Skip to content

Missing length normalization for grpo #10

@stepartm

Description

@stepartm

The problem is in the function run_grpo_microbatch_train_step.
Its docstring implies that the function should expect constant_normalize_factor as an input argument(which is very convenient for ablation studies on length normalization):

constant_normalize_factor: int | None, provided if we want to sum over

And yet there is no such argument in the function definition😢

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions