Epoch: 0001 train_loss= 1.38718 train_acc= 0.26367 val_loss= 1.39050 val_acc= 0.25000 time= 0.57816
Epoch: 0002 train_loss= 1.38733 train_acc= 0.26953 val_loss= 1.38899 val_acc= 0.25000 time= 0.00000
Epoch: 0003 train_loss= 1.38633 train_acc= 0.26562 val_loss= 1.38752 val_acc= 0.25000 time= 0.01563
Epoch: 0004 train_loss= 1.38422 train_acc= 0.26367 val_loss= 1.38606 val_acc= 0.25000 time= 0.00000
Epoch: 0005 train_loss= 1.38283 train_acc= 0.26367 val_loss= 1.38457 val_acc= 0.25000 time= 0.01563
Epoch: 0006 train_loss= 1.38222 train_acc= 0.26367 val_loss= 1.38312 val_acc= 0.25000 time= 0.00000
Epoch: 0007 train_loss= 1.38016 train_acc= 0.26367 val_loss= 1.38170 val_acc= 0.25000 time= 0.01562
Epoch: 0008 train_loss= 1.38048 train_acc= 0.26367 val_loss= 1.38034 val_acc= 0.25000 time= 0.00000
Epoch: 0009 train_loss= 1.37952 train_acc= 0.26953 val_loss= 1.37899 val_acc= 0.25000 time= 0.00000
Epoch: 0010 train_loss= 1.37880 train_acc= 0.26367 val_loss= 1.37766 val_acc= 0.25000 time= 0.01563
Epoch: 0011 train_loss= 1.37869 train_acc= 0.25781 val_loss= 1.37641 val_acc= 0.25000 time= 0.00000
Epoch: 0012 train_loss= 1.37627 train_acc= 0.28125 val_loss= 1.37521 val_acc= 0.28333 time= 0.01563
Epoch: 0013 train_loss= 1.37499 train_acc= 0.30273 val_loss= 1.37415 val_acc= 0.35000 time= 0.00000
Epoch: 0014 train_loss= 1.37628 train_acc= 0.28516 val_loss= 1.37312 val_acc= 0.35000 time= 0.01562
Epoch: 0015 train_loss= 1.37684 train_acc= 0.28516 val_loss= 1.37224 val_acc= 0.35000 time= 0.00000
Epoch: 0016 train_loss= 1.37684 train_acc= 0.28516 val_loss= 1.37151 val_acc= 0.35000 time= 0.00000
Epoch: 0017 train_loss= 1.37440 train_acc= 0.29102 val_loss= 1.37086 val_acc= 0.35000 time= 0.01563
Epoch: 0018 train_loss= 1.37620 train_acc= 0.28906 val_loss= 1.37029 val_acc= 0.35000 time= 0.00000
Epoch: 0019 train_loss= 1.37598 train_acc= 0.28906 val_loss= 1.36985 val_acc= 0.35000 time= 0.01563
Epoch: 0020 train_loss= 1.37583 train_acc= 0.29297 val_loss= 1.36949 val_acc= 0.35000 time= 0.00000
Epoch: 0021 train_loss= 1.37599 train_acc= 0.28906 val_loss= 1.36922 val_acc= 0.35000 time= 0.00000
Epoch: 0022 train_loss= 1.37471 train_acc= 0.29102 val_loss= 1.36904 val_acc= 0.35000 time= 0.01563
Epoch: 0023 train_loss= 1.37541 train_acc= 0.29102 val_loss= 1.36893 val_acc= 0.35000 time= 0.00000
Epoch: 0024 train_loss= 1.37547 train_acc= 0.29102 val_loss= 1.36887 val_acc= 0.35000 time= 0.01563
Epoch: 0025 train_loss= 1.37489 train_acc= 0.29102 val_loss= 1.36898 val_acc= 0.35000 time= 0.00000
Epoch: 0026 train_loss= 1.37815 train_acc= 0.29102 val_loss= 1.36921 val_acc= 0.35000 time= 0.01563
Epoch: 0027 train_loss= 1.37739 train_acc= 0.29102 val_loss= 1.36942 val_acc= 0.35000 time= 0.00000
Epoch: 0028 train_loss= 1.37625 train_acc= 0.29102 val_loss= 1.36968 val_acc= 0.35000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.37383 accuracy= 0.31667 time= 0.00000 
