Epoch: 0001 train_loss= 2.63798 train_acc= 0.50364 val_loss= 1.07524 val_acc= 0.49180 time= 0.35940
Epoch: 0002 train_loss= 1.28907 train_acc= 0.51273 val_loss= 1.02183 val_acc= 0.52459 time= 0.00000
Epoch: 0003 train_loss= 1.08092 train_acc= 0.48000 val_loss= 1.05890 val_acc= 0.54098 time= 0.01563
Epoch: 0004 train_loss= 1.32155 train_acc= 0.53455 val_loss= 0.99946 val_acc= 0.55738 time= 0.01563
Epoch: 0005 train_loss= 1.11530 train_acc= 0.49091 val_loss= 0.93350 val_acc= 0.54098 time= 0.01563
Epoch: 0006 train_loss= 1.14600 train_acc= 0.50182 val_loss= 0.85440 val_acc= 0.50820 time= 0.01562
Epoch: 0007 train_loss= 0.95541 train_acc= 0.51273 val_loss= 0.77140 val_acc= 0.47541 time= 0.00000
Epoch: 0008 train_loss= 0.91216 train_acc= 0.52909 val_loss= 0.77702 val_acc= 0.50820 time= 0.01563
Epoch: 0009 train_loss= 1.39967 train_acc= 0.51273 val_loss= 0.79914 val_acc= 0.52459 time= 0.01563
Epoch: 0010 train_loss= 1.04871 train_acc= 0.51091 val_loss= 0.83526 val_acc= 0.52459 time= 0.01563
Epoch: 0011 train_loss= 1.69887 train_acc= 0.51818 val_loss= 0.84958 val_acc= 0.50820 time= 0.01563
Epoch: 0012 train_loss= 1.25137 train_acc= 0.46909 val_loss= 0.83778 val_acc= 0.50820 time= 0.01563
Epoch: 0013 train_loss= 0.82203 train_acc= 0.52364 val_loss= 0.83260 val_acc= 0.52459 time= 0.01510
Epoch: 0014 train_loss= 2.37064 train_acc= 0.49636 val_loss= 0.79756 val_acc= 0.52459 time= 0.01200
Epoch: 0015 train_loss= 0.86696 train_acc= 0.48909 val_loss= 0.77429 val_acc= 0.54098 time= 0.01200
Epoch: 0016 train_loss= 1.67271 train_acc= 0.47636 val_loss= 0.74964 val_acc= 0.55738 time= 0.01200
Epoch: 0017 train_loss= 1.86426 train_acc= 0.50364 val_loss= 0.75440 val_acc= 0.54098 time= 0.01300
Epoch: 0018 train_loss= 0.86811 train_acc= 0.48545 val_loss= 0.80370 val_acc= 0.50820 time= 0.01300
Early stopping...
Optimization Finished!
Test set results: cost= 0.92606 accuracy= 0.50820 time= 0.00600 
