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

Why does not large batch size like 128, 256 work well? #100

Open
bad-meets-joke opened this issue Apr 19, 2023 · 0 comments
Open

Why does not large batch size like 128, 256 work well? #100

bad-meets-joke opened this issue Apr 19, 2023 · 0 comments

Comments

@bad-meets-joke
Copy link

Hi,

I see batch_size =2 in all experiments of the paper. To make training faster, I set batch_size =128 or 256 on my dataset with the same model, however, the performance is very unsatisfying.

Could you tell me the reason why choosing so mall batch size?Thanks.

@bad-meets-joke bad-meets-joke changed the title Why does not large batch size like 128, 256 work well in my dataset? Why does not large batch size like 128, 256 work well? Apr 19, 2023
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

1 participant