Epoch: 0001 train_loss= 2.08723 train_acc= 0.11321 val_loss= 2.08763 val_acc= 0.10345 time= 0.67508
Epoch: 0002 train_loss= 2.08505 train_acc= 0.11321 val_loss= 2.08491 val_acc= 0.20690 time= 0.00000
Epoch: 0003 train_loss= 2.08346 train_acc= 0.13747 val_loss= 2.08332 val_acc= 0.20690 time= 0.01562
Epoch: 0004 train_loss= 2.08195 train_acc= 0.12938 val_loss= 2.08233 val_acc= 0.20690 time= 0.00000
Epoch: 0005 train_loss= 2.08060 train_acc= 0.12938 val_loss= 2.08159 val_acc= 0.20690 time= 0.01563
Epoch: 0006 train_loss= 2.07947 train_acc= 0.12938 val_loss= 2.08085 val_acc= 0.20690 time= 0.00000
Epoch: 0007 train_loss= 2.07773 train_acc= 0.12938 val_loss= 2.08011 val_acc= 0.20690 time= 0.01563
Epoch: 0008 train_loss= 2.07669 train_acc= 0.13208 val_loss= 2.07941 val_acc= 0.20690 time= 0.00000
Epoch: 0009 train_loss= 2.07570 train_acc= 0.12938 val_loss= 2.07877 val_acc= 0.20690 time= 0.00000
Epoch: 0010 train_loss= 2.07491 train_acc= 0.13208 val_loss= 2.07829 val_acc= 0.20690 time= 0.01562
Epoch: 0011 train_loss= 2.07350 train_acc= 0.12938 val_loss= 2.07795 val_acc= 0.20690 time= 0.00000
Epoch: 0012 train_loss= 2.07305 train_acc= 0.13208 val_loss= 2.07776 val_acc= 0.20690 time= 0.01563
Epoch: 0013 train_loss= 2.07112 train_acc= 0.13477 val_loss= 2.07771 val_acc= 0.20690 time= 0.00000
Epoch: 0014 train_loss= 2.06968 train_acc= 0.12938 val_loss= 2.07780 val_acc= 0.20690 time= 0.01563
Epoch: 0015 train_loss= 2.07020 train_acc= 0.13747 val_loss= 2.07804 val_acc= 0.13793 time= 0.00000
Epoch: 0016 train_loss= 2.06626 train_acc= 0.17520 val_loss= 2.07842 val_acc= 0.13793 time= 0.01562
Epoch: 0017 train_loss= 2.06615 train_acc= 0.15903 val_loss= 2.07897 val_acc= 0.13793 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.07367 accuracy= 0.08475 time= 0.00000 
