Epoch: 0001 train_loss= 2.14855 train_acc= 0.13208 val_loss= 2.08413 val_acc= 0.06897 time= 0.64418
Epoch: 0002 train_loss= 2.09668 train_acc= 0.15849 val_loss= 2.06599 val_acc= 0.06897 time= 0.01562
Epoch: 0003 train_loss= 2.06440 train_acc= 0.19245 val_loss= 2.05528 val_acc= 0.06897 time= 0.01563
Epoch: 0004 train_loss= 2.06929 train_acc= 0.15849 val_loss= 2.04556 val_acc= 0.06897 time= 0.01563
Epoch: 0005 train_loss= 2.09214 train_acc= 0.16604 val_loss= 2.05652 val_acc= 0.06897 time= 0.00000
Epoch: 0006 train_loss= 2.08153 train_acc= 0.19245 val_loss= 2.06768 val_acc= 0.06897 time= 0.01563
Epoch: 0007 train_loss= 2.07499 train_acc= 0.18491 val_loss= 2.08266 val_acc= 0.06897 time= 0.02465
Epoch: 0008 train_loss= 2.05128 train_acc= 0.16981 val_loss= 2.10109 val_acc= 0.06897 time= 0.01400
Epoch: 0009 train_loss= 2.04770 train_acc= 0.18868 val_loss= 2.10595 val_acc= 0.06897 time= 0.01400
Epoch: 0010 train_loss= 2.02623 train_acc= 0.19245 val_loss= 2.11241 val_acc= 0.06897 time= 0.01300
Epoch: 0011 train_loss= 2.04409 train_acc= 0.21509 val_loss= 2.10993 val_acc= 0.10345 time= 0.01500
Epoch: 0012 train_loss= 2.04418 train_acc= 0.18868 val_loss= 2.09897 val_acc= 0.13793 time= 0.01600
Early stopping...
Optimization Finished!
Test set results: cost= 2.04521 accuracy= 0.13559 time= 0.00600 
