Epoch: 0001 train_loss= 0.70642 train_acc= 0.44848 val_loss= 0.68411 val_acc= 0.65574 time= 0.24906
Epoch: 0002 train_loss= 0.69892 train_acc= 0.46667 val_loss= 0.68776 val_acc= 0.65574 time= 0.00600
Epoch: 0003 train_loss= 0.69256 train_acc= 0.52424 val_loss= 0.69152 val_acc= 0.65574 time= 0.00500
Epoch: 0004 train_loss= 0.69942 train_acc= 0.46970 val_loss= 0.69557 val_acc= 0.36066 time= 0.00500
Epoch: 0005 train_loss= 0.69406 train_acc= 0.49697 val_loss= 0.69964 val_acc= 0.34426 time= 0.00400
Epoch: 0006 train_loss= 0.69287 train_acc= 0.46364 val_loss= 0.70381 val_acc= 0.34426 time= 0.00500
Epoch: 0007 train_loss= 0.69444 train_acc= 0.53333 val_loss= 0.70815 val_acc= 0.34426 time= 0.00600
Epoch: 0008 train_loss= 0.69378 train_acc= 0.52121 val_loss= 0.71239 val_acc= 0.34426 time= 0.00500
Epoch: 0009 train_loss= 0.69086 train_acc= 0.54242 val_loss= 0.71646 val_acc= 0.34426 time= 0.00500
Epoch: 0010 train_loss= 0.68905 train_acc= 0.52424 val_loss= 0.72027 val_acc= 0.34426 time= 0.00500
Epoch: 0011 train_loss= 0.69171 train_acc= 0.52121 val_loss= 0.72348 val_acc= 0.34426 time= 0.00400
Epoch: 0012 train_loss= 0.69232 train_acc= 0.54242 val_loss= 0.72553 val_acc= 0.34426 time= 0.00500
Early stopping...
Optimization Finished!
Test set results: cost= 0.71251 accuracy= 0.45082 time= 0.00200 
