Closed hjing100 closed 1 year ago
CUDA Version: 12.0
升级torch和torchvision版本:
torch 1.10.1
torchvision 0.11.2
运行显示:
Evaluating: 0%| | 0/15000 [00:00<?, ?it/s]
Traceback (most recent call last):
File "cli.py", line 284, in
解决方法: conda install pytorch torchvision cudatoolkit=11.3 -c pytorch
执行: python3 cli.py \ --method pet \ --pattern_ids 0 1 2 3 4 \ --data_dir ag_news_csv \ --model_type albert \ --model_name_or_path albert-xxlarge-v2 \ --task_name agnews \ --output_dir output \ --do_train \ --do_eval \ --pet_per_gpu_train_batch_size 2 \ --pet_gradient_accumulation_steps 8 \ --pet_max_steps 250 \ --sc_per_gpu_unlabeled_batch_size 2 \ --sc_gradient_accumulation_steps 8 \ --sc_max_steps 5000 有报错: Evaluating: 0%| | 0/15000 [00:00<?, ?it/s] Traceback (most recent call last): File "cli.py", line 282, in
main()
File "cli.py", line 263, in main
no_distillation=args.no_distillation, seed=args.seed)
File "/home/123456/projects/prompt/pet-master/pet/modeling.py", line 249, in train_pet
save_unlabeled_logits=not no_distillation, seed=seed)
File "/home/123456/projects/prompt/pet-master/pet/modeling.py", line 355, in train_pet_ensemble
unlabeled_data=unlabeled_data))
File "/home/123456/projects/prompt/pet-master/pet/modeling.py", line 434, in train_single_model
results_dict['train_set_before_training'] = evaluate(model, train_data, eval_config)['scores']['acc']
File "/home/123456/projects/prompt/pet-master/pet/modeling.py", line 490, in evaluate
n_gpu=config.n_gpu, decoding_strategy=config.decoding_strategy, priming=config.priming)
File "/home/123456/projects/prompt/pet-master/pet/wrapper.py", line 376, in eval
logits = EVALUATION_STEP_FUNCTIONSself.config.wrapper_type(batch)
File "/home/123456/projects/prompt/pet-master/pet/wrapper.py", line 524, in mlm_eval_step
outputs = self.model(inputs)
File "/home/123456/.conda/envs/python36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, *kwargs)
File "/home/123456/.conda/envs/python36/lib/python3.6/site-packages/transformers/modeling_albert.py", line 814, in forward
output_hidden_states=output_hidden_states,
File "/home/123456/.conda/envs/python36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(input, kwargs)
File "/home/123456/.conda/envs/python36/lib/python3.6/site-packages/transformers/modeling_albert.py", line 563, in forward
output_hidden_states=output_hidden_states,
File "/home/123456/.conda/envs/python36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, *kwargs)
File "/home/123456/.conda/envs/python36/lib/python3.6/site-packages/transformers/modeling_albert.py", line 327, in forward
hidden_states = self.embedding_hidden_mapping_in(hidden_states)
File "/home/123456/.conda/envs/python36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(input, **kwargs)
File "/home/123456/.conda/envs/python36/lib/python3.6/site-packages/torch/nn/modules/linear.py", line 87, in forward
return F.linear(input, self.weight, self.bias)
File "/home/123456/.conda/envs/python36/lib/python3.6/site-packages/torch/nn/functional.py", line 1612, in linear
output = input.matmul(weight.t())
RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling
cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)