Epoch: 0001 train_loss= 0.70102 train_acc= 0.50000 val_loss= 0.69968 val_acc= 0.47541 time= 0.14068
Epoch: 0002 train_loss= 0.69771 train_acc= 0.54545 val_loss= 0.69884 val_acc= 0.47541 time= 0.01562
Epoch: 0003 train_loss= 0.69487 train_acc= 0.54242 val_loss= 0.69869 val_acc= 0.47541 time= 0.01563
Epoch: 0004 train_loss= 0.69300 train_acc= 0.54242 val_loss= 0.69894 val_acc= 0.47541 time= 0.00000
Epoch: 0005 train_loss= 0.69186 train_acc= 0.54848 val_loss= 0.69929 val_acc= 0.47541 time= 0.01563
Epoch: 0006 train_loss= 0.69139 train_acc= 0.54242 val_loss= 0.69983 val_acc= 0.47541 time= 0.00000
Epoch: 0007 train_loss= 0.69018 train_acc= 0.54545 val_loss= 0.70040 val_acc= 0.47541 time= 0.01563
Epoch: 0008 train_loss= 0.68992 train_acc= 0.54848 val_loss= 0.70084 val_acc= 0.47541 time= 0.01563
Epoch: 0009 train_loss= 0.68876 train_acc= 0.56364 val_loss= 0.70126 val_acc= 0.47541 time= 0.01020
Epoch: 0010 train_loss= 0.68852 train_acc= 0.57273 val_loss= 0.70144 val_acc= 0.49180 time= 0.01000
Epoch: 0011 train_loss= 0.68862 train_acc= 0.55758 val_loss= 0.70133 val_acc= 0.49180 time= 0.00900
Epoch: 0012 train_loss= 0.68689 train_acc= 0.57879 val_loss= 0.70133 val_acc= 0.49180 time= 0.01000
Early stopping...
Optimization Finished!
Test set results: cost= 0.68942 accuracy= 0.54098 time= 0.00400 
