Skip to content

Implementating training with allava checkpoints #14

@estelleafl

Description

@estelleafl

Hi!
Thank you for sharing your work
Im trying to train using the checkpoitns and scripts you provided on huggingface as well as the LLaVA code base
However, for the 3 models, Im getting the following error:
RuntimeError: Trying to backward through the graph a second time (or directly access saved tensors after they have already been freed). Saved intermediate values of the graph are freed when you call .backward() or autograd.grad(). Specify retain_graph=True if you need to backward through the graph a second time or if you need to access saved tensors after calling backward.

Would you have any idea why?

Thank you

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions