Epoch: 0001 train_loss= 1.39359 train_acc= 0.32123 val_loss= 1.41736 val_acc= 0.23214 time= 0.82819
Epoch: 0002 train_loss= 1.39192 train_acc= 0.32682 val_loss= 1.41124 val_acc= 0.23214 time= 0.00000
Epoch: 0003 train_loss= 1.38984 train_acc= 0.32821 val_loss= 1.40539 val_acc= 0.23214 time= 0.01562
Epoch: 0004 train_loss= 1.38581 train_acc= 0.32682 val_loss= 1.39977 val_acc= 0.23214 time= 0.00000
Epoch: 0005 train_loss= 1.38500 train_acc= 0.32542 val_loss= 1.39439 val_acc= 0.23214 time= 0.01563
Epoch: 0006 train_loss= 1.38222 train_acc= 0.32682 val_loss= 1.38937 val_acc= 0.23214 time= 0.00000
Epoch: 0007 train_loss= 1.38015 train_acc= 0.32682 val_loss= 1.38491 val_acc= 0.23214 time= 0.02118
Epoch: 0008 train_loss= 1.37868 train_acc= 0.32682 val_loss= 1.38119 val_acc= 0.23214 time= 0.00000
Epoch: 0009 train_loss= 1.37706 train_acc= 0.32682 val_loss= 1.37829 val_acc= 0.23214 time= 0.01050
Epoch: 0010 train_loss= 1.37566 train_acc= 0.32682 val_loss= 1.37616 val_acc= 0.23214 time= 0.01563
Epoch: 0011 train_loss= 1.37510 train_acc= 0.32682 val_loss= 1.37491 val_acc= 0.23214 time= 0.00000
Epoch: 0012 train_loss= 1.37388 train_acc= 0.32682 val_loss= 1.37445 val_acc= 0.23214 time= 0.01563
Epoch: 0013 train_loss= 1.37395 train_acc= 0.32542 val_loss= 1.37459 val_acc= 0.23214 time= 0.00000
Epoch: 0014 train_loss= 1.37293 train_acc= 0.32682 val_loss= 1.37493 val_acc= 0.23214 time= 0.01563
Epoch: 0015 train_loss= 1.37410 train_acc= 0.32682 val_loss= 1.37539 val_acc= 0.23214 time= 0.00000
Epoch: 0016 train_loss= 1.37379 train_acc= 0.32682 val_loss= 1.37619 val_acc= 0.23214 time= 0.01563
Epoch: 0017 train_loss= 1.37155 train_acc= 0.32682 val_loss= 1.37725 val_acc= 0.23214 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.37713 accuracy= 0.29204 time= 0.00000 
