It seems you have faced the problem of exploding gradients (which has been mentioned elsewhere: DestVI Tensor Nan Error). Let’s use smaller learning_rate to see if it can help troubleshoot the problem.
Best,
It seems you have faced the problem of exploding gradients (which has been mentioned elsewhere: DestVI Tensor Nan Error). Let’s use smaller learning_rate to see if it can help troubleshoot the problem.
Best,