prediction_step 是否合理 #6248
Unanswered
MountainHolder
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
/src/llamafactory/train/sft/trainer.py 里的prediction_step 的目的是什么?看上去像是为了让predict流程能跑通,强制让input和label的seq_len相等,但是这个真的符合实际问题吗?如果我输入的数据是identify,那么input就是instruct,label就是output,input经过经过神经网络输出的logit跟output计算交叉熵的目的是什么?
Beta Was this translation helpful? Give feedback.
All reactions