Yufan Andrew Liu

Same problem, did you solve this? @BingzeWu

What do you mean by mini-batch? I've trained this with a batch size of 64, but the model only considers single-batch training, and NaN values still appear after several steps....

Hi Zhiyi, not yet, but you may find the NaN in the input feature part, and mask then with average or some constant to start the training, unfortunately, I did...