Epoch: 0001 train_loss= 1.39663 train_acc= 0.23242 val_loss= 1.37788 val_acc= 0.37500 time= 0.51566
Epoch: 0002 train_loss= 1.39164 train_acc= 0.23242 val_loss= 1.37914 val_acc= 0.37500 time= 0.01563
Epoch: 0003 train_loss= 1.38896 train_acc= 0.23242 val_loss= 1.38030 val_acc= 0.30357 time= 0.00000
Epoch: 0004 train_loss= 1.38675 train_acc= 0.28516 val_loss= 1.38166 val_acc= 0.28571 time= 0.01563
Epoch: 0005 train_loss= 1.38440 train_acc= 0.32227 val_loss= 1.38275 val_acc= 0.28571 time= 0.00000
Epoch: 0006 train_loss= 1.38243 train_acc= 0.32227 val_loss= 1.38395 val_acc= 0.28571 time= 0.01562
Epoch: 0007 train_loss= 1.38082 train_acc= 0.32227 val_loss= 1.38563 val_acc= 0.28571 time= 0.00000
Epoch: 0008 train_loss= 1.38030 train_acc= 0.32227 val_loss= 1.38726 val_acc= 0.28571 time= 0.01563
Epoch: 0009 train_loss= 1.37870 train_acc= 0.32227 val_loss= 1.38895 val_acc= 0.28571 time= 0.00000
Epoch: 0010 train_loss= 1.37716 train_acc= 0.32227 val_loss= 1.39050 val_acc= 0.28571 time= 0.01563
Epoch: 0011 train_loss= 1.37590 train_acc= 0.32227 val_loss= 1.39182 val_acc= 0.28571 time= 0.00000
Epoch: 0012 train_loss= 1.37453 train_acc= 0.32227 val_loss= 1.39282 val_acc= 0.28571 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 1.38416 accuracy= 0.28319 time= 0.00000 
