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

[Help] <title>关于微调ptuning不能达到训练集的效果,且不破坏原有结构实验 #674

Open
1 task done
Bingoyww opened this issue Apr 10, 2024 · 0 comments

Comments

@Bingoyww
Copy link

Is there an existing issue for this?

  • I have searched the existing issues

Current Behavior

1)跑通广告数据集的代码;
2)运行自己数据集;
3)发现破坏原有结构的,即问些普通的问题,回答错误;
4)issues 里有人说是--learning_rate 1e-4,太大了,要改为--learning_rate 1e-5,运行3万epoch;
5)已运行了3万次,确实没有破坏结构,但还是达不到训练集的效果,比如在1.5万次时,可以做到“question:哪个组适用于小于13kg的婴儿床的组。 answer:适用于小于13kg的婴儿床的组是A组。”,训练集为“适用于小于13kg的婴儿床的组是C组。”,之后的1.5万次,很难训练成功。其他的问答集也如此。

Expected Behavior

No response

Steps To Reproduce

请问有什么方法,让大模型拟合问答集。

Environment

- OS:
- Python:
- Transformers:
- PyTorch:
- CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) :

Anything else?

No response

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

1 participant