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

Random Seed #13

Open
GMarzinotto opened this issue Oct 11, 2018 · 0 comments
Open

Random Seed #13

GMarzinotto opened this issue Oct 11, 2018 · 0 comments

Comments

@GMarzinotto
Copy link

Hello,

First thank you very much for this contribution!

However, when I try to train the model from scratch
I'm getting, lower performance. (about 1pt of f-score)
I'm able to download your model and reproduce de results in your paper but I'm not able to retrain it.

I believe this may be due to a difference in the random seed, a different hyper-parameter configuration or a difference in software/hardware.

The configurations and random seed provided in this repo are the same used in the paper?

Kind regards,
Gabriel M

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