Skip to content

Question about hyperparameters settings and end losses #9

@kwang3939

Description

@kwang3939

Hi, I've been trying to run this code. But I couldn't find details about hyperparameters settings like initial learning rate and expected end training and validation losses from the paper. So I'm wondering if there are any suggestions on the parameters settings and what end loss curves and accuracy should I expect? 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