Epoch: 0001 train_loss= 2.07470 train_acc= 0.16173 val_loss= 2.07726 val_acc= 0.17241 time= 0.91498
Epoch: 0002 train_loss= 2.07276 train_acc= 0.16173 val_loss= 2.07302 val_acc= 0.17241 time= 0.00500
Epoch: 0003 train_loss= 2.07120 train_acc= 0.14016 val_loss= 2.06896 val_acc= 0.17241 time= 0.00500
Epoch: 0004 train_loss= 2.06864 train_acc= 0.14286 val_loss= 2.06528 val_acc= 0.17241 time= 0.00600
Epoch: 0005 train_loss= 2.06685 train_acc= 0.15633 val_loss= 2.06185 val_acc= 0.17241 time= 0.00500
Epoch: 0006 train_loss= 2.06318 train_acc= 0.16981 val_loss= 2.05897 val_acc= 0.17241 time= 0.00500
Epoch: 0007 train_loss= 2.06100 train_acc= 0.16442 val_loss= 2.05658 val_acc= 0.17241 time= 0.00500
Epoch: 0008 train_loss= 2.05877 train_acc= 0.15903 val_loss= 2.05464 val_acc= 0.17241 time= 0.00500
Epoch: 0009 train_loss= 2.05634 train_acc= 0.16173 val_loss= 2.05318 val_acc= 0.17241 time= 0.00500
Epoch: 0010 train_loss= 2.05786 train_acc= 0.15364 val_loss= 2.05226 val_acc= 0.17241 time= 0.00500
Epoch: 0011 train_loss= 2.05521 train_acc= 0.16173 val_loss= 2.05183 val_acc= 0.17241 time= 0.00600
Epoch: 0012 train_loss= 2.05215 train_acc= 0.16712 val_loss= 2.05182 val_acc= 0.17241 time= 0.00600
Epoch: 0013 train_loss= 2.05386 train_acc= 0.15903 val_loss= 2.05214 val_acc= 0.17241 time= 0.00500
Epoch: 0014 train_loss= 2.05338 train_acc= 0.15903 val_loss= 2.05278 val_acc= 0.17241 time= 0.00500
Epoch: 0015 train_loss= 2.05254 train_acc= 0.16173 val_loss= 2.05370 val_acc= 0.17241 time= 0.00600
Epoch: 0016 train_loss= 2.05174 train_acc= 0.15633 val_loss= 2.05478 val_acc= 0.17241 time= 0.00600
Early stopping...
Optimization Finished!
Test set results: cost= 2.07298 accuracy= 0.18644 time= 0.00200 
