【R1 SFT Bug，loss should start from 1】 #6226
447428054
started this conversation in
Community | Show and tell
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
The model was not loaded successfully, and training started with randomly initialized parameters.
https://zhuanlan.zhihu.com/p/26682456562
Beta Was this translation helpful? Give feedback.
All reactions