Skip to content

Conversational dataset support for Online DPO #2075

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 24 commits into from
Sep 18, 2024
Merged

Conversational dataset support for Online DPO #2075

merged 24 commits into from
Sep 18, 2024

Conversation

qgallouedec
Copy link
Member

@qgallouedec qgallouedec commented Sep 16, 2024 •
edited
Loading

What does this PR do?

Item of #2071

Changes:

Major

  • Added conversational dataset support to Online DPO (and consequently to Nash-MD and XPO)
  • Removed applying the chat template in the example script (XPO, Nash-MD and Online DPO)
  • Added tests for conversational dataset support (XPO, Nash-MD and Online DPO)
  • Added a better default learning rate for OnlineDPOConfig (consequently changes the default for XPOConfig and NashMDConfig) (similar to [KTO] learning rate recomentations for kto #2070)
  • Changed the structure of the doc of XPO, Nash-MD and Online DPO to have
    1. Overview
    2. Quick start
    3. Usage tips
    4. Example script
    5. Logged metrics
    6. Autofocus of config and trainer

Minor

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 qgallouedec mentioned this pull request Sep 16, 2024
Open
29 tasks
@HuggingFaceDocBuilderDev
Copy link

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.

@qgallouedec qgallouedec marked this pull request as ready for review September 18, 2024 08:22
@qgallouedec qgallouedec merged commit 6920c2d into main Sep 18, 2024
10 checks passed
@qgallouedec qgallouedec deleted the online-dpo-dataset-support branch September 18, 2024 12:10
yxliu-TAMU pushed a commit to mincheolseong/ECEN743-GRPO-Project-Proposal that referenced this pull request Apr 20, 2025
@qgallouedec
Conversational dataset support for Online DPO (huggingface#2075)
5c64418 
* first modifications in the documentation

* Add script for processing ultrafeedback prompt dataset

* Remove unused variable in ultrafeedback.py

* style

* apply chat template within the init

* extend test

* new default lr

* nash md and xpo conv test

* Update prompt length check to 512 characters

* remove `maybe_apply_chat_template` in XPO and Nash examples

* polish online dpo doc

* better section name

* LogCompletionsCallback doc

* optional generation config

* reorder stats (consistency with online dpo)

* update online dpo doc

* format online dpo config

* format nash_md config

* update nash md

* Nash MD -> Nash-MD

* xpo doc

* doc
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@kashif kashif kashif approved these changes

@edbeeching edbeeching Awaiting requested review from edbeeching

@lewtun lewtun Awaiting requested review from lewtun

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@qgallouedec @HuggingFaceDocBuilderDev @kashif