Epoch: 0001 train_loss= 0.69948 train_acc= 0.51299 val_loss= 0.69847 val_acc= 0.42623 time= 0.81255
Epoch: 0002 train_loss= 0.69766 train_acc= 0.49610 val_loss= 0.69719 val_acc= 0.62295 time= 0.00600
Epoch: 0003 train_loss= 0.69799 train_acc= 0.47792 val_loss= 0.69632 val_acc= 0.59016 time= 0.00600
Epoch: 0004 train_loss= 0.69834 train_acc= 0.49740 val_loss= 0.69639 val_acc= 0.62295 time= 0.00600
Epoch: 0005 train_loss= 0.69672 train_acc= 0.52078 val_loss= 0.69662 val_acc= 0.55738 time= 0.00700
Epoch: 0006 train_loss= 0.69668 train_acc= 0.52468 val_loss= 0.69676 val_acc= 0.45902 time= 0.00600
Epoch: 0007 train_loss= 0.69542 train_acc= 0.52078 val_loss= 0.69690 val_acc= 0.40984 time= 0.00600
Epoch: 0008 train_loss= 0.69507 train_acc= 0.50000 val_loss= 0.69672 val_acc= 0.40984 time= 0.00600
Epoch: 0009 train_loss= 0.69571 train_acc= 0.52338 val_loss= 0.69674 val_acc= 0.40984 time= 0.00700
Epoch: 0010 train_loss= 0.69610 train_acc= 0.49091 val_loss= 0.69675 val_acc= 0.40984 time= 0.00600
Epoch: 0011 train_loss= 0.69474 train_acc= 0.50649 val_loss= 0.69664 val_acc= 0.40984 time= 0.00562
Epoch: 0012 train_loss= 0.69418 train_acc= 0.49481 val_loss= 0.69625 val_acc= 0.40984 time= 0.00000
Epoch: 0013 train_loss= 0.69515 train_acc= 0.51169 val_loss= 0.69587 val_acc= 0.39344 time= 0.00000
Epoch: 0014 train_loss= 0.69439 train_acc= 0.49351 val_loss= 0.69548 val_acc= 0.42623 time= 0.01563
Epoch: 0015 train_loss= 0.69331 train_acc= 0.53636 val_loss= 0.69511 val_acc= 0.44262 time= 0.00000
Epoch: 0016 train_loss= 0.69369 train_acc= 0.51818 val_loss= 0.69487 val_acc= 0.44262 time= 0.00000
Epoch: 0017 train_loss= 0.69305 train_acc= 0.50779 val_loss= 0.69470 val_acc= 0.49180 time= 0.01563
Epoch: 0018 train_loss= 0.69271 train_acc= 0.47662 val_loss= 0.69452 val_acc= 0.49180 time= 0.00000
Epoch: 0019 train_loss= 0.69286 train_acc= 0.51429 val_loss= 0.69444 val_acc= 0.49180 time= 0.00000
Epoch: 0020 train_loss= 0.69367 train_acc= 0.49351 val_loss= 0.69430 val_acc= 0.50820 time= 0.01563
Epoch: 0021 train_loss= 0.69302 train_acc= 0.51558 val_loss= 0.69419 val_acc= 0.52459 time= 0.00000
Epoch: 0022 train_loss= 0.69299 train_acc= 0.52597 val_loss= 0.69405 val_acc= 0.59016 time= 0.01563
Epoch: 0023 train_loss= 0.69281 train_acc= 0.50649 val_loss= 0.69400 val_acc= 0.59016 time= 0.00000
Epoch: 0024 train_loss= 0.69284 train_acc= 0.51558 val_loss= 0.69411 val_acc= 0.59016 time= 0.01563
Epoch: 0025 train_loss= 0.69265 train_acc= 0.54416 val_loss= 0.69432 val_acc= 0.54098 time= 0.00000
Epoch: 0026 train_loss= 0.69381 train_acc= 0.49221 val_loss= 0.69467 val_acc= 0.49180 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69220 accuracy= 0.48361 time= 0.00000 
