feat(sft): make only_unmask_final configurable in SFTConfig#2516
Open
yuki-97 wants to merge 3 commits into
Open
feat(sft): make only_unmask_final configurable in SFTConfig#2516yuki-97 wants to merge 3 commits into
yuki-97 wants to merge 3 commits into
Conversation
For multi-turn SFT tasks where only the final assistant response should be trained on, the only_unmask_final flag in add_loss_mask_to_message_log was not accessible through SFTConfig. Add only_unmask_final as a configurable boolean in SFTConfig and wire it through to both training and validation loss mask calls. Defaults to false to preserve existing behavior. Closes #2219 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: Yuki Huang <yukih@nvidia.com>
yuki-97
added
the
CI:Lfast
Contributor
Author
|
/ok to test 3308519 |
Signed-off-by: Yuki Huang <yukih@nvidia.com>
Contributor
Author
|
/ok to test 26ad6e4 |
4 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Continues #2268, thanks for the contribution @Ai-chan-0411.
Issue
Closes #2219.
Summary
only_unmask_final: booltoSFTConfigandsft.yaml(defaults tofalse).add_loss_mask_to_message_login both the train and validation paths.Test plan
test_add_loss_mask_to_chat_message_logtests.