Epoch: 0001 train_loss= 2.09219 train_acc= 0.12399 val_loss= 2.07767 val_acc= 0.20690 time= 0.80511
Epoch: 0002 train_loss= 2.07976 train_acc= 0.15903 val_loss= 2.07734 val_acc= 0.20690 time= 0.01000
Epoch: 0003 train_loss= 2.08826 train_acc= 0.13747 val_loss= 2.07712 val_acc= 0.20690 time= 0.00900
Epoch: 0004 train_loss= 2.08256 train_acc= 0.15633 val_loss= 2.07721 val_acc= 0.13793 time= 0.01000
Epoch: 0005 train_loss= 2.06880 train_acc= 0.17251 val_loss= 2.07752 val_acc= 0.17241 time= 0.01100
Epoch: 0006 train_loss= 2.06890 train_acc= 0.14016 val_loss= 2.07791 val_acc= 0.20690 time= 0.01000
Epoch: 0007 train_loss= 2.07051 train_acc= 0.16981 val_loss= 2.07848 val_acc= 0.10345 time= 0.01000
Epoch: 0008 train_loss= 2.08088 train_acc= 0.14016 val_loss= 2.07928 val_acc= 0.10345 time= 0.00900
Epoch: 0009 train_loss= 2.06653 train_acc= 0.18329 val_loss= 2.07982 val_acc= 0.06897 time= 0.00900
Epoch: 0010 train_loss= 2.06694 train_acc= 0.16981 val_loss= 2.08022 val_acc= 0.06897 time= 0.01000
Epoch: 0011 train_loss= 2.06246 train_acc= 0.15903 val_loss= 2.08059 val_acc= 0.06897 time= 0.01100
Epoch: 0012 train_loss= 2.06454 train_acc= 0.16173 val_loss= 2.08080 val_acc= 0.06897 time= 0.01000
Early stopping...
Optimization Finished!
Test set results: cost= 2.05707 accuracy= 0.13559 time= 0.00500 
