Epoch: 0001 train_loss= 1.39440 train_acc= 0.20847 val_loss= 1.39252 val_acc= 0.23214 time= 0.18751
Epoch: 0002 train_loss= 1.39117 train_acc= 0.32573 val_loss= 1.39136 val_acc= 0.23214 time= 0.00000
Epoch: 0003 train_loss= 1.38824 train_acc= 0.32573 val_loss= 1.39100 val_acc= 0.23214 time= 0.01563
Epoch: 0004 train_loss= 1.38589 train_acc= 0.32573 val_loss= 1.39133 val_acc= 0.23214 time= 0.01563
Epoch: 0005 train_loss= 1.38402 train_acc= 0.32573 val_loss= 1.39214 val_acc= 0.23214 time= 0.01563
Epoch: 0006 train_loss= 1.38283 train_acc= 0.32573 val_loss= 1.39327 val_acc= 0.23214 time= 0.01563
Epoch: 0007 train_loss= 1.38186 train_acc= 0.32573 val_loss= 1.39467 val_acc= 0.23214 time= 0.00000
Epoch: 0008 train_loss= 1.38108 train_acc= 0.32573 val_loss= 1.39641 val_acc= 0.23214 time= 0.00000
Epoch: 0009 train_loss= 1.37982 train_acc= 0.32573 val_loss= 1.39830 val_acc= 0.23214 time= 0.01563
Epoch: 0010 train_loss= 1.38010 train_acc= 0.32573 val_loss= 1.40011 val_acc= 0.23214 time= 0.02058
Epoch: 0011 train_loss= 1.37960 train_acc= 0.32573 val_loss= 1.40186 val_acc= 0.23214 time= 0.01100
Epoch: 0012 train_loss= 1.37856 train_acc= 0.32573 val_loss= 1.40352 val_acc= 0.23214 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38603 accuracy= 0.31858 time= 0.00000 
