Skip to content

Stop training when the loss is not changing much #3

@BJohn-dev

Description

@BJohn-dev

the learning process should be stopped by sufficient basis not just by limiting.
Infinite loop until loss doesn't moves a lot.

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions