Skip to content

Gradient update is extremely slow #23

@AshStuff

Description

@AshStuff

I am trying to train a Image-Text Contrastive learning model and I am using a Functional Approach. The number of grad steps are 32 and the batch size per step is 32 which makes the total batch size as 1024.

Any idea how to increase the speed while doing the gradient update ?

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