Skip to content
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

Online DPO and Online trainer refactor #1809

Merged
merged 23 commits into from
Jul 18, 2024
Merged

Online DPO and Online trainer refactor #1809

merged 23 commits into from
Jul 18, 2024

Commits on Jul 3, 2024

  1. online dpo trainer based on rloo trainer

    @mnoukhov
    mnoukhov committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    94353cb View commit details
    Browse the repository at this point in the history

Commits on Jul 5, 2024

  1. push changes

    @vwxyzjn
    vwxyzjn committed Jul 5, 2024
    Configuration menu
    Copy the full SHA
    d88ee55 View commit details
    Browse the repository at this point in the history

Commits on Jul 9, 2024

  1. refactor

    @vwxyzjn
    vwxyzjn committed Jul 9, 2024
    Configuration menu
    Copy the full SHA
    1a45ec4 View commit details
    Browse the repository at this point in the history

  2. use batch_generation method

    @vwxyzjn
    vwxyzjn committed Jul 9, 2024
    Configuration menu
    Copy the full SHA
    5a3bd05 View commit details
    Browse the repository at this point in the history

  3. precommit

    @vwxyzjn
    vwxyzjn committed Jul 9, 2024
    Configuration menu
    Copy the full SHA
    aa67767 View commit details
    Browse the repository at this point in the history

  4. remove breakpoint()

    @vwxyzjn
    vwxyzjn committed Jul 9, 2024
    Configuration menu
    Copy the full SHA
    576c098 View commit details
    Browse the repository at this point in the history

  5. quick refactor

    @vwxyzjn
    vwxyzjn committed Jul 9, 2024
    Configuration menu
    Copy the full SHA
    c5a1612 View commit details
    Browse the repository at this point in the history

Commits on Jul 11, 2024

  1. push the current changes

    @vwxyzjn
    vwxyzjn committed Jul 11, 2024
    Configuration menu
    Copy the full SHA
    e264126 View commit details
    Browse the repository at this point in the history

Commits on Jul 15, 2024

  1. quick change

    @vwxyzjn
    vwxyzjn committed Jul 15, 2024
    Configuration menu
    Copy the full SHA
    9653edb View commit details
    Browse the repository at this point in the history

  2. refactor

    @vwxyzjn
    vwxyzjn committed Jul 15, 2024
    Configuration menu
    Copy the full SHA
    798d1d6 View commit details
    Browse the repository at this point in the history

  3. use the config name as the experiment name

    @vwxyzjn
    vwxyzjn committed Jul 15, 2024
    Configuration menu
    Copy the full SHA
    6562bc2 View commit details
    Browse the repository at this point in the history

Commits on Jul 16, 2024

  1. fix logging

    @vwxyzjn
    vwxyzjn committed Jul 16, 2024
    Configuration menu
    Copy the full SHA
    7a0c273 View commit details
    Browse the repository at this point in the history

  2. update online DPO docs

    @vwxyzjn
    vwxyzjn committed Jul 16, 2024
    Configuration menu
    Copy the full SHA
    7e03124 View commit details
    Browse the repository at this point in the history

Commits on Jul 17, 2024

  1. push docs

    @vwxyzjn
    vwxyzjn committed Jul 17, 2024
    Configuration menu
    Copy the full SHA
    245b4d6 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into online-trainer-refactor

    @vwxyzjn
    vwxyzjn authored Jul 17, 2024
    Configuration menu
    Copy the full SHA
    c9af013 View commit details
    Browse the repository at this point in the history

  3. increment global step so tensorboard works again.

    @vwxyzjn
    vwxyzjn committed Jul 17, 2024
    Configuration menu
    Copy the full SHA
    5edfb77 View commit details
    Browse the repository at this point in the history

  4. precommit

    @vwxyzjn
    vwxyzjn committed Jul 17, 2024
    Configuration menu
    Copy the full SHA
    33413b5 View commit details
    Browse the repository at this point in the history

  5. remove unused common online trainer

    @vwxyzjn
    vwxyzjn committed Jul 17, 2024
    Configuration menu
    Copy the full SHA
    791628d View commit details
    Browse the repository at this point in the history

  6. add online DPO docs

    @vwxyzjn
    vwxyzjn committed Jul 17, 2024
    Configuration menu
    Copy the full SHA
    5fa26df View commit details
    Browse the repository at this point in the history

Commits on Jul 18, 2024

  1. quick refactor

    @vwxyzjn
    vwxyzjn committed Jul 18, 2024
    Configuration menu
    Copy the full SHA
    375e90b View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into online-trainer-refactor

    @vwxyzjn
    vwxyzjn committed Jul 18, 2024
    Configuration menu
    Copy the full SHA
    709c7c0 View commit details
    Browse the repository at this point in the history

  3. push changes

    @vwxyzjn
    vwxyzjn committed Jul 18, 2024
    Configuration menu
    Copy the full SHA
    3b0ef48 View commit details
    Browse the repository at this point in the history

  4. Update docs/source/online_dpo_trainer.md 

    Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
    @vwxyzjn @qgallouedec
    vwxyzjn and qgallouedec authored Jul 18, 2024
    Configuration menu
    Copy the full SHA
    2c532aa View commit details
    Browse the repository at this point in the history