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.

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

关于微调数据量 #1274

Open
CNXDZS opened this issue Dec 3, 2024 · 3 comments
Open

关于微调数据量 #1274

CNXDZS opened this issue Dec 3, 2024 · 3 comments

Comments

@CNXDZS
Copy link

CNXDZS commented Dec 3, 2024

作者好,目前打算基于bge-m3模型做垂直领域微调,有几个疑惑。
1.分别做全参和lora微调,微调数据的数据量您这边有好的建议吗?
2.微调数据需要专业数据和通用数据按照一定比例混合吗?
感谢!

@PineREN
Copy link

PineREN commented Dec 3, 2024

有问到或者查到吗?我也有相同的疑问

@CNXDZS
Copy link
Author

CNXDZS commented Dec 3, 2024

有问到或者查到吗?我也有相同的疑问

数据量和是否需要混合还没有查到。但是看了下代码,bge-m3属于encoder_only结构,项目里貌似不支持这种结构的lora微调。

@PineREN
Copy link

PineREN commented Dec 3, 2024

我用了四十万条数据训练试试,没有混合通用数据,看看结果。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants