-
Notifications
You must be signed in to change notification settings - Fork 1.2k
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
[Judges] use the pair-judges in online-preference trainers #2243
base: main
Are you sure you want to change the base?
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. |
@kashif can you also add an example in the online dpo documentation? And a test? |
working on test thanks! |
Co-authored-by: Quentin Gallouédec <[email protected]>
Co-authored-by: Quentin Gallouédec <[email protected]>
self.processing_class.decode(ids[:context_length], skip_special_tokens=True) | ||
for ids in prompt_completion_ids[:num_examples] | ||
] |
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.
can we use batch_decode
here?
# self._log_statistics( | ||
# model_data, | ||
# mixture_data, | ||
# model_logprobs_model_data.detach(), | ||
# ref_logprobs_model_data, | ||
# probability, | ||
# score.detach(), | ||
# kl_div.detach(), | ||
# context_length, | ||
# ) |
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.
wip?
Co-authored-by: Quentin Gallouédec <[email protected]>
Co-authored-by: Quentin Gallouédec <[email protected]>
Co-authored-by: Quentin Gallouédec <[email protected]>
What does this PR do?
add support for judges API in online-pref methods