-
Notifications
You must be signed in to change notification settings - Fork 62
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.
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
NeuronORPOTrainer #719
NeuronORPOTrainer #719
Conversation
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
@michaelbenayoun the CI is failing with your changes: can you check what went wrong so that we can start reviewing the pull-request ? |
I did not add tests so I do not think it is related. I will still check. For now I am debugging NaN loss when |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the pull-request ! LGTM, but I would like the changes to the original trl code to appear more clearly.
Can I merge? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, thanks !
What does this PR do?
Adds initial support for the ORPOTRainer but without parallelism support.