Skip to content

Question: what training setup was used for the released adapter? #2

Description

@dkx2077

Hi, thanks for open-sourcing this project.

I’m trying to reproduce the performance of the Hugging Face pretrained adapter from scratch, but my results are much worse than the released checkpoint. I trained using the default README / training script settings (Qwen3-VL-2B-Instruct, Wikipedia, 1000 samples, 5k–100k chars, max_pages=6, 10 epochs, lr=1e-4, batch_size=1), but the final quality is still quite poor.

Were there any important training details not covered in the README, such as data filtering, seeds, longer training, different sampling, or extra tuning?

Any guidance would be very helpful. Thanks.

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