[train] Add per-token hard masking for off-policy correction#1264
Merged
erictang000 merged 7 commits intomainfrom Mar 4, 2026
Merged
[train] Add per-token hard masking for off-policy correction#1264erictang000 merged 7 commits intomainfrom
erictang000 merged 7 commits intomainfrom
Conversation
Zeros individual tokens where the train/infer importance ratio falls
outside configurable bounds, while keeping the rest of the sequence.
Unlike outlier_token_mask (which rejects entire sequences), this
surgically removes only the divergent tokens.
Configure with:
off_policy_correction.token_mask_eps_low: 0.2 # lower bound = 0.8
off_policy_correction.token_mask_eps_high: 0.28 # upper bound = 1.28
For full IS-corrected masking, combine with tis_ratio_type: "token".
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Collaborator
|
Collaborator
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
…ggs/per-token-masking
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
Collaborator
|
token metric propagated correctly: 
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
off_policy_correction.token_mask_eps_low/hightis_ratio_type: "token"