[SFTTrainer] Add warning for wrong padding_side#550
Merged
younesbelkada merged 4 commits intomainfrom Jul 22, 2023
Merged
Conversation
lvwerra
approved these changes
Jul 21, 2023
|
The documentation is not available anymore as the PR was closed or merged. |
yxliu-TAMU
pushed a commit
to mincheolseong/ECEN743-GRPO-Project-Proposal
that referenced
this pull request
Apr 20, 2025
* add warning for wrong padding_side * add warning * revert * oops
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
While debugging why some users got 0 loss when fine-tuning Llama-2 on Guanaco, it seems the issue was caused by padding tokens being appended on the left.
The fix for that model seems to be to force
tokenizer.padding_side = "right"to successfully fine-tune Llama-2. Therefore we advise users to do that for their training.Related: https://gist.github.com/younesbelkada/9f7f75c94bdc1981c8ca5cc937d4a4da?permalink_comment_id=4636728#gistcomment-4636728
cc @lvwerra