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

启用Unsloth测试LLaMa3 #250

Open

difonjohaiv opened this issue May 10, 2024 · 0 comments

difonjohaiv commented May 10, 2024 •

edited

首先，非常感谢作者的开源工作！

在用Firefly框架测试微调LLaMa3之后，开启了unsloth微调，微调过程的显存开销变小，然而时间花销更大了。

测试模型：unsloth/llama-3-8b-bnb-4bit
微调参数：firefly项目中的llama3-8b-sft-qlora.json

下图是use_unsloth=true，微调的时间为54 minutes

下图是use_unsloth=false，微调的时间为49 minutes

请问是我的哪个步骤出错了吗？

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