[multi-lora] 1/n - 5, fix: skip zero-std metrics for reward-less samples - #2728
Open
yushengsu-thu wants to merge 1 commit into
Open
[multi-lora] 1/n - 5, fix: skip zero-std metrics for reward-less samples#2728yushengsu-thu wants to merge 1 commit into
yushengsu-thu wants to merge 1 commit into
Conversation
Batches whose samples carry no reward have no reward plane; treating missing rewards as zero-std groups is meaningless and crashes the round() bucketing on None. Return no zero-std metrics instead.
yushengsu-thu
marked this pull request as ready for review
August 23, 2026 23:59
yushengsu-thu
requested review from
fzyzcjy,
maocheng23 and
yueming-yuan
as code owners
August 23, 2026 23:59
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
There was a problem hiding this comment.
Claude Code Review
This repository is configured for manual code reviews. Comment @claude review for a one-time review, or @claude review always to subscribe this PR to a review on every future push.
Tip: disable this comment in your organization's Code Review settings.
yushengsu-thu
added
run-ci-megatron
run-ci-lora
run-ci-lora-native
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Batches whose samples carry no reward have no reward plane: treating missing rewards as zero-std groups is meaningless, and the
round()bucketing crashes onNone. Return no zero-std metrics for such batches instead.Extracted from #2273; the stack rebases after this merges.