Epoch: 0001 train_loss= 0.82377 train_acc= 0.48701 val_loss= 0.73206 val_acc= 0.45902 time= 0.27579
Epoch: 0002 train_loss= 0.76212 train_acc= 0.52727 val_loss= 0.73648 val_acc= 0.44262 time= 0.01562
Epoch: 0003 train_loss= 0.79019 train_acc= 0.45065 val_loss= 0.77679 val_acc= 0.45902 time= 0.01563
Epoch: 0004 train_loss= 0.80789 train_acc= 0.54545 val_loss= 0.80695 val_acc= 0.45902 time= 0.01563
Epoch: 0005 train_loss= 0.83783 train_acc= 0.54545 val_loss= 0.81063 val_acc= 0.44262 time= 0.01563
Epoch: 0006 train_loss= 1.01997 train_acc= 0.53636 val_loss= 0.78471 val_acc= 0.44262 time= 0.01563
Epoch: 0007 train_loss= 0.80185 train_acc= 0.46364 val_loss= 0.77698 val_acc= 0.44262 time= 0.00000
Epoch: 0008 train_loss= 0.80811 train_acc= 0.52078 val_loss= 0.77261 val_acc= 0.45902 time= 0.01563
Epoch: 0009 train_loss= 0.89119 train_acc= 0.51558 val_loss= 0.75150 val_acc= 0.45902 time= 0.01563
Epoch: 0010 train_loss= 0.93641 train_acc= 0.54675 val_loss= 0.72878 val_acc= 0.45902 time= 0.01563
Epoch: 0011 train_loss= 0.73893 train_acc= 0.50649 val_loss= 0.72013 val_acc= 0.49180 time= 0.01563
Epoch: 0012 train_loss= 0.72337 train_acc= 0.52208 val_loss= 0.71647 val_acc= 0.47541 time= 0.01563
Epoch: 0013 train_loss= 0.75076 train_acc= 0.53377 val_loss= 0.71729 val_acc= 0.47541 time= 0.00000
Epoch: 0014 train_loss= 0.76264 train_acc= 0.46234 val_loss= 0.71972 val_acc= 0.52459 time= 0.01563
Epoch: 0015 train_loss= 0.70314 train_acc= 0.55455 val_loss= 0.72375 val_acc= 0.50820 time= 0.01563
Epoch: 0016 train_loss= 0.80849 train_acc= 0.51169 val_loss= 0.72697 val_acc= 0.49180 time= 0.01563
Epoch: 0017 train_loss= 0.86327 train_acc= 0.46364 val_loss= 0.72584 val_acc= 0.50820 time= 0.01563
Epoch: 0018 train_loss= 0.83791 train_acc= 0.45325 val_loss= 0.72033 val_acc= 0.50820 time= 0.01563
Epoch: 0019 train_loss= 0.72683 train_acc= 0.52987 val_loss= 0.71701 val_acc= 0.52459 time= 0.00000
Epoch: 0020 train_loss= 0.71564 train_acc= 0.50649 val_loss= 0.71484 val_acc= 0.42623 time= 0.01563
Epoch: 0021 train_loss= 0.71316 train_acc= 0.50130 val_loss= 0.71374 val_acc= 0.40984 time= 0.01563
Epoch: 0022 train_loss= 0.71714 train_acc= 0.51558 val_loss= 0.71392 val_acc= 0.44262 time= 0.01563
Epoch: 0023 train_loss= 0.76649 train_acc= 0.45584 val_loss= 0.71595 val_acc= 0.50820 time= 0.01563
Epoch: 0024 train_loss= 0.71640 train_acc= 0.52987 val_loss= 0.72073 val_acc= 0.47541 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.72014 accuracy= 0.41803 time= 0.00000 
