New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

#

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Jump to bottom

Issue on handling eos when tensor_fn.create_attention_mask #59

Open

AnselCmy opened this issue Mar 7, 2025 · 1 comment

AnselCmy commented Mar 7, 2025 •

edited

Loading

Hi, thanks for the great work. I found that the eos token will be masked out when use tensor_fn.create_attention_mask.
https://github.com/ZihanWang314/RAGEN/blob/4c457dc3a9509394c56acc97bb68e85cd19a4c75/ragen/llm_agent/tensor_helper.py#L35C1-L37C72
I don't know if this will have an effect on learning when to stop for models. Thanks!

Owner

ZihanWang314 commented Mar 7, 2025

Thanks for the nice catch! Will check!

# for free to join this conversation on GitHub. Already have an account? # to comment