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

No clip to loss within Qwen2VLGRPOTrainer #21

Open
Vincex0 opened this issue Feb 21, 2025 · 0 comments
Open

No clip to loss within Qwen2VLGRPOTrainer #21

Vincex0 opened this issue Feb 21, 2025 · 0 comments

Comments

@Vincex0
Copy link

Vincex0 commented Feb 21, 2025

Hey in the original paper there is a clip term that I don't see here, during training the grad norm can sometimes be pretty high, leading to instability
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
1 participant
@Vincex0