Skip to content

dapo-bug #3846

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

Merged
merged 1 commit into from
Apr 12, 2025
Merged

dapo-bug #3846

merged 1 commit into from
Apr 12, 2025

Conversation

Evilxya
Copy link
Contributor

@Evilxya Evilxya commented Apr 11, 2025

这里判断该batch中的数据均有效时,不应该直接跳出,因为batch里的数据还未添加至总batch中。

@hjh0119
Copy link
Collaborator

hjh0119 commented Apr 11, 2025

这里的判断是对上一轮生成的数据(第一轮的话是判断dynamic sampling前的数据),所以不存在还未添加到总batch的情况?

@Evilxya
Copy link
Contributor Author

Evilxya commented Apr 11, 2025

这里的判断是对上一轮生成的数据(第一轮的话是判断dynamic sampling前的数据),所以不存在还未添加到总batch的情况?

如果是第一轮,确实符合条件,但是valid_sample为空,因此会报一次warning。如果不是第一轮,只有在上一轮数据量不够一个batch的情况下才会继续生成数据,而新的数据如果整个batch都符合条件就会直接跳出,但此时valid_sample中并没有添加新的batch中的数据,因此数据量还是不够一个batch,会继续报warning并使用原始的数据。

@hjh0119 hjh0119 merged commit cc1ece3 into modelscope:main Apr 12, 2025
2 checks passed
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

Successfully merging this pull request may close these issues.

2 participants