Epoch: 0001 train_loss= 2.08704 train_acc= 0.13585 val_loss= 2.08464 val_acc= 0.20690 time= 0.25002
Epoch: 0002 train_loss= 2.08459 train_acc= 0.14340 val_loss= 2.08234 val_acc= 0.20690 time= 0.01562
Epoch: 0003 train_loss= 2.08242 train_acc= 0.13962 val_loss= 2.08007 val_acc= 0.20690 time= 0.00000
Epoch: 0004 train_loss= 2.08027 train_acc= 0.13962 val_loss= 2.07797 val_acc= 0.20690 time= 0.01563
Epoch: 0005 train_loss= 2.07798 train_acc= 0.13962 val_loss= 2.07611 val_acc= 0.20690 time= 0.00000
Epoch: 0006 train_loss= 2.07628 train_acc= 0.13962 val_loss= 2.07453 val_acc= 0.20690 time= 0.01563
Epoch: 0007 train_loss= 2.07397 train_acc= 0.13962 val_loss= 2.07318 val_acc= 0.20690 time= 0.01563
Epoch: 0008 train_loss= 2.07217 train_acc= 0.13962 val_loss= 2.07207 val_acc= 0.20690 time= 0.00000
Epoch: 0009 train_loss= 2.07046 train_acc= 0.13962 val_loss= 2.07125 val_acc= 0.20690 time= 0.01563
Epoch: 0010 train_loss= 2.06840 train_acc= 0.13962 val_loss= 2.07075 val_acc= 0.20690 time= 0.00000
Epoch: 0011 train_loss= 2.06595 train_acc= 0.13962 val_loss= 2.07061 val_acc= 0.20690 time= 0.01563
Epoch: 0012 train_loss= 2.06487 train_acc= 0.13962 val_loss= 2.07087 val_acc= 0.20690 time= 0.01563
Epoch: 0013 train_loss= 2.06273 train_acc= 0.13962 val_loss= 2.07157 val_acc= 0.20690 time= 0.00000
Epoch: 0014 train_loss= 2.06242 train_acc= 0.15472 val_loss= 2.07273 val_acc= 0.20690 time= 0.01563
Epoch: 0015 train_loss= 2.06011 train_acc= 0.16604 val_loss= 2.07440 val_acc= 0.10345 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08426 accuracy= 0.13559 time= 0.01563 
