New issue

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

#

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

Already on GitHub? # to your account

Jump to bottom

Low score during training extractor #1

Open

2001092236 opened this issue Jul 14, 2022 · 0 comments

2001092236 commented Jul 14, 2022 •

edited

Loading

I used your dataset ('Keywords Extractor Dataset') to train the extractor.

After the training (it takes 300,000 steps) I evaluated the precision, recall and f1 predictions on the test dataset.

The model showed a very low score:
precision: 0.001
recall: 0.0005
f1: 0.04

rouge-1: 0.23
rouge-2: 0.04
rouge-l: 0.24

Hyperparameters wasn't changed.

Could you please explain how to achieve the same results in your paper?
Maybe I should use other hyperparameters?

# for free to join this conversation on GitHub. Already have an account? # to comment