JordanAsh

Hello, The default learning rate in our implementation is different from what we use in our paper. To me it looks like it's probably too low -- I'd try increasing...

I'm not sure what you mean by task model. Even though different learning rates may all achieve perfect training accuracy, they often produce different test accuracies. On Wed, Jan 6,...

Good find! Yes, I actually have that changed on my end but haven't pushed to git yet. I'll do so as soon as I get a moment. That said, barring...

Yes, the default learning rate isn't correct. It should be an order of magnitude lower, I believe. On Wed, Jul 29, 2020 at 7:21 PM Sungwon Han wrote: > Thank...

Right, I'm saying that I believe the learning rate in the paper is off by an order of magnitude. On Wed, Jul 29, 2020 at 10:56 PM Sungwon Han wrote:...