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

关于混合微调的数据格式 #37

Open
zyzyyy123 opened this issue Sep 11, 2024 · 1 comment
Open

关于混合微调的数据格式 #37

zyzyyy123 opened this issue Sep 11, 2024 · 1 comment

Comments

@zyzyyy123
Copy link

您好,请问关于混合微调阶段,预训练数据和指令微调数据放在一起训练,数据格式是怎么统一组织的呢?我理解预训练的数据格式是一段text,而指令微调有instruction和output

@zyzyyy123 zyzyyy123 changed the title 关于混合微调 关于混合微调的数据格式 Sep 11, 2024
@ShomyLiu
Copy link

任务都是next token prediction,在数据组织的时候,label有所区分即可,指令数据值计算output的loss,其他部分可以设置为-100,从而用Cross Entropy函数可以自动忽略, 对于文本数据的话,就正常计算即可。

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