Epoch: 0001 train_loss= 2.78967 train_acc= 0.48000 val_loss= 1.12589 val_acc= 0.39344 time= 0.46110
Epoch: 0002 train_loss= 1.17859 train_acc= 0.45818 val_loss= 0.82152 val_acc= 0.50820 time= 0.01400
Epoch: 0003 train_loss= 1.11748 train_acc= 0.48182 val_loss= 0.70668 val_acc= 0.59016 time= 0.01400
Epoch: 0004 train_loss= 1.81780 train_acc= 0.50727 val_loss= 0.69693 val_acc= 0.62295 time= 0.01500
Epoch: 0005 train_loss= 1.60293 train_acc= 0.48182 val_loss= 0.68781 val_acc= 0.59016 time= 0.01200
Epoch: 0006 train_loss= 0.85921 train_acc= 0.49091 val_loss= 0.68822 val_acc= 0.55738 time= 0.01400
Epoch: 0007 train_loss= 0.92548 train_acc= 0.47273 val_loss= 0.69181 val_acc= 0.57377 time= 0.01400
Epoch: 0008 train_loss= 0.97704 train_acc= 0.52909 val_loss= 0.71676 val_acc= 0.55738 time= 0.01300
Epoch: 0009 train_loss= 1.25766 train_acc= 0.48545 val_loss= 0.78203 val_acc= 0.52459 time= 0.01500
Epoch: 0010 train_loss= 0.91868 train_acc= 0.46545 val_loss= 0.84560 val_acc= 0.49180 time= 0.01400
Epoch: 0011 train_loss= 0.90293 train_acc= 0.52000 val_loss= 0.91360 val_acc= 0.47541 time= 0.01500
Epoch: 0012 train_loss= 1.05412 train_acc= 0.46545 val_loss= 0.94268 val_acc= 0.47541 time= 0.01500
Early stopping...
Optimization Finished!
Test set results: cost= 0.83376 accuracy= 0.50820 time= 0.00500 
