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

Training Loss Function prints 0 #9

Open
renespeck opened this issue Jan 13, 2021 · 2 comments
Open

Training Loss Function prints 0 #9

renespeck opened this issue Jan 13, 2021 · 2 comments

Comments

@renespeck
Copy link

Hi thanks for the code.

I successfully ran the application with the default configuration 'gat'.

I tried to run the application with a 'transformer' configuration, so encoder and decoder are transformer.
The applications starts and runs but the Training Loss Function always prints 0. (I tried several parameters in the configurations but nothing changed)

I'm not sure what happens, is my data wrong, my configuration wrong or is it maybe a bug?
My training data, are files of lines with sentences.

So do you have a example configuration and input data so run a 'transformer' based network?

Any help is highly appreciated.

Thank you.

@DwaraknathT
Copy link
Collaborator

Could you please provide some log files or error stack to trace ?

@renespeck
Copy link
Author

renespeck commented Feb 16, 2021

Hi sure, the link to the log shows the preprocess first and then the training log at line 80. My environment list starts at line 5432.

https://gist.github.com/renespeck/c6a667883cf6601d61608d07e1d337fe

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