Epoch: 0001 train_loss= 2.12727 train_acc= 0.09057 val_loss= 2.10231 val_acc= 0.13793 time= 0.39657
Epoch: 0002 train_loss= 2.10267 train_acc= 0.08679 val_loss= 2.09943 val_acc= 0.13793 time= 0.00900
Epoch: 0003 train_loss= 2.10583 train_acc= 0.08679 val_loss= 2.09682 val_acc= 0.13793 time= 0.00800
Epoch: 0004 train_loss= 2.10103 train_acc= 0.08679 val_loss= 2.09463 val_acc= 0.10345 time= 0.00900
Epoch: 0005 train_loss= 2.09916 train_acc= 0.12453 val_loss= 2.09279 val_acc= 0.06897 time= 0.00900
Epoch: 0006 train_loss= 2.08442 train_acc= 0.11698 val_loss= 2.09148 val_acc= 0.13793 time= 0.00800
Epoch: 0007 train_loss= 2.07922 train_acc= 0.13208 val_loss= 2.09065 val_acc= 0.10345 time= 0.00700
Epoch: 0008 train_loss= 2.07699 train_acc= 0.14340 val_loss= 2.09012 val_acc= 0.10345 time= 0.00700
Epoch: 0009 train_loss= 2.07086 train_acc= 0.14717 val_loss= 2.08978 val_acc= 0.17241 time= 0.00800
Epoch: 0010 train_loss= 2.07655 train_acc= 0.15849 val_loss= 2.08966 val_acc= 0.17241 time= 0.00700
Epoch: 0011 train_loss= 2.06372 train_acc= 0.20755 val_loss= 2.08979 val_acc= 0.17241 time= 0.00800
Epoch: 0012 train_loss= 2.06498 train_acc= 0.16981 val_loss= 2.09017 val_acc= 0.17241 time= 0.00800
Epoch: 0013 train_loss= 2.06287 train_acc= 0.16604 val_loss= 2.09083 val_acc= 0.17241 time= 0.00700
Epoch: 0014 train_loss= 2.06720 train_acc= 0.17736 val_loss= 2.09153 val_acc= 0.17241 time= 0.00800
Early stopping...
Optimization Finished!
Test set results: cost= 2.08287 accuracy= 0.15254 time= 0.00300 
