So indeed with cross-entropy loss I see two plateaus! Here’s rank 2:
(note that I’ve offset the loss to so that equality of Z and C is zero loss)
I have trouble getting rank 10 to find the zero-loss solution:
But the phenomenology at full rank is unchanged:
So indeed with cross-entropy loss I see two plateaus! Here’s rank 2:
(note that I’ve offset the loss to so that equality of Z and C is zero loss)
I have trouble getting rank 10 to find the zero-loss solution:
But the phenomenology at full rank is unchanged: