (0.7347) acc1: 81.2500 (82.3085) acc5: 96.8750 (97.0262) [2021-03-28 14:05:28 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7215 (0.7452) acc1: 79.6875 (82.0884) acc5: 96.8750 (96.6082) [2021-03-28 14:05:29 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7573 (0.7579) acc1: 81.1321 (82.0160) acc5: 95.3125 (96.6080) [2021-03-28 14:05:45 swin_base_patch4_window7_224] INFO: * Acc@1 83.270 Acc@5 96.386 loss 0.742 [2021-03-28 14:05:45 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.3% [2021-03-28 14:05:45 swin_base_patch4_window7_224] INFO: Max accuracy: 83.34% [2021-03-28 14:05:50 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 0/1251] eta: 1:46:42 lr: 0.000024 loss: 2.2089 (2.2089) grad_norm: 3.9030 (3.9030) time: 5.1181 [2021-03-28 14:05:56 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 10/1251] eta: 0:21:42 lr: 0.000024 loss: 2.5424 (2.5448) grad_norm: 3.5002 (3.8325) time: 1.0496 [2021-03-28 14:06:03 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 20/1251] eta: 0:17:26 lr: 0.000024 loss: 2.6118 (2.6177) grad_norm: 3.3481 (3.5880) time: 0.6366 [2021-03-28 14:06:09 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 30/1251] eta: 0:15:50 lr: 0.000024 loss: 2.6902 (2.6048) grad_norm: 3.4775 (4.3074) time: 0.6293 [2021-03-28 14:06:15 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 40/1251] eta: 0:15:00 lr: 0.000024 loss: 2.6902 (2.6090) grad_norm: 3.3191 (4.0343) time: 0.6316 [2021-03-28 14:06:22 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 50/1251] eta: 0:14:27 lr: 0.000024 loss: 2.6894 (2.5985) grad_norm: 3.2972 (4.0717) time: 0.6350 [2021-03-28 14:06:28 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 60/1251] eta: 0:14:03 lr: 0.000024 loss: 2.6894 (2.6083) grad_norm: 3.3302 (3.9483) time: 0.6350 [2021-03-28 14:06:34 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 70/1251] eta: 0:13:42 lr: 0.000024 loss: 2.8226 (2.6378) grad_norm: 3.3828 (4.2405) time: 0.6314 [2021-03-28 14:06:40 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 80/1251] eta: 0:13:26 lr: 0.000024 loss: 2.8226 (2.6391) grad_norm: 3.3735 (4.1324) time: 0.6290 [2021-03-28 14:06:47 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 90/1251] eta: 0:13:11 lr: 0.000024 loss: 2.6042 (2.6456) grad_norm: 3.1624 (4.3736) time: 0.6281 [2021-03-28 14:06:53 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 100/1251] eta: 0:12:58 lr: 0.000024 loss: 2.7070 (2.6321) grad_norm: 3.1465 (4.2925) time: 0.6292 [2021-03-28 14:06:59 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 110/1251] eta: 0:12:47 lr: 0.000024 loss: 2.5583 (2.6296) grad_norm: 3.4140 (4.2886) time: 0.6334 [2021-03-28 14:07:06 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 120/1251] eta: 0:12:37 lr: 0.000024 loss: 2.6809 (2.6322) grad_norm: 3.4287 (4.2359) time: 0.6342 [2021-03-28 14:07:12 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 130/1251] eta: 0:12:27 lr: 0.000024 loss: 2.8029 (2.6390) grad_norm: 3.2504 (4.1648) time: 0.6316 [2021-03-28 14:07:18 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 140/1251] eta: 0:12:17 lr: 0.000024 loss: 2.7531 (2.6432) grad_norm: 3.3812 (4.1321) time: 0.6277 [2021-03-28 14:07:25 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 150/1251] eta: 0:12:09 lr: 0.000024 loss: 2.7322 (2.6414) grad_norm: 3.3977 (4.1021) time: 0.6368 [2021-03-28 14:07:31 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 160/1251] eta: 0:12:00 lr: 0.000024 loss: 2.8100 (2.6452) grad_norm: 3.1635 (4.0877) time: 0.6398 [2021-03-28 14:07:37 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 170/1251] eta: 0:11:51 lr: 0.000024 loss: 2.8518 (2.6369) grad_norm: 3.1798 (4.0471) time: 0.6263 [2021-03-28 14:07:44 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 180/1251] eta: 0:11:43 lr: 0.000024 loss: 2.3865 (2.6367) grad_norm: 3.1798 (3.9989) time: 0.6296 [2021-03-28 14:07:50 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 190/1251] eta: 0:11:36 lr: 0.000024 loss: 2.3865 (2.6261) grad_norm: 3.1628 (3.9674) time: 0.6382 [2021-03-28 14:07:56 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 200/1251] eta: 0:11:28 lr: 0.000024 loss: 2.4757 (2.6201) grad_norm: 3.4941 (3.9745) time: 0.6356 [2021-03-28 14:08:03 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 210/1251] eta: 0:11:20 lr: 0.000024 loss: 2.5894 (2.6189) grad_norm: 3.6680 (3.9743) time: 0.6305 [2021-03-28 14:08:09 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 220/1251] eta: 0:11:12 lr: 0.000024 loss: 2.7674 (2.6244) grad_norm: 3.2042 (3.9424) time: 0.6261 [2021-03-28 14:08:15 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 230/1251] eta: 0:11:05 lr: 0.000024 loss: 2.7674 (2.6364) grad_norm: 3.1712 (3.9258) time: 0.6275 [2021-03-28 14:08:22 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 240/1251] eta: 0:10:57 lr: 0.000024 loss: 2.9118 (2.6461) grad_norm: 3.2674 (3.9216) time: 0.6316 [2021-03-28 14:08:28 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 250/1251] eta: 0:10:50 lr: 0.000024 loss: 2.8425 (2.6471) grad_norm: 3.1227 (3.8914) time: 0.6299 [2021-03-28 14:08:34 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 260/1251] eta: 0:10:43 lr: 0.000024 loss: 2.7461 (2.6459) grad_norm: 3.1659 (3.8787) time: 0.6267 [2021-03-28 14:08:40 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 270/1251] eta: 0:10:35 lr: 0.000024 loss: 2.5379 (2.6381) grad_norm: 3.1659 (3.8539) time: 0.6249 [2021-03-28 14:08:47 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 280/1251] eta: 0:10:28 lr: 0.000024 loss: 2.7744 (2.6478) grad_norm: 3.6261 (3.8633) time: 0.6253 [2021-03-28 14:08:53 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 290/1251] eta: 0:10:21 lr: 0.000024 loss: 2.8603 (2.6499) grad_norm: 3.6532 (3.8592) time: 0.6291 [2021-03-28 14:08:59 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 300/1251] eta: 0:10:14 lr: 0.000024 loss: 2.8067 (2.6507) grad_norm: 3.4310 (3.8463) time: 0.6308 [2021-03-28 14:09:06 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 310/1251] eta: 0:10:07 lr: 0.000024 loss: 2.8089 (2.6520) grad_norm: 3.6524 (3.8568) time: 0.6368 [2021-03-28 14:09:12 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 320/1251] eta: 0:10:01 lr: 0.000024 loss: 2.7488 (2.6499) grad_norm: 3.1898 (3.8373) time: 0.6368 [2021-03-28 14:09:18 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 330/1251] eta: 0:09:53 lr: 0.000024 loss: 2.7239 (2.6465) grad_norm: 3.1898 (3.8267) time: 0.6266 [2021-03-28 14:09:24 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 340/1251] eta: 0:09:46 lr: 0.000024 loss: 2.7957 (2.6521) grad_norm: 3.4550 (3.8296) time: 0.6204 [2021-03-28 14:09:31 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 350/1251] eta: 0:09:39 lr: 0.000024 loss: 2.8523 (2.6573) grad_norm: 3.3356 (3.8167) time: 0.6221 [2021-03-28 14:09:37 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 360/1251] eta: 0:09:33 lr: 0.000024 loss: 2.8988 (2.6667) grad_norm: 3.3988 (3.8173) time: 0.6345 [2021-03-28 14:09:43 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 370/1251] eta: 0:09:26 lr: 0.000024 loss: 2.8953 (2.6667) grad_norm: 3.6847 (3.8196) time: 0.6364 [2021-03-28 14:09:50 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 380/1251] eta: 0:09:19 lr: 0.000024 loss: 2.8169 (2.6683) grad_norm: 3.3130 (3.7982) time: 0.6296 [2021-03-28 14:09:56 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 390/1251] eta: 0:09:12 lr: 0.000024 loss: 2.8872 (2.6752) grad_norm: 3.1564 (3.7993) time: 0.6251 [2021-03-28 14:10:02 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 400/1251] eta: 0:09:06 lr: 0.000024 loss: 2.8500 (2.6690) grad_norm: 3.2972 (3.7852) time: 0.6221 [2021-03-28 14:10:08 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 410/1251] eta: 0:08:59 lr: 0.000024 loss: 2.4560 (2.6666) grad_norm: 3.1088 (3.7713) time: 0.6240 [2021-03-28 14:10:15 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 420/1251] eta: 0:08:52 lr: 0.000024 loss: 2.7351 (2.6691) grad_norm: 3.2992 (3.8923) time: 0.6282 [2021-03-28 14:10:21 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 430/1251] eta: 0:08:46 lr: 0.000024 loss: 2.5948 (2.6646) grad_norm: 3.4030 (3.8795) time: 0.6347 [2021-03-28 14:10:27 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 440/1251] eta: 0:08:39 lr: 0.000024 loss: 2.5948 (2.6656) grad_norm: 3.4030 (3.9078) time: 0.6346 [2021-03-28 14:10:34 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 450/1251] eta: 0:08:33 lr: 0.000024 loss: 2.8223 (2.6666) grad_norm: 3.5101 (3.9045) time: 0.6337 [2021-03-28 14:10:40 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 460/1251] eta: 0:08:26 lr: 0.000024 loss: 2.7786 (2.6694) grad_norm: 3.4815 (3.8968) time: 0.6397 [2021-03-28 14:10:47 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 470/1251] eta: 0:08:20 lr: 0.000024 loss: 2.7614 (2.6709) grad_norm: 3.3928 (3.8898) time: 0.6404 [2021-03-28 14:10:53 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 480/1251] eta: 0:08:13 lr: 0.000024 loss: 2.7019 (2.6711) grad_norm: 3.3475 (3.8834) time: 0.6361 [2021-03-28 14:10:59 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 490/1251] eta: 0:08:07 lr: 0.000024 loss: 2.7750 (2.6743) grad_norm: 3.6167 (3.8793) time: 0.6299 [2021-03-28 14:11:05 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 500/1251] eta: 0:08:00 lr: 0.000024 loss: 2.6790 (2.6693) grad_norm: 3.5758 (3.8701) time: 0.6260 [2021-03-28 14:11:12 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 510/1251] eta: 0:07:54 lr: 0.000024 loss: 2.5571 (2.6696) grad_norm: 3.4751 (3.8797) time: 0.6278 [2021-03-28 14:11:18 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 520/1251] eta: 0:07:47 lr: 0.000024 loss: 2.6674 (2.6675) grad_norm: 3.1668 (3.8658) time: 0.6303 [2021-03-28 14:11:24 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 530/1251] eta: 0:07:41 lr: 0.000024 loss: 2.6584 (2.6668) grad_norm: 3.1698 (3.8604) time: 0.6338 [2021-03-28 14:11:31 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 540/1251] eta: 0:07:34 lr: 0.000024 loss: 2.7829 (2.6711) grad_norm: 3.3921 (3.8574) time: 0.6304 [2021-03-28 14:11:37 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 550/1251] eta: 0:07:28 lr: 0.000024 loss: 2.8390 (2.6707) grad_norm: 3.2838 (3.8481) time: 0.6360 [2021-03-28 14:11:43 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 560/1251] eta: 0:07:21 lr: 0.000024 loss: 2.7359 (2.6694) grad_norm: 3.3456 (3.8436) time: 0.6408 [2021-03-28 14:11:50 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 570/1251] eta: 0:07:15 lr: 0.000024 loss: 2.8363 (2.6744) grad_norm: 3.2979 (3.8354) time: 0.6321 [2021-03-28 14:11:56 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 580/1251] eta: 0:07:08 lr: 0.000024 loss: 2.8363 (2.6730) grad_norm: 3.2979 (3.8494) time: 0.6326 [2021-03-28 14:12:02 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 590/1251] eta: 0:07:02 lr: 0.000024 loss: 2.7252 (2.6734) grad_norm: 3.2379 (3.8373) time: 0.6333 [2021-03-28 14:12:09 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 600/1251] eta: 0:06:56 lr: 0.000024 loss: 2.5550 (2.6706) grad_norm: 3.2086 (3.8387) time: 0.6357 [2021-03-28 14:12:15 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 610/1251] eta: 0:06:49 lr: 0.000024 loss: 2.5457 (2.6692) grad_norm: 3.4871 (nan) time: 0.6362 [2021-03-28 14:12:22 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 620/1251] eta: 0:06:43 lr: 0.000024 loss: 2.6965 (2.6705) grad_norm: 3.3668 (nan) time: 0.6372 [2021-03-28 14:12:28 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 630/1251] eta: 0:06:36 lr: 0.000024 loss: 2.7915 (2.6693) grad_norm: 3.2648 (nan) time: 0.6400 [2021-03-28 14:12:34 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 640/1251] eta: 0:06:30 lr: 0.000024 loss: 2.7305 (2.6670) grad_norm: 3.5222 (nan) time: 0.6389 [2021-03-28 14:12:41 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 650/1251] eta: 0:06:23 lr: 0.000024 loss: 2.6366 (2.6662) grad_norm: 3.5222 (nan) time: 0.6365 [2021-03-28 14:12:47 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 660/1251] eta: 0:06:17 lr: 0.000024 loss: 2.6366 (2.6649) grad_norm: 3.4291 (nan) time: 0.6309 [2021-03-28 14:12:53 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 670/1251] eta: 0:06:11 lr: 0.000024 loss: 2.7341 (2.6656) grad_norm: 3.2198 (nan) time: 0.6374 [2021-03-28 14:13:00 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 680/1251] eta: 0:06:04 lr: 0.000024 loss: 2.6839 (2.6664) grad_norm: 3.3946 (nan) time: 0.6425 [2021-03-28 14:13:06 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 690/1251] eta: 0:05:58 lr: 0.000024 loss: 2.8813 (2.6689) grad_norm: 3.3821 (nan) time: 0.6366 [2021-03-28 14:13:13 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 700/1251] eta: 0:05:51 lr: 0.000024 loss: 2.8991 (2.6695) grad_norm: 3.2494 (nan) time: 0.6346 [2021-03-28 14:13:19 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 710/1251] eta: 0:05:45 lr: 0.000024 loss: 2.7953 (2.6684) grad_norm: 3.2062 (nan) time: 0.6366 [2021-03-28 14:13:25 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 720/1251] eta: 0:05:39 lr: 0.000024 loss: 2.5989 (2.6679) grad_norm: 3.3986 (nan) time: 0.6395 [2021-03-28 14:13:32 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 730/1251] eta: 0:05:32 lr: 0.000024 loss: 2.6378 (2.6692) grad_norm: 3.3986 (nan) time: 0.6369 [2021-03-28 14:13:38 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 740/1251] eta: 0:05:26 lr: 0.000024 loss: 2.7657 (2.6721) grad_norm: 3.1623 (nan) time: 0.6400 [2021-03-28 14:13:45 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 750/1251] eta: 0:05:20 lr: 0.000024 loss: 2.8644 (2.6727) grad_norm: 3.1976 (nan) time: 0.6501 [2021-03-28 14:13:51 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 760/1251] eta: 0:05:13 lr: 0.000024 loss: 2.7222 (2.6719) grad_norm: 3.1993 (nan) time: 0.6433 [2021-03-28 14:13:57 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 770/1251] eta: 0:05:07 lr: 0.000024 loss: 2.7222 (2.6747) grad_norm: 3.0160 (nan) time: 0.6290 [2021-03-28 14:14:04 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 780/1251] eta: 0:05:00 lr: 0.000024 loss: 2.7105 (2.6744) grad_norm: 3.2508 (nan) time: 0.6299 [2021-03-28 14:14:10 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 790/1251] eta: 0:04:54 lr: 0.000024 loss: 2.6345 (2.6730) grad_norm: 3.3792 (nan) time: 0.6331 [2021-03-28 14:14:16 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 800/1251] eta: 0:04:47 lr: 0.000024 loss: 2.6033 (2.6725) grad_norm: 3.3949 (nan) time: 0.6313 [2021-03-28 14:14:23 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 810/1251] eta: 0:04:41 lr: 0.000023 loss: 2.5801 (2.6695) grad_norm: 3.5783 (nan) time: 0.6320 [2021-03-28 14:14:29 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 820/1251] eta: 0:04:35 lr: 0.000023 loss: 2.6380 (2.6693) grad_norm: 3.2856 (nan) time: 0.6269 [2021-03-28 14:14:35 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 830/1251] eta: 0:04:28 lr: 0.000023 loss: 2.9027 (2.6724) grad_norm: 3.3102 (nan) time: 0.6217 [2021-03-28 14:14:41 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 840/1251] eta: 0:04:22 lr: 0.000023 loss: 2.8058 (2.6724) grad_norm: 3.3102 (nan) time: 0.6227 [2021-03-28 14:14:48 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 850/1251] eta: 0:04:15 lr: 0.000023 loss: 2.6954 (2.6732) grad_norm: 3.2619 (nan) time: 0.6292 [2021-03-28 14:14:54 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 860/1251] eta: 0:04:09 lr: 0.000023 loss: 2.8538 (2.6740) grad_norm: 3.3098 (nan) time: 0.6331 [2021-03-28 14:15:00 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 870/1251] eta: 0:04:02 lr: 0.000023 loss: 2.7311 (2.6736) grad_norm: 3.2024 (nan) time: 0.6320 [2021-03-28 14:15:06 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 880/1251] eta: 0:03:56 lr: 0.000023 loss: 2.8539 (2.6761) grad_norm: 3.0449 (nan) time: 0.6301 [2021-03-28 14:15:13 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 890/1251] eta: 0:03:50 lr: 0.000023 loss: 2.8912 (2.6760) grad_norm: 3.1526 (nan) time: 0.6310 [2021-03-28 14:15:19 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 900/1251] eta: 0:03:43 lr: 0.000023 loss: 2.7874 (2.6764) grad_norm: 3.3187 (nan) time: 0.6322 [2021-03-28 14:15:25 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 910/1251] eta: 0:03:37 lr: 0.000023 loss: 2.7147 (2.6750) grad_norm: 3.3187 (nan) time: 0.6281 [2021-03-28 14:15:32 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 920/1251] eta: 0:03:30 lr: 0.000023 loss: 2.5295 (2.6721) grad_norm: 3.3330 (nan) time: 0.6311 [2021-03-28 14:15:38 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 930/1251] eta: 0:03:24 lr: 0.000023 loss: 2.6131 (2.6729) grad_norm: 3.3654 (nan) time: 0.6394 [2021-03-28 14:15:44 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 940/1251] eta: 0:03:18 lr: 0.000023 loss: 2.8344 (2.6733) grad_norm: 3.2951 (nan) time: 0.6354 [2021-03-28 14:15:51 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 950/1251] eta: 0:03:11 lr: 0.000023 loss: 2.8344 (2.6724) grad_norm: 3.5197 (nan) time: 0.6345 [2021-03-28 14:15:57 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 960/1251] eta: 0:03:05 lr: 0.000023 loss: 2.6277 (2.6692) grad_norm: 3.5748 (nan) time: 0.6327 [2021-03-28 14:16:03 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 970/1251] eta: 0:02:59 lr: 0.000023 loss: 2.6872 (2.6707) grad_norm: 3.5590 (nan) time: 0.6263 [2021-03-28 14:16:10 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 980/1251] eta: 0:02:52 lr: 0.000023 loss: 2.7115 (2.6693) grad_norm: 3.5590 (nan) time: 0.6264 [2021-03-28 14:16:16 swin_base_patch4_window7_224] INFO: Epoch: [277] [ 990/1251] eta: 0:02:46 lr: 0.000023 loss: 2.6045 (2.6688) grad_norm: 3.5645 (nan) time: 0.6263 [2021-03-28 14:16:22 swin_base_patch4_window7_224] INFO: Epoch: [277] [1000/1251] eta: 0:02:39 lr: 0.000023 loss: 2.6045 (2.6683) grad_norm: 3.4505 (nan) time: 0.6249 [2021-03-28 14:16:28 swin_base_patch4_window7_224] INFO: Epoch: [277] [1010/1251] eta: 0:02:33 lr: 0.000023 loss: 2.6061 (2.6660) grad_norm: 3.2496 (nan) time: 0.6263 [2021-03-28 14:16:35 swin_base_patch4_window7_224] INFO: Epoch: [277] [1020/1251] eta: 0:02:27 lr: 0.000023 loss: 2.6263 (2.6660) grad_norm: 3.2348 (nan) time: 0.6353 [2021-03-28 14:16:41 swin_base_patch4_window7_224] INFO: Epoch: [277] [1030/1251] eta: 0:02:20 lr: 0.000023 loss: 2.6263 (2.6657) grad_norm: 3.4366 (nan) time: 0.6343 [2021-03-28 14:16:47 swin_base_patch4_window7_224] INFO: Epoch: [277] [1040/1251] eta: 0:02:14 lr: 0.000023 loss: 2.4467 (2.6634) grad_norm: 3.4328 (nan) time: 0.6268 [2021-03-28 14:16:54 swin_base_patch4_window7_224] INFO: Epoch: [277] [1050/1251] eta: 0:02:07 lr: 0.000023 loss: 2.4096 (2.6620) grad_norm: 3.2970 (nan) time: 0.6359 [2021-03-28 14:17:00 swin_base_patch4_window7_224] INFO: Epoch: [277] [1060/1251] eta: 0:02:01 lr: 0.000023 loss: 2.8285 (2.6638) grad_norm: 3.3682 (nan) time: 0.6455 [2021-03-28 14:17:07 swin_base_patch4_window7_224] INFO: Epoch: [277] [1070/1251] eta: 0:01:55 lr: 0.000023 loss: 2.8169 (2.6625) grad_norm: 3.3682 (nan) time: 0.6389 [2021-03-28 14:17:13 swin_base_patch4_window7_224] INFO: Epoch: [277] [1080/1251] eta: 0:01:48 lr: 0.000023 loss: 2.7054 (2.6637) grad_norm: 3.3260 (nan) time: 0.6344 [2021-03-28 14:17:19 swin_base_patch4_window7_224] INFO: Epoch: [277] [1090/1251] eta: 0:01:42 lr: 0.000023 loss: 2.7493 (2.6639) grad_norm: 3.3260 (nan) time: 0.6362 [2021-03-28 14:17:26 swin_base_patch4_window7_224] INFO: Epoch: [277] [1100/1251] eta: 0:01:36 lr: 0.000023 loss: 2.7493 (2.6633) grad_norm: 3.3279 (nan) time: 0.6352 [2021-03-28 14:17:32 swin_base_patch4_window7_224] INFO: Epoch: [277] [1110/1251] eta: 0:01:29 lr: 0.000023 loss: 2.6818 (2.6650) grad_norm: 3.3279 (nan) time: 0.6335 [2021-03-28 14:17:38 swin_base_patch4_window7_224] INFO: Epoch: [277] [1120/1251] eta: 0:01:23 lr: 0.000023 loss: 2.7668 (2.6657) grad_norm: 3.6336 (nan) time: 0.6362 [2021-03-28 14:17:45 swin_base_patch4_window7_224] INFO: Epoch: [277] [1130/1251] eta: 0:01:17 lr: 0.000023 loss: 2.7322 (2.6650) grad_norm: 3.0952 (nan) time: 0.6373 [2021-03-28 14:17:51 swin_base_patch4_window7_224] INFO: Epoch: [277] [1140/1251] eta: 0:01:10 lr: 0.000023 loss: 2.5487 (2.6625) grad_norm: 2.9849 (nan) time: 0.6310 [2021-03-28 14:17:57 swin_base_patch4_window7_224] INFO: Epoch: [277] [1150/1251] eta: 0:01:04 lr: 0.000023 loss: 2.5487 (2.6639) grad_norm: 3.5001 (nan) time: 0.6244 [2021-03-28 14:18:04 swin_base_patch4_window7_224] INFO: Epoch: [277] [1160/1251] eta: 0:00:57 lr: 0.000023 loss: 2.5778 (2.6630) grad_norm: 3.4715 (nan) time: 0.6286 [2021-03-28 14:18:10 swin_base_patch4_window7_224] INFO: Epoch: [277] [1170/1251] eta: 0:00:51 lr: 0.000023 loss: 2.5689 (2.6629) grad_norm: 3.3675 (nan) time: 0.6376 [2021-03-28 14:18:16 swin_base_patch4_window7_224] INFO: Epoch: [277] [1180/1251] eta: 0:00:45 lr: 0.000023 loss: 2.8260 (2.6656) grad_norm: 3.4016 (nan) time: 0.6380 [2021-03-28 14:18:23 swin_base_patch4_window7_224] INFO: Epoch: [277] [1190/1251] eta: 0:00:38 lr: 0.000023 loss: 2.8892 (2.6660) grad_norm: 3.6345 (nan) time: 0.6350 [2021-03-28 14:18:29 swin_base_patch4_window7_224] INFO: Epoch: [277] [1200/1251] eta: 0:00:32 lr: 0.000023 loss: 2.7224 (2.6655) grad_norm: 3.4726 (nan) time: 0.6324 [2021-03-28 14:18:35 swin_base_patch4_window7_224] INFO: Epoch: [277] [1210/1251] eta: 0:00:26 lr: 0.000023 loss: 2.7860 (2.6659) grad_norm: 3.1787 (nan) time: 0.6305 [2021-03-28 14:18:42 swin_base_patch4_window7_224] INFO: Epoch: [277] [1220/1251] eta: 0:00:19 lr: 0.000023 loss: 2.7860 (2.6656) grad_norm: 3.3336 (nan) time: 0.6299 [2021-03-28 14:18:48 swin_base_patch4_window7_224] INFO: Epoch: [277] [1230/1251] eta: 0:00:13 lr: 0.000023 loss: 2.7416 (2.6664) grad_norm: 3.1710 (nan) time: 0.6280 [2021-03-28 14:18:54 swin_base_patch4_window7_224] INFO: Epoch: [277] [1240/1251] eta: 0:00:06 lr: 0.000023 loss: 3.0167 (2.6696) grad_norm: 3.3034 (nan) time: 0.6284 [2021-03-28 14:19:01 swin_base_patch4_window7_224] INFO: Epoch: [277] [1250/1251] eta: 0:00:00 lr: 0.000023 loss: 2.7258 (2.6677) grad_norm: 3.4615 (nan) time: 0.6292 [2021-03-28 14:19:14 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:20 loss: 0.7767 (0.7767) acc1: 79.6875 (79.6875) acc5: 98.4375 (98.4375) [2021-03-28 14:19:17 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7308 (0.7188) acc1: 82.8125 (82.8125) acc5: 98.4375 (97.5852) [2021-03-28 14:19:19 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7658 (0.7556) acc1: 81.2500 (81.9940) acc5: 95.3125 (96.6518) [2021-03-28 14:19:22 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7668 (0.7711) acc1: 81.2500 (82.0565) acc5: 95.3125 (96.4214) [2021-03-28 14:19:24 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7536 (0.7575) acc1: 82.8125 (82.0503) acc5: 96.8750 (96.5320) [2021-03-28 14:19:25 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7078 (0.7512) acc1: 82.8125 (82.2400) acc5: 96.8750 (96.5120) [2021-03-28 14:19:41 swin_base_patch4_window7_224] INFO: * Acc@1 83.296 Acc@5 96.428 loss 0.742 [2021-03-28 14:19:41 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.3% [2021-03-28 14:19:41 swin_base_patch4_window7_224] INFO: Max accuracy: 83.34% [2021-03-28 14:19:46 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 0/1251] eta: 1:42:13 lr: 0.000023 loss: 2.8765 (2.8765) grad_norm: 4.2286 (4.2286) time: 4.9027 [2021-03-28 14:19:52 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 10/1251] eta: 0:21:14 lr: 0.000023 loss: 2.9511 (2.8117) grad_norm: 3.6757 (4.2209) time: 1.0266 [2021-03-28 14:19:59 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 20/1251] eta: 0:17:15 lr: 0.000023 loss: 2.8340 (2.7306) grad_norm: 3.3930 (3.7472) time: 0.6380 [2021-03-28 14:20:05 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 30/1251] eta: 0:15:46 lr: 0.000023 loss: 2.8006 (2.6796) grad_norm: 3.3221 (3.7274) time: 0.6366 [2021-03-28 14:20:11 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 40/1251] eta: 0:14:57 lr: 0.000023 loss: 2.6628 (2.6444) grad_norm: 3.4103 (3.6766) time: 0.6355 [2021-03-28 14:20:18 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 50/1251] eta: 0:14:23 lr: 0.000023 loss: 2.5963 (2.6184) grad_norm: 3.6180 (3.6871) time: 0.6325 [2021-03-28 14:20:24 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 60/1251] eta: 0:13:59 lr: 0.000023 loss: 2.7059 (2.6178) grad_norm: 3.5692 (3.6416) time: 0.6307 [2021-03-28 14:20:30 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 70/1251] eta: 0:13:41 lr: 0.000023 loss: 2.7479 (2.6515) grad_norm: 3.2272 (3.6077) time: 0.6347 [2021-03-28 14:20:37 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 80/1251] eta: 0:13:23 lr: 0.000023 loss: 2.7479 (2.6437) grad_norm: 3.3291 (3.5764) time: 0.6308 [2021-03-28 14:20:43 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 90/1251] eta: 0:13:11 lr: 0.000023 loss: 2.6572 (2.6325) grad_norm: 3.3291 (3.5847) time: 0.6326 [2021-03-28 14:20:49 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 100/1251] eta: 0:12:58 lr: 0.000023 loss: 2.7463 (2.6538) grad_norm: 3.2841 (3.5638) time: 0.6373 [2021-03-28 14:20:56 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 110/1251] eta: 0:12:48 lr: 0.000023 loss: 2.8632 (2.6674) grad_norm: 3.2147 (3.5495) time: 0.6363 [2021-03-28 14:21:02 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 120/1251] eta: 0:12:38 lr: 0.000023 loss: 2.8528 (2.6694) grad_norm: 3.1647 (3.5289) time: 0.6385 [2021-03-28 14:21:08 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 130/1251] eta: 0:12:28 lr: 0.000023 loss: 2.8528 (2.6750) grad_norm: 3.3048 (3.5187) time: 0.6368 [2021-03-28 14:21:15 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 140/1251] eta: 0:12:19 lr: 0.000023 loss: 2.6915 (2.6718) grad_norm: 3.3419 (3.5186) time: 0.6351 [2021-03-28 14:21:21 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 150/1251] eta: 0:12:09 lr: 0.000023 loss: 2.5830 (2.6646) grad_norm: 3.4206 (3.5610) time: 0.6295 [2021-03-28 14:21:27 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 160/1251] eta: 0:12:00 lr: 0.000023 loss: 2.5134 (2.6637) grad_norm: 3.1968 (3.5575) time: 0.6224 [2021-03-28 14:21:34 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 170/1251] eta: 0:11:52 lr: 0.000023 loss: 2.7403 (2.6583) grad_norm: 3.2236 (3.5484) time: 0.6286 [2021-03-28 14:21:40 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 180/1251] eta: 0:11:44 lr: 0.000023 loss: 2.6120 (2.6533) grad_norm: 3.4089 (3.5559) time: 0.6375 [2021-03-28 14:21:46 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 190/1251] eta: 0:11:36 lr: 0.000023 loss: 2.6730 (2.6549) grad_norm: 3.3810 (3.5735) time: 0.6386 [2021-03-28 14:21:53 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 200/1251] eta: 0:11:29 lr: 0.000023 loss: 2.7190 (2.6585) grad_norm: 3.4130 (3.5777) time: 0.6423 [2021-03-28 14:21:59 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 210/1251] eta: 0:11:21 lr: 0.000023 loss: 2.8298 (2.6662) grad_norm: 3.4212 (3.6218) time: 0.6356 [2021-03-28 14:22:05 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 220/1251] eta: 0:11:13 lr: 0.000023 loss: 2.7303 (2.6612) grad_norm: 3.6655 (3.6211) time: 0.6276 [2021-03-28 14:22:12 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 230/1251] eta: 0:11:06 lr: 0.000023 loss: 2.7096 (2.6621) grad_norm: 3.5321 (3.6146) time: 0.6276 [2021-03-28 14:22:18 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 240/1251] eta: 0:10:58 lr: 0.000023 loss: 2.6019 (2.6535) grad_norm: 3.5321 (3.6212) time: 0.6264 [2021-03-28 14:22:24 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 250/1251] eta: 0:10:51 lr: 0.000023 loss: 2.7330 (2.6658) grad_norm: 3.3237 (3.6161) time: 0.6315 [2021-03-28 14:22:31 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 260/1251] eta: 0:10:44 lr: 0.000023 loss: 2.9001 (2.6667) grad_norm: 3.3808 (3.6344) time: 0.6362 [2021-03-28 14:22:37 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 270/1251] eta: 0:10:37 lr: 0.000023 loss: 2.7026 (2.6663) grad_norm: 3.4920 (3.6437) time: 0.6351 [2021-03-28 14:22:43 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 280/1251] eta: 0:10:30 lr: 0.000023 loss: 2.6655 (2.6607) grad_norm: 3.4416 (3.6624) time: 0.6418 [2021-03-28 14:22:50 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 290/1251] eta: 0:10:23 lr: 0.000023 loss: 2.7324 (2.6663) grad_norm: 3.2561 (3.6648) time: 0.6351 [2021-03-28 14:22:56 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 300/1251] eta: 0:10:16 lr: 0.000023 loss: 2.8200 (2.6624) grad_norm: 3.4031 (3.6736) time: 0.6268 [2021-03-28 14:23:02 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 310/1251] eta: 0:10:09 lr: 0.000023 loss: 2.8200 (2.6704) grad_norm: 3.4478 (3.6795) time: 0.6351 [2021-03-28 14:23:09 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 320/1251] eta: 0:10:02 lr: 0.000023 loss: 2.7735 (2.6723) grad_norm: 3.4118 (3.6861) time: 0.6370 [2021-03-28 14:23:15 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 330/1251] eta: 0:09:55 lr: 0.000023 loss: 2.9225 (2.6800) grad_norm: 3.7620 (3.7049) time: 0.6302 [2021-03-28 14:23:21 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 340/1251] eta: 0:09:48 lr: 0.000023 loss: 2.8011 (2.6800) grad_norm: 3.7620 (3.7060) time: 0.6275 [2021-03-28 14:23:28 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 350/1251] eta: 0:09:41 lr: 0.000023 loss: 2.7496 (2.6833) grad_norm: 3.3496 (3.6951) time: 0.6319 [2021-03-28 14:23:34 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 360/1251] eta: 0:09:35 lr: 0.000023 loss: 2.7345 (2.6839) grad_norm: 3.2321 (3.6889) time: 0.6355 [2021-03-28 14:23:40 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 370/1251] eta: 0:09:28 lr: 0.000023 loss: 2.7345 (2.6881) grad_norm: 3.1586 (3.6987) time: 0.6345 [2021-03-28 14:23:47 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 380/1251] eta: 0:09:21 lr: 0.000023 loss: 2.6471 (2.6785) grad_norm: 3.2476 (3.7013) time: 0.6345 [2021-03-28 14:23:53 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 390/1251] eta: 0:09:15 lr: 0.000023 loss: 2.4496 (2.6780) grad_norm: 3.2476 (3.6944) time: 0.6377 [2021-03-28 14:23:59 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 400/1251] eta: 0:09:08 lr: 0.000023 loss: 2.7693 (2.6787) grad_norm: 3.2292 (3.6914) time: 0.6370 [2021-03-28 14:24:06 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 410/1251] eta: 0:09:01 lr: 0.000023 loss: 2.5932 (2.6712) grad_norm: 3.2891 (3.6823) time: 0.6349 [2021-03-28 14:24:12 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 420/1251] eta: 0:08:55 lr: 0.000023 loss: 2.6223 (2.6703) grad_norm: 3.1707 (3.6716) time: 0.6312 [2021-03-28 14:24:18 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 430/1251] eta: 0:08:48 lr: 0.000023 loss: 2.8670 (2.6742) grad_norm: 3.1669 (3.6672) time: 0.6306 [2021-03-28 14:24:25 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 440/1251] eta: 0:08:41 lr: 0.000023 loss: 2.8033 (2.6758) grad_norm: 3.4023 (3.6654) time: 0.6329 [2021-03-28 14:24:31 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 450/1251] eta: 0:08:35 lr: 0.000023 loss: 2.7661 (2.6789) grad_norm: 3.3770 (3.6584) time: 0.6338 [2021-03-28 14:24:37 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 460/1251] eta: 0:08:28 lr: 0.000023 loss: 2.8739 (2.6819) grad_norm: 3.1989 (3.6505) time: 0.6346 [2021-03-28 14:24:44 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 470/1251] eta: 0:08:22 lr: 0.000023 loss: 2.8192 (2.6832) grad_norm: 3.1295 (3.6430) time: 0.6346 [2021-03-28 14:24:50 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 480/1251] eta: 0:08:15 lr: 0.000023 loss: 2.7900 (2.6832) grad_norm: 3.3712 (3.6444) time: 0.6294 [2021-03-28 14:24:56 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 490/1251] eta: 0:08:08 lr: 0.000023 loss: 2.7168 (2.6812) grad_norm: 3.4316 (3.6371) time: 0.6259 [2021-03-28 14:25:03 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 500/1251] eta: 0:08:02 lr: 0.000023 loss: 2.6797 (2.6812) grad_norm: 3.1505 (3.6297) time: 0.6339 [2021-03-28 14:25:09 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 510/1251] eta: 0:07:55 lr: 0.000023 loss: 2.6797 (2.6812) grad_norm: 3.3078 (3.6305) time: 0.6388 [2021-03-28 14:25:15 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 520/1251] eta: 0:07:49 lr: 0.000023 loss: 2.6372 (2.6764) grad_norm: 3.5260 (3.6334) time: 0.6367 [2021-03-28 14:25:22 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 530/1251] eta: 0:07:42 lr: 0.000023 loss: 2.4530 (2.6749) grad_norm: 3.6130 (3.6374) time: 0.6356 [2021-03-28 14:25:28 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 540/1251] eta: 0:07:36 lr: 0.000023 loss: 2.7101 (2.6733) grad_norm: 3.4102 (3.6354) time: 0.6342 [2021-03-28 14:25:35 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 550/1251] eta: 0:07:29 lr: 0.000023 loss: 2.7123 (2.6717) grad_norm: 3.4265 (3.6352) time: 0.6452 [2021-03-28 14:25:41 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 560/1251] eta: 0:07:23 lr: 0.000023 loss: 2.7597 (2.6737) grad_norm: 3.3086 (3.6316) time: 0.6487 [2021-03-28 14:25:48 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 570/1251] eta: 0:07:17 lr: 0.000023 loss: 2.9273 (2.6780) grad_norm: 3.3073 (3.6305) time: 0.6403 [2021-03-28 14:25:54 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 580/1251] eta: 0:07:10 lr: 0.000023 loss: 2.8843 (2.6770) grad_norm: 3.4557 (3.7296) time: 0.6411 [2021-03-28 14:26:00 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 590/1251] eta: 0:07:04 lr: 0.000023 loss: 2.5029 (2.6743) grad_norm: 3.3115 (3.7249) time: 0.6322 [2021-03-28 14:26:06 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 600/1251] eta: 0:06:57 lr: 0.000023 loss: 2.6297 (2.6741) grad_norm: 3.2625 (3.7294) time: 0.6260 [2021-03-28 14:26:13 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 610/1251] eta: 0:06:51 lr: 0.000023 loss: 2.8394 (2.6752) grad_norm: 3.4228 (3.7333) time: 0.6334 [2021-03-28 14:26:19 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 620/1251] eta: 0:06:44 lr: 0.000022 loss: 2.6134 (2.6722) grad_norm: 3.5766 (3.7349) time: 0.6356 [2021-03-28 14:26:26 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 630/1251] eta: 0:06:38 lr: 0.000022 loss: 2.6658 (2.6737) grad_norm: 3.5766 (3.7565) time: 0.6343 [2021-03-28 14:26:32 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 640/1251] eta: 0:06:31 lr: 0.000022 loss: 2.6658 (2.6713) grad_norm: 3.7729 (3.7593) time: 0.6316 [2021-03-28 14:26:38 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 650/1251] eta: 0:06:25 lr: 0.000022 loss: 2.7048 (2.6725) grad_norm: 3.4425 (3.7783) time: 0.6282 [2021-03-28 14:26:44 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 660/1251] eta: 0:06:18 lr: 0.000022 loss: 2.8044 (2.6728) grad_norm: 3.5353 (3.7888) time: 0.6249 [2021-03-28 14:26:51 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 670/1251] eta: 0:06:12 lr: 0.000022 loss: 2.5558 (2.6699) grad_norm: 3.5254 (3.7874) time: 0.6299 [2021-03-28 14:26:57 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 680/1251] eta: 0:06:05 lr: 0.000022 loss: 2.5410 (2.6702) grad_norm: 3.9289 (3.8034) time: 0.6303 [2021-03-28 14:27:03 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 690/1251] eta: 0:05:59 lr: 0.000022 loss: 2.5410 (2.6691) grad_norm: 3.7072 (3.7967) time: 0.6285 [2021-03-28 14:27:10 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 700/1251] eta: 0:05:52 lr: 0.000022 loss: 2.6118 (2.6695) grad_norm: 3.2584 (3.7941) time: 0.6340 [2021-03-28 14:27:16 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 710/1251] eta: 0:05:46 lr: 0.000022 loss: 2.6118 (2.6670) grad_norm: 3.3291 (3.7965) time: 0.6338 [2021-03-28 14:27:22 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 720/1251] eta: 0:05:39 lr: 0.000022 loss: 2.5455 (2.6662) grad_norm: 3.5543 (3.8004) time: 0.6357 [2021-03-28 14:27:29 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 730/1251] eta: 0:05:33 lr: 0.000022 loss: 2.6722 (2.6644) grad_norm: 3.5543 (3.8008) time: 0.6368 [2021-03-28 14:27:35 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 740/1251] eta: 0:05:26 lr: 0.000022 loss: 2.6722 (2.6652) grad_norm: 3.3292 (3.7983) time: 0.6399 [2021-03-28 14:27:42 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 750/1251] eta: 0:05:20 lr: 0.000022 loss: 2.8920 (2.6674) grad_norm: 3.4773 (3.7969) time: 0.6442 [2021-03-28 14:27:48 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 760/1251] eta: 0:05:14 lr: 0.000022 loss: 2.8305 (2.6663) grad_norm: 3.5545 (3.7949) time: 0.6428 [2021-03-28 14:27:54 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 770/1251] eta: 0:05:07 lr: 0.000022 loss: 2.8608 (2.6705) grad_norm: 3.4378 (3.7925) time: 0.6334 [2021-03-28 14:28:01 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 780/1251] eta: 0:05:01 lr: 0.000022 loss: 2.8608 (2.6708) grad_norm: 3.7229 (3.7936) time: 0.6295 [2021-03-28 14:28:07 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 790/1251] eta: 0:04:54 lr: 0.000022 loss: 2.7779 (2.6709) grad_norm: 3.6252 (3.7948) time: 0.6314 [2021-03-28 14:28:13 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 800/1251] eta: 0:04:48 lr: 0.000022 loss: 2.8196 (2.6733) grad_norm: 3.2829 (3.7911) time: 0.6303 [2021-03-28 14:28:19 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 810/1251] eta: 0:04:41 lr: 0.000022 loss: 2.9217 (2.6746) grad_norm: 3.3689 (3.7918) time: 0.6290 [2021-03-28 14:28:26 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 820/1251] eta: 0:04:35 lr: 0.000022 loss: 2.8600 (2.6765) grad_norm: 3.7853 (3.7924) time: 0.6273 [2021-03-28 14:28:32 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 830/1251] eta: 0:04:29 lr: 0.000022 loss: 2.8302 (2.6776) grad_norm: 3.5842 (3.7965) time: 0.6313 [2021-03-28 14:28:39 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 840/1251] eta: 0:04:22 lr: 0.000022 loss: 2.8302 (2.6780) grad_norm: 3.9094 (3.7984) time: 0.6377 [2021-03-28 14:28:45 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 850/1251] eta: 0:04:16 lr: 0.000022 loss: 2.5408 (2.6749) grad_norm: 3.5594 (3.7941) time: 0.6370 [2021-03-28 14:28:51 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 860/1251] eta: 0:04:09 lr: 0.000022 loss: 2.7525 (2.6759) grad_norm: 3.3794 (3.7916) time: 0.6287 [2021-03-28 14:28:58 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 870/1251] eta: 0:04:03 lr: 0.000022 loss: 2.9144 (2.6763) grad_norm: 3.2769 (3.7861) time: 0.6363 [2021-03-28 14:29:04 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 880/1251] eta: 0:03:57 lr: 0.000022 loss: 2.8199 (2.6772) grad_norm: 3.2929 (3.7837) time: 0.6400 [2021-03-28 14:29:10 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 890/1251] eta: 0:03:50 lr: 0.000022 loss: 2.8547 (2.6777) grad_norm: 3.5137 (3.7825) time: 0.6329 [2021-03-28 14:29:17 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 900/1251] eta: 0:03:44 lr: 0.000022 loss: 2.9277 (2.6785) grad_norm: 3.5081 (3.7778) time: 0.6312 [2021-03-28 14:29:23 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 910/1251] eta: 0:03:37 lr: 0.000022 loss: 2.7627 (2.6803) grad_norm: 3.2511 (3.7731) time: 0.6256 [2021-03-28 14:29:29 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 920/1251] eta: 0:03:31 lr: 0.000022 loss: 2.7729 (2.6818) grad_norm: 3.3010 (3.7713) time: 0.6284 [2021-03-28 14:29:35 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 930/1251] eta: 0:03:24 lr: 0.000022 loss: 2.7357 (2.6811) grad_norm: 3.3127 (3.7673) time: 0.6292 [2021-03-28 14:29:42 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 940/1251] eta: 0:03:18 lr: 0.000022 loss: 2.6992 (2.6803) grad_norm: 3.0349 (3.7770) time: 0.6276 [2021-03-28 14:29:48 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 950/1251] eta: 0:03:12 lr: 0.000022 loss: 2.7099 (2.6809) grad_norm: 3.5810 (3.7768) time: 0.6305 [2021-03-28 14:29:54 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 960/1251] eta: 0:03:05 lr: 0.000022 loss: 2.7024 (2.6800) grad_norm: 3.6415 (3.7886) time: 0.6344 [2021-03-28 14:30:01 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 970/1251] eta: 0:02:59 lr: 0.000022 loss: 2.6465 (2.6790) grad_norm: 3.3061 (3.7833) time: 0.6334 [2021-03-28 14:30:07 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 980/1251] eta: 0:02:52 lr: 0.000022 loss: 2.7759 (2.6802) grad_norm: 3.1848 (3.7821) time: 0.6312 [2021-03-28 14:30:13 swin_base_patch4_window7_224] INFO: Epoch: [278] [ 990/1251] eta: 0:02:46 lr: 0.000022 loss: 2.7002 (2.6797) grad_norm: 3.3524 (3.7815) time: 0.6375 [2021-03-28 14:30:20 swin_base_patch4_window7_224] INFO: Epoch: [278] [1000/1251] eta: 0:02:40 lr: 0.000022 loss: 2.8403 (2.6796) grad_norm: 3.4507 (3.7794) time: 0.6380 [2021-03-28 14:30:26 swin_base_patch4_window7_224] INFO: Epoch: [278] [1010/1251] eta: 0:02:33 lr: 0.000022 loss: 2.8581 (2.6808) grad_norm: 3.3922 (3.7800) time: 0.6345 [2021-03-28 14:30:32 swin_base_patch4_window7_224] INFO: Epoch: [278] [1020/1251] eta: 0:02:27 lr: 0.000022 loss: 2.8665 (2.6822) grad_norm: 3.3962 (3.7799) time: 0.6356 [2021-03-28 14:30:39 swin_base_patch4_window7_224] INFO: Epoch: [278] [1030/1251] eta: 0:02:20 lr: 0.000022 loss: 2.7026 (2.6810) grad_norm: 3.3296 (3.7816) time: 0.6345 [2021-03-28 14:30:45 swin_base_patch4_window7_224] INFO: Epoch: [278] [1040/1251] eta: 0:02:14 lr: 0.000022 loss: 2.5003 (2.6794) grad_norm: 3.3296 (3.7830) time: 0.6306 [2021-03-28 14:30:51 swin_base_patch4_window7_224] INFO: Epoch: [278] [1050/1251] eta: 0:02:08 lr: 0.000022 loss: 2.5457 (2.6795) grad_norm: 3.5074 (3.7852) time: 0.6292 [2021-03-28 14:30:58 swin_base_patch4_window7_224] INFO: Epoch: [278] [1060/1251] eta: 0:02:01 lr: 0.000022 loss: 2.7044 (2.6795) grad_norm: 3.6861 (3.7883) time: 0.6334 [2021-03-28 14:31:04 swin_base_patch4_window7_224] INFO: Epoch: [278] [1070/1251] eta: 0:01:55 lr: 0.000022 loss: 2.9496 (2.6816) grad_norm: 3.7478 (3.7875) time: 0.6337 [2021-03-28 14:31:10 swin_base_patch4_window7_224] INFO: Epoch: [278] [1080/1251] eta: 0:01:49 lr: 0.000022 loss: 2.8938 (2.6819) grad_norm: 3.6359 (3.7836) time: 0.6268 [2021-03-28 14:31:17 swin_base_patch4_window7_224] INFO: Epoch: [278] [1090/1251] eta: 0:01:42 lr: 0.000022 loss: 2.7236 (2.6831) grad_norm: 3.4910 (3.7828) time: 0.6288 [2021-03-28 14:31:23 swin_base_patch4_window7_224] INFO: Epoch: [278] [1100/1251] eta: 0:01:36 lr: 0.000022 loss: 2.7096 (2.6827) grad_norm: 3.4910 (3.7857) time: 0.6341 [2021-03-28 14:31:29 swin_base_patch4_window7_224] INFO: Epoch: [278] [1110/1251] eta: 0:01:29 lr: 0.000022 loss: 2.7785 (2.6830) grad_norm: 3.3212 (3.7829) time: 0.6313 [2021-03-28 14:31:36 swin_base_patch4_window7_224] INFO: Epoch: [278] [1120/1251] eta: 0:01:23 lr: 0.000022 loss: 2.7785 (2.6834) grad_norm: 3.3372 (3.7850) time: 0.6331 [2021-03-28 14:31:42 swin_base_patch4_window7_224] INFO: Epoch: [278] [1130/1251] eta: 0:01:17 lr: 0.000022 loss: 2.7938 (2.6840) grad_norm: 3.3424 (3.7800) time: 0.6332 [2021-03-28 14:31:48 swin_base_patch4_window7_224] INFO: Epoch: [278] [1140/1251] eta: 0:01:10 lr: 0.000022 loss: 2.8392 (2.6850) grad_norm: 3.3424 (3.7961) time: 0.6300 [2021-03-28 14:31:55 swin_base_patch4_window7_224] INFO: Epoch: [278] [1150/1251] eta: 0:01:04 lr: 0.000022 loss: 2.9157 (2.6859) grad_norm: 3.5752 (3.7947) time: 0.6308 [2021-03-28 14:32:01 swin_base_patch4_window7_224] INFO: Epoch: [278] [1160/1251] eta: 0:00:57 lr: 0.000022 loss: 2.7686 (2.6856) grad_norm: 3.3392 (3.7961) time: 0.6340 [2021-03-28 14:32:07 swin_base_patch4_window7_224] INFO: Epoch: [278] [1170/1251] eta: 0:00:51 lr: 0.000022 loss: 2.6379 (2.6851) grad_norm: 3.2239 (3.8034) time: 0.6319 [2021-03-28 14:32:14 swin_base_patch4_window7_224] INFO: Epoch: [278] [1180/1251] eta: 0:00:45 lr: 0.000022 loss: 2.6085 (2.6837) grad_norm: 3.4183 (3.8036) time: 0.6324 [2021-03-28 14:32:20 swin_base_patch4_window7_224] INFO: Epoch: [278] [1190/1251] eta: 0:00:38 lr: 0.000022 loss: 2.6220 (2.6827) grad_norm: 3.5086 (3.8022) time: 0.6352 [2021-03-28 14:32:26 swin_base_patch4_window7_224] INFO: Epoch: [278] [1200/1251] eta: 0:00:32 lr: 0.000022 loss: 2.6601 (2.6828) grad_norm: 3.6811 (3.8014) time: 0.6348 [2021-03-28 14:32:33 swin_base_patch4_window7_224] INFO: Epoch: [278] [1210/1251] eta: 0:00:26 lr: 0.000022 loss: 2.7949 (2.6845) grad_norm: 3.2852 (3.7977) time: 0.6309 [2021-03-28 14:32:39 swin_base_patch4_window7_224] INFO: Epoch: [278] [1220/1251] eta: 0:00:19 lr: 0.000022 loss: 2.8940 (2.6856) grad_norm: 3.2913 (3.7971) time: 0.6273 [2021-03-28 14:32:45 swin_base_patch4_window7_224] INFO: Epoch: [278] [1230/1251] eta: 0:00:13 lr: 0.000022 loss: 2.8175 (2.6848) grad_norm: 3.5020 (3.7990) time: 0.6281 [2021-03-28 14:32:51 swin_base_patch4_window7_224] INFO: Epoch: [278] [1240/1251] eta: 0:00:07 lr: 0.000022 loss: 2.8002 (2.6865) grad_norm: 3.4221 (3.7982) time: 0.6208 [2021-03-28 14:32:57 swin_base_patch4_window7_224] INFO: Epoch: [278] [1250/1251] eta: 0:00:00 lr: 0.000022 loss: 2.8002 (2.6866) grad_norm: 3.6560 (3.8007) time: 0.6153 [2021-03-28 14:33:17 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:23 loss: 0.9595 (0.9595) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-28 14:33:19 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8150 (0.7373) acc1: 81.2500 (80.9659) acc5: 96.8750 (97.1591) [2021-03-28 14:33:22 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7656 (0.7597) acc1: 81.2500 (81.3988) acc5: 96.8750 (96.6518) [2021-03-28 14:33:23 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7656 (0.7637) acc1: 81.2500 (81.6532) acc5: 96.8750 (96.4214) [2021-03-28 14:33:25 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7528 (0.7547) acc1: 82.8125 (82.0122) acc5: 96.8750 (96.4177) [2021-03-28 14:33:26 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7528 (0.7547) acc1: 81.2500 (82.0480) acc5: 96.8750 (96.4800) [2021-03-28 14:33:42 swin_base_patch4_window7_224] INFO: * Acc@1 83.282 Acc@5 96.418 loss 0.743 [2021-03-28 14:33:42 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.3% [2021-03-28 14:33:42 swin_base_patch4_window7_224] INFO: Max accuracy: 83.34% [2021-03-28 14:33:48 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 0/1251] eta: 2:03:34 lr: 0.000022 loss: 2.4890 (2.4890) grad_norm: 4.1053 (4.1053) time: 5.9269 [2021-03-28 14:33:54 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 10/1251] eta: 0:23:12 lr: 0.000022 loss: 2.5669 (2.5855) grad_norm: 3.4404 (5.6397) time: 1.1218 [2021-03-28 14:34:01 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 20/1251] eta: 0:18:17 lr: 0.000022 loss: 2.7508 (2.7200) grad_norm: 3.4150 (4.7877) time: 0.6399 [2021-03-28 14:34:07 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 30/1251] eta: 0:16:22 lr: 0.000022 loss: 2.7508 (2.6016) grad_norm: 3.5047 (4.4209) time: 0.6306 [2021-03-28 14:34:13 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 40/1251] eta: 0:15:24 lr: 0.000022 loss: 2.3969 (2.5803) grad_norm: 3.5047 (4.2287) time: 0.6282 [2021-03-28 14:34:20 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 50/1251] eta: 0:14:44 lr: 0.000022 loss: 2.5791 (2.6007) grad_norm: 3.6444 (4.2106) time: 0.6304 [2021-03-28 14:34:26 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 60/1251] eta: 0:14:19 lr: 0.000022 loss: 2.7626 (2.6318) grad_norm: 3.3715 (4.0658) time: 0.6367 [2021-03-28 14:34:32 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 70/1251] eta: 0:13:57 lr: 0.000022 loss: 2.7494 (2.6426) grad_norm: 3.3715 (4.0180) time: 0.6383 [2021-03-28 14:34:39 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 80/1251] eta: 0:13:39 lr: 0.000022 loss: 2.7048 (2.6460) grad_norm: 3.4767 (3.9493) time: 0.6328 [2021-03-28 14:34:45 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 90/1251] eta: 0:13:24 lr: 0.000022 loss: 2.7048 (2.6568) grad_norm: 3.4816 (3.9649) time: 0.6378 [2021-03-28 14:34:51 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 100/1251] eta: 0:13:11 lr: 0.000022 loss: 2.6770 (2.6569) grad_norm: 4.0358 (4.1090) time: 0.6385 [2021-03-28 14:34:58 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 110/1251] eta: 0:12:58 lr: 0.000022 loss: 2.6206 (2.6543) grad_norm: 3.5745 (4.0452) time: 0.6323 [2021-03-28 14:35:04 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 120/1251] eta: 0:12:46 lr: 0.000022 loss: 2.6550 (2.6545) grad_norm: 3.4066 (4.0385) time: 0.6253 [2021-03-28 14:35:10 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 130/1251] eta: 0:12:36 lr: 0.000022 loss: 2.8037 (2.6582) grad_norm: 3.9245 (4.0791) time: 0.6352 [2021-03-28 14:35:17 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 140/1251] eta: 0:12:26 lr: 0.000022 loss: 2.5664 (2.6410) grad_norm: 3.4328 (4.0534) time: 0.6406 [2021-03-28 14:35:23 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 150/1251] eta: 0:12:17 lr: 0.000022 loss: 2.6547 (2.6480) grad_norm: 3.2240 (4.0093) time: 0.6330 [2021-03-28 14:35:29 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 160/1251] eta: 0:12:07 lr: 0.000022 loss: 2.6661 (2.6370) grad_norm: 3.2271 (3.9915) time: 0.6277 [2021-03-28 14:35:36 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 170/1251] eta: 0:11:58 lr: 0.000022 loss: 2.5019 (2.6336) grad_norm: 3.2271 (3.9659) time: 0.6296 [2021-03-28 14:35:42 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 180/1251] eta: 0:11:50 lr: 0.000022 loss: 2.6696 (2.6376) grad_norm: 3.4517 (3.9865) time: 0.6392 [2021-03-28 14:35:48 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 190/1251] eta: 0:11:41 lr: 0.000022 loss: 2.7974 (2.6434) grad_norm: 3.4517 (3.9618) time: 0.6344 [2021-03-28 14:35:55 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 200/1251] eta: 0:11:34 lr: 0.000022 loss: 2.8153 (2.6485) grad_norm: 3.4648 (3.9688) time: 0.6312 [2021-03-28 14:36:01 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 210/1251] eta: 0:11:26 lr: 0.000022 loss: 2.4258 (2.6316) grad_norm: 3.7105 (3.9495) time: 0.6342 [2021-03-28 14:36:07 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 220/1251] eta: 0:11:18 lr: 0.000022 loss: 2.4862 (2.6430) grad_norm: 3.5162 (3.9336) time: 0.6354 [2021-03-28 14:36:14 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 230/1251] eta: 0:11:10 lr: 0.000022 loss: 2.7657 (2.6365) grad_norm: 3.1504 (3.9021) time: 0.6312 [2021-03-28 14:36:20 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 240/1251] eta: 0:11:02 lr: 0.000022 loss: 2.7777 (2.6415) grad_norm: 3.1359 (3.8823) time: 0.6244 [2021-03-28 14:36:26 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 250/1251] eta: 0:10:55 lr: 0.000022 loss: 2.7584 (2.6348) grad_norm: 3.1939 (3.8554) time: 0.6337 [2021-03-28 14:36:33 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 260/1251] eta: 0:10:48 lr: 0.000022 loss: 2.7190 (2.6341) grad_norm: 3.1511 (3.8461) time: 0.6381 [2021-03-28 14:36:39 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 270/1251] eta: 0:10:40 lr: 0.000022 loss: 2.7340 (2.6364) grad_norm: 3.4175 (3.8472) time: 0.6310 [2021-03-28 14:36:45 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 280/1251] eta: 0:10:33 lr: 0.000022 loss: 2.7998 (2.6383) grad_norm: 3.5057 (3.8563) time: 0.6298 [2021-03-28 14:36:52 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 290/1251] eta: 0:10:25 lr: 0.000022 loss: 2.7742 (2.6395) grad_norm: 3.4883 (3.8444) time: 0.6288 [2021-03-28 14:36:58 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 300/1251] eta: 0:10:18 lr: 0.000022 loss: 2.7816 (2.6461) grad_norm: 3.4400 (3.8493) time: 0.6296 [2021-03-28 14:37:04 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 310/1251] eta: 0:10:11 lr: 0.000022 loss: 2.7810 (2.6408) grad_norm: 3.4740 (3.8402) time: 0.6334 [2021-03-28 14:37:11 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 320/1251] eta: 0:10:05 lr: 0.000022 loss: 2.4941 (2.6434) grad_norm: 3.3950 (3.8498) time: 0.6383 [2021-03-28 14:37:17 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 330/1251] eta: 0:09:58 lr: 0.000022 loss: 2.7297 (2.6480) grad_norm: 3.3950 (3.8722) time: 0.6383 [2021-03-28 14:37:23 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 340/1251] eta: 0:09:51 lr: 0.000022 loss: 2.7478 (2.6499) grad_norm: 3.4712 (3.8611) time: 0.6316 [2021-03-28 14:37:30 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 350/1251] eta: 0:09:44 lr: 0.000022 loss: 2.7478 (2.6455) grad_norm: 3.3033 (3.8554) time: 0.6350 [2021-03-28 14:37:36 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 360/1251] eta: 0:09:37 lr: 0.000022 loss: 2.5448 (2.6437) grad_norm: 3.2991 (3.8421) time: 0.6352 [2021-03-28 14:37:42 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 370/1251] eta: 0:09:30 lr: 0.000022 loss: 2.4750 (2.6412) grad_norm: 3.3092 (3.8677) time: 0.6333 [2021-03-28 14:37:49 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 380/1251] eta: 0:09:24 lr: 0.000022 loss: 2.6158 (2.6483) grad_norm: 3.5633 (3.8656) time: 0.6432 [2021-03-28 14:37:55 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 390/1251] eta: 0:09:17 lr: 0.000022 loss: 2.7737 (2.6451) grad_norm: 3.6148 (3.8599) time: 0.6398 [2021-03-28 14:38:02 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 400/1251] eta: 0:09:10 lr: 0.000022 loss: 2.5460 (2.6419) grad_norm: 3.3730 (3.8481) time: 0.6330 [2021-03-28 14:38:08 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 410/1251] eta: 0:09:03 lr: 0.000022 loss: 2.5381 (2.6374) grad_norm: 3.1614 (3.8349) time: 0.6350 [2021-03-28 14:38:14 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 420/1251] eta: 0:08:57 lr: 0.000022 loss: 2.6864 (2.6418) grad_norm: 3.1614 (3.8310) time: 0.6339 [2021-03-28 14:38:21 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 430/1251] eta: 0:08:50 lr: 0.000022 loss: 2.7916 (2.6450) grad_norm: 3.6161 (3.8336) time: 0.6350 [2021-03-28 14:38:27 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 440/1251] eta: 0:08:44 lr: 0.000022 loss: 2.8650 (2.6490) grad_norm: 3.4948 (3.8277) time: 0.6389 [2021-03-28 14:38:33 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 450/1251] eta: 0:08:37 lr: 0.000022 loss: 2.7579 (2.6470) grad_norm: 3.4178 (3.8219) time: 0.6426 [2021-03-28 14:38:40 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 460/1251] eta: 0:08:30 lr: 0.000022 loss: 2.7705 (2.6527) grad_norm: 3.5139 (3.8340) time: 0.6353 [2021-03-28 14:38:46 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 470/1251] eta: 0:08:23 lr: 0.000022 loss: 2.6304 (2.6485) grad_norm: 3.5172 (3.8345) time: 0.6273 [2021-03-28 14:38:52 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 480/1251] eta: 0:08:17 lr: 0.000021 loss: 2.5970 (2.6434) grad_norm: 3.4657 (3.8386) time: 0.6281 [2021-03-28 14:38:59 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 490/1251] eta: 0:08:10 lr: 0.000021 loss: 2.5970 (2.6428) grad_norm: 3.2263 (3.8258) time: 0.6318 [2021-03-28 14:39:05 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 500/1251] eta: 0:08:03 lr: 0.000021 loss: 2.5450 (2.6412) grad_norm: 3.4379 (3.8350) time: 0.6327 [2021-03-28 14:39:11 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 510/1251] eta: 0:07:57 lr: 0.000021 loss: 2.7725 (2.6444) grad_norm: 4.0175 (3.8381) time: 0.6338 [2021-03-28 14:39:18 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 520/1251] eta: 0:07:50 lr: 0.000021 loss: 2.8100 (2.6448) grad_norm: 3.4920 (3.8432) time: 0.6368 [2021-03-28 14:39:24 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 530/1251] eta: 0:07:44 lr: 0.000021 loss: 2.8024 (2.6483) grad_norm: 3.4757 (3.8396) time: 0.6347 [2021-03-28 14:39:30 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 540/1251] eta: 0:07:37 lr: 0.000021 loss: 2.7461 (2.6482) grad_norm: 3.5085 (3.8428) time: 0.6315 [2021-03-28 14:39:37 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 550/1251] eta: 0:07:31 lr: 0.000021 loss: 2.6205 (2.6465) grad_norm: 3.7501 (3.8411) time: 0.6421 [2021-03-28 14:39:43 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 560/1251] eta: 0:07:24 lr: 0.000021 loss: 2.6205 (2.6430) grad_norm: 3.5487 (3.8396) time: 0.6493 [2021-03-28 14:39:50 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 570/1251] eta: 0:07:18 lr: 0.000021 loss: 2.7875 (2.6474) grad_norm: 3.2391 (3.8360) time: 0.6354 [2021-03-28 14:39:56 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 580/1251] eta: 0:07:11 lr: 0.000021 loss: 2.8892 (2.6492) grad_norm: 3.2391 (3.8296) time: 0.6292 [2021-03-28 14:40:02 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 590/1251] eta: 0:07:05 lr: 0.000021 loss: 2.7307 (2.6512) grad_norm: 3.4674 (3.8250) time: 0.6330 [2021-03-28 14:40:08 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 600/1251] eta: 0:06:58 lr: 0.000021 loss: 2.7153 (2.6525) grad_norm: 3.5150 (3.8234) time: 0.6292 [2021-03-28 14:40:15 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 610/1251] eta: 0:06:51 lr: 0.000021 loss: 2.7153 (2.6550) grad_norm: 3.3663 (3.8159) time: 0.6279 [2021-03-28 14:40:21 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 620/1251] eta: 0:06:45 lr: 0.000021 loss: 2.8041 (2.6568) grad_norm: 3.4504 (3.8161) time: 0.6298 [2021-03-28 14:40:27 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 630/1251] eta: 0:06:38 lr: 0.000021 loss: 2.8370 (2.6594) grad_norm: 3.2977 (3.8118) time: 0.6318 [2021-03-28 14:40:34 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 640/1251] eta: 0:06:32 lr: 0.000021 loss: 2.8669 (2.6621) grad_norm: 3.2205 (3.8195) time: 0.6390 [2021-03-28 14:40:40 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 650/1251] eta: 0:06:25 lr: 0.000021 loss: 2.7002 (2.6590) grad_norm: 3.6865 (3.8200) time: 0.6339 [2021-03-28 14:40:46 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 660/1251] eta: 0:06:19 lr: 0.000021 loss: 2.7243 (2.6601) grad_norm: 3.3906 (3.8142) time: 0.6320 [2021-03-28 14:40:53 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 670/1251] eta: 0:06:12 lr: 0.000021 loss: 2.7350 (2.6598) grad_norm: 3.2982 (3.8078) time: 0.6358 [2021-03-28 14:40:59 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 680/1251] eta: 0:06:06 lr: 0.000021 loss: 2.7444 (2.6614) grad_norm: 3.2982 (3.8046) time: 0.6354 [2021-03-28 14:41:06 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 690/1251] eta: 0:06:00 lr: 0.000021 loss: 2.7664 (2.6609) grad_norm: 3.4984 (3.8037) time: 0.6402 [2021-03-28 14:41:12 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 700/1251] eta: 0:05:53 lr: 0.000021 loss: 2.7688 (2.6618) grad_norm: 3.3022 (3.8123) time: 0.6370 [2021-03-28 14:41:18 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 710/1251] eta: 0:05:47 lr: 0.000021 loss: 2.7688 (2.6619) grad_norm: 3.3022 (3.8214) time: 0.6377 [2021-03-28 14:41:25 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 720/1251] eta: 0:05:40 lr: 0.000021 loss: 2.6500 (2.6606) grad_norm: 3.3609 (3.8126) time: 0.6417 [2021-03-28 14:41:31 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 730/1251] eta: 0:05:34 lr: 0.000021 loss: 2.5055 (2.6573) grad_norm: 3.1788 (3.8155) time: 0.6368 [2021-03-28 14:41:38 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 740/1251] eta: 0:05:27 lr: 0.000021 loss: 2.6312 (2.6584) grad_norm: 3.1965 (3.8222) time: 0.6422 [2021-03-28 14:41:44 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 750/1251] eta: 0:05:21 lr: 0.000021 loss: 2.8171 (2.6598) grad_norm: 3.1636 (3.8177) time: 0.6407 [2021-03-28 14:41:50 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 760/1251] eta: 0:05:14 lr: 0.000021 loss: 2.6657 (2.6596) grad_norm: 3.1950 (3.8100) time: 0.6275 [2021-03-28 14:41:57 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 770/1251] eta: 0:05:08 lr: 0.000021 loss: 2.6044 (2.6578) grad_norm: 3.2096 (3.8042) time: 0.6292 [2021-03-28 14:42:03 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 780/1251] eta: 0:05:02 lr: 0.000021 loss: 2.4629 (2.6572) grad_norm: 3.1724 (3.7972) time: 0.6355 [2021-03-28 14:42:09 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 790/1251] eta: 0:04:55 lr: 0.000021 loss: 2.7901 (2.6578) grad_norm: 3.1763 (3.7918) time: 0.6327 [2021-03-28 14:42:16 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 800/1251] eta: 0:04:49 lr: 0.000021 loss: 2.8390 (2.6601) grad_norm: 3.3075 (3.7851) time: 0.6327 [2021-03-28 14:42:22 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 810/1251] eta: 0:04:42 lr: 0.000021 loss: 2.8376 (2.6610) grad_norm: 3.3075 (3.7851) time: 0.6360 [2021-03-28 14:42:28 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 820/1251] eta: 0:04:36 lr: 0.000021 loss: 2.8586 (2.6630) grad_norm: 3.5114 (3.7962) time: 0.6292 [2021-03-28 14:42:34 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 830/1251] eta: 0:04:29 lr: 0.000021 loss: 2.8586 (2.6643) grad_norm: 3.3678 (3.7930) time: 0.6256 [2021-03-28 14:42:41 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 840/1251] eta: 0:04:23 lr: 0.000021 loss: 2.7905 (2.6640) grad_norm: 3.3104 (3.7885) time: 0.6321 [2021-03-28 14:42:47 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 850/1251] eta: 0:04:16 lr: 0.000021 loss: 2.5523 (2.6618) grad_norm: 3.1482 (3.7823) time: 0.6336 [2021-03-28 14:42:53 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 860/1251] eta: 0:04:10 lr: 0.000021 loss: 2.5523 (2.6626) grad_norm: 3.1006 (3.7760) time: 0.6294 [2021-03-28 14:43:00 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 870/1251] eta: 0:04:03 lr: 0.000021 loss: 2.6197 (2.6622) grad_norm: 2.9856 (3.7735) time: 0.6296 [2021-03-28 14:43:06 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 880/1251] eta: 0:03:57 lr: 0.000021 loss: 2.6537 (2.6626) grad_norm: 3.2538 (3.7758) time: 0.6338 [2021-03-28 14:43:12 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 890/1251] eta: 0:03:51 lr: 0.000021 loss: 2.8534 (2.6641) grad_norm: 3.3748 (3.7758) time: 0.6321 [2021-03-28 14:43:19 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 900/1251] eta: 0:03:44 lr: 0.000021 loss: 2.8313 (2.6661) grad_norm: 3.2299 (3.7822) time: 0.6322 [2021-03-28 14:43:25 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 910/1251] eta: 0:03:38 lr: 0.000021 loss: 2.7025 (2.6645) grad_norm: 3.1803 (3.7783) time: 0.6361 [2021-03-28 14:43:31 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 920/1251] eta: 0:03:31 lr: 0.000021 loss: 2.6222 (2.6650) grad_norm: 3.5168 (3.7788) time: 0.6367 [2021-03-28 14:43:38 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 930/1251] eta: 0:03:25 lr: 0.000021 loss: 2.6222 (2.6642) grad_norm: 3.3438 (3.7747) time: 0.6453 [2021-03-28 14:43:44 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 940/1251] eta: 0:03:18 lr: 0.000021 loss: 2.7723 (2.6658) grad_norm: 3.2934 (3.7710) time: 0.6385 [2021-03-28 14:43:50 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 950/1251] eta: 0:03:12 lr: 0.000021 loss: 2.8578 (2.6661) grad_norm: 3.2934 (3.7649) time: 0.6247 [2021-03-28 14:43:57 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 960/1251] eta: 0:03:06 lr: 0.000021 loss: 2.7993 (2.6644) grad_norm: 3.2874 (3.7632) time: 0.6324 [2021-03-28 14:44:03 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 970/1251] eta: 0:02:59 lr: 0.000021 loss: 2.7380 (2.6645) grad_norm: 3.3225 (3.7727) time: 0.6381 [2021-03-28 14:44:10 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 980/1251] eta: 0:02:53 lr: 0.000021 loss: 2.5935 (2.6626) grad_norm: 3.3881 (3.7771) time: 0.6356 [2021-03-28 14:44:16 swin_base_patch4_window7_224] INFO: Epoch: [279] [ 990/1251] eta: 0:02:46 lr: 0.000021 loss: 2.4743 (2.6608) grad_norm: 3.5239 (3.7748) time: 0.6371 [2021-03-28 14:44:22 swin_base_patch4_window7_224] INFO: Epoch: [279] [1000/1251] eta: 0:02:40 lr: 0.000021 loss: 2.4915 (2.6600) grad_norm: 3.5239 (3.7740) time: 0.6387 [2021-03-28 14:44:29 swin_base_patch4_window7_224] INFO: Epoch: [279] [1010/1251] eta: 0:02:34 lr: 0.000021 loss: 2.6140 (2.6585) grad_norm: 3.6518 (3.7748) time: 0.6361 [2021-03-28 14:44:35 swin_base_patch4_window7_224] INFO: Epoch: [279] [1020/1251] eta: 0:02:27 lr: 0.000021 loss: 2.9128 (2.6615) grad_norm: 3.3401 (3.7751) time: 0.6424 [2021-03-28 14:44:42 swin_base_patch4_window7_224] INFO: Epoch: [279] [1030/1251] eta: 0:02:21 lr: 0.000021 loss: 2.9314 (2.6611) grad_norm: 3.0468 (3.7692) time: 0.6438 [2021-03-28 14:44:48 swin_base_patch4_window7_224] INFO: Epoch: [279] [1040/1251] eta: 0:02:14 lr: 0.000021 loss: 2.8139 (2.6620) grad_norm: 3.2260 (3.7658) time: 0.6376 [2021-03-28 14:44:54 swin_base_patch4_window7_224] INFO: Epoch: [279] [1050/1251] eta: 0:02:08 lr: 0.000021 loss: 2.7816 (2.6624) grad_norm: 3.3185 (3.7632) time: 0.6385 [2021-03-28 14:45:01 swin_base_patch4_window7_224] INFO: Epoch: [279] [1060/1251] eta: 0:02:02 lr: 0.000021 loss: 2.7602 (2.6624) grad_norm: 3.5330 (3.7611) time: 0.6396 [2021-03-28 14:45:07 swin_base_patch4_window7_224] INFO: Epoch: [279] [1070/1251] eta: 0:01:55 lr: 0.000021 loss: 2.6803 (2.6622) grad_norm: 3.2558 (3.7582) time: 0.6404 [2021-03-28 14:45:14 swin_base_patch4_window7_224] INFO: Epoch: [279] [1080/1251] eta: 0:01:49 lr: 0.000021 loss: 2.7922 (2.6627) grad_norm: 3.3127 (3.7590) time: 0.6411 [2021-03-28 14:45:20 swin_base_patch4_window7_224] INFO: Epoch: [279] [1090/1251] eta: 0:01:42 lr: 0.000021 loss: 2.7623 (2.6623) grad_norm: 3.4393 (3.7573) time: 0.6364 [2021-03-28 14:45:26 swin_base_patch4_window7_224] INFO: Epoch: [279] [1100/1251] eta: 0:01:36 lr: 0.000021 loss: 2.7451 (2.6624) grad_norm: 3.4439 (3.7543) time: 0.6392 [2021-03-28 14:45:33 swin_base_patch4_window7_224] INFO: Epoch: [279] [1110/1251] eta: 0:01:30 lr: 0.000021 loss: 2.7617 (2.6635) grad_norm: 3.4985 (3.7562) time: 0.6413 [2021-03-28 14:45:39 swin_base_patch4_window7_224] INFO: Epoch: [279] [1120/1251] eta: 0:01:23 lr: 0.000021 loss: 2.5056 (2.6609) grad_norm: 3.5708 (3.7553) time: 0.6438 [2021-03-28 14:45:46 swin_base_patch4_window7_224] INFO: Epoch: [279] [1130/1251] eta: 0:01:17 lr: 0.000021 loss: 2.5768 (2.6613) grad_norm: 3.5345 (3.7551) time: 0.6438 [2021-03-28 14:45:52 swin_base_patch4_window7_224] INFO: Epoch: [279] [1140/1251] eta: 0:01:11 lr: 0.000021 loss: 2.6943 (2.6606) grad_norm: 3.5196 (3.7528) time: 0.6402 [2021-03-28 14:45:58 swin_base_patch4_window7_224] INFO: Epoch: [279] [1150/1251] eta: 0:01:04 lr: 0.000021 loss: 2.6807 (2.6608) grad_norm: 3.5196 (3.7487) time: 0.6354 [2021-03-28 14:46:05 swin_base_patch4_window7_224] INFO: Epoch: [279] [1160/1251] eta: 0:00:58 lr: 0.000021 loss: 2.6416 (2.6604) grad_norm: 3.1769 (3.7457) time: 0.6367 [2021-03-28 14:46:11 swin_base_patch4_window7_224] INFO: Epoch: [279] [1170/1251] eta: 0:00:51 lr: 0.000021 loss: 2.6542 (2.6600) grad_norm: 3.1240 (3.7437) time: 0.6398 [2021-03-28 14:46:17 swin_base_patch4_window7_224] INFO: Epoch: [279] [1180/1251] eta: 0:00:45 lr: 0.000021 loss: 2.8424 (2.6618) grad_norm: 3.1792 (3.7424) time: 0.6304 [2021-03-28 14:46:24 swin_base_patch4_window7_224] INFO: Epoch: [279] [1190/1251] eta: 0:00:39 lr: 0.000021 loss: 2.8670 (2.6631) grad_norm: 3.3169 (3.7403) time: 0.6288 [2021-03-28 14:46:30 swin_base_patch4_window7_224] INFO: Epoch: [279] [1200/1251] eta: 0:00:32 lr: 0.000021 loss: 2.8075 (2.6643) grad_norm: 3.3169 (3.7397) time: 0.6308 [2021-03-28 14:46:36 swin_base_patch4_window7_224] INFO: Epoch: [279] [1210/1251] eta: 0:00:26 lr: 0.000021 loss: 2.7780 (2.6640) grad_norm: 3.4179 (3.7408) time: 0.6312 [2021-03-28 14:46:43 swin_base_patch4_window7_224] INFO: Epoch: [279] [1220/1251] eta: 0:00:19 lr: 0.000021 loss: 2.7604 (2.6655) grad_norm: 3.3838 (3.7365) time: 0.6338 [2021-03-28 14:46:49 swin_base_patch4_window7_224] INFO: Epoch: [279] [1230/1251] eta: 0:00:13 lr: 0.000021 loss: 2.8348 (2.6664) grad_norm: 3.3838 (3.7365) time: 0.6373 [2021-03-28 14:46:55 swin_base_patch4_window7_224] INFO: Epoch: [279] [1240/1251] eta: 0:00:07 lr: 0.000021 loss: 2.8603 (2.6668) grad_norm: 3.5549 (3.7357) time: 0.6356 [2021-03-28 14:47:02 swin_base_patch4_window7_224] INFO: Epoch: [279] [1250/1251] eta: 0:00:00 lr: 0.000021 loss: 2.7420 (2.6661) grad_norm: 3.4285 (3.7361) time: 0.6281 [2021-03-28 14:47:18 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:49 loss: 0.9738 (0.9738) acc1: 75.0000 (75.0000) acc5: 95.3125 (95.3125) [2021-03-28 14:47:20 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.7885 (0.8179) acc1: 79.6875 (79.2614) acc5: 96.8750 (96.1648) [2021-03-28 14:47:23 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.6880 (0.7655) acc1: 81.2500 (80.5060) acc5: 96.8750 (96.6518) [2021-03-28 14:47:25 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6880 (0.7656) acc1: 81.2500 (80.7460) acc5: 96.8750 (96.5726) [2021-03-28 14:47:27 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7346 (0.7652) acc1: 81.2500 (81.0976) acc5: 96.8750 (96.7607) [2021-03-28 14:47:28 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7349 (0.7531) acc1: 84.3750 (81.9520) acc5: 96.8750 (96.6080) [2021-03-28 14:47:45 swin_base_patch4_window7_224] INFO: * Acc@1 83.276 Acc@5 96.382 loss 0.743 [2021-03-28 14:47:45 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.3% [2021-03-28 14:47:45 swin_base_patch4_window7_224] INFO: Max accuracy: 83.34% [2021-03-28 14:47:49 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 0/1251] eta: 1:23:13 lr: 0.000021 loss: 2.3291 (2.3291) grad_norm: 3.8141 (3.8141) time: 3.9913 [2021-03-28 14:47:56 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 10/1251] eta: 0:20:07 lr: 0.000021 loss: 2.6176 (2.5071) grad_norm: 3.6415 (3.7207) time: 0.9734 [2021-03-28 14:48:02 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 20/1251] eta: 0:16:34 lr: 0.000021 loss: 2.6680 (2.5673) grad_norm: 3.4504 (3.6974) time: 0.6489 [2021-03-28 14:48:08 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 30/1251] eta: 0:15:17 lr: 0.000021 loss: 2.6667 (2.6072) grad_norm: 3.4504 (3.5905) time: 0.6288 [2021-03-28 14:48:15 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 40/1251] eta: 0:14:36 lr: 0.000021 loss: 2.5675 (2.5912) grad_norm: 3.5933 (3.8801) time: 0.6357 [2021-03-28 14:48:21 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 50/1251] eta: 0:14:08 lr: 0.000021 loss: 2.7607 (2.6093) grad_norm: 3.4450 (3.8703) time: 0.6377 [2021-03-28 14:48:28 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 60/1251] eta: 0:13:48 lr: 0.000021 loss: 2.7748 (2.6278) grad_norm: 3.4450 (3.8405) time: 0.6381 [2021-03-28 14:48:34 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 70/1251] eta: 0:13:30 lr: 0.000021 loss: 2.7748 (2.6364) grad_norm: 3.7808 (3.9226) time: 0.6338 [2021-03-28 14:48:40 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 80/1251] eta: 0:13:16 lr: 0.000021 loss: 2.9050 (2.6675) grad_norm: 3.8424 (3.9049) time: 0.6337 [2021-03-28 14:48:46 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 90/1251] eta: 0:13:03 lr: 0.000021 loss: 2.7551 (2.6533) grad_norm: 3.3455 (3.8503) time: 0.6353 [2021-03-28 14:48:53 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 100/1251] eta: 0:12:51 lr: 0.000021 loss: 2.5354 (2.6470) grad_norm: 3.4280 (3.9271) time: 0.6299 [2021-03-28 14:48:59 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 110/1251] eta: 0:12:41 lr: 0.000021 loss: 2.8217 (2.6411) grad_norm: 3.7042 (3.9161) time: 0.6355 [2021-03-28 14:49:06 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 120/1251] eta: 0:12:32 lr: 0.000021 loss: 2.6637 (2.6309) grad_norm: 3.5654 (3.9407) time: 0.6377 [2021-03-28 14:49:12 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 130/1251] eta: 0:12:23 lr: 0.000021 loss: 2.7113 (2.6362) grad_norm: 3.4140 (3.9064) time: 0.6391 [2021-03-28 14:49:18 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 140/1251] eta: 0:12:14 lr: 0.000021 loss: 2.7125 (2.6403) grad_norm: 3.3831 (3.9023) time: 0.6378 [2021-03-28 14:49:25 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 150/1251] eta: 0:12:06 lr: 0.000021 loss: 2.7661 (2.6438) grad_norm: 3.6964 (3.8929) time: 0.6335 [2021-03-28 14:49:31 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 160/1251] eta: 0:11:57 lr: 0.000021 loss: 2.9232 (2.6577) grad_norm: 3.6326 (3.8915) time: 0.6323 [2021-03-28 14:49:37 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 170/1251] eta: 0:11:48 lr: 0.000021 loss: 2.8867 (2.6630) grad_norm: 3.4823 (3.8706) time: 0.6268 [2021-03-28 14:49:44 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 180/1251] eta: 0:11:40 lr: 0.000021 loss: 2.6035 (2.6449) grad_norm: 3.4655 (3.8604) time: 0.6292 [2021-03-28 14:49:50 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 190/1251] eta: 0:11:33 lr: 0.000021 loss: 2.5420 (2.6456) grad_norm: 3.3997 (3.8328) time: 0.6338 [2021-03-28 14:49:56 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 200/1251] eta: 0:11:25 lr: 0.000021 loss: 2.7675 (2.6472) grad_norm: 3.2717 (3.8511) time: 0.6337 [2021-03-28 14:50:03 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 210/1251] eta: 0:11:18 lr: 0.000021 loss: 2.7887 (2.6519) grad_norm: 3.2345 (3.8368) time: 0.6365 [2021-03-28 14:50:09 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 220/1251] eta: 0:11:11 lr: 0.000021 loss: 2.7887 (2.6573) grad_norm: 3.1068 (3.8203) time: 0.6364 [2021-03-28 14:50:15 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 230/1251] eta: 0:11:03 lr: 0.000021 loss: 2.7217 (2.6652) grad_norm: 3.1258 (3.8056) time: 0.6331 [2021-03-28 14:50:22 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 240/1251] eta: 0:10:56 lr: 0.000021 loss: 2.7217 (2.6605) grad_norm: 3.3582 (3.7943) time: 0.6281 [2021-03-28 14:50:28 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 250/1251] eta: 0:10:48 lr: 0.000021 loss: 2.5920 (2.6558) grad_norm: 3.4213 (3.7875) time: 0.6245 [2021-03-28 14:50:34 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 260/1251] eta: 0:10:42 lr: 0.000021 loss: 2.7440 (2.6566) grad_norm: 3.4148 (3.7629) time: 0.6370 [2021-03-28 14:50:41 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 270/1251] eta: 0:10:34 lr: 0.000021 loss: 2.8115 (2.6535) grad_norm: 3.0461 (3.7516) time: 0.6365 [2021-03-28 14:50:47 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 280/1251] eta: 0:10:27 lr: 0.000021 loss: 2.6438 (2.6536) grad_norm: 3.2657 (3.7509) time: 0.6271 [2021-03-28 14:50:53 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 290/1251] eta: 0:10:20 lr: 0.000021 loss: 2.6438 (2.6530) grad_norm: 3.5930 (3.7729) time: 0.6271 [2021-03-28 14:50:59 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 300/1251] eta: 0:10:14 lr: 0.000021 loss: 2.8373 (2.6534) grad_norm: 3.6477 (3.7882) time: 0.6327 [2021-03-28 14:51:06 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 310/1251] eta: 0:10:07 lr: 0.000021 loss: 2.8033 (2.6502) grad_norm: 3.6477 (3.8039) time: 0.6401 [2021-03-28 14:51:12 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 320/1251] eta: 0:10:00 lr: 0.000021 loss: 2.8318 (2.6539) grad_norm: 3.3952 (3.7999) time: 0.6359 [2021-03-28 14:51:18 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 330/1251] eta: 0:09:53 lr: 0.000021 loss: 2.8193 (2.6576) grad_norm: 3.1907 (3.8001) time: 0.6272 [2021-03-28 14:51:25 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 340/1251] eta: 0:09:46 lr: 0.000021 loss: 2.7559 (2.6592) grad_norm: 3.2327 (3.7929) time: 0.6242 [2021-03-28 14:51:31 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 350/1251] eta: 0:09:40 lr: 0.000021 loss: 2.7967 (2.6630) grad_norm: 3.3625 (3.8019) time: 0.6329 [2021-03-28 14:51:37 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 360/1251] eta: 0:09:33 lr: 0.000021 loss: 2.8194 (2.6692) grad_norm: 3.3975 (3.8332) time: 0.6349 [2021-03-28 14:51:44 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 370/1251] eta: 0:09:26 lr: 0.000021 loss: 2.7543 (2.6640) grad_norm: 3.4651 (3.8311) time: 0.6353 [2021-03-28 14:51:50 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 380/1251] eta: 0:09:20 lr: 0.000020 loss: 2.6852 (2.6674) grad_norm: 3.5933 (3.8442) time: 0.6369 [2021-03-28 14:51:56 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 390/1251] eta: 0:09:13 lr: 0.000020 loss: 2.6232 (2.6643) grad_norm: 3.5623 (3.8442) time: 0.6295 [2021-03-28 14:52:03 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 400/1251] eta: 0:09:06 lr: 0.000020 loss: 2.7252 (2.6662) grad_norm: 3.4299 (3.8361) time: 0.6278 [2021-03-28 14:52:09 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 410/1251] eta: 0:08:59 lr: 0.000020 loss: 2.6995 (2.6613) grad_norm: 3.6053 (3.8319) time: 0.6321 [2021-03-28 14:52:15 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 420/1251] eta: 0:08:53 lr: 0.000020 loss: 2.3704 (2.6572) grad_norm: 3.6982 (3.8457) time: 0.6311 [2021-03-28 14:52:22 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 430/1251] eta: 0:08:46 lr: 0.000020 loss: 2.7755 (2.6594) grad_norm: 3.5325 (3.8387) time: 0.6305 [2021-03-28 14:52:28 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 440/1251] eta: 0:08:40 lr: 0.000020 loss: 2.8263 (2.6572) grad_norm: 3.1772 (3.8287) time: 0.6365 [2021-03-28 14:52:34 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 450/1251] eta: 0:08:33 lr: 0.000020 loss: 2.6956 (2.6586) grad_norm: 3.1974 (3.8247) time: 0.6354 [2021-03-28 14:52:41 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 460/1251] eta: 0:08:26 lr: 0.000020 loss: 2.6354 (2.6550) grad_norm: 3.4851 (3.8151) time: 0.6280 [2021-03-28 14:52:47 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 470/1251] eta: 0:08:20 lr: 0.000020 loss: 2.6082 (2.6535) grad_norm: 3.3479 (3.8066) time: 0.6312 [2021-03-28 14:52:53 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 480/1251] eta: 0:08:13 lr: 0.000020 loss: 2.7491 (2.6523) grad_norm: 3.3521 (3.8207) time: 0.6337 [2021-03-28 14:53:00 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 490/1251] eta: 0:08:07 lr: 0.000020 loss: 2.7491 (2.6540) grad_norm: 3.4192 (3.8167) time: 0.6273 [2021-03-28 14:53:06 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 500/1251] eta: 0:08:00 lr: 0.000020 loss: 2.7031 (2.6522) grad_norm: 3.6153 (3.8198) time: 0.6240 [2021-03-28 14:53:12 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 510/1251] eta: 0:07:54 lr: 0.000020 loss: 2.8048 (2.6564) grad_norm: 3.5233 (3.8161) time: 0.6284 [2021-03-28 14:53:18 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 520/1251] eta: 0:07:47 lr: 0.000020 loss: 2.8854 (2.6540) grad_norm: 3.3311 (3.8089) time: 0.6283 [2021-03-28 14:53:25 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 530/1251] eta: 0:07:40 lr: 0.000020 loss: 2.4136 (2.6513) grad_norm: 3.3758 (3.8125) time: 0.6277 [2021-03-28 14:53:31 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 540/1251] eta: 0:07:34 lr: 0.000020 loss: 2.7082 (2.6529) grad_norm: 3.3758 (3.8123) time: 0.6313 [2021-03-28 14:53:37 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 550/1251] eta: 0:07:28 lr: 0.000020 loss: 2.7192 (2.6522) grad_norm: 3.4748 (3.8124) time: 0.6395 [2021-03-28 14:53:44 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 560/1251] eta: 0:07:21 lr: 0.000020 loss: 2.7211 (2.6536) grad_norm: 3.5301 (3.8125) time: 0.6361 [2021-03-28 14:53:50 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 570/1251] eta: 0:07:15 lr: 0.000020 loss: 2.9097 (2.6587) grad_norm: 3.6907 (3.8182) time: 0.6279 [2021-03-28 14:53:56 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 580/1251] eta: 0:07:08 lr: 0.000020 loss: 2.9097 (2.6604) grad_norm: 3.5806 (3.8142) time: 0.6298 [2021-03-28 14:54:03 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 590/1251] eta: 0:07:02 lr: 0.000020 loss: 2.7394 (2.6596) grad_norm: 3.5805 (3.8159) time: 0.6301 [2021-03-28 14:54:09 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 600/1251] eta: 0:06:55 lr: 0.000020 loss: 2.6409 (2.6603) grad_norm: 3.5661 (3.8135) time: 0.6330 [2021-03-28 14:54:15 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 610/1251] eta: 0:06:49 lr: 0.000020 loss: 2.7268 (2.6597) grad_norm: 3.4422 (3.8076) time: 0.6328 [2021-03-28 14:54:22 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 620/1251] eta: 0:06:42 lr: 0.000020 loss: 2.5717 (2.6581) grad_norm: 3.4572 (3.8114) time: 0.6289 [2021-03-28 14:54:28 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 630/1251] eta: 0:06:36 lr: 0.000020 loss: 2.6807 (2.6564) grad_norm: 3.1391 (3.8035) time: 0.6244 [2021-03-28 14:54:34 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 640/1251] eta: 0:06:29 lr: 0.000020 loss: 2.9110 (2.6590) grad_norm: 3.2303 (3.8035) time: 0.6254 [2021-03-28 14:54:40 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 650/1251] eta: 0:06:23 lr: 0.000020 loss: 2.7945 (2.6541) grad_norm: 3.4176 (3.7959) time: 0.6293 [2021-03-28 14:54:47 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 660/1251] eta: 0:06:16 lr: 0.000020 loss: 2.6999 (2.6550) grad_norm: 3.3639 (3.7894) time: 0.6272 [2021-03-28 14:54:53 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 670/1251] eta: 0:06:10 lr: 0.000020 loss: 2.7516 (2.6549) grad_norm: 3.5884 (3.8018) time: 0.6290 [2021-03-28 14:54:59 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 680/1251] eta: 0:06:04 lr: 0.000020 loss: 2.5710 (2.6528) grad_norm: 3.6878 (3.8251) time: 0.6403 [2021-03-28 14:55:06 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 690/1251] eta: 0:05:57 lr: 0.000020 loss: 2.5606 (2.6508) grad_norm: 3.4901 (3.8222) time: 0.6426 [2021-03-28 14:55:12 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 700/1251] eta: 0:05:51 lr: 0.000020 loss: 2.6077 (2.6540) grad_norm: 3.6061 (3.8245) time: 0.6363 [2021-03-28 14:55:18 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 710/1251] eta: 0:05:44 lr: 0.000020 loss: 2.8651 (2.6556) grad_norm: 3.5059 (3.8371) time: 0.6323 [2021-03-28 14:55:25 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 720/1251] eta: 0:05:38 lr: 0.000020 loss: 2.8069 (2.6574) grad_norm: 3.3036 (3.8319) time: 0.6341 [2021-03-28 14:55:31 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 730/1251] eta: 0:05:32 lr: 0.000020 loss: 2.7613 (2.6546) grad_norm: 3.3052 (3.8304) time: 0.6384 [2021-03-28 14:55:38 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 740/1251] eta: 0:05:25 lr: 0.000020 loss: 2.7532 (2.6556) grad_norm: 3.3215 (3.8261) time: 0.6433 [2021-03-28 14:55:44 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 750/1251] eta: 0:05:19 lr: 0.000020 loss: 2.7506 (2.6540) grad_norm: 3.4668 (3.8266) time: 0.6367 [2021-03-28 14:55:50 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 760/1251] eta: 0:05:13 lr: 0.000020 loss: 2.7956 (2.6564) grad_norm: 3.4747 (3.8241) time: 0.6324 [2021-03-28 14:55:57 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 770/1251] eta: 0:05:06 lr: 0.000020 loss: 2.7956 (2.6543) grad_norm: 3.2280 (3.8160) time: 0.6367 [2021-03-28 14:56:03 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 780/1251] eta: 0:05:00 lr: 0.000020 loss: 2.5964 (2.6532) grad_norm: 3.1742 (3.8089) time: 0.6292 [2021-03-28 14:56:09 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 790/1251] eta: 0:04:53 lr: 0.000020 loss: 2.5964 (2.6521) grad_norm: 3.2594 (3.8190) time: 0.6267 [2021-03-28 14:56:16 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 800/1251] eta: 0:04:47 lr: 0.000020 loss: 2.6297 (2.6511) grad_norm: 3.6516 (inf) time: 0.6363 [2021-03-28 14:56:22 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 810/1251] eta: 0:04:41 lr: 0.000020 loss: 2.8467 (2.6545) grad_norm: 3.5009 (inf) time: 0.6370 [2021-03-28 14:56:28 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 820/1251] eta: 0:04:34 lr: 0.000020 loss: 2.8856 (2.6559) grad_norm: 3.4379 (inf) time: 0.6286 [2021-03-28 14:56:35 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 830/1251] eta: 0:04:28 lr: 0.000020 loss: 2.6335 (2.6566) grad_norm: 3.7208 (inf) time: 0.6292 [2021-03-28 14:56:41 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 840/1251] eta: 0:04:21 lr: 0.000020 loss: 2.7904 (2.6578) grad_norm: 3.4732 (inf) time: 0.6330 [2021-03-28 14:56:47 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 850/1251] eta: 0:04:15 lr: 0.000020 loss: 2.8175 (2.6605) grad_norm: 3.4615 (inf) time: 0.6340 [2021-03-28 14:56:54 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 860/1251] eta: 0:04:09 lr: 0.000020 loss: 2.7509 (2.6600) grad_norm: 3.7483 (inf) time: 0.6387 [2021-03-28 14:57:00 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 870/1251] eta: 0:04:02 lr: 0.000020 loss: 2.7215 (2.6593) grad_norm: 3.6152 (inf) time: 0.6414 [2021-03-28 14:57:07 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 880/1251] eta: 0:03:56 lr: 0.000020 loss: 2.8164 (2.6610) grad_norm: 3.5701 (inf) time: 0.6434 [2021-03-28 14:57:13 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 890/1251] eta: 0:03:49 lr: 0.000020 loss: 2.8152 (2.6608) grad_norm: 3.5080 (inf) time: 0.6374 [2021-03-28 14:57:19 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 900/1251] eta: 0:03:43 lr: 0.000020 loss: 2.8813 (2.6621) grad_norm: 3.5990 (inf) time: 0.6268 [2021-03-28 14:57:25 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 910/1251] eta: 0:03:37 lr: 0.000020 loss: 2.9845 (2.6639) grad_norm: 3.3401 (inf) time: 0.6271 [2021-03-28 14:57:32 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 920/1251] eta: 0:03:30 lr: 0.000020 loss: 2.7039 (2.6638) grad_norm: 3.1262 (inf) time: 0.6345 [2021-03-28 14:57:38 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 930/1251] eta: 0:03:24 lr: 0.000020 loss: 2.6893 (2.6625) grad_norm: 3.4967 (inf) time: 0.6365 [2021-03-28 14:57:44 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 940/1251] eta: 0:03:18 lr: 0.000020 loss: 2.6670 (2.6623) grad_norm: 3.5471 (inf) time: 0.6340 [2021-03-28 14:57:51 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 950/1251] eta: 0:03:11 lr: 0.000020 loss: 2.4763 (2.6591) grad_norm: 3.4475 (inf) time: 0.6307 [2021-03-28 14:57:57 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 960/1251] eta: 0:03:05 lr: 0.000020 loss: 2.6685 (2.6597) grad_norm: 3.1311 (inf) time: 0.6281 [2021-03-28 14:58:03 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 970/1251] eta: 0:02:58 lr: 0.000020 loss: 2.7470 (2.6585) grad_norm: 3.1851 (inf) time: 0.6337 [2021-03-28 14:58:10 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 980/1251] eta: 0:02:52 lr: 0.000020 loss: 2.6402 (2.6593) grad_norm: 3.4099 (inf) time: 0.6358 [2021-03-28 14:58:16 swin_base_patch4_window7_224] INFO: Epoch: [280] [ 990/1251] eta: 0:02:46 lr: 0.000020 loss: 2.6402 (2.6581) grad_norm: 3.5186 (inf) time: 0.6295 [2021-03-28 14:58:22 swin_base_patch4_window7_224] INFO: Epoch: [280] [1000/1251] eta: 0:02:39 lr: 0.000020 loss: 2.6806 (2.6601) grad_norm: 3.6017 (inf) time: 0.6280 [2021-03-28 14:58:29 swin_base_patch4_window7_224] INFO: Epoch: [280] [1010/1251] eta: 0:02:33 lr: 0.000020 loss: 2.9439 (2.6618) grad_norm: 3.5541 (inf) time: 0.6380 [2021-03-28 14:58:35 swin_base_patch4_window7_224] INFO: Epoch: [280] [1020/1251] eta: 0:02:27 lr: 0.000020 loss: 2.8080 (2.6618) grad_norm: 3.5541 (inf) time: 0.6366 [2021-03-28 14:58:41 swin_base_patch4_window7_224] INFO: Epoch: [280] [1030/1251] eta: 0:02:20 lr: 0.000020 loss: 2.7935 (2.6618) grad_norm: 3.3176 (inf) time: 0.6325 [2021-03-28 14:58:48 swin_base_patch4_window7_224] INFO: Epoch: [280] [1040/1251] eta: 0:02:14 lr: 0.000020 loss: 2.7670 (2.6622) grad_norm: 3.3269 (inf) time: 0.6350 [2021-03-28 14:58:54 swin_base_patch4_window7_224] INFO: Epoch: [280] [1050/1251] eta: 0:02:07 lr: 0.000020 loss: 2.7231 (2.6623) grad_norm: 3.3655 (inf) time: 0.6372 [2021-03-28 14:59:00 swin_base_patch4_window7_224] INFO: Epoch: [280] [1060/1251] eta: 0:02:01 lr: 0.000020 loss: 2.5312 (2.6607) grad_norm: 3.3200 (inf) time: 0.6376 [2021-03-28 14:59:07 swin_base_patch4_window7_224] INFO: Epoch: [280] [1070/1251] eta: 0:01:55 lr: 0.000020 loss: 2.5312 (2.6603) grad_norm: 3.1713 (inf) time: 0.6308 [2021-03-28 14:59:13 swin_base_patch4_window7_224] INFO: Epoch: [280] [1080/1251] eta: 0:01:48 lr: 0.000020 loss: 2.7339 (2.6597) grad_norm: 3.2300 (inf) time: 0.6306 [2021-03-28 14:59:20 swin_base_patch4_window7_224] INFO: Epoch: [280] [1090/1251] eta: 0:01:42 lr: 0.000020 loss: 2.7561 (2.6601) grad_norm: 3.6789 (inf) time: 0.6369 [2021-03-28 14:59:26 swin_base_patch4_window7_224] INFO: Epoch: [280] [1100/1251] eta: 0:01:36 lr: 0.000020 loss: 2.8025 (2.6605) grad_norm: 3.6789 (inf) time: 0.6364 [2021-03-28 14:59:32 swin_base_patch4_window7_224] INFO: Epoch: [280] [1110/1251] eta: 0:01:29 lr: 0.000020 loss: 2.8377 (2.6611) grad_norm: 3.3521 (inf) time: 0.6338 [2021-03-28 14:59:38 swin_base_patch4_window7_224] INFO: Epoch: [280] [1120/1251] eta: 0:01:23 lr: 0.000020 loss: 2.8377 (2.6611) grad_norm: 3.3078 (inf) time: 0.6311 [2021-03-28 14:59:45 swin_base_patch4_window7_224] INFO: Epoch: [280] [1130/1251] eta: 0:01:16 lr: 0.000020 loss: 2.7302 (2.6604) grad_norm: 3.1777 (inf) time: 0.6325 [2021-03-28 14:59:51 swin_base_patch4_window7_224] INFO: Epoch: [280] [1140/1251] eta: 0:01:10 lr: 0.000020 loss: 2.7161 (2.6599) grad_norm: 3.1777 (inf) time: 0.6371 [2021-03-28 14:59:58 swin_base_patch4_window7_224] INFO: Epoch: [280] [1150/1251] eta: 0:01:04 lr: 0.000020 loss: 2.7179 (2.6608) grad_norm: 3.2045 (inf) time: 0.6340 [2021-03-28 15:00:04 swin_base_patch4_window7_224] INFO: Epoch: [280] [1160/1251] eta: 0:00:57 lr: 0.000020 loss: 2.7742 (2.6598) grad_norm: 3.2253 (inf) time: 0.6297 [2021-03-28 15:00:10 swin_base_patch4_window7_224] INFO: Epoch: [280] [1170/1251] eta: 0:00:51 lr: 0.000020 loss: 2.7027 (2.6591) grad_norm: 3.5064 (inf) time: 0.6301 [2021-03-28 15:00:17 swin_base_patch4_window7_224] INFO: Epoch: [280] [1180/1251] eta: 0:00:45 lr: 0.000020 loss: 2.5366 (2.6587) grad_norm: 3.6369 (inf) time: 0.6383 [2021-03-28 15:00:23 swin_base_patch4_window7_224] INFO: Epoch: [280] [1190/1251] eta: 0:00:38 lr: 0.000020 loss: 2.6647 (2.6589) grad_norm: 3.5134 (inf) time: 0.6407 [2021-03-28 15:00:29 swin_base_patch4_window7_224] INFO: Epoch: [280] [1200/1251] eta: 0:00:32 lr: 0.000020 loss: 2.6522 (2.6584) grad_norm: 3.5942 (inf) time: 0.6390 [2021-03-28 15:00:36 swin_base_patch4_window7_224] INFO: Epoch: [280] [1210/1251] eta: 0:00:26 lr: 0.000020 loss: 2.5494 (2.6568) grad_norm: 3.6890 (inf) time: 0.6389 [2021-03-28 15:00:42 swin_base_patch4_window7_224] INFO: Epoch: [280] [1220/1251] eta: 0:00:19 lr: 0.000020 loss: 2.5562 (2.6568) grad_norm: 3.5395 (inf) time: 0.6337 [2021-03-28 15:00:48 swin_base_patch4_window7_224] INFO: Epoch: [280] [1230/1251] eta: 0:00:13 lr: 0.000020 loss: 2.6339 (2.6568) grad_norm: 3.5395 (inf) time: 0.6328 [2021-03-28 15:00:55 swin_base_patch4_window7_224] INFO: Epoch: [280] [1240/1251] eta: 0:00:06 lr: 0.000020 loss: 2.7024 (2.6572) grad_norm: 3.3070 (inf) time: 0.6317 [2021-03-28 15:01:01 swin_base_patch4_window7_224] INFO: Epoch: [280] [1250/1251] eta: 0:00:00 lr: 0.000020 loss: 2.8723 (2.6582) grad_norm: 3.3070 (inf) time: 0.6271 [2021-03-28 15:02:10 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:02 loss: 0.5733 (0.5733) acc1: 85.9375 (85.9375) acc5: 98.4375 (98.4375) [2021-03-28 15:02:11 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7770 (0.6698) acc1: 85.9375 (85.2273) acc5: 98.4375 (97.7273) [2021-03-28 15:02:13 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7797 (0.7149) acc1: 82.8125 (83.1845) acc5: 96.8750 (96.9494) [2021-03-28 15:02:14 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7915 (0.7469) acc1: 79.6875 (82.5101) acc5: 95.3125 (96.2198) [2021-03-28 15:02:16 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7221 (0.7463) acc1: 84.3750 (82.6601) acc5: 96.8750 (96.3415) [2021-03-28 15:02:17 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7221 (0.7527) acc1: 82.8125 (82.2400) acc5: 96.8750 (96.5440) [2021-03-28 15:02:31 swin_base_patch4_window7_224] INFO: * Acc@1 83.340 Acc@5 96.418 loss 0.743 [2021-03-28 15:02:31 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.3% [2021-03-28 15:02:31 swin_base_patch4_window7_224] INFO: Max accuracy: 83.34% [2021-03-28 15:02:35 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 0/1251] eta: 1:26:18 lr: 0.000020 loss: 2.8586 (2.8586) grad_norm: 3.2885 (3.2885) time: 4.1395 [2021-03-28 15:02:42 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 10/1251] eta: 0:20:23 lr: 0.000020 loss: 2.5514 (2.5884) grad_norm: 4.0095 (4.6894) time: 0.9856 [2021-03-28 15:02:49 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 20/1251] eta: 0:16:48 lr: 0.000020 loss: 2.6993 (2.6337) grad_norm: 3.6544 (4.4046) time: 0.6536 [2021-03-28 15:02:55 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 30/1251] eta: 0:15:29 lr: 0.000020 loss: 2.7550 (2.5759) grad_norm: 3.2782 (4.2516) time: 0.6376 [2021-03-28 15:03:01 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 40/1251] eta: 0:14:45 lr: 0.000020 loss: 2.5522 (2.5570) grad_norm: 3.3376 (4.0923) time: 0.6380 [2021-03-28 15:03:08 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 50/1251] eta: 0:14:15 lr: 0.000020 loss: 2.8381 (2.6349) grad_norm: 3.5598 (4.0905) time: 0.6362 [2021-03-28 15:03:14 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 60/1251] eta: 0:13:51 lr: 0.000020 loss: 2.8991 (2.6639) grad_norm: 3.4657 (4.0207) time: 0.6318 [2021-03-28 15:03:20 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 70/1251] eta: 0:13:34 lr: 0.000020 loss: 2.8593 (2.6846) grad_norm: 3.4657 (4.1263) time: 0.6327 [2021-03-28 15:03:27 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 80/1251] eta: 0:13:18 lr: 0.000020 loss: 2.7757 (2.6830) grad_norm: 3.5645 (4.1322) time: 0.6326 [2021-03-28 15:03:33 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 90/1251] eta: 0:13:06 lr: 0.000020 loss: 2.7842 (2.6923) grad_norm: 3.5173 (4.0609) time: 0.6333 [2021-03-28 15:03:39 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 100/1251] eta: 0:12:55 lr: 0.000020 loss: 2.8402 (2.6946) grad_norm: 3.3777 (4.0597) time: 0.6397 [2021-03-28 15:03:46 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 110/1251] eta: 0:12:43 lr: 0.000020 loss: 2.7771 (2.7049) grad_norm: 3.3894 (4.0068) time: 0.6312 [2021-03-28 15:03:52 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 120/1251] eta: 0:12:33 lr: 0.000020 loss: 2.8422 (2.7055) grad_norm: 3.3894 (3.9787) time: 0.6292 [2021-03-28 15:03:58 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 130/1251] eta: 0:12:24 lr: 0.000020 loss: 2.8422 (2.7099) grad_norm: 3.3442 (3.9432) time: 0.6349 [2021-03-28 15:04:05 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 140/1251] eta: 0:12:14 lr: 0.000020 loss: 2.8151 (2.6968) grad_norm: 3.3188 (3.9253) time: 0.6299 [2021-03-28 15:04:11 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 150/1251] eta: 0:12:05 lr: 0.000020 loss: 2.7023 (2.7044) grad_norm: 3.4910 (3.9344) time: 0.6273 [2021-03-28 15:04:17 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 160/1251] eta: 0:11:57 lr: 0.000020 loss: 2.6242 (2.6945) grad_norm: 3.5870 (3.9217) time: 0.6290 [2021-03-28 15:04:24 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 170/1251] eta: 0:11:48 lr: 0.000020 loss: 2.7222 (2.7017) grad_norm: 3.3994 (3.9029) time: 0.6316 [2021-03-28 15:04:30 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 180/1251] eta: 0:11:41 lr: 0.000020 loss: 2.7300 (2.7000) grad_norm: 3.2094 (3.8632) time: 0.6367 [2021-03-28 15:04:36 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 190/1251] eta: 0:11:34 lr: 0.000020 loss: 2.5886 (2.6926) grad_norm: 3.3829 (3.8931) time: 0.6409 [2021-03-28 15:04:43 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 200/1251] eta: 0:11:26 lr: 0.000020 loss: 2.7990 (2.7008) grad_norm: 3.5710 (3.8720) time: 0.6399 [2021-03-28 15:04:49 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 210/1251] eta: 0:11:19 lr: 0.000020 loss: 2.7708 (2.6878) grad_norm: 3.6728 (3.9051) time: 0.6364 [2021-03-28 15:04:55 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 220/1251] eta: 0:11:11 lr: 0.000020 loss: 2.6970 (2.6937) grad_norm: 3.8099 (3.8978) time: 0.6286 [2021-03-28 15:05:02 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 230/1251] eta: 0:11:03 lr: 0.000020 loss: 2.8138 (2.6935) grad_norm: 3.3557 (3.8728) time: 0.6245 [2021-03-28 15:05:08 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 240/1251] eta: 0:10:56 lr: 0.000020 loss: 2.7736 (2.6889) grad_norm: 3.3912 (3.8701) time: 0.6309 [2021-03-28 15:05:14 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 250/1251] eta: 0:10:49 lr: 0.000020 loss: 2.7735 (2.6861) grad_norm: 3.3335 (3.8720) time: 0.6352 [2021-03-28 15:05:21 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 260/1251] eta: 0:10:42 lr: 0.000020 loss: 2.5575 (2.6777) grad_norm: 3.4670 (3.9089) time: 0.6367 [2021-03-28 15:05:27 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 270/1251] eta: 0:10:35 lr: 0.000020 loss: 2.5213 (2.6700) grad_norm: 3.7816 (3.9065) time: 0.6311 [2021-03-28 15:05:33 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 280/1251] eta: 0:10:28 lr: 0.000020 loss: 2.6734 (2.6747) grad_norm: 3.6083 (3.8929) time: 0.6285 [2021-03-28 15:05:39 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 290/1251] eta: 0:10:21 lr: 0.000020 loss: 2.8184 (2.6771) grad_norm: 3.4629 (3.8773) time: 0.6281 [2021-03-28 15:05:46 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 300/1251] eta: 0:10:14 lr: 0.000020 loss: 2.7264 (2.6755) grad_norm: 3.4629 (3.8764) time: 0.6281 [2021-03-28 15:05:52 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 310/1251] eta: 0:10:07 lr: 0.000020 loss: 2.7130 (2.6760) grad_norm: 3.5001 (3.8791) time: 0.6334 [2021-03-28 15:05:59 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 320/1251] eta: 0:10:00 lr: 0.000020 loss: 2.7443 (2.6729) grad_norm: 3.4599 (3.8704) time: 0.6368 [2021-03-28 15:06:05 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 330/1251] eta: 0:09:53 lr: 0.000019 loss: 2.7727 (2.6742) grad_norm: 3.1469 (3.8559) time: 0.6340 [2021-03-28 15:06:11 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 340/1251] eta: 0:09:47 lr: 0.000019 loss: 2.8657 (2.6820) grad_norm: 3.2030 (3.8619) time: 0.6301 [2021-03-28 15:06:17 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 350/1251] eta: 0:09:40 lr: 0.000019 loss: 2.9138 (2.6841) grad_norm: 3.4275 (3.8671) time: 0.6307 [2021-03-28 15:06:24 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 360/1251] eta: 0:09:33 lr: 0.000019 loss: 2.7493 (2.6816) grad_norm: 3.4072 (3.8765) time: 0.6313 [2021-03-28 15:06:30 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 370/1251] eta: 0:09:26 lr: 0.000019 loss: 2.7392 (2.6821) grad_norm: 3.4289 (3.8738) time: 0.6363 [2021-03-28 15:06:36 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 380/1251] eta: 0:09:20 lr: 0.000019 loss: 2.5182 (2.6785) grad_norm: 3.4668 (3.8641) time: 0.6328 [2021-03-28 15:06:43 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 390/1251] eta: 0:09:13 lr: 0.000019 loss: 2.5187 (2.6781) grad_norm: 3.4668 (3.8593) time: 0.6281 [2021-03-28 15:06:49 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 400/1251] eta: 0:09:06 lr: 0.000019 loss: 2.6592 (2.6744) grad_norm: 3.4747 (3.8555) time: 0.6261 [2021-03-28 15:06:55 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 410/1251] eta: 0:08:59 lr: 0.000019 loss: 2.3367 (2.6666) grad_norm: 3.5808 (3.8496) time: 0.6263 [2021-03-28 15:07:02 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 420/1251] eta: 0:08:53 lr: 0.000019 loss: 2.4245 (2.6665) grad_norm: 3.5531 (3.8423) time: 0.6308 [2021-03-28 15:07:08 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 430/1251] eta: 0:08:46 lr: 0.000019 loss: 2.6465 (2.6648) grad_norm: 3.4373 (3.8340) time: 0.6292 [2021-03-28 15:07:14 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 440/1251] eta: 0:08:40 lr: 0.000019 loss: 2.6598 (2.6649) grad_norm: 3.2243 (3.8258) time: 0.6316 [2021-03-28 15:07:21 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 450/1251] eta: 0:08:33 lr: 0.000019 loss: 2.6653 (2.6616) grad_norm: 3.1300 (3.8171) time: 0.6345 [2021-03-28 15:07:27 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 460/1251] eta: 0:08:26 lr: 0.000019 loss: 2.6302 (2.6577) grad_norm: 3.1823 (3.8140) time: 0.6328 [2021-03-28 15:07:33 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 470/1251] eta: 0:08:20 lr: 0.000019 loss: 2.6567 (2.6619) grad_norm: 3.2136 (3.8021) time: 0.6343 [2021-03-28 15:07:40 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 480/1251] eta: 0:08:13 lr: 0.000019 loss: 2.6567 (2.6622) grad_norm: 3.2100 (3.7923) time: 0.6361 [2021-03-28 15:07:46 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 490/1251] eta: 0:08:07 lr: 0.000019 loss: 2.5922 (2.6624) grad_norm: 3.2514 (3.7911) time: 0.6354 [2021-03-28 15:07:52 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 500/1251] eta: 0:08:00 lr: 0.000019 loss: 2.5922 (2.6599) grad_norm: 3.3335 (3.7948) time: 0.6320 [2021-03-28 15:07:59 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 510/1251] eta: 0:07:54 lr: 0.000019 loss: 2.6647 (2.6622) grad_norm: 3.6131 (3.7959) time: 0.6368 [2021-03-28 15:08:05 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 520/1251] eta: 0:07:48 lr: 0.000019 loss: 2.8543 (2.6633) grad_norm: 3.6722 (3.8098) time: 0.6420 [2021-03-28 15:08:11 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 530/1251] eta: 0:07:41 lr: 0.000019 loss: 2.5894 (2.6611) grad_norm: 3.7997 (3.8173) time: 0.6363 [2021-03-28 15:08:18 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 540/1251] eta: 0:07:35 lr: 0.000019 loss: 2.2583 (2.6532) grad_norm: 3.7211 (3.8143) time: 0.6330 [2021-03-28 15:08:24 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 550/1251] eta: 0:07:28 lr: 0.000019 loss: 2.4689 (2.6518) grad_norm: 3.2229 (3.8096) time: 0.6388 [2021-03-28 15:08:31 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 560/1251] eta: 0:07:22 lr: 0.000019 loss: 2.6172 (2.6500) grad_norm: 3.2210 (3.7994) time: 0.6442 [2021-03-28 15:08:37 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 570/1251] eta: 0:07:16 lr: 0.000019 loss: 2.6169 (2.6479) grad_norm: 3.5326 (3.8003) time: 0.6490 [2021-03-28 15:08:44 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 580/1251] eta: 0:07:09 lr: 0.000019 loss: 2.5775 (2.6462) grad_norm: 3.5399 (3.8183) time: 0.6529 [2021-03-28 15:08:50 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 590/1251] eta: 0:07:03 lr: 0.000019 loss: 2.5698 (2.6450) grad_norm: 3.4952 (3.8126) time: 0.6458 [2021-03-28 15:08:56 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 600/1251] eta: 0:06:56 lr: 0.000019 loss: 2.7931 (2.6485) grad_norm: 3.3075 (3.8071) time: 0.6358 [2021-03-28 15:09:03 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 610/1251] eta: 0:06:50 lr: 0.000019 loss: 2.7795 (2.6480) grad_norm: 3.1842 (3.8073) time: 0.6392 [2021-03-28 15:09:09 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 620/1251] eta: 0:06:44 lr: 0.000019 loss: 2.6715 (2.6450) grad_norm: 3.5807 (3.8075) time: 0.6396 [2021-03-28 15:09:16 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 630/1251] eta: 0:06:37 lr: 0.000019 loss: 2.6997 (2.6456) grad_norm: 3.4642 (3.8046) time: 0.6345 [2021-03-28 15:09:22 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 640/1251] eta: 0:06:31 lr: 0.000019 loss: 2.7215 (2.6460) grad_norm: 3.7117 (3.8094) time: 0.6382 [2021-03-28 15:09:28 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 650/1251] eta: 0:06:24 lr: 0.000019 loss: 2.7650 (2.6475) grad_norm: 3.6228 (3.8048) time: 0.6319 [2021-03-28 15:09:34 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 660/1251] eta: 0:06:18 lr: 0.000019 loss: 2.7650 (2.6488) grad_norm: 3.4446 (3.8024) time: 0.6227 [2021-03-28 15:09:41 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 670/1251] eta: 0:06:11 lr: 0.000019 loss: 2.7895 (2.6494) grad_norm: 3.4446 (3.8009) time: 0.6248 [2021-03-28 15:09:47 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 680/1251] eta: 0:06:05 lr: 0.000019 loss: 2.7596 (2.6504) grad_norm: 3.4993 (3.7967) time: 0.6288 [2021-03-28 15:09:53 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 690/1251] eta: 0:05:58 lr: 0.000019 loss: 2.6285 (2.6466) grad_norm: 3.4738 (3.7940) time: 0.6320 [2021-03-28 15:10:00 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 700/1251] eta: 0:05:52 lr: 0.000019 loss: 2.6202 (2.6490) grad_norm: 3.4738 (3.7964) time: 0.6275 [2021-03-28 15:10:06 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 710/1251] eta: 0:05:45 lr: 0.000019 loss: 2.7263 (2.6487) grad_norm: 3.3913 (3.7918) time: 0.6223 [2021-03-28 15:10:12 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 720/1251] eta: 0:05:39 lr: 0.000019 loss: 2.7307 (2.6514) grad_norm: 3.4556 (3.7898) time: 0.6291 [2021-03-28 15:10:19 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 730/1251] eta: 0:05:32 lr: 0.000019 loss: 2.8337 (2.6508) grad_norm: 3.5229 (3.8206) time: 0.6359 [2021-03-28 15:10:25 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 740/1251] eta: 0:05:26 lr: 0.000019 loss: 2.7180 (2.6513) grad_norm: 3.3647 (3.8175) time: 0.6347 [2021-03-28 15:10:31 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 750/1251] eta: 0:05:20 lr: 0.000019 loss: 2.6693 (2.6532) grad_norm: 3.3255 (3.8271) time: 0.6350 [2021-03-28 15:10:38 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 760/1251] eta: 0:05:13 lr: 0.000019 loss: 2.7007 (2.6530) grad_norm: 3.1561 (3.8196) time: 0.6391 [2021-03-28 15:10:44 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 770/1251] eta: 0:05:07 lr: 0.000019 loss: 2.8182 (2.6557) grad_norm: 3.3152 (3.8196) time: 0.6420 [2021-03-28 15:10:50 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 780/1251] eta: 0:05:00 lr: 0.000019 loss: 2.8807 (2.6580) grad_norm: 3.4768 (3.8202) time: 0.6419 [2021-03-28 15:10:57 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 790/1251] eta: 0:04:54 lr: 0.000019 loss: 2.8907 (2.6606) grad_norm: 3.4320 (3.8153) time: 0.6357 [2021-03-28 15:11:03 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 800/1251] eta: 0:04:48 lr: 0.000019 loss: 2.7792 (2.6599) grad_norm: 3.4311 (3.8155) time: 0.6383 [2021-03-28 15:11:10 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 810/1251] eta: 0:04:41 lr: 0.000019 loss: 2.6537 (2.6609) grad_norm: 3.4859 (3.8151) time: 0.6399 [2021-03-28 15:11:16 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 820/1251] eta: 0:04:35 lr: 0.000019 loss: 2.7301 (2.6608) grad_norm: 3.3756 (3.8135) time: 0.6329 [2021-03-28 15:11:22 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 830/1251] eta: 0:04:28 lr: 0.000019 loss: 2.7301 (2.6607) grad_norm: 3.3669 (3.8116) time: 0.6387 [2021-03-28 15:11:29 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 840/1251] eta: 0:04:22 lr: 0.000019 loss: 2.6472 (2.6588) grad_norm: 3.5496 (3.8110) time: 0.6386 [2021-03-28 15:11:35 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 850/1251] eta: 0:04:16 lr: 0.000019 loss: 2.6641 (2.6579) grad_norm: 3.6041 (3.8077) time: 0.6305 [2021-03-28 15:11:41 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 860/1251] eta: 0:04:09 lr: 0.000019 loss: 2.7760 (2.6578) grad_norm: 3.4495 (3.8079) time: 0.6334 [2021-03-28 15:11:48 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 870/1251] eta: 0:04:03 lr: 0.000019 loss: 2.7999 (2.6591) grad_norm: 3.4536 (3.8052) time: 0.6395 [2021-03-28 15:11:54 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 880/1251] eta: 0:03:56 lr: 0.000019 loss: 2.7486 (2.6556) grad_norm: 3.4571 (3.8039) time: 0.6361 [2021-03-28 15:12:00 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 890/1251] eta: 0:03:50 lr: 0.000019 loss: 2.5796 (2.6557) grad_norm: 3.3362 (3.7965) time: 0.6287 [2021-03-28 15:12:07 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 900/1251] eta: 0:03:44 lr: 0.000019 loss: 2.5796 (2.6542) grad_norm: 3.2421 (3.7915) time: 0.6324 [2021-03-28 15:12:13 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 910/1251] eta: 0:03:37 lr: 0.000019 loss: 2.6853 (2.6557) grad_norm: 3.2421 (3.7912) time: 0.6384 [2021-03-28 15:12:19 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 920/1251] eta: 0:03:31 lr: 0.000019 loss: 2.7113 (2.6536) grad_norm: 3.2316 (3.7866) time: 0.6343 [2021-03-28 15:12:26 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 930/1251] eta: 0:03:24 lr: 0.000019 loss: 2.6797 (2.6545) grad_norm: 3.2485 (3.7823) time: 0.6387 [2021-03-28 15:12:32 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 940/1251] eta: 0:03:18 lr: 0.000019 loss: 2.6797 (2.6557) grad_norm: 3.4225 (3.7786) time: 0.6392 [2021-03-28 15:12:39 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 950/1251] eta: 0:03:12 lr: 0.000019 loss: 2.7819 (2.6572) grad_norm: 3.4225 (3.7744) time: 0.6364 [2021-03-28 15:12:45 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 960/1251] eta: 0:03:05 lr: 0.000019 loss: 2.6889 (2.6552) grad_norm: 3.6296 (3.7796) time: 0.6366 [2021-03-28 15:12:51 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 970/1251] eta: 0:02:59 lr: 0.000019 loss: 2.7366 (2.6563) grad_norm: 3.4801 (3.7761) time: 0.6300 [2021-03-28 15:12:58 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 980/1251] eta: 0:02:52 lr: 0.000019 loss: 2.8095 (2.6576) grad_norm: 3.2580 (3.7726) time: 0.6305 [2021-03-28 15:13:04 swin_base_patch4_window7_224] INFO: Epoch: [281] [ 990/1251] eta: 0:02:46 lr: 0.000019 loss: 2.7876 (2.6570) grad_norm: 3.2704 (3.7737) time: 0.6287 [2021-03-28 15:13:10 swin_base_patch4_window7_224] INFO: Epoch: [281] [1000/1251] eta: 0:02:40 lr: 0.000019 loss: 2.6697 (2.6574) grad_norm: 3.4499 (3.7743) time: 0.6317 [2021-03-28 15:13:17 swin_base_patch4_window7_224] INFO: Epoch: [281] [1010/1251] eta: 0:02:33 lr: 0.000019 loss: 2.6697 (2.6561) grad_norm: 3.5415 (3.7788) time: 0.6365 [2021-03-28 15:13:23 swin_base_patch4_window7_224] INFO: Epoch: [281] [1020/1251] eta: 0:02:27 lr: 0.000019 loss: 2.6870 (2.6567) grad_norm: 3.8253 (3.7879) time: 0.6354 [2021-03-28 15:13:29 swin_base_patch4_window7_224] INFO: Epoch: [281] [1030/1251] eta: 0:02:20 lr: 0.000019 loss: 2.7343 (2.6560) grad_norm: 3.3228 (3.7853) time: 0.6311 [2021-03-28 15:13:36 swin_base_patch4_window7_224] INFO: Epoch: [281] [1040/1251] eta: 0:02:14 lr: 0.000019 loss: 2.5801 (2.6547) grad_norm: 3.4026 (3.7858) time: 0.6300 [2021-03-28 15:13:42 swin_base_patch4_window7_224] INFO: Epoch: [281] [1050/1251] eta: 0:02:08 lr: 0.000019 loss: 2.6906 (2.6550) grad_norm: 3.4459 (3.7826) time: 0.6277 [2021-03-28 15:13:48 swin_base_patch4_window7_224] INFO: Epoch: [281] [1060/1251] eta: 0:02:01 lr: 0.000019 loss: 2.6102 (2.6535) grad_norm: 3.2774 (3.7792) time: 0.6284 [2021-03-28 15:13:54 swin_base_patch4_window7_224] INFO: Epoch: [281] [1070/1251] eta: 0:01:55 lr: 0.000019 loss: 2.6225 (2.6545) grad_norm: 3.3910 (3.7784) time: 0.6361 [2021-03-28 15:14:01 swin_base_patch4_window7_224] INFO: Epoch: [281] [1080/1251] eta: 0:01:49 lr: 0.000019 loss: 2.7411 (2.6560) grad_norm: 3.4473 (3.7798) time: 0.6316 [2021-03-28 15:14:07 swin_base_patch4_window7_224] INFO: Epoch: [281] [1090/1251] eta: 0:01:42 lr: 0.000019 loss: 2.8892 (2.6569) grad_norm: 3.6556 (3.7788) time: 0.6301 [2021-03-28 15:14:13 swin_base_patch4_window7_224] INFO: Epoch: [281] [1100/1251] eta: 0:01:36 lr: 0.000019 loss: 2.8967 (2.6564) grad_norm: 3.4707 (3.7770) time: 0.6294 [2021-03-28 15:14:20 swin_base_patch4_window7_224] INFO: Epoch: [281] [1110/1251] eta: 0:01:29 lr: 0.000019 loss: 2.7533 (2.6580) grad_norm: 3.4707 (3.7874) time: 0.6241 [2021-03-28 15:14:26 swin_base_patch4_window7_224] INFO: Epoch: [281] [1120/1251] eta: 0:01:23 lr: 0.000019 loss: 2.7365 (2.6585) grad_norm: 3.5277 (3.7890) time: 0.6263 [2021-03-28 15:14:32 swin_base_patch4_window7_224] INFO: Epoch: [281] [1130/1251] eta: 0:01:17 lr: 0.000019 loss: 2.7365 (2.6596) grad_norm: 3.5870 (3.7895) time: 0.6283 [2021-03-28 15:14:39 swin_base_patch4_window7_224] INFO: Epoch: [281] [1140/1251] eta: 0:01:10 lr: 0.000019 loss: 2.5855 (2.6574) grad_norm: 3.3363 (3.7837) time: 0.6329 [2021-03-28 15:14:45 swin_base_patch4_window7_224] INFO: Epoch: [281] [1150/1251] eta: 0:01:04 lr: 0.000019 loss: 2.7802 (2.6579) grad_norm: 3.3149 (3.8018) time: 0.6310 [2021-03-28 15:14:51 swin_base_patch4_window7_224] INFO: Epoch: [281] [1160/1251] eta: 0:00:57 lr: 0.000019 loss: 2.5795 (2.6556) grad_norm: 3.5763 (3.8036) time: 0.6295 [2021-03-28 15:14:57 swin_base_patch4_window7_224] INFO: Epoch: [281] [1170/1251] eta: 0:00:51 lr: 0.000019 loss: 2.7762 (2.6577) grad_norm: 3.3523 (3.7999) time: 0.6376 [2021-03-28 15:15:04 swin_base_patch4_window7_224] INFO: Epoch: [281] [1180/1251] eta: 0:00:45 lr: 0.000019 loss: 2.7919 (2.6578) grad_norm: 3.3683 (3.7983) time: 0.6342 [2021-03-28 15:15:10 swin_base_patch4_window7_224] INFO: Epoch: [281] [1190/1251] eta: 0:00:38 lr: 0.000019 loss: 2.7771 (2.6579) grad_norm: 3.3842 (3.7950) time: 0.6336 [2021-03-28 15:15:16 swin_base_patch4_window7_224] INFO: Epoch: [281] [1200/1251] eta: 0:00:32 lr: 0.000019 loss: 2.6726 (2.6571) grad_norm: 3.2116 (3.7938) time: 0.6313 [2021-03-28 15:15:23 swin_base_patch4_window7_224] INFO: Epoch: [281] [1210/1251] eta: 0:00:26 lr: 0.000019 loss: 2.6558 (2.6569) grad_norm: 3.8140 (3.7967) time: 0.6246 [2021-03-28 15:15:29 swin_base_patch4_window7_224] INFO: Epoch: [281] [1220/1251] eta: 0:00:19 lr: 0.000019 loss: 2.5471 (2.6550) grad_norm: 3.8934 (3.7976) time: 0.6292 [2021-03-28 15:15:35 swin_base_patch4_window7_224] INFO: Epoch: [281] [1230/1251] eta: 0:00:13 lr: 0.000019 loss: 2.3072 (2.6546) grad_norm: 3.2330 (3.7935) time: 0.6307 [2021-03-28 15:15:41 swin_base_patch4_window7_224] INFO: Epoch: [281] [1240/1251] eta: 0:00:07 lr: 0.000019 loss: 2.6870 (2.6554) grad_norm: 3.2302 (3.7911) time: 0.6246 [2021-03-28 15:15:48 swin_base_patch4_window7_224] INFO: Epoch: [281] [1250/1251] eta: 0:00:00 lr: 0.000019 loss: 2.7475 (2.6566) grad_norm: 3.2981 (3.7882) time: 0.6142 [2021-03-28 15:15:58 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:06 loss: 0.8091 (0.8091) acc1: 79.6875 (79.6875) acc5: 95.3125 (95.3125) [2021-03-28 15:16:01 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7066 (0.7356) acc1: 84.3750 (83.5227) acc5: 96.8750 (96.5909) [2021-03-28 15:16:03 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7486 (0.7776) acc1: 82.8125 (82.5149) acc5: 95.3125 (96.0565) [2021-03-28 15:16:05 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8580 (0.7829) acc1: 81.2500 (82.6109) acc5: 95.3125 (96.1190) [2021-03-28 15:16:08 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6940 (0.7606) acc1: 81.2500 (82.3171) acc5: 96.8750 (96.3796) [2021-03-28 15:16:09 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6843 (0.7504) acc1: 81.2500 (82.4640) acc5: 96.8750 (96.4800) [2021-03-28 15:16:23 swin_base_patch4_window7_224] INFO: * Acc@1 83.376 Acc@5 96.420 loss 0.740 [2021-03-28 15:16:23 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 15:16:23 swin_base_patch4_window7_224] INFO: Max accuracy: 83.38% [2021-03-28 15:16:28 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 0/1251] eta: 1:31:30 lr: 0.000019 loss: 3.1869 (3.1869) grad_norm: 3.4298 (3.4298) time: 4.3885 [2021-03-28 15:16:34 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 10/1251] eta: 0:20:08 lr: 0.000019 loss: 2.8220 (2.7263) grad_norm: 3.9414 (3.9787) time: 0.9738 [2021-03-28 15:16:40 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 20/1251] eta: 0:16:41 lr: 0.000019 loss: 2.7641 (2.6519) grad_norm: 3.7897 (3.7737) time: 0.6345 [2021-03-28 15:16:47 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 30/1251] eta: 0:15:19 lr: 0.000019 loss: 2.7641 (2.7147) grad_norm: 3.4358 (3.7286) time: 0.6319 [2021-03-28 15:16:53 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 40/1251] eta: 0:14:35 lr: 0.000019 loss: 2.6404 (2.6311) grad_norm: 3.3696 (3.7402) time: 0.6288 [2021-03-28 15:16:59 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 50/1251] eta: 0:14:07 lr: 0.000019 loss: 2.3901 (2.5739) grad_norm: 3.4242 (3.7885) time: 0.6326 [2021-03-28 15:17:06 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 60/1251] eta: 0:13:47 lr: 0.000019 loss: 2.4992 (2.5926) grad_norm: 3.6377 (3.7890) time: 0.6359 [2021-03-28 15:17:12 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 70/1251] eta: 0:13:31 lr: 0.000019 loss: 2.8385 (2.5979) grad_norm: 3.6339 (3.7859) time: 0.6396 [2021-03-28 15:17:18 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 80/1251] eta: 0:13:18 lr: 0.000019 loss: 2.8152 (2.5937) grad_norm: 3.5669 (3.7875) time: 0.6422 [2021-03-28 15:17:25 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 90/1251] eta: 0:13:04 lr: 0.000019 loss: 2.7121 (2.6049) grad_norm: 3.5787 (3.8008) time: 0.6341 [2021-03-28 15:17:31 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 100/1251] eta: 0:12:53 lr: 0.000019 loss: 2.6153 (2.6067) grad_norm: 3.7333 (3.8239) time: 0.6331 [2021-03-28 15:17:37 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 110/1251] eta: 0:12:42 lr: 0.000019 loss: 2.8021 (2.6250) grad_norm: 3.6879 (3.8075) time: 0.6371 [2021-03-28 15:17:44 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 120/1251] eta: 0:12:32 lr: 0.000019 loss: 2.8021 (2.6266) grad_norm: 3.5565 (3.8459) time: 0.6331 [2021-03-28 15:17:50 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 130/1251] eta: 0:12:22 lr: 0.000019 loss: 2.6863 (2.6310) grad_norm: 3.6204 (3.8373) time: 0.6299 [2021-03-28 15:17:56 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 140/1251] eta: 0:12:14 lr: 0.000019 loss: 2.7111 (2.6324) grad_norm: 3.8001 (3.8659) time: 0.6315 [2021-03-28 15:18:03 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 150/1251] eta: 0:12:04 lr: 0.000019 loss: 2.6619 (2.6301) grad_norm: 3.6775 (3.8813) time: 0.6298 [2021-03-28 15:18:09 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 160/1251] eta: 0:11:56 lr: 0.000019 loss: 2.4478 (2.6286) grad_norm: 3.6239 (3.9079) time: 0.6250 [2021-03-28 15:18:15 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 170/1251] eta: 0:11:47 lr: 0.000019 loss: 2.6086 (2.6192) grad_norm: 3.6393 (3.9027) time: 0.6263 [2021-03-28 15:18:22 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 180/1251] eta: 0:11:39 lr: 0.000019 loss: 2.7860 (2.6224) grad_norm: 3.2706 (3.8770) time: 0.6290 [2021-03-28 15:18:28 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 190/1251] eta: 0:11:31 lr: 0.000019 loss: 2.7860 (2.6214) grad_norm: 3.1601 (3.8495) time: 0.6291 [2021-03-28 15:18:34 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 200/1251] eta: 0:11:23 lr: 0.000019 loss: 2.5550 (2.6227) grad_norm: 3.4607 (3.8770) time: 0.6264 [2021-03-28 15:18:40 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 210/1251] eta: 0:11:16 lr: 0.000019 loss: 2.8253 (2.6331) grad_norm: 3.6761 (3.8620) time: 0.6310 [2021-03-28 15:18:47 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 220/1251] eta: 0:11:09 lr: 0.000019 loss: 2.8072 (2.6353) grad_norm: 3.4754 (3.8457) time: 0.6323 [2021-03-28 15:18:53 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 230/1251] eta: 0:11:01 lr: 0.000019 loss: 2.6271 (2.6242) grad_norm: 3.4754 (3.8759) time: 0.6280 [2021-03-28 15:18:59 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 240/1251] eta: 0:10:54 lr: 0.000019 loss: 2.4024 (2.6194) grad_norm: 3.3806 (3.8487) time: 0.6332 [2021-03-28 15:19:06 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 250/1251] eta: 0:10:47 lr: 0.000019 loss: 2.6312 (2.6236) grad_norm: 3.3520 (3.8387) time: 0.6369 [2021-03-28 15:19:12 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 260/1251] eta: 0:10:40 lr: 0.000019 loss: 2.7547 (2.6251) grad_norm: 3.4150 (3.8564) time: 0.6336 [2021-03-28 15:19:18 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 270/1251] eta: 0:10:33 lr: 0.000019 loss: 2.7727 (2.6239) grad_norm: 3.5735 (3.8660) time: 0.6315 [2021-03-28 15:19:25 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 280/1251] eta: 0:10:26 lr: 0.000019 loss: 2.8004 (2.6176) grad_norm: 3.6749 (3.8661) time: 0.6306 [2021-03-28 15:19:31 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 290/1251] eta: 0:10:19 lr: 0.000019 loss: 2.7749 (2.6209) grad_norm: 3.6053 (3.8597) time: 0.6267 [2021-03-28 15:19:37 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 300/1251] eta: 0:10:12 lr: 0.000019 loss: 2.9412 (2.6323) grad_norm: 3.8583 (3.8596) time: 0.6302 [2021-03-28 15:19:44 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 310/1251] eta: 0:10:06 lr: 0.000019 loss: 2.7948 (2.6311) grad_norm: 3.9499 (3.8583) time: 0.6390 [2021-03-28 15:19:50 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 320/1251] eta: 0:09:59 lr: 0.000019 loss: 2.7398 (2.6363) grad_norm: 3.2898 (3.8527) time: 0.6377 [2021-03-28 15:19:56 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 330/1251] eta: 0:09:52 lr: 0.000019 loss: 2.9505 (2.6473) grad_norm: 3.5316 (3.8511) time: 0.6278 [2021-03-28 15:20:03 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 340/1251] eta: 0:09:46 lr: 0.000019 loss: 2.9505 (2.6469) grad_norm: 3.5650 (3.8513) time: 0.6332 [2021-03-28 15:20:09 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 350/1251] eta: 0:09:39 lr: 0.000018 loss: 2.6026 (2.6503) grad_norm: 3.5647 (3.8461) time: 0.6395 [2021-03-28 15:20:15 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 360/1251] eta: 0:09:32 lr: 0.000018 loss: 2.6600 (2.6495) grad_norm: 3.5149 (3.8372) time: 0.6342 [2021-03-28 15:20:22 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 370/1251] eta: 0:09:26 lr: 0.000018 loss: 2.6600 (2.6441) grad_norm: 3.6467 (3.8617) time: 0.6323 [2021-03-28 15:20:28 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 380/1251] eta: 0:09:19 lr: 0.000018 loss: 2.6903 (2.6451) grad_norm: 3.6467 (3.8542) time: 0.6350 [2021-03-28 15:20:34 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 390/1251] eta: 0:09:13 lr: 0.000018 loss: 2.6781 (2.6411) grad_norm: 3.4529 (3.8654) time: 0.6411 [2021-03-28 15:20:41 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 400/1251] eta: 0:09:06 lr: 0.000018 loss: 2.7707 (2.6425) grad_norm: 3.2950 (3.8502) time: 0.6316 [2021-03-28 15:20:47 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 410/1251] eta: 0:08:59 lr: 0.000018 loss: 2.8562 (2.6435) grad_norm: 3.5297 (3.8437) time: 0.6276 [2021-03-28 15:20:53 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 420/1251] eta: 0:08:53 lr: 0.000018 loss: 2.9098 (2.6488) grad_norm: 3.5699 (3.8389) time: 0.6314 [2021-03-28 15:21:00 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 430/1251] eta: 0:08:46 lr: 0.000018 loss: 2.8258 (2.6487) grad_norm: 3.3639 (3.8472) time: 0.6320 [2021-03-28 15:21:06 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 440/1251] eta: 0:08:39 lr: 0.000018 loss: 2.4798 (2.6413) grad_norm: 3.3321 (3.8437) time: 0.6320 [2021-03-28 15:21:12 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 450/1251] eta: 0:08:33 lr: 0.000018 loss: 2.4564 (2.6410) grad_norm: 3.2950 (3.8345) time: 0.6287 [2021-03-28 15:21:19 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 460/1251] eta: 0:08:26 lr: 0.000018 loss: 2.7413 (2.6433) grad_norm: 3.2953 (3.8292) time: 0.6268 [2021-03-28 15:21:25 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 470/1251] eta: 0:08:20 lr: 0.000018 loss: 2.6045 (2.6377) grad_norm: 3.3484 (3.8398) time: 0.6306 [2021-03-28 15:21:31 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 480/1251] eta: 0:08:13 lr: 0.000018 loss: 2.5255 (2.6384) grad_norm: 3.4080 (3.8358) time: 0.6367 [2021-03-28 15:21:38 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 490/1251] eta: 0:08:07 lr: 0.000018 loss: 2.7907 (2.6415) grad_norm: 3.4733 (3.8494) time: 0.6391 [2021-03-28 15:21:44 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 500/1251] eta: 0:08:00 lr: 0.000018 loss: 2.7907 (2.6460) grad_norm: 3.2798 (3.8426) time: 0.6343 [2021-03-28 15:21:50 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 510/1251] eta: 0:07:53 lr: 0.000018 loss: 2.7025 (2.6476) grad_norm: 3.3041 (3.8421) time: 0.6233 [2021-03-28 15:21:56 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 520/1251] eta: 0:07:47 lr: 0.000018 loss: 2.5946 (2.6441) grad_norm: 3.2056 (3.8342) time: 0.6221 [2021-03-28 15:22:03 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 530/1251] eta: 0:07:40 lr: 0.000018 loss: 2.6587 (2.6441) grad_norm: 3.0640 (3.8369) time: 0.6285 [2021-03-28 15:22:09 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 540/1251] eta: 0:07:34 lr: 0.000018 loss: 2.7353 (2.6467) grad_norm: 3.3821 (3.8353) time: 0.6267 [2021-03-28 15:22:15 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 550/1251] eta: 0:07:28 lr: 0.000018 loss: 2.8637 (2.6432) grad_norm: 3.3679 (3.8307) time: 0.6395 [2021-03-28 15:22:22 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 560/1251] eta: 0:07:21 lr: 0.000018 loss: 2.6446 (2.6445) grad_norm: 3.4487 (3.8379) time: 0.6515 [2021-03-28 15:22:28 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 570/1251] eta: 0:07:15 lr: 0.000018 loss: 2.8436 (2.6477) grad_norm: 3.8795 (3.8488) time: 0.6408 [2021-03-28 15:22:35 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 580/1251] eta: 0:07:08 lr: 0.000018 loss: 2.6968 (2.6449) grad_norm: 3.8100 (3.8593) time: 0.6358 [2021-03-28 15:22:41 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 590/1251] eta: 0:07:02 lr: 0.000018 loss: 2.6264 (2.6453) grad_norm: 3.5818 (3.8669) time: 0.6396 [2021-03-28 15:22:47 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 600/1251] eta: 0:06:56 lr: 0.000018 loss: 2.7691 (2.6460) grad_norm: 3.4906 (3.8650) time: 0.6378 [2021-03-28 15:22:54 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 610/1251] eta: 0:06:49 lr: 0.000018 loss: 2.7734 (2.6463) grad_norm: 3.4830 (3.8629) time: 0.6288 [2021-03-28 15:23:00 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 620/1251] eta: 0:06:43 lr: 0.000018 loss: 2.3434 (2.6389) grad_norm: 3.4830 (3.8615) time: 0.6310 [2021-03-28 15:23:06 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 630/1251] eta: 0:06:36 lr: 0.000018 loss: 2.3434 (2.6362) grad_norm: 3.5087 (3.8567) time: 0.6354 [2021-03-28 15:23:13 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 640/1251] eta: 0:06:30 lr: 0.000018 loss: 2.7017 (2.6378) grad_norm: 3.6036 (3.8637) time: 0.6298 [2021-03-28 15:23:19 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 650/1251] eta: 0:06:23 lr: 0.000018 loss: 2.7777 (2.6389) grad_norm: 3.5400 (3.8578) time: 0.6339 [2021-03-28 15:23:26 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 660/1251] eta: 0:06:17 lr: 0.000018 loss: 2.7246 (2.6385) grad_norm: 3.5250 (3.8687) time: 0.6425 [2021-03-28 15:23:32 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 670/1251] eta: 0:06:11 lr: 0.000018 loss: 2.7246 (2.6399) grad_norm: 3.1197 (3.8693) time: 0.6390 [2021-03-28 15:23:38 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 680/1251] eta: 0:06:04 lr: 0.000018 loss: 2.6326 (2.6385) grad_norm: 3.1897 (3.8615) time: 0.6331 [2021-03-28 15:23:45 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 690/1251] eta: 0:05:58 lr: 0.000018 loss: 2.6467 (2.6406) grad_norm: 3.4969 (3.8688) time: 0.6333 [2021-03-28 15:23:51 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 700/1251] eta: 0:05:51 lr: 0.000018 loss: 2.9066 (2.6416) grad_norm: 3.6015 (3.8631) time: 0.6394 [2021-03-28 15:23:57 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 710/1251] eta: 0:05:45 lr: 0.000018 loss: 2.7315 (2.6415) grad_norm: 3.3815 (3.8598) time: 0.6335 [2021-03-28 15:24:03 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 720/1251] eta: 0:05:38 lr: 0.000018 loss: 2.8053 (2.6428) grad_norm: 3.2844 (3.8522) time: 0.6251 [2021-03-28 15:24:10 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 730/1251] eta: 0:05:32 lr: 0.000018 loss: 2.8415 (2.6436) grad_norm: 3.1793 (3.8673) time: 0.6324 [2021-03-28 15:24:16 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 740/1251] eta: 0:05:26 lr: 0.000018 loss: 2.6353 (2.6413) grad_norm: 3.2963 (3.8627) time: 0.6411 [2021-03-28 15:24:23 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 750/1251] eta: 0:05:19 lr: 0.000018 loss: 2.7408 (2.6447) grad_norm: 3.2963 (3.8586) time: 0.6401 [2021-03-28 15:24:29 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 760/1251] eta: 0:05:13 lr: 0.000018 loss: 2.6664 (2.6428) grad_norm: 3.6694 (3.8616) time: 0.6361 [2021-03-28 15:24:35 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 770/1251] eta: 0:05:06 lr: 0.000018 loss: 2.6117 (2.6456) grad_norm: 3.6017 (3.8636) time: 0.6352 [2021-03-28 15:24:42 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 780/1251] eta: 0:05:00 lr: 0.000018 loss: 2.9091 (2.6451) grad_norm: 3.5999 (3.8703) time: 0.6354 [2021-03-28 15:24:48 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 790/1251] eta: 0:04:54 lr: 0.000018 loss: 2.8043 (2.6459) grad_norm: 3.6327 (3.8655) time: 0.6292 [2021-03-28 15:24:54 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 800/1251] eta: 0:04:47 lr: 0.000018 loss: 2.8049 (2.6453) grad_norm: 3.6003 (3.8635) time: 0.6252 [2021-03-28 15:25:01 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 810/1251] eta: 0:04:41 lr: 0.000018 loss: 2.5589 (2.6444) grad_norm: 3.1906 (3.8548) time: 0.6298 [2021-03-28 15:25:07 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 820/1251] eta: 0:04:34 lr: 0.000018 loss: 2.5589 (2.6444) grad_norm: 3.2511 (3.8545) time: 0.6327 [2021-03-28 15:25:13 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 830/1251] eta: 0:04:28 lr: 0.000018 loss: 2.7850 (2.6454) grad_norm: 3.6474 (3.8547) time: 0.6334 [2021-03-28 15:25:20 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 840/1251] eta: 0:04:22 lr: 0.000018 loss: 2.8012 (2.6461) grad_norm: 3.6081 (3.8505) time: 0.6315 [2021-03-28 15:25:26 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 850/1251] eta: 0:04:15 lr: 0.000018 loss: 2.8974 (2.6480) grad_norm: 3.6081 (3.8508) time: 0.6317 [2021-03-28 15:25:32 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 860/1251] eta: 0:04:09 lr: 0.000018 loss: 2.7756 (2.6466) grad_norm: 3.6312 (3.8472) time: 0.6301 [2021-03-28 15:25:38 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 870/1251] eta: 0:04:02 lr: 0.000018 loss: 2.6091 (2.6461) grad_norm: 3.5534 (3.8485) time: 0.6255 [2021-03-28 15:25:45 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 880/1251] eta: 0:03:56 lr: 0.000018 loss: 2.6926 (2.6468) grad_norm: 3.5534 (3.8478) time: 0.6280 [2021-03-28 15:25:51 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 890/1251] eta: 0:03:50 lr: 0.000018 loss: 2.8329 (2.6488) grad_norm: 3.4514 (3.8479) time: 0.6346 [2021-03-28 15:25:57 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 900/1251] eta: 0:03:43 lr: 0.000018 loss: 2.8319 (2.6507) grad_norm: 3.4651 (3.8509) time: 0.6361 [2021-03-28 15:26:04 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 910/1251] eta: 0:03:37 lr: 0.000018 loss: 2.8355 (2.6531) grad_norm: 3.5514 (3.8499) time: 0.6296 [2021-03-28 15:26:10 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 920/1251] eta: 0:03:30 lr: 0.000018 loss: 2.8182 (2.6524) grad_norm: 3.5514 (3.8497) time: 0.6283 [2021-03-28 15:26:16 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 930/1251] eta: 0:03:24 lr: 0.000018 loss: 2.6464 (2.6513) grad_norm: 3.5642 (3.8485) time: 0.6330 [2021-03-28 15:26:23 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 940/1251] eta: 0:03:18 lr: 0.000018 loss: 2.6533 (2.6505) grad_norm: 3.4365 (3.8471) time: 0.6364 [2021-03-28 15:26:29 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 950/1251] eta: 0:03:11 lr: 0.000018 loss: 2.7694 (2.6514) grad_norm: 3.3648 (3.8495) time: 0.6369 [2021-03-28 15:26:35 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 960/1251] eta: 0:03:05 lr: 0.000018 loss: 2.7368 (2.6520) grad_norm: 3.7289 (3.8577) time: 0.6328 [2021-03-28 15:26:42 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 970/1251] eta: 0:02:58 lr: 0.000018 loss: 2.5985 (2.6502) grad_norm: 3.6566 (3.8551) time: 0.6338 [2021-03-28 15:26:48 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 980/1251] eta: 0:02:52 lr: 0.000018 loss: 2.5985 (2.6502) grad_norm: 3.5527 (3.8536) time: 0.6384 [2021-03-28 15:26:55 swin_base_patch4_window7_224] INFO: Epoch: [282] [ 990/1251] eta: 0:02:46 lr: 0.000018 loss: 2.7897 (2.6505) grad_norm: 3.4159 (3.8501) time: 0.6385 [2021-03-28 15:27:01 swin_base_patch4_window7_224] INFO: Epoch: [282] [1000/1251] eta: 0:02:39 lr: 0.000018 loss: 2.7300 (2.6520) grad_norm: 3.3307 (3.8477) time: 0.6296 [2021-03-28 15:27:07 swin_base_patch4_window7_224] INFO: Epoch: [282] [1010/1251] eta: 0:02:33 lr: 0.000018 loss: 2.7131 (2.6512) grad_norm: 3.2874 (3.8439) time: 0.6276 [2021-03-28 15:27:13 swin_base_patch4_window7_224] INFO: Epoch: [282] [1020/1251] eta: 0:02:27 lr: 0.000018 loss: 2.4900 (2.6507) grad_norm: 3.1934 (3.8378) time: 0.6274 [2021-03-28 15:27:20 swin_base_patch4_window7_224] INFO: Epoch: [282] [1030/1251] eta: 0:02:20 lr: 0.000018 loss: 2.6398 (2.6509) grad_norm: 3.2699 (3.8402) time: 0.6254 [2021-03-28 15:27:26 swin_base_patch4_window7_224] INFO: Epoch: [282] [1040/1251] eta: 0:02:14 lr: 0.000018 loss: 2.6814 (2.6512) grad_norm: 3.4828 (3.8373) time: 0.6354 [2021-03-28 15:27:32 swin_base_patch4_window7_224] INFO: Epoch: [282] [1050/1251] eta: 0:02:07 lr: 0.000018 loss: 2.8086 (2.6517) grad_norm: 3.5425 (3.8395) time: 0.6414 [2021-03-28 15:27:39 swin_base_patch4_window7_224] INFO: Epoch: [282] [1060/1251] eta: 0:02:01 lr: 0.000018 loss: 2.8332 (2.6517) grad_norm: 3.5610 (3.8369) time: 0.6378 [2021-03-28 15:27:45 swin_base_patch4_window7_224] INFO: Epoch: [282] [1070/1251] eta: 0:01:55 lr: 0.000018 loss: 2.8332 (2.6516) grad_norm: 3.5090 (3.8361) time: 0.6317 [2021-03-28 15:27:51 swin_base_patch4_window7_224] INFO: Epoch: [282] [1080/1251] eta: 0:01:48 lr: 0.000018 loss: 2.7810 (2.6531) grad_norm: 3.5727 (3.8328) time: 0.6328 [2021-03-28 15:27:58 swin_base_patch4_window7_224] INFO: Epoch: [282] [1090/1251] eta: 0:01:42 lr: 0.000018 loss: 2.6813 (2.6525) grad_norm: 3.5563 (3.8301) time: 0.6347 [2021-03-28 15:28:04 swin_base_patch4_window7_224] INFO: Epoch: [282] [1100/1251] eta: 0:01:36 lr: 0.000018 loss: 2.5290 (2.6525) grad_norm: 3.2686 (3.8255) time: 0.6368 [2021-03-28 15:28:11 swin_base_patch4_window7_224] INFO: Epoch: [282] [1110/1251] eta: 0:01:29 lr: 0.000018 loss: 2.6646 (2.6527) grad_norm: 3.3257 (3.8236) time: 0.6379 [2021-03-28 15:28:17 swin_base_patch4_window7_224] INFO: Epoch: [282] [1120/1251] eta: 0:01:23 lr: 0.000018 loss: 2.6798 (2.6537) grad_norm: 3.3257 (3.8196) time: 0.6323 [2021-03-28 15:28:23 swin_base_patch4_window7_224] INFO: Epoch: [282] [1130/1251] eta: 0:01:16 lr: 0.000018 loss: 2.6932 (2.6548) grad_norm: 3.3114 (3.8164) time: 0.6301 [2021-03-28 15:28:29 swin_base_patch4_window7_224] INFO: Epoch: [282] [1140/1251] eta: 0:01:10 lr: 0.000018 loss: 2.7774 (2.6557) grad_norm: 3.5912 (3.8160) time: 0.6311 [2021-03-28 15:28:36 swin_base_patch4_window7_224] INFO: Epoch: [282] [1150/1251] eta: 0:01:04 lr: 0.000018 loss: 2.8263 (2.6558) grad_norm: 3.5180 (3.8114) time: 0.6325 [2021-03-28 15:28:42 swin_base_patch4_window7_224] INFO: Epoch: [282] [1160/1251] eta: 0:00:57 lr: 0.000018 loss: 2.8044 (2.6543) grad_norm: 3.2132 (3.8087) time: 0.6345 [2021-03-28 15:28:49 swin_base_patch4_window7_224] INFO: Epoch: [282] [1170/1251] eta: 0:00:51 lr: 0.000018 loss: 2.6518 (2.6534) grad_norm: 3.3228 (3.8078) time: 0.6394 [2021-03-28 15:28:55 swin_base_patch4_window7_224] INFO: Epoch: [282] [1180/1251] eta: 0:00:45 lr: 0.000018 loss: 2.7870 (2.6558) grad_norm: 3.2485 (3.8031) time: 0.6374 [2021-03-28 15:29:01 swin_base_patch4_window7_224] INFO: Epoch: [282] [1190/1251] eta: 0:00:38 lr: 0.000018 loss: 2.7870 (2.6555) grad_norm: 3.2485 (3.7984) time: 0.6321 [2021-03-28 15:29:08 swin_base_patch4_window7_224] INFO: Epoch: [282] [1200/1251] eta: 0:00:32 lr: 0.000018 loss: 2.7387 (2.6569) grad_norm: 3.3978 (3.8038) time: 0.6336 [2021-03-28 15:29:14 swin_base_patch4_window7_224] INFO: Epoch: [282] [1210/1251] eta: 0:00:26 lr: 0.000018 loss: 2.6997 (2.6555) grad_norm: 3.4236 (3.8037) time: 0.6286 [2021-03-28 15:29:20 swin_base_patch4_window7_224] INFO: Epoch: [282] [1220/1251] eta: 0:00:19 lr: 0.000018 loss: 2.6032 (2.6549) grad_norm: 3.3268 (3.8028) time: 0.6233 [2021-03-28 15:29:26 swin_base_patch4_window7_224] INFO: Epoch: [282] [1230/1251] eta: 0:00:13 lr: 0.000018 loss: 2.5164 (2.6529) grad_norm: 3.3652 (3.8041) time: 0.6227 [2021-03-28 15:29:33 swin_base_patch4_window7_224] INFO: Epoch: [282] [1240/1251] eta: 0:00:06 lr: 0.000018 loss: 2.4852 (2.6529) grad_norm: 3.3652 (3.8018) time: 0.6241 [2021-03-28 15:29:39 swin_base_patch4_window7_224] INFO: Epoch: [282] [1250/1251] eta: 0:00:00 lr: 0.000018 loss: 2.8532 (2.6541) grad_norm: 3.1739 (3.7982) time: 0.6281 [2021-03-28 15:29:48 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:52 loss: 0.8627 (0.8627) acc1: 73.4375 (73.4375) acc5: 96.8750 (96.8750) [2021-03-28 15:29:50 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.6985 (0.7171) acc1: 84.3750 (83.2386) acc5: 96.8750 (96.4489) [2021-03-28 15:29:52 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7088 (0.7413) acc1: 82.8125 (82.8125) acc5: 95.3125 (96.2798) [2021-03-28 15:29:54 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7388 (0.7317) acc1: 82.8125 (82.9637) acc5: 96.8750 (96.5222) [2021-03-28 15:29:56 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7329 (0.7352) acc1: 82.8125 (82.9268) acc5: 96.8750 (96.4558) [2021-03-28 15:29:58 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7330 (0.7449) acc1: 82.8125 (82.5280) acc5: 96.8750 (96.5760) [2021-03-28 15:30:10 swin_base_patch4_window7_224] INFO: * Acc@1 83.386 Acc@5 96.472 loss 0.737 [2021-03-28 15:30:10 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 15:30:10 swin_base_patch4_window7_224] INFO: Max accuracy: 83.39% [2021-03-28 15:30:15 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 0/1251] eta: 1:28:07 lr: 0.000018 loss: 1.8482 (1.8482) grad_norm: 2.8631 (2.8631) time: 4.2262 [2021-03-28 15:30:21 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 10/1251] eta: 0:20:17 lr: 0.000018 loss: 2.7408 (2.6014) grad_norm: 3.5408 (3.6933) time: 0.9810 [2021-03-28 15:30:28 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 20/1251] eta: 0:16:50 lr: 0.000018 loss: 2.7408 (2.5975) grad_norm: 3.2897 (3.4450) time: 0.6506 [2021-03-28 15:30:34 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 30/1251] eta: 0:15:25 lr: 0.000018 loss: 2.6591 (2.6328) grad_norm: 3.1614 (3.7623) time: 0.6350 [2021-03-28 15:30:40 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 40/1251] eta: 0:14:41 lr: 0.000018 loss: 2.6264 (2.6083) grad_norm: 3.5237 (3.7537) time: 0.6308 [2021-03-28 15:30:47 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 50/1251] eta: 0:14:12 lr: 0.000018 loss: 2.5995 (2.6007) grad_norm: 3.3394 (3.6705) time: 0.6346 [2021-03-28 15:30:53 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 60/1251] eta: 0:13:47 lr: 0.000018 loss: 2.6330 (2.6312) grad_norm: 3.1208 (3.6078) time: 0.6272 [2021-03-28 15:30:59 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 70/1251] eta: 0:13:31 lr: 0.000018 loss: 2.8824 (2.6428) grad_norm: 3.1773 (3.5491) time: 0.6295 [2021-03-28 15:31:06 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 80/1251] eta: 0:13:17 lr: 0.000018 loss: 2.8758 (2.6526) grad_norm: 3.1986 (3.5491) time: 0.6380 [2021-03-28 15:31:12 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 90/1251] eta: 0:13:04 lr: 0.000018 loss: 2.6924 (2.6495) grad_norm: 3.2979 (3.5400) time: 0.6352 [2021-03-28 15:31:18 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 100/1251] eta: 0:12:52 lr: 0.000018 loss: 2.5206 (2.6362) grad_norm: 3.5800 (3.5674) time: 0.6320 [2021-03-28 15:31:25 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 110/1251] eta: 0:12:41 lr: 0.000018 loss: 2.6560 (2.6325) grad_norm: 3.4475 (3.5793) time: 0.6312 [2021-03-28 15:31:31 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 120/1251] eta: 0:12:30 lr: 0.000018 loss: 2.7102 (2.6204) grad_norm: 3.3055 (3.5714) time: 0.6269 [2021-03-28 15:31:37 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 130/1251] eta: 0:12:21 lr: 0.000018 loss: 2.5746 (2.6057) grad_norm: 3.3121 (3.5619) time: 0.6252 [2021-03-28 15:31:43 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 140/1251] eta: 0:12:11 lr: 0.000018 loss: 2.6413 (2.6039) grad_norm: 3.3398 (3.5460) time: 0.6241 [2021-03-28 15:31:50 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 150/1251] eta: 0:12:03 lr: 0.000018 loss: 2.7749 (2.6131) grad_norm: 3.3398 (3.5290) time: 0.6298 [2021-03-28 15:31:56 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 160/1251] eta: 0:11:54 lr: 0.000018 loss: 2.6953 (2.6054) grad_norm: 3.3112 (3.5193) time: 0.6346 [2021-03-28 15:32:02 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 170/1251] eta: 0:11:46 lr: 0.000018 loss: 2.6828 (2.6144) grad_norm: 3.4313 (3.5390) time: 0.6293 [2021-03-28 15:32:09 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 180/1251] eta: 0:11:38 lr: 0.000018 loss: 2.7519 (2.6260) grad_norm: 3.6270 (3.5467) time: 0.6309 [2021-03-28 15:32:15 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 190/1251] eta: 0:11:30 lr: 0.000018 loss: 2.8271 (2.6399) grad_norm: 3.4711 (3.5361) time: 0.6294 [2021-03-28 15:32:21 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 200/1251] eta: 0:11:23 lr: 0.000018 loss: 2.8271 (2.6505) grad_norm: 3.6147 (3.6746) time: 0.6291 [2021-03-28 15:32:28 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 210/1251] eta: 0:11:16 lr: 0.000018 loss: 2.7833 (2.6489) grad_norm: 3.7808 (3.6784) time: 0.6361 [2021-03-28 15:32:34 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 220/1251] eta: 0:11:08 lr: 0.000018 loss: 2.6189 (2.6462) grad_norm: 3.4725 (3.6769) time: 0.6340 [2021-03-28 15:32:40 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 230/1251] eta: 0:11:01 lr: 0.000018 loss: 2.7397 (2.6485) grad_norm: 3.6409 (3.7079) time: 0.6288 [2021-03-28 15:32:47 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 240/1251] eta: 0:10:54 lr: 0.000018 loss: 2.7815 (2.6526) grad_norm: 3.6998 (3.7533) time: 0.6315 [2021-03-28 15:32:53 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 250/1251] eta: 0:10:47 lr: 0.000018 loss: 2.7658 (2.6500) grad_norm: 4.0222 (3.7611) time: 0.6345 [2021-03-28 15:32:59 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 260/1251] eta: 0:10:40 lr: 0.000018 loss: 2.5773 (2.6472) grad_norm: 3.8095 (3.7588) time: 0.6333 [2021-03-28 15:33:06 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 270/1251] eta: 0:10:33 lr: 0.000018 loss: 2.7911 (2.6563) grad_norm: 3.5121 (3.7460) time: 0.6336 [2021-03-28 15:33:12 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 280/1251] eta: 0:10:26 lr: 0.000018 loss: 2.8279 (2.6589) grad_norm: 3.3070 (3.7383) time: 0.6349 [2021-03-28 15:33:18 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 290/1251] eta: 0:10:19 lr: 0.000018 loss: 2.6808 (2.6599) grad_norm: 3.3007 (3.7305) time: 0.6324 [2021-03-28 15:33:25 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 300/1251] eta: 0:10:12 lr: 0.000018 loss: 2.7355 (2.6649) grad_norm: 3.2782 (3.7260) time: 0.6295 [2021-03-28 15:33:31 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 310/1251] eta: 0:10:05 lr: 0.000018 loss: 2.6443 (2.6571) grad_norm: 3.3847 (3.7204) time: 0.6240 [2021-03-28 15:33:37 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 320/1251] eta: 0:09:58 lr: 0.000018 loss: 2.6443 (2.6621) grad_norm: 3.5209 (3.7226) time: 0.6238 [2021-03-28 15:33:43 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 330/1251] eta: 0:09:51 lr: 0.000018 loss: 2.6872 (2.6602) grad_norm: 3.6160 (3.7761) time: 0.6279 [2021-03-28 15:33:50 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 340/1251] eta: 0:09:45 lr: 0.000018 loss: 2.5926 (2.6672) grad_norm: 3.5428 (3.7657) time: 0.6334 [2021-03-28 15:33:56 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 350/1251] eta: 0:09:38 lr: 0.000018 loss: 2.5926 (2.6603) grad_norm: 3.5428 (3.7974) time: 0.6343 [2021-03-28 15:34:02 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 360/1251] eta: 0:09:31 lr: 0.000018 loss: 2.6403 (2.6625) grad_norm: 3.6805 (3.8215) time: 0.6303 [2021-03-28 15:34:09 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 370/1251] eta: 0:09:25 lr: 0.000018 loss: 2.8006 (2.6661) grad_norm: 3.6805 (3.8249) time: 0.6314 [2021-03-28 15:34:15 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 380/1251] eta: 0:09:18 lr: 0.000018 loss: 2.7836 (2.6613) grad_norm: 3.2641 (3.8086) time: 0.6267 [2021-03-28 15:34:21 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 390/1251] eta: 0:09:11 lr: 0.000018 loss: 2.7103 (2.6604) grad_norm: 3.0663 (3.8285) time: 0.6284 [2021-03-28 15:34:28 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 400/1251] eta: 0:09:05 lr: 0.000018 loss: 2.8339 (2.6636) grad_norm: 3.4427 (3.8179) time: 0.6373 [2021-03-28 15:34:34 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 410/1251] eta: 0:08:58 lr: 0.000018 loss: 2.7372 (2.6601) grad_norm: 3.4365 (3.8128) time: 0.6322 [2021-03-28 15:34:40 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 420/1251] eta: 0:08:51 lr: 0.000018 loss: 2.6763 (2.6617) grad_norm: 3.4623 (3.8086) time: 0.6244 [2021-03-28 15:34:46 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 430/1251] eta: 0:08:45 lr: 0.000018 loss: 2.7896 (2.6590) grad_norm: 3.5304 (3.8084) time: 0.6268 [2021-03-28 15:34:53 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 440/1251] eta: 0:08:38 lr: 0.000018 loss: 2.8322 (2.6651) grad_norm: 3.4685 (3.8019) time: 0.6284 [2021-03-28 15:34:59 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 450/1251] eta: 0:08:31 lr: 0.000017 loss: 2.8083 (2.6662) grad_norm: 3.4465 (3.8147) time: 0.6238 [2021-03-28 15:35:05 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 460/1251] eta: 0:08:25 lr: 0.000017 loss: 2.6668 (2.6638) grad_norm: 3.5567 (3.8092) time: 0.6229 [2021-03-28 15:35:11 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 470/1251] eta: 0:08:18 lr: 0.000017 loss: 2.5816 (2.6624) grad_norm: 3.4106 (3.8072) time: 0.6295 [2021-03-28 15:35:18 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 480/1251] eta: 0:08:12 lr: 0.000017 loss: 2.5161 (2.6576) grad_norm: 3.6964 (3.8144) time: 0.6309 [2021-03-28 15:35:24 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 490/1251] eta: 0:08:05 lr: 0.000017 loss: 2.5843 (2.6593) grad_norm: 3.6188 (3.8069) time: 0.6298 [2021-03-28 15:35:30 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 500/1251] eta: 0:07:59 lr: 0.000017 loss: 2.6783 (2.6587) grad_norm: 3.2596 (3.8156) time: 0.6312 [2021-03-28 15:35:37 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 510/1251] eta: 0:07:52 lr: 0.000017 loss: 2.6763 (2.6585) grad_norm: 3.2897 (3.8204) time: 0.6279 [2021-03-28 15:35:43 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 520/1251] eta: 0:07:46 lr: 0.000017 loss: 2.8627 (2.6617) grad_norm: 3.2415 (3.8109) time: 0.6275 [2021-03-28 15:35:49 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 530/1251] eta: 0:07:39 lr: 0.000017 loss: 2.8372 (2.6615) grad_norm: 3.2415 (3.8030) time: 0.6314 [2021-03-28 15:35:56 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 540/1251] eta: 0:07:33 lr: 0.000017 loss: 2.6862 (2.6578) grad_norm: 3.3689 (3.7969) time: 0.6324 [2021-03-28 15:36:02 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 550/1251] eta: 0:07:27 lr: 0.000017 loss: 2.6785 (2.6581) grad_norm: 3.5093 (3.8002) time: 0.6459 [2021-03-28 15:36:08 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 560/1251] eta: 0:07:20 lr: 0.000017 loss: 2.7524 (2.6591) grad_norm: 3.4842 (3.8052) time: 0.6456 [2021-03-28 15:36:15 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 570/1251] eta: 0:07:14 lr: 0.000017 loss: 2.6788 (2.6557) grad_norm: 3.4842 (3.8460) time: 0.6317 [2021-03-28 15:36:21 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 580/1251] eta: 0:07:07 lr: 0.000017 loss: 2.6846 (2.6567) grad_norm: 3.4729 (3.8393) time: 0.6348 [2021-03-28 15:36:27 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 590/1251] eta: 0:07:01 lr: 0.000017 loss: 2.7867 (2.6588) grad_norm: 3.4566 (3.8375) time: 0.6346 [2021-03-28 15:36:34 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 600/1251] eta: 0:06:55 lr: 0.000017 loss: 2.7859 (2.6609) grad_norm: 3.4906 (3.8303) time: 0.6374 [2021-03-28 15:36:40 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 610/1251] eta: 0:06:48 lr: 0.000017 loss: 2.8334 (2.6612) grad_norm: 3.4224 (3.8354) time: 0.6400 [2021-03-28 15:36:47 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 620/1251] eta: 0:06:42 lr: 0.000017 loss: 2.8009 (2.6617) grad_norm: 3.3887 (3.8276) time: 0.6352 [2021-03-28 15:36:53 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 630/1251] eta: 0:06:35 lr: 0.000017 loss: 2.7894 (2.6614) grad_norm: 3.3156 (3.8266) time: 0.6295 [2021-03-28 15:36:59 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 640/1251] eta: 0:06:29 lr: 0.000017 loss: 2.6549 (2.6590) grad_norm: 3.4087 (3.8274) time: 0.6292 [2021-03-28 15:37:06 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 650/1251] eta: 0:06:23 lr: 0.000017 loss: 2.6549 (2.6602) grad_norm: 3.4815 (3.8240) time: 0.6354 [2021-03-28 15:37:12 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 660/1251] eta: 0:06:16 lr: 0.000017 loss: 2.6335 (2.6588) grad_norm: 3.4335 (3.8213) time: 0.6352 [2021-03-28 15:37:18 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 670/1251] eta: 0:06:10 lr: 0.000017 loss: 2.6335 (2.6594) grad_norm: 3.4335 (3.8167) time: 0.6302 [2021-03-28 15:37:24 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 680/1251] eta: 0:06:03 lr: 0.000017 loss: 2.6378 (2.6589) grad_norm: 3.4979 (3.8149) time: 0.6257 [2021-03-28 15:37:31 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 690/1251] eta: 0:05:57 lr: 0.000017 loss: 2.5915 (2.6557) grad_norm: 3.4587 (3.8159) time: 0.6266 [2021-03-28 15:37:37 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 700/1251] eta: 0:05:50 lr: 0.000017 loss: 2.6381 (2.6561) grad_norm: 3.1484 (3.8150) time: 0.6297 [2021-03-28 15:37:43 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 710/1251] eta: 0:05:44 lr: 0.000017 loss: 2.8645 (2.6574) grad_norm: 3.2993 (3.8124) time: 0.6320 [2021-03-28 15:37:50 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 720/1251] eta: 0:05:38 lr: 0.000017 loss: 2.9641 (2.6594) grad_norm: 3.5831 (3.8233) time: 0.6295 [2021-03-28 15:37:56 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 730/1251] eta: 0:05:31 lr: 0.000017 loss: 3.0949 (2.6633) grad_norm: 3.6664 (3.8222) time: 0.6278 [2021-03-28 15:38:02 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 740/1251] eta: 0:05:25 lr: 0.000017 loss: 2.9869 (2.6659) grad_norm: 3.5346 (3.8169) time: 0.6396 [2021-03-28 15:38:09 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 750/1251] eta: 0:05:18 lr: 0.000017 loss: 2.7248 (2.6633) grad_norm: 3.4152 (3.8151) time: 0.6421 [2021-03-28 15:38:15 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 760/1251] eta: 0:05:12 lr: 0.000017 loss: 2.7510 (2.6649) grad_norm: 3.4152 (3.8118) time: 0.6356 [2021-03-28 15:38:21 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 770/1251] eta: 0:05:06 lr: 0.000017 loss: 2.7298 (2.6637) grad_norm: 3.4010 (3.8089) time: 0.6333 [2021-03-28 15:38:28 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 780/1251] eta: 0:04:59 lr: 0.000017 loss: 2.6248 (2.6642) grad_norm: 3.5025 (3.8089) time: 0.6327 [2021-03-28 15:38:34 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 790/1251] eta: 0:04:53 lr: 0.000017 loss: 2.6248 (2.6651) grad_norm: 3.5324 (3.8096) time: 0.6314 [2021-03-28 15:38:40 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 800/1251] eta: 0:04:46 lr: 0.000017 loss: 2.7088 (2.6644) grad_norm: 3.7578 (inf) time: 0.6272 [2021-03-28 15:38:47 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 810/1251] eta: 0:04:40 lr: 0.000017 loss: 2.5712 (2.6619) grad_norm: 3.6594 (inf) time: 0.6289 [2021-03-28 15:38:53 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 820/1251] eta: 0:04:34 lr: 0.000017 loss: 2.6093 (2.6623) grad_norm: 3.7229 (inf) time: 0.6295 [2021-03-28 15:38:59 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 830/1251] eta: 0:04:27 lr: 0.000017 loss: 2.7464 (2.6606) grad_norm: 3.7229 (inf) time: 0.6336 [2021-03-28 15:39:06 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 840/1251] eta: 0:04:21 lr: 0.000017 loss: 2.7307 (2.6596) grad_norm: 3.6138 (inf) time: 0.6350 [2021-03-28 15:39:12 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 850/1251] eta: 0:04:15 lr: 0.000017 loss: 2.8139 (2.6599) grad_norm: 3.7411 (inf) time: 0.6347 [2021-03-28 15:39:19 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 860/1251] eta: 0:04:08 lr: 0.000017 loss: 2.8974 (2.6619) grad_norm: 3.6604 (inf) time: 0.6439 [2021-03-28 15:39:25 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 870/1251] eta: 0:04:02 lr: 0.000017 loss: 2.8817 (2.6634) grad_norm: 3.4987 (inf) time: 0.6456 [2021-03-28 15:39:31 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 880/1251] eta: 0:03:56 lr: 0.000017 loss: 2.8378 (2.6640) grad_norm: 3.4412 (inf) time: 0.6442 [2021-03-28 15:39:38 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 890/1251] eta: 0:03:49 lr: 0.000017 loss: 2.6433 (2.6642) grad_norm: 3.4412 (inf) time: 0.6439 [2021-03-28 15:39:44 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 900/1251] eta: 0:03:43 lr: 0.000017 loss: 2.4580 (2.6625) grad_norm: 3.4513 (inf) time: 0.6423 [2021-03-28 15:39:50 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 910/1251] eta: 0:03:37 lr: 0.000017 loss: 2.5989 (2.6608) grad_norm: 3.4620 (inf) time: 0.6326 [2021-03-28 15:39:57 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 920/1251] eta: 0:03:30 lr: 0.000017 loss: 2.6266 (2.6603) grad_norm: 3.7088 (inf) time: 0.6256 [2021-03-28 15:40:03 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 930/1251] eta: 0:03:24 lr: 0.000017 loss: 2.6282 (2.6599) grad_norm: 3.9593 (inf) time: 0.6278 [2021-03-28 15:40:09 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 940/1251] eta: 0:03:17 lr: 0.000017 loss: 2.5888 (2.6576) grad_norm: 3.5881 (inf) time: 0.6315 [2021-03-28 15:40:16 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 950/1251] eta: 0:03:11 lr: 0.000017 loss: 2.5061 (2.6573) grad_norm: 3.2517 (inf) time: 0.6345 [2021-03-28 15:40:22 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 960/1251] eta: 0:03:05 lr: 0.000017 loss: 2.7029 (2.6583) grad_norm: 3.2591 (inf) time: 0.6380 [2021-03-28 15:40:29 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 970/1251] eta: 0:02:58 lr: 0.000017 loss: 2.7764 (2.6588) grad_norm: 3.3039 (inf) time: 0.6408 [2021-03-28 15:40:35 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 980/1251] eta: 0:02:52 lr: 0.000017 loss: 2.7764 (2.6580) grad_norm: 3.3779 (inf) time: 0.6322 [2021-03-28 15:40:41 swin_base_patch4_window7_224] INFO: Epoch: [283] [ 990/1251] eta: 0:02:46 lr: 0.000017 loss: 2.7471 (2.6592) grad_norm: 3.5448 (inf) time: 0.6250 [2021-03-28 15:40:47 swin_base_patch4_window7_224] INFO: Epoch: [283] [1000/1251] eta: 0:02:39 lr: 0.000017 loss: 2.7173 (2.6581) grad_norm: 3.3897 (inf) time: 0.6271 [2021-03-28 15:40:54 swin_base_patch4_window7_224] INFO: Epoch: [283] [1010/1251] eta: 0:02:33 lr: 0.000017 loss: 2.7765 (2.6598) grad_norm: 3.3897 (inf) time: 0.6356 [2021-03-28 15:41:00 swin_base_patch4_window7_224] INFO: Epoch: [283] [1020/1251] eta: 0:02:26 lr: 0.000017 loss: 2.7765 (2.6585) grad_norm: 3.2554 (inf) time: 0.6420 [2021-03-28 15:41:07 swin_base_patch4_window7_224] INFO: Epoch: [283] [1030/1251] eta: 0:02:20 lr: 0.000017 loss: 2.6893 (2.6599) grad_norm: 3.5016 (inf) time: 0.6436 [2021-03-28 15:41:13 swin_base_patch4_window7_224] INFO: Epoch: [283] [1040/1251] eta: 0:02:14 lr: 0.000017 loss: 2.8028 (2.6581) grad_norm: 3.6158 (inf) time: 0.6389 [2021-03-28 15:41:19 swin_base_patch4_window7_224] INFO: Epoch: [283] [1050/1251] eta: 0:02:07 lr: 0.000017 loss: 2.6856 (2.6586) grad_norm: 3.5619 (inf) time: 0.6339 [2021-03-28 15:41:26 swin_base_patch4_window7_224] INFO: Epoch: [283] [1060/1251] eta: 0:02:01 lr: 0.000017 loss: 2.7585 (2.6593) grad_norm: 3.4225 (inf) time: 0.6309 [2021-03-28 15:41:32 swin_base_patch4_window7_224] INFO: Epoch: [283] [1070/1251] eta: 0:01:55 lr: 0.000017 loss: 2.7585 (2.6584) grad_norm: 3.2862 (inf) time: 0.6312 [2021-03-28 15:41:38 swin_base_patch4_window7_224] INFO: Epoch: [283] [1080/1251] eta: 0:01:48 lr: 0.000017 loss: 2.6707 (2.6582) grad_norm: 3.3056 (inf) time: 0.6307 [2021-03-28 15:41:45 swin_base_patch4_window7_224] INFO: Epoch: [283] [1090/1251] eta: 0:01:42 lr: 0.000017 loss: 2.6707 (2.6577) grad_norm: 3.4003 (inf) time: 0.6318 [2021-03-28 15:41:51 swin_base_patch4_window7_224] INFO: Epoch: [283] [1100/1251] eta: 0:01:36 lr: 0.000017 loss: 2.5976 (2.6553) grad_norm: 3.3983 (inf) time: 0.6362 [2021-03-28 15:41:57 swin_base_patch4_window7_224] INFO: Epoch: [283] [1110/1251] eta: 0:01:29 lr: 0.000017 loss: 2.7194 (2.6563) grad_norm: 3.4026 (inf) time: 0.6336 [2021-03-28 15:42:04 swin_base_patch4_window7_224] INFO: Epoch: [283] [1120/1251] eta: 0:01:23 lr: 0.000017 loss: 2.7579 (2.6569) grad_norm: 3.4899 (inf) time: 0.6322 [2021-03-28 15:42:10 swin_base_patch4_window7_224] INFO: Epoch: [283] [1130/1251] eta: 0:01:16 lr: 0.000017 loss: 2.7579 (2.6572) grad_norm: 3.7835 (inf) time: 0.6324 [2021-03-28 15:42:16 swin_base_patch4_window7_224] INFO: Epoch: [283] [1140/1251] eta: 0:01:10 lr: 0.000017 loss: 2.7698 (2.6561) grad_norm: 3.6693 (inf) time: 0.6317 [2021-03-28 15:42:23 swin_base_patch4_window7_224] INFO: Epoch: [283] [1150/1251] eta: 0:01:04 lr: 0.000017 loss: 2.7698 (2.6560) grad_norm: 3.5444 (inf) time: 0.6358 [2021-03-28 15:42:29 swin_base_patch4_window7_224] INFO: Epoch: [283] [1160/1251] eta: 0:00:57 lr: 0.000017 loss: 2.6120 (2.6555) grad_norm: 3.5444 (inf) time: 0.6336 [2021-03-28 15:42:35 swin_base_patch4_window7_224] INFO: Epoch: [283] [1170/1251] eta: 0:00:51 lr: 0.000017 loss: 2.5761 (2.6549) grad_norm: 3.4022 (inf) time: 0.6328 [2021-03-28 15:42:42 swin_base_patch4_window7_224] INFO: Epoch: [283] [1180/1251] eta: 0:00:45 lr: 0.000017 loss: 2.6488 (2.6546) grad_norm: 3.2838 (inf) time: 0.6363 [2021-03-28 15:42:48 swin_base_patch4_window7_224] INFO: Epoch: [283] [1190/1251] eta: 0:00:38 lr: 0.000017 loss: 2.6785 (2.6547) grad_norm: 3.3984 (inf) time: 0.6351 [2021-03-28 15:42:54 swin_base_patch4_window7_224] INFO: Epoch: [283] [1200/1251] eta: 0:00:32 lr: 0.000017 loss: 2.7485 (2.6553) grad_norm: 4.0212 (inf) time: 0.6334 [2021-03-28 15:43:01 swin_base_patch4_window7_224] INFO: Epoch: [283] [1210/1251] eta: 0:00:26 lr: 0.000017 loss: 2.8183 (2.6568) grad_norm: 3.6473 (inf) time: 0.6345 [2021-03-28 15:43:07 swin_base_patch4_window7_224] INFO: Epoch: [283] [1220/1251] eta: 0:00:19 lr: 0.000017 loss: 2.7651 (2.6556) grad_norm: 3.4735 (inf) time: 0.6353 [2021-03-28 15:43:13 swin_base_patch4_window7_224] INFO: Epoch: [283] [1230/1251] eta: 0:00:13 lr: 0.000017 loss: 2.7171 (2.6554) grad_norm: 3.4620 (inf) time: 0.6336 [2021-03-28 15:43:20 swin_base_patch4_window7_224] INFO: Epoch: [283] [1240/1251] eta: 0:00:06 lr: 0.000017 loss: 2.8412 (2.6558) grad_norm: 3.3614 (inf) time: 0.6275 [2021-03-28 15:43:26 swin_base_patch4_window7_224] INFO: Epoch: [283] [1250/1251] eta: 0:00:00 lr: 0.000017 loss: 2.7933 (2.6560) grad_norm: 3.2306 (inf) time: 0.6147 [2021-03-28 15:43:41 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:49 loss: 0.5379 (0.5379) acc1: 87.5000 (87.5000) acc5: 98.4375 (98.4375) [2021-03-28 15:43:44 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7716 (0.7402) acc1: 82.8125 (82.1023) acc5: 96.8750 (96.5909) [2021-03-28 15:43:46 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7716 (0.7284) acc1: 81.2500 (81.6964) acc5: 96.8750 (97.0238) [2021-03-28 15:43:49 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6635 (0.7313) acc1: 82.8125 (82.0565) acc5: 96.8750 (97.0262) [2021-03-28 15:43:51 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6729 (0.7258) acc1: 84.3750 (82.4695) acc5: 96.8750 (96.9893) [2021-03-28 15:43:52 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6996 (0.7541) acc1: 84.3750 (82.4000) acc5: 96.8750 (96.5760) [2021-03-28 15:44:06 swin_base_patch4_window7_224] INFO: * Acc@1 83.328 Acc@5 96.432 loss 0.741 [2021-03-28 15:44:06 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.3% [2021-03-28 15:44:06 swin_base_patch4_window7_224] INFO: Max accuracy: 83.39% [2021-03-28 15:44:10 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 0/1251] eta: 1:25:35 lr: 0.000017 loss: 2.9113 (2.9113) grad_norm: 3.8558 (3.8558) time: 4.1049 [2021-03-28 15:44:17 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 10/1251] eta: 0:20:24 lr: 0.000017 loss: 2.7767 (2.7037) grad_norm: 3.6974 (3.9272) time: 0.9864 [2021-03-28 15:44:23 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 20/1251] eta: 0:16:46 lr: 0.000017 loss: 2.5322 (2.5588) grad_norm: 3.5146 (3.8552) time: 0.6534 [2021-03-28 15:44:29 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 30/1251] eta: 0:15:25 lr: 0.000017 loss: 2.4760 (2.5640) grad_norm: 3.3741 (3.7125) time: 0.6321 [2021-03-28 15:44:36 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 40/1251] eta: 0:14:42 lr: 0.000017 loss: 2.5697 (2.5831) grad_norm: 3.3489 (3.6689) time: 0.6345 [2021-03-28 15:44:42 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 50/1251] eta: 0:14:11 lr: 0.000017 loss: 2.8094 (2.5999) grad_norm: 3.5219 (3.6964) time: 0.6328 [2021-03-28 15:44:48 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 60/1251] eta: 0:13:49 lr: 0.000017 loss: 2.6248 (2.5873) grad_norm: 3.5354 (3.6779) time: 0.6303 [2021-03-28 15:44:55 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 70/1251] eta: 0:13:33 lr: 0.000017 loss: 2.6416 (2.6008) grad_norm: 3.5330 (3.6895) time: 0.6374 [2021-03-28 15:45:01 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 80/1251] eta: 0:13:18 lr: 0.000017 loss: 2.7741 (2.6086) grad_norm: 3.8237 (3.7766) time: 0.6380 [2021-03-28 15:45:07 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 90/1251] eta: 0:13:04 lr: 0.000017 loss: 2.7077 (2.6269) grad_norm: 3.7183 (3.7726) time: 0.6290 [2021-03-28 15:45:14 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 100/1251] eta: 0:12:52 lr: 0.000017 loss: 2.7077 (2.6210) grad_norm: 3.6405 (3.8350) time: 0.6283 [2021-03-28 15:45:20 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 110/1251] eta: 0:12:41 lr: 0.000017 loss: 2.8005 (2.6310) grad_norm: 3.4932 (3.8119) time: 0.6310 [2021-03-28 15:45:26 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 120/1251] eta: 0:12:31 lr: 0.000017 loss: 2.7867 (2.6288) grad_norm: 3.3514 (3.8256) time: 0.6315 [2021-03-28 15:45:33 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 130/1251] eta: 0:12:22 lr: 0.000017 loss: 2.7776 (2.6347) grad_norm: 3.3514 (3.7982) time: 0.6349 [2021-03-28 15:45:39 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 140/1251] eta: 0:12:13 lr: 0.000017 loss: 2.8407 (2.6466) grad_norm: 3.2924 (3.7836) time: 0.6336 [2021-03-28 15:45:45 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 150/1251] eta: 0:12:04 lr: 0.000017 loss: 2.8318 (2.6414) grad_norm: 3.5371 (3.9074) time: 0.6313 [2021-03-28 15:45:52 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 160/1251] eta: 0:11:56 lr: 0.000017 loss: 2.6634 (2.6363) grad_norm: 3.6176 (3.9075) time: 0.6296 [2021-03-28 15:45:58 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 170/1251] eta: 0:11:48 lr: 0.000017 loss: 2.6634 (2.6425) grad_norm: 3.6268 (3.9147) time: 0.6322 [2021-03-28 15:46:04 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 180/1251] eta: 0:11:40 lr: 0.000017 loss: 2.9327 (2.6631) grad_norm: 3.8283 (3.9201) time: 0.6340 [2021-03-28 15:46:11 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 190/1251] eta: 0:11:33 lr: 0.000017 loss: 2.9016 (2.6608) grad_norm: 3.5719 (3.9512) time: 0.6360 [2021-03-28 15:46:17 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 200/1251] eta: 0:11:25 lr: 0.000017 loss: 2.6394 (2.6613) grad_norm: 3.3912 (4.2144) time: 0.6394 [2021-03-28 15:46:24 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 210/1251] eta: 0:11:18 lr: 0.000017 loss: 2.7825 (2.6614) grad_norm: 3.4463 (4.1968) time: 0.6359 [2021-03-28 15:46:30 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 220/1251] eta: 0:11:11 lr: 0.000017 loss: 2.7825 (2.6554) grad_norm: 3.4059 (4.1789) time: 0.6419 [2021-03-28 15:46:36 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 230/1251] eta: 0:11:03 lr: 0.000017 loss: 2.7179 (2.6596) grad_norm: 3.9748 (4.2005) time: 0.6348 [2021-03-28 15:46:43 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 240/1251] eta: 0:10:56 lr: 0.000017 loss: 2.7725 (2.6522) grad_norm: 3.9432 (4.1773) time: 0.6292 [2021-03-28 15:46:49 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 250/1251] eta: 0:10:49 lr: 0.000017 loss: 2.2411 (2.6373) grad_norm: 3.4360 (4.1552) time: 0.6382 [2021-03-28 15:46:55 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 260/1251] eta: 0:10:42 lr: 0.000017 loss: 2.6966 (2.6418) grad_norm: 3.5589 (4.1352) time: 0.6312 [2021-03-28 15:47:02 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 270/1251] eta: 0:10:35 lr: 0.000017 loss: 2.6966 (2.6367) grad_norm: 3.8155 (4.1523) time: 0.6269 [2021-03-28 15:47:08 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 280/1251] eta: 0:10:28 lr: 0.000017 loss: 2.6202 (2.6379) grad_norm: 3.9211 (4.1481) time: 0.6321 [2021-03-28 15:47:14 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 290/1251] eta: 0:10:21 lr: 0.000017 loss: 2.8055 (2.6386) grad_norm: 3.4799 (4.1236) time: 0.6375 [2021-03-28 15:47:21 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 300/1251] eta: 0:10:14 lr: 0.000017 loss: 2.9004 (2.6457) grad_norm: 3.4488 (4.1034) time: 0.6398 [2021-03-28 15:47:27 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 310/1251] eta: 0:10:07 lr: 0.000017 loss: 2.7132 (2.6388) grad_norm: 3.4576 (4.0968) time: 0.6308 [2021-03-28 15:47:33 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 320/1251] eta: 0:10:01 lr: 0.000017 loss: 2.5006 (2.6345) grad_norm: 3.8776 (4.0964) time: 0.6332 [2021-03-28 15:47:40 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 330/1251] eta: 0:09:54 lr: 0.000017 loss: 2.6999 (2.6372) grad_norm: 3.7168 (4.0862) time: 0.6380 [2021-03-28 15:47:46 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 340/1251] eta: 0:09:47 lr: 0.000017 loss: 2.7182 (2.6369) grad_norm: 3.5657 (4.0712) time: 0.6315 [2021-03-28 15:47:52 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 350/1251] eta: 0:09:40 lr: 0.000017 loss: 2.7447 (2.6399) grad_norm: 3.5509 (4.0730) time: 0.6282 [2021-03-28 15:47:59 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 360/1251] eta: 0:09:34 lr: 0.000017 loss: 2.8623 (2.6439) grad_norm: 3.5905 (4.0665) time: 0.6340 [2021-03-28 15:48:05 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 370/1251] eta: 0:09:27 lr: 0.000017 loss: 2.7459 (2.6422) grad_norm: 3.5914 (4.0603) time: 0.6342 [2021-03-28 15:48:11 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 380/1251] eta: 0:09:20 lr: 0.000017 loss: 2.6662 (2.6416) grad_norm: 3.9912 (4.1015) time: 0.6297 [2021-03-28 15:48:18 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 390/1251] eta: 0:09:13 lr: 0.000017 loss: 2.6767 (2.6421) grad_norm: 3.9469 (4.0971) time: 0.6306 [2021-03-28 15:48:24 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 400/1251] eta: 0:09:07 lr: 0.000017 loss: 2.6208 (2.6381) grad_norm: 3.8134 (4.0905) time: 0.6291 [2021-03-28 15:48:30 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 410/1251] eta: 0:09:00 lr: 0.000017 loss: 2.6208 (2.6378) grad_norm: 3.6443 (4.0797) time: 0.6274 [2021-03-28 15:48:37 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 420/1251] eta: 0:08:53 lr: 0.000017 loss: 2.6540 (2.6399) grad_norm: 3.3583 (4.0622) time: 0.6334 [2021-03-28 15:48:43 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 430/1251] eta: 0:08:47 lr: 0.000017 loss: 2.7164 (2.6408) grad_norm: 3.3392 (4.0544) time: 0.6342 [2021-03-28 15:48:49 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 440/1251] eta: 0:08:40 lr: 0.000017 loss: 2.8028 (2.6462) grad_norm: 3.5607 (4.0550) time: 0.6279 [2021-03-28 15:48:55 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 450/1251] eta: 0:08:33 lr: 0.000017 loss: 2.8120 (2.6461) grad_norm: 3.8315 (4.0707) time: 0.6281 [2021-03-28 15:49:02 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 460/1251] eta: 0:08:27 lr: 0.000017 loss: 2.6942 (2.6451) grad_norm: 3.7626 (4.0706) time: 0.6304 [2021-03-28 15:49:08 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 470/1251] eta: 0:08:20 lr: 0.000017 loss: 2.6208 (2.6423) grad_norm: 3.4018 (4.0646) time: 0.6338 [2021-03-28 15:49:14 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 480/1251] eta: 0:08:14 lr: 0.000017 loss: 2.6208 (2.6434) grad_norm: 3.2635 (4.0633) time: 0.6352 [2021-03-28 15:49:21 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 490/1251] eta: 0:08:07 lr: 0.000017 loss: 2.7842 (2.6440) grad_norm: 3.2900 (4.0521) time: 0.6327 [2021-03-28 15:49:27 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 500/1251] eta: 0:08:01 lr: 0.000017 loss: 2.7746 (2.6424) grad_norm: 3.3927 (4.0444) time: 0.6343 [2021-03-28 15:49:33 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 510/1251] eta: 0:07:54 lr: 0.000017 loss: 2.8128 (2.6472) grad_norm: 3.5533 (4.0927) time: 0.6384 [2021-03-28 15:49:40 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 520/1251] eta: 0:07:48 lr: 0.000017 loss: 2.8732 (2.6470) grad_norm: 3.7942 (4.0927) time: 0.6358 [2021-03-28 15:49:46 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 530/1251] eta: 0:07:41 lr: 0.000017 loss: 2.7479 (2.6473) grad_norm: 3.4747 (4.0769) time: 0.6415 [2021-03-28 15:49:53 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 540/1251] eta: 0:07:35 lr: 0.000017 loss: 2.7461 (2.6474) grad_norm: 3.1754 (4.0679) time: 0.6367 [2021-03-28 15:49:59 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 550/1251] eta: 0:07:29 lr: 0.000017 loss: 2.7461 (2.6495) grad_norm: 3.8538 (4.0668) time: 0.6405 [2021-03-28 15:50:06 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 560/1251] eta: 0:07:22 lr: 0.000017 loss: 2.7319 (2.6474) grad_norm: 3.6002 (4.0563) time: 0.6500 [2021-03-28 15:50:12 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 570/1251] eta: 0:07:16 lr: 0.000017 loss: 2.5508 (2.6468) grad_norm: 3.5966 (4.0545) time: 0.6372 [2021-03-28 15:50:18 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 580/1251] eta: 0:07:09 lr: 0.000017 loss: 2.7535 (2.6469) grad_norm: 3.6724 (4.0592) time: 0.6361 [2021-03-28 15:50:25 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 590/1251] eta: 0:07:03 lr: 0.000017 loss: 2.7888 (2.6481) grad_norm: 3.6724 (4.0546) time: 0.6371 [2021-03-28 15:50:31 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 600/1251] eta: 0:06:56 lr: 0.000017 loss: 2.7687 (2.6497) grad_norm: 3.5107 (4.0472) time: 0.6274 [2021-03-28 15:50:37 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 610/1251] eta: 0:06:50 lr: 0.000017 loss: 2.6937 (2.6495) grad_norm: 3.4136 (4.0454) time: 0.6260 [2021-03-28 15:50:43 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 620/1251] eta: 0:06:43 lr: 0.000017 loss: 2.4975 (2.6474) grad_norm: 3.3179 (4.0348) time: 0.6280 [2021-03-28 15:50:50 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 630/1251] eta: 0:06:37 lr: 0.000017 loss: 2.5098 (2.6474) grad_norm: 3.3827 (4.0426) time: 0.6284 [2021-03-28 15:50:56 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 640/1251] eta: 0:06:30 lr: 0.000016 loss: 2.5479 (2.6465) grad_norm: 3.3827 (4.0346) time: 0.6320 [2021-03-28 15:51:02 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 650/1251] eta: 0:06:24 lr: 0.000016 loss: 2.5479 (2.6457) grad_norm: 3.3427 (4.0255) time: 0.6346 [2021-03-28 15:51:09 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 660/1251] eta: 0:06:17 lr: 0.000016 loss: 2.6764 (2.6469) grad_norm: 3.3082 (4.0174) time: 0.6349 [2021-03-28 15:51:15 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 670/1251] eta: 0:06:11 lr: 0.000016 loss: 2.7024 (2.6479) grad_norm: 3.4875 (4.1450) time: 0.6320 [2021-03-28 15:51:21 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 680/1251] eta: 0:06:04 lr: 0.000016 loss: 2.7277 (2.6472) grad_norm: 3.4037 (4.1329) time: 0.6288 [2021-03-28 15:51:28 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 690/1251] eta: 0:05:58 lr: 0.000016 loss: 2.7925 (2.6505) grad_norm: 3.2221 (4.1227) time: 0.6277 [2021-03-28 15:51:34 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 700/1251] eta: 0:05:51 lr: 0.000016 loss: 2.7925 (2.6517) grad_norm: 3.2221 (4.1218) time: 0.6299 [2021-03-28 15:51:40 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 710/1251] eta: 0:05:45 lr: 0.000016 loss: 2.7541 (2.6523) grad_norm: 3.4319 (4.1152) time: 0.6282 [2021-03-28 15:51:46 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 720/1251] eta: 0:05:39 lr: 0.000016 loss: 2.7515 (2.6538) grad_norm: 3.2782 (4.1097) time: 0.6267 [2021-03-28 15:51:53 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 730/1251] eta: 0:05:32 lr: 0.000016 loss: 2.7108 (2.6523) grad_norm: 3.4487 (4.1035) time: 0.6343 [2021-03-28 15:51:59 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 740/1251] eta: 0:05:26 lr: 0.000016 loss: 2.7108 (2.6547) grad_norm: 3.5797 (4.0995) time: 0.6389 [2021-03-28 15:52:06 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 750/1251] eta: 0:05:19 lr: 0.000016 loss: 2.8554 (2.6541) grad_norm: 3.4167 (4.0952) time: 0.6380 [2021-03-28 15:52:12 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 760/1251] eta: 0:05:13 lr: 0.000016 loss: 2.4947 (2.6511) grad_norm: 3.4167 (4.0912) time: 0.6377 [2021-03-28 15:52:18 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 770/1251] eta: 0:05:07 lr: 0.000016 loss: 2.5649 (2.6506) grad_norm: 3.4423 (4.0875) time: 0.6314 [2021-03-28 15:52:25 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 780/1251] eta: 0:05:00 lr: 0.000016 loss: 2.6875 (2.6512) grad_norm: 3.4177 (4.0802) time: 0.6254 [2021-03-28 15:52:31 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 790/1251] eta: 0:04:54 lr: 0.000016 loss: 2.5238 (2.6492) grad_norm: 3.2178 (4.0719) time: 0.6309 [2021-03-28 15:52:37 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 800/1251] eta: 0:04:47 lr: 0.000016 loss: 2.4280 (2.6480) grad_norm: 3.2178 (4.0647) time: 0.6342 [2021-03-28 15:52:44 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 810/1251] eta: 0:04:41 lr: 0.000016 loss: 2.6381 (2.6491) grad_norm: 3.8466 (4.0648) time: 0.6326 [2021-03-28 15:52:50 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 820/1251] eta: 0:04:34 lr: 0.000016 loss: 2.8358 (2.6489) grad_norm: 3.6844 (4.0570) time: 0.6340 [2021-03-28 15:52:56 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 830/1251] eta: 0:04:28 lr: 0.000016 loss: 2.8358 (2.6513) grad_norm: 3.4433 (4.0521) time: 0.6330 [2021-03-28 15:53:02 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 840/1251] eta: 0:04:22 lr: 0.000016 loss: 2.8392 (2.6532) grad_norm: 3.5790 (4.0541) time: 0.6309 [2021-03-28 15:53:09 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 850/1251] eta: 0:04:15 lr: 0.000016 loss: 2.8392 (2.6547) grad_norm: 3.6218 (4.0471) time: 0.6344 [2021-03-28 15:53:15 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 860/1251] eta: 0:04:09 lr: 0.000016 loss: 2.8524 (2.6577) grad_norm: 3.5168 (4.0435) time: 0.6361 [2021-03-28 15:53:22 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 870/1251] eta: 0:04:02 lr: 0.000016 loss: 2.8524 (2.6595) grad_norm: 3.5086 (4.0387) time: 0.6378 [2021-03-28 15:53:28 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 880/1251] eta: 0:03:56 lr: 0.000016 loss: 2.7335 (2.6589) grad_norm: 3.4546 (4.0317) time: 0.6380 [2021-03-28 15:53:34 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 890/1251] eta: 0:03:50 lr: 0.000016 loss: 2.7994 (2.6588) grad_norm: 3.3107 (4.0306) time: 0.6350 [2021-03-28 15:53:41 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 900/1251] eta: 0:03:43 lr: 0.000016 loss: 2.8270 (2.6580) grad_norm: 3.4238 (4.0226) time: 0.6373 [2021-03-28 15:53:47 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 910/1251] eta: 0:03:37 lr: 0.000016 loss: 2.9261 (2.6594) grad_norm: 3.5024 (4.0312) time: 0.6394 [2021-03-28 15:53:53 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 920/1251] eta: 0:03:31 lr: 0.000016 loss: 2.8981 (2.6614) grad_norm: 3.6095 (4.0274) time: 0.6375 [2021-03-28 15:54:00 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 930/1251] eta: 0:03:24 lr: 0.000016 loss: 2.7640 (2.6608) grad_norm: 3.3219 (4.0199) time: 0.6349 [2021-03-28 15:54:06 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 940/1251] eta: 0:03:18 lr: 0.000016 loss: 2.6392 (2.6604) grad_norm: 3.2668 (4.0143) time: 0.6339 [2021-03-28 15:54:12 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 950/1251] eta: 0:03:11 lr: 0.000016 loss: 2.7352 (2.6604) grad_norm: 3.5532 (4.0166) time: 0.6329 [2021-03-28 15:54:19 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 960/1251] eta: 0:03:05 lr: 0.000016 loss: 2.8342 (2.6609) grad_norm: 3.7047 (4.0127) time: 0.6324 [2021-03-28 15:54:25 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 970/1251] eta: 0:02:59 lr: 0.000016 loss: 2.8342 (2.6614) grad_norm: 3.6395 (4.0083) time: 0.6364 [2021-03-28 15:54:31 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 980/1251] eta: 0:02:52 lr: 0.000016 loss: 2.6893 (2.6592) grad_norm: 3.6395 (4.0076) time: 0.6313 [2021-03-28 15:54:38 swin_base_patch4_window7_224] INFO: Epoch: [284] [ 990/1251] eta: 0:02:46 lr: 0.000016 loss: 2.5106 (2.6588) grad_norm: 3.5560 (4.0026) time: 0.6305 [2021-03-28 15:54:44 swin_base_patch4_window7_224] INFO: Epoch: [284] [1000/1251] eta: 0:02:39 lr: 0.000016 loss: 2.7028 (2.6593) grad_norm: 3.3784 (3.9992) time: 0.6350 [2021-03-28 15:54:50 swin_base_patch4_window7_224] INFO: Epoch: [284] [1010/1251] eta: 0:02:33 lr: 0.000016 loss: 2.7596 (2.6601) grad_norm: 3.4147 (3.9959) time: 0.6329 [2021-03-28 15:54:57 swin_base_patch4_window7_224] INFO: Epoch: [284] [1020/1251] eta: 0:02:27 lr: 0.000016 loss: 2.7204 (2.6609) grad_norm: 3.3919 (4.0024) time: 0.6301 [2021-03-28 15:55:03 swin_base_patch4_window7_224] INFO: Epoch: [284] [1030/1251] eta: 0:02:20 lr: 0.000016 loss: 2.7271 (2.6594) grad_norm: 3.4844 (4.0012) time: 0.6264 [2021-03-28 15:55:09 swin_base_patch4_window7_224] INFO: Epoch: [284] [1040/1251] eta: 0:02:14 lr: 0.000016 loss: 2.3070 (2.6579) grad_norm: 3.6385 (3.9968) time: 0.6259 [2021-03-28 15:55:16 swin_base_patch4_window7_224] INFO: Epoch: [284] [1050/1251] eta: 0:02:08 lr: 0.000016 loss: 2.7122 (2.6583) grad_norm: 3.3144 (3.9940) time: 0.6295 [2021-03-28 15:55:22 swin_base_patch4_window7_224] INFO: Epoch: [284] [1060/1251] eta: 0:02:01 lr: 0.000016 loss: 2.7287 (2.6559) grad_norm: 3.3427 (3.9884) time: 0.6382 [2021-03-28 15:55:28 swin_base_patch4_window7_224] INFO: Epoch: [284] [1070/1251] eta: 0:01:55 lr: 0.000016 loss: 2.7287 (2.6557) grad_norm: 3.5294 (3.9942) time: 0.6389 [2021-03-28 15:55:35 swin_base_patch4_window7_224] INFO: Epoch: [284] [1080/1251] eta: 0:01:48 lr: 0.000016 loss: 2.7148 (2.6553) grad_norm: 3.9820 (3.9972) time: 0.6350 [2021-03-28 15:55:41 swin_base_patch4_window7_224] INFO: Epoch: [284] [1090/1251] eta: 0:01:42 lr: 0.000016 loss: 2.8485 (2.6569) grad_norm: 3.4372 (3.9932) time: 0.6338 [2021-03-28 15:55:47 swin_base_patch4_window7_224] INFO: Epoch: [284] [1100/1251] eta: 0:01:36 lr: 0.000016 loss: 2.9388 (2.6586) grad_norm: 3.5464 (3.9902) time: 0.6299 [2021-03-28 15:55:54 swin_base_patch4_window7_224] INFO: Epoch: [284] [1110/1251] eta: 0:01:29 lr: 0.000016 loss: 2.5943 (2.6579) grad_norm: 3.5246 (3.9866) time: 0.6260 [2021-03-28 15:56:00 swin_base_patch4_window7_224] INFO: Epoch: [284] [1120/1251] eta: 0:01:23 lr: 0.000016 loss: 2.7079 (2.6591) grad_norm: 3.4496 (3.9825) time: 0.6275 [2021-03-28 15:56:06 swin_base_patch4_window7_224] INFO: Epoch: [284] [1130/1251] eta: 0:01:17 lr: 0.000016 loss: 2.7497 (2.6585) grad_norm: 3.3590 (3.9781) time: 0.6288 [2021-03-28 15:56:13 swin_base_patch4_window7_224] INFO: Epoch: [284] [1140/1251] eta: 0:01:10 lr: 0.000016 loss: 2.6549 (2.6572) grad_norm: 3.1624 (3.9722) time: 0.6328 [2021-03-28 15:56:19 swin_base_patch4_window7_224] INFO: Epoch: [284] [1150/1251] eta: 0:01:04 lr: 0.000016 loss: 2.7003 (2.6569) grad_norm: 3.2055 (3.9707) time: 0.6317 [2021-03-28 15:56:25 swin_base_patch4_window7_224] INFO: Epoch: [284] [1160/1251] eta: 0:00:57 lr: 0.000016 loss: 2.6676 (2.6568) grad_norm: 3.6869 (3.9722) time: 0.6279 [2021-03-28 15:56:31 swin_base_patch4_window7_224] INFO: Epoch: [284] [1170/1251] eta: 0:00:51 lr: 0.000016 loss: 2.6462 (2.6563) grad_norm: 3.2687 (3.9672) time: 0.6327 [2021-03-28 15:56:38 swin_base_patch4_window7_224] INFO: Epoch: [284] [1180/1251] eta: 0:00:45 lr: 0.000016 loss: 2.5999 (2.6562) grad_norm: 3.4184 (3.9673) time: 0.6336 [2021-03-28 15:56:44 swin_base_patch4_window7_224] INFO: Epoch: [284] [1190/1251] eta: 0:00:38 lr: 0.000016 loss: 2.8919 (2.6580) grad_norm: 3.4495 (inf) time: 0.6259 [2021-03-28 15:56:50 swin_base_patch4_window7_224] INFO: Epoch: [284] [1200/1251] eta: 0:00:32 lr: 0.000016 loss: 2.7875 (2.6580) grad_norm: 3.3804 (inf) time: 0.6227 [2021-03-28 15:56:57 swin_base_patch4_window7_224] INFO: Epoch: [284] [1210/1251] eta: 0:00:26 lr: 0.000016 loss: 2.6703 (2.6575) grad_norm: 3.2561 (inf) time: 0.6264 [2021-03-28 15:57:03 swin_base_patch4_window7_224] INFO: Epoch: [284] [1220/1251] eta: 0:00:19 lr: 0.000016 loss: 2.7392 (2.6576) grad_norm: 3.1886 (inf) time: 0.6251 [2021-03-28 15:57:09 swin_base_patch4_window7_224] INFO: Epoch: [284] [1230/1251] eta: 0:00:13 lr: 0.000016 loss: 2.4745 (2.6557) grad_norm: 3.4647 (inf) time: 0.6226 [2021-03-28 15:57:15 swin_base_patch4_window7_224] INFO: Epoch: [284] [1240/1251] eta: 0:00:06 lr: 0.000016 loss: 2.3539 (2.6546) grad_norm: 3.4618 (inf) time: 0.6198 [2021-03-28 15:57:21 swin_base_patch4_window7_224] INFO: Epoch: [284] [1250/1251] eta: 0:00:00 lr: 0.000016 loss: 2.5957 (2.6539) grad_norm: 3.1784 (inf) time: 0.6142 [2021-03-28 15:57:33 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:46 loss: 0.6592 (0.6592) acc1: 84.3750 (84.3750) acc5: 98.4375 (98.4375) [2021-03-28 15:57:35 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.6792 (0.7140) acc1: 84.3750 (83.8068) acc5: 98.4375 (97.4432) [2021-03-28 15:57:38 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7094 (0.7211) acc1: 82.8125 (82.8869) acc5: 96.8750 (97.0238) [2021-03-28 15:57:41 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7142 (0.7330) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8246) [2021-03-28 15:57:43 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7142 (0.7272) acc1: 82.8125 (82.5838) acc5: 96.8750 (96.9131) [2021-03-28 15:57:44 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7632 (0.7550) acc1: 79.6875 (82.2400) acc5: 96.8750 (96.4160) [2021-03-28 15:57:57 swin_base_patch4_window7_224] INFO: * Acc@1 83.360 Acc@5 96.380 loss 0.742 [2021-03-28 15:57:57 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 15:57:57 swin_base_patch4_window7_224] INFO: Max accuracy: 83.39% [2021-03-28 15:58:02 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 0/1251] eta: 1:32:25 lr: 0.000016 loss: 2.5203 (2.5203) grad_norm: 5.1104 (5.1104) time: 4.4327 [2021-03-28 15:58:08 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 10/1251] eta: 0:20:06 lr: 0.000016 loss: 2.7230 (2.6365) grad_norm: 3.3343 (3.5045) time: 0.9718 [2021-03-28 15:58:14 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 20/1251] eta: 0:16:43 lr: 0.000016 loss: 2.6246 (2.5962) grad_norm: 3.1176 (3.4389) time: 0.6340 [2021-03-28 15:58:21 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 30/1251] eta: 0:15:22 lr: 0.000016 loss: 2.7542 (2.6380) grad_norm: 3.2652 (3.4764) time: 0.6371 [2021-03-28 15:58:27 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 40/1251] eta: 0:14:41 lr: 0.000016 loss: 2.8068 (2.6810) grad_norm: 3.4658 (3.4983) time: 0.6365 [2021-03-28 15:58:34 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 50/1251] eta: 0:14:13 lr: 0.000016 loss: 2.6992 (2.6781) grad_norm: 3.4658 (3.6170) time: 0.6413 [2021-03-28 15:58:40 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 60/1251] eta: 0:13:51 lr: 0.000016 loss: 2.6753 (2.6806) grad_norm: 3.5495 (3.6183) time: 0.6383 [2021-03-28 15:58:46 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 70/1251] eta: 0:13:32 lr: 0.000016 loss: 2.6002 (2.6595) grad_norm: 3.4946 (3.6371) time: 0.6308 [2021-03-28 15:58:53 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 80/1251] eta: 0:13:18 lr: 0.000016 loss: 2.6465 (2.6561) grad_norm: 3.3788 (3.6433) time: 0.6316 [2021-03-28 15:58:59 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 90/1251] eta: 0:13:05 lr: 0.000016 loss: 2.7290 (2.6500) grad_norm: 3.3819 (3.6751) time: 0.6330 [2021-03-28 15:59:05 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 100/1251] eta: 0:12:54 lr: 0.000016 loss: 2.7290 (2.6533) grad_norm: 3.4635 (3.8084) time: 0.6340 [2021-03-28 15:59:12 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 110/1251] eta: 0:12:42 lr: 0.000016 loss: 2.7742 (2.6602) grad_norm: 3.4635 (3.8164) time: 0.6339 [2021-03-28 15:59:18 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 120/1251] eta: 0:12:34 lr: 0.000016 loss: 2.7604 (2.6627) grad_norm: 3.4652 (3.7923) time: 0.6387 [2021-03-28 15:59:24 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 130/1251] eta: 0:12:24 lr: 0.000016 loss: 2.7829 (2.6720) grad_norm: 3.3768 (3.7960) time: 0.6384 [2021-03-28 15:59:31 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 140/1251] eta: 0:12:14 lr: 0.000016 loss: 2.7865 (2.6632) grad_norm: 3.4158 (3.7731) time: 0.6287 [2021-03-28 15:59:37 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 150/1251] eta: 0:12:05 lr: 0.000016 loss: 2.5493 (2.6510) grad_norm: 3.5621 (3.7787) time: 0.6267 [2021-03-28 15:59:43 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 160/1251] eta: 0:11:56 lr: 0.000016 loss: 2.6396 (2.6558) grad_norm: 3.5614 (3.7562) time: 0.6263 [2021-03-28 15:59:49 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 170/1251] eta: 0:11:48 lr: 0.000016 loss: 2.8610 (2.6657) grad_norm: 3.5203 (3.7753) time: 0.6299 [2021-03-28 15:59:56 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 180/1251] eta: 0:11:40 lr: 0.000016 loss: 2.5804 (2.6469) grad_norm: 3.8408 (3.7852) time: 0.6310 [2021-03-28 16:00:02 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 190/1251] eta: 0:11:33 lr: 0.000016 loss: 2.4248 (2.6430) grad_norm: 3.4009 (3.7865) time: 0.6368 [2021-03-28 16:00:09 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 200/1251] eta: 0:11:26 lr: 0.000016 loss: 2.4586 (2.6313) grad_norm: 3.2672 (3.7595) time: 0.6417 [2021-03-28 16:00:15 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 210/1251] eta: 0:11:18 lr: 0.000016 loss: 2.5455 (2.6350) grad_norm: 3.2400 (3.7414) time: 0.6325 [2021-03-28 16:00:21 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 220/1251] eta: 0:11:11 lr: 0.000016 loss: 2.7484 (2.6275) grad_norm: 3.5426 (3.7285) time: 0.6337 [2021-03-28 16:00:28 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 230/1251] eta: 0:11:04 lr: 0.000016 loss: 2.7585 (2.6407) grad_norm: 3.5565 (3.7304) time: 0.6424 [2021-03-28 16:00:34 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 240/1251] eta: 0:10:57 lr: 0.000016 loss: 2.9240 (2.6477) grad_norm: 3.4390 (3.7129) time: 0.6360 [2021-03-28 16:00:40 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 250/1251] eta: 0:10:50 lr: 0.000016 loss: 2.5911 (2.6353) grad_norm: 3.3104 (3.6987) time: 0.6331 [2021-03-28 16:00:47 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 260/1251] eta: 0:10:42 lr: 0.000016 loss: 2.3762 (2.6358) grad_norm: 3.3104 (3.6917) time: 0.6349 [2021-03-28 16:00:53 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 270/1251] eta: 0:10:35 lr: 0.000016 loss: 2.7922 (2.6365) grad_norm: 3.5100 (3.7038) time: 0.6316 [2021-03-28 16:00:59 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 280/1251] eta: 0:10:28 lr: 0.000016 loss: 2.8665 (2.6415) grad_norm: 3.7084 (3.7104) time: 0.6298 [2021-03-28 16:01:06 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 290/1251] eta: 0:10:21 lr: 0.000016 loss: 2.6518 (2.6346) grad_norm: 3.5492 (3.7117) time: 0.6263 [2021-03-28 16:01:12 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 300/1251] eta: 0:10:14 lr: 0.000016 loss: 2.6333 (2.6390) grad_norm: 3.5146 (3.7094) time: 0.6267 [2021-03-28 16:01:18 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 310/1251] eta: 0:10:07 lr: 0.000016 loss: 2.7356 (2.6392) grad_norm: 3.7846 (3.7240) time: 0.6297 [2021-03-28 16:01:24 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 320/1251] eta: 0:10:00 lr: 0.000016 loss: 2.7356 (2.6421) grad_norm: 3.7846 (3.7176) time: 0.6298 [2021-03-28 16:01:31 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 330/1251] eta: 0:09:53 lr: 0.000016 loss: 2.8379 (2.6474) grad_norm: 3.4999 (3.7198) time: 0.6331 [2021-03-28 16:01:37 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 340/1251] eta: 0:09:46 lr: 0.000016 loss: 2.8304 (2.6500) grad_norm: 3.3822 (3.7240) time: 0.6322 [2021-03-28 16:01:43 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 350/1251] eta: 0:09:40 lr: 0.000016 loss: 2.7350 (2.6566) grad_norm: 3.4712 (3.7249) time: 0.6274 [2021-03-28 16:01:50 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 360/1251] eta: 0:09:33 lr: 0.000016 loss: 2.7469 (2.6559) grad_norm: 3.5606 (3.7274) time: 0.6260 [2021-03-28 16:01:56 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 370/1251] eta: 0:09:26 lr: 0.000016 loss: 2.7312 (2.6560) grad_norm: 3.4949 (3.7284) time: 0.6283 [2021-03-28 16:02:02 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 380/1251] eta: 0:09:19 lr: 0.000016 loss: 2.8073 (2.6614) grad_norm: 3.3182 (3.7179) time: 0.6314 [2021-03-28 16:02:09 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 390/1251] eta: 0:09:13 lr: 0.000016 loss: 2.9029 (2.6598) grad_norm: 3.2122 (3.7105) time: 0.6340 [2021-03-28 16:02:15 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 400/1251] eta: 0:09:06 lr: 0.000016 loss: 2.7228 (2.6539) grad_norm: 3.1966 (3.7224) time: 0.6368 [2021-03-28 16:02:21 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 410/1251] eta: 0:08:59 lr: 0.000016 loss: 2.5352 (2.6475) grad_norm: 3.2321 (3.7186) time: 0.6322 [2021-03-28 16:02:28 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 420/1251] eta: 0:08:53 lr: 0.000016 loss: 2.6284 (2.6503) grad_norm: 3.4056 (3.7208) time: 0.6327 [2021-03-28 16:02:34 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 430/1251] eta: 0:08:46 lr: 0.000016 loss: 2.7234 (2.6476) grad_norm: 3.7028 (3.7235) time: 0.6392 [2021-03-28 16:02:40 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 440/1251] eta: 0:08:40 lr: 0.000016 loss: 2.5669 (2.6442) grad_norm: 3.4551 (3.7140) time: 0.6405 [2021-03-28 16:02:47 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 450/1251] eta: 0:08:33 lr: 0.000016 loss: 2.6827 (2.6466) grad_norm: 3.2634 (3.7088) time: 0.6376 [2021-03-28 16:02:53 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 460/1251] eta: 0:08:27 lr: 0.000016 loss: 2.6872 (2.6450) grad_norm: 3.3374 (3.7136) time: 0.6332 [2021-03-28 16:02:59 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 470/1251] eta: 0:08:20 lr: 0.000016 loss: 2.6626 (2.6430) grad_norm: 3.3371 (3.7094) time: 0.6313 [2021-03-28 16:03:06 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 480/1251] eta: 0:08:14 lr: 0.000016 loss: 2.5302 (2.6398) grad_norm: 3.4544 (3.7165) time: 0.6344 [2021-03-28 16:03:12 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 490/1251] eta: 0:08:07 lr: 0.000016 loss: 2.5534 (2.6390) grad_norm: 3.4797 (3.7359) time: 0.6349 [2021-03-28 16:03:19 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 500/1251] eta: 0:08:01 lr: 0.000016 loss: 2.5862 (2.6379) grad_norm: 3.4797 (3.7338) time: 0.6355 [2021-03-28 16:03:25 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 510/1251] eta: 0:07:54 lr: 0.000016 loss: 2.6471 (2.6396) grad_norm: 3.5271 (3.7518) time: 0.6408 [2021-03-28 16:03:31 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 520/1251] eta: 0:07:48 lr: 0.000016 loss: 2.6471 (2.6365) grad_norm: 3.7887 (3.7567) time: 0.6419 [2021-03-28 16:03:38 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 530/1251] eta: 0:07:42 lr: 0.000016 loss: 2.7448 (2.6406) grad_norm: 3.6526 (3.7534) time: 0.6407 [2021-03-28 16:03:44 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 540/1251] eta: 0:07:35 lr: 0.000016 loss: 2.7645 (2.6417) grad_norm: 3.4738 (3.7481) time: 0.6403 [2021-03-28 16:03:51 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 550/1251] eta: 0:07:29 lr: 0.000016 loss: 2.7146 (2.6428) grad_norm: 3.4016 (3.7421) time: 0.6443 [2021-03-28 16:03:57 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 560/1251] eta: 0:07:22 lr: 0.000016 loss: 2.6742 (2.6447) grad_norm: 3.3331 (3.7413) time: 0.6417 [2021-03-28 16:04:03 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 570/1251] eta: 0:07:16 lr: 0.000016 loss: 2.6773 (2.6431) grad_norm: 3.4061 (3.7378) time: 0.6363 [2021-03-28 16:04:10 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 580/1251] eta: 0:07:10 lr: 0.000016 loss: 2.6773 (2.6419) grad_norm: 3.4307 (3.7329) time: 0.6379 [2021-03-28 16:04:16 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 590/1251] eta: 0:07:03 lr: 0.000016 loss: 2.4899 (2.6383) grad_norm: 3.2599 (3.7323) time: 0.6389 [2021-03-28 16:04:23 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 600/1251] eta: 0:06:57 lr: 0.000016 loss: 2.4798 (2.6387) grad_norm: 3.2664 (3.7270) time: 0.6411 [2021-03-28 16:04:29 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 610/1251] eta: 0:06:50 lr: 0.000016 loss: 2.6065 (2.6377) grad_norm: 3.3458 (3.7251) time: 0.6362 [2021-03-28 16:04:35 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 620/1251] eta: 0:06:44 lr: 0.000016 loss: 2.7874 (2.6385) grad_norm: 3.4792 (3.7275) time: 0.6304 [2021-03-28 16:04:42 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 630/1251] eta: 0:06:37 lr: 0.000016 loss: 2.8108 (2.6388) grad_norm: 3.4572 (3.7228) time: 0.6330 [2021-03-28 16:04:48 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 640/1251] eta: 0:06:31 lr: 0.000016 loss: 2.7770 (2.6392) grad_norm: 3.3738 (3.7197) time: 0.6300 [2021-03-28 16:04:54 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 650/1251] eta: 0:06:24 lr: 0.000016 loss: 2.6164 (2.6372) grad_norm: 3.5466 (3.7173) time: 0.6277 [2021-03-28 16:05:00 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 660/1251] eta: 0:06:18 lr: 0.000016 loss: 2.4496 (2.6367) grad_norm: 3.5270 (3.7213) time: 0.6332 [2021-03-28 16:05:07 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 670/1251] eta: 0:06:11 lr: 0.000016 loss: 2.7676 (2.6389) grad_norm: 3.5144 (3.7174) time: 0.6308 [2021-03-28 16:05:13 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 680/1251] eta: 0:06:05 lr: 0.000016 loss: 2.7998 (2.6390) grad_norm: 3.6351 (3.7236) time: 0.6274 [2021-03-28 16:05:19 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 690/1251] eta: 0:05:58 lr: 0.000016 loss: 2.7998 (2.6390) grad_norm: 3.6351 (3.7230) time: 0.6312 [2021-03-28 16:05:26 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 700/1251] eta: 0:05:52 lr: 0.000016 loss: 2.8006 (2.6395) grad_norm: 3.3548 (3.7229) time: 0.6369 [2021-03-28 16:05:32 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 710/1251] eta: 0:05:45 lr: 0.000016 loss: 2.8206 (2.6435) grad_norm: 3.5554 (3.7273) time: 0.6386 [2021-03-28 16:05:38 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 720/1251] eta: 0:05:39 lr: 0.000016 loss: 2.8489 (2.6434) grad_norm: 3.5465 (3.7239) time: 0.6322 [2021-03-28 16:05:45 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 730/1251] eta: 0:05:33 lr: 0.000016 loss: 2.7885 (2.6449) grad_norm: 3.3478 (3.7245) time: 0.6304 [2021-03-28 16:05:51 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 740/1251] eta: 0:05:26 lr: 0.000016 loss: 2.7112 (2.6444) grad_norm: 3.4652 (3.7270) time: 0.6381 [2021-03-28 16:05:58 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 750/1251] eta: 0:05:20 lr: 0.000016 loss: 2.7256 (2.6461) grad_norm: 3.5170 (3.7230) time: 0.6376 [2021-03-28 16:06:04 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 760/1251] eta: 0:05:13 lr: 0.000016 loss: 2.8218 (2.6462) grad_norm: 3.4023 (3.7235) time: 0.6283 [2021-03-28 16:06:10 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 770/1251] eta: 0:05:07 lr: 0.000016 loss: 2.8313 (2.6477) grad_norm: 3.4515 (3.7260) time: 0.6370 [2021-03-28 16:06:17 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 780/1251] eta: 0:05:01 lr: 0.000016 loss: 2.9248 (2.6515) grad_norm: 3.4209 (3.7306) time: 0.6419 [2021-03-28 16:06:23 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 790/1251] eta: 0:04:54 lr: 0.000016 loss: 2.9311 (2.6509) grad_norm: 3.4452 (3.7334) time: 0.6341 [2021-03-28 16:06:29 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 800/1251] eta: 0:04:48 lr: 0.000016 loss: 2.9311 (2.6532) grad_norm: 3.6840 (3.7332) time: 0.6317 [2021-03-28 16:06:36 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 810/1251] eta: 0:04:41 lr: 0.000016 loss: 2.8116 (2.6515) grad_norm: 3.4295 (3.7326) time: 0.6286 [2021-03-28 16:06:42 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 820/1251] eta: 0:04:35 lr: 0.000016 loss: 2.7566 (2.6544) grad_norm: 3.3010 (3.7273) time: 0.6289 [2021-03-28 16:06:48 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 830/1251] eta: 0:04:28 lr: 0.000016 loss: 2.8475 (2.6546) grad_norm: 3.2552 (3.7238) time: 0.6392 [2021-03-28 16:06:55 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 840/1251] eta: 0:04:22 lr: 0.000016 loss: 2.7018 (2.6531) grad_norm: 3.5459 (3.7235) time: 0.6439 [2021-03-28 16:07:01 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 850/1251] eta: 0:04:16 lr: 0.000016 loss: 2.5495 (2.6530) grad_norm: 3.5459 (3.7266) time: 0.6368 [2021-03-28 16:07:07 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 860/1251] eta: 0:04:09 lr: 0.000016 loss: 2.7756 (2.6524) grad_norm: 3.3278 (3.7304) time: 0.6328 [2021-03-28 16:07:14 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 870/1251] eta: 0:04:03 lr: 0.000016 loss: 2.6056 (2.6519) grad_norm: 3.3784 (3.7330) time: 0.6369 [2021-03-28 16:07:20 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 880/1251] eta: 0:03:56 lr: 0.000016 loss: 2.7024 (2.6517) grad_norm: 3.4669 (3.7379) time: 0.6426 [2021-03-28 16:07:26 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 890/1251] eta: 0:03:50 lr: 0.000016 loss: 2.6789 (2.6501) grad_norm: 3.8114 (3.7394) time: 0.6350 [2021-03-28 16:07:33 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 900/1251] eta: 0:03:44 lr: 0.000016 loss: 2.6347 (2.6491) grad_norm: 3.8196 (3.7412) time: 0.6251 [2021-03-28 16:07:39 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 910/1251] eta: 0:03:37 lr: 0.000016 loss: 2.7010 (2.6504) grad_norm: 3.3652 (3.7357) time: 0.6280 [2021-03-28 16:07:45 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 920/1251] eta: 0:03:31 lr: 0.000016 loss: 2.8466 (2.6530) grad_norm: 3.3412 (3.7353) time: 0.6305 [2021-03-28 16:07:52 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 930/1251] eta: 0:03:24 lr: 0.000016 loss: 2.7148 (2.6528) grad_norm: 3.6752 (3.7393) time: 0.6352 [2021-03-28 16:07:58 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 940/1251] eta: 0:03:18 lr: 0.000016 loss: 2.6696 (2.6521) grad_norm: 3.5673 (3.7441) time: 0.6321 [2021-03-28 16:08:04 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 950/1251] eta: 0:03:12 lr: 0.000015 loss: 2.6299 (2.6510) grad_norm: 3.5872 (3.7475) time: 0.6245 [2021-03-28 16:08:11 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 960/1251] eta: 0:03:05 lr: 0.000015 loss: 2.5113 (2.6507) grad_norm: 3.5872 (3.7480) time: 0.6338 [2021-03-28 16:08:17 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 970/1251] eta: 0:02:59 lr: 0.000015 loss: 2.7580 (2.6511) grad_norm: 3.4440 (3.7495) time: 0.6434 [2021-03-28 16:08:23 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 980/1251] eta: 0:02:52 lr: 0.000015 loss: 2.7138 (2.6506) grad_norm: 3.6130 (3.7526) time: 0.6414 [2021-03-28 16:08:30 swin_base_patch4_window7_224] INFO: Epoch: [285] [ 990/1251] eta: 0:02:46 lr: 0.000015 loss: 2.7874 (2.6536) grad_norm: 3.6240 (3.7538) time: 0.6406 [2021-03-28 16:08:36 swin_base_patch4_window7_224] INFO: Epoch: [285] [1000/1251] eta: 0:02:40 lr: 0.000015 loss: 2.9100 (2.6539) grad_norm: 3.8401 (3.7570) time: 0.6448 [2021-03-28 16:08:43 swin_base_patch4_window7_224] INFO: Epoch: [285] [1010/1251] eta: 0:02:33 lr: 0.000015 loss: 2.7152 (2.6537) grad_norm: 3.3598 (3.7637) time: 0.6402 [2021-03-28 16:08:49 swin_base_patch4_window7_224] INFO: Epoch: [285] [1020/1251] eta: 0:02:27 lr: 0.000015 loss: 2.8377 (2.6543) grad_norm: 3.3472 (3.7655) time: 0.6379 [2021-03-28 16:08:55 swin_base_patch4_window7_224] INFO: Epoch: [285] [1030/1251] eta: 0:02:21 lr: 0.000015 loss: 2.8494 (2.6560) grad_norm: 3.3692 (3.7676) time: 0.6372 [2021-03-28 16:09:02 swin_base_patch4_window7_224] INFO: Epoch: [285] [1040/1251] eta: 0:02:14 lr: 0.000015 loss: 2.7616 (2.6560) grad_norm: 3.3742 (3.7690) time: 0.6312 [2021-03-28 16:09:08 swin_base_patch4_window7_224] INFO: Epoch: [285] [1050/1251] eta: 0:02:08 lr: 0.000015 loss: 2.7165 (2.6570) grad_norm: 3.6937 (3.7729) time: 0.6282 [2021-03-28 16:09:14 swin_base_patch4_window7_224] INFO: Epoch: [285] [1060/1251] eta: 0:02:01 lr: 0.000015 loss: 2.6672 (2.6565) grad_norm: 3.6510 (3.7744) time: 0.6263 [2021-03-28 16:09:21 swin_base_patch4_window7_224] INFO: Epoch: [285] [1070/1251] eta: 0:01:55 lr: 0.000015 loss: 2.8219 (2.6593) grad_norm: 3.5611 (3.7834) time: 0.6248 [2021-03-28 16:09:27 swin_base_patch4_window7_224] INFO: Epoch: [285] [1080/1251] eta: 0:01:49 lr: 0.000015 loss: 2.8584 (2.6595) grad_norm: 3.5080 (3.7852) time: 0.6276 [2021-03-28 16:09:33 swin_base_patch4_window7_224] INFO: Epoch: [285] [1090/1251] eta: 0:01:42 lr: 0.000015 loss: 2.8213 (2.6600) grad_norm: 3.5259 (3.7838) time: 0.6348 [2021-03-28 16:09:39 swin_base_patch4_window7_224] INFO: Epoch: [285] [1100/1251] eta: 0:01:36 lr: 0.000015 loss: 2.7514 (2.6595) grad_norm: 3.8745 (3.7872) time: 0.6317 [2021-03-28 16:09:46 swin_base_patch4_window7_224] INFO: Epoch: [285] [1110/1251] eta: 0:01:29 lr: 0.000015 loss: 2.7055 (2.6589) grad_norm: 3.8745 (3.7855) time: 0.6286 [2021-03-28 16:09:52 swin_base_patch4_window7_224] INFO: Epoch: [285] [1120/1251] eta: 0:01:23 lr: 0.000015 loss: 2.6749 (2.6570) grad_norm: 3.3835 (3.7841) time: 0.6336 [2021-03-28 16:09:59 swin_base_patch4_window7_224] INFO: Epoch: [285] [1130/1251] eta: 0:01:17 lr: 0.000015 loss: 2.5097 (2.6567) grad_norm: 3.2513 (3.7807) time: 0.6336 [2021-03-28 16:10:05 swin_base_patch4_window7_224] INFO: Epoch: [285] [1140/1251] eta: 0:01:10 lr: 0.000015 loss: 2.6458 (2.6567) grad_norm: 3.2859 (3.7800) time: 0.6330 [2021-03-28 16:10:11 swin_base_patch4_window7_224] INFO: Epoch: [285] [1150/1251] eta: 0:01:04 lr: 0.000015 loss: 2.6458 (2.6563) grad_norm: 3.5594 (3.7794) time: 0.6349 [2021-03-28 16:10:18 swin_base_patch4_window7_224] INFO: Epoch: [285] [1160/1251] eta: 0:00:58 lr: 0.000015 loss: 2.7065 (2.6569) grad_norm: 3.5441 (3.7793) time: 0.6380 [2021-03-28 16:10:24 swin_base_patch4_window7_224] INFO: Epoch: [285] [1170/1251] eta: 0:00:51 lr: 0.000015 loss: 2.7913 (2.6574) grad_norm: 3.5441 (3.7794) time: 0.6306 [2021-03-28 16:10:30 swin_base_patch4_window7_224] INFO: Epoch: [285] [1180/1251] eta: 0:00:45 lr: 0.000015 loss: 2.7343 (2.6576) grad_norm: 3.7093 (3.7762) time: 0.6300 [2021-03-28 16:10:37 swin_base_patch4_window7_224] INFO: Epoch: [285] [1190/1251] eta: 0:00:38 lr: 0.000015 loss: 2.7277 (2.6576) grad_norm: 3.7443 (3.7739) time: 0.6385 [2021-03-28 16:10:43 swin_base_patch4_window7_224] INFO: Epoch: [285] [1200/1251] eta: 0:00:32 lr: 0.000015 loss: 2.7211 (2.6571) grad_norm: 3.8569 (3.7839) time: 0.6370 [2021-03-28 16:10:49 swin_base_patch4_window7_224] INFO: Epoch: [285] [1210/1251] eta: 0:00:26 lr: 0.000015 loss: 2.8099 (2.6587) grad_norm: 3.7672 (3.7825) time: 0.6311 [2021-03-28 16:10:56 swin_base_patch4_window7_224] INFO: Epoch: [285] [1220/1251] eta: 0:00:19 lr: 0.000015 loss: 2.7375 (2.6582) grad_norm: 3.6733 (3.7833) time: 0.6310 [2021-03-28 16:11:02 swin_base_patch4_window7_224] INFO: Epoch: [285] [1230/1251] eta: 0:00:13 lr: 0.000015 loss: 2.5554 (2.6577) grad_norm: 3.7657 (3.7890) time: 0.6322 [2021-03-28 16:11:08 swin_base_patch4_window7_224] INFO: Epoch: [285] [1240/1251] eta: 0:00:07 lr: 0.000015 loss: 2.5374 (2.6564) grad_norm: 3.8918 (3.8322) time: 0.6339 [2021-03-28 16:11:14 swin_base_patch4_window7_224] INFO: Epoch: [285] [1250/1251] eta: 0:00:00 lr: 0.000015 loss: 2.7842 (2.6581) grad_norm: 3.6332 (3.8303) time: 0.6291 [2021-03-28 16:12:34 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.7187 (0.7187) acc1: 82.8125 (82.8125) acc5: 98.4375 (98.4375) [2021-03-28 16:12:35 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7187 (0.7456) acc1: 82.8125 (82.3864) acc5: 96.8750 (96.7330) [2021-03-28 16:12:36 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7201 (0.7807) acc1: 79.6875 (81.3988) acc5: 96.8750 (96.5030) [2021-03-28 16:12:38 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7182 (0.7538) acc1: 79.6875 (81.8044) acc5: 96.8750 (96.8246) [2021-03-28 16:12:39 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7147 (0.7420) acc1: 82.8125 (82.2790) acc5: 96.8750 (96.7226) [2021-03-28 16:12:40 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7683 (0.7508) acc1: 82.8125 (82.4000) acc5: 96.8750 (96.5440) [2021-03-28 16:12:50 swin_base_patch4_window7_224] INFO: * Acc@1 83.320 Acc@5 96.484 loss 0.737 [2021-03-28 16:12:50 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.3% [2021-03-28 16:12:50 swin_base_patch4_window7_224] INFO: Max accuracy: 83.39% [2021-03-28 16:12:55 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 0/1251] eta: 1:27:47 lr: 0.000015 loss: 2.9086 (2.9086) grad_norm: 3.9305 (3.9305) time: 4.2103 [2021-03-28 16:13:01 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 10/1251] eta: 0:19:55 lr: 0.000015 loss: 2.9086 (2.6108) grad_norm: 3.4927 (3.5142) time: 0.9634 [2021-03-28 16:13:07 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 20/1251] eta: 0:16:36 lr: 0.000015 loss: 2.8209 (2.6987) grad_norm: 3.4826 (3.6203) time: 0.6394 [2021-03-28 16:13:14 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 30/1251] eta: 0:15:20 lr: 0.000015 loss: 2.7389 (2.6573) grad_norm: 3.4056 (3.6437) time: 0.6385 [2021-03-28 16:13:20 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 40/1251] eta: 0:14:39 lr: 0.000015 loss: 2.6100 (2.6591) grad_norm: 3.3360 (3.6753) time: 0.6391 [2021-03-28 16:13:27 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 50/1251] eta: 0:14:09 lr: 0.000015 loss: 2.7235 (2.6640) grad_norm: 3.8222 (3.7972) time: 0.6343 [2021-03-28 16:13:33 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 60/1251] eta: 0:13:46 lr: 0.000015 loss: 2.7669 (2.6701) grad_norm: 4.0242 (3.8045) time: 0.6279 [2021-03-28 16:13:39 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 70/1251] eta: 0:13:31 lr: 0.000015 loss: 2.7246 (2.6516) grad_norm: 3.2830 (3.8316) time: 0.6361 [2021-03-28 16:13:46 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 80/1251] eta: 0:13:17 lr: 0.000015 loss: 2.6619 (2.6484) grad_norm: 3.4146 (3.8063) time: 0.6420 [2021-03-28 16:13:52 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 90/1251] eta: 0:13:04 lr: 0.000015 loss: 2.7366 (2.6693) grad_norm: 3.4809 (3.7612) time: 0.6353 [2021-03-28 16:13:58 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 100/1251] eta: 0:12:51 lr: 0.000015 loss: 2.7348 (2.6619) grad_norm: 3.3021 (3.7715) time: 0.6263 [2021-03-28 16:14:05 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 110/1251] eta: 0:12:41 lr: 0.000015 loss: 2.6190 (2.6544) grad_norm: 3.3021 (3.7837) time: 0.6294 [2021-03-28 16:14:11 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 120/1251] eta: 0:12:32 lr: 0.000015 loss: 2.6190 (2.6479) grad_norm: 3.4045 (3.7622) time: 0.6393 [2021-03-28 16:14:17 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 130/1251] eta: 0:12:22 lr: 0.000015 loss: 2.7520 (2.6583) grad_norm: 3.4240 (3.7776) time: 0.6350 [2021-03-28 16:14:24 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 140/1251] eta: 0:12:13 lr: 0.000015 loss: 2.8708 (2.6742) grad_norm: 3.8054 (3.8695) time: 0.6294 [2021-03-28 16:14:30 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 150/1251] eta: 0:12:05 lr: 0.000015 loss: 2.8782 (2.6749) grad_norm: 3.7390 (4.1813) time: 0.6334 [2021-03-28 16:14:36 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 160/1251] eta: 0:11:56 lr: 0.000015 loss: 2.8062 (2.6704) grad_norm: 3.6312 (4.1864) time: 0.6326 [2021-03-28 16:14:43 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 170/1251] eta: 0:11:48 lr: 0.000015 loss: 2.6729 (2.6693) grad_norm: 3.6312 (4.1610) time: 0.6325 [2021-03-28 16:14:49 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 180/1251] eta: 0:11:40 lr: 0.000015 loss: 2.6768 (2.6667) grad_norm: 3.4666 (4.1329) time: 0.6320 [2021-03-28 16:14:55 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 190/1251] eta: 0:11:33 lr: 0.000015 loss: 2.7703 (2.6685) grad_norm: 3.6030 (4.1546) time: 0.6335 [2021-03-28 16:15:02 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 200/1251] eta: 0:11:26 lr: 0.000015 loss: 2.7742 (2.6682) grad_norm: 3.6104 (4.1266) time: 0.6413 [2021-03-28 16:15:08 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 210/1251] eta: 0:11:18 lr: 0.000015 loss: 2.6465 (2.6633) grad_norm: 3.5751 (4.1430) time: 0.6383 [2021-03-28 16:15:14 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 220/1251] eta: 0:11:11 lr: 0.000015 loss: 2.7755 (2.6668) grad_norm: 3.4440 (4.1333) time: 0.6335 [2021-03-28 16:15:21 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 230/1251] eta: 0:11:03 lr: 0.000015 loss: 2.8178 (2.6679) grad_norm: 3.5484 (4.1366) time: 0.6299 [2021-03-28 16:15:27 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 240/1251] eta: 0:10:56 lr: 0.000015 loss: 2.7227 (2.6689) grad_norm: 3.6826 (4.1410) time: 0.6327 [2021-03-28 16:15:33 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 250/1251] eta: 0:10:49 lr: 0.000015 loss: 2.7520 (2.6722) grad_norm: 3.7193 (4.1287) time: 0.6366 [2021-03-28 16:15:40 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 260/1251] eta: 0:10:42 lr: 0.000015 loss: 2.7520 (2.6722) grad_norm: 3.7163 (4.1327) time: 0.6304 [2021-03-28 16:15:46 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 270/1251] eta: 0:10:34 lr: 0.000015 loss: 2.6774 (2.6707) grad_norm: 3.4918 (4.1134) time: 0.6256 [2021-03-28 16:15:52 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 280/1251] eta: 0:10:27 lr: 0.000015 loss: 2.5765 (2.6618) grad_norm: 3.4207 (4.0910) time: 0.6273 [2021-03-28 16:15:59 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 290/1251] eta: 0:10:20 lr: 0.000015 loss: 2.5765 (2.6587) grad_norm: 3.4674 (4.0746) time: 0.6336 [2021-03-28 16:16:05 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 300/1251] eta: 0:10:13 lr: 0.000015 loss: 2.7741 (2.6681) grad_norm: 3.5799 (4.0536) time: 0.6314 [2021-03-28 16:16:11 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 310/1251] eta: 0:10:07 lr: 0.000015 loss: 2.8663 (2.6664) grad_norm: 3.1656 (4.0274) time: 0.6328 [2021-03-28 16:16:17 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 320/1251] eta: 0:10:00 lr: 0.000015 loss: 2.6039 (2.6615) grad_norm: 3.1702 (4.0102) time: 0.6349 [2021-03-28 16:16:24 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 330/1251] eta: 0:09:53 lr: 0.000015 loss: 2.6039 (2.6589) grad_norm: 3.4225 (4.0070) time: 0.6305 [2021-03-28 16:16:30 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 340/1251] eta: 0:09:46 lr: 0.000015 loss: 2.5618 (2.6527) grad_norm: 3.6933 (4.0009) time: 0.6285 [2021-03-28 16:16:36 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 350/1251] eta: 0:09:39 lr: 0.000015 loss: 2.4807 (2.6477) grad_norm: 3.5205 (3.9933) time: 0.6250 [2021-03-28 16:16:43 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 360/1251] eta: 0:09:32 lr: 0.000015 loss: 2.6254 (2.6508) grad_norm: 3.4433 (3.9869) time: 0.6227 [2021-03-28 16:16:49 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 370/1251] eta: 0:09:25 lr: 0.000015 loss: 2.6801 (2.6483) grad_norm: 3.3533 (3.9824) time: 0.6246 [2021-03-28 16:16:55 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 380/1251] eta: 0:09:19 lr: 0.000015 loss: 2.6276 (2.6462) grad_norm: 3.4609 (3.9725) time: 0.6297 [2021-03-28 16:17:01 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 390/1251] eta: 0:09:12 lr: 0.000015 loss: 2.7303 (2.6488) grad_norm: 3.4609 (3.9717) time: 0.6335 [2021-03-28 16:17:08 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 400/1251] eta: 0:09:05 lr: 0.000015 loss: 2.7832 (2.6484) grad_norm: 3.3918 (3.9703) time: 0.6296 [2021-03-28 16:17:14 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 410/1251] eta: 0:08:59 lr: 0.000015 loss: 2.7889 (2.6516) grad_norm: 3.3375 (3.9558) time: 0.6281 [2021-03-28 16:17:20 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 420/1251] eta: 0:08:52 lr: 0.000015 loss: 2.8202 (2.6531) grad_norm: 3.6926 (3.9556) time: 0.6262 [2021-03-28 16:17:27 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 430/1251] eta: 0:08:45 lr: 0.000015 loss: 2.6481 (2.6496) grad_norm: 3.8189 (3.9483) time: 0.6265 [2021-03-28 16:17:33 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 440/1251] eta: 0:08:39 lr: 0.000015 loss: 2.7137 (2.6529) grad_norm: 3.5311 (3.9410) time: 0.6346 [2021-03-28 16:17:39 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 450/1251] eta: 0:08:32 lr: 0.000015 loss: 2.7038 (2.6479) grad_norm: 3.5062 (3.9383) time: 0.6322 [2021-03-28 16:17:45 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 460/1251] eta: 0:08:26 lr: 0.000015 loss: 2.6940 (2.6496) grad_norm: 3.5062 (3.9391) time: 0.6274 [2021-03-28 16:17:52 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 470/1251] eta: 0:08:19 lr: 0.000015 loss: 2.8018 (2.6496) grad_norm: 3.5237 (3.9321) time: 0.6259 [2021-03-28 16:17:58 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 480/1251] eta: 0:08:13 lr: 0.000015 loss: 2.7954 (2.6518) grad_norm: 3.4934 (3.9388) time: 0.6313 [2021-03-28 16:18:04 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 490/1251] eta: 0:08:06 lr: 0.000015 loss: 2.7221 (2.6517) grad_norm: 3.4934 (3.9331) time: 0.6337 [2021-03-28 16:18:11 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 500/1251] eta: 0:07:59 lr: 0.000015 loss: 2.7173 (2.6530) grad_norm: 3.6113 (3.9267) time: 0.6291 [2021-03-28 16:18:17 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 510/1251] eta: 0:07:53 lr: 0.000015 loss: 2.8333 (2.6546) grad_norm: 3.7018 (3.9218) time: 0.6340 [2021-03-28 16:18:24 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 520/1251] eta: 0:07:47 lr: 0.000015 loss: 2.7905 (2.6565) grad_norm: 3.5461 (3.9209) time: 0.6405 [2021-03-28 16:18:30 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 530/1251] eta: 0:07:40 lr: 0.000015 loss: 2.7905 (2.6604) grad_norm: 3.6248 (3.9238) time: 0.6371 [2021-03-28 16:18:36 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 540/1251] eta: 0:07:34 lr: 0.000015 loss: 2.6200 (2.6546) grad_norm: 3.8515 (3.9415) time: 0.6320 [2021-03-28 16:18:43 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 550/1251] eta: 0:07:28 lr: 0.000015 loss: 2.4117 (2.6526) grad_norm: 3.7564 (3.9354) time: 0.6432 [2021-03-28 16:18:49 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 560/1251] eta: 0:07:21 lr: 0.000015 loss: 2.7166 (2.6553) grad_norm: 3.5346 (3.9329) time: 0.6479 [2021-03-28 16:18:55 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 570/1251] eta: 0:07:15 lr: 0.000015 loss: 2.7166 (2.6551) grad_norm: 3.4870 (3.9280) time: 0.6377 [2021-03-28 16:19:02 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 580/1251] eta: 0:07:08 lr: 0.000015 loss: 2.6621 (2.6558) grad_norm: 3.4870 (3.9559) time: 0.6345 [2021-03-28 16:19:08 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 590/1251] eta: 0:07:02 lr: 0.000015 loss: 2.7064 (2.6523) grad_norm: 3.5424 (3.9656) time: 0.6366 [2021-03-28 16:19:15 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 600/1251] eta: 0:06:55 lr: 0.000015 loss: 2.6559 (2.6514) grad_norm: 3.8976 (3.9801) time: 0.6376 [2021-03-28 16:19:21 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 610/1251] eta: 0:06:49 lr: 0.000015 loss: 2.7241 (2.6519) grad_norm: 3.5320 (3.9713) time: 0.6325 [2021-03-28 16:19:27 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 620/1251] eta: 0:06:43 lr: 0.000015 loss: 2.7687 (2.6543) grad_norm: 3.4259 (3.9830) time: 0.6313 [2021-03-28 16:19:34 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 630/1251] eta: 0:06:36 lr: 0.000015 loss: 2.7134 (2.6554) grad_norm: 3.3497 (3.9729) time: 0.6394 [2021-03-28 16:19:40 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 640/1251] eta: 0:06:30 lr: 0.000015 loss: 2.6102 (2.6535) grad_norm: 3.3985 (3.9867) time: 0.6412 [2021-03-28 16:19:46 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 650/1251] eta: 0:06:23 lr: 0.000015 loss: 2.6824 (2.6543) grad_norm: 3.8253 (3.9826) time: 0.6386 [2021-03-28 16:19:53 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 660/1251] eta: 0:06:17 lr: 0.000015 loss: 2.8323 (2.6563) grad_norm: 3.3863 (3.9784) time: 0.6322 [2021-03-28 16:19:59 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 670/1251] eta: 0:06:10 lr: 0.000015 loss: 2.8046 (2.6566) grad_norm: 3.4912 (3.9721) time: 0.6268 [2021-03-28 16:20:05 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 680/1251] eta: 0:06:04 lr: 0.000015 loss: 2.6168 (2.6544) grad_norm: 3.4912 (3.9662) time: 0.6267 [2021-03-28 16:20:11 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 690/1251] eta: 0:05:57 lr: 0.000015 loss: 2.5254 (2.6528) grad_norm: 3.6237 (3.9682) time: 0.6262 [2021-03-28 16:20:18 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 700/1251] eta: 0:05:51 lr: 0.000015 loss: 2.5254 (2.6501) grad_norm: 3.4375 (3.9601) time: 0.6293 [2021-03-28 16:20:24 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 710/1251] eta: 0:05:45 lr: 0.000015 loss: 2.7945 (2.6526) grad_norm: 3.5658 (3.9576) time: 0.6313 [2021-03-28 16:20:30 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 720/1251] eta: 0:05:38 lr: 0.000015 loss: 2.7248 (2.6521) grad_norm: 3.6525 (3.9522) time: 0.6306 [2021-03-28 16:20:37 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 730/1251] eta: 0:05:32 lr: 0.000015 loss: 2.6794 (2.6527) grad_norm: 3.5214 (3.9462) time: 0.6301 [2021-03-28 16:20:43 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 740/1251] eta: 0:05:25 lr: 0.000015 loss: 2.8536 (2.6542) grad_norm: 3.4955 (3.9430) time: 0.6405 [2021-03-28 16:20:50 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 750/1251] eta: 0:05:19 lr: 0.000015 loss: 2.9438 (2.6546) grad_norm: 3.4788 (3.9422) time: 0.6465 [2021-03-28 16:20:56 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 760/1251] eta: 0:05:13 lr: 0.000015 loss: 2.9064 (2.6560) grad_norm: 3.7475 (3.9489) time: 0.6382 [2021-03-28 16:21:02 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 770/1251] eta: 0:05:06 lr: 0.000015 loss: 2.8441 (2.6579) grad_norm: 3.5617 (3.9442) time: 0.6360 [2021-03-28 16:21:09 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 780/1251] eta: 0:05:00 lr: 0.000015 loss: 2.8445 (2.6594) grad_norm: 3.5100 (3.9469) time: 0.6393 [2021-03-28 16:21:15 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 790/1251] eta: 0:04:54 lr: 0.000015 loss: 2.8445 (2.6605) grad_norm: 3.7237 (3.9452) time: 0.6325 [2021-03-28 16:21:21 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 800/1251] eta: 0:04:47 lr: 0.000015 loss: 2.6201 (2.6584) grad_norm: 3.7810 (3.9456) time: 0.6234 [2021-03-28 16:21:28 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 810/1251] eta: 0:04:41 lr: 0.000015 loss: 2.7162 (2.6608) grad_norm: 3.7440 (3.9490) time: 0.6260 [2021-03-28 16:21:34 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 820/1251] eta: 0:04:34 lr: 0.000015 loss: 2.7637 (2.6626) grad_norm: 3.4591 (3.9489) time: 0.6344 [2021-03-28 16:21:40 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 830/1251] eta: 0:04:28 lr: 0.000015 loss: 2.7637 (2.6640) grad_norm: 3.4795 (3.9752) time: 0.6375 [2021-03-28 16:21:47 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 840/1251] eta: 0:04:21 lr: 0.000015 loss: 2.5786 (2.6610) grad_norm: 3.8706 (3.9713) time: 0.6340 [2021-03-28 16:21:53 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 850/1251] eta: 0:04:15 lr: 0.000015 loss: 2.5542 (2.6614) grad_norm: 3.5154 (3.9663) time: 0.6344 [2021-03-28 16:21:59 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 860/1251] eta: 0:04:09 lr: 0.000015 loss: 2.7400 (2.6617) grad_norm: 3.5493 (3.9700) time: 0.6373 [2021-03-28 16:22:06 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 870/1251] eta: 0:04:02 lr: 0.000015 loss: 2.8613 (2.6641) grad_norm: 3.7748 (3.9697) time: 0.6416 [2021-03-28 16:22:12 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 880/1251] eta: 0:03:56 lr: 0.000015 loss: 2.7116 (2.6630) grad_norm: 3.6840 (3.9667) time: 0.6349 [2021-03-28 16:22:18 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 890/1251] eta: 0:03:50 lr: 0.000015 loss: 2.6102 (2.6635) grad_norm: 3.3483 (3.9636) time: 0.6288 [2021-03-28 16:22:25 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 900/1251] eta: 0:03:43 lr: 0.000015 loss: 2.7703 (2.6662) grad_norm: 3.3483 (3.9614) time: 0.6347 [2021-03-28 16:22:31 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 910/1251] eta: 0:03:37 lr: 0.000015 loss: 2.8419 (2.6645) grad_norm: 3.6033 (3.9624) time: 0.6346 [2021-03-28 16:22:37 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 920/1251] eta: 0:03:30 lr: 0.000015 loss: 2.6914 (2.6647) grad_norm: 3.6472 (3.9619) time: 0.6324 [2021-03-28 16:22:44 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 930/1251] eta: 0:03:24 lr: 0.000015 loss: 2.7159 (2.6644) grad_norm: 3.6360 (3.9620) time: 0.6316 [2021-03-28 16:22:50 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 940/1251] eta: 0:03:18 lr: 0.000015 loss: 2.7258 (2.6649) grad_norm: 3.3801 (3.9579) time: 0.6351 [2021-03-28 16:22:57 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 950/1251] eta: 0:03:11 lr: 0.000015 loss: 2.7189 (2.6644) grad_norm: 3.5724 (3.9605) time: 0.6429 [2021-03-28 16:23:03 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 960/1251] eta: 0:03:05 lr: 0.000015 loss: 2.6922 (2.6643) grad_norm: 3.6775 (3.9600) time: 0.6396 [2021-03-28 16:23:09 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 970/1251] eta: 0:02:59 lr: 0.000015 loss: 2.6195 (2.6628) grad_norm: 3.5658 (3.9558) time: 0.6323 [2021-03-28 16:23:16 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 980/1251] eta: 0:02:52 lr: 0.000015 loss: 2.7246 (2.6637) grad_norm: 3.3427 (3.9515) time: 0.6288 [2021-03-28 16:23:22 swin_base_patch4_window7_224] INFO: Epoch: [286] [ 990/1251] eta: 0:02:46 lr: 0.000015 loss: 2.7474 (2.6637) grad_norm: 3.3427 (3.9443) time: 0.6262 [2021-03-28 16:23:28 swin_base_patch4_window7_224] INFO: Epoch: [286] [1000/1251] eta: 0:02:39 lr: 0.000015 loss: 2.7027 (2.6619) grad_norm: 3.3041 (3.9412) time: 0.6268 [2021-03-28 16:23:34 swin_base_patch4_window7_224] INFO: Epoch: [286] [1010/1251] eta: 0:02:33 lr: 0.000015 loss: 2.6345 (2.6618) grad_norm: 3.3641 (3.9366) time: 0.6306 [2021-03-28 16:23:41 swin_base_patch4_window7_224] INFO: Epoch: [286] [1020/1251] eta: 0:02:27 lr: 0.000015 loss: 2.6345 (2.6613) grad_norm: 3.3447 (3.9324) time: 0.6286 [2021-03-28 16:23:47 swin_base_patch4_window7_224] INFO: Epoch: [286] [1030/1251] eta: 0:02:20 lr: 0.000015 loss: 2.6531 (2.6628) grad_norm: 3.2507 (3.9266) time: 0.6249 [2021-03-28 16:23:53 swin_base_patch4_window7_224] INFO: Epoch: [286] [1040/1251] eta: 0:02:14 lr: 0.000015 loss: 2.8006 (2.6635) grad_norm: 3.1559 (3.9219) time: 0.6277 [2021-03-28 16:24:00 swin_base_patch4_window7_224] INFO: Epoch: [286] [1050/1251] eta: 0:02:07 lr: 0.000015 loss: 2.7127 (2.6633) grad_norm: 3.3032 (3.9270) time: 0.6313 [2021-03-28 16:24:06 swin_base_patch4_window7_224] INFO: Epoch: [286] [1060/1251] eta: 0:02:01 lr: 0.000015 loss: 2.6389 (2.6635) grad_norm: 3.3032 (3.9251) time: 0.6324 [2021-03-28 16:24:12 swin_base_patch4_window7_224] INFO: Epoch: [286] [1070/1251] eta: 0:01:55 lr: 0.000015 loss: 2.6389 (2.6623) grad_norm: 3.3021 (3.9233) time: 0.6289 [2021-03-28 16:24:18 swin_base_patch4_window7_224] INFO: Epoch: [286] [1080/1251] eta: 0:01:48 lr: 0.000015 loss: 2.6853 (2.6623) grad_norm: 3.4710 (3.9216) time: 0.6260 [2021-03-28 16:24:25 swin_base_patch4_window7_224] INFO: Epoch: [286] [1090/1251] eta: 0:01:42 lr: 0.000015 loss: 2.7977 (2.6640) grad_norm: 3.5519 (3.9210) time: 0.6329 [2021-03-28 16:24:31 swin_base_patch4_window7_224] INFO: Epoch: [286] [1100/1251] eta: 0:01:36 lr: 0.000015 loss: 2.6907 (2.6621) grad_norm: 3.4733 (3.9168) time: 0.6377 [2021-03-28 16:24:37 swin_base_patch4_window7_224] INFO: Epoch: [286] [1110/1251] eta: 0:01:29 lr: 0.000015 loss: 2.6353 (2.6625) grad_norm: 3.3852 (3.9124) time: 0.6291 [2021-03-28 16:24:44 swin_base_patch4_window7_224] INFO: Epoch: [286] [1120/1251] eta: 0:01:23 lr: 0.000015 loss: 2.5959 (2.6604) grad_norm: 3.3751 (3.9333) time: 0.6230 [2021-03-28 16:24:50 swin_base_patch4_window7_224] INFO: Epoch: [286] [1130/1251] eta: 0:01:16 lr: 0.000015 loss: 2.4800 (2.6590) grad_norm: 3.3427 (3.9295) time: 0.6264 [2021-03-28 16:24:56 swin_base_patch4_window7_224] INFO: Epoch: [286] [1140/1251] eta: 0:01:10 lr: 0.000015 loss: 2.8283 (2.6607) grad_norm: 3.4178 (3.9275) time: 0.6299 [2021-03-28 16:25:03 swin_base_patch4_window7_224] INFO: Epoch: [286] [1150/1251] eta: 0:01:04 lr: 0.000015 loss: 2.7461 (2.6599) grad_norm: 3.4784 (3.9271) time: 0.6309 [2021-03-28 16:25:09 swin_base_patch4_window7_224] INFO: Epoch: [286] [1160/1251] eta: 0:00:57 lr: 0.000015 loss: 2.5741 (2.6578) grad_norm: 3.5497 (3.9334) time: 0.6369 [2021-03-28 16:25:15 swin_base_patch4_window7_224] INFO: Epoch: [286] [1170/1251] eta: 0:00:51 lr: 0.000015 loss: 2.7038 (2.6593) grad_norm: 3.6196 (3.9388) time: 0.6388 [2021-03-28 16:25:22 swin_base_patch4_window7_224] INFO: Epoch: [286] [1180/1251] eta: 0:00:45 lr: 0.000015 loss: 2.7855 (2.6598) grad_norm: 3.6196 (3.9407) time: 0.6326 [2021-03-28 16:25:28 swin_base_patch4_window7_224] INFO: Epoch: [286] [1190/1251] eta: 0:00:38 lr: 0.000015 loss: 2.7403 (2.6604) grad_norm: 3.7514 (3.9414) time: 0.6315 [2021-03-28 16:25:34 swin_base_patch4_window7_224] INFO: Epoch: [286] [1200/1251] eta: 0:00:32 lr: 0.000015 loss: 2.6187 (2.6596) grad_norm: 3.9330 (3.9610) time: 0.6319 [2021-03-28 16:25:41 swin_base_patch4_window7_224] INFO: Epoch: [286] [1210/1251] eta: 0:00:26 lr: 0.000015 loss: 2.6659 (2.6602) grad_norm: 3.7069 (3.9589) time: 0.6313 [2021-03-28 16:25:47 swin_base_patch4_window7_224] INFO: Epoch: [286] [1220/1251] eta: 0:00:19 lr: 0.000015 loss: 2.7048 (2.6584) grad_norm: 3.7171 (3.9669) time: 0.6315 [2021-03-28 16:25:53 swin_base_patch4_window7_224] INFO: Epoch: [286] [1230/1251] eta: 0:00:13 lr: 0.000015 loss: 2.6740 (2.6585) grad_norm: 3.8307 (3.9644) time: 0.6285 [2021-03-28 16:25:59 swin_base_patch4_window7_224] INFO: Epoch: [286] [1240/1251] eta: 0:00:06 lr: 0.000015 loss: 2.6740 (2.6563) grad_norm: 3.6310 (3.9623) time: 0.6233 [2021-03-28 16:26:05 swin_base_patch4_window7_224] INFO: Epoch: [286] [1250/1251] eta: 0:00:00 lr: 0.000015 loss: 2.7292 (2.6588) grad_norm: 3.5650 (3.9591) time: 0.6158 [2021-03-28 16:26:18 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:37 loss: 0.5032 (0.5032) acc1: 90.6250 (90.6250) acc5: 96.8750 (96.8750) [2021-03-28 16:26:21 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.7371 (0.7208) acc1: 84.3750 (82.8125) acc5: 96.8750 (96.8750) [2021-03-28 16:26:23 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7317 (0.7203) acc1: 79.6875 (83.2589) acc5: 96.8750 (96.8750) [2021-03-28 16:26:25 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7258 (0.7280) acc1: 79.6875 (82.6109) acc5: 96.8750 (96.8750) [2021-03-28 16:26:27 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7689 (0.7323) acc1: 82.8125 (82.9649) acc5: 96.8750 (96.8369) [2021-03-28 16:26:28 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8297 (0.7556) acc1: 79.6875 (82.3360) acc5: 95.3125 (96.6720) [2021-03-28 16:26:43 swin_base_patch4_window7_224] INFO: * Acc@1 83.404 Acc@5 96.460 loss 0.739 [2021-03-28 16:26:43 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 16:26:43 swin_base_patch4_window7_224] INFO: Max accuracy: 83.40% [2021-03-28 16:26:48 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 0/1251] eta: 1:30:01 lr: 0.000015 loss: 2.0620 (2.0620) grad_norm: 3.7973 (3.7973) time: 4.3176 [2021-03-28 16:26:54 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 10/1251] eta: 0:20:21 lr: 0.000015 loss: 2.7543 (2.6295) grad_norm: 3.4527 (3.5780) time: 0.9843 [2021-03-28 16:27:00 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 20/1251] eta: 0:16:46 lr: 0.000015 loss: 2.7628 (2.6695) grad_norm: 3.4437 (3.6718) time: 0.6424 [2021-03-28 16:27:07 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 30/1251] eta: 0:15:26 lr: 0.000015 loss: 2.6915 (2.6571) grad_norm: 3.4567 (3.7260) time: 0.6347 [2021-03-28 16:27:13 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 40/1251] eta: 0:14:39 lr: 0.000015 loss: 2.7170 (2.7008) grad_norm: 3.5414 (3.6877) time: 0.6299 [2021-03-28 16:27:19 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 50/1251] eta: 0:14:10 lr: 0.000015 loss: 2.8220 (2.7075) grad_norm: 3.4255 (3.7678) time: 0.6301 [2021-03-28 16:27:26 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 60/1251] eta: 0:13:47 lr: 0.000015 loss: 2.7493 (2.6672) grad_norm: 3.4575 (3.7703) time: 0.6299 [2021-03-28 16:27:32 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 70/1251] eta: 0:13:30 lr: 0.000015 loss: 2.7292 (2.6695) grad_norm: 3.6485 (3.8482) time: 0.6299 [2021-03-28 16:27:38 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 80/1251] eta: 0:13:17 lr: 0.000015 loss: 2.7292 (2.6496) grad_norm: 3.8204 (3.8702) time: 0.6405 [2021-03-28 16:27:45 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 90/1251] eta: 0:13:04 lr: 0.000015 loss: 2.3159 (2.6296) grad_norm: 3.5641 (3.9324) time: 0.6391 [2021-03-28 16:27:51 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 100/1251] eta: 0:12:54 lr: 0.000015 loss: 2.4819 (2.6447) grad_norm: 3.3333 (3.8901) time: 0.6388 [2021-03-28 16:27:58 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 110/1251] eta: 0:12:42 lr: 0.000015 loss: 2.8011 (2.6393) grad_norm: 3.3514 (3.8620) time: 0.6360 [2021-03-28 16:28:04 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 120/1251] eta: 0:12:32 lr: 0.000015 loss: 2.6747 (2.6455) grad_norm: 3.4644 (3.8316) time: 0.6268 [2021-03-28 16:28:10 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 130/1251] eta: 0:12:22 lr: 0.000015 loss: 2.5056 (2.6237) grad_norm: 3.4644 (3.8099) time: 0.6262 [2021-03-28 16:28:16 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 140/1251] eta: 0:12:13 lr: 0.000015 loss: 2.7387 (2.6354) grad_norm: 3.2632 (3.7812) time: 0.6275 [2021-03-28 16:28:23 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 150/1251] eta: 0:12:04 lr: 0.000014 loss: 2.8135 (2.6426) grad_norm: 3.3227 (3.7676) time: 0.6287 [2021-03-28 16:28:29 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 160/1251] eta: 0:11:55 lr: 0.000014 loss: 2.7185 (2.6406) grad_norm: 3.3366 (3.7748) time: 0.6272 [2021-03-28 16:28:35 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 170/1251] eta: 0:11:47 lr: 0.000014 loss: 2.7419 (2.6435) grad_norm: 3.4057 (3.7668) time: 0.6296 [2021-03-28 16:28:42 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 180/1251] eta: 0:11:39 lr: 0.000014 loss: 2.7419 (2.6472) grad_norm: 3.4229 (3.8367) time: 0.6337 [2021-03-28 16:28:48 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 190/1251] eta: 0:11:31 lr: 0.000014 loss: 2.7017 (2.6446) grad_norm: 3.6147 (3.8223) time: 0.6304 [2021-03-28 16:28:54 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 200/1251] eta: 0:11:24 lr: 0.000014 loss: 2.7532 (2.6520) grad_norm: 3.5536 (3.8003) time: 0.6297 [2021-03-28 16:29:01 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 210/1251] eta: 0:11:16 lr: 0.000014 loss: 2.5659 (2.6432) grad_norm: 3.5125 (3.7938) time: 0.6340 [2021-03-28 16:29:07 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 220/1251] eta: 0:11:09 lr: 0.000014 loss: 2.5199 (2.6452) grad_norm: 3.5310 (3.7878) time: 0.6332 [2021-03-28 16:29:13 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 230/1251] eta: 0:11:02 lr: 0.000014 loss: 2.5564 (2.6382) grad_norm: 3.5168 (3.7968) time: 0.6311 [2021-03-28 16:29:19 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 240/1251] eta: 0:10:54 lr: 0.000014 loss: 2.7471 (2.6482) grad_norm: 3.6839 (3.8197) time: 0.6291 [2021-03-28 16:29:26 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 250/1251] eta: 0:10:47 lr: 0.000014 loss: 2.9165 (2.6579) grad_norm: 3.6618 (3.8193) time: 0.6300 [2021-03-28 16:29:32 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 260/1251] eta: 0:10:40 lr: 0.000014 loss: 2.7564 (2.6515) grad_norm: 3.5680 (3.8159) time: 0.6329 [2021-03-28 16:29:38 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 270/1251] eta: 0:10:33 lr: 0.000014 loss: 2.5958 (2.6543) grad_norm: 3.2233 (3.7993) time: 0.6311 [2021-03-28 16:29:45 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 280/1251] eta: 0:10:26 lr: 0.000014 loss: 2.8119 (2.6560) grad_norm: 3.5003 (3.8139) time: 0.6320 [2021-03-28 16:29:51 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 290/1251] eta: 0:10:19 lr: 0.000014 loss: 2.7270 (2.6520) grad_norm: 3.3148 (3.7956) time: 0.6337 [2021-03-28 16:29:57 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 300/1251] eta: 0:10:12 lr: 0.000014 loss: 2.5717 (2.6490) grad_norm: 3.5450 (3.8331) time: 0.6297 [2021-03-28 16:30:04 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 310/1251] eta: 0:10:06 lr: 0.000014 loss: 2.5266 (2.6457) grad_norm: 3.5655 (3.8484) time: 0.6314 [2021-03-28 16:30:10 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 320/1251] eta: 0:09:59 lr: 0.000014 loss: 2.6429 (2.6440) grad_norm: 3.4197 (3.8481) time: 0.6308 [2021-03-28 16:30:16 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 330/1251] eta: 0:09:52 lr: 0.000014 loss: 2.7220 (2.6468) grad_norm: 3.5956 (3.8545) time: 0.6324 [2021-03-28 16:30:23 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 340/1251] eta: 0:09:45 lr: 0.000014 loss: 2.7306 (2.6458) grad_norm: 3.5956 (3.8504) time: 0.6353 [2021-03-28 16:30:29 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 350/1251] eta: 0:09:39 lr: 0.000014 loss: 2.7306 (2.6451) grad_norm: 3.5092 (3.8539) time: 0.6341 [2021-03-28 16:30:35 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 360/1251] eta: 0:09:32 lr: 0.000014 loss: 2.6940 (2.6447) grad_norm: 3.7964 (3.8620) time: 0.6347 [2021-03-28 16:30:42 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 370/1251] eta: 0:09:25 lr: 0.000014 loss: 2.8366 (2.6491) grad_norm: 3.7661 (3.8655) time: 0.6287 [2021-03-28 16:30:48 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 380/1251] eta: 0:09:19 lr: 0.000014 loss: 2.8931 (2.6546) grad_norm: 3.6996 (3.8711) time: 0.6267 [2021-03-28 16:30:54 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 390/1251] eta: 0:09:12 lr: 0.000014 loss: 2.7964 (2.6578) grad_norm: 3.5242 (3.8684) time: 0.6322 [2021-03-28 16:31:00 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 400/1251] eta: 0:09:05 lr: 0.000014 loss: 2.7210 (2.6550) grad_norm: 3.4593 (3.8511) time: 0.6290 [2021-03-28 16:31:07 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 410/1251] eta: 0:08:58 lr: 0.000014 loss: 2.7326 (2.6608) grad_norm: 3.3183 (3.8515) time: 0.6252 [2021-03-28 16:31:13 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 420/1251] eta: 0:08:52 lr: 0.000014 loss: 2.8560 (2.6629) grad_norm: 3.5225 (3.8473) time: 0.6273 [2021-03-28 16:31:19 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 430/1251] eta: 0:08:45 lr: 0.000014 loss: 2.7560 (2.6611) grad_norm: 3.5225 (3.8414) time: 0.6280 [2021-03-28 16:31:26 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 440/1251] eta: 0:08:39 lr: 0.000014 loss: 2.7320 (2.6605) grad_norm: 3.4423 (3.8345) time: 0.6329 [2021-03-28 16:31:32 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 450/1251] eta: 0:08:32 lr: 0.000014 loss: 2.8879 (2.6651) grad_norm: 3.4008 (3.8279) time: 0.6327 [2021-03-28 16:31:38 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 460/1251] eta: 0:08:26 lr: 0.000014 loss: 2.8705 (2.6672) grad_norm: 3.4702 (3.8320) time: 0.6291 [2021-03-28 16:31:45 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 470/1251] eta: 0:08:19 lr: 0.000014 loss: 2.7505 (2.6675) grad_norm: 3.4702 (3.8206) time: 0.6265 [2021-03-28 16:31:51 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 480/1251] eta: 0:08:12 lr: 0.000014 loss: 2.7254 (2.6675) grad_norm: 3.4965 (3.8279) time: 0.6274 [2021-03-28 16:31:57 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 490/1251] eta: 0:08:06 lr: 0.000014 loss: 2.7122 (2.6645) grad_norm: 3.5321 (3.8322) time: 0.6286 [2021-03-28 16:32:03 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 500/1251] eta: 0:07:59 lr: 0.000014 loss: 2.7287 (2.6673) grad_norm: 3.4436 (3.8292) time: 0.6273 [2021-03-28 16:32:10 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 510/1251] eta: 0:07:53 lr: 0.000014 loss: 2.7813 (2.6672) grad_norm: 3.3013 (3.8227) time: 0.6282 [2021-03-28 16:32:16 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 520/1251] eta: 0:07:46 lr: 0.000014 loss: 2.5280 (2.6604) grad_norm: 3.5544 (3.8262) time: 0.6278 [2021-03-28 16:32:22 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 530/1251] eta: 0:07:40 lr: 0.000014 loss: 2.5481 (2.6624) grad_norm: 3.6781 (3.8309) time: 0.6255 [2021-03-28 16:32:28 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 540/1251] eta: 0:07:33 lr: 0.000014 loss: 2.9705 (2.6671) grad_norm: 3.7893 (3.8357) time: 0.6253 [2021-03-28 16:32:35 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 550/1251] eta: 0:07:27 lr: 0.000014 loss: 2.8432 (2.6700) grad_norm: 3.7858 (3.9915) time: 0.6312 [2021-03-28 16:32:41 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 560/1251] eta: 0:07:20 lr: 0.000014 loss: 2.7500 (2.6704) grad_norm: 3.5273 (3.9897) time: 0.6308 [2021-03-28 16:32:47 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 570/1251] eta: 0:07:14 lr: 0.000014 loss: 2.5999 (2.6692) grad_norm: 3.5193 (3.9950) time: 0.6250 [2021-03-28 16:32:54 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 580/1251] eta: 0:07:07 lr: 0.000014 loss: 2.6703 (2.6697) grad_norm: 3.4631 (3.9891) time: 0.6225 [2021-03-28 16:33:00 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 590/1251] eta: 0:07:00 lr: 0.000014 loss: 2.9032 (2.6707) grad_norm: 3.3275 (3.9800) time: 0.6207 [2021-03-28 16:33:06 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 600/1251] eta: 0:06:54 lr: 0.000014 loss: 2.6230 (2.6699) grad_norm: 3.3275 (3.9694) time: 0.6200 [2021-03-28 16:33:12 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 610/1251] eta: 0:06:48 lr: 0.000014 loss: 2.6230 (2.6704) grad_norm: 3.4867 (3.9710) time: 0.6307 [2021-03-28 16:33:19 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 620/1251] eta: 0:06:41 lr: 0.000014 loss: 2.6423 (2.6680) grad_norm: 3.7111 (3.9690) time: 0.6349 [2021-03-28 16:33:25 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 630/1251] eta: 0:06:35 lr: 0.000014 loss: 2.6126 (2.6680) grad_norm: 3.3992 (3.9608) time: 0.6316 [2021-03-28 16:33:31 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 640/1251] eta: 0:06:28 lr: 0.000014 loss: 2.6674 (2.6677) grad_norm: 3.6090 (3.9638) time: 0.6390 [2021-03-28 16:33:38 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 650/1251] eta: 0:06:22 lr: 0.000014 loss: 2.7438 (2.6681) grad_norm: 4.2134 (3.9755) time: 0.6418 [2021-03-28 16:33:44 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 660/1251] eta: 0:06:16 lr: 0.000014 loss: 2.7479 (2.6711) grad_norm: 4.0703 (3.9780) time: 0.6370 [2021-03-28 16:33:50 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 670/1251] eta: 0:06:09 lr: 0.000014 loss: 2.7567 (2.6711) grad_norm: 3.6112 (3.9720) time: 0.6302 [2021-03-28 16:33:57 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 680/1251] eta: 0:06:03 lr: 0.000014 loss: 2.6181 (2.6706) grad_norm: 3.3155 (3.9680) time: 0.6268 [2021-03-28 16:34:03 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 690/1251] eta: 0:05:56 lr: 0.000014 loss: 2.6181 (2.6708) grad_norm: 3.6468 (3.9612) time: 0.6253 [2021-03-28 16:34:09 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 700/1251] eta: 0:05:50 lr: 0.000014 loss: 2.8444 (2.6731) grad_norm: 3.4036 (3.9623) time: 0.6282 [2021-03-28 16:34:15 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 710/1251] eta: 0:05:43 lr: 0.000014 loss: 2.6778 (2.6710) grad_norm: 3.3487 (3.9653) time: 0.6274 [2021-03-28 16:34:22 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 720/1251] eta: 0:05:37 lr: 0.000014 loss: 2.6778 (2.6725) grad_norm: 3.4359 (3.9609) time: 0.6280 [2021-03-28 16:34:28 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 730/1251] eta: 0:05:31 lr: 0.000014 loss: 2.7126 (2.6712) grad_norm: 3.8930 (3.9632) time: 0.6378 [2021-03-28 16:34:35 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 740/1251] eta: 0:05:24 lr: 0.000014 loss: 2.6531 (2.6703) grad_norm: 3.6189 (3.9581) time: 0.6372 [2021-03-28 16:34:41 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 750/1251] eta: 0:05:18 lr: 0.000014 loss: 2.6542 (2.6706) grad_norm: 3.4244 (3.9598) time: 0.6342 [2021-03-28 16:34:47 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 760/1251] eta: 0:05:12 lr: 0.000014 loss: 2.7432 (2.6723) grad_norm: 3.6656 (3.9633) time: 0.6351 [2021-03-28 16:34:54 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 770/1251] eta: 0:05:05 lr: 0.000014 loss: 2.8970 (2.6735) grad_norm: 3.5812 (3.9585) time: 0.6328 [2021-03-28 16:35:00 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 780/1251] eta: 0:04:59 lr: 0.000014 loss: 2.8976 (2.6751) grad_norm: 3.3647 (3.9529) time: 0.6345 [2021-03-28 16:35:06 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 790/1251] eta: 0:04:53 lr: 0.000014 loss: 2.8056 (2.6741) grad_norm: 3.2585 (3.9491) time: 0.6354 [2021-03-28 16:35:13 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 800/1251] eta: 0:04:46 lr: 0.000014 loss: 2.6174 (2.6747) grad_norm: 3.4110 (3.9475) time: 0.6353 [2021-03-28 16:35:19 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 810/1251] eta: 0:04:40 lr: 0.000014 loss: 2.6310 (2.6757) grad_norm: 3.5904 (3.9537) time: 0.6299 [2021-03-28 16:35:25 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 820/1251] eta: 0:04:33 lr: 0.000014 loss: 2.6165 (2.6727) grad_norm: 3.5916 (3.9493) time: 0.6263 [2021-03-28 16:35:32 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 830/1251] eta: 0:04:27 lr: 0.000014 loss: 2.4166 (2.6684) grad_norm: 3.4979 (3.9492) time: 0.6354 [2021-03-28 16:35:38 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 840/1251] eta: 0:04:21 lr: 0.000014 loss: 2.4166 (2.6662) grad_norm: 3.7039 (3.9479) time: 0.6387 [2021-03-28 16:35:44 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 850/1251] eta: 0:04:14 lr: 0.000014 loss: 2.6310 (2.6653) grad_norm: 3.5928 (3.9457) time: 0.6328 [2021-03-28 16:35:51 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 860/1251] eta: 0:04:08 lr: 0.000014 loss: 2.7158 (2.6642) grad_norm: 3.5524 (3.9445) time: 0.6305 [2021-03-28 16:35:57 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 870/1251] eta: 0:04:02 lr: 0.000014 loss: 2.6412 (2.6638) grad_norm: 3.7848 (3.9442) time: 0.6304 [2021-03-28 16:36:03 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 880/1251] eta: 0:03:55 lr: 0.000014 loss: 2.5642 (2.6630) grad_norm: 3.7201 (3.9415) time: 0.6328 [2021-03-28 16:36:10 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 890/1251] eta: 0:03:49 lr: 0.000014 loss: 2.7178 (2.6641) grad_norm: 3.5119 (3.9362) time: 0.6395 [2021-03-28 16:36:16 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 900/1251] eta: 0:03:43 lr: 0.000014 loss: 2.8273 (2.6643) grad_norm: 3.3727 (3.9304) time: 0.6388 [2021-03-28 16:36:22 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 910/1251] eta: 0:03:36 lr: 0.000014 loss: 2.8285 (2.6643) grad_norm: 3.4469 (3.9300) time: 0.6325 [2021-03-28 16:36:29 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 920/1251] eta: 0:03:30 lr: 0.000014 loss: 2.7135 (2.6627) grad_norm: 3.6813 (3.9490) time: 0.6284 [2021-03-28 16:36:35 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 930/1251] eta: 0:03:23 lr: 0.000014 loss: 2.7135 (2.6638) grad_norm: 3.7535 (3.9502) time: 0.6325 [2021-03-28 16:36:41 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 940/1251] eta: 0:03:17 lr: 0.000014 loss: 2.7855 (2.6639) grad_norm: 3.6138 (3.9476) time: 0.6347 [2021-03-28 16:36:48 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 950/1251] eta: 0:03:11 lr: 0.000014 loss: 2.6483 (2.6616) grad_norm: 3.4282 (3.9448) time: 0.6360 [2021-03-28 16:36:54 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 960/1251] eta: 0:03:04 lr: 0.000014 loss: 2.3473 (2.6597) grad_norm: 3.4781 (3.9624) time: 0.6293 [2021-03-28 16:37:00 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 970/1251] eta: 0:02:58 lr: 0.000014 loss: 2.3473 (2.6577) grad_norm: 3.5375 (3.9681) time: 0.6271 [2021-03-28 16:37:07 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 980/1251] eta: 0:02:52 lr: 0.000014 loss: 2.7172 (2.6586) grad_norm: 3.4982 (3.9657) time: 0.6341 [2021-03-28 16:37:13 swin_base_patch4_window7_224] INFO: Epoch: [287] [ 990/1251] eta: 0:02:45 lr: 0.000014 loss: 2.7350 (2.6592) grad_norm: 3.4710 (3.9606) time: 0.6336 [2021-03-28 16:37:19 swin_base_patch4_window7_224] INFO: Epoch: [287] [1000/1251] eta: 0:02:39 lr: 0.000014 loss: 2.5759 (2.6578) grad_norm: 3.4710 (3.9560) time: 0.6308 [2021-03-28 16:37:26 swin_base_patch4_window7_224] INFO: Epoch: [287] [1010/1251] eta: 0:02:33 lr: 0.000014 loss: 2.4608 (2.6556) grad_norm: 3.3664 (3.9519) time: 0.6300 [2021-03-28 16:37:32 swin_base_patch4_window7_224] INFO: Epoch: [287] [1020/1251] eta: 0:02:26 lr: 0.000014 loss: 2.5650 (2.6550) grad_norm: 3.4225 (3.9535) time: 0.6313 [2021-03-28 16:37:38 swin_base_patch4_window7_224] INFO: Epoch: [287] [1030/1251] eta: 0:02:20 lr: 0.000014 loss: 2.6562 (2.6542) grad_norm: 3.7884 (3.9535) time: 0.6345 [2021-03-28 16:37:45 swin_base_patch4_window7_224] INFO: Epoch: [287] [1040/1251] eta: 0:02:14 lr: 0.000014 loss: 2.6874 (2.6530) grad_norm: 3.9396 (3.9527) time: 0.6390 [2021-03-28 16:37:51 swin_base_patch4_window7_224] INFO: Epoch: [287] [1050/1251] eta: 0:02:07 lr: 0.000014 loss: 2.6408 (2.6537) grad_norm: 3.4823 (3.9585) time: 0.6341 [2021-03-28 16:37:57 swin_base_patch4_window7_224] INFO: Epoch: [287] [1060/1251] eta: 0:02:01 lr: 0.000014 loss: 2.6250 (2.6529) grad_norm: 3.4062 (3.9519) time: 0.6327 [2021-03-28 16:38:04 swin_base_patch4_window7_224] INFO: Epoch: [287] [1070/1251] eta: 0:01:54 lr: 0.000014 loss: 2.6236 (2.6514) grad_norm: 3.4062 (3.9514) time: 0.6337 [2021-03-28 16:38:10 swin_base_patch4_window7_224] INFO: Epoch: [287] [1080/1251] eta: 0:01:48 lr: 0.000014 loss: 2.6601 (2.6513) grad_norm: 3.7608 (3.9489) time: 0.6309 [2021-03-28 16:38:16 swin_base_patch4_window7_224] INFO: Epoch: [287] [1090/1251] eta: 0:01:42 lr: 0.000014 loss: 2.7759 (2.6518) grad_norm: 3.6451 (3.9477) time: 0.6331 [2021-03-28 16:38:22 swin_base_patch4_window7_224] INFO: Epoch: [287] [1100/1251] eta: 0:01:35 lr: 0.000014 loss: 2.6656 (2.6513) grad_norm: 3.8236 (3.9513) time: 0.6296 [2021-03-28 16:38:29 swin_base_patch4_window7_224] INFO: Epoch: [287] [1110/1251] eta: 0:01:29 lr: 0.000014 loss: 2.5876 (2.6527) grad_norm: 4.0052 (3.9501) time: 0.6289 [2021-03-28 16:38:35 swin_base_patch4_window7_224] INFO: Epoch: [287] [1120/1251] eta: 0:01:23 lr: 0.000014 loss: 2.6907 (2.6527) grad_norm: 3.5168 (3.9459) time: 0.6292 [2021-03-28 16:38:41 swin_base_patch4_window7_224] INFO: Epoch: [287] [1130/1251] eta: 0:01:16 lr: 0.000014 loss: 2.7132 (2.6526) grad_norm: 3.7077 (3.9508) time: 0.6262 [2021-03-28 16:38:48 swin_base_patch4_window7_224] INFO: Epoch: [287] [1140/1251] eta: 0:01:10 lr: 0.000014 loss: 2.5858 (2.6509) grad_norm: 3.7517 (3.9497) time: 0.6292 [2021-03-28 16:38:54 swin_base_patch4_window7_224] INFO: Epoch: [287] [1150/1251] eta: 0:01:04 lr: 0.000014 loss: 2.7601 (2.6523) grad_norm: 3.5126 (3.9484) time: 0.6301 [2021-03-28 16:39:00 swin_base_patch4_window7_224] INFO: Epoch: [287] [1160/1251] eta: 0:00:57 lr: 0.000014 loss: 2.7826 (2.6522) grad_norm: 3.7803 (3.9549) time: 0.6333 [2021-03-28 16:39:07 swin_base_patch4_window7_224] INFO: Epoch: [287] [1170/1251] eta: 0:00:51 lr: 0.000014 loss: 2.7840 (2.6540) grad_norm: 3.6777 (3.9511) time: 0.6347 [2021-03-28 16:39:13 swin_base_patch4_window7_224] INFO: Epoch: [287] [1180/1251] eta: 0:00:45 lr: 0.000014 loss: 2.7727 (2.6534) grad_norm: 3.4959 (3.9484) time: 0.6281 [2021-03-28 16:39:19 swin_base_patch4_window7_224] INFO: Epoch: [287] [1190/1251] eta: 0:00:38 lr: 0.000014 loss: 2.7099 (2.6535) grad_norm: 3.5838 (3.9473) time: 0.6304 [2021-03-28 16:39:26 swin_base_patch4_window7_224] INFO: Epoch: [287] [1200/1251] eta: 0:00:32 lr: 0.000014 loss: 2.7600 (2.6540) grad_norm: 3.5464 (3.9441) time: 0.6360 [2021-03-28 16:39:32 swin_base_patch4_window7_224] INFO: Epoch: [287] [1210/1251] eta: 0:00:26 lr: 0.000014 loss: 2.6871 (2.6537) grad_norm: 3.5464 (3.9430) time: 0.6357 [2021-03-28 16:39:38 swin_base_patch4_window7_224] INFO: Epoch: [287] [1220/1251] eta: 0:00:19 lr: 0.000014 loss: 2.5731 (2.6530) grad_norm: 3.3464 (3.9380) time: 0.6389 [2021-03-28 16:39:45 swin_base_patch4_window7_224] INFO: Epoch: [287] [1230/1251] eta: 0:00:13 lr: 0.000014 loss: 2.7234 (2.6535) grad_norm: 3.5812 (3.9363) time: 0.6375 [2021-03-28 16:39:51 swin_base_patch4_window7_224] INFO: Epoch: [287] [1240/1251] eta: 0:00:06 lr: 0.000014 loss: 2.8000 (2.6544) grad_norm: 3.5812 (3.9374) time: 0.6312 [2021-03-28 16:39:57 swin_base_patch4_window7_224] INFO: Epoch: [287] [1250/1251] eta: 0:00:00 lr: 0.000014 loss: 2.7618 (2.6554) grad_norm: 3.4834 (3.9343) time: 0.6301 [2021-03-28 16:40:12 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:03 loss: 0.7065 (0.7065) acc1: 85.9375 (85.9375) acc5: 96.8750 (96.8750) [2021-03-28 16:40:14 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.7985 (0.7904) acc1: 81.2500 (82.6705) acc5: 95.3125 (95.5966) [2021-03-28 16:40:16 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7578 (0.7823) acc1: 81.2500 (82.0685) acc5: 96.8750 (96.2054) [2021-03-28 16:40:18 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6817 (0.7411) acc1: 82.8125 (82.6109) acc5: 96.8750 (96.6230) [2021-03-28 16:40:20 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6652 (0.7396) acc1: 82.8125 (82.3933) acc5: 96.8750 (96.5701) [2021-03-28 16:40:22 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7061 (0.7522) acc1: 81.2500 (82.1440) acc5: 96.8750 (96.5120) [2021-03-28 16:40:36 swin_base_patch4_window7_224] INFO: * Acc@1 83.378 Acc@5 96.454 loss 0.738 [2021-03-28 16:40:36 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 16:40:36 swin_base_patch4_window7_224] INFO: Max accuracy: 83.40% [2021-03-28 16:40:40 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 0/1251] eta: 1:33:24 lr: 0.000014 loss: 2.4981 (2.4981) grad_norm: 3.7079 (3.7079) time: 4.4797 [2021-03-28 16:40:47 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 10/1251] eta: 0:20:22 lr: 0.000014 loss: 2.7141 (2.7091) grad_norm: 3.4433 (3.5466) time: 0.9849 [2021-03-28 16:40:53 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 20/1251] eta: 0:16:51 lr: 0.000014 loss: 2.7283 (2.6190) grad_norm: 3.4433 (3.5959) time: 0.6385 [2021-03-28 16:41:00 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 30/1251] eta: 0:15:34 lr: 0.000014 loss: 2.9079 (2.6793) grad_norm: 3.6418 (3.7991) time: 0.6445 [2021-03-28 16:41:06 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 40/1251] eta: 0:14:49 lr: 0.000014 loss: 2.8907 (2.6667) grad_norm: 3.8795 (3.7685) time: 0.6427 [2021-03-28 16:41:12 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 50/1251] eta: 0:14:18 lr: 0.000014 loss: 2.5610 (2.6325) grad_norm: 3.3597 (3.7148) time: 0.6357 [2021-03-28 16:41:18 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 60/1251] eta: 0:13:53 lr: 0.000014 loss: 2.4376 (2.6116) grad_norm: 3.3497 (3.6644) time: 0.6293 [2021-03-28 16:41:25 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 70/1251] eta: 0:13:36 lr: 0.000014 loss: 2.5826 (2.6354) grad_norm: 3.3497 (3.6486) time: 0.6312 [2021-03-28 16:41:31 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 80/1251] eta: 0:13:19 lr: 0.000014 loss: 2.7856 (2.6267) grad_norm: 3.7956 (3.7514) time: 0.6296 [2021-03-28 16:41:37 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 90/1251] eta: 0:13:05 lr: 0.000014 loss: 2.7005 (2.6361) grad_norm: 3.6532 (3.7249) time: 0.6250 [2021-03-28 16:41:44 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 100/1251] eta: 0:12:54 lr: 0.000014 loss: 2.7005 (2.6522) grad_norm: 3.4705 (3.7227) time: 0.6330 [2021-03-28 16:41:50 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 110/1251] eta: 0:12:44 lr: 0.000014 loss: 2.8418 (2.6523) grad_norm: 3.2400 (3.7310) time: 0.6418 [2021-03-28 16:41:57 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 120/1251] eta: 0:12:34 lr: 0.000014 loss: 2.8418 (2.6624) grad_norm: 3.2400 (3.7595) time: 0.6414 [2021-03-28 16:42:03 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 130/1251] eta: 0:12:25 lr: 0.000014 loss: 2.6570 (2.6476) grad_norm: 3.7337 (3.7711) time: 0.6361 [2021-03-28 16:42:09 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 140/1251] eta: 0:12:17 lr: 0.000014 loss: 2.7067 (2.6531) grad_norm: 3.5155 (3.8012) time: 0.6404 [2021-03-28 16:42:16 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 150/1251] eta: 0:12:09 lr: 0.000014 loss: 2.8451 (2.6728) grad_norm: 3.4614 (3.7821) time: 0.6438 [2021-03-28 16:42:22 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 160/1251] eta: 0:12:00 lr: 0.000014 loss: 2.9247 (2.6701) grad_norm: 3.4236 (3.7596) time: 0.6370 [2021-03-28 16:42:28 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 170/1251] eta: 0:11:51 lr: 0.000014 loss: 2.6944 (2.6659) grad_norm: 3.3789 (3.7433) time: 0.6262 [2021-03-28 16:42:35 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 180/1251] eta: 0:11:43 lr: 0.000014 loss: 2.7425 (2.6709) grad_norm: 3.3744 (3.7225) time: 0.6265 [2021-03-28 16:42:41 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 190/1251] eta: 0:11:35 lr: 0.000014 loss: 2.7016 (2.6560) grad_norm: 3.3967 (3.7141) time: 0.6299 [2021-03-28 16:42:47 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 200/1251] eta: 0:11:27 lr: 0.000014 loss: 2.5574 (2.6635) grad_norm: 3.4912 (3.7265) time: 0.6287 [2021-03-28 16:42:54 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 210/1251] eta: 0:11:20 lr: 0.000014 loss: 2.6920 (2.6635) grad_norm: 3.7346 (3.7354) time: 0.6382 [2021-03-28 16:43:00 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 220/1251] eta: 0:11:13 lr: 0.000014 loss: 2.7587 (2.6701) grad_norm: 3.7525 (3.7423) time: 0.6466 [2021-03-28 16:43:07 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 230/1251] eta: 0:11:06 lr: 0.000014 loss: 2.8177 (2.6717) grad_norm: 3.8072 (inf) time: 0.6419 [2021-03-28 16:43:13 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 240/1251] eta: 0:10:58 lr: 0.000014 loss: 2.7840 (2.6755) grad_norm: 3.4862 (inf) time: 0.6301 [2021-03-28 16:43:19 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 250/1251] eta: 0:10:51 lr: 0.000014 loss: 2.8558 (2.6835) grad_norm: 3.4263 (inf) time: 0.6311 [2021-03-28 16:43:25 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 260/1251] eta: 0:10:44 lr: 0.000014 loss: 2.7728 (2.6789) grad_norm: 3.7689 (inf) time: 0.6360 [2021-03-28 16:43:32 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 270/1251] eta: 0:10:36 lr: 0.000014 loss: 2.6446 (2.6761) grad_norm: 3.5804 (inf) time: 0.6316 [2021-03-28 16:43:38 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 280/1251] eta: 0:10:29 lr: 0.000014 loss: 2.6914 (2.6719) grad_norm: 3.3408 (inf) time: 0.6285 [2021-03-28 16:43:44 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 290/1251] eta: 0:10:22 lr: 0.000014 loss: 2.6416 (2.6717) grad_norm: 3.3408 (inf) time: 0.6295 [2021-03-28 16:43:51 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 300/1251] eta: 0:10:15 lr: 0.000014 loss: 2.7511 (2.6706) grad_norm: 3.3135 (inf) time: 0.6306 [2021-03-28 16:43:57 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 310/1251] eta: 0:10:08 lr: 0.000014 loss: 2.6614 (2.6648) grad_norm: 3.4868 (inf) time: 0.6302 [2021-03-28 16:44:03 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 320/1251] eta: 0:10:01 lr: 0.000014 loss: 2.6614 (2.6665) grad_norm: 3.5188 (inf) time: 0.6329 [2021-03-28 16:44:10 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 330/1251] eta: 0:09:55 lr: 0.000014 loss: 2.6734 (2.6633) grad_norm: 3.4470 (inf) time: 0.6368 [2021-03-28 16:44:16 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 340/1251] eta: 0:09:48 lr: 0.000014 loss: 2.6229 (2.6584) grad_norm: 3.4626 (inf) time: 0.6362 [2021-03-28 16:44:22 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 350/1251] eta: 0:09:41 lr: 0.000014 loss: 2.5985 (2.6593) grad_norm: 3.7333 (inf) time: 0.6341 [2021-03-28 16:44:29 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 360/1251] eta: 0:09:34 lr: 0.000014 loss: 2.6592 (2.6588) grad_norm: 3.8038 (inf) time: 0.6302 [2021-03-28 16:44:35 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 370/1251] eta: 0:09:27 lr: 0.000014 loss: 2.6592 (2.6603) grad_norm: 3.4820 (inf) time: 0.6270 [2021-03-28 16:44:41 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 380/1251] eta: 0:09:21 lr: 0.000014 loss: 2.6178 (2.6594) grad_norm: 3.5827 (inf) time: 0.6288 [2021-03-28 16:44:48 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 390/1251] eta: 0:09:14 lr: 0.000014 loss: 2.7610 (2.6588) grad_norm: 3.6556 (inf) time: 0.6328 [2021-03-28 16:44:54 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 400/1251] eta: 0:09:07 lr: 0.000014 loss: 2.7312 (2.6575) grad_norm: 3.5733 (inf) time: 0.6350 [2021-03-28 16:45:00 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 410/1251] eta: 0:09:01 lr: 0.000014 loss: 2.6542 (2.6595) grad_norm: 3.2773 (inf) time: 0.6321 [2021-03-28 16:45:07 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 420/1251] eta: 0:08:54 lr: 0.000014 loss: 2.6708 (2.6618) grad_norm: 3.4888 (inf) time: 0.6314 [2021-03-28 16:45:13 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 430/1251] eta: 0:08:47 lr: 0.000014 loss: 2.8595 (2.6662) grad_norm: 3.7170 (inf) time: 0.6319 [2021-03-28 16:45:19 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 440/1251] eta: 0:08:41 lr: 0.000014 loss: 2.8750 (2.6667) grad_norm: 3.5714 (inf) time: 0.6387 [2021-03-28 16:45:26 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 450/1251] eta: 0:08:34 lr: 0.000014 loss: 2.7021 (2.6649) grad_norm: 3.4340 (inf) time: 0.6413 [2021-03-28 16:45:32 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 460/1251] eta: 0:08:28 lr: 0.000014 loss: 2.6088 (2.6629) grad_norm: 3.6954 (inf) time: 0.6302 [2021-03-28 16:45:38 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 470/1251] eta: 0:08:21 lr: 0.000014 loss: 2.6332 (2.6635) grad_norm: 3.6954 (inf) time: 0.6292 [2021-03-28 16:45:45 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 480/1251] eta: 0:08:15 lr: 0.000014 loss: 2.8006 (2.6626) grad_norm: 3.4772 (inf) time: 0.6359 [2021-03-28 16:45:51 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 490/1251] eta: 0:08:08 lr: 0.000014 loss: 2.8722 (2.6600) grad_norm: 3.4954 (inf) time: 0.6385 [2021-03-28 16:45:57 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 500/1251] eta: 0:08:01 lr: 0.000014 loss: 2.7757 (2.6590) grad_norm: 3.5382 (inf) time: 0.6347 [2021-03-28 16:46:04 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 510/1251] eta: 0:07:55 lr: 0.000014 loss: 2.6349 (2.6580) grad_norm: 3.7138 (inf) time: 0.6280 [2021-03-28 16:46:10 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 520/1251] eta: 0:07:48 lr: 0.000014 loss: 2.5794 (2.6559) grad_norm: 3.7138 (inf) time: 0.6283 [2021-03-28 16:46:16 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 530/1251] eta: 0:07:42 lr: 0.000014 loss: 2.6812 (2.6559) grad_norm: 3.5144 (inf) time: 0.6264 [2021-03-28 16:46:23 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 540/1251] eta: 0:07:35 lr: 0.000014 loss: 2.6987 (2.6580) grad_norm: 3.7139 (inf) time: 0.6272 [2021-03-28 16:46:29 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 550/1251] eta: 0:07:29 lr: 0.000014 loss: 2.6303 (2.6557) grad_norm: 3.5513 (inf) time: 0.6303 [2021-03-28 16:46:35 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 560/1251] eta: 0:07:22 lr: 0.000014 loss: 2.5877 (2.6561) grad_norm: 3.8535 (inf) time: 0.6329 [2021-03-28 16:46:42 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 570/1251] eta: 0:07:16 lr: 0.000014 loss: 2.7459 (2.6574) grad_norm: 3.8535 (inf) time: 0.6352 [2021-03-28 16:46:48 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 580/1251] eta: 0:07:09 lr: 0.000014 loss: 2.8255 (2.6613) grad_norm: 3.3068 (inf) time: 0.6356 [2021-03-28 16:46:54 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 590/1251] eta: 0:07:03 lr: 0.000014 loss: 2.8044 (2.6606) grad_norm: 3.3109 (inf) time: 0.6346 [2021-03-28 16:47:00 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 600/1251] eta: 0:06:56 lr: 0.000014 loss: 2.7050 (2.6608) grad_norm: 3.4010 (inf) time: 0.6285 [2021-03-28 16:47:07 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 610/1251] eta: 0:06:50 lr: 0.000014 loss: 2.7114 (2.6601) grad_norm: 3.5931 (inf) time: 0.6288 [2021-03-28 16:47:13 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 620/1251] eta: 0:06:43 lr: 0.000014 loss: 2.7820 (2.6623) grad_norm: 3.9291 (inf) time: 0.6333 [2021-03-28 16:47:19 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 630/1251] eta: 0:06:37 lr: 0.000014 loss: 2.8419 (2.6640) grad_norm: 3.4565 (inf) time: 0.6354 [2021-03-28 16:47:26 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 640/1251] eta: 0:06:30 lr: 0.000014 loss: 2.7948 (2.6634) grad_norm: 3.4642 (inf) time: 0.6350 [2021-03-28 16:47:32 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 650/1251] eta: 0:06:24 lr: 0.000014 loss: 2.7185 (2.6636) grad_norm: 3.6352 (inf) time: 0.6344 [2021-03-28 16:47:39 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 660/1251] eta: 0:06:17 lr: 0.000014 loss: 2.7035 (2.6615) grad_norm: 3.5676 (inf) time: 0.6371 [2021-03-28 16:47:45 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 670/1251] eta: 0:06:11 lr: 0.000014 loss: 2.6635 (2.6609) grad_norm: 3.6363 (inf) time: 0.6420 [2021-03-28 16:47:51 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 680/1251] eta: 0:06:05 lr: 0.000014 loss: 2.6351 (2.6598) grad_norm: 3.6983 (inf) time: 0.6365 [2021-03-28 16:47:58 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 690/1251] eta: 0:05:58 lr: 0.000014 loss: 2.6753 (2.6605) grad_norm: 3.5061 (inf) time: 0.6315 [2021-03-28 16:48:04 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 700/1251] eta: 0:05:52 lr: 0.000014 loss: 2.7220 (2.6578) grad_norm: 3.5061 (inf) time: 0.6365 [2021-03-28 16:48:10 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 710/1251] eta: 0:05:45 lr: 0.000014 loss: 2.7696 (2.6597) grad_norm: 3.5614 (inf) time: 0.6351 [2021-03-28 16:48:17 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 720/1251] eta: 0:05:39 lr: 0.000014 loss: 2.7902 (2.6561) grad_norm: 3.6786 (inf) time: 0.6357 [2021-03-28 16:48:23 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 730/1251] eta: 0:05:33 lr: 0.000014 loss: 2.7350 (2.6574) grad_norm: 3.6560 (inf) time: 0.6385 [2021-03-28 16:48:29 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 740/1251] eta: 0:05:26 lr: 0.000014 loss: 2.7268 (2.6555) grad_norm: 3.6754 (inf) time: 0.6333 [2021-03-28 16:48:36 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 750/1251] eta: 0:05:20 lr: 0.000014 loss: 2.7397 (2.6568) grad_norm: 3.6212 (inf) time: 0.6361 [2021-03-28 16:48:42 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 760/1251] eta: 0:05:13 lr: 0.000014 loss: 2.8225 (2.6594) grad_norm: 3.4972 (inf) time: 0.6376 [2021-03-28 16:48:49 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 770/1251] eta: 0:05:07 lr: 0.000014 loss: 2.6935 (2.6579) grad_norm: 3.5540 (inf) time: 0.6372 [2021-03-28 16:48:55 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 780/1251] eta: 0:05:00 lr: 0.000014 loss: 2.6935 (2.6599) grad_norm: 3.4992 (inf) time: 0.6337 [2021-03-28 16:49:01 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 790/1251] eta: 0:04:54 lr: 0.000014 loss: 2.7878 (2.6609) grad_norm: 3.4992 (inf) time: 0.6328 [2021-03-28 16:49:08 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 800/1251] eta: 0:04:48 lr: 0.000013 loss: 2.6591 (2.6577) grad_norm: 3.4278 (inf) time: 0.6320 [2021-03-28 16:49:14 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 810/1251] eta: 0:04:41 lr: 0.000013 loss: 2.2311 (2.6556) grad_norm: 3.4029 (inf) time: 0.6263 [2021-03-28 16:49:20 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 820/1251] eta: 0:04:35 lr: 0.000013 loss: 2.5220 (2.6553) grad_norm: 3.5045 (inf) time: 0.6294 [2021-03-28 16:49:27 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 830/1251] eta: 0:04:28 lr: 0.000013 loss: 2.6982 (2.6557) grad_norm: 3.5045 (inf) time: 0.6366 [2021-03-28 16:49:33 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 840/1251] eta: 0:04:22 lr: 0.000013 loss: 2.7562 (2.6569) grad_norm: 3.7083 (inf) time: 0.6333 [2021-03-28 16:49:39 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 850/1251] eta: 0:04:15 lr: 0.000013 loss: 2.6748 (2.6560) grad_norm: 3.6273 (inf) time: 0.6247 [2021-03-28 16:49:45 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 860/1251] eta: 0:04:09 lr: 0.000013 loss: 2.5785 (2.6557) grad_norm: 3.5990 (inf) time: 0.6356 [2021-03-28 16:49:52 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 870/1251] eta: 0:04:03 lr: 0.000013 loss: 2.7082 (2.6578) grad_norm: 3.6107 (inf) time: 0.6364 [2021-03-28 16:49:58 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 880/1251] eta: 0:03:56 lr: 0.000013 loss: 2.7798 (2.6579) grad_norm: 3.4369 (inf) time: 0.6329 [2021-03-28 16:50:05 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 890/1251] eta: 0:03:50 lr: 0.000013 loss: 2.7678 (2.6602) grad_norm: 3.3841 (inf) time: 0.6367 [2021-03-28 16:50:11 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 900/1251] eta: 0:03:43 lr: 0.000013 loss: 2.7093 (2.6594) grad_norm: 3.4611 (inf) time: 0.6321 [2021-03-28 16:50:17 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 910/1251] eta: 0:03:37 lr: 0.000013 loss: 2.6584 (2.6600) grad_norm: 3.5482 (inf) time: 0.6325 [2021-03-28 16:50:24 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 920/1251] eta: 0:03:31 lr: 0.000013 loss: 2.8733 (2.6627) grad_norm: 3.6955 (inf) time: 0.6353 [2021-03-28 16:50:30 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 930/1251] eta: 0:03:24 lr: 0.000013 loss: 2.8565 (2.6624) grad_norm: 3.8151 (inf) time: 0.6306 [2021-03-28 16:50:36 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 940/1251] eta: 0:03:18 lr: 0.000013 loss: 2.7314 (2.6623) grad_norm: 3.3378 (inf) time: 0.6304 [2021-03-28 16:50:42 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 950/1251] eta: 0:03:11 lr: 0.000013 loss: 2.7230 (2.6625) grad_norm: 3.3096 (inf) time: 0.6282 [2021-03-28 16:50:49 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 960/1251] eta: 0:03:05 lr: 0.000013 loss: 2.7230 (2.6612) grad_norm: 3.3755 (inf) time: 0.6328 [2021-03-28 16:50:55 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 970/1251] eta: 0:02:59 lr: 0.000013 loss: 2.4579 (2.6595) grad_norm: 3.4098 (inf) time: 0.6350 [2021-03-28 16:51:01 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 980/1251] eta: 0:02:52 lr: 0.000013 loss: 2.4609 (2.6579) grad_norm: 3.3467 (inf) time: 0.6343 [2021-03-28 16:51:08 swin_base_patch4_window7_224] INFO: Epoch: [288] [ 990/1251] eta: 0:02:46 lr: 0.000013 loss: 2.5592 (2.6566) grad_norm: 3.3467 (inf) time: 0.6378 [2021-03-28 16:51:14 swin_base_patch4_window7_224] INFO: Epoch: [288] [1000/1251] eta: 0:02:40 lr: 0.000013 loss: 2.4636 (2.6544) grad_norm: 3.4364 (inf) time: 0.6350 [2021-03-28 16:51:20 swin_base_patch4_window7_224] INFO: Epoch: [288] [1010/1251] eta: 0:02:33 lr: 0.000013 loss: 2.4636 (2.6539) grad_norm: 3.6451 (inf) time: 0.6278 [2021-03-28 16:51:27 swin_base_patch4_window7_224] INFO: Epoch: [288] [1020/1251] eta: 0:02:27 lr: 0.000013 loss: 2.6673 (2.6526) grad_norm: 3.5311 (inf) time: 0.6212 [2021-03-28 16:51:33 swin_base_patch4_window7_224] INFO: Epoch: [288] [1030/1251] eta: 0:02:20 lr: 0.000013 loss: 2.6868 (2.6543) grad_norm: 3.5311 (inf) time: 0.6295 [2021-03-28 16:51:39 swin_base_patch4_window7_224] INFO: Epoch: [288] [1040/1251] eta: 0:02:14 lr: 0.000013 loss: 2.8950 (2.6551) grad_norm: 3.4055 (inf) time: 0.6365 [2021-03-28 16:51:46 swin_base_patch4_window7_224] INFO: Epoch: [288] [1050/1251] eta: 0:02:08 lr: 0.000013 loss: 2.7466 (2.6536) grad_norm: 3.3540 (inf) time: 0.6375 [2021-03-28 16:51:52 swin_base_patch4_window7_224] INFO: Epoch: [288] [1060/1251] eta: 0:02:01 lr: 0.000013 loss: 2.5499 (2.6519) grad_norm: 3.4787 (inf) time: 0.6356 [2021-03-28 16:51:58 swin_base_patch4_window7_224] INFO: Epoch: [288] [1070/1251] eta: 0:01:55 lr: 0.000013 loss: 2.6833 (2.6530) grad_norm: 3.4618 (inf) time: 0.6297 [2021-03-28 16:52:05 swin_base_patch4_window7_224] INFO: Epoch: [288] [1080/1251] eta: 0:01:48 lr: 0.000013 loss: 2.7579 (2.6529) grad_norm: 3.5105 (inf) time: 0.6364 [2021-03-28 16:52:11 swin_base_patch4_window7_224] INFO: Epoch: [288] [1090/1251] eta: 0:01:42 lr: 0.000013 loss: 2.6733 (2.6541) grad_norm: 3.5105 (inf) time: 0.6392 [2021-03-28 16:52:17 swin_base_patch4_window7_224] INFO: Epoch: [288] [1100/1251] eta: 0:01:36 lr: 0.000013 loss: 2.6483 (2.6537) grad_norm: 3.7644 (inf) time: 0.6297 [2021-03-28 16:52:24 swin_base_patch4_window7_224] INFO: Epoch: [288] [1110/1251] eta: 0:01:29 lr: 0.000013 loss: 2.4944 (2.6522) grad_norm: 3.6113 (inf) time: 0.6345 [2021-03-28 16:52:30 swin_base_patch4_window7_224] INFO: Epoch: [288] [1120/1251] eta: 0:01:23 lr: 0.000013 loss: 2.5801 (2.6520) grad_norm: 3.2733 (inf) time: 0.6427 [2021-03-28 16:52:37 swin_base_patch4_window7_224] INFO: Epoch: [288] [1130/1251] eta: 0:01:17 lr: 0.000013 loss: 2.7575 (2.6525) grad_norm: 3.4176 (inf) time: 0.6398 [2021-03-28 16:52:43 swin_base_patch4_window7_224] INFO: Epoch: [288] [1140/1251] eta: 0:01:10 lr: 0.000013 loss: 2.5708 (2.6500) grad_norm: 3.5461 (inf) time: 0.6319 [2021-03-28 16:52:49 swin_base_patch4_window7_224] INFO: Epoch: [288] [1150/1251] eta: 0:01:04 lr: 0.000013 loss: 2.3226 (2.6488) grad_norm: 3.8154 (inf) time: 0.6334 [2021-03-28 16:52:56 swin_base_patch4_window7_224] INFO: Epoch: [288] [1160/1251] eta: 0:00:57 lr: 0.000013 loss: 2.5885 (2.6471) grad_norm: 3.5272 (inf) time: 0.6354 [2021-03-28 16:53:02 swin_base_patch4_window7_224] INFO: Epoch: [288] [1170/1251] eta: 0:00:51 lr: 0.000013 loss: 2.5602 (2.6470) grad_norm: 3.5251 (inf) time: 0.6385 [2021-03-28 16:53:08 swin_base_patch4_window7_224] INFO: Epoch: [288] [1180/1251] eta: 0:00:45 lr: 0.000013 loss: 2.8092 (2.6489) grad_norm: 3.5251 (inf) time: 0.6380 [2021-03-28 16:53:15 swin_base_patch4_window7_224] INFO: Epoch: [288] [1190/1251] eta: 0:00:38 lr: 0.000013 loss: 2.8092 (2.6499) grad_norm: 3.5602 (inf) time: 0.6303 [2021-03-28 16:53:21 swin_base_patch4_window7_224] INFO: Epoch: [288] [1200/1251] eta: 0:00:32 lr: 0.000013 loss: 2.8068 (2.6519) grad_norm: 3.5187 (inf) time: 0.6313 [2021-03-28 16:53:27 swin_base_patch4_window7_224] INFO: Epoch: [288] [1210/1251] eta: 0:00:26 lr: 0.000013 loss: 2.8329 (2.6517) grad_norm: 3.5187 (inf) time: 0.6330 [2021-03-28 16:53:34 swin_base_patch4_window7_224] INFO: Epoch: [288] [1220/1251] eta: 0:00:19 lr: 0.000013 loss: 2.6068 (2.6513) grad_norm: 3.5535 (inf) time: 0.6379 [2021-03-28 16:53:40 swin_base_patch4_window7_224] INFO: Epoch: [288] [1230/1251] eta: 0:00:13 lr: 0.000013 loss: 2.6124 (2.6511) grad_norm: 3.5411 (inf) time: 0.6357 [2021-03-28 16:53:46 swin_base_patch4_window7_224] INFO: Epoch: [288] [1240/1251] eta: 0:00:07 lr: 0.000013 loss: 2.8425 (2.6535) grad_norm: 3.4064 (inf) time: 0.6319 [2021-03-28 16:53:53 swin_base_patch4_window7_224] INFO: Epoch: [288] [1250/1251] eta: 0:00:00 lr: 0.000013 loss: 2.7802 (2.6525) grad_norm: 3.3879 (inf) time: 0.6267 [2021-03-28 16:54:06 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:03 loss: 0.7824 (0.7824) acc1: 81.2500 (81.2500) acc5: 98.4375 (98.4375) [2021-03-28 16:54:07 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.7602 (0.7512) acc1: 81.2500 (83.0966) acc5: 96.8750 (96.3068) [2021-03-28 16:54:09 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7520 (0.7505) acc1: 82.8125 (83.1845) acc5: 95.3125 (96.2798) [2021-03-28 16:54:11 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.7943 (0.7892) acc1: 81.2500 (81.5524) acc5: 95.3125 (96.0685) [2021-03-28 16:54:13 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7449 (0.7583) acc1: 81.2500 (82.0884) acc5: 96.8750 (96.5701) [2021-03-28 16:54:14 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6738 (0.7512) acc1: 82.8125 (82.1120) acc5: 96.8750 (96.5440) [2021-03-28 16:54:33 swin_base_patch4_window7_224] INFO: * Acc@1 83.330 Acc@5 96.438 loss 0.737 [2021-03-28 16:54:33 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.3% [2021-03-28 16:54:33 swin_base_patch4_window7_224] INFO: Max accuracy: 83.40% [2021-03-28 16:54:38 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 0/1251] eta: 1:36:58 lr: 0.000013 loss: 2.5728 (2.5728) grad_norm: 3.0322 (3.0322) time: 4.6513 [2021-03-28 16:54:44 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 10/1251] eta: 0:20:45 lr: 0.000013 loss: 2.5728 (2.5902) grad_norm: 3.3368 (3.3789) time: 1.0034 [2021-03-28 16:54:50 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 20/1251] eta: 0:16:51 lr: 0.000013 loss: 2.7639 (2.6483) grad_norm: 3.5138 (3.6123) time: 0.6304 [2021-03-28 16:54:57 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 30/1251] eta: 0:15:29 lr: 0.000013 loss: 2.8903 (2.6455) grad_norm: 3.5842 (3.7632) time: 0.6287 [2021-03-28 16:55:03 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 40/1251] eta: 0:14:43 lr: 0.000013 loss: 2.4962 (2.5874) grad_norm: 3.3919 (3.6419) time: 0.6333 [2021-03-28 16:55:09 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 50/1251] eta: 0:14:13 lr: 0.000013 loss: 2.3059 (2.5493) grad_norm: 3.5525 (3.8168) time: 0.6319 [2021-03-28 16:55:16 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 60/1251] eta: 0:13:51 lr: 0.000013 loss: 2.6580 (2.5625) grad_norm: 3.8587 (4.0176) time: 0.6338 [2021-03-28 16:55:22 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 70/1251] eta: 0:13:36 lr: 0.000013 loss: 2.8242 (2.5715) grad_norm: 3.6413 (3.9311) time: 0.6409 [2021-03-28 16:55:29 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 80/1251] eta: 0:13:21 lr: 0.000013 loss: 2.8206 (2.5911) grad_norm: 3.4782 (3.8819) time: 0.6403 [2021-03-28 16:55:35 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 90/1251] eta: 0:13:10 lr: 0.000013 loss: 2.6678 (2.5741) grad_norm: 3.4210 (3.8207) time: 0.6436 [2021-03-28 16:55:41 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 100/1251] eta: 0:12:58 lr: 0.000013 loss: 2.4696 (2.5758) grad_norm: 3.2824 (3.8234) time: 0.6436 [2021-03-28 16:55:48 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 110/1251] eta: 0:12:46 lr: 0.000013 loss: 2.5312 (2.5883) grad_norm: 3.4605 (3.8134) time: 0.6324 [2021-03-28 16:55:54 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 120/1251] eta: 0:12:36 lr: 0.000013 loss: 2.7004 (2.5816) grad_norm: 3.5531 (3.8344) time: 0.6354 [2021-03-28 16:56:00 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 130/1251] eta: 0:12:27 lr: 0.000013 loss: 2.6409 (2.5759) grad_norm: 3.4601 (3.8087) time: 0.6369 [2021-03-28 16:56:07 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 140/1251] eta: 0:12:18 lr: 0.000013 loss: 2.7148 (2.5987) grad_norm: 3.2796 (3.7903) time: 0.6353 [2021-03-28 16:56:13 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 150/1251] eta: 0:12:09 lr: 0.000013 loss: 2.7305 (2.5942) grad_norm: 3.5761 (3.7892) time: 0.6348 [2021-03-28 16:56:20 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 160/1251] eta: 0:12:01 lr: 0.000013 loss: 2.6087 (2.5991) grad_norm: 3.4738 (3.8148) time: 0.6363 [2021-03-28 16:56:26 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 170/1251] eta: 0:11:53 lr: 0.000013 loss: 2.7749 (2.6054) grad_norm: 3.4624 (3.8090) time: 0.6430 [2021-03-28 16:56:32 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 180/1251] eta: 0:11:45 lr: 0.000013 loss: 2.7763 (2.6087) grad_norm: 3.6557 (3.8049) time: 0.6410 [2021-03-28 16:56:39 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 190/1251] eta: 0:11:37 lr: 0.000013 loss: 2.6428 (2.6085) grad_norm: 3.6382 (3.8005) time: 0.6331 [2021-03-28 16:56:45 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 200/1251] eta: 0:11:29 lr: 0.000013 loss: 2.4501 (2.6041) grad_norm: 3.4477 (3.8156) time: 0.6322 [2021-03-28 16:56:51 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 210/1251] eta: 0:11:21 lr: 0.000013 loss: 2.6005 (2.6027) grad_norm: 3.4477 (3.8042) time: 0.6333 [2021-03-28 16:56:58 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 220/1251] eta: 0:11:14 lr: 0.000013 loss: 2.7547 (2.6148) grad_norm: 3.5480 (3.7990) time: 0.6322 [2021-03-28 16:57:04 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 230/1251] eta: 0:11:06 lr: 0.000013 loss: 2.7637 (2.6213) grad_norm: 3.2969 (3.7740) time: 0.6303 [2021-03-28 16:57:10 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 240/1251] eta: 0:10:59 lr: 0.000013 loss: 2.7637 (2.6263) grad_norm: 3.1099 (3.7583) time: 0.6301 [2021-03-28 16:57:17 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 250/1251] eta: 0:10:52 lr: 0.000013 loss: 2.7684 (2.6259) grad_norm: 3.3085 (3.7579) time: 0.6361 [2021-03-28 16:57:23 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 260/1251] eta: 0:10:45 lr: 0.000013 loss: 2.3975 (2.6256) grad_norm: 3.5075 (3.7556) time: 0.6387 [2021-03-28 16:57:29 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 270/1251] eta: 0:10:38 lr: 0.000013 loss: 2.4498 (2.6211) grad_norm: 3.4742 (3.7679) time: 0.6368 [2021-03-28 16:57:36 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 280/1251] eta: 0:10:30 lr: 0.000013 loss: 2.6210 (2.6242) grad_norm: 3.4506 (3.7556) time: 0.6330 [2021-03-28 16:57:42 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 290/1251] eta: 0:10:23 lr: 0.000013 loss: 2.7638 (2.6273) grad_norm: 3.5621 (3.7882) time: 0.6307 [2021-03-28 16:57:48 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 300/1251] eta: 0:10:17 lr: 0.000013 loss: 2.7638 (2.6320) grad_norm: 3.4948 (3.7786) time: 0.6363 [2021-03-28 16:57:55 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 310/1251] eta: 0:10:10 lr: 0.000013 loss: 2.6817 (2.6289) grad_norm: 3.3161 (3.7926) time: 0.6366 [2021-03-28 16:58:01 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 320/1251] eta: 0:10:02 lr: 0.000013 loss: 2.6597 (2.6289) grad_norm: 3.4823 (3.7937) time: 0.6290 [2021-03-28 16:58:07 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 330/1251] eta: 0:09:56 lr: 0.000013 loss: 2.7062 (2.6305) grad_norm: 3.4823 (3.7870) time: 0.6296 [2021-03-28 16:58:14 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 340/1251] eta: 0:09:49 lr: 0.000013 loss: 2.6848 (2.6267) grad_norm: 3.4387 (3.7899) time: 0.6364 [2021-03-28 16:58:20 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 350/1251] eta: 0:09:42 lr: 0.000013 loss: 2.6370 (2.6274) grad_norm: 3.8248 (3.7928) time: 0.6418 [2021-03-28 16:58:27 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 360/1251] eta: 0:09:36 lr: 0.000013 loss: 2.7834 (2.6275) grad_norm: 3.5701 (3.8021) time: 0.6410 [2021-03-28 16:58:33 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 370/1251] eta: 0:09:29 lr: 0.000013 loss: 2.7673 (2.6288) grad_norm: 3.8744 (3.8092) time: 0.6306 [2021-03-28 16:58:39 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 380/1251] eta: 0:09:22 lr: 0.000013 loss: 2.6853 (2.6228) grad_norm: 3.4420 (3.8697) time: 0.6265 [2021-03-28 16:58:45 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 390/1251] eta: 0:09:15 lr: 0.000013 loss: 2.6994 (2.6269) grad_norm: 3.4436 (3.8671) time: 0.6309 [2021-03-28 16:58:52 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 400/1251] eta: 0:09:08 lr: 0.000013 loss: 2.8312 (2.6255) grad_norm: 3.5827 (3.8599) time: 0.6306 [2021-03-28 16:58:58 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 410/1251] eta: 0:09:01 lr: 0.000013 loss: 2.6498 (2.6252) grad_norm: 3.5517 (3.8668) time: 0.6277 [2021-03-28 16:59:04 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 420/1251] eta: 0:08:55 lr: 0.000013 loss: 2.5277 (2.6198) grad_norm: 3.6462 (3.8683) time: 0.6294 [2021-03-28 16:59:11 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 430/1251] eta: 0:08:48 lr: 0.000013 loss: 2.5897 (2.6222) grad_norm: 3.5794 (3.8655) time: 0.6381 [2021-03-28 16:59:17 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 440/1251] eta: 0:08:42 lr: 0.000013 loss: 2.5897 (2.6194) grad_norm: 3.5410 (3.8764) time: 0.6411 [2021-03-28 16:59:24 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 450/1251] eta: 0:08:35 lr: 0.000013 loss: 2.5906 (2.6192) grad_norm: 3.4478 (3.8708) time: 0.6366 [2021-03-28 16:59:30 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 460/1251] eta: 0:08:28 lr: 0.000013 loss: 2.7632 (2.6169) grad_norm: 3.4583 (3.8636) time: 0.6318 [2021-03-28 16:59:36 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 470/1251] eta: 0:08:22 lr: 0.000013 loss: 2.6911 (2.6186) grad_norm: 3.5137 (3.8632) time: 0.6297 [2021-03-28 16:59:42 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 480/1251] eta: 0:08:15 lr: 0.000013 loss: 2.6911 (2.6211) grad_norm: 3.9898 (3.8647) time: 0.6320 [2021-03-28 16:59:49 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 490/1251] eta: 0:08:09 lr: 0.000013 loss: 2.5708 (2.6144) grad_norm: 3.5904 (3.8734) time: 0.6316 [2021-03-28 16:59:55 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 500/1251] eta: 0:08:02 lr: 0.000013 loss: 2.5708 (2.6211) grad_norm: 3.4114 (3.8652) time: 0.6278 [2021-03-28 17:00:01 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 510/1251] eta: 0:07:55 lr: 0.000013 loss: 2.9297 (2.6217) grad_norm: 3.2149 (3.8538) time: 0.6295 [2021-03-28 17:00:08 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 520/1251] eta: 0:07:49 lr: 0.000013 loss: 2.7477 (2.6249) grad_norm: 3.2390 (3.8513) time: 0.6388 [2021-03-28 17:00:14 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 530/1251] eta: 0:07:42 lr: 0.000013 loss: 2.8214 (2.6248) grad_norm: 3.3553 (3.8517) time: 0.6351 [2021-03-28 17:00:20 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 540/1251] eta: 0:07:36 lr: 0.000013 loss: 2.8537 (2.6266) grad_norm: 3.7730 (3.8519) time: 0.6288 [2021-03-28 17:00:27 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 550/1251] eta: 0:07:29 lr: 0.000013 loss: 2.7986 (2.6268) grad_norm: 3.8729 (3.8522) time: 0.6374 [2021-03-28 17:00:33 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 560/1251] eta: 0:07:23 lr: 0.000013 loss: 2.7383 (2.6266) grad_norm: 3.6750 (3.8612) time: 0.6404 [2021-03-28 17:00:40 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 570/1251] eta: 0:07:16 lr: 0.000013 loss: 2.6137 (2.6259) grad_norm: 3.3120 (3.8567) time: 0.6385 [2021-03-28 17:00:46 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 580/1251] eta: 0:07:10 lr: 0.000013 loss: 2.7628 (2.6288) grad_norm: 3.3786 (3.8904) time: 0.6329 [2021-03-28 17:00:52 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 590/1251] eta: 0:07:03 lr: 0.000013 loss: 2.8740 (2.6303) grad_norm: 3.8236 (3.8905) time: 0.6349 [2021-03-28 17:00:59 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 600/1251] eta: 0:06:57 lr: 0.000013 loss: 2.6027 (2.6291) grad_norm: 3.8236 (3.8940) time: 0.6379 [2021-03-28 17:01:05 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 610/1251] eta: 0:06:50 lr: 0.000013 loss: 2.6360 (2.6329) grad_norm: 3.7489 (3.9663) time: 0.6286 [2021-03-28 17:01:11 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 620/1251] eta: 0:06:44 lr: 0.000013 loss: 2.8229 (2.6319) grad_norm: 3.3938 (3.9599) time: 0.6330 [2021-03-28 17:01:18 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 630/1251] eta: 0:06:37 lr: 0.000013 loss: 2.5108 (2.6278) grad_norm: 3.3124 (3.9530) time: 0.6364 [2021-03-28 17:01:24 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 640/1251] eta: 0:06:31 lr: 0.000013 loss: 2.5104 (2.6269) grad_norm: 3.4059 (3.9463) time: 0.6357 [2021-03-28 17:01:30 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 650/1251] eta: 0:06:25 lr: 0.000013 loss: 2.5848 (2.6248) grad_norm: 3.6299 (3.9460) time: 0.6373 [2021-03-28 17:01:37 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 660/1251] eta: 0:06:18 lr: 0.000013 loss: 2.6810 (2.6261) grad_norm: 3.7679 (3.9465) time: 0.6353 [2021-03-28 17:01:43 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 670/1251] eta: 0:06:12 lr: 0.000013 loss: 2.7696 (2.6268) grad_norm: 3.6088 (3.9484) time: 0.6353 [2021-03-28 17:01:49 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 680/1251] eta: 0:06:05 lr: 0.000013 loss: 2.7027 (2.6245) grad_norm: 3.5510 (3.9454) time: 0.6373 [2021-03-28 17:01:56 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 690/1251] eta: 0:05:59 lr: 0.000013 loss: 2.6170 (2.6252) grad_norm: 3.5279 (3.9495) time: 0.6325 [2021-03-28 17:02:02 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 700/1251] eta: 0:05:52 lr: 0.000013 loss: 2.6957 (2.6258) grad_norm: 3.6644 (3.9513) time: 0.6273 [2021-03-28 17:02:08 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 710/1251] eta: 0:05:46 lr: 0.000013 loss: 2.6506 (2.6242) grad_norm: 3.6644 (3.9495) time: 0.6337 [2021-03-28 17:02:15 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 720/1251] eta: 0:05:39 lr: 0.000013 loss: 2.6652 (2.6244) grad_norm: 3.6189 (3.9457) time: 0.6337 [2021-03-28 17:02:21 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 730/1251] eta: 0:05:33 lr: 0.000013 loss: 2.7722 (2.6262) grad_norm: 3.3748 (3.9358) time: 0.6303 [2021-03-28 17:02:27 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 740/1251] eta: 0:05:26 lr: 0.000013 loss: 2.6561 (2.6239) grad_norm: 3.2628 (3.9371) time: 0.6313 [2021-03-28 17:02:34 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 750/1251] eta: 0:05:20 lr: 0.000013 loss: 2.4976 (2.6253) grad_norm: 3.6632 (3.9430) time: 0.6317 [2021-03-28 17:02:40 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 760/1251] eta: 0:05:14 lr: 0.000013 loss: 2.7978 (2.6269) grad_norm: 3.6632 (3.9460) time: 0.6319 [2021-03-28 17:02:46 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 770/1251] eta: 0:05:07 lr: 0.000013 loss: 2.7245 (2.6245) grad_norm: 3.4805 (3.9395) time: 0.6289 [2021-03-28 17:02:53 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 780/1251] eta: 0:05:01 lr: 0.000013 loss: 2.7245 (2.6280) grad_norm: 3.4263 (3.9337) time: 0.6300 [2021-03-28 17:02:59 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 790/1251] eta: 0:04:54 lr: 0.000013 loss: 2.8423 (2.6263) grad_norm: 3.4788 (3.9373) time: 0.6299 [2021-03-28 17:03:05 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 800/1251] eta: 0:04:48 lr: 0.000013 loss: 2.7902 (2.6264) grad_norm: 3.7494 (3.9340) time: 0.6279 [2021-03-28 17:03:11 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 810/1251] eta: 0:04:41 lr: 0.000013 loss: 2.8571 (2.6288) grad_norm: 3.6198 (3.9317) time: 0.6346 [2021-03-28 17:03:18 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 820/1251] eta: 0:04:35 lr: 0.000013 loss: 2.7976 (2.6308) grad_norm: 3.6198 (3.9303) time: 0.6420 [2021-03-28 17:03:24 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 830/1251] eta: 0:04:29 lr: 0.000013 loss: 2.7254 (2.6304) grad_norm: 3.5643 (3.9258) time: 0.6380 [2021-03-28 17:03:31 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 840/1251] eta: 0:04:22 lr: 0.000013 loss: 2.6378 (2.6282) grad_norm: 3.4132 (3.9306) time: 0.6358 [2021-03-28 17:03:37 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 850/1251] eta: 0:04:16 lr: 0.000013 loss: 2.7389 (2.6293) grad_norm: 3.4333 (3.9313) time: 0.6408 [2021-03-28 17:03:43 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 860/1251] eta: 0:04:09 lr: 0.000013 loss: 2.7829 (2.6316) grad_norm: 3.5666 (3.9297) time: 0.6371 [2021-03-28 17:03:50 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 870/1251] eta: 0:04:03 lr: 0.000013 loss: 2.8238 (2.6323) grad_norm: 3.6567 (3.9318) time: 0.6353 [2021-03-28 17:03:56 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 880/1251] eta: 0:03:57 lr: 0.000013 loss: 2.6968 (2.6334) grad_norm: 3.6512 (3.9324) time: 0.6407 [2021-03-28 17:04:03 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 890/1251] eta: 0:03:50 lr: 0.000013 loss: 2.6474 (2.6338) grad_norm: 3.5907 (3.9290) time: 0.6372 [2021-03-28 17:04:09 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 900/1251] eta: 0:03:44 lr: 0.000013 loss: 2.6232 (2.6326) grad_norm: 3.7203 (3.9290) time: 0.6334 [2021-03-28 17:04:15 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 910/1251] eta: 0:03:37 lr: 0.000013 loss: 2.5568 (2.6317) grad_norm: 3.7837 (3.9358) time: 0.6365 [2021-03-28 17:04:22 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 920/1251] eta: 0:03:31 lr: 0.000013 loss: 2.7806 (2.6336) grad_norm: 3.7473 (3.9358) time: 0.6338 [2021-03-28 17:04:28 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 930/1251] eta: 0:03:25 lr: 0.000013 loss: 2.9080 (2.6369) grad_norm: 3.7500 (3.9412) time: 0.6328 [2021-03-28 17:04:34 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 940/1251] eta: 0:03:18 lr: 0.000013 loss: 2.8341 (2.6373) grad_norm: 3.7500 (3.9517) time: 0.6378 [2021-03-28 17:04:41 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 950/1251] eta: 0:03:12 lr: 0.000013 loss: 2.8048 (2.6384) grad_norm: 3.4791 (3.9500) time: 0.6324 [2021-03-28 17:04:47 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 960/1251] eta: 0:03:05 lr: 0.000013 loss: 2.7088 (2.6369) grad_norm: 3.6968 (3.9574) time: 0.6251 [2021-03-28 17:04:53 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 970/1251] eta: 0:02:59 lr: 0.000013 loss: 2.6122 (2.6382) grad_norm: 3.8297 (3.9582) time: 0.6261 [2021-03-28 17:04:59 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 980/1251] eta: 0:02:52 lr: 0.000013 loss: 2.8959 (2.6394) grad_norm: 3.6874 (3.9539) time: 0.6304 [2021-03-28 17:05:06 swin_base_patch4_window7_224] INFO: Epoch: [289] [ 990/1251] eta: 0:02:46 lr: 0.000013 loss: 2.8633 (2.6394) grad_norm: 3.4594 (3.9541) time: 0.6339 [2021-03-28 17:05:12 swin_base_patch4_window7_224] INFO: Epoch: [289] [1000/1251] eta: 0:02:40 lr: 0.000013 loss: 2.7484 (2.6391) grad_norm: 3.5852 (3.9515) time: 0.6304 [2021-03-28 17:05:18 swin_base_patch4_window7_224] INFO: Epoch: [289] [1010/1251] eta: 0:02:33 lr: 0.000013 loss: 2.7383 (2.6399) grad_norm: 3.5996 (3.9512) time: 0.6262 [2021-03-28 17:05:25 swin_base_patch4_window7_224] INFO: Epoch: [289] [1020/1251] eta: 0:02:27 lr: 0.000013 loss: 2.6782 (2.6391) grad_norm: 3.5506 (3.9485) time: 0.6293 [2021-03-28 17:05:31 swin_base_patch4_window7_224] INFO: Epoch: [289] [1030/1251] eta: 0:02:20 lr: 0.000013 loss: 2.7467 (2.6386) grad_norm: 3.6443 (3.9790) time: 0.6340 [2021-03-28 17:05:37 swin_base_patch4_window7_224] INFO: Epoch: [289] [1040/1251] eta: 0:02:14 lr: 0.000013 loss: 2.7487 (2.6380) grad_norm: 3.4372 (3.9745) time: 0.6296 [2021-03-28 17:05:44 swin_base_patch4_window7_224] INFO: Epoch: [289] [1050/1251] eta: 0:02:08 lr: 0.000013 loss: 2.5908 (2.6381) grad_norm: 4.0036 (3.9830) time: 0.6293 [2021-03-28 17:05:50 swin_base_patch4_window7_224] INFO: Epoch: [289] [1060/1251] eta: 0:02:01 lr: 0.000013 loss: 2.6994 (2.6386) grad_norm: 4.2887 (3.9845) time: 0.6340 [2021-03-28 17:05:56 swin_base_patch4_window7_224] INFO: Epoch: [289] [1070/1251] eta: 0:01:55 lr: 0.000013 loss: 2.6994 (2.6357) grad_norm: 3.4993 (3.9793) time: 0.6337 [2021-03-28 17:06:03 swin_base_patch4_window7_224] INFO: Epoch: [289] [1080/1251] eta: 0:01:49 lr: 0.000013 loss: 2.7775 (2.6377) grad_norm: 3.4100 (3.9784) time: 0.6325 [2021-03-28 17:06:09 swin_base_patch4_window7_224] INFO: Epoch: [289] [1090/1251] eta: 0:01:42 lr: 0.000013 loss: 2.8193 (2.6387) grad_norm: 3.7407 (3.9970) time: 0.6364 [2021-03-28 17:06:15 swin_base_patch4_window7_224] INFO: Epoch: [289] [1100/1251] eta: 0:01:36 lr: 0.000013 loss: 2.7224 (2.6392) grad_norm: 3.6858 (3.9973) time: 0.6375 [2021-03-28 17:06:22 swin_base_patch4_window7_224] INFO: Epoch: [289] [1110/1251] eta: 0:01:29 lr: 0.000013 loss: 2.6928 (2.6387) grad_norm: 3.6858 (3.9963) time: 0.6297 [2021-03-28 17:06:28 swin_base_patch4_window7_224] INFO: Epoch: [289] [1120/1251] eta: 0:01:23 lr: 0.000013 loss: 2.5377 (2.6388) grad_norm: 3.6130 (3.9936) time: 0.6238 [2021-03-28 17:06:34 swin_base_patch4_window7_224] INFO: Epoch: [289] [1130/1251] eta: 0:01:17 lr: 0.000013 loss: 2.6082 (2.6388) grad_norm: 3.6130 (3.9917) time: 0.6278 [2021-03-28 17:06:40 swin_base_patch4_window7_224] INFO: Epoch: [289] [1140/1251] eta: 0:01:10 lr: 0.000013 loss: 2.6929 (2.6380) grad_norm: 3.5462 (3.9902) time: 0.6333 [2021-03-28 17:06:47 swin_base_patch4_window7_224] INFO: Epoch: [289] [1150/1251] eta: 0:01:04 lr: 0.000013 loss: 2.5165 (2.6359) grad_norm: 3.3339 (3.9864) time: 0.6316 [2021-03-28 17:06:53 swin_base_patch4_window7_224] INFO: Epoch: [289] [1160/1251] eta: 0:00:57 lr: 0.000013 loss: 2.6048 (2.6361) grad_norm: 3.4619 (3.9836) time: 0.6357 [2021-03-28 17:07:00 swin_base_patch4_window7_224] INFO: Epoch: [289] [1170/1251] eta: 0:00:51 lr: 0.000013 loss: 2.7440 (2.6360) grad_norm: 3.4837 (3.9810) time: 0.6370 [2021-03-28 17:07:06 swin_base_patch4_window7_224] INFO: Epoch: [289] [1180/1251] eta: 0:00:45 lr: 0.000013 loss: 2.7110 (2.6359) grad_norm: 3.3483 (3.9763) time: 0.6334 [2021-03-28 17:07:12 swin_base_patch4_window7_224] INFO: Epoch: [289] [1190/1251] eta: 0:00:38 lr: 0.000013 loss: 2.7799 (2.6366) grad_norm: 3.5341 (3.9744) time: 0.6356 [2021-03-28 17:07:19 swin_base_patch4_window7_224] INFO: Epoch: [289] [1200/1251] eta: 0:00:32 lr: 0.000013 loss: 2.8346 (2.6379) grad_norm: 3.7789 (3.9750) time: 0.6328 [2021-03-28 17:07:25 swin_base_patch4_window7_224] INFO: Epoch: [289] [1210/1251] eta: 0:00:26 lr: 0.000013 loss: 2.7461 (2.6371) grad_norm: 3.8292 (3.9762) time: 0.6263 [2021-03-28 17:07:31 swin_base_patch4_window7_224] INFO: Epoch: [289] [1220/1251] eta: 0:00:19 lr: 0.000013 loss: 2.5944 (2.6372) grad_norm: 3.5574 (3.9733) time: 0.6228 [2021-03-28 17:07:37 swin_base_patch4_window7_224] INFO: Epoch: [289] [1230/1251] eta: 0:00:13 lr: 0.000013 loss: 2.7593 (2.6376) grad_norm: 3.4255 (3.9706) time: 0.6234 [2021-03-28 17:07:44 swin_base_patch4_window7_224] INFO: Epoch: [289] [1240/1251] eta: 0:00:07 lr: 0.000013 loss: 2.7593 (2.6375) grad_norm: 3.4255 (3.9694) time: 0.6326 [2021-03-28 17:07:50 swin_base_patch4_window7_224] INFO: Epoch: [289] [1250/1251] eta: 0:00:00 lr: 0.000013 loss: 2.7553 (2.6382) grad_norm: 3.4301 (3.9688) time: 0.6378 [2021-03-28 17:08:03 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:57 loss: 0.8581 (0.8581) acc1: 79.6875 (79.6875) acc5: 96.8750 (96.8750) [2021-03-28 17:08:05 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.8581 (0.7925) acc1: 82.8125 (82.1023) acc5: 95.3125 (95.5966) [2021-03-28 17:08:08 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.6880 (0.7355) acc1: 82.8125 (82.5893) acc5: 96.8750 (96.5774) [2021-03-28 17:08:10 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6779 (0.7301) acc1: 82.8125 (82.7117) acc5: 98.4375 (96.8246) [2021-03-28 17:08:12 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6779 (0.7507) acc1: 82.8125 (82.3552) acc5: 96.8750 (96.6463) [2021-03-28 17:08:13 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7616 (0.7475) acc1: 82.8125 (82.4640) acc5: 96.8750 (96.6400) [2021-03-28 17:08:31 swin_base_patch4_window7_224] INFO: * Acc@1 83.402 Acc@5 96.466 loss 0.735 [2021-03-28 17:08:31 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 17:08:31 swin_base_patch4_window7_224] INFO: Max accuracy: 83.40% [2021-03-28 17:08:35 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 0/1251] eta: 1:25:45 lr: 0.000013 loss: 2.8601 (2.8601) grad_norm: 5.1932 (5.1932) time: 4.1130 [2021-03-28 17:08:42 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 10/1251] eta: 0:20:08 lr: 0.000013 loss: 2.7494 (2.7385) grad_norm: 4.3864 (4.9247) time: 0.9739 [2021-03-28 17:08:48 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 20/1251] eta: 0:16:48 lr: 0.000013 loss: 2.6594 (2.6241) grad_norm: 3.6795 (4.4989) time: 0.6548 [2021-03-28 17:08:55 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 30/1251] eta: 0:15:28 lr: 0.000013 loss: 2.5682 (2.6083) grad_norm: 3.5883 (4.5995) time: 0.6427 [2021-03-28 17:09:01 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 40/1251] eta: 0:14:43 lr: 0.000013 loss: 2.7426 (2.6128) grad_norm: 3.5953 (4.3747) time: 0.6353 [2021-03-28 17:09:07 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 50/1251] eta: 0:14:12 lr: 0.000013 loss: 2.6681 (2.5917) grad_norm: 3.4610 (4.2121) time: 0.6316 [2021-03-28 17:09:14 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 60/1251] eta: 0:13:52 lr: 0.000013 loss: 2.6064 (2.5665) grad_norm: 3.5905 (4.1758) time: 0.6356 [2021-03-28 17:09:20 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 70/1251] eta: 0:13:34 lr: 0.000013 loss: 2.5436 (2.5483) grad_norm: 3.6186 (4.1296) time: 0.6375 [2021-03-28 17:09:26 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 80/1251] eta: 0:13:18 lr: 0.000013 loss: 2.7084 (2.5806) grad_norm: 3.4744 (4.0807) time: 0.6289 [2021-03-28 17:09:33 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 90/1251] eta: 0:13:06 lr: 0.000013 loss: 2.8004 (2.6146) grad_norm: 3.5447 (4.0716) time: 0.6344 [2021-03-28 17:09:39 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 100/1251] eta: 0:12:55 lr: 0.000013 loss: 2.7619 (2.6146) grad_norm: 3.4808 (4.0173) time: 0.6401 [2021-03-28 17:09:45 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 110/1251] eta: 0:12:44 lr: 0.000013 loss: 2.7045 (2.6156) grad_norm: 3.6599 (4.0186) time: 0.6359 [2021-03-28 17:09:52 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 120/1251] eta: 0:12:34 lr: 0.000013 loss: 2.7045 (2.6209) grad_norm: 3.6922 (4.0897) time: 0.6339 [2021-03-28 17:09:58 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 130/1251] eta: 0:12:24 lr: 0.000013 loss: 2.6914 (2.6099) grad_norm: 3.4802 (4.0720) time: 0.6343 [2021-03-28 17:10:04 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 140/1251] eta: 0:12:15 lr: 0.000013 loss: 2.7359 (2.6189) grad_norm: 3.4516 (4.0379) time: 0.6358 [2021-03-28 17:10:11 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 150/1251] eta: 0:12:06 lr: 0.000013 loss: 2.8646 (2.6314) grad_norm: 3.3686 (4.0281) time: 0.6325 [2021-03-28 17:10:17 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 160/1251] eta: 0:11:58 lr: 0.000013 loss: 2.8898 (2.6381) grad_norm: 3.6770 (4.0240) time: 0.6288 [2021-03-28 17:10:23 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 170/1251] eta: 0:11:50 lr: 0.000013 loss: 2.8667 (2.6509) grad_norm: 3.9785 (4.0375) time: 0.6338 [2021-03-28 17:10:30 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 180/1251] eta: 0:11:43 lr: 0.000013 loss: 2.8094 (2.6528) grad_norm: 3.7037 (4.0209) time: 0.6415 [2021-03-28 17:10:36 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 190/1251] eta: 0:11:34 lr: 0.000013 loss: 2.7889 (2.6565) grad_norm: 3.4381 (3.9921) time: 0.6372 [2021-03-28 17:10:42 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 200/1251] eta: 0:11:27 lr: 0.000013 loss: 2.6484 (2.6478) grad_norm: 3.4399 (4.0098) time: 0.6305 [2021-03-28 17:10:49 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 210/1251] eta: 0:11:19 lr: 0.000013 loss: 2.6199 (2.6473) grad_norm: 3.5423 (3.9917) time: 0.6276 [2021-03-28 17:10:55 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 220/1251] eta: 0:11:11 lr: 0.000013 loss: 2.5226 (2.6338) grad_norm: 3.4927 (3.9736) time: 0.6296 [2021-03-28 17:11:01 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 230/1251] eta: 0:11:04 lr: 0.000013 loss: 2.4872 (2.6284) grad_norm: 3.6102 (3.9651) time: 0.6367 [2021-03-28 17:11:08 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 240/1251] eta: 0:10:57 lr: 0.000013 loss: 2.6805 (2.6281) grad_norm: 3.7543 (3.9583) time: 0.6401 [2021-03-28 17:11:14 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 250/1251] eta: 0:10:50 lr: 0.000013 loss: 2.7545 (2.6292) grad_norm: 3.7396 (3.9438) time: 0.6328 [2021-03-28 17:11:21 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 260/1251] eta: 0:10:43 lr: 0.000013 loss: 2.8185 (2.6346) grad_norm: 3.5801 (3.9220) time: 0.6331 [2021-03-28 17:11:27 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 270/1251] eta: 0:10:36 lr: 0.000013 loss: 2.7935 (2.6349) grad_norm: 3.4658 (3.9238) time: 0.6378 [2021-03-28 17:11:33 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 280/1251] eta: 0:10:29 lr: 0.000013 loss: 2.7719 (2.6439) grad_norm: 3.4223 (3.9000) time: 0.6361 [2021-03-28 17:11:40 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 290/1251] eta: 0:10:23 lr: 0.000013 loss: 2.5901 (2.6319) grad_norm: 3.2057 (3.8942) time: 0.6427 [2021-03-28 17:11:46 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 300/1251] eta: 0:10:15 lr: 0.000013 loss: 2.5259 (2.6296) grad_norm: 3.4832 (3.8857) time: 0.6377 [2021-03-28 17:11:52 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 310/1251] eta: 0:10:08 lr: 0.000013 loss: 2.6789 (2.6338) grad_norm: 3.5485 (3.8894) time: 0.6269 [2021-03-28 17:11:59 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 320/1251] eta: 0:10:01 lr: 0.000013 loss: 2.7381 (2.6327) grad_norm: 3.7734 (3.8765) time: 0.6233 [2021-03-28 17:12:05 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 330/1251] eta: 0:09:54 lr: 0.000013 loss: 2.8192 (2.6338) grad_norm: 3.6740 (3.8848) time: 0.6264 [2021-03-28 17:12:11 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 340/1251] eta: 0:09:47 lr: 0.000013 loss: 2.8280 (2.6366) grad_norm: 3.4918 (3.8740) time: 0.6307 [2021-03-28 17:12:17 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 350/1251] eta: 0:09:40 lr: 0.000013 loss: 2.7259 (2.6369) grad_norm: 3.4926 (3.9111) time: 0.6266 [2021-03-28 17:12:24 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 360/1251] eta: 0:09:34 lr: 0.000013 loss: 2.6574 (2.6353) grad_norm: 3.7230 (3.9039) time: 0.6280 [2021-03-28 17:12:30 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 370/1251] eta: 0:09:27 lr: 0.000013 loss: 2.7872 (2.6378) grad_norm: 3.4084 (3.9026) time: 0.6314 [2021-03-28 17:12:36 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 380/1251] eta: 0:09:20 lr: 0.000013 loss: 2.7609 (2.6416) grad_norm: 3.8505 (3.9117) time: 0.6354 [2021-03-28 17:12:43 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 390/1251] eta: 0:09:14 lr: 0.000013 loss: 2.7309 (2.6410) grad_norm: 3.9483 (3.9105) time: 0.6369 [2021-03-28 17:12:49 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 400/1251] eta: 0:09:07 lr: 0.000013 loss: 2.6865 (2.6376) grad_norm: 3.7201 (3.9037) time: 0.6315 [2021-03-28 17:12:55 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 410/1251] eta: 0:09:00 lr: 0.000013 loss: 2.6578 (2.6392) grad_norm: 3.7201 (3.9162) time: 0.6295 [2021-03-28 17:13:02 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 420/1251] eta: 0:08:54 lr: 0.000013 loss: 2.5608 (2.6396) grad_norm: 3.6273 (3.9201) time: 0.6379 [2021-03-28 17:13:08 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 430/1251] eta: 0:08:47 lr: 0.000013 loss: 2.6673 (2.6425) grad_norm: 3.6273 (3.9316) time: 0.6370 [2021-03-28 17:13:14 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 440/1251] eta: 0:08:40 lr: 0.000013 loss: 2.7731 (2.6460) grad_norm: 3.8467 (3.9292) time: 0.6272 [2021-03-28 17:13:21 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 450/1251] eta: 0:08:34 lr: 0.000013 loss: 2.7166 (2.6431) grad_norm: 3.7800 (3.9268) time: 0.6325 [2021-03-28 17:13:27 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 460/1251] eta: 0:08:28 lr: 0.000013 loss: 2.7130 (2.6447) grad_norm: 3.7609 (3.9328) time: 0.6419 [2021-03-28 17:13:34 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 470/1251] eta: 0:08:21 lr: 0.000013 loss: 2.7176 (2.6431) grad_norm: 3.5670 (3.9257) time: 0.6423 [2021-03-28 17:13:40 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 480/1251] eta: 0:08:14 lr: 0.000013 loss: 2.7328 (2.6459) grad_norm: 3.4229 (3.9165) time: 0.6349 [2021-03-28 17:13:46 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 490/1251] eta: 0:08:08 lr: 0.000013 loss: 2.7896 (2.6458) grad_norm: 3.3110 (3.9163) time: 0.6335 [2021-03-28 17:13:52 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 500/1251] eta: 0:08:01 lr: 0.000012 loss: 2.7896 (2.6456) grad_norm: 3.3661 (3.9096) time: 0.6291 [2021-03-28 17:13:59 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 510/1251] eta: 0:07:55 lr: 0.000012 loss: 2.7100 (2.6450) grad_norm: 3.4562 (3.9061) time: 0.6232 [2021-03-28 17:14:05 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 520/1251] eta: 0:07:48 lr: 0.000012 loss: 2.7063 (2.6419) grad_norm: 3.5869 (3.9147) time: 0.6237 [2021-03-28 17:14:11 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 530/1251] eta: 0:07:41 lr: 0.000012 loss: 2.7081 (2.6433) grad_norm: 3.6884 (3.9350) time: 0.6295 [2021-03-28 17:14:18 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 540/1251] eta: 0:07:35 lr: 0.000012 loss: 2.6692 (2.6400) grad_norm: 3.7371 (3.9323) time: 0.6322 [2021-03-28 17:14:24 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 550/1251] eta: 0:07:28 lr: 0.000012 loss: 2.6015 (2.6398) grad_norm: 3.5880 (3.9251) time: 0.6319 [2021-03-28 17:14:30 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 560/1251] eta: 0:07:22 lr: 0.000012 loss: 2.8207 (2.6424) grad_norm: 3.5991 (3.9247) time: 0.6393 [2021-03-28 17:14:37 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 570/1251] eta: 0:07:16 lr: 0.000012 loss: 2.8207 (2.6444) grad_norm: 3.5742 (3.9173) time: 0.6438 [2021-03-28 17:14:43 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 580/1251] eta: 0:07:09 lr: 0.000012 loss: 2.6723 (2.6438) grad_norm: 3.4429 (3.9171) time: 0.6390 [2021-03-28 17:14:49 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 590/1251] eta: 0:07:03 lr: 0.000012 loss: 2.7739 (2.6458) grad_norm: 3.4745 (3.9133) time: 0.6329 [2021-03-28 17:14:56 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 600/1251] eta: 0:06:56 lr: 0.000012 loss: 2.8475 (2.6481) grad_norm: 3.6900 (3.9103) time: 0.6294 [2021-03-28 17:15:02 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 610/1251] eta: 0:06:50 lr: 0.000012 loss: 2.7382 (2.6453) grad_norm: 3.4238 (3.9120) time: 0.6289 [2021-03-28 17:15:08 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 620/1251] eta: 0:06:43 lr: 0.000012 loss: 2.6547 (2.6463) grad_norm: 3.4238 (3.9117) time: 0.6299 [2021-03-28 17:15:15 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 630/1251] eta: 0:06:37 lr: 0.000012 loss: 2.6547 (2.6443) grad_norm: 3.4095 (3.9048) time: 0.6270 [2021-03-28 17:15:21 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 640/1251] eta: 0:06:30 lr: 0.000012 loss: 2.7132 (2.6433) grad_norm: 3.3721 (3.9023) time: 0.6358 [2021-03-28 17:15:27 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 650/1251] eta: 0:06:24 lr: 0.000012 loss: 2.7686 (2.6445) grad_norm: 3.7016 (3.9068) time: 0.6415 [2021-03-28 17:15:34 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 660/1251] eta: 0:06:17 lr: 0.000012 loss: 2.6532 (2.6432) grad_norm: 3.5020 (3.8993) time: 0.6311 [2021-03-28 17:15:40 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 670/1251] eta: 0:06:11 lr: 0.000012 loss: 2.6532 (2.6434) grad_norm: 3.3903 (3.8984) time: 0.6287 [2021-03-28 17:15:46 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 680/1251] eta: 0:06:04 lr: 0.000012 loss: 2.6005 (2.6407) grad_norm: 3.3694 (3.9001) time: 0.6275 [2021-03-28 17:15:53 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 690/1251] eta: 0:05:58 lr: 0.000012 loss: 2.6305 (2.6429) grad_norm: 3.3458 (3.9155) time: 0.6298 [2021-03-28 17:15:59 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 700/1251] eta: 0:05:51 lr: 0.000012 loss: 2.8259 (2.6447) grad_norm: 3.3458 (3.9105) time: 0.6355 [2021-03-28 17:16:05 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 710/1251] eta: 0:05:45 lr: 0.000012 loss: 2.7943 (2.6444) grad_norm: 3.5336 (3.9116) time: 0.6308 [2021-03-28 17:16:12 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 720/1251] eta: 0:05:39 lr: 0.000012 loss: 2.7618 (2.6451) grad_norm: 3.5836 (3.9076) time: 0.6309 [2021-03-28 17:16:18 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 730/1251] eta: 0:05:32 lr: 0.000012 loss: 2.3984 (2.6417) grad_norm: 3.6187 (3.9171) time: 0.6343 [2021-03-28 17:16:24 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 740/1251] eta: 0:05:26 lr: 0.000012 loss: 2.5688 (2.6402) grad_norm: 3.4406 (3.9157) time: 0.6334 [2021-03-28 17:16:31 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 750/1251] eta: 0:05:19 lr: 0.000012 loss: 2.6744 (2.6405) grad_norm: 3.4406 (3.9164) time: 0.6337 [2021-03-28 17:16:37 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 760/1251] eta: 0:05:13 lr: 0.000012 loss: 2.8284 (2.6406) grad_norm: 3.3432 (3.9139) time: 0.6330 [2021-03-28 17:16:43 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 770/1251] eta: 0:05:07 lr: 0.000012 loss: 2.5447 (2.6385) grad_norm: 3.4060 (3.9123) time: 0.6336 [2021-03-28 17:16:50 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 780/1251] eta: 0:05:00 lr: 0.000012 loss: 2.5433 (2.6384) grad_norm: 3.5996 (3.9095) time: 0.6307 [2021-03-28 17:16:56 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 790/1251] eta: 0:04:54 lr: 0.000012 loss: 2.6324 (2.6374) grad_norm: 3.7438 (3.9134) time: 0.6253 [2021-03-28 17:17:02 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 800/1251] eta: 0:04:47 lr: 0.000012 loss: 2.7114 (2.6392) grad_norm: 3.8138 (3.9168) time: 0.6256 [2021-03-28 17:17:08 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 810/1251] eta: 0:04:41 lr: 0.000012 loss: 2.7497 (2.6411) grad_norm: 3.4837 (3.9104) time: 0.6341 [2021-03-28 17:17:15 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 820/1251] eta: 0:04:34 lr: 0.000012 loss: 2.7617 (2.6408) grad_norm: 3.4712 (3.9141) time: 0.6361 [2021-03-28 17:17:21 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 830/1251] eta: 0:04:28 lr: 0.000012 loss: 2.9161 (2.6420) grad_norm: 3.5234 (3.9094) time: 0.6350 [2021-03-28 17:17:28 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 840/1251] eta: 0:04:22 lr: 0.000012 loss: 2.7002 (2.6413) grad_norm: 3.3506 (3.9062) time: 0.6393 [2021-03-28 17:17:34 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 850/1251] eta: 0:04:15 lr: 0.000012 loss: 2.7344 (2.6425) grad_norm: 3.3506 (3.9044) time: 0.6369 [2021-03-28 17:17:40 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 860/1251] eta: 0:04:09 lr: 0.000012 loss: 2.7916 (2.6436) grad_norm: 3.8558 (3.9147) time: 0.6347 [2021-03-28 17:17:47 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 870/1251] eta: 0:04:02 lr: 0.000012 loss: 2.7916 (2.6442) grad_norm: 3.9740 (3.9149) time: 0.6315 [2021-03-28 17:17:53 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 880/1251] eta: 0:03:56 lr: 0.000012 loss: 2.6770 (2.6416) grad_norm: 3.5193 (3.9175) time: 0.6301 [2021-03-28 17:17:59 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 890/1251] eta: 0:03:50 lr: 0.000012 loss: 2.5209 (2.6399) grad_norm: 3.5193 (3.9132) time: 0.6268 [2021-03-28 17:18:05 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 900/1251] eta: 0:03:43 lr: 0.000012 loss: 2.5696 (2.6399) grad_norm: 3.3581 (3.9097) time: 0.6251 [2021-03-28 17:18:12 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 910/1251] eta: 0:03:37 lr: 0.000012 loss: 2.6250 (2.6401) grad_norm: 3.3581 (3.9040) time: 0.6334 [2021-03-28 17:18:18 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 920/1251] eta: 0:03:30 lr: 0.000012 loss: 2.8850 (2.6432) grad_norm: 3.5988 (3.9186) time: 0.6338 [2021-03-28 17:18:25 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 930/1251] eta: 0:03:24 lr: 0.000012 loss: 2.8751 (2.6435) grad_norm: 3.8745 (3.9185) time: 0.6359 [2021-03-28 17:18:31 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 940/1251] eta: 0:03:18 lr: 0.000012 loss: 2.7485 (2.6440) grad_norm: 3.5204 (3.9181) time: 0.6388 [2021-03-28 17:18:37 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 950/1251] eta: 0:03:11 lr: 0.000012 loss: 2.7776 (2.6442) grad_norm: 3.7723 (3.9185) time: 0.6283 [2021-03-28 17:18:43 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 960/1251] eta: 0:03:05 lr: 0.000012 loss: 2.6818 (2.6442) grad_norm: 3.7723 (3.9168) time: 0.6291 [2021-03-28 17:18:50 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 970/1251] eta: 0:02:58 lr: 0.000012 loss: 2.6583 (2.6442) grad_norm: 3.4422 (3.9155) time: 0.6333 [2021-03-28 17:18:56 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 980/1251] eta: 0:02:52 lr: 0.000012 loss: 2.7941 (2.6453) grad_norm: 3.6409 (3.9170) time: 0.6318 [2021-03-28 17:19:02 swin_base_patch4_window7_224] INFO: Epoch: [290] [ 990/1251] eta: 0:02:46 lr: 0.000012 loss: 2.7326 (2.6435) grad_norm: 3.5865 (3.9177) time: 0.6353 [2021-03-28 17:19:09 swin_base_patch4_window7_224] INFO: Epoch: [290] [1000/1251] eta: 0:02:39 lr: 0.000012 loss: 2.3994 (2.6417) grad_norm: 3.5087 (3.9207) time: 0.6379 [2021-03-28 17:19:15 swin_base_patch4_window7_224] INFO: Epoch: [290] [1010/1251] eta: 0:02:33 lr: 0.000012 loss: 2.5588 (2.6424) grad_norm: 3.6450 (3.9171) time: 0.6338 [2021-03-28 17:19:22 swin_base_patch4_window7_224] INFO: Epoch: [290] [1020/1251] eta: 0:02:27 lr: 0.000012 loss: 2.5736 (2.6399) grad_norm: 3.3387 (3.9195) time: 0.6329 [2021-03-28 17:19:28 swin_base_patch4_window7_224] INFO: Epoch: [290] [1030/1251] eta: 0:02:20 lr: 0.000012 loss: 2.5736 (2.6396) grad_norm: 3.4453 (3.9178) time: 0.6371 [2021-03-28 17:19:34 swin_base_patch4_window7_224] INFO: Epoch: [290] [1040/1251] eta: 0:02:14 lr: 0.000012 loss: 2.7261 (2.6395) grad_norm: 3.5551 (3.9184) time: 0.6328 [2021-03-28 17:19:40 swin_base_patch4_window7_224] INFO: Epoch: [290] [1050/1251] eta: 0:02:07 lr: 0.000012 loss: 2.6072 (2.6398) grad_norm: 3.5519 (3.9183) time: 0.6283 [2021-03-28 17:19:47 swin_base_patch4_window7_224] INFO: Epoch: [290] [1060/1251] eta: 0:02:01 lr: 0.000012 loss: 2.7109 (2.6401) grad_norm: 3.5519 (3.9166) time: 0.6314 [2021-03-28 17:19:53 swin_base_patch4_window7_224] INFO: Epoch: [290] [1070/1251] eta: 0:01:55 lr: 0.000012 loss: 2.6250 (2.6386) grad_norm: 3.4170 (3.9125) time: 0.6287 [2021-03-28 17:19:59 swin_base_patch4_window7_224] INFO: Epoch: [290] [1080/1251] eta: 0:01:48 lr: 0.000012 loss: 2.5972 (2.6389) grad_norm: 3.5433 (3.9089) time: 0.6287 [2021-03-28 17:20:06 swin_base_patch4_window7_224] INFO: Epoch: [290] [1090/1251] eta: 0:01:42 lr: 0.000012 loss: 2.8771 (2.6394) grad_norm: 3.6305 (3.9185) time: 0.6342 [2021-03-28 17:20:12 swin_base_patch4_window7_224] INFO: Epoch: [290] [1100/1251] eta: 0:01:36 lr: 0.000012 loss: 2.6519 (2.6389) grad_norm: 3.6064 (3.9174) time: 0.6326 [2021-03-28 17:20:18 swin_base_patch4_window7_224] INFO: Epoch: [290] [1110/1251] eta: 0:01:29 lr: 0.000012 loss: 2.5571 (2.6385) grad_norm: 3.7494 (3.9191) time: 0.6281 [2021-03-28 17:20:25 swin_base_patch4_window7_224] INFO: Epoch: [290] [1120/1251] eta: 0:01:23 lr: 0.000012 loss: 2.4272 (2.6359) grad_norm: 3.8068 (3.9196) time: 0.6302 [2021-03-28 17:20:31 swin_base_patch4_window7_224] INFO: Epoch: [290] [1130/1251] eta: 0:01:16 lr: 0.000012 loss: 2.5057 (2.6367) grad_norm: 3.4159 (3.9179) time: 0.6339 [2021-03-28 17:20:37 swin_base_patch4_window7_224] INFO: Epoch: [290] [1140/1251] eta: 0:01:10 lr: 0.000012 loss: 2.7114 (2.6362) grad_norm: 3.2825 (3.9142) time: 0.6327 [2021-03-28 17:20:44 swin_base_patch4_window7_224] INFO: Epoch: [290] [1150/1251] eta: 0:01:04 lr: 0.000012 loss: 2.6818 (2.6366) grad_norm: 3.3493 (3.9148) time: 0.6368 [2021-03-28 17:20:50 swin_base_patch4_window7_224] INFO: Epoch: [290] [1160/1251] eta: 0:00:57 lr: 0.000012 loss: 2.5851 (2.6337) grad_norm: 3.4191 (3.9101) time: 0.6324 [2021-03-28 17:20:56 swin_base_patch4_window7_224] INFO: Epoch: [290] [1170/1251] eta: 0:00:51 lr: 0.000012 loss: 2.4809 (2.6328) grad_norm: 3.3000 (3.9113) time: 0.6315 [2021-03-28 17:21:03 swin_base_patch4_window7_224] INFO: Epoch: [290] [1180/1251] eta: 0:00:45 lr: 0.000012 loss: 2.6869 (2.6336) grad_norm: 3.4966 (3.9124) time: 0.6357 [2021-03-28 17:21:09 swin_base_patch4_window7_224] INFO: Epoch: [290] [1190/1251] eta: 0:00:38 lr: 0.000012 loss: 2.5395 (2.6320) grad_norm: 3.5982 (3.9098) time: 0.6404 [2021-03-28 17:21:15 swin_base_patch4_window7_224] INFO: Epoch: [290] [1200/1251] eta: 0:00:32 lr: 0.000012 loss: 2.4895 (2.6312) grad_norm: 3.3784 (3.9189) time: 0.6409 [2021-03-28 17:21:22 swin_base_patch4_window7_224] INFO: Epoch: [290] [1210/1251] eta: 0:00:26 lr: 0.000012 loss: 2.7211 (2.6322) grad_norm: 3.3618 (3.9211) time: 0.6319 [2021-03-28 17:21:28 swin_base_patch4_window7_224] INFO: Epoch: [290] [1220/1251] eta: 0:00:19 lr: 0.000012 loss: 2.7994 (2.6333) grad_norm: 3.3185 (3.9172) time: 0.6373 [2021-03-28 17:21:35 swin_base_patch4_window7_224] INFO: Epoch: [290] [1230/1251] eta: 0:00:13 lr: 0.000012 loss: 2.7793 (2.6339) grad_norm: 3.3662 (3.9161) time: 0.6393 [2021-03-28 17:21:41 swin_base_patch4_window7_224] INFO: Epoch: [290] [1240/1251] eta: 0:00:06 lr: 0.000012 loss: 2.7348 (2.6350) grad_norm: 3.7960 (3.9184) time: 0.6278 [2021-03-28 17:21:47 swin_base_patch4_window7_224] INFO: Epoch: [290] [1250/1251] eta: 0:00:00 lr: 0.000012 loss: 2.6762 (2.6331) grad_norm: 3.6857 (3.9157) time: 0.6269 [2021-03-28 17:23:14 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 0.7323 (0.7323) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-28 17:23:15 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.7781 (0.7744) acc1: 81.2500 (81.6761) acc5: 96.8750 (95.7386) [2021-03-28 17:23:17 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7458 (0.7616) acc1: 81.2500 (82.4405) acc5: 96.8750 (96.3542) [2021-03-28 17:23:18 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7014 (0.7515) acc1: 82.8125 (82.3589) acc5: 96.8750 (96.6734) [2021-03-28 17:23:20 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.6817 (0.7471) acc1: 81.2500 (82.3552) acc5: 96.8750 (96.5320) [2021-03-28 17:23:21 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7414 (0.7526) acc1: 81.2500 (82.1760) acc5: 96.8750 (96.6400) [2021-03-28 17:23:34 swin_base_patch4_window7_224] INFO: * Acc@1 83.436 Acc@5 96.422 loss 0.739 [2021-03-28 17:23:34 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 17:23:34 swin_base_patch4_window7_224] INFO: Max accuracy: 83.44% [2021-03-28 17:23:38 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 0/1251] eta: 1:25:17 lr: 0.000012 loss: 2.7403 (2.7403) grad_norm: 4.6364 (4.6364) time: 4.0905 [2021-03-28 17:23:44 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 10/1251] eta: 0:19:47 lr: 0.000012 loss: 2.8057 (2.7436) grad_norm: 4.0737 (4.5026) time: 0.9567 [2021-03-28 17:23:50 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 20/1251] eta: 0:16:28 lr: 0.000012 loss: 2.8464 (2.7062) grad_norm: 3.6290 (4.3831) time: 0.6384 [2021-03-28 17:23:57 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 30/1251] eta: 0:15:17 lr: 0.000012 loss: 2.5962 (2.6573) grad_norm: 3.3978 (4.0750) time: 0.6387 [2021-03-28 17:24:03 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 40/1251] eta: 0:14:32 lr: 0.000012 loss: 2.5860 (2.6183) grad_norm: 3.5204 (3.9956) time: 0.6346 [2021-03-28 17:24:09 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 50/1251] eta: 0:14:03 lr: 0.000012 loss: 2.6523 (2.5957) grad_norm: 3.6725 (3.9746) time: 0.6270 [2021-03-28 17:24:16 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 60/1251] eta: 0:13:44 lr: 0.000012 loss: 2.6672 (2.5885) grad_norm: 3.2783 (3.9010) time: 0.6326 [2021-03-28 17:24:22 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 70/1251] eta: 0:13:27 lr: 0.000012 loss: 2.7513 (2.6209) grad_norm: 3.4776 (4.0066) time: 0.6340 [2021-03-28 17:24:29 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 80/1251] eta: 0:13:13 lr: 0.000012 loss: 2.8296 (2.6532) grad_norm: 3.7349 (3.9881) time: 0.6352 [2021-03-28 17:24:35 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 90/1251] eta: 0:12:59 lr: 0.000012 loss: 2.7229 (2.6204) grad_norm: 3.4386 (3.9234) time: 0.6305 [2021-03-28 17:24:41 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 100/1251] eta: 0:12:49 lr: 0.000012 loss: 2.6548 (2.6311) grad_norm: 3.4377 (3.8923) time: 0.6297 [2021-03-28 17:24:47 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 110/1251] eta: 0:12:38 lr: 0.000012 loss: 2.8152 (2.6354) grad_norm: 3.5006 (3.8976) time: 0.6327 [2021-03-28 17:24:54 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 120/1251] eta: 0:12:27 lr: 0.000012 loss: 2.7158 (2.6220) grad_norm: 3.4684 (3.8948) time: 0.6256 [2021-03-28 17:25:00 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 130/1251] eta: 0:12:19 lr: 0.000012 loss: 2.7762 (2.6378) grad_norm: 3.6227 (3.9143) time: 0.6299 [2021-03-28 17:25:06 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 140/1251] eta: 0:12:10 lr: 0.000012 loss: 2.8254 (2.6400) grad_norm: 3.7821 (3.9350) time: 0.6371 [2021-03-28 17:25:13 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 150/1251] eta: 0:12:03 lr: 0.000012 loss: 2.7772 (2.6456) grad_norm: 3.9834 (3.9854) time: 0.6397 [2021-03-28 17:25:19 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 160/1251] eta: 0:11:54 lr: 0.000012 loss: 2.6164 (2.6381) grad_norm: 3.4139 (3.9506) time: 0.6363 [2021-03-28 17:25:25 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 170/1251] eta: 0:11:46 lr: 0.000012 loss: 2.7481 (2.6507) grad_norm: 3.3138 (3.9550) time: 0.6295 [2021-03-28 17:25:32 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 180/1251] eta: 0:11:38 lr: 0.000012 loss: 2.8865 (2.6619) grad_norm: 3.5261 (3.9340) time: 0.6277 [2021-03-28 17:25:38 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 190/1251] eta: 0:11:30 lr: 0.000012 loss: 2.8865 (2.6617) grad_norm: 3.3632 (3.9522) time: 0.6270 [2021-03-28 17:25:44 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 200/1251] eta: 0:11:23 lr: 0.000012 loss: 2.7251 (2.6528) grad_norm: 3.3542 (3.9473) time: 0.6332 [2021-03-28 17:25:51 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 210/1251] eta: 0:11:15 lr: 0.000012 loss: 2.7209 (2.6591) grad_norm: 3.4160 (3.9274) time: 0.6334 [2021-03-28 17:25:57 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 220/1251] eta: 0:11:08 lr: 0.000012 loss: 2.7927 (2.6642) grad_norm: 3.4160 (3.9147) time: 0.6268 [2021-03-28 17:26:03 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 230/1251] eta: 0:11:00 lr: 0.000012 loss: 2.7224 (2.6633) grad_norm: 3.2980 (3.8895) time: 0.6277 [2021-03-28 17:26:10 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 240/1251] eta: 0:10:53 lr: 0.000012 loss: 2.7366 (2.6623) grad_norm: 3.3494 (3.8942) time: 0.6306 [2021-03-28 17:26:16 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 250/1251] eta: 0:10:46 lr: 0.000012 loss: 2.7928 (2.6697) grad_norm: 3.4727 (3.8940) time: 0.6342 [2021-03-28 17:26:22 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 260/1251] eta: 0:10:40 lr: 0.000012 loss: 2.8522 (2.6765) grad_norm: 3.6712 (3.9199) time: 0.6362 [2021-03-28 17:26:29 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 270/1251] eta: 0:10:33 lr: 0.000012 loss: 2.9041 (2.6760) grad_norm: 3.8221 (3.9357) time: 0.6348 [2021-03-28 17:26:35 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 280/1251] eta: 0:10:26 lr: 0.000012 loss: 2.7271 (2.6715) grad_norm: 3.8221 (3.9323) time: 0.6314 [2021-03-28 17:26:41 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 290/1251] eta: 0:10:19 lr: 0.000012 loss: 2.6312 (2.6714) grad_norm: 3.4401 (3.9190) time: 0.6278 [2021-03-28 17:26:47 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 300/1251] eta: 0:10:12 lr: 0.000012 loss: 2.6312 (2.6679) grad_norm: 3.3090 (3.9073) time: 0.6261 [2021-03-28 17:26:54 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 310/1251] eta: 0:10:05 lr: 0.000012 loss: 2.7161 (2.6658) grad_norm: 3.5137 (3.8976) time: 0.6247 [2021-03-28 17:27:00 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 320/1251] eta: 0:09:58 lr: 0.000012 loss: 2.7474 (2.6722) grad_norm: 3.6323 (3.8972) time: 0.6271 [2021-03-28 17:27:06 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 330/1251] eta: 0:09:51 lr: 0.000012 loss: 2.8165 (2.6684) grad_norm: 3.7696 (3.9195) time: 0.6306 [2021-03-28 17:27:13 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 340/1251] eta: 0:09:45 lr: 0.000012 loss: 2.4738 (2.6630) grad_norm: 3.7603 (3.9102) time: 0.6355 [2021-03-28 17:27:19 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 350/1251] eta: 0:09:38 lr: 0.000012 loss: 2.4237 (2.6542) grad_norm: 3.2961 (3.8985) time: 0.6380 [2021-03-28 17:27:25 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 360/1251] eta: 0:09:31 lr: 0.000012 loss: 2.5620 (2.6557) grad_norm: 3.2961 (3.8832) time: 0.6344 [2021-03-28 17:27:32 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 370/1251] eta: 0:09:25 lr: 0.000012 loss: 2.6363 (2.6547) grad_norm: 3.1938 (3.8722) time: 0.6332 [2021-03-28 17:27:38 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 380/1251] eta: 0:09:18 lr: 0.000012 loss: 2.7419 (2.6560) grad_norm: 3.2006 (3.8601) time: 0.6329 [2021-03-28 17:27:44 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 390/1251] eta: 0:09:11 lr: 0.000012 loss: 2.7976 (2.6556) grad_norm: 3.3562 (3.8500) time: 0.6331 [2021-03-28 17:27:51 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 400/1251] eta: 0:09:05 lr: 0.000012 loss: 2.7706 (2.6542) grad_norm: 3.2310 (3.8368) time: 0.6374 [2021-03-28 17:27:57 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 410/1251] eta: 0:08:58 lr: 0.000012 loss: 2.6119 (2.6518) grad_norm: 3.6252 (3.8506) time: 0.6318 [2021-03-28 17:28:03 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 420/1251] eta: 0:08:52 lr: 0.000012 loss: 2.6306 (2.6548) grad_norm: 4.0986 (3.8591) time: 0.6230 [2021-03-28 17:28:09 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 430/1251] eta: 0:08:45 lr: 0.000012 loss: 2.6341 (2.6518) grad_norm: 3.5593 (3.8497) time: 0.6250 [2021-03-28 17:28:16 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 440/1251] eta: 0:08:38 lr: 0.000012 loss: 2.6341 (2.6536) grad_norm: 3.4896 (3.8443) time: 0.6308 [2021-03-28 17:28:22 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 450/1251] eta: 0:08:32 lr: 0.000012 loss: 2.7816 (2.6521) grad_norm: 3.5524 (3.8452) time: 0.6311 [2021-03-28 17:28:28 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 460/1251] eta: 0:08:25 lr: 0.000012 loss: 2.5838 (2.6500) grad_norm: 3.6947 (3.8378) time: 0.6292 [2021-03-28 17:28:35 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 470/1251] eta: 0:08:19 lr: 0.000012 loss: 2.7437 (2.6504) grad_norm: 3.6947 (3.8343) time: 0.6300 [2021-03-28 17:28:41 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 480/1251] eta: 0:08:12 lr: 0.000012 loss: 2.6386 (2.6501) grad_norm: 3.5473 (3.8353) time: 0.6361 [2021-03-28 17:28:47 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 490/1251] eta: 0:08:06 lr: 0.000012 loss: 2.5371 (2.6477) grad_norm: 3.4065 (3.8368) time: 0.6350 [2021-03-28 17:28:54 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 500/1251] eta: 0:07:59 lr: 0.000012 loss: 2.5520 (2.6474) grad_norm: 3.4163 (3.8318) time: 0.6325 [2021-03-28 17:29:00 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 510/1251] eta: 0:07:53 lr: 0.000012 loss: 2.6733 (2.6469) grad_norm: 3.4872 (3.8356) time: 0.6395 [2021-03-28 17:29:06 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 520/1251] eta: 0:07:46 lr: 0.000012 loss: 2.3636 (2.6404) grad_norm: 3.6978 (3.8351) time: 0.6305 [2021-03-28 17:29:13 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 530/1251] eta: 0:07:40 lr: 0.000012 loss: 2.2353 (2.6386) grad_norm: 3.8024 (3.8496) time: 0.6301 [2021-03-28 17:29:19 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 540/1251] eta: 0:07:34 lr: 0.000012 loss: 2.5833 (2.6375) grad_norm: 3.8956 (3.8493) time: 0.6373 [2021-03-28 17:29:26 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 550/1251] eta: 0:07:27 lr: 0.000012 loss: 2.5951 (2.6373) grad_norm: 3.6549 (3.8477) time: 0.6442 [2021-03-28 17:29:32 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 560/1251] eta: 0:07:21 lr: 0.000012 loss: 2.5951 (2.6364) grad_norm: 3.3967 (3.8438) time: 0.6460 [2021-03-28 17:29:38 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 570/1251] eta: 0:07:14 lr: 0.000012 loss: 2.5877 (2.6333) grad_norm: 3.3288 (3.8453) time: 0.6351 [2021-03-28 17:29:45 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 580/1251] eta: 0:07:08 lr: 0.000012 loss: 2.6209 (2.6331) grad_norm: 3.3415 (3.8429) time: 0.6292 [2021-03-28 17:29:51 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 590/1251] eta: 0:07:01 lr: 0.000012 loss: 2.7608 (2.6343) grad_norm: 3.4947 (3.8439) time: 0.6300 [2021-03-28 17:29:57 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 600/1251] eta: 0:06:55 lr: 0.000012 loss: 2.9453 (2.6360) grad_norm: 3.7949 (3.8545) time: 0.6333 [2021-03-28 17:30:04 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 610/1251] eta: 0:06:48 lr: 0.000012 loss: 2.9608 (2.6372) grad_norm: 4.0616 (3.8597) time: 0.6279 [2021-03-28 17:30:10 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 620/1251] eta: 0:06:42 lr: 0.000012 loss: 2.4507 (2.6336) grad_norm: 3.7961 (3.8632) time: 0.6316 [2021-03-28 17:30:16 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 630/1251] eta: 0:06:36 lr: 0.000012 loss: 2.5983 (2.6352) grad_norm: 3.3717 (3.8562) time: 0.6371 [2021-03-28 17:30:23 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 640/1251] eta: 0:06:29 lr: 0.000012 loss: 2.8075 (2.6354) grad_norm: 3.3717 (3.8493) time: 0.6298 [2021-03-28 17:30:29 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 650/1251] eta: 0:06:23 lr: 0.000012 loss: 2.7118 (2.6350) grad_norm: 3.4492 (inf) time: 0.6269 [2021-03-28 17:30:35 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 660/1251] eta: 0:06:16 lr: 0.000012 loss: 2.7433 (2.6377) grad_norm: 3.4910 (inf) time: 0.6311 [2021-03-28 17:30:41 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 670/1251] eta: 0:06:10 lr: 0.000012 loss: 2.8456 (2.6378) grad_norm: 3.4337 (inf) time: 0.6303 [2021-03-28 17:30:48 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 680/1251] eta: 0:06:03 lr: 0.000012 loss: 2.6074 (2.6357) grad_norm: 3.4337 (inf) time: 0.6274 [2021-03-28 17:30:54 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 690/1251] eta: 0:05:57 lr: 0.000012 loss: 2.6761 (2.6377) grad_norm: 3.4732 (inf) time: 0.6273 [2021-03-28 17:31:01 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 700/1251] eta: 0:05:51 lr: 0.000012 loss: 2.8096 (2.6402) grad_norm: 3.5732 (inf) time: 0.6370 [2021-03-28 17:31:07 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 710/1251] eta: 0:05:44 lr: 0.000012 loss: 2.8640 (2.6434) grad_norm: 3.7710 (inf) time: 0.6420 [2021-03-28 17:31:13 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 720/1251] eta: 0:05:38 lr: 0.000012 loss: 2.7635 (2.6408) grad_norm: 3.6529 (inf) time: 0.6354 [2021-03-28 17:31:20 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 730/1251] eta: 0:05:32 lr: 0.000012 loss: 2.6078 (2.6437) grad_norm: 3.7723 (inf) time: 0.6364 [2021-03-28 17:31:26 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 740/1251] eta: 0:05:25 lr: 0.000012 loss: 2.7212 (2.6418) grad_norm: 3.8554 (inf) time: 0.6357 [2021-03-28 17:31:32 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 750/1251] eta: 0:05:19 lr: 0.000012 loss: 2.5853 (2.6411) grad_norm: 3.5852 (inf) time: 0.6355 [2021-03-28 17:31:39 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 760/1251] eta: 0:05:12 lr: 0.000012 loss: 2.8328 (2.6441) grad_norm: 3.5087 (inf) time: 0.6358 [2021-03-28 17:31:45 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 770/1251] eta: 0:05:06 lr: 0.000012 loss: 2.8328 (2.6424) grad_norm: 3.3386 (inf) time: 0.6364 [2021-03-28 17:31:51 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 780/1251] eta: 0:05:00 lr: 0.000012 loss: 2.7608 (2.6440) grad_norm: 3.3563 (inf) time: 0.6393 [2021-03-28 17:31:58 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 790/1251] eta: 0:04:53 lr: 0.000012 loss: 2.8202 (2.6437) grad_norm: 3.5390 (inf) time: 0.6362 [2021-03-28 17:32:04 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 800/1251] eta: 0:04:47 lr: 0.000012 loss: 2.8202 (2.6454) grad_norm: 3.5390 (inf) time: 0.6318 [2021-03-28 17:32:10 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 810/1251] eta: 0:04:40 lr: 0.000012 loss: 2.8115 (2.6450) grad_norm: 3.7232 (inf) time: 0.6363 [2021-03-28 17:32:17 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 820/1251] eta: 0:04:34 lr: 0.000012 loss: 2.7297 (2.6461) grad_norm: 3.6481 (inf) time: 0.6363 [2021-03-28 17:32:23 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 830/1251] eta: 0:04:28 lr: 0.000012 loss: 2.6884 (2.6462) grad_norm: 3.2692 (inf) time: 0.6304 [2021-03-28 17:32:29 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 840/1251] eta: 0:04:21 lr: 0.000012 loss: 2.5837 (2.6455) grad_norm: 3.4579 (inf) time: 0.6325 [2021-03-28 17:32:36 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 850/1251] eta: 0:04:15 lr: 0.000012 loss: 2.3788 (2.6437) grad_norm: 3.5227 (inf) time: 0.6308 [2021-03-28 17:32:42 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 860/1251] eta: 0:04:09 lr: 0.000012 loss: 2.6884 (2.6465) grad_norm: 3.7560 (inf) time: 0.6306 [2021-03-28 17:32:48 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 870/1251] eta: 0:04:02 lr: 0.000012 loss: 2.8606 (2.6484) grad_norm: 3.5045 (inf) time: 0.6330 [2021-03-28 17:32:55 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 880/1251] eta: 0:03:56 lr: 0.000012 loss: 2.8606 (2.6494) grad_norm: 3.5045 (inf) time: 0.6272 [2021-03-28 17:33:01 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 890/1251] eta: 0:03:49 lr: 0.000012 loss: 2.8162 (2.6503) grad_norm: 3.7719 (inf) time: 0.6372 [2021-03-28 17:33:07 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 900/1251] eta: 0:03:43 lr: 0.000012 loss: 2.6993 (2.6501) grad_norm: 3.7719 (inf) time: 0.6381 [2021-03-28 17:33:14 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 910/1251] eta: 0:03:37 lr: 0.000012 loss: 2.6968 (2.6511) grad_norm: 3.4280 (inf) time: 0.6287 [2021-03-28 17:33:20 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 920/1251] eta: 0:03:30 lr: 0.000012 loss: 2.8415 (2.6507) grad_norm: 3.4280 (inf) time: 0.6280 [2021-03-28 17:33:26 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 930/1251] eta: 0:03:24 lr: 0.000012 loss: 2.7961 (2.6501) grad_norm: 3.6591 (inf) time: 0.6237 [2021-03-28 17:33:33 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 940/1251] eta: 0:03:17 lr: 0.000012 loss: 2.6711 (2.6513) grad_norm: 3.6753 (inf) time: 0.6298 [2021-03-28 17:33:39 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 950/1251] eta: 0:03:11 lr: 0.000012 loss: 2.7558 (2.6530) grad_norm: 3.3784 (inf) time: 0.6360 [2021-03-28 17:33:45 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 960/1251] eta: 0:03:05 lr: 0.000012 loss: 2.7530 (2.6500) grad_norm: 3.2415 (inf) time: 0.6311 [2021-03-28 17:33:52 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 970/1251] eta: 0:02:58 lr: 0.000012 loss: 2.5759 (2.6504) grad_norm: 3.4089 (inf) time: 0.6292 [2021-03-28 17:33:58 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 980/1251] eta: 0:02:52 lr: 0.000012 loss: 2.8332 (2.6525) grad_norm: 3.4089 (inf) time: 0.6309 [2021-03-28 17:34:04 swin_base_patch4_window7_224] INFO: Epoch: [291] [ 990/1251] eta: 0:02:46 lr: 0.000012 loss: 2.8332 (2.6536) grad_norm: 3.4055 (inf) time: 0.6295 [2021-03-28 17:34:10 swin_base_patch4_window7_224] INFO: Epoch: [291] [1000/1251] eta: 0:02:39 lr: 0.000012 loss: 2.8043 (2.6542) grad_norm: 3.3474 (inf) time: 0.6335 [2021-03-28 17:34:17 swin_base_patch4_window7_224] INFO: Epoch: [291] [1010/1251] eta: 0:02:33 lr: 0.000012 loss: 2.8043 (2.6548) grad_norm: 3.1392 (inf) time: 0.6395 [2021-03-28 17:34:23 swin_base_patch4_window7_224] INFO: Epoch: [291] [1020/1251] eta: 0:02:26 lr: 0.000012 loss: 2.7720 (2.6559) grad_norm: 3.1981 (inf) time: 0.6357 [2021-03-28 17:34:30 swin_base_patch4_window7_224] INFO: Epoch: [291] [1030/1251] eta: 0:02:20 lr: 0.000012 loss: 2.7115 (2.6557) grad_norm: 3.6579 (inf) time: 0.6315 [2021-03-28 17:34:36 swin_base_patch4_window7_224] INFO: Epoch: [291] [1040/1251] eta: 0:02:14 lr: 0.000012 loss: 2.7280 (2.6565) grad_norm: 3.4210 (inf) time: 0.6299 [2021-03-28 17:34:42 swin_base_patch4_window7_224] INFO: Epoch: [291] [1050/1251] eta: 0:02:07 lr: 0.000012 loss: 2.8571 (2.6584) grad_norm: 3.9180 (inf) time: 0.6287 [2021-03-28 17:34:49 swin_base_patch4_window7_224] INFO: Epoch: [291] [1060/1251] eta: 0:02:01 lr: 0.000012 loss: 2.8702 (2.6603) grad_norm: 3.8478 (inf) time: 0.6355 [2021-03-28 17:34:55 swin_base_patch4_window7_224] INFO: Epoch: [291] [1070/1251] eta: 0:01:55 lr: 0.000012 loss: 2.6478 (2.6593) grad_norm: 3.3500 (inf) time: 0.6365 [2021-03-28 17:35:01 swin_base_patch4_window7_224] INFO: Epoch: [291] [1080/1251] eta: 0:01:48 lr: 0.000012 loss: 2.6478 (2.6588) grad_norm: 3.5233 (inf) time: 0.6347 [2021-03-28 17:35:08 swin_base_patch4_window7_224] INFO: Epoch: [291] [1090/1251] eta: 0:01:42 lr: 0.000012 loss: 2.6568 (2.6573) grad_norm: 3.5233 (inf) time: 0.6360 [2021-03-28 17:35:14 swin_base_patch4_window7_224] INFO: Epoch: [291] [1100/1251] eta: 0:01:36 lr: 0.000012 loss: 2.6186 (2.6565) grad_norm: 3.4763 (inf) time: 0.6350 [2021-03-28 17:35:20 swin_base_patch4_window7_224] INFO: Epoch: [291] [1110/1251] eta: 0:01:29 lr: 0.000012 loss: 2.4521 (2.6548) grad_norm: 3.5141 (inf) time: 0.6333 [2021-03-28 17:35:26 swin_base_patch4_window7_224] INFO: Epoch: [291] [1120/1251] eta: 0:01:23 lr: 0.000012 loss: 2.6560 (2.6557) grad_norm: 3.5630 (inf) time: 0.6287 [2021-03-28 17:35:33 swin_base_patch4_window7_224] INFO: Epoch: [291] [1130/1251] eta: 0:01:16 lr: 0.000012 loss: 2.7188 (2.6561) grad_norm: 4.0123 (inf) time: 0.6341 [2021-03-28 17:35:39 swin_base_patch4_window7_224] INFO: Epoch: [291] [1140/1251] eta: 0:01:10 lr: 0.000012 loss: 2.7188 (2.6562) grad_norm: 4.0123 (inf) time: 0.6443 [2021-03-28 17:35:46 swin_base_patch4_window7_224] INFO: Epoch: [291] [1150/1251] eta: 0:01:04 lr: 0.000012 loss: 2.7961 (2.6578) grad_norm: 3.5397 (inf) time: 0.6364 [2021-03-28 17:35:52 swin_base_patch4_window7_224] INFO: Epoch: [291] [1160/1251] eta: 0:00:57 lr: 0.000012 loss: 2.8390 (2.6582) grad_norm: 3.3562 (inf) time: 0.6332 [2021-03-28 17:35:58 swin_base_patch4_window7_224] INFO: Epoch: [291] [1170/1251] eta: 0:00:51 lr: 0.000012 loss: 2.8056 (2.6585) grad_norm: 3.3562 (inf) time: 0.6382 [2021-03-28 17:36:05 swin_base_patch4_window7_224] INFO: Epoch: [291] [1180/1251] eta: 0:00:45 lr: 0.000012 loss: 2.7328 (2.6589) grad_norm: 3.5706 (inf) time: 0.6396 [2021-03-28 17:36:11 swin_base_patch4_window7_224] INFO: Epoch: [291] [1190/1251] eta: 0:00:38 lr: 0.000012 loss: 2.6207 (2.6563) grad_norm: 3.3956 (inf) time: 0.6331 [2021-03-28 17:36:17 swin_base_patch4_window7_224] INFO: Epoch: [291] [1200/1251] eta: 0:00:32 lr: 0.000012 loss: 2.6522 (2.6581) grad_norm: 3.6086 (inf) time: 0.6275 [2021-03-28 17:36:24 swin_base_patch4_window7_224] INFO: Epoch: [291] [1210/1251] eta: 0:00:26 lr: 0.000012 loss: 2.6901 (2.6577) grad_norm: 3.5772 (inf) time: 0.6314 [2021-03-28 17:36:30 swin_base_patch4_window7_224] INFO: Epoch: [291] [1220/1251] eta: 0:00:19 lr: 0.000012 loss: 2.5415 (2.6566) grad_norm: 3.5772 (inf) time: 0.6267 [2021-03-28 17:36:36 swin_base_patch4_window7_224] INFO: Epoch: [291] [1230/1251] eta: 0:00:13 lr: 0.000012 loss: 2.5233 (2.6559) grad_norm: 3.5589 (inf) time: 0.6255 [2021-03-28 17:36:43 swin_base_patch4_window7_224] INFO: Epoch: [291] [1240/1251] eta: 0:00:06 lr: 0.000012 loss: 2.7087 (2.6573) grad_norm: 3.5589 (inf) time: 0.6285 [2021-03-28 17:36:49 swin_base_patch4_window7_224] INFO: Epoch: [291] [1250/1251] eta: 0:00:00 lr: 0.000012 loss: 2.8231 (2.6579) grad_norm: 3.5459 (inf) time: 0.6265 [2021-03-28 17:37:04 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:37 loss: 0.9473 (0.9473) acc1: 78.1250 (78.1250) acc5: 95.3125 (95.3125) [2021-03-28 17:37:06 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.6559 (0.7293) acc1: 84.3750 (83.6648) acc5: 96.8750 (96.3068) [2021-03-28 17:37:09 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.6742 (0.7554) acc1: 82.8125 (82.1429) acc5: 96.8750 (96.3542) [2021-03-28 17:37:11 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7884 (0.7809) acc1: 81.2500 (81.8044) acc5: 96.8750 (96.3710) [2021-03-28 17:37:13 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7884 (0.7772) acc1: 81.2500 (81.5930) acc5: 96.8750 (96.3796) [2021-03-28 17:37:14 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7094 (0.7537) acc1: 81.2500 (82.4000) acc5: 96.8750 (96.4800) [2021-03-28 17:37:32 swin_base_patch4_window7_224] INFO: * Acc@1 83.396 Acc@5 96.446 loss 0.740 [2021-03-28 17:37:32 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 17:37:32 swin_base_patch4_window7_224] INFO: Max accuracy: 83.44% [2021-03-28 17:37:36 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 0/1251] eta: 1:24:21 lr: 0.000012 loss: 2.8561 (2.8561) grad_norm: 3.0343 (3.0343) time: 4.0463 [2021-03-28 17:37:42 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 10/1251] eta: 0:20:01 lr: 0.000012 loss: 2.8470 (2.7914) grad_norm: 3.2365 (3.7065) time: 0.9679 [2021-03-28 17:37:49 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 20/1251] eta: 0:16:34 lr: 0.000012 loss: 2.7731 (2.7644) grad_norm: 3.4501 (3.7019) time: 0.6456 [2021-03-28 17:37:55 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 30/1251] eta: 0:15:22 lr: 0.000012 loss: 2.6815 (2.6961) grad_norm: 3.7987 (3.7813) time: 0.6383 [2021-03-28 17:38:02 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 40/1251] eta: 0:14:38 lr: 0.000012 loss: 2.6348 (2.6427) grad_norm: 3.7987 (3.8316) time: 0.6394 [2021-03-28 17:38:08 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 50/1251] eta: 0:14:09 lr: 0.000012 loss: 2.6290 (2.6393) grad_norm: 3.5801 (3.7274) time: 0.6329 [2021-03-28 17:38:14 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 60/1251] eta: 0:13:47 lr: 0.000012 loss: 2.8052 (2.6611) grad_norm: 3.4104 (3.7349) time: 0.6324 [2021-03-28 17:38:21 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 70/1251] eta: 0:13:31 lr: 0.000012 loss: 2.8612 (2.6737) grad_norm: 3.6813 (3.7486) time: 0.6347 [2021-03-28 17:38:27 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 80/1251] eta: 0:13:15 lr: 0.000012 loss: 2.6673 (2.6762) grad_norm: 3.7727 (3.7704) time: 0.6312 [2021-03-28 17:38:33 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 90/1251] eta: 0:13:01 lr: 0.000012 loss: 2.7487 (2.6800) grad_norm: 3.7656 (3.7701) time: 0.6242 [2021-03-28 17:38:39 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 100/1251] eta: 0:12:49 lr: 0.000012 loss: 2.7296 (2.6784) grad_norm: 3.6314 (3.7733) time: 0.6273 [2021-03-28 17:38:46 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 110/1251] eta: 0:12:38 lr: 0.000012 loss: 2.7094 (2.6711) grad_norm: 3.6668 (3.7981) time: 0.6276 [2021-03-28 17:38:52 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 120/1251] eta: 0:12:29 lr: 0.000012 loss: 2.7870 (2.6820) grad_norm: 3.8080 (3.8185) time: 0.6301 [2021-03-28 17:38:58 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 130/1251] eta: 0:12:19 lr: 0.000012 loss: 2.8800 (2.6896) grad_norm: 3.3442 (3.7993) time: 0.6311 [2021-03-28 17:39:05 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 140/1251] eta: 0:12:11 lr: 0.000012 loss: 2.7957 (2.6973) grad_norm: 3.4521 (3.7861) time: 0.6315 [2021-03-28 17:39:11 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 150/1251] eta: 0:12:03 lr: 0.000012 loss: 2.6991 (2.6998) grad_norm: 3.6552 (3.7973) time: 0.6375 [2021-03-28 17:39:17 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 160/1251] eta: 0:11:55 lr: 0.000012 loss: 2.6991 (2.6961) grad_norm: 3.7067 (3.8016) time: 0.6374 [2021-03-28 17:39:24 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 170/1251] eta: 0:11:47 lr: 0.000012 loss: 2.7403 (2.6904) grad_norm: 3.7357 (3.8304) time: 0.6372 [2021-03-28 17:39:30 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 180/1251] eta: 0:11:39 lr: 0.000012 loss: 2.7403 (2.6957) grad_norm: 3.4304 (3.8012) time: 0.6347 [2021-03-28 17:39:36 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 190/1251] eta: 0:11:31 lr: 0.000012 loss: 2.7216 (2.6945) grad_norm: 3.6172 (3.8109) time: 0.6281 [2021-03-28 17:39:43 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 200/1251] eta: 0:11:24 lr: 0.000012 loss: 2.7848 (2.6978) grad_norm: 3.7586 (3.8639) time: 0.6293 [2021-03-28 17:39:49 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 210/1251] eta: 0:11:16 lr: 0.000012 loss: 2.7796 (2.6941) grad_norm: 3.4097 (3.8593) time: 0.6317 [2021-03-28 17:39:55 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 220/1251] eta: 0:11:09 lr: 0.000012 loss: 2.7575 (2.6977) grad_norm: 3.4048 (3.8762) time: 0.6321 [2021-03-28 17:40:02 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 230/1251] eta: 0:11:01 lr: 0.000012 loss: 2.7575 (2.6929) grad_norm: 3.5197 (3.9038) time: 0.6329 [2021-03-28 17:40:08 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 240/1251] eta: 0:10:55 lr: 0.000012 loss: 2.5688 (2.6933) grad_norm: 3.5610 (3.9022) time: 0.6370 [2021-03-28 17:40:14 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 250/1251] eta: 0:10:48 lr: 0.000012 loss: 2.7862 (2.6941) grad_norm: 3.5642 (3.9039) time: 0.6382 [2021-03-28 17:40:21 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 260/1251] eta: 0:10:41 lr: 0.000012 loss: 2.7862 (2.6945) grad_norm: 3.5642 (3.9194) time: 0.6377 [2021-03-28 17:40:27 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 270/1251] eta: 0:10:35 lr: 0.000012 loss: 2.6606 (2.6903) grad_norm: 3.7629 (3.9173) time: 0.6463 [2021-03-28 17:40:34 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 280/1251] eta: 0:10:28 lr: 0.000012 loss: 2.6173 (2.6909) grad_norm: 3.7997 (3.9135) time: 0.6423 [2021-03-28 17:40:40 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 290/1251] eta: 0:10:21 lr: 0.000012 loss: 2.7774 (2.6931) grad_norm: 3.7997 (3.9256) time: 0.6322 [2021-03-28 17:40:46 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 300/1251] eta: 0:10:14 lr: 0.000012 loss: 2.7989 (2.6932) grad_norm: 3.5959 (3.9151) time: 0.6343 [2021-03-28 17:40:53 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 310/1251] eta: 0:10:07 lr: 0.000012 loss: 2.7385 (2.6918) grad_norm: 3.5937 (3.9149) time: 0.6369 [2021-03-28 17:40:59 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 320/1251] eta: 0:10:00 lr: 0.000012 loss: 2.6573 (2.6871) grad_norm: 3.9010 (3.9172) time: 0.6324 [2021-03-28 17:41:05 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 330/1251] eta: 0:09:54 lr: 0.000012 loss: 2.4503 (2.6821) grad_norm: 3.5272 (3.9100) time: 0.6391 [2021-03-28 17:41:12 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 340/1251] eta: 0:09:47 lr: 0.000012 loss: 2.7403 (2.6829) grad_norm: 3.4786 (3.9485) time: 0.6393 [2021-03-28 17:41:18 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 350/1251] eta: 0:09:41 lr: 0.000012 loss: 2.6819 (2.6770) grad_norm: 3.6109 (3.9398) time: 0.6389 [2021-03-28 17:41:25 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 360/1251] eta: 0:09:34 lr: 0.000012 loss: 2.7441 (2.6827) grad_norm: 3.5055 (3.9280) time: 0.6408 [2021-03-28 17:41:31 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 370/1251] eta: 0:09:27 lr: 0.000012 loss: 2.7936 (2.6857) grad_norm: 3.5055 (3.9336) time: 0.6329 [2021-03-28 17:41:37 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 380/1251] eta: 0:09:21 lr: 0.000012 loss: 2.7588 (2.6839) grad_norm: 3.5188 (3.9316) time: 0.6379 [2021-03-28 17:41:44 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 390/1251] eta: 0:09:14 lr: 0.000012 loss: 2.7588 (2.6819) grad_norm: 3.6179 (3.9244) time: 0.6377 [2021-03-28 17:41:50 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 400/1251] eta: 0:09:07 lr: 0.000012 loss: 2.6937 (2.6819) grad_norm: 3.6368 (3.9262) time: 0.6355 [2021-03-28 17:41:56 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 410/1251] eta: 0:09:01 lr: 0.000012 loss: 2.6938 (2.6818) grad_norm: 3.7726 (3.9267) time: 0.6382 [2021-03-28 17:42:03 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 420/1251] eta: 0:08:54 lr: 0.000012 loss: 2.7365 (2.6827) grad_norm: 3.6213 (3.9164) time: 0.6316 [2021-03-28 17:42:09 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 430/1251] eta: 0:08:48 lr: 0.000012 loss: 2.7298 (2.6822) grad_norm: 3.4447 (3.9076) time: 0.6361 [2021-03-28 17:42:16 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 440/1251] eta: 0:08:41 lr: 0.000012 loss: 2.7448 (2.6843) grad_norm: 3.3017 (3.9093) time: 0.6402 [2021-03-28 17:42:22 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 450/1251] eta: 0:08:34 lr: 0.000012 loss: 2.8447 (2.6869) grad_norm: 3.7315 (3.9226) time: 0.6334 [2021-03-28 17:42:28 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 460/1251] eta: 0:08:28 lr: 0.000012 loss: 2.7598 (2.6859) grad_norm: 3.4946 (3.9163) time: 0.6331 [2021-03-28 17:42:35 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 470/1251] eta: 0:08:21 lr: 0.000012 loss: 2.8463 (2.6900) grad_norm: 3.4118 (3.9308) time: 0.6355 [2021-03-28 17:42:41 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 480/1251] eta: 0:08:15 lr: 0.000012 loss: 2.8463 (2.6882) grad_norm: 3.7387 (3.9257) time: 0.6322 [2021-03-28 17:42:47 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 490/1251] eta: 0:08:08 lr: 0.000012 loss: 2.6559 (2.6889) grad_norm: 3.5592 (3.9202) time: 0.6296 [2021-03-28 17:42:54 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 500/1251] eta: 0:08:02 lr: 0.000012 loss: 2.7890 (2.6903) grad_norm: 3.4528 (3.9091) time: 0.6346 [2021-03-28 17:43:00 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 510/1251] eta: 0:07:55 lr: 0.000012 loss: 2.7890 (2.6899) grad_norm: 3.6696 (3.9163) time: 0.6329 [2021-03-28 17:43:06 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 520/1251] eta: 0:07:49 lr: 0.000012 loss: 2.8539 (2.6920) grad_norm: 3.9325 (3.9104) time: 0.6373 [2021-03-28 17:43:13 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 530/1251] eta: 0:07:42 lr: 0.000012 loss: 2.8346 (2.6908) grad_norm: 3.5517 (3.9195) time: 0.6364 [2021-03-28 17:43:19 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 540/1251] eta: 0:07:35 lr: 0.000012 loss: 2.8111 (2.6923) grad_norm: 3.4468 (3.9103) time: 0.6257 [2021-03-28 17:43:25 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 550/1251] eta: 0:07:29 lr: 0.000012 loss: 2.9304 (2.6953) grad_norm: 3.4452 (3.9031) time: 0.6407 [2021-03-28 17:43:32 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 560/1251] eta: 0:07:23 lr: 0.000012 loss: 2.9304 (2.6951) grad_norm: 3.7452 (3.9046) time: 0.6484 [2021-03-28 17:43:38 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 570/1251] eta: 0:07:16 lr: 0.000012 loss: 2.8021 (2.6964) grad_norm: 3.7452 (3.8995) time: 0.6320 [2021-03-28 17:43:44 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 580/1251] eta: 0:07:10 lr: 0.000012 loss: 2.6529 (2.6940) grad_norm: 3.7000 (3.8999) time: 0.6339 [2021-03-28 17:43:51 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 590/1251] eta: 0:07:03 lr: 0.000012 loss: 2.7115 (2.6926) grad_norm: 3.8521 (3.8970) time: 0.6420 [2021-03-28 17:43:57 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 600/1251] eta: 0:06:57 lr: 0.000012 loss: 2.7716 (2.6918) grad_norm: 3.8126 (3.8991) time: 0.6370 [2021-03-28 17:44:04 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 610/1251] eta: 0:06:50 lr: 0.000012 loss: 2.5122 (2.6885) grad_norm: 3.6138 (3.9151) time: 0.6335 [2021-03-28 17:44:10 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 620/1251] eta: 0:06:44 lr: 0.000012 loss: 2.5122 (2.6855) grad_norm: 3.5690 (3.9084) time: 0.6374 [2021-03-28 17:44:16 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 630/1251] eta: 0:06:37 lr: 0.000012 loss: 2.5733 (2.6836) grad_norm: 3.6514 (3.9041) time: 0.6356 [2021-03-28 17:44:23 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 640/1251] eta: 0:06:31 lr: 0.000012 loss: 2.5726 (2.6810) grad_norm: 3.5440 (3.8979) time: 0.6337 [2021-03-28 17:44:29 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 650/1251] eta: 0:06:25 lr: 0.000012 loss: 2.7308 (2.6799) grad_norm: 3.5333 (3.8946) time: 0.6389 [2021-03-28 17:44:35 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 660/1251] eta: 0:06:18 lr: 0.000012 loss: 2.7308 (2.6792) grad_norm: 3.7287 (3.9032) time: 0.6334 [2021-03-28 17:44:42 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 670/1251] eta: 0:06:12 lr: 0.000012 loss: 2.4815 (2.6742) grad_norm: 3.9005 (3.9095) time: 0.6312 [2021-03-28 17:44:48 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 680/1251] eta: 0:06:05 lr: 0.000012 loss: 2.4843 (2.6737) grad_norm: 3.9277 (3.9093) time: 0.6359 [2021-03-28 17:44:54 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 690/1251] eta: 0:05:59 lr: 0.000012 loss: 2.6958 (2.6726) grad_norm: 3.4257 (3.9039) time: 0.6350 [2021-03-28 17:45:01 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 700/1251] eta: 0:05:52 lr: 0.000012 loss: 2.7829 (2.6724) grad_norm: 3.8587 (3.9102) time: 0.6371 [2021-03-28 17:45:07 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 710/1251] eta: 0:05:46 lr: 0.000011 loss: 2.8963 (2.6729) grad_norm: 3.8587 (3.9790) time: 0.6391 [2021-03-28 17:45:13 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 720/1251] eta: 0:05:39 lr: 0.000011 loss: 2.6360 (2.6698) grad_norm: 3.5685 (3.9753) time: 0.6351 [2021-03-28 17:45:20 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 730/1251] eta: 0:05:33 lr: 0.000011 loss: 2.6197 (2.6707) grad_norm: 3.7937 (3.9739) time: 0.6313 [2021-03-28 17:45:26 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 740/1251] eta: 0:05:27 lr: 0.000011 loss: 2.7269 (2.6689) grad_norm: 4.0508 (3.9817) time: 0.6346 [2021-03-28 17:45:33 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 750/1251] eta: 0:05:20 lr: 0.000011 loss: 2.5840 (2.6668) grad_norm: 4.2800 (3.9882) time: 0.6412 [2021-03-28 17:45:39 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 760/1251] eta: 0:05:14 lr: 0.000011 loss: 2.4798 (2.6637) grad_norm: 3.7664 (3.9870) time: 0.6449 [2021-03-28 17:45:46 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 770/1251] eta: 0:05:07 lr: 0.000011 loss: 2.4216 (2.6598) grad_norm: 3.5782 (3.9857) time: 0.6475 [2021-03-28 17:45:52 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 780/1251] eta: 0:05:01 lr: 0.000011 loss: 2.5831 (2.6591) grad_norm: 3.5815 (3.9915) time: 0.6438 [2021-03-28 17:45:58 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 790/1251] eta: 0:04:55 lr: 0.000011 loss: 2.7036 (2.6599) grad_norm: 3.5815 (4.0006) time: 0.6340 [2021-03-28 17:46:05 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 800/1251] eta: 0:04:48 lr: 0.000011 loss: 2.7125 (2.6594) grad_norm: 3.4818 (4.0009) time: 0.6306 [2021-03-28 17:46:11 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 810/1251] eta: 0:04:42 lr: 0.000011 loss: 2.6661 (2.6572) grad_norm: 3.5290 (3.9969) time: 0.6312 [2021-03-28 17:46:17 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 820/1251] eta: 0:04:35 lr: 0.000011 loss: 2.6661 (2.6576) grad_norm: 3.4279 (3.9901) time: 0.6265 [2021-03-28 17:46:24 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 830/1251] eta: 0:04:29 lr: 0.000011 loss: 2.7131 (2.6575) grad_norm: 3.5066 (3.9862) time: 0.6332 [2021-03-28 17:46:30 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 840/1251] eta: 0:04:22 lr: 0.000011 loss: 2.7131 (2.6592) grad_norm: 3.5202 (3.9834) time: 0.6414 [2021-03-28 17:46:36 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 850/1251] eta: 0:04:16 lr: 0.000011 loss: 2.6620 (2.6582) grad_norm: 3.6039 (3.9808) time: 0.6360 [2021-03-28 17:46:43 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 860/1251] eta: 0:04:10 lr: 0.000011 loss: 2.7534 (2.6585) grad_norm: 3.4874 (3.9749) time: 0.6316 [2021-03-28 17:46:49 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 870/1251] eta: 0:04:03 lr: 0.000011 loss: 2.6139 (2.6563) grad_norm: 3.5828 (3.9756) time: 0.6319 [2021-03-28 17:46:55 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 880/1251] eta: 0:03:57 lr: 0.000011 loss: 2.7145 (2.6578) grad_norm: 3.7876 (3.9730) time: 0.6353 [2021-03-28 17:47:02 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 890/1251] eta: 0:03:50 lr: 0.000011 loss: 2.7902 (2.6575) grad_norm: 3.7041 (3.9789) time: 0.6403 [2021-03-28 17:47:08 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 900/1251] eta: 0:03:44 lr: 0.000011 loss: 2.7344 (2.6563) grad_norm: 3.4674 (3.9735) time: 0.6313 [2021-03-28 17:47:14 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 910/1251] eta: 0:03:38 lr: 0.000011 loss: 2.6641 (2.6557) grad_norm: 3.7971 (3.9778) time: 0.6342 [2021-03-28 17:47:21 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 920/1251] eta: 0:03:31 lr: 0.000011 loss: 2.5961 (2.6545) grad_norm: 3.8519 (3.9759) time: 0.6392 [2021-03-28 17:47:27 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 930/1251] eta: 0:03:25 lr: 0.000011 loss: 2.6122 (2.6530) grad_norm: 3.7808 (3.9788) time: 0.6362 [2021-03-28 17:47:33 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 940/1251] eta: 0:03:18 lr: 0.000011 loss: 2.6281 (2.6519) grad_norm: 3.7808 (3.9856) time: 0.6390 [2021-03-28 17:47:40 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 950/1251] eta: 0:03:12 lr: 0.000011 loss: 2.5109 (2.6520) grad_norm: 3.5685 (3.9816) time: 0.6378 [2021-03-28 17:47:46 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 960/1251] eta: 0:03:05 lr: 0.000011 loss: 2.5577 (2.6513) grad_norm: 3.5249 (3.9853) time: 0.6365 [2021-03-28 17:47:52 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 970/1251] eta: 0:02:59 lr: 0.000011 loss: 2.6197 (2.6508) grad_norm: 3.7614 (3.9914) time: 0.6292 [2021-03-28 17:47:59 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 980/1251] eta: 0:02:53 lr: 0.000011 loss: 2.5898 (2.6499) grad_norm: 3.9767 (3.9907) time: 0.6322 [2021-03-28 17:48:05 swin_base_patch4_window7_224] INFO: Epoch: [292] [ 990/1251] eta: 0:02:46 lr: 0.000011 loss: 2.5898 (2.6497) grad_norm: 3.7927 (3.9934) time: 0.6367 [2021-03-28 17:48:11 swin_base_patch4_window7_224] INFO: Epoch: [292] [1000/1251] eta: 0:02:40 lr: 0.000011 loss: 2.6290 (2.6497) grad_norm: 3.4691 (3.9909) time: 0.6323 [2021-03-28 17:48:18 swin_base_patch4_window7_224] INFO: Epoch: [292] [1010/1251] eta: 0:02:33 lr: 0.000011 loss: 2.6605 (2.6495) grad_norm: 3.5551 (3.9895) time: 0.6362 [2021-03-28 17:48:24 swin_base_patch4_window7_224] INFO: Epoch: [292] [1020/1251] eta: 0:02:27 lr: 0.000011 loss: 2.6756 (2.6489) grad_norm: 3.5886 (3.9858) time: 0.6399 [2021-03-28 17:48:31 swin_base_patch4_window7_224] INFO: Epoch: [292] [1030/1251] eta: 0:02:21 lr: 0.000011 loss: 2.7221 (2.6498) grad_norm: 3.5686 (3.9828) time: 0.6328 [2021-03-28 17:48:37 swin_base_patch4_window7_224] INFO: Epoch: [292] [1040/1251] eta: 0:02:14 lr: 0.000011 loss: 2.7834 (2.6490) grad_norm: 3.7016 (4.0008) time: 0.6316 [2021-03-28 17:48:43 swin_base_patch4_window7_224] INFO: Epoch: [292] [1050/1251] eta: 0:02:08 lr: 0.000011 loss: 2.6184 (2.6473) grad_norm: 3.8493 (4.0216) time: 0.6310 [2021-03-28 17:48:50 swin_base_patch4_window7_224] INFO: Epoch: [292] [1060/1251] eta: 0:02:01 lr: 0.000011 loss: 2.6045 (2.6454) grad_norm: 3.6369 (4.0200) time: 0.6295 [2021-03-28 17:48:56 swin_base_patch4_window7_224] INFO: Epoch: [292] [1070/1251] eta: 0:01:55 lr: 0.000011 loss: 2.6127 (2.6462) grad_norm: 3.6369 (4.0190) time: 0.6373 [2021-03-28 17:49:02 swin_base_patch4_window7_224] INFO: Epoch: [292] [1080/1251] eta: 0:01:49 lr: 0.000011 loss: 2.6446 (2.6462) grad_norm: 4.0452 (4.0292) time: 0.6360 [2021-03-28 17:49:09 swin_base_patch4_window7_224] INFO: Epoch: [292] [1090/1251] eta: 0:01:42 lr: 0.000011 loss: 2.4292 (2.6424) grad_norm: 4.2923 (4.0289) time: 0.6297 [2021-03-28 17:49:15 swin_base_patch4_window7_224] INFO: Epoch: [292] [1100/1251] eta: 0:01:36 lr: 0.000011 loss: 2.2099 (2.6416) grad_norm: 3.5988 (4.0256) time: 0.6319 [2021-03-28 17:49:21 swin_base_patch4_window7_224] INFO: Epoch: [292] [1110/1251] eta: 0:01:30 lr: 0.000011 loss: 2.3790 (2.6397) grad_norm: 3.4824 (4.0284) time: 0.6330 [2021-03-28 17:49:28 swin_base_patch4_window7_224] INFO: Epoch: [292] [1120/1251] eta: 0:01:23 lr: 0.000011 loss: 2.6428 (2.6404) grad_norm: 3.4676 (4.0226) time: 0.6304 [2021-03-28 17:49:34 swin_base_patch4_window7_224] INFO: Epoch: [292] [1130/1251] eta: 0:01:17 lr: 0.000011 loss: 2.9183 (2.6430) grad_norm: 3.3790 (4.0191) time: 0.6373 [2021-03-28 17:49:40 swin_base_patch4_window7_224] INFO: Epoch: [292] [1140/1251] eta: 0:01:10 lr: 0.000011 loss: 2.9024 (2.6448) grad_norm: 3.5199 (4.0457) time: 0.6403 [2021-03-28 17:49:47 swin_base_patch4_window7_224] INFO: Epoch: [292] [1150/1251] eta: 0:01:04 lr: 0.000011 loss: 2.8285 (2.6446) grad_norm: 3.5199 (4.0448) time: 0.6364 [2021-03-28 17:49:53 swin_base_patch4_window7_224] INFO: Epoch: [292] [1160/1251] eta: 0:00:58 lr: 0.000011 loss: 2.7624 (2.6449) grad_norm: 3.5086 (4.0426) time: 0.6376 [2021-03-28 17:49:59 swin_base_patch4_window7_224] INFO: Epoch: [292] [1170/1251] eta: 0:00:51 lr: 0.000011 loss: 2.6710 (2.6443) grad_norm: 3.4721 (4.0397) time: 0.6334 [2021-03-28 17:50:06 swin_base_patch4_window7_224] INFO: Epoch: [292] [1180/1251] eta: 0:00:45 lr: 0.000011 loss: 2.5375 (2.6437) grad_norm: 3.4836 (4.0615) time: 0.6296 [2021-03-28 17:50:12 swin_base_patch4_window7_224] INFO: Epoch: [292] [1190/1251] eta: 0:00:38 lr: 0.000011 loss: 2.5375 (2.6423) grad_norm: 3.3062 (4.0558) time: 0.6311 [2021-03-28 17:50:18 swin_base_patch4_window7_224] INFO: Epoch: [292] [1200/1251] eta: 0:00:32 lr: 0.000011 loss: 2.6287 (2.6423) grad_norm: 3.3062 (4.0560) time: 0.6319 [2021-03-28 17:50:25 swin_base_patch4_window7_224] INFO: Epoch: [292] [1210/1251] eta: 0:00:26 lr: 0.000011 loss: 2.7960 (2.6440) grad_norm: 3.8068 (4.0577) time: 0.6318 [2021-03-28 17:50:31 swin_base_patch4_window7_224] INFO: Epoch: [292] [1220/1251] eta: 0:00:19 lr: 0.000011 loss: 2.8380 (2.6453) grad_norm: 3.8527 (4.0555) time: 0.6353 [2021-03-28 17:50:37 swin_base_patch4_window7_224] INFO: Epoch: [292] [1230/1251] eta: 0:00:13 lr: 0.000011 loss: 2.6870 (2.6443) grad_norm: 3.4722 (4.0500) time: 0.6344 [2021-03-28 17:50:44 swin_base_patch4_window7_224] INFO: Epoch: [292] [1240/1251] eta: 0:00:07 lr: 0.000011 loss: 2.6687 (2.6449) grad_norm: 3.4784 (4.0610) time: 0.6318 [2021-03-28 17:50:50 swin_base_patch4_window7_224] INFO: Epoch: [292] [1250/1251] eta: 0:00:00 lr: 0.000011 loss: 2.6333 (2.6434) grad_norm: 3.4951 (4.0572) time: 0.6232 [2021-03-28 17:51:01 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:42 loss: 0.5487 (0.5487) acc1: 84.3750 (84.3750) acc5: 100.0000 (100.0000) [2021-03-28 17:51:04 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.7575 (0.7366) acc1: 82.8125 (82.9545) acc5: 96.8750 (97.1591) [2021-03-28 17:51:07 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.7529 (0.7351) acc1: 82.8125 (83.4077) acc5: 96.8750 (96.8750) [2021-03-28 17:51:09 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7323 (0.7519) acc1: 82.8125 (82.9133) acc5: 96.8750 (96.4718) [2021-03-28 17:51:12 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7323 (0.7403) acc1: 82.8125 (83.2317) acc5: 96.8750 (96.6082) [2021-03-28 17:51:13 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7476 (0.7488) acc1: 82.8125 (82.5920) acc5: 96.8750 (96.5440) [2021-03-28 17:51:30 swin_base_patch4_window7_224] INFO: * Acc@1 83.396 Acc@5 96.438 loss 0.737 [2021-03-28 17:51:30 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 17:51:30 swin_base_patch4_window7_224] INFO: Max accuracy: 83.44% [2021-03-28 17:51:36 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 0/1251] eta: 1:53:45 lr: 0.000011 loss: 2.3632 (2.3632) grad_norm: 3.3867 (3.3867) time: 5.4563 [2021-03-28 17:51:42 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 10/1251] eta: 0:22:08 lr: 0.000011 loss: 2.8155 (2.6727) grad_norm: 3.3867 (4.2391) time: 1.0709 [2021-03-28 17:51:49 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 20/1251] eta: 0:17:42 lr: 0.000011 loss: 2.8306 (2.7064) grad_norm: 3.8669 (4.0995) time: 0.6338 [2021-03-28 17:51:55 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 30/1251] eta: 0:16:01 lr: 0.000011 loss: 2.6985 (2.6404) grad_norm: 3.4388 (3.9690) time: 0.6311 [2021-03-28 17:52:01 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 40/1251] eta: 0:15:08 lr: 0.000011 loss: 2.5046 (2.6032) grad_norm: 3.3812 (3.8854) time: 0.6305 [2021-03-28 17:52:07 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 50/1251] eta: 0:14:32 lr: 0.000011 loss: 2.6433 (2.6290) grad_norm: 3.5120 (3.8040) time: 0.6322 [2021-03-28 17:52:14 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 60/1251] eta: 0:14:06 lr: 0.000011 loss: 2.6824 (2.6396) grad_norm: 3.2993 (3.7714) time: 0.6298 [2021-03-28 17:52:20 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 70/1251] eta: 0:13:45 lr: 0.000011 loss: 2.7237 (2.6556) grad_norm: 3.5111 (3.7449) time: 0.6283 [2021-03-28 17:52:26 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 80/1251] eta: 0:13:27 lr: 0.000011 loss: 2.6144 (2.6578) grad_norm: 3.6327 (3.8278) time: 0.6260 [2021-03-28 17:52:33 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 90/1251] eta: 0:13:12 lr: 0.000011 loss: 2.5889 (2.6603) grad_norm: 3.6529 (3.8356) time: 0.6257 [2021-03-28 17:52:39 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 100/1251] eta: 0:12:59 lr: 0.000011 loss: 2.5627 (2.6367) grad_norm: 3.5629 (3.8561) time: 0.6275 [2021-03-28 17:52:45 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 110/1251] eta: 0:12:48 lr: 0.000011 loss: 2.4012 (2.6211) grad_norm: 3.5765 (3.9029) time: 0.6312 [2021-03-28 17:52:52 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 120/1251] eta: 0:12:37 lr: 0.000011 loss: 2.6482 (2.6127) grad_norm: 3.5765 (3.8962) time: 0.6333 [2021-03-28 17:52:58 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 130/1251] eta: 0:12:27 lr: 0.000011 loss: 2.7141 (2.6200) grad_norm: 3.5549 (3.8834) time: 0.6289 [2021-03-28 17:53:04 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 140/1251] eta: 0:12:18 lr: 0.000011 loss: 2.7794 (2.6288) grad_norm: 3.7220 (3.9117) time: 0.6299 [2021-03-28 17:53:10 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 150/1251] eta: 0:12:08 lr: 0.000011 loss: 2.5989 (2.6170) grad_norm: 3.4339 (3.8875) time: 0.6299 [2021-03-28 17:53:17 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 160/1251] eta: 0:11:59 lr: 0.000011 loss: 2.3977 (2.6108) grad_norm: 3.4521 (3.8768) time: 0.6246 [2021-03-28 17:53:23 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 170/1251] eta: 0:11:50 lr: 0.000011 loss: 2.4547 (2.6064) grad_norm: 3.5211 (3.9793) time: 0.6263 [2021-03-28 17:53:29 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 180/1251] eta: 0:11:42 lr: 0.000011 loss: 2.7163 (2.6036) grad_norm: 3.8110 (4.0277) time: 0.6274 [2021-03-28 17:53:35 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 190/1251] eta: 0:11:34 lr: 0.000011 loss: 2.6402 (2.5938) grad_norm: 3.8605 (4.0315) time: 0.6259 [2021-03-28 17:53:42 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 200/1251] eta: 0:11:26 lr: 0.000011 loss: 2.7522 (2.6045) grad_norm: 4.1275 (4.0510) time: 0.6278 [2021-03-28 17:53:48 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 210/1251] eta: 0:11:18 lr: 0.000011 loss: 2.6676 (2.5975) grad_norm: 3.6345 (4.0273) time: 0.6296 [2021-03-28 17:53:54 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 220/1251] eta: 0:11:10 lr: 0.000011 loss: 2.6033 (2.6046) grad_norm: 3.4470 (4.0175) time: 0.6278 [2021-03-28 17:54:01 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 230/1251] eta: 0:11:03 lr: 0.000011 loss: 2.6551 (2.6032) grad_norm: 3.5979 (4.0196) time: 0.6253 [2021-03-28 17:54:07 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 240/1251] eta: 0:10:55 lr: 0.000011 loss: 2.7103 (2.6044) grad_norm: 3.5199 (4.0042) time: 0.6249 [2021-03-28 17:54:13 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 250/1251] eta: 0:10:48 lr: 0.000011 loss: 2.7303 (2.6114) grad_norm: 3.2956 (4.0250) time: 0.6258 [2021-03-28 17:54:19 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 260/1251] eta: 0:10:41 lr: 0.000011 loss: 2.8834 (2.6208) grad_norm: 3.5105 (4.0043) time: 0.6306 [2021-03-28 17:54:26 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 270/1251] eta: 0:10:34 lr: 0.000011 loss: 2.8362 (2.6195) grad_norm: 3.3909 (3.9793) time: 0.6387 [2021-03-28 17:54:32 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 280/1251] eta: 0:10:27 lr: 0.000011 loss: 2.7725 (2.6171) grad_norm: 3.4781 (3.9747) time: 0.6350 [2021-03-28 17:54:38 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 290/1251] eta: 0:10:20 lr: 0.000011 loss: 2.5842 (2.6174) grad_norm: 3.6589 (3.9641) time: 0.6305 [2021-03-28 17:54:45 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 300/1251] eta: 0:10:13 lr: 0.000011 loss: 2.6864 (2.6165) grad_norm: 3.6470 (3.9703) time: 0.6343 [2021-03-28 17:54:51 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 310/1251] eta: 0:10:06 lr: 0.000011 loss: 2.7298 (2.6189) grad_norm: 3.6177 (3.9644) time: 0.6311 [2021-03-28 17:54:57 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 320/1251] eta: 0:10:00 lr: 0.000011 loss: 2.6752 (2.6232) grad_norm: 3.6265 (3.9624) time: 0.6329 [2021-03-28 17:55:04 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 330/1251] eta: 0:09:53 lr: 0.000011 loss: 2.8330 (2.6310) grad_norm: 3.7463 (3.9494) time: 0.6349 [2021-03-28 17:55:10 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 340/1251] eta: 0:09:46 lr: 0.000011 loss: 2.8689 (2.6366) grad_norm: 3.5242 (3.9428) time: 0.6315 [2021-03-28 17:55:17 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 350/1251] eta: 0:09:40 lr: 0.000011 loss: 2.7429 (2.6357) grad_norm: 3.5242 (3.9316) time: 0.6361 [2021-03-28 17:55:23 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 360/1251] eta: 0:09:33 lr: 0.000011 loss: 2.7429 (2.6390) grad_norm: 3.4097 (3.9177) time: 0.6395 [2021-03-28 17:55:29 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 370/1251] eta: 0:09:26 lr: 0.000011 loss: 2.7880 (2.6376) grad_norm: 3.4617 (3.9124) time: 0.6298 [2021-03-28 17:55:35 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 380/1251] eta: 0:09:19 lr: 0.000011 loss: 2.6630 (2.6357) grad_norm: 3.7277 (3.9128) time: 0.6280 [2021-03-28 17:55:42 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 390/1251] eta: 0:09:13 lr: 0.000011 loss: 2.6783 (2.6351) grad_norm: 3.7702 (3.9219) time: 0.6369 [2021-03-28 17:55:48 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 400/1251] eta: 0:09:07 lr: 0.000011 loss: 2.8541 (2.6400) grad_norm: 3.6305 (3.9190) time: 0.6400 [2021-03-28 17:55:55 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 410/1251] eta: 0:09:00 lr: 0.000011 loss: 2.8815 (2.6392) grad_norm: 3.6305 (3.9174) time: 0.6344 [2021-03-28 17:56:01 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 420/1251] eta: 0:08:53 lr: 0.000011 loss: 2.7595 (2.6369) grad_norm: 3.5189 (3.9110) time: 0.6267 [2021-03-28 17:56:07 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 430/1251] eta: 0:08:46 lr: 0.000011 loss: 2.7170 (2.6397) grad_norm: 3.5189 (3.9127) time: 0.6288 [2021-03-28 17:56:14 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 440/1251] eta: 0:08:40 lr: 0.000011 loss: 2.9203 (2.6446) grad_norm: 3.7764 (3.9116) time: 0.6355 [2021-03-28 17:56:20 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 450/1251] eta: 0:08:33 lr: 0.000011 loss: 2.6664 (2.6438) grad_norm: 3.7144 (3.9194) time: 0.6322 [2021-03-28 17:56:26 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 460/1251] eta: 0:08:26 lr: 0.000011 loss: 2.6620 (2.6462) grad_norm: 3.5265 (3.9250) time: 0.6238 [2021-03-28 17:56:32 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 470/1251] eta: 0:08:20 lr: 0.000011 loss: 2.7276 (2.6466) grad_norm: 3.4175 (3.9242) time: 0.6281 [2021-03-28 17:56:39 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 480/1251] eta: 0:08:13 lr: 0.000011 loss: 2.7356 (2.6465) grad_norm: 3.5517 (3.9175) time: 0.6346 [2021-03-28 17:56:45 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 490/1251] eta: 0:08:07 lr: 0.000011 loss: 2.6817 (2.6469) grad_norm: 3.5824 (3.9195) time: 0.6350 [2021-03-28 17:56:51 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 500/1251] eta: 0:08:00 lr: 0.000011 loss: 2.6143 (2.6435) grad_norm: 3.6674 (3.9262) time: 0.6333 [2021-03-28 17:56:58 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 510/1251] eta: 0:07:54 lr: 0.000011 loss: 2.6143 (2.6446) grad_norm: 3.6674 (3.9201) time: 0.6328 [2021-03-28 17:57:04 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 520/1251] eta: 0:07:48 lr: 0.000011 loss: 2.7504 (2.6435) grad_norm: 3.7223 (3.9186) time: 0.6358 [2021-03-28 17:57:10 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 530/1251] eta: 0:07:41 lr: 0.000011 loss: 2.5686 (2.6430) grad_norm: 3.9551 (3.9228) time: 0.6356 [2021-03-28 17:57:17 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 540/1251] eta: 0:07:35 lr: 0.000011 loss: 2.7318 (2.6408) grad_norm: 3.4974 (3.9197) time: 0.6354 [2021-03-28 17:57:23 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 550/1251] eta: 0:07:28 lr: 0.000011 loss: 2.7722 (2.6430) grad_norm: 3.4822 (3.9120) time: 0.6471 [2021-03-28 17:57:30 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 560/1251] eta: 0:07:22 lr: 0.000011 loss: 2.7647 (2.6417) grad_norm: 3.4644 (3.9158) time: 0.6498 [2021-03-28 17:57:36 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 570/1251] eta: 0:07:15 lr: 0.000011 loss: 2.6840 (2.6430) grad_norm: 3.4230 (3.9139) time: 0.6370 [2021-03-28 17:57:42 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 580/1251] eta: 0:07:09 lr: 0.000011 loss: 2.8090 (2.6460) grad_norm: 3.7374 (3.9250) time: 0.6317 [2021-03-28 17:57:49 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 590/1251] eta: 0:07:02 lr: 0.000011 loss: 2.7636 (2.6440) grad_norm: 3.7374 (3.9220) time: 0.6304 [2021-03-28 17:57:55 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 600/1251] eta: 0:06:56 lr: 0.000011 loss: 2.5841 (2.6420) grad_norm: 3.4698 (3.9523) time: 0.6327 [2021-03-28 17:58:02 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 610/1251] eta: 0:06:50 lr: 0.000011 loss: 2.4823 (2.6350) grad_norm: 3.4463 (3.9636) time: 0.6406 [2021-03-28 17:58:08 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 620/1251] eta: 0:06:43 lr: 0.000011 loss: 2.4754 (2.6334) grad_norm: 3.6414 (3.9637) time: 0.6391 [2021-03-28 17:58:14 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 630/1251] eta: 0:06:37 lr: 0.000011 loss: 2.6296 (2.6366) grad_norm: 3.6414 (3.9588) time: 0.6289 [2021-03-28 17:58:20 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 640/1251] eta: 0:06:30 lr: 0.000011 loss: 2.7722 (2.6353) grad_norm: 3.5992 (3.9543) time: 0.6256 [2021-03-28 17:58:27 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 650/1251] eta: 0:06:24 lr: 0.000011 loss: 2.5884 (2.6346) grad_norm: 3.6948 (3.9576) time: 0.6304 [2021-03-28 17:58:33 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 660/1251] eta: 0:06:17 lr: 0.000011 loss: 2.6730 (2.6350) grad_norm: 3.7231 (3.9529) time: 0.6329 [2021-03-28 17:58:39 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 670/1251] eta: 0:06:11 lr: 0.000011 loss: 2.7282 (2.6357) grad_norm: 3.6891 (3.9491) time: 0.6328 [2021-03-28 17:58:46 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 680/1251] eta: 0:06:04 lr: 0.000011 loss: 2.7929 (2.6373) grad_norm: 3.4094 (3.9515) time: 0.6368 [2021-03-28 17:58:52 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 690/1251] eta: 0:05:58 lr: 0.000011 loss: 2.8058 (2.6375) grad_norm: 3.4094 (3.9808) time: 0.6362 [2021-03-28 17:58:59 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 700/1251] eta: 0:05:52 lr: 0.000011 loss: 2.7032 (2.6352) grad_norm: 3.7619 (3.9785) time: 0.6366 [2021-03-28 17:59:05 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 710/1251] eta: 0:05:45 lr: 0.000011 loss: 2.7032 (2.6352) grad_norm: 3.7659 (nan) time: 0.6365 [2021-03-28 17:59:11 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 720/1251] eta: 0:05:39 lr: 0.000011 loss: 2.4786 (2.6327) grad_norm: 3.8051 (nan) time: 0.6315 [2021-03-28 17:59:17 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 730/1251] eta: 0:05:32 lr: 0.000011 loss: 2.3787 (2.6302) grad_norm: 3.6804 (nan) time: 0.6313 [2021-03-28 17:59:24 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 740/1251] eta: 0:05:26 lr: 0.000011 loss: 2.5064 (2.6297) grad_norm: 3.5275 (nan) time: 0.6388 [2021-03-28 17:59:30 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 750/1251] eta: 0:05:20 lr: 0.000011 loss: 2.7179 (2.6303) grad_norm: 3.3925 (nan) time: 0.6451 [2021-03-28 17:59:37 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 760/1251] eta: 0:05:13 lr: 0.000011 loss: 2.6739 (2.6282) grad_norm: 3.4802 (nan) time: 0.6349 [2021-03-28 17:59:43 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 770/1251] eta: 0:05:07 lr: 0.000011 loss: 2.6348 (2.6292) grad_norm: 3.8571 (nan) time: 0.6235 [2021-03-28 17:59:49 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 780/1251] eta: 0:05:00 lr: 0.000011 loss: 2.8020 (2.6306) grad_norm: 3.4711 (nan) time: 0.6266 [2021-03-28 17:59:56 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 790/1251] eta: 0:04:54 lr: 0.000011 loss: 2.6048 (2.6270) grad_norm: 3.4524 (nan) time: 0.6323 [2021-03-28 18:00:02 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 800/1251] eta: 0:04:47 lr: 0.000011 loss: 2.7362 (2.6297) grad_norm: 3.4245 (nan) time: 0.6296 [2021-03-28 18:00:08 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 810/1251] eta: 0:04:41 lr: 0.000011 loss: 2.8157 (2.6304) grad_norm: 3.3907 (nan) time: 0.6283 [2021-03-28 18:00:14 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 820/1251] eta: 0:04:35 lr: 0.000011 loss: 2.7651 (2.6319) grad_norm: 3.6247 (nan) time: 0.6329 [2021-03-28 18:00:21 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 830/1251] eta: 0:04:28 lr: 0.000011 loss: 2.7651 (2.6318) grad_norm: 3.6602 (nan) time: 0.6314 [2021-03-28 18:00:27 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 840/1251] eta: 0:04:22 lr: 0.000011 loss: 2.5458 (2.6307) grad_norm: 3.8062 (nan) time: 0.6307 [2021-03-28 18:00:33 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 850/1251] eta: 0:04:15 lr: 0.000011 loss: 2.6847 (2.6315) grad_norm: 3.7160 (nan) time: 0.6354 [2021-03-28 18:00:40 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 860/1251] eta: 0:04:09 lr: 0.000011 loss: 2.6847 (2.6320) grad_norm: 3.7695 (nan) time: 0.6330 [2021-03-28 18:00:46 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 870/1251] eta: 0:04:02 lr: 0.000011 loss: 2.6941 (2.6319) grad_norm: 3.8537 (nan) time: 0.6278 [2021-03-28 18:00:52 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 880/1251] eta: 0:03:56 lr: 0.000011 loss: 2.7128 (2.6320) grad_norm: 3.6496 (nan) time: 0.6257 [2021-03-28 18:00:59 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 890/1251] eta: 0:03:50 lr: 0.000011 loss: 2.7704 (2.6314) grad_norm: 3.6545 (nan) time: 0.6339 [2021-03-28 18:01:05 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 900/1251] eta: 0:03:43 lr: 0.000011 loss: 2.7524 (2.6299) grad_norm: 3.6823 (nan) time: 0.6374 [2021-03-28 18:01:11 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 910/1251] eta: 0:03:37 lr: 0.000011 loss: 2.5398 (2.6294) grad_norm: 3.8488 (nan) time: 0.6316 [2021-03-28 18:01:18 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 920/1251] eta: 0:03:30 lr: 0.000011 loss: 2.6604 (2.6305) grad_norm: 3.6861 (nan) time: 0.6322 [2021-03-28 18:01:24 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 930/1251] eta: 0:03:24 lr: 0.000011 loss: 2.8141 (2.6320) grad_norm: 3.2786 (nan) time: 0.6334 [2021-03-28 18:01:30 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 940/1251] eta: 0:03:18 lr: 0.000011 loss: 2.9016 (2.6343) grad_norm: 3.5634 (nan) time: 0.6310 [2021-03-28 18:01:37 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 950/1251] eta: 0:03:11 lr: 0.000011 loss: 2.8626 (2.6351) grad_norm: 3.5634 (nan) time: 0.6341 [2021-03-28 18:01:43 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 960/1251] eta: 0:03:05 lr: 0.000011 loss: 2.6038 (2.6347) grad_norm: 3.5391 (nan) time: 0.6345 [2021-03-28 18:01:49 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 970/1251] eta: 0:02:59 lr: 0.000011 loss: 2.6271 (2.6349) grad_norm: 3.4470 (nan) time: 0.6305 [2021-03-28 18:01:56 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 980/1251] eta: 0:02:52 lr: 0.000011 loss: 2.7325 (2.6360) grad_norm: 3.5941 (nan) time: 0.6300 [2021-03-28 18:02:02 swin_base_patch4_window7_224] INFO: Epoch: [293] [ 990/1251] eta: 0:02:46 lr: 0.000011 loss: 2.7257 (2.6355) grad_norm: 3.2704 (nan) time: 0.6337 [2021-03-28 18:02:08 swin_base_patch4_window7_224] INFO: Epoch: [293] [1000/1251] eta: 0:02:39 lr: 0.000011 loss: 2.6206 (2.6336) grad_norm: 3.2882 (nan) time: 0.6393 [2021-03-28 18:02:15 swin_base_patch4_window7_224] INFO: Epoch: [293] [1010/1251] eta: 0:02:33 lr: 0.000011 loss: 2.6206 (2.6330) grad_norm: 3.5567 (nan) time: 0.6346 [2021-03-28 18:02:21 swin_base_patch4_window7_224] INFO: Epoch: [293] [1020/1251] eta: 0:02:27 lr: 0.000011 loss: 2.5199 (2.6305) grad_norm: 3.5896 (nan) time: 0.6334 [2021-03-28 18:02:27 swin_base_patch4_window7_224] INFO: Epoch: [293] [1030/1251] eta: 0:02:20 lr: 0.000011 loss: 2.4526 (2.6299) grad_norm: 3.4045 (nan) time: 0.6286 [2021-03-28 18:02:34 swin_base_patch4_window7_224] INFO: Epoch: [293] [1040/1251] eta: 0:02:14 lr: 0.000011 loss: 2.6728 (2.6293) grad_norm: 3.6748 (nan) time: 0.6267 [2021-03-28 18:02:40 swin_base_patch4_window7_224] INFO: Epoch: [293] [1050/1251] eta: 0:02:07 lr: 0.000011 loss: 2.4282 (2.6271) grad_norm: 3.8377 (nan) time: 0.6350 [2021-03-28 18:02:46 swin_base_patch4_window7_224] INFO: Epoch: [293] [1060/1251] eta: 0:02:01 lr: 0.000011 loss: 2.4063 (2.6265) grad_norm: 3.5072 (nan) time: 0.6383 [2021-03-28 18:02:53 swin_base_patch4_window7_224] INFO: Epoch: [293] [1070/1251] eta: 0:01:55 lr: 0.000011 loss: 2.4962 (2.6251) grad_norm: 3.8156 (nan) time: 0.6393 [2021-03-28 18:02:59 swin_base_patch4_window7_224] INFO: Epoch: [293] [1080/1251] eta: 0:01:48 lr: 0.000011 loss: 2.6206 (2.6243) grad_norm: 3.8462 (nan) time: 0.6333 [2021-03-28 18:03:05 swin_base_patch4_window7_224] INFO: Epoch: [293] [1090/1251] eta: 0:01:42 lr: 0.000011 loss: 2.5733 (2.6236) grad_norm: 3.7093 (nan) time: 0.6321 [2021-03-28 18:03:12 swin_base_patch4_window7_224] INFO: Epoch: [293] [1100/1251] eta: 0:01:36 lr: 0.000011 loss: 2.6473 (2.6244) grad_norm: 3.2422 (nan) time: 0.6307 [2021-03-28 18:03:18 swin_base_patch4_window7_224] INFO: Epoch: [293] [1110/1251] eta: 0:01:29 lr: 0.000011 loss: 2.7680 (2.6240) grad_norm: 3.5387 (nan) time: 0.6291 [2021-03-28 18:03:24 swin_base_patch4_window7_224] INFO: Epoch: [293] [1120/1251] eta: 0:01:23 lr: 0.000011 loss: 2.7120 (2.6243) grad_norm: 3.8648 (nan) time: 0.6326 [2021-03-28 18:03:31 swin_base_patch4_window7_224] INFO: Epoch: [293] [1130/1251] eta: 0:01:17 lr: 0.000011 loss: 2.6161 (2.6234) grad_norm: 3.5361 (nan) time: 0.6291 [2021-03-28 18:03:37 swin_base_patch4_window7_224] INFO: Epoch: [293] [1140/1251] eta: 0:01:10 lr: 0.000011 loss: 2.4985 (2.6223) grad_norm: 4.0318 (nan) time: 0.6288 [2021-03-28 18:03:43 swin_base_patch4_window7_224] INFO: Epoch: [293] [1150/1251] eta: 0:01:04 lr: 0.000011 loss: 2.6924 (2.6234) grad_norm: 3.7664 (nan) time: 0.6316 [2021-03-28 18:03:49 swin_base_patch4_window7_224] INFO: Epoch: [293] [1160/1251] eta: 0:00:57 lr: 0.000011 loss: 2.6924 (2.6217) grad_norm: 3.4168 (nan) time: 0.6266 [2021-03-28 18:03:56 swin_base_patch4_window7_224] INFO: Epoch: [293] [1170/1251] eta: 0:00:51 lr: 0.000011 loss: 2.6794 (2.6214) grad_norm: 3.4904 (nan) time: 0.6256 [2021-03-28 18:04:02 swin_base_patch4_window7_224] INFO: Epoch: [293] [1180/1251] eta: 0:00:45 lr: 0.000011 loss: 2.3699 (2.6199) grad_norm: 3.5433 (nan) time: 0.6327 [2021-03-28 18:04:08 swin_base_patch4_window7_224] INFO: Epoch: [293] [1190/1251] eta: 0:00:38 lr: 0.000011 loss: 2.7591 (2.6211) grad_norm: 3.5433 (nan) time: 0.6308 [2021-03-28 18:04:15 swin_base_patch4_window7_224] INFO: Epoch: [293] [1200/1251] eta: 0:00:32 lr: 0.000011 loss: 2.6793 (2.6201) grad_norm: 3.5431 (nan) time: 0.6257 [2021-03-28 18:04:21 swin_base_patch4_window7_224] INFO: Epoch: [293] [1210/1251] eta: 0:00:26 lr: 0.000011 loss: 2.5317 (2.6184) grad_norm: 3.5135 (nan) time: 0.6262 [2021-03-28 18:04:27 swin_base_patch4_window7_224] INFO: Epoch: [293] [1220/1251] eta: 0:00:19 lr: 0.000011 loss: 2.6277 (2.6188) grad_norm: 3.6887 (nan) time: 0.6267 [2021-03-28 18:04:33 swin_base_patch4_window7_224] INFO: Epoch: [293] [1230/1251] eta: 0:00:13 lr: 0.000011 loss: 2.6383 (2.6180) grad_norm: 3.6764 (nan) time: 0.6260 [2021-03-28 18:04:40 swin_base_patch4_window7_224] INFO: Epoch: [293] [1240/1251] eta: 0:00:06 lr: 0.000011 loss: 2.7822 (2.6198) grad_norm: 3.6023 (nan) time: 0.6268 [2021-03-28 18:04:46 swin_base_patch4_window7_224] INFO: Epoch: [293] [1250/1251] eta: 0:00:00 lr: 0.000011 loss: 2.6861 (2.6187) grad_norm: 3.4197 (nan) time: 0.6276 [2021-03-28 18:04:58 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:20 loss: 0.9155 (0.9155) acc1: 84.3750 (84.3750) acc5: 95.3125 (95.3125) [2021-03-28 18:05:01 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8381 (0.7742) acc1: 81.2500 (81.6761) acc5: 96.8750 (96.5909) [2021-03-28 18:05:03 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7184 (0.7192) acc1: 84.3750 (83.1101) acc5: 96.8750 (96.7262) [2021-03-28 18:05:05 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7806 (0.7545) acc1: 84.3750 (82.6109) acc5: 95.3125 (96.2702) [2021-03-28 18:05:06 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7827 (0.7508) acc1: 81.2500 (82.6220) acc5: 96.8750 (96.4177) [2021-03-28 18:05:08 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7010 (0.7449) acc1: 82.8125 (82.3040) acc5: 96.8750 (96.5760) [2021-03-28 18:05:24 swin_base_patch4_window7_224] INFO: * Acc@1 83.414 Acc@5 96.496 loss 0.734 [2021-03-28 18:05:24 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 18:05:24 swin_base_patch4_window7_224] INFO: Max accuracy: 83.44% [2021-03-28 18:05:29 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 0/1251] eta: 1:27:09 lr: 0.000011 loss: 2.8935 (2.8935) grad_norm: 3.2602 (3.2602) time: 4.1805 [2021-03-28 18:05:35 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 10/1251] eta: 0:20:10 lr: 0.000011 loss: 2.8935 (2.7624) grad_norm: 3.7570 (3.8049) time: 0.9758 [2021-03-28 18:05:42 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 20/1251] eta: 0:16:46 lr: 0.000011 loss: 2.7515 (2.7438) grad_norm: 3.7570 (3.8574) time: 0.6493 [2021-03-28 18:05:48 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 30/1251] eta: 0:15:26 lr: 0.000011 loss: 2.7707 (2.7367) grad_norm: 3.8022 (3.8435) time: 0.6392 [2021-03-28 18:05:54 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 40/1251] eta: 0:14:42 lr: 0.000011 loss: 2.7119 (2.7171) grad_norm: 3.7228 (3.8141) time: 0.6360 [2021-03-28 18:06:00 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 50/1251] eta: 0:14:10 lr: 0.000011 loss: 2.7119 (2.7195) grad_norm: 3.4507 (3.8120) time: 0.6307 [2021-03-28 18:06:07 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 60/1251] eta: 0:13:47 lr: 0.000011 loss: 2.6357 (2.6624) grad_norm: 3.3597 (3.8475) time: 0.6252 [2021-03-28 18:06:13 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 70/1251] eta: 0:13:31 lr: 0.000011 loss: 2.5821 (2.6778) grad_norm: 3.5741 (3.8874) time: 0.6333 [2021-03-28 18:06:20 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 80/1251] eta: 0:13:18 lr: 0.000011 loss: 2.7264 (2.6675) grad_norm: 3.5578 (3.8277) time: 0.6438 [2021-03-28 18:06:26 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 90/1251] eta: 0:13:05 lr: 0.000011 loss: 2.5468 (2.6495) grad_norm: 3.2593 (3.7723) time: 0.6400 [2021-03-28 18:06:32 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 100/1251] eta: 0:12:53 lr: 0.000011 loss: 2.5067 (2.6470) grad_norm: 3.3010 (3.7938) time: 0.6320 [2021-03-28 18:06:39 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 110/1251] eta: 0:12:43 lr: 0.000011 loss: 2.5569 (2.6274) grad_norm: 3.6770 (3.8488) time: 0.6344 [2021-03-28 18:06:45 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 120/1251] eta: 0:12:33 lr: 0.000011 loss: 2.7090 (2.6423) grad_norm: 3.1866 (3.8010) time: 0.6344 [2021-03-28 18:06:51 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 130/1251] eta: 0:12:23 lr: 0.000011 loss: 2.7214 (2.6247) grad_norm: 3.0262 (3.7559) time: 0.6303 [2021-03-28 18:06:58 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 140/1251] eta: 0:12:15 lr: 0.000011 loss: 2.7202 (2.6375) grad_norm: 3.1922 (3.7785) time: 0.6393 [2021-03-28 18:07:04 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 150/1251] eta: 0:12:07 lr: 0.000011 loss: 2.7202 (2.6299) grad_norm: 3.3992 (3.7978) time: 0.6440 [2021-03-28 18:07:10 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 160/1251] eta: 0:11:58 lr: 0.000011 loss: 2.7155 (2.6366) grad_norm: 3.6536 (3.8293) time: 0.6292 [2021-03-28 18:07:17 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 170/1251] eta: 0:11:50 lr: 0.000011 loss: 2.8166 (2.6419) grad_norm: 3.5347 (3.8132) time: 0.6295 [2021-03-28 18:07:23 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 180/1251] eta: 0:11:42 lr: 0.000011 loss: 2.8199 (2.6471) grad_norm: 3.1035 (3.7770) time: 0.6390 [2021-03-28 18:07:29 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 190/1251] eta: 0:11:34 lr: 0.000011 loss: 2.7743 (2.6525) grad_norm: 3.0996 (3.7602) time: 0.6348 [2021-03-28 18:07:36 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 200/1251] eta: 0:11:26 lr: 0.000011 loss: 2.5864 (2.6477) grad_norm: 3.4815 (3.7631) time: 0.6319 [2021-03-28 18:07:42 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 210/1251] eta: 0:11:19 lr: 0.000011 loss: 2.3428 (2.6283) grad_norm: 3.4815 (3.7508) time: 0.6344 [2021-03-28 18:07:48 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 220/1251] eta: 0:11:12 lr: 0.000011 loss: 2.4368 (2.6331) grad_norm: 3.5037 (3.7468) time: 0.6339 [2021-03-28 18:07:55 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 230/1251] eta: 0:11:04 lr: 0.000011 loss: 2.7729 (2.6249) grad_norm: 3.6776 (3.7510) time: 0.6333 [2021-03-28 18:08:01 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 240/1251] eta: 0:10:57 lr: 0.000011 loss: 2.6680 (2.6233) grad_norm: 3.5331 (3.7517) time: 0.6346 [2021-03-28 18:08:08 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 250/1251] eta: 0:10:50 lr: 0.000011 loss: 2.6778 (2.6198) grad_norm: 3.6947 (3.7975) time: 0.6371 [2021-03-28 18:08:14 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 260/1251] eta: 0:10:43 lr: 0.000011 loss: 2.7722 (2.6230) grad_norm: 3.7117 (3.7962) time: 0.6422 [2021-03-28 18:08:20 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 270/1251] eta: 0:10:37 lr: 0.000011 loss: 2.7722 (2.6233) grad_norm: 3.6230 (3.7940) time: 0.6457 [2021-03-28 18:08:27 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 280/1251] eta: 0:10:30 lr: 0.000011 loss: 2.6728 (2.6296) grad_norm: 3.5891 (3.7892) time: 0.6361 [2021-03-28 18:08:33 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 290/1251] eta: 0:10:22 lr: 0.000011 loss: 2.6765 (2.6321) grad_norm: 3.5302 (3.8084) time: 0.6264 [2021-03-28 18:08:39 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 300/1251] eta: 0:10:15 lr: 0.000011 loss: 2.6869 (2.6303) grad_norm: 3.4399 (3.8033) time: 0.6284 [2021-03-28 18:08:46 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 310/1251] eta: 0:10:08 lr: 0.000011 loss: 2.7531 (2.6345) grad_norm: 3.3823 (3.7960) time: 0.6339 [2021-03-28 18:08:52 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 320/1251] eta: 0:10:02 lr: 0.000011 loss: 2.7531 (2.6354) grad_norm: 3.6631 (3.7916) time: 0.6362 [2021-03-28 18:08:58 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 330/1251] eta: 0:09:55 lr: 0.000011 loss: 2.8063 (2.6385) grad_norm: 3.6430 (3.7888) time: 0.6320 [2021-03-28 18:09:05 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 340/1251] eta: 0:09:48 lr: 0.000011 loss: 2.8268 (2.6402) grad_norm: 3.8261 (3.8113) time: 0.6334 [2021-03-28 18:09:11 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 350/1251] eta: 0:09:41 lr: 0.000011 loss: 2.8268 (2.6448) grad_norm: 3.8261 (3.8111) time: 0.6347 [2021-03-28 18:09:17 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 360/1251] eta: 0:09:34 lr: 0.000011 loss: 2.7265 (2.6424) grad_norm: 3.5865 (3.8294) time: 0.6300 [2021-03-28 18:09:24 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 370/1251] eta: 0:09:28 lr: 0.000011 loss: 2.4733 (2.6362) grad_norm: 3.6153 (3.8337) time: 0.6340 [2021-03-28 18:09:30 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 380/1251] eta: 0:09:21 lr: 0.000011 loss: 2.5474 (2.6345) grad_norm: 3.6213 (3.8334) time: 0.6378 [2021-03-28 18:09:36 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 390/1251] eta: 0:09:14 lr: 0.000011 loss: 2.6339 (2.6371) grad_norm: 3.6900 (3.8270) time: 0.6315 [2021-03-28 18:09:43 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 400/1251] eta: 0:09:08 lr: 0.000011 loss: 2.6339 (2.6376) grad_norm: 3.6900 (3.8312) time: 0.6299 [2021-03-28 18:09:49 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 410/1251] eta: 0:09:01 lr: 0.000011 loss: 2.6993 (2.6405) grad_norm: 3.7824 (3.8463) time: 0.6322 [2021-03-28 18:09:55 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 420/1251] eta: 0:08:54 lr: 0.000011 loss: 2.8317 (2.6422) grad_norm: 3.7509 (3.8609) time: 0.6322 [2021-03-28 18:10:02 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 430/1251] eta: 0:08:47 lr: 0.000011 loss: 2.7831 (2.6398) grad_norm: 3.5487 (3.8494) time: 0.6299 [2021-03-28 18:10:08 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 440/1251] eta: 0:08:41 lr: 0.000011 loss: 2.6010 (2.6381) grad_norm: 3.5487 (3.8723) time: 0.6301 [2021-03-28 18:10:14 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 450/1251] eta: 0:08:34 lr: 0.000011 loss: 2.5401 (2.6333) grad_norm: 3.8212 (3.8973) time: 0.6343 [2021-03-28 18:10:21 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 460/1251] eta: 0:08:28 lr: 0.000011 loss: 2.4746 (2.6271) grad_norm: 3.5958 (3.9039) time: 0.6379 [2021-03-28 18:10:27 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 470/1251] eta: 0:08:21 lr: 0.000011 loss: 2.4829 (2.6257) grad_norm: 3.9385 (3.9071) time: 0.6413 [2021-03-28 18:10:33 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 480/1251] eta: 0:08:15 lr: 0.000011 loss: 2.6408 (2.6246) grad_norm: 3.3233 (3.9000) time: 0.6412 [2021-03-28 18:10:40 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 490/1251] eta: 0:08:08 lr: 0.000011 loss: 2.6624 (2.6261) grad_norm: 3.6730 (3.9146) time: 0.6374 [2021-03-28 18:10:46 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 500/1251] eta: 0:08:02 lr: 0.000011 loss: 2.6929 (2.6259) grad_norm: 3.9641 (3.9233) time: 0.6395 [2021-03-28 18:10:53 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 510/1251] eta: 0:07:55 lr: 0.000011 loss: 2.7702 (2.6261) grad_norm: 4.1980 (3.9291) time: 0.6353 [2021-03-28 18:10:59 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 520/1251] eta: 0:07:49 lr: 0.000011 loss: 2.7501 (2.6228) grad_norm: 3.6598 (3.9231) time: 0.6287 [2021-03-28 18:11:05 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 530/1251] eta: 0:07:42 lr: 0.000011 loss: 2.6148 (2.6220) grad_norm: 3.6598 (3.9696) time: 0.6335 [2021-03-28 18:11:11 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 540/1251] eta: 0:07:36 lr: 0.000011 loss: 2.8634 (2.6267) grad_norm: 3.6610 (3.9617) time: 0.6308 [2021-03-28 18:11:18 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 550/1251] eta: 0:07:29 lr: 0.000011 loss: 2.8679 (2.6282) grad_norm: 3.5369 (3.9975) time: 0.6418 [2021-03-28 18:11:25 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 560/1251] eta: 0:07:23 lr: 0.000011 loss: 2.6711 (2.6266) grad_norm: 3.3673 (3.9885) time: 0.6525 [2021-03-28 18:11:31 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 570/1251] eta: 0:07:16 lr: 0.000011 loss: 2.7250 (2.6290) grad_norm: 3.3363 (3.9815) time: 0.6374 [2021-03-28 18:11:37 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 580/1251] eta: 0:07:10 lr: 0.000011 loss: 2.6524 (2.6246) grad_norm: 3.4789 (3.9726) time: 0.6336 [2021-03-28 18:11:44 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 590/1251] eta: 0:07:03 lr: 0.000011 loss: 2.5566 (2.6245) grad_norm: 3.6630 (3.9734) time: 0.6351 [2021-03-28 18:11:50 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 600/1251] eta: 0:06:57 lr: 0.000011 loss: 2.5945 (2.6214) grad_norm: 3.7954 (3.9709) time: 0.6288 [2021-03-28 18:11:56 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 610/1251] eta: 0:06:50 lr: 0.000011 loss: 2.5945 (2.6205) grad_norm: 3.5886 (3.9703) time: 0.6324 [2021-03-28 18:12:03 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 620/1251] eta: 0:06:44 lr: 0.000011 loss: 2.7403 (2.6206) grad_norm: 3.5316 (3.9622) time: 0.6383 [2021-03-28 18:12:09 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 630/1251] eta: 0:06:38 lr: 0.000011 loss: 2.5982 (2.6191) grad_norm: 3.3021 (3.9695) time: 0.6353 [2021-03-28 18:12:15 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 640/1251] eta: 0:06:31 lr: 0.000011 loss: 2.7927 (2.6223) grad_norm: 3.6907 (3.9693) time: 0.6281 [2021-03-28 18:12:21 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 650/1251] eta: 0:06:24 lr: 0.000011 loss: 2.7718 (2.6203) grad_norm: 3.7232 (3.9663) time: 0.6252 [2021-03-28 18:12:28 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 660/1251] eta: 0:06:18 lr: 0.000011 loss: 2.7696 (2.6231) grad_norm: 3.7210 (3.9664) time: 0.6339 [2021-03-28 18:12:34 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 670/1251] eta: 0:06:11 lr: 0.000011 loss: 2.7746 (2.6257) grad_norm: 3.8266 (3.9753) time: 0.6328 [2021-03-28 18:12:40 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 680/1251] eta: 0:06:05 lr: 0.000011 loss: 2.7746 (2.6270) grad_norm: 3.8266 (3.9820) time: 0.6340 [2021-03-28 18:12:47 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 690/1251] eta: 0:05:59 lr: 0.000011 loss: 2.8267 (2.6285) grad_norm: 3.6911 (3.9804) time: 0.6362 [2021-03-28 18:12:53 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 700/1251] eta: 0:05:52 lr: 0.000011 loss: 2.5611 (2.6261) grad_norm: 3.6911 (3.9796) time: 0.6257 [2021-03-28 18:12:59 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 710/1251] eta: 0:05:46 lr: 0.000011 loss: 2.5611 (2.6260) grad_norm: 3.7821 (3.9735) time: 0.6284 [2021-03-28 18:13:06 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 720/1251] eta: 0:05:39 lr: 0.000011 loss: 2.8200 (2.6280) grad_norm: 3.7873 (3.9775) time: 0.6322 [2021-03-28 18:13:12 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 730/1251] eta: 0:05:33 lr: 0.000011 loss: 2.7236 (2.6271) grad_norm: 4.0519 (3.9781) time: 0.6355 [2021-03-28 18:13:18 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 740/1251] eta: 0:05:26 lr: 0.000011 loss: 2.7236 (2.6293) grad_norm: 3.7300 (3.9762) time: 0.6391 [2021-03-28 18:13:25 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 750/1251] eta: 0:05:20 lr: 0.000011 loss: 2.7860 (2.6292) grad_norm: 3.5495 (3.9773) time: 0.6351 [2021-03-28 18:13:31 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 760/1251] eta: 0:05:13 lr: 0.000011 loss: 2.7516 (2.6294) grad_norm: 3.7618 (3.9772) time: 0.6302 [2021-03-28 18:13:37 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 770/1251] eta: 0:05:07 lr: 0.000011 loss: 2.7650 (2.6307) grad_norm: 3.6650 (3.9744) time: 0.6349 [2021-03-28 18:13:44 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 780/1251] eta: 0:05:01 lr: 0.000011 loss: 2.6978 (2.6286) grad_norm: 3.5929 (3.9701) time: 0.6416 [2021-03-28 18:13:50 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 790/1251] eta: 0:04:54 lr: 0.000011 loss: 2.6389 (2.6286) grad_norm: 3.5929 (3.9662) time: 0.6305 [2021-03-28 18:13:56 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 800/1251] eta: 0:04:48 lr: 0.000011 loss: 2.5891 (2.6267) grad_norm: 3.6421 (3.9655) time: 0.6286 [2021-03-28 18:14:03 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 810/1251] eta: 0:04:41 lr: 0.000011 loss: 2.5891 (2.6272) grad_norm: 3.6421 (3.9615) time: 0.6366 [2021-03-28 18:14:09 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 820/1251] eta: 0:04:35 lr: 0.000011 loss: 2.8096 (2.6295) grad_norm: 3.7939 (3.9703) time: 0.6396 [2021-03-28 18:14:16 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 830/1251] eta: 0:04:29 lr: 0.000011 loss: 2.8061 (2.6307) grad_norm: 3.8169 (3.9758) time: 0.6339 [2021-03-28 18:14:22 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 840/1251] eta: 0:04:22 lr: 0.000011 loss: 2.7273 (2.6321) grad_norm: 3.7540 (3.9756) time: 0.6311 [2021-03-28 18:14:28 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 850/1251] eta: 0:04:16 lr: 0.000011 loss: 2.8073 (2.6347) grad_norm: 3.6075 (3.9738) time: 0.6372 [2021-03-28 18:14:35 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 860/1251] eta: 0:04:09 lr: 0.000011 loss: 2.7798 (2.6338) grad_norm: 3.4228 (3.9682) time: 0.6321 [2021-03-28 18:14:41 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 870/1251] eta: 0:04:03 lr: 0.000011 loss: 2.6761 (2.6333) grad_norm: 3.5264 (3.9688) time: 0.6326 [2021-03-28 18:14:47 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 880/1251] eta: 0:03:57 lr: 0.000011 loss: 2.5668 (2.6323) grad_norm: 3.7250 (3.9734) time: 0.6395 [2021-03-28 18:14:54 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 890/1251] eta: 0:03:50 lr: 0.000011 loss: 2.6368 (2.6337) grad_norm: 3.6660 (3.9776) time: 0.6391 [2021-03-28 18:15:00 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 900/1251] eta: 0:03:44 lr: 0.000011 loss: 2.6101 (2.6329) grad_norm: 3.5066 (3.9811) time: 0.6346 [2021-03-28 18:15:06 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 910/1251] eta: 0:03:37 lr: 0.000011 loss: 2.5961 (2.6346) grad_norm: 3.5066 (3.9765) time: 0.6333 [2021-03-28 18:15:13 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 920/1251] eta: 0:03:31 lr: 0.000011 loss: 2.5881 (2.6308) grad_norm: 3.3546 (3.9734) time: 0.6335 [2021-03-28 18:15:19 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 930/1251] eta: 0:03:24 lr: 0.000011 loss: 2.4877 (2.6318) grad_norm: 3.3022 (3.9672) time: 0.6344 [2021-03-28 18:15:25 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 940/1251] eta: 0:03:18 lr: 0.000011 loss: 2.8334 (2.6329) grad_norm: 3.4606 (3.9773) time: 0.6321 [2021-03-28 18:15:32 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 950/1251] eta: 0:03:12 lr: 0.000011 loss: 2.7735 (2.6339) grad_norm: 3.7908 (3.9769) time: 0.6300 [2021-03-28 18:15:38 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 960/1251] eta: 0:03:05 lr: 0.000011 loss: 2.7172 (2.6330) grad_norm: 3.9158 (3.9822) time: 0.6367 [2021-03-28 18:15:44 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 970/1251] eta: 0:02:59 lr: 0.000011 loss: 2.5990 (2.6311) grad_norm: 3.8512 (3.9801) time: 0.6373 [2021-03-28 18:15:51 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 980/1251] eta: 0:02:53 lr: 0.000011 loss: 2.5751 (2.6310) grad_norm: 3.4264 (3.9740) time: 0.6353 [2021-03-28 18:15:57 swin_base_patch4_window7_224] INFO: Epoch: [294] [ 990/1251] eta: 0:02:46 lr: 0.000011 loss: 2.6962 (2.6319) grad_norm: 3.5725 (3.9706) time: 0.6381 [2021-03-28 18:16:04 swin_base_patch4_window7_224] INFO: Epoch: [294] [1000/1251] eta: 0:02:40 lr: 0.000011 loss: 2.7159 (2.6326) grad_norm: 3.5725 (3.9666) time: 0.6398 [2021-03-28 18:16:10 swin_base_patch4_window7_224] INFO: Epoch: [294] [1010/1251] eta: 0:02:33 lr: 0.000011 loss: 2.6723 (2.6327) grad_norm: 3.5748 (3.9681) time: 0.6358 [2021-03-28 18:16:16 swin_base_patch4_window7_224] INFO: Epoch: [294] [1020/1251] eta: 0:02:27 lr: 0.000011 loss: 2.5646 (2.6316) grad_norm: 3.4367 (3.9624) time: 0.6356 [2021-03-28 18:16:23 swin_base_patch4_window7_224] INFO: Epoch: [294] [1030/1251] eta: 0:02:21 lr: 0.000011 loss: 2.6698 (2.6317) grad_norm: 3.3781 (3.9598) time: 0.6376 [2021-03-28 18:16:29 swin_base_patch4_window7_224] INFO: Epoch: [294] [1040/1251] eta: 0:02:14 lr: 0.000011 loss: 2.6084 (2.6305) grad_norm: 3.5332 (3.9566) time: 0.6337 [2021-03-28 18:16:35 swin_base_patch4_window7_224] INFO: Epoch: [294] [1050/1251] eta: 0:02:08 lr: 0.000011 loss: 2.7118 (2.6319) grad_norm: 3.5332 (3.9556) time: 0.6331 [2021-03-28 18:16:42 swin_base_patch4_window7_224] INFO: Epoch: [294] [1060/1251] eta: 0:02:01 lr: 0.000011 loss: 2.7835 (2.6316) grad_norm: 3.8509 (3.9529) time: 0.6353 [2021-03-28 18:16:48 swin_base_patch4_window7_224] INFO: Epoch: [294] [1070/1251] eta: 0:01:55 lr: 0.000011 loss: 2.6532 (2.6308) grad_norm: 3.5530 (3.9537) time: 0.6290 [2021-03-28 18:16:54 swin_base_patch4_window7_224] INFO: Epoch: [294] [1080/1251] eta: 0:01:49 lr: 0.000011 loss: 2.7706 (2.6322) grad_norm: 3.5784 (3.9591) time: 0.6284 [2021-03-28 18:17:01 swin_base_patch4_window7_224] INFO: Epoch: [294] [1090/1251] eta: 0:01:42 lr: 0.000011 loss: 2.8908 (2.6329) grad_norm: 3.5784 (3.9605) time: 0.6350 [2021-03-28 18:17:07 swin_base_patch4_window7_224] INFO: Epoch: [294] [1100/1251] eta: 0:01:36 lr: 0.000011 loss: 2.5542 (2.6308) grad_norm: 3.4308 (3.9594) time: 0.6322 [2021-03-28 18:17:13 swin_base_patch4_window7_224] INFO: Epoch: [294] [1110/1251] eta: 0:01:29 lr: 0.000011 loss: 2.5212 (2.6299) grad_norm: 3.4311 (3.9653) time: 0.6334 [2021-03-28 18:17:20 swin_base_patch4_window7_224] INFO: Epoch: [294] [1120/1251] eta: 0:01:23 lr: 0.000011 loss: 2.6172 (2.6298) grad_norm: 3.3734 (3.9626) time: 0.6424 [2021-03-28 18:17:26 swin_base_patch4_window7_224] INFO: Epoch: [294] [1130/1251] eta: 0:01:17 lr: 0.000011 loss: 2.5548 (2.6275) grad_norm: 3.4847 (3.9620) time: 0.6385 [2021-03-28 18:17:32 swin_base_patch4_window7_224] INFO: Epoch: [294] [1140/1251] eta: 0:01:10 lr: 0.000011 loss: 2.4681 (2.6269) grad_norm: 3.4847 (3.9625) time: 0.6317 [2021-03-28 18:17:39 swin_base_patch4_window7_224] INFO: Epoch: [294] [1150/1251] eta: 0:01:04 lr: 0.000011 loss: 2.5712 (2.6267) grad_norm: 3.5604 (3.9658) time: 0.6314 [2021-03-28 18:17:45 swin_base_patch4_window7_224] INFO: Epoch: [294] [1160/1251] eta: 0:00:58 lr: 0.000011 loss: 2.6893 (2.6282) grad_norm: 3.5092 (3.9756) time: 0.6305 [2021-03-28 18:17:51 swin_base_patch4_window7_224] INFO: Epoch: [294] [1170/1251] eta: 0:00:51 lr: 0.000011 loss: 2.8471 (2.6283) grad_norm: 3.5894 (3.9760) time: 0.6309 [2021-03-28 18:17:58 swin_base_patch4_window7_224] INFO: Epoch: [294] [1180/1251] eta: 0:00:45 lr: 0.000011 loss: 2.6740 (2.6270) grad_norm: 3.7184 (3.9716) time: 0.6352 [2021-03-28 18:18:04 swin_base_patch4_window7_224] INFO: Epoch: [294] [1190/1251] eta: 0:00:38 lr: 0.000011 loss: 2.7190 (2.6281) grad_norm: 3.3905 (3.9684) time: 0.6396 [2021-03-28 18:18:10 swin_base_patch4_window7_224] INFO: Epoch: [294] [1200/1251] eta: 0:00:32 lr: 0.000011 loss: 2.9099 (2.6304) grad_norm: 3.5439 (3.9679) time: 0.6345 [2021-03-28 18:18:17 swin_base_patch4_window7_224] INFO: Epoch: [294] [1210/1251] eta: 0:00:26 lr: 0.000011 loss: 2.7643 (2.6297) grad_norm: 3.7680 (3.9748) time: 0.6248 [2021-03-28 18:18:23 swin_base_patch4_window7_224] INFO: Epoch: [294] [1220/1251] eta: 0:00:19 lr: 0.000011 loss: 2.6427 (2.6299) grad_norm: 3.9804 (3.9752) time: 0.6265 [2021-03-28 18:18:29 swin_base_patch4_window7_224] INFO: Epoch: [294] [1230/1251] eta: 0:00:13 lr: 0.000011 loss: 2.7833 (2.6299) grad_norm: 3.4289 (3.9696) time: 0.6291 [2021-03-28 18:18:35 swin_base_patch4_window7_224] INFO: Epoch: [294] [1240/1251] eta: 0:00:07 lr: 0.000011 loss: 2.6739 (2.6290) grad_norm: 3.3689 (3.9696) time: 0.6269 [2021-03-28 18:18:42 swin_base_patch4_window7_224] INFO: Epoch: [294] [1250/1251] eta: 0:00:00 lr: 0.000011 loss: 2.7091 (2.6298) grad_norm: 3.7924 (3.9734) time: 0.6280 [2021-03-28 18:18:54 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:59 loss: 0.9242 (0.9242) acc1: 75.0000 (75.0000) acc5: 95.3125 (95.3125) [2021-03-28 18:18:56 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7544 (0.7944) acc1: 81.2500 (80.5398) acc5: 96.8750 (96.3068) [2021-03-28 18:18:59 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7347 (0.7655) acc1: 81.2500 (81.6964) acc5: 96.8750 (96.2798) [2021-03-28 18:19:01 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7256 (0.7790) acc1: 81.2500 (81.9052) acc5: 95.3125 (96.3206) [2021-03-28 18:19:03 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7070 (0.7444) acc1: 82.8125 (82.5457) acc5: 96.8750 (96.4939) [2021-03-28 18:19:04 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7014 (0.7485) acc1: 82.8125 (82.4320) acc5: 96.8750 (96.5760) [2021-03-28 18:19:19 swin_base_patch4_window7_224] INFO: * Acc@1 83.422 Acc@5 96.434 loss 0.739 [2021-03-28 18:19:19 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 18:19:19 swin_base_patch4_window7_224] INFO: Max accuracy: 83.44% [2021-03-28 18:19:23 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 0/1251] eta: 1:31:32 lr: 0.000011 loss: 1.8945 (1.8945) grad_norm: 4.6108 (4.6108) time: 4.3901 [2021-03-28 18:19:30 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 10/1251] eta: 0:20:15 lr: 0.000011 loss: 2.9474 (2.7590) grad_norm: 3.6432 (3.6451) time: 0.9791 [2021-03-28 18:19:36 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 20/1251] eta: 0:16:38 lr: 0.000011 loss: 2.9369 (2.7406) grad_norm: 3.6432 (3.7547) time: 0.6324 [2021-03-28 18:19:42 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 30/1251] eta: 0:15:21 lr: 0.000011 loss: 2.6943 (2.6975) grad_norm: 3.3513 (3.6029) time: 0.6308 [2021-03-28 18:19:49 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 40/1251] eta: 0:14:40 lr: 0.000011 loss: 2.5827 (2.5999) grad_norm: 3.3513 (3.6710) time: 0.6380 [2021-03-28 18:19:55 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 50/1251] eta: 0:14:09 lr: 0.000011 loss: 2.5884 (2.6159) grad_norm: 3.4578 (3.7018) time: 0.6348 [2021-03-28 18:20:01 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 60/1251] eta: 0:13:48 lr: 0.000011 loss: 2.6240 (2.6099) grad_norm: 3.4578 (3.8052) time: 0.6307 [2021-03-28 18:20:08 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 70/1251] eta: 0:13:31 lr: 0.000011 loss: 2.7300 (2.6244) grad_norm: 3.5116 (3.7868) time: 0.6337 [2021-03-28 18:20:14 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 80/1251] eta: 0:13:16 lr: 0.000011 loss: 2.6091 (2.6153) grad_norm: 3.6367 (3.8082) time: 0.6331 [2021-03-28 18:20:20 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 90/1251] eta: 0:13:04 lr: 0.000011 loss: 2.5818 (2.5977) grad_norm: 3.5825 (3.7980) time: 0.6376 [2021-03-28 18:20:27 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 100/1251] eta: 0:12:53 lr: 0.000011 loss: 2.5976 (2.6081) grad_norm: 3.5503 (3.7931) time: 0.6408 [2021-03-28 18:20:33 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 110/1251] eta: 0:12:43 lr: 0.000011 loss: 2.8754 (2.6245) grad_norm: 3.6749 (3.7817) time: 0.6394 [2021-03-28 18:20:40 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 120/1251] eta: 0:12:33 lr: 0.000011 loss: 2.8780 (2.6420) grad_norm: 3.5575 (3.8013) time: 0.6347 [2021-03-28 18:20:46 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 130/1251] eta: 0:12:23 lr: 0.000011 loss: 2.6555 (2.6334) grad_norm: 3.5474 (3.8241) time: 0.6310 [2021-03-28 18:20:52 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 140/1251] eta: 0:12:13 lr: 0.000011 loss: 2.5706 (2.6368) grad_norm: 3.4221 (3.8092) time: 0.6284 [2021-03-28 18:20:58 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 150/1251] eta: 0:12:05 lr: 0.000011 loss: 2.7939 (2.6454) grad_norm: 3.5325 (3.8009) time: 0.6272 [2021-03-28 18:21:05 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 160/1251] eta: 0:11:56 lr: 0.000011 loss: 2.8790 (2.6587) grad_norm: 3.5655 (3.8149) time: 0.6316 [2021-03-28 18:21:11 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 170/1251] eta: 0:11:48 lr: 0.000011 loss: 2.8947 (2.6561) grad_norm: 3.8861 (3.9011) time: 0.6346 [2021-03-28 18:21:17 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 180/1251] eta: 0:11:40 lr: 0.000011 loss: 2.8246 (2.6655) grad_norm: 3.9777 (3.9288) time: 0.6333 [2021-03-28 18:21:24 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 190/1251] eta: 0:11:33 lr: 0.000011 loss: 2.8054 (2.6672) grad_norm: 3.8194 (3.9293) time: 0.6300 [2021-03-28 18:21:30 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 200/1251] eta: 0:11:25 lr: 0.000011 loss: 2.6725 (2.6679) grad_norm: 3.8468 (3.9437) time: 0.6325 [2021-03-28 18:21:36 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 210/1251] eta: 0:11:17 lr: 0.000011 loss: 2.5558 (2.6576) grad_norm: 3.8468 (3.9448) time: 0.6324 [2021-03-28 18:21:43 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 220/1251] eta: 0:11:10 lr: 0.000011 loss: 2.5857 (2.6530) grad_norm: 3.5013 (3.9371) time: 0.6292 [2021-03-28 18:21:49 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 230/1251] eta: 0:11:03 lr: 0.000011 loss: 2.4743 (2.6449) grad_norm: 3.7165 (3.9277) time: 0.6301 [2021-03-28 18:21:55 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 240/1251] eta: 0:10:55 lr: 0.000011 loss: 2.4508 (2.6377) grad_norm: 3.8473 (3.9319) time: 0.6299 [2021-03-28 18:22:02 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 250/1251] eta: 0:10:48 lr: 0.000011 loss: 2.6511 (2.6336) grad_norm: 3.8355 (3.9441) time: 0.6281 [2021-03-28 18:22:08 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 260/1251] eta: 0:10:41 lr: 0.000011 loss: 2.6511 (2.6370) grad_norm: 3.3591 (3.9257) time: 0.6301 [2021-03-28 18:22:14 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 270/1251] eta: 0:10:34 lr: 0.000011 loss: 2.7758 (2.6479) grad_norm: 3.3448 (3.9086) time: 0.6350 [2021-03-28 18:22:20 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 280/1251] eta: 0:10:27 lr: 0.000011 loss: 2.8718 (2.6551) grad_norm: 3.3448 (3.9091) time: 0.6323 [2021-03-28 18:22:27 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 290/1251] eta: 0:10:20 lr: 0.000011 loss: 2.9419 (2.6605) grad_norm: 3.4033 (3.9121) time: 0.6286 [2021-03-28 18:22:33 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 300/1251] eta: 0:10:13 lr: 0.000011 loss: 2.7474 (2.6526) grad_norm: 3.5845 (3.9151) time: 0.6311 [2021-03-28 18:22:39 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 310/1251] eta: 0:10:06 lr: 0.000011 loss: 2.6967 (2.6532) grad_norm: 3.5845 (3.9107) time: 0.6310 [2021-03-28 18:22:46 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 320/1251] eta: 0:09:59 lr: 0.000011 loss: 2.7841 (2.6546) grad_norm: 3.4899 (3.9030) time: 0.6340 [2021-03-28 18:22:52 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 330/1251] eta: 0:09:53 lr: 0.000011 loss: 2.8313 (2.6529) grad_norm: 3.5800 (3.9002) time: 0.6384 [2021-03-28 18:22:59 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 340/1251] eta: 0:09:46 lr: 0.000011 loss: 2.6351 (2.6542) grad_norm: 3.8660 (3.8964) time: 0.6375 [2021-03-28 18:23:05 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 350/1251] eta: 0:09:39 lr: 0.000011 loss: 2.6035 (2.6518) grad_norm: 3.9257 (3.9177) time: 0.6300 [2021-03-28 18:23:11 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 360/1251] eta: 0:09:32 lr: 0.000011 loss: 2.4463 (2.6493) grad_norm: 3.7325 (3.9154) time: 0.6261 [2021-03-28 18:23:17 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 370/1251] eta: 0:09:25 lr: 0.000011 loss: 2.4047 (2.6473) grad_norm: 3.4205 (3.9067) time: 0.6253 [2021-03-28 18:23:24 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 380/1251] eta: 0:09:19 lr: 0.000011 loss: 2.6213 (2.6456) grad_norm: 3.3471 (3.8918) time: 0.6254 [2021-03-28 18:23:30 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 390/1251] eta: 0:09:12 lr: 0.000011 loss: 2.5668 (2.6425) grad_norm: 3.3769 (3.8876) time: 0.6312 [2021-03-28 18:23:36 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 400/1251] eta: 0:09:05 lr: 0.000011 loss: 2.2949 (2.6370) grad_norm: 3.7215 (3.8851) time: 0.6325 [2021-03-28 18:23:43 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 410/1251] eta: 0:08:59 lr: 0.000011 loss: 2.6061 (2.6371) grad_norm: 3.7394 (3.8834) time: 0.6305 [2021-03-28 18:23:49 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 420/1251] eta: 0:08:52 lr: 0.000011 loss: 2.5788 (2.6336) grad_norm: 3.6324 (3.8988) time: 0.6294 [2021-03-28 18:23:55 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 430/1251] eta: 0:08:46 lr: 0.000011 loss: 2.5788 (2.6339) grad_norm: 3.5533 (3.9161) time: 0.6287 [2021-03-28 18:24:01 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 440/1251] eta: 0:08:39 lr: 0.000011 loss: 2.7451 (2.6318) grad_norm: 3.6082 (3.9166) time: 0.6318 [2021-03-28 18:24:08 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 450/1251] eta: 0:08:33 lr: 0.000011 loss: 2.7451 (2.6347) grad_norm: 3.6082 (3.9187) time: 0.6368 [2021-03-28 18:24:14 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 460/1251] eta: 0:08:26 lr: 0.000011 loss: 2.7986 (2.6359) grad_norm: 3.5619 (3.9173) time: 0.6338 [2021-03-28 18:24:21 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 470/1251] eta: 0:08:20 lr: 0.000011 loss: 2.7800 (2.6382) grad_norm: 3.5619 (3.9119) time: 0.6362 [2021-03-28 18:24:27 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 480/1251] eta: 0:08:13 lr: 0.000011 loss: 2.6506 (2.6338) grad_norm: 3.6326 (3.9072) time: 0.6357 [2021-03-28 18:24:33 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 490/1251] eta: 0:08:07 lr: 0.000011 loss: 2.6164 (2.6330) grad_norm: 3.6326 (3.9031) time: 0.6328 [2021-03-28 18:24:40 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 500/1251] eta: 0:08:00 lr: 0.000011 loss: 2.6164 (2.6299) grad_norm: 3.8224 (3.9047) time: 0.6364 [2021-03-28 18:24:46 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 510/1251] eta: 0:07:53 lr: 0.000011 loss: 2.7028 (2.6326) grad_norm: 3.8543 (3.9105) time: 0.6303 [2021-03-28 18:24:52 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 520/1251] eta: 0:07:47 lr: 0.000011 loss: 2.9461 (2.6375) grad_norm: 3.7557 (3.9163) time: 0.6273 [2021-03-28 18:24:59 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 530/1251] eta: 0:07:41 lr: 0.000011 loss: 2.8820 (2.6414) grad_norm: 3.6037 (3.9091) time: 0.6337 [2021-03-28 18:25:05 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 540/1251] eta: 0:07:34 lr: 0.000011 loss: 2.6539 (2.6403) grad_norm: 3.4744 (3.9135) time: 0.6316 [2021-03-28 18:25:11 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 550/1251] eta: 0:07:28 lr: 0.000011 loss: 2.4687 (2.6421) grad_norm: 3.5565 (3.9292) time: 0.6363 [2021-03-28 18:25:18 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 560/1251] eta: 0:07:21 lr: 0.000011 loss: 2.8592 (2.6432) grad_norm: 3.3926 (3.9211) time: 0.6430 [2021-03-28 18:25:24 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 570/1251] eta: 0:07:15 lr: 0.000011 loss: 2.7432 (2.6436) grad_norm: 3.3208 (3.9136) time: 0.6365 [2021-03-28 18:25:30 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 580/1251] eta: 0:07:08 lr: 0.000011 loss: 2.5945 (2.6385) grad_norm: 3.5908 (3.9136) time: 0.6306 [2021-03-28 18:25:37 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 590/1251] eta: 0:07:02 lr: 0.000011 loss: 2.4581 (2.6380) grad_norm: 3.6681 (3.9118) time: 0.6310 [2021-03-28 18:25:43 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 600/1251] eta: 0:06:56 lr: 0.000011 loss: 2.8269 (2.6376) grad_norm: 3.6174 (3.9157) time: 0.6417 [2021-03-28 18:25:49 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 610/1251] eta: 0:06:49 lr: 0.000011 loss: 2.7345 (2.6360) grad_norm: 3.5746 (3.9168) time: 0.6402 [2021-03-28 18:25:56 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 620/1251] eta: 0:06:43 lr: 0.000011 loss: 2.5291 (2.6366) grad_norm: 3.5884 (3.9181) time: 0.6302 [2021-03-28 18:26:02 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 630/1251] eta: 0:06:36 lr: 0.000011 loss: 2.7169 (2.6382) grad_norm: 3.7400 (3.9256) time: 0.6335 [2021-03-28 18:26:08 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 640/1251] eta: 0:06:30 lr: 0.000011 loss: 2.8022 (2.6362) grad_norm: 3.6735 (3.9394) time: 0.6332 [2021-03-28 18:26:15 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 650/1251] eta: 0:06:23 lr: 0.000011 loss: 2.8688 (2.6378) grad_norm: 3.6735 (3.9457) time: 0.6331 [2021-03-28 18:26:21 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 660/1251] eta: 0:06:17 lr: 0.000011 loss: 2.9047 (2.6391) grad_norm: 3.6169 (3.9434) time: 0.6373 [2021-03-28 18:26:27 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 670/1251] eta: 0:06:10 lr: 0.000011 loss: 2.7993 (2.6365) grad_norm: 3.4332 (3.9375) time: 0.6314 [2021-03-28 18:26:34 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 680/1251] eta: 0:06:04 lr: 0.000011 loss: 2.7482 (2.6378) grad_norm: 3.4225 (3.9335) time: 0.6291 [2021-03-28 18:26:40 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 690/1251] eta: 0:05:58 lr: 0.000011 loss: 2.6242 (2.6365) grad_norm: 3.5335 (3.9310) time: 0.6314 [2021-03-28 18:26:46 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 700/1251] eta: 0:05:51 lr: 0.000011 loss: 2.8193 (2.6394) grad_norm: 4.0016 (3.9375) time: 0.6322 [2021-03-28 18:26:53 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 710/1251] eta: 0:05:45 lr: 0.000011 loss: 2.8787 (2.6389) grad_norm: 3.9980 (3.9355) time: 0.6317 [2021-03-28 18:26:59 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 720/1251] eta: 0:05:38 lr: 0.000011 loss: 2.4588 (2.6340) grad_norm: 3.4173 (3.9334) time: 0.6314 [2021-03-28 18:27:05 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 730/1251] eta: 0:05:32 lr: 0.000011 loss: 2.5190 (2.6356) grad_norm: 3.4230 (3.9335) time: 0.6314 [2021-03-28 18:27:12 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 740/1251] eta: 0:05:26 lr: 0.000011 loss: 2.7421 (2.6360) grad_norm: 3.4230 (3.9387) time: 0.6398 [2021-03-28 18:27:18 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 750/1251] eta: 0:05:19 lr: 0.000011 loss: 2.7543 (2.6371) grad_norm: 3.4207 (3.9358) time: 0.6444 [2021-03-28 18:27:25 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 760/1251] eta: 0:05:13 lr: 0.000011 loss: 2.5397 (2.6360) grad_norm: 3.9366 (3.9438) time: 0.6422 [2021-03-28 18:27:31 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 770/1251] eta: 0:05:06 lr: 0.000011 loss: 2.6272 (2.6379) grad_norm: 3.9271 (3.9485) time: 0.6356 [2021-03-28 18:27:37 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 780/1251] eta: 0:05:00 lr: 0.000011 loss: 2.5628 (2.6362) grad_norm: 3.5709 (3.9455) time: 0.6258 [2021-03-28 18:27:44 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 790/1251] eta: 0:04:54 lr: 0.000011 loss: 2.6048 (2.6360) grad_norm: 3.6827 (3.9546) time: 0.6364 [2021-03-28 18:27:50 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 800/1251] eta: 0:04:47 lr: 0.000011 loss: 2.6613 (2.6355) grad_norm: 3.7493 (3.9517) time: 0.6364 [2021-03-28 18:27:56 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 810/1251] eta: 0:04:41 lr: 0.000011 loss: 2.7643 (2.6354) grad_norm: 3.8684 (3.9534) time: 0.6242 [2021-03-28 18:28:02 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 820/1251] eta: 0:04:34 lr: 0.000011 loss: 2.8318 (2.6344) grad_norm: 3.7372 (3.9503) time: 0.6266 [2021-03-28 18:28:09 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 830/1251] eta: 0:04:28 lr: 0.000011 loss: 2.8750 (2.6359) grad_norm: 3.4272 (3.9504) time: 0.6349 [2021-03-28 18:28:15 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 840/1251] eta: 0:04:22 lr: 0.000011 loss: 2.5876 (2.6328) grad_norm: 3.8851 (3.9619) time: 0.6390 [2021-03-28 18:28:22 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 850/1251] eta: 0:04:15 lr: 0.000011 loss: 2.4156 (2.6323) grad_norm: 3.8937 (3.9771) time: 0.6405 [2021-03-28 18:28:28 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 860/1251] eta: 0:04:09 lr: 0.000011 loss: 2.5368 (2.6313) grad_norm: 3.8551 (3.9841) time: 0.6377 [2021-03-28 18:28:34 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 870/1251] eta: 0:04:02 lr: 0.000011 loss: 2.6849 (2.6338) grad_norm: 3.9580 (3.9815) time: 0.6357 [2021-03-28 18:28:41 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 880/1251] eta: 0:03:56 lr: 0.000011 loss: 2.7185 (2.6333) grad_norm: 3.5775 (3.9784) time: 0.6359 [2021-03-28 18:28:47 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 890/1251] eta: 0:03:50 lr: 0.000010 loss: 2.7934 (2.6361) grad_norm: 3.7294 (3.9834) time: 0.6346 [2021-03-28 18:28:53 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 900/1251] eta: 0:03:43 lr: 0.000010 loss: 2.7934 (2.6350) grad_norm: 4.0211 (3.9807) time: 0.6368 [2021-03-28 18:29:00 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 910/1251] eta: 0:03:37 lr: 0.000010 loss: 2.4873 (2.6334) grad_norm: 3.4036 (3.9786) time: 0.6334 [2021-03-28 18:29:06 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 920/1251] eta: 0:03:30 lr: 0.000010 loss: 2.7930 (2.6349) grad_norm: 3.3620 (3.9844) time: 0.6327 [2021-03-28 18:29:12 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 930/1251] eta: 0:03:24 lr: 0.000010 loss: 2.8023 (2.6349) grad_norm: 3.6299 (3.9835) time: 0.6342 [2021-03-28 18:29:19 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 940/1251] eta: 0:03:18 lr: 0.000010 loss: 2.8023 (2.6366) grad_norm: 3.6651 (3.9808) time: 0.6335 [2021-03-28 18:29:25 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 950/1251] eta: 0:03:11 lr: 0.000010 loss: 2.8141 (2.6362) grad_norm: 3.7761 (3.9788) time: 0.6278 [2021-03-28 18:29:31 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 960/1251] eta: 0:03:05 lr: 0.000010 loss: 2.7725 (2.6366) grad_norm: 3.6551 (3.9769) time: 0.6297 [2021-03-28 18:29:38 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 970/1251] eta: 0:02:59 lr: 0.000010 loss: 2.7972 (2.6376) grad_norm: 3.7997 (3.9834) time: 0.6347 [2021-03-28 18:29:44 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 980/1251] eta: 0:02:52 lr: 0.000010 loss: 2.6419 (2.6368) grad_norm: 3.8967 (3.9836) time: 0.6281 [2021-03-28 18:29:50 swin_base_patch4_window7_224] INFO: Epoch: [295] [ 990/1251] eta: 0:02:46 lr: 0.000010 loss: 2.5569 (2.6365) grad_norm: 3.7303 (3.9824) time: 0.6284 [2021-03-28 18:29:57 swin_base_patch4_window7_224] INFO: Epoch: [295] [1000/1251] eta: 0:02:39 lr: 0.000010 loss: 2.6608 (2.6372) grad_norm: 3.7153 (3.9806) time: 0.6321 [2021-03-28 18:30:03 swin_base_patch4_window7_224] INFO: Epoch: [295] [1010/1251] eta: 0:02:33 lr: 0.000010 loss: 2.6855 (2.6374) grad_norm: 3.6037 (3.9781) time: 0.6324 [2021-03-28 18:30:09 swin_base_patch4_window7_224] INFO: Epoch: [295] [1020/1251] eta: 0:02:27 lr: 0.000010 loss: 2.7662 (2.6373) grad_norm: 3.5948 (3.9822) time: 0.6300 [2021-03-28 18:30:15 swin_base_patch4_window7_224] INFO: Epoch: [295] [1030/1251] eta: 0:02:20 lr: 0.000010 loss: 2.7856 (2.6396) grad_norm: 3.6625 (3.9792) time: 0.6287 [2021-03-28 18:30:22 swin_base_patch4_window7_224] INFO: Epoch: [295] [1040/1251] eta: 0:02:14 lr: 0.000010 loss: 2.7755 (2.6409) grad_norm: 3.6013 (3.9735) time: 0.6331 [2021-03-28 18:30:28 swin_base_patch4_window7_224] INFO: Epoch: [295] [1050/1251] eta: 0:02:07 lr: 0.000010 loss: 2.6992 (2.6394) grad_norm: 3.6706 (3.9736) time: 0.6365 [2021-03-28 18:30:35 swin_base_patch4_window7_224] INFO: Epoch: [295] [1060/1251] eta: 0:02:01 lr: 0.000010 loss: 2.6686 (2.6394) grad_norm: 3.5581 (3.9698) time: 0.6382 [2021-03-28 18:30:41 swin_base_patch4_window7_224] INFO: Epoch: [295] [1070/1251] eta: 0:01:55 lr: 0.000010 loss: 2.6686 (2.6390) grad_norm: 3.4150 (3.9649) time: 0.6362 [2021-03-28 18:30:47 swin_base_patch4_window7_224] INFO: Epoch: [295] [1080/1251] eta: 0:01:48 lr: 0.000010 loss: 2.6835 (2.6379) grad_norm: 3.4345 (3.9606) time: 0.6299 [2021-03-28 18:30:54 swin_base_patch4_window7_224] INFO: Epoch: [295] [1090/1251] eta: 0:01:42 lr: 0.000010 loss: 2.7816 (2.6395) grad_norm: 3.5679 (3.9637) time: 0.6292 [2021-03-28 18:31:00 swin_base_patch4_window7_224] INFO: Epoch: [295] [1100/1251] eta: 0:01:36 lr: 0.000010 loss: 2.7458 (2.6403) grad_norm: 3.4954 (3.9605) time: 0.6294 [2021-03-28 18:31:06 swin_base_patch4_window7_224] INFO: Epoch: [295] [1110/1251] eta: 0:01:29 lr: 0.000010 loss: 2.6700 (2.6398) grad_norm: 3.4954 (3.9661) time: 0.6299 [2021-03-28 18:31:12 swin_base_patch4_window7_224] INFO: Epoch: [295] [1120/1251] eta: 0:01:23 lr: 0.000010 loss: 2.6704 (2.6396) grad_norm: 3.8037 (3.9674) time: 0.6304 [2021-03-28 18:31:19 swin_base_patch4_window7_224] INFO: Epoch: [295] [1130/1251] eta: 0:01:16 lr: 0.000010 loss: 2.6881 (2.6403) grad_norm: 3.7013 (3.9693) time: 0.6274 [2021-03-28 18:31:25 swin_base_patch4_window7_224] INFO: Epoch: [295] [1140/1251] eta: 0:01:10 lr: 0.000010 loss: 2.6881 (2.6390) grad_norm: 3.3989 (3.9698) time: 0.6279 [2021-03-28 18:31:31 swin_base_patch4_window7_224] INFO: Epoch: [295] [1150/1251] eta: 0:01:04 lr: 0.000010 loss: 2.6097 (2.6391) grad_norm: 3.6248 (3.9704) time: 0.6373 [2021-03-28 18:31:38 swin_base_patch4_window7_224] INFO: Epoch: [295] [1160/1251] eta: 0:00:57 lr: 0.000010 loss: 2.6097 (2.6374) grad_norm: 3.6248 (3.9702) time: 0.6366 [2021-03-28 18:31:44 swin_base_patch4_window7_224] INFO: Epoch: [295] [1170/1251] eta: 0:00:51 lr: 0.000010 loss: 2.3402 (2.6354) grad_norm: 3.5770 (3.9680) time: 0.6304 [2021-03-28 18:31:50 swin_base_patch4_window7_224] INFO: Epoch: [295] [1180/1251] eta: 0:00:45 lr: 0.000010 loss: 2.5930 (2.6368) grad_norm: 3.5092 (3.9655) time: 0.6313 [2021-03-28 18:31:57 swin_base_patch4_window7_224] INFO: Epoch: [295] [1190/1251] eta: 0:00:38 lr: 0.000010 loss: 2.6756 (2.6352) grad_norm: 3.5342 (3.9672) time: 0.6317 [2021-03-28 18:32:03 swin_base_patch4_window7_224] INFO: Epoch: [295] [1200/1251] eta: 0:00:32 lr: 0.000010 loss: 2.6756 (2.6352) grad_norm: 3.6280 (3.9657) time: 0.6340 [2021-03-28 18:32:09 swin_base_patch4_window7_224] INFO: Epoch: [295] [1210/1251] eta: 0:00:26 lr: 0.000010 loss: 2.7106 (2.6351) grad_norm: 3.7152 (3.9636) time: 0.6329 [2021-03-28 18:32:16 swin_base_patch4_window7_224] INFO: Epoch: [295] [1220/1251] eta: 0:00:19 lr: 0.000010 loss: 2.5552 (2.6342) grad_norm: 3.6315 (3.9616) time: 0.6341 [2021-03-28 18:32:22 swin_base_patch4_window7_224] INFO: Epoch: [295] [1230/1251] eta: 0:00:13 lr: 0.000010 loss: 2.5552 (2.6346) grad_norm: 3.3407 (3.9596) time: 0.6312 [2021-03-28 18:32:28 swin_base_patch4_window7_224] INFO: Epoch: [295] [1240/1251] eta: 0:00:06 lr: 0.000010 loss: 2.7474 (2.6356) grad_norm: 3.5700 (3.9644) time: 0.6309 [2021-03-28 18:32:35 swin_base_patch4_window7_224] INFO: Epoch: [295] [1250/1251] eta: 0:00:00 lr: 0.000010 loss: 2.7474 (2.6345) grad_norm: 3.7169 (3.9641) time: 0.6319 [2021-03-28 18:33:48 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.7136 (0.7136) acc1: 84.3750 (84.3750) acc5: 95.3125 (95.3125) [2021-03-28 18:33:49 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.6548 (0.6978) acc1: 84.3750 (84.2330) acc5: 96.8750 (96.8750) [2021-03-28 18:33:51 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.6613 (0.7134) acc1: 82.8125 (83.2589) acc5: 96.8750 (96.8006) [2021-03-28 18:33:52 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7473 (0.7424) acc1: 81.2500 (83.0141) acc5: 95.3125 (96.5726) [2021-03-28 18:33:53 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7473 (0.7548) acc1: 82.8125 (82.6601) acc5: 96.8750 (96.5701) [2021-03-28 18:33:54 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7251 (0.7521) acc1: 81.2500 (82.4960) acc5: 96.8750 (96.4800) [2021-03-28 18:34:10 swin_base_patch4_window7_224] INFO: * Acc@1 83.460 Acc@5 96.430 loss 0.740 [2021-03-28 18:34:10 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.5% [2021-03-28 18:34:10 swin_base_patch4_window7_224] INFO: Max accuracy: 83.46% [2021-03-28 18:34:14 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 0/1251] eta: 1:30:14 lr: 0.000010 loss: 2.8534 (2.8534) grad_norm: 4.6414 (4.6414) time: 4.3280 [2021-03-28 18:34:21 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 10/1251] eta: 0:20:20 lr: 0.000010 loss: 2.8828 (2.7592) grad_norm: 3.3440 (3.4873) time: 0.9833 [2021-03-28 18:34:27 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 20/1251] eta: 0:16:39 lr: 0.000010 loss: 2.8720 (2.6692) grad_norm: 3.4963 (3.7494) time: 0.6362 [2021-03-28 18:34:33 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 30/1251] eta: 0:15:22 lr: 0.000010 loss: 2.8261 (2.6572) grad_norm: 3.4294 (3.7381) time: 0.6306 [2021-03-28 18:34:40 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 40/1251] eta: 0:14:40 lr: 0.000010 loss: 2.8185 (2.7009) grad_norm: 3.4156 (3.8331) time: 0.6376 [2021-03-28 18:34:46 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 50/1251] eta: 0:14:06 lr: 0.000010 loss: 2.8185 (2.7409) grad_norm: 3.5530 (nan) time: 0.6263 [2021-03-28 18:34:52 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 60/1251] eta: 0:13:47 lr: 0.000010 loss: 2.8819 (2.7544) grad_norm: 3.3461 (nan) time: 0.6282 [2021-03-28 18:34:58 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 70/1251] eta: 0:13:29 lr: 0.000010 loss: 2.8167 (2.7537) grad_norm: 3.3465 (nan) time: 0.6346 [2021-03-28 18:35:05 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 80/1251] eta: 0:13:14 lr: 0.000010 loss: 2.6858 (2.7295) grad_norm: 3.4839 (nan) time: 0.6307 [2021-03-28 18:35:11 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 90/1251] eta: 0:13:02 lr: 0.000010 loss: 2.5470 (2.6954) grad_norm: 3.7258 (nan) time: 0.6357 [2021-03-28 18:35:17 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 100/1251] eta: 0:12:52 lr: 0.000010 loss: 2.5470 (2.6677) grad_norm: 3.4780 (nan) time: 0.6381 [2021-03-28 18:35:24 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 110/1251] eta: 0:12:42 lr: 0.000010 loss: 2.3792 (2.6459) grad_norm: 3.6175 (nan) time: 0.6396 [2021-03-28 18:35:30 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 120/1251] eta: 0:12:32 lr: 0.000010 loss: 2.6699 (2.6545) grad_norm: 4.2728 (nan) time: 0.6355 [2021-03-28 18:35:37 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 130/1251] eta: 0:12:23 lr: 0.000010 loss: 2.6711 (2.6429) grad_norm: 4.1955 (nan) time: 0.6339 [2021-03-28 18:35:43 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 140/1251] eta: 0:12:14 lr: 0.000010 loss: 2.6630 (2.6438) grad_norm: 3.5404 (nan) time: 0.6355 [2021-03-28 18:35:49 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 150/1251] eta: 0:12:05 lr: 0.000010 loss: 2.6774 (2.6496) grad_norm: 3.5404 (nan) time: 0.6333 [2021-03-28 18:35:56 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 160/1251] eta: 0:11:57 lr: 0.000010 loss: 2.6668 (2.6419) grad_norm: 3.6276 (nan) time: 0.6356 [2021-03-28 18:36:02 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 170/1251] eta: 0:11:49 lr: 0.000010 loss: 2.7264 (2.6429) grad_norm: 3.8093 (nan) time: 0.6398 [2021-03-28 18:36:08 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 180/1251] eta: 0:11:41 lr: 0.000010 loss: 2.8014 (2.6455) grad_norm: 4.0846 (nan) time: 0.6349 [2021-03-28 18:36:15 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 190/1251] eta: 0:11:33 lr: 0.000010 loss: 2.5864 (2.6472) grad_norm: 3.7036 (nan) time: 0.6268 [2021-03-28 18:36:21 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 200/1251] eta: 0:11:25 lr: 0.000010 loss: 2.5858 (2.6395) grad_norm: 3.4779 (nan) time: 0.6282 [2021-03-28 18:36:27 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 210/1251] eta: 0:11:18 lr: 0.000010 loss: 2.5969 (2.6376) grad_norm: 3.6332 (nan) time: 0.6321 [2021-03-28 18:36:34 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 220/1251] eta: 0:11:10 lr: 0.000010 loss: 2.6997 (2.6404) grad_norm: 3.6124 (nan) time: 0.6332 [2021-03-28 18:36:40 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 230/1251] eta: 0:11:03 lr: 0.000010 loss: 2.7169 (2.6417) grad_norm: 3.6550 (nan) time: 0.6362 [2021-03-28 18:36:46 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 240/1251] eta: 0:10:56 lr: 0.000010 loss: 2.6718 (2.6453) grad_norm: 3.6550 (nan) time: 0.6386 [2021-03-28 18:36:53 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 250/1251] eta: 0:10:49 lr: 0.000010 loss: 2.7793 (2.6499) grad_norm: 3.4628 (nan) time: 0.6376 [2021-03-28 18:36:59 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 260/1251] eta: 0:10:42 lr: 0.000010 loss: 2.8033 (2.6544) grad_norm: 3.7709 (nan) time: 0.6332 [2021-03-28 18:37:05 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 270/1251] eta: 0:10:35 lr: 0.000010 loss: 2.7716 (2.6569) grad_norm: 3.8277 (nan) time: 0.6339 [2021-03-28 18:37:12 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 280/1251] eta: 0:10:28 lr: 0.000010 loss: 2.8596 (2.6596) grad_norm: 3.5549 (nan) time: 0.6333 [2021-03-28 18:37:18 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 290/1251] eta: 0:10:21 lr: 0.000010 loss: 2.8596 (2.6580) grad_norm: 3.5549 (nan) time: 0.6289 [2021-03-28 18:37:24 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 300/1251] eta: 0:10:14 lr: 0.000010 loss: 2.7478 (2.6574) grad_norm: 3.7678 (nan) time: 0.6262 [2021-03-28 18:37:30 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 310/1251] eta: 0:10:07 lr: 0.000010 loss: 2.6383 (2.6518) grad_norm: 3.6860 (nan) time: 0.6255 [2021-03-28 18:37:37 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 320/1251] eta: 0:10:00 lr: 0.000010 loss: 2.6383 (2.6530) grad_norm: 3.4650 (nan) time: 0.6242 [2021-03-28 18:37:43 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 330/1251] eta: 0:09:53 lr: 0.000010 loss: 2.7336 (2.6493) grad_norm: 3.4309 (nan) time: 0.6246 [2021-03-28 18:37:49 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 340/1251] eta: 0:09:46 lr: 0.000010 loss: 2.6254 (2.6485) grad_norm: 3.5934 (nan) time: 0.6251 [2021-03-28 18:37:55 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 350/1251] eta: 0:09:39 lr: 0.000010 loss: 2.5677 (2.6437) grad_norm: 3.3936 (nan) time: 0.6219 [2021-03-28 18:38:02 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 360/1251] eta: 0:09:32 lr: 0.000010 loss: 2.6427 (2.6434) grad_norm: 3.6726 (nan) time: 0.6330 [2021-03-28 18:38:08 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 370/1251] eta: 0:09:25 lr: 0.000010 loss: 2.6427 (2.6442) grad_norm: 3.6556 (nan) time: 0.6325 [2021-03-28 18:38:14 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 380/1251] eta: 0:09:19 lr: 0.000010 loss: 2.7228 (2.6445) grad_norm: 3.4424 (nan) time: 0.6298 [2021-03-28 18:38:21 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 390/1251] eta: 0:09:12 lr: 0.000010 loss: 2.6725 (2.6415) grad_norm: 3.4130 (nan) time: 0.6344 [2021-03-28 18:38:27 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 400/1251] eta: 0:09:06 lr: 0.000010 loss: 2.6823 (2.6442) grad_norm: 3.5932 (nan) time: 0.6317 [2021-03-28 18:38:33 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 410/1251] eta: 0:08:59 lr: 0.000010 loss: 2.7621 (2.6451) grad_norm: 3.6571 (nan) time: 0.6310 [2021-03-28 18:38:40 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 420/1251] eta: 0:08:52 lr: 0.000010 loss: 2.5942 (2.6413) grad_norm: 3.7490 (nan) time: 0.6293 [2021-03-28 18:38:46 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 430/1251] eta: 0:08:46 lr: 0.000010 loss: 2.8556 (2.6455) grad_norm: 3.5791 (nan) time: 0.6297 [2021-03-28 18:38:52 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 440/1251] eta: 0:08:39 lr: 0.000010 loss: 2.8598 (2.6469) grad_norm: 3.2970 (nan) time: 0.6248 [2021-03-28 18:38:58 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 450/1251] eta: 0:08:32 lr: 0.000010 loss: 2.6593 (2.6475) grad_norm: 3.2970 (nan) time: 0.6236 [2021-03-28 18:39:05 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 460/1251] eta: 0:08:26 lr: 0.000010 loss: 2.7270 (2.6464) grad_norm: 3.8882 (nan) time: 0.6312 [2021-03-28 18:39:11 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 470/1251] eta: 0:08:19 lr: 0.000010 loss: 2.7270 (2.6465) grad_norm: 4.0595 (nan) time: 0.6311 [2021-03-28 18:39:17 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 480/1251] eta: 0:08:13 lr: 0.000010 loss: 2.6257 (2.6444) grad_norm: 3.8298 (nan) time: 0.6300 [2021-03-28 18:39:24 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 490/1251] eta: 0:08:06 lr: 0.000010 loss: 2.6993 (2.6485) grad_norm: 3.6717 (nan) time: 0.6345 [2021-03-28 18:39:30 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 500/1251] eta: 0:08:00 lr: 0.000010 loss: 2.6993 (2.6472) grad_norm: 3.9044 (nan) time: 0.6316 [2021-03-28 18:39:36 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 510/1251] eta: 0:07:53 lr: 0.000010 loss: 2.5285 (2.6460) grad_norm: 3.9044 (nan) time: 0.6249 [2021-03-28 18:39:43 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 520/1251] eta: 0:07:46 lr: 0.000010 loss: 2.7457 (2.6495) grad_norm: 3.5439 (nan) time: 0.6260 [2021-03-28 18:39:49 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 530/1251] eta: 0:07:40 lr: 0.000010 loss: 2.7321 (2.6465) grad_norm: 3.5439 (nan) time: 0.6296 [2021-03-28 18:39:55 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 540/1251] eta: 0:07:34 lr: 0.000010 loss: 2.5472 (2.6459) grad_norm: 3.4241 (nan) time: 0.6355 [2021-03-28 18:40:02 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 550/1251] eta: 0:07:27 lr: 0.000010 loss: 2.4414 (2.6398) grad_norm: 3.3278 (nan) time: 0.6442 [2021-03-28 18:40:08 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 560/1251] eta: 0:07:21 lr: 0.000010 loss: 2.4145 (2.6379) grad_norm: 3.2451 (nan) time: 0.6408 [2021-03-28 18:40:14 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 570/1251] eta: 0:07:14 lr: 0.000010 loss: 2.5976 (2.6375) grad_norm: 3.6293 (nan) time: 0.6335 [2021-03-28 18:40:21 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 580/1251] eta: 0:07:08 lr: 0.000010 loss: 2.6013 (2.6370) grad_norm: 3.5488 (nan) time: 0.6313 [2021-03-28 18:40:27 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 590/1251] eta: 0:07:01 lr: 0.000010 loss: 2.5616 (2.6363) grad_norm: 3.8055 (nan) time: 0.6321 [2021-03-28 18:40:34 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 600/1251] eta: 0:06:55 lr: 0.000010 loss: 2.5802 (2.6371) grad_norm: 3.8816 (nan) time: 0.6407 [2021-03-28 18:40:40 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 610/1251] eta: 0:06:49 lr: 0.000010 loss: 2.8236 (2.6400) grad_norm: 3.6138 (nan) time: 0.6414 [2021-03-28 18:40:46 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 620/1251] eta: 0:06:42 lr: 0.000010 loss: 2.8493 (2.6412) grad_norm: 3.9935 (nan) time: 0.6306 [2021-03-28 18:40:52 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 630/1251] eta: 0:06:36 lr: 0.000010 loss: 2.6670 (2.6405) grad_norm: 3.6031 (nan) time: 0.6282 [2021-03-28 18:40:59 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 640/1251] eta: 0:06:29 lr: 0.000010 loss: 2.6670 (2.6425) grad_norm: 3.4151 (nan) time: 0.6369 [2021-03-28 18:41:05 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 650/1251] eta: 0:06:23 lr: 0.000010 loss: 2.9229 (2.6456) grad_norm: 3.8839 (nan) time: 0.6331 [2021-03-28 18:41:11 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 660/1251] eta: 0:06:16 lr: 0.000010 loss: 2.8457 (2.6422) grad_norm: 3.6086 (nan) time: 0.6259 [2021-03-28 18:41:18 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 670/1251] eta: 0:06:10 lr: 0.000010 loss: 2.6214 (2.6402) grad_norm: 3.5269 (nan) time: 0.6307 [2021-03-28 18:41:24 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 680/1251] eta: 0:06:04 lr: 0.000010 loss: 2.6500 (2.6410) grad_norm: 3.2827 (nan) time: 0.6303 [2021-03-28 18:41:30 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 690/1251] eta: 0:05:57 lr: 0.000010 loss: 2.6356 (2.6382) grad_norm: 3.3334 (nan) time: 0.6280 [2021-03-28 18:41:37 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 700/1251] eta: 0:05:51 lr: 0.000010 loss: 2.3114 (2.6321) grad_norm: 3.6483 (nan) time: 0.6265 [2021-03-28 18:41:43 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 710/1251] eta: 0:05:44 lr: 0.000010 loss: 2.2912 (2.6316) grad_norm: 3.2946 (nan) time: 0.6301 [2021-03-28 18:41:49 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 720/1251] eta: 0:05:38 lr: 0.000010 loss: 2.4859 (2.6293) grad_norm: 3.4971 (nan) time: 0.6346 [2021-03-28 18:41:56 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 730/1251] eta: 0:05:32 lr: 0.000010 loss: 2.6280 (2.6297) grad_norm: 3.6698 (nan) time: 0.6407 [2021-03-28 18:42:02 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 740/1251] eta: 0:05:25 lr: 0.000010 loss: 2.7336 (2.6298) grad_norm: 3.6170 (nan) time: 0.6413 [2021-03-28 18:42:08 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 750/1251] eta: 0:05:19 lr: 0.000010 loss: 2.5618 (2.6301) grad_norm: 3.4632 (nan) time: 0.6359 [2021-03-28 18:42:15 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 760/1251] eta: 0:05:12 lr: 0.000010 loss: 2.5894 (2.6298) grad_norm: 3.4419 (nan) time: 0.6398 [2021-03-28 18:42:21 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 770/1251] eta: 0:05:06 lr: 0.000010 loss: 2.6552 (2.6325) grad_norm: 3.5264 (nan) time: 0.6345 [2021-03-28 18:42:27 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 780/1251] eta: 0:05:00 lr: 0.000010 loss: 2.9167 (2.6344) grad_norm: 3.4028 (nan) time: 0.6297 [2021-03-28 18:42:34 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 790/1251] eta: 0:04:53 lr: 0.000010 loss: 2.7474 (2.6342) grad_norm: 3.4028 (nan) time: 0.6361 [2021-03-28 18:42:40 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 800/1251] eta: 0:04:47 lr: 0.000010 loss: 2.7194 (2.6347) grad_norm: 3.5756 (nan) time: 0.6366 [2021-03-28 18:42:47 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 810/1251] eta: 0:04:40 lr: 0.000010 loss: 2.7515 (2.6373) grad_norm: 3.4897 (nan) time: 0.6345 [2021-03-28 18:42:53 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 820/1251] eta: 0:04:34 lr: 0.000010 loss: 2.8124 (2.6370) grad_norm: 3.4270 (nan) time: 0.6357 [2021-03-28 18:42:59 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 830/1251] eta: 0:04:28 lr: 0.000010 loss: 2.7431 (2.6365) grad_norm: 3.4400 (nan) time: 0.6335 [2021-03-28 18:43:06 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 840/1251] eta: 0:04:21 lr: 0.000010 loss: 2.3758 (2.6321) grad_norm: 3.5130 (nan) time: 0.6314 [2021-03-28 18:43:12 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 850/1251] eta: 0:04:15 lr: 0.000010 loss: 2.3236 (2.6295) grad_norm: 3.6924 (nan) time: 0.6311 [2021-03-28 18:43:18 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 860/1251] eta: 0:04:08 lr: 0.000010 loss: 2.3759 (2.6273) grad_norm: 3.3747 (nan) time: 0.6282 [2021-03-28 18:43:24 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 870/1251] eta: 0:04:02 lr: 0.000010 loss: 2.6108 (2.6276) grad_norm: 3.5006 (nan) time: 0.6280 [2021-03-28 18:43:31 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 880/1251] eta: 0:03:56 lr: 0.000010 loss: 2.6504 (2.6276) grad_norm: 3.6964 (nan) time: 0.6336 [2021-03-28 18:43:37 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 890/1251] eta: 0:03:49 lr: 0.000010 loss: 2.6202 (2.6282) grad_norm: 3.8735 (nan) time: 0.6331 [2021-03-28 18:43:43 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 900/1251] eta: 0:03:43 lr: 0.000010 loss: 2.5394 (2.6274) grad_norm: 3.8704 (nan) time: 0.6342 [2021-03-28 18:43:50 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 910/1251] eta: 0:03:37 lr: 0.000010 loss: 2.8969 (2.6305) grad_norm: 3.8704 (nan) time: 0.6379 [2021-03-28 18:43:56 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 920/1251] eta: 0:03:30 lr: 0.000010 loss: 2.9686 (2.6320) grad_norm: 3.7443 (nan) time: 0.6341 [2021-03-28 18:44:03 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 930/1251] eta: 0:03:24 lr: 0.000010 loss: 2.8005 (2.6314) grad_norm: 3.9784 (nan) time: 0.6388 [2021-03-28 18:44:09 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 940/1251] eta: 0:03:18 lr: 0.000010 loss: 2.7430 (2.6320) grad_norm: 3.3365 (nan) time: 0.6399 [2021-03-28 18:44:15 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 950/1251] eta: 0:03:11 lr: 0.000010 loss: 2.8124 (2.6327) grad_norm: 3.3339 (nan) time: 0.6415 [2021-03-28 18:44:22 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 960/1251] eta: 0:03:05 lr: 0.000010 loss: 2.7964 (2.6332) grad_norm: 3.3575 (nan) time: 0.6460 [2021-03-28 18:44:28 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 970/1251] eta: 0:02:58 lr: 0.000010 loss: 2.7484 (2.6333) grad_norm: 3.4257 (nan) time: 0.6418 [2021-03-28 18:44:35 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 980/1251] eta: 0:02:52 lr: 0.000010 loss: 2.5627 (2.6310) grad_norm: 3.5040 (nan) time: 0.6378 [2021-03-28 18:44:41 swin_base_patch4_window7_224] INFO: Epoch: [296] [ 990/1251] eta: 0:02:46 lr: 0.000010 loss: 2.5280 (2.6308) grad_norm: 3.8139 (nan) time: 0.6327 [2021-03-28 18:44:47 swin_base_patch4_window7_224] INFO: Epoch: [296] [1000/1251] eta: 0:02:39 lr: 0.000010 loss: 2.7768 (2.6333) grad_norm: 3.5885 (nan) time: 0.6292 [2021-03-28 18:44:53 swin_base_patch4_window7_224] INFO: Epoch: [296] [1010/1251] eta: 0:02:33 lr: 0.000010 loss: 2.7601 (2.6326) grad_norm: 3.3548 (nan) time: 0.6268 [2021-03-28 18:45:00 swin_base_patch4_window7_224] INFO: Epoch: [296] [1020/1251] eta: 0:02:27 lr: 0.000010 loss: 2.6452 (2.6330) grad_norm: 3.6284 (nan) time: 0.6262 [2021-03-28 18:45:06 swin_base_patch4_window7_224] INFO: Epoch: [296] [1030/1251] eta: 0:02:20 lr: 0.000010 loss: 2.5964 (2.6315) grad_norm: 3.5630 (nan) time: 0.6330 [2021-03-28 18:45:12 swin_base_patch4_window7_224] INFO: Epoch: [296] [1040/1251] eta: 0:02:14 lr: 0.000010 loss: 2.5342 (2.6314) grad_norm: 3.4922 (nan) time: 0.6341 [2021-03-28 18:45:19 swin_base_patch4_window7_224] INFO: Epoch: [296] [1050/1251] eta: 0:02:07 lr: 0.000010 loss: 2.6414 (2.6314) grad_norm: 3.5617 (nan) time: 0.6276 [2021-03-28 18:45:25 swin_base_patch4_window7_224] INFO: Epoch: [296] [1060/1251] eta: 0:02:01 lr: 0.000010 loss: 2.6392 (2.6319) grad_norm: 3.6599 (nan) time: 0.6241 [2021-03-28 18:45:31 swin_base_patch4_window7_224] INFO: Epoch: [296] [1070/1251] eta: 0:01:55 lr: 0.000010 loss: 2.6392 (2.6324) grad_norm: 3.6057 (nan) time: 0.6293 [2021-03-28 18:45:38 swin_base_patch4_window7_224] INFO: Epoch: [296] [1080/1251] eta: 0:01:48 lr: 0.000010 loss: 2.7281 (2.6333) grad_norm: 3.4902 (nan) time: 0.6307 [2021-03-28 18:45:44 swin_base_patch4_window7_224] INFO: Epoch: [296] [1090/1251] eta: 0:01:42 lr: 0.000010 loss: 2.7428 (2.6351) grad_norm: 3.4822 (nan) time: 0.6295 [2021-03-28 18:45:50 swin_base_patch4_window7_224] INFO: Epoch: [296] [1100/1251] eta: 0:01:36 lr: 0.000010 loss: 2.6499 (2.6348) grad_norm: 3.6569 (nan) time: 0.6334 [2021-03-28 18:45:57 swin_base_patch4_window7_224] INFO: Epoch: [296] [1110/1251] eta: 0:01:29 lr: 0.000010 loss: 2.3906 (2.6312) grad_norm: 3.4234 (nan) time: 0.6359 [2021-03-28 18:46:03 swin_base_patch4_window7_224] INFO: Epoch: [296] [1120/1251] eta: 0:01:23 lr: 0.000010 loss: 2.5526 (2.6311) grad_norm: 3.3930 (nan) time: 0.6338 [2021-03-28 18:46:09 swin_base_patch4_window7_224] INFO: Epoch: [296] [1130/1251] eta: 0:01:16 lr: 0.000010 loss: 2.6276 (2.6304) grad_norm: 3.3773 (nan) time: 0.6266 [2021-03-28 18:46:15 swin_base_patch4_window7_224] INFO: Epoch: [296] [1140/1251] eta: 0:01:10 lr: 0.000010 loss: 2.6239 (2.6301) grad_norm: 3.4306 (nan) time: 0.6292 [2021-03-28 18:46:22 swin_base_patch4_window7_224] INFO: Epoch: [296] [1150/1251] eta: 0:01:04 lr: 0.000010 loss: 2.6271 (2.6285) grad_norm: 3.6135 (nan) time: 0.6338 [2021-03-28 18:46:28 swin_base_patch4_window7_224] INFO: Epoch: [296] [1160/1251] eta: 0:00:57 lr: 0.000010 loss: 2.5876 (2.6281) grad_norm: 3.4870 (nan) time: 0.6358 [2021-03-28 18:46:35 swin_base_patch4_window7_224] INFO: Epoch: [296] [1170/1251] eta: 0:00:51 lr: 0.000010 loss: 2.6347 (2.6299) grad_norm: 3.4528 (nan) time: 0.6397 [2021-03-28 18:46:41 swin_base_patch4_window7_224] INFO: Epoch: [296] [1180/1251] eta: 0:00:45 lr: 0.000010 loss: 2.8558 (2.6311) grad_norm: 3.4138 (nan) time: 0.6418 [2021-03-28 18:46:47 swin_base_patch4_window7_224] INFO: Epoch: [296] [1190/1251] eta: 0:00:38 lr: 0.000010 loss: 2.7623 (2.6310) grad_norm: 3.5634 (nan) time: 0.6371 [2021-03-28 18:46:54 swin_base_patch4_window7_224] INFO: Epoch: [296] [1200/1251] eta: 0:00:32 lr: 0.000010 loss: 2.6633 (2.6303) grad_norm: 3.5906 (nan) time: 0.6343 [2021-03-28 18:47:00 swin_base_patch4_window7_224] INFO: Epoch: [296] [1210/1251] eta: 0:00:26 lr: 0.000010 loss: 2.6220 (2.6300) grad_norm: 3.5571 (nan) time: 0.6293 [2021-03-28 18:47:06 swin_base_patch4_window7_224] INFO: Epoch: [296] [1220/1251] eta: 0:00:19 lr: 0.000010 loss: 2.6119 (2.6292) grad_norm: 3.7046 (nan) time: 0.6294 [2021-03-28 18:47:13 swin_base_patch4_window7_224] INFO: Epoch: [296] [1230/1251] eta: 0:00:13 lr: 0.000010 loss: 2.6948 (2.6298) grad_norm: 3.4875 (nan) time: 0.6334 [2021-03-28 18:47:19 swin_base_patch4_window7_224] INFO: Epoch: [296] [1240/1251] eta: 0:00:06 lr: 0.000010 loss: 2.7707 (2.6311) grad_norm: 3.4505 (nan) time: 0.6295 [2021-03-28 18:47:25 swin_base_patch4_window7_224] INFO: Epoch: [296] [1250/1251] eta: 0:00:00 lr: 0.000010 loss: 2.7848 (2.6314) grad_norm: 3.7282 (nan) time: 0.6197 [2021-03-28 18:47:37 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:51 loss: 0.9539 (0.9539) acc1: 81.2500 (81.2500) acc5: 93.7500 (93.7500) [2021-03-28 18:47:39 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.6944 (0.7610) acc1: 82.8125 (82.6705) acc5: 96.8750 (96.7330) [2021-03-28 18:47:42 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.6944 (0.7473) acc1: 82.8125 (82.6637) acc5: 96.8750 (96.8750) [2021-03-28 18:47:45 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7051 (0.7390) acc1: 82.8125 (82.7117) acc5: 96.8750 (96.8246) [2021-03-28 18:47:47 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7653 (0.7696) acc1: 79.6875 (82.0503) acc5: 96.8750 (96.5701) [2021-03-28 18:47:48 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7381 (0.7531) acc1: 79.6875 (82.4640) acc5: 96.8750 (96.6080) [2021-03-28 18:48:05 swin_base_patch4_window7_224] INFO: * Acc@1 83.406 Acc@5 96.442 loss 0.739 [2021-03-28 18:48:05 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 18:48:05 swin_base_patch4_window7_224] INFO: Max accuracy: 83.46% [2021-03-28 18:48:10 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 0/1251] eta: 1:35:35 lr: 0.000010 loss: 2.9622 (2.9622) grad_norm: 3.7695 (3.7695) time: 4.5849 [2021-03-28 18:48:16 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 10/1251] eta: 0:20:32 lr: 0.000010 loss: 2.7180 (2.6003) grad_norm: 3.7048 (3.7403) time: 0.9931 [2021-03-28 18:48:23 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 20/1251] eta: 0:16:53 lr: 0.000010 loss: 2.7585 (2.6611) grad_norm: 3.6404 (3.7036) time: 0.6352 [2021-03-28 18:48:29 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 30/1251] eta: 0:15:25 lr: 0.000010 loss: 2.8358 (2.7548) grad_norm: 3.6404 (3.7604) time: 0.6292 [2021-03-28 18:48:35 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 40/1251] eta: 0:14:38 lr: 0.000010 loss: 2.8630 (2.7361) grad_norm: 3.6595 (3.9271) time: 0.6227 [2021-03-28 18:48:41 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 50/1251] eta: 0:14:08 lr: 0.000010 loss: 2.7961 (2.7225) grad_norm: 3.6595 (3.9759) time: 0.6269 [2021-03-28 18:48:48 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 60/1251] eta: 0:13:45 lr: 0.000010 loss: 2.8120 (2.7182) grad_norm: 3.6756 (4.1240) time: 0.6279 [2021-03-28 18:48:54 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 70/1251] eta: 0:13:27 lr: 0.000010 loss: 2.8191 (2.7378) grad_norm: 3.7581 (4.1634) time: 0.6257 [2021-03-28 18:49:00 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 80/1251] eta: 0:13:12 lr: 0.000010 loss: 2.8237 (2.7422) grad_norm: 3.7312 (4.0963) time: 0.6254 [2021-03-28 18:49:06 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 90/1251] eta: 0:12:59 lr: 0.000010 loss: 2.5733 (2.7125) grad_norm: 3.6421 (4.0618) time: 0.6276 [2021-03-28 18:49:13 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 100/1251] eta: 0:12:48 lr: 0.000010 loss: 2.5605 (2.6975) grad_norm: 3.6976 (4.0848) time: 0.6293 [2021-03-28 18:49:19 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 110/1251] eta: 0:12:39 lr: 0.000010 loss: 2.5764 (2.6942) grad_norm: 3.8966 (4.0878) time: 0.6369 [2021-03-28 18:49:25 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 120/1251] eta: 0:12:29 lr: 0.000010 loss: 2.7689 (2.6881) grad_norm: 3.8285 (4.1155) time: 0.6373 [2021-03-28 18:49:32 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 130/1251] eta: 0:12:20 lr: 0.000010 loss: 2.7635 (2.6822) grad_norm: 3.6786 (4.0998) time: 0.6332 [2021-03-28 18:49:38 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 140/1251] eta: 0:12:12 lr: 0.000010 loss: 2.7381 (2.6770) grad_norm: 3.6707 (4.0838) time: 0.6389 [2021-03-28 18:49:44 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 150/1251] eta: 0:12:02 lr: 0.000010 loss: 2.7381 (2.6776) grad_norm: 3.5771 (4.0515) time: 0.6303 [2021-03-28 18:49:51 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 160/1251] eta: 0:11:55 lr: 0.000010 loss: 2.7471 (2.6797) grad_norm: 3.6930 (4.0491) time: 0.6297 [2021-03-28 18:49:57 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 170/1251] eta: 0:11:46 lr: 0.000010 loss: 2.7547 (2.6668) grad_norm: 3.7319 (4.0504) time: 0.6357 [2021-03-28 18:50:03 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 180/1251] eta: 0:11:38 lr: 0.000010 loss: 2.3950 (2.6548) grad_norm: 3.6931 (4.0821) time: 0.6284 [2021-03-28 18:50:10 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 190/1251] eta: 0:11:30 lr: 0.000010 loss: 2.4224 (2.6438) grad_norm: 3.6931 (4.0873) time: 0.6255 [2021-03-28 18:50:16 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 200/1251] eta: 0:11:23 lr: 0.000010 loss: 2.6923 (2.6515) grad_norm: 3.5264 (4.0794) time: 0.6283 [2021-03-28 18:50:22 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 210/1251] eta: 0:11:15 lr: 0.000010 loss: 2.7416 (2.6512) grad_norm: 3.5667 (4.0630) time: 0.6290 [2021-03-28 18:50:29 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 220/1251] eta: 0:11:08 lr: 0.000010 loss: 2.4895 (2.6461) grad_norm: 3.7374 (4.0862) time: 0.6312 [2021-03-28 18:50:35 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 230/1251] eta: 0:11:01 lr: 0.000010 loss: 2.5048 (2.6450) grad_norm: 3.7374 (4.0752) time: 0.6324 [2021-03-28 18:50:41 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 240/1251] eta: 0:10:53 lr: 0.000010 loss: 2.7045 (2.6403) grad_norm: 3.7004 (4.0710) time: 0.6301 [2021-03-28 18:50:47 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 250/1251] eta: 0:10:46 lr: 0.000010 loss: 2.4845 (2.6273) grad_norm: 3.5924 (4.0446) time: 0.6270 [2021-03-28 18:50:54 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 260/1251] eta: 0:10:39 lr: 0.000010 loss: 2.4416 (2.6248) grad_norm: 3.5924 (4.0494) time: 0.6266 [2021-03-28 18:51:00 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 270/1251] eta: 0:10:32 lr: 0.000010 loss: 2.6150 (2.6267) grad_norm: 4.0800 (4.0802) time: 0.6287 [2021-03-28 18:51:06 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 280/1251] eta: 0:10:25 lr: 0.000010 loss: 2.7083 (2.6297) grad_norm: 3.5754 (4.0589) time: 0.6260 [2021-03-28 18:51:12 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 290/1251] eta: 0:10:18 lr: 0.000010 loss: 2.7083 (2.6238) grad_norm: 3.4378 (4.0419) time: 0.6240 [2021-03-28 18:51:19 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 300/1251] eta: 0:10:11 lr: 0.000010 loss: 2.6493 (2.6278) grad_norm: 3.6063 (4.0321) time: 0.6340 [2021-03-28 18:51:25 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 310/1251] eta: 0:10:05 lr: 0.000010 loss: 2.7768 (2.6283) grad_norm: 3.6941 (4.0255) time: 0.6413 [2021-03-28 18:51:32 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 320/1251] eta: 0:09:58 lr: 0.000010 loss: 2.6562 (2.6251) grad_norm: 3.6941 (4.0225) time: 0.6366 [2021-03-28 18:51:38 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 330/1251] eta: 0:09:51 lr: 0.000010 loss: 2.5272 (2.6227) grad_norm: 3.5656 (4.0110) time: 0.6350 [2021-03-28 18:51:44 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 340/1251] eta: 0:09:44 lr: 0.000010 loss: 2.6981 (2.6303) grad_norm: 3.7031 (4.0196) time: 0.6313 [2021-03-28 18:51:51 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 350/1251] eta: 0:09:38 lr: 0.000010 loss: 2.7900 (2.6314) grad_norm: 3.9446 (4.0170) time: 0.6312 [2021-03-28 18:51:57 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 360/1251] eta: 0:09:31 lr: 0.000010 loss: 2.6931 (2.6287) grad_norm: 3.5587 (4.0106) time: 0.6371 [2021-03-28 18:52:03 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 370/1251] eta: 0:09:25 lr: 0.000010 loss: 2.5431 (2.6239) grad_norm: 3.3666 (3.9942) time: 0.6313 [2021-03-28 18:52:10 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 380/1251] eta: 0:09:18 lr: 0.000010 loss: 2.6043 (2.6258) grad_norm: 3.4585 (3.9956) time: 0.6278 [2021-03-28 18:52:16 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 390/1251] eta: 0:09:11 lr: 0.000010 loss: 2.6218 (2.6262) grad_norm: 3.6987 (3.9979) time: 0.6262 [2021-03-28 18:52:22 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 400/1251] eta: 0:09:04 lr: 0.000010 loss: 2.5431 (2.6263) grad_norm: 3.6730 (3.9948) time: 0.6272 [2021-03-28 18:52:28 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 410/1251] eta: 0:08:58 lr: 0.000010 loss: 2.5642 (2.6248) grad_norm: 3.3274 (3.9791) time: 0.6287 [2021-03-28 18:52:35 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 420/1251] eta: 0:08:51 lr: 0.000010 loss: 2.7158 (2.6257) grad_norm: 3.5122 (3.9869) time: 0.6313 [2021-03-28 18:52:41 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 430/1251] eta: 0:08:45 lr: 0.000010 loss: 2.6284 (2.6251) grad_norm: 3.6452 (3.9911) time: 0.6368 [2021-03-28 18:52:48 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 440/1251] eta: 0:08:38 lr: 0.000010 loss: 2.6284 (2.6273) grad_norm: 3.6928 (3.9996) time: 0.6369 [2021-03-28 18:52:54 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 450/1251] eta: 0:08:32 lr: 0.000010 loss: 2.8072 (2.6306) grad_norm: 3.5603 (3.9976) time: 0.6347 [2021-03-28 18:53:00 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 460/1251] eta: 0:08:25 lr: 0.000010 loss: 2.7621 (2.6307) grad_norm: 3.5603 (3.9896) time: 0.6274 [2021-03-28 18:53:06 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 470/1251] eta: 0:08:18 lr: 0.000010 loss: 2.7621 (2.6340) grad_norm: 3.6634 (3.9883) time: 0.6231 [2021-03-28 18:53:13 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 480/1251] eta: 0:08:12 lr: 0.000010 loss: 2.6389 (2.6285) grad_norm: 3.5562 (3.9802) time: 0.6266 [2021-03-28 18:53:19 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 490/1251] eta: 0:08:06 lr: 0.000010 loss: 2.4466 (2.6271) grad_norm: 3.6615 (3.9896) time: 0.6323 [2021-03-28 18:53:25 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 500/1251] eta: 0:07:59 lr: 0.000010 loss: 2.6234 (2.6244) grad_norm: 4.0292 (3.9975) time: 0.6341 [2021-03-28 18:53:32 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 510/1251] eta: 0:07:53 lr: 0.000010 loss: 2.6234 (2.6241) grad_norm: 3.8421 (3.9914) time: 0.6382 [2021-03-28 18:53:38 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 520/1251] eta: 0:07:46 lr: 0.000010 loss: 2.6359 (2.6262) grad_norm: 3.7934 (3.9928) time: 0.6374 [2021-03-28 18:53:44 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 530/1251] eta: 0:07:40 lr: 0.000010 loss: 2.7526 (2.6274) grad_norm: 4.1047 (4.0050) time: 0.6332 [2021-03-28 18:53:51 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 540/1251] eta: 0:07:33 lr: 0.000010 loss: 2.7519 (2.6234) grad_norm: 4.0200 (4.0047) time: 0.6304 [2021-03-28 18:53:57 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 550/1251] eta: 0:07:27 lr: 0.000010 loss: 2.7561 (2.6288) grad_norm: 3.7356 (3.9992) time: 0.6427 [2021-03-28 18:54:04 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 560/1251] eta: 0:07:21 lr: 0.000010 loss: 2.9091 (2.6307) grad_norm: 3.5688 (4.0160) time: 0.6542 [2021-03-28 18:54:10 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 570/1251] eta: 0:07:14 lr: 0.000010 loss: 2.8006 (2.6310) grad_norm: 3.6649 (4.0142) time: 0.6378 [2021-03-28 18:54:16 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 580/1251] eta: 0:07:08 lr: 0.000010 loss: 2.7282 (2.6272) grad_norm: 3.7330 (4.0191) time: 0.6342 [2021-03-28 18:54:23 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 590/1251] eta: 0:07:02 lr: 0.000010 loss: 2.5612 (2.6261) grad_norm: 3.7330 (4.0173) time: 0.6402 [2021-03-28 18:54:29 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 600/1251] eta: 0:06:55 lr: 0.000010 loss: 2.6531 (2.6281) grad_norm: 3.5119 (4.0193) time: 0.6364 [2021-03-28 18:54:35 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 610/1251] eta: 0:06:49 lr: 0.000010 loss: 2.8315 (2.6276) grad_norm: 3.6400 (4.0139) time: 0.6349 [2021-03-28 18:54:42 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 620/1251] eta: 0:06:42 lr: 0.000010 loss: 2.6927 (2.6300) grad_norm: 3.7252 (4.0170) time: 0.6283 [2021-03-28 18:54:48 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 630/1251] eta: 0:06:36 lr: 0.000010 loss: 2.7333 (2.6328) grad_norm: 3.7124 (4.0112) time: 0.6266 [2021-03-28 18:54:54 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 640/1251] eta: 0:06:29 lr: 0.000010 loss: 2.7277 (2.6302) grad_norm: 3.7124 (4.0157) time: 0.6324 [2021-03-28 18:55:01 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 650/1251] eta: 0:06:23 lr: 0.000010 loss: 2.4006 (2.6267) grad_norm: 3.7386 (4.0119) time: 0.6347 [2021-03-28 18:55:07 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 660/1251] eta: 0:06:17 lr: 0.000010 loss: 2.5692 (2.6271) grad_norm: 3.4917 (4.0087) time: 0.6352 [2021-03-28 18:55:13 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 670/1251] eta: 0:06:10 lr: 0.000010 loss: 2.7050 (2.6281) grad_norm: 3.9421 (4.0090) time: 0.6360 [2021-03-28 18:55:20 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 680/1251] eta: 0:06:04 lr: 0.000010 loss: 2.7025 (2.6275) grad_norm: 3.8157 (4.0038) time: 0.6393 [2021-03-28 18:55:26 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 690/1251] eta: 0:05:57 lr: 0.000010 loss: 2.7284 (2.6281) grad_norm: 3.6506 (3.9996) time: 0.6414 [2021-03-28 18:55:33 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 700/1251] eta: 0:05:51 lr: 0.000010 loss: 2.6970 (2.6270) grad_norm: 3.5995 (4.0044) time: 0.6351 [2021-03-28 18:55:39 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 710/1251] eta: 0:05:45 lr: 0.000010 loss: 2.6820 (2.6270) grad_norm: 3.9057 (4.0042) time: 0.6336 [2021-03-28 18:55:45 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 720/1251] eta: 0:05:38 lr: 0.000010 loss: 2.6930 (2.6260) grad_norm: 3.7966 (4.0092) time: 0.6385 [2021-03-28 18:55:52 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 730/1251] eta: 0:05:32 lr: 0.000010 loss: 2.5807 (2.6245) grad_norm: 3.7457 (4.0061) time: 0.6388 [2021-03-28 18:55:58 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 740/1251] eta: 0:05:26 lr: 0.000010 loss: 2.7603 (2.6280) grad_norm: 3.6772 (4.0030) time: 0.6427 [2021-03-28 18:56:05 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 750/1251] eta: 0:05:19 lr: 0.000010 loss: 2.7417 (2.6287) grad_norm: 3.8541 (4.0074) time: 0.6444 [2021-03-28 18:56:11 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 760/1251] eta: 0:05:13 lr: 0.000010 loss: 2.7475 (2.6316) grad_norm: 3.6548 (4.0057) time: 0.6382 [2021-03-28 18:56:17 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 770/1251] eta: 0:05:06 lr: 0.000010 loss: 2.7480 (2.6294) grad_norm: 3.4370 (3.9995) time: 0.6352 [2021-03-28 18:56:24 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 780/1251] eta: 0:05:00 lr: 0.000010 loss: 2.6055 (2.6310) grad_norm: 3.3145 (4.0042) time: 0.6354 [2021-03-28 18:56:30 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 790/1251] eta: 0:04:54 lr: 0.000010 loss: 2.7368 (2.6314) grad_norm: 3.4924 (4.0024) time: 0.6371 [2021-03-28 18:56:36 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 800/1251] eta: 0:04:47 lr: 0.000010 loss: 2.7368 (2.6305) grad_norm: 3.4924 (3.9961) time: 0.6372 [2021-03-28 18:56:43 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 810/1251] eta: 0:04:41 lr: 0.000010 loss: 2.4308 (2.6283) grad_norm: 3.4917 (3.9909) time: 0.6353 [2021-03-28 18:56:49 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 820/1251] eta: 0:04:34 lr: 0.000010 loss: 2.6268 (2.6300) grad_norm: 3.6983 (3.9875) time: 0.6395 [2021-03-28 18:56:56 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 830/1251] eta: 0:04:28 lr: 0.000010 loss: 2.7112 (2.6283) grad_norm: 3.5982 (3.9931) time: 0.6438 [2021-03-28 18:57:02 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 840/1251] eta: 0:04:22 lr: 0.000010 loss: 2.4005 (2.6255) grad_norm: 3.7235 (3.9984) time: 0.6357 [2021-03-28 18:57:08 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 850/1251] eta: 0:04:15 lr: 0.000010 loss: 2.1422 (2.6203) grad_norm: 3.7235 (3.9941) time: 0.6281 [2021-03-28 18:57:15 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 860/1251] eta: 0:04:09 lr: 0.000010 loss: 2.6444 (2.6214) grad_norm: 3.4164 (4.0059) time: 0.6366 [2021-03-28 18:57:21 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 870/1251] eta: 0:04:03 lr: 0.000010 loss: 2.7589 (2.6204) grad_norm: 3.5757 (4.0115) time: 0.6405 [2021-03-28 18:57:27 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 880/1251] eta: 0:03:56 lr: 0.000010 loss: 2.4750 (2.6183) grad_norm: 3.6287 (4.0085) time: 0.6332 [2021-03-28 18:57:34 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 890/1251] eta: 0:03:50 lr: 0.000010 loss: 2.4750 (2.6182) grad_norm: 3.5852 (4.0072) time: 0.6358 [2021-03-28 18:57:40 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 900/1251] eta: 0:03:43 lr: 0.000010 loss: 2.5641 (2.6167) grad_norm: 3.5852 (4.0094) time: 0.6392 [2021-03-28 18:57:46 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 910/1251] eta: 0:03:37 lr: 0.000010 loss: 2.7146 (2.6181) grad_norm: 3.6026 (4.0075) time: 0.6372 [2021-03-28 18:57:53 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 920/1251] eta: 0:03:31 lr: 0.000010 loss: 2.8196 (2.6196) grad_norm: 3.5836 (inf) time: 0.6306 [2021-03-28 18:57:59 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 930/1251] eta: 0:03:24 lr: 0.000010 loss: 2.7588 (2.6203) grad_norm: 3.7100 (inf) time: 0.6282 [2021-03-28 18:58:05 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 940/1251] eta: 0:03:18 lr: 0.000010 loss: 2.7740 (2.6221) grad_norm: 3.7622 (inf) time: 0.6292 [2021-03-28 18:58:12 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 950/1251] eta: 0:03:11 lr: 0.000010 loss: 2.7076 (2.6202) grad_norm: 3.7060 (inf) time: 0.6324 [2021-03-28 18:58:18 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 960/1251] eta: 0:03:05 lr: 0.000010 loss: 2.4432 (2.6191) grad_norm: 3.5020 (inf) time: 0.6360 [2021-03-28 18:58:24 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 970/1251] eta: 0:02:59 lr: 0.000010 loss: 2.6152 (2.6191) grad_norm: 3.4496 (inf) time: 0.6323 [2021-03-28 18:58:31 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 980/1251] eta: 0:02:52 lr: 0.000010 loss: 2.5053 (2.6188) grad_norm: 3.8615 (inf) time: 0.6283 [2021-03-28 18:58:37 swin_base_patch4_window7_224] INFO: Epoch: [297] [ 990/1251] eta: 0:02:46 lr: 0.000010 loss: 2.6798 (2.6204) grad_norm: 3.5770 (inf) time: 0.6297 [2021-03-28 18:58:43 swin_base_patch4_window7_224] INFO: Epoch: [297] [1000/1251] eta: 0:02:39 lr: 0.000010 loss: 2.8569 (2.6207) grad_norm: 3.4400 (inf) time: 0.6364 [2021-03-28 18:58:50 swin_base_patch4_window7_224] INFO: Epoch: [297] [1010/1251] eta: 0:02:33 lr: 0.000010 loss: 2.5777 (2.6211) grad_norm: 3.7373 (inf) time: 0.6404 [2021-03-28 18:58:56 swin_base_patch4_window7_224] INFO: Epoch: [297] [1020/1251] eta: 0:02:27 lr: 0.000010 loss: 2.6119 (2.6214) grad_norm: 4.0165 (inf) time: 0.6429 [2021-03-28 18:59:03 swin_base_patch4_window7_224] INFO: Epoch: [297] [1030/1251] eta: 0:02:20 lr: 0.000010 loss: 2.6119 (2.6205) grad_norm: 3.7837 (inf) time: 0.6365 [2021-03-28 18:59:09 swin_base_patch4_window7_224] INFO: Epoch: [297] [1040/1251] eta: 0:02:14 lr: 0.000010 loss: 2.6019 (2.6217) grad_norm: 3.5305 (inf) time: 0.6324 [2021-03-28 18:59:15 swin_base_patch4_window7_224] INFO: Epoch: [297] [1050/1251] eta: 0:02:08 lr: 0.000010 loss: 2.7076 (2.6224) grad_norm: 3.3961 (inf) time: 0.6330 [2021-03-28 18:59:21 swin_base_patch4_window7_224] INFO: Epoch: [297] [1060/1251] eta: 0:02:01 lr: 0.000010 loss: 2.8666 (2.6245) grad_norm: 3.8012 (inf) time: 0.6302 [2021-03-28 18:59:28 swin_base_patch4_window7_224] INFO: Epoch: [297] [1070/1251] eta: 0:01:55 lr: 0.000010 loss: 2.8215 (2.6249) grad_norm: 3.9012 (inf) time: 0.6280 [2021-03-28 18:59:34 swin_base_patch4_window7_224] INFO: Epoch: [297] [1080/1251] eta: 0:01:48 lr: 0.000010 loss: 2.6388 (2.6235) grad_norm: 3.6494 (inf) time: 0.6310 [2021-03-28 18:59:40 swin_base_patch4_window7_224] INFO: Epoch: [297] [1090/1251] eta: 0:01:42 lr: 0.000010 loss: 2.5718 (2.6236) grad_norm: 3.5185 (inf) time: 0.6337 [2021-03-28 18:59:47 swin_base_patch4_window7_224] INFO: Epoch: [297] [1100/1251] eta: 0:01:36 lr: 0.000010 loss: 2.9088 (2.6257) grad_norm: 3.7070 (inf) time: 0.6325 [2021-03-28 18:59:53 swin_base_patch4_window7_224] INFO: Epoch: [297] [1110/1251] eta: 0:01:29 lr: 0.000010 loss: 2.7796 (2.6244) grad_norm: 3.4869 (inf) time: 0.6371 [2021-03-28 18:59:59 swin_base_patch4_window7_224] INFO: Epoch: [297] [1120/1251] eta: 0:01:23 lr: 0.000010 loss: 2.4312 (2.6224) grad_norm: 3.4869 (inf) time: 0.6344 [2021-03-28 19:00:06 swin_base_patch4_window7_224] INFO: Epoch: [297] [1130/1251] eta: 0:01:17 lr: 0.000010 loss: 2.7104 (2.6247) grad_norm: 3.9851 (inf) time: 0.6318 [2021-03-28 19:00:12 swin_base_patch4_window7_224] INFO: Epoch: [297] [1140/1251] eta: 0:01:10 lr: 0.000010 loss: 2.8095 (2.6253) grad_norm: 4.1489 (inf) time: 0.6306 [2021-03-28 19:00:18 swin_base_patch4_window7_224] INFO: Epoch: [297] [1150/1251] eta: 0:01:04 lr: 0.000010 loss: 2.6794 (2.6235) grad_norm: 4.1489 (inf) time: 0.6246 [2021-03-28 19:00:25 swin_base_patch4_window7_224] INFO: Epoch: [297] [1160/1251] eta: 0:00:57 lr: 0.000010 loss: 2.6621 (2.6241) grad_norm: 4.0361 (inf) time: 0.6290 [2021-03-28 19:00:31 swin_base_patch4_window7_224] INFO: Epoch: [297] [1170/1251] eta: 0:00:51 lr: 0.000010 loss: 2.7480 (2.6241) grad_norm: 3.6914 (inf) time: 0.6307 [2021-03-28 19:00:37 swin_base_patch4_window7_224] INFO: Epoch: [297] [1180/1251] eta: 0:00:45 lr: 0.000010 loss: 2.6920 (2.6239) grad_norm: 3.6181 (inf) time: 0.6332 [2021-03-28 19:00:44 swin_base_patch4_window7_224] INFO: Epoch: [297] [1190/1251] eta: 0:00:38 lr: 0.000010 loss: 2.5069 (2.6215) grad_norm: 3.5829 (inf) time: 0.6346 [2021-03-28 19:00:50 swin_base_patch4_window7_224] INFO: Epoch: [297] [1200/1251] eta: 0:00:32 lr: 0.000010 loss: 2.5986 (2.6213) grad_norm: 3.5675 (inf) time: 0.6330 [2021-03-28 19:00:56 swin_base_patch4_window7_224] INFO: Epoch: [297] [1210/1251] eta: 0:00:26 lr: 0.000010 loss: 2.6337 (2.6213) grad_norm: 3.7261 (inf) time: 0.6354 [2021-03-28 19:01:03 swin_base_patch4_window7_224] INFO: Epoch: [297] [1220/1251] eta: 0:00:19 lr: 0.000010 loss: 2.8616 (2.6238) grad_norm: 3.4890 (inf) time: 0.6306 [2021-03-28 19:01:09 swin_base_patch4_window7_224] INFO: Epoch: [297] [1230/1251] eta: 0:00:13 lr: 0.000010 loss: 2.8616 (2.6230) grad_norm: 3.2062 (inf) time: 0.6291 [2021-03-28 19:01:15 swin_base_patch4_window7_224] INFO: Epoch: [297] [1240/1251] eta: 0:00:06 lr: 0.000010 loss: 2.6278 (2.6227) grad_norm: 3.4854 (inf) time: 0.6269 [2021-03-28 19:01:21 swin_base_patch4_window7_224] INFO: Epoch: [297] [1250/1251] eta: 0:00:00 lr: 0.000010 loss: 2.6278 (2.6217) grad_norm: 3.8513 (inf) time: 0.6175 [2021-03-28 19:01:35 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:19 loss: 0.4825 (0.4825) acc1: 89.0625 (89.0625) acc5: 100.0000 (100.0000) [2021-03-28 19:01:38 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.7588 (0.7789) acc1: 81.2500 (81.8182) acc5: 96.8750 (95.4545) [2021-03-28 19:01:40 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7588 (0.7597) acc1: 81.2500 (82.3661) acc5: 96.8750 (96.5774) [2021-03-28 19:01:42 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6345 (0.7220) acc1: 84.3750 (82.9133) acc5: 96.8750 (96.8750) [2021-03-28 19:01:44 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7320 (0.7509) acc1: 81.2500 (82.3171) acc5: 96.8750 (96.5701) [2021-03-28 19:01:45 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8236 (0.7497) acc1: 81.2500 (82.2400) acc5: 95.3125 (96.5440) [2021-03-28 19:02:03 swin_base_patch4_window7_224] INFO: * Acc@1 83.448 Acc@5 96.462 loss 0.738 [2021-03-28 19:02:03 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 19:02:03 swin_base_patch4_window7_224] INFO: Max accuracy: 83.46% [2021-03-28 19:02:08 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 0/1251] eta: 1:34:26 lr: 0.000010 loss: 2.8909 (2.8909) grad_norm: 3.6697 (3.6697) time: 4.5292 [2021-03-28 19:02:14 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 10/1251] eta: 0:20:41 lr: 0.000010 loss: 2.7063 (2.5138) grad_norm: 3.7106 (4.3859) time: 1.0005 [2021-03-28 19:02:20 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 20/1251] eta: 0:16:56 lr: 0.000010 loss: 2.5697 (2.4917) grad_norm: 3.5566 (4.0609) time: 0.6405 [2021-03-28 19:02:27 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 30/1251] eta: 0:15:30 lr: 0.000010 loss: 2.6984 (2.5860) grad_norm: 3.5566 (4.0052) time: 0.6312 [2021-03-28 19:02:33 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 40/1251] eta: 0:14:45 lr: 0.000010 loss: 2.7408 (2.6149) grad_norm: 3.8405 (4.0091) time: 0.6314 [2021-03-28 19:02:40 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 50/1251] eta: 0:14:17 lr: 0.000010 loss: 2.7408 (2.6208) grad_norm: 3.7743 (4.0101) time: 0.6387 [2021-03-28 19:02:46 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 60/1251] eta: 0:13:51 lr: 0.000010 loss: 2.4055 (2.5574) grad_norm: 3.9279 (4.0552) time: 0.6323 [2021-03-28 19:02:52 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 70/1251] eta: 0:13:34 lr: 0.000010 loss: 2.4557 (2.5592) grad_norm: 3.2427 (3.9632) time: 0.6288 [2021-03-28 19:02:58 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 80/1251] eta: 0:13:17 lr: 0.000010 loss: 2.5451 (2.5502) grad_norm: 3.5270 (inf) time: 0.6273 [2021-03-28 19:03:05 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 90/1251] eta: 0:13:03 lr: 0.000010 loss: 2.7084 (2.5613) grad_norm: 3.7519 (inf) time: 0.6206 [2021-03-28 19:03:11 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 100/1251] eta: 0:12:52 lr: 0.000010 loss: 2.7085 (2.5743) grad_norm: 3.8741 (inf) time: 0.6295 [2021-03-28 19:03:17 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 110/1251] eta: 0:12:40 lr: 0.000010 loss: 2.6487 (2.5862) grad_norm: 3.9972 (inf) time: 0.6312 [2021-03-28 19:03:24 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 120/1251] eta: 0:12:31 lr: 0.000010 loss: 2.5691 (2.5670) grad_norm: 3.5670 (inf) time: 0.6323 [2021-03-28 19:03:30 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 130/1251] eta: 0:12:22 lr: 0.000010 loss: 2.6818 (2.5718) grad_norm: 3.5287 (inf) time: 0.6356 [2021-03-28 19:03:36 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 140/1251] eta: 0:12:12 lr: 0.000010 loss: 2.6818 (2.5772) grad_norm: 3.3728 (inf) time: 0.6266 [2021-03-28 19:03:42 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 150/1251] eta: 0:12:03 lr: 0.000010 loss: 2.6798 (2.5838) grad_norm: 3.5938 (inf) time: 0.6240 [2021-03-28 19:03:49 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 160/1251] eta: 0:11:54 lr: 0.000010 loss: 2.6961 (2.5898) grad_norm: 3.8326 (inf) time: 0.6272 [2021-03-28 19:03:55 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 170/1251] eta: 0:11:46 lr: 0.000010 loss: 2.6904 (2.5882) grad_norm: 3.5430 (inf) time: 0.6267 [2021-03-28 19:04:01 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 180/1251] eta: 0:11:39 lr: 0.000010 loss: 2.7428 (2.6034) grad_norm: 3.5282 (inf) time: 0.6339 [2021-03-28 19:04:08 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 190/1251] eta: 0:11:31 lr: 0.000010 loss: 2.6701 (2.6057) grad_norm: 3.6433 (inf) time: 0.6406 [2021-03-28 19:04:14 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 200/1251] eta: 0:11:24 lr: 0.000010 loss: 2.6131 (2.6010) grad_norm: 3.5860 (inf) time: 0.6353 [2021-03-28 19:04:20 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 210/1251] eta: 0:11:17 lr: 0.000010 loss: 2.6335 (2.5991) grad_norm: 3.5860 (inf) time: 0.6375 [2021-03-28 19:04:27 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 220/1251] eta: 0:11:09 lr: 0.000010 loss: 2.5747 (2.6034) grad_norm: 3.8214 (inf) time: 0.6375 [2021-03-28 19:04:33 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 230/1251] eta: 0:11:02 lr: 0.000010 loss: 2.5747 (2.5987) grad_norm: 3.7661 (inf) time: 0.6343 [2021-03-28 19:04:40 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 240/1251] eta: 0:10:56 lr: 0.000010 loss: 2.6354 (2.5982) grad_norm: 3.7661 (inf) time: 0.6398 [2021-03-28 19:04:46 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 250/1251] eta: 0:10:49 lr: 0.000010 loss: 2.6354 (2.6019) grad_norm: 3.7396 (inf) time: 0.6380 [2021-03-28 19:04:52 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 260/1251] eta: 0:10:42 lr: 0.000010 loss: 2.7300 (2.6020) grad_norm: 3.5401 (inf) time: 0.6374 [2021-03-28 19:04:59 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 270/1251] eta: 0:10:35 lr: 0.000010 loss: 2.7300 (2.6093) grad_norm: 3.4699 (inf) time: 0.6444 [2021-03-28 19:05:05 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 280/1251] eta: 0:10:28 lr: 0.000010 loss: 2.7653 (2.6151) grad_norm: 3.5962 (inf) time: 0.6398 [2021-03-28 19:05:11 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 290/1251] eta: 0:10:21 lr: 0.000010 loss: 2.7255 (2.6148) grad_norm: 3.9634 (inf) time: 0.6321 [2021-03-28 19:05:18 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 300/1251] eta: 0:10:14 lr: 0.000010 loss: 2.6852 (2.6178) grad_norm: 3.7936 (inf) time: 0.6315 [2021-03-28 19:05:24 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 310/1251] eta: 0:10:07 lr: 0.000010 loss: 2.7382 (2.6244) grad_norm: 3.7936 (inf) time: 0.6299 [2021-03-28 19:05:30 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 320/1251] eta: 0:10:00 lr: 0.000010 loss: 2.8817 (2.6267) grad_norm: 3.6886 (inf) time: 0.6290 [2021-03-28 19:05:37 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 330/1251] eta: 0:09:53 lr: 0.000010 loss: 2.6835 (2.6286) grad_norm: 3.6931 (inf) time: 0.6302 [2021-03-28 19:05:43 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 340/1251] eta: 0:09:46 lr: 0.000010 loss: 2.6835 (2.6314) grad_norm: 3.8107 (inf) time: 0.6269 [2021-03-28 19:05:49 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 350/1251] eta: 0:09:40 lr: 0.000010 loss: 2.6693 (2.6319) grad_norm: 3.5639 (inf) time: 0.6268 [2021-03-28 19:05:55 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 360/1251] eta: 0:09:33 lr: 0.000010 loss: 2.5764 (2.6339) grad_norm: 3.4003 (inf) time: 0.6249 [2021-03-28 19:06:02 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 370/1251] eta: 0:09:26 lr: 0.000010 loss: 2.6545 (2.6333) grad_norm: 3.2950 (inf) time: 0.6259 [2021-03-28 19:06:08 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 380/1251] eta: 0:09:19 lr: 0.000010 loss: 2.7213 (2.6388) grad_norm: 3.5888 (inf) time: 0.6294 [2021-03-28 19:06:14 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 390/1251] eta: 0:09:12 lr: 0.000010 loss: 2.7897 (2.6409) grad_norm: 3.9450 (inf) time: 0.6259 [2021-03-28 19:06:21 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 400/1251] eta: 0:09:06 lr: 0.000010 loss: 2.7360 (2.6422) grad_norm: 3.5952 (inf) time: 0.6270 [2021-03-28 19:06:27 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 410/1251] eta: 0:08:59 lr: 0.000010 loss: 2.7403 (2.6423) grad_norm: 3.5518 (inf) time: 0.6319 [2021-03-28 19:06:33 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 420/1251] eta: 0:08:52 lr: 0.000010 loss: 2.7251 (2.6369) grad_norm: 3.6922 (inf) time: 0.6345 [2021-03-28 19:06:40 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 430/1251] eta: 0:08:46 lr: 0.000010 loss: 2.6601 (2.6377) grad_norm: 3.6922 (inf) time: 0.6332 [2021-03-28 19:06:46 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 440/1251] eta: 0:08:39 lr: 0.000010 loss: 2.6967 (2.6374) grad_norm: 3.5886 (inf) time: 0.6348 [2021-03-28 19:06:52 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 450/1251] eta: 0:08:33 lr: 0.000010 loss: 2.7507 (2.6368) grad_norm: 3.5886 (inf) time: 0.6345 [2021-03-28 19:06:59 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 460/1251] eta: 0:08:26 lr: 0.000010 loss: 2.6702 (2.6373) grad_norm: 3.5838 (inf) time: 0.6314 [2021-03-28 19:07:05 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 470/1251] eta: 0:08:20 lr: 0.000010 loss: 2.3928 (2.6327) grad_norm: 3.6817 (inf) time: 0.6350 [2021-03-28 19:07:11 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 480/1251] eta: 0:08:13 lr: 0.000010 loss: 2.3320 (2.6298) grad_norm: 3.7148 (inf) time: 0.6384 [2021-03-28 19:07:18 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 490/1251] eta: 0:08:07 lr: 0.000010 loss: 2.6894 (2.6315) grad_norm: 3.7768 (inf) time: 0.6319 [2021-03-28 19:07:24 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 500/1251] eta: 0:08:00 lr: 0.000010 loss: 2.7469 (2.6305) grad_norm: 3.7768 (inf) time: 0.6272 [2021-03-28 19:07:30 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 510/1251] eta: 0:07:54 lr: 0.000010 loss: 2.5789 (2.6282) grad_norm: 3.7156 (inf) time: 0.6266 [2021-03-28 19:07:36 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 520/1251] eta: 0:07:47 lr: 0.000010 loss: 2.5789 (2.6256) grad_norm: 3.4195 (inf) time: 0.6309 [2021-03-28 19:07:43 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 530/1251] eta: 0:07:41 lr: 0.000010 loss: 2.6867 (2.6295) grad_norm: 3.4958 (inf) time: 0.6339 [2021-03-28 19:07:49 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 540/1251] eta: 0:07:34 lr: 0.000010 loss: 2.5955 (2.6240) grad_norm: 3.7523 (inf) time: 0.6346 [2021-03-28 19:07:56 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 550/1251] eta: 0:07:28 lr: 0.000010 loss: 2.5063 (2.6248) grad_norm: 3.5397 (inf) time: 0.6433 [2021-03-28 19:08:02 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 560/1251] eta: 0:07:22 lr: 0.000010 loss: 2.6407 (2.6225) grad_norm: 3.5377 (inf) time: 0.6499 [2021-03-28 19:08:08 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 570/1251] eta: 0:07:15 lr: 0.000010 loss: 2.6742 (2.6212) grad_norm: 3.8374 (inf) time: 0.6411 [2021-03-28 19:08:15 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 580/1251] eta: 0:07:09 lr: 0.000010 loss: 2.7679 (2.6227) grad_norm: 3.9206 (inf) time: 0.6295 [2021-03-28 19:08:21 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 590/1251] eta: 0:07:02 lr: 0.000010 loss: 2.7703 (2.6231) grad_norm: 3.8673 (inf) time: 0.6290 [2021-03-28 19:08:27 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 600/1251] eta: 0:06:56 lr: 0.000010 loss: 2.7128 (2.6222) grad_norm: 3.6302 (inf) time: 0.6353 [2021-03-28 19:08:34 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 610/1251] eta: 0:06:49 lr: 0.000010 loss: 2.7816 (2.6239) grad_norm: 3.6277 (inf) time: 0.6357 [2021-03-28 19:08:40 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 620/1251] eta: 0:06:43 lr: 0.000010 loss: 2.7893 (2.6238) grad_norm: 3.5679 (inf) time: 0.6288 [2021-03-28 19:08:46 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 630/1251] eta: 0:06:36 lr: 0.000010 loss: 2.5852 (2.6207) grad_norm: 3.6878 (inf) time: 0.6307 [2021-03-28 19:08:53 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 640/1251] eta: 0:06:30 lr: 0.000010 loss: 2.3363 (2.6189) grad_norm: 3.7795 (inf) time: 0.6320 [2021-03-28 19:08:59 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 650/1251] eta: 0:06:23 lr: 0.000010 loss: 2.3719 (2.6165) grad_norm: 3.6199 (inf) time: 0.6254 [2021-03-28 19:09:05 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 660/1251] eta: 0:06:17 lr: 0.000010 loss: 2.4390 (2.6130) grad_norm: 3.5519 (inf) time: 0.6303 [2021-03-28 19:09:12 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 670/1251] eta: 0:06:10 lr: 0.000010 loss: 2.5966 (2.6143) grad_norm: 3.7711 (inf) time: 0.6307 [2021-03-28 19:09:18 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 680/1251] eta: 0:06:04 lr: 0.000010 loss: 2.5621 (2.6122) grad_norm: 3.7711 (inf) time: 0.6249 [2021-03-28 19:09:24 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 690/1251] eta: 0:05:57 lr: 0.000010 loss: 2.5496 (2.6122) grad_norm: 3.7929 (inf) time: 0.6270 [2021-03-28 19:09:30 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 700/1251] eta: 0:05:51 lr: 0.000010 loss: 2.4913 (2.6104) grad_norm: 3.9359 (inf) time: 0.6288 [2021-03-28 19:09:37 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 710/1251] eta: 0:05:44 lr: 0.000010 loss: 2.7011 (2.6112) grad_norm: 3.8281 (inf) time: 0.6278 [2021-03-28 19:09:43 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 720/1251] eta: 0:05:38 lr: 0.000010 loss: 2.7470 (2.6131) grad_norm: 3.4556 (inf) time: 0.6349 [2021-03-28 19:09:49 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 730/1251] eta: 0:05:32 lr: 0.000010 loss: 2.6483 (2.6141) grad_norm: 3.5380 (inf) time: 0.6368 [2021-03-28 19:09:56 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 740/1251] eta: 0:05:25 lr: 0.000010 loss: 2.7610 (2.6154) grad_norm: 3.8405 (inf) time: 0.6312 [2021-03-28 19:10:02 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 750/1251] eta: 0:05:19 lr: 0.000010 loss: 2.6676 (2.6143) grad_norm: 3.8829 (inf) time: 0.6369 [2021-03-28 19:10:09 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 760/1251] eta: 0:05:13 lr: 0.000010 loss: 2.6286 (2.6152) grad_norm: 3.7983 (inf) time: 0.6399 [2021-03-28 19:10:15 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 770/1251] eta: 0:05:06 lr: 0.000010 loss: 2.5168 (2.6132) grad_norm: 3.7039 (inf) time: 0.6349 [2021-03-28 19:10:21 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 780/1251] eta: 0:05:00 lr: 0.000010 loss: 2.7507 (2.6153) grad_norm: 3.6476 (inf) time: 0.6268 [2021-03-28 19:10:27 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 790/1251] eta: 0:04:53 lr: 0.000010 loss: 2.7507 (2.6144) grad_norm: 3.5642 (inf) time: 0.6238 [2021-03-28 19:10:34 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 800/1251] eta: 0:04:47 lr: 0.000010 loss: 2.8072 (2.6163) grad_norm: 3.6139 (inf) time: 0.6293 [2021-03-28 19:10:40 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 810/1251] eta: 0:04:40 lr: 0.000010 loss: 2.6212 (2.6148) grad_norm: 3.7929 (inf) time: 0.6343 [2021-03-28 19:10:46 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 820/1251] eta: 0:04:34 lr: 0.000010 loss: 2.4029 (2.6122) grad_norm: 3.8625 (inf) time: 0.6273 [2021-03-28 19:10:52 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 830/1251] eta: 0:04:28 lr: 0.000010 loss: 2.5657 (2.6136) grad_norm: 3.7122 (inf) time: 0.6234 [2021-03-28 19:10:59 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 840/1251] eta: 0:04:21 lr: 0.000010 loss: 2.7595 (2.6119) grad_norm: 3.7122 (inf) time: 0.6352 [2021-03-28 19:11:05 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 850/1251] eta: 0:04:15 lr: 0.000010 loss: 2.5270 (2.6106) grad_norm: 3.7824 (inf) time: 0.6402 [2021-03-28 19:11:12 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 860/1251] eta: 0:04:08 lr: 0.000010 loss: 2.5527 (2.6093) grad_norm: 3.6834 (inf) time: 0.6317 [2021-03-28 19:11:18 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 870/1251] eta: 0:04:02 lr: 0.000010 loss: 2.5877 (2.6086) grad_norm: 3.8808 (inf) time: 0.6313 [2021-03-28 19:11:24 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 880/1251] eta: 0:03:56 lr: 0.000010 loss: 2.6708 (2.6081) grad_norm: 3.6821 (inf) time: 0.6414 [2021-03-28 19:11:31 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 890/1251] eta: 0:03:49 lr: 0.000010 loss: 2.7269 (2.6090) grad_norm: 3.6911 (inf) time: 0.6390 [2021-03-28 19:11:37 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 900/1251] eta: 0:03:43 lr: 0.000010 loss: 2.5882 (2.6078) grad_norm: 3.9000 (inf) time: 0.6359 [2021-03-28 19:11:43 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 910/1251] eta: 0:03:37 lr: 0.000010 loss: 2.6881 (2.6087) grad_norm: 3.5303 (inf) time: 0.6401 [2021-03-28 19:11:50 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 920/1251] eta: 0:03:30 lr: 0.000010 loss: 2.6873 (2.6070) grad_norm: 3.2860 (inf) time: 0.6386 [2021-03-28 19:11:56 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 930/1251] eta: 0:03:24 lr: 0.000010 loss: 2.5673 (2.6080) grad_norm: 3.5562 (inf) time: 0.6358 [2021-03-28 19:12:02 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 940/1251] eta: 0:03:18 lr: 0.000010 loss: 2.6923 (2.6083) grad_norm: 3.8643 (inf) time: 0.6300 [2021-03-28 19:12:09 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 950/1251] eta: 0:03:11 lr: 0.000010 loss: 2.5643 (2.6072) grad_norm: 3.8643 (inf) time: 0.6277 [2021-03-28 19:12:15 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 960/1251] eta: 0:03:05 lr: 0.000010 loss: 2.6561 (2.6093) grad_norm: 4.3495 (inf) time: 0.6322 [2021-03-28 19:12:21 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 970/1251] eta: 0:02:58 lr: 0.000010 loss: 2.7024 (2.6076) grad_norm: 3.7327 (inf) time: 0.6288 [2021-03-28 19:12:28 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 980/1251] eta: 0:02:52 lr: 0.000010 loss: 2.4880 (2.6066) grad_norm: 4.2317 (inf) time: 0.6267 [2021-03-28 19:12:34 swin_base_patch4_window7_224] INFO: Epoch: [298] [ 990/1251] eta: 0:02:46 lr: 0.000010 loss: 2.6793 (2.6062) grad_norm: 4.4251 (inf) time: 0.6313 [2021-03-28 19:12:40 swin_base_patch4_window7_224] INFO: Epoch: [298] [1000/1251] eta: 0:02:39 lr: 0.000010 loss: 2.5911 (2.6039) grad_norm: 3.7774 (inf) time: 0.6375 [2021-03-28 19:12:47 swin_base_patch4_window7_224] INFO: Epoch: [298] [1010/1251] eta: 0:02:33 lr: 0.000010 loss: 2.5255 (2.6044) grad_norm: 3.7774 (inf) time: 0.6347 [2021-03-28 19:12:53 swin_base_patch4_window7_224] INFO: Epoch: [298] [1020/1251] eta: 0:02:26 lr: 0.000010 loss: 2.6976 (2.6046) grad_norm: 3.7306 (inf) time: 0.6260 [2021-03-28 19:12:59 swin_base_patch4_window7_224] INFO: Epoch: [298] [1030/1251] eta: 0:02:20 lr: 0.000010 loss: 2.7015 (2.6048) grad_norm: 3.6880 (inf) time: 0.6323 [2021-03-28 19:13:06 swin_base_patch4_window7_224] INFO: Epoch: [298] [1040/1251] eta: 0:02:14 lr: 0.000010 loss: 2.7015 (2.6050) grad_norm: 3.6754 (inf) time: 0.6296 [2021-03-28 19:13:12 swin_base_patch4_window7_224] INFO: Epoch: [298] [1050/1251] eta: 0:02:07 lr: 0.000010 loss: 2.5285 (2.6031) grad_norm: 3.5825 (inf) time: 0.6247 [2021-03-28 19:13:18 swin_base_patch4_window7_224] INFO: Epoch: [298] [1060/1251] eta: 0:02:01 lr: 0.000010 loss: 2.6060 (2.6049) grad_norm: 3.5015 (inf) time: 0.6312 [2021-03-28 19:13:24 swin_base_patch4_window7_224] INFO: Epoch: [298] [1070/1251] eta: 0:01:55 lr: 0.000010 loss: 2.8330 (2.6057) grad_norm: 3.7720 (inf) time: 0.6332 [2021-03-28 19:13:31 swin_base_patch4_window7_224] INFO: Epoch: [298] [1080/1251] eta: 0:01:48 lr: 0.000010 loss: 2.7217 (2.6067) grad_norm: 3.7873 (inf) time: 0.6336 [2021-03-28 19:13:37 swin_base_patch4_window7_224] INFO: Epoch: [298] [1090/1251] eta: 0:01:42 lr: 0.000010 loss: 2.7105 (2.6063) grad_norm: 3.6986 (inf) time: 0.6287 [2021-03-28 19:13:43 swin_base_patch4_window7_224] INFO: Epoch: [298] [1100/1251] eta: 0:01:36 lr: 0.000010 loss: 2.7377 (2.6074) grad_norm: 3.6669 (inf) time: 0.6240 [2021-03-28 19:13:50 swin_base_patch4_window7_224] INFO: Epoch: [298] [1110/1251] eta: 0:01:29 lr: 0.000010 loss: 2.7475 (2.6068) grad_norm: 3.6524 (inf) time: 0.6291 [2021-03-28 19:13:56 swin_base_patch4_window7_224] INFO: Epoch: [298] [1120/1251] eta: 0:01:23 lr: 0.000010 loss: 2.5981 (2.6067) grad_norm: 3.6524 (inf) time: 0.6304 [2021-03-28 19:14:02 swin_base_patch4_window7_224] INFO: Epoch: [298] [1130/1251] eta: 0:01:16 lr: 0.000010 loss: 2.6484 (2.6068) grad_norm: 3.7865 (inf) time: 0.6282 [2021-03-28 19:14:09 swin_base_patch4_window7_224] INFO: Epoch: [298] [1140/1251] eta: 0:01:10 lr: 0.000010 loss: 2.8325 (2.6065) grad_norm: 3.8442 (inf) time: 0.6348 [2021-03-28 19:14:15 swin_base_patch4_window7_224] INFO: Epoch: [298] [1150/1251] eta: 0:01:04 lr: 0.000010 loss: 2.3689 (2.6050) grad_norm: 3.7774 (inf) time: 0.6348 [2021-03-28 19:14:21 swin_base_patch4_window7_224] INFO: Epoch: [298] [1160/1251] eta: 0:00:57 lr: 0.000010 loss: 2.6438 (2.6058) grad_norm: 3.7774 (inf) time: 0.6302 [2021-03-28 19:14:28 swin_base_patch4_window7_224] INFO: Epoch: [298] [1170/1251] eta: 0:00:51 lr: 0.000010 loss: 2.6438 (2.6058) grad_norm: 3.6040 (inf) time: 0.6295 [2021-03-28 19:14:34 swin_base_patch4_window7_224] INFO: Epoch: [298] [1180/1251] eta: 0:00:45 lr: 0.000010 loss: 2.8577 (2.6084) grad_norm: 3.6492 (inf) time: 0.6353 [2021-03-28 19:14:40 swin_base_patch4_window7_224] INFO: Epoch: [298] [1190/1251] eta: 0:00:38 lr: 0.000010 loss: 2.8577 (2.6078) grad_norm: 3.9916 (inf) time: 0.6391 [2021-03-28 19:14:47 swin_base_patch4_window7_224] INFO: Epoch: [298] [1200/1251] eta: 0:00:32 lr: 0.000010 loss: 2.7793 (2.6087) grad_norm: 3.7936 (inf) time: 0.6337 [2021-03-28 19:14:53 swin_base_patch4_window7_224] INFO: Epoch: [298] [1210/1251] eta: 0:00:26 lr: 0.000010 loss: 2.7793 (2.6091) grad_norm: 3.5767 (inf) time: 0.6294 [2021-03-28 19:14:59 swin_base_patch4_window7_224] INFO: Epoch: [298] [1220/1251] eta: 0:00:19 lr: 0.000010 loss: 2.6509 (2.6088) grad_norm: 3.4155 (inf) time: 0.6301 [2021-03-28 19:15:05 swin_base_patch4_window7_224] INFO: Epoch: [298] [1230/1251] eta: 0:00:13 lr: 0.000010 loss: 2.7549 (2.6102) grad_norm: 3.6827 (inf) time: 0.6285 [2021-03-28 19:15:12 swin_base_patch4_window7_224] INFO: Epoch: [298] [1240/1251] eta: 0:00:06 lr: 0.000010 loss: 2.6879 (2.6100) grad_norm: 3.8607 (inf) time: 0.6229 [2021-03-28 19:15:18 swin_base_patch4_window7_224] INFO: Epoch: [298] [1250/1251] eta: 0:00:00 lr: 0.000010 loss: 2.5595 (2.6092) grad_norm: 3.7400 (inf) time: 0.6272 [2021-03-28 19:15:31 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:26 loss: 0.8703 (0.8703) acc1: 73.4375 (73.4375) acc5: 96.8750 (96.8750) [2021-03-28 19:15:33 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8561 (0.8450) acc1: 78.1250 (80.6818) acc5: 96.8750 (96.4489) [2021-03-28 19:15:36 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8284 (0.8283) acc1: 82.8125 (81.5476) acc5: 95.3125 (96.1310) [2021-03-28 19:15:38 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7712 (0.7834) acc1: 84.3750 (81.9556) acc5: 95.3125 (96.4214) [2021-03-28 19:15:40 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6332 (0.7515) acc1: 84.3750 (82.3933) acc5: 98.4375 (96.6845) [2021-03-28 19:15:41 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6587 (0.7523) acc1: 81.2500 (82.1440) acc5: 96.8750 (96.6400) [2021-03-28 19:15:58 swin_base_patch4_window7_224] INFO: * Acc@1 83.440 Acc@5 96.446 loss 0.738 [2021-03-28 19:15:58 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.4% [2021-03-28 19:15:58 swin_base_patch4_window7_224] INFO: Max accuracy: 83.46% [2021-03-28 19:16:03 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 0/1251] eta: 1:44:09 lr: 0.000010 loss: 2.8213 (2.8213) grad_norm: 3.5165 (3.5165) time: 4.9957 [2021-03-28 19:16:10 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 10/1251] eta: 0:21:15 lr: 0.000010 loss: 2.8477 (2.8678) grad_norm: 3.5165 (3.5348) time: 1.0281 [2021-03-28 19:16:16 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 20/1251] eta: 0:17:13 lr: 0.000010 loss: 2.8477 (2.8437) grad_norm: 3.4407 (3.6071) time: 0.6314 [2021-03-28 19:16:22 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 30/1251] eta: 0:15:44 lr: 0.000010 loss: 2.7990 (2.7731) grad_norm: 3.6581 (3.7249) time: 0.6340 [2021-03-28 19:16:29 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 40/1251] eta: 0:14:57 lr: 0.000010 loss: 2.7990 (2.7677) grad_norm: 3.6966 (3.7481) time: 0.6373 [2021-03-28 19:16:35 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 50/1251] eta: 0:14:24 lr: 0.000010 loss: 2.6367 (2.7183) grad_norm: 3.8813 (3.8955) time: 0.6370 [2021-03-28 19:16:41 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 60/1251] eta: 0:14:00 lr: 0.000010 loss: 2.4478 (2.6618) grad_norm: 3.8558 (3.9115) time: 0.6350 [2021-03-28 19:16:48 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 70/1251] eta: 0:13:41 lr: 0.000010 loss: 2.5507 (2.6864) grad_norm: 3.6815 (3.8952) time: 0.6341 [2021-03-28 19:16:54 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 80/1251] eta: 0:13:25 lr: 0.000010 loss: 2.7209 (2.6727) grad_norm: 4.0632 (3.9189) time: 0.6315 [2021-03-28 19:17:00 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 90/1251] eta: 0:13:11 lr: 0.000010 loss: 2.7075 (2.6704) grad_norm: 4.1189 (3.9543) time: 0.6315 [2021-03-28 19:17:07 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 100/1251] eta: 0:12:58 lr: 0.000010 loss: 2.5699 (2.6650) grad_norm: 4.1303 (4.8011) time: 0.6319 [2021-03-28 19:17:13 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 110/1251] eta: 0:12:47 lr: 0.000010 loss: 2.7792 (2.6762) grad_norm: 3.8795 (4.7470) time: 0.6318 [2021-03-28 19:17:19 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 120/1251] eta: 0:12:36 lr: 0.000010 loss: 2.8624 (2.6932) grad_norm: 3.7066 (4.7441) time: 0.6282 [2021-03-28 19:17:25 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 130/1251] eta: 0:12:25 lr: 0.000010 loss: 2.8054 (2.6828) grad_norm: 3.6871 (4.6665) time: 0.6210 [2021-03-28 19:17:32 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 140/1251] eta: 0:12:16 lr: 0.000010 loss: 2.7210 (2.6882) grad_norm: 3.6871 (4.6160) time: 0.6263 [2021-03-28 19:17:38 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 150/1251] eta: 0:12:06 lr: 0.000010 loss: 2.7781 (2.6866) grad_norm: 3.8333 (4.5761) time: 0.6287 [2021-03-28 19:17:44 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 160/1251] eta: 0:11:57 lr: 0.000010 loss: 2.5451 (2.6714) grad_norm: 3.8333 (4.5910) time: 0.6220 [2021-03-28 19:17:51 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 170/1251] eta: 0:11:49 lr: 0.000010 loss: 2.5002 (2.6653) grad_norm: 3.6497 (4.5382) time: 0.6291 [2021-03-28 19:17:57 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 180/1251] eta: 0:11:41 lr: 0.000010 loss: 2.4904 (2.6494) grad_norm: 3.6497 (4.5037) time: 0.6375 [2021-03-28 19:18:03 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 190/1251] eta: 0:11:33 lr: 0.000010 loss: 2.5098 (2.6442) grad_norm: 3.5338 (4.4663) time: 0.6276 [2021-03-28 19:18:10 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 200/1251] eta: 0:11:25 lr: 0.000010 loss: 2.5939 (2.6388) grad_norm: 3.6729 (4.4579) time: 0.6277 [2021-03-28 19:18:16 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 210/1251] eta: 0:11:18 lr: 0.000010 loss: 2.5939 (2.6357) grad_norm: 3.8047 (4.4425) time: 0.6336 [2021-03-28 19:18:22 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 220/1251] eta: 0:11:10 lr: 0.000010 loss: 2.4141 (2.6269) grad_norm: 3.9160 (4.4382) time: 0.6287 [2021-03-28 19:18:28 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 230/1251] eta: 0:11:03 lr: 0.000010 loss: 2.5780 (2.6303) grad_norm: 4.0575 (4.4398) time: 0.6274 [2021-03-28 19:18:35 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 240/1251] eta: 0:10:55 lr: 0.000010 loss: 2.5883 (2.6292) grad_norm: 3.8294 (4.4205) time: 0.6305 [2021-03-28 19:18:41 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 250/1251] eta: 0:10:48 lr: 0.000010 loss: 2.8202 (2.6385) grad_norm: 3.6897 (4.4012) time: 0.6334 [2021-03-28 19:18:47 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 260/1251] eta: 0:10:41 lr: 0.000010 loss: 2.7557 (2.6358) grad_norm: 3.7480 (4.3834) time: 0.6296 [2021-03-28 19:18:54 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 270/1251] eta: 0:10:34 lr: 0.000010 loss: 2.6126 (2.6320) grad_norm: 3.6677 (4.3519) time: 0.6275 [2021-03-28 19:19:00 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 280/1251] eta: 0:10:27 lr: 0.000010 loss: 2.7048 (2.6306) grad_norm: 3.6108 (4.3389) time: 0.6295 [2021-03-28 19:19:06 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 290/1251] eta: 0:10:20 lr: 0.000010 loss: 2.6591 (2.6267) grad_norm: 3.6108 (4.3009) time: 0.6314 [2021-03-28 19:19:13 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 300/1251] eta: 0:10:13 lr: 0.000010 loss: 2.5441 (2.6224) grad_norm: 3.6904 (4.2946) time: 0.6383 [2021-03-28 19:19:19 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 310/1251] eta: 0:10:07 lr: 0.000010 loss: 2.7592 (2.6263) grad_norm: 3.8332 (4.2766) time: 0.6410 [2021-03-28 19:19:25 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 320/1251] eta: 0:10:00 lr: 0.000010 loss: 2.8247 (2.6261) grad_norm: 3.5480 (4.2704) time: 0.6346 [2021-03-28 19:19:32 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 330/1251] eta: 0:09:53 lr: 0.000010 loss: 2.8160 (2.6281) grad_norm: 3.5118 (4.2502) time: 0.6310 [2021-03-28 19:19:38 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 340/1251] eta: 0:09:46 lr: 0.000010 loss: 2.7352 (2.6282) grad_norm: 3.6225 (4.2432) time: 0.6324 [2021-03-28 19:19:44 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 350/1251] eta: 0:09:40 lr: 0.000010 loss: 2.7352 (2.6296) grad_norm: 3.6932 (4.2577) time: 0.6378 [2021-03-28 19:19:51 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 360/1251] eta: 0:09:33 lr: 0.000010 loss: 2.7098 (2.6296) grad_norm: 3.6107 (4.2414) time: 0.6351 [2021-03-28 19:19:57 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 370/1251] eta: 0:09:26 lr: 0.000010 loss: 2.7040 (2.6289) grad_norm: 3.5186 (4.2324) time: 0.6333 [2021-03-28 19:20:03 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 380/1251] eta: 0:09:20 lr: 0.000010 loss: 2.6659 (2.6267) grad_norm: 3.5186 (4.2114) time: 0.6335 [2021-03-28 19:20:10 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 390/1251] eta: 0:09:13 lr: 0.000010 loss: 2.8893 (2.6337) grad_norm: 3.6313 (4.2049) time: 0.6293 [2021-03-28 19:20:16 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 400/1251] eta: 0:09:06 lr: 0.000010 loss: 2.8014 (2.6330) grad_norm: 3.6177 (4.1944) time: 0.6362 [2021-03-28 19:20:22 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 410/1251] eta: 0:09:00 lr: 0.000010 loss: 2.5129 (2.6369) grad_norm: 3.8379 (4.1911) time: 0.6350 [2021-03-28 19:20:29 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 420/1251] eta: 0:08:53 lr: 0.000010 loss: 2.6631 (2.6357) grad_norm: 3.7347 (4.1765) time: 0.6230 [2021-03-28 19:20:35 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 430/1251] eta: 0:08:46 lr: 0.000010 loss: 2.6635 (2.6381) grad_norm: 3.5948 (4.1735) time: 0.6260 [2021-03-28 19:20:41 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 440/1251] eta: 0:08:39 lr: 0.000010 loss: 2.6451 (2.6367) grad_norm: 3.5827 (4.1588) time: 0.6269 [2021-03-28 19:20:47 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 450/1251] eta: 0:08:33 lr: 0.000010 loss: 2.6033 (2.6332) grad_norm: 3.5827 (4.1546) time: 0.6231 [2021-03-28 19:20:54 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 460/1251] eta: 0:08:26 lr: 0.000010 loss: 2.6981 (2.6352) grad_norm: 3.8803 (4.1514) time: 0.6260 [2021-03-28 19:21:00 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 470/1251] eta: 0:08:19 lr: 0.000010 loss: 2.7872 (2.6357) grad_norm: 3.5441 (4.1435) time: 0.6255 [2021-03-28 19:21:06 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 480/1251] eta: 0:08:13 lr: 0.000010 loss: 2.6730 (2.6352) grad_norm: 3.7038 (4.1355) time: 0.6309 [2021-03-28 19:21:13 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 490/1251] eta: 0:08:06 lr: 0.000010 loss: 2.7596 (2.6346) grad_norm: 3.7164 (4.1365) time: 0.6338 [2021-03-28 19:21:19 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 500/1251] eta: 0:08:00 lr: 0.000010 loss: 2.5167 (2.6289) grad_norm: 3.8030 (4.1391) time: 0.6322 [2021-03-28 19:21:25 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 510/1251] eta: 0:07:53 lr: 0.000010 loss: 2.5473 (2.6295) grad_norm: 3.7906 (4.1288) time: 0.6340 [2021-03-28 19:21:32 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 520/1251] eta: 0:07:47 lr: 0.000010 loss: 2.6579 (2.6309) grad_norm: 3.6182 (4.1250) time: 0.6362 [2021-03-28 19:21:38 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 530/1251] eta: 0:07:41 lr: 0.000010 loss: 2.6255 (2.6272) grad_norm: 3.6182 (4.1179) time: 0.6340 [2021-03-28 19:21:44 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 540/1251] eta: 0:07:34 lr: 0.000010 loss: 2.4217 (2.6246) grad_norm: 3.5432 (4.1092) time: 0.6304 [2021-03-28 19:21:51 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 550/1251] eta: 0:07:28 lr: 0.000010 loss: 2.6274 (2.6262) grad_norm: 3.5432 (4.1121) time: 0.6474 [2021-03-28 19:21:57 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 560/1251] eta: 0:07:21 lr: 0.000010 loss: 2.7228 (2.6297) grad_norm: 3.7246 (4.1125) time: 0.6496 [2021-03-28 19:22:04 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 570/1251] eta: 0:07:15 lr: 0.000010 loss: 2.6802 (2.6295) grad_norm: 3.7393 (4.1075) time: 0.6345 [2021-03-28 19:22:10 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 580/1251] eta: 0:07:09 lr: 0.000010 loss: 2.8268 (2.6350) grad_norm: 3.7393 (4.1095) time: 0.6314 [2021-03-28 19:22:16 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 590/1251] eta: 0:07:02 lr: 0.000010 loss: 2.8331 (2.6333) grad_norm: 4.0693 (4.1183) time: 0.6297 [2021-03-28 19:22:23 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 600/1251] eta: 0:06:56 lr: 0.000010 loss: 2.7504 (2.6351) grad_norm: 3.9626 (4.1190) time: 0.6310 [2021-03-28 19:22:29 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 610/1251] eta: 0:06:49 lr: 0.000010 loss: 2.8097 (2.6355) grad_norm: 3.9626 (4.1269) time: 0.6357 [2021-03-28 19:22:35 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 620/1251] eta: 0:06:43 lr: 0.000010 loss: 2.7873 (2.6370) grad_norm: 3.8455 (4.1216) time: 0.6329 [2021-03-28 19:22:42 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 630/1251] eta: 0:06:36 lr: 0.000010 loss: 2.7873 (2.6374) grad_norm: 3.8002 (4.1211) time: 0.6304 [2021-03-28 19:22:48 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 640/1251] eta: 0:06:30 lr: 0.000010 loss: 2.8088 (2.6403) grad_norm: 3.9110 (4.1413) time: 0.6329 [2021-03-28 19:22:54 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 650/1251] eta: 0:06:23 lr: 0.000010 loss: 2.9287 (2.6418) grad_norm: 3.7582 (4.1374) time: 0.6285 [2021-03-28 19:23:00 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 660/1251] eta: 0:06:17 lr: 0.000010 loss: 2.6470 (2.6425) grad_norm: 3.7065 (4.1313) time: 0.6299 [2021-03-28 19:23:07 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 670/1251] eta: 0:06:10 lr: 0.000010 loss: 2.5104 (2.6378) grad_norm: 3.6949 (4.1284) time: 0.6283 [2021-03-28 19:23:13 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 680/1251] eta: 0:06:04 lr: 0.000010 loss: 2.4612 (2.6381) grad_norm: 3.6949 (4.1226) time: 0.6256 [2021-03-28 19:23:19 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 690/1251] eta: 0:05:57 lr: 0.000010 loss: 2.7105 (2.6376) grad_norm: 3.8469 (4.1246) time: 0.6240 [2021-03-28 19:23:26 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 700/1251] eta: 0:05:51 lr: 0.000010 loss: 2.7094 (2.6381) grad_norm: 3.9180 (4.1186) time: 0.6309 [2021-03-28 19:23:32 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 710/1251] eta: 0:05:45 lr: 0.000010 loss: 2.7903 (2.6386) grad_norm: 3.7628 (4.1135) time: 0.6390 [2021-03-28 19:23:38 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 720/1251] eta: 0:05:38 lr: 0.000010 loss: 2.8263 (2.6390) grad_norm: 3.4891 (4.1042) time: 0.6386 [2021-03-28 19:23:45 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 730/1251] eta: 0:05:32 lr: 0.000010 loss: 2.4979 (2.6372) grad_norm: 3.4768 (4.1059) time: 0.6395 [2021-03-28 19:23:51 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 740/1251] eta: 0:05:26 lr: 0.000010 loss: 2.6867 (2.6377) grad_norm: 3.7803 (4.1014) time: 0.6428 [2021-03-28 19:23:58 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 750/1251] eta: 0:05:19 lr: 0.000010 loss: 2.7018 (2.6346) grad_norm: 3.7801 (4.0993) time: 0.6424 [2021-03-28 19:24:04 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 760/1251] eta: 0:05:13 lr: 0.000010 loss: 2.7399 (2.6366) grad_norm: 4.0511 (4.1112) time: 0.6334 [2021-03-28 19:24:10 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 770/1251] eta: 0:05:06 lr: 0.000010 loss: 2.7914 (2.6372) grad_norm: 3.8621 (4.1069) time: 0.6297 [2021-03-28 19:24:16 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 780/1251] eta: 0:05:00 lr: 0.000010 loss: 2.7243 (2.6368) grad_norm: 3.5398 (4.1047) time: 0.6286 [2021-03-28 19:24:23 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 790/1251] eta: 0:04:53 lr: 0.000010 loss: 2.5058 (2.6364) grad_norm: 3.5483 (4.0989) time: 0.6264 [2021-03-28 19:24:29 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 800/1251] eta: 0:04:47 lr: 0.000010 loss: 2.4708 (2.6352) grad_norm: 3.8262 (4.1051) time: 0.6311 [2021-03-28 19:24:35 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 810/1251] eta: 0:04:41 lr: 0.000010 loss: 2.6353 (2.6374) grad_norm: 3.7691 (4.1003) time: 0.6340 [2021-03-28 19:24:42 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 820/1251] eta: 0:04:34 lr: 0.000010 loss: 2.6353 (2.6355) grad_norm: 3.5954 (4.0953) time: 0.6365 [2021-03-28 19:24:48 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 830/1251] eta: 0:04:28 lr: 0.000010 loss: 2.6525 (2.6373) grad_norm: 3.8987 (4.1000) time: 0.6353 [2021-03-28 19:24:54 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 840/1251] eta: 0:04:21 lr: 0.000010 loss: 2.7791 (2.6376) grad_norm: 4.1807 (4.1011) time: 0.6306 [2021-03-28 19:25:01 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 850/1251] eta: 0:04:15 lr: 0.000010 loss: 2.6306 (2.6362) grad_norm: 3.4104 (4.0982) time: 0.6315 [2021-03-28 19:25:07 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 860/1251] eta: 0:04:09 lr: 0.000010 loss: 2.6059 (2.6371) grad_norm: 3.5444 (4.0985) time: 0.6347 [2021-03-28 19:25:14 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 870/1251] eta: 0:04:02 lr: 0.000010 loss: 2.6566 (2.6365) grad_norm: 3.5060 (4.0949) time: 0.6388 [2021-03-28 19:25:20 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 880/1251] eta: 0:03:56 lr: 0.000010 loss: 2.6566 (2.6358) grad_norm: 3.4674 (4.0878) time: 0.6376 [2021-03-28 19:25:26 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 890/1251] eta: 0:03:50 lr: 0.000010 loss: 2.5270 (2.6346) grad_norm: 3.5373 (4.0851) time: 0.6362 [2021-03-28 19:25:33 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 900/1251] eta: 0:03:43 lr: 0.000010 loss: 2.6491 (2.6356) grad_norm: 4.0611 (4.0843) time: 0.6312 [2021-03-28 19:25:39 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 910/1251] eta: 0:03:37 lr: 0.000010 loss: 2.6836 (2.6350) grad_norm: 4.1149 (4.0857) time: 0.6262 [2021-03-28 19:25:45 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 920/1251] eta: 0:03:30 lr: 0.000010 loss: 2.6370 (2.6337) grad_norm: 3.6545 (4.0816) time: 0.6326 [2021-03-28 19:25:51 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 930/1251] eta: 0:03:24 lr: 0.000010 loss: 2.6622 (2.6344) grad_norm: 3.7438 (4.0825) time: 0.6308 [2021-03-28 19:25:58 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 940/1251] eta: 0:03:18 lr: 0.000010 loss: 2.6495 (2.6317) grad_norm: 3.7438 (4.0768) time: 0.6260 [2021-03-28 19:26:04 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 950/1251] eta: 0:03:11 lr: 0.000010 loss: 2.5794 (2.6303) grad_norm: 3.5456 (4.0715) time: 0.6319 [2021-03-28 19:26:10 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 960/1251] eta: 0:03:05 lr: 0.000010 loss: 2.6073 (2.6297) grad_norm: 3.7688 (4.0750) time: 0.6336 [2021-03-28 19:26:17 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 970/1251] eta: 0:02:58 lr: 0.000010 loss: 2.6073 (2.6294) grad_norm: 3.9848 (4.0755) time: 0.6335 [2021-03-28 19:26:23 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 980/1251] eta: 0:02:52 lr: 0.000010 loss: 2.5798 (2.6291) grad_norm: 3.6984 (4.0722) time: 0.6323 [2021-03-28 19:26:30 swin_base_patch4_window7_224] INFO: Epoch: [299] [ 990/1251] eta: 0:02:46 lr: 0.000010 loss: 2.5825 (2.6282) grad_norm: 3.5181 (4.0679) time: 0.6395 [2021-03-28 19:26:36 swin_base_patch4_window7_224] INFO: Epoch: [299] [1000/1251] eta: 0:02:39 lr: 0.000010 loss: 2.5510 (2.6266) grad_norm: 3.5389 (4.0650) time: 0.6345 [2021-03-28 19:26:42 swin_base_patch4_window7_224] INFO: Epoch: [299] [1010/1251] eta: 0:02:33 lr: 0.000010 loss: 2.7231 (2.6286) grad_norm: 3.4724 (4.0572) time: 0.6287 [2021-03-28 19:26:48 swin_base_patch4_window7_224] INFO: Epoch: [299] [1020/1251] eta: 0:02:27 lr: 0.000010 loss: 2.8311 (2.6299) grad_norm: 3.5044 (4.0566) time: 0.6352 [2021-03-28 19:26:55 swin_base_patch4_window7_224] INFO: Epoch: [299] [1030/1251] eta: 0:02:20 lr: 0.000010 loss: 2.7411 (2.6308) grad_norm: 4.1234 (4.0628) time: 0.6327 [2021-03-28 19:27:01 swin_base_patch4_window7_224] INFO: Epoch: [299] [1040/1251] eta: 0:02:14 lr: 0.000010 loss: 2.5688 (2.6291) grad_norm: 4.1234 (4.0606) time: 0.6272 [2021-03-28 19:27:07 swin_base_patch4_window7_224] INFO: Epoch: [299] [1050/1251] eta: 0:02:07 lr: 0.000010 loss: 2.3477 (2.6283) grad_norm: 3.7405 (4.0707) time: 0.6254 [2021-03-28 19:27:14 swin_base_patch4_window7_224] INFO: Epoch: [299] [1060/1251] eta: 0:02:01 lr: 0.000010 loss: 2.6203 (2.6278) grad_norm: 3.7405 (4.0734) time: 0.6286 [2021-03-28 19:27:20 swin_base_patch4_window7_224] INFO: Epoch: [299] [1070/1251] eta: 0:01:55 lr: 0.000010 loss: 2.5752 (2.6269) grad_norm: 3.7296 (4.0716) time: 0.6333 [2021-03-28 19:27:26 swin_base_patch4_window7_224] INFO: Epoch: [299] [1080/1251] eta: 0:01:48 lr: 0.000010 loss: 2.5752 (2.6259) grad_norm: 3.7296 (4.0733) time: 0.6365 [2021-03-28 19:27:33 swin_base_patch4_window7_224] INFO: Epoch: [299] [1090/1251] eta: 0:01:42 lr: 0.000010 loss: 2.6215 (2.6266) grad_norm: 3.6159 (4.0707) time: 0.6289 [2021-03-28 19:27:39 swin_base_patch4_window7_224] INFO: Epoch: [299] [1100/1251] eta: 0:01:36 lr: 0.000010 loss: 2.7387 (2.6274) grad_norm: 3.3618 (4.0644) time: 0.6259 [2021-03-28 19:27:45 swin_base_patch4_window7_224] INFO: Epoch: [299] [1110/1251] eta: 0:01:29 lr: 0.000010 loss: 2.8778 (2.6276) grad_norm: 3.3967 (4.0723) time: 0.6360 [2021-03-28 19:27:52 swin_base_patch4_window7_224] INFO: Epoch: [299] [1120/1251] eta: 0:01:23 lr: 0.000010 loss: 2.6363 (2.6261) grad_norm: 3.7042 (4.0691) time: 0.6346 [2021-03-28 19:27:58 swin_base_patch4_window7_224] INFO: Epoch: [299] [1130/1251] eta: 0:01:16 lr: 0.000010 loss: 2.7402 (2.6266) grad_norm: 3.5051 (4.0628) time: 0.6339 [2021-03-28 19:28:04 swin_base_patch4_window7_224] INFO: Epoch: [299] [1140/1251] eta: 0:01:10 lr: 0.000010 loss: 2.7718 (2.6257) grad_norm: 3.6229 (4.0609) time: 0.6330 [2021-03-28 19:28:11 swin_base_patch4_window7_224] INFO: Epoch: [299] [1150/1251] eta: 0:01:04 lr: 0.000010 loss: 2.8247 (2.6269) grad_norm: 3.7755 (4.0590) time: 0.6314 [2021-03-28 19:28:17 swin_base_patch4_window7_224] INFO: Epoch: [299] [1160/1251] eta: 0:00:57 lr: 0.000010 loss: 2.8856 (2.6272) grad_norm: 3.7673 (4.0600) time: 0.6298 [2021-03-28 19:28:23 swin_base_patch4_window7_224] INFO: Epoch: [299] [1170/1251] eta: 0:00:51 lr: 0.000010 loss: 2.8043 (2.6283) grad_norm: 3.8260 (4.0693) time: 0.6262 [2021-03-28 19:28:29 swin_base_patch4_window7_224] INFO: Epoch: [299] [1180/1251] eta: 0:00:45 lr: 0.000010 loss: 2.8043 (2.6283) grad_norm: 3.7714 (4.0664) time: 0.6316 [2021-03-28 19:28:36 swin_base_patch4_window7_224] INFO: Epoch: [299] [1190/1251] eta: 0:00:38 lr: 0.000010 loss: 2.4226 (2.6254) grad_norm: 3.4794 (4.0630) time: 0.6339 [2021-03-28 19:28:42 swin_base_patch4_window7_224] INFO: Epoch: [299] [1200/1251] eta: 0:00:32 lr: 0.000010 loss: 2.3134 (2.6239) grad_norm: 3.6042 (4.0634) time: 0.6363 [2021-03-28 19:28:48 swin_base_patch4_window7_224] INFO: Epoch: [299] [1210/1251] eta: 0:00:26 lr: 0.000010 loss: 2.5499 (2.6243) grad_norm: 3.7809 (4.0631) time: 0.6345 [2021-03-28 19:28:55 swin_base_patch4_window7_224] INFO: Epoch: [299] [1220/1251] eta: 0:00:19 lr: 0.000010 loss: 2.7411 (2.6245) grad_norm: 3.7853 (4.0618) time: 0.6344 [2021-03-28 19:29:01 swin_base_patch4_window7_224] INFO: Epoch: [299] [1230/1251] eta: 0:00:13 lr: 0.000010 loss: 2.7767 (2.6264) grad_norm: 3.7957 (4.0665) time: 0.6339 [2021-03-28 19:29:07 swin_base_patch4_window7_224] INFO: Epoch: [299] [1240/1251] eta: 0:00:06 lr: 0.000010 loss: 2.7767 (2.6259) grad_norm: 3.6788 (4.0619) time: 0.6234 [2021-03-28 19:29:13 swin_base_patch4_window7_224] INFO: Epoch: [299] [1250/1251] eta: 0:00:00 lr: 0.000010 loss: 2.6957 (2.6281) grad_norm: 3.5019 (4.0592) time: 0.6164 [2021-03-28 19:30:34 swin_base_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:04 loss: 0.6758 (0.6758) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-28 19:30:36 swin_base_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.6827 (0.7468) acc1: 82.8125 (83.0966) acc5: 96.8750 (97.1591) [2021-03-28 19:30:37 swin_base_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.6995 (0.7237) acc1: 82.8125 (83.4821) acc5: 96.8750 (97.2470) [2021-03-28 19:30:39 swin_base_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7442 (0.7506) acc1: 81.2500 (82.5605) acc5: 96.8750 (96.6230) [2021-03-28 19:30:40 swin_base_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7598 (0.7376) acc1: 81.2500 (82.6982) acc5: 96.8750 (96.8369) [2021-03-28 19:30:41 swin_base_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7663 (0.7547) acc1: 81.2500 (82.3040) acc5: 96.8750 (96.5120) [2021-03-28 19:30:54 swin_base_patch4_window7_224] INFO: * Acc@1 83.476 Acc@5 96.468 loss 0.739 [2021-03-28 19:30:54 swin_base_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.5% [2021-03-28 19:30:54 swin_base_patch4_window7_224] INFO: Max accuracy: 83.48%