Epoch: 0001 train_loss= 2.10193 train_acc= 0.11321 val_loss= 2.07576 val_acc= 0.13793 time= 0.28127
Epoch: 0002 train_loss= 2.08470 train_acc= 0.12399 val_loss= 2.07156 val_acc= 0.17241 time= 0.01562
Epoch: 0003 train_loss= 2.08413 train_acc= 0.15633 val_loss= 2.06789 val_acc= 0.20690 time= 0.01563
Epoch: 0004 train_loss= 2.08637 train_acc= 0.12399 val_loss= 2.06470 val_acc= 0.27586 time= 0.00000
Epoch: 0005 train_loss= 2.08063 train_acc= 0.14016 val_loss= 2.06215 val_acc= 0.27586 time= 0.01563
Epoch: 0006 train_loss= 2.07149 train_acc= 0.17251 val_loss= 2.05965 val_acc= 0.27586 time= 0.01563
Epoch: 0007 train_loss= 2.07433 train_acc= 0.15364 val_loss= 2.05753 val_acc= 0.20690 time= 0.00000
Epoch: 0008 train_loss= 2.07292 train_acc= 0.16173 val_loss= 2.05581 val_acc= 0.20690 time= 0.01563
Epoch: 0009 train_loss= 2.06971 train_acc= 0.15364 val_loss= 2.05474 val_acc= 0.13793 time= 0.01563
Epoch: 0010 train_loss= 2.06406 train_acc= 0.17790 val_loss= 2.05382 val_acc= 0.10345 time= 0.01563
Epoch: 0011 train_loss= 2.06124 train_acc= 0.16981 val_loss= 2.05344 val_acc= 0.10345 time= 0.00000
Epoch: 0012 train_loss= 2.06514 train_acc= 0.17520 val_loss= 2.05334 val_acc= 0.10345 time= 0.01563
Epoch: 0013 train_loss= 2.06222 train_acc= 0.17520 val_loss= 2.05325 val_acc= 0.10345 time= 0.01563
Epoch: 0014 train_loss= 2.05790 train_acc= 0.18868 val_loss= 2.05303 val_acc= 0.06897 time= 0.00000
Epoch: 0015 train_loss= 2.06497 train_acc= 0.16712 val_loss= 2.05334 val_acc= 0.06897 time= 0.01563
Epoch: 0016 train_loss= 2.06246 train_acc= 0.19407 val_loss= 2.05404 val_acc= 0.06897 time= 0.00000
Epoch: 0017 train_loss= 2.06255 train_acc= 0.19946 val_loss= 2.05444 val_acc= 0.06897 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.10503 accuracy= 0.13559 time= 0.00000 
