Epoch: 0001 train_loss= 2.42265 train_acc= 0.27362 val_loss= 1.66858 val_acc= 0.21429 time= 0.33929
Epoch: 0002 train_loss= 2.62547 train_acc= 0.27036 val_loss= 1.63050 val_acc= 0.30357 time= 0.02500
Epoch: 0003 train_loss= 3.51360 train_acc= 0.30945 val_loss= 1.54550 val_acc= 0.30357 time= 0.02401
Epoch: 0004 train_loss= 2.27921 train_acc= 0.34202 val_loss= 1.47729 val_acc= 0.30357 time= 0.02501
Epoch: 0005 train_loss= 1.90575 train_acc= 0.25081 val_loss= 1.48373 val_acc= 0.32143 time= 0.02601
Epoch: 0006 train_loss= 2.23929 train_acc= 0.23779 val_loss= 1.47706 val_acc= 0.32143 time= 0.02201
Epoch: 0007 train_loss= 1.46972 train_acc= 0.25081 val_loss= 1.45875 val_acc= 0.33929 time= 0.02601
Epoch: 0008 train_loss= 1.54677 train_acc= 0.28339 val_loss= 1.44795 val_acc= 0.33929 time= 0.02301
Epoch: 0009 train_loss= 1.53728 train_acc= 0.31270 val_loss= 1.43965 val_acc= 0.37500 time= 0.02501
Epoch: 0010 train_loss= 1.86028 train_acc= 0.28339 val_loss= 1.41809 val_acc= 0.33929 time= 0.02601
Epoch: 0011 train_loss= 1.66304 train_acc= 0.33225 val_loss= 1.41121 val_acc= 0.33929 time= 0.02601
Epoch: 0012 train_loss= 2.02047 train_acc= 0.19870 val_loss= 1.42352 val_acc= 0.19643 time= 0.02701
Epoch: 0013 train_loss= 1.54894 train_acc= 0.28664 val_loss= 1.43158 val_acc= 0.12500 time= 0.02700
Epoch: 0014 train_loss= 1.50588 train_acc= 0.23779 val_loss= 1.43271 val_acc= 0.17857 time= 0.02601
Epoch: 0015 train_loss= 1.49722 train_acc= 0.25733 val_loss= 1.43406 val_acc= 0.17857 time= 0.02701
Epoch: 0016 train_loss= 1.45939 train_acc= 0.29967 val_loss= 1.43432 val_acc= 0.16071 time= 0.02200
Epoch: 0017 train_loss= 1.59814 train_acc= 0.26059 val_loss= 1.43319 val_acc= 0.16071 time= 0.02301
Early stopping...
Optimization Finished!
Test set results: cost= 1.40366 accuracy= 0.23009 time= 0.01200 
