Expose generation index to tool callables in GRPOTrainer #4894
+131
−2
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Outdated suggestions cannot be applied.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.
What does this PR do?
When using
GRPOTrainerwith tools, the trainer generates multiple completions per prompt (num_generations), then executes tool calls for each completion via_tool_call_loop. However, tool callables have no way to know which completion triggered them.The fix exposes the completion index to tool callables by inspecting each tool's signature at initialization and caching whether it accepts a
_completion_idxparameter. During tool execution in_tool_call_loop, if a tool declares this parameter, the trainer passes the current completion index; otherwise it calls the tool normally. This allows tools to know which of the multiple generated completions triggered them, enabling per-completion attribution for reward functions without breaking existing tools that don't need this information.Fixes #4866
Before submitting
Pull Request section?
to it if that's the case.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.