Epoch: 0001 train_loss= 0.69367 train_acc= 0.53030 val_loss= 0.69487 val_acc= 0.49180 time= 0.28481
Epoch: 0002 train_loss= 0.69401 train_acc= 0.51212 val_loss= 0.69526 val_acc= 0.49180 time= 0.00000
Epoch: 0003 train_loss= 0.69444 train_acc= 0.51515 val_loss= 0.69585 val_acc= 0.49180 time= 0.00000
Epoch: 0004 train_loss= 0.69297 train_acc= 0.49697 val_loss= 0.69644 val_acc= 0.49180 time= 0.01562
Epoch: 0005 train_loss= 0.69219 train_acc= 0.51212 val_loss= 0.69699 val_acc= 0.49180 time= 0.00000
Epoch: 0006 train_loss= 0.69367 train_acc= 0.51515 val_loss= 0.69701 val_acc= 0.49180 time= 0.00000
Epoch: 0007 train_loss= 0.69363 train_acc= 0.52121 val_loss= 0.69675 val_acc= 0.49180 time= 0.01563
Epoch: 0008 train_loss= 0.69345 train_acc= 0.51818 val_loss= 0.69638 val_acc= 0.49180 time= 0.00000
Epoch: 0009 train_loss= 0.69351 train_acc= 0.51515 val_loss= 0.69591 val_acc= 0.49180 time= 0.00000
Epoch: 0010 train_loss= 0.69226 train_acc= 0.51818 val_loss= 0.69547 val_acc= 0.49180 time= 0.01563
Epoch: 0011 train_loss= 0.69329 train_acc= 0.52121 val_loss= 0.69508 val_acc= 0.49180 time= 0.00000
Epoch: 0012 train_loss= 0.69072 train_acc= 0.53030 val_loss= 0.69479 val_acc= 0.49180 time= 0.00000
Epoch: 0013 train_loss= 0.69250 train_acc= 0.51212 val_loss= 0.69458 val_acc= 0.49180 time= 0.00000
Epoch: 0014 train_loss= 0.69258 train_acc= 0.52121 val_loss= 0.69439 val_acc= 0.49180 time= 0.00000
Epoch: 0015 train_loss= 0.69249 train_acc= 0.52121 val_loss= 0.69424 val_acc= 0.49180 time= 0.00000
Epoch: 0016 train_loss= 0.69292 train_acc= 0.51212 val_loss= 0.69411 val_acc= 0.49180 time= 0.00000
Epoch: 0017 train_loss= 0.69272 train_acc= 0.52121 val_loss= 0.69408 val_acc= 0.49180 time= 0.01563
Epoch: 0018 train_loss= 0.69422 train_acc= 0.51818 val_loss= 0.69406 val_acc= 0.49180 time= 0.00000
Epoch: 0019 train_loss= 0.69190 train_acc= 0.52424 val_loss= 0.69407 val_acc= 0.49180 time= 0.00000
Epoch: 0020 train_loss= 0.69338 train_acc= 0.51212 val_loss= 0.69411 val_acc= 0.49180 time= 0.01903
Epoch: 0021 train_loss= 0.69337 train_acc= 0.50000 val_loss= 0.69417 val_acc= 0.49180 time= 0.00202
Epoch: 0022 train_loss= 0.69184 train_acc= 0.51515 val_loss= 0.69425 val_acc= 0.49180 time= 0.00000
Epoch: 0023 train_loss= 0.69315 train_acc= 0.51212 val_loss= 0.69438 val_acc= 0.49180 time= 0.01050
Early stopping...
Optimization Finished!
Test set results: cost= 0.69212 accuracy= 0.53279 time= 0.00000 
