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

Potential Exploding Gradients Problem? #7

Open
navajain19 opened this issue Aug 25, 2022 · 2 comments
Open

Potential Exploding Gradients Problem? #7

navajain19 opened this issue Aug 25, 2022 · 2 comments

Comments

@navajain19
Copy link

Hi @sophiajw! I was wondered if you have ever encountered the following problem when training your model. Based on what I've found online, it appears to be an exploding gradients problem, and I have been experimenting with different learning rate schedules. Thanks!
image

@sophiajw
Copy link
Owner

Hey navajain19,
did you use the latest version of the repo? Indeed, I also encountered this before and it was as an exploding gradient problem. In a previous commit, another user corrected a typo in the gaussian weight init (0.02 instead of 0.2), which led to the same mistake.

@navajain19
Copy link
Author

Hi - thanks for letting me know. I gaussian weight init is indeed 0.02, but I am just experimenting with another learning rate scheduler, so it could be that the LR got too high. Thanks for confirming this for me.

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