Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Traing loss #48

Open
XyFighting opened this issue Nov 3, 2024 · 2 comments
Open

Traing loss #48

XyFighting opened this issue Nov 3, 2024 · 2 comments

Comments

@XyFighting
Copy link

Hi, thanks for your amazing work!

I've encountered an issue with NaN losses when using MambaVision to train on CIFAR100 dataset. Could you suggest solutions to solve it?
Training_loss

@ahatamiz
Copy link
Collaborator

ahatamiz commented Nov 3, 2024

Hi @XyFighting , the best recommendation is to lower the learning rate. The settings used in ImageNet experiment may not be optimal for other datasets.

@XyFighting
Copy link
Author

Hi, thanks for your reply!
I have decreased the learning rate. However, when the training process proceeds after dozens of epochs, there are still NAN losses. Could you further suggest solutions to solve it?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants