Training Flair Few Shot Learning Model Results in an OSError Related to Model Loading

Question

When I am creating a few shot learning model by finetuning tars-base, the model crashes after training without saving to my local drive like it's supposed to. The training completed all epochs before crashing. The same code has worked in the past.

Code:

# 1. what label do you want to predict?
label_type = 'label'

# 2. make a label dictionary
label_dict = corpus.make_label_dictionary(label_type=label_type)

# 3. start from our existing TARS base model for English
tars = TARSClassifier.load("tars-base")

# 4. switch to a new task (TARS can do multiple tasks so you must define one)
tars.add_and_switch_to_new_task(task_name="classification",
                                label_dictionary=label_dict,
                                label_type=label_type,
                                )

# 5. initialize the text classifier trainer
trainer = ModelTrainer(tars, corpus)

# 6. start the training
trainer.train(base_path='../example_data/models/few_shot_model_flair',  # path to store the model artifacts
              learning_rate=0.02,  # use very small learning rate
              mini_batch_size=1,
              max_epochs=20,  # terminate after 20 epochs
              patience=1
              )

Error:

HTTPError                                 Traceback (most recent call last)
File ~/Documents/env/lib/python3.9/site-packages/huggingface_hub/utils/_errors.py:213, in hf_raise_for_status(response, endpoint_name)
    212 try:
--> 213     response.raise_for_status()
    214 except HTTPError as e:

File ~/Documents/env/lib/python3.9/site-packages/requests/models.py:1021, in Response.raise_for_status(self)
   1020 if http_error_msg:
-> 1021     raise HTTPError(http_error_msg, response=self)

HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/None/resolve/main/tokenizer_config.json

The above exception was the direct cause of the following exception:

RepositoryNotFoundError                   Traceback (most recent call last)
File ~/Documents/env/lib/python3.9/site-packages/transformers/utils/hub.py:409, in cached_file(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, use_auth_token, revision, local_files_only, subfolder, user_agent, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash)
    407 try:
    408     # Load from URL or cache if already cached
--> 409     resolved_file = hf_hub_download(
    410         path_or_repo_id,
    411         filename,
    412         subfolder=None if len(subfolder) == 0 else subfolder,
    413         revision=revision,
    414         cache_dir=cache_dir,
...
    434         f"'https://huggingface.co/{path_or_repo_id}' for available revisions."
    435     )

OSError: None is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo with `use_auth_token` or log in with `huggingface-cli login` and pass `use_auth_token=True`.

Flair 0.12.1

Pytorch 1.13.1

Transformers 4.25.1

Training Flair Few Shot Learning Model Results in an OSError Related to Model Loading

0 Answers0