Closed ywb2018 closed 1 year ago
help please. 1、why excess loss do not follow the paper: max(excess-loss, 0)。
We do clip the excess loss here: https://github.com/sangmichaelxie/doremi/blob/80c8b4d5840ca83c2121f5a4b48a0170e088e574/doremi/trainer.py#L232
help please.
1、why excess loss do not follow the paper: max(excess-loss, 0)。