Epoch: 0001 train_loss= 1.39049 train_acc= 0.28516 val_loss= 1.37681 val_acc= 0.39286 time= 0.53129
Epoch: 0002 train_loss= 1.38745 train_acc= 0.28711 val_loss= 1.37238 val_acc= 0.39286 time= 0.00000
Epoch: 0003 train_loss= 1.38632 train_acc= 0.28711 val_loss= 1.36815 val_acc= 0.39286 time= 0.01562
Epoch: 0004 train_loss= 1.38414 train_acc= 0.28711 val_loss= 1.36398 val_acc= 0.39286 time= 0.01563
Epoch: 0005 train_loss= 1.38256 train_acc= 0.28711 val_loss= 1.35999 val_acc= 0.39286 time= 0.00000
Epoch: 0006 train_loss= 1.38151 train_acc= 0.28711 val_loss= 1.35615 val_acc= 0.39286 time= 0.01562
Epoch: 0007 train_loss= 1.37984 train_acc= 0.28711 val_loss= 1.35260 val_acc= 0.39286 time= 0.00000
Epoch: 0008 train_loss= 1.37867 train_acc= 0.28711 val_loss= 1.34937 val_acc= 0.39286 time= 0.01563
Epoch: 0009 train_loss= 1.37901 train_acc= 0.28711 val_loss= 1.34676 val_acc= 0.39286 time= 0.00000
Epoch: 0010 train_loss= 1.37818 train_acc= 0.28516 val_loss= 1.34454 val_acc= 0.39286 time= 0.01563
Epoch: 0011 train_loss= 1.37798 train_acc= 0.28711 val_loss= 1.34277 val_acc= 0.39286 time= 0.00000
Epoch: 0012 train_loss= 1.37722 train_acc= 0.28711 val_loss= 1.34153 val_acc= 0.39286 time= 0.01563
Epoch: 0013 train_loss= 1.37730 train_acc= 0.28711 val_loss= 1.34075 val_acc= 0.39286 time= 0.00000
Epoch: 0014 train_loss= 1.37850 train_acc= 0.28711 val_loss= 1.34043 val_acc= 0.39286 time= 0.01562
Epoch: 0015 train_loss= 1.37673 train_acc= 0.28711 val_loss= 1.34042 val_acc= 0.39286 time= 0.00000
Epoch: 0016 train_loss= 1.37690 train_acc= 0.28711 val_loss= 1.34067 val_acc= 0.39286 time= 0.01563
Epoch: 0017 train_loss= 1.37529 train_acc= 0.28711 val_loss= 1.34113 val_acc= 0.39286 time= 0.00000
Epoch: 0018 train_loss= 1.37812 train_acc= 0.28906 val_loss= 1.34194 val_acc= 0.39286 time= 0.01563
Epoch: 0019 train_loss= 1.37626 train_acc= 0.28906 val_loss= 1.34270 val_acc= 0.39286 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.38669 accuracy= 0.31858 time= 0.01563 
