Yu-Gong

Loss nan occurred in the fastdiff training time

3

Hello, Huang ! Will there be a loss nan when training fastdiff without loading preweights? How to handle the parameters or adjust them if this happens.and the loss always nonconvergence。how...

Could you provide the training script and the training sequence of several models in it?

清问能否提供训练脚本，还有里面的几个模型的训练顺序是怎么样的？