Epoch: 0001 train_loss= 2.09374 train_acc= 0.11321 val_loss= 2.07363 val_acc= 0.10345 time= 0.07812
Epoch: 0002 train_loss= 2.08482 train_acc= 0.12579 val_loss= 2.07006 val_acc= 0.20690 time= 0.00000
Epoch: 0003 train_loss= 2.08722 train_acc= 0.11321 val_loss= 2.06711 val_acc= 0.20690 time= 0.01563
Epoch: 0004 train_loss= 2.08409 train_acc= 0.14465 val_loss= 2.06455 val_acc= 0.20690 time= 0.01563
Epoch: 0005 train_loss= 2.07864 train_acc= 0.14465 val_loss= 2.06237 val_acc= 0.20690 time= 0.00000
Epoch: 0006 train_loss= 2.07580 train_acc= 0.17610 val_loss= 2.06048 val_acc= 0.20690 time= 0.01563
Epoch: 0007 train_loss= 2.06865 train_acc= 0.15723 val_loss= 2.05892 val_acc= 0.20690 time= 0.00000
Epoch: 0008 train_loss= 2.06618 train_acc= 0.16352 val_loss= 2.05773 val_acc= 0.20690 time= 0.01563
Epoch: 0009 train_loss= 2.06838 train_acc= 0.15723 val_loss= 2.05690 val_acc= 0.20690 time= 0.00000
Epoch: 0010 train_loss= 2.07066 train_acc= 0.16352 val_loss= 2.05687 val_acc= 0.20690 time= 0.01563
Epoch: 0011 train_loss= 2.06435 train_acc= 0.16352 val_loss= 2.05725 val_acc= 0.20690 time= 0.00000
Epoch: 0012 train_loss= 2.06122 train_acc= 0.16352 val_loss= 2.05781 val_acc= 0.20690 time= 0.01563
Epoch: 0013 train_loss= 2.06591 train_acc= 0.15723 val_loss= 2.05831 val_acc= 0.20690 time= 0.01563
Epoch: 0014 train_loss= 2.05572 train_acc= 0.16352 val_loss= 2.05912 val_acc= 0.20690 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08435 accuracy= 0.13559 time= 0.00000 
