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.

Sign up for GitHub

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

Jump to bottom

About the result of lora fine-tuning #15

Open
lucasliunju opened this issue Nov 12, 2023 · 2 comments
Open

About the result of lora fine-tuning #15

lucasliunju opened this issue Nov 12, 2023 · 2 comments

Comments

@lucasliunju
Copy link

May I ask the result of this lora fine-tuning on MMLU task.

Thanks!

Best,
Lucas
@bing0037
Copy link

Same question. Could you provide the best result with LLaMA 1 or LLaMA2 on Vicuna and give the hyperparameters (num of epoch/learning rate/lora_r/batch_size)?
I wanna reproduce your result ans use it as the baseline. Training loss or MMLU or alpaca_eval results are appreciated!

@bing0037
Copy link

@little51 Could you please provide any information?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@bing0037 @lucasliunju