Epoch: 0001 train_loss= 0.91640 train_acc= 0.55455 val_loss= 0.70359 val_acc= 0.57377 time= 0.17190
Epoch: 0002 train_loss= 0.78373 train_acc= 0.53273 val_loss= 0.70439 val_acc= 0.49180 time= 0.01562
Epoch: 0003 train_loss= 0.97932 train_acc= 0.42182 val_loss= 0.71213 val_acc= 0.49180 time= 0.01563
Epoch: 0004 train_loss= 0.75719 train_acc= 0.52545 val_loss= 0.72582 val_acc= 0.45902 time= 0.01563
Epoch: 0005 train_loss= 0.86534 train_acc= 0.48364 val_loss= 0.71381 val_acc= 0.44262 time= 0.01563
Epoch: 0006 train_loss= 0.75314 train_acc= 0.54364 val_loss= 0.71651 val_acc= 0.44262 time= 0.01563
Epoch: 0007 train_loss= 0.72826 train_acc= 0.50545 val_loss= 0.71537 val_acc= 0.45902 time= 0.01563
Epoch: 0008 train_loss= 0.73414 train_acc= 0.49636 val_loss= 0.70929 val_acc= 0.47541 time= 0.00000
Epoch: 0009 train_loss= 0.76806 train_acc= 0.46727 val_loss= 0.70079 val_acc= 0.45902 time= 0.01563
Epoch: 0010 train_loss= 0.76417 train_acc= 0.52727 val_loss= 0.69632 val_acc= 0.47541 time= 0.01563
Epoch: 0011 train_loss= 0.83700 train_acc= 0.46727 val_loss= 0.69644 val_acc= 0.54098 time= 0.01563
Epoch: 0012 train_loss= 0.76839 train_acc= 0.47636 val_loss= 0.70997 val_acc= 0.49180 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69882 accuracy= 0.52459 time= 0.00000 
