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

The setting of hyperparameters to get the best performance #28

Open
A-zhudong opened this issue Aug 20, 2021 · 2 comments
Open

The setting of hyperparameters to get the best performance #28

A-zhudong opened this issue Aug 20, 2021 · 2 comments

Comments

@A-zhudong
Copy link

A-zhudong commented Aug 20, 2021

Hi Tian:
I have tried to reproduce your result like "MAE_model = 0.039" using your dataset.

The best MAE’s we achieved with Eq. 4 and Eq. 5 are 0.136 eV/atom and 0.039 eV/atom

But it is hard to set the hyperparameters correctly. Could you please share your settings of hypermeters?

Thank you and looking forward to your reply.

@txie-93
Copy link
Owner

txie-93 commented Aug 20, 2021

I think you probably need to have many more epochs. The default number of epochs is 30 which is too small. Try setting --epochs to 1000 and see if it improves your performance.

@A-zhudong
Copy link
Author

I think you probably need to have many more epochs. The default number of epochs is 30 which is too small. Try setting --epochs to 1000 and see if it improves your performance.

Thank you for your reply. The MAE decreased a lot. 感谢

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

2 participants