Epoch: 0001 train_loss= 2.08909 train_acc= 0.05283 val_loss= 2.09112 val_acc= 0.10345 time= 0.48486
Epoch: 0002 train_loss= 2.08604 train_acc= 0.04906 val_loss= 2.09029 val_acc= 0.10345 time= 0.00000
Epoch: 0003 train_loss= 2.08360 train_acc= 0.07547 val_loss= 2.08955 val_acc= 0.20690 time= 0.01562
Epoch: 0004 train_loss= 2.08150 train_acc= 0.15849 val_loss= 2.08890 val_acc= 0.20690 time= 0.00000
Epoch: 0005 train_loss= 2.07757 train_acc= 0.16604 val_loss= 2.08827 val_acc= 0.20690 time= 0.00000
Epoch: 0006 train_loss= 2.07525 train_acc= 0.16981 val_loss= 2.08786 val_acc= 0.20690 time= 0.01563
Epoch: 0007 train_loss= 2.07425 train_acc= 0.16981 val_loss= 2.08767 val_acc= 0.20690 time= 0.00000
Epoch: 0008 train_loss= 2.07135 train_acc= 0.16981 val_loss= 2.08782 val_acc= 0.20690 time= 0.00000
Epoch: 0009 train_loss= 2.06807 train_acc= 0.16604 val_loss= 2.08831 val_acc= 0.20690 time= 0.00000
Epoch: 0010 train_loss= 2.06453 train_acc= 0.16981 val_loss= 2.08908 val_acc= 0.20690 time= 0.01563
Epoch: 0011 train_loss= 2.06132 train_acc= 0.17358 val_loss= 2.09022 val_acc= 0.20690 time= 0.00000
Epoch: 0012 train_loss= 2.05929 train_acc= 0.16981 val_loss= 2.09168 val_acc= 0.20690 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08324 accuracy= 0.08475 time= 0.01563 
