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

code run stop early at 40 epochs #14

Open
lee29321 opened this issue Feb 1, 2024 · 0 comments
Open

code run stop early at 40 epochs #14

lee29321 opened this issue Feb 1, 2024 · 0 comments

Comments

@lee29321
Copy link

lee29321 commented Feb 1, 2024

I am running the script with real device 1T1R with Ag:a-Si case.
I am trying to run the training to the 125 epochs. After I compile the code and run, the output would stop at 35-40 epochs without sending any error message. The accuracy until the end of the epoch is expected.

I have tried to reduce the batch size or change the learning rate. However, it doesn't solve the problem and the accuracy went low to 50%. I also tried to change the learning rate of alpha and beta, however, the total epochs still maintains 38-40 epochs.

Could you please let me know how to change the condition to make the code run for 125 epochs?

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