Fix cosine_scaled_reward compatibility with GRPO
#229
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
qgallouedec
commented
Feb 7, 2025
lewtun
approved these changes
Feb 7, 2025
| @@ -26,7 +26,7 @@ | |||
| from transformers.trainer_utils import get_last_checkpoint | |||
|
|
|||
| from open_r1.configs import GRPOConfig | |||
| from open_r1.rewards import accuracy_reward, cosine_scaled_reward, format_reward, reasoning_steps_reward | |||
| from open_r1.rewards import accuracy_reward, format_reward, get_cosine_scaled_reward, reasoning_steps_reward | |||
There was a problem hiding this comment.
turbo nit: given the other reward functions aren't getters, what about we call this cosine_scaled_reward and use_cosine_scaled_reward as the inner function
There was a problem hiding this comment.
I think I would be more confusing actually, for 2 reasons
- You would read this in the registery:
REWARD_FUNCS_REGISTRY = {
"accuracy": accuracy_reward,
"format": format_reward,
"reasoning_steps": reasoning_steps_reward,
"cosine": cosine_scaled_reward(min_value_wrong=min_value_wrong, ...)
}- In the logged metrics, you'd have this annoying
_:
{..., 'rewards/accuracy_reward': 0.6, 'rewards/format_reward': 0.0, 'rewards/_cosine_scaled_reward': 0.0, 'epoch': 0.0}
There was a problem hiding this comment.
ah good point. let's keep the getter then
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Outdated suggestions cannot be applied.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.
No description provided.