Skip to content

Training details #6

Description

@Allencheng97

Dear Authors,

Thank you for your great work.

I noticed that in the closed issue (#1), you mentioned that you used the default settings from LLaMA-Factory. However, I am still unclear about the exact training configuration.

If you are referring to the example configurations in LLaMA-Factory, it seems that only a Qwen3 LoRA training example is provided there. Since I would like to reproduce the results in the paper as accurately as possible, could you kindly provide the exact training parameters or the YAML configuration file used in your experiments?

That would be very helpful for reproducibility. Thank you in advance.

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