Epoch: 0001 train_loss= 0.70485 train_acc= 0.54909 val_loss= 0.89294 val_acc= 0.50000 time= 0.20314
Epoch: 0002 train_loss= 0.85934 train_acc= 0.48545 val_loss= 1.01914 val_acc= 0.50000 time= 0.01562
Epoch: 0003 train_loss= 0.84164 train_acc= 0.53636 val_loss= 0.98473 val_acc= 0.48387 time= 0.01563
Epoch: 0004 train_loss= 1.09671 train_acc= 0.53091 val_loss= 0.87968 val_acc= 0.48387 time= 0.01563
Epoch: 0005 train_loss= 0.77526 train_acc= 0.51091 val_loss= 0.80593 val_acc= 0.45161 time= 0.00000
Epoch: 0006 train_loss= 0.81977 train_acc= 0.53636 val_loss= 0.75165 val_acc= 0.51613 time= 0.01563
Epoch: 0007 train_loss= 0.81460 train_acc= 0.52364 val_loss= 0.78791 val_acc= 0.45161 time= 0.01563
Epoch: 0008 train_loss= 1.15649 train_acc= 0.47455 val_loss= 0.88132 val_acc= 0.41935 time= 0.01563
Epoch: 0009 train_loss= 0.78425 train_acc= 0.50727 val_loss= 0.97283 val_acc= 0.46774 time= 0.01563
Epoch: 0010 train_loss= 0.82478 train_acc= 0.47455 val_loss= 1.01849 val_acc= 0.46774 time= 0.01563
Epoch: 0011 train_loss= 1.03311 train_acc= 0.50182 val_loss= 0.93142 val_acc= 0.46774 time= 0.01563
Epoch: 0012 train_loss= 1.31282 train_acc= 0.45455 val_loss= 0.80258 val_acc= 0.48387 time= 0.01563
Epoch: 0013 train_loss= 1.21841 train_acc= 0.48000 val_loss= 0.75913 val_acc= 0.46774 time= 0.00000
Epoch: 0014 train_loss= 0.85298 train_acc= 0.49455 val_loss= 0.76538 val_acc= 0.41935 time= 0.01563
Epoch: 0015 train_loss= 0.78802 train_acc= 0.51091 val_loss= 0.78963 val_acc= 0.48387 time= 0.01563
Epoch: 0016 train_loss= 0.78622 train_acc= 0.49455 val_loss= 0.82759 val_acc= 0.46774 time= 0.01563
Epoch: 0017 train_loss= 0.82837 train_acc= 0.53455 val_loss= 0.86322 val_acc= 0.46774 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.71933 accuracy= 0.54032 time= 0.00000 
