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

How to get the configuration file after sft #24

Closed
lzy37ld opened this issue Dec 15, 2024 · 1 comment
Closed

How to get the configuration file after sft #24

lzy37ld opened this issue Dec 15, 2024 · 1 comment

Comments

@lzy37ld
Copy link

lzy37ld commented Dec 15, 2024

Hi, thanks for your great job. I am trying to play around with your code but met some issues.

If I understand correctly, I have to configure a file like test_webarena_lite.raw.json for the corresponding instruction from webrl-sft-data. However, I have no idea about the supposed configuration file for each task instruction from webrl-sft-data, for example the site and start-url. Could u pls give some help here? Appreciate!

@lzy37ld
Copy link
Author

lzy37ld commented Dec 15, 2024

Besides, I guess we need the reward function from VAB-lite given the line 3 of algorithm 1 in the paper. Could u help with this as well? Thanks!
@QZH-777 @Xiao9905

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