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.

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

Loss is #21

Open
HuaYuexia opened this issue Feb 3, 2024 · 4 comments
Open

Loss is #21

HuaYuexia opened this issue Feb 3, 2024 · 4 comments

Comments

@HuaYuexia
Copy link

No description provided.

@HuaYuexia
Copy link
Author

Loss is nan
image

@AmingWu
Copy link
Owner

AmingWu commented Feb 3, 2024

The learning rate is set to 0.001. And the batchsize is set to 4. Welcome to communicate with me. Thanks.

@HuaYuexia
Copy link
Author

HuaYuexia commented Feb 5, 2024 •
edited
Loading

The learning rate is set to 0.001. And the batchsize is set to 4. Welcome to communicate with me. Thanks.

My learning rate is set to 0.001 too.The difference is that I used two gpus with a batch size of 8.The only way to get it to work properly is to reduce the learning rate to 1e-5, but then it won't converge, why is that?Sincerely look forward to your guidance, although this may be a naive question for you.

@xiao-song2022
Copy link

Thank you for your reply. The problem has been successfully resolved.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@AmingWu @xiao-song2022 @HuaYuexia