Epoch: 0001 train_loss= 2.10437 train_acc= 0.15094 val_loss= 2.11150 val_acc= 0.06897 time= 0.18751
Epoch: 0002 train_loss= 2.10822 train_acc= 0.13585 val_loss= 2.09974 val_acc= 0.06897 time= 0.00000
Epoch: 0003 train_loss= 2.08385 train_acc= 0.17358 val_loss= 2.09117 val_acc= 0.06897 time= 0.01562
Epoch: 0004 train_loss= 2.08708 train_acc= 0.15849 val_loss= 2.08415 val_acc= 0.03448 time= 0.01563
Epoch: 0005 train_loss= 2.07448 train_acc= 0.13962 val_loss= 2.07872 val_acc= 0.13793 time= 0.01563
Epoch: 0006 train_loss= 2.07819 train_acc= 0.14717 val_loss= 2.07422 val_acc= 0.10345 time= 0.00000
Epoch: 0007 train_loss= 2.06795 train_acc= 0.16226 val_loss= 2.07213 val_acc= 0.13793 time= 0.01563
Epoch: 0008 train_loss= 2.06570 train_acc= 0.15472 val_loss= 2.07049 val_acc= 0.13793 time= 0.01563
Epoch: 0009 train_loss= 2.05801 train_acc= 0.17736 val_loss= 2.07020 val_acc= 0.17241 time= 0.00000
Epoch: 0010 train_loss= 2.06863 train_acc= 0.16981 val_loss= 2.07115 val_acc= 0.17241 time= 0.01562
Epoch: 0011 train_loss= 2.05252 train_acc= 0.16981 val_loss= 2.07271 val_acc= 0.17241 time= 0.01563
Epoch: 0012 train_loss= 2.05599 train_acc= 0.17736 val_loss= 2.07473 val_acc= 0.17241 time= 0.00000
Epoch: 0013 train_loss= 2.05617 train_acc= 0.17736 val_loss= 2.07725 val_acc= 0.17241 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.08513 accuracy= 0.11864 time= 0.00000 
