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

训练时loss一直为0 #21

Open
FWLamb opened this issue Feb 10, 2025 · 5 comments
Open

训练时loss一直为0 #21

FWLamb opened this issue Feb 10, 2025 · 5 comments

Comments

@FWLamb
Copy link

FWLamb commented Feb 10, 2025

拉去训练任务后，loss一直为0，会是什么原因导致的呢？

Image
@lllfx
Copy link

lllfx commented Feb 10, 2025

我复现也是这样的。

Image

@FWLamb
Copy link
Author

FWLamb commented Feb 10, 2025

我复现也是这样的。

Image

推理有效果吗？

@lllfx
Copy link

lllfx commented Feb 10, 2025

我复现也是这样的。
Image

推理有效果吗？

没效果，训练后变差了

@anine09
Copy link
Contributor

anine09 commented Feb 10, 2025

其实我也没有什么头绪，我自己遇到了类似的情况，前90步loss一直为0，我们还在讨论

@anine09
Copy link
Contributor

anine09 commented Feb 10, 2025

或许可以参考 huggingface/trl#2703 (comment)

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
@lllfx @anine09 @FWLamb