Epoch: 0001 train_loss= 2.08800 train_acc= 0.10512 val_loss= 2.08442 val_acc= 0.10345 time= 0.72002
Epoch: 0002 train_loss= 2.08606 train_acc= 0.12399 val_loss= 2.08477 val_acc= 0.17241 time= 0.00900
Epoch: 0003 train_loss= 2.08388 train_acc= 0.15364 val_loss= 2.08548 val_acc= 0.17241 time= 0.01000
Epoch: 0004 train_loss= 2.08236 train_acc= 0.15094 val_loss= 2.08643 val_acc= 0.17241 time= 0.01000
Epoch: 0005 train_loss= 2.08085 train_acc= 0.15094 val_loss= 2.08709 val_acc= 0.17241 time= 0.01100
Epoch: 0006 train_loss= 2.07984 train_acc= 0.15633 val_loss= 2.08761 val_acc= 0.17241 time= 0.01000
Epoch: 0007 train_loss= 2.07823 train_acc= 0.15094 val_loss= 2.08829 val_acc= 0.17241 time= 0.01100
Epoch: 0008 train_loss= 2.07715 train_acc= 0.15094 val_loss= 2.08924 val_acc= 0.17241 time= 0.01100
Epoch: 0009 train_loss= 2.07463 train_acc= 0.15633 val_loss= 2.09034 val_acc= 0.17241 time= 0.01500
Epoch: 0010 train_loss= 2.07399 train_acc= 0.15364 val_loss= 2.09150 val_acc= 0.17241 time= 0.01200
Epoch: 0011 train_loss= 2.07245 train_acc= 0.15903 val_loss= 2.09279 val_acc= 0.17241 time= 0.01200
Epoch: 0012 train_loss= 2.07167 train_acc= 0.16712 val_loss= 2.09426 val_acc= 0.17241 time= 0.01300
Early stopping...
Optimization Finished!
Test set results: cost= 2.05874 accuracy= 0.16949 time= 0.00500 
