Remove dead token attributes from experimental trainers#5565
Merged
albertvillanova merged 2 commits intoApr 17, 2026
Conversation
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit af504f5. Configure here.
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
qgallouedec
approved these changes
Apr 16, 2026
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Remove dead token attributes from experimental trainers.
This PR refactors the initialization logic across several experimental trainer classes by removing redundant assignments of the
pad_tokenattribute. The changes ensure that only the necessary token ID attributes are set, leading to a cleaner and more consistent codebase.Follow-up to:
Changes
self.pad_token = tokenizer.pad_tokenin theOnlineDPOTrainer,SDFTTrainer, andSSDTrainerclasses, as only the token IDs are required for downstream processing. [BaseSelfDistillationTrainer, removed assignments forself.pad_token,self.pad_token_id, andself.eos_token_id, streamlining the initialization to only include relevant attributes.Note
Low Risk
Small refactor removing an unused attribute; behavior should be unchanged as padding continues to use
pad_token_id/eos_token_id.Overview
Removes redundant
self.pad_token = tokenizer.pad_tokenassignments from several experimental trainers (OnlineDPOTrainer,SDFTTrainer,BaseSelfDistillationTrainer,SSDTrainer), standardizing on storing onlypad_token_id/eos_token_idafter ensuring a pad token is set on the tokenizer.This is a small cleanup to eliminate dead attributes and keep trainer initialization consistent without changing generation/padding behavior.
Reviewed by Cursor Bugbot for commit 9e432f2. Bugbot is set up for automated code reviews on this repo. Configure here.