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.

Sign up for GitHub

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

Jump to bottom

deepsped 单机多卡QLORA训练，损失函数先减后增 #104

Open

qingjiaozyn opened this issue Oct 24, 2023 · 1 comment

qingjiaozyn commented Oct 24, 2023

Member

wangzaistone commented Oct 25, 2023

It's about tiaining trick and experience , your trianing epoch is too large to keep a good effect. For your image , 4 epoch is enough.

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