Skip to content

[QUESTION] Llava VQA performance #1042

Description

@benoriol

Hello,

What is the expected VQAv2 accuracy of the instruction-finetuned model? Should it reach ~80 as reported by LLaVa1.5? After training for a few thousand steps I get under 70. Not sure if it is just a matter of training for longer or there is any other issue with the training recipe.
Also it seems the LR is 1e-6 vs the 2e-5 reported in LlaVa hyperparameters. Is this intentional? What scores did you get with this recipe?

Thanks,
Benet

Probably for @jon-barker or @trintamaki ?

Activity

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

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions