Epoch: 0001 train_loss= 1.40625 train_acc= 0.27344 val_loss= 1.41127 val_acc= 0.28571 time= 0.37503
Epoch: 0002 train_loss= 1.41286 train_acc= 0.24414 val_loss= 1.39900 val_acc= 0.28571 time= 0.01562
Epoch: 0003 train_loss= 1.40014 train_acc= 0.25000 val_loss= 1.38873 val_acc= 0.28571 time= 0.01563
Epoch: 0004 train_loss= 1.40076 train_acc= 0.25195 val_loss= 1.38064 val_acc= 0.30357 time= 0.01563
Epoch: 0005 train_loss= 1.38719 train_acc= 0.25391 val_loss= 1.37420 val_acc= 0.35714 time= 0.01563
Epoch: 0006 train_loss= 1.38034 train_acc= 0.25781 val_loss= 1.36885 val_acc= 0.37500 time= 0.00000
Epoch: 0007 train_loss= 1.38862 train_acc= 0.29492 val_loss= 1.36484 val_acc= 0.37500 time= 0.01563
Epoch: 0008 train_loss= 1.38914 train_acc= 0.32422 val_loss= 1.36212 val_acc= 0.37500 time= 0.01562
Epoch: 0009 train_loss= 1.39080 train_acc= 0.30469 val_loss= 1.36055 val_acc= 0.37500 time= 0.01563
Epoch: 0010 train_loss= 1.36958 train_acc= 0.31641 val_loss= 1.35975 val_acc= 0.39286 time= 0.01563
Epoch: 0011 train_loss= 1.38081 train_acc= 0.32227 val_loss= 1.35917 val_acc= 0.39286 time= 0.01563
Epoch: 0012 train_loss= 1.36946 train_acc= 0.29297 val_loss= 1.35893 val_acc= 0.37500 time= 0.01562
Epoch: 0013 train_loss= 1.39550 train_acc= 0.29297 val_loss= 1.35901 val_acc= 0.33929 time= 0.01563
Epoch: 0014 train_loss= 1.38323 train_acc= 0.29492 val_loss= 1.35928 val_acc= 0.33929 time= 0.01563
Epoch: 0015 train_loss= 1.37170 train_acc= 0.29492 val_loss= 1.35927 val_acc= 0.35714 time= 0.01563
Epoch: 0016 train_loss= 1.37376 train_acc= 0.29297 val_loss= 1.35938 val_acc= 0.35714 time= 0.01562
Epoch: 0017 train_loss= 1.37974 train_acc= 0.31836 val_loss= 1.35990 val_acc= 0.35714 time= 0.01563
Epoch: 0018 train_loss= 1.37210 train_acc= 0.30273 val_loss= 1.36045 val_acc= 0.35714 time= 0.02744
Early stopping...
Optimization Finished!
Test set results: cost= 1.40737 accuracy= 0.26549 time= 0.00800 
