FIX Error in VLM fine-tuning notebook #338
Merged
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
In the notebook, get_peft_model(model) is called, which mutates the base model. Then the same model is passed to SFTTrainer with a PEFT config, which leads to another call to get_peft_model under the hood and thus to PEFT being applied twice. This fix removes the manual get_peft_model call and lets trl handle this. We lose the ability to inspect the number of trainable parameters but IMO this is the simplest solution.
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
|
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. |
Member
Author
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Outdated suggestions cannot be applied.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.
What does this PR do?
In the notebook,
get_peft_model(model)is called, which mutates the base model. Then the samemodelis passed toSFTTrainerwith a PEFT config, which leads to another call toget_peft_modelunder the hood and thus to PEFT being applied twice.This fix removes the manual
get_peft_modelcall and lets trl handle this. We lose the ability to inspect the number of trainable parameters but IMO this is the simplest solution.