fix: add truncation warning to TRL generate paths#242
Merged
Conversation
Add a truncation check after both generation paths (Outlines constrained and HF unconstrained) in generate_fn. When the output length reaches max_new_tokens - 1, a warning is logged suggesting to increase max_new_tokens or enable constrained_decoding. This helps diagnose cases where the model generates excessively long reasoning that gets cut off before producing a parseable action. Also replaced the tautological truncation tests in test_trl_robustness.py (which reimplemented the check logic inline) with tests that exercise the actual generate_fn code path by calling it through the rollout function with mocked torch and model.generate. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
abrichr
added a commit
that referenced
this pull request
Mar 29, 2026
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
generate_fninsidemake_waa_rollout_func. When output length reachesmax_new_tokens - 1, a warning is logged suggesting to increasemax_new_tokensor enableconstrained_decoding.test_trl_robustness.py(which reimplemented the check logic inline in the mock) with tests that exercise the actualgenerate_fncode path by calling it through the rollout function with mockedtorchandmodel.generate.Test plan
test_truncation_warning_logged_hf_path— verifies warning fires when completion hits max_new_tokenstest_no_truncation_warning_when_short— verifies no warning for short completionstest_trl_robustness.pyandtest_trl_rollout.pypass🤖 Generated with Claude Code