Epoch: 0001 train_loss= 1.39872 train_acc= 0.19274 val_loss= 1.39054 val_acc= 0.17857 time= 0.87543
Epoch: 0002 train_loss= 1.39722 train_acc= 0.19693 val_loss= 1.39004 val_acc= 0.17857 time= 0.00000
Epoch: 0003 train_loss= 1.39492 train_acc= 0.19134 val_loss= 1.38962 val_acc= 0.17857 time= 0.00000
Epoch: 0004 train_loss= 1.39417 train_acc= 0.19693 val_loss= 1.38926 val_acc= 0.19643 time= 0.01563
Epoch: 0005 train_loss= 1.39401 train_acc= 0.23603 val_loss= 1.38894 val_acc= 0.28571 time= 0.00000
Epoch: 0006 train_loss= 1.39249 train_acc= 0.24441 val_loss= 1.38866 val_acc= 0.26786 time= 0.01563
Epoch: 0007 train_loss= 1.39306 train_acc= 0.22765 val_loss= 1.38841 val_acc= 0.26786 time= 0.00000
Epoch: 0008 train_loss= 1.39111 train_acc= 0.24721 val_loss= 1.38820 val_acc= 0.26786 time= 0.01563
Epoch: 0009 train_loss= 1.39024 train_acc= 0.25698 val_loss= 1.38803 val_acc= 0.26786 time= 0.00000
Epoch: 0010 train_loss= 1.38876 train_acc= 0.25279 val_loss= 1.38790 val_acc= 0.26786 time= 0.01563
Epoch: 0011 train_loss= 1.38915 train_acc= 0.25419 val_loss= 1.38779 val_acc= 0.26786 time= 0.00000
Epoch: 0012 train_loss= 1.38793 train_acc= 0.25419 val_loss= 1.38772 val_acc= 0.26786 time= 0.01563
Epoch: 0013 train_loss= 1.38726 train_acc= 0.25279 val_loss= 1.38769 val_acc= 0.26786 time= 0.00000
Epoch: 0014 train_loss= 1.38658 train_acc= 0.25140 val_loss= 1.38769 val_acc= 0.26786 time= 0.01563
Epoch: 0015 train_loss= 1.38628 train_acc= 0.25279 val_loss= 1.38773 val_acc= 0.26786 time= 0.00000
Epoch: 0016 train_loss= 1.38540 train_acc= 0.25419 val_loss= 1.38778 val_acc= 0.26786 time= 0.01563
Epoch: 0017 train_loss= 1.38482 train_acc= 0.24860 val_loss= 1.38786 val_acc= 0.26786 time= 0.00000
Epoch: 0018 train_loss= 1.38487 train_acc= 0.25419 val_loss= 1.38795 val_acc= 0.26786 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38491 accuracy= 0.25664 time= 0.00000 
