Epoch: 0001 train_loss= 2.07868 train_acc= 0.16352 val_loss= 2.08269 val_acc= 0.06897 time= 0.31252
Epoch: 0002 train_loss= 2.06747 train_acc= 0.15094 val_loss= 2.07423 val_acc= 0.10345 time= 0.01563
Epoch: 0003 train_loss= 2.07424 train_acc= 0.13836 val_loss= 2.06514 val_acc= 0.13793 time= 0.01563
Epoch: 0004 train_loss= 2.06542 train_acc= 0.20126 val_loss= 2.05957 val_acc= 0.20690 time= 0.01563
Epoch: 0005 train_loss= 2.06604 train_acc= 0.16352 val_loss= 2.05987 val_acc= 0.20690 time= 0.01563
Epoch: 0006 train_loss= 2.06582 train_acc= 0.16352 val_loss= 2.06289 val_acc= 0.20690 time= 0.01562
Epoch: 0007 train_loss= 2.04102 train_acc= 0.17610 val_loss= 2.06205 val_acc= 0.20690 time= 0.01563
Epoch: 0008 train_loss= 2.05100 train_acc= 0.17610 val_loss= 2.05685 val_acc= 0.20690 time= 0.01562
Epoch: 0009 train_loss= 2.01706 train_acc= 0.23899 val_loss= 2.05009 val_acc= 0.20690 time= 0.00000
Epoch: 0010 train_loss= 2.07003 train_acc= 0.17610 val_loss= 2.04152 val_acc= 0.13793 time= 0.01563
Epoch: 0011 train_loss= 2.04387 train_acc= 0.20126 val_loss= 2.03916 val_acc= 0.17241 time= 0.01563
Epoch: 0012 train_loss= 2.04300 train_acc= 0.19497 val_loss= 2.04070 val_acc= 0.20690 time= 0.01563
Epoch: 0013 train_loss= 1.99883 train_acc= 0.23270 val_loss= 2.04430 val_acc= 0.17241 time= 0.01563
Epoch: 0014 train_loss= 2.03195 train_acc= 0.18239 val_loss= 2.04726 val_acc= 0.13793 time= 0.01563
Epoch: 0015 train_loss= 2.00679 train_acc= 0.20755 val_loss= 2.05059 val_acc= 0.03448 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.07526 accuracy= 0.11864 time= 0.01563 
