-
Notifications
You must be signed in to change notification settings - Fork 61
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
论文中的一阶段训练疑问 #13
Comments
Hi @J-G-Y ,
|
您好,请问下:我看了代码是做微调,没有经过预训练,为什么能够把领域知识注入到模型,我的理解和增大微调数据量没有本质的区别,还是在做微调只是数据变化了。一直在这个地方没有理解清楚,期待您的回答。 |
@zhou-wjjw 你好, |
|
作者您好,刚入行的小白。跟您请教一些论文的思路问题。
文章中提到了“we only optimize the output loss and do not learn from the input loss.”
而本文的中心思想也是降低持续预训练和有监督微调的差异。
因此跟您请教以下问题:
1.构造完的问题答案对是只进行有监督微调的嘛(持续预训练数据和有监督数据混合后的QA数据)
2.如果第一个问题是直接进行有监督微调,那么对比直接构造大量的领域数据去进行有监督微调的做法,差异性在哪
期待您的回复。Thanks
The text was updated successfully, but these errors were encountered: