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

Quality after 20 epoch training #15

Open
thanhnew2001 opened this issue Jan 18, 2024 · 2 comments
Open

Quality after 20 epoch training #15

thanhnew2001 opened this issue Jan 18, 2024 · 2 comments

Comments

@thanhnew2001
Copy link

Hello, I tried your script and the resulting model took about 10 hours to train on single 3060 but the quality is still not very good. How could I improve it?

@thanhnew2001
Copy link
Author

image image image

@F4k3r22
Copy link

F4k3r22 commented Jul 11, 2024

Increase the batch size to 16 or 32, the epochs maybe to 25 or 30, increase the sq_len to 512 or 1024, the d_model to 768 or 1024. And make other options that you can modify in the config.py to improve the model. I hope I have helped you :b

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

2 participants