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

Add RLHF Reward Trainer and Loss #3435

Closed
wants to merge 30 commits into from
Closed

Add RLHF Reward Trainer and Loss #3435

wants to merge 30 commits into from

Commits on Jun 5, 2023

  1. Make preprocessing modifications V1

    @asdataminer
    asdataminer committed Jun 5, 2023
    Configuration menu
    Copy the full SHA
    2bc1d01 View commit details
    Browse the repository at this point in the history

  2. Add dataset validation

    @asdataminer
    asdataminer committed Jun 5, 2023
    Configuration menu
    Copy the full SHA
    d6cc331 View commit details
    Browse the repository at this point in the history

  3. Small edit

    @asdataminer
    asdataminer committed Jun 5, 2023
    Configuration menu
    Copy the full SHA
    ea07940 View commit details
    Browse the repository at this point in the history

Commits on Jun 7, 2023

  1. Add tests

    @asdataminer
    asdataminer committed Jun 7, 2023
    Configuration menu
    Copy the full SHA
    e993d7b View commit details
    Browse the repository at this point in the history

Commits on Jun 8, 2023

  1. Small edits

    @asdataminer
    asdataminer committed Jun 8, 2023
    Configuration menu
    Copy the full SHA
    98db29b View commit details
    Browse the repository at this point in the history

  2. Another small edit

    @asdataminer
    asdataminer committed Jun 8, 2023
    Configuration menu
    Copy the full SHA
    518feca View commit details
    Browse the repository at this point in the history

Commits on Jun 12, 2023

  1. Modify processing strategy

    @asdataminer
    asdataminer committed Jun 12, 2023
    Configuration menu
    Copy the full SHA
    8ac5101 View commit details
    Browse the repository at this point in the history

  2. Small edit

    @asdataminer
    asdataminer committed Jun 12, 2023
    Configuration menu
    Copy the full SHA
    b61a174 View commit details
    Browse the repository at this point in the history

  3. Another small edit

    @asdataminer
    asdataminer committed Jun 12, 2023
    Configuration menu
    Copy the full SHA
    e78152d View commit details
    Browse the repository at this point in the history

  4. Small edit

    @asdataminer
    asdataminer committed Jun 12, 2023
    Configuration menu
    Copy the full SHA
    440cbec View commit details
    Browse the repository at this point in the history

Commits on Jun 13, 2023

  1. Add loss items

    @asdataminer
    asdataminer committed Jun 13, 2023
    Configuration menu
    Copy the full SHA
    b12f8ac View commit details
    Browse the repository at this point in the history

  2. Add trainer

    @asdataminer
    asdataminer committed Jun 13, 2023
    Configuration menu
    Copy the full SHA
    936194d View commit details
    Browse the repository at this point in the history

  3. Modify reward model trainer

    @asdataminer
    asdataminer committed Jun 13, 2023
    Configuration menu
    Copy the full SHA
    2b74e7b View commit details
    Browse the repository at this point in the history

  4. Small edits

    @asdataminer
    asdataminer committed Jun 13, 2023
    Configuration menu
    Copy the full SHA
    becf832 View commit details
    Browse the repository at this point in the history

  5. Add trainer, data edits

    @asdataminer
    asdataminer committed Jun 13, 2023
    Configuration menu
    Copy the full SHA
    7d4243f View commit details
    Browse the repository at this point in the history

Commits on Jun 14, 2023

  1. Add schema changes

    @asdataminer
    asdataminer committed Jun 14, 2023
    Configuration menu
    Copy the full SHA
    316e2bf View commit details
    Browse the repository at this point in the history

  2. Add refactored processing logic and trainer

    @asdataminer
    asdataminer committed Jun 14, 2023
    Configuration menu
    Copy the full SHA
    dd675d6 View commit details
    Browse the repository at this point in the history

  3. Style edits

    @asdataminer
    asdataminer committed Jun 14, 2023
    Configuration menu
    Copy the full SHA
    cae42ad View commit details
    Browse the repository at this point in the history

  4. Modify tests

    @asdataminer
    asdataminer committed Jun 14, 2023
    Configuration menu
    Copy the full SHA
    a0808cf View commit details
    Browse the repository at this point in the history

Commits on Jun 15, 2023

  1. More test edits

    @asdataminer
    asdataminer committed Jun 15, 2023
    Configuration menu
    Copy the full SHA
    9b46959 View commit details
    Browse the repository at this point in the history

  2. Make reward model a separate model type

    @asdataminer
    asdataminer committed Jun 15, 2023
    Configuration menu
    Copy the full SHA
    cc40f7c View commit details
    Browse the repository at this point in the history

  3. Additional refactor edits

    @asdataminer
    asdataminer committed Jun 15, 2023
    Configuration menu
    Copy the full SHA
    a93a1b8 View commit details
    Browse the repository at this point in the history

  4. Style edits

    @asdataminer
    asdataminer committed Jun 15, 2023
    Configuration menu
    Copy the full SHA
    e311741 View commit details
    Browse the repository at this point in the history

  5. Add text encoder

    @asdataminer
    asdataminer committed Jun 15, 2023
    Configuration menu
    Copy the full SHA
    1662827 View commit details
    Browse the repository at this point in the history

  6. Small edits

    @asdataminer
    asdataminer committed Jun 15, 2023
    Configuration menu
    Copy the full SHA
    4860265 View commit details
    Browse the repository at this point in the history

  7. Modify trainer, tests passing

    @asdataminer
    asdataminer committed Jun 15, 2023
    Configuration menu
    Copy the full SHA
    9cf18d6 View commit details
    Browse the repository at this point in the history

Commits on Jun 20, 2023

  1. Bug fix

    @asdataminer
    asdataminer committed Jun 20, 2023
    Configuration menu
    Copy the full SHA
    82bbffe View commit details
    Browse the repository at this point in the history

  2. Small edit

    @asdataminer
    asdataminer committed Jun 20, 2023
    Configuration menu
    Copy the full SHA
    3675f42 View commit details
    Browse the repository at this point in the history

  3. Another edit

    @asdataminer
    asdataminer committed Jun 20, 2023
    Configuration menu
    Copy the full SHA
    4f852ea View commit details
    Browse the repository at this point in the history

  4. Reward loss test

    @asdataminer
    asdataminer committed Jun 20, 2023
    Configuration menu
    Copy the full SHA
    b6ef5d1 View commit details
    Browse the repository at this point in the history