Skip to content

change of seed registered as improvement? #466

Description

@Clement-Lelievre

Hi there,

thanks for this repo.

The idea of a model training another one looks promising.

Juts one thought: looking at the image shown in the README, the change of seed is registered as a valid step to lower the loss (it's the last step on the graph) while it is just "luck" in a way isn't it, unless I'm missing smthg?
I understand that in the end the change of seed led to a stronger checkpoint as per the eval, but it still feels a bit random to me.

So I'm wondering if there's a way to better separate actual gains (ones that always lower the val) and lucky gains (eg a mere change of seed).

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