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

Code to fine-tune CONSEQ model using constrastive loss #7

Closed
rajesh-gupta-14 opened this issue May 3, 2022 · 1 comment
Closed

Code to fine-tune CONSEQ model using constrastive loss #7

rajesh-gupta-14 opened this issue May 3, 2022 · 1 comment

Comments

@rajesh-gupta-14
Copy link

Hi,

Thank you for sharing wonderful ideas and the code repository for improving the factual consistency of summarization.

I had a question regarding the code base. I am wondering if the repository also includes the code to fine-tune CONSEQ model using constrastive loss? As far as I can tell, the repo only includes code to preprocess the dataset into positive and negative samples. Please correct me if I am wrong. Appreciate your time and response. Thank you!
@fnan
Copy link

fnan commented May 6, 2022

Thanks for pointing out. Finetuning code is in scripts/launch_sagemaker_unlikelihood_cnndm.py and scripts/launch_sagemaker_unlikelihood_xsum.py. Fixed the README.

@fnan fnan closed this as completed May 6, 2022
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
@fnan @rajesh-gupta-14