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 @ethancaballero, I was hard to reproduce results from meta optimizer papers so at some point I just gave up and shared this code just as an example of how it can be implemented in PyTorch.
Meta optimizers are very slow so I didn't validate any design decisions properly.
In line 81 & 135 of meta_optimizer.py
Why do you input grads & params (and loss as well in line 135) into metaoptimizer?
Did you try with & without, and one version worked better? In 1606.04474, they seem to just input grads into metaoptimizer.
The text was updated successfully, but these errors were encountered: