During training, train loss and validation loss became nan, does this matter?

[nce3xin]

When I ran cnn.py, during training, train loss and validation loss became nan after step 50, is this normal? I wonder why losses remains nan……

[leonJCY]

Me too, Do you use gpu ? I had this problem when I use CPU to train.

[leonJCY]

If you use gpu, it is 2080ti for me, then all the problems will be gone

[wentixiaogege]

10 step becaome nan.. using cpu~~~

[wentixiaogege]

change lr ,10 times smaller , work~;