Skip to content

Parameters for NUM_ROLLOUT and ROLLOUT_MAX_RESPONSE_LEN #1

Description

@YunshengGeorge

Hi authors,

I had a quick question about reproducing your results for the Qwen3-4B distilling Qwen3-1.7B setup. I'm trying to pin down the exact values for NUM_ROLLOUT and ROLLOUT_MAX_RESPONSE_LEN. Some of the .sh files in your repo set NUM_ROLLOUT=50 and ROLLOUT_MAX_RESPONSE_LEN=64, but when I run with those, all the methods (entropy-based, TIP, and TA-OPD) end up underperforming the naive OPD baseline on AIME2024. I did manage to reproduce that baseline exactly though (0.10). For reference, I have the token selection ratio set to 10%.

It's totally possible I'm missing something on my end. Aside from NUM_ROLLOUT and ROLLOUT_MAX_RESPONSE_LEN, are there any other settings or details I might be overlooking? Thanks so much for the help!

Best,
George

Activity

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

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions