请问在1.45k步数下，未出现注意力模型，但是loss已经低于0.3，是否说明样本太少？ #864
Unanswered
fatinghenji
asked this question in
Q&A
Replies: 1 comment
-
|
放弃吧，我记得作者在之前的回答里说至少要5个G还是说要100个小时来着，所以除非音源是天天演讲的知名人物，但是这样的人是不可能会让你练模型的，拿那个75K的模型做一些增量训练效果会非常好的 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
RT，补充图像如下：
总样本库约1.5小时，从头开始训练。
Beta Was this translation helpful? Give feedback.
All reactions