Epoch: 0001 train_loss= 2.08594 train_acc= 0.15472 val_loss= 2.10564 val_acc= 0.20690 time= 0.49798
Epoch: 0002 train_loss= 2.08144 train_acc= 0.15472 val_loss= 2.10720 val_acc= 0.20690 time= 0.01562
Epoch: 0003 train_loss= 2.07867 train_acc= 0.15472 val_loss= 2.10859 val_acc= 0.20690 time= 0.00000
Epoch: 0004 train_loss= 2.07377 train_acc= 0.15472 val_loss= 2.10983 val_acc= 0.20690 time= 0.00000
Epoch: 0005 train_loss= 2.07321 train_acc= 0.15472 val_loss= 2.11061 val_acc= 0.20690 time= 0.01563
Epoch: 0006 train_loss= 2.07011 train_acc= 0.15472 val_loss= 2.11122 val_acc= 0.20690 time= 0.00000
Epoch: 0007 train_loss= 2.06714 train_acc= 0.15472 val_loss= 2.11190 val_acc= 0.20690 time= 0.00000
Epoch: 0008 train_loss= 2.06509 train_acc= 0.15472 val_loss= 2.11234 val_acc= 0.20690 time= 0.00000
Epoch: 0009 train_loss= 2.06145 train_acc= 0.15849 val_loss= 2.11261 val_acc= 0.20690 time= 0.01563
Epoch: 0010 train_loss= 2.05933 train_acc= 0.15472 val_loss= 2.11292 val_acc= 0.20690 time= 0.00000
Epoch: 0011 train_loss= 2.05888 train_acc= 0.15472 val_loss= 2.11320 val_acc= 0.20690 time= 0.00000
Epoch: 0012 train_loss= 2.05752 train_acc= 0.15472 val_loss= 2.11342 val_acc= 0.20690 time= 0.01971
Early stopping...
Optimization Finished!
Test set results: cost= 2.04862 accuracy= 0.16949 time= 0.00101 
