Epoch: 0001 train_loss= 2.06926 train_acc= 0.15633 val_loss= 2.06411 val_acc= 0.27586 time= 0.29689
Epoch: 0002 train_loss= 2.07920 train_acc= 0.16981 val_loss= 2.05390 val_acc= 0.20690 time= 0.01563
Epoch: 0003 train_loss= 2.07621 train_acc= 0.17520 val_loss= 2.04548 val_acc= 0.20690 time= 0.01562
Epoch: 0004 train_loss= 2.05824 train_acc= 0.16712 val_loss= 2.03821 val_acc= 0.20690 time= 0.00000
Epoch: 0005 train_loss= 2.06281 train_acc= 0.17251 val_loss= 2.03231 val_acc= 0.20690 time= 0.01563
Epoch: 0006 train_loss= 2.06365 train_acc= 0.19407 val_loss= 2.02680 val_acc= 0.20690 time= 0.00000
Epoch: 0007 train_loss= 2.06062 train_acc= 0.17251 val_loss= 2.02197 val_acc= 0.20690 time= 0.01563
Epoch: 0008 train_loss= 2.05741 train_acc= 0.17790 val_loss= 2.01792 val_acc= 0.20690 time= 0.01563
Epoch: 0009 train_loss= 2.05793 train_acc= 0.17790 val_loss= 2.01415 val_acc= 0.20690 time= 0.00000
Epoch: 0010 train_loss= 2.04846 train_acc= 0.17251 val_loss= 2.01218 val_acc= 0.20690 time= 0.01563
Epoch: 0011 train_loss= 2.05435 train_acc= 0.17251 val_loss= 2.01016 val_acc= 0.20690 time= 0.00000
Epoch: 0012 train_loss= 2.04705 train_acc= 0.18059 val_loss= 2.00866 val_acc= 0.20690 time= 0.01563
Epoch: 0013 train_loss= 2.04693 train_acc= 0.16981 val_loss= 2.00864 val_acc= 0.17241 time= 0.01563
Epoch: 0014 train_loss= 2.05200 train_acc= 0.18059 val_loss= 2.00874 val_acc= 0.17241 time= 0.00000
Epoch: 0015 train_loss= 2.04953 train_acc= 0.16712 val_loss= 2.00971 val_acc= 0.06897 time= 0.01563
Epoch: 0016 train_loss= 2.04454 train_acc= 0.18598 val_loss= 2.01201 val_acc= 0.10345 time= 0.00000
Epoch: 0017 train_loss= 2.04144 train_acc= 0.18059 val_loss= 2.01436 val_acc= 0.06897 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 2.10177 accuracy= 0.15254 time= 0.00000 
