Epoch: 0001 train_loss= 1.62981 train_acc= 0.26059 val_loss= 1.66351 val_acc= 0.21429 time= 0.34669
Epoch: 0002 train_loss= 1.80698 train_acc= 0.24430 val_loss= 1.61274 val_acc= 0.23214 time= 0.03201
Epoch: 0003 train_loss= 1.50057 train_acc= 0.22801 val_loss= 1.51710 val_acc= 0.23214 time= 0.02901
Epoch: 0004 train_loss= 1.51246 train_acc= 0.23779 val_loss= 1.48377 val_acc= 0.23214 time= 0.02401
Epoch: 0005 train_loss= 1.43987 train_acc= 0.22476 val_loss= 1.44851 val_acc= 0.25000 time= 0.02501
Epoch: 0006 train_loss= 1.40812 train_acc= 0.23453 val_loss= 1.41194 val_acc= 0.21429 time= 0.02300
Epoch: 0007 train_loss= 1.57874 train_acc= 0.23779 val_loss= 1.37638 val_acc= 0.25000 time= 0.02301
Epoch: 0008 train_loss= 1.58536 train_acc= 0.28339 val_loss= 1.37063 val_acc= 0.26786 time= 0.02301
Epoch: 0009 train_loss= 1.61911 train_acc= 0.27362 val_loss= 1.37911 val_acc= 0.35714 time= 0.02233
Epoch: 0010 train_loss= 1.41295 train_acc= 0.25733 val_loss= 1.38030 val_acc= 0.30357 time= 0.02268
Epoch: 0011 train_loss= 1.44735 train_acc= 0.23453 val_loss= 1.38022 val_acc= 0.30357 time= 0.02301
Epoch: 0012 train_loss= 1.38300 train_acc= 0.26059 val_loss= 1.38039 val_acc= 0.28571 time= 0.02301
Epoch: 0013 train_loss= 1.38138 train_acc= 0.28990 val_loss= 1.38043 val_acc= 0.33929 time= 0.02501
Epoch: 0014 train_loss= 1.64888 train_acc= 0.27362 val_loss= 1.38133 val_acc= 0.28571 time= 0.02301
Epoch: 0015 train_loss= 1.38659 train_acc= 0.29642 val_loss= 1.38166 val_acc= 0.30357 time= 0.02701
Epoch: 0016 train_loss= 1.38291 train_acc= 0.29642 val_loss= 1.38211 val_acc= 0.32143 time= 0.02601
Epoch: 0017 train_loss= 1.40425 train_acc= 0.29967 val_loss= 1.38228 val_acc= 0.32143 time= 0.02286
Early stopping...
Optimization Finished!
Test set results: cost= 1.39875 accuracy= 0.30088 time= 0.01000 
