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

How to replicate the results in the paper? #28

Open
yyoshikai opened this issue Oct 7, 2024 · 0 comments
Open

How to replicate the results in the paper? #28

yyoshikai opened this issue Oct 7, 2024 · 0 comments

Comments

@yyoshikai
Copy link

Hello, thank you for providing the codes.

I was trying to replicate the results in the paper about generative performance on MOSES dataset, but I failed. Which weight in https://www.kaggle.com/datasets/virajbagal/ligflow-final-weights should be used? I tried moses_newtokens.pt and moses_scaf_wholeseq_newtokens.pt and did

python generate/generate.py --model_weight moses_newtokens.pt --csv_name generate --gen_size 30000

python generate/generate.py --model_weight moses_scaf_wholeseq_newtokens.pt --csv_name moses_scaf_wholeseq_newtokens --gen_size 30000 --scaffold

but FCD/Test and FCD/TestSF did not reach the results in Table 1. Am I forgetting some arguments?

Thank you very much!

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