Epoch: 0001 train_loss= 1.41410 train_acc= 0.23633 val_loss= 1.39132 val_acc= 0.25000 time= 0.46455
Epoch: 0002 train_loss= 1.39886 train_acc= 0.23828 val_loss= 1.38455 val_acc= 0.28571 time= 0.01500
Epoch: 0003 train_loss= 1.39425 train_acc= 0.25195 val_loss= 1.38028 val_acc= 0.33929 time= 0.01500
Epoch: 0004 train_loss= 1.38682 train_acc= 0.30469 val_loss= 1.37796 val_acc= 0.30357 time= 0.01400
Epoch: 0005 train_loss= 1.38372 train_acc= 0.26562 val_loss= 1.37721 val_acc= 0.33929 time= 0.01700
Epoch: 0006 train_loss= 1.38847 train_acc= 0.29102 val_loss= 1.37639 val_acc= 0.30357 time= 0.01500
Epoch: 0007 train_loss= 1.38213 train_acc= 0.30469 val_loss= 1.37645 val_acc= 0.30357 time= 0.01500
Epoch: 0008 train_loss= 1.37895 train_acc= 0.29492 val_loss= 1.37635 val_acc= 0.30357 time= 0.01300
Epoch: 0009 train_loss= 1.38134 train_acc= 0.30273 val_loss= 1.37599 val_acc= 0.30357 time= 0.01500
Epoch: 0010 train_loss= 1.38753 train_acc= 0.28516 val_loss= 1.37535 val_acc= 0.30357 time= 0.01500
Epoch: 0011 train_loss= 1.40097 train_acc= 0.28906 val_loss= 1.37535 val_acc= 0.28571 time= 0.01400
Epoch: 0012 train_loss= 1.37397 train_acc= 0.31445 val_loss= 1.37593 val_acc= 0.28571 time= 0.01500
Epoch: 0013 train_loss= 1.37011 train_acc= 0.30664 val_loss= 1.37673 val_acc= 0.28571 time= 0.01400
Early stopping...
Optimization Finished!
Test set results: cost= 1.37118 accuracy= 0.31858 time= 0.00600 
