You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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!
The text was updated successfully, but these errors were encountered:
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.
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.
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!

The text was updated successfully, but these errors were encountered: