Epoch: 0001 train_loss= 2.08635 train_acc= 0.12938 val_loss= 2.07217 val_acc= 0.20690 time= 0.83489
Epoch: 0002 train_loss= 2.08554 train_acc= 0.12938 val_loss= 2.07300 val_acc= 0.20690 time= 0.00000
Epoch: 0003 train_loss= 2.08449 train_acc= 0.12399 val_loss= 2.07381 val_acc= 0.20690 time= 0.01562
Epoch: 0004 train_loss= 2.08362 train_acc= 0.12668 val_loss= 2.07467 val_acc= 0.20690 time= 0.00000
Epoch: 0005 train_loss= 2.08275 train_acc= 0.14016 val_loss= 2.07555 val_acc= 0.20690 time= 0.00000
Epoch: 0006 train_loss= 2.08060 train_acc= 0.13747 val_loss= 2.07650 val_acc= 0.24138 time= 0.01563
Epoch: 0007 train_loss= 2.07994 train_acc= 0.13477 val_loss= 2.07754 val_acc= 0.24138 time= 0.00000
Epoch: 0008 train_loss= 2.07982 train_acc= 0.14555 val_loss= 2.07870 val_acc= 0.17241 time= 0.01563
Epoch: 0009 train_loss= 2.07843 train_acc= 0.14555 val_loss= 2.08004 val_acc= 0.13793 time= 0.00000
Epoch: 0010 train_loss= 2.07717 train_acc= 0.17520 val_loss= 2.08159 val_acc= 0.13793 time= 0.00000
Epoch: 0011 train_loss= 2.07642 train_acc= 0.15903 val_loss= 2.08333 val_acc= 0.13793 time= 0.01563
Epoch: 0012 train_loss= 2.07521 train_acc= 0.16173 val_loss= 2.08526 val_acc= 0.13793 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08355 accuracy= 0.13559 time= 0.00000 
