Include rationale of the model responses on prepare_dataset
if available
#317
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Outdated suggestions cannot be applied.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_dataset
function to include therationale
of 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
rationale
is available in the dataset (thePreferenceTasks
that generate it will add it to the dataset), the binarized dataset will contain the columnschosen_rationale
andrejected_rationale
.Closes #316.