Fix : Move max_seq_length, packing, and dataset_kwargs to SFTConfig from SFTTrainer in finetune_sft_peft notebook #217
Conversation
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
BishmoyPaul
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Changes Made
This PR moves SFTTrainer arguments (
max_seq_length,packing, anddataset_kwargs) to SFTConfig to match updated TRL implementation (reference: https://github.com/huggingface/trl/blob/main/trl/trainer/sft_config.py) in finetune_sft_peft.ipynbRelated: unslothai/unsloth#1264 (comment)
Notebooks Modified:
Note: This PR does NOT address the
tokenizertoprocessing_classchange, as that's already covered in PR #214. These changes complement each other but are independent. In order to run the notebook, it is advised to incorporate both the changes.