Epoch: 0001 train_loss= 0.70102 train_acc= 0.52597 val_loss= 0.69855 val_acc= 0.50000 time= 0.37776
Epoch: 0002 train_loss= 0.69801 train_acc= 0.51948 val_loss= 0.69693 val_acc= 0.50000 time= 0.01563
Epoch: 0003 train_loss= 0.69557 train_acc= 0.51948 val_loss= 0.69616 val_acc= 0.50000 time= 0.00000
Epoch: 0004 train_loss= 0.69408 train_acc= 0.51948 val_loss= 0.69597 val_acc= 0.50000 time= 0.01563
Epoch: 0005 train_loss= 0.69309 train_acc= 0.51948 val_loss= 0.69610 val_acc= 0.50000 time= 0.01563
Epoch: 0006 train_loss= 0.69254 train_acc= 0.51948 val_loss= 0.69626 val_acc= 0.50000 time= 0.00000
Epoch: 0007 train_loss= 0.69217 train_acc= 0.51948 val_loss= 0.69635 val_acc= 0.50000 time= 0.01563
Epoch: 0008 train_loss= 0.69238 train_acc= 0.51948 val_loss= 0.69639 val_acc= 0.50000 time= 0.01563
Epoch: 0009 train_loss= 0.69226 train_acc= 0.52078 val_loss= 0.69640 val_acc= 0.50000 time= 0.01563
Epoch: 0010 train_loss= 0.69211 train_acc= 0.52078 val_loss= 0.69633 val_acc= 0.50000 time= 0.00000
Epoch: 0011 train_loss= 0.69198 train_acc= 0.52208 val_loss= 0.69619 val_acc= 0.50000 time= 0.01563
Epoch: 0012 train_loss= 0.69208 train_acc= 0.52468 val_loss= 0.69608 val_acc= 0.50000 time= 0.01571
Epoch: 0013 train_loss= 0.69167 train_acc= 0.52727 val_loss= 0.69599 val_acc= 0.50000 time= 0.00000
Epoch: 0014 train_loss= 0.69164 train_acc= 0.53247 val_loss= 0.69599 val_acc= 0.50000 time= 0.00000
Epoch: 0015 train_loss= 0.69130 train_acc= 0.53636 val_loss= 0.69617 val_acc= 0.50000 time= 0.01563
Epoch: 0016 train_loss= 0.69129 train_acc= 0.52597 val_loss= 0.69624 val_acc= 0.50000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.68863 accuracy= 0.56452 time= 0.00000 
