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

请问这几个数据集在哪里可以找到和网站交互 #11

Closed
wangjinghan666 opened this issue Nov 28, 2024 · 3 comments
Closed

Comments

@wangjinghan666
Copy link

Screenshot_2024-11-28-13-20-43-184_com android browser
请问要进行sft训练的话需要LLaMA-Factory/data/dataset_info.json里面提到的数据集,但是我在这里只找到了web_policy_sft和几个其他的数据集,没有看到像web_orm这个,请问是应该把dataset_info.json里面的其他的数据集删掉再运行么,另外我还有一个问题就是,我们的代理是如何和web进行交换的呢,我在这里没有找到像是playwright或是其他工具相关的代码

@QZH-777
Copy link
Collaborator

QZH-777 commented Nov 28, 2024

Sorry, web_orm dataset is not released. We will release the trained ORM later.
For interaction, please refer to the interaction and evaluation section of README.

@wangjinghan666
Copy link
Author

Sorry, web_orm dataset is not released. We will release the trained ORM later. For interaction, please refer to the interaction and evaluation section of README.

那我们用这里现有的文件还能进行sft训练么,没有orm的数据是不是以为着我们不能训练critic lm了

@QZH-777
Copy link
Collaborator

QZH-777 commented Nov 28, 2024

Sorry, web_orm dataset is not released. We will release the trained ORM later. For interaction, please refer to the interaction and evaluation section of README.

那我们用这里现有的文件还能进行sft训练么,没有orm的数据是不是以为着我们不能训练critic lm了

SFT training can still be performed, and the training data is web_policy_sft.json. Critic training needs to rely on ORM to label the interaction data, but does not require ORM training data. We will release ORM as soon as possible.

@QZH-777 QZH-777 closed this as completed Dec 1, 2024
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