Include rationale of the model responses on prepare_dataset if available
#317
Conversation
This file contains 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
plaguss
changed the title
prepare_dataset if available
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Outdated suggestions cannot be applied.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.
Description
This PR updates the
dataset.utils.prepare_datasetfunction to include therationaleof the model chosen/rejected, if the rationale is available in the original dataset (aside from the tests, tested locally it works with the disticoder-dpo dataset).If
rationaleis available in the dataset (thePreferenceTasksthat generate it will add it to the dataset), the binarized dataset will contain the columnschosen_rationaleandrejected_rationale.Closes #316.