Skip to content

Any progress on making the training batchable? #81

@yassineAlouini

Description

@yassineAlouini

Did anyone manage to make the model converge (both stage 1 and stage 2) using a batch size larger than 1?
If not, what are the blockers to achieve such a thing.

As long as my experience goes, stage 1 seems to be unstable for a batch larger than 1.
For stage 2 though, given a good collate function and good masking, it must be achievable.

Any comments on this are more than welcome, thanks!

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