Optionally save value model + GRPO #523
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
vwxyzjn
approved these changes
Jan 21, 2025
hamishivi
changed the title
vwxyzjn
reviewed
Jan 23, 2025
| # print(f"{logprobs[0][:40]=}, {ref_logprobs[0][:40]=}, {kl.sum(1)=}") | ||
| non_score_reward = -args.beta * kl | ||
| non_score_reward_sum = non_score_reward.sum(1) | ||
| rlhf_reward = scores + non_score_reward_sum |
There was a problem hiding this comment.
Let's still log the rlhf_reward
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I want to be able to look at the value models we learn and see what happens, so this is to add that :)
Also adds GRPO ray code.
Need to test all this out but is exciting.