I am -loving- this combined Rectifed Adam (RAdam) + LookAhead optimizer. It's freaky stable and powerful, especially for my purposes. Only weird thing to keep in mind- I've had to multiply my learning rates by over 100x to maximally take advantage.https://medium.com/@lessw/new-deep-learning-optimizer-ranger-synergistic-combination-of-radam-lookahead-for-the-best-of-2dc83f79a48d …
-
-
Ooohhh good to hear that, my last classifier (a dog breed classifier based on the Stanford dataset, 120 classes all very close together) took ages to train with LR 10e-6 to 10e-4. Can't wait to test this new RAdam with a huge LR :)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.