-
Notifications
You must be signed in to change notification settings - Fork 184
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
updates returns zeros #1101
Comments
Hello @GeophyAI, It depends on the optimizer. We cannot help without a concrete example of what you are trying to do. |
I'm using optax.masked and optax.chain for assigning different learning rate to different paramemter groups, something like the following implementation:
When my model only have 1 group parameter, it works fine, when the parameter is larger than 1, the updates always be zeros. |
I found that when I replace the line |
I'm using optax for training something,
updates, opt_state = opt.update(gradient, opt_state)
, when I check the updates, I found that it contains only zeros, but the gradients do have values. In which situations this goona be happen?The text was updated successfully, but these errors were encountered: