Epoch: 0001 train_loss= 2.19295 train_acc= 0.09811 val_loss= 2.04867 val_acc= 0.20690 time= 0.55058
Epoch: 0002 train_loss= 2.12964 train_acc= 0.11321 val_loss= 2.06431 val_acc= 0.17241 time= 0.01700
Epoch: 0003 train_loss= 2.09906 train_acc= 0.14340 val_loss= 2.07872 val_acc= 0.13793 time= 0.01700
Epoch: 0004 train_loss= 2.08307 train_acc= 0.13585 val_loss= 2.09296 val_acc= 0.17241 time= 0.01800
Epoch: 0005 train_loss= 2.06563 train_acc= 0.16604 val_loss= 2.10146 val_acc= 0.17241 time= 0.01800
Epoch: 0006 train_loss= 2.05180 train_acc= 0.14717 val_loss= 2.10862 val_acc= 0.17241 time= 0.01800
Epoch: 0007 train_loss= 2.04865 train_acc= 0.19245 val_loss= 2.11299 val_acc= 0.13793 time= 0.01600
Epoch: 0008 train_loss= 2.04959 train_acc= 0.15472 val_loss= 2.11775 val_acc= 0.13793 time= 0.01600
Epoch: 0009 train_loss= 2.04122 train_acc= 0.20755 val_loss= 2.12328 val_acc= 0.13793 time= 0.01700
Epoch: 0010 train_loss= 2.05214 train_acc= 0.19245 val_loss= 2.12740 val_acc= 0.13793 time= 0.01700
Epoch: 0011 train_loss= 2.07530 train_acc= 0.20377 val_loss= 2.12671 val_acc= 0.13793 time= 0.01700
Epoch: 0012 train_loss= 2.05723 train_acc= 0.19245 val_loss= 2.12488 val_acc= 0.13793 time= 0.01600
Early stopping...
Optimization Finished!
Test set results: cost= 2.06022 accuracy= 0.18644 time= 0.00800 
