Epoch: 0001 train_loss= 0.84466 train_acc= 0.44416 val_loss= 0.77126 val_acc= 0.47541 time= 0.82485
Epoch: 0002 train_loss= 0.87665 train_acc= 0.48961 val_loss= 0.75271 val_acc= 0.50820 time= 0.01400
Epoch: 0003 train_loss= 0.87134 train_acc= 0.49870 val_loss= 0.73055 val_acc= 0.50820 time= 0.01213
Epoch: 0004 train_loss= 0.92857 train_acc= 0.50649 val_loss= 0.72256 val_acc= 0.50820 time= 0.01370
Epoch: 0005 train_loss= 0.81879 train_acc= 0.47792 val_loss= 0.71593 val_acc= 0.54098 time= 0.01195
Epoch: 0006 train_loss= 0.92777 train_acc= 0.47922 val_loss= 0.71275 val_acc= 0.52459 time= 0.01379
Epoch: 0007 train_loss= 0.90198 train_acc= 0.51818 val_loss= 0.71441 val_acc= 0.50820 time= 0.01412
Epoch: 0008 train_loss= 0.87122 train_acc= 0.48701 val_loss= 0.72271 val_acc= 0.49180 time= 0.01200
Epoch: 0009 train_loss= 0.97990 train_acc= 0.49221 val_loss= 0.74320 val_acc= 0.50820 time= 0.01352
Epoch: 0010 train_loss= 0.81340 train_acc= 0.50390 val_loss= 0.75132 val_acc= 0.45902 time= 0.01300
Epoch: 0011 train_loss= 0.88802 train_acc= 0.49091 val_loss= 0.76761 val_acc= 0.40984 time= 0.01096
Epoch: 0012 train_loss= 0.75573 train_acc= 0.49091 val_loss= 0.78193 val_acc= 0.42623 time= 0.01226
Early stopping...
Optimization Finished!
Test set results: cost= 0.93879 accuracy= 0.50000 time= 0.00600 
