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

No f1, precision and recall scores during training #63

Open
adap7 opened this issue Jul 17, 2024 · 0 comments
Open

No f1, precision and recall scores during training #63

adap7 opened this issue Jul 17, 2024 · 0 comments

Comments

@adap7
Copy link

adap7 commented Jul 17, 2024

I am currently training a model:
encoder_id = "bert-base-cased"
model = SpanMarkerModel.from_pretrained(
encoder_id,
labels=labels,
model_max_length=512,
entity_max_length=512,
marker_max_length=256
)
During the training process, only the overall accuracy is displayed, but no additional metrics are provided (f1, recall and precision are 0), Training Loss and Validation Loss seem to be improving, but overall accuracy is also constant throughout training. When evaluating on the test set the same problem appears, f1, precision and recall are 0, overall accuracy is the same as for training. As I am new to this, I am unsure if this is expected behavior. The size of my training set is 329 for training and 219 for testing.

Request:
Could you please provide guidance on whether this is the expected behavior and, if not, how to obtain additional metrics during the training process? Thank you for your assistance.

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

No branches or pull requests

1 participant