Skip to content

lr=0? #37

@adrianwestermeier

Description

@adrianwestermeier

Hi, in your paper you state that you use the same learning rate schedule as in the paper "attention is all you need". But I cannot find any implementation of it in your code. Moreover the learning rate in your adam optimizer is set to 0. Can you give me a hint where all this is handled in the code?

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