Epoch: 0001 train_loss= 2.08576 train_acc= 0.14286 val_loss= 2.08392 val_acc= 0.10345 time= 0.32815
Epoch: 0002 train_loss= 2.08395 train_acc= 0.14555 val_loss= 2.08201 val_acc= 0.10345 time= 0.01563
Epoch: 0003 train_loss= 2.08220 train_acc= 0.14555 val_loss= 2.08045 val_acc= 0.10345 time= 0.00000
Epoch: 0004 train_loss= 2.08042 train_acc= 0.14555 val_loss= 2.07890 val_acc= 0.10345 time= 0.01563
Epoch: 0005 train_loss= 2.07911 train_acc= 0.14555 val_loss= 2.07734 val_acc= 0.10345 time= 0.01563
Epoch: 0006 train_loss= 2.07774 train_acc= 0.14286 val_loss= 2.07593 val_acc= 0.10345 time= 0.00000
Epoch: 0007 train_loss= 2.07602 train_acc= 0.14555 val_loss= 2.07472 val_acc= 0.10345 time= 0.01562
Epoch: 0008 train_loss= 2.07443 train_acc= 0.14286 val_loss= 2.07379 val_acc= 0.10345 time= 0.01563
Epoch: 0009 train_loss= 2.07298 train_acc= 0.14555 val_loss= 2.07308 val_acc= 0.10345 time= 0.00000
Epoch: 0010 train_loss= 2.07069 train_acc= 0.14555 val_loss= 2.07257 val_acc= 0.10345 time= 0.01563
Epoch: 0011 train_loss= 2.06970 train_acc= 0.14286 val_loss= 2.07222 val_acc= 0.10345 time= 0.01562
Epoch: 0012 train_loss= 2.06840 train_acc= 0.14016 val_loss= 2.07212 val_acc= 0.10345 time= 0.00000
Epoch: 0013 train_loss= 2.06722 train_acc= 0.13208 val_loss= 2.07219 val_acc= 0.13793 time= 0.01563
Epoch: 0014 train_loss= 2.06600 train_acc= 0.14016 val_loss= 2.07250 val_acc= 0.13793 time= 0.01563
Epoch: 0015 train_loss= 2.06386 train_acc= 0.16173 val_loss= 2.07295 val_acc= 0.13793 time= 0.00000
Epoch: 0016 train_loss= 2.06251 train_acc= 0.16442 val_loss= 2.07364 val_acc= 0.13793 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.04110 accuracy= 0.13559 time= 0.00000 
