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

Weighted Cross Entropy Loss #404

Open
winglian opened this issue Nov 21, 2024 · 4 comments · Fixed by #420
Open

Weighted Cross Entropy Loss #404

winglian opened this issue Nov 21, 2024 · 4 comments · Fixed by #420

Comments

@winglian
Copy link
Contributor

🚀 The feature, motivation and pitch

Allow for passing a weighting tensor to weight the CEL similar to C-RLFT where some tokens or inputs in the batch may have lower weighting to the overall loss. see https://arxiv.org/abs/2309.11235

Alternatives

No response

Additional context

No response
@pramodith
Copy link
Collaborator

#take I can work on this next week.

@ByronHsu
Copy link
Collaborator

@pramodith any updates?

@pramodith
Copy link
Collaborator

@ByronHsu sorry been busy with some personal stuff, I'll have this ready by Friday at the latest.

This was referenced Dec 2, 2024
Closed
Merged
@Tcc0403 Tcc0403 reopened this Dec 29, 2024
@Tcc0403
Copy link
Collaborator

Tcc0403 commented Dec 29, 2024

Todo: sample/token level weight

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
4 participants
@winglian @pramodith @ByronHsu @Tcc0403