代码训练时报错

[dbbice]

python3 main.py -dataset WN18RR \

              -batch_size 128 \
              -pretrained_model bert-large-uncased \
              -desc_max_length 40 \
              -lr 5e-4 \
              -prompt_length 10 \
              -alpha 0.1 \
              -n_lar 8 \
              -label_smoothing 0.1 \
              -embed_dim 144 \
              -k_w 12 \
              -k_h 12 \
              -alpha_step 0.00001

Traceback (most recent call last): File "/home/wsco/anaconda3/envs/env_DRE/lib/python3.6/site-packages/transformers/configuration_utils.py", line 604, in _get_config_dict user_agent=user_agent, File "/home/wsco/anaconda3/envs/env_DRE/lib/python3.6/site-packages/transformers/utils/hub.py", line 290, in cached_path local_files_only=local_files_only, File "/home/wsco/anaconda3/envs/env_DRE/lib/python3.6/site-packages/transformers/utils/hub.py", line 546, in get_from_cache "Connection error, and we cannot find the requested files in the cached path." ValueError: Connection error, and we cannot find the requested files in the cached path. Please try again or make sure your Internet connection is on.

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "main.py", line 176, in configs.vocab_size = AutoConfig.from_pretrained(configs.pretrained_model).vocab_size File "/home/wsco/anaconda3/envs/env_DRE/lib/python3.6/site-packages/transformers/models/auto/configuration_auto.py", line 652, in from_pretrained configdict, = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, kwargs) File "/home/wsco/anaconda3/envs/env_DRE/lib/python3.6/site-packages/transformers/configuration_utils.py", line 548, in get_config_dict config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, kwargs) File "/home/wsco/anaconda3/envs/env_DRE/lib/python3.6/site-packages/transformers/configuration_utils.py", line 630, in _get_config_dict f"We couldn't connect to '{HUGGINGFACE_CO_RESOLVE_ENDPOINT}' to load this model, couldn't find it in the cached " OSError: We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it looks like bert-large-uncased is not the path to a directory containing a {configuration_file} file. Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/transformers/installation#offline-mode'.

—————————————————— 您好~请问这个问题应该怎么解决

[chenchens190009]

Hi @dbbice,

Thank you for your attention.

This is obviously an internet connection issue. The code will donwload the bert model on huggingface hub before training. Please try this snippet on your server to verify you can reach huggingface hub.

from transformers import AutoConfig
vocab_size = AutoConfig.from_pretrained('bert-base-uncased').vocab_size