Skip to content

failed to train model #1499

@qiqingzhixin

Description

@qiqingzhixin

[00:27:25] [#15] Loss A: 0.20026, Loss B: 0.2247109/20/2025 00:27:25 CRITICAL NaN Detected. Loss: [0.21266034245491028, nan]
09/20/2025 00:27:25 CRITICAL Error caught! Exiting...
09/20/2025 00:27:25 ERROR Caught exception in thread: '_training'
09/20/2025 00:27:25 ERROR A NaN was detected and you have NaN protection enabled. Training has been terminated.

how to deal it

Image

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