Repository navigation
feat(gdpval): allow partial_completion on the final stage - #3912
Merged
Merged
Conversation
Signed-off-by: Serge Panev <spanev@nvidia.com>
yaoyu-33
added
area:environment
Contributor
Author
|
/ok to test 4d8b8cd |
agronskiy
approved these changes
Oct 2, 2026
Contributor
|
🔄 Merge queue validation started! You can track the progress here: https://github.com/NVIDIA-NeMo/Gym/actions/runs/36974775290 |
Contributor
|
🔄 Merge queue validation started! You can track the progress here: https://github.com/NVIDIA-NeMo/Gym/actions/runs/36974854800 |
5 tasks done
This branch was previously deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Ports #3770 from
gdpval-develto main. #3687 madepartial_completionunavailable on the final stage; this lets the final stage use it too.comparison/final_stage_partial_accepted: 1andcomparison/final_stage_degraded: 0, and emits the flatcomparison/eval_elo/comparison/normalized_elo, even when the observed row count is below the expected count.comparison/final_stage_completestays exact.final_stage_degraded: 1and no flat headline.accepted_stage_row_count) and in the stage journal, so resume cannot change which rows count.partial_completionentry in the config table is updated to match.Two files conflicted with main (the README
stagesrow and a test import); both are resolved to keep main's text plus the new behavior.Test plan
resources_servers/gdpval/tests+tests/unit_tests/test_rollout_collection.py+test_dispatch_latency.py: 908 passed.ruff checkandruff format --checkclean.