Epoch: 0001 train_loss= 0.70084 train_acc= 0.53636 val_loss= 0.70158 val_acc= 0.37705 time= 0.25573
Epoch: 0002 train_loss= 0.69712 train_acc= 0.54182 val_loss= 0.70332 val_acc= 0.37705 time= 0.01567
Epoch: 0003 train_loss= 0.69407 train_acc= 0.54182 val_loss= 0.70627 val_acc= 0.37705 time= 0.01563
Epoch: 0004 train_loss= 0.69219 train_acc= 0.54182 val_loss= 0.71013 val_acc= 0.37705 time= 0.01563
Epoch: 0005 train_loss= 0.69062 train_acc= 0.54182 val_loss= 0.71437 val_acc= 0.37705 time= 0.00000
Epoch: 0006 train_loss= 0.68943 train_acc= 0.54364 val_loss= 0.71859 val_acc= 0.37705 time= 0.01563
Epoch: 0007 train_loss= 0.68905 train_acc= 0.54182 val_loss= 0.72238 val_acc= 0.37705 time= 0.01563
Epoch: 0008 train_loss= 0.68933 train_acc= 0.54182 val_loss= 0.72527 val_acc= 0.37705 time= 0.00000
Epoch: 0009 train_loss= 0.68909 train_acc= 0.54182 val_loss= 0.72691 val_acc= 0.37705 time= 0.01563
Epoch: 0010 train_loss= 0.68943 train_acc= 0.54182 val_loss= 0.72742 val_acc= 0.37705 time= 0.01563
Epoch: 0011 train_loss= 0.68961 train_acc= 0.54182 val_loss= 0.72694 val_acc= 0.37705 time= 0.00000
Epoch: 0012 train_loss= 0.68858 train_acc= 0.54364 val_loss= 0.72580 val_acc= 0.37705 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69069 accuracy= 0.54098 time= 0.00000 
