Epoch: 0001 train_loss= 0.69470 train_acc= 0.50130 val_loss= 0.69208 val_acc= 0.57377 time= 0.87990
Epoch: 0002 train_loss= 0.69412 train_acc= 0.51429 val_loss= 0.69297 val_acc= 0.59016 time= 0.00000
Epoch: 0003 train_loss= 0.69551 train_acc= 0.48831 val_loss= 0.69402 val_acc= 0.47541 time= 0.01519
Epoch: 0004 train_loss= 0.69275 train_acc= 0.49481 val_loss= 0.69505 val_acc= 0.37705 time= 0.00000
Epoch: 0005 train_loss= 0.69434 train_acc= 0.49740 val_loss= 0.69596 val_acc= 0.42623 time= 0.00000
Epoch: 0006 train_loss= 0.69405 train_acc= 0.49351 val_loss= 0.69620 val_acc= 0.42623 time= 0.01563
Epoch: 0007 train_loss= 0.69267 train_acc= 0.49351 val_loss= 0.69627 val_acc= 0.42623 time= 0.00000
Epoch: 0008 train_loss= 0.69387 train_acc= 0.51429 val_loss= 0.69633 val_acc= 0.42623 time= 0.00000
Epoch: 0009 train_loss= 0.69316 train_acc= 0.51299 val_loss= 0.69656 val_acc= 0.42623 time= 0.01563
Epoch: 0010 train_loss= 0.69358 train_acc= 0.49221 val_loss= 0.69650 val_acc= 0.42623 time= 0.00000
Epoch: 0011 train_loss= 0.69327 train_acc= 0.52208 val_loss= 0.69619 val_acc= 0.42623 time= 0.00000
Epoch: 0012 train_loss= 0.69510 train_acc= 0.48571 val_loss= 0.69554 val_acc= 0.44262 time= 0.01563
Epoch: 0013 train_loss= 0.69358 train_acc= 0.48312 val_loss= 0.69464 val_acc= 0.39344 time= 0.00000
Epoch: 0014 train_loss= 0.69367 train_acc= 0.53506 val_loss= 0.69392 val_acc= 0.54098 time= 0.01563
Epoch: 0015 train_loss= 0.69285 train_acc= 0.48182 val_loss= 0.69314 val_acc= 0.59016 time= 0.00000
Epoch: 0016 train_loss= 0.69388 train_acc= 0.50909 val_loss= 0.69252 val_acc= 0.57377 time= 0.00000
Epoch: 0017 train_loss= 0.69313 train_acc= 0.50390 val_loss= 0.69217 val_acc= 0.57377 time= 0.01563
Epoch: 0018 train_loss= 0.69431 train_acc= 0.49870 val_loss= 0.69201 val_acc= 0.57377 time= 0.00000
Epoch: 0019 train_loss= 0.69282 train_acc= 0.50909 val_loss= 0.69208 val_acc= 0.57377 time= 0.00000
Epoch: 0020 train_loss= 0.69326 train_acc= 0.48961 val_loss= 0.69235 val_acc= 0.57377 time= 0.01563
Epoch: 0021 train_loss= 0.69198 train_acc= 0.50390 val_loss= 0.69280 val_acc= 0.57377 time= 0.00000
Epoch: 0022 train_loss= 0.69392 train_acc= 0.50649 val_loss= 0.69314 val_acc= 0.59016 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69273 accuracy= 0.54918 time= 0.00000 
