Epoch: 0001 train_loss= 2.08732 train_acc= 0.12453 val_loss= 2.08275 val_acc= 0.34483 time= 0.45010
Epoch: 0002 train_loss= 2.08415 train_acc= 0.16226 val_loss= 2.07656 val_acc= 0.34483 time= 0.00700
Epoch: 0003 train_loss= 2.08083 train_acc= 0.16226 val_loss= 2.07015 val_acc= 0.34483 time= 0.00900
Epoch: 0004 train_loss= 2.07758 train_acc= 0.15849 val_loss= 2.06400 val_acc= 0.34483 time= 0.00700
Epoch: 0005 train_loss= 2.07437 train_acc= 0.15849 val_loss= 2.05806 val_acc= 0.34483 time= 0.00800
Epoch: 0006 train_loss= 2.07123 train_acc= 0.15849 val_loss= 2.05230 val_acc= 0.34483 time= 0.00800
Epoch: 0007 train_loss= 2.06803 train_acc= 0.16226 val_loss= 2.04694 val_acc= 0.34483 time= 0.00700
Epoch: 0008 train_loss= 2.06572 train_acc= 0.16226 val_loss= 2.04206 val_acc= 0.34483 time= 0.00700
Epoch: 0009 train_loss= 2.06362 train_acc= 0.16226 val_loss= 2.03794 val_acc= 0.34483 time= 0.00800
Epoch: 0010 train_loss= 2.06040 train_acc= 0.15849 val_loss= 2.03434 val_acc= 0.34483 time= 0.00600
Epoch: 0011 train_loss= 2.05858 train_acc= 0.15849 val_loss= 2.03120 val_acc= 0.34483 time= 0.00900
Epoch: 0012 train_loss= 2.05668 train_acc= 0.16226 val_loss= 2.02870 val_acc= 0.34483 time= 0.00600
Epoch: 0013 train_loss= 2.05482 train_acc= 0.16226 val_loss= 2.02712 val_acc= 0.34483 time= 0.00700
Epoch: 0014 train_loss= 2.05165 train_acc= 0.16226 val_loss= 2.02644 val_acc= 0.34483 time= 0.00700
Epoch: 0015 train_loss= 2.04956 train_acc= 0.15849 val_loss= 2.02653 val_acc= 0.34483 time= 0.00800
Epoch: 0016 train_loss= 2.05068 train_acc= 0.15849 val_loss= 2.02719 val_acc= 0.34483 time= 0.00700
Epoch: 0017 train_loss= 2.04845 train_acc= 0.16226 val_loss= 2.02827 val_acc= 0.34483 time= 0.00800
Epoch: 0018 train_loss= 2.04672 train_acc= 0.16226 val_loss= 2.03008 val_acc= 0.34483 time= 0.00800
Epoch: 0019 train_loss= 2.04457 train_acc= 0.15849 val_loss= 2.03262 val_acc= 0.34483 time= 0.01000
Early stopping...
Optimization Finished!
Test set results: cost= 2.09919 accuracy= 0.13559 time= 0.00400 
