Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Bugfix/bi attention mask #12

Merged
merged 3 commits into from
May 31, 2024
Merged

Bugfix/bi attention mask #12

merged 3 commits into from
May 31, 2024

Conversation

SeanLee97
Copy link
Contributor

  • fix bug: attention_mask=None
  • upgrade transformers

@SeanLee97
Copy link
Contributor Author

The results is satisfied, below is the first epoch training on conll23:

{'eval_loss': 0.09728734195232391, 'eval_precision': 0.9292478113274969, 'eval_recall': 0.9364422038170688, 'eval_f1': 0.9328311362209667, 'eval_accuracy': 0.9861776229865041, 'eval_runtime': 59.9648, 'eval_samples_per_second': 57.584, 'eval_steps_per_second': 7.204, 'epoch': 1.0}

@SeanLee97 SeanLee97 merged commit 8688388 into main May 31, 2024
8 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant