Epoch: 0001 train_loss= 2.26289 train_acc= 0.23828 val_loss= 1.96334 val_acc= 0.16071 time= 0.62504
Epoch: 0002 train_loss= 1.78129 train_acc= 0.25781 val_loss= 1.78477 val_acc= 0.26786 time= 0.01563
Epoch: 0003 train_loss= 2.39897 train_acc= 0.22266 val_loss= 1.73108 val_acc= 0.30357 time= 0.03125
Epoch: 0004 train_loss= 2.09510 train_acc= 0.24805 val_loss= 1.67719 val_acc= 0.30357 time= 0.01562
Epoch: 0005 train_loss= 1.72686 train_acc= 0.32422 val_loss= 1.59444 val_acc= 0.30357 time= 0.03125
Epoch: 0006 train_loss= 1.66203 train_acc= 0.27930 val_loss= 1.51161 val_acc= 0.35714 time= 0.01563
Epoch: 0007 train_loss= 1.83195 train_acc= 0.29883 val_loss= 1.44151 val_acc= 0.37500 time= 0.03125
Epoch: 0008 train_loss= 1.85127 train_acc= 0.29492 val_loss= 1.38829 val_acc= 0.35714 time= 0.01562
Epoch: 0009 train_loss= 2.15565 train_acc= 0.25000 val_loss= 1.34267 val_acc= 0.37500 time= 0.03125
Epoch: 0010 train_loss= 1.65042 train_acc= 0.31055 val_loss= 1.33748 val_acc= 0.37500 time= 0.01563
Epoch: 0011 train_loss= 1.57240 train_acc= 0.23047 val_loss= 1.39029 val_acc= 0.39286 time= 0.03125
Epoch: 0012 train_loss= 1.55555 train_acc= 0.25781 val_loss= 1.38935 val_acc= 0.41071 time= 0.03125
Epoch: 0013 train_loss= 1.81165 train_acc= 0.31445 val_loss= 1.38214 val_acc= 0.41071 time= 0.03125
Epoch: 0014 train_loss= 1.41918 train_acc= 0.28516 val_loss= 1.38612 val_acc= 0.41071 time= 0.01563
Epoch: 0015 train_loss= 1.46962 train_acc= 0.32422 val_loss= 1.39141 val_acc= 0.41071 time= 0.03125
Epoch: 0016 train_loss= 1.42890 train_acc= 0.26562 val_loss= 1.39525 val_acc= 0.41071 time= 0.01563
Epoch: 0017 train_loss= 1.39998 train_acc= 0.32227 val_loss= 1.39967 val_acc= 0.37500 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.37380 accuracy= 0.37168 time= 0.01563 
