Skip to content

Some question regarding using partial answer as training objective #25

@chanchimin

Description

@chanchimin

Hello, thank you for your great work! And I have some question about the step-dpo, the dataset on hf ("xinlai/Math-Step-DPO-10K") seems like taking "prompt" as input, and use "chosen" and "rejected" during training ("full_chosen" and "full_rejected" is assumingly not used. ), then under this circumstanding, won't the model tend to generate the partial response during inference? I am not sure if I am understanding right here, feel free to correct me, thank you!

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