🔮 Fix unused precomputed ref log probs in DPO

[dakru012]

What does this PR do?

This PR extends the PreferenceCollator to handle precompute_ref_log_probs.
Additionally, some comments regarding the default data_collator are fixed.

Fixes # #2423

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a GitHub issue? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[qgallouedec]

LGTM, thanks for the fix!
I've tested by hand, it's internally working as expected.

[HuggingFaceDocBuilderDev]

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.