Epoch: 0001 train_loss= 1.53472 train_acc= 0.49221 val_loss= 0.98504 val_acc= 0.45902 time= 0.28127
Epoch: 0002 train_loss= 0.76530 train_acc= 0.49351 val_loss= 0.80385 val_acc= 0.44262 time= 0.01563
Epoch: 0003 train_loss= 0.84888 train_acc= 0.51429 val_loss= 0.74489 val_acc= 0.54098 time= 0.01563
Epoch: 0004 train_loss= 1.35564 train_acc= 0.50909 val_loss= 0.74502 val_acc= 0.52459 time= 0.01563
Epoch: 0005 train_loss= 1.00380 train_acc= 0.50779 val_loss= 0.72450 val_acc= 0.50820 time= 0.00000
Epoch: 0006 train_loss= 0.83924 train_acc= 0.50519 val_loss= 0.72909 val_acc= 0.49180 time= 0.01563
Epoch: 0007 train_loss= 1.07316 train_acc= 0.49091 val_loss= 0.75884 val_acc= 0.49180 time= 0.01563
Epoch: 0008 train_loss= 0.91855 train_acc= 0.50649 val_loss= 0.75197 val_acc= 0.49180 time= 0.01563
Epoch: 0009 train_loss= 1.00125 train_acc= 0.50909 val_loss= 0.73486 val_acc= 0.52459 time= 0.01563
Epoch: 0010 train_loss= 1.49343 train_acc= 0.50000 val_loss= 0.70165 val_acc= 0.54098 time= 0.01563
Epoch: 0011 train_loss= 0.93643 train_acc= 0.53506 val_loss= 0.68608 val_acc= 0.57377 time= 0.00000
Epoch: 0012 train_loss= 1.30521 train_acc= 0.47922 val_loss= 0.69257 val_acc= 0.50820 time= 0.01563
Epoch: 0013 train_loss= 1.15598 train_acc= 0.50779 val_loss= 0.68825 val_acc= 0.50820 time= 0.01563
Epoch: 0014 train_loss= 1.10723 train_acc= 0.52078 val_loss= 0.69201 val_acc= 0.52459 time= 0.01563
Epoch: 0015 train_loss= 1.35998 train_acc= 0.51948 val_loss= 0.70858 val_acc= 0.49180 time= 0.01563
Epoch: 0016 train_loss= 1.02186 train_acc= 0.49351 val_loss= 0.72001 val_acc= 0.47541 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.76405 accuracy= 0.45082 time= 0.00000 
