-
Notifications
You must be signed in to change notification settings - Fork 610
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
I have tried training multiple times, but NaN keeps occurring consistently. #142
Comments
i solve |
I met the same problem. Can you tell me how to solve this issue? Thanks a lot. |
set the lr to 1e-6 may help. |
change adam_epsilon to 1e-4. |
Is there any better training effect? The training results here are not as good as the original weights. |
I want to train this code on my own dataset. What is the minimum GPU and Ram requirements??? |
58G gpu |
I continuously train multiple times, but NaN occurs. I haven't changed the training parameters, but NaN appears in the loss during training. What could be the problem?
The text was updated successfully, but these errors were encountered: