Epoch: 0001 train_loss= 2.11969 train_acc= 0.10243 val_loss= 2.07768 val_acc= 0.17241 time= 0.66415
Epoch: 0002 train_loss= 2.11470 train_acc= 0.11321 val_loss= 2.07896 val_acc= 0.20690 time= 0.00900
Epoch: 0003 train_loss= 2.10305 train_acc= 0.12129 val_loss= 2.08014 val_acc= 0.27586 time= 0.01000
Epoch: 0004 train_loss= 2.08756 train_acc= 0.10782 val_loss= 2.08148 val_acc= 0.17241 time= 0.00900
Epoch: 0005 train_loss= 2.09172 train_acc= 0.11590 val_loss= 2.08361 val_acc= 0.10345 time= 0.01000
Epoch: 0006 train_loss= 2.08524 train_acc= 0.14825 val_loss= 2.08556 val_acc= 0.06897 time= 0.01000
Epoch: 0007 train_loss= 2.07589 train_acc= 0.17251 val_loss= 2.08714 val_acc= 0.10345 time= 0.00900
Epoch: 0008 train_loss= 2.07564 train_acc= 0.15903 val_loss= 2.08840 val_acc= 0.13793 time= 0.01000
Epoch: 0009 train_loss= 2.07528 train_acc= 0.14825 val_loss= 2.08923 val_acc= 0.13793 time= 0.01000
Epoch: 0010 train_loss= 2.06354 train_acc= 0.17520 val_loss= 2.09027 val_acc= 0.13793 time= 0.01100
Epoch: 0011 train_loss= 2.06231 train_acc= 0.18329 val_loss= 2.09132 val_acc= 0.13793 time= 0.00900
Epoch: 0012 train_loss= 2.05981 train_acc= 0.17790 val_loss= 2.09236 val_acc= 0.13793 time= 0.00900
Early stopping...
Optimization Finished!
Test set results: cost= 2.09278 accuracy= 0.15254 time= 0.00500 
