Epoch: 0001 train_loss= 2.08764 train_acc= 0.04906 val_loss= 2.08674 val_acc= 0.13793 time= 0.44310
Epoch: 0002 train_loss= 2.08513 train_acc= 0.13585 val_loss= 2.08663 val_acc= 0.06897 time= 0.00900
Epoch: 0003 train_loss= 2.08274 train_acc= 0.16226 val_loss= 2.08687 val_acc= 0.06897 time= 0.00800
Epoch: 0004 train_loss= 2.08029 train_acc= 0.15094 val_loss= 2.08759 val_acc= 0.06897 time= 0.00800
Epoch: 0005 train_loss= 2.07800 train_acc= 0.15849 val_loss= 2.08870 val_acc= 0.06897 time= 0.00900
Epoch: 0006 train_loss= 2.07585 train_acc= 0.14717 val_loss= 2.09018 val_acc= 0.06897 time= 0.01000
Epoch: 0007 train_loss= 2.07399 train_acc= 0.15094 val_loss= 2.09174 val_acc= 0.06897 time= 0.01000
Epoch: 0008 train_loss= 2.07243 train_acc= 0.15472 val_loss= 2.09352 val_acc= 0.06897 time= 0.00800
Epoch: 0009 train_loss= 2.07033 train_acc= 0.16226 val_loss= 2.09549 val_acc= 0.06897 time= 0.00900
Epoch: 0010 train_loss= 2.06998 train_acc= 0.17358 val_loss= 2.09750 val_acc= 0.06897 time= 0.00800
Epoch: 0011 train_loss= 2.06746 train_acc= 0.15472 val_loss= 2.09947 val_acc= 0.06897 time= 0.00900
Epoch: 0012 train_loss= 2.06543 train_acc= 0.15094 val_loss= 2.10134 val_acc= 0.06897 time= 0.00900
Early stopping...
Optimization Finished!
Test set results: cost= 2.07496 accuracy= 0.08475 time= 0.00300 
