Epoch: 0001 train_loss= 2.09855 train_acc= 0.12453 val_loss= 2.06649 val_acc= 0.13793 time= 0.39680
Epoch: 0002 train_loss= 2.08614 train_acc= 0.14717 val_loss= 2.07330 val_acc= 0.13793 time= 0.00800
Epoch: 0003 train_loss= 2.07476 train_acc= 0.12453 val_loss= 2.07965 val_acc= 0.13793 time= 0.00700
Epoch: 0004 train_loss= 2.07889 train_acc= 0.12075 val_loss= 2.08609 val_acc= 0.10345 time= 0.00700
Epoch: 0005 train_loss= 2.07542 train_acc= 0.16981 val_loss= 2.09215 val_acc= 0.10345 time= 0.00800
Epoch: 0006 train_loss= 2.06339 train_acc= 0.16226 val_loss= 2.09833 val_acc= 0.06897 time= 0.00800
Epoch: 0007 train_loss= 2.06213 train_acc= 0.13208 val_loss= 2.10395 val_acc= 0.03448 time= 0.00900
Epoch: 0008 train_loss= 2.05220 train_acc= 0.14340 val_loss= 2.10978 val_acc= 0.00000 time= 0.00800
Epoch: 0009 train_loss= 2.05740 train_acc= 0.12453 val_loss= 2.11546 val_acc= 0.00000 time= 0.00900
Epoch: 0010 train_loss= 2.04827 train_acc= 0.17358 val_loss= 2.12041 val_acc= 0.00000 time= 0.00700
Epoch: 0011 train_loss= 2.05802 train_acc= 0.14717 val_loss= 2.12557 val_acc= 0.00000 time= 0.00700
Epoch: 0012 train_loss= 2.04558 train_acc= 0.15849 val_loss= 2.13062 val_acc= 0.00000 time= 0.00800
Early stopping...
Optimization Finished!
Test set results: cost= 2.03135 accuracy= 0.08475 time= 0.00400 
