Skip to content

the learning rate of word_language_model #757

Open
@zhangyingbit

Description

@zhangyingbit

Hi, I have a question about the learning rate in the example "word_language_model",
the init lr = 20, which seems very large, can you tell me why lr is set to equal 20?
Thanks a lot!
If you have some advices about improving the performance, please let me know and thanks

Activity

kienld3049

kienld3049 commented on Sep 12, 2022

@kienld3049

i also have the same question. Look like nobody answers that

AlbertMa123

AlbertMa123 commented on Mar 28, 2024

@AlbertMa123

me too, when i used lr=20, then the loss was very strange and crazy......

msaroufim

msaroufim commented on Apr 2, 2024

@msaroufim
Member

I'm happy to accept contributions for a more reasonable learning rate

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

      Development

      No branches or pull requests

        Participants

        @msaroufim@zhangyingbit@AlbertMa123@kienld3049

        Issue actions

          the learning rate of word_language_model · Issue #757 · pytorch/examples