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.

Sign up for GitHub

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

Jump to bottom

f1 score became 0 #1

Open

huge-melon opened this issue Jun 12, 2020 · 1 comment

huge-melon commented Jun 12, 2020

Why f1 score falls to zero when I'm training the model. Do you have some idea?

Owner

ThanhDucPham commented Jun 12, 2020 •

edited

Loading

Hi, I have encountered with this problem, I think we have some reasons:

Our model need more epoch to learn about these label difference to "O" label. Then, let's try more epoch.
In this repos, I use Adadelta optimizer according to the original paper, but as I know, Adadelta converge very slow, so try Adam optimizer. It work for me with this repos: https://github.com/ThanhDucPham/Event-Detection-and-Domain-Adaptation-with-Convolutional-Neural-Networks/blob/master/model.py

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment