Epoch: 0001 train_loss= 2.10493 train_acc= 0.11698 val_loss= 2.06689 val_acc= 0.13793 time= 0.37615
Epoch: 0002 train_loss= 2.08782 train_acc= 0.12075 val_loss= 2.06460 val_acc= 0.17241 time= 0.00800
Epoch: 0003 train_loss= 2.08282 train_acc= 0.12830 val_loss= 2.06284 val_acc= 0.20690 time= 0.00800
Epoch: 0004 train_loss= 2.07638 train_acc= 0.15849 val_loss= 2.06130 val_acc= 0.17241 time= 0.00800
Epoch: 0005 train_loss= 2.06914 train_acc= 0.14717 val_loss= 2.05959 val_acc= 0.24138 time= 0.00700
Epoch: 0006 train_loss= 2.07757 train_acc= 0.15472 val_loss= 2.05823 val_acc= 0.24138 time= 0.00700
Epoch: 0007 train_loss= 2.06833 train_acc= 0.13585 val_loss= 2.05681 val_acc= 0.31034 time= 0.00800
Epoch: 0008 train_loss= 2.05401 train_acc= 0.15472 val_loss= 2.05567 val_acc= 0.31034 time= 0.00700
Epoch: 0009 train_loss= 2.05748 train_acc= 0.15472 val_loss= 2.05485 val_acc= 0.31034 time= 0.00900
Epoch: 0010 train_loss= 2.05843 train_acc= 0.13962 val_loss= 2.05438 val_acc= 0.31034 time= 0.00800
Epoch: 0011 train_loss= 2.05472 train_acc= 0.14717 val_loss= 2.05433 val_acc= 0.31034 time= 0.00800
Epoch: 0012 train_loss= 2.06116 train_acc= 0.16981 val_loss= 2.05510 val_acc= 0.27586 time= 0.00800
Epoch: 0013 train_loss= 2.05281 train_acc= 0.17736 val_loss= 2.05614 val_acc= 0.27586 time= 0.00700
Epoch: 0014 train_loss= 2.06135 train_acc= 0.17358 val_loss= 2.05779 val_acc= 0.27586 time= 0.00800
Early stopping...
Optimization Finished!
Test set results: cost= 2.01562 accuracy= 0.23729 time= 0.00300 
