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

about without pretraining #64

Open
aoyamatarou opened this issue Nov 14, 2022 · 0 comments
Open

about without pretraining #64

aoyamatarou opened this issue Nov 14, 2022 · 0 comments

Comments

@aoyamatarou
Copy link

Thank you for your great research and for publishing your source code.

I would like to do a reproduction experiment of amazon-dataset without pretrain.

You wrote in your README.md

If you would like to train all models from scratch, please set the hyperparameter pretrain as 0.
In this case, please set the number of epochs and the criteria of early stopping larger.

Specifically, what values should be set for epochs and the criteria of early stopping?

And if so, how long will it take to learn? (I suppose it depends on the specs of the machine.)

I would appreciate your answer.
Thank you.

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