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

SFT数据格式问题 #311

Open
lovelyturtle opened this issue Apr 8, 2024 · 1 comment
Open

SFT数据格式问题 #311

lovelyturtle opened this issue Apr 8, 2024 · 1 comment

Comments

@lovelyturtle
Copy link

感觉markdown给的数据格式有问题;
数据集只有一列"task"是把整个输入全部计算了loss,但SFT的正确做法应该要mask掉human的部分不参与损失计算。
如果是SFT格式的,数据集应该提供"input"和"target"两列;代码没有问题,但是这部分的markdown文档有问题

@ZHangZHengEric
Copy link
Collaborator

其实学习human的内容,也没有问题,有一些试验表明会提高效果,当然这种方式效率低一些。
代码其实支持这两种方式

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