Add masked importance sampling for FSDP backend (#1063).#1
Merged
zijiexia merged 5 commits intozijiexia:zijie_dev_branchfrom Dec 16, 2025
Merged
Add masked importance sampling for FSDP backend (#1063).#1zijiexia merged 5 commits intozijiexia:zijie_dev_branchfrom
zijiexia merged 5 commits intozijiexia:zijie_dev_branchfrom
Conversation
Author
|
Here are the results I run with 4xH200 GPUs (using examples/train_infer_mismatch_helper/run-qwen3-4b-fsdp-mis.sh): 
Unfortunately, the original mismatch of training and rollout engine is quite marginal, so the MIS just has no effect. Thus I add a pytest script to test the functionality. |
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
5 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Hi Zijie, I have my code here. Please feel free to take a look, thank you!
Summary: