只用一个任务进行指令精调 #586
Antiman-cmyk
started this conversation in
General
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
请问有没有人试过只用于一个任务进行指令精调的效果,或者说这样做合不合理呢?我尝试了用不同instructions的表达方式,但是任务监督的目标是一致的,发现这样训练的loss特别小,大概只有零点几,然后大模型的能力都退化了,测试阶段只会做tune过的这一个任务,而且不理解输入的prompt,不管输入什么,都是只做训练的任务,感觉和以前普通的小模型一样,想请教一下有什么改进方式呢?
Beta Was this translation helpful? Give feedback.
All reactions