Taehyun Lee

Different hyper-parameter between the paper and the code? (lora_alpha and a global batch size)

3

Hello, thank you for sharing the source code. While trying to reproduce **SST2 task result with RoBERTa-base model**, I've encountered some questions regarding the hyper-parameters, lora_alpha, and a global batch...

Could you provide some pretrained checkpoints?

1

Hello. I am interested in this project and I'd like to run a demo. Could you post some checkpoint files for us enthusiasts if you don't mind? And I'd really...