Epoch: 0001 train_loss= 0.76699 train_acc= 0.52338 val_loss= 0.77244 val_acc= 0.44262 time= 1.04244
Epoch: 0002 train_loss= 0.73928 train_acc= 0.50130 val_loss= 0.82275 val_acc= 0.44262 time= 0.01562
Epoch: 0003 train_loss= 0.74797 train_acc= 0.53766 val_loss= 0.79956 val_acc= 0.44262 time= 0.03125
Epoch: 0004 train_loss= 0.72446 train_acc= 0.52727 val_loss= 0.72701 val_acc= 0.40984 time= 0.03125
Epoch: 0005 train_loss= 0.73786 train_acc= 0.50390 val_loss= 0.70474 val_acc= 0.54098 time= 0.01562
Epoch: 0006 train_loss= 0.71750 train_acc= 0.50390 val_loss= 0.70216 val_acc= 0.57377 time= 0.03125
Epoch: 0007 train_loss= 0.76134 train_acc= 0.44675 val_loss= 0.70464 val_acc= 0.55738 time= 0.01563
Epoch: 0008 train_loss= 0.71110 train_acc= 0.51429 val_loss= 0.71063 val_acc= 0.49180 time= 0.03125
Epoch: 0009 train_loss= 0.71940 train_acc= 0.48701 val_loss= 0.71719 val_acc= 0.49180 time= 0.01563
Epoch: 0010 train_loss= 0.72141 train_acc= 0.48312 val_loss= 0.72744 val_acc= 0.44262 time= 0.01563
Epoch: 0011 train_loss= 0.70473 train_acc= 0.53896 val_loss= 0.73128 val_acc= 0.40984 time= 0.03125
Epoch: 0012 train_loss= 0.70409 train_acc= 0.51429 val_loss= 0.72770 val_acc= 0.42623 time= 0.01563
Epoch: 0013 train_loss= 0.71582 train_acc= 0.54545 val_loss= 0.71816 val_acc= 0.50820 time= 0.03125
Epoch: 0014 train_loss= 0.71056 train_acc= 0.49221 val_loss= 0.71508 val_acc= 0.49180 time= 0.01563
Epoch: 0015 train_loss= 0.70975 train_acc= 0.53636 val_loss= 0.71491 val_acc= 0.52459 time= 0.03125
Epoch: 0016 train_loss= 0.70140 train_acc= 0.51818 val_loss= 0.71469 val_acc= 0.54098 time= 0.01563
Epoch: 0017 train_loss= 0.69321 train_acc= 0.53896 val_loss= 0.71457 val_acc= 0.54098 time= 0.01563
Epoch: 0018 train_loss= 0.69874 train_acc= 0.53896 val_loss= 0.71451 val_acc= 0.55738 time= 0.03609
Epoch: 0019 train_loss= 0.77278 train_acc= 0.53117 val_loss= 0.71500 val_acc= 0.52459 time= 0.01100
Epoch: 0020 train_loss= 0.69945 train_acc= 0.56234 val_loss= 0.71601 val_acc= 0.47541 time= 0.03125
Epoch: 0021 train_loss= 0.70022 train_acc= 0.51948 val_loss= 0.71681 val_acc= 0.49180 time= 0.01563
Epoch: 0022 train_loss= 0.69427 train_acc= 0.52208 val_loss= 0.71752 val_acc= 0.47541 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 0.72331 accuracy= 0.44262 time= 0.01563 
