🧨 DFT

[qgallouedec]

What does this PR do?

Fixes # (issue)

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?
• 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.

[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.

[lewtun]

Very clean PR! LGTM with a question on whether we should unit test the new loss type arg, similar to what we do with DPO here:

trl/tests/test_dpo_trainer.py

Line 221 in 1b799a2

def test_train_loss_types(self, loss_type):

[kashif]

I'll add the flag for liger kernel when there is a new release.

[cmpatino]

LGTM!

[qgallouedec]

Very clean PR! LGTM with a question on whether we should unit test the new loss type arg, similar to what we do with DPO here:

trl/tests/test_dpo_trainer.py

Line 221 in 1b799a2

def test_train_loss_types(self, loss_type):

where is my head?

added