Skip to content
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.

Sign up for GitHub

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

Jump to bottom

模型只会加减，不会乘除。。。 #77

Open
LianhaoXue opened this issue Feb 18, 2025 · 3 comments
Open

模型只会加减，不会乘除。。。 #77

LianhaoXue opened this issue Feb 18, 2025 · 3 comments

Comments

@LianhaoXue
Copy link

8*A100（80G）

qwen2.5-3B-base模型

训练了200个step，模型只会加减法，不会乘除法。涉及加减法的一般能答对，乘除法的就答不出来，这是为什么。
@GaryZhu1996
Copy link

7B模型也表现出了这个问题，是step不够的原因吗

@sworddish
Copy link

The base model should know "how to do the multiplication" or "what is multiplication" otherwise you have to let it know, or change a more capable model

@LianhaoXue
Copy link
Author

7B模型也表现出了这个问题，是step不够的原因吗

是的，多训练一些step，就能会一些简单的乘除

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@sworddish @GaryZhu1996 @LianhaoXue