Epoch: 0001 train_loss= 0.86413 train_acc= 0.55455 val_loss= 0.85205 val_acc= 0.37097 time= 0.14064
Epoch: 0002 train_loss= 0.84584 train_acc= 0.52121 val_loss= 0.72627 val_acc= 0.51613 time= 0.01861
Epoch: 0003 train_loss= 0.85552 train_acc= 0.49697 val_loss= 0.89287 val_acc= 0.51613 time= 0.00203
Epoch: 0004 train_loss= 1.49497 train_acc= 0.49697 val_loss= 0.86483 val_acc= 0.51613 time= 0.01100
Epoch: 0005 train_loss= 1.17801 train_acc= 0.49394 val_loss= 0.74916 val_acc= 0.51613 time= 0.01563
Epoch: 0006 train_loss= 1.01212 train_acc= 0.52121 val_loss= 0.71671 val_acc= 0.50000 time= 0.01563
Epoch: 0007 train_loss= 0.87670 train_acc= 0.47576 val_loss= 0.72160 val_acc= 0.45161 time= 0.00000
Epoch: 0008 train_loss= 0.86386 train_acc= 0.52121 val_loss= 0.77137 val_acc= 0.37097 time= 0.01563
Epoch: 0009 train_loss= 0.99787 train_acc= 0.52121 val_loss= 0.79140 val_acc= 0.33871 time= 0.01563
Epoch: 0010 train_loss= 1.06023 train_acc= 0.50000 val_loss= 0.76868 val_acc= 0.33871 time= 0.00000
Epoch: 0011 train_loss= 0.83003 train_acc= 0.49697 val_loss= 0.76888 val_acc= 0.30645 time= 0.01563
Epoch: 0012 train_loss= 0.82435 train_acc= 0.53030 val_loss= 0.77670 val_acc= 0.32258 time= 0.01563
Epoch: 0013 train_loss= 0.87927 train_acc= 0.49697 val_loss= 0.78271 val_acc= 0.30645 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.71887 accuracy= 0.54032 time= 0.00000 
