Repository navigation
Fix fully_async stale-drop count and carry-over execution mode (P0-S follow-up) - #257
Merged
Merged
Conversation
michaellchung
force-pushed
the
s23-pr-15-image-pins
branch
from
October 14, 2026 11:33
e701f8e to
1e8dc49
Compare
Miles resets _metric_stale_groups in get_metrics right after the trained-groups hook, so the value is already per round; subtracting the previous reading turned 9, 0, 10, 0 into 9, -9, 10, -10. Report it as read. Rounds whose rollout overlaps training (Miles and verl fully_async) now label rl_rollout_carry_over with execution_mode "partitioned-overlap"; the profile keeps its partitioned-serial step-scheduling mode, and the driver lets carry-over fields replace the profile label for that event. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
michaellchung
marked this pull request as ready for review
October 14, 2026 11:33
michaellchung
force-pushed
the
s23-p0s-fix
branch
from
October 14, 2026 11:33
4cc2c28 to
1ae3392
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Two fixes to the P0-S rollout/training overlap from #245, found during review of the P0-S GPU evidence, plus the golden samples that the first fix invalidates.
What changed
fully_async_prompts.py: Miles resets_metric_stale_groupsinget_metricsright after the trained-groups hook, so the value is already per round. Subtracting the previous reading turned 9, 0, 10, 0 into 9, -9, 10, -10. The value is now reported as read.rl_rollout_carry_overwith execution modepartitioned-overlap. The profile keeps itspartitioned-serialstep-scheduling mode; the driver lets carry-over fields replace the profile label for that event only.rollout_meta_hook.pychanged, so its source hash changed: 8 decoupling golden samples are regenerated, with a hash-migration record.Behavior changes / compatibility
rl_rollout_carry_over.execution_modeispartitioned-overlapfor fully_async rounds (waspartitioned-serial).Tests
Depends on
#256. Branch rebased with no tree change; the GPU code baseline
s23-p0s-fix@7a8485e5has the same tree.Not verified on GPU
Not run on GPU yet. The S23 GPU runs (third stage) use this branch as their code baseline.
🤖 Generated with Claude Code