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

Request for Detailed Hyperparameter Settings for Reproducibility #6

Open
KEVIN666666666 opened this issue Oct 22, 2024 · 0 comments
Open

Comments

@KEVIN666666666
Copy link

Dear authors,

Thank you for sharing your inspiring work and providing the codebase.

However, while trying to reproduce the results presented in the paper, I noticed that the detailed hyperparameter settings for each dataset are not provided. The hyperparameter ranges mentioned are quite broad, and finding the optimal settings without additional guidance is challenging and time-consuming.

For the sake of reproducibility and to help the community better understand and validate the contributions of your work, could you please share the specific hyperparameter configurations (e.g., learning rate, batch size and loss weight) used for each dataset (e.g., OfficeHome, VLCS, and Terra Incognita) in the experiments? Providing these details would greatly facilitate reproducing the reported results and conducting further research based on your work.

Thank you for your time and consideration!

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