Skip to content

grpo训练过程张量不匹配 #3645

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
Closed
xdlzr opened this issue Mar 25, 2025 · 5 comments
Closed

grpo训练过程张量不匹配 #3645

xdlzr opened this issue Mar 25, 2025 · 5 comments

Comments

@xdlzr
Copy link

xdlzr commented Mar 25, 2025

RuntimeError: The expanded size of the tensor (1) must match the existing size (0) at non-singleton dimension 0. Target sizes: [1]. Tensor sizes: [0]想请问在grpo训练过程中出现这个报错，应该怎么解决
@hjh0119
Copy link
Collaborator

hjh0119 commented Mar 25, 2025

Does the main branch have this issue?

@xdlzr
Copy link
Author

xdlzr commented Mar 25, 2025

是的 请问您知道怎么解决这个问题吗，比较急 我检查了我的数据集应该没问题 。自定义的奖励函数 不知道如何排查

@hjh0119
Copy link
Collaborator

hjh0119 commented Mar 25, 2025

Is there an issue with the provided reward function?

@xdlzr
Copy link
Author

xdlzr commented Mar 25, 2025

我们可以邮件沟通一下吗请问

@hjh0119
Copy link
Collaborator

hjh0119 commented Mar 25, 2025

You can join the WeChat discussion group: #3076

@hjh0119 hjh0119 closed this as completed Mar 25, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@hjh0119 @xdlzr