[DPO] add 'bco_pair' loss_type #1524
Merged
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
|
thanks @seanexp perhaps lets also add some description in the DPO docs too? |
|
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. |
|
Ah yes! I'll work on it. |
kashif
approved these changes
Apr 12, 2024
younesbelkada
approved these changes
Apr 22, 2024
kashif
pushed a commit
to kashif/trl
that referenced
this pull request
Apr 23, 2024
* add 'bco_pair' loss_type * add BCO description to DPO doc --------- Co-authored-by: sean.jung <[email protected]>
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Outdated suggestions cannot be applied.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.
add Binary Classifier Optimization (BCO) loss function from https://arxiv.org/abs/2404.04656
Implemented bce loss and reward shift in the paper.
I will make separate PR for unpaired version of BCO after rebase and polishing.