Epoch: 0001 train_loss= 2.97085 train_acc= 0.31006 val_loss= 1.85189 val_acc= 0.25000 time= 1.00236
Epoch: 0002 train_loss= 2.17267 train_acc= 0.29330 val_loss= 1.46078 val_acc= 0.39286 time= 0.01563
Epoch: 0003 train_loss= 1.89214 train_acc= 0.26536 val_loss= 1.43629 val_acc= 0.44643 time= 0.03125
Epoch: 0004 train_loss= 2.18540 train_acc= 0.25838 val_loss= 1.47247 val_acc= 0.42857 time= 0.03125
Epoch: 0005 train_loss= 2.04605 train_acc= 0.24860 val_loss= 1.51736 val_acc= 0.33929 time= 0.01572
Epoch: 0006 train_loss= 1.98608 train_acc= 0.26955 val_loss= 1.51484 val_acc= 0.28571 time= 0.03126
Epoch: 0007 train_loss= 1.65547 train_acc= 0.27793 val_loss= 1.48116 val_acc= 0.30357 time= 0.03125
Epoch: 0008 train_loss= 1.93361 train_acc= 0.25140 val_loss= 1.42959 val_acc= 0.30357 time= 0.01563
Epoch: 0009 train_loss= 1.53945 train_acc= 0.27095 val_loss= 1.39653 val_acc= 0.33929 time= 0.03125
Epoch: 0010 train_loss= 1.42331 train_acc= 0.25000 val_loss= 1.38945 val_acc= 0.39286 time= 0.01563
Epoch: 0011 train_loss= 1.57510 train_acc= 0.27095 val_loss= 1.39215 val_acc= 0.41071 time= 0.03125
Epoch: 0012 train_loss= 1.44980 train_acc= 0.26257 val_loss= 1.39237 val_acc= 0.39286 time= 0.02120
Epoch: 0013 train_loss= 1.48313 train_acc= 0.27514 val_loss= 1.39247 val_acc= 0.35714 time= 0.02613
Epoch: 0014 train_loss= 1.44328 train_acc= 0.23045 val_loss= 1.39247 val_acc= 0.33929 time= 0.01563
Epoch: 0015 train_loss= 1.40639 train_acc= 0.23603 val_loss= 1.39255 val_acc= 0.28571 time= 0.03125
Epoch: 0016 train_loss= 1.52416 train_acc= 0.27654 val_loss= 1.39296 val_acc= 0.26786 time= 0.01563
Epoch: 0017 train_loss= 1.41345 train_acc= 0.25140 val_loss= 1.39328 val_acc= 0.25000 time= 0.03125
Epoch: 0018 train_loss= 1.39828 train_acc= 0.29330 val_loss= 1.39361 val_acc= 0.21429 time= 0.03125
Epoch: 0019 train_loss= 1.47202 train_acc= 0.28631 val_loss= 1.39402 val_acc= 0.25000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.39606 accuracy= 0.25664 time= 0.01562 
