Epoch: 0001 train_loss= 2.13678 train_acc= 0.10566 val_loss= 2.04323 val_acc= 0.17241 time= 0.59379
Epoch: 0002 train_loss= 2.12846 train_acc= 0.12075 val_loss= 2.05562 val_acc= 0.20690 time= 0.01562
Epoch: 0003 train_loss= 2.11133 train_acc= 0.12830 val_loss= 2.07918 val_acc= 0.20690 time= 0.01563
Epoch: 0004 train_loss= 2.07357 train_acc= 0.13962 val_loss= 2.09901 val_acc= 0.20690 time= 0.01563
Epoch: 0005 train_loss= 2.05511 train_acc= 0.16604 val_loss= 2.11845 val_acc= 0.20690 time= 0.01562
Epoch: 0006 train_loss= 2.05781 train_acc= 0.17736 val_loss= 2.13405 val_acc= 0.17241 time= 0.01563
Epoch: 0007 train_loss= 2.04406 train_acc= 0.18113 val_loss= 2.15133 val_acc= 0.17241 time= 0.00000
Epoch: 0008 train_loss= 2.06211 train_acc= 0.18113 val_loss= 2.16649 val_acc= 0.13793 time= 0.01563
Epoch: 0009 train_loss= 2.04793 train_acc= 0.19245 val_loss= 2.17916 val_acc= 0.06897 time= 0.01562
Epoch: 0010 train_loss= 2.05181 train_acc= 0.18491 val_loss= 2.18848 val_acc= 0.06897 time= 0.01563
Epoch: 0011 train_loss= 2.04218 train_acc= 0.21509 val_loss= 2.19787 val_acc= 0.03448 time= 0.01563
Epoch: 0012 train_loss= 2.04875 train_acc= 0.20000 val_loss= 2.20356 val_acc= 0.03448 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.08153 accuracy= 0.16949 time= 0.00000 
