Fine-tuning a model on a token classification task

When training my Token-Classification model i get this error:

HTTPError: 400 Client Error: Bad Request for url: https://huggingface.co/api/repos/create - Only regular characters and ‘-’, ‘_’, ‘.’ are accepted. ‘–’ and ‘…’ are forbidden. ‘-’ and ‘.’ cannot start or end the name. The name cannot end with “.git”. Max length is 96.

I use the Notebook for Token-Classification on: model_checkpoint = “tbosse/bert-base-german-cased-finetuned-subj_preTrained_with_noisyData”

The error happens when trying to pass everything to a Trainer:

trainer = Trainer(
    model,
    args,
    train_dataset=tokenized_datasets["train"],
    eval_dataset=tokenized_datasets["validation"],
    data_collator=data_collator,
    tokenizer=tokenizer,
    compute_metrics=compute_metrics
)
---------------------------------------------------------------------------
HTTPError                                 Traceback (most recent call last)
<ipython-input-55-d8301846d702> in <module>()
      6     data_collator=data_collator,
      7     tokenizer=tokenizer,
----> 8     compute_metrics=compute_metrics
      9 )

7 frames
/usr/local/lib/python3.7/dist-packages/requests/models.py in raise_for_status(self)
    939 
    940         if http_error_msg:
--> 941             raise HTTPError(http_error_msg, response=self)
    942 
    943     def close(self):

There seems to be a similar Topic:

Fine-tune a model on translation: - Beginners - Hugging Face Forums

I already tried removing the “/” from the model_checkpoint, that only created different errors.

Welcome to Hugging Face Forum :hugs:

I checked on Hub and saw you were able to create repository which was your problem. Was it solved?

No, i still have the same problem. Those repositories were created when changing the model_checkpoint to “bert-base-german-cased”, to see if that seemed to be the problem.

The issue is resolved. I changed the name in TrainingArguments to make sure there is no “/” in the name and now it works.