Fix GRPO config validation in case num_generations_eval is specified and different than num_generations
#4682
+15
−6
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Outdated suggestions cannot be applied.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.
Fix evaluation batch size validation to use
num_generations_evalwhen specifiedProblem:
The validation check in
GRPOConfig.__post_init__(lines 830-836) (trl/trl/trainer/grpo_config.py
Line 832 in 1cbd346
always validates the evaluation batch size divisibility against
num_generations, even whennum_generations_evalis explicitly set.Solution:
Modified the check to use
num_generations_evalwhen it's set, falling back tonum_generationsonly whennum_generations_evalis None.Impact:
num_generations_evalparameterChanges:
Before submitting
Pull Request section?
to it if that's the case.