feat(grpo): add sequence-level logprob error metrics - #2559
Merged
Conversation
macandro96
force-pushed
the
amahishi/seq-logprob-error-metrics
branch
from
May 22, 2026 18:49
8e33bc7 to
cd28deb
Compare
Contributor
Author
|
/ok to test cd28deb |
Contributor
|
Overall change looks good. Can you take a look at the test failure? https://github.com/NVIDIA-NeMo/RL/actions/runs/26306657989/job/77450890117?pr=2559. Also, can we include some tests for the new metrics? |
macandro96
force-pushed
the
amahishi/seq-logprob-error-metrics
branch
from
May 26, 2026 22:09
c076b75 to
8c7f147
Compare
macandro96
force-pushed
the
amahishi/seq-logprob-error-metrics
branch
from
May 26, 2026 23:10
8c7f147 to
fad476e
Compare
|
Auto-sync is disabled for ready for review pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
Signed-off-by: Anish Mahishi <amahishi@cw-dfw-cs-001-vscode-02.cm.cluster>
Signed-off-by: Anish Mahishi <amahishi@cw-dfw-cs-001-vscode-02.cm.cluster>
Contributor
Author
|
/ok to test fb02284 |
Contributor
Author
|
@yfw I made some changes - could you please review again? |
yfw
approved these changes
May 28, 2026
vigneshwaran
pushed a commit
to vigneshwaran/RL
that referenced
this pull request
May 28, 2026
Signed-off-by: Yi-Fu Wu <yifu.wu@gmail.com> Signed-off-by: Anish Mahishi <amahishi@cw-dfw-cs-001-vscode-02.cm.cluster> Co-authored-by: Yi-Fu Wu <yifu.wu@gmail.com> Co-authored-by: Jiaqi Zeng <jiaqiz@nvidia.com> Co-authored-by: Anish Mahishi <amahishi@cw-dfw-cs-001-vscode-02.cm.cluster>
2 tasks
4 tasks
4 tasks
qiaochuz-nv
added a commit
that referenced
this pull request
May 28, 2026
Adds CPU-runnable unit coverage for the 3 dict-access lines at grpo_sync.py:773-781 introduced by the #2559 follow-up fix. Signed-off-by: Qiaochu Zhu <qiaochuz@nvidia.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
2 participants
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 ?
Summary
grpo.seq_logprob_error_threshold.force_on_policy_ratio=Trueskip behavior unless sequence-level masking requires real prev logprobs.Issues
Related: #1910 (adds more monitoring metrics)
Closes: #1950
Usage
# Add a code snippet demonstrating how to use thisBefore your PR is "Ready for review"
Pre checks:
Additional Information