Epoch: 0001 train_loss= 0.79046 train_acc= 0.50390 val_loss= 0.90281 val_acc= 0.60656 time= 0.75689
Epoch: 0002 train_loss= 0.91347 train_acc= 0.52727 val_loss= 0.84346 val_acc= 0.62295 time= 0.01700
Epoch: 0003 train_loss= 1.19495 train_acc= 0.51688 val_loss= 0.80070 val_acc= 0.62295 time= 0.01500
Epoch: 0004 train_loss= 0.88832 train_acc= 0.50779 val_loss= 0.75297 val_acc= 0.59016 time= 0.01200
Epoch: 0005 train_loss= 1.17278 train_acc= 0.51948 val_loss= 0.70300 val_acc= 0.57377 time= 0.01400
Epoch: 0006 train_loss= 0.83831 train_acc= 0.51429 val_loss= 0.68344 val_acc= 0.59016 time= 0.01338
Epoch: 0007 train_loss= 0.82213 train_acc= 0.51948 val_loss= 0.69364 val_acc= 0.55738 time= 0.01300
Epoch: 0008 train_loss= 0.78117 train_acc= 0.52468 val_loss= 0.71250 val_acc= 0.55738 time= 0.01300
Epoch: 0009 train_loss= 0.80787 train_acc= 0.49481 val_loss= 0.71960 val_acc= 0.54098 time= 0.01334
Epoch: 0010 train_loss= 0.88001 train_acc= 0.52208 val_loss= 0.72454 val_acc= 0.54098 time= 0.01300
Epoch: 0011 train_loss= 0.96280 train_acc= 0.51039 val_loss= 0.72450 val_acc= 0.54098 time= 0.01501
Epoch: 0012 train_loss= 0.98906 train_acc= 0.51299 val_loss= 0.71510 val_acc= 0.57377 time= 0.01500
Epoch: 0013 train_loss= 0.77497 train_acc= 0.50519 val_loss= 0.70638 val_acc= 0.55738 time= 0.01300
Epoch: 0014 train_loss= 0.80816 train_acc= 0.52597 val_loss= 0.70237 val_acc= 0.45902 time= 0.01500
Epoch: 0015 train_loss= 0.74490 train_acc= 0.52597 val_loss= 0.70024 val_acc= 0.45902 time= 0.01300
Epoch: 0016 train_loss= 0.91168 train_acc= 0.48182 val_loss= 0.69831 val_acc= 0.49180 time= 0.01400
Epoch: 0017 train_loss= 0.78027 train_acc= 0.52597 val_loss= 0.69716 val_acc= 0.52459 time= 0.01300
Epoch: 0018 train_loss= 0.74993 train_acc= 0.49091 val_loss= 0.69628 val_acc= 0.52459 time= 0.01400
Epoch: 0019 train_loss= 0.77877 train_acc= 0.54416 val_loss= 0.69491 val_acc= 0.52459 time= 0.01400
Epoch: 0020 train_loss= 0.75711 train_acc= 0.52468 val_loss= 0.69383 val_acc= 0.52459 time= 0.01300
Epoch: 0021 train_loss= 0.74448 train_acc= 0.53896 val_loss= 0.69323 val_acc= 0.52459 time= 0.01200
Epoch: 0022 train_loss= 0.76888 train_acc= 0.47662 val_loss= 0.69303 val_acc= 0.50820 time= 0.01400
Epoch: 0023 train_loss= 0.77367 train_acc= 0.52727 val_loss= 0.69261 val_acc= 0.50820 time= 0.01300
Epoch: 0024 train_loss= 0.78063 train_acc= 0.47662 val_loss= 0.69265 val_acc= 0.52459 time= 0.01300
Epoch: 0025 train_loss= 0.74505 train_acc= 0.47792 val_loss= 0.69355 val_acc= 0.49180 time= 0.01300
Epoch: 0026 train_loss= 0.74827 train_acc= 0.46623 val_loss= 0.69464 val_acc= 0.49180 time= 0.01400
Early stopping...
Optimization Finished!
Test set results: cost= 0.69891 accuracy= 0.59016 time= 0.00600 
