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

训练集损失 和 验证集损失 一直维持在 一点几,不下降 #64

Open
youzihaha opened this issue Aug 23, 2024 · 2 comments

Comments

@youzihaha
Copy link

用您的 这个模型 ,加上llama-chinese框架,训练十几万条数据(通用单轮数据+个人单轮数据),训练的时候 ,训练集损失 和 验证集损失 一直维持在 一点几,不下降,有什么办法吗

@CrazyBoyM
Copy link
Owner

全量微调或者lora微调时把lmhead、norm layer也解开一起训练

@CrazyBoyM
Copy link
Owner

另外不是说 loss越低越好,建议根据公司需求构建相关评测指标,每学习xx步/轮eval一次中间数据作为对模型训练的可视化监控,纯看loss的方式比较低级,无法满足实际训练生产需求。

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