Epoch: 0001 train_loss= 0.69449 train_acc= 0.48831 val_loss= 0.69214 val_acc= 0.59016 time= 0.90091
Epoch: 0002 train_loss= 0.69188 train_acc= 0.52338 val_loss= 0.68946 val_acc= 0.60656 time= 0.00700
Epoch: 0003 train_loss= 0.69081 train_acc= 0.54935 val_loss= 0.68711 val_acc= 0.60656 time= 0.00700
Epoch: 0004 train_loss= 0.69329 train_acc= 0.53636 val_loss= 0.68535 val_acc= 0.60656 time= 0.00700
Epoch: 0005 train_loss= 0.69294 train_acc= 0.53896 val_loss= 0.68438 val_acc= 0.60656 time= 0.00900
Epoch: 0006 train_loss= 0.69119 train_acc= 0.54026 val_loss= 0.68362 val_acc= 0.60656 time= 0.00800
Epoch: 0007 train_loss= 0.69145 train_acc= 0.53896 val_loss= 0.68329 val_acc= 0.60656 time= 0.01000
Epoch: 0008 train_loss= 0.69260 train_acc= 0.54156 val_loss= 0.68332 val_acc= 0.60656 time= 0.00800
Epoch: 0009 train_loss= 0.69353 train_acc= 0.53117 val_loss= 0.68367 val_acc= 0.60656 time= 0.01000
Epoch: 0010 train_loss= 0.69210 train_acc= 0.52987 val_loss= 0.68411 val_acc= 0.60656 time= 0.00900
Epoch: 0011 train_loss= 0.68990 train_acc= 0.52857 val_loss= 0.68452 val_acc= 0.60656 time= 0.00900
Epoch: 0012 train_loss= 0.69095 train_acc= 0.53377 val_loss= 0.68493 val_acc= 0.60656 time= 0.01100
Early stopping...
Optimization Finished!
Test set results: cost= 0.69755 accuracy= 0.46721 time= 0.00400 
