Epoch: 0001 train_loss= 1.65730 train_acc= 0.24219 val_loss= 1.33190 val_acc= 0.33929 time= 0.60991
Epoch: 0002 train_loss= 1.71744 train_acc= 0.25977 val_loss= 1.36054 val_acc= 0.32143 time= 0.01562
Epoch: 0003 train_loss= 1.42149 train_acc= 0.26758 val_loss= 1.39563 val_acc= 0.23214 time= 0.03125
Epoch: 0004 train_loss= 1.69814 train_acc= 0.26172 val_loss= 1.40727 val_acc= 0.25000 time= 0.01563
Epoch: 0005 train_loss= 1.46454 train_acc= 0.26172 val_loss= 1.44013 val_acc= 0.33929 time= 0.03125
Epoch: 0006 train_loss= 1.57926 train_acc= 0.26562 val_loss= 1.44944 val_acc= 0.28571 time= 0.01563
Epoch: 0007 train_loss= 1.42293 train_acc= 0.28320 val_loss= 1.44924 val_acc= 0.28571 time= 0.01562
Epoch: 0008 train_loss= 1.53399 train_acc= 0.27539 val_loss= 1.44029 val_acc= 0.28571 time= 0.03125
Epoch: 0009 train_loss= 1.80544 train_acc= 0.26562 val_loss= 1.42802 val_acc= 0.30357 time= 0.01563
Epoch: 0010 train_loss= 1.48461 train_acc= 0.23828 val_loss= 1.41646 val_acc= 0.28571 time= 0.03125
Epoch: 0011 train_loss= 1.50413 train_acc= 0.25586 val_loss= 1.40874 val_acc= 0.35714 time= 0.01563
Epoch: 0012 train_loss= 1.57050 train_acc= 0.29492 val_loss= 1.40467 val_acc= 0.39286 time= 0.01563
Epoch: 0013 train_loss= 1.41605 train_acc= 0.31641 val_loss= 1.40162 val_acc= 0.33929 time= 0.03125
Epoch: 0014 train_loss= 1.40097 train_acc= 0.27539 val_loss= 1.40004 val_acc= 0.33929 time= 0.01563
Epoch: 0015 train_loss= 1.45598 train_acc= 0.29492 val_loss= 1.39805 val_acc= 0.35714 time= 0.03125
Epoch: 0016 train_loss= 1.55527 train_acc= 0.22852 val_loss= 1.39687 val_acc= 0.37500 time= 0.01563
Epoch: 0017 train_loss= 1.38212 train_acc= 0.31641 val_loss= 1.39606 val_acc= 0.37500 time= 0.01563
Epoch: 0018 train_loss= 1.37341 train_acc= 0.30469 val_loss= 1.39547 val_acc= 0.37500 time= 0.03125
Epoch: 0019 train_loss= 1.38236 train_acc= 0.29883 val_loss= 1.39549 val_acc= 0.37500 time= 0.01563
Epoch: 0020 train_loss= 1.40908 train_acc= 0.31445 val_loss= 1.39535 val_acc= 0.37500 time= 0.03125
Epoch: 0021 train_loss= 1.42216 train_acc= 0.28906 val_loss= 1.39492 val_acc= 0.37500 time= 0.01563
Epoch: 0022 train_loss= 1.38737 train_acc= 0.29297 val_loss= 1.39416 val_acc= 0.37500 time= 0.03125
Epoch: 0023 train_loss= 1.37371 train_acc= 0.30859 val_loss= 1.39353 val_acc= 0.37500 time= 0.01563
Epoch: 0024 train_loss= 1.38316 train_acc= 0.31836 val_loss= 1.39309 val_acc= 0.37500 time= 0.01563
Epoch: 0025 train_loss= 1.46941 train_acc= 0.24609 val_loss= 1.39363 val_acc= 0.37500 time= 0.03125
Epoch: 0026 train_loss= 1.36892 train_acc= 0.32812 val_loss= 1.39458 val_acc= 0.37500 time= 0.01563
Epoch: 0027 train_loss= 1.37424 train_acc= 0.31250 val_loss= 1.39571 val_acc= 0.37500 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38637 accuracy= 0.29204 time= 0.01563 
