when I run the shell,hava a CUDA error to me. it will runing on a right status if i use cpu.

[WavesLi]

python3 run_classifier_word.py --task_name NEWS --do_train --do_eval --data_dir $GLUE_DIR/ --vocab_file $BERT_BASE_DIR/vocab.txt --bert_config_file $BERT_BASE_DIR/bert_config.json --init_checkpoint $BERT_BASE_DIR/pytorch_model.bin --max_seq_length 256 --train_batch_size 24 --learning_rate 2e-5 --num_train_epochs 50.0 --output_dir ./newsAll_output/ --local_rank 3
04/16/2019 16:33:35 - INFO - main - device cuda:3 n_gpu 1 distributed training True
04/16/2019 16:33:35 - INFO - main - LOOKING AT /home/gpu0/Litao/Bert/Bert-Pytorch-Chinese-TextClassification/Corpus/train.tsv
label_list.size:10

Traceback (most recent call last):
File "run_classifier_word.py", line 704, in
main()
File "run_classifier_word.py", line 559, in main
model.to(device)
File "/opt/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 381, in to
return self._apply(convert)
File "/opt/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 187, in _apply
module._apply(fn)
File "/opt/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 187, in _apply
module._apply(fn)
File "/opt/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 187, in _apply
module._apply(fn)
File "/opt/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 193, in _apply
param.data = fn(param.data)
File "/opt/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 379, in convert
return t.to(device, dtype if t.is_floating_point() else None, non_blocking)
RuntimeError: CUDA error: invalid device ordinal

[WavesLi]

@xieyufei1993 I guess this question because my GPU is too small to run the shell.Can you tell me about you GPU's memory?

[zhanlaoban]

@WavesLi I guess you only have one GPU in your PC, and that the parameter local_rank is 3 is not for you. So setting local_rank default which is -1 will work.

[bruce0715]

@xieyufei1993 I guess this question because my GPU is too small to run the shell.Can you tell me about you GPU's memory?

My GPU is 2080 ti 11GB, but it still out of memory...

[WavesLi]

You need a smaller batch.

…

---Original--- From: "Bruce Zhu"<notifications@github.com> Date: Tue, Jul 23, 2019 07:05 AM To: "xieyufei1993/Bert-Pytorch-Chinese-TextClassification"<Bert-Pytorch-Chinese-TextClassification@noreply.github.com>; Cc: "Mention"<mention@noreply.github.com>;"WavesLi"<2585441465@qq.com>; Subject: Re: [xieyufei1993/Bert-Pytorch-Chinese-TextClassification] when I run the shell,hava a CUDA error to me. it will runing on a right status if i use cpu. (#2) @xieyufei1993 I guess this question because my GPU is too small to run the shell.Can you tell me about you GPU's memory? My GPU is 2080 ti 11GB, but it still out of memory... — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.