Epoch: 0001 train_loss= 1.51231 train_acc= 0.23828 val_loss= 1.59985 val_acc= 0.16071 time= 0.60942
Epoch: 0002 train_loss= 1.69647 train_acc= 0.26562 val_loss= 1.56352 val_acc= 0.16071 time= 0.03125
Epoch: 0003 train_loss= 1.60613 train_acc= 0.25977 val_loss= 1.48081 val_acc= 0.17857 time= 0.01563
Epoch: 0004 train_loss= 1.52811 train_acc= 0.26758 val_loss= 1.46266 val_acc= 0.17857 time= 0.03125
Epoch: 0005 train_loss= 1.97537 train_acc= 0.26562 val_loss= 1.44042 val_acc= 0.23214 time= 0.01563
Epoch: 0006 train_loss= 1.49387 train_acc= 0.24023 val_loss= 1.41579 val_acc= 0.23214 time= 0.01562
Epoch: 0007 train_loss= 1.55618 train_acc= 0.29883 val_loss= 1.39209 val_acc= 0.32143 time= 0.03125
Epoch: 0008 train_loss= 1.49538 train_acc= 0.26953 val_loss= 1.38273 val_acc= 0.33929 time= 0.01563
Epoch: 0009 train_loss= 1.41206 train_acc= 0.27734 val_loss= 1.38002 val_acc= 0.33929 time= 0.03125
Epoch: 0010 train_loss= 1.41688 train_acc= 0.27930 val_loss= 1.37917 val_acc= 0.33929 time= 0.01563
Epoch: 0011 train_loss= 1.39229 train_acc= 0.30078 val_loss= 1.37889 val_acc= 0.33929 time= 0.03125
Epoch: 0012 train_loss= 1.38982 train_acc= 0.29102 val_loss= 1.37951 val_acc= 0.33929 time= 0.01563
Epoch: 0013 train_loss= 1.39150 train_acc= 0.28906 val_loss= 1.38073 val_acc= 0.33929 time= 0.03125
Epoch: 0014 train_loss= 1.40346 train_acc= 0.29883 val_loss= 1.38182 val_acc= 0.33929 time= 0.01563
Epoch: 0015 train_loss= 1.38592 train_acc= 0.30273 val_loss= 1.38324 val_acc= 0.33929 time= 0.03125
Epoch: 0016 train_loss= 1.46123 train_acc= 0.30078 val_loss= 1.38659 val_acc= 0.35714 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.40125 accuracy= 0.29204 time= 0.01563 
