Segmentation fault (core dumped)

[koanatakiyo]

Hello,

I got the error message Segmentation fault (core dumped) all the time when I am trying to run the ITA model for all three datasets.

Here are the full log messages:
CUDA_VISIBLE_DEVICES=0 python train.py --config config/xlmr-large-first_10epoch_1batch_4accumulate_0.000005lr_10000lrrate_en_monolingual_crf_fast_norelearn_sentbatch_sentloss_nodev_finetune_snap_doc_joint_multiview_posterior_4temperature_captionobj_classattr_vinvl_ocr_ner24.yaml
/home/xxx/microF1base/KB-NER/flair/utils/params.py:104: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
dict_merge.dict_merge(params_dict, yaml.load(f))
2023-06-27 03:04:02,031 Reading data from ITA/datasets/snap
2023-06-27 03:04:02,031 Train: ITA/datasets/snap/train.txt
2023-06-27 03:04:02,031 Dev: ITA/datasets/snap/dev.txt
2023-06-27 03:04:02,031 Test: ITA/datasets/snap/test.txt
2023-06-27 03:04:03,014 Reading data from ITA/datasets/snap_doc_caption_vinvl_classattr_ocr
2023-06-27 03:04:03,014 Train: ITA/datasets/snap_doc_caption_vinvl_classattr_ocr/train.txt
2023-06-27 03:04:03,014 Dev: ITA/datasets/snap_doc_caption_vinvl_classattr_ocr/dev.txt
2023-06-27 03:04:03,014 Test: ITA/datasets/snap_doc_caption_vinvl_classattr_ocr/test.txt
2023-06-27 03:04:13,532 {b'': 0, b'O': 1, b'S-ORG': 2, b'S-MISC': 3, b'B-ORG': 4, b'I-ORG': 5, b'E-ORG': 6, b'B-PER': 7, b'E-PER': 8, b'S-PER': 9, b'B-MISC': 10, b'I-MISC': 11, b'E-MISC': 12, b'S-LOC': 13, b'B-LOC': 14, b'E-LOC': 15, b'I-LOC': 16, b'I-PER': 17, b'S-X': 18, b'': 19, b'': 20}
2023-06-27 03:04:13,532 Corpus: 8580 train + 2864 dev + 2918 test sentences
Segmentation fault (core dumped)

It happens to all three datasets. Any idea how to fix the issues? Thank you so much in advance.

[koanatakiyo]

There is no instruction on the version of Python and there is no version 7.1.2 for nltk.

I installed python==3.7.15 and nltk==3.5. Other packages were installed strictly based on the requirement.

[andrew6072]

I have the same issue. Did you firgure out how to fix it yet?

[Neva1213]

我也遇到了相同的问题，请问你们解决了吗