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

difference on loss between two fit() #506

Open

ZongyuWu97 opened this issue Dec 22, 2024 · 0 comments

ZongyuWu97 commented Dec 22, 2024

I did a fit to my model and another fit on the next line. But the loss is different

Here you can see that after 1000 steps the loss is 3.6e-6

But when I starts another 1000 steps, the loss begin from 1.5e-5 which is not inheriting from the loss above.

Do I need to manually save and load the parameters between two fit()?

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