Add optional r1-style thinking reward #551
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
natolambert
approved these changes
Feb 5, 2025
| result = strict_format_reward_func([valid, invalid]) | ||
| assert result == [1.0, 0.0], f"Multiple responses failed, got {result}" | ||
| print("✓ Multiple responses passed") | ||
|
|
||
|
|
||
| # debug code | ||
| if __name__ == "__main__": |
There was a problem hiding this comment.
@vwxyzjn lets add this to the tests check we have?
Also, let's make the scale of the reward set by a hyperparam / config? Could get tricky reward shaping issues.
hamishivi
approved these changes
Feb 6, 2025
open_instruct/ground_truth_utils.py
Outdated
| @@ -139,7 +139,7 @@ def verify_flan_sample(model_output, ground_truth_answer): | |||
|
|
|||
| def soft_format_reward_func(responses: list[str]) -> list[float]: | |||
There was a problem hiding this comment.
Would agree with nathan that it feels like reward weight should be a param (and maybe even what pattern you are looking for?), to help with tuning reward stuff in the future.
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Outdated suggestions cannot be applied.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.
https://beaker.allen.ai/orgs/ai2/workspaces/tulu-3-dev/work/01JKA2SEKQ1E2QJN9SVSKGRKFQ?taskId=01JKA2SEKXC7BP2XB5KJC1C9TA&jobId=01JKA2SERKZ0JWH0HGFRETSYEX